diff options
author | Erik Johnston <erik@matrix.org> | 2024-06-26 13:15:14 +0100 |
---|---|---|
committer | Erik Johnston <erik@matrix.org> | 2024-06-26 13:15:14 +0100 |
commit | dac74db74ee63cc8218f46e1bd092c9d99b5cef6 (patch) | |
tree | a2c64f97839f826637e74eaaa2726185e67f4932 | |
parent | Handle SQLite (diff) | |
parent | Fixes to the table of contents in the README (#17329) (diff) | |
download | synapse-dac74db74ee63cc8218f46e1bd092c9d99b5cef6.tar.xz |
Merge remote-tracking branch 'origin/develop' into erikj/faster_auth_chains
236 files changed, 13555 insertions, 3429 deletions
diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index 1632170c9d..d3114882d7 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -2,4 +2,4 @@ (using a matrix.org account if necessary). We do not use GitHub issues for support. -**If you want to report a security issue** please see https://matrix.org/security-disclosure-policy/ +**If you want to report a security issue** please see https://element.io/security/security-disclosure-policy diff --git a/.github/ISSUE_TEMPLATE/BUG_REPORT.yml b/.github/ISSUE_TEMPLATE/BUG_REPORT.yml index 77a04109dd..ebd36a9398 100644 --- a/.github/ISSUE_TEMPLATE/BUG_REPORT.yml +++ b/.github/ISSUE_TEMPLATE/BUG_REPORT.yml @@ -7,7 +7,7 @@ body: **THIS IS NOT A SUPPORT CHANNEL!** **IF YOU HAVE SUPPORT QUESTIONS ABOUT RUNNING OR CONFIGURING YOUR OWN HOME SERVER**, please ask in **[#synapse:matrix.org](https://matrix.to/#/#synapse:matrix.org)** (using a matrix.org account if necessary). - If you want to report a security issue, please see https://matrix.org/security-disclosure-policy/ + If you want to report a security issue, please see https://element.io/security/security-disclosure-policy This is a bug report form. By following the instructions below and completing the sections with your information, you will help the us to get all the necessary data to fix your issue. diff --git a/.github/workflows/docker.yml b/.github/workflows/docker.yml index 391e9c96ff..06aaeb851f 100644 --- a/.github/workflows/docker.yml +++ b/.github/workflows/docker.yml @@ -72,7 +72,7 @@ jobs: - name: Build and push all platforms id: build-and-push - uses: docker/build-push-action@v5 + uses: docker/build-push-action@v6 with: push: true labels: | diff --git a/.github/workflows/docs-pr-netlify.yaml b/.github/workflows/docs-pr-netlify.yaml index 277083ded3..6d184a21e0 100644 --- a/.github/workflows/docs-pr-netlify.yaml +++ b/.github/workflows/docs-pr-netlify.yaml @@ -14,7 +14,7 @@ jobs: # There's a 'download artifact' action, but it hasn't been updated for the workflow_run action # (https://github.com/actions/download-artifact/issues/60) so instead we get this mess: - name: 📥 Download artifact - uses: dawidd6/action-download-artifact@09f2f74827fd3a8607589e5ad7f9398816f540fe # v3.1.4 + uses: dawidd6/action-download-artifact@bf251b5aa9c2f7eeb574a96ee720e24f801b7c11 # v6 with: workflow: docs-pr.yaml run_id: ${{ github.event.workflow_run.id }} diff --git a/.github/workflows/release-artifacts.yml b/.github/workflows/release-artifacts.yml index 5d4a4fe1d6..9f0feffd94 100644 --- a/.github/workflows/release-artifacts.yml +++ b/.github/workflows/release-artifacts.yml @@ -102,7 +102,7 @@ jobs: runs-on: ${{ matrix.os }} strategy: matrix: - os: [ubuntu-20.04, macos-11] + os: [ubuntu-20.04, macos-12] arch: [x86_64, aarch64] # is_pr is a flag used to exclude certain jobs from the matrix on PRs. # It is not read by the rest of the workflow. @@ -112,9 +112,9 @@ jobs: exclude: # Don't build macos wheels on PR CI. - is_pr: true - os: "macos-11" + os: "macos-12" # Don't build aarch64 wheels on mac. - - os: "macos-11" + - os: "macos-12" arch: aarch64 # Don't build aarch64 wheels on PR CI. - is_pr: true @@ -130,7 +130,7 @@ jobs: python-version: "3.x" - name: Install cibuildwheel - run: python -m pip install cibuildwheel==2.16.2 + run: python -m pip install cibuildwheel==2.19.1 - name: Set up QEMU to emulate aarch64 if: matrix.arch == 'aarch64' diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml index 20afe311fe..cdd881fbe1 100644 --- a/.github/workflows/tests.yml +++ b/.github/workflows/tests.yml @@ -479,6 +479,9 @@ jobs: volumes: - ${{ github.workspace }}:/src env: + # If this is a pull request to a release branch, use that branch as default branch for sytest, else use develop + # This works because the release script always create a branch on the sytest repo with the same name as the release branch + SYTEST_DEFAULT_BRANCH: ${{ startsWith(github.base_ref, 'release-') && github.base_ref || 'develop' }} SYTEST_BRANCH: ${{ github.head_ref }} POSTGRES: ${{ matrix.job.postgres && 1}} MULTI_POSTGRES: ${{ (matrix.job.postgres == 'multi-postgres') || '' }} diff --git a/CHANGES.md b/CHANGES.md index fec9581174..9060b84853 100644 --- a/CHANGES.md +++ b/CHANGES.md @@ -1,3 +1,148 @@ +# Synapse 1.109.0 (2024-06-18) + +### Internal Changes + +- Fix the building of binary wheels for macOS by switching to macOS 12 CI runners. ([\#17319](https://github.com/element-hq/synapse/issues/17319)) + + + + +# Synapse 1.109.0rc3 (2024-06-17) + +### Bugfixes + +- When rolling back to a previous Synapse version and then forwards again to this release, don't require server operators to manually run SQL. ([\#17305](https://github.com/element-hq/synapse/issues/17305), [\#17309](https://github.com/element-hq/synapse/issues/17309)) + +### Internal Changes + +- Use the release branch for sytest in release-branch PRs. ([\#17306](https://github.com/element-hq/synapse/issues/17306)) + + + + +# Synapse 1.109.0rc2 (2024-06-11) + +### Bugfixes + +- Fix bug where one-time-keys were not always included in `/sync` response when using workers. Introduced in v1.109.0rc1. ([\#17275](https://github.com/element-hq/synapse/issues/17275)) +- Fix bug where `/sync` could get stuck due to edge case in device lists handling. Introduced in v1.109.0rc1. ([\#17292](https://github.com/element-hq/synapse/issues/17292)) + + + + +# Synapse 1.109.0rc1 (2024-06-04) + +### Features + +- Add the ability to auto-accept invites on the behalf of users. See the [`auto_accept_invites`](https://element-hq.github.io/synapse/latest/usage/configuration/config_documentation.html#auto-accept-invites) config option for details. ([\#17147](https://github.com/element-hq/synapse/issues/17147)) +- Add experimental [MSC3575](https://github.com/matrix-org/matrix-spec-proposals/pull/3575) Sliding Sync `/sync/e2ee` endpoint for to-device messages and device encryption info. ([\#17167](https://github.com/element-hq/synapse/issues/17167)) +- Support [MSC3916](https://github.com/matrix-org/matrix-spec-proposals/issues/3916) by adding unstable media endpoints to `/_matrix/client`. ([\#17213](https://github.com/element-hq/synapse/issues/17213)) +- Add logging to tasks managed by the task scheduler, showing CPU and database usage. ([\#17219](https://github.com/element-hq/synapse/issues/17219)) + +### Bugfixes + +- Fix deduplicating of membership events to not create unused state groups. ([\#17164](https://github.com/element-hq/synapse/issues/17164)) +- Fix bug where duplicate events could be sent down sync when using workers that are overloaded. ([\#17215](https://github.com/element-hq/synapse/issues/17215)) +- Ignore attempts to send to-device messages to bad users, to avoid log spam when we try to connect to the bad server. ([\#17240](https://github.com/element-hq/synapse/issues/17240)) +- Fix handling of duplicate concurrent uploading of device one-time-keys. ([\#17241](https://github.com/element-hq/synapse/issues/17241)) +- Fix reporting of default tags to Sentry, such as worker name. Broke in v1.108.0. ([\#17251](https://github.com/element-hq/synapse/issues/17251)) +- Fix bug where typing updates would not be sent when using workers after a restart. ([\#17252](https://github.com/element-hq/synapse/issues/17252)) + +### Improved Documentation + +- Update the LemonLDAP documentation to say that claims should be explicitly included in the returned `id_token`, as Synapse won't request them. ([\#17204](https://github.com/element-hq/synapse/issues/17204)) + +### Internal Changes + +- Improve DB usage when fetching related events. ([\#17083](https://github.com/element-hq/synapse/issues/17083)) +- Log exceptions when failing to auto-join new user according to the `auto_join_rooms` option. ([\#17176](https://github.com/element-hq/synapse/issues/17176)) +- Reduce work of calculating outbound device lists updates. ([\#17211](https://github.com/element-hq/synapse/issues/17211)) +- Improve performance of calculating device lists changes in `/sync`. ([\#17216](https://github.com/element-hq/synapse/issues/17216)) +- Move towards using `MultiWriterIdGenerator` everywhere. ([\#17226](https://github.com/element-hq/synapse/issues/17226)) +- Replaces all usages of `StreamIdGenerator` with `MultiWriterIdGenerator`. ([\#17229](https://github.com/element-hq/synapse/issues/17229)) +- Change the `allow_unsafe_locale` config option to also apply when setting up new databases. ([\#17238](https://github.com/element-hq/synapse/issues/17238)) +- Fix errors in logs about closing incorrect logging contexts when media gets rejected by a module. ([\#17239](https://github.com/element-hq/synapse/issues/17239), [\#17246](https://github.com/element-hq/synapse/issues/17246)) +- Clean out invalid destinations from `device_federation_outbox` table. ([\#17242](https://github.com/element-hq/synapse/issues/17242)) +- Stop logging errors when receiving invalid User IDs in key querys requests. ([\#17250](https://github.com/element-hq/synapse/issues/17250)) + + + +### Updates to locked dependencies + +* Bump anyhow from 1.0.83 to 1.0.86. ([\#17220](https://github.com/element-hq/synapse/issues/17220)) +* Bump bcrypt from 4.1.2 to 4.1.3. ([\#17224](https://github.com/element-hq/synapse/issues/17224)) +* Bump lxml from 5.2.1 to 5.2.2. ([\#17261](https://github.com/element-hq/synapse/issues/17261)) +* Bump mypy-zope from 1.0.3 to 1.0.4. ([\#17262](https://github.com/element-hq/synapse/issues/17262)) +* Bump phonenumbers from 8.13.35 to 8.13.37. ([\#17235](https://github.com/element-hq/synapse/issues/17235)) +* Bump prometheus-client from 0.19.0 to 0.20.0. ([\#17233](https://github.com/element-hq/synapse/issues/17233)) +* Bump pyasn1 from 0.5.1 to 0.6.0. ([\#17223](https://github.com/element-hq/synapse/issues/17223)) +* Bump pyicu from 2.13 to 2.13.1. ([\#17236](https://github.com/element-hq/synapse/issues/17236)) +* Bump pyopenssl from 24.0.0 to 24.1.0. ([\#17234](https://github.com/element-hq/synapse/issues/17234)) +* Bump serde from 1.0.201 to 1.0.202. ([\#17221](https://github.com/element-hq/synapse/issues/17221)) +* Bump serde from 1.0.202 to 1.0.203. ([\#17232](https://github.com/element-hq/synapse/issues/17232)) +* Bump twine from 5.0.0 to 5.1.0. ([\#17225](https://github.com/element-hq/synapse/issues/17225)) +* Bump types-psycopg2 from 2.9.21.20240311 to 2.9.21.20240417. ([\#17222](https://github.com/element-hq/synapse/issues/17222)) +* Bump types-pyopenssl from 24.0.0.20240311 to 24.1.0.20240425. ([\#17260](https://github.com/element-hq/synapse/issues/17260)) + +# Synapse 1.108.0 (2024-05-28) + +No significant changes since 1.108.0rc1. + + + + +# Synapse 1.108.0rc1 (2024-05-21) + +### Features + +- Add a feature that allows clients to query the configured federation whitelist. Disabled by default. ([\#16848](https://github.com/element-hq/synapse/issues/16848), [\#17199](https://github.com/element-hq/synapse/issues/17199)) +- Add the ability to allow numeric user IDs with a specific prefix when in the CAS flow. Contributed by Aurélien Grimpard. ([\#17098](https://github.com/element-hq/synapse/issues/17098)) + +### Bugfixes + +- Fix bug where push rules would be empty in `/sync` for some accounts. Introduced in v1.93.0. ([\#17142](https://github.com/element-hq/synapse/issues/17142)) +- Add support for optional whitespace around the Federation API's `Authorization` header's parameter commas. ([\#17145](https://github.com/element-hq/synapse/issues/17145)) +- Fix bug where disabling room publication prevented public rooms being created on workers. ([\#17177](https://github.com/element-hq/synapse/issues/17177), [\#17184](https://github.com/element-hq/synapse/issues/17184)) + +### Improved Documentation + +- Document [`/v1/make_knock`](https://spec.matrix.org/v1.10/server-server-api/#get_matrixfederationv1make_knockroomiduserid) and [`/v1/send_knock/`](https://spec.matrix.org/v1.10/server-server-api/#put_matrixfederationv1send_knockroomideventid) federation endpoints as worker-compatible. ([\#17058](https://github.com/element-hq/synapse/issues/17058)) +- Update User Admin API with note about prefixing OIDC external_id providers. ([\#17139](https://github.com/element-hq/synapse/issues/17139)) +- Clarify the state of the created room when using the `autocreate_auto_join_room_preset` config option. ([\#17150](https://github.com/element-hq/synapse/issues/17150)) +- Update the Admin FAQ with the current libjemalloc version for latest Debian stable. Additionally update the name of the "push_rules" stream in the Workers documentation. ([\#17171](https://github.com/element-hq/synapse/issues/17171)) + +### Internal Changes + +- Add note to reflect that [MSC3886](https://github.com/matrix-org/matrix-spec-proposals/pull/3886) is closed but will remain supported for some time. ([\#17151](https://github.com/element-hq/synapse/issues/17151)) +- Update dependency PyO3 to 0.21. ([\#17162](https://github.com/element-hq/synapse/issues/17162)) +- Fixes linter errors found in PR #17147. ([\#17166](https://github.com/element-hq/synapse/issues/17166)) +- Bump black from 24.2.0 to 24.4.2. ([\#17170](https://github.com/element-hq/synapse/issues/17170)) +- Cache literal sync filter validation for performance. ([\#17186](https://github.com/element-hq/synapse/issues/17186)) +- Improve performance by fixing a reactor pause. ([\#17192](https://github.com/element-hq/synapse/issues/17192)) +- Route `/make_knock` and `/send_knock` federation APIs to the federation reader worker in Complement test runs. ([\#17195](https://github.com/element-hq/synapse/issues/17195)) +- Prepare sync handler to be able to return different sync responses (`SyncVersion`). ([\#17200](https://github.com/element-hq/synapse/issues/17200)) +- Organize the sync cache key parameter outside of the sync config (separate concerns). ([\#17201](https://github.com/element-hq/synapse/issues/17201)) +- Refactor `SyncResultBuilder` assembly to its own function. ([\#17202](https://github.com/element-hq/synapse/issues/17202)) +- Rename to be obvious: `joined_rooms` -> `joined_room_ids`. ([\#17203](https://github.com/element-hq/synapse/issues/17203), [\#17208](https://github.com/element-hq/synapse/issues/17208)) +- Add a short pause when rate-limiting a request. ([\#17210](https://github.com/element-hq/synapse/issues/17210)) + + + +### Updates to locked dependencies + +* Bump cryptography from 42.0.5 to 42.0.7. ([\#17180](https://github.com/element-hq/synapse/issues/17180)) +* Bump gitpython from 3.1.41 to 3.1.43. ([\#17181](https://github.com/element-hq/synapse/issues/17181)) +* Bump immutabledict from 4.1.0 to 4.2.0. ([\#17179](https://github.com/element-hq/synapse/issues/17179)) +* Bump sentry-sdk from 1.40.3 to 2.1.1. ([\#17178](https://github.com/element-hq/synapse/issues/17178)) +* Bump serde from 1.0.200 to 1.0.201. ([\#17183](https://github.com/element-hq/synapse/issues/17183)) +* Bump serde_json from 1.0.116 to 1.0.117. ([\#17182](https://github.com/element-hq/synapse/issues/17182)) + +Synapse 1.107.0 (2024-05-14) +============================ + +No significant changes since 1.107.0rc1. + + # Synapse 1.107.0rc1 (2024-05-07) ### Features diff --git a/Cargo.lock b/Cargo.lock index 59d43ece2d..1955c1a4e7 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -13,9 +13,9 @@ dependencies = [ [[package]] name = "anyhow" -version = "1.0.83" +version = "1.0.86" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "25bdb32cbbdce2b519a9cd7df3a678443100e265d5e25ca763b7572a5104f5f3" +checksum = "b3d1d046238990b9cf5bcde22a3fb3584ee5cf65fb2765f454ed428c7a0063da" [[package]] name = "arc-swap" @@ -212,9 +212,9 @@ dependencies = [ [[package]] name = "lazy_static" -version = "1.4.0" +version = "1.5.0" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "e2abad23fbc42b3700f2f279844dc832adb2b2eb069b2df918f455c4e18cc646" +checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe" [[package]] name = "libc" @@ -444,9 +444,9 @@ dependencies = [ [[package]] name = "regex" -version = "1.10.4" +version = "1.10.5" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "c117dbdfde9c8308975b6a18d71f3f385c89461f7b3fb054288ecf2a2058ba4c" +checksum = "b91213439dad192326a0d7c6ee3955910425f441d7038e0d6933b0aec5c4517f" dependencies = [ "aho-corasick", "memchr", @@ -485,18 +485,18 @@ checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49" [[package]] name = "serde" -version = "1.0.200" +version = "1.0.203" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "ddc6f9cc94d67c0e21aaf7eda3a010fd3af78ebf6e096aa6e2e13c79749cce4f" +checksum = "7253ab4de971e72fb7be983802300c30b5a7f0c2e56fab8abfc6a214307c0094" dependencies = [ "serde_derive", ] [[package]] name = "serde_derive" -version = "1.0.200" +version = "1.0.203" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "856f046b9400cee3c8c94ed572ecdb752444c24528c035cd35882aad6f492bcb" +checksum = "500cbc0ebeb6f46627f50f3f5811ccf6bf00643be300b4c3eabc0ef55dc5b5ba" dependencies = [ "proc-macro2", "quote", @@ -505,9 +505,9 @@ dependencies = [ [[package]] name = "serde_json" -version = "1.0.116" +version = "1.0.117" source = "registry+https://github.com/rust-lang/crates.io-index" -checksum = "3e17db7126d17feb94eb3fad46bf1a96b034e8aacbc2e775fe81505f8b0b2813" +checksum = "455182ea6142b14f93f4bc5320a2b31c1f266b66a4a5c858b013302a5d8cbfc3" dependencies = [ "itoa", "ryu", diff --git a/README.rst b/README.rst index d13dc0cb78..145315a7fe 100644 --- a/README.rst +++ b/README.rst @@ -1,21 +1,34 @@ -========================================================================= -Synapse |support| |development| |documentation| |license| |pypi| |python| -========================================================================= +.. image:: https://github.com/element-hq/product/assets/87339233/7abf477a-5277-47f3-be44-ea44917d8ed7 + :height: 60px -Synapse is an open-source `Matrix <https://matrix.org/>`_ homeserver written and -maintained by the Matrix.org Foundation. We began rapid development in 2014, -reaching v1.0.0 in 2019. Development on Synapse and the Matrix protocol itself continues -in earnest today. +**Element Synapse - Matrix homeserver implementation** -Briefly, Matrix is an open standard for communications on the internet, supporting -federation, encryption and VoIP. Matrix.org has more to say about the `goals of the -Matrix project <https://matrix.org/docs/guides/introduction>`_, and the `formal specification -<https://spec.matrix.org/>`_ describes the technical details. +|support| |development| |documentation| |license| |pypi| |python| + +Synapse is an open source `Matrix <https://matrix.org>`_ homeserver +implementation, written and maintained by `Element <https://element.io>`_. +`Matrix <https://github.com/matrix-org>`_ is the open standard for +secure and interoperable real time communications. You can directly run +and manage the source code in this repository, available under an AGPL +license. There is no support provided from Element unless you have a +subscription. + +Subscription alternative +======================== + +Alternatively, for those that need an enterprise-ready solution, Element +Server Suite (ESS) is `available as a subscription <https://element.io/pricing>`_. +ESS builds on Synapse to offer a complete Matrix-based backend including the full +`Admin Console product <https://element.io/enterprise-functionality/admin-console>`_, +giving admins the power to easily manage an organization-wide +deployment. It includes advanced identity management, auditing, +moderation and data retention options as well as Long Term Support and +SLAs. ESS can be used to support any Matrix-based frontend client. .. contents:: -Installing and configuration -============================ +🛠️ Installing and configuration +=============================== The Synapse documentation describes `how to install Synapse <https://element-hq.github.io/synapse/latest/setup/installation.html>`_. We recommend using `Docker images <https://element-hq.github.io/synapse/latest/setup/installation.html#docker-images-and-ansible-playbooks>`_ or `Debian packages from Matrix.org @@ -105,8 +118,8 @@ Following this advice ensures that even if an XSS is found in Synapse, the impact to other applications will be minimal. -Testing a new installation -========================== +🧪 Testing a new installation +============================ The easiest way to try out your new Synapse installation is by connecting to it from a web client. @@ -159,8 +172,20 @@ the form of:: As when logging in, you will need to specify a "Custom server". Specify your desired ``localpart`` in the 'User name' box. -Troubleshooting and support -=========================== +🎯 Troubleshooting and support +============================= + +🚀 Professional support +---------------------- + +Enterprise quality support for Synapse including SLAs is available as part of an +`Element Server Suite (ESS) <https://element.io/pricing>` subscription. + +If you are an existing ESS subscriber then you can raise a `support request <https://ems.element.io/support>` +and access the `knowledge base <https://ems-docs.element.io>`. + +🤝 Community support +------------------- The `Admin FAQ <https://element-hq.github.io/synapse/latest/usage/administration/admin_faq.html>`_ includes tips on dealing with some common problems. For more details, see @@ -176,8 +201,8 @@ issues for support requests, only for bug reports and feature requests. .. |docs| replace:: ``docs`` .. _docs: docs -Identity Servers -================ +🪪 Identity Servers +================== Identity servers have the job of mapping email addresses and other 3rd Party IDs (3PIDs) to Matrix user IDs, as well as verifying the ownership of 3PIDs @@ -206,8 +231,8 @@ an email address with your account, or send an invite to another user via their email address. -Development -=========== +🛠️ Development +============== We welcome contributions to Synapse from the community! The best place to get started is our @@ -225,8 +250,8 @@ Alongside all that, join our developer community on Matrix: `#synapse-dev:matrix.org <https://matrix.to/#/#synapse-dev:matrix.org>`_, featuring real humans! -.. |support| image:: https://img.shields.io/matrix/synapse:matrix.org?label=support&logo=matrix - :alt: (get support on #synapse:matrix.org) +.. |support| image:: https://img.shields.io/badge/matrix-community%20support-success + :alt: (get community support in #synapse:matrix.org) :target: https://matrix.to/#/#synapse:matrix.org .. |development| image:: https://img.shields.io/matrix/synapse-dev:matrix.org?label=development&logo=matrix diff --git a/changelog.d/17139.doc b/changelog.d/17139.doc deleted file mode 100644 index a6d5408cac..0000000000 --- a/changelog.d/17139.doc +++ /dev/null @@ -1 +0,0 @@ -Update User Admin API with note about prefixing OIDC external_id providers. diff --git a/changelog.d/17145.bugfix b/changelog.d/17145.bugfix deleted file mode 100644 index 5c1e600f4e..0000000000 --- a/changelog.d/17145.bugfix +++ /dev/null @@ -1 +0,0 @@ -Add support for optional whitespace around the Federation API's `Authorization` header's parameter commas. diff --git a/changelog.d/17150.doc b/changelog.d/17150.doc deleted file mode 100644 index 109f192818..0000000000 --- a/changelog.d/17150.doc +++ /dev/null @@ -1 +0,0 @@ -Clarify the state of the created room when using the `autocreate_auto_join_room_preset` config option. \ No newline at end of file diff --git a/changelog.d/17151.misc b/changelog.d/17151.misc deleted file mode 100644 index 7b23c1e18e..0000000000 --- a/changelog.d/17151.misc +++ /dev/null @@ -1 +0,0 @@ -Add note to reflect that [MSC3886](https://github.com/matrix-org/matrix-spec-proposals/pull/3886) is closed but will support will remain for some time. diff --git a/changelog.d/17162.misc b/changelog.d/17162.misc deleted file mode 100644 index 5cbc086e04..0000000000 --- a/changelog.d/17162.misc +++ /dev/null @@ -1 +0,0 @@ -Update dependency PyO3 to 0.21. diff --git a/changelog.d/17187.feature b/changelog.d/17187.feature new file mode 100644 index 0000000000..50383cb4a4 --- /dev/null +++ b/changelog.d/17187.feature @@ -0,0 +1 @@ +Add initial implementation of an experimental [MSC3575](https://github.com/matrix-org/matrix-spec-proposals/pull/3575) Sliding Sync `/sync` endpoint. diff --git a/changelog.d/17198.misc b/changelog.d/17198.misc new file mode 100644 index 0000000000..8973eb2bac --- /dev/null +++ b/changelog.d/17198.misc @@ -0,0 +1 @@ +Remove unused `expire_access_token` option in the Synapse Docker config file. Contributed by @AaronDewes. \ No newline at end of file diff --git a/changelog.d/17254.bugfix b/changelog.d/17254.bugfix new file mode 100644 index 0000000000..b0d61309e2 --- /dev/null +++ b/changelog.d/17254.bugfix @@ -0,0 +1 @@ +Fix searching for users with their exact localpart whose ID includes a hyphen. diff --git a/changelog.d/17255.feature b/changelog.d/17255.feature new file mode 100644 index 0000000000..4093de1146 --- /dev/null +++ b/changelog.d/17255.feature @@ -0,0 +1 @@ +Add support for [MSC823](https://github.com/matrix-org/matrix-spec-proposals/pull/3823) - Account suspension. \ No newline at end of file diff --git a/changelog.d/17256.feature b/changelog.d/17256.feature new file mode 100644 index 0000000000..6ec4cb7a31 --- /dev/null +++ b/changelog.d/17256.feature @@ -0,0 +1 @@ + Improve ratelimiting in Synapse (#17256). \ No newline at end of file diff --git a/changelog.d/17265.misc b/changelog.d/17265.misc new file mode 100644 index 0000000000..e6d4d8b4ee --- /dev/null +++ b/changelog.d/17265.misc @@ -0,0 +1 @@ +Use fully-qualified `PersistedEventPosition` when returning `RoomsForUser` to facilitate proper comparisons and `RoomStreamToken` generation. diff --git a/changelog.d/17266.misc b/changelog.d/17266.misc new file mode 100644 index 0000000000..ce8c4ab086 --- /dev/null +++ b/changelog.d/17266.misc @@ -0,0 +1 @@ +Add debug logging for when room keys are uploaded, including whether they are replacing other room keys. \ No newline at end of file diff --git a/changelog.d/17270.feature b/changelog.d/17270.feature new file mode 100644 index 0000000000..4ea5e7be85 --- /dev/null +++ b/changelog.d/17270.feature @@ -0,0 +1 @@ +Add support for the unstable [MSC4151](https://github.com/matrix-org/matrix-spec-proposals/pull/4151) report room API. diff --git a/changelog.d/17271.misc b/changelog.d/17271.misc new file mode 100644 index 0000000000..915d717ad7 --- /dev/null +++ b/changelog.d/17271.misc @@ -0,0 +1 @@ +Handle OTK uploads off master. diff --git a/changelog.d/17272.bugfix b/changelog.d/17272.bugfix new file mode 100644 index 0000000000..83e7ca426a --- /dev/null +++ b/changelog.d/17272.bugfix @@ -0,0 +1 @@ +Fix wrong retention policy being used when filtering events. diff --git a/changelog.d/17273.misc b/changelog.d/17273.misc new file mode 100644 index 0000000000..2c1c6bc0d5 --- /dev/null +++ b/changelog.d/17273.misc @@ -0,0 +1 @@ +Don't try and resync devices for remote users whose servers are marked as down. diff --git a/changelog.d/17275.bugfix b/changelog.d/17275.bugfix new file mode 100644 index 0000000000..eb522bb997 --- /dev/null +++ b/changelog.d/17275.bugfix @@ -0,0 +1 @@ +Fix bug where OTKs were not always included in `/sync` response when using workers. diff --git a/changelog.d/17276.feature b/changelog.d/17276.feature new file mode 100644 index 0000000000..a1edfae0aa --- /dev/null +++ b/changelog.d/17276.feature @@ -0,0 +1 @@ +Filter for public and empty rooms added to Admin-API [List Room API](https://element-hq.github.io/synapse/latest/admin_api/rooms.html#list-room-api). diff --git a/changelog.d/17277.feature b/changelog.d/17277.feature new file mode 100644 index 0000000000..5c16342c11 --- /dev/null +++ b/changelog.d/17277.feature @@ -0,0 +1 @@ +Add `is_dm` filtering to experimental [MSC3575](https://github.com/matrix-org/matrix-spec-proposals/pull/3575) Sliding Sync `/sync` endpoint. diff --git a/changelog.d/17279.misc b/changelog.d/17279.misc new file mode 100644 index 0000000000..2090b11d7f --- /dev/null +++ b/changelog.d/17279.misc @@ -0,0 +1 @@ +Re-organize Pydantic models and types used in handlers. diff --git a/changelog.d/17281.feature b/changelog.d/17281.feature new file mode 100644 index 0000000000..fce512692c --- /dev/null +++ b/changelog.d/17281.feature @@ -0,0 +1 @@ +Add `is_encrypted` filtering to experimental [MSC3575](https://github.com/matrix-org/matrix-spec-proposals/pull/3575) Sliding Sync `/sync` endpoint. diff --git a/changelog.d/17282.feature b/changelog.d/17282.feature new file mode 100644 index 0000000000..334709a3a7 --- /dev/null +++ b/changelog.d/17282.feature @@ -0,0 +1 @@ +Include user membership in events served to clients, per MSC4115. \ No newline at end of file diff --git a/changelog.d/17283.bugfix b/changelog.d/17283.bugfix new file mode 100644 index 0000000000..98c1f05cc2 --- /dev/null +++ b/changelog.d/17283.bugfix @@ -0,0 +1 @@ +Fix a long-standing bug where an invalid 'from' parameter to [`/notifications`](https://spec.matrix.org/v1.10/client-server-api/#get_matrixclientv3notifications) would result in an Internal Server Error. \ No newline at end of file diff --git a/changelog.d/17284.feature b/changelog.d/17284.feature new file mode 100644 index 0000000000..015d925e7c --- /dev/null +++ b/changelog.d/17284.feature @@ -0,0 +1 @@ +Do not require user-interactive authentication for uploading cross-signing keys for the first time, per MSC3967. \ No newline at end of file diff --git a/changelog.d/17293.feature b/changelog.d/17293.feature new file mode 100644 index 0000000000..60ca7721a0 --- /dev/null +++ b/changelog.d/17293.feature @@ -0,0 +1 @@ +Add `stream_ordering` sort to experimental [MSC3575](https://github.com/matrix-org/matrix-spec-proposals/pull/3575) Sliding Sync `/sync` endpoint. diff --git a/changelog.d/17294.feature b/changelog.d/17294.feature new file mode 100644 index 0000000000..33aac7b0bc --- /dev/null +++ b/changelog.d/17294.feature @@ -0,0 +1,2 @@ +`register_new_matrix_user` now supports a --password-file flag, which +is useful for scripting. diff --git a/changelog.d/17295.bugfix b/changelog.d/17295.bugfix new file mode 100644 index 0000000000..4484253bb8 --- /dev/null +++ b/changelog.d/17295.bugfix @@ -0,0 +1 @@ +Fix edge case in `/sync` returning the wrong the state when using sharded event persisters. diff --git a/changelog.d/17296.feature b/changelog.d/17296.feature new file mode 100644 index 0000000000..4ea5e7be85 --- /dev/null +++ b/changelog.d/17296.feature @@ -0,0 +1 @@ +Add support for the unstable [MSC4151](https://github.com/matrix-org/matrix-spec-proposals/pull/4151) report room API. diff --git a/changelog.d/17297.misc b/changelog.d/17297.misc new file mode 100644 index 0000000000..7ec351d2c1 --- /dev/null +++ b/changelog.d/17297.misc @@ -0,0 +1 @@ +Bump `mypy` from 1.8.0 to 1.9.0. \ No newline at end of file diff --git a/changelog.d/17300.misc b/changelog.d/17300.misc new file mode 100644 index 0000000000..cdc40bb2e5 --- /dev/null +++ b/changelog.d/17300.misc @@ -0,0 +1 @@ +Expose the worker instance that persisted the event on `event.internal_metadata.instance_name`. diff --git a/changelog.d/17301.bugfix b/changelog.d/17301.bugfix new file mode 100644 index 0000000000..50383cb4a4 --- /dev/null +++ b/changelog.d/17301.bugfix @@ -0,0 +1 @@ +Add initial implementation of an experimental [MSC3575](https://github.com/matrix-org/matrix-spec-proposals/pull/3575) Sliding Sync `/sync` endpoint. diff --git a/changelog.d/17304.feature b/changelog.d/17304.feature new file mode 100644 index 0000000000..a969d8bf58 --- /dev/null +++ b/changelog.d/17304.feature @@ -0,0 +1,2 @@ +`register_new_matrix_user` now supports a --exists-ok flag to allow registration of users that already exist in the database. +This is useful for scripts that bootstrap user accounts with initial passwords. diff --git a/changelog.d/17308.doc b/changelog.d/17308.doc new file mode 100644 index 0000000000..7ae080a684 --- /dev/null +++ b/changelog.d/17308.doc @@ -0,0 +1 @@ +Add missing quotes for example for `exclude_rooms_from_sync`. diff --git a/changelog.d/17322.feature b/changelog.d/17322.feature new file mode 100644 index 0000000000..85386c2df7 --- /dev/null +++ b/changelog.d/17322.feature @@ -0,0 +1 @@ +Add support for via query parameter from MSC415. diff --git a/changelog.d/17324.misc b/changelog.d/17324.misc new file mode 100644 index 0000000000..c0d7196ee0 --- /dev/null +++ b/changelog.d/17324.misc @@ -0,0 +1 @@ +Update the README with Element branding, improve headers and fix the #synapse:matrix.org support room link rendering. \ No newline at end of file diff --git a/changelog.d/17325.misc b/changelog.d/17325.misc new file mode 100644 index 0000000000..1a4ce7ceec --- /dev/null +++ b/changelog.d/17325.misc @@ -0,0 +1 @@ +This is a changelog so tests will run. \ No newline at end of file diff --git a/changelog.d/17329.doc b/changelog.d/17329.doc new file mode 100644 index 0000000000..2486256dad --- /dev/null +++ b/changelog.d/17329.doc @@ -0,0 +1 @@ +Update header in the README to visually fix the the auto-generated table of contents. \ No newline at end of file diff --git a/changelog.d/17331.misc b/changelog.d/17331.misc new file mode 100644 index 0000000000..79d3f33996 --- /dev/null +++ b/changelog.d/17331.misc @@ -0,0 +1 @@ +Change path of the experimental [MSC3575](https://github.com/matrix-org/matrix-spec-proposals/pull/3575) Sliding Sync implementation to `/org.matrix.simplified_msc3575/sync` since our simplified API is slightly incompatible with what's in the current MSC. diff --git a/changelog.d/17333.misc b/changelog.d/17333.misc new file mode 100644 index 0000000000..d3ef0b3777 --- /dev/null +++ b/changelog.d/17333.misc @@ -0,0 +1 @@ +Handle device lists notifications for large accounts more efficiently in worker mode. diff --git a/changelog.d/17335.feature b/changelog.d/17335.feature new file mode 100644 index 0000000000..c6beed42ed --- /dev/null +++ b/changelog.d/17335.feature @@ -0,0 +1 @@ +Add `is_invite` filtering to experimental [MSC3575](https://github.com/matrix-org/matrix-spec-proposals/pull/3575) Sliding Sync `/sync` endpoint. diff --git a/changelog.d/17336.bugfix b/changelog.d/17336.bugfix new file mode 100644 index 0000000000..618834302e --- /dev/null +++ b/changelog.d/17336.bugfix @@ -0,0 +1 @@ +Fix email notification subject when invited to a space. diff --git a/changelog.d/17338.misc b/changelog.d/17338.misc new file mode 100644 index 0000000000..1a81bdef85 --- /dev/null +++ b/changelog.d/17338.misc @@ -0,0 +1 @@ +Do not block event sending/receiving while calculating large event auth chains. diff --git a/changelog.d/17339.misc b/changelog.d/17339.misc new file mode 100644 index 0000000000..1d7cb96c8b --- /dev/null +++ b/changelog.d/17339.misc @@ -0,0 +1 @@ +Tidy up `parse_integer` docs and call sites to reflect the fact that they require non-negative integers by default, and bring `parse_integer_from_args` default in alignment. Contributed by Denis Kasak (@dkasak). diff --git a/changelog.d/17341.doc b/changelog.d/17341.doc new file mode 100644 index 0000000000..353c8adbe8 --- /dev/null +++ b/changelog.d/17341.doc @@ -0,0 +1 @@ +Fix stale references to the Foundation's Security Disclosure Policy. diff --git a/changelog.d/17347.doc b/changelog.d/17347.doc new file mode 100644 index 0000000000..6cd41be60f --- /dev/null +++ b/changelog.d/17347.doc @@ -0,0 +1 @@ +Add default values for `rc_invites.per_issuer` to docs. diff --git a/changelog.d/17348.doc b/changelog.d/17348.doc new file mode 100644 index 0000000000..4ce42bbadb --- /dev/null +++ b/changelog.d/17348.doc @@ -0,0 +1 @@ +Fix an error in the docs for `search_all_users` parameter under `user_directory`. diff --git a/changelog.d/17350.feature b/changelog.d/17350.feature new file mode 100644 index 0000000000..709366f5b8 --- /dev/null +++ b/changelog.d/17350.feature @@ -0,0 +1,2 @@ +Support [MSC3916](https://github.com/matrix-org/matrix-spec-proposals/blob/rav/authentication-for-media/proposals/3916-authentication-for-media.md) +by adding a federation /download endpoint. \ No newline at end of file diff --git a/changelog.d/17358.misc b/changelog.d/17358.misc new file mode 100644 index 0000000000..d3ef0b3777 --- /dev/null +++ b/changelog.d/17358.misc @@ -0,0 +1 @@ +Handle device lists notifications for large accounts more efficiently in worker mode. diff --git a/debian/changelog b/debian/changelog index 06b61b5d1b..731eacf20f 100644 --- a/debian/changelog +++ b/debian/changelog @@ -1,3 +1,51 @@ +matrix-synapse-py3 (1.109.0+nmu1) UNRELEASED; urgency=medium + + * `register_new_matrix_user` now supports a --password-file and a --exists-ok flag. + + -- Synapse Packaging team <packages@matrix.org> Tue, 18 Jun 2024 13:29:36 +0100 + +matrix-synapse-py3 (1.109.0) stable; urgency=medium + + * New synapse release 1.109.0. + + -- Synapse Packaging team <packages@matrix.org> Tue, 18 Jun 2024 09:45:15 +0000 + +matrix-synapse-py3 (1.109.0~rc3) stable; urgency=medium + + * New synapse release 1.109.0rc3. + + -- Synapse Packaging team <packages@matrix.org> Mon, 17 Jun 2024 12:05:24 +0000 + +matrix-synapse-py3 (1.109.0~rc2) stable; urgency=medium + + * New synapse release 1.109.0rc2. + + -- Synapse Packaging team <packages@matrix.org> Tue, 11 Jun 2024 13:20:17 +0000 + +matrix-synapse-py3 (1.109.0~rc1) stable; urgency=medium + + * New Synapse release 1.109.0rc1. + + -- Synapse Packaging team <packages@matrix.org> Tue, 04 Jun 2024 09:42:46 +0100 + +matrix-synapse-py3 (1.108.0) stable; urgency=medium + + * New Synapse release 1.108.0. + + -- Synapse Packaging team <packages@matrix.org> Tue, 28 May 2024 11:54:22 +0100 + +matrix-synapse-py3 (1.108.0~rc1) stable; urgency=medium + + * New Synapse release 1.108.0rc1. + + -- Synapse Packaging team <packages@matrix.org> Tue, 21 May 2024 10:54:13 +0100 + +matrix-synapse-py3 (1.107.0) stable; urgency=medium + + * New Synapse release 1.107.0. + + -- Synapse Packaging team <packages@matrix.org> Tue, 14 May 2024 14:15:34 +0100 + matrix-synapse-py3 (1.107.0~rc1) stable; urgency=medium * New Synapse release 1.107.0rc1. diff --git a/debian/register_new_matrix_user.ronn b/debian/register_new_matrix_user.ronn index 0410b1f4cd..aa305ec671 100644 --- a/debian/register_new_matrix_user.ronn +++ b/debian/register_new_matrix_user.ronn @@ -31,8 +31,12 @@ A sample YAML file accepted by `register_new_matrix_user` is described below: Local part of the new user. Will prompt if omitted. * `-p`, `--password`: - New password for user. Will prompt if omitted. Supplying the password - on the command line is not recommended. Use the STDIN instead. + New password for user. Will prompt if this option and `--password-file` are omitted. + Supplying the password on the command line is not recommended. + + * `--password-file`: + File containing the new password for user. If set, overrides `--password`. + This is a more secure alternative to specifying the password on the command line. * `-a`, `--admin`: Register new user as an admin. Will prompt if omitted. @@ -44,6 +48,9 @@ A sample YAML file accepted by `register_new_matrix_user` is described below: Shared secret as defined in server config file. This is an optional parameter as it can be also supplied via the YAML file. + * `--exists-ok`: + Do not fail if the user already exists. The user account will be not updated in this case. + * `server_url`: URL of the home server. Defaults to 'https://localhost:8448'. diff --git a/docker/complement/conf/workers-shared-extra.yaml.j2 b/docker/complement/conf/workers-shared-extra.yaml.j2 index 4c41ee7709..6588b3ce14 100644 --- a/docker/complement/conf/workers-shared-extra.yaml.j2 +++ b/docker/complement/conf/workers-shared-extra.yaml.j2 @@ -105,8 +105,6 @@ experimental_features: # Expose a room summary for public rooms msc3266_enabled: true - msc4115_membership_on_events: true - server_notices: system_mxid_localpart: _server system_mxid_display_name: "Server Alert" diff --git a/docker/conf/homeserver.yaml b/docker/conf/homeserver.yaml index c412ba2e87..2890990705 100644 --- a/docker/conf/homeserver.yaml +++ b/docker/conf/homeserver.yaml @@ -176,7 +176,6 @@ app_service_config_files: {% endif %} macaroon_secret_key: "{{ SYNAPSE_MACAROON_SECRET_KEY }}" -expire_access_token: False ## Signing Keys ## diff --git a/docker/configure_workers_and_start.py b/docker/configure_workers_and_start.py index 77534a4f4f..063f3727f9 100755 --- a/docker/configure_workers_and_start.py +++ b/docker/configure_workers_and_start.py @@ -211,6 +211,8 @@ WORKERS_CONFIG: Dict[str, Dict[str, Any]] = { "^/_matrix/federation/(v1|v2)/make_leave/", "^/_matrix/federation/(v1|v2)/send_join/", "^/_matrix/federation/(v1|v2)/send_leave/", + "^/_matrix/federation/v1/make_knock/", + "^/_matrix/federation/v1/send_knock/", "^/_matrix/federation/(v1|v2)/invite/", "^/_matrix/federation/(v1|v2)/query_auth/", "^/_matrix/federation/(v1|v2)/event_auth/", diff --git a/docs/admin_api/rooms.md b/docs/admin_api/rooms.md index 6935ec4a45..8e3a367e90 100644 --- a/docs/admin_api/rooms.md +++ b/docs/admin_api/rooms.md @@ -36,6 +36,10 @@ The following query parameters are available: - the room's name, - the local part of the room's canonical alias, or - the complete (local and server part) room's id (case sensitive). +* `public_rooms` - Optional flag to filter public rooms. If `true`, only public rooms are queried. If `false`, public rooms are excluded from + the query. When the flag is absent (the default), **both** public and non-public rooms are included in the search results. +* `empty_rooms` - Optional flag to filter empty rooms. A room is empty if joined_members is zero. If `true`, only empty rooms are queried. If `false`, empty rooms are excluded from + the query. When the flag is absent (the default), **both** empty and non-empty rooms are included in the search results. Defaults to no filtering. diff --git a/docs/openid.md b/docs/openid.md index 9773a7de52..7a10b1615b 100644 --- a/docs/openid.md +++ b/docs/openid.md @@ -525,6 +525,8 @@ oidc_providers: (`Options > Security > ID Token signature algorithm` and `Options > Security > Access Token signature algorithm`) - Scopes: OpenID, Email and Profile +- Force claims into `id_token` + (`Options > Advanced > Force claims to be returned in ID Token`) - Allowed redirection addresses for login (`Options > Basic > Allowed redirection addresses for login` ) : `[synapse public baseurl]/_synapse/client/oidc/callback` diff --git a/docs/postgres.md b/docs/postgres.md index ae34f7689b..d06f0cda10 100644 --- a/docs/postgres.md +++ b/docs/postgres.md @@ -242,12 +242,11 @@ host all all ::1/128 ident ### Fixing incorrect `COLLATE` or `CTYPE` -Synapse will refuse to set up a new database if it has the wrong values of -`COLLATE` and `CTYPE` set. Synapse will also refuse to start an existing database with incorrect values -of `COLLATE` and `CTYPE` unless the config flag `allow_unsafe_locale`, found in the -`database` section of the config, is set to true. Using different locales can cause issues if the locale library is updated from -underneath the database, or if a different version of the locale is used on any -replicas. +Synapse will refuse to start when using a database with incorrect values of +`COLLATE` and `CTYPE` unless the config flag `allow_unsafe_locale`, found in the +`database` section of the config, is set to true. Using different locales can +cause issues if the locale library is updated from underneath the database, or +if a different version of the locale is used on any replicas. If you have a database with an unsafe locale, the safest way to fix the issue is to dump the database and recreate it with the correct locale parameter (as shown above). It is also possible to change the @@ -256,13 +255,3 @@ however extreme care must be taken to avoid database corruption. Note that the above may fail with an error about duplicate rows if corruption has already occurred, and such duplicate rows will need to be manually removed. - -### Fixing inconsistent sequences error - -Synapse uses Postgres sequences to generate IDs for various tables. A sequence -and associated table can get out of sync if, for example, Synapse has been -downgraded and then upgraded again. - -To fix the issue shut down Synapse (including any and all workers) and run the -SQL command included in the error message. Once done Synapse should start -successfully. diff --git a/docs/usage/administration/admin_faq.md b/docs/usage/administration/admin_faq.md index 0d98f73fb1..a1184d0375 100644 --- a/docs/usage/administration/admin_faq.md +++ b/docs/usage/administration/admin_faq.md @@ -250,10 +250,10 @@ Using [libjemalloc](https://jemalloc.net) can also yield a significant improvement in overall memory use, and especially in terms of giving back RAM to the OS. To use it, the library must simply be put in the LD_PRELOAD environment variable when launching Synapse. On Debian, this -can be done by installing the `libjemalloc1` package and adding this +can be done by installing the `libjemalloc2` package and adding this line to `/etc/default/matrix-synapse`: - LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libjemalloc.so.1 + LD_PRELOAD=/usr/lib/x86_64-linux-gnu/libjemalloc.so.2 This made a significant difference on Python 2.7 - it's unclear how much of an improvement it provides on Python 3.x. diff --git a/docs/usage/configuration/config_documentation.md b/docs/usage/configuration/config_documentation.md index 2046bf4564..80a7bf9d21 100644 --- a/docs/usage/configuration/config_documentation.md +++ b/docs/usage/configuration/config_documentation.md @@ -1232,6 +1232,31 @@ federation_domain_whitelist: - syd.example.com ``` --- +### `federation_whitelist_endpoint_enabled` + +Enables an endpoint for fetching the federation whitelist config. + +The request method and path is `GET /_synapse/client/v1/config/federation_whitelist`, and the +response format is: + +```json +{ + "whitelist_enabled": true, // Whether the federation whitelist is being enforced + "whitelist": [ // Which server names are allowed by the whitelist + "example.com" + ] +} +``` + +If `whitelist_enabled` is `false` then the server is permitted to federate with all others. + +The endpoint requires authentication. + +Example configuration: +```yaml +federation_whitelist_endpoint_enabled: true +``` +--- ### `federation_metrics_domains` Report prometheus metrics on the age of PDUs being sent to and received from @@ -1734,8 +1759,9 @@ rc_3pid_validation: ### `rc_invites` This option sets ratelimiting how often invites can be sent in a room or to a -specific user. `per_room` defaults to `per_second: 0.3`, `burst_count: 10` and -`per_user` defaults to `per_second: 0.003`, `burst_count: 5`. +specific user. `per_room` defaults to `per_second: 0.3`, `burst_count: 10`, +`per_user` defaults to `per_second: 0.003`, `burst_count: 5`, and `per_issuer` +defaults to `per_second: 0.3`, `burst_count: 10`. Client requests that invite user(s) when [creating a room](https://spec.matrix.org/v1.2/client-server-api/#post_matrixclientv3createroom) @@ -1921,6 +1947,24 @@ Example configuration: max_image_pixels: 35M ``` --- +### `remote_media_download_burst_count` + +Remote media downloads are ratelimited using a [leaky bucket algorithm](https://en.wikipedia.org/wiki/Leaky_bucket), where a given "bucket" is keyed to the IP address of the requester when requesting remote media downloads. This configuration option sets the size of the bucket against which the size in bytes of downloads are penalized - if the bucket is full, ie a given number of bytes have already been downloaded, further downloads will be denied until the bucket drains. Defaults to 500MiB. See also `remote_media_download_per_second` which determines the rate at which the "bucket" is emptied and thus has available space to authorize new requests. + +Example configuration: +```yaml +remote_media_download_burst_count: 200M +``` +--- +### `remote_media_download_per_second` + +Works in conjunction with `remote_media_download_burst_count` to ratelimit remote media downloads - this configuration option determines the rate at which the "bucket" (see above) leaks in bytes per second. As requests are made to download remote media, the size of those requests in bytes is added to the bucket, and once the bucket has reached it's capacity, no more requests will be allowed until a number of bytes has "drained" from the bucket. This setting determines the rate at which bytes drain from the bucket, with the practical effect that the larger the number, the faster the bucket leaks, allowing for more bytes downloaded over a shorter period of time. Defaults to 87KiB per second. See also `remote_media_download_burst_count`. + +Example configuration: +```yaml +remote_media_download_per_second: 40K +``` +--- ### `prevent_media_downloads_from` A list of domains to never download media from. Media from these @@ -2675,7 +2719,7 @@ Example configuration: session_lifetime: 24h ``` --- -### `refresh_access_token_lifetime` +### `refreshable_access_token_lifetime` Time that an access token remains valid for, if the session is using refresh tokens. @@ -3533,6 +3577,15 @@ Has the following sub-options: users. This allows the CAS SSO flow to be limited to sign in only, rather than automatically registering users that have a valid SSO login but do not have a pre-registered account. Defaults to true. +* `allow_numeric_ids`: set to 'true' allow numeric user IDs (default false). + This allows CAS SSO flow to provide user IDs composed of numbers only. + These identifiers will be prefixed by the letter "u" by default. + The prefix can be configured using the "numeric_ids_prefix" option. + Be careful to choose the prefix correctly to avoid any possible conflicts + (e.g. user 1234 becomes u1234 when a user u1234 already exists). +* `numeric_ids_prefix`: the prefix you wish to add in front of a numeric user ID + when the "allow_numeric_ids" option is set to "true". + By default, the prefix is the letter "u" and only alphanumeric characters are allowed. *Added in Synapse 1.93.0.* @@ -3547,6 +3600,8 @@ cas_config: userGroup: "staff" department: None enable_registration: true + allow_numeric_ids: true + numeric_ids_prefix: "numericuser" ``` --- ### `sso` @@ -3752,7 +3807,8 @@ This setting defines options related to the user directory. This option has the following sub-options: * `enabled`: Defines whether users can search the user directory. If false then empty responses are returned to all queries. Defaults to true. -* `search_all_users`: Defines whether to search all users visible to your HS at the time the search is performed. If set to true, will return all users who share a room with the user from the homeserver. +* `search_all_users`: Defines whether to search all users visible to your homeserver at the time the search is performed. + If set to true, will return all users known to the homeserver matching the search query. If false, search results will only contain users visible in public rooms and users sharing a room with the requester. Defaults to false. @@ -4096,7 +4152,7 @@ By default, no room is excluded. Example configuration: ```yaml exclude_rooms_from_sync: - - !foo:example.com + - "!foo:example.com" ``` --- @@ -4559,3 +4615,32 @@ background_updates: min_batch_size: 10 default_batch_size: 50 ``` +--- +## Auto Accept Invites +Configuration settings related to automatically accepting invites. + +--- +### `auto_accept_invites` + +Automatically accepting invites controls whether users are presented with an invite request or if they +are instead automatically joined to a room when receiving an invite. Set the `enabled` sub-option to true to +enable auto-accepting invites. Defaults to false. +This setting has the following sub-options: +* `enabled`: Whether to run the auto-accept invites logic. Defaults to false. +* `only_for_direct_messages`: Whether invites should be automatically accepted for all room types, or only + for direct messages. Defaults to false. +* `only_from_local_users`: Whether to only automatically accept invites from users on this homeserver. Defaults to false. +* `worker_to_run_on`: Which worker to run this module on. This must match the "worker_name". + +NOTE: Care should be taken not to enable this setting if the `synapse_auto_accept_invite` module is enabled and installed. +The two modules will compete to perform the same task and may result in undesired behaviour. For example, multiple join +events could be generated from a single invite. + +Example configuration: +```yaml +auto_accept_invites: + enabled: true + only_for_direct_messages: true + only_from_local_users: true + worker_to_run_on: "worker_1" +``` diff --git a/docs/welcome_and_overview.md b/docs/welcome_and_overview.md index ae5d0f5d90..b88fed7e44 100644 --- a/docs/welcome_and_overview.md +++ b/docs/welcome_and_overview.md @@ -62,6 +62,6 @@ following documentation: ## Reporting a security vulnerability -If you've found a security issue in Synapse or any other Matrix.org Foundation -project, please report it to us in accordance with our [Security Disclosure -Policy](https://www.matrix.org/security-disclosure-policy/). Thank you! +If you've found a security issue in Synapse or any other Element project, +please report it to us in accordance with our [Security Disclosure +Policy](https://element.io/security/security-disclosure-policy). Thank you! diff --git a/docs/workers.md b/docs/workers.md index 82f4bfc1d1..1f6bfd9e7f 100644 --- a/docs/workers.md +++ b/docs/workers.md @@ -211,6 +211,8 @@ information. ^/_matrix/federation/v1/make_leave/ ^/_matrix/federation/(v1|v2)/send_join/ ^/_matrix/federation/(v1|v2)/send_leave/ + ^/_matrix/federation/v1/make_knock/ + ^/_matrix/federation/v1/send_knock/ ^/_matrix/federation/(v1|v2)/invite/ ^/_matrix/federation/v1/event_auth/ ^/_matrix/federation/v1/timestamp_to_event/ @@ -535,7 +537,7 @@ the stream writer for the `presence` stream: ##### The `push_rules` stream The following endpoints should be routed directly to the worker configured as -the stream writer for the `push` stream: +the stream writer for the `push_rules` stream: ^/_matrix/client/(api/v1|r0|v3|unstable)/pushrules/ diff --git a/poetry.lock b/poetry.lock index 502f45f8bb..1bae0ea388 100644 --- a/poetry.lock +++ b/poetry.lock @@ -35,13 +35,13 @@ tests-no-zope = ["attrs[tests-mypy]", "cloudpickle", "hypothesis", "pympler", "p [[package]] name = "authlib" -version = "1.3.0" +version = "1.3.1" description = "The ultimate Python library in building OAuth and OpenID Connect servers and clients." optional = true python-versions = ">=3.8" files = [ - {file = "Authlib-1.3.0-py2.py3-none-any.whl", hash = "sha256:9637e4de1fb498310a56900b3e2043a206b03cb11c05422014b0302cbc814be3"}, - {file = "Authlib-1.3.0.tar.gz", hash = "sha256:959ea62a5b7b5123c5059758296122b57cd2585ae2ed1c0622c21b371ffdae06"}, + {file = "Authlib-1.3.1-py2.py3-none-any.whl", hash = "sha256:d35800b973099bbadc49b42b256ecb80041ad56b7fe1216a362c7943c088f377"}, + {file = "authlib-1.3.1.tar.gz", hash = "sha256:7ae843f03c06c5c0debd63c9db91f9fda64fa62a42a77419fa15fbb7e7a58917"}, ] [package.dependencies] @@ -67,38 +67,38 @@ visualize = ["Twisted (>=16.1.1)", "graphviz (>0.5.1)"] [[package]] name = "bcrypt" -version = "4.1.2" +version = "4.1.3" description = "Modern password hashing for your software and your servers" optional = false python-versions = ">=3.7" files = [ - {file = "bcrypt-4.1.2-cp37-abi3-macosx_10_12_universal2.whl", hash = "sha256:ac621c093edb28200728a9cca214d7e838529e557027ef0581685909acd28b5e"}, - {file = "bcrypt-4.1.2-cp37-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ea505c97a5c465ab8c3ba75c0805a102ce526695cd6818c6de3b1a38f6f60da1"}, - {file = "bcrypt-4.1.2-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:57fa9442758da926ed33a91644649d3e340a71e2d0a5a8de064fb621fd5a3326"}, - {file = "bcrypt-4.1.2-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:eb3bd3321517916696233b5e0c67fd7d6281f0ef48e66812db35fc963a422a1c"}, - {file = "bcrypt-4.1.2-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:6cad43d8c63f34b26aef462b6f5e44fdcf9860b723d2453b5d391258c4c8e966"}, - {file = "bcrypt-4.1.2-cp37-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:44290ccc827d3a24604f2c8bcd00d0da349e336e6503656cb8192133e27335e2"}, - {file = "bcrypt-4.1.2-cp37-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:732b3920a08eacf12f93e6b04ea276c489f1c8fb49344f564cca2adb663b3e4c"}, - {file = "bcrypt-4.1.2-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:1c28973decf4e0e69cee78c68e30a523be441972c826703bb93099868a8ff5b5"}, - {file = "bcrypt-4.1.2-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:b8df79979c5bae07f1db22dcc49cc5bccf08a0380ca5c6f391cbb5790355c0b0"}, - {file = "bcrypt-4.1.2-cp37-abi3-win32.whl", hash = "sha256:fbe188b878313d01b7718390f31528be4010fed1faa798c5a1d0469c9c48c369"}, - {file = "bcrypt-4.1.2-cp37-abi3-win_amd64.whl", hash = "sha256:9800ae5bd5077b13725e2e3934aa3c9c37e49d3ea3d06318010aa40f54c63551"}, - {file = "bcrypt-4.1.2-cp39-abi3-macosx_10_12_universal2.whl", hash = "sha256:71b8be82bc46cedd61a9f4ccb6c1a493211d031415a34adde3669ee1b0afbb63"}, - {file = "bcrypt-4.1.2-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:68e3c6642077b0c8092580c819c1684161262b2e30c4f45deb000c38947bf483"}, - {file = "bcrypt-4.1.2-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:387e7e1af9a4dd636b9505a465032f2f5cb8e61ba1120e79a0e1cd0b512f3dfc"}, - {file = "bcrypt-4.1.2-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:f70d9c61f9c4ca7d57f3bfe88a5ccf62546ffbadf3681bb1e268d9d2e41c91a7"}, - {file = "bcrypt-4.1.2-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:2a298db2a8ab20056120b45e86c00a0a5eb50ec4075b6142db35f593b97cb3fb"}, - {file = "bcrypt-4.1.2-cp39-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:ba55e40de38a24e2d78d34c2d36d6e864f93e0d79d0b6ce915e4335aa81d01b1"}, - {file = "bcrypt-4.1.2-cp39-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:3566a88234e8de2ccae31968127b0ecccbb4cddb629da744165db72b58d88ca4"}, - {file = "bcrypt-4.1.2-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:b90e216dc36864ae7132cb151ffe95155a37a14e0de3a8f64b49655dd959ff9c"}, - {file = "bcrypt-4.1.2-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:69057b9fc5093ea1ab00dd24ede891f3e5e65bee040395fb1e66ee196f9c9b4a"}, - {file = "bcrypt-4.1.2-cp39-abi3-win32.whl", hash = "sha256:02d9ef8915f72dd6daaef40e0baeef8a017ce624369f09754baf32bb32dba25f"}, - {file = "bcrypt-4.1.2-cp39-abi3-win_amd64.whl", hash = "sha256:be3ab1071662f6065899fe08428e45c16aa36e28bc42921c4901a191fda6ee42"}, - {file = "bcrypt-4.1.2-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:d75fc8cd0ba23f97bae88a6ec04e9e5351ff3c6ad06f38fe32ba50cbd0d11946"}, - {file = "bcrypt-4.1.2-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:a97e07e83e3262599434816f631cc4c7ca2aa8e9c072c1b1a7fec2ae809a1d2d"}, - {file = "bcrypt-4.1.2-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:e51c42750b7585cee7892c2614be0d14107fad9581d1738d954a262556dd1aab"}, - {file = "bcrypt-4.1.2-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:ba4e4cc26610581a6329b3937e02d319f5ad4b85b074846bf4fef8a8cf51e7bb"}, - {file = "bcrypt-4.1.2.tar.gz", hash = "sha256:33313a1200a3ae90b75587ceac502b048b840fc69e7f7a0905b5f87fac7a1258"}, + {file = "bcrypt-4.1.3-cp37-abi3-macosx_10_12_universal2.whl", hash = "sha256:48429c83292b57bf4af6ab75809f8f4daf52aa5d480632e53707805cc1ce9b74"}, + {file = "bcrypt-4.1.3-cp37-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4a8bea4c152b91fd8319fef4c6a790da5c07840421c2b785084989bf8bbb7455"}, + {file = "bcrypt-4.1.3-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3d3b317050a9a711a5c7214bf04e28333cf528e0ed0ec9a4e55ba628d0f07c1a"}, + {file = "bcrypt-4.1.3-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:094fd31e08c2b102a14880ee5b3d09913ecf334cd604af27e1013c76831f7b05"}, + {file = "bcrypt-4.1.3-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:4fb253d65da30d9269e0a6f4b0de32bd657a0208a6f4e43d3e645774fb5457f3"}, + {file = "bcrypt-4.1.3-cp37-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:193bb49eeeb9c1e2db9ba65d09dc6384edd5608d9d672b4125e9320af9153a15"}, + {file = "bcrypt-4.1.3-cp37-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:8cbb119267068c2581ae38790e0d1fbae65d0725247a930fc9900c285d95725d"}, + {file = "bcrypt-4.1.3-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:6cac78a8d42f9d120b3987f82252bdbeb7e6e900a5e1ba37f6be6fe4e3848286"}, + {file = "bcrypt-4.1.3-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:01746eb2c4299dd0ae1670234bf77704f581dd72cc180f444bfe74eb80495b64"}, + {file = "bcrypt-4.1.3-cp37-abi3-win32.whl", hash = "sha256:037c5bf7c196a63dcce75545c8874610c600809d5d82c305dd327cd4969995bf"}, + {file = "bcrypt-4.1.3-cp37-abi3-win_amd64.whl", hash = "sha256:8a893d192dfb7c8e883c4576813bf18bb9d59e2cfd88b68b725990f033f1b978"}, + {file = "bcrypt-4.1.3-cp39-abi3-macosx_10_12_universal2.whl", hash = "sha256:0d4cf6ef1525f79255ef048b3489602868c47aea61f375377f0d00514fe4a78c"}, + {file = "bcrypt-4.1.3-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f5698ce5292a4e4b9e5861f7e53b1d89242ad39d54c3da451a93cac17b61921a"}, + {file = "bcrypt-4.1.3-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ec3c2e1ca3e5c4b9edb94290b356d082b721f3f50758bce7cce11d8a7c89ce84"}, + {file = "bcrypt-4.1.3-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:3a5be252fef513363fe281bafc596c31b552cf81d04c5085bc5dac29670faa08"}, + {file = "bcrypt-4.1.3-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:5f7cd3399fbc4ec290378b541b0cf3d4398e4737a65d0f938c7c0f9d5e686611"}, + {file = "bcrypt-4.1.3-cp39-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:c4c8d9b3e97209dd7111bf726e79f638ad9224b4691d1c7cfefa571a09b1b2d6"}, + {file = "bcrypt-4.1.3-cp39-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:31adb9cbb8737a581a843e13df22ffb7c84638342de3708a98d5c986770f2834"}, + {file = "bcrypt-4.1.3-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:551b320396e1d05e49cc18dd77d970accd52b322441628aca04801bbd1d52a73"}, + {file = "bcrypt-4.1.3-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:6717543d2c110a155e6821ce5670c1f512f602eabb77dba95717ca76af79867d"}, + {file = "bcrypt-4.1.3-cp39-abi3-win32.whl", hash = "sha256:6004f5229b50f8493c49232b8e75726b568535fd300e5039e255d919fc3a07f2"}, + {file = "bcrypt-4.1.3-cp39-abi3-win_amd64.whl", hash = "sha256:2505b54afb074627111b5a8dc9b6ae69d0f01fea65c2fcaea403448c503d3991"}, + {file = "bcrypt-4.1.3-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:cb9c707c10bddaf9e5ba7cdb769f3e889e60b7d4fea22834b261f51ca2b89fed"}, + {file = "bcrypt-4.1.3-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:9f8ea645eb94fb6e7bea0cf4ba121c07a3a182ac52876493870033141aa687bc"}, + {file = "bcrypt-4.1.3-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:f44a97780677e7ac0ca393bd7982b19dbbd8d7228c1afe10b128fd9550eef5f1"}, + {file = "bcrypt-4.1.3-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:d84702adb8f2798d813b17d8187d27076cca3cd52fe3686bb07a9083930ce650"}, + {file = "bcrypt-4.1.3.tar.gz", hash = "sha256:2ee15dd749f5952fe3f0430d0ff6b74082e159c50332a1413d51b5689cf06623"}, ] [package.extras] @@ -107,33 +107,33 @@ typecheck = ["mypy"] [[package]] name = "black" -version = "24.2.0" +version = "24.4.2" description = "The uncompromising code formatter." optional = false python-versions = ">=3.8" files = [ - {file = "black-24.2.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:6981eae48b3b33399c8757036c7f5d48a535b962a7c2310d19361edeef64ce29"}, - {file = "black-24.2.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d533d5e3259720fdbc1b37444491b024003e012c5173f7d06825a77508085430"}, - {file = "black-24.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:61a0391772490ddfb8a693c067df1ef5227257e72b0e4108482b8d41b5aee13f"}, - {file = "black-24.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:992e451b04667116680cb88f63449267c13e1ad134f30087dec8527242e9862a"}, - {file = "black-24.2.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:163baf4ef40e6897a2a9b83890e59141cc8c2a98f2dda5080dc15c00ee1e62cd"}, - {file = "black-24.2.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:e37c99f89929af50ffaf912454b3e3b47fd64109659026b678c091a4cd450fb2"}, - {file = "black-24.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4f9de21bafcba9683853f6c96c2d515e364aee631b178eaa5145fc1c61a3cc92"}, - {file = "black-24.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:9db528bccb9e8e20c08e716b3b09c6bdd64da0dd129b11e160bf082d4642ac23"}, - {file = "black-24.2.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:d84f29eb3ee44859052073b7636533ec995bd0f64e2fb43aeceefc70090e752b"}, - {file = "black-24.2.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:1e08fb9a15c914b81dd734ddd7fb10513016e5ce7e6704bdd5e1251ceee51ac9"}, - {file = "black-24.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:810d445ae6069ce64030c78ff6127cd9cd178a9ac3361435708b907d8a04c693"}, - {file = "black-24.2.0-cp312-cp312-win_amd64.whl", hash = "sha256:ba15742a13de85e9b8f3239c8f807723991fbfae24bad92d34a2b12e81904982"}, - {file = "black-24.2.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:7e53a8c630f71db01b28cd9602a1ada68c937cbf2c333e6ed041390d6968faf4"}, - {file = "black-24.2.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:93601c2deb321b4bad8f95df408e3fb3943d85012dddb6121336b8e24a0d1218"}, - {file = "black-24.2.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a0057f800de6acc4407fe75bb147b0c2b5cbb7c3ed110d3e5999cd01184d53b0"}, - {file = "black-24.2.0-cp38-cp38-win_amd64.whl", hash = "sha256:faf2ee02e6612577ba0181f4347bcbcf591eb122f7841ae5ba233d12c39dcb4d"}, - {file = "black-24.2.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:057c3dc602eaa6fdc451069bd027a1b2635028b575a6c3acfd63193ced20d9c8"}, - {file = "black-24.2.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:08654d0797e65f2423f850fc8e16a0ce50925f9337fb4a4a176a7aa4026e63f8"}, - {file = "black-24.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ca610d29415ee1a30a3f30fab7a8f4144e9d34c89a235d81292a1edb2b55f540"}, - {file = "black-24.2.0-cp39-cp39-win_amd64.whl", hash = "sha256:4dd76e9468d5536abd40ffbc7a247f83b2324f0c050556d9c371c2b9a9a95e31"}, - {file = "black-24.2.0-py3-none-any.whl", hash = "sha256:e8a6ae970537e67830776488bca52000eaa37fa63b9988e8c487458d9cd5ace6"}, - {file = "black-24.2.0.tar.gz", hash = "sha256:bce4f25c27c3435e4dace4815bcb2008b87e167e3bf4ee47ccdc5ce906eb4894"}, + {file = "black-24.4.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:dd1b5a14e417189db4c7b64a6540f31730713d173f0b63e55fabd52d61d8fdce"}, + {file = "black-24.4.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8e537d281831ad0e71007dcdcbe50a71470b978c453fa41ce77186bbe0ed6021"}, + {file = "black-24.4.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:eaea3008c281f1038edb473c1aa8ed8143a5535ff18f978a318f10302b254063"}, + {file = "black-24.4.2-cp310-cp310-win_amd64.whl", hash = "sha256:7768a0dbf16a39aa5e9a3ded568bb545c8c2727396d063bbaf847df05b08cd96"}, + {file = "black-24.4.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:257d724c2c9b1660f353b36c802ccece186a30accc7742c176d29c146df6e474"}, + {file = "black-24.4.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:bdde6f877a18f24844e381d45e9947a49e97933573ac9d4345399be37621e26c"}, + {file = "black-24.4.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e151054aa00bad1f4e1f04919542885f89f5f7d086b8a59e5000e6c616896ffb"}, + {file = "black-24.4.2-cp311-cp311-win_amd64.whl", hash = "sha256:7e122b1c4fb252fd85df3ca93578732b4749d9be076593076ef4d07a0233c3e1"}, + {file = "black-24.4.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:accf49e151c8ed2c0cdc528691838afd217c50412534e876a19270fea1e28e2d"}, + {file = "black-24.4.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:88c57dc656038f1ab9f92b3eb5335ee9b021412feaa46330d5eba4e51fe49b04"}, + {file = "black-24.4.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:be8bef99eb46d5021bf053114442914baeb3649a89dc5f3a555c88737e5e98fc"}, + {file = "black-24.4.2-cp312-cp312-win_amd64.whl", hash = "sha256:415e686e87dbbe6f4cd5ef0fbf764af7b89f9057b97c908742b6008cc554b9c0"}, + {file = "black-24.4.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:bf10f7310db693bb62692609b397e8d67257c55f949abde4c67f9cc574492cc7"}, + {file = "black-24.4.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:98e123f1d5cfd42f886624d84464f7756f60ff6eab89ae845210631714f6db94"}, + {file = "black-24.4.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:48a85f2cb5e6799a9ef05347b476cce6c182d6c71ee36925a6c194d074336ef8"}, + {file = "black-24.4.2-cp38-cp38-win_amd64.whl", hash = "sha256:b1530ae42e9d6d5b670a34db49a94115a64596bc77710b1d05e9801e62ca0a7c"}, + {file = "black-24.4.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:37aae07b029fa0174d39daf02748b379399b909652a806e5708199bd93899da1"}, + {file = "black-24.4.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:da33a1a5e49c4122ccdfd56cd021ff1ebc4a1ec4e2d01594fef9b6f267a9e741"}, + {file = "black-24.4.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ef703f83fc32e131e9bcc0a5094cfe85599e7109f896fe8bc96cc402f3eb4b6e"}, + {file = "black-24.4.2-cp39-cp39-win_amd64.whl", hash = "sha256:b9176b9832e84308818a99a561e90aa479e73c523b3f77afd07913380ae2eab7"}, + {file = "black-24.4.2-py3-none-any.whl", hash = "sha256:d36ed1124bb81b32f8614555b34cc4259c3fbc7eec17870e8ff8ded335b58d8c"}, + {file = "black-24.4.2.tar.gz", hash = "sha256:c872b53057f000085da66a19c55d68f6f8ddcac2642392ad3a355878406fbd4d"}, ] [package.dependencies] @@ -403,43 +403,43 @@ files = [ [[package]] name = "cryptography" -version = "42.0.5" +version = "42.0.7" description = "cryptography is a package which provides cryptographic recipes and primitives to Python developers." optional = false python-versions = ">=3.7" files = [ - {file = "cryptography-42.0.5-cp37-abi3-macosx_10_12_universal2.whl", hash = "sha256:a30596bae9403a342c978fb47d9b0ee277699fa53bbafad14706af51fe543d16"}, - {file = "cryptography-42.0.5-cp37-abi3-macosx_10_12_x86_64.whl", hash = "sha256:b7ffe927ee6531c78f81aa17e684e2ff617daeba7f189f911065b2ea2d526dec"}, - {file = "cryptography-42.0.5-cp37-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2424ff4c4ac7f6b8177b53c17ed5d8fa74ae5955656867f5a8affaca36a27abb"}, - {file = "cryptography-42.0.5-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:329906dcc7b20ff3cad13c069a78124ed8247adcac44b10bea1130e36caae0b4"}, - {file = "cryptography-42.0.5-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:b03c2ae5d2f0fc05f9a2c0c997e1bc18c8229f392234e8a0194f202169ccd278"}, - {file = "cryptography-42.0.5-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:f8837fe1d6ac4a8052a9a8ddab256bc006242696f03368a4009be7ee3075cdb7"}, - {file = "cryptography-42.0.5-cp37-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:0270572b8bd2c833c3981724b8ee9747b3ec96f699a9665470018594301439ee"}, - {file = "cryptography-42.0.5-cp37-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:b8cac287fafc4ad485b8a9b67d0ee80c66bf3574f655d3b97ef2e1082360faf1"}, - {file = "cryptography-42.0.5-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:16a48c23a62a2f4a285699dba2e4ff2d1cff3115b9df052cdd976a18856d8e3d"}, - {file = "cryptography-42.0.5-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:2bce03af1ce5a5567ab89bd90d11e7bbdff56b8af3acbbec1faded8f44cb06da"}, - {file = "cryptography-42.0.5-cp37-abi3-win32.whl", hash = "sha256:b6cd2203306b63e41acdf39aa93b86fb566049aeb6dc489b70e34bcd07adca74"}, - {file = "cryptography-42.0.5-cp37-abi3-win_amd64.whl", hash = "sha256:98d8dc6d012b82287f2c3d26ce1d2dd130ec200c8679b6213b3c73c08b2b7940"}, - {file = "cryptography-42.0.5-cp39-abi3-macosx_10_12_universal2.whl", hash = "sha256:5e6275c09d2badf57aea3afa80d975444f4be8d3bc58f7f80d2a484c6f9485c8"}, - {file = "cryptography-42.0.5-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e4985a790f921508f36f81831817cbc03b102d643b5fcb81cd33df3fa291a1a1"}, - {file = "cryptography-42.0.5-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7cde5f38e614f55e28d831754e8a3bacf9ace5d1566235e39d91b35502d6936e"}, - {file = "cryptography-42.0.5-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:7367d7b2eca6513681127ebad53b2582911d1736dc2ffc19f2c3ae49997496bc"}, - {file = "cryptography-42.0.5-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:cd2030f6650c089aeb304cf093f3244d34745ce0cfcc39f20c6fbfe030102e2a"}, - {file = "cryptography-42.0.5-cp39-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:a2913c5375154b6ef2e91c10b5720ea6e21007412f6437504ffea2109b5a33d7"}, - {file = "cryptography-42.0.5-cp39-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:c41fb5e6a5fe9ebcd58ca3abfeb51dffb5d83d6775405305bfa8715b76521922"}, - {file = "cryptography-42.0.5-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:3eaafe47ec0d0ffcc9349e1708be2aaea4c6dd4978d76bf6eb0cb2c13636c6fc"}, - {file = "cryptography-42.0.5-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:1b95b98b0d2af784078fa69f637135e3c317091b615cd0905f8b8a087e86fa30"}, - {file = "cryptography-42.0.5-cp39-abi3-win32.whl", hash = "sha256:1f71c10d1e88467126f0efd484bd44bca5e14c664ec2ede64c32f20875c0d413"}, - {file = "cryptography-42.0.5-cp39-abi3-win_amd64.whl", hash = "sha256:a011a644f6d7d03736214d38832e030d8268bcff4a41f728e6030325fea3e400"}, - {file = "cryptography-42.0.5-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:9481ffe3cf013b71b2428b905c4f7a9a4f76ec03065b05ff499bb5682a8d9ad8"}, - {file = "cryptography-42.0.5-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:ba334e6e4b1d92442b75ddacc615c5476d4ad55cc29b15d590cc6b86efa487e2"}, - {file = "cryptography-42.0.5-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:ba3e4a42397c25b7ff88cdec6e2a16c2be18720f317506ee25210f6d31925f9c"}, - {file = "cryptography-42.0.5-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:111a0d8553afcf8eb02a4fea6ca4f59d48ddb34497aa8706a6cf536f1a5ec576"}, - {file = "cryptography-42.0.5-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:cd65d75953847815962c84a4654a84850b2bb4aed3f26fadcc1c13892e1e29f6"}, - {file = "cryptography-42.0.5-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:e807b3188f9eb0eaa7bbb579b462c5ace579f1cedb28107ce8b48a9f7ad3679e"}, - {file = "cryptography-42.0.5-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:f12764b8fffc7a123f641d7d049d382b73f96a34117e0b637b80643169cec8ac"}, - {file = "cryptography-42.0.5-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:37dd623507659e08be98eec89323469e8c7b4c1407c85112634ae3dbdb926fdd"}, - {file = "cryptography-42.0.5.tar.gz", hash = "sha256:6fe07eec95dfd477eb9530aef5bead34fec819b3aaf6c5bd6d20565da607bfe1"}, + {file = "cryptography-42.0.7-cp37-abi3-macosx_10_12_universal2.whl", hash = "sha256:a987f840718078212fdf4504d0fd4c6effe34a7e4740378e59d47696e8dfb477"}, + {file = "cryptography-42.0.7-cp37-abi3-macosx_10_12_x86_64.whl", hash = "sha256:bd13b5e9b543532453de08bcdc3cc7cebec6f9883e886fd20a92f26940fd3e7a"}, + {file = "cryptography-42.0.7-cp37-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a79165431551042cc9d1d90e6145d5d0d3ab0f2d66326c201d9b0e7f5bf43604"}, + {file = "cryptography-42.0.7-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a47787a5e3649008a1102d3df55424e86606c9bae6fb77ac59afe06d234605f8"}, + {file = "cryptography-42.0.7-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:02c0eee2d7133bdbbc5e24441258d5d2244beb31da5ed19fbb80315f4bbbff55"}, + {file = "cryptography-42.0.7-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:5e44507bf8d14b36b8389b226665d597bc0f18ea035d75b4e53c7b1ea84583cc"}, + {file = "cryptography-42.0.7-cp37-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:7f8b25fa616d8b846aef64b15c606bb0828dbc35faf90566eb139aa9cff67af2"}, + {file = "cryptography-42.0.7-cp37-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:93a3209f6bb2b33e725ed08ee0991b92976dfdcf4e8b38646540674fc7508e13"}, + {file = "cryptography-42.0.7-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:e6b8f1881dac458c34778d0a424ae5769de30544fc678eac51c1c8bb2183e9da"}, + {file = "cryptography-42.0.7-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:3de9a45d3b2b7d8088c3fbf1ed4395dfeff79d07842217b38df14ef09ce1d8d7"}, + {file = "cryptography-42.0.7-cp37-abi3-win32.whl", hash = "sha256:789caea816c6704f63f6241a519bfa347f72fbd67ba28d04636b7c6b7da94b0b"}, + {file = "cryptography-42.0.7-cp37-abi3-win_amd64.whl", hash = "sha256:8cb8ce7c3347fcf9446f201dc30e2d5a3c898d009126010cbd1f443f28b52678"}, + {file = "cryptography-42.0.7-cp39-abi3-macosx_10_12_universal2.whl", hash = "sha256:a3a5ac8b56fe37f3125e5b72b61dcde43283e5370827f5233893d461b7360cd4"}, + {file = "cryptography-42.0.7-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:779245e13b9a6638df14641d029add5dc17edbef6ec915688f3acb9e720a5858"}, + {file = "cryptography-42.0.7-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0d563795db98b4cd57742a78a288cdbdc9daedac29f2239793071fe114f13785"}, + {file = "cryptography-42.0.7-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:31adb7d06fe4383226c3e963471f6837742889b3c4caa55aac20ad951bc8ffda"}, + {file = "cryptography-42.0.7-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:efd0bf5205240182e0f13bcaea41be4fdf5c22c5129fc7ced4a0282ac86998c9"}, + {file = "cryptography-42.0.7-cp39-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:a9bc127cdc4ecf87a5ea22a2556cab6c7eda2923f84e4f3cc588e8470ce4e42e"}, + {file = "cryptography-42.0.7-cp39-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:3577d029bc3f4827dd5bf8bf7710cac13527b470bbf1820a3f394adb38ed7d5f"}, + {file = "cryptography-42.0.7-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:2e47577f9b18723fa294b0ea9a17d5e53a227867a0a4904a1a076d1646d45ca1"}, + {file = "cryptography-42.0.7-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:1a58839984d9cb34c855197043eaae2c187d930ca6d644612843b4fe8513c886"}, + {file = "cryptography-42.0.7-cp39-abi3-win32.whl", hash = "sha256:e6b79d0adb01aae87e8a44c2b64bc3f3fe59515280e00fb6d57a7267a2583cda"}, + {file = "cryptography-42.0.7-cp39-abi3-win_amd64.whl", hash = "sha256:16268d46086bb8ad5bf0a2b5544d8a9ed87a0e33f5e77dd3c3301e63d941a83b"}, + {file = "cryptography-42.0.7-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:2954fccea107026512b15afb4aa664a5640cd0af630e2ee3962f2602693f0c82"}, + {file = "cryptography-42.0.7-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:362e7197754c231797ec45ee081f3088a27a47c6c01eff2ac83f60f85a50fe60"}, + {file = "cryptography-42.0.7-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:4f698edacf9c9e0371112792558d2f705b5645076cc0aaae02f816a0171770fd"}, + {file = "cryptography-42.0.7-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:5482e789294854c28237bba77c4c83be698be740e31a3ae5e879ee5444166582"}, + {file = "cryptography-42.0.7-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:e9b2a6309f14c0497f348d08a065d52f3020656f675819fc405fb63bbcd26562"}, + {file = "cryptography-42.0.7-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:d8e3098721b84392ee45af2dd554c947c32cc52f862b6a3ae982dbb90f577f14"}, + {file = "cryptography-42.0.7-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:c65f96dad14f8528a447414125e1fc8feb2ad5a272b8f68477abbcc1ea7d94b9"}, + {file = "cryptography-42.0.7-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:36017400817987670037fbb0324d71489b6ead6231c9604f8fc1f7d008087c68"}, + {file = "cryptography-42.0.7.tar.gz", hash = "sha256:ecbfbc00bf55888edda9868a4cf927205de8499e7fabe6c050322298382953f2"}, ] [package.dependencies] @@ -524,20 +524,21 @@ smmap = ">=3.0.1,<6" [[package]] name = "gitpython" -version = "3.1.41" +version = "3.1.43" description = "GitPython is a Python library used to interact with Git repositories" optional = false python-versions = ">=3.7" files = [ - {file = "GitPython-3.1.41-py3-none-any.whl", hash = "sha256:c36b6634d069b3f719610175020a9aed919421c87552185b085e04fbbdb10b7c"}, - {file = "GitPython-3.1.41.tar.gz", hash = "sha256:ed66e624884f76df22c8e16066d567aaa5a37d5b5fa19db2c6df6f7156db9048"}, + {file = "GitPython-3.1.43-py3-none-any.whl", hash = "sha256:eec7ec56b92aad751f9912a73404bc02ba212a23adb2c7098ee668417051a1ff"}, + {file = "GitPython-3.1.43.tar.gz", hash = "sha256:35f314a9f878467f5453cc1fee295c3e18e52f1b99f10f6cf5b1682e968a9e7c"}, ] [package.dependencies] gitdb = ">=4.0.1,<5" [package.extras] -test = ["black", "coverage[toml]", "ddt (>=1.1.1,!=1.4.3)", "mock", "mypy", "pre-commit", "pytest (>=7.3.1)", "pytest-cov", "pytest-instafail", "pytest-mock", "pytest-sugar", "sumtypes"] +doc = ["sphinx (==4.3.2)", "sphinx-autodoc-typehints", "sphinx-rtd-theme", "sphinxcontrib-applehelp (>=1.0.2,<=1.0.4)", "sphinxcontrib-devhelp (==1.0.2)", "sphinxcontrib-htmlhelp (>=2.0.0,<=2.0.1)", "sphinxcontrib-qthelp (==1.0.3)", "sphinxcontrib-serializinghtml (==1.1.5)"] +test = ["coverage[toml]", "ddt (>=1.1.1,!=1.4.3)", "mock", "mypy", "pre-commit", "pytest (>=7.3.1)", "pytest-cov", "pytest-instafail", "pytest-mock", "pytest-sugar", "typing-extensions"] [[package]] name = "hiredis" @@ -782,13 +783,13 @@ files = [ [[package]] name = "immutabledict" -version = "4.1.0" +version = "4.2.0" description = "Immutable wrapper around dictionaries (a fork of frozendict)" optional = false python-versions = ">=3.8,<4.0" files = [ - {file = "immutabledict-4.1.0-py3-none-any.whl", hash = "sha256:c176e99aa90aedb81716ad35218bb2055d049b549626db4523dbe011cf2f32ac"}, - {file = "immutabledict-4.1.0.tar.gz", hash = "sha256:93d100ccd2cd09a1fd3f136b9328c6e59529ba341de8bb499437f6819159fe8a"}, + {file = "immutabledict-4.2.0-py3-none-any.whl", hash = "sha256:d728b2c2410d698d95e6200237feb50a695584d20289ad3379a439aa3d90baba"}, + {file = "immutabledict-4.2.0.tar.gz", hash = "sha256:e003fd81aad2377a5a758bf7e1086cf3b70b63e9a5cc2f46bce8d0a2b4727c5f"}, ] [[package]] @@ -911,13 +912,13 @@ trio = ["async_generator", "trio"] [[package]] name = "jinja2" -version = "3.1.3" +version = "3.1.4" description = "A very fast and expressive template engine." optional = false python-versions = ">=3.7" files = [ - {file = "Jinja2-3.1.3-py3-none-any.whl", hash = "sha256:7d6d50dd97d52cbc355597bd845fabfbac3f551e1f99619e39a35ce8c370b5fa"}, - {file = "Jinja2-3.1.3.tar.gz", hash = "sha256:ac8bd6544d4bb2c9792bf3a159e80bba8fda7f07e81bc3aed565432d5925ba90"}, + {file = "jinja2-3.1.4-py3-none-any.whl", hash = "sha256:bc5dd2abb727a5319567b7a813e6a2e7318c39f4f487cfe6c89c6f9c7d25197d"}, + {file = "jinja2-3.1.4.tar.gz", hash = "sha256:4a3aee7acbbe7303aede8e9648d13b8bf88a429282aa6122a993f0ac800cb369"}, ] [package.dependencies] @@ -1004,165 +1005,153 @@ pyasn1 = ">=0.4.6" [[package]] name = "lxml" -version = "5.2.1" +version = "5.2.2" description = "Powerful and Pythonic XML processing library combining libxml2/libxslt with the ElementTree API." optional = true python-versions = ">=3.6" files = [ - {file = "lxml-5.2.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:1f7785f4f789fdb522729ae465adcaa099e2a3441519df750ebdccc481d961a1"}, - {file = "lxml-5.2.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:6cc6ee342fb7fa2471bd9b6d6fdfc78925a697bf5c2bcd0a302e98b0d35bfad3"}, - {file = "lxml-5.2.1-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:794f04eec78f1d0e35d9e0c36cbbb22e42d370dda1609fb03bcd7aeb458c6377"}, - {file = "lxml-5.2.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c817d420c60a5183953c783b0547d9eb43b7b344a2c46f69513d5952a78cddf3"}, - {file = "lxml-5.2.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2213afee476546a7f37c7a9b4ad4d74b1e112a6fafffc9185d6d21f043128c81"}, - {file = "lxml-5.2.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b070bbe8d3f0f6147689bed981d19bbb33070225373338df755a46893528104a"}, - {file = "lxml-5.2.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e02c5175f63effbd7c5e590399c118d5db6183bbfe8e0d118bdb5c2d1b48d937"}, - {file = "lxml-5.2.1-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:3dc773b2861b37b41a6136e0b72a1a44689a9c4c101e0cddb6b854016acc0aa8"}, - {file = "lxml-5.2.1-cp310-cp310-manylinux_2_28_ppc64le.whl", hash = "sha256:d7520db34088c96cc0e0a3ad51a4fd5b401f279ee112aa2b7f8f976d8582606d"}, - {file = "lxml-5.2.1-cp310-cp310-manylinux_2_28_s390x.whl", hash = "sha256:bcbf4af004f98793a95355980764b3d80d47117678118a44a80b721c9913436a"}, - {file = "lxml-5.2.1-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:a2b44bec7adf3e9305ce6cbfa47a4395667e744097faed97abb4728748ba7d47"}, - {file = "lxml-5.2.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:1c5bb205e9212d0ebddf946bc07e73fa245c864a5f90f341d11ce7b0b854475d"}, - {file = "lxml-5.2.1-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:2c9d147f754b1b0e723e6afb7ba1566ecb162fe4ea657f53d2139bbf894d050a"}, - {file = "lxml-5.2.1-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:3545039fa4779be2df51d6395e91a810f57122290864918b172d5dc7ca5bb433"}, - {file = "lxml-5.2.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a91481dbcddf1736c98a80b122afa0f7296eeb80b72344d7f45dc9f781551f56"}, - {file = "lxml-5.2.1-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:2ddfe41ddc81f29a4c44c8ce239eda5ade4e7fc305fb7311759dd6229a080052"}, - {file = "lxml-5.2.1-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:a7baf9ffc238e4bf401299f50e971a45bfcc10a785522541a6e3179c83eabf0a"}, - {file = "lxml-5.2.1-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:31e9a882013c2f6bd2f2c974241bf4ba68c85eba943648ce88936d23209a2e01"}, - {file = "lxml-5.2.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:0a15438253b34e6362b2dc41475e7f80de76320f335e70c5528b7148cac253a1"}, - {file = "lxml-5.2.1-cp310-cp310-win32.whl", hash = "sha256:6992030d43b916407c9aa52e9673612ff39a575523c5f4cf72cdef75365709a5"}, - {file = "lxml-5.2.1-cp310-cp310-win_amd64.whl", hash = "sha256:da052e7962ea2d5e5ef5bc0355d55007407087392cf465b7ad84ce5f3e25fe0f"}, - {file = "lxml-5.2.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:70ac664a48aa64e5e635ae5566f5227f2ab7f66a3990d67566d9907edcbbf867"}, - {file = "lxml-5.2.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:1ae67b4e737cddc96c99461d2f75d218bdf7a0c3d3ad5604d1f5e7464a2f9ffe"}, - {file = "lxml-5.2.1-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f18a5a84e16886898e51ab4b1d43acb3083c39b14c8caeb3589aabff0ee0b270"}, - {file = "lxml-5.2.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c6f2c8372b98208ce609c9e1d707f6918cc118fea4e2c754c9f0812c04ca116d"}, - {file = "lxml-5.2.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:394ed3924d7a01b5bd9a0d9d946136e1c2f7b3dc337196d99e61740ed4bc6fe1"}, - {file = "lxml-5.2.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5d077bc40a1fe984e1a9931e801e42959a1e6598edc8a3223b061d30fbd26bbc"}, - {file = "lxml-5.2.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:764b521b75701f60683500d8621841bec41a65eb739b8466000c6fdbc256c240"}, - {file = "lxml-5.2.1-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:3a6b45da02336895da82b9d472cd274b22dc27a5cea1d4b793874eead23dd14f"}, - {file = "lxml-5.2.1-cp311-cp311-manylinux_2_28_ppc64le.whl", hash = "sha256:5ea7b6766ac2dfe4bcac8b8595107665a18ef01f8c8343f00710b85096d1b53a"}, - {file = "lxml-5.2.1-cp311-cp311-manylinux_2_28_s390x.whl", hash = "sha256:e196a4ff48310ba62e53a8e0f97ca2bca83cdd2fe2934d8b5cb0df0a841b193a"}, - {file = "lxml-5.2.1-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:200e63525948e325d6a13a76ba2911f927ad399ef64f57898cf7c74e69b71095"}, - {file = "lxml-5.2.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:dae0ed02f6b075426accbf6b2863c3d0a7eacc1b41fb40f2251d931e50188dad"}, - {file = "lxml-5.2.1-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:ab31a88a651039a07a3ae327d68ebdd8bc589b16938c09ef3f32a4b809dc96ef"}, - {file = "lxml-5.2.1-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:df2e6f546c4df14bc81f9498bbc007fbb87669f1bb707c6138878c46b06f6510"}, - {file = "lxml-5.2.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:5dd1537e7cc06efd81371f5d1a992bd5ab156b2b4f88834ca852de4a8ea523fa"}, - {file = "lxml-5.2.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:9b9ec9c9978b708d488bec36b9e4c94d88fd12ccac3e62134a9d17ddba910ea9"}, - {file = "lxml-5.2.1-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:8e77c69d5892cb5ba71703c4057091e31ccf534bd7f129307a4d084d90d014b8"}, - {file = "lxml-5.2.1-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:a8d5c70e04aac1eda5c829a26d1f75c6e5286c74743133d9f742cda8e53b9c2f"}, - {file = "lxml-5.2.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:c94e75445b00319c1fad60f3c98b09cd63fe1134a8a953dcd48989ef42318534"}, - {file = "lxml-5.2.1-cp311-cp311-win32.whl", hash = "sha256:4951e4f7a5680a2db62f7f4ab2f84617674d36d2d76a729b9a8be4b59b3659be"}, - {file = "lxml-5.2.1-cp311-cp311-win_amd64.whl", hash = "sha256:5c670c0406bdc845b474b680b9a5456c561c65cf366f8db5a60154088c92d102"}, - {file = "lxml-5.2.1-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:abc25c3cab9ec7fcd299b9bcb3b8d4a1231877e425c650fa1c7576c5107ab851"}, - {file = "lxml-5.2.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:6935bbf153f9a965f1e07c2649c0849d29832487c52bb4a5c5066031d8b44fd5"}, - {file = "lxml-5.2.1-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d793bebb202a6000390a5390078e945bbb49855c29c7e4d56a85901326c3b5d9"}, - {file = "lxml-5.2.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:afd5562927cdef7c4f5550374acbc117fd4ecc05b5007bdfa57cc5355864e0a4"}, - {file = "lxml-5.2.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0e7259016bc4345a31af861fdce942b77c99049d6c2107ca07dc2bba2435c1d9"}, - {file = "lxml-5.2.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:530e7c04f72002d2f334d5257c8a51bf409db0316feee7c87e4385043be136af"}, - {file = "lxml-5.2.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:59689a75ba8d7ffca577aefd017d08d659d86ad4585ccc73e43edbfc7476781a"}, - {file = "lxml-5.2.1-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:f9737bf36262046213a28e789cc82d82c6ef19c85a0cf05e75c670a33342ac2c"}, - {file = "lxml-5.2.1-cp312-cp312-manylinux_2_28_ppc64le.whl", hash = "sha256:3a74c4f27167cb95c1d4af1c0b59e88b7f3e0182138db2501c353555f7ec57f4"}, - {file = "lxml-5.2.1-cp312-cp312-manylinux_2_28_s390x.whl", hash = "sha256:68a2610dbe138fa8c5826b3f6d98a7cfc29707b850ddcc3e21910a6fe51f6ca0"}, - {file = "lxml-5.2.1-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:f0a1bc63a465b6d72569a9bba9f2ef0334c4e03958e043da1920299100bc7c08"}, - {file = "lxml-5.2.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:c2d35a1d047efd68027817b32ab1586c1169e60ca02c65d428ae815b593e65d4"}, - {file = "lxml-5.2.1-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:79bd05260359170f78b181b59ce871673ed01ba048deef4bf49a36ab3e72e80b"}, - {file = "lxml-5.2.1-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:865bad62df277c04beed9478fe665b9ef63eb28fe026d5dedcb89b537d2e2ea6"}, - {file = "lxml-5.2.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:44f6c7caff88d988db017b9b0e4ab04934f11e3e72d478031efc7edcac6c622f"}, - {file = "lxml-5.2.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:71e97313406ccf55d32cc98a533ee05c61e15d11b99215b237346171c179c0b0"}, - {file = "lxml-5.2.1-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:057cdc6b86ab732cf361f8b4d8af87cf195a1f6dc5b0ff3de2dced242c2015e0"}, - {file = "lxml-5.2.1-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:f3bbbc998d42f8e561f347e798b85513ba4da324c2b3f9b7969e9c45b10f6169"}, - {file = "lxml-5.2.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:491755202eb21a5e350dae00c6d9a17247769c64dcf62d8c788b5c135e179dc4"}, - {file = "lxml-5.2.1-cp312-cp312-win32.whl", hash = "sha256:8de8f9d6caa7f25b204fc861718815d41cbcf27ee8f028c89c882a0cf4ae4134"}, - {file = "lxml-5.2.1-cp312-cp312-win_amd64.whl", hash = "sha256:f2a9efc53d5b714b8df2b4b3e992accf8ce5bbdfe544d74d5c6766c9e1146a3a"}, - {file = "lxml-5.2.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:70a9768e1b9d79edca17890175ba915654ee1725975d69ab64813dd785a2bd5c"}, - {file = "lxml-5.2.1-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c38d7b9a690b090de999835f0443d8aa93ce5f2064035dfc48f27f02b4afc3d0"}, - {file = "lxml-5.2.1-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5670fb70a828663cc37552a2a85bf2ac38475572b0e9b91283dc09efb52c41d1"}, - {file = "lxml-5.2.1-cp36-cp36m-manylinux_2_28_x86_64.whl", hash = "sha256:958244ad566c3ffc385f47dddde4145088a0ab893504b54b52c041987a8c1863"}, - {file = "lxml-5.2.1-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:b6241d4eee5f89453307c2f2bfa03b50362052ca0af1efecf9fef9a41a22bb4f"}, - {file = "lxml-5.2.1-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:2a66bf12fbd4666dd023b6f51223aed3d9f3b40fef06ce404cb75bafd3d89536"}, - {file = "lxml-5.2.1-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:9123716666e25b7b71c4e1789ec829ed18663152008b58544d95b008ed9e21e9"}, - {file = "lxml-5.2.1-cp36-cp36m-musllinux_1_1_s390x.whl", hash = "sha256:0c3f67e2aeda739d1cc0b1102c9a9129f7dc83901226cc24dd72ba275ced4218"}, - {file = "lxml-5.2.1-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:5d5792e9b3fb8d16a19f46aa8208987cfeafe082363ee2745ea8b643d9cc5b45"}, - {file = "lxml-5.2.1-cp36-cp36m-musllinux_1_2_aarch64.whl", hash = "sha256:88e22fc0a6684337d25c994381ed8a1580a6f5ebebd5ad41f89f663ff4ec2885"}, - {file = "lxml-5.2.1-cp36-cp36m-musllinux_1_2_ppc64le.whl", hash = "sha256:21c2e6b09565ba5b45ae161b438e033a86ad1736b8c838c766146eff8ceffff9"}, - {file = "lxml-5.2.1-cp36-cp36m-musllinux_1_2_s390x.whl", hash = "sha256:afbbdb120d1e78d2ba8064a68058001b871154cc57787031b645c9142b937a62"}, - {file = "lxml-5.2.1-cp36-cp36m-musllinux_1_2_x86_64.whl", hash = "sha256:627402ad8dea044dde2eccde4370560a2b750ef894c9578e1d4f8ffd54000461"}, - {file = "lxml-5.2.1-cp36-cp36m-win32.whl", hash = "sha256:e89580a581bf478d8dcb97d9cd011d567768e8bc4095f8557b21c4d4c5fea7d0"}, - {file = "lxml-5.2.1-cp36-cp36m-win_amd64.whl", hash = "sha256:59565f10607c244bc4c05c0c5fa0c190c990996e0c719d05deec7030c2aa8289"}, - {file = "lxml-5.2.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:857500f88b17a6479202ff5fe5f580fc3404922cd02ab3716197adf1ef628029"}, - {file = "lxml-5.2.1-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:56c22432809085b3f3ae04e6e7bdd36883d7258fcd90e53ba7b2e463efc7a6af"}, - {file = "lxml-5.2.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a55ee573116ba208932e2d1a037cc4b10d2c1cb264ced2184d00b18ce585b2c0"}, - {file = "lxml-5.2.1-cp37-cp37m-manylinux_2_28_x86_64.whl", hash = "sha256:6cf58416653c5901e12624e4013708b6e11142956e7f35e7a83f1ab02f3fe456"}, - {file = "lxml-5.2.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:64c2baa7774bc22dd4474248ba16fe1a7f611c13ac6123408694d4cc93d66dbd"}, - {file = "lxml-5.2.1-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:74b28c6334cca4dd704e8004cba1955af0b778cf449142e581e404bd211fb619"}, - {file = "lxml-5.2.1-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:7221d49259aa1e5a8f00d3d28b1e0b76031655ca74bb287123ef56c3db92f213"}, - {file = "lxml-5.2.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:3dbe858ee582cbb2c6294dc85f55b5f19c918c2597855e950f34b660f1a5ede6"}, - {file = "lxml-5.2.1-cp37-cp37m-musllinux_1_2_aarch64.whl", hash = "sha256:04ab5415bf6c86e0518d57240a96c4d1fcfc3cb370bb2ac2a732b67f579e5a04"}, - {file = "lxml-5.2.1-cp37-cp37m-musllinux_1_2_ppc64le.whl", hash = "sha256:6ab833e4735a7e5533711a6ea2df26459b96f9eec36d23f74cafe03631647c41"}, - {file = "lxml-5.2.1-cp37-cp37m-musllinux_1_2_s390x.whl", hash = "sha256:f443cdef978430887ed55112b491f670bba6462cea7a7742ff8f14b7abb98d75"}, - {file = "lxml-5.2.1-cp37-cp37m-musllinux_1_2_x86_64.whl", hash = "sha256:9e2addd2d1866fe112bc6f80117bcc6bc25191c5ed1bfbcf9f1386a884252ae8"}, - {file = "lxml-5.2.1-cp37-cp37m-win32.whl", hash = "sha256:f51969bac61441fd31f028d7b3b45962f3ecebf691a510495e5d2cd8c8092dbd"}, - {file = "lxml-5.2.1-cp37-cp37m-win_amd64.whl", hash = "sha256:b0b58fbfa1bf7367dde8a557994e3b1637294be6cf2169810375caf8571a085c"}, - {file = "lxml-5.2.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:804f74efe22b6a227306dd890eecc4f8c59ff25ca35f1f14e7482bbce96ef10b"}, - {file = "lxml-5.2.1-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:08802f0c56ed150cc6885ae0788a321b73505d2263ee56dad84d200cab11c07a"}, - {file = "lxml-5.2.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0f8c09ed18ecb4ebf23e02b8e7a22a05d6411911e6fabef3a36e4f371f4f2585"}, - {file = "lxml-5.2.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e3d30321949861404323c50aebeb1943461a67cd51d4200ab02babc58bd06a86"}, - {file = "lxml-5.2.1-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:b560e3aa4b1d49e0e6c847d72665384db35b2f5d45f8e6a5c0072e0283430533"}, - {file = "lxml-5.2.1-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:058a1308914f20784c9f4674036527e7c04f7be6fb60f5d61353545aa7fcb739"}, - {file = "lxml-5.2.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:adfb84ca6b87e06bc6b146dc7da7623395db1e31621c4785ad0658c5028b37d7"}, - {file = "lxml-5.2.1-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:417d14450f06d51f363e41cace6488519038f940676ce9664b34ebf5653433a5"}, - {file = "lxml-5.2.1-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:a2dfe7e2473f9b59496247aad6e23b405ddf2e12ef0765677b0081c02d6c2c0b"}, - {file = "lxml-5.2.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:bf2e2458345d9bffb0d9ec16557d8858c9c88d2d11fed53998512504cd9df49b"}, - {file = "lxml-5.2.1-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:58278b29cb89f3e43ff3e0c756abbd1518f3ee6adad9e35b51fb101c1c1daaec"}, - {file = "lxml-5.2.1-cp38-cp38-musllinux_1_2_ppc64le.whl", hash = "sha256:64641a6068a16201366476731301441ce93457eb8452056f570133a6ceb15fca"}, - {file = "lxml-5.2.1-cp38-cp38-musllinux_1_2_s390x.whl", hash = "sha256:78bfa756eab503673991bdcf464917ef7845a964903d3302c5f68417ecdc948c"}, - {file = "lxml-5.2.1-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:11a04306fcba10cd9637e669fd73aa274c1c09ca64af79c041aa820ea992b637"}, - {file = "lxml-5.2.1-cp38-cp38-win32.whl", hash = "sha256:66bc5eb8a323ed9894f8fa0ee6cb3e3fb2403d99aee635078fd19a8bc7a5a5da"}, - {file = "lxml-5.2.1-cp38-cp38-win_amd64.whl", hash = "sha256:9676bfc686fa6a3fa10cd4ae6b76cae8be26eb5ec6811d2a325636c460da1806"}, - {file = "lxml-5.2.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:cf22b41fdae514ee2f1691b6c3cdeae666d8b7fa9434de445f12bbeee0cf48dd"}, - {file = "lxml-5.2.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:ec42088248c596dbd61d4ae8a5b004f97a4d91a9fd286f632e42e60b706718d7"}, - {file = "lxml-5.2.1-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cd53553ddad4a9c2f1f022756ae64abe16da1feb497edf4d9f87f99ec7cf86bd"}, - {file = "lxml-5.2.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:feaa45c0eae424d3e90d78823f3828e7dc42a42f21ed420db98da2c4ecf0a2cb"}, - {file = "lxml-5.2.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ddc678fb4c7e30cf830a2b5a8d869538bc55b28d6c68544d09c7d0d8f17694dc"}, - {file = "lxml-5.2.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:853e074d4931dbcba7480d4dcab23d5c56bd9607f92825ab80ee2bd916edea53"}, - {file = "lxml-5.2.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cc4691d60512798304acb9207987e7b2b7c44627ea88b9d77489bbe3e6cc3bd4"}, - {file = "lxml-5.2.1-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:beb72935a941965c52990f3a32d7f07ce869fe21c6af8b34bf6a277b33a345d3"}, - {file = "lxml-5.2.1-cp39-cp39-manylinux_2_28_ppc64le.whl", hash = "sha256:6588c459c5627fefa30139be4d2e28a2c2a1d0d1c265aad2ba1935a7863a4913"}, - {file = "lxml-5.2.1-cp39-cp39-manylinux_2_28_s390x.whl", hash = "sha256:588008b8497667f1ddca7c99f2f85ce8511f8f7871b4a06ceede68ab62dff64b"}, - {file = "lxml-5.2.1-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:b6787b643356111dfd4032b5bffe26d2f8331556ecb79e15dacb9275da02866e"}, - {file = "lxml-5.2.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:7c17b64b0a6ef4e5affae6a3724010a7a66bda48a62cfe0674dabd46642e8b54"}, - {file = "lxml-5.2.1-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:27aa20d45c2e0b8cd05da6d4759649170e8dfc4f4e5ef33a34d06f2d79075d57"}, - {file = "lxml-5.2.1-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:d4f2cc7060dc3646632d7f15fe68e2fa98f58e35dd5666cd525f3b35d3fed7f8"}, - {file = "lxml-5.2.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:ff46d772d5f6f73564979cd77a4fffe55c916a05f3cb70e7c9c0590059fb29ef"}, - {file = "lxml-5.2.1-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:96323338e6c14e958d775700ec8a88346014a85e5de73ac7967db0367582049b"}, - {file = "lxml-5.2.1-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:52421b41ac99e9d91934e4d0d0fe7da9f02bfa7536bb4431b4c05c906c8c6919"}, - {file = "lxml-5.2.1-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:7a7efd5b6d3e30d81ec68ab8a88252d7c7c6f13aaa875009fe3097eb4e30b84c"}, - {file = "lxml-5.2.1-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:0ed777c1e8c99b63037b91f9d73a6aad20fd035d77ac84afcc205225f8f41188"}, - {file = "lxml-5.2.1-cp39-cp39-win32.whl", hash = "sha256:644df54d729ef810dcd0f7732e50e5ad1bd0a135278ed8d6bcb06f33b6b6f708"}, - {file = "lxml-5.2.1-cp39-cp39-win_amd64.whl", hash = "sha256:9ca66b8e90daca431b7ca1408cae085d025326570e57749695d6a01454790e95"}, - {file = "lxml-5.2.1-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:9b0ff53900566bc6325ecde9181d89afadc59c5ffa39bddf084aaedfe3b06a11"}, - {file = "lxml-5.2.1-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fd6037392f2d57793ab98d9e26798f44b8b4da2f2464388588f48ac52c489ea1"}, - {file = "lxml-5.2.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8b9c07e7a45bb64e21df4b6aa623cb8ba214dfb47d2027d90eac197329bb5e94"}, - {file = "lxml-5.2.1-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:3249cc2989d9090eeac5467e50e9ec2d40704fea9ab72f36b034ea34ee65ca98"}, - {file = "lxml-5.2.1-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:f42038016852ae51b4088b2862126535cc4fc85802bfe30dea3500fdfaf1864e"}, - {file = "lxml-5.2.1-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:533658f8fbf056b70e434dff7e7aa611bcacb33e01f75de7f821810e48d1bb66"}, - {file = "lxml-5.2.1-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:622020d4521e22fb371e15f580d153134bfb68d6a429d1342a25f051ec72df1c"}, - {file = "lxml-5.2.1-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:efa7b51824aa0ee957ccd5a741c73e6851de55f40d807f08069eb4c5a26b2baa"}, - {file = "lxml-5.2.1-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9c6ad0fbf105f6bcc9300c00010a2ffa44ea6f555df1a2ad95c88f5656104817"}, - {file = "lxml-5.2.1-pp37-pypy37_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:e233db59c8f76630c512ab4a4daf5a5986da5c3d5b44b8e9fc742f2a24dbd460"}, - {file = "lxml-5.2.1-pp37-pypy37_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:6a014510830df1475176466b6087fc0c08b47a36714823e58d8b8d7709132a96"}, - {file = "lxml-5.2.1-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:d38c8f50ecf57f0463399569aa388b232cf1a2ffb8f0a9a5412d0db57e054860"}, - {file = "lxml-5.2.1-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:5aea8212fb823e006b995c4dda533edcf98a893d941f173f6c9506126188860d"}, - {file = "lxml-5.2.1-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ff097ae562e637409b429a7ac958a20aab237a0378c42dabaa1e3abf2f896e5f"}, - {file = "lxml-5.2.1-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0f5d65c39f16717a47c36c756af0fb36144069c4718824b7533f803ecdf91138"}, - {file = "lxml-5.2.1-pp38-pypy38_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:3d0c3dd24bb4605439bf91068598d00c6370684f8de4a67c2992683f6c309d6b"}, - {file = "lxml-5.2.1-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:e32be23d538753a8adb6c85bd539f5fd3b15cb987404327c569dfc5fd8366e85"}, - {file = "lxml-5.2.1-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:cc518cea79fd1e2f6c90baafa28906d4309d24f3a63e801d855e7424c5b34144"}, - {file = "lxml-5.2.1-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:a0af35bd8ebf84888373630f73f24e86bf016642fb8576fba49d3d6b560b7cbc"}, - {file = "lxml-5.2.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f8aca2e3a72f37bfc7b14ba96d4056244001ddcc18382bd0daa087fd2e68a354"}, - {file = "lxml-5.2.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5ca1e8188b26a819387b29c3895c47a5e618708fe6f787f3b1a471de2c4a94d9"}, - {file = "lxml-5.2.1-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:c8ba129e6d3b0136a0f50345b2cb3db53f6bda5dd8c7f5d83fbccba97fb5dcb5"}, - {file = "lxml-5.2.1-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:e998e304036198b4f6914e6a1e2b6f925208a20e2042563d9734881150c6c246"}, - {file = "lxml-5.2.1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:d3be9b2076112e51b323bdf6d5a7f8a798de55fb8d95fcb64bd179460cdc0704"}, - {file = "lxml-5.2.1.tar.gz", hash = "sha256:3f7765e69bbce0906a7c74d5fe46d2c7a7596147318dbc08e4a2431f3060e306"}, + {file = "lxml-5.2.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:364d03207f3e603922d0d3932ef363d55bbf48e3647395765f9bfcbdf6d23632"}, + {file = "lxml-5.2.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:50127c186f191b8917ea2fb8b206fbebe87fd414a6084d15568c27d0a21d60db"}, + {file = "lxml-5.2.2-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:74e4f025ef3db1c6da4460dd27c118d8cd136d0391da4e387a15e48e5c975147"}, + {file = "lxml-5.2.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:981a06a3076997adf7c743dcd0d7a0415582661e2517c7d961493572e909aa1d"}, + {file = "lxml-5.2.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:aef5474d913d3b05e613906ba4090433c515e13ea49c837aca18bde190853dff"}, + {file = "lxml-5.2.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1e275ea572389e41e8b039ac076a46cb87ee6b8542df3fff26f5baab43713bca"}, + {file = "lxml-5.2.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f5b65529bb2f21ac7861a0e94fdbf5dc0daab41497d18223b46ee8515e5ad297"}, + {file = "lxml-5.2.2-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:bcc98f911f10278d1daf14b87d65325851a1d29153caaf146877ec37031d5f36"}, + {file = "lxml-5.2.2-cp310-cp310-manylinux_2_28_ppc64le.whl", hash = "sha256:b47633251727c8fe279f34025844b3b3a3e40cd1b198356d003aa146258d13a2"}, + {file = "lxml-5.2.2-cp310-cp310-manylinux_2_28_s390x.whl", hash = "sha256:fbc9d316552f9ef7bba39f4edfad4a734d3d6f93341232a9dddadec4f15d425f"}, + {file = "lxml-5.2.2-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:13e69be35391ce72712184f69000cda04fc89689429179bc4c0ae5f0b7a8c21b"}, + {file = "lxml-5.2.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:3b6a30a9ab040b3f545b697cb3adbf3696c05a3a68aad172e3fd7ca73ab3c835"}, + {file = "lxml-5.2.2-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:a233bb68625a85126ac9f1fc66d24337d6e8a0f9207b688eec2e7c880f012ec0"}, + {file = "lxml-5.2.2-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:dfa7c241073d8f2b8e8dbc7803c434f57dbb83ae2a3d7892dd068d99e96efe2c"}, + {file = "lxml-5.2.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:1a7aca7964ac4bb07680d5c9d63b9d7028cace3e2d43175cb50bba8c5ad33316"}, + {file = "lxml-5.2.2-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:ae4073a60ab98529ab8a72ebf429f2a8cc612619a8c04e08bed27450d52103c0"}, + {file = "lxml-5.2.2-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:ffb2be176fed4457e445fe540617f0252a72a8bc56208fd65a690fdb1f57660b"}, + {file = "lxml-5.2.2-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:e290d79a4107d7d794634ce3e985b9ae4f920380a813717adf61804904dc4393"}, + {file = "lxml-5.2.2-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:96e85aa09274955bb6bd483eaf5b12abadade01010478154b0ec70284c1b1526"}, + {file = "lxml-5.2.2-cp310-cp310-win32.whl", hash = "sha256:f956196ef61369f1685d14dad80611488d8dc1ef00be57c0c5a03064005b0f30"}, + {file = "lxml-5.2.2-cp310-cp310-win_amd64.whl", hash = "sha256:875a3f90d7eb5c5d77e529080d95140eacb3c6d13ad5b616ee8095447b1d22e7"}, + {file = "lxml-5.2.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:45f9494613160d0405682f9eee781c7e6d1bf45f819654eb249f8f46a2c22545"}, + {file = "lxml-5.2.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b0b3f2df149efb242cee2ffdeb6674b7f30d23c9a7af26595099afaf46ef4e88"}, + {file = "lxml-5.2.2-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d28cb356f119a437cc58a13f8135ab8a4c8ece18159eb9194b0d269ec4e28083"}, + {file = "lxml-5.2.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:657a972f46bbefdbba2d4f14413c0d079f9ae243bd68193cb5061b9732fa54c1"}, + {file = "lxml-5.2.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b74b9ea10063efb77a965a8d5f4182806fbf59ed068b3c3fd6f30d2ac7bee734"}, + {file = "lxml-5.2.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:07542787f86112d46d07d4f3c4e7c760282011b354d012dc4141cc12a68cef5f"}, + {file = "lxml-5.2.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:303f540ad2dddd35b92415b74b900c749ec2010e703ab3bfd6660979d01fd4ed"}, + {file = "lxml-5.2.2-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:2eb2227ce1ff998faf0cd7fe85bbf086aa41dfc5af3b1d80867ecfe75fb68df3"}, + {file = "lxml-5.2.2-cp311-cp311-manylinux_2_28_ppc64le.whl", hash = "sha256:1d8a701774dfc42a2f0b8ccdfe7dbc140500d1049e0632a611985d943fcf12df"}, + {file = "lxml-5.2.2-cp311-cp311-manylinux_2_28_s390x.whl", hash = "sha256:56793b7a1a091a7c286b5f4aa1fe4ae5d1446fe742d00cdf2ffb1077865db10d"}, + {file = "lxml-5.2.2-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:eb00b549b13bd6d884c863554566095bf6fa9c3cecb2e7b399c4bc7904cb33b5"}, + {file = "lxml-5.2.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:1a2569a1f15ae6c8c64108a2cd2b4a858fc1e13d25846be0666fc144715e32ab"}, + {file = "lxml-5.2.2-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:8cf85a6e40ff1f37fe0f25719aadf443686b1ac7652593dc53c7ef9b8492b115"}, + {file = "lxml-5.2.2-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:d237ba6664b8e60fd90b8549a149a74fcc675272e0e95539a00522e4ca688b04"}, + {file = "lxml-5.2.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:0b3f5016e00ae7630a4b83d0868fca1e3d494c78a75b1c7252606a3a1c5fc2ad"}, + {file = "lxml-5.2.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:23441e2b5339bc54dc949e9e675fa35efe858108404ef9aa92f0456929ef6fe8"}, + {file = "lxml-5.2.2-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:2fb0ba3e8566548d6c8e7dd82a8229ff47bd8fb8c2da237607ac8e5a1b8312e5"}, + {file = "lxml-5.2.2-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:79d1fb9252e7e2cfe4de6e9a6610c7cbb99b9708e2c3e29057f487de5a9eaefa"}, + {file = "lxml-5.2.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:6dcc3d17eac1df7859ae01202e9bb11ffa8c98949dcbeb1069c8b9a75917e01b"}, + {file = "lxml-5.2.2-cp311-cp311-win32.whl", hash = "sha256:4c30a2f83677876465f44c018830f608fa3c6a8a466eb223535035fbc16f3438"}, + {file = "lxml-5.2.2-cp311-cp311-win_amd64.whl", hash = "sha256:49095a38eb333aaf44c06052fd2ec3b8f23e19747ca7ec6f6c954ffea6dbf7be"}, + {file = "lxml-5.2.2-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:7429e7faa1a60cad26ae4227f4dd0459efde239e494c7312624ce228e04f6391"}, + {file = "lxml-5.2.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:50ccb5d355961c0f12f6cf24b7187dbabd5433f29e15147a67995474f27d1776"}, + {file = "lxml-5.2.2-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:dc911208b18842a3a57266d8e51fc3cfaccee90a5351b92079beed912a7914c2"}, + {file = "lxml-5.2.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:33ce9e786753743159799fdf8e92a5da351158c4bfb6f2db0bf31e7892a1feb5"}, + {file = "lxml-5.2.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ec87c44f619380878bd49ca109669c9f221d9ae6883a5bcb3616785fa8f94c97"}, + {file = "lxml-5.2.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:08ea0f606808354eb8f2dfaac095963cb25d9d28e27edcc375d7b30ab01abbf6"}, + {file = "lxml-5.2.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75a9632f1d4f698b2e6e2e1ada40e71f369b15d69baddb8968dcc8e683839b18"}, + {file = "lxml-5.2.2-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:74da9f97daec6928567b48c90ea2c82a106b2d500f397eeb8941e47d30b1ca85"}, + {file = "lxml-5.2.2-cp312-cp312-manylinux_2_28_ppc64le.whl", hash = "sha256:0969e92af09c5687d769731e3f39ed62427cc72176cebb54b7a9d52cc4fa3b73"}, + {file = "lxml-5.2.2-cp312-cp312-manylinux_2_28_s390x.whl", hash = "sha256:9164361769b6ca7769079f4d426a41df6164879f7f3568be9086e15baca61466"}, + {file = "lxml-5.2.2-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:d26a618ae1766279f2660aca0081b2220aca6bd1aa06b2cf73f07383faf48927"}, + {file = "lxml-5.2.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:ab67ed772c584b7ef2379797bf14b82df9aa5f7438c5b9a09624dd834c1c1aaf"}, + {file = "lxml-5.2.2-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:3d1e35572a56941b32c239774d7e9ad724074d37f90c7a7d499ab98761bd80cf"}, + {file = "lxml-5.2.2-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:8268cbcd48c5375f46e000adb1390572c98879eb4f77910c6053d25cc3ac2c67"}, + {file = "lxml-5.2.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:e282aedd63c639c07c3857097fc0e236f984ceb4089a8b284da1c526491e3f3d"}, + {file = "lxml-5.2.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6dfdc2bfe69e9adf0df4915949c22a25b39d175d599bf98e7ddf620a13678585"}, + {file = "lxml-5.2.2-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:4aefd911793b5d2d7a921233a54c90329bf3d4a6817dc465f12ffdfe4fc7b8fe"}, + {file = "lxml-5.2.2-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:8b8df03a9e995b6211dafa63b32f9d405881518ff1ddd775db4e7b98fb545e1c"}, + {file = "lxml-5.2.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:f11ae142f3a322d44513de1018b50f474f8f736bc3cd91d969f464b5bfef8836"}, + {file = "lxml-5.2.2-cp312-cp312-win32.whl", hash = "sha256:16a8326e51fcdffc886294c1e70b11ddccec836516a343f9ed0f82aac043c24a"}, + {file = "lxml-5.2.2-cp312-cp312-win_amd64.whl", hash = "sha256:bbc4b80af581e18568ff07f6395c02114d05f4865c2812a1f02f2eaecf0bfd48"}, + {file = "lxml-5.2.2-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:e3d9d13603410b72787579769469af730c38f2f25505573a5888a94b62b920f8"}, + {file = "lxml-5.2.2-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:38b67afb0a06b8575948641c1d6d68e41b83a3abeae2ca9eed2ac59892b36706"}, + {file = "lxml-5.2.2-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c689d0d5381f56de7bd6966a4541bff6e08bf8d3871bbd89a0c6ab18aa699573"}, + {file = "lxml-5.2.2-cp36-cp36m-manylinux_2_28_x86_64.whl", hash = "sha256:cf2a978c795b54c539f47964ec05e35c05bd045db5ca1e8366988c7f2fe6b3ce"}, + {file = "lxml-5.2.2-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:739e36ef7412b2bd940f75b278749106e6d025e40027c0b94a17ef7968d55d56"}, + {file = "lxml-5.2.2-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:d8bbcd21769594dbba9c37d3c819e2d5847656ca99c747ddb31ac1701d0c0ed9"}, + {file = "lxml-5.2.2-cp36-cp36m-musllinux_1_2_x86_64.whl", hash = "sha256:2304d3c93f2258ccf2cf7a6ba8c761d76ef84948d87bf9664e14d203da2cd264"}, + {file = "lxml-5.2.2-cp36-cp36m-win32.whl", hash = "sha256:02437fb7308386867c8b7b0e5bc4cd4b04548b1c5d089ffb8e7b31009b961dc3"}, + {file = "lxml-5.2.2-cp36-cp36m-win_amd64.whl", hash = "sha256:edcfa83e03370032a489430215c1e7783128808fd3e2e0a3225deee278585196"}, + {file = "lxml-5.2.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:28bf95177400066596cdbcfc933312493799382879da504633d16cf60bba735b"}, + {file = "lxml-5.2.2-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3a745cc98d504d5bd2c19b10c79c61c7c3df9222629f1b6210c0368177589fb8"}, + {file = "lxml-5.2.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1b590b39ef90c6b22ec0be925b211298e810b4856909c8ca60d27ffbca6c12e6"}, + {file = "lxml-5.2.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b336b0416828022bfd5a2e3083e7f5ba54b96242159f83c7e3eebaec752f1716"}, + {file = "lxml-5.2.2-cp37-cp37m-manylinux_2_28_aarch64.whl", hash = "sha256:c2faf60c583af0d135e853c86ac2735ce178f0e338a3c7f9ae8f622fd2eb788c"}, + {file = "lxml-5.2.2-cp37-cp37m-manylinux_2_28_x86_64.whl", hash = "sha256:4bc6cb140a7a0ad1f7bc37e018d0ed690b7b6520ade518285dc3171f7a117905"}, + {file = "lxml-5.2.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:7ff762670cada8e05b32bf1e4dc50b140790909caa8303cfddc4d702b71ea184"}, + {file = "lxml-5.2.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:57f0a0bbc9868e10ebe874e9f129d2917750adf008fe7b9c1598c0fbbfdde6a6"}, + {file = "lxml-5.2.2-cp37-cp37m-musllinux_1_2_aarch64.whl", hash = "sha256:a6d2092797b388342c1bc932077ad232f914351932353e2e8706851c870bca1f"}, + {file = "lxml-5.2.2-cp37-cp37m-musllinux_1_2_x86_64.whl", hash = "sha256:60499fe961b21264e17a471ec296dcbf4365fbea611bf9e303ab69db7159ce61"}, + {file = "lxml-5.2.2-cp37-cp37m-win32.whl", hash = "sha256:d9b342c76003c6b9336a80efcc766748a333573abf9350f4094ee46b006ec18f"}, + {file = "lxml-5.2.2-cp37-cp37m-win_amd64.whl", hash = "sha256:b16db2770517b8799c79aa80f4053cd6f8b716f21f8aca962725a9565ce3ee40"}, + {file = "lxml-5.2.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:7ed07b3062b055d7a7f9d6557a251cc655eed0b3152b76de619516621c56f5d3"}, + {file = "lxml-5.2.2-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f60fdd125d85bf9c279ffb8e94c78c51b3b6a37711464e1f5f31078b45002421"}, + {file = "lxml-5.2.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8a7e24cb69ee5f32e003f50e016d5fde438010c1022c96738b04fc2423e61706"}, + {file = "lxml-5.2.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:23cfafd56887eaed93d07bc4547abd5e09d837a002b791e9767765492a75883f"}, + {file = "lxml-5.2.2-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:19b4e485cd07b7d83e3fe3b72132e7df70bfac22b14fe4bf7a23822c3a35bff5"}, + {file = "lxml-5.2.2-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:7ce7ad8abebe737ad6143d9d3bf94b88b93365ea30a5b81f6877ec9c0dee0a48"}, + {file = "lxml-5.2.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:e49b052b768bb74f58c7dda4e0bdf7b79d43a9204ca584ffe1fb48a6f3c84c66"}, + {file = "lxml-5.2.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:d14a0d029a4e176795cef99c056d58067c06195e0c7e2dbb293bf95c08f772a3"}, + {file = "lxml-5.2.2-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:be49ad33819d7dcc28a309b86d4ed98e1a65f3075c6acd3cd4fe32103235222b"}, + {file = "lxml-5.2.2-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:a6d17e0370d2516d5bb9062c7b4cb731cff921fc875644c3d751ad857ba9c5b1"}, + {file = "lxml-5.2.2-cp38-cp38-win32.whl", hash = "sha256:5b8c041b6265e08eac8a724b74b655404070b636a8dd6d7a13c3adc07882ef30"}, + {file = "lxml-5.2.2-cp38-cp38-win_amd64.whl", hash = "sha256:f61efaf4bed1cc0860e567d2ecb2363974d414f7f1f124b1df368bbf183453a6"}, + {file = "lxml-5.2.2-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:fb91819461b1b56d06fa4bcf86617fac795f6a99d12239fb0c68dbeba41a0a30"}, + {file = "lxml-5.2.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:d4ed0c7cbecde7194cd3228c044e86bf73e30a23505af852857c09c24e77ec5d"}, + {file = "lxml-5.2.2-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:54401c77a63cc7d6dc4b4e173bb484f28a5607f3df71484709fe037c92d4f0ed"}, + {file = "lxml-5.2.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:625e3ef310e7fa3a761d48ca7ea1f9d8718a32b1542e727d584d82f4453d5eeb"}, + {file = "lxml-5.2.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:519895c99c815a1a24a926d5b60627ce5ea48e9f639a5cd328bda0515ea0f10c"}, + {file = "lxml-5.2.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c7079d5eb1c1315a858bbf180000757db8ad904a89476653232db835c3114001"}, + {file = "lxml-5.2.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:343ab62e9ca78094f2306aefed67dcfad61c4683f87eee48ff2fd74902447726"}, + {file = "lxml-5.2.2-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:cd9e78285da6c9ba2d5c769628f43ef66d96ac3085e59b10ad4f3707980710d3"}, + {file = "lxml-5.2.2-cp39-cp39-manylinux_2_28_ppc64le.whl", hash = "sha256:546cf886f6242dff9ec206331209db9c8e1643ae642dea5fdbecae2453cb50fd"}, + {file = "lxml-5.2.2-cp39-cp39-manylinux_2_28_s390x.whl", hash = "sha256:02f6a8eb6512fdc2fd4ca10a49c341c4e109aa6e9448cc4859af5b949622715a"}, + {file = "lxml-5.2.2-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:339ee4a4704bc724757cd5dd9dc8cf4d00980f5d3e6e06d5847c1b594ace68ab"}, + {file = "lxml-5.2.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:0a028b61a2e357ace98b1615fc03f76eb517cc028993964fe08ad514b1e8892d"}, + {file = "lxml-5.2.2-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:f90e552ecbad426eab352e7b2933091f2be77115bb16f09f78404861c8322981"}, + {file = "lxml-5.2.2-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:d83e2d94b69bf31ead2fa45f0acdef0757fa0458a129734f59f67f3d2eb7ef32"}, + {file = "lxml-5.2.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:a02d3c48f9bb1e10c7788d92c0c7db6f2002d024ab6e74d6f45ae33e3d0288a3"}, + {file = "lxml-5.2.2-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:6d68ce8e7b2075390e8ac1e1d3a99e8b6372c694bbe612632606d1d546794207"}, + {file = "lxml-5.2.2-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:453d037e09a5176d92ec0fd282e934ed26d806331a8b70ab431a81e2fbabf56d"}, + {file = "lxml-5.2.2-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:3b019d4ee84b683342af793b56bb35034bd749e4cbdd3d33f7d1107790f8c472"}, + {file = "lxml-5.2.2-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:cb3942960f0beb9f46e2a71a3aca220d1ca32feb5a398656be934320804c0df9"}, + {file = "lxml-5.2.2-cp39-cp39-win32.whl", hash = "sha256:ac6540c9fff6e3813d29d0403ee7a81897f1d8ecc09a8ff84d2eea70ede1cdbf"}, + {file = "lxml-5.2.2-cp39-cp39-win_amd64.whl", hash = "sha256:610b5c77428a50269f38a534057444c249976433f40f53e3b47e68349cca1425"}, + {file = "lxml-5.2.2-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:b537bd04d7ccd7c6350cdaaaad911f6312cbd61e6e6045542f781c7f8b2e99d2"}, + {file = "lxml-5.2.2-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4820c02195d6dfb7b8508ff276752f6b2ff8b64ae5d13ebe02e7667e035000b9"}, + {file = "lxml-5.2.2-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f2a09f6184f17a80897172863a655467da2b11151ec98ba8d7af89f17bf63dae"}, + {file = "lxml-5.2.2-pp310-pypy310_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:76acba4c66c47d27c8365e7c10b3d8016a7da83d3191d053a58382311a8bf4e1"}, + {file = "lxml-5.2.2-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:b128092c927eaf485928cec0c28f6b8bead277e28acf56800e972aa2c2abd7a2"}, + {file = "lxml-5.2.2-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:ae791f6bd43305aade8c0e22f816b34f3b72b6c820477aab4d18473a37e8090b"}, + {file = "lxml-5.2.2-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:a2f6a1bc2460e643785a2cde17293bd7a8f990884b822f7bca47bee0a82fc66b"}, + {file = "lxml-5.2.2-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8e8d351ff44c1638cb6e980623d517abd9f580d2e53bfcd18d8941c052a5a009"}, + {file = "lxml-5.2.2-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bec4bd9133420c5c52d562469c754f27c5c9e36ee06abc169612c959bd7dbb07"}, + {file = "lxml-5.2.2-pp37-pypy37_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:55ce6b6d803890bd3cc89975fca9de1dff39729b43b73cb15ddd933b8bc20484"}, + {file = "lxml-5.2.2-pp37-pypy37_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:8ab6a358d1286498d80fe67bd3d69fcbc7d1359b45b41e74c4a26964ca99c3f8"}, + {file = "lxml-5.2.2-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:06668e39e1f3c065349c51ac27ae430719d7806c026fec462e5693b08b95696b"}, + {file = "lxml-5.2.2-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:9cd5323344d8ebb9fb5e96da5de5ad4ebab993bbf51674259dbe9d7a18049525"}, + {file = "lxml-5.2.2-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:89feb82ca055af0fe797a2323ec9043b26bc371365847dbe83c7fd2e2f181c34"}, + {file = "lxml-5.2.2-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e481bba1e11ba585fb06db666bfc23dbe181dbafc7b25776156120bf12e0d5a6"}, + {file = "lxml-5.2.2-pp38-pypy38_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:9d6c6ea6a11ca0ff9cd0390b885984ed31157c168565702959c25e2191674a14"}, + {file = "lxml-5.2.2-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:3d98de734abee23e61f6b8c2e08a88453ada7d6486dc7cdc82922a03968928db"}, + {file = "lxml-5.2.2-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:69ab77a1373f1e7563e0fb5a29a8440367dec051da6c7405333699d07444f511"}, + {file = "lxml-5.2.2-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:34e17913c431f5ae01d8658dbf792fdc457073dcdfbb31dc0cc6ab256e664a8d"}, + {file = "lxml-5.2.2-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:05f8757b03208c3f50097761be2dea0aba02e94f0dc7023ed73a7bb14ff11eb0"}, + {file = "lxml-5.2.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6a520b4f9974b0a0a6ed73c2154de57cdfd0c8800f4f15ab2b73238ffed0b36e"}, + {file = "lxml-5.2.2-pp39-pypy39_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:5e097646944b66207023bc3c634827de858aebc226d5d4d6d16f0b77566ea182"}, + {file = "lxml-5.2.2-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:b5e4ef22ff25bfd4ede5f8fb30f7b24446345f3e79d9b7455aef2836437bc38a"}, + {file = "lxml-5.2.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:ff69a9a0b4b17d78170c73abe2ab12084bdf1691550c5629ad1fe7849433f324"}, + {file = "lxml-5.2.2.tar.gz", hash = "sha256:bb2dc4898180bea79863d5487e5f9c7c34297414bad54bcd0f0852aee9cfdb87"}, ] [package.extras] @@ -1330,103 +1319,103 @@ files = [ [[package]] name = "msgpack" -version = "1.0.7" +version = "1.0.8" description = "MessagePack serializer" optional = false python-versions = ">=3.8" files = [ - {file = "msgpack-1.0.7-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:04ad6069c86e531682f9e1e71b71c1c3937d6014a7c3e9edd2aa81ad58842862"}, - {file = "msgpack-1.0.7-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:cca1b62fe70d761a282496b96a5e51c44c213e410a964bdffe0928e611368329"}, - {file = "msgpack-1.0.7-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e50ebce52f41370707f1e21a59514e3375e3edd6e1832f5e5235237db933c98b"}, - {file = "msgpack-1.0.7-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4a7b4f35de6a304b5533c238bee86b670b75b03d31b7797929caa7a624b5dda6"}, - {file = "msgpack-1.0.7-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:28efb066cde83c479dfe5a48141a53bc7e5f13f785b92ddde336c716663039ee"}, - {file = "msgpack-1.0.7-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4cb14ce54d9b857be9591ac364cb08dc2d6a5c4318c1182cb1d02274029d590d"}, - {file = "msgpack-1.0.7-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:b573a43ef7c368ba4ea06050a957c2a7550f729c31f11dd616d2ac4aba99888d"}, - {file = "msgpack-1.0.7-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:ccf9a39706b604d884d2cb1e27fe973bc55f2890c52f38df742bc1d79ab9f5e1"}, - {file = "msgpack-1.0.7-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:cb70766519500281815dfd7a87d3a178acf7ce95390544b8c90587d76b227681"}, - {file = "msgpack-1.0.7-cp310-cp310-win32.whl", hash = "sha256:b610ff0f24e9f11c9ae653c67ff8cc03c075131401b3e5ef4b82570d1728f8a9"}, - {file = "msgpack-1.0.7-cp310-cp310-win_amd64.whl", hash = "sha256:a40821a89dc373d6427e2b44b572efc36a2778d3f543299e2f24eb1a5de65415"}, - {file = "msgpack-1.0.7-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:576eb384292b139821c41995523654ad82d1916da6a60cff129c715a6223ea84"}, - {file = "msgpack-1.0.7-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:730076207cb816138cf1af7f7237b208340a2c5e749707457d70705715c93b93"}, - {file = "msgpack-1.0.7-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:85765fdf4b27eb5086f05ac0491090fc76f4f2b28e09d9350c31aac25a5aaff8"}, - {file = "msgpack-1.0.7-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3476fae43db72bd11f29a5147ae2f3cb22e2f1a91d575ef130d2bf49afd21c46"}, - {file = "msgpack-1.0.7-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6d4c80667de2e36970ebf74f42d1088cc9ee7ef5f4e8c35eee1b40eafd33ca5b"}, - {file = "msgpack-1.0.7-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5b0bf0effb196ed76b7ad883848143427a73c355ae8e569fa538365064188b8e"}, - {file = "msgpack-1.0.7-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:f9a7c509542db4eceed3dcf21ee5267ab565a83555c9b88a8109dcecc4709002"}, - {file = "msgpack-1.0.7-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:84b0daf226913133f899ea9b30618722d45feffa67e4fe867b0b5ae83a34060c"}, - {file = "msgpack-1.0.7-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:ec79ff6159dffcc30853b2ad612ed572af86c92b5168aa3fc01a67b0fa40665e"}, - {file = "msgpack-1.0.7-cp311-cp311-win32.whl", hash = "sha256:3e7bf4442b310ff154b7bb9d81eb2c016b7d597e364f97d72b1acc3817a0fdc1"}, - {file = "msgpack-1.0.7-cp311-cp311-win_amd64.whl", hash = "sha256:3f0c8c6dfa6605ab8ff0611995ee30d4f9fcff89966cf562733b4008a3d60d82"}, - {file = "msgpack-1.0.7-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:f0936e08e0003f66bfd97e74ee530427707297b0d0361247e9b4f59ab78ddc8b"}, - {file = "msgpack-1.0.7-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:98bbd754a422a0b123c66a4c341de0474cad4a5c10c164ceed6ea090f3563db4"}, - {file = "msgpack-1.0.7-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:b291f0ee7961a597cbbcc77709374087fa2a9afe7bdb6a40dbbd9b127e79afee"}, - {file = "msgpack-1.0.7-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ebbbba226f0a108a7366bf4b59bf0f30a12fd5e75100c630267d94d7f0ad20e5"}, - {file = "msgpack-1.0.7-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1e2d69948e4132813b8d1131f29f9101bc2c915f26089a6d632001a5c1349672"}, - {file = "msgpack-1.0.7-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bdf38ba2d393c7911ae989c3bbba510ebbcdf4ecbdbfec36272abe350c454075"}, - {file = "msgpack-1.0.7-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:993584fc821c58d5993521bfdcd31a4adf025c7d745bbd4d12ccfecf695af5ba"}, - {file = "msgpack-1.0.7-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:52700dc63a4676669b341ba33520f4d6e43d3ca58d422e22ba66d1736b0a6e4c"}, - {file = "msgpack-1.0.7-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:e45ae4927759289c30ccba8d9fdce62bb414977ba158286b5ddaf8df2cddb5c5"}, - {file = "msgpack-1.0.7-cp312-cp312-win32.whl", hash = "sha256:27dcd6f46a21c18fa5e5deed92a43d4554e3df8d8ca5a47bf0615d6a5f39dbc9"}, - {file = "msgpack-1.0.7-cp312-cp312-win_amd64.whl", hash = "sha256:7687e22a31e976a0e7fc99c2f4d11ca45eff652a81eb8c8085e9609298916dcf"}, - {file = "msgpack-1.0.7-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:5b6ccc0c85916998d788b295765ea0e9cb9aac7e4a8ed71d12e7d8ac31c23c95"}, - {file = "msgpack-1.0.7-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:235a31ec7db685f5c82233bddf9858748b89b8119bf4538d514536c485c15fe0"}, - {file = "msgpack-1.0.7-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:cab3db8bab4b7e635c1c97270d7a4b2a90c070b33cbc00c99ef3f9be03d3e1f7"}, - {file = "msgpack-1.0.7-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0bfdd914e55e0d2c9e1526de210f6fe8ffe9705f2b1dfcc4aecc92a4cb4b533d"}, - {file = "msgpack-1.0.7-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:36e17c4592231a7dbd2ed09027823ab295d2791b3b1efb2aee874b10548b7524"}, - {file = "msgpack-1.0.7-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:38949d30b11ae5f95c3c91917ee7a6b239f5ec276f271f28638dec9156f82cfc"}, - {file = "msgpack-1.0.7-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:ff1d0899f104f3921d94579a5638847f783c9b04f2d5f229392ca77fba5b82fc"}, - {file = "msgpack-1.0.7-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:dc43f1ec66eb8440567186ae2f8c447d91e0372d793dfe8c222aec857b81a8cf"}, - {file = "msgpack-1.0.7-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:dd632777ff3beaaf629f1ab4396caf7ba0bdd075d948a69460d13d44357aca4c"}, - {file = "msgpack-1.0.7-cp38-cp38-win32.whl", hash = "sha256:4e71bc4416de195d6e9b4ee93ad3f2f6b2ce11d042b4d7a7ee00bbe0358bd0c2"}, - {file = "msgpack-1.0.7-cp38-cp38-win_amd64.whl", hash = "sha256:8f5b234f567cf76ee489502ceb7165c2a5cecec081db2b37e35332b537f8157c"}, - {file = "msgpack-1.0.7-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:bfef2bb6ef068827bbd021017a107194956918ab43ce4d6dc945ffa13efbc25f"}, - {file = "msgpack-1.0.7-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:484ae3240666ad34cfa31eea7b8c6cd2f1fdaae21d73ce2974211df099a95d81"}, - {file = "msgpack-1.0.7-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3967e4ad1aa9da62fd53e346ed17d7b2e922cba5ab93bdd46febcac39be636fc"}, - {file = "msgpack-1.0.7-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8dd178c4c80706546702c59529ffc005681bd6dc2ea234c450661b205445a34d"}, - {file = "msgpack-1.0.7-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f6ffbc252eb0d229aeb2f9ad051200668fc3a9aaa8994e49f0cb2ffe2b7867e7"}, - {file = "msgpack-1.0.7-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:822ea70dc4018c7e6223f13affd1c5c30c0f5c12ac1f96cd8e9949acddb48a61"}, - {file = "msgpack-1.0.7-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:384d779f0d6f1b110eae74cb0659d9aa6ff35aaf547b3955abf2ab4c901c4819"}, - {file = "msgpack-1.0.7-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:f64e376cd20d3f030190e8c32e1c64582eba56ac6dc7d5b0b49a9d44021b52fd"}, - {file = "msgpack-1.0.7-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:5ed82f5a7af3697b1c4786053736f24a0efd0a1b8a130d4c7bfee4b9ded0f08f"}, - {file = "msgpack-1.0.7-cp39-cp39-win32.whl", hash = "sha256:f26a07a6e877c76a88e3cecac8531908d980d3d5067ff69213653649ec0f60ad"}, - {file = "msgpack-1.0.7-cp39-cp39-win_amd64.whl", hash = "sha256:1dc93e8e4653bdb5910aed79f11e165c85732067614f180f70534f056da97db3"}, - {file = "msgpack-1.0.7.tar.gz", hash = "sha256:572efc93db7a4d27e404501975ca6d2d9775705c2d922390d878fcf768d92c87"}, + {file = "msgpack-1.0.8-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:505fe3d03856ac7d215dbe005414bc28505d26f0c128906037e66d98c4e95868"}, + {file = "msgpack-1.0.8-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:e6b7842518a63a9f17107eb176320960ec095a8ee3b4420b5f688e24bf50c53c"}, + {file = "msgpack-1.0.8-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:376081f471a2ef24828b83a641a02c575d6103a3ad7fd7dade5486cad10ea659"}, + {file = "msgpack-1.0.8-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5e390971d082dba073c05dbd56322427d3280b7cc8b53484c9377adfbae67dc2"}, + {file = "msgpack-1.0.8-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:00e073efcba9ea99db5acef3959efa45b52bc67b61b00823d2a1a6944bf45982"}, + {file = "msgpack-1.0.8-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:82d92c773fbc6942a7a8b520d22c11cfc8fd83bba86116bfcf962c2f5c2ecdaa"}, + {file = "msgpack-1.0.8-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:9ee32dcb8e531adae1f1ca568822e9b3a738369b3b686d1477cbc643c4a9c128"}, + {file = "msgpack-1.0.8-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:e3aa7e51d738e0ec0afbed661261513b38b3014754c9459508399baf14ae0c9d"}, + {file = "msgpack-1.0.8-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:69284049d07fce531c17404fcba2bb1df472bc2dcdac642ae71a2d079d950653"}, + {file = "msgpack-1.0.8-cp310-cp310-win32.whl", hash = "sha256:13577ec9e247f8741c84d06b9ece5f654920d8365a4b636ce0e44f15e07ec693"}, + {file = "msgpack-1.0.8-cp310-cp310-win_amd64.whl", hash = "sha256:e532dbd6ddfe13946de050d7474e3f5fb6ec774fbb1a188aaf469b08cf04189a"}, + {file = "msgpack-1.0.8-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:9517004e21664f2b5a5fd6333b0731b9cf0817403a941b393d89a2f1dc2bd836"}, + {file = "msgpack-1.0.8-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d16a786905034e7e34098634b184a7d81f91d4c3d246edc6bd7aefb2fd8ea6ad"}, + {file = "msgpack-1.0.8-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:e2872993e209f7ed04d963e4b4fbae72d034844ec66bc4ca403329db2074377b"}, + {file = "msgpack-1.0.8-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5c330eace3dd100bdb54b5653b966de7f51c26ec4a7d4e87132d9b4f738220ba"}, + {file = "msgpack-1.0.8-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:83b5c044f3eff2a6534768ccfd50425939e7a8b5cf9a7261c385de1e20dcfc85"}, + {file = "msgpack-1.0.8-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1876b0b653a808fcd50123b953af170c535027bf1d053b59790eebb0aeb38950"}, + {file = "msgpack-1.0.8-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:dfe1f0f0ed5785c187144c46a292b8c34c1295c01da12e10ccddfc16def4448a"}, + {file = "msgpack-1.0.8-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:3528807cbbb7f315bb81959d5961855e7ba52aa60a3097151cb21956fbc7502b"}, + {file = "msgpack-1.0.8-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e2f879ab92ce502a1e65fce390eab619774dda6a6ff719718069ac94084098ce"}, + {file = "msgpack-1.0.8-cp311-cp311-win32.whl", hash = "sha256:26ee97a8261e6e35885c2ecd2fd4a6d38252246f94a2aec23665a4e66d066305"}, + {file = "msgpack-1.0.8-cp311-cp311-win_amd64.whl", hash = "sha256:eadb9f826c138e6cf3c49d6f8de88225a3c0ab181a9b4ba792e006e5292d150e"}, + {file = "msgpack-1.0.8-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:114be227f5213ef8b215c22dde19532f5da9652e56e8ce969bf0a26d7c419fee"}, + {file = "msgpack-1.0.8-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:d661dc4785affa9d0edfdd1e59ec056a58b3dbb9f196fa43587f3ddac654ac7b"}, + {file = "msgpack-1.0.8-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:d56fd9f1f1cdc8227d7b7918f55091349741904d9520c65f0139a9755952c9e8"}, + {file = "msgpack-1.0.8-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0726c282d188e204281ebd8de31724b7d749adebc086873a59efb8cf7ae27df3"}, + {file = "msgpack-1.0.8-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8db8e423192303ed77cff4dce3a4b88dbfaf43979d280181558af5e2c3c71afc"}, + {file = "msgpack-1.0.8-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:99881222f4a8c2f641f25703963a5cefb076adffd959e0558dc9f803a52d6a58"}, + {file = "msgpack-1.0.8-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:b5505774ea2a73a86ea176e8a9a4a7c8bf5d521050f0f6f8426afe798689243f"}, + {file = "msgpack-1.0.8-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:ef254a06bcea461e65ff0373d8a0dd1ed3aa004af48839f002a0c994a6f72d04"}, + {file = "msgpack-1.0.8-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:e1dd7839443592d00e96db831eddb4111a2a81a46b028f0facd60a09ebbdd543"}, + {file = "msgpack-1.0.8-cp312-cp312-win32.whl", hash = "sha256:64d0fcd436c5683fdd7c907eeae5e2cbb5eb872fafbc03a43609d7941840995c"}, + {file = "msgpack-1.0.8-cp312-cp312-win_amd64.whl", hash = "sha256:74398a4cf19de42e1498368c36eed45d9528f5fd0155241e82c4082b7e16cffd"}, + {file = "msgpack-1.0.8-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:0ceea77719d45c839fd73abcb190b8390412a890df2f83fb8cf49b2a4b5c2f40"}, + {file = "msgpack-1.0.8-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1ab0bbcd4d1f7b6991ee7c753655b481c50084294218de69365f8f1970d4c151"}, + {file = "msgpack-1.0.8-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:1cce488457370ffd1f953846f82323cb6b2ad2190987cd4d70b2713e17268d24"}, + {file = "msgpack-1.0.8-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3923a1778f7e5ef31865893fdca12a8d7dc03a44b33e2a5f3295416314c09f5d"}, + {file = "msgpack-1.0.8-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a22e47578b30a3e199ab067a4d43d790249b3c0587d9a771921f86250c8435db"}, + {file = "msgpack-1.0.8-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bd739c9251d01e0279ce729e37b39d49a08c0420d3fee7f2a4968c0576678f77"}, + {file = "msgpack-1.0.8-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:d3420522057ebab1728b21ad473aa950026d07cb09da41103f8e597dfbfaeb13"}, + {file = "msgpack-1.0.8-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:5845fdf5e5d5b78a49b826fcdc0eb2e2aa7191980e3d2cfd2a30303a74f212e2"}, + {file = "msgpack-1.0.8-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:6a0e76621f6e1f908ae52860bdcb58e1ca85231a9b0545e64509c931dd34275a"}, + {file = "msgpack-1.0.8-cp38-cp38-win32.whl", hash = "sha256:374a8e88ddab84b9ada695d255679fb99c53513c0a51778796fcf0944d6c789c"}, + {file = "msgpack-1.0.8-cp38-cp38-win_amd64.whl", hash = "sha256:f3709997b228685fe53e8c433e2df9f0cdb5f4542bd5114ed17ac3c0129b0480"}, + {file = "msgpack-1.0.8-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:f51bab98d52739c50c56658cc303f190785f9a2cd97b823357e7aeae54c8f68a"}, + {file = "msgpack-1.0.8-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:73ee792784d48aa338bba28063e19a27e8d989344f34aad14ea6e1b9bd83f596"}, + {file = "msgpack-1.0.8-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:f9904e24646570539a8950400602d66d2b2c492b9010ea7e965025cb71d0c86d"}, + {file = "msgpack-1.0.8-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e75753aeda0ddc4c28dce4c32ba2f6ec30b1b02f6c0b14e547841ba5b24f753f"}, + {file = "msgpack-1.0.8-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5dbf059fb4b7c240c873c1245ee112505be27497e90f7c6591261c7d3c3a8228"}, + {file = "msgpack-1.0.8-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4916727e31c28be8beaf11cf117d6f6f188dcc36daae4e851fee88646f5b6b18"}, + {file = "msgpack-1.0.8-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:7938111ed1358f536daf311be244f34df7bf3cdedb3ed883787aca97778b28d8"}, + {file = "msgpack-1.0.8-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:493c5c5e44b06d6c9268ce21b302c9ca055c1fd3484c25ba41d34476c76ee746"}, + {file = "msgpack-1.0.8-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:5fbb160554e319f7b22ecf530a80a3ff496d38e8e07ae763b9e82fadfe96f273"}, + {file = "msgpack-1.0.8-cp39-cp39-win32.whl", hash = "sha256:f9af38a89b6a5c04b7d18c492c8ccf2aee7048aff1ce8437c4683bb5a1df893d"}, + {file = "msgpack-1.0.8-cp39-cp39-win_amd64.whl", hash = "sha256:ed59dd52075f8fc91da6053b12e8c89e37aa043f8986efd89e61fae69dc1b011"}, + {file = "msgpack-1.0.8.tar.gz", hash = "sha256:95c02b0e27e706e48d0e5426d1710ca78e0f0628d6e89d5b5a5b91a5f12274f3"}, ] [[package]] name = "mypy" -version = "1.8.0" +version = "1.9.0" description = "Optional static typing for Python" optional = false python-versions = ">=3.8" files = [ - {file = "mypy-1.8.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:485a8942f671120f76afffff70f259e1cd0f0cfe08f81c05d8816d958d4577d3"}, - {file = "mypy-1.8.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:df9824ac11deaf007443e7ed2a4a26bebff98d2bc43c6da21b2b64185da011c4"}, - {file = "mypy-1.8.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2afecd6354bbfb6e0160f4e4ad9ba6e4e003b767dd80d85516e71f2e955ab50d"}, - {file = "mypy-1.8.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:8963b83d53ee733a6e4196954502b33567ad07dfd74851f32be18eb932fb1cb9"}, - {file = "mypy-1.8.0-cp310-cp310-win_amd64.whl", hash = "sha256:e46f44b54ebddbeedbd3d5b289a893219065ef805d95094d16a0af6630f5d410"}, - {file = "mypy-1.8.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:855fe27b80375e5c5878492f0729540db47b186509c98dae341254c8f45f42ae"}, - {file = "mypy-1.8.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:4c886c6cce2d070bd7df4ec4a05a13ee20c0aa60cb587e8d1265b6c03cf91da3"}, - {file = "mypy-1.8.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d19c413b3c07cbecf1f991e2221746b0d2a9410b59cb3f4fb9557f0365a1a817"}, - {file = "mypy-1.8.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:9261ed810972061388918c83c3f5cd46079d875026ba97380f3e3978a72f503d"}, - {file = "mypy-1.8.0-cp311-cp311-win_amd64.whl", hash = "sha256:51720c776d148bad2372ca21ca29256ed483aa9a4cdefefcef49006dff2a6835"}, - {file = "mypy-1.8.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:52825b01f5c4c1c4eb0db253ec09c7aa17e1a7304d247c48b6f3599ef40db8bd"}, - {file = "mypy-1.8.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:f5ac9a4eeb1ec0f1ccdc6f326bcdb464de5f80eb07fb38b5ddd7b0de6bc61e55"}, - {file = "mypy-1.8.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:afe3fe972c645b4632c563d3f3eff1cdca2fa058f730df2b93a35e3b0c538218"}, - {file = "mypy-1.8.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:42c6680d256ab35637ef88891c6bd02514ccb7e1122133ac96055ff458f93fc3"}, - {file = "mypy-1.8.0-cp312-cp312-win_amd64.whl", hash = "sha256:720a5ca70e136b675af3af63db533c1c8c9181314d207568bbe79051f122669e"}, - {file = "mypy-1.8.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:028cf9f2cae89e202d7b6593cd98db6759379f17a319b5faf4f9978d7084cdc6"}, - {file = "mypy-1.8.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:4e6d97288757e1ddba10dd9549ac27982e3e74a49d8d0179fc14d4365c7add66"}, - {file = "mypy-1.8.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7f1478736fcebb90f97e40aff11a5f253af890c845ee0c850fe80aa060a267c6"}, - {file = "mypy-1.8.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:42419861b43e6962a649068a61f4a4839205a3ef525b858377a960b9e2de6e0d"}, - {file = "mypy-1.8.0-cp38-cp38-win_amd64.whl", hash = "sha256:2b5b6c721bd4aabaadead3a5e6fa85c11c6c795e0c81a7215776ef8afc66de02"}, - {file = "mypy-1.8.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:5c1538c38584029352878a0466f03a8ee7547d7bd9f641f57a0f3017a7c905b8"}, - {file = "mypy-1.8.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:4ef4be7baf08a203170f29e89d79064463b7fc7a0908b9d0d5114e8009c3a259"}, - {file = "mypy-1.8.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7178def594014aa6c35a8ff411cf37d682f428b3b5617ca79029d8ae72f5402b"}, - {file = "mypy-1.8.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:ab3c84fa13c04aeeeabb2a7f67a25ef5d77ac9d6486ff33ded762ef353aa5592"}, - {file = "mypy-1.8.0-cp39-cp39-win_amd64.whl", hash = "sha256:99b00bc72855812a60d253420d8a2eae839b0afa4938f09f4d2aa9bb4654263a"}, - {file = "mypy-1.8.0-py3-none-any.whl", hash = "sha256:538fd81bb5e430cc1381a443971c0475582ff9f434c16cd46d2c66763ce85d9d"}, - {file = "mypy-1.8.0.tar.gz", hash = "sha256:6ff8b244d7085a0b425b56d327b480c3b29cafbd2eff27316a004f9a7391ae07"}, + {file = "mypy-1.9.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:f8a67616990062232ee4c3952f41c779afac41405806042a8126fe96e098419f"}, + {file = "mypy-1.9.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d357423fa57a489e8c47b7c85dfb96698caba13d66e086b412298a1a0ea3b0ed"}, + {file = "mypy-1.9.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:49c87c15aed320de9b438ae7b00c1ac91cd393c1b854c2ce538e2a72d55df150"}, + {file = "mypy-1.9.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:48533cdd345c3c2e5ef48ba3b0d3880b257b423e7995dada04248725c6f77374"}, + {file = "mypy-1.9.0-cp310-cp310-win_amd64.whl", hash = "sha256:4d3dbd346cfec7cb98e6cbb6e0f3c23618af826316188d587d1c1bc34f0ede03"}, + {file = "mypy-1.9.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:653265f9a2784db65bfca694d1edd23093ce49740b2244cde583aeb134c008f3"}, + {file = "mypy-1.9.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:3a3c007ff3ee90f69cf0a15cbcdf0995749569b86b6d2f327af01fd1b8aee9dc"}, + {file = "mypy-1.9.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2418488264eb41f69cc64a69a745fad4a8f86649af4b1041a4c64ee61fc61129"}, + {file = "mypy-1.9.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:68edad3dc7d70f2f17ae4c6c1b9471a56138ca22722487eebacfd1eb5321d612"}, + {file = "mypy-1.9.0-cp311-cp311-win_amd64.whl", hash = "sha256:85ca5fcc24f0b4aeedc1d02f93707bccc04733f21d41c88334c5482219b1ccb3"}, + {file = "mypy-1.9.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:aceb1db093b04db5cd390821464504111b8ec3e351eb85afd1433490163d60cd"}, + {file = "mypy-1.9.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:0235391f1c6f6ce487b23b9dbd1327b4ec33bb93934aa986efe8a9563d9349e6"}, + {file = "mypy-1.9.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d4d5ddc13421ba3e2e082a6c2d74c2ddb3979c39b582dacd53dd5d9431237185"}, + {file = "mypy-1.9.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:190da1ee69b427d7efa8aa0d5e5ccd67a4fb04038c380237a0d96829cb157913"}, + {file = "mypy-1.9.0-cp312-cp312-win_amd64.whl", hash = "sha256:fe28657de3bfec596bbeef01cb219833ad9d38dd5393fc649f4b366840baefe6"}, + {file = "mypy-1.9.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:e54396d70be04b34f31d2edf3362c1edd023246c82f1730bbf8768c28db5361b"}, + {file = "mypy-1.9.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:5e6061f44f2313b94f920e91b204ec600982961e07a17e0f6cd83371cb23f5c2"}, + {file = "mypy-1.9.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:81a10926e5473c5fc3da8abb04119a1f5811a236dc3a38d92015cb1e6ba4cb9e"}, + {file = "mypy-1.9.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:b685154e22e4e9199fc95f298661deea28aaede5ae16ccc8cbb1045e716b3e04"}, + {file = "mypy-1.9.0-cp38-cp38-win_amd64.whl", hash = "sha256:5d741d3fc7c4da608764073089e5f58ef6352bedc223ff58f2f038c2c4698a89"}, + {file = "mypy-1.9.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:587ce887f75dd9700252a3abbc9c97bbe165a4a630597845c61279cf32dfbf02"}, + {file = "mypy-1.9.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:f88566144752999351725ac623471661c9d1cd8caa0134ff98cceeea181789f4"}, + {file = "mypy-1.9.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:61758fabd58ce4b0720ae1e2fea5cfd4431591d6d590b197775329264f86311d"}, + {file = "mypy-1.9.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:e49499be624dead83927e70c756970a0bc8240e9f769389cdf5714b0784ca6bf"}, + {file = "mypy-1.9.0-cp39-cp39-win_amd64.whl", hash = "sha256:571741dc4194b4f82d344b15e8837e8c5fcc462d66d076748142327626a1b6e9"}, + {file = "mypy-1.9.0-py3-none-any.whl", hash = "sha256:a260627a570559181a9ea5de61ac6297aa5af202f06fd7ab093ce74e7181e43e"}, + {file = "mypy-1.9.0.tar.gz", hash = "sha256:3cc5da0127e6a478cddd906068496a97a7618a21ce9b54bde5bf7e539c7af974"}, ] [package.dependencies] @@ -1453,17 +1442,17 @@ files = [ [[package]] name = "mypy-zope" -version = "1.0.3" +version = "1.0.4" description = "Plugin for mypy to support zope interfaces" optional = false python-versions = "*" files = [ - {file = "mypy-zope-1.0.3.tar.gz", hash = "sha256:149081bd2754d947747baefac569bb1c2bc127b4a2cc1fa505492336946bb3b4"}, - {file = "mypy_zope-1.0.3-py3-none-any.whl", hash = "sha256:7a30ce1a2589173f0be66662c9a9179f75737afc40e4104df4c76fb5a8421c14"}, + {file = "mypy-zope-1.0.4.tar.gz", hash = "sha256:a9569e73ae85a65247787d98590fa6d4290e76f26aabe035d1c3e94a0b9ab6ee"}, + {file = "mypy_zope-1.0.4-py3-none-any.whl", hash = "sha256:c7298f93963a84f2b145c2b5cc98709fc2a5be4adf54bfe23fa7fdd8fd19c975"}, ] [package.dependencies] -mypy = ">=1.0.0,<1.9.0" +mypy = ">=1.0.0,<1.10.0" "zope.interface" = "*" "zope.schema" = "*" @@ -1472,13 +1461,13 @@ test = ["lxml", "pytest (>=4.6)", "pytest-cov"] [[package]] name = "netaddr" -version = "1.2.1" +version = "1.3.0" description = "A network address manipulation library for Python" optional = false python-versions = ">=3.7" files = [ - {file = "netaddr-1.2.1-py3-none-any.whl", hash = "sha256:bd9e9534b0d46af328cf64f0e5a23a5a43fca292df221c85580b27394793496e"}, - {file = "netaddr-1.2.1.tar.gz", hash = "sha256:6eb8fedf0412c6d294d06885c110de945cf4d22d2b510d0404f4e06950857987"}, + {file = "netaddr-1.3.0-py3-none-any.whl", hash = "sha256:c2c6a8ebe5554ce33b7d5b3a306b71bbb373e000bbbf2350dd5213cc56e3dbbe"}, + {file = "netaddr-1.3.0.tar.gz", hash = "sha256:5c3c3d9895b551b763779ba7db7a03487dc1f8e3b385af819af341ae9ef6e48a"}, ] [package.extras] @@ -1499,13 +1488,13 @@ tests = ["Sphinx", "doubles", "flake8", "flake8-quotes", "gevent", "mock", "pyte [[package]] name = "packaging" -version = "24.0" +version = "24.1" description = "Core utilities for Python packages" optional = false -python-versions = ">=3.7" +python-versions = ">=3.8" files = [ - {file = "packaging-24.0-py3-none-any.whl", hash = "sha256:2ddfb553fdf02fb784c234c7ba6ccc288296ceabec964ad2eae3777778130bc5"}, - {file = "packaging-24.0.tar.gz", hash = "sha256:eb82c5e3e56209074766e6885bb04b8c38a0c015d0a30036ebe7ece34c9989e9"}, + {file = "packaging-24.1-py3-none-any.whl", hash = "sha256:5b8f2217dbdbd2f7f384c41c628544e6d52f2d0f53c6d0c3ea61aa5d1d7ff124"}, + {file = "packaging-24.1.tar.gz", hash = "sha256:026ed72c8ed3fcce5bf8950572258698927fd1dbda10a5e981cdf0ac37f4f002"}, ] [[package]] @@ -1535,13 +1524,13 @@ files = [ [[package]] name = "phonenumbers" -version = "8.13.35" +version = "8.13.39" description = "Python version of Google's common library for parsing, formatting, storing and validating international phone numbers." optional = false python-versions = "*" files = [ - {file = "phonenumbers-8.13.35-py2.py3-none-any.whl", hash = "sha256:58286a8e617bd75f541e04313b28c36398be6d4443a778c85e9617a93c391310"}, - {file = "phonenumbers-8.13.35.tar.gz", hash = "sha256:64f061a967dcdae11e1c59f3688649e697b897110a33bb74d5a69c3e35321245"}, + {file = "phonenumbers-8.13.39-py2.py3-none-any.whl", hash = "sha256:3ad2d086fa71e7eef409001b9195ac54bebb0c6e3e752209b558ca192c9229a0"}, + {file = "phonenumbers-8.13.39.tar.gz", hash = "sha256:db7ca4970d206b2056231105300753b1a5b229f43416f8c2b3010e63fbb68d77"}, ] [[package]] @@ -1672,13 +1661,13 @@ test = ["appdirs (==1.4.4)", "covdefaults (>=2.2.2)", "pytest (>=7.2.1)", "pytes [[package]] name = "prometheus-client" -version = "0.19.0" +version = "0.20.0" description = "Python client for the Prometheus monitoring system." optional = false python-versions = ">=3.8" files = [ - {file = "prometheus_client-0.19.0-py3-none-any.whl", hash = "sha256:c88b1e6ecf6b41cd8fb5731c7ae919bf66df6ec6fafa555cd6c0e16ca169ae92"}, - {file = "prometheus_client-0.19.0.tar.gz", hash = "sha256:4585b0d1223148c27a225b10dbec5ae9bc4c81a99a3fa80774fa6209935324e1"}, + {file = "prometheus_client-0.20.0-py3-none-any.whl", hash = "sha256:cde524a85bce83ca359cc837f28b8c0db5cac7aa653a588fd7e84ba061c329e7"}, + {file = "prometheus_client-0.20.0.tar.gz", hash = "sha256:287629d00b147a32dcb2be0b9df905da599b2d82f80377083ec8463309a4bb89"}, ] [package.extras] @@ -1735,13 +1724,13 @@ psycopg2 = "*" [[package]] name = "pyasn1" -version = "0.5.1" +version = "0.6.0" description = "Pure-Python implementation of ASN.1 types and DER/BER/CER codecs (X.208)" optional = false -python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,>=2.7" +python-versions = ">=3.8" files = [ - {file = "pyasn1-0.5.1-py2.py3-none-any.whl", hash = "sha256:4439847c58d40b1d0a573d07e3856e95333f1976294494c325775aeca506eb58"}, - {file = "pyasn1-0.5.1.tar.gz", hash = "sha256:6d391a96e59b23130a5cfa74d6fd7f388dbbe26cc8f1edf39fdddf08d9d6676c"}, + {file = "pyasn1-0.6.0-py2.py3-none-any.whl", hash = "sha256:cca4bb0f2df5504f02f6f8a775b6e416ff9b0b3b16f7ee80b5a3153d9b804473"}, + {file = "pyasn1-0.6.0.tar.gz", hash = "sha256:3a35ab2c4b5ef98e17dfdec8ab074046fbda76e281c5a706ccd82328cfc8f64c"}, ] [[package]] @@ -1914,12 +1903,12 @@ plugins = ["importlib-metadata"] [[package]] name = "pyicu" -version = "2.13" +version = "2.13.1" description = "Python extension wrapping the ICU C++ API" optional = true python-versions = "*" files = [ - {file = "PyICU-2.13.tar.gz", hash = "sha256:d481be888975df3097c2790241bbe8518f65c9676a74957cdbe790e559c828f6"}, + {file = "PyICU-2.13.1.tar.gz", hash = "sha256:d4919085eaa07da12bade8ee721e7bbf7ade0151ca0f82946a26c8f4b98cdceb"}, ] [[package]] @@ -1996,13 +1985,13 @@ tests = ["hypothesis (>=3.27.0)", "pytest (>=3.2.1,!=3.3.0)"] [[package]] name = "pyopenssl" -version = "24.0.0" +version = "24.1.0" description = "Python wrapper module around the OpenSSL library" optional = false python-versions = ">=3.7" files = [ - {file = "pyOpenSSL-24.0.0-py3-none-any.whl", hash = "sha256:ba07553fb6fd6a7a2259adb9b84e12302a9a8a75c44046e8bb5d3e5ee887e3c3"}, - {file = "pyOpenSSL-24.0.0.tar.gz", hash = "sha256:6aa33039a93fffa4563e655b61d11364d01264be8ccb49906101e02a334530bf"}, + {file = "pyOpenSSL-24.1.0-py3-none-any.whl", hash = "sha256:17ed5be5936449c5418d1cd269a1a9e9081bc54c17aed272b45856a3d3dc86ad"}, + {file = "pyOpenSSL-24.1.0.tar.gz", hash = "sha256:cabed4bfaa5df9f1a16c0ef64a0cb65318b5cd077a7eda7d6970131ca2f41a6f"}, ] [package.dependencies] @@ -2010,7 +1999,7 @@ cryptography = ">=41.0.5,<43" [package.extras] docs = ["sphinx (!=5.2.0,!=5.2.0.post0,!=7.2.5)", "sphinx-rtd-theme"] -test = ["flaky", "pretend", "pytest (>=3.0.1)"] +test = ["pretend", "pytest (>=3.0.1)", "pytest-rerunfailures"] [[package]] name = "pysaml2" @@ -2168,13 +2157,13 @@ rpds-py = ">=0.7.0" [[package]] name = "requests" -version = "2.31.0" +version = "2.32.2" description = "Python HTTP for Humans." optional = false -python-versions = ">=3.7" +python-versions = ">=3.8" files = [ - {file = "requests-2.31.0-py3-none-any.whl", hash = "sha256:58cd2187c01e70e6e26505bca751777aa9f2ee0b7f4300988b709f44e013003f"}, - {file = "requests-2.31.0.tar.gz", hash = "sha256:942c5a758f98d790eaed1a29cb6eefc7ffb0d1cf7af05c3d2791656dbd6ad1e1"}, + {file = "requests-2.32.2-py3-none-any.whl", hash = "sha256:fc06670dd0ed212426dfeb94fc1b983d917c4f9847c863f313c9dfaaffb7c23c"}, + {file = "requests-2.32.2.tar.gz", hash = "sha256:dd951ff5ecf3e3b3aa26b40703ba77495dab41da839ae72ef3c8e5d8e2433289"}, ] [package.dependencies] @@ -2398,36 +2387,41 @@ doc = ["Sphinx", "sphinx-rtd-theme"] [[package]] name = "sentry-sdk" -version = "1.40.3" +version = "2.6.0" description = "Python client for Sentry (https://sentry.io)" optional = true -python-versions = "*" +python-versions = ">=3.6" files = [ - {file = "sentry-sdk-1.40.3.tar.gz", hash = "sha256:3c2b027979bb400cd65a47970e64f8cef8acda86b288a27f42a98692505086cd"}, - {file = "sentry_sdk-1.40.3-py2.py3-none-any.whl", hash = "sha256:73383f28311ae55602bb6cc3b013830811135ba5521e41333a6e68f269413502"}, + {file = "sentry_sdk-2.6.0-py2.py3-none-any.whl", hash = "sha256:422b91cb49378b97e7e8d0e8d5a1069df23689d45262b86f54988a7db264e874"}, + {file = "sentry_sdk-2.6.0.tar.gz", hash = "sha256:65cc07e9c6995c5e316109f138570b32da3bd7ff8d0d0ee4aaf2628c3dd8127d"}, ] [package.dependencies] certifi = "*" -urllib3 = {version = ">=1.26.11", markers = "python_version >= \"3.6\""} +urllib3 = ">=1.26.11" [package.extras] aiohttp = ["aiohttp (>=3.5)"] +anthropic = ["anthropic (>=0.16)"] arq = ["arq (>=0.23)"] asyncpg = ["asyncpg (>=0.23)"] beam = ["apache-beam (>=2.12)"] bottle = ["bottle (>=0.12.13)"] celery = ["celery (>=3)"] +celery-redbeat = ["celery-redbeat (>=2)"] chalice = ["chalice (>=1.16.0)"] clickhouse-driver = ["clickhouse-driver (>=0.2.0)"] django = ["django (>=1.8)"] falcon = ["falcon (>=1.4)"] fastapi = ["fastapi (>=0.79.0)"] flask = ["blinker (>=1.1)", "flask (>=0.11)", "markupsafe"] -grpcio = ["grpcio (>=1.21.1)"] +grpcio = ["grpcio (>=1.21.1)", "protobuf (>=3.8.0)"] httpx = ["httpx (>=0.16.0)"] huey = ["huey (>=2)"] +huggingface-hub = ["huggingface-hub (>=0.22)"] +langchain = ["langchain (>=0.0.210)"] loguru = ["loguru (>=0.5)"] +openai = ["openai (>=1.0.0)", "tiktoken (>=0.3.0)"] opentelemetry = ["opentelemetry-distro (>=0.35b0)"] opentelemetry-experimental = ["opentelemetry-distro (>=0.40b0,<1.0)", "opentelemetry-instrumentation-aiohttp-client (>=0.40b0,<1.0)", "opentelemetry-instrumentation-django (>=0.40b0,<1.0)", "opentelemetry-instrumentation-fastapi (>=0.40b0,<1.0)", "opentelemetry-instrumentation-flask (>=0.40b0,<1.0)", "opentelemetry-instrumentation-requests (>=0.40b0,<1.0)", "opentelemetry-instrumentation-sqlite3 (>=0.40b0,<1.0)", "opentelemetry-instrumentation-urllib (>=0.40b0,<1.0)"] pure-eval = ["asttokens", "executing", "pure-eval"] @@ -2604,22 +2598,22 @@ files = [ [[package]] name = "tornado" -version = "6.4" +version = "6.4.1" description = "Tornado is a Python web framework and asynchronous networking library, originally developed at FriendFeed." optional = true -python-versions = ">= 3.8" +python-versions = ">=3.8" files = [ - {file = "tornado-6.4-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:02ccefc7d8211e5a7f9e8bc3f9e5b0ad6262ba2fbb683a6443ecc804e5224ce0"}, - {file = "tornado-6.4-cp38-abi3-macosx_10_9_x86_64.whl", hash = "sha256:27787de946a9cffd63ce5814c33f734c627a87072ec7eed71f7fc4417bb16263"}, - {file = "tornado-6.4-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f7894c581ecdcf91666a0912f18ce5e757213999e183ebfc2c3fdbf4d5bd764e"}, - {file = "tornado-6.4-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e43bc2e5370a6a8e413e1e1cd0c91bedc5bd62a74a532371042a18ef19e10579"}, - {file = "tornado-6.4-cp38-abi3-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f0251554cdd50b4b44362f73ad5ba7126fc5b2c2895cc62b14a1c2d7ea32f212"}, - {file = "tornado-6.4-cp38-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:fd03192e287fbd0899dd8f81c6fb9cbbc69194d2074b38f384cb6fa72b80e9c2"}, - {file = "tornado-6.4-cp38-abi3-musllinux_1_1_i686.whl", hash = "sha256:88b84956273fbd73420e6d4b8d5ccbe913c65d31351b4c004ae362eba06e1f78"}, - {file = "tornado-6.4-cp38-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:71ddfc23a0e03ef2df1c1397d859868d158c8276a0603b96cf86892bff58149f"}, - {file = "tornado-6.4-cp38-abi3-win32.whl", hash = "sha256:6f8a6c77900f5ae93d8b4ae1196472d0ccc2775cc1dfdc9e7727889145c45052"}, - {file = "tornado-6.4-cp38-abi3-win_amd64.whl", hash = "sha256:10aeaa8006333433da48dec9fe417877f8bcc21f48dda8d661ae79da357b2a63"}, - {file = "tornado-6.4.tar.gz", hash = "sha256:72291fa6e6bc84e626589f1c29d90a5a6d593ef5ae68052ee2ef000dfd273dee"}, + {file = "tornado-6.4.1-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:163b0aafc8e23d8cdc3c9dfb24c5368af84a81e3364745ccb4427669bf84aec8"}, + {file = "tornado-6.4.1-cp38-abi3-macosx_10_9_x86_64.whl", hash = "sha256:6d5ce3437e18a2b66fbadb183c1d3364fb03f2be71299e7d10dbeeb69f4b2a14"}, + {file = "tornado-6.4.1-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e2e20b9113cd7293f164dc46fffb13535266e713cdb87bd2d15ddb336e96cfc4"}, + {file = "tornado-6.4.1-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8ae50a504a740365267b2a8d1a90c9fbc86b780a39170feca9bcc1787ff80842"}, + {file = "tornado-6.4.1-cp38-abi3-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:613bf4ddf5c7a95509218b149b555621497a6cc0d46ac341b30bd9ec19eac7f3"}, + {file = "tornado-6.4.1-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:25486eb223babe3eed4b8aecbac33b37e3dd6d776bc730ca14e1bf93888b979f"}, + {file = "tornado-6.4.1-cp38-abi3-musllinux_1_2_i686.whl", hash = "sha256:454db8a7ecfcf2ff6042dde58404164d969b6f5d58b926da15e6b23817950fc4"}, + {file = "tornado-6.4.1-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:a02a08cc7a9314b006f653ce40483b9b3c12cda222d6a46d4ac63bb6c9057698"}, + {file = "tornado-6.4.1-cp38-abi3-win32.whl", hash = "sha256:d9a566c40b89757c9aa8e6f032bcdb8ca8795d7c1a9762910c722b1635c9de4d"}, + {file = "tornado-6.4.1-cp38-abi3-win_amd64.whl", hash = "sha256:b24b8982ed444378d7f21d563f4180a2de31ced9d8d84443907a0a64da2072e7"}, + {file = "tornado-6.4.1.tar.gz", hash = "sha256:92d3ab53183d8c50f8204a51e6f91d18a15d5ef261e84d452800d4ff6fc504e9"}, ] [[package]] @@ -2667,13 +2661,13 @@ docs = ["sphinx (<7.0.0)"] [[package]] name = "twine" -version = "5.0.0" +version = "5.1.0" description = "Collection of utilities for publishing packages on PyPI" optional = false python-versions = ">=3.8" files = [ - {file = "twine-5.0.0-py3-none-any.whl", hash = "sha256:a262933de0b484c53408f9edae2e7821c1c45a3314ff2df9bdd343aa7ab8edc0"}, - {file = "twine-5.0.0.tar.gz", hash = "sha256:89b0cc7d370a4b66421cc6102f269aa910fe0f1861c124f573cf2ddedbc10cf4"}, + {file = "twine-5.1.0-py3-none-any.whl", hash = "sha256:fe1d814395bfe50cfbe27783cb74efe93abeac3f66deaeb6c8390e4e92bacb43"}, + {file = "twine-5.1.0.tar.gz", hash = "sha256:4d74770c88c4fcaf8134d2a6a9d863e40f08255ff7d8e2acb3cbbd57d25f6e9d"}, ] [package.dependencies] @@ -2777,6 +2771,20 @@ files = [ types-html5lib = "*" [[package]] +name = "types-cffi" +version = "1.16.0.20240331" +description = "Typing stubs for cffi" +optional = false +python-versions = ">=3.8" +files = [ + {file = "types-cffi-1.16.0.20240331.tar.gz", hash = "sha256:b8b20d23a2b89cfed5f8c5bc53b0cb8677c3aac6d970dbc771e28b9c698f5dee"}, + {file = "types_cffi-1.16.0.20240331-py3-none-any.whl", hash = "sha256:a363e5ea54a4eb6a4a105d800685fde596bc318089b025b27dee09849fe41ff0"}, +] + +[package.dependencies] +types-setuptools = "*" + +[[package]] name = "types-commonmark" version = "0.9.2.20240106" description = "Typing stubs for commonmark" @@ -2800,13 +2808,13 @@ files = [ [[package]] name = "types-jsonschema" -version = "4.21.0.20240311" +version = "4.22.0.20240610" description = "Typing stubs for jsonschema" optional = false python-versions = ">=3.8" files = [ - {file = "types-jsonschema-4.21.0.20240311.tar.gz", hash = "sha256:f7165ce70abd91df490c73b089873afd2899c5e56430ee495b64f851ad01f287"}, - {file = "types_jsonschema-4.21.0.20240311-py3-none-any.whl", hash = "sha256:e872f5661513824edf9698f73a66c9c114713d93eab58699bd0532e7e6db5750"}, + {file = "types-jsonschema-4.22.0.20240610.tar.gz", hash = "sha256:f82ab9fe756e3a2642ea9712c46b403ce61eb380b939b696cff3252af42f65b0"}, + {file = "types_jsonschema-4.22.0.20240610-py3-none-any.whl", hash = "sha256:89996b9bd1928f820a0e252b2844be21cd2e55d062b6fa1048d88453006ad89e"}, ] [package.dependencies] @@ -2814,13 +2822,13 @@ referencing = "*" [[package]] name = "types-netaddr" -version = "1.2.0.20240219" +version = "1.3.0.20240530" description = "Typing stubs for netaddr" optional = false python-versions = ">=3.8" files = [ - {file = "types-netaddr-1.2.0.20240219.tar.gz", hash = "sha256:984e70ad838218d3032f37f05a7e294f7b007fe274ec9d774265c8c06698395f"}, - {file = "types_netaddr-1.2.0.20240219-py3-none-any.whl", hash = "sha256:b26144e878acb8a1a9008e6997863714db04f8029a0f7f6bfe483c977d21b522"}, + {file = "types-netaddr-1.3.0.20240530.tar.gz", hash = "sha256:742c2ec1f202b666f544223e2616b34f1f13df80c91e5aeaaa93a72e4d0774ea"}, + {file = "types_netaddr-1.3.0.20240530-py3-none-any.whl", hash = "sha256:354998d018e326da4f1d9b005fc91137b7c2c473aaf03c4ef64bf83c6861b440"}, ] [[package]] @@ -2836,49 +2844,50 @@ files = [ [[package]] name = "types-pillow" -version = "10.2.0.20240423" +version = "10.2.0.20240520" description = "Typing stubs for Pillow" optional = false python-versions = ">=3.8" files = [ - {file = "types-Pillow-10.2.0.20240423.tar.gz", hash = "sha256:696e68b9b6a58548fc307a8669830469237c5b11809ddf978ac77fafa79251cd"}, - {file = "types_Pillow-10.2.0.20240423-py3-none-any.whl", hash = "sha256:bd12923093b96c91d523efcdb66967a307f1a843bcfaf2d5a529146c10a9ced3"}, + {file = "types-Pillow-10.2.0.20240520.tar.gz", hash = "sha256:130b979195465fa1e1676d8e81c9c7c30319e8e95b12fae945e8f0d525213107"}, + {file = "types_Pillow-10.2.0.20240520-py3-none-any.whl", hash = "sha256:33c36494b380e2a269bb742181bea5d9b00820367822dbd3760f07210a1da23d"}, ] [[package]] name = "types-psycopg2" -version = "2.9.21.20240311" +version = "2.9.21.20240417" description = "Typing stubs for psycopg2" optional = false python-versions = ">=3.8" files = [ - {file = "types-psycopg2-2.9.21.20240311.tar.gz", hash = "sha256:722945dffa6a729bebc660f14137f37edfcead5a2c15eb234212a7d017ee8072"}, - {file = "types_psycopg2-2.9.21.20240311-py3-none-any.whl", hash = "sha256:2e137ae2b516ee0dbaab6f555086b6cfb723ba4389d67f551b0336adf4efcf1b"}, + {file = "types-psycopg2-2.9.21.20240417.tar.gz", hash = "sha256:05db256f4a459fb21a426b8e7fca0656c3539105ff0208eaf6bdaf406a387087"}, + {file = "types_psycopg2-2.9.21.20240417-py3-none-any.whl", hash = "sha256:644d6644d64ebbe37203229b00771012fb3b3bddd507a129a2e136485990e4f8"}, ] [[package]] name = "types-pyopenssl" -version = "24.0.0.20240311" +version = "24.1.0.20240425" description = "Typing stubs for pyOpenSSL" optional = false python-versions = ">=3.8" files = [ - {file = "types-pyOpenSSL-24.0.0.20240311.tar.gz", hash = "sha256:7bca00cfc4e7ef9c5d2663c6a1c068c35798e59670595439f6296e7ba3d58083"}, - {file = "types_pyOpenSSL-24.0.0.20240311-py3-none-any.whl", hash = "sha256:6e8e8bfad34924067333232c93f7fc4b369856d8bea0d5c9d1808cb290ab1972"}, + {file = "types-pyOpenSSL-24.1.0.20240425.tar.gz", hash = "sha256:0a7e82626c1983dc8dc59292bf20654a51c3c3881bcbb9b337c1da6e32f0204e"}, + {file = "types_pyOpenSSL-24.1.0.20240425-py3-none-any.whl", hash = "sha256:f51a156835555dd2a1f025621e8c4fbe7493470331afeef96884d1d29bf3a473"}, ] [package.dependencies] cryptography = ">=35.0.0" +types-cffi = "*" [[package]] name = "types-pyyaml" -version = "6.0.12.12" +version = "6.0.12.20240311" description = "Typing stubs for PyYAML" optional = false -python-versions = "*" +python-versions = ">=3.8" files = [ - {file = "types-PyYAML-6.0.12.12.tar.gz", hash = "sha256:334373d392fde0fdf95af5c3f1661885fa10c52167b14593eb856289e1855062"}, - {file = "types_PyYAML-6.0.12.12-py3-none-any.whl", hash = "sha256:c05bc6c158facb0676674b7f11fe3960db4f389718e19e62bd2b84d6205cfd24"}, + {file = "types-PyYAML-6.0.12.20240311.tar.gz", hash = "sha256:a9e0f0f88dc835739b0c1ca51ee90d04ca2a897a71af79de9aec5f38cb0a5342"}, + {file = "types_PyYAML-6.0.12.20240311-py3-none-any.whl", hash = "sha256:b845b06a1c7e54b8e5b4c683043de0d9caf205e7434b3edc678ff2411979b8f6"}, ] [[package]] @@ -2908,13 +2917,13 @@ files = [ [[package]] name = "typing-extensions" -version = "4.11.0" +version = "4.12.2" description = "Backported and Experimental Type Hints for Python 3.8+" optional = false python-versions = ">=3.8" files = [ - {file = "typing_extensions-4.11.0-py3-none-any.whl", hash = "sha256:c1f94d72897edaf4ce775bb7558d5b79d8126906a14ea5ed1635921406c0387a"}, - {file = "typing_extensions-4.11.0.tar.gz", hash = "sha256:83f085bd5ca59c80295fc2a82ab5dac679cbe02b9f33f7d83af68e241bea51b0"}, + {file = "typing_extensions-4.12.2-py3-none-any.whl", hash = "sha256:04e5ca0351e0f3f85c6853954072df659d0d13fac324d0072316b67d7794700d"}, + {file = "typing_extensions-4.12.2.tar.gz", hash = "sha256:1a7ead55c7e559dd4dee8856e3a88b41225abfe1ce8df57b7c13915fe121ffb8"}, ] [[package]] @@ -2930,18 +2939,18 @@ files = [ [[package]] name = "urllib3" -version = "2.0.7" +version = "2.2.2" description = "HTTP library with thread-safe connection pooling, file post, and more." optional = false -python-versions = ">=3.7" +python-versions = ">=3.8" files = [ - {file = "urllib3-2.0.7-py3-none-any.whl", hash = "sha256:fdb6d215c776278489906c2f8916e6e7d4f5a9b602ccbcfdf7f016fc8da0596e"}, - {file = "urllib3-2.0.7.tar.gz", hash = "sha256:c97dfde1f7bd43a71c8d2a58e369e9b2bf692d1334ea9f9cae55add7d0dd0f84"}, + {file = "urllib3-2.2.2-py3-none-any.whl", hash = "sha256:a448b2f64d686155468037e1ace9f2d2199776e17f0a46610480d311f73e3472"}, + {file = "urllib3-2.2.2.tar.gz", hash = "sha256:dd505485549a7a552833da5e6063639d0d177c04f23bc3864e41e5dc5f612168"}, ] [package.extras] brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)"] -secure = ["certifi", "cryptography (>=1.9)", "idna (>=2.0.0)", "pyopenssl (>=17.1.0)", "urllib3-secure-extra"] +h2 = ["h2 (>=4,<5)"] socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"] zstd = ["zstandard (>=0.18.0)"] @@ -3178,4 +3187,4 @@ user-search = ["pyicu"] [metadata] lock-version = "2.0" python-versions = "^3.8.0" -content-hash = "987f8eccaa222367b1a2e15b0d496586ca50d46ca1277e69694922d31c93ce5b" +content-hash = "107c8fb5c67360340854fbdba3c085fc5f9c7be24bcb592596a914eea621faea" diff --git a/pyproject.toml b/pyproject.toml index 48aac66f63..1485016a5a 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -96,7 +96,7 @@ module-name = "synapse.synapse_rust" [tool.poetry] name = "matrix-synapse" -version = "1.107.0rc1" +version = "1.109.0" description = "Homeserver for the Matrix decentralised comms protocol" authors = ["Matrix.org Team and Contributors <packages@matrix.org>"] license = "AGPL-3.0-or-later" @@ -200,10 +200,8 @@ netaddr = ">=0.7.18" # add a lower bound to the Jinja2 dependency. Jinja2 = ">=3.0" bleach = ">=1.4.3" -# We use `ParamSpec` and `Concatenate`, which were added in `typing-extensions` 3.10.0.0. -# Additionally we need https://github.com/python/typing/pull/817 to allow types to be -# generic over ParamSpecs. -typing-extensions = ">=3.10.0.1" +# We use `Self`, which were added in `typing-extensions` 4.0. +typing-extensions = ">=4.0" # We enforce that we have a `cryptography` version that bundles an `openssl` # with the latest security patches. cryptography = ">=3.4.7" diff --git a/rust/src/events/internal_metadata.rs b/rust/src/events/internal_metadata.rs index 63774fbd54..ad87825f16 100644 --- a/rust/src/events/internal_metadata.rs +++ b/rust/src/events/internal_metadata.rs @@ -204,6 +204,8 @@ pub struct EventInternalMetadata { /// The stream ordering of this event. None, until it has been persisted. #[pyo3(get, set)] stream_ordering: Option<NonZeroI64>, + #[pyo3(get, set)] + instance_name: Option<String>, /// whether this event is an outlier (ie, whether we have the state at that /// point in the DAG) @@ -232,6 +234,7 @@ impl EventInternalMetadata { Ok(EventInternalMetadata { data, stream_ordering: None, + instance_name: None, outlier: false, }) } diff --git a/scripts-dev/complement.sh b/scripts-dev/complement.sh index b306b80749..4ad547bc7e 100755 --- a/scripts-dev/complement.sh +++ b/scripts-dev/complement.sh @@ -223,7 +223,6 @@ test_packages=( ./tests/msc3930 ./tests/msc3902 ./tests/msc3967 - ./tests/msc4115 ) # Enable dirty runs, so tests will reuse the same container where possible. diff --git a/synapse/_scripts/register_new_matrix_user.py b/synapse/_scripts/register_new_matrix_user.py index 77a7129ee2..14cb21c7fb 100644 --- a/synapse/_scripts/register_new_matrix_user.py +++ b/synapse/_scripts/register_new_matrix_user.py @@ -52,6 +52,7 @@ def request_registration( user_type: Optional[str] = None, _print: Callable[[str], None] = print, exit: Callable[[int], None] = sys.exit, + exists_ok: bool = False, ) -> None: url = "%s/_synapse/admin/v1/register" % (server_location.rstrip("/"),) @@ -97,6 +98,10 @@ def request_registration( r = requests.post(url, json=data) if r.status_code != 200: + response = r.json() + if exists_ok and response["errcode"] == "M_USER_IN_USE": + _print("User already exists. Skipping.") + return _print("ERROR! Received %d %s" % (r.status_code, r.reason)) if 400 <= r.status_code < 500: try: @@ -115,6 +120,7 @@ def register_new_user( shared_secret: str, admin: Optional[bool], user_type: Optional[str], + exists_ok: bool = False, ) -> None: if not user: try: @@ -154,7 +160,13 @@ def register_new_user( admin = False request_registration( - user, password, server_location, shared_secret, bool(admin), user_type + user, + password, + server_location, + shared_secret, + bool(admin), + user_type, + exists_ok=exists_ok, ) @@ -174,10 +186,22 @@ def main() -> None: help="Local part of the new user. Will prompt if omitted.", ) parser.add_argument( + "--exists-ok", + action="store_true", + help="Do not fail if user already exists.", + ) + password_group = parser.add_mutually_exclusive_group() + password_group.add_argument( "-p", "--password", default=None, - help="New password for user. Will prompt if omitted.", + help="New password for user. Will prompt for a password if " + "this flag and `--password-file` are both omitted.", + ) + password_group.add_argument( + "--password-file", + default=None, + help="File containing the new password for user. If set, will override `--password`.", ) parser.add_argument( "-t", @@ -185,6 +209,7 @@ def main() -> None: default=None, help="User type as specified in synapse.api.constants.UserTypes", ) + admin_group = parser.add_mutually_exclusive_group() admin_group.add_argument( "-a", @@ -247,6 +272,11 @@ def main() -> None: print(_NO_SHARED_SECRET_OPTS_ERROR, file=sys.stderr) sys.exit(1) + if args.password_file: + password = _read_file(args.password_file, "password-file").strip() + else: + password = args.password + if args.server_url: server_url = args.server_url elif config is not None: @@ -270,7 +300,13 @@ def main() -> None: admin = args.admin register_new_user( - args.user, args.password, server_url, secret, admin, args.user_type + args.user, + password, + server_url, + secret, + admin, + args.user_type, + exists_ok=args.exists_ok, ) diff --git a/synapse/_scripts/synapse_port_db.py b/synapse/_scripts/synapse_port_db.py index 1e56f46911..3bb4a34938 100755 --- a/synapse/_scripts/synapse_port_db.py +++ b/synapse/_scripts/synapse_port_db.py @@ -777,22 +777,74 @@ class Porter: await self._setup_events_stream_seqs() await self._setup_sequence( "un_partial_stated_event_stream_sequence", - ("un_partial_stated_event_stream",), + [("un_partial_stated_event_stream", "stream_id")], ) await self._setup_sequence( - "device_inbox_sequence", ("device_inbox", "device_federation_outbox") + "device_inbox_sequence", + [ + ("device_inbox", "stream_id"), + ("device_federation_outbox", "stream_id"), + ], ) await self._setup_sequence( "account_data_sequence", - ("room_account_data", "room_tags_revisions", "account_data"), + [ + ("room_account_data", "stream_id"), + ("room_tags_revisions", "stream_id"), + ("account_data", "stream_id"), + ], + ) + await self._setup_sequence( + "receipts_sequence", + [ + ("receipts_linearized", "stream_id"), + ], + ) + await self._setup_sequence( + "presence_stream_sequence", + [ + ("presence_stream", "stream_id"), + ], ) - await self._setup_sequence("receipts_sequence", ("receipts_linearized",)) - await self._setup_sequence("presence_stream_sequence", ("presence_stream",)) await self._setup_auth_chain_sequence() await self._setup_sequence( "application_services_txn_id_seq", - ("application_services_txns",), - "txn_id", + [ + ( + "application_services_txns", + "txn_id", + ) + ], + ) + await self._setup_sequence( + "device_lists_sequence", + [ + ("device_lists_stream", "stream_id"), + ("user_signature_stream", "stream_id"), + ("device_lists_outbound_pokes", "stream_id"), + ("device_lists_changes_in_room", "stream_id"), + ("device_lists_remote_pending", "stream_id"), + ("device_lists_changes_converted_stream_position", "stream_id"), + ], + ) + await self._setup_sequence( + "e2e_cross_signing_keys_sequence", + [ + ("e2e_cross_signing_keys", "stream_id"), + ], + ) + await self._setup_sequence( + "push_rules_stream_sequence", + [ + ("push_rules_stream", "stream_id"), + ], + ) + await self._setup_sequence( + "pushers_sequence", + [ + ("pushers", "id"), + ("deleted_pushers", "stream_id"), + ], ) # Step 3. Get tables. @@ -1101,12 +1153,11 @@ class Porter: async def _setup_sequence( self, sequence_name: str, - stream_id_tables: Iterable[str], - column_name: str = "stream_id", + stream_id_tables: Iterable[Tuple[str, str]], ) -> None: """Set a sequence to the correct value.""" current_stream_ids = [] - for stream_id_table in stream_id_tables: + for stream_id_table, column_name in stream_id_tables: max_stream_id = cast( int, await self.sqlite_store.db_pool.simple_select_one_onecol( diff --git a/synapse/api/constants.py b/synapse/api/constants.py index 0a9123c56b..9265a271d2 100644 --- a/synapse/api/constants.py +++ b/synapse/api/constants.py @@ -50,7 +50,7 @@ class Membership: KNOCK: Final = "knock" LEAVE: Final = "leave" BAN: Final = "ban" - LIST: Final = (INVITE, JOIN, KNOCK, LEAVE, BAN) + LIST: Final = {INVITE, JOIN, KNOCK, LEAVE, BAN} class PresenceState: @@ -238,7 +238,7 @@ class EventUnsignedContentFields: """Fields found inside the 'unsigned' data on events""" # Requesting user's membership, per MSC4115 - MSC4115_MEMBERSHIP: Final = "io.element.msc4115.membership" + MEMBERSHIP: Final = "membership" class RoomTypes: diff --git a/synapse/api/ratelimiting.py b/synapse/api/ratelimiting.py index a73626bc86..a99a9e09fc 100644 --- a/synapse/api/ratelimiting.py +++ b/synapse/api/ratelimiting.py @@ -316,6 +316,10 @@ class Ratelimiter: ) if not allowed: + # We pause for a bit here to stop clients from "tight-looping" on + # retrying their request. + await self.clock.sleep(0.5) + raise LimitExceededError( limiter_name=self._limiter_name, retry_after_ms=int(1000 * (time_allowed - time_now_s)), diff --git a/synapse/app/_base.py b/synapse/app/_base.py index 3182608f73..4cc260d551 100644 --- a/synapse/app/_base.py +++ b/synapse/app/_base.py @@ -68,6 +68,7 @@ from synapse.config._base import format_config_error from synapse.config.homeserver import HomeServerConfig from synapse.config.server import ListenerConfig, ManholeConfig, TCPListenerConfig from synapse.crypto import context_factory +from synapse.events.auto_accept_invites import InviteAutoAccepter from synapse.events.presence_router import load_legacy_presence_router from synapse.handlers.auth import load_legacy_password_auth_providers from synapse.http.site import SynapseSite @@ -582,6 +583,11 @@ async def start(hs: "HomeServer") -> None: m = module(config, module_api) logger.info("Loaded module %s", m) + if hs.config.auto_accept_invites.enabled: + # Start the local auto_accept_invites module. + m = InviteAutoAccepter(hs.config.auto_accept_invites, module_api) + logger.info("Loaded local module %s", m) + load_legacy_spam_checkers(hs) load_legacy_third_party_event_rules(hs) load_legacy_presence_router(hs) @@ -675,17 +681,17 @@ def setup_sentry(hs: "HomeServer") -> None: ) # We set some default tags that give some context to this instance - with sentry_sdk.configure_scope() as scope: - scope.set_tag("matrix_server_name", hs.config.server.server_name) + global_scope = sentry_sdk.Scope.get_global_scope() + global_scope.set_tag("matrix_server_name", hs.config.server.server_name) - app = ( - hs.config.worker.worker_app - if hs.config.worker.worker_app - else "synapse.app.homeserver" - ) - name = hs.get_instance_name() - scope.set_tag("worker_app", app) - scope.set_tag("worker_name", name) + app = ( + hs.config.worker.worker_app + if hs.config.worker.worker_app + else "synapse.app.homeserver" + ) + name = hs.get_instance_name() + global_scope.set_tag("worker_app", app) + global_scope.set_tag("worker_name", name) def setup_sdnotify(hs: "HomeServer") -> None: diff --git a/synapse/config/_base.pyi b/synapse/config/_base.pyi index fc51aed234..d9cb0da38b 100644 --- a/synapse/config/_base.pyi +++ b/synapse/config/_base.pyi @@ -23,6 +23,7 @@ from synapse.config import ( # noqa: F401 api, appservice, auth, + auto_accept_invites, background_updates, cache, captcha, @@ -120,6 +121,7 @@ class RootConfig: federation: federation.FederationConfig retention: retention.RetentionConfig background_updates: background_updates.BackgroundUpdateConfig + auto_accept_invites: auto_accept_invites.AutoAcceptInvitesConfig config_classes: List[Type["Config"]] = ... config_files: List[str] diff --git a/synapse/config/auto_accept_invites.py b/synapse/config/auto_accept_invites.py new file mode 100644 index 0000000000..d90e13a510 --- /dev/null +++ b/synapse/config/auto_accept_invites.py @@ -0,0 +1,43 @@ +# +# This file is licensed under the Affero General Public License (AGPL) version 3. +# +# Copyright (C) 2024 New Vector, Ltd +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as +# published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# See the GNU Affero General Public License for more details: +# <https://www.gnu.org/licenses/agpl-3.0.html>. +# +# Originally licensed under the Apache License, Version 2.0: +# <http://www.apache.org/licenses/LICENSE-2.0>. +# +# [This file includes modifications made by New Vector Limited] +# +# +from typing import Any + +from synapse.types import JsonDict + +from ._base import Config + + +class AutoAcceptInvitesConfig(Config): + section = "auto_accept_invites" + + def read_config(self, config: JsonDict, **kwargs: Any) -> None: + auto_accept_invites_config = config.get("auto_accept_invites") or {} + + self.enabled = auto_accept_invites_config.get("enabled", False) + + self.accept_invites_only_for_direct_messages = auto_accept_invites_config.get( + "only_for_direct_messages", False + ) + + self.accept_invites_only_from_local_users = auto_accept_invites_config.get( + "only_from_local_users", False + ) + + self.worker_to_run_on = auto_accept_invites_config.get("worker_to_run_on") diff --git a/synapse/config/cas.py b/synapse/config/cas.py index d23dcf96b2..fa59c350c1 100644 --- a/synapse/config/cas.py +++ b/synapse/config/cas.py @@ -66,6 +66,17 @@ class CasConfig(Config): self.cas_enable_registration = cas_config.get("enable_registration", True) + self.cas_allow_numeric_ids = cas_config.get("allow_numeric_ids") + self.cas_numeric_ids_prefix = cas_config.get("numeric_ids_prefix") + if ( + self.cas_numeric_ids_prefix is not None + and self.cas_numeric_ids_prefix.isalnum() is False + ): + raise ConfigError( + "Only alphanumeric characters are allowed for numeric IDs prefix", + ("cas_config", "numeric_ids_prefix"), + ) + self.idp_name = cas_config.get("idp_name", "CAS") self.idp_icon = cas_config.get("idp_icon") self.idp_brand = cas_config.get("idp_brand") @@ -77,6 +88,8 @@ class CasConfig(Config): self.cas_displayname_attribute = None self.cas_required_attributes = [] self.cas_enable_registration = False + self.cas_allow_numeric_ids = False + self.cas_numeric_ids_prefix = "u" # CAS uses a legacy required attributes mapping, not the one provided by diff --git a/synapse/config/experimental.py b/synapse/config/experimental.py index 749452ce93..1b72727b75 100644 --- a/synapse/config/experimental.py +++ b/synapse/config/experimental.py @@ -332,6 +332,9 @@ class ExperimentalConfig(Config): # MSC3391: Removing account data. self.msc3391_enabled = experimental.get("msc3391_enabled", False) + # MSC3575 (Sliding Sync API endpoints) + self.msc3575_enabled: bool = experimental.get("msc3575_enabled", False) + # MSC3773: Thread notifications self.msc3773_enabled: bool = experimental.get("msc3773_enabled", False) @@ -390,9 +393,6 @@ class ExperimentalConfig(Config): # MSC3391: Removing account data. self.msc3391_enabled = experimental.get("msc3391_enabled", False) - # MSC3967: Do not require UIA when first uploading cross signing keys - self.msc3967_enabled = experimental.get("msc3967_enabled", False) - # MSC3861: Matrix architecture change to delegate authentication via OIDC try: self.msc3861 = MSC3861(**experimental.get("msc3861", {})) @@ -433,6 +433,16 @@ class ExperimentalConfig(Config): ("experimental", "msc4108_delegation_endpoint"), ) - self.msc4115_membership_on_events = experimental.get( - "msc4115_membership_on_events", False + self.msc3823_account_suspension = experimental.get( + "msc3823_account_suspension", False + ) + + self.msc3916_authenticated_media_enabled = experimental.get( + "msc3916_authenticated_media_enabled", False ) + + # MSC4151: Report room API (Client-Server API) + self.msc4151_enabled: bool = experimental.get("msc4151_enabled", False) + + # MSC4156: Migrate server_name to via + self.msc4156_enabled: bool = experimental.get("msc4156_enabled", False) diff --git a/synapse/config/federation.py b/synapse/config/federation.py index 9032effac3..cf29fa2562 100644 --- a/synapse/config/federation.py +++ b/synapse/config/federation.py @@ -42,6 +42,10 @@ class FederationConfig(Config): for domain in federation_domain_whitelist: self.federation_domain_whitelist[domain] = True + self.federation_whitelist_endpoint_enabled = config.get( + "federation_whitelist_endpoint_enabled", False + ) + federation_metrics_domains = config.get("federation_metrics_domains") or [] validate_config( _METRICS_FOR_DOMAINS_SCHEMA, diff --git a/synapse/config/homeserver.py b/synapse/config/homeserver.py index 72e93ed04f..e36c0bd6ae 100644 --- a/synapse/config/homeserver.py +++ b/synapse/config/homeserver.py @@ -23,6 +23,7 @@ from .account_validity import AccountValidityConfig from .api import ApiConfig from .appservice import AppServiceConfig from .auth import AuthConfig +from .auto_accept_invites import AutoAcceptInvitesConfig from .background_updates import BackgroundUpdateConfig from .cache import CacheConfig from .captcha import CaptchaConfig @@ -105,4 +106,5 @@ class HomeServerConfig(RootConfig): RedisConfig, ExperimentalConfig, BackgroundUpdateConfig, + AutoAcceptInvitesConfig, ] diff --git a/synapse/config/ratelimiting.py b/synapse/config/ratelimiting.py index d2cb4576df..3fa33f5373 100644 --- a/synapse/config/ratelimiting.py +++ b/synapse/config/ratelimiting.py @@ -218,3 +218,13 @@ class RatelimitConfig(Config): "rc_media_create", defaults={"per_second": 10, "burst_count": 50}, ) + + self.remote_media_downloads = RatelimitSettings( + key="rc_remote_media_downloads", + per_second=self.parse_size( + config.get("remote_media_download_per_second", "87K") + ), + burst_count=self.parse_size( + config.get("remote_media_download_burst_count", "500M") + ), + ) diff --git a/synapse/events/auto_accept_invites.py b/synapse/events/auto_accept_invites.py new file mode 100644 index 0000000000..d88ec51d9d --- /dev/null +++ b/synapse/events/auto_accept_invites.py @@ -0,0 +1,196 @@ +# +# This file is licensed under the Affero General Public License (AGPL) version 3. +# +# Copyright 2021 The Matrix.org Foundation C.I.C +# Copyright (C) 2024 New Vector, Ltd +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as +# published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# See the GNU Affero General Public License for more details: +# <https://www.gnu.org/licenses/agpl-3.0.html>. +# +# Originally licensed under the Apache License, Version 2.0: +# <http://www.apache.org/licenses/LICENSE-2.0>. +# +# [This file includes modifications made by New Vector Limited] +# +# +import logging +from http import HTTPStatus +from typing import Any, Dict, Tuple + +from synapse.api.constants import AccountDataTypes, EventTypes, Membership +from synapse.api.errors import SynapseError +from synapse.config.auto_accept_invites import AutoAcceptInvitesConfig +from synapse.module_api import EventBase, ModuleApi, run_as_background_process + +logger = logging.getLogger(__name__) + + +class InviteAutoAccepter: + def __init__(self, config: AutoAcceptInvitesConfig, api: ModuleApi): + # Keep a reference to the Module API. + self._api = api + self._config = config + + if not self._config.enabled: + return + + should_run_on_this_worker = config.worker_to_run_on == self._api.worker_name + + if not should_run_on_this_worker: + logger.info( + "Not accepting invites on this worker (configured: %r, here: %r)", + config.worker_to_run_on, + self._api.worker_name, + ) + return + + logger.info( + "Accepting invites on this worker (here: %r)", self._api.worker_name + ) + + # Register the callback. + self._api.register_third_party_rules_callbacks( + on_new_event=self.on_new_event, + ) + + async def on_new_event(self, event: EventBase, *args: Any) -> None: + """Listens for new events, and if the event is an invite for a local user then + automatically accepts it. + + Args: + event: The incoming event. + """ + # Check if the event is an invite for a local user. + is_invite_for_local_user = ( + event.type == EventTypes.Member + and event.is_state() + and event.membership == Membership.INVITE + and self._api.is_mine(event.state_key) + ) + + # Only accept invites for direct messages if the configuration mandates it. + is_direct_message = event.content.get("is_direct", False) + is_allowed_by_direct_message_rules = ( + not self._config.accept_invites_only_for_direct_messages + or is_direct_message is True + ) + + # Only accept invites from remote users if the configuration mandates it. + is_from_local_user = self._api.is_mine(event.sender) + is_allowed_by_local_user_rules = ( + not self._config.accept_invites_only_from_local_users + or is_from_local_user is True + ) + + if ( + is_invite_for_local_user + and is_allowed_by_direct_message_rules + and is_allowed_by_local_user_rules + ): + # Make the user join the room. We run this as a background process to circumvent a race condition + # that occurs when responding to invites over federation (see https://github.com/matrix-org/synapse-auto-accept-invite/issues/12) + run_as_background_process( + "retry_make_join", + self._retry_make_join, + event.state_key, + event.state_key, + event.room_id, + "join", + bg_start_span=False, + ) + + if is_direct_message: + # Mark this room as a direct message! + await self._mark_room_as_direct_message( + event.state_key, event.sender, event.room_id + ) + + async def _mark_room_as_direct_message( + self, user_id: str, dm_user_id: str, room_id: str + ) -> None: + """ + Marks a room (`room_id`) as a direct message with the counterparty `dm_user_id` + from the perspective of the user `user_id`. + + Args: + user_id: the user for whom the membership is changing + dm_user_id: the user performing the membership change + room_id: room id of the room the user is invited to + """ + + # This is a dict of User IDs to tuples of Room IDs + # (get_global will return a frozendict of tuples as it freezes the data, + # but we should accept either frozen or unfrozen variants.) + # Be careful: we convert the outer frozendict into a dict here, + # but the contents of the dict are still frozen (tuples in lieu of lists, + # etc.) + dm_map: Dict[str, Tuple[str, ...]] = dict( + await self._api.account_data_manager.get_global( + user_id, AccountDataTypes.DIRECT + ) + or {} + ) + + if dm_user_id not in dm_map: + dm_map[dm_user_id] = (room_id,) + else: + dm_rooms_for_user = dm_map[dm_user_id] + assert isinstance(dm_rooms_for_user, (tuple, list)) + + dm_map[dm_user_id] = tuple(dm_rooms_for_user) + (room_id,) + + await self._api.account_data_manager.put_global( + user_id, AccountDataTypes.DIRECT, dm_map + ) + + async def _retry_make_join( + self, sender: str, target: str, room_id: str, new_membership: str + ) -> None: + """ + A function to retry sending the `make_join` request with an increasing backoff. This is + implemented to work around a race condition when receiving invites over federation. + + Args: + sender: the user performing the membership change + target: the user for whom the membership is changing + room_id: room id of the room to join to + new_membership: the type of membership event (in this case will be "join") + """ + + sleep = 0 + retries = 0 + join_event = None + + while retries < 5: + try: + await self._api.sleep(sleep) + join_event = await self._api.update_room_membership( + sender=sender, + target=target, + room_id=room_id, + new_membership=new_membership, + ) + except SynapseError as e: + if e.code == HTTPStatus.FORBIDDEN: + logger.debug( + f"Update_room_membership was forbidden. This can sometimes be expected for remote invites. Exception: {e}" + ) + else: + logger.warn( + f"Update_room_membership raised the following unexpected (SynapseError) exception: {e}" + ) + except Exception as e: + logger.warn( + f"Update_room_membership raised the following unexpected exception: {e}" + ) + + sleep = 2**retries + retries += 1 + + if join_event is not None: + break diff --git a/synapse/events/utils.py b/synapse/events/utils.py index 0772472312..b997d82d71 100644 --- a/synapse/events/utils.py +++ b/synapse/events/utils.py @@ -90,6 +90,7 @@ def prune_event(event: EventBase) -> EventBase: pruned_event.internal_metadata.stream_ordering = ( event.internal_metadata.stream_ordering ) + pruned_event.internal_metadata.instance_name = event.internal_metadata.instance_name pruned_event.internal_metadata.outlier = event.internal_metadata.outlier # Mark the event as redacted @@ -116,6 +117,7 @@ def clone_event(event: EventBase) -> EventBase: new_event.internal_metadata.stream_ordering = ( event.internal_metadata.stream_ordering ) + new_event.internal_metadata.instance_name = event.internal_metadata.instance_name new_event.internal_metadata.outlier = event.internal_metadata.outlier return new_event diff --git a/synapse/events/validator.py b/synapse/events/validator.py index 62f0b67dbd..73b63b77f2 100644 --- a/synapse/events/validator.py +++ b/synapse/events/validator.py @@ -47,9 +47,9 @@ from synapse.events.utils import ( validate_canonicaljson, ) from synapse.http.servlet import validate_json_object -from synapse.rest.models import RequestBodyModel from synapse.storage.controllers.state import server_acl_evaluator_from_event from synapse.types import EventID, JsonDict, RoomID, StrCollection, UserID +from synapse.types.rest import RequestBodyModel class EventValidator: diff --git a/synapse/federation/federation_client.py b/synapse/federation/federation_client.py index e613eb87a6..f0f5a37a57 100644 --- a/synapse/federation/federation_client.py +++ b/synapse/federation/federation_client.py @@ -56,6 +56,7 @@ from synapse.api.errors import ( SynapseError, UnsupportedRoomVersionError, ) +from synapse.api.ratelimiting import Ratelimiter from synapse.api.room_versions import ( KNOWN_ROOM_VERSIONS, EventFormatVersions, @@ -1877,6 +1878,8 @@ class FederationClient(FederationBase): output_stream: BinaryIO, max_size: int, max_timeout_ms: int, + download_ratelimiter: Ratelimiter, + ip_address: str, ) -> Tuple[int, Dict[bytes, List[bytes]]]: try: return await self.transport_layer.download_media_v3( @@ -1885,6 +1888,8 @@ class FederationClient(FederationBase): output_stream=output_stream, max_size=max_size, max_timeout_ms=max_timeout_ms, + download_ratelimiter=download_ratelimiter, + ip_address=ip_address, ) except HttpResponseException as e: # If an error is received that is due to an unrecognised endpoint, @@ -1905,6 +1910,8 @@ class FederationClient(FederationBase): output_stream=output_stream, max_size=max_size, max_timeout_ms=max_timeout_ms, + download_ratelimiter=download_ratelimiter, + ip_address=ip_address, ) diff --git a/synapse/federation/federation_server.py b/synapse/federation/federation_server.py index 7ffc650aa1..1932fa82a4 100644 --- a/synapse/federation/federation_server.py +++ b/synapse/federation/federation_server.py @@ -674,7 +674,7 @@ class FederationServer(FederationBase): # This is in addition to the HS-level rate limiting applied by # BaseFederationServlet. # type-ignore: mypy doesn't seem able to deduce the type of the limiter(!?) - await self._room_member_handler._join_rate_per_room_limiter.ratelimit( # type: ignore[has-type] + await self._room_member_handler._join_rate_per_room_limiter.ratelimit( requester=None, key=room_id, update=False, @@ -717,7 +717,7 @@ class FederationServer(FederationBase): SynapseTags.SEND_JOIN_RESPONSE_IS_PARTIAL_STATE, caller_supports_partial_state, ) - await self._room_member_handler._join_rate_per_room_limiter.ratelimit( # type: ignore[has-type] + await self._room_member_handler._join_rate_per_room_limiter.ratelimit( requester=None, key=room_id, update=False, diff --git a/synapse/federation/transport/client.py b/synapse/federation/transport/client.py index de408f7f8d..af1336fe5f 100644 --- a/synapse/federation/transport/client.py +++ b/synapse/federation/transport/client.py @@ -43,6 +43,7 @@ import ijson from synapse.api.constants import Direction, Membership from synapse.api.errors import Codes, HttpResponseException, SynapseError +from synapse.api.ratelimiting import Ratelimiter from synapse.api.room_versions import RoomVersion from synapse.api.urls import ( FEDERATION_UNSTABLE_PREFIX, @@ -819,6 +820,8 @@ class TransportLayerClient: output_stream: BinaryIO, max_size: int, max_timeout_ms: int, + download_ratelimiter: Ratelimiter, + ip_address: str, ) -> Tuple[int, Dict[bytes, List[bytes]]]: path = f"/_matrix/media/r0/download/{destination}/{media_id}" @@ -834,6 +837,8 @@ class TransportLayerClient: "allow_remote": "false", "timeout_ms": str(max_timeout_ms), }, + download_ratelimiter=download_ratelimiter, + ip_address=ip_address, ) async def download_media_v3( @@ -843,6 +848,8 @@ class TransportLayerClient: output_stream: BinaryIO, max_size: int, max_timeout_ms: int, + download_ratelimiter: Ratelimiter, + ip_address: str, ) -> Tuple[int, Dict[bytes, List[bytes]]]: path = f"/_matrix/media/v3/download/{destination}/{media_id}" @@ -862,6 +869,8 @@ class TransportLayerClient: "allow_redirect": "true", }, follow_redirects=True, + download_ratelimiter=download_ratelimiter, + ip_address=ip_address, ) diff --git a/synapse/federation/transport/server/__init__.py b/synapse/federation/transport/server/__init__.py index bac569e977..edaf0196d6 100644 --- a/synapse/federation/transport/server/__init__.py +++ b/synapse/federation/transport/server/__init__.py @@ -33,6 +33,7 @@ from synapse.federation.transport.server.federation import ( FEDERATION_SERVLET_CLASSES, FederationAccountStatusServlet, FederationUnstableClientKeysClaimServlet, + FederationUnstableMediaDownloadServlet, ) from synapse.http.server import HttpServer, JsonResource from synapse.http.servlet import ( @@ -315,6 +316,13 @@ def register_servlets( ): continue + if servletclass == FederationUnstableMediaDownloadServlet: + if ( + not hs.config.server.enable_media_repo + or not hs.config.experimental.msc3916_authenticated_media_enabled + ): + continue + servletclass( hs=hs, authenticator=authenticator, diff --git a/synapse/federation/transport/server/_base.py b/synapse/federation/transport/server/_base.py index db0f5076a9..4e2717b565 100644 --- a/synapse/federation/transport/server/_base.py +++ b/synapse/federation/transport/server/_base.py @@ -360,13 +360,29 @@ class BaseFederationServlet: "request" ) return None + if ( + func.__self__.__class__.__name__ # type: ignore + == "FederationUnstableMediaDownloadServlet" + ): + response = await func( + origin, content, request, *args, **kwargs + ) + else: + response = await func( + origin, content, request.args, *args, **kwargs + ) + else: + if ( + func.__self__.__class__.__name__ # type: ignore + == "FederationUnstableMediaDownloadServlet" + ): + response = await func( + origin, content, request, *args, **kwargs + ) + else: response = await func( origin, content, request.args, *args, **kwargs ) - else: - response = await func( - origin, content, request.args, *args, **kwargs - ) finally: # if we used the origin's context as the parent, add a new span using # the servlet span as a parent, so that we have a link diff --git a/synapse/federation/transport/server/federation.py b/synapse/federation/transport/server/federation.py index a59734785f..67bb907050 100644 --- a/synapse/federation/transport/server/federation.py +++ b/synapse/federation/transport/server/federation.py @@ -44,10 +44,13 @@ from synapse.federation.transport.server._base import ( ) from synapse.http.servlet import ( parse_boolean_from_args, + parse_integer, parse_integer_from_args, parse_string_from_args, parse_strings_from_args, ) +from synapse.http.site import SynapseRequest +from synapse.media._base import DEFAULT_MAX_TIMEOUT_MS, MAXIMUM_ALLOWED_MAX_TIMEOUT_MS from synapse.types import JsonDict from synapse.util import SYNAPSE_VERSION from synapse.util.ratelimitutils import FederationRateLimiter @@ -787,6 +790,43 @@ class FederationAccountStatusServlet(BaseFederationServerServlet): return 200, {"account_statuses": statuses, "failures": failures} +class FederationUnstableMediaDownloadServlet(BaseFederationServerServlet): + """ + Implementation of new federation media `/download` endpoint outlined in MSC3916. Returns + a multipart/mixed response consisting of a JSON object and the requested media + item. This endpoint only returns local media. + """ + + PATH = "/media/download/(?P<media_id>[^/]*)" + PREFIX = FEDERATION_UNSTABLE_PREFIX + "/org.matrix.msc3916" + RATELIMIT = True + + def __init__( + self, + hs: "HomeServer", + ratelimiter: FederationRateLimiter, + authenticator: Authenticator, + server_name: str, + ): + super().__init__(hs, authenticator, ratelimiter, server_name) + self.media_repo = self.hs.get_media_repository() + + async def on_GET( + self, + origin: Optional[str], + content: Literal[None], + request: SynapseRequest, + media_id: str, + ) -> None: + max_timeout_ms = parse_integer( + request, "timeout_ms", default=DEFAULT_MAX_TIMEOUT_MS + ) + max_timeout_ms = min(max_timeout_ms, MAXIMUM_ALLOWED_MAX_TIMEOUT_MS) + await self.media_repo.get_local_media( + request, media_id, None, max_timeout_ms, federation=True + ) + + FEDERATION_SERVLET_CLASSES: Tuple[Type[BaseFederationServlet], ...] = ( FederationSendServlet, FederationEventServlet, @@ -818,4 +858,5 @@ FEDERATION_SERVLET_CLASSES: Tuple[Type[BaseFederationServlet], ...] = ( FederationV1SendKnockServlet, FederationMakeKnockServlet, FederationAccountStatusServlet, + FederationUnstableMediaDownloadServlet, ) diff --git a/synapse/handlers/admin.py b/synapse/handlers/admin.py index 702d40332c..ec35784c5f 100644 --- a/synapse/handlers/admin.py +++ b/synapse/handlers/admin.py @@ -42,7 +42,6 @@ class AdminHandler: self._device_handler = hs.get_device_handler() self._storage_controllers = hs.get_storage_controllers() self._state_storage_controller = self._storage_controllers.state - self._hs_config = hs.config self._msc3866_enabled = hs.config.experimental.msc3866.enabled async def get_whois(self, user: UserID) -> JsonMapping: @@ -126,13 +125,7 @@ class AdminHandler: # Get all rooms the user is in or has been in rooms = await self._store.get_rooms_for_local_user_where_membership_is( user_id, - membership_list=( - Membership.JOIN, - Membership.LEAVE, - Membership.BAN, - Membership.INVITE, - Membership.KNOCK, - ), + membership_list=Membership.LIST, ) # We only try and fetch events for rooms the user has been in. If @@ -179,7 +172,7 @@ class AdminHandler: if room.membership == Membership.JOIN: stream_ordering = self._store.get_room_max_stream_ordering() else: - stream_ordering = room.stream_ordering + stream_ordering = room.event_pos.stream from_key = RoomStreamToken(topological=0, stream=0) to_key = RoomStreamToken(stream=stream_ordering) @@ -221,7 +214,6 @@ class AdminHandler: self._storage_controllers, user_id, events, - msc4115_membership_on_events=self._hs_config.experimental.msc4115_membership_on_events, ) writer.write_events(room_id, events) diff --git a/synapse/handlers/cas.py b/synapse/handlers/cas.py index 153123ee83..cc3d641b7d 100644 --- a/synapse/handlers/cas.py +++ b/synapse/handlers/cas.py @@ -78,6 +78,8 @@ class CasHandler: self._cas_displayname_attribute = hs.config.cas.cas_displayname_attribute self._cas_required_attributes = hs.config.cas.cas_required_attributes self._cas_enable_registration = hs.config.cas.cas_enable_registration + self._cas_allow_numeric_ids = hs.config.cas.cas_allow_numeric_ids + self._cas_numeric_ids_prefix = hs.config.cas.cas_numeric_ids_prefix self._http_client = hs.get_proxied_http_client() @@ -188,6 +190,9 @@ class CasHandler: for child in root[0]: if child.tag.endswith("user"): user = child.text + # if numeric user IDs are allowed and username is numeric then we add the prefix so Synapse can handle it + if self._cas_allow_numeric_ids and user is not None and user.isdigit(): + user = f"{self._cas_numeric_ids_prefix}{user}" if child.tag.endswith("attributes"): for attribute in child: # ElementTree library expands the namespace in diff --git a/synapse/handlers/device.py b/synapse/handlers/device.py index 67953a3ed9..0432d97109 100644 --- a/synapse/handlers/device.py +++ b/synapse/handlers/device.py @@ -159,20 +159,32 @@ class DeviceWorkerHandler: @cancellable async def get_device_changes_in_shared_rooms( - self, user_id: str, room_ids: StrCollection, from_token: StreamToken + self, + user_id: str, + room_ids: StrCollection, + from_token: StreamToken, + now_token: Optional[StreamToken] = None, ) -> Set[str]: """Get the set of users whose devices have changed who share a room with the given user. """ + now_device_lists_key = self.store.get_device_stream_token() + if now_token: + now_device_lists_key = now_token.device_list_key + changed_users = await self.store.get_device_list_changes_in_rooms( - room_ids, from_token.device_list_key + room_ids, + from_token.device_list_key, + now_device_lists_key, ) if changed_users is not None: # We also check if the given user has changed their device. If # they're in no rooms then the above query won't include them. changed = await self.store.get_users_whose_devices_changed( - from_token.device_list_key, [user_id] + from_token.device_list_key, + [user_id], + to_key=now_device_lists_key, ) changed_users.update(changed) return changed_users @@ -190,7 +202,9 @@ class DeviceWorkerHandler: tracked_users.add(user_id) changed = await self.store.get_users_whose_devices_changed( - from_token.device_list_key, tracked_users + from_token.device_list_key, + tracked_users, + to_key=now_device_lists_key, ) return changed @@ -892,6 +906,13 @@ class DeviceHandler(DeviceWorkerHandler): context=opentracing_context, ) + await self.store.mark_redundant_device_lists_pokes( + user_id=user_id, + device_id=device_id, + room_id=room_id, + converted_upto_stream_id=stream_id, + ) + # Notify replication that we've updated the device list stream. self.notifier.notify_replication() diff --git a/synapse/handlers/devicemessage.py b/synapse/handlers/devicemessage.py index 79be7c97c8..e56bdb4072 100644 --- a/synapse/handlers/devicemessage.py +++ b/synapse/handlers/devicemessage.py @@ -236,6 +236,13 @@ class DeviceMessageHandler: local_messages = {} remote_messages: Dict[str, Dict[str, Dict[str, JsonDict]]] = {} for user_id, by_device in messages.items(): + if not UserID.is_valid(user_id): + logger.warning( + "Ignoring attempt to send device message to invalid user: %r", + user_id, + ) + continue + # add an opentracing log entry for each message for device_id, message_content in by_device.items(): log_kv( diff --git a/synapse/handlers/e2e_keys.py b/synapse/handlers/e2e_keys.py index 1ece54ccfc..668cec513b 100644 --- a/synapse/handlers/e2e_keys.py +++ b/synapse/handlers/e2e_keys.py @@ -35,6 +35,7 @@ from synapse.api.errors import CodeMessageException, Codes, NotFoundError, Synap from synapse.handlers.device import DeviceHandler from synapse.logging.context import make_deferred_yieldable, run_in_background from synapse.logging.opentracing import log_kv, set_tag, tag_args, trace +from synapse.replication.http.devices import ReplicationUploadKeysForUserRestServlet from synapse.types import ( JsonDict, JsonMapping, @@ -45,7 +46,10 @@ from synapse.types import ( from synapse.util import json_decoder from synapse.util.async_helpers import Linearizer, concurrently_execute from synapse.util.cancellation import cancellable -from synapse.util.retryutils import NotRetryingDestination +from synapse.util.retryutils import ( + NotRetryingDestination, + filter_destinations_by_retry_limiter, +) if TYPE_CHECKING: from synapse.server import HomeServer @@ -53,6 +57,9 @@ if TYPE_CHECKING: logger = logging.getLogger(__name__) +ONE_TIME_KEY_UPLOAD = "one_time_key_upload_lock" + + class E2eKeysHandler: def __init__(self, hs: "HomeServer"): self.config = hs.config @@ -62,6 +69,7 @@ class E2eKeysHandler: self._appservice_handler = hs.get_application_service_handler() self.is_mine = hs.is_mine self.clock = hs.get_clock() + self._worker_lock_handler = hs.get_worker_locks_handler() federation_registry = hs.get_federation_registry() @@ -82,6 +90,12 @@ class E2eKeysHandler: edu_updater.incoming_signing_key_update, ) + self.device_key_uploader = self.upload_device_keys_for_user + else: + self.device_key_uploader = ( + ReplicationUploadKeysForUserRestServlet.make_client(hs) + ) + # doesn't really work as part of the generic query API, because the # query request requires an object POST, but we abuse the # "query handler" interface. @@ -145,6 +159,11 @@ class E2eKeysHandler: remote_queries = {} for user_id, device_ids in device_keys_query.items(): + if not UserID.is_valid(user_id): + # Ignore invalid user IDs, which is the same behaviour as if + # the user existed but had no keys. + continue + # we use UserID.from_string to catch invalid user ids if self.is_mine(UserID.from_string(user_id)): local_query[user_id] = device_ids @@ -259,10 +278,8 @@ class E2eKeysHandler: "%d destinations to query devices for", len(remote_queries_not_in_cache) ) - async def _query( - destination_queries: Tuple[str, Dict[str, Iterable[str]]] - ) -> None: - destination, queries = destination_queries + async def _query(destination: str) -> None: + queries = remote_queries_not_in_cache[destination] return await self._query_devices_for_destination( results, cross_signing_keys, @@ -272,9 +289,20 @@ class E2eKeysHandler: timeout, ) + # Only try and fetch keys for destinations that are not marked as + # down. + filtered_destinations = await filter_destinations_by_retry_limiter( + remote_queries_not_in_cache.keys(), + self.clock, + self.store, + # Let's give an arbitrary grace period for those hosts that are + # only recently down + retry_due_within_ms=60 * 1000, + ) + await concurrently_execute( _query, - remote_queries_not_in_cache.items(), + filtered_destinations, 10, delay_cancellation=True, ) @@ -775,36 +803,17 @@ class E2eKeysHandler: "one_time_keys": A mapping from algorithm to number of keys for that algorithm, including those previously persisted. """ - # This can only be called from the main process. - assert isinstance(self.device_handler, DeviceHandler) - time_now = self.clock.time_msec() # TODO: Validate the JSON to make sure it has the right keys. device_keys = keys.get("device_keys", None) if device_keys: - logger.info( - "Updating device_keys for device %r for user %s at %d", - device_id, - user_id, - time_now, - ) - log_kv( - { - "message": "Updating device_keys for user.", - "user_id": user_id, - "device_id": device_id, - } - ) - # TODO: Sign the JSON with the server key - changed = await self.store.set_e2e_device_keys( - user_id, device_id, time_now, device_keys + await self.device_key_uploader( + user_id=user_id, + device_id=device_id, + keys={"device_keys": device_keys}, ) - if changed: - # Only notify about device updates *if* the keys actually changed - await self.device_handler.notify_device_update(user_id, [device_id]) - else: - log_kv({"message": "Not updating device_keys for user", "user_id": user_id}) + one_time_keys = keys.get("one_time_keys", None) if one_time_keys: log_kv( @@ -840,60 +849,106 @@ class E2eKeysHandler: {"message": "Did not update fallback_keys", "reason": "no keys given"} ) - # the device should have been registered already, but it may have been - # deleted due to a race with a DELETE request. Or we may be using an - # old access_token without an associated device_id. Either way, we - # need to double-check the device is registered to avoid ending up with - # keys without a corresponding device. - await self.device_handler.check_device_registered(user_id, device_id) - result = await self.store.count_e2e_one_time_keys(user_id, device_id) set_tag("one_time_key_counts", str(result)) return {"one_time_key_counts": result} - async def _upload_one_time_keys_for_user( - self, user_id: str, device_id: str, time_now: int, one_time_keys: JsonDict + @tag_args + async def upload_device_keys_for_user( + self, user_id: str, device_id: str, keys: JsonDict ) -> None: + """ + Args: + user_id: user whose keys are being uploaded. + device_id: device whose keys are being uploaded. + device_keys: the `device_keys` of an /keys/upload request. + + """ + # This can only be called from the main process. + assert isinstance(self.device_handler, DeviceHandler) + + time_now = self.clock.time_msec() + + device_keys = keys["device_keys"] logger.info( - "Adding one_time_keys %r for device %r for user %r at %d", - one_time_keys.keys(), + "Updating device_keys for device %r for user %s at %d", device_id, user_id, time_now, ) + log_kv( + { + "message": "Updating device_keys for user.", + "user_id": user_id, + "device_id": device_id, + } + ) + # TODO: Sign the JSON with the server key + changed = await self.store.set_e2e_device_keys( + user_id, device_id, time_now, device_keys + ) + if changed: + # Only notify about device updates *if* the keys actually changed + await self.device_handler.notify_device_update(user_id, [device_id]) - # make a list of (alg, id, key) tuples - key_list = [] - for key_id, key_obj in one_time_keys.items(): - algorithm, key_id = key_id.split(":") - key_list.append((algorithm, key_id, key_obj)) + # the device should have been registered already, but it may have been + # deleted due to a race with a DELETE request. Or we may be using an + # old access_token without an associated device_id. Either way, we + # need to double-check the device is registered to avoid ending up with + # keys without a corresponding device. + await self.device_handler.check_device_registered(user_id, device_id) - # First we check if we have already persisted any of the keys. - existing_key_map = await self.store.get_e2e_one_time_keys( - user_id, device_id, [k_id for _, k_id, _ in key_list] - ) + async def _upload_one_time_keys_for_user( + self, user_id: str, device_id: str, time_now: int, one_time_keys: JsonDict + ) -> None: + # We take out a lock so that we don't have to worry about a client + # sending duplicate requests. + lock_key = f"{user_id}_{device_id}" + async with self._worker_lock_handler.acquire_lock( + ONE_TIME_KEY_UPLOAD, lock_key + ): + logger.info( + "Adding one_time_keys %r for device %r for user %r at %d", + one_time_keys.keys(), + device_id, + user_id, + time_now, + ) - new_keys = [] # Keys that we need to insert. (alg, id, json) tuples. - for algorithm, key_id, key in key_list: - ex_json = existing_key_map.get((algorithm, key_id), None) - if ex_json: - if not _one_time_keys_match(ex_json, key): - raise SynapseError( - 400, - ( - "One time key %s:%s already exists. " - "Old key: %s; new key: %r" + # make a list of (alg, id, key) tuples + key_list = [] + for key_id, key_obj in one_time_keys.items(): + algorithm, key_id = key_id.split(":") + key_list.append((algorithm, key_id, key_obj)) + + # First we check if we have already persisted any of the keys. + existing_key_map = await self.store.get_e2e_one_time_keys( + user_id, device_id, [k_id for _, k_id, _ in key_list] + ) + + new_keys = [] # Keys that we need to insert. (alg, id, json) tuples. + for algorithm, key_id, key in key_list: + ex_json = existing_key_map.get((algorithm, key_id), None) + if ex_json: + if not _one_time_keys_match(ex_json, key): + raise SynapseError( + 400, + ( + "One time key %s:%s already exists. " + "Old key: %s; new key: %r" + ) + % (algorithm, key_id, ex_json, key), ) - % (algorithm, key_id, ex_json, key), + else: + new_keys.append( + (algorithm, key_id, encode_canonical_json(key).decode("ascii")) ) - else: - new_keys.append( - (algorithm, key_id, encode_canonical_json(key).decode("ascii")) - ) - log_kv({"message": "Inserting new one_time_keys.", "keys": new_keys}) - await self.store.add_e2e_one_time_keys(user_id, device_id, time_now, new_keys) + log_kv({"message": "Inserting new one_time_keys.", "keys": new_keys}) + await self.store.add_e2e_one_time_keys( + user_id, device_id, time_now, new_keys + ) async def upload_signing_keys_for_user( self, user_id: str, keys: JsonDict diff --git a/synapse/handlers/e2e_room_keys.py b/synapse/handlers/e2e_room_keys.py index e76a51ba30..99f9f6e64a 100644 --- a/synapse/handlers/e2e_room_keys.py +++ b/synapse/handlers/e2e_room_keys.py @@ -247,6 +247,12 @@ class E2eRoomKeysHandler: if current_room_key: if self._should_replace_room_key(current_room_key, room_key): log_kv({"message": "Replacing room key."}) + logger.debug( + "Replacing room key. room=%s session=%s user=%s", + room_id, + session_id, + user_id, + ) # updates are done one at a time in the DB, so send # updates right away rather than batching them up, # like we do with the inserts @@ -256,6 +262,12 @@ class E2eRoomKeysHandler: changed = True else: log_kv({"message": "Not replacing room_key."}) + logger.debug( + "Not replacing room key. room=%s session=%s user=%s", + room_id, + session_id, + user_id, + ) else: log_kv( { @@ -265,6 +277,12 @@ class E2eRoomKeysHandler: } ) log_kv({"message": "Replacing room key."}) + logger.debug( + "Inserting new room key. room=%s session=%s user=%s", + room_id, + session_id, + user_id, + ) to_insert.append((room_id, session_id, room_key)) changed = True diff --git a/synapse/handlers/events.py b/synapse/handlers/events.py index 09d553cff1..3f46032a43 100644 --- a/synapse/handlers/events.py +++ b/synapse/handlers/events.py @@ -148,7 +148,6 @@ class EventHandler: def __init__(self, hs: "HomeServer"): self.store = hs.get_datastores().main self._storage_controllers = hs.get_storage_controllers() - self._config = hs.config async def get_event( self, @@ -194,7 +193,6 @@ class EventHandler: user.to_string(), [event], is_peeking=is_peeking, - msc4115_membership_on_events=self._config.experimental.msc4115_membership_on_events, ) if not filtered: diff --git a/synapse/handlers/initial_sync.py b/synapse/handlers/initial_sync.py index d99fc4bec0..bd3c87f5f4 100644 --- a/synapse/handlers/initial_sync.py +++ b/synapse/handlers/initial_sync.py @@ -199,7 +199,7 @@ class InitialSyncHandler: ) elif event.membership == Membership.LEAVE: room_end_token = RoomStreamToken( - stream=event.stream_ordering, + stream=event.event_pos.stream, ) deferred_room_state = run_in_background( self._state_storage_controller.get_state_for_events, @@ -224,7 +224,6 @@ class InitialSyncHandler: self._storage_controllers, user_id, messages, - msc4115_membership_on_events=self.hs.config.experimental.msc4115_membership_on_events, ) start_token = now_token.copy_and_replace(StreamKeyType.ROOM, token) @@ -383,7 +382,6 @@ class InitialSyncHandler: requester.user.to_string(), messages, is_peeking=is_peeking, - msc4115_membership_on_events=self.hs.config.experimental.msc4115_membership_on_events, ) start_token = StreamToken.START.copy_and_replace(StreamKeyType.ROOM, token) @@ -498,7 +496,6 @@ class InitialSyncHandler: requester.user.to_string(), messages, is_peeking=is_peeking, - msc4115_membership_on_events=self.hs.config.experimental.msc4115_membership_on_events, ) start_token = now_token.copy_and_replace(StreamKeyType.ROOM, token) diff --git a/synapse/handlers/message.py b/synapse/handlers/message.py index ccaa5508ff..5aa48230ec 100644 --- a/synapse/handlers/message.py +++ b/synapse/handlers/message.py @@ -201,7 +201,7 @@ class MessageHandler: if at_token: last_event_id = ( - await self.store.get_last_event_in_room_before_stream_ordering( + await self.store.get_last_event_id_in_room_before_stream_ordering( room_id, end_token=at_token.room_key, ) @@ -496,13 +496,6 @@ class EventCreationHandler: self.room_prejoin_state_types = self.hs.config.api.room_prejoin_state - self.membership_types_to_include_profile_data_in = { - Membership.JOIN, - Membership.KNOCK, - } - if self.hs.config.server.include_profile_data_on_invite: - self.membership_types_to_include_profile_data_in.add(Membership.INVITE) - self.send_event = ReplicationSendEventRestServlet.make_client(hs) self.send_events = ReplicationSendEventsRestServlet.make_client(hs) @@ -594,8 +587,6 @@ class EventCreationHandler: Creates an FrozenEvent object, filling out auth_events, prev_events, etc. - Adds display names to Join membership events. - Args: requester event_dict: An entire event @@ -651,6 +642,17 @@ class EventCreationHandler: """ await self.auth_blocking.check_auth_blocking(requester=requester) + if event_dict["type"] == EventTypes.Message: + requester_suspended = await self.store.get_user_suspended_status( + requester.user.to_string() + ) + if requester_suspended: + raise SynapseError( + 403, + "Sending messages while account is suspended is not allowed.", + Codes.USER_ACCOUNT_SUSPENDED, + ) + if event_dict["type"] == EventTypes.Create and event_dict["state_key"] == "": room_version_id = event_dict["content"]["room_version"] maybe_room_version_obj = KNOWN_ROOM_VERSIONS.get(room_version_id) @@ -672,29 +674,6 @@ class EventCreationHandler: self.validator.validate_builder(builder) - if builder.type == EventTypes.Member: - membership = builder.content.get("membership", None) - target = UserID.from_string(builder.state_key) - - if membership in self.membership_types_to_include_profile_data_in: - # If event doesn't include a display name, add one. - profile = self.profile_handler - content = builder.content - - try: - if "displayname" not in content: - displayname = await profile.get_displayname(target) - if displayname is not None: - content["displayname"] = displayname - if "avatar_url" not in content: - avatar_url = await profile.get_avatar_url(target) - if avatar_url is not None: - content["avatar_url"] = avatar_url - except Exception as e: - logger.info( - "Failed to get profile information for %r: %s", target, e - ) - is_exempt = await self._is_exempt_from_privacy_policy(builder, requester) if require_consent and not is_exempt: await self.assert_accepted_privacy_policy(requester) @@ -1583,6 +1562,7 @@ class EventCreationHandler: # stream_ordering entry manually (as it was persisted on # another worker). event.internal_metadata.stream_ordering = stream_id + event.internal_metadata.instance_name = writer_instance return event diff --git a/synapse/handlers/pagination.py b/synapse/handlers/pagination.py index 6617105cdb..872c85fbad 100644 --- a/synapse/handlers/pagination.py +++ b/synapse/handlers/pagination.py @@ -27,7 +27,6 @@ from synapse.api.constants import Direction, EventTypes, Membership from synapse.api.errors import SynapseError from synapse.api.filtering import Filter from synapse.events.utils import SerializeEventConfig -from synapse.handlers.room import ShutdownRoomParams, ShutdownRoomResponse from synapse.handlers.worker_lock import NEW_EVENT_DURING_PURGE_LOCK_NAME from synapse.logging.opentracing import trace from synapse.metrics.background_process_metrics import run_as_background_process @@ -41,6 +40,7 @@ from synapse.types import ( StreamKeyType, TaskStatus, ) +from synapse.types.handlers import ShutdownRoomParams, ShutdownRoomResponse from synapse.types.state import StateFilter from synapse.util.async_helpers import ReadWriteLock from synapse.visibility import filter_events_for_client @@ -623,7 +623,6 @@ class PaginationHandler: user_id, events, is_peeking=(member_event_id is None), - msc4115_membership_on_events=self.hs.config.experimental.msc4115_membership_on_events, ) # if after the filter applied there are no more events diff --git a/synapse/handlers/profile.py b/synapse/handlers/profile.py index e51e282a9f..6663d4b271 100644 --- a/synapse/handlers/profile.py +++ b/synapse/handlers/profile.py @@ -20,7 +20,7 @@ # import logging import random -from typing import TYPE_CHECKING, Optional, Union +from typing import TYPE_CHECKING, List, Optional, Union from synapse.api.errors import ( AuthError, @@ -64,8 +64,10 @@ class ProfileHandler: self.user_directory_handler = hs.get_user_directory_handler() self.request_ratelimiter = hs.get_request_ratelimiter() - self.max_avatar_size = hs.config.server.max_avatar_size - self.allowed_avatar_mimetypes = hs.config.server.allowed_avatar_mimetypes + self.max_avatar_size: Optional[int] = hs.config.server.max_avatar_size + self.allowed_avatar_mimetypes: Optional[List[str]] = ( + hs.config.server.allowed_avatar_mimetypes + ) self._is_mine_server_name = hs.is_mine_server_name @@ -337,6 +339,12 @@ class ProfileHandler: return False if self.max_avatar_size: + if media_info.media_length is None: + logger.warning( + "Forbidding avatar change to %s: unknown media size", + mxc, + ) + return False # Ensure avatar does not exceed max allowed avatar size if media_info.media_length > self.max_avatar_size: logger.warning( diff --git a/synapse/handlers/register.py b/synapse/handlers/register.py index e48e70db04..c200e29569 100644 --- a/synapse/handlers/register.py +++ b/synapse/handlers/register.py @@ -590,7 +590,7 @@ class RegistrationHandler: # moving away from bare excepts is a good thing to do. logger.error("Failed to join new user to %r: %r", r, e) except Exception as e: - logger.error("Failed to join new user to %r: %r", r, e) + logger.error("Failed to join new user to %r: %r", r, e, exc_info=True) async def _auto_join_rooms(self, user_id: str) -> None: """Automatically joins users to auto join rooms - creating the room in the first place diff --git a/synapse/handlers/relations.py b/synapse/handlers/relations.py index c5cee8860b..efe31e81f9 100644 --- a/synapse/handlers/relations.py +++ b/synapse/handlers/relations.py @@ -95,7 +95,6 @@ class RelationsHandler: self._event_handler = hs.get_event_handler() self._event_serializer = hs.get_event_client_serializer() self._event_creation_handler = hs.get_event_creation_handler() - self._config = hs.config async def get_relations( self, @@ -164,7 +163,6 @@ class RelationsHandler: user_id, events, is_peeking=(member_event_id is None), - msc4115_membership_on_events=self._config.experimental.msc4115_membership_on_events, ) # The relations returned for the requested event do include their @@ -393,9 +391,9 @@ class RelationsHandler: # Attempt to find another event to use as the latest event. potential_events, _ = await self._main_store.get_relations_for_event( + room_id, event_id, event, - room_id, RelationTypes.THREAD, direction=Direction.FORWARDS, ) @@ -610,7 +608,6 @@ class RelationsHandler: user_id, events, is_peeking=(member_event_id is None), - msc4115_membership_on_events=self._config.experimental.msc4115_membership_on_events, ) aggregations = await self.get_bundled_aggregations( diff --git a/synapse/handlers/room.py b/synapse/handlers/room.py index 51739a2653..2302d283a7 100644 --- a/synapse/handlers/room.py +++ b/synapse/handlers/room.py @@ -40,7 +40,6 @@ from typing import ( ) import attr -from typing_extensions import TypedDict import synapse.events.snapshot from synapse.api.constants import ( @@ -88,6 +87,7 @@ from synapse.types import ( UserID, create_requester, ) +from synapse.types.handlers import ShutdownRoomParams, ShutdownRoomResponse from synapse.types.state import StateFilter from synapse.util import stringutils from synapse.util.caches.response_cache import ResponseCache @@ -1476,7 +1476,6 @@ class RoomContextHandler: user.to_string(), events, is_peeking=is_peeking, - msc4115_membership_on_events=self.hs.config.experimental.msc4115_membership_on_events, ) event = await self.store.get_event( @@ -1780,63 +1779,6 @@ class RoomEventSource(EventSource[RoomStreamToken, EventBase]): return self.store.get_current_room_stream_token_for_room_id(room_id) -class ShutdownRoomParams(TypedDict): - """ - Attributes: - requester_user_id: - User who requested the action. Will be recorded as putting the room on the - blocking list. - new_room_user_id: - If set, a new room will be created with this user ID - as the creator and admin, and all users in the old room will be - moved into that room. If not set, no new room will be created - and the users will just be removed from the old room. - new_room_name: - A string representing the name of the room that new users will - be invited to. Defaults to `Content Violation Notification` - message: - A string containing the first message that will be sent as - `new_room_user_id` in the new room. Ideally this will clearly - convey why the original room was shut down. - Defaults to `Sharing illegal content on this server is not - permitted and rooms in violation will be blocked.` - block: - If set to `true`, this room will be added to a blocking list, - preventing future attempts to join the room. Defaults to `false`. - purge: - If set to `true`, purge the given room from the database. - force_purge: - If set to `true`, the room will be purged from database - even if there are still users joined to the room. - """ - - requester_user_id: Optional[str] - new_room_user_id: Optional[str] - new_room_name: Optional[str] - message: Optional[str] - block: bool - purge: bool - force_purge: bool - - -class ShutdownRoomResponse(TypedDict): - """ - Attributes: - kicked_users: An array of users (`user_id`) that were kicked. - failed_to_kick_users: - An array of users (`user_id`) that that were not kicked. - local_aliases: - An array of strings representing the local aliases that were - migrated from the old room to the new. - new_room_id: A string representing the room ID of the new room. - """ - - kicked_users: List[str] - failed_to_kick_users: List[str] - local_aliases: List[str] - new_room_id: Optional[str] - - class RoomShutdownHandler: DEFAULT_MESSAGE = ( "Sharing illegal content on this server is not permitted and rooms in" diff --git a/synapse/handlers/room_member.py b/synapse/handlers/room_member.py index 655c78e150..51b9772329 100644 --- a/synapse/handlers/room_member.py +++ b/synapse/handlers/room_member.py @@ -106,6 +106,13 @@ class RoomMemberHandler(metaclass=abc.ABCMeta): self.event_auth_handler = hs.get_event_auth_handler() self._worker_lock_handler = hs.get_worker_locks_handler() + self._membership_types_to_include_profile_data_in = { + Membership.JOIN, + Membership.KNOCK, + } + if self.hs.config.server.include_profile_data_on_invite: + self._membership_types_to_include_profile_data_in.add(Membership.INVITE) + self.member_linearizer: Linearizer = Linearizer(name="member") self.member_as_limiter = Linearizer(max_count=10, name="member_as_limiter") @@ -785,9 +792,8 @@ class RoomMemberHandler(metaclass=abc.ABCMeta): if ( not self.allow_per_room_profiles and not is_requester_server_notices_user ) or requester.shadow_banned: - # Strip profile data, knowing that new profile data will be added to the - # event's content in event_creation_handler.create_event() using the target's - # global profile. + # Strip profile data, knowing that new profile data will be added to + # the event's content below using the target's global profile. content.pop("displayname", None) content.pop("avatar_url", None) @@ -823,6 +829,29 @@ class RoomMemberHandler(metaclass=abc.ABCMeta): if action in ["kick", "unban"]: effective_membership_state = "leave" + if effective_membership_state not in Membership.LIST: + raise SynapseError(400, "Invalid membership key") + + # Add profile data for joins etc, if no per-room profile. + if ( + effective_membership_state + in self._membership_types_to_include_profile_data_in + ): + # If event doesn't include a display name, add one. + profile = self.profile_handler + + try: + if "displayname" not in content: + displayname = await profile.get_displayname(target) + if displayname is not None: + content["displayname"] = displayname + if "avatar_url" not in content: + avatar_url = await profile.get_avatar_url(target) + if avatar_url is not None: + content["avatar_url"] = avatar_url + except Exception as e: + logger.info("Failed to get profile information for %r: %s", target, e) + # if this is a join with a 3pid signature, we may need to turn a 3pid # invite into a normal invite before we can handle the join. if third_party_signed is not None: diff --git a/synapse/handlers/search.py b/synapse/handlers/search.py index fdbe98de3b..a7d52fa648 100644 --- a/synapse/handlers/search.py +++ b/synapse/handlers/search.py @@ -483,7 +483,6 @@ class SearchHandler: self._storage_controllers, user.to_string(), filtered_events, - msc4115_membership_on_events=self.hs.config.experimental.msc4115_membership_on_events, ) events.sort(key=lambda e: -rank_map[e.event_id]) @@ -585,7 +584,6 @@ class SearchHandler: self._storage_controllers, user.to_string(), filtered_events, - msc4115_membership_on_events=self.hs.config.experimental.msc4115_membership_on_events, ) room_events.extend(events) @@ -673,14 +671,12 @@ class SearchHandler: self._storage_controllers, user.to_string(), res.events_before, - msc4115_membership_on_events=self.hs.config.experimental.msc4115_membership_on_events, ) events_after = await filter_events_for_client( self._storage_controllers, user.to_string(), res.events_after, - msc4115_membership_on_events=self.hs.config.experimental.msc4115_membership_on_events, ) context: JsonDict = { diff --git a/synapse/handlers/sliding_sync.py b/synapse/handlers/sliding_sync.py new file mode 100644 index 0000000000..847a638bba --- /dev/null +++ b/synapse/handlers/sliding_sync.py @@ -0,0 +1,680 @@ +# +# This file is licensed under the Affero General Public License (AGPL) version 3. +# +# Copyright (C) 2024 New Vector, Ltd +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as +# published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# See the GNU Affero General Public License for more details: +# <https://www.gnu.org/licenses/agpl-3.0.html>. +# +# Originally licensed under the Apache License, Version 2.0: +# <http://www.apache.org/licenses/LICENSE-2.0>. +# +# [This file includes modifications made by New Vector Limited] +# +# +import logging +from typing import TYPE_CHECKING, Dict, List, Optional, Tuple + +from immutabledict import immutabledict + +from synapse.api.constants import AccountDataTypes, EventTypes, Membership +from synapse.events import EventBase +from synapse.storage.roommember import RoomsForUser +from synapse.types import ( + PersistedEventPosition, + Requester, + RoomStreamToken, + StreamToken, + UserID, +) +from synapse.types.handlers import OperationType, SlidingSyncConfig, SlidingSyncResult +from synapse.types.state import StateFilter + +if TYPE_CHECKING: + from synapse.server import HomeServer + +logger = logging.getLogger(__name__) + + +def convert_event_to_rooms_for_user(event: EventBase) -> RoomsForUser: + """ + Quick helper to convert an event to a `RoomsForUser` object. + """ + # These fields should be present for all persisted events + assert event.internal_metadata.stream_ordering is not None + assert event.internal_metadata.instance_name is not None + + return RoomsForUser( + room_id=event.room_id, + sender=event.sender, + membership=event.membership, + event_id=event.event_id, + event_pos=PersistedEventPosition( + event.internal_metadata.instance_name, + event.internal_metadata.stream_ordering, + ), + room_version_id=event.room_version.identifier, + ) + + +def filter_membership_for_sync(*, membership: str, user_id: str, sender: str) -> bool: + """ + Returns True if the membership event should be included in the sync response, + otherwise False. + + Attributes: + membership: The membership state of the user in the room. + user_id: The user ID that the membership applies to + sender: The person who sent the membership event + """ + + # Everything except `Membership.LEAVE` because we want everything that's *still* + # relevant to the user. There are few more things to include in the sync response + # (newly_left) but those are handled separately. + # + # This logic includes kicks (leave events where the sender is not the same user) and + # can be read as "anything that isn't a leave or a leave with a different sender". + return membership != Membership.LEAVE or sender != user_id + + +class SlidingSyncHandler: + def __init__(self, hs: "HomeServer"): + self.clock = hs.get_clock() + self.store = hs.get_datastores().main + self.storage_controllers = hs.get_storage_controllers() + self.auth_blocking = hs.get_auth_blocking() + self.notifier = hs.get_notifier() + self.event_sources = hs.get_event_sources() + self.rooms_to_exclude_globally = hs.config.server.rooms_to_exclude_from_sync + + async def wait_for_sync_for_user( + self, + requester: Requester, + sync_config: SlidingSyncConfig, + from_token: Optional[StreamToken] = None, + timeout_ms: int = 0, + ) -> SlidingSyncResult: + """ + Get the sync for a client if we have new data for it now. Otherwise + wait for new data to arrive on the server. If the timeout expires, then + return an empty sync result. + + Args: + requester: The user making the request + sync_config: Sync configuration + from_token: The point in the stream to sync from. Token of the end of the + previous batch. May be `None` if this is the initial sync request. + timeout_ms: The time in milliseconds to wait for new data to arrive. If 0, + we will immediately but there might not be any new data so we just return an + empty response. + """ + # If the user is not part of the mau group, then check that limits have + # not been exceeded (if not part of the group by this point, almost certain + # auth_blocking will occur) + await self.auth_blocking.check_auth_blocking(requester=requester) + + # TODO: If the To-Device extension is enabled and we have a `from_token`, delete + # any to-device messages before that token (since we now know that the device + # has received them). (see sync v2 for how to do this) + + # If we're working with a user-provided token, we need to make sure to wait for + # this worker to catch up with the token so we don't skip past any incoming + # events or future events if the user is nefariously, manually modifying the + # token. + if from_token is not None: + # We need to make sure this worker has caught up with the token. If + # this returns false, it means we timed out waiting, and we should + # just return an empty response. + before_wait_ts = self.clock.time_msec() + if not await self.notifier.wait_for_stream_token(from_token): + logger.warning( + "Timed out waiting for worker to catch up. Returning empty response" + ) + return SlidingSyncResult.empty(from_token) + + # If we've spent significant time waiting to catch up, take it off + # the timeout. + after_wait_ts = self.clock.time_msec() + if after_wait_ts - before_wait_ts > 1_000: + timeout_ms -= after_wait_ts - before_wait_ts + timeout_ms = max(timeout_ms, 0) + + # We're going to respond immediately if the timeout is 0 or if this is an + # initial sync (without a `from_token`) so we can avoid calling + # `notifier.wait_for_events()`. + if timeout_ms == 0 or from_token is None: + now_token = self.event_sources.get_current_token() + result = await self.current_sync_for_user( + sync_config, + from_token=from_token, + to_token=now_token, + ) + else: + # Otherwise, we wait for something to happen and report it to the user. + async def current_sync_callback( + before_token: StreamToken, after_token: StreamToken + ) -> SlidingSyncResult: + return await self.current_sync_for_user( + sync_config, + from_token=from_token, + to_token=after_token, + ) + + result = await self.notifier.wait_for_events( + sync_config.user.to_string(), + timeout_ms, + current_sync_callback, + from_token=from_token, + ) + + return result + + async def current_sync_for_user( + self, + sync_config: SlidingSyncConfig, + to_token: StreamToken, + from_token: Optional[StreamToken] = None, + ) -> SlidingSyncResult: + """ + Generates the response body of a Sliding Sync result, represented as a + `SlidingSyncResult`. + + We fetch data according to the token range (> `from_token` and <= `to_token`). + + Args: + sync_config: Sync configuration + to_token: The point in the stream to sync up to. + from_token: The point in the stream to sync from. Token of the end of the + previous batch. May be `None` if this is the initial sync request. + """ + user_id = sync_config.user.to_string() + app_service = self.store.get_app_service_by_user_id(user_id) + if app_service: + # We no longer support AS users using /sync directly. + # See https://github.com/matrix-org/matrix-doc/issues/1144 + raise NotImplementedError() + + # Assemble sliding window lists + lists: Dict[str, SlidingSyncResult.SlidingWindowList] = {} + if sync_config.lists: + # Get all of the room IDs that the user should be able to see in the sync + # response + sync_room_map = await self.get_sync_room_ids_for_user( + sync_config.user, + from_token=from_token, + to_token=to_token, + ) + + for list_key, list_config in sync_config.lists.items(): + # Apply filters + filtered_sync_room_map = sync_room_map + if list_config.filters is not None: + filtered_sync_room_map = await self.filter_rooms( + sync_config.user, sync_room_map, list_config.filters, to_token + ) + + sorted_room_info = await self.sort_rooms( + filtered_sync_room_map, to_token + ) + + ops: List[SlidingSyncResult.SlidingWindowList.Operation] = [] + if list_config.ranges: + for range in list_config.ranges: + ops.append( + SlidingSyncResult.SlidingWindowList.Operation( + op=OperationType.SYNC, + range=range, + room_ids=[ + room_id + for room_id, _ in sorted_room_info[ + range[0] : range[1] + ] + ], + ) + ) + + lists[list_key] = SlidingSyncResult.SlidingWindowList( + count=len(sorted_room_info), + ops=ops, + ) + + return SlidingSyncResult( + next_pos=to_token, + lists=lists, + # TODO: Gather room data for rooms in lists and `sync_config.room_subscriptions` + rooms={}, + extensions={}, + ) + + async def get_sync_room_ids_for_user( + self, + user: UserID, + to_token: StreamToken, + from_token: Optional[StreamToken] = None, + ) -> Dict[str, RoomsForUser]: + """ + Fetch room IDs that should be listed for this user in the sync response (the + full room list that will be filtered, sorted, and sliced). + + We're looking for rooms where the user has the following state in the token + range (> `from_token` and <= `to_token`): + + - `invite`, `join`, `knock`, `ban` membership events + - Kicks (`leave` membership events where `sender` is different from the + `user_id`/`state_key`) + - `newly_left` (rooms that were left during the given token range) + - In order for bans/kicks to not show up in sync, you need to `/forget` those + rooms. This doesn't modify the event itself though and only adds the + `forgotten` flag to the `room_memberships` table in Synapse. There isn't a way + to tell when a room was forgotten at the moment so we can't factor it into the + from/to range. + + Args: + user: User to fetch rooms for + to_token: The token to fetch rooms up to. + from_token: The point in the stream to sync from. + + Returns: + A dictionary of room IDs that should be listed in the sync response along + with membership information in that room at the time of `to_token`. + """ + user_id = user.to_string() + + # First grab a current snapshot rooms for the user + # (also handles forgotten rooms) + room_for_user_list = await self.store.get_rooms_for_local_user_where_membership_is( + user_id=user_id, + # We want to fetch any kind of membership (joined and left rooms) in order + # to get the `event_pos` of the latest room membership event for the + # user. + # + # We will filter out the rooms that don't belong below (see + # `filter_membership_for_sync`) + membership_list=Membership.LIST, + excluded_rooms=self.rooms_to_exclude_globally, + ) + + # If the user has never joined any rooms before, we can just return an empty list + if not room_for_user_list: + return {} + + # Our working list of rooms that can show up in the sync response + sync_room_id_set = { + room_for_user.room_id: room_for_user + for room_for_user in room_for_user_list + if filter_membership_for_sync( + membership=room_for_user.membership, + user_id=user_id, + sender=room_for_user.sender, + ) + } + + # Get the `RoomStreamToken` that represents the spot we queried up to when we got + # our membership snapshot from `get_rooms_for_local_user_where_membership_is()`. + # + # First, we need to get the max stream_ordering of each event persister instance + # that we queried events from. + instance_to_max_stream_ordering_map: Dict[str, int] = {} + for room_for_user in room_for_user_list: + instance_name = room_for_user.event_pos.instance_name + stream_ordering = room_for_user.event_pos.stream + + current_instance_max_stream_ordering = ( + instance_to_max_stream_ordering_map.get(instance_name) + ) + if ( + current_instance_max_stream_ordering is None + or stream_ordering > current_instance_max_stream_ordering + ): + instance_to_max_stream_ordering_map[instance_name] = stream_ordering + + # Then assemble the `RoomStreamToken` + membership_snapshot_token = RoomStreamToken( + # Minimum position in the `instance_map` + stream=min(instance_to_max_stream_ordering_map.values()), + instance_map=immutabledict(instance_to_max_stream_ordering_map), + ) + + # Since we fetched the users room list at some point in time after the from/to + # tokens, we need to revert/rewind some membership changes to match the point in + # time of the `to_token`. In particular, we need to make these fixups: + # + # - 1a) Remove rooms that the user joined after the `to_token` + # - 1b) Add back rooms that the user left after the `to_token` + # - 2) Add back newly_left rooms (> `from_token` and <= `to_token`) + # + # Below, we're doing two separate lookups for membership changes. We could + # request everything for both fixups in one range, [`from_token.room_key`, + # `membership_snapshot_token`), but we want to avoid raw `stream_ordering` + # comparison without `instance_name` (which is flawed). We could refactor + # `event.internal_metadata` to include `instance_name` but it might turn out a + # little difficult and a bigger, broader Synapse change than we want to make. + + # 1) ----------------------------------------------------- + + # 1) Fetch membership changes that fall in the range from `to_token` up to + # `membership_snapshot_token` + # + # If our `to_token` is already the same or ahead of the latest room membership + # for the user, we don't need to do any "2)" fix-ups and can just straight-up + # use the room list from the snapshot as a base (nothing has changed) + membership_change_events_after_to_token = [] + if not membership_snapshot_token.is_before_or_eq(to_token.room_key): + membership_change_events_after_to_token = ( + await self.store.get_membership_changes_for_user( + user_id, + from_key=to_token.room_key, + to_key=membership_snapshot_token, + excluded_rooms=self.rooms_to_exclude_globally, + ) + ) + + # 1) Assemble a list of the last membership events in some given ranges. Someone + # could have left and joined multiple times during the given range but we only + # care about end-result so we grab the last one. + last_membership_change_by_room_id_after_to_token: Dict[str, EventBase] = {} + # We also need the first membership event after the `to_token` so we can step + # backward to the previous membership that would apply to the from/to range. + first_membership_change_by_room_id_after_to_token: Dict[str, EventBase] = {} + for event in membership_change_events_after_to_token: + last_membership_change_by_room_id_after_to_token[event.room_id] = event + # Only set if we haven't already set it + first_membership_change_by_room_id_after_to_token.setdefault( + event.room_id, event + ) + + # 1) Fixup + for ( + last_membership_change_after_to_token + ) in last_membership_change_by_room_id_after_to_token.values(): + room_id = last_membership_change_after_to_token.room_id + + # We want to find the first membership change after the `to_token` then step + # backward to know the membership in the from/to range. + first_membership_change_after_to_token = ( + first_membership_change_by_room_id_after_to_token.get(room_id) + ) + assert first_membership_change_after_to_token is not None, ( + "If there was a `last_membership_change_after_to_token` that we're iterating over, " + + "then there should be corresponding a first change. For example, even if there " + + "is only one event after the `to_token`, the first and last event will be same event. " + + "This is probably a mistake in assembling the `last_membership_change_by_room_id_after_to_token`" + + "/`first_membership_change_by_room_id_after_to_token` dicts above." + ) + # TODO: Instead of reading from `unsigned`, refactor this to use the + # `current_state_delta_stream` table in the future. Probably a new + # `get_membership_changes_for_user()` function that uses + # `current_state_delta_stream` with a join to `room_memberships`. This would + # help in state reset scenarios since `prev_content` is looking at the + # current branch vs the current room state. This is all just data given to + # the client so no real harm to data integrity, but we'd like to be nice to + # the client. Since the `current_state_delta_stream` table is new, it + # doesn't have all events in it. Since this is Sliding Sync, if we ever need + # to, we can signal the client to throw all of their state away by sending + # "operation: RESET". + prev_content = first_membership_change_after_to_token.unsigned.get( + "prev_content", {} + ) + prev_membership = prev_content.get("membership", None) + prev_sender = first_membership_change_after_to_token.unsigned.get( + "prev_sender", None + ) + + # Check if the previous membership (membership that applies to the from/to + # range) should be included in our `sync_room_id_set` + should_prev_membership_be_included = ( + prev_membership is not None + and prev_sender is not None + and filter_membership_for_sync( + membership=prev_membership, + user_id=user_id, + sender=prev_sender, + ) + ) + + # Check if the last membership (membership that applies to our snapshot) was + # already included in our `sync_room_id_set` + was_last_membership_already_included = filter_membership_for_sync( + membership=last_membership_change_after_to_token.membership, + user_id=user_id, + sender=last_membership_change_after_to_token.sender, + ) + + # 1a) Add back rooms that the user left after the `to_token` + # + # For example, if the last membership event after the `to_token` is a leave + # event, then the room was excluded from `sync_room_id_set` when we first + # crafted it above. We should add these rooms back as long as the user also + # was part of the room before the `to_token`. + if ( + not was_last_membership_already_included + and should_prev_membership_be_included + ): + sync_room_id_set[room_id] = convert_event_to_rooms_for_user( + last_membership_change_after_to_token + ) + # 1b) Remove rooms that the user joined (hasn't left) after the `to_token` + # + # For example, if the last membership event after the `to_token` is a "join" + # event, then the room was included `sync_room_id_set` when we first crafted + # it above. We should remove these rooms as long as the user also wasn't + # part of the room before the `to_token`. + elif ( + was_last_membership_already_included + and not should_prev_membership_be_included + ): + del sync_room_id_set[room_id] + + # 2) ----------------------------------------------------- + # We fix-up newly_left rooms after the first fixup because it may have removed + # some left rooms that we can figure out our newly_left in the following code + + # 2) Fetch membership changes that fall in the range from `from_token` up to `to_token` + membership_change_events_in_from_to_range = [] + if from_token: + membership_change_events_in_from_to_range = ( + await self.store.get_membership_changes_for_user( + user_id, + from_key=from_token.room_key, + to_key=to_token.room_key, + excluded_rooms=self.rooms_to_exclude_globally, + ) + ) + + # 2) Assemble a list of the last membership events in some given ranges. Someone + # could have left and joined multiple times during the given range but we only + # care about end-result so we grab the last one. + last_membership_change_by_room_id_in_from_to_range: Dict[str, EventBase] = {} + for event in membership_change_events_in_from_to_range: + last_membership_change_by_room_id_in_from_to_range[event.room_id] = event + + # 2) Fixup + for ( + last_membership_change_in_from_to_range + ) in last_membership_change_by_room_id_in_from_to_range.values(): + room_id = last_membership_change_in_from_to_range.room_id + + # 2) Add back newly_left rooms (> `from_token` and <= `to_token`). We + # include newly_left rooms because the last event that the user should see + # is their own leave event + if last_membership_change_in_from_to_range.membership == Membership.LEAVE: + sync_room_id_set[room_id] = convert_event_to_rooms_for_user( + last_membership_change_in_from_to_range + ) + + return sync_room_id_set + + async def filter_rooms( + self, + user: UserID, + sync_room_map: Dict[str, RoomsForUser], + filters: SlidingSyncConfig.SlidingSyncList.Filters, + to_token: StreamToken, + ) -> Dict[str, RoomsForUser]: + """ + Filter rooms based on the sync request. + + Args: + user: User to filter rooms for + sync_room_map: Dictionary of room IDs to sort along with membership + information in the room at the time of `to_token`. + filters: Filters to apply + to_token: We filter based on the state of the room at this token + + Returns: + A filtered dictionary of room IDs along with membership information in the + room at the time of `to_token`. + """ + user_id = user.to_string() + + # TODO: Apply filters + # + # TODO: Exclude partially stated rooms unless the `required_state` has + # `["m.room.member", "$LAZY"]` + + filtered_room_id_set = set(sync_room_map.keys()) + + # Filter for Direct-Message (DM) rooms + if filters.is_dm is not None: + # We're using global account data (`m.direct`) instead of checking for + # `is_direct` on membership events because that property only appears for + # the invitee membership event (doesn't show up for the inviter). Account + # data is set by the client so it needs to be scrutinized. + # + # We're unable to take `to_token` into account for global account data since + # we only keep track of the latest account data for the user. + dm_map = await self.store.get_global_account_data_by_type_for_user( + user_id, AccountDataTypes.DIRECT + ) + + # Flatten out the map + dm_room_id_set = set() + if isinstance(dm_map, dict): + for room_ids in dm_map.values(): + # Account data should be a list of room IDs. Ignore anything else + if isinstance(room_ids, list): + for room_id in room_ids: + if isinstance(room_id, str): + dm_room_id_set.add(room_id) + + if filters.is_dm: + # Only DM rooms please + filtered_room_id_set = filtered_room_id_set.intersection(dm_room_id_set) + else: + # Only non-DM rooms please + filtered_room_id_set = filtered_room_id_set.difference(dm_room_id_set) + + if filters.spaces: + raise NotImplementedError() + + # Filter for encrypted rooms + if filters.is_encrypted is not None: + # Make a copy so we don't run into an error: `Set changed size during + # iteration`, when we filter out and remove items + for room_id in list(filtered_room_id_set): + state_at_to_token = await self.storage_controllers.state.get_state_at( + room_id, + to_token, + state_filter=StateFilter.from_types( + [(EventTypes.RoomEncryption, "")] + ), + ) + is_encrypted = state_at_to_token.get((EventTypes.RoomEncryption, "")) + + # If we're looking for encrypted rooms, filter out rooms that are not + # encrypted and vice versa + if (filters.is_encrypted and not is_encrypted) or ( + not filters.is_encrypted and is_encrypted + ): + filtered_room_id_set.remove(room_id) + + # Filter for rooms that the user has been invited to + if filters.is_invite is not None: + # Make a copy so we don't run into an error: `Set changed size during + # iteration`, when we filter out and remove items + for room_id in list(filtered_room_id_set): + room_for_user = sync_room_map[room_id] + # If we're looking for invite rooms, filter out rooms that the user is + # not invited to and vice versa + if ( + filters.is_invite and room_for_user.membership != Membership.INVITE + ) or ( + not filters.is_invite + and room_for_user.membership == Membership.INVITE + ): + filtered_room_id_set.remove(room_id) + + if filters.room_types: + raise NotImplementedError() + + if filters.not_room_types: + raise NotImplementedError() + + if filters.room_name_like: + raise NotImplementedError() + + if filters.tags: + raise NotImplementedError() + + if filters.not_tags: + raise NotImplementedError() + + # Assemble a new sync room map but only with the `filtered_room_id_set` + return {room_id: sync_room_map[room_id] for room_id in filtered_room_id_set} + + async def sort_rooms( + self, + sync_room_map: Dict[str, RoomsForUser], + to_token: StreamToken, + ) -> List[Tuple[str, RoomsForUser]]: + """ + Sort by `stream_ordering` of the last event that the user should see in the + room. `stream_ordering` is unique so we get a stable sort. + + Args: + sync_room_map: Dictionary of room IDs to sort along with membership + information in the room at the time of `to_token`. + to_token: We sort based on the events in the room at this token (<= `to_token`) + + Returns: + A sorted list of room IDs by `stream_ordering` along with membership information. + """ + + # Assemble a map of room ID to the `stream_ordering` of the last activity that the + # user should see in the room (<= `to_token`) + last_activity_in_room_map: Dict[str, int] = {} + for room_id, room_for_user in sync_room_map.items(): + # If they are fully-joined to the room, let's find the latest activity + # at/before the `to_token`. + if room_for_user.membership == Membership.JOIN: + last_event_result = ( + await self.store.get_last_event_pos_in_room_before_stream_ordering( + room_id, to_token.room_key + ) + ) + + # If the room has no events at/before the `to_token`, this is probably a + # mistake in the code that generates the `sync_room_map` since that should + # only give us rooms that the user had membership in during the token range. + assert last_event_result is not None + + _, event_pos = last_event_result + + last_activity_in_room_map[room_id] = event_pos.stream + else: + # Otherwise, if the user has left/been invited/knocked/been banned from + # a room, they shouldn't see anything past that point. + last_activity_in_room_map[room_id] = room_for_user.event_pos.stream + + return sorted( + sync_room_map.items(), + # Sort by the last activity (stream_ordering) in the room + key=lambda room_info: last_activity_in_room_map[room_info[0]], + # We want descending order + reverse=True, + ) diff --git a/synapse/handlers/sso.py b/synapse/handlers/sso.py index f275d4f35a..ee74289b6c 100644 --- a/synapse/handlers/sso.py +++ b/synapse/handlers/sso.py @@ -817,7 +817,7 @@ class SsoHandler: server_name = profile["avatar_url"].split("/")[-2] media_id = profile["avatar_url"].split("/")[-1] if self._is_mine_server_name(server_name): - media = await self._media_repo.store.get_local_media(media_id) + media = await self._media_repo.store.get_local_media(media_id) # type: ignore[has-type] if media is not None and upload_name == media.upload_name: logger.info("skipping saving the user avatar") return True diff --git a/synapse/handlers/sync.py b/synapse/handlers/sync.py index 8ff45a3353..e2563428d2 100644 --- a/synapse/handlers/sync.py +++ b/synapse/handlers/sync.py @@ -20,6 +20,7 @@ # import itertools import logging +from enum import Enum from typing import ( TYPE_CHECKING, AbstractSet, @@ -27,11 +28,14 @@ from typing import ( Dict, FrozenSet, List, + Literal, Mapping, Optional, Sequence, Set, Tuple, + Union, + overload, ) import attr @@ -112,12 +116,30 @@ LAZY_LOADED_MEMBERS_CACHE_MAX_SIZE = 100 SyncRequestKey = Tuple[Any, ...] +class SyncVersion(Enum): + """ + Enum for specifying the version of sync request. This is used to key which type of + sync response that we are generating. + + This is different than the `sync_type` you might see used in other code below; which + specifies the sub-type sync request (e.g. initial_sync, full_state_sync, + incremental_sync) and is really only relevant for the `/sync` v2 endpoint. + """ + + # These string values are semantically significant because they are used in the the + # metrics + + # Traditional `/sync` endpoint + SYNC_V2 = "sync_v2" + # Part of MSC3575 Sliding Sync + E2EE_SYNC = "e2ee_sync" + + @attr.s(slots=True, frozen=True, auto_attribs=True) class SyncConfig: user: UserID filter_collection: FilterCollection is_guest: bool - request_key: SyncRequestKey device_id: Optional[str] @@ -262,6 +284,47 @@ class SyncResult: or self.device_lists ) + @staticmethod + def empty( + next_batch: StreamToken, + device_one_time_keys_count: JsonMapping, + device_unused_fallback_key_types: List[str], + ) -> "SyncResult": + "Return a new empty result" + return SyncResult( + next_batch=next_batch, + presence=[], + account_data=[], + joined=[], + invited=[], + knocked=[], + archived=[], + to_device=[], + device_lists=DeviceListUpdates(), + device_one_time_keys_count=device_one_time_keys_count, + device_unused_fallback_key_types=device_unused_fallback_key_types, + ) + + +@attr.s(slots=True, frozen=True, auto_attribs=True) +class E2eeSyncResult: + """ + Attributes: + next_batch: Token for the next sync + to_device: List of direct messages for the device. + device_lists: List of user_ids whose devices have changed + device_one_time_keys_count: Dict of algorithm to count for one time keys + for this device + device_unused_fallback_key_types: List of key types that have an unused fallback + key + """ + + next_batch: StreamToken + to_device: List[JsonDict] + device_lists: DeviceListUpdates + device_one_time_keys_count: JsonMapping + device_unused_fallback_key_types: List[str] + class SyncHandler: def __init__(self, hs: "HomeServer"): @@ -305,17 +368,68 @@ class SyncHandler: self.rooms_to_exclude_globally = hs.config.server.rooms_to_exclude_from_sync + @overload async def wait_for_sync_for_user( self, requester: Requester, sync_config: SyncConfig, + sync_version: Literal[SyncVersion.SYNC_V2], + request_key: SyncRequestKey, since_token: Optional[StreamToken] = None, timeout: int = 0, full_state: bool = False, - ) -> SyncResult: + ) -> SyncResult: ... + + @overload + async def wait_for_sync_for_user( + self, + requester: Requester, + sync_config: SyncConfig, + sync_version: Literal[SyncVersion.E2EE_SYNC], + request_key: SyncRequestKey, + since_token: Optional[StreamToken] = None, + timeout: int = 0, + full_state: bool = False, + ) -> E2eeSyncResult: ... + + @overload + async def wait_for_sync_for_user( + self, + requester: Requester, + sync_config: SyncConfig, + sync_version: SyncVersion, + request_key: SyncRequestKey, + since_token: Optional[StreamToken] = None, + timeout: int = 0, + full_state: bool = False, + ) -> Union[SyncResult, E2eeSyncResult]: ... + + async def wait_for_sync_for_user( + self, + requester: Requester, + sync_config: SyncConfig, + sync_version: SyncVersion, + request_key: SyncRequestKey, + since_token: Optional[StreamToken] = None, + timeout: int = 0, + full_state: bool = False, + ) -> Union[SyncResult, E2eeSyncResult]: """Get the sync for a client if we have new data for it now. Otherwise wait for new data to arrive on the server. If the timeout expires, then return an empty sync result. + + Args: + requester: The user requesting the sync response. + sync_config: Config/info necessary to process the sync request. + sync_version: Determines what kind of sync response to generate. + request_key: The key to use for caching the response. + since_token: The point in the stream to sync from. + timeout: How long to wait for new data to arrive before giving up. + full_state: Whether to return the full state for each room. + + Returns: + When `SyncVersion.SYNC_V2`, returns a full `SyncResult`. + When `SyncVersion.E2EE_SYNC`, returns a `E2eeSyncResult`. """ # If the user is not part of the mau group, then check that limits have # not been exceeded (if not part of the group by this point, almost certain @@ -324,9 +438,10 @@ class SyncHandler: await self.auth_blocking.check_auth_blocking(requester=requester) res = await self.response_cache.wrap( - sync_config.request_key, + request_key, self._wait_for_sync_for_user, sync_config, + sync_version, since_token, timeout, full_state, @@ -335,14 +450,48 @@ class SyncHandler: logger.debug("Returning sync response for %s", user_id) return res + @overload async def _wait_for_sync_for_user( self, sync_config: SyncConfig, + sync_version: Literal[SyncVersion.SYNC_V2], since_token: Optional[StreamToken], timeout: int, full_state: bool, cache_context: ResponseCacheContext[SyncRequestKey], - ) -> SyncResult: + ) -> SyncResult: ... + + @overload + async def _wait_for_sync_for_user( + self, + sync_config: SyncConfig, + sync_version: Literal[SyncVersion.E2EE_SYNC], + since_token: Optional[StreamToken], + timeout: int, + full_state: bool, + cache_context: ResponseCacheContext[SyncRequestKey], + ) -> E2eeSyncResult: ... + + @overload + async def _wait_for_sync_for_user( + self, + sync_config: SyncConfig, + sync_version: SyncVersion, + since_token: Optional[StreamToken], + timeout: int, + full_state: bool, + cache_context: ResponseCacheContext[SyncRequestKey], + ) -> Union[SyncResult, E2eeSyncResult]: ... + + async def _wait_for_sync_for_user( + self, + sync_config: SyncConfig, + sync_version: SyncVersion, + since_token: Optional[StreamToken], + timeout: int, + full_state: bool, + cache_context: ResponseCacheContext[SyncRequestKey], + ) -> Union[SyncResult, E2eeSyncResult]: """The start of the machinery that produces a /sync response. See https://spec.matrix.org/v1.1/client-server-api/#syncing for full details. @@ -363,9 +512,50 @@ class SyncHandler: else: sync_type = "incremental_sync" + sync_label = f"{sync_version}:{sync_type}" + context = current_context() if context: - context.tag = sync_type + context.tag = sync_label + + if since_token is not None: + # We need to make sure this worker has caught up with the token. If + # this returns false it means we timed out waiting, and we should + # just return an empty response. + start = self.clock.time_msec() + if not await self.notifier.wait_for_stream_token(since_token): + logger.warning( + "Timed out waiting for worker to catch up. Returning empty response" + ) + device_id = sync_config.device_id + one_time_keys_count: JsonMapping = {} + unused_fallback_key_types: List[str] = [] + if device_id: + user_id = sync_config.user.to_string() + # TODO: We should have a way to let clients differentiate between the states of: + # * no change in OTK count since the provided since token + # * the server has zero OTKs left for this device + # Spec issue: https://github.com/matrix-org/matrix-doc/issues/3298 + one_time_keys_count = await self.store.count_e2e_one_time_keys( + user_id, device_id + ) + unused_fallback_key_types = list( + await self.store.get_e2e_unused_fallback_key_types( + user_id, device_id + ) + ) + + cache_context.should_cache = False # Don't cache empty responses + return SyncResult.empty( + since_token, one_time_keys_count, unused_fallback_key_types + ) + + # If we've spent significant time waiting to catch up, take it off + # the timeout. + now = self.clock.time_msec() + if now - start > 1_000: + timeout -= now - start + timeout = max(timeout, 0) # if we have a since token, delete any to-device messages before that token # (since we now know that the device has received them) @@ -383,15 +573,19 @@ class SyncHandler: if timeout == 0 or since_token is None or full_state: # we are going to return immediately, so don't bother calling # notifier.wait_for_events. - result: SyncResult = await self.current_sync_for_user( - sync_config, since_token, full_state=full_state + result: Union[SyncResult, E2eeSyncResult] = ( + await self.current_sync_for_user( + sync_config, sync_version, since_token, full_state=full_state + ) ) else: # Otherwise, we wait for something to happen and report it to the user. async def current_sync_callback( before_token: StreamToken, after_token: StreamToken - ) -> SyncResult: - return await self.current_sync_for_user(sync_config, since_token) + ) -> Union[SyncResult, E2eeSyncResult]: + return await self.current_sync_for_user( + sync_config, sync_version, since_token + ) result = await self.notifier.wait_for_events( sync_config.user.to_string(), @@ -416,27 +610,81 @@ class SyncHandler: lazy_loaded = "true" else: lazy_loaded = "false" - non_empty_sync_counter.labels(sync_type, lazy_loaded).inc() + non_empty_sync_counter.labels(sync_label, lazy_loaded).inc() return result + @overload async def current_sync_for_user( self, sync_config: SyncConfig, + sync_version: Literal[SyncVersion.SYNC_V2], since_token: Optional[StreamToken] = None, full_state: bool = False, - ) -> SyncResult: - """Generates the response body of a sync result, represented as a SyncResult. + ) -> SyncResult: ... + + @overload + async def current_sync_for_user( + self, + sync_config: SyncConfig, + sync_version: Literal[SyncVersion.E2EE_SYNC], + since_token: Optional[StreamToken] = None, + full_state: bool = False, + ) -> E2eeSyncResult: ... + + @overload + async def current_sync_for_user( + self, + sync_config: SyncConfig, + sync_version: SyncVersion, + since_token: Optional[StreamToken] = None, + full_state: bool = False, + ) -> Union[SyncResult, E2eeSyncResult]: ... + + async def current_sync_for_user( + self, + sync_config: SyncConfig, + sync_version: SyncVersion, + since_token: Optional[StreamToken] = None, + full_state: bool = False, + ) -> Union[SyncResult, E2eeSyncResult]: + """ + Generates the response body of a sync result, represented as a + `SyncResult`/`E2eeSyncResult`. This is a wrapper around `generate_sync_result` which starts an open tracing span to track the sync. See `generate_sync_result` for the next part of your indoctrination. + + Args: + sync_config: Config/info necessary to process the sync request. + sync_version: Determines what kind of sync response to generate. + since_token: The point in the stream to sync from.p. + full_state: Whether to return the full state for each room. + + Returns: + When `SyncVersion.SYNC_V2`, returns a full `SyncResult`. + When `SyncVersion.E2EE_SYNC`, returns a `E2eeSyncResult`. """ with start_active_span("sync.current_sync_for_user"): log_kv({"since_token": since_token}) - sync_result = await self.generate_sync_result( - sync_config, since_token, full_state - ) + + # Go through the `/sync` v2 path + if sync_version == SyncVersion.SYNC_V2: + sync_result: Union[SyncResult, E2eeSyncResult] = ( + await self.generate_sync_result( + sync_config, since_token, full_state + ) + ) + # Go through the MSC3575 Sliding Sync `/sync/e2ee` path + elif sync_version == SyncVersion.E2EE_SYNC: + sync_result = await self.generate_e2ee_sync_result( + sync_config, since_token + ) + else: + raise Exception( + f"Unknown sync_version (this is a Synapse problem): {sync_version}" + ) set_tag(SynapseTags.SYNC_RESULT, bool(sync_result)) return sync_result @@ -596,7 +844,6 @@ class SyncHandler: sync_config.user.to_string(), recents, always_include_ids=current_state_ids, - msc4115_membership_on_events=self.hs_config.experimental.msc4115_membership_on_events, ) log_kv({"recents_after_visibility_filtering": len(recents)}) else: @@ -682,7 +929,6 @@ class SyncHandler: sync_config.user.to_string(), loaded_recents, always_include_ids=current_state_ids, - msc4115_membership_on_events=self.hs_config.experimental.msc4115_membership_on_events, ) loaded_recents = [] @@ -733,89 +979,6 @@ class SyncHandler: bundled_aggregations=bundled_aggregations, ) - async def get_state_after_event( - self, - event_id: str, - state_filter: Optional[StateFilter] = None, - await_full_state: bool = True, - ) -> StateMap[str]: - """ - Get the room state after the given event - - Args: - event_id: event of interest - state_filter: The state filter used to fetch state from the database. - await_full_state: if `True`, will block if we do not yet have complete state - at the event and `state_filter` is not satisfied by partial state. - Defaults to `True`. - """ - state_ids = await self._state_storage_controller.get_state_ids_for_event( - event_id, - state_filter=state_filter or StateFilter.all(), - await_full_state=await_full_state, - ) - - # using get_metadata_for_events here (instead of get_event) sidesteps an issue - # with redactions: if `event_id` is a redaction event, and we don't have the - # original (possibly because it got purged), get_event will refuse to return - # the redaction event, which isn't terribly helpful here. - # - # (To be fair, in that case we could assume it's *not* a state event, and - # therefore we don't need to worry about it. But still, it seems cleaner just - # to pull the metadata.) - m = (await self.store.get_metadata_for_events([event_id]))[event_id] - if m.state_key is not None and m.rejection_reason is None: - state_ids = dict(state_ids) - state_ids[(m.event_type, m.state_key)] = event_id - - return state_ids - - async def get_state_at( - self, - room_id: str, - stream_position: StreamToken, - state_filter: Optional[StateFilter] = None, - await_full_state: bool = True, - ) -> StateMap[str]: - """Get the room state at a particular stream position - - Args: - room_id: room for which to get state - stream_position: point at which to get state - state_filter: The state filter used to fetch state from the database. - await_full_state: if `True`, will block if we do not yet have complete state - at the last event in the room before `stream_position` and - `state_filter` is not satisfied by partial state. Defaults to `True`. - """ - # FIXME: This gets the state at the latest event before the stream ordering, - # which might not be the same as the "current state" of the room at the time - # of the stream token if there were multiple forward extremities at the time. - last_event_id = await self.store.get_last_event_in_room_before_stream_ordering( - room_id, - end_token=stream_position.room_key, - ) - - if last_event_id: - state = await self.get_state_after_event( - last_event_id, - state_filter=state_filter or StateFilter.all(), - await_full_state=await_full_state, - ) - - else: - # no events in this room - so presumably no state - state = {} - - # (erikj) This should be rarely hit, but we've had some reports that - # we get more state down gappy syncs than we should, so let's add - # some logging. - logger.info( - "Failed to find any events in room %s at %s", - room_id, - stream_position.room_key, - ) - return state - async def compute_summary( self, room_id: str, @@ -1189,7 +1352,7 @@ class SyncHandler: await_full_state = True lazy_load_members = False - state_at_timeline_end = await self.get_state_at( + state_at_timeline_end = await self._state_storage_controller.get_state_at( room_id, stream_position=end_token, state_filter=state_filter, @@ -1273,7 +1436,7 @@ class SyncHandler: # We need to make sure the first event in our batch points to the # last event in the previous batch. last_event_id_prev_batch = ( - await self.store.get_last_event_in_room_before_stream_ordering( + await self.store.get_last_event_id_in_room_before_stream_ordering( room_id, end_token=since_token.room_key, ) @@ -1317,7 +1480,7 @@ class SyncHandler: else: # We can get here if the user has ignored the senders of all # the recent events. - state_at_timeline_start = await self.get_state_at( + state_at_timeline_start = await self._state_storage_controller.get_state_at( room_id, stream_position=end_token, state_filter=state_filter, @@ -1339,14 +1502,14 @@ class SyncHandler: # about them). state_filter = StateFilter.all() - state_at_previous_sync = await self.get_state_at( + state_at_previous_sync = await self._state_storage_controller.get_state_at( room_id, stream_position=since_token, state_filter=state_filter, await_full_state=await_full_state, ) - state_at_timeline_end = await self.get_state_at( + state_at_timeline_end = await self._state_storage_controller.get_state_at( room_id, stream_position=end_token, state_filter=state_filter, @@ -1518,128 +1681,17 @@ class SyncHandler: # See https://github.com/matrix-org/matrix-doc/issues/1144 raise NotImplementedError() - # Note: we get the users room list *before* we get the current token, this - # avoids checking back in history if rooms are joined after the token is fetched. - token_before_rooms = self.event_sources.get_current_token() - mutable_joined_room_ids = set(await self.store.get_rooms_for_user(user_id)) - - # NB: The now_token gets changed by some of the generate_sync_* methods, - # this is due to some of the underlying streams not supporting the ability - # to query up to a given point. - # Always use the `now_token` in `SyncResultBuilder` - now_token = self.event_sources.get_current_token() - log_kv({"now_token": now_token}) - - # Since we fetched the users room list before the token, there's a small window - # during which membership events may have been persisted, so we fetch these now - # and modify the joined room list for any changes between the get_rooms_for_user - # call and the get_current_token call. - membership_change_events = [] - if since_token: - membership_change_events = await self.store.get_membership_changes_for_user( - user_id, - since_token.room_key, - now_token.room_key, - self.rooms_to_exclude_globally, - ) - - mem_last_change_by_room_id: Dict[str, EventBase] = {} - for event in membership_change_events: - mem_last_change_by_room_id[event.room_id] = event - - # For the latest membership event in each room found, add/remove the room ID - # from the joined room list accordingly. In this case we only care if the - # latest change is JOIN. - - for room_id, event in mem_last_change_by_room_id.items(): - assert event.internal_metadata.stream_ordering - if ( - event.internal_metadata.stream_ordering - < token_before_rooms.room_key.stream - ): - continue - - logger.info( - "User membership change between getting rooms and current token: %s %s %s", - user_id, - event.membership, - room_id, - ) - # User joined a room - we have to then check the room state to ensure we - # respect any bans if there's a race between the join and ban events. - if event.membership == Membership.JOIN: - user_ids_in_room = await self.store.get_users_in_room(room_id) - if user_id in user_ids_in_room: - mutable_joined_room_ids.add(room_id) - # The user left the room, or left and was re-invited but not joined yet - else: - mutable_joined_room_ids.discard(room_id) - - # Tweak the set of rooms to return to the client for eager (non-lazy) syncs. - mutable_rooms_to_exclude = set(self.rooms_to_exclude_globally) - if not sync_config.filter_collection.lazy_load_members(): - # Non-lazy syncs should never include partially stated rooms. - # Exclude all partially stated rooms from this sync. - results = await self.store.is_partial_state_room_batched( - mutable_joined_room_ids - ) - mutable_rooms_to_exclude.update( - room_id - for room_id, is_partial_state in results.items() - if is_partial_state - ) - membership_change_events = [ - event - for event in membership_change_events - if not results.get(event.room_id, False) - ] - - # Incremental eager syncs should additionally include rooms that - # - we are joined to - # - are full-stated - # - became fully-stated at some point during the sync period - # (These rooms will have been omitted during a previous eager sync.) - forced_newly_joined_room_ids: Set[str] = set() - if since_token and not sync_config.filter_collection.lazy_load_members(): - un_partial_stated_rooms = ( - await self.store.get_un_partial_stated_rooms_between( - since_token.un_partial_stated_rooms_key, - now_token.un_partial_stated_rooms_key, - mutable_joined_room_ids, - ) - ) - results = await self.store.is_partial_state_room_batched( - un_partial_stated_rooms - ) - forced_newly_joined_room_ids.update( - room_id - for room_id, is_partial_state in results.items() - if not is_partial_state - ) - - # Now we have our list of joined room IDs, exclude as configured and freeze - joined_room_ids = frozenset( - room_id - for room_id in mutable_joined_room_ids - if room_id not in mutable_rooms_to_exclude + sync_result_builder = await self.get_sync_result_builder( + sync_config, + since_token, + full_state, ) logger.debug( "Calculating sync response for %r between %s and %s", sync_config.user, - since_token, - now_token, - ) - - sync_result_builder = SyncResultBuilder( - sync_config, - full_state, - since_token=since_token, - now_token=now_token, - joined_room_ids=joined_room_ids, - excluded_room_ids=frozenset(mutable_rooms_to_exclude), - forced_newly_joined_room_ids=frozenset(forced_newly_joined_room_ids), - membership_change_events=membership_change_events, + sync_result_builder.since_token, + sync_result_builder.now_token, ) logger.debug("Fetching account data") @@ -1751,6 +1803,242 @@ class SyncHandler: next_batch=sync_result_builder.now_token, ) + async def generate_e2ee_sync_result( + self, + sync_config: SyncConfig, + since_token: Optional[StreamToken] = None, + ) -> E2eeSyncResult: + """ + Generates the response body of a MSC3575 Sliding Sync `/sync/e2ee` result. + + This is represented by a `E2eeSyncResult` struct, which is built from small + pieces using a `SyncResultBuilder`. The `sync_result_builder` is passed as a + mutable ("inout") parameter to various helper functions. These retrieve and + process the data which forms the sync body, often writing to the + `sync_result_builder` to store their output. + + At the end, we transfer data from the `sync_result_builder` to a new `E2eeSyncResult` + instance to signify that the sync calculation is complete. + """ + user_id = sync_config.user.to_string() + app_service = self.store.get_app_service_by_user_id(user_id) + if app_service: + # We no longer support AS users using /sync directly. + # See https://github.com/matrix-org/matrix-doc/issues/1144 + raise NotImplementedError() + + sync_result_builder = await self.get_sync_result_builder( + sync_config, + since_token, + full_state=False, + ) + + # 1. Calculate `to_device` events + await self._generate_sync_entry_for_to_device(sync_result_builder) + + # 2. Calculate `device_lists` + # Device list updates are sent if a since token is provided. + device_lists = DeviceListUpdates() + include_device_list_updates = bool(since_token and since_token.device_list_key) + if include_device_list_updates: + # Note that _generate_sync_entry_for_rooms sets sync_result_builder.joined, which + # is used in calculate_user_changes below. + # + # TODO: Running `_generate_sync_entry_for_rooms()` is a lot of work just to + # figure out the membership changes/derived info needed for + # `_generate_sync_entry_for_device_list()`. In the future, we should try to + # refactor this away. + ( + newly_joined_rooms, + newly_left_rooms, + ) = await self._generate_sync_entry_for_rooms(sync_result_builder) + + # This uses the sync_result_builder.joined which is set in + # `_generate_sync_entry_for_rooms`, if that didn't find any joined + # rooms for some reason it is a no-op. + ( + newly_joined_or_invited_or_knocked_users, + newly_left_users, + ) = sync_result_builder.calculate_user_changes() + + device_lists = await self._generate_sync_entry_for_device_list( + sync_result_builder, + newly_joined_rooms=newly_joined_rooms, + newly_joined_or_invited_or_knocked_users=newly_joined_or_invited_or_knocked_users, + newly_left_rooms=newly_left_rooms, + newly_left_users=newly_left_users, + ) + + # 3. Calculate `device_one_time_keys_count` and `device_unused_fallback_key_types` + device_id = sync_config.device_id + one_time_keys_count: JsonMapping = {} + unused_fallback_key_types: List[str] = [] + if device_id: + # TODO: We should have a way to let clients differentiate between the states of: + # * no change in OTK count since the provided since token + # * the server has zero OTKs left for this device + # Spec issue: https://github.com/matrix-org/matrix-doc/issues/3298 + one_time_keys_count = await self.store.count_e2e_one_time_keys( + user_id, device_id + ) + unused_fallback_key_types = list( + await self.store.get_e2e_unused_fallback_key_types(user_id, device_id) + ) + + return E2eeSyncResult( + to_device=sync_result_builder.to_device, + device_lists=device_lists, + device_one_time_keys_count=one_time_keys_count, + device_unused_fallback_key_types=unused_fallback_key_types, + next_batch=sync_result_builder.now_token, + ) + + async def get_sync_result_builder( + self, + sync_config: SyncConfig, + since_token: Optional[StreamToken] = None, + full_state: bool = False, + ) -> "SyncResultBuilder": + """ + Assemble a `SyncResultBuilder` with all of the initial context to + start building up the sync response: + + - Membership changes between the last sync and the current sync. + - Joined room IDs (minus any rooms to exclude). + - Rooms that became fully-stated/un-partial stated since the last sync. + + Args: + sync_config: Config/info necessary to process the sync request. + since_token: The point in the stream to sync from. + full_state: Whether to return the full state for each room. + + Returns: + `SyncResultBuilder` ready to start generating parts of the sync response. + """ + user_id = sync_config.user.to_string() + + # Note: we get the users room list *before* we get the `now_token`, this + # avoids checking back in history if rooms are joined after the token is fetched. + token_before_rooms = self.event_sources.get_current_token() + mutable_joined_room_ids = set(await self.store.get_rooms_for_user(user_id)) + + # NB: The `now_token` gets changed by some of the `generate_sync_*` methods, + # this is due to some of the underlying streams not supporting the ability + # to query up to a given point. + # Always use the `now_token` in `SyncResultBuilder` + now_token = self.event_sources.get_current_token() + log_kv({"now_token": now_token}) + + # Since we fetched the users room list before calculating the `now_token` (see + # above), there's a small window during which membership events may have been + # persisted, so we fetch these now and modify the joined room list for any + # changes between the get_rooms_for_user call and the get_current_token call. + membership_change_events = [] + if since_token: + membership_change_events = await self.store.get_membership_changes_for_user( + user_id, + since_token.room_key, + now_token.room_key, + self.rooms_to_exclude_globally, + ) + + last_membership_change_by_room_id: Dict[str, EventBase] = {} + for event in membership_change_events: + last_membership_change_by_room_id[event.room_id] = event + + # For the latest membership event in each room found, add/remove the room ID + # from the joined room list accordingly. In this case we only care if the + # latest change is JOIN. + + for room_id, event in last_membership_change_by_room_id.items(): + assert event.internal_metadata.stream_ordering + # As a shortcut, skip any events that happened before we got our + # `get_rooms_for_user()` snapshot (any changes are already represented + # in that list). + if ( + event.internal_metadata.stream_ordering + < token_before_rooms.room_key.stream + ): + continue + + logger.info( + "User membership change between getting rooms and current token: %s %s %s", + user_id, + event.membership, + room_id, + ) + # User joined a room - we have to then check the room state to ensure we + # respect any bans if there's a race between the join and ban events. + if event.membership == Membership.JOIN: + user_ids_in_room = await self.store.get_users_in_room(room_id) + if user_id in user_ids_in_room: + mutable_joined_room_ids.add(room_id) + # The user left the room, or left and was re-invited but not joined yet + else: + mutable_joined_room_ids.discard(room_id) + + # Tweak the set of rooms to return to the client for eager (non-lazy) syncs. + mutable_rooms_to_exclude = set(self.rooms_to_exclude_globally) + if not sync_config.filter_collection.lazy_load_members(): + # Non-lazy syncs should never include partially stated rooms. + # Exclude all partially stated rooms from this sync. + results = await self.store.is_partial_state_room_batched( + mutable_joined_room_ids + ) + mutable_rooms_to_exclude.update( + room_id + for room_id, is_partial_state in results.items() + if is_partial_state + ) + membership_change_events = [ + event + for event in membership_change_events + if not results.get(event.room_id, False) + ] + + # Incremental eager syncs should additionally include rooms that + # - we are joined to + # - are full-stated + # - became fully-stated at some point during the sync period + # (These rooms will have been omitted during a previous eager sync.) + forced_newly_joined_room_ids: Set[str] = set() + if since_token and not sync_config.filter_collection.lazy_load_members(): + un_partial_stated_rooms = ( + await self.store.get_un_partial_stated_rooms_between( + since_token.un_partial_stated_rooms_key, + now_token.un_partial_stated_rooms_key, + mutable_joined_room_ids, + ) + ) + results = await self.store.is_partial_state_room_batched( + un_partial_stated_rooms + ) + forced_newly_joined_room_ids.update( + room_id + for room_id, is_partial_state in results.items() + if not is_partial_state + ) + + # Now we have our list of joined room IDs, exclude as configured and freeze + joined_room_ids = frozenset( + room_id + for room_id in mutable_joined_room_ids + if room_id not in mutable_rooms_to_exclude + ) + + sync_result_builder = SyncResultBuilder( + sync_config, + full_state, + since_token=since_token, + now_token=now_token, + joined_room_ids=joined_room_ids, + excluded_room_ids=frozenset(mutable_rooms_to_exclude), + forced_newly_joined_room_ids=frozenset(forced_newly_joined_room_ids), + membership_change_events=membership_change_events, + ) + + return sync_result_builder + @measure_func("_generate_sync_entry_for_device_list") async def _generate_sync_entry_for_device_list( self, @@ -1799,42 +2087,18 @@ class SyncHandler: users_that_have_changed = set() - joined_rooms = sync_result_builder.joined_room_ids + joined_room_ids = sync_result_builder.joined_room_ids # Step 1a, check for changes in devices of users we share a room # with - # - # We do this in two different ways depending on what we have cached. - # If we already have a list of all the user that have changed since - # the last sync then it's likely more efficient to compare the rooms - # they're in with the rooms the syncing user is in. - # - # If we don't have that info cached then we get all the users that - # share a room with our user and check if those users have changed. - cache_result = self.store.get_cached_device_list_changes( - since_token.device_list_key - ) - if cache_result.hit: - changed_users = cache_result.entities - - result = await self.store.get_rooms_for_users(changed_users) - - for changed_user_id, entries in result.items(): - # Check if the changed user shares any rooms with the user, - # or if the changed user is the syncing user (as we always - # want to include device list updates of their own devices). - if user_id == changed_user_id or any( - rid in joined_rooms for rid in entries - ): - users_that_have_changed.add(changed_user_id) - else: - users_that_have_changed = ( - await self._device_handler.get_device_changes_in_shared_rooms( - user_id, - sync_result_builder.joined_room_ids, - from_token=since_token, - ) + users_that_have_changed = ( + await self._device_handler.get_device_changes_in_shared_rooms( + user_id, + joined_room_ids, + from_token=since_token, + now_token=sync_result_builder.now_token, ) + ) # Step 1b, check for newly joined rooms for room_id in newly_joined_rooms: @@ -1858,7 +2122,7 @@ class SyncHandler: # Remove any users that we still share a room with. left_users_rooms = await self.store.get_rooms_for_users(newly_left_users) for user_id, entries in left_users_rooms.items(): - if any(rid in joined_rooms for rid in entries): + if any(rid in joined_room_ids for rid in entries): newly_left_users.discard(user_id) return DeviceListUpdates(changed=users_that_have_changed, left=newly_left_users) @@ -1945,23 +2209,19 @@ class SyncHandler: ) if push_rules_changed: - global_account_data = { - AccountDataTypes.PUSH_RULES: await self._push_rules_handler.push_rules_for_user( - sync_config.user - ), - **global_account_data, - } + global_account_data = dict(global_account_data) + global_account_data[AccountDataTypes.PUSH_RULES] = ( + await self._push_rules_handler.push_rules_for_user(sync_config.user) + ) else: all_global_account_data = await self.store.get_global_account_data_for_user( user_id ) - global_account_data = { - AccountDataTypes.PUSH_RULES: await self._push_rules_handler.push_rules_for_user( - sync_config.user - ), - **all_global_account_data, - } + global_account_data = dict(all_global_account_data) + global_account_data[AccountDataTypes.PUSH_RULES] = ( + await self._push_rules_handler.push_rules_for_user(sync_config.user) + ) account_data_for_user = ( await sync_config.filter_collection.filter_global_account_data( @@ -2248,7 +2508,7 @@ class SyncHandler: continue if room_id in sync_result_builder.joined_room_ids or has_join: - old_state_ids = await self.get_state_at( + old_state_ids = await self._state_storage_controller.get_state_at( room_id, since_token, state_filter=StateFilter.from_types([(EventTypes.Member, user_id)]), @@ -2278,12 +2538,14 @@ class SyncHandler: newly_left_rooms.append(room_id) else: if not old_state_ids: - old_state_ids = await self.get_state_at( - room_id, - since_token, - state_filter=StateFilter.from_types( - [(EventTypes.Member, user_id)] - ), + old_state_ids = ( + await self._state_storage_controller.get_state_at( + room_id, + since_token, + state_filter=StateFilter.from_types( + [(EventTypes.Member, user_id)] + ), + ) ) old_mem_ev_id = old_state_ids.get( (EventTypes.Member, user_id), None @@ -2488,7 +2750,7 @@ class SyncHandler: continue leave_token = now_token.copy_and_replace( - StreamKeyType.ROOM, RoomStreamToken(stream=event.stream_ordering) + StreamKeyType.ROOM, RoomStreamToken(stream=event.event_pos.stream) ) room_entries.append( RoomSyncResultBuilder( diff --git a/synapse/handlers/typing.py b/synapse/handlers/typing.py index 7619d91c98..4c87718337 100644 --- a/synapse/handlers/typing.py +++ b/synapse/handlers/typing.py @@ -477,9 +477,9 @@ class TypingWriterHandler(FollowerTypingHandler): rows = [] for room_id in changed_rooms: - serial = self._room_serials[room_id] - if last_id < serial <= current_id: - typing = self._room_typing[room_id] + serial = self._room_serials.get(room_id) + if serial and last_id < serial <= current_id: + typing = self._room_typing.get(room_id, set()) rows.append((serial, [room_id, list(typing)])) rows.sort() diff --git a/synapse/http/matrixfederationclient.py b/synapse/http/matrixfederationclient.py index c73a589e6c..104b803b0f 100644 --- a/synapse/http/matrixfederationclient.py +++ b/synapse/http/matrixfederationclient.py @@ -57,7 +57,7 @@ from twisted.internet.interfaces import IReactorTime from twisted.internet.task import Cooperator from twisted.web.client import ResponseFailed from twisted.web.http_headers import Headers -from twisted.web.iweb import IAgent, IBodyProducer, IResponse +from twisted.web.iweb import UNKNOWN_LENGTH, IAgent, IBodyProducer, IResponse import synapse.metrics import synapse.util.retryutils @@ -68,6 +68,7 @@ from synapse.api.errors import ( RequestSendFailed, SynapseError, ) +from synapse.api.ratelimiting import Ratelimiter from synapse.crypto.context_factory import FederationPolicyForHTTPS from synapse.http import QuieterFileBodyProducer from synapse.http.client import ( @@ -1411,9 +1412,11 @@ class MatrixFederationHttpClient: destination: str, path: str, output_stream: BinaryIO, + download_ratelimiter: Ratelimiter, + ip_address: str, + max_size: int, args: Optional[QueryParams] = None, retry_on_dns_fail: bool = True, - max_size: Optional[int] = None, ignore_backoff: bool = False, follow_redirects: bool = False, ) -> Tuple[int, Dict[bytes, List[bytes]]]: @@ -1422,6 +1425,10 @@ class MatrixFederationHttpClient: destination: The remote server to send the HTTP request to. path: The HTTP path to GET. output_stream: File to write the response body to. + download_ratelimiter: a ratelimiter to limit remote media downloads, keyed to + requester IP + ip_address: IP address of the requester + max_size: maximum allowable size in bytes of the file args: Optional dictionary used to create the query string. ignore_backoff: true to ignore the historical backoff data and try the request anyway. @@ -1441,11 +1448,27 @@ class MatrixFederationHttpClient: federation whitelist RequestSendFailed: If there were problems connecting to the remote, due to e.g. DNS failures, connection timeouts etc. + SynapseError: If the requested file exceeds ratelimits """ request = MatrixFederationRequest( method="GET", destination=destination, path=path, query=args ) + # check for a minimum balance of 1MiB in ratelimiter before initiating request + send_req, _ = await download_ratelimiter.can_do_action( + requester=None, key=ip_address, n_actions=1048576, update=False + ) + + if not send_req: + msg = "Requested file size exceeds ratelimits" + logger.warning( + "{%s} [%s] %s", + request.txn_id, + request.destination, + msg, + ) + raise SynapseError(HTTPStatus.TOO_MANY_REQUESTS, msg, Codes.LIMIT_EXCEEDED) + response = await self._send_request( request, retry_on_dns_fail=retry_on_dns_fail, @@ -1455,12 +1478,36 @@ class MatrixFederationHttpClient: headers = dict(response.headers.getAllRawHeaders()) + expected_size = response.length + # if we don't get an expected length then use the max length + if expected_size == UNKNOWN_LENGTH: + expected_size = max_size + logger.debug( + f"File size unknown, assuming file is max allowable size: {max_size}" + ) + + read_body, _ = await download_ratelimiter.can_do_action( + requester=None, + key=ip_address, + n_actions=expected_size, + ) + if not read_body: + msg = "Requested file size exceeds ratelimits" + logger.warning( + "{%s} [%s] %s", + request.txn_id, + request.destination, + msg, + ) + raise SynapseError(HTTPStatus.TOO_MANY_REQUESTS, msg, Codes.LIMIT_EXCEEDED) + try: - d = read_body_with_max_size(response, output_stream, max_size) + # add a byte of headroom to max size as function errs at >= + d = read_body_with_max_size(response, output_stream, expected_size + 1) d.addTimeout(self.default_timeout_seconds, self.reactor) length = await make_deferred_yieldable(d) except BodyExceededMaxSize: - msg = "Requested file is too large > %r bytes" % (max_size,) + msg = "Requested file is too large > %r bytes" % (expected_size,) logger.warning( "{%s} [%s] %s", request.txn_id, diff --git a/synapse/http/servlet.py b/synapse/http/servlet.py index ab12951da8..08b8ff7afd 100644 --- a/synapse/http/servlet.py +++ b/synapse/http/servlet.py @@ -119,14 +119,15 @@ def parse_integer( default: value to use if the parameter is absent, defaults to None. required: whether to raise a 400 SynapseError if the parameter is absent, defaults to False. - negative: whether to allow negative integers, defaults to True. + negative: whether to allow negative integers, defaults to False (disallowing + negatives). Returns: An int value or the default. Raises: SynapseError: if the parameter is absent and required, if the parameter is present and not an integer, or if the - parameter is illegitimate negative. + parameter is illegitimately negative. """ args: Mapping[bytes, Sequence[bytes]] = request.args # type: ignore return parse_integer_from_args(args, name, default, required, negative) @@ -164,7 +165,7 @@ def parse_integer_from_args( name: str, default: Optional[int] = None, required: bool = False, - negative: bool = True, + negative: bool = False, ) -> Optional[int]: """Parse an integer parameter from the request string @@ -174,7 +175,8 @@ def parse_integer_from_args( default: value to use if the parameter is absent, defaults to None. required: whether to raise a 400 SynapseError if the parameter is absent, defaults to False. - negative: whether to allow negative integers, defaults to True. + negative: whether to allow negative integers, defaults to False (disallowing + negatives). Returns: An int value or the default. @@ -182,7 +184,7 @@ def parse_integer_from_args( Raises: SynapseError: if the parameter is absent and required, if the parameter is present and not an integer, or if the - parameter is illegitimate negative. + parameter is illegitimately negative. """ name_bytes = name.encode("ascii") diff --git a/synapse/media/_base.py b/synapse/media/_base.py index 3fbed6062f..7ad0b7c3cf 100644 --- a/synapse/media/_base.py +++ b/synapse/media/_base.py @@ -25,7 +25,16 @@ import os import urllib from abc import ABC, abstractmethod from types import TracebackType -from typing import Awaitable, Dict, Generator, List, Optional, Tuple, Type +from typing import ( + TYPE_CHECKING, + Awaitable, + Dict, + Generator, + List, + Optional, + Tuple, + Type, +) import attr @@ -37,8 +46,13 @@ from synapse.api.errors import Codes, cs_error from synapse.http.server import finish_request, respond_with_json from synapse.http.site import SynapseRequest from synapse.logging.context import make_deferred_yieldable +from synapse.util import Clock from synapse.util.stringutils import is_ascii +if TYPE_CHECKING: + from synapse.storage.databases.main.media_repository import LocalMedia + + logger = logging.getLogger(__name__) # list all text content types that will have the charset default to UTF-8 when @@ -260,6 +274,68 @@ def _can_encode_filename_as_token(x: str) -> bool: return True +async def respond_with_multipart_responder( + clock: Clock, + request: SynapseRequest, + responder: "Optional[Responder]", + media_info: "LocalMedia", +) -> None: + """ + Responds to requests originating from the federation media `/download` endpoint by + streaming a multipart/mixed response + + Args: + clock: + request: the federation request to respond to + responder: the responder which will send the response + media_info: metadata about the media item + """ + if not responder: + respond_404(request) + return + + # If we have a responder we *must* use it as a context manager. + with responder: + if request._disconnected: + logger.warning( + "Not sending response to request %s, already disconnected.", request + ) + return + + from synapse.media.media_storage import MultipartFileConsumer + + # note that currently the json_object is just {}, this will change when linked media + # is implemented + multipart_consumer = MultipartFileConsumer( + clock, request, media_info.media_type, {}, media_info.media_length + ) + + logger.debug("Responding to media request with responder %s", responder) + if media_info.media_length is not None: + content_length = multipart_consumer.content_length() + assert content_length is not None + request.setHeader(b"Content-Length", b"%d" % (content_length,)) + + request.setHeader( + b"Content-Type", + b"multipart/mixed; boundary=%s" % multipart_consumer.boundary, + ) + + try: + await responder.write_to_consumer(multipart_consumer) + except Exception as e: + # The majority of the time this will be due to the client having gone + # away. Unfortunately, Twisted simply throws a generic exception at us + # in that case. + logger.warning("Failed to write to consumer: %s %s", type(e), e) + + # Unregister the producer, if it has one, so Twisted doesn't complain + if request.producer: + request.unregisterProducer() + + finish_request(request) + + async def respond_with_responder( request: SynapseRequest, responder: "Optional[Responder]", diff --git a/synapse/media/media_repository.py b/synapse/media/media_repository.py index 0e875132f6..1436329fad 100644 --- a/synapse/media/media_repository.py +++ b/synapse/media/media_repository.py @@ -42,6 +42,7 @@ from synapse.api.errors import ( SynapseError, cs_error, ) +from synapse.api.ratelimiting import Ratelimiter from synapse.config.repository import ThumbnailRequirement from synapse.http.server import respond_with_json from synapse.http.site import SynapseRequest @@ -53,6 +54,7 @@ from synapse.media._base import ( ThumbnailInfo, get_filename_from_headers, respond_404, + respond_with_multipart_responder, respond_with_responder, ) from synapse.media.filepath import MediaFilePaths @@ -111,6 +113,12 @@ class MediaRepository: ) self.prevent_media_downloads_from = hs.config.media.prevent_media_downloads_from + self.download_ratelimiter = Ratelimiter( + store=hs.get_storage_controllers().main, + clock=hs.get_clock(), + cfg=hs.config.ratelimiting.remote_media_downloads, + ) + # List of StorageProviders where we should search for media and # potentially upload to. storage_providers = [] @@ -422,6 +430,7 @@ class MediaRepository: media_id: str, name: Optional[str], max_timeout_ms: int, + federation: bool = False, ) -> None: """Responds to requests for local media, if exists, or returns 404. @@ -433,6 +442,7 @@ class MediaRepository: the filename in the Content-Disposition header of the response. max_timeout_ms: the maximum number of milliseconds to wait for the media to be uploaded. + federation: whether the local media being fetched is for a federation request Returns: Resolves once a response has successfully been written to request @@ -453,9 +463,14 @@ class MediaRepository: file_info = FileInfo(None, media_id, url_cache=bool(url_cache)) responder = await self.media_storage.fetch_media(file_info) - await respond_with_responder( - request, responder, media_type, media_length, upload_name - ) + if federation: + await respond_with_multipart_responder( + self.clock, request, responder, media_info + ) + else: + await respond_with_responder( + request, responder, media_type, media_length, upload_name + ) async def get_remote_media( self, @@ -464,6 +479,7 @@ class MediaRepository: media_id: str, name: Optional[str], max_timeout_ms: int, + ip_address: str, ) -> None: """Respond to requests for remote media. @@ -475,6 +491,7 @@ class MediaRepository: the filename in the Content-Disposition header of the response. max_timeout_ms: the maximum number of milliseconds to wait for the media to be uploaded. + ip_address: the IP address of the requester Returns: Resolves once a response has successfully been written to request @@ -500,7 +517,11 @@ class MediaRepository: key = (server_name, media_id) async with self.remote_media_linearizer.queue(key): responder, media_info = await self._get_remote_media_impl( - server_name, media_id, max_timeout_ms + server_name, + media_id, + max_timeout_ms, + self.download_ratelimiter, + ip_address, ) # We deliberately stream the file outside the lock @@ -517,7 +538,7 @@ class MediaRepository: respond_404(request) async def get_remote_media_info( - self, server_name: str, media_id: str, max_timeout_ms: int + self, server_name: str, media_id: str, max_timeout_ms: int, ip_address: str ) -> RemoteMedia: """Gets the media info associated with the remote file, downloading if necessary. @@ -527,6 +548,7 @@ class MediaRepository: media_id: The media ID of the content (as defined by the remote server). max_timeout_ms: the maximum number of milliseconds to wait for the media to be uploaded. + ip_address: IP address of the requester Returns: The media info of the file @@ -542,7 +564,11 @@ class MediaRepository: key = (server_name, media_id) async with self.remote_media_linearizer.queue(key): responder, media_info = await self._get_remote_media_impl( - server_name, media_id, max_timeout_ms + server_name, + media_id, + max_timeout_ms, + self.download_ratelimiter, + ip_address, ) # Ensure we actually use the responder so that it releases resources @@ -553,7 +579,12 @@ class MediaRepository: return media_info async def _get_remote_media_impl( - self, server_name: str, media_id: str, max_timeout_ms: int + self, + server_name: str, + media_id: str, + max_timeout_ms: int, + download_ratelimiter: Ratelimiter, + ip_address: str, ) -> Tuple[Optional[Responder], RemoteMedia]: """Looks for media in local cache, if not there then attempt to download from remote server. @@ -564,6 +595,9 @@ class MediaRepository: remote server). max_timeout_ms: the maximum number of milliseconds to wait for the media to be uploaded. + download_ratelimiter: a ratelimiter limiting remote media downloads, keyed to + requester IP. + ip_address: the IP address of the requester Returns: A tuple of responder and the media info of the file. @@ -596,7 +630,7 @@ class MediaRepository: try: media_info = await self._download_remote_file( - server_name, media_id, max_timeout_ms + server_name, media_id, max_timeout_ms, download_ratelimiter, ip_address ) except SynapseError: raise @@ -630,6 +664,8 @@ class MediaRepository: server_name: str, media_id: str, max_timeout_ms: int, + download_ratelimiter: Ratelimiter, + ip_address: str, ) -> RemoteMedia: """Attempt to download the remote file from the given server name, using the given file_id as the local id. @@ -641,6 +677,9 @@ class MediaRepository: locally generated. max_timeout_ms: the maximum number of milliseconds to wait for the media to be uploaded. + download_ratelimiter: a ratelimiter limiting remote media downloads, keyed to + requester IP + ip_address: the IP address of the requester Returns: The media info of the file. @@ -650,7 +689,7 @@ class MediaRepository: file_info = FileInfo(server_name=server_name, file_id=file_id) - with self.media_storage.store_into_file(file_info) as (f, fname, finish): + async with self.media_storage.store_into_file(file_info) as (f, fname): try: length, headers = await self.client.download_media( server_name, @@ -658,6 +697,8 @@ class MediaRepository: output_stream=f, max_size=self.max_upload_size, max_timeout_ms=max_timeout_ms, + download_ratelimiter=download_ratelimiter, + ip_address=ip_address, ) except RequestSendFailed as e: logger.warning( @@ -693,8 +734,6 @@ class MediaRepository: ) raise SynapseError(502, "Failed to fetch remote media") - await finish() - if b"Content-Type" in headers: media_type = headers[b"Content-Type"][0].decode("ascii") else: @@ -1045,17 +1084,17 @@ class MediaRepository: ), ) - with self.media_storage.store_into_file(file_info) as ( - f, - fname, - finish, - ): + async with self.media_storage.store_into_file(file_info) as (f, fname): try: await self.media_storage.write_to_file(t_byte_source, f) - await finish() finally: t_byte_source.close() + # We flush and close the file to ensure that the bytes have + # been written before getting the size. + f.flush() + f.close() + t_len = os.path.getsize(fname) # Write to database diff --git a/synapse/media/media_storage.py b/synapse/media/media_storage.py index b45b319f5c..1be2c9b5f5 100644 --- a/synapse/media/media_storage.py +++ b/synapse/media/media_storage.py @@ -19,36 +19,49 @@ # # import contextlib +import json import logging import os import shutil +from contextlib import closing +from io import BytesIO from types import TracebackType from typing import ( IO, TYPE_CHECKING, Any, - Awaitable, + AsyncIterator, BinaryIO, Callable, - Generator, + List, Optional, Sequence, Tuple, Type, + Union, + cast, ) +from uuid import uuid4 import attr +from zope.interface import implementer +from twisted.internet import interfaces from twisted.internet.defer import Deferred from twisted.internet.interfaces import IConsumer from twisted.protocols.basic import FileSender from synapse.api.errors import NotFoundError -from synapse.logging.context import defer_to_thread, make_deferred_yieldable +from synapse.logging.context import ( + defer_to_thread, + make_deferred_yieldable, + run_in_background, +) from synapse.logging.opentracing import start_active_span, trace, trace_with_opname from synapse.util import Clock from synapse.util.file_consumer import BackgroundFileConsumer +from ..types import JsonDict from ._base import FileInfo, Responder from .filepath import MediaFilePaths @@ -58,6 +71,8 @@ if TYPE_CHECKING: logger = logging.getLogger(__name__) +CRLF = b"\r\n" + class MediaStorage: """Responsible for storing/fetching files from local sources. @@ -97,11 +112,9 @@ class MediaStorage: the file path written to in the primary media store """ - with self.store_into_file(file_info) as (f, fname, finish_cb): + async with self.store_into_file(file_info) as (f, fname): # Write to the main media repository await self.write_to_file(source, f) - # Write to the other storage providers - await finish_cb() return fname @@ -111,32 +124,27 @@ class MediaStorage: await defer_to_thread(self.reactor, _write_file_synchronously, source, output) @trace_with_opname("MediaStorage.store_into_file") - @contextlib.contextmanager - def store_into_file( + @contextlib.asynccontextmanager + async def store_into_file( self, file_info: FileInfo - ) -> Generator[Tuple[BinaryIO, str, Callable[[], Awaitable[None]]], None, None]: - """Context manager used to get a file like object to write into, as + ) -> AsyncIterator[Tuple[BinaryIO, str]]: + """Async Context manager used to get a file like object to write into, as described by file_info. - Actually yields a 3-tuple (file, fname, finish_cb), where file is a file - like object that can be written to, fname is the absolute path of file - on disk, and finish_cb is a function that returns an awaitable. + Actually yields a 2-tuple (file, fname,), where file is a file + like object that can be written to and fname is the absolute path of file + on disk. fname can be used to read the contents from after upload, e.g. to generate thumbnails. - finish_cb must be called and waited on after the file has been successfully been - written to. Should not be called if there was an error. Checks for spam and - stores the file into the configured storage providers. - Args: file_info: Info about the file to store Example: - with media_storage.store_into_file(info) as (f, fname, finish_cb): + async with media_storage.store_into_file(info) as (f, fname,): # .. write into f ... - await finish_cb() """ path = self._file_info_to_path(file_info) @@ -145,69 +153,44 @@ class MediaStorage: dirname = os.path.dirname(fname) os.makedirs(dirname, exist_ok=True) - finished_called = [False] - - main_media_repo_write_trace_scope = start_active_span( - "writing to main media repo" - ) - main_media_repo_write_trace_scope.__enter__() - try: - with open(fname, "wb") as f: - - async def finish() -> None: - # When someone calls finish, we assume they are done writing to the main media repo - main_media_repo_write_trace_scope.__exit__(None, None, None) - - with start_active_span("writing to other storage providers"): - # Ensure that all writes have been flushed and close the - # file. - f.flush() - f.close() - - spam_check = await self._spam_checker_module_callbacks.check_media_file_for_spam( - ReadableFileWrapper(self.clock, fname), file_info - ) - if spam_check != self._spam_checker_module_callbacks.NOT_SPAM: - logger.info("Blocking media due to spam checker") - # Note that we'll delete the stored media, due to the - # try/except below. The media also won't be stored in - # the DB. - # We currently ignore any additional field returned by - # the spam-check API. - raise SpamMediaException(errcode=spam_check[0]) - - for provider in self.storage_providers: - with start_active_span(str(provider)): - await provider.store_file(path, file_info) - - finished_called[0] = True - - yield f, fname, finish + with start_active_span("writing to main media repo"): + with open(fname, "wb") as f: + yield f, fname + + with start_active_span("writing to other storage providers"): + spam_check = ( + await self._spam_checker_module_callbacks.check_media_file_for_spam( + ReadableFileWrapper(self.clock, fname), file_info + ) + ) + if spam_check != self._spam_checker_module_callbacks.NOT_SPAM: + logger.info("Blocking media due to spam checker") + # Note that we'll delete the stored media, due to the + # try/except below. The media also won't be stored in + # the DB. + # We currently ignore any additional field returned by + # the spam-check API. + raise SpamMediaException(errcode=spam_check[0]) + + for provider in self.storage_providers: + with start_active_span(str(provider)): + await provider.store_file(path, file_info) + except Exception as e: try: - main_media_repo_write_trace_scope.__exit__( - type(e), None, e.__traceback__ - ) os.remove(fname) except Exception: pass raise e from None - if not finished_called: - exc = Exception("Finished callback not called") - main_media_repo_write_trace_scope.__exit__( - type(exc), None, exc.__traceback__ - ) - raise exc - async def fetch_media(self, file_info: FileInfo) -> Optional[Responder]: """Attempts to fetch media described by file_info from the local cache and configured storage providers. Args: - file_info + file_info: Metadata about the media file Returns: Returns a Responder if the file was found, otherwise None. @@ -349,7 +332,7 @@ class FileResponder(Responder): """Wraps an open file that can be sent to a request. Args: - open_file: A file like object to be streamed ot the client, + open_file: A file like object to be streamed to the client, is closed when finished streaming. """ @@ -403,3 +386,240 @@ class ReadableFileWrapper: # We yield to the reactor by sleeping for 0 seconds. await self.clock.sleep(0) + + +@implementer(interfaces.IConsumer) +@implementer(interfaces.IPushProducer) +class MultipartFileConsumer: + """Wraps a given consumer so that any data that gets written to it gets + converted to a multipart format. + """ + + def __init__( + self, + clock: Clock, + wrapped_consumer: interfaces.IConsumer, + file_content_type: str, + json_object: JsonDict, + content_length: Optional[int] = None, + ) -> None: + self.clock = clock + self.wrapped_consumer = wrapped_consumer + self.json_field = json_object + self.json_field_written = False + self.content_type_written = False + self.file_content_type = file_content_type + self.boundary = uuid4().hex.encode("ascii") + + # The producer that registered with us, and if it's a push or pull + # producer. + self.producer: Optional["interfaces.IProducer"] = None + self.streaming: Optional[bool] = None + + # Whether the wrapped consumer has asked us to pause. + self.paused = False + + self.length = content_length + + ### IConsumer APIs ### + + def registerProducer( + self, producer: "interfaces.IProducer", streaming: bool + ) -> None: + """ + Register to receive data from a producer. + + This sets self to be a consumer for a producer. When this object runs + out of data (as when a send(2) call on a socket succeeds in moving the + last data from a userspace buffer into a kernelspace buffer), it will + ask the producer to resumeProducing(). + + For L{IPullProducer} providers, C{resumeProducing} will be called once + each time data is required. + + For L{IPushProducer} providers, C{pauseProducing} will be called + whenever the write buffer fills up and C{resumeProducing} will only be + called when it empties. The consumer will only call C{resumeProducing} + to balance a previous C{pauseProducing} call; the producer is assumed + to start in an un-paused state. + + @param streaming: C{True} if C{producer} provides L{IPushProducer}, + C{False} if C{producer} provides L{IPullProducer}. + + @raise RuntimeError: If a producer is already registered. + """ + self.producer = producer + self.streaming = streaming + + self.wrapped_consumer.registerProducer(self, True) + + # kick off producing if `self.producer` is not a streaming producer + if not streaming: + self.resumeProducing() + + def unregisterProducer(self) -> None: + """ + Stop consuming data from a producer, without disconnecting. + """ + self.wrapped_consumer.write(CRLF + b"--" + self.boundary + b"--" + CRLF) + self.wrapped_consumer.unregisterProducer() + self.paused = True + + def write(self, data: bytes) -> None: + """ + The producer will write data by calling this method. + + The implementation must be non-blocking and perform whatever + buffering is necessary. If the producer has provided enough data + for now and it is a L{IPushProducer}, the consumer may call its + C{pauseProducing} method. + """ + if not self.json_field_written: + self.wrapped_consumer.write(CRLF + b"--" + self.boundary + CRLF) + + content_type = Header(b"Content-Type", b"application/json") + self.wrapped_consumer.write(bytes(content_type) + CRLF) + + json_field = json.dumps(self.json_field) + json_bytes = json_field.encode("utf-8") + self.wrapped_consumer.write(CRLF + json_bytes) + self.wrapped_consumer.write(CRLF + b"--" + self.boundary + CRLF) + + self.json_field_written = True + + # if we haven't written the content type yet, do so + if not self.content_type_written: + type = self.file_content_type.encode("utf-8") + content_type = Header(b"Content-Type", type) + self.wrapped_consumer.write(bytes(content_type) + CRLF + CRLF) + self.content_type_written = True + + self.wrapped_consumer.write(data) + + ### IPushProducer APIs ### + + def stopProducing(self) -> None: + """ + Stop producing data. + + This tells a producer that its consumer has died, so it must stop + producing data for good. + """ + assert self.producer is not None + + self.paused = True + self.producer.stopProducing() + + def pauseProducing(self) -> None: + """ + Pause producing data. + + Tells a producer that it has produced too much data to process for + the time being, and to stop until C{resumeProducing()} is called. + """ + assert self.producer is not None + + self.paused = True + + if self.streaming: + cast("interfaces.IPushProducer", self.producer).pauseProducing() + else: + self.paused = True + + def resumeProducing(self) -> None: + """ + Resume producing data. + + This tells a producer to re-add itself to the main loop and produce + more data for its consumer. + """ + assert self.producer is not None + + if self.streaming: + cast("interfaces.IPushProducer", self.producer).resumeProducing() + else: + # If the producer is not a streaming producer we need to start + # repeatedly calling `resumeProducing` in a loop. + run_in_background(self._resumeProducingRepeatedly) + + def content_length(self) -> Optional[int]: + """ + Calculate the content length of the multipart response + in bytes. + """ + if not self.length: + return None + # calculate length of json field and content-type header + json_field = json.dumps(self.json_field) + json_bytes = json_field.encode("utf-8") + json_length = len(json_bytes) + + type = self.file_content_type.encode("utf-8") + content_type = Header(b"Content-Type", type) + type_length = len(bytes(content_type)) + + # 154 is the length of the elements that aren't variable, ie + # CRLFs and boundary strings, etc + self.length += json_length + type_length + 154 + + return self.length + + ### Internal APIs. ### + + async def _resumeProducingRepeatedly(self) -> None: + assert self.producer is not None + assert not self.streaming + + producer = cast("interfaces.IPullProducer", self.producer) + + self.paused = False + while not self.paused: + producer.resumeProducing() + await self.clock.sleep(0) + + +class Header: + """ + `Header` This class is a tiny wrapper that produces + request headers. We can't use standard python header + class because it encodes unicode fields using =? bla bla ?= + encoding, which is correct, but no one in HTTP world expects + that, everyone wants utf-8 raw bytes. (stolen from treq.multipart) + + """ + + def __init__( + self, + name: bytes, + value: Any, + params: Optional[List[Tuple[Any, Any]]] = None, + ): + self.name = name + self.value = value + self.params = params or [] + + def add_param(self, name: Any, value: Any) -> None: + self.params.append((name, value)) + + def __bytes__(self) -> bytes: + with closing(BytesIO()) as h: + h.write(self.name + b": " + escape(self.value).encode("us-ascii")) + if self.params: + for name, val in self.params: + h.write(b"; ") + h.write(escape(name).encode("us-ascii")) + h.write(b"=") + h.write(b'"' + escape(val).encode("utf-8") + b'"') + h.seek(0) + return h.read() + + +def escape(value: Union[str, bytes]) -> str: + """ + This function prevents header values from corrupting the request, + a newline in the file name parameter makes form-data request unreadable + for a majority of parsers. (stolen from treq.multipart) + """ + if isinstance(value, bytes): + value = value.decode("utf-8") + return value.replace("\r", "").replace("\n", "").replace('"', '\\"') diff --git a/synapse/media/thumbnailer.py b/synapse/media/thumbnailer.py index 5538020bec..f8a9560784 100644 --- a/synapse/media/thumbnailer.py +++ b/synapse/media/thumbnailer.py @@ -22,11 +22,27 @@ import logging from io import BytesIO from types import TracebackType -from typing import Optional, Tuple, Type +from typing import TYPE_CHECKING, List, Optional, Tuple, Type from PIL import Image +from synapse.api.errors import Codes, SynapseError, cs_error +from synapse.config.repository import THUMBNAIL_SUPPORTED_MEDIA_FORMAT_MAP +from synapse.http.server import respond_with_json +from synapse.http.site import SynapseRequest from synapse.logging.opentracing import trace +from synapse.media._base import ( + FileInfo, + ThumbnailInfo, + respond_404, + respond_with_file, + respond_with_responder, +) +from synapse.media.media_storage import MediaStorage + +if TYPE_CHECKING: + from synapse.media.media_repository import MediaRepository + from synapse.server import HomeServer logger = logging.getLogger(__name__) @@ -231,3 +247,473 @@ class Thumbnailer: def __del__(self) -> None: # Make sure we actually do close the image, rather than leak data. self.close() + + +class ThumbnailProvider: + def __init__( + self, + hs: "HomeServer", + media_repo: "MediaRepository", + media_storage: MediaStorage, + ): + self.hs = hs + self.media_repo = media_repo + self.media_storage = media_storage + self.store = hs.get_datastores().main + self.dynamic_thumbnails = hs.config.media.dynamic_thumbnails + + async def respond_local_thumbnail( + self, + request: SynapseRequest, + media_id: str, + width: int, + height: int, + method: str, + m_type: str, + max_timeout_ms: int, + ) -> None: + media_info = await self.media_repo.get_local_media_info( + request, media_id, max_timeout_ms + ) + if not media_info: + return + + thumbnail_infos = await self.store.get_local_media_thumbnails(media_id) + await self._select_and_respond_with_thumbnail( + request, + width, + height, + method, + m_type, + thumbnail_infos, + media_id, + media_id, + url_cache=bool(media_info.url_cache), + server_name=None, + ) + + async def select_or_generate_local_thumbnail( + self, + request: SynapseRequest, + media_id: str, + desired_width: int, + desired_height: int, + desired_method: str, + desired_type: str, + max_timeout_ms: int, + ) -> None: + media_info = await self.media_repo.get_local_media_info( + request, media_id, max_timeout_ms + ) + + if not media_info: + return + + thumbnail_infos = await self.store.get_local_media_thumbnails(media_id) + for info in thumbnail_infos: + t_w = info.width == desired_width + t_h = info.height == desired_height + t_method = info.method == desired_method + t_type = info.type == desired_type + + if t_w and t_h and t_method and t_type: + file_info = FileInfo( + server_name=None, + file_id=media_id, + url_cache=bool(media_info.url_cache), + thumbnail=info, + ) + + responder = await self.media_storage.fetch_media(file_info) + if responder: + await respond_with_responder( + request, responder, info.type, info.length + ) + return + + logger.debug("We don't have a thumbnail of that size. Generating") + + # Okay, so we generate one. + file_path = await self.media_repo.generate_local_exact_thumbnail( + media_id, + desired_width, + desired_height, + desired_method, + desired_type, + url_cache=bool(media_info.url_cache), + ) + + if file_path: + await respond_with_file(request, desired_type, file_path) + else: + logger.warning("Failed to generate thumbnail") + raise SynapseError(400, "Failed to generate thumbnail.") + + async def select_or_generate_remote_thumbnail( + self, + request: SynapseRequest, + server_name: str, + media_id: str, + desired_width: int, + desired_height: int, + desired_method: str, + desired_type: str, + max_timeout_ms: int, + ip_address: str, + ) -> None: + media_info = await self.media_repo.get_remote_media_info( + server_name, media_id, max_timeout_ms, ip_address + ) + if not media_info: + respond_404(request) + return + + thumbnail_infos = await self.store.get_remote_media_thumbnails( + server_name, media_id + ) + + file_id = media_info.filesystem_id + + for info in thumbnail_infos: + t_w = info.width == desired_width + t_h = info.height == desired_height + t_method = info.method == desired_method + t_type = info.type == desired_type + + if t_w and t_h and t_method and t_type: + file_info = FileInfo( + server_name=server_name, + file_id=file_id, + thumbnail=info, + ) + + responder = await self.media_storage.fetch_media(file_info) + if responder: + await respond_with_responder( + request, responder, info.type, info.length + ) + return + + logger.debug("We don't have a thumbnail of that size. Generating") + + # Okay, so we generate one. + file_path = await self.media_repo.generate_remote_exact_thumbnail( + server_name, + file_id, + media_id, + desired_width, + desired_height, + desired_method, + desired_type, + ) + + if file_path: + await respond_with_file(request, desired_type, file_path) + else: + logger.warning("Failed to generate thumbnail") + raise SynapseError(400, "Failed to generate thumbnail.") + + async def respond_remote_thumbnail( + self, + request: SynapseRequest, + server_name: str, + media_id: str, + width: int, + height: int, + method: str, + m_type: str, + max_timeout_ms: int, + ip_address: str, + ) -> None: + # TODO: Don't download the whole remote file + # We should proxy the thumbnail from the remote server instead of + # downloading the remote file and generating our own thumbnails. + media_info = await self.media_repo.get_remote_media_info( + server_name, media_id, max_timeout_ms, ip_address + ) + if not media_info: + return + + thumbnail_infos = await self.store.get_remote_media_thumbnails( + server_name, media_id + ) + await self._select_and_respond_with_thumbnail( + request, + width, + height, + method, + m_type, + thumbnail_infos, + media_id, + media_info.filesystem_id, + url_cache=False, + server_name=server_name, + ) + + async def _select_and_respond_with_thumbnail( + self, + request: SynapseRequest, + desired_width: int, + desired_height: int, + desired_method: str, + desired_type: str, + thumbnail_infos: List[ThumbnailInfo], + media_id: str, + file_id: str, + url_cache: bool, + server_name: Optional[str] = None, + ) -> None: + """ + Respond to a request with an appropriate thumbnail from the previously generated thumbnails. + + Args: + request: The incoming request. + desired_width: The desired width, the returned thumbnail may be larger than this. + desired_height: The desired height, the returned thumbnail may be larger than this. + desired_method: The desired method used to generate the thumbnail. + desired_type: The desired content-type of the thumbnail. + thumbnail_infos: A list of thumbnail info of candidate thumbnails. + file_id: The ID of the media that a thumbnail is being requested for. + url_cache: True if this is from a URL cache. + server_name: The server name, if this is a remote thumbnail. + """ + logger.debug( + "_select_and_respond_with_thumbnail: media_id=%s desired=%sx%s (%s) thumbnail_infos=%s", + media_id, + desired_width, + desired_height, + desired_method, + thumbnail_infos, + ) + + # If `dynamic_thumbnails` is enabled, we expect Synapse to go down a + # different code path to handle it. + assert not self.dynamic_thumbnails + + if thumbnail_infos: + file_info = self._select_thumbnail( + desired_width, + desired_height, + desired_method, + desired_type, + thumbnail_infos, + file_id, + url_cache, + server_name, + ) + if not file_info: + logger.info("Couldn't find a thumbnail matching the desired inputs") + respond_404(request) + return + + # The thumbnail property must exist. + assert file_info.thumbnail is not None + + responder = await self.media_storage.fetch_media(file_info) + if responder: + await respond_with_responder( + request, + responder, + file_info.thumbnail.type, + file_info.thumbnail.length, + ) + return + + # If we can't find the thumbnail we regenerate it. This can happen + # if e.g. we've deleted the thumbnails but still have the original + # image somewhere. + # + # Since we have an entry for the thumbnail in the DB we a) know we + # have have successfully generated the thumbnail in the past (so we + # don't need to worry about repeatedly failing to generate + # thumbnails), and b) have already calculated that appropriate + # width/height/method so we can just call the "generate exact" + # methods. + + # First let's check that we do actually have the original image + # still. This will throw a 404 if we don't. + # TODO: We should refetch the thumbnails for remote media. + await self.media_storage.ensure_media_is_in_local_cache( + FileInfo(server_name, file_id, url_cache=url_cache) + ) + + if server_name: + await self.media_repo.generate_remote_exact_thumbnail( + server_name, + file_id=file_id, + media_id=media_id, + t_width=file_info.thumbnail.width, + t_height=file_info.thumbnail.height, + t_method=file_info.thumbnail.method, + t_type=file_info.thumbnail.type, + ) + else: + await self.media_repo.generate_local_exact_thumbnail( + media_id=media_id, + t_width=file_info.thumbnail.width, + t_height=file_info.thumbnail.height, + t_method=file_info.thumbnail.method, + t_type=file_info.thumbnail.type, + url_cache=url_cache, + ) + + responder = await self.media_storage.fetch_media(file_info) + await respond_with_responder( + request, + responder, + file_info.thumbnail.type, + file_info.thumbnail.length, + ) + else: + # This might be because: + # 1. We can't create thumbnails for the given media (corrupted or + # unsupported file type), or + # 2. The thumbnailing process never ran or errored out initially + # when the media was first uploaded (these bugs should be + # reported and fixed). + # Note that we don't attempt to generate a thumbnail now because + # `dynamic_thumbnails` is disabled. + logger.info("Failed to find any generated thumbnails") + + assert request.path is not None + respond_with_json( + request, + 400, + cs_error( + "Cannot find any thumbnails for the requested media ('%s'). This might mean the media is not a supported_media_format=(%s) or that thumbnailing failed for some other reason. (Dynamic thumbnails are disabled on this server.)" + % ( + request.path.decode(), + ", ".join(THUMBNAIL_SUPPORTED_MEDIA_FORMAT_MAP.keys()), + ), + code=Codes.UNKNOWN, + ), + send_cors=True, + ) + + def _select_thumbnail( + self, + desired_width: int, + desired_height: int, + desired_method: str, + desired_type: str, + thumbnail_infos: List[ThumbnailInfo], + file_id: str, + url_cache: bool, + server_name: Optional[str], + ) -> Optional[FileInfo]: + """ + Choose an appropriate thumbnail from the previously generated thumbnails. + + Args: + desired_width: The desired width, the returned thumbnail may be larger than this. + desired_height: The desired height, the returned thumbnail may be larger than this. + desired_method: The desired method used to generate the thumbnail. + desired_type: The desired content-type of the thumbnail. + thumbnail_infos: A list of thumbnail infos of candidate thumbnails. + file_id: The ID of the media that a thumbnail is being requested for. + url_cache: True if this is from a URL cache. + server_name: The server name, if this is a remote thumbnail. + + Returns: + The thumbnail which best matches the desired parameters. + """ + desired_method = desired_method.lower() + + # The chosen thumbnail. + thumbnail_info = None + + d_w = desired_width + d_h = desired_height + + if desired_method == "crop": + # Thumbnails that match equal or larger sizes of desired width/height. + crop_info_list: List[ + Tuple[int, int, int, bool, Optional[int], ThumbnailInfo] + ] = [] + # Other thumbnails. + crop_info_list2: List[ + Tuple[int, int, int, bool, Optional[int], ThumbnailInfo] + ] = [] + for info in thumbnail_infos: + # Skip thumbnails generated with different methods. + if info.method != "crop": + continue + + t_w = info.width + t_h = info.height + aspect_quality = abs(d_w * t_h - d_h * t_w) + min_quality = 0 if d_w <= t_w and d_h <= t_h else 1 + size_quality = abs((d_w - t_w) * (d_h - t_h)) + type_quality = desired_type != info.type + length_quality = info.length + if t_w >= d_w or t_h >= d_h: + crop_info_list.append( + ( + aspect_quality, + min_quality, + size_quality, + type_quality, + length_quality, + info, + ) + ) + else: + crop_info_list2.append( + ( + aspect_quality, + min_quality, + size_quality, + type_quality, + length_quality, + info, + ) + ) + # Pick the most appropriate thumbnail. Some values of `desired_width` and + # `desired_height` may result in a tie, in which case we avoid comparing on + # the thumbnail info and pick the thumbnail that appears earlier + # in the list of candidates. + if crop_info_list: + thumbnail_info = min(crop_info_list, key=lambda t: t[:-1])[-1] + elif crop_info_list2: + thumbnail_info = min(crop_info_list2, key=lambda t: t[:-1])[-1] + elif desired_method == "scale": + # Thumbnails that match equal or larger sizes of desired width/height. + info_list: List[Tuple[int, bool, int, ThumbnailInfo]] = [] + # Other thumbnails. + info_list2: List[Tuple[int, bool, int, ThumbnailInfo]] = [] + + for info in thumbnail_infos: + # Skip thumbnails generated with different methods. + if info.method != "scale": + continue + + t_w = info.width + t_h = info.height + size_quality = abs((d_w - t_w) * (d_h - t_h)) + type_quality = desired_type != info.type + length_quality = info.length + if t_w >= d_w or t_h >= d_h: + info_list.append((size_quality, type_quality, length_quality, info)) + else: + info_list2.append( + (size_quality, type_quality, length_quality, info) + ) + # Pick the most appropriate thumbnail. Some values of `desired_width` and + # `desired_height` may result in a tie, in which case we avoid comparing on + # the thumbnail info and pick the thumbnail that appears earlier + # in the list of candidates. + if info_list: + thumbnail_info = min(info_list, key=lambda t: t[:-1])[-1] + elif info_list2: + thumbnail_info = min(info_list2, key=lambda t: t[:-1])[-1] + + if thumbnail_info: + return FileInfo( + file_id=file_id, + url_cache=url_cache, + server_name=server_name, + thumbnail=thumbnail_info, + ) + + # No matching thumbnail was found. + return None diff --git a/synapse/media/url_previewer.py b/synapse/media/url_previewer.py index 3897823b35..2e65a04789 100644 --- a/synapse/media/url_previewer.py +++ b/synapse/media/url_previewer.py @@ -592,7 +592,7 @@ class UrlPreviewer: file_info = FileInfo(server_name=None, file_id=file_id, url_cache=True) - with self.media_storage.store_into_file(file_info) as (f, fname, finish): + async with self.media_storage.store_into_file(file_info) as (f, fname): if url.startswith("data:"): if not allow_data_urls: raise SynapseError( @@ -603,8 +603,6 @@ class UrlPreviewer: else: download_result = await self._download_url(url, f) - await finish() - try: time_now_ms = self.clock.time_msec() diff --git a/synapse/notifier.py b/synapse/notifier.py index 7c1cd3b5f2..c87eb748c0 100644 --- a/synapse/notifier.py +++ b/synapse/notifier.py @@ -721,7 +721,6 @@ class Notifier: user.to_string(), new_events, is_peeking=is_peeking, - msc4115_membership_on_events=self.hs.config.experimental.msc4115_membership_on_events, ) elif keyname == StreamKeyType.PRESENCE: now = self.clock.time_msec() @@ -763,6 +762,29 @@ class Notifier: return result + async def wait_for_stream_token(self, stream_token: StreamToken) -> bool: + """Wait for this worker to catch up with the given stream token.""" + + start = self.clock.time_msec() + while True: + current_token = self.event_sources.get_current_token() + if stream_token.is_before_or_eq(current_token): + return True + + now = self.clock.time_msec() + + if now - start > 10_000: + return False + + logger.info( + "Waiting for current token to reach %s; currently at %s", + stream_token, + current_token, + ) + + # TODO: be better + await self.clock.sleep(0.5) + async def _get_room_ids( self, user: UserID, explicit_room_id: Optional[str] ) -> Tuple[StrCollection, bool]: diff --git a/synapse/push/mailer.py b/synapse/push/mailer.py index 49ce9d6dda..cf611bd90b 100644 --- a/synapse/push/mailer.py +++ b/synapse/push/mailer.py @@ -28,7 +28,7 @@ import jinja2 from markupsafe import Markup from prometheus_client import Counter -from synapse.api.constants import EventTypes, Membership, RoomTypes +from synapse.api.constants import EventContentFields, EventTypes, Membership, RoomTypes from synapse.api.errors import StoreError from synapse.config.emailconfig import EmailSubjectConfig from synapse.events import EventBase @@ -532,7 +532,6 @@ class Mailer: self._storage_controllers, user_id, results.events_before, - msc4115_membership_on_events=self.hs.config.experimental.msc4115_membership_on_events, ) the_events.append(notif_event) @@ -717,7 +716,8 @@ class Mailer: ) if ( create_event - and create_event.content.get("room_type") == RoomTypes.SPACE + and create_event.content.get(EventContentFields.ROOM_TYPE) + == RoomTypes.SPACE ): return self.email_subjects.invite_from_person_to_space % { "person": inviter_name, diff --git a/synapse/replication/tcp/client.py b/synapse/replication/tcp/client.py index ba257d34e6..3dddbb70b4 100644 --- a/synapse/replication/tcp/client.py +++ b/synapse/replication/tcp/client.py @@ -55,6 +55,7 @@ from synapse.replication.tcp.streams.partial_state import ( ) from synapse.types import PersistedEventPosition, ReadReceipt, StreamKeyType, UserID from synapse.util.async_helpers import Linearizer, timeout_deferred +from synapse.util.iterutils import batch_iter from synapse.util.metrics import Measure if TYPE_CHECKING: @@ -111,6 +112,21 @@ class ReplicationDataHandler: token: stream token for this batch of rows rows: a list of Stream.ROW_TYPE objects as returned by Stream.parse_row. """ + all_room_ids: Set[str] = set() + if stream_name == DeviceListsStream.NAME: + if any(not row.is_signature and not row.hosts_calculated for row in rows): + prev_token = self.store.get_device_stream_token() + all_room_ids = await self.store.get_all_device_list_changes( + prev_token, token + ) + self.store.device_lists_in_rooms_have_changed(all_room_ids, token) + + # If we're sending federation we need to update the device lists + # outbound pokes stream change cache with updated hosts. + if self.send_handler and any(row.hosts_calculated for row in rows): + hosts = await self.store.get_destinations_for_device(token) + self.store.device_lists_outbound_pokes_have_changed(hosts, token) + self.store.process_replication_rows(stream_name, instance_name, token, rows) # NOTE: this must be called after process_replication_rows to ensure any # cache invalidations are first handled before any stream ID advances. @@ -145,14 +161,14 @@ class ReplicationDataHandler: StreamKeyType.TO_DEVICE, token, users=entities ) elif stream_name == DeviceListsStream.NAME: - all_room_ids: Set[str] = set() - for row in rows: - if row.entity.startswith("@") and not row.is_signature: - room_ids = await self.store.get_rooms_for_user(row.entity) - all_room_ids.update(room_ids) - self.notifier.on_new_event( - StreamKeyType.DEVICE_LIST, token, rooms=all_room_ids - ) + # `all_room_ids` can be large, so let's wake up those streams in batches + for batched_room_ids in batch_iter(all_room_ids, 100): + self.notifier.on_new_event( + StreamKeyType.DEVICE_LIST, token, rooms=batched_room_ids + ) + + # Yield to reactor so that we don't block. + await self._clock.sleep(0) elif stream_name == PushersStream.NAME: for row in rows: if row.deleted: @@ -423,12 +439,11 @@ class FederationSenderHandler: # The entities are either user IDs (starting with '@') whose devices # have changed, or remote servers that we need to tell about # changes. - hosts = { - row.entity - for row in rows - if not row.entity.startswith("@") and not row.is_signature - } - await self.federation_sender.send_device_messages(hosts, immediate=False) + if any(row.hosts_calculated for row in rows): + hosts = await self.store.get_destinations_for_device(token) + await self.federation_sender.send_device_messages( + hosts, immediate=False + ) elif stream_name == ToDeviceStream.NAME: # The to_device stream includes stuff to be pushed to both local diff --git a/synapse/replication/tcp/streams/_base.py b/synapse/replication/tcp/streams/_base.py index 661206c841..d021904de7 100644 --- a/synapse/replication/tcp/streams/_base.py +++ b/synapse/replication/tcp/streams/_base.py @@ -549,10 +549,14 @@ class DeviceListsStream(_StreamFromIdGen): @attr.s(slots=True, frozen=True, auto_attribs=True) class DeviceListsStreamRow: - entity: str + user_id: str # Indicates that a user has signed their own device with their user-signing key is_signature: bool + # Indicates if this is a notification that we've calculated the hosts we + # need to send the update to. + hosts_calculated: bool + NAME = "device_lists" ROW_TYPE = DeviceListsStreamRow @@ -594,13 +598,13 @@ class DeviceListsStream(_StreamFromIdGen): upper_limit_token = min(upper_limit_token, signatures_to_token) device_updates = [ - (stream_id, (entity, False)) - for stream_id, (entity,) in device_updates + (stream_id, (entity, False, hosts)) + for stream_id, (entity, hosts) in device_updates if stream_id <= upper_limit_token ] signatures_updates = [ - (stream_id, (entity, True)) + (stream_id, (entity, True, False)) for stream_id, (entity,) in signatures_updates if stream_id <= upper_limit_token ] diff --git a/synapse/rest/__init__.py b/synapse/rest/__init__.py index 534dc0e276..0024ccf708 100644 --- a/synapse/rest/__init__.py +++ b/synapse/rest/__init__.py @@ -53,7 +53,7 @@ from synapse.rest.client import ( register, relations, rendezvous, - report_event, + reporting, room, room_keys, room_upgrade_rest_servlet, @@ -128,7 +128,7 @@ class ClientRestResource(JsonResource): tags.register_servlets(hs, client_resource) account_data.register_servlets(hs, client_resource) if is_main_process: - report_event.register_servlets(hs, client_resource) + reporting.register_servlets(hs, client_resource) openid.register_servlets(hs, client_resource) notifications.register_servlets(hs, client_resource) devices.register_servlets(hs, client_resource) diff --git a/synapse/rest/admin/__init__.py b/synapse/rest/admin/__init__.py index 6da1d79168..cdaee17451 100644 --- a/synapse/rest/admin/__init__.py +++ b/synapse/rest/admin/__init__.py @@ -101,6 +101,7 @@ from synapse.rest.admin.users import ( ResetPasswordRestServlet, SearchUsersRestServlet, ShadowBanRestServlet, + SuspendAccountRestServlet, UserAdminServlet, UserByExternalId, UserByThreePid, @@ -327,6 +328,8 @@ def register_servlets(hs: "HomeServer", http_server: HttpServer) -> None: BackgroundUpdateRestServlet(hs).register(http_server) BackgroundUpdateStartJobRestServlet(hs).register(http_server) ExperimentalFeaturesRestServlet(hs).register(http_server) + if hs.config.experimental.msc3823_account_suspension: + SuspendAccountRestServlet(hs).register(http_server) def register_servlets_for_client_rest_resource( diff --git a/synapse/rest/admin/experimental_features.py b/synapse/rest/admin/experimental_features.py index 52eb9e62db..c5a00c490c 100644 --- a/synapse/rest/admin/experimental_features.py +++ b/synapse/rest/admin/experimental_features.py @@ -41,7 +41,6 @@ class ExperimentalFeature(str, Enum): MSC3026 = "msc3026" MSC3881 = "msc3881" - MSC3967 = "msc3967" class ExperimentalFeaturesRestServlet(RestServlet): diff --git a/synapse/rest/admin/federation.py b/synapse/rest/admin/federation.py index 14ab4644cb..d85a04b825 100644 --- a/synapse/rest/admin/federation.py +++ b/synapse/rest/admin/federation.py @@ -61,8 +61,8 @@ class ListDestinationsRestServlet(RestServlet): async def on_GET(self, request: SynapseRequest) -> Tuple[int, JsonDict]: await assert_requester_is_admin(self._auth, request) - start = parse_integer(request, "from", default=0, negative=False) - limit = parse_integer(request, "limit", default=100, negative=False) + start = parse_integer(request, "from", default=0) + limit = parse_integer(request, "limit", default=100) destination = parse_string(request, "destination") @@ -181,8 +181,8 @@ class DestinationMembershipRestServlet(RestServlet): if not await self._store.is_destination_known(destination): raise NotFoundError("Unknown destination") - start = parse_integer(request, "from", default=0, negative=False) - limit = parse_integer(request, "limit", default=100, negative=False) + start = parse_integer(request, "from", default=0) + limit = parse_integer(request, "limit", default=100) direction = parse_enum(request, "dir", Direction, default=Direction.FORWARDS) diff --git a/synapse/rest/admin/media.py b/synapse/rest/admin/media.py index a05b7252ec..ee6a681285 100644 --- a/synapse/rest/admin/media.py +++ b/synapse/rest/admin/media.py @@ -311,8 +311,8 @@ class DeleteMediaByDateSize(RestServlet): ) -> Tuple[int, JsonDict]: await assert_requester_is_admin(self.auth, request) - before_ts = parse_integer(request, "before_ts", required=True, negative=False) - size_gt = parse_integer(request, "size_gt", default=0, negative=False) + before_ts = parse_integer(request, "before_ts", required=True) + size_gt = parse_integer(request, "size_gt", default=0) keep_profiles = parse_boolean(request, "keep_profiles", default=True) if before_ts < 30000000000: # Dec 1970 in milliseconds, Aug 2920 in seconds @@ -377,8 +377,8 @@ class UserMediaRestServlet(RestServlet): if user is None: raise NotFoundError("Unknown user") - start = parse_integer(request, "from", default=0, negative=False) - limit = parse_integer(request, "limit", default=100, negative=False) + start = parse_integer(request, "from", default=0) + limit = parse_integer(request, "limit", default=100) # If neither `order_by` nor `dir` is set, set the default order # to newest media is on top for backward compatibility. @@ -421,8 +421,8 @@ class UserMediaRestServlet(RestServlet): if user is None: raise NotFoundError("Unknown user") - start = parse_integer(request, "from", default=0, negative=False) - limit = parse_integer(request, "limit", default=100, negative=False) + start = parse_integer(request, "from", default=0) + limit = parse_integer(request, "limit", default=100) # If neither `order_by` nor `dir` is set, set the default order # to newest media is on top for backward compatibility. diff --git a/synapse/rest/admin/rooms.py b/synapse/rest/admin/rooms.py index 0d86a4e15f..01f9de9ffa 100644 --- a/synapse/rest/admin/rooms.py +++ b/synapse/rest/admin/rooms.py @@ -35,6 +35,7 @@ from synapse.http.servlet import ( ResolveRoomIdMixin, RestServlet, assert_params_in_dict, + parse_boolean, parse_enum, parse_integer, parse_json, @@ -242,13 +243,23 @@ class ListRoomRestServlet(RestServlet): errcode=Codes.INVALID_PARAM, ) + public_rooms = parse_boolean(request, "public_rooms") + empty_rooms = parse_boolean(request, "empty_rooms") + direction = parse_enum(request, "dir", Direction, default=Direction.FORWARDS) reverse_order = True if direction == Direction.BACKWARDS else False # Return list of rooms according to parameters rooms, total_rooms = await self.store.get_rooms_paginate( - start, limit, order_by, reverse_order, search_term + start, + limit, + order_by, + reverse_order, + search_term, + public_rooms, + empty_rooms, ) + response = { # next_token should be opaque, so return a value the client can parse "offset": start, diff --git a/synapse/rest/admin/statistics.py b/synapse/rest/admin/statistics.py index dc27a41dd9..0adc5b7005 100644 --- a/synapse/rest/admin/statistics.py +++ b/synapse/rest/admin/statistics.py @@ -63,10 +63,10 @@ class UserMediaStatisticsRestServlet(RestServlet): ), ) - start = parse_integer(request, "from", default=0, negative=False) - limit = parse_integer(request, "limit", default=100, negative=False) - from_ts = parse_integer(request, "from_ts", default=0, negative=False) - until_ts = parse_integer(request, "until_ts", negative=False) + start = parse_integer(request, "from", default=0) + limit = parse_integer(request, "limit", default=100) + from_ts = parse_integer(request, "from_ts", default=0) + until_ts = parse_integer(request, "until_ts") if until_ts is not None: if until_ts <= from_ts: diff --git a/synapse/rest/admin/users.py b/synapse/rest/admin/users.py index 5bf12c4979..ad515bd5a3 100644 --- a/synapse/rest/admin/users.py +++ b/synapse/rest/admin/users.py @@ -27,11 +27,13 @@ from typing import TYPE_CHECKING, Dict, List, Optional, Tuple, Union import attr +from synapse._pydantic_compat import HAS_PYDANTIC_V2 from synapse.api.constants import Direction, UserTypes from synapse.api.errors import Codes, NotFoundError, SynapseError from synapse.http.servlet import ( RestServlet, assert_params_in_dict, + parse_and_validate_json_object_from_request, parse_boolean, parse_enum, parse_integer, @@ -49,10 +51,17 @@ from synapse.rest.client._base import client_patterns from synapse.storage.databases.main.registration import ExternalIDReuseException from synapse.storage.databases.main.stats import UserSortOrder from synapse.types import JsonDict, JsonMapping, UserID +from synapse.types.rest import RequestBodyModel if TYPE_CHECKING: from synapse.server import HomeServer +if TYPE_CHECKING or HAS_PYDANTIC_V2: + from pydantic.v1 import StrictBool +else: + from pydantic import StrictBool + + logger = logging.getLogger(__name__) @@ -90,8 +99,8 @@ class UsersRestServletV2(RestServlet): async def on_GET(self, request: SynapseRequest) -> Tuple[int, JsonDict]: await assert_requester_is_admin(self.auth, request) - start = parse_integer(request, "from", default=0, negative=False) - limit = parse_integer(request, "limit", default=100, negative=False) + start = parse_integer(request, "from", default=0) + limit = parse_integer(request, "limit", default=100) user_id = parse_string(request, "user_id") name = parse_string(request, "name", encoding="utf-8") @@ -732,6 +741,36 @@ class DeactivateAccountRestServlet(RestServlet): return HTTPStatus.OK, {"id_server_unbind_result": id_server_unbind_result} +class SuspendAccountRestServlet(RestServlet): + PATTERNS = admin_patterns("/suspend/(?P<target_user_id>[^/]*)$") + + def __init__(self, hs: "HomeServer"): + self.auth = hs.get_auth() + self.is_mine = hs.is_mine + self.store = hs.get_datastores().main + + class PutBody(RequestBodyModel): + suspend: StrictBool + + async def on_PUT( + self, request: SynapseRequest, target_user_id: str + ) -> Tuple[int, JsonDict]: + requester = await self.auth.get_user_by_req(request) + await assert_user_is_admin(self.auth, requester) + + if not self.is_mine(UserID.from_string(target_user_id)): + raise SynapseError(HTTPStatus.BAD_REQUEST, "Can only suspend local users") + + if not await self.store.get_user_by_id(target_user_id): + raise NotFoundError("User not found") + + body = parse_and_validate_json_object_from_request(request, self.PutBody) + suspend = body.suspend + await self.store.set_user_suspended_status(target_user_id, suspend) + + return HTTPStatus.OK, {f"user_{target_user_id}_suspended": suspend} + + class AccountValidityRenewServlet(RestServlet): PATTERNS = admin_patterns("/account_validity/validity$") diff --git a/synapse/rest/client/account.py b/synapse/rest/client/account.py index 6ac07d354c..8daa449f9e 100644 --- a/synapse/rest/client/account.py +++ b/synapse/rest/client/account.py @@ -56,14 +56,14 @@ from synapse.http.servlet import ( from synapse.http.site import SynapseRequest from synapse.metrics import threepid_send_requests from synapse.push.mailer import Mailer -from synapse.rest.client.models import ( +from synapse.types import JsonDict +from synapse.types.rest import RequestBodyModel +from synapse.types.rest.client import ( AuthenticationData, ClientSecretStr, EmailRequestTokenBody, MsisdnRequestTokenBody, ) -from synapse.rest.models import RequestBodyModel -from synapse.types import JsonDict from synapse.util.msisdn import phone_number_to_msisdn from synapse.util.stringutils import assert_valid_client_secret, random_string from synapse.util.threepids import check_3pid_allowed, validate_email diff --git a/synapse/rest/client/devices.py b/synapse/rest/client/devices.py index b1b803549e..8313d687b7 100644 --- a/synapse/rest/client/devices.py +++ b/synapse/rest/client/devices.py @@ -42,9 +42,9 @@ from synapse.http.servlet import ( ) from synapse.http.site import SynapseRequest from synapse.rest.client._base import client_patterns, interactive_auth_handler -from synapse.rest.client.models import AuthenticationData -from synapse.rest.models import RequestBodyModel from synapse.types import JsonDict +from synapse.types.rest import RequestBodyModel +from synapse.types.rest.client import AuthenticationData if TYPE_CHECKING: from synapse.server import HomeServer diff --git a/synapse/rest/client/directory.py b/synapse/rest/client/directory.py index 8099fdf3e4..11fdd0f7c6 100644 --- a/synapse/rest/client/directory.py +++ b/synapse/rest/client/directory.py @@ -41,8 +41,8 @@ from synapse.http.servlet import ( ) from synapse.http.site import SynapseRequest from synapse.rest.client._base import client_patterns -from synapse.rest.models import RequestBodyModel from synapse.types import JsonDict, RoomAlias +from synapse.types.rest import RequestBodyModel if TYPE_CHECKING: from synapse.server import HomeServer diff --git a/synapse/rest/client/keys.py b/synapse/rest/client/keys.py index a0017257ce..67de634eab 100644 --- a/synapse/rest/client/keys.py +++ b/synapse/rest/client/keys.py @@ -36,7 +36,6 @@ from synapse.http.servlet import ( ) from synapse.http.site import SynapseRequest from synapse.logging.opentracing import log_kv, set_tag -from synapse.replication.http.devices import ReplicationUploadKeysForUserRestServlet from synapse.rest.client._base import client_patterns, interactive_auth_handler from synapse.types import JsonDict, StreamToken from synapse.util.cancellation import cancellable @@ -105,13 +104,8 @@ class KeyUploadServlet(RestServlet): self.auth = hs.get_auth() self.e2e_keys_handler = hs.get_e2e_keys_handler() self.device_handler = hs.get_device_handler() - - if hs.config.worker.worker_app is None: - # if main process - self.key_uploader = self.e2e_keys_handler.upload_keys_for_user - else: - # then a worker - self.key_uploader = ReplicationUploadKeysForUserRestServlet.make_client(hs) + self._clock = hs.get_clock() + self._store = hs.get_datastores().main async def on_POST( self, request: SynapseRequest, device_id: Optional[str] @@ -151,9 +145,10 @@ class KeyUploadServlet(RestServlet): 400, "To upload keys, you must pass device_id when authenticating" ) - result = await self.key_uploader( + result = await self.e2e_keys_handler.upload_keys_for_user( user_id=user_id, device_id=device_id, keys=body ) + return 200, result @@ -387,44 +382,35 @@ class SigningKeyUploadServlet(RestServlet): master_key_updatable_without_uia, ) = await self.e2e_keys_handler.check_cross_signing_setup(user_id) - # Before MSC3967 we required UIA both when setting up cross signing for the - # first time and when resetting the device signing key. With MSC3967 we only - # require UIA when resetting cross-signing, and not when setting up the first - # time. Because there is no UIA in MSC3861, for now we throw an error if the - # user tries to reset the device signing key when MSC3861 is enabled, but allow - # first-time setup. - if self.hs.config.experimental.msc3861.enabled: - # The auth service has to explicitly mark the master key as replaceable - # without UIA to reset the device signing key with MSC3861. - if is_cross_signing_setup and not master_key_updatable_without_uia: - config = self.hs.config.experimental.msc3861 - if config.account_management_url is not None: - url = f"{config.account_management_url}?action=org.matrix.cross_signing_reset" - else: - url = config.issuer - - raise SynapseError( - HTTPStatus.NOT_IMPLEMENTED, - "To reset your end-to-end encryption cross-signing identity, " - f"you first need to approve it at {url} and then try again.", - Codes.UNRECOGNIZED, - ) - # But first-time setup is fine - - elif self.hs.config.experimental.msc3967_enabled: - # MSC3967 allows this endpoint to 200 OK for idempotency. Resending exactly the same - # keys should just 200 OK without doing a UIA prompt. - keys_are_different = await self.e2e_keys_handler.has_different_keys( - user_id, body - ) - if not keys_are_different: - # FIXME: we do not fallthrough to upload_signing_keys_for_user because confusingly - # if we do, we 500 as it looks like it tries to INSERT the same key twice, causing a - # unique key constraint violation. This sounds like a bug? - return 200, {} - # the keys are different, is x-signing set up? If no, then the keys don't exist which is - # why they are different. If yes, then we need to UIA to change them. - if is_cross_signing_setup: + # Resending exactly the same keys should just 200 OK without doing a UIA prompt. + keys_are_different = await self.e2e_keys_handler.has_different_keys( + user_id, body + ) + if not keys_are_different: + return 200, {} + + # The keys are different; is x-signing set up? If no, then this is first-time + # setup, and that is allowed without UIA, per MSC3967. + # If yes, then we need to authenticate the change. + if is_cross_signing_setup: + # With MSC3861, UIA is not possible. Instead, the auth service has to + # explicitly mark the master key as replaceable. + if self.hs.config.experimental.msc3861.enabled: + if not master_key_updatable_without_uia: + config = self.hs.config.experimental.msc3861 + if config.account_management_url is not None: + url = f"{config.account_management_url}?action=org.matrix.cross_signing_reset" + else: + url = config.issuer + + raise SynapseError( + HTTPStatus.NOT_IMPLEMENTED, + "To reset your end-to-end encryption cross-signing identity, " + f"you first need to approve it at {url} and then try again.", + Codes.UNRECOGNIZED, + ) + else: + # Without MSC3861, we require UIA. await self.auth_handler.validate_user_via_ui_auth( requester, request, @@ -433,18 +419,6 @@ class SigningKeyUploadServlet(RestServlet): # Do not allow skipping of UIA auth. can_skip_ui_auth=False, ) - # Otherwise we don't require UIA since we are setting up cross signing for first time - else: - # Previous behaviour is to always require UIA but allow it to be skipped - await self.auth_handler.validate_user_via_ui_auth( - requester, - request, - body, - "add a device signing key to your account", - # Allow skipping of UI auth since this is frequently called directly - # after login and it is silly to ask users to re-auth immediately. - can_skip_ui_auth=True, - ) result = await self.e2e_keys_handler.upload_signing_keys_for_user(user_id, body) return 200, result diff --git a/synapse/rest/client/knock.py b/synapse/rest/client/knock.py index ff52a9bf8c..e31687fc13 100644 --- a/synapse/rest/client/knock.py +++ b/synapse/rest/client/knock.py @@ -53,6 +53,7 @@ class KnockRoomAliasServlet(RestServlet): super().__init__() self.room_member_handler = hs.get_room_member_handler() self.auth = hs.get_auth() + self._support_via = hs.config.experimental.msc4156_enabled async def on_POST( self, @@ -74,6 +75,13 @@ class KnockRoomAliasServlet(RestServlet): remote_room_hosts = parse_strings_from_args( args, "server_name", required=False ) + if self._support_via: + remote_room_hosts = parse_strings_from_args( + args, + "org.matrix.msc4156.via", + default=remote_room_hosts, + required=False, + ) elif RoomAlias.is_valid(room_identifier): handler = self.room_member_handler room_alias = RoomAlias.from_string(room_identifier) diff --git a/synapse/rest/client/media.py b/synapse/rest/client/media.py new file mode 100644 index 0000000000..0c089163c1 --- /dev/null +++ b/synapse/rest/client/media.py @@ -0,0 +1,207 @@ +# +# This file is licensed under the Affero General Public License (AGPL) version 3. +# +# Copyright 2020 The Matrix.org Foundation C.I.C. +# Copyright 2015, 2016 OpenMarket Ltd +# Copyright (C) 2024 New Vector, Ltd +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as +# published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# See the GNU Affero General Public License for more details: +# <https://www.gnu.org/licenses/agpl-3.0.html>. +# +# Originally licensed under the Apache License, Version 2.0: +# <http://www.apache.org/licenses/LICENSE-2.0>. +# +# [This file includes modifications made by New Vector Limited] +# +# + +import logging +import re + +from synapse.http.server import ( + HttpServer, + respond_with_json, + respond_with_json_bytes, + set_corp_headers, + set_cors_headers, +) +from synapse.http.servlet import RestServlet, parse_integer, parse_string +from synapse.http.site import SynapseRequest +from synapse.media._base import ( + DEFAULT_MAX_TIMEOUT_MS, + MAXIMUM_ALLOWED_MAX_TIMEOUT_MS, + respond_404, +) +from synapse.media.media_repository import MediaRepository +from synapse.media.media_storage import MediaStorage +from synapse.media.thumbnailer import ThumbnailProvider +from synapse.server import HomeServer +from synapse.util.stringutils import parse_and_validate_server_name + +logger = logging.getLogger(__name__) + + +class UnstablePreviewURLServlet(RestServlet): + """ + Same as `GET /_matrix/media/r0/preview_url`, this endpoint provides a generic preview API + for URLs which outputs Open Graph (https://ogp.me/) responses (with some Matrix + specific additions). + + This does have trade-offs compared to other designs: + + * Pros: + * Simple and flexible; can be used by any clients at any point + * Cons: + * If each homeserver provides one of these independently, all the homeservers in a + room may needlessly DoS the target URI + * The URL metadata must be stored somewhere, rather than just using Matrix + itself to store the media. + * Matrix cannot be used to distribute the metadata between homeservers. + """ + + PATTERNS = [ + re.compile(r"^/_matrix/client/unstable/org.matrix.msc3916/media/preview_url$") + ] + + def __init__( + self, + hs: "HomeServer", + media_repo: "MediaRepository", + media_storage: MediaStorage, + ): + super().__init__() + + self.auth = hs.get_auth() + self.clock = hs.get_clock() + self.media_repo = media_repo + self.media_storage = media_storage + assert self.media_repo.url_previewer is not None + self.url_previewer = self.media_repo.url_previewer + + async def on_GET(self, request: SynapseRequest) -> None: + requester = await self.auth.get_user_by_req(request) + url = parse_string(request, "url", required=True) + ts = parse_integer(request, "ts") + if ts is None: + ts = self.clock.time_msec() + + og = await self.url_previewer.preview(url, requester.user, ts) + respond_with_json_bytes(request, 200, og, send_cors=True) + + +class UnstableMediaConfigResource(RestServlet): + PATTERNS = [ + re.compile(r"^/_matrix/client/unstable/org.matrix.msc3916/media/config$") + ] + + def __init__(self, hs: "HomeServer"): + super().__init__() + config = hs.config + self.clock = hs.get_clock() + self.auth = hs.get_auth() + self.limits_dict = {"m.upload.size": config.media.max_upload_size} + + async def on_GET(self, request: SynapseRequest) -> None: + await self.auth.get_user_by_req(request) + respond_with_json(request, 200, self.limits_dict, send_cors=True) + + +class UnstableThumbnailResource(RestServlet): + PATTERNS = [ + re.compile( + "/_matrix/client/unstable/org.matrix.msc3916/media/thumbnail/(?P<server_name>[^/]*)/(?P<media_id>[^/]*)$" + ) + ] + + def __init__( + self, + hs: "HomeServer", + media_repo: "MediaRepository", + media_storage: MediaStorage, + ): + super().__init__() + + self.store = hs.get_datastores().main + self.media_repo = media_repo + self.media_storage = media_storage + self.dynamic_thumbnails = hs.config.media.dynamic_thumbnails + self._is_mine_server_name = hs.is_mine_server_name + self._server_name = hs.hostname + self.prevent_media_downloads_from = hs.config.media.prevent_media_downloads_from + self.thumbnailer = ThumbnailProvider(hs, media_repo, media_storage) + self.auth = hs.get_auth() + + async def on_GET( + self, request: SynapseRequest, server_name: str, media_id: str + ) -> None: + # Validate the server name, raising if invalid + parse_and_validate_server_name(server_name) + await self.auth.get_user_by_req(request) + + set_cors_headers(request) + set_corp_headers(request) + width = parse_integer(request, "width", required=True) + height = parse_integer(request, "height", required=True) + method = parse_string(request, "method", "scale") + # TODO Parse the Accept header to get an prioritised list of thumbnail types. + m_type = "image/png" + max_timeout_ms = parse_integer( + request, "timeout_ms", default=DEFAULT_MAX_TIMEOUT_MS + ) + max_timeout_ms = min(max_timeout_ms, MAXIMUM_ALLOWED_MAX_TIMEOUT_MS) + + if self._is_mine_server_name(server_name): + if self.dynamic_thumbnails: + await self.thumbnailer.select_or_generate_local_thumbnail( + request, media_id, width, height, method, m_type, max_timeout_ms + ) + else: + await self.thumbnailer.respond_local_thumbnail( + request, media_id, width, height, method, m_type, max_timeout_ms + ) + self.media_repo.mark_recently_accessed(None, media_id) + else: + # Don't let users download media from configured domains, even if it + # is already downloaded. This is Trust & Safety tooling to make some + # media inaccessible to local users. + # See `prevent_media_downloads_from` config docs for more info. + if server_name in self.prevent_media_downloads_from: + respond_404(request) + return + + ip_address = request.getClientAddress().host + remote_resp_function = ( + self.thumbnailer.select_or_generate_remote_thumbnail + if self.dynamic_thumbnails + else self.thumbnailer.respond_remote_thumbnail + ) + await remote_resp_function( + request, + server_name, + media_id, + width, + height, + method, + m_type, + max_timeout_ms, + ip_address, + ) + self.media_repo.mark_recently_accessed(server_name, media_id) + + +def register_servlets(hs: "HomeServer", http_server: HttpServer) -> None: + if hs.config.experimental.msc3916_authenticated_media_enabled: + media_repo = hs.get_media_repository() + if hs.config.media.url_preview_enabled: + UnstablePreviewURLServlet( + hs, media_repo, media_repo.media_storage + ).register(http_server) + UnstableMediaConfigResource(hs).register(http_server) + UnstableThumbnailResource(hs, media_repo, media_repo.media_storage).register( + http_server + ) diff --git a/synapse/rest/client/models.py b/synapse/rest/client/models.py deleted file mode 100644 index fc1aed2889..0000000000 --- a/synapse/rest/client/models.py +++ /dev/null @@ -1,99 +0,0 @@ -# -# This file is licensed under the Affero General Public License (AGPL) version 3. -# -# Copyright 2022 The Matrix.org Foundation C.I.C. -# Copyright (C) 2023 New Vector, Ltd -# -# This program is free software: you can redistribute it and/or modify -# it under the terms of the GNU Affero General Public License as -# published by the Free Software Foundation, either version 3 of the -# License, or (at your option) any later version. -# -# See the GNU Affero General Public License for more details: -# <https://www.gnu.org/licenses/agpl-3.0.html>. -# -# Originally licensed under the Apache License, Version 2.0: -# <http://www.apache.org/licenses/LICENSE-2.0>. -# -# [This file includes modifications made by New Vector Limited] -# -# -from typing import TYPE_CHECKING, Dict, Optional - -from synapse._pydantic_compat import HAS_PYDANTIC_V2 - -if TYPE_CHECKING or HAS_PYDANTIC_V2: - from pydantic.v1 import Extra, StrictInt, StrictStr, constr, validator -else: - from pydantic import Extra, StrictInt, StrictStr, constr, validator - -from synapse.rest.models import RequestBodyModel -from synapse.util.threepids import validate_email - - -class AuthenticationData(RequestBodyModel): - """ - Data used during user-interactive authentication. - - (The name "Authentication Data" is taken directly from the spec.) - - Additional keys will be present, depending on the `type` field. Use - `.dict(exclude_unset=True)` to access them. - """ - - class Config: - extra = Extra.allow - - session: Optional[StrictStr] = None - type: Optional[StrictStr] = None - - -if TYPE_CHECKING: - ClientSecretStr = StrictStr -else: - # See also assert_valid_client_secret() - ClientSecretStr = constr( - regex="[0-9a-zA-Z.=_-]", # noqa: F722 - min_length=1, - max_length=255, - strict=True, - ) - - -class ThreepidRequestTokenBody(RequestBodyModel): - client_secret: ClientSecretStr - id_server: Optional[StrictStr] - id_access_token: Optional[StrictStr] - next_link: Optional[StrictStr] - send_attempt: StrictInt - - @validator("id_access_token", always=True) - def token_required_for_identity_server( - cls, token: Optional[str], values: Dict[str, object] - ) -> Optional[str]: - if values.get("id_server") is not None and token is None: - raise ValueError("id_access_token is required if an id_server is supplied.") - return token - - -class EmailRequestTokenBody(ThreepidRequestTokenBody): - email: StrictStr - - # Canonicalise the email address. The addresses are all stored canonicalised - # in the database. This allows the user to reset his password without having to - # know the exact spelling (eg. upper and lower case) of address in the database. - # Without this, an email stored in the database as "foo@bar.com" would cause - # user requests for "FOO@bar.com" to raise a Not Found error. - _email_validator = validator("email", allow_reuse=True)(validate_email) - - -if TYPE_CHECKING: - ISO3116_1_Alpha_2 = StrictStr -else: - # Per spec: two-letter uppercase ISO-3166-1-alpha-2 - ISO3116_1_Alpha_2 = constr(regex="[A-Z]{2}", strict=True) - - -class MsisdnRequestTokenBody(ThreepidRequestTokenBody): - country: ISO3116_1_Alpha_2 - phone_number: StrictStr diff --git a/synapse/rest/client/notifications.py b/synapse/rest/client/notifications.py index be9b584748..168ce50d3f 100644 --- a/synapse/rest/client/notifications.py +++ b/synapse/rest/client/notifications.py @@ -32,6 +32,7 @@ from synapse.http.servlet import RestServlet, parse_integer, parse_string from synapse.http.site import SynapseRequest from synapse.types import JsonDict +from ...api.errors import SynapseError from ._base import client_patterns if TYPE_CHECKING: @@ -56,7 +57,22 @@ class NotificationsServlet(RestServlet): requester = await self.auth.get_user_by_req(request) user_id = requester.user.to_string() - from_token = parse_string(request, "from", required=False) + # While this is intended to be "string" to clients, the 'from' token + # is actually based on a numeric ID. So it must parse to an int. + from_token_str = parse_string(request, "from", required=False) + if from_token_str is not None: + # Parse to an integer. + try: + from_token = int(from_token_str) + except ValueError: + # If it doesn't parse to an integer, then this cannot possibly be a valid + # pagination token, as we only hand out integers. + raise SynapseError( + 400, 'Query parameter "from" contains unrecognised token' + ) + else: + from_token = None + limit = parse_integer(request, "limit", default=50) only = parse_string(request, "only", required=False) diff --git a/synapse/rest/client/profile.py b/synapse/rest/client/profile.py index 0323f6afa1..c1a80c5c3d 100644 --- a/synapse/rest/client/profile.py +++ b/synapse/rest/client/profile.py @@ -108,6 +108,19 @@ class ProfileDisplaynameRestServlet(RestServlet): propagate = _read_propagate(self.hs, request) + requester_suspended = ( + await self.hs.get_datastores().main.get_user_suspended_status( + requester.user.to_string() + ) + ) + + if requester_suspended: + raise SynapseError( + 403, + "Updating displayname while account is suspended is not allowed.", + Codes.USER_ACCOUNT_SUSPENDED, + ) + await self.profile_handler.set_displayname( user, requester, new_name, is_admin, propagate=propagate ) @@ -167,6 +180,19 @@ class ProfileAvatarURLRestServlet(RestServlet): propagate = _read_propagate(self.hs, request) + requester_suspended = ( + await self.hs.get_datastores().main.get_user_suspended_status( + requester.user.to_string() + ) + ) + + if requester_suspended: + raise SynapseError( + 403, + "Updating avatar URL while account is suspended is not allowed.", + Codes.USER_ACCOUNT_SUSPENDED, + ) + await self.profile_handler.set_avatar_url( user, requester, new_avatar_url, is_admin, propagate=propagate ) diff --git a/synapse/rest/client/report_event.py b/synapse/rest/client/reporting.py index 447281931e..4eee53e5a8 100644 --- a/synapse/rest/client/report_event.py +++ b/synapse/rest/client/reporting.py @@ -23,17 +23,28 @@ import logging from http import HTTPStatus from typing import TYPE_CHECKING, Tuple +from synapse._pydantic_compat import HAS_PYDANTIC_V2 from synapse.api.errors import AuthError, Codes, NotFoundError, SynapseError from synapse.http.server import HttpServer -from synapse.http.servlet import RestServlet, parse_json_object_from_request +from synapse.http.servlet import ( + RestServlet, + parse_and_validate_json_object_from_request, + parse_json_object_from_request, +) from synapse.http.site import SynapseRequest from synapse.types import JsonDict +from synapse.types.rest import RequestBodyModel from ._base import client_patterns if TYPE_CHECKING: from synapse.server import HomeServer +if TYPE_CHECKING or HAS_PYDANTIC_V2: + from pydantic.v1 import StrictStr +else: + from pydantic import StrictStr + logger = logging.getLogger(__name__) @@ -95,5 +106,57 @@ class ReportEventRestServlet(RestServlet): return 200, {} +class ReportRoomRestServlet(RestServlet): + """This endpoint lets clients report a room for abuse. + + Whilst MSC4151 is not yet merged, this unstable endpoint is enabled on matrix.org + for content moderation purposes, and therefore backwards compatibility should be + carefully considered when changing anything on this endpoint. + + More details on the MSC: https://github.com/matrix-org/matrix-spec-proposals/pull/4151 + """ + + PATTERNS = client_patterns( + "/org.matrix.msc4151/rooms/(?P<room_id>[^/]*)/report$", + releases=[], + v1=False, + unstable=True, + ) + + def __init__(self, hs: "HomeServer"): + super().__init__() + self.hs = hs + self.auth = hs.get_auth() + self.clock = hs.get_clock() + self.store = hs.get_datastores().main + + class PostBody(RequestBodyModel): + reason: StrictStr + + async def on_POST( + self, request: SynapseRequest, room_id: str + ) -> Tuple[int, JsonDict]: + requester = await self.auth.get_user_by_req(request) + user_id = requester.user.to_string() + + body = parse_and_validate_json_object_from_request(request, self.PostBody) + + room = await self.store.get_room(room_id) + if room is None: + raise NotFoundError("Room does not exist") + + await self.store.add_room_report( + room_id=room_id, + user_id=user_id, + reason=body.reason, + received_ts=self.clock.time_msec(), + ) + + return 200, {} + + def register_servlets(hs: "HomeServer", http_server: HttpServer) -> None: ReportEventRestServlet(hs).register(http_server) + + if hs.config.experimental.msc4151_enabled: + ReportRoomRestServlet(hs).register(http_server) diff --git a/synapse/rest/client/room.py b/synapse/rest/client/room.py index fb4d44211e..903c74f6d8 100644 --- a/synapse/rest/client/room.py +++ b/synapse/rest/client/room.py @@ -292,6 +292,9 @@ class RoomStateEventRestServlet(RestServlet): try: if event_type == EventTypes.Member: membership = content.get("membership", None) + if not isinstance(membership, str): + raise SynapseError(400, "Invalid membership (must be a string)") + event_id, _ = await self.room_member_handler.update_membership( requester, target=UserID.from_string(state_key), @@ -414,6 +417,7 @@ class JoinRoomAliasServlet(ResolveRoomIdMixin, TransactionRestServlet): super().__init__(hs) super(ResolveRoomIdMixin, self).__init__(hs) # ensure the Mixin is set up self.auth = hs.get_auth() + self._support_via = hs.config.experimental.msc4156_enabled def register(self, http_server: HttpServer) -> None: # /join/$room_identifier[/$txn_id] @@ -432,6 +436,13 @@ class JoinRoomAliasServlet(ResolveRoomIdMixin, TransactionRestServlet): # twisted.web.server.Request.args is incorrectly defined as Optional[Any] args: Dict[bytes, List[bytes]] = request.args # type: ignore remote_room_hosts = parse_strings_from_args(args, "server_name", required=False) + if self._support_via: + remote_room_hosts = parse_strings_from_args( + args, + "org.matrix.msc4156.via", + default=remote_room_hosts, + required=False, + ) room_id, remote_room_hosts = await self.resolve_room_id( room_identifier, remote_room_hosts, @@ -499,7 +510,7 @@ class PublicRoomListRestServlet(RestServlet): if server: raise e - limit: Optional[int] = parse_integer(request, "limit", 0, negative=False) + limit: Optional[int] = parse_integer(request, "limit", 0) since_token = parse_string(request, "since") if limit == 0: @@ -1109,6 +1120,20 @@ class RoomRedactEventRestServlet(TransactionRestServlet): ) -> Tuple[int, JsonDict]: content = parse_json_object_from_request(request) + requester_suspended = await self._store.get_user_suspended_status( + requester.user.to_string() + ) + + if requester_suspended: + event = await self._store.get_event(event_id, allow_none=True) + if event: + if event.sender != requester.user.to_string(): + raise SynapseError( + 403, + "You can only redact your own events while account is suspended.", + Codes.USER_ACCOUNT_SUSPENDED, + ) + # Ensure the redacts property in the content matches the one provided in # the URL. room_version = await self._store.get_room_version(room_id) @@ -1419,16 +1444,7 @@ class RoomHierarchyRestServlet(RestServlet): requester = await self._auth.get_user_by_req(request, allow_guest=True) max_depth = parse_integer(request, "max_depth") - if max_depth is not None and max_depth < 0: - raise SynapseError( - 400, "'max_depth' must be a non-negative integer", Codes.BAD_JSON - ) - limit = parse_integer(request, "limit") - if limit is not None and limit <= 0: - raise SynapseError( - 400, "'limit' must be a positive integer", Codes.BAD_JSON - ) return 200, await self._room_summary_handler.get_room_hierarchy( requester, diff --git a/synapse/rest/client/sync.py b/synapse/rest/client/sync.py index 2b103ca6a8..b5ab0d8534 100644 --- a/synapse/rest/client/sync.py +++ b/synapse/rest/client/sync.py @@ -33,6 +33,7 @@ from synapse.events.utils import ( format_event_raw, ) from synapse.handlers.presence import format_user_presence_state +from synapse.handlers.sliding_sync import SlidingSyncConfig, SlidingSyncResult from synapse.handlers.sync import ( ArchivedSyncResult, InvitedSyncResult, @@ -40,13 +41,22 @@ from synapse.handlers.sync import ( KnockedSyncResult, SyncConfig, SyncResult, + SyncVersion, ) from synapse.http.server import HttpServer -from synapse.http.servlet import RestServlet, parse_boolean, parse_integer, parse_string +from synapse.http.servlet import ( + RestServlet, + parse_and_validate_json_object_from_request, + parse_boolean, + parse_integer, + parse_string, +) from synapse.http.site import SynapseRequest from synapse.logging.opentracing import trace_with_opname from synapse.types import JsonDict, Requester, StreamToken +from synapse.types.rest.client import SlidingSyncBody from synapse.util import json_decoder +from synapse.util.caches.lrucache import LruCache from ._base import client_patterns, set_timeline_upper_limit @@ -110,6 +120,11 @@ class SyncRestServlet(RestServlet): self._msc2654_enabled = hs.config.experimental.msc2654_enabled self._msc3773_enabled = hs.config.experimental.msc3773_enabled + self._json_filter_cache: LruCache[str, bool] = LruCache( + max_size=1000, + cache_name="sync_valid_filter", + ) + async def on_GET(self, request: SynapseRequest) -> Tuple[int, JsonDict]: # This will always be set by the time Twisted calls us. assert request.args is not None @@ -177,7 +192,13 @@ class SyncRestServlet(RestServlet): filter_object = json_decoder.decode(filter_id) except Exception: raise SynapseError(400, "Invalid filter JSON", errcode=Codes.NOT_JSON) - self.filtering.check_valid_filter(filter_object) + + # We cache the validation, as this can get quite expensive if people use + # a literal json blob as a query param. + if not self._json_filter_cache.get(filter_id): + self.filtering.check_valid_filter(filter_object) + self._json_filter_cache[filter_id] = True + set_timeline_upper_limit( filter_object, self.hs.config.server.filter_timeline_limit ) @@ -197,7 +218,6 @@ class SyncRestServlet(RestServlet): user=user, filter_collection=filter_collection, is_guest=requester.is_guest, - request_key=request_key, device_id=device_id, ) @@ -220,6 +240,8 @@ class SyncRestServlet(RestServlet): sync_result = await self.sync_handler.wait_for_sync_for_user( requester, sync_config, + SyncVersion.SYNC_V2, + request_key, since_token=since_token, timeout=timeout, full_state=full_state, @@ -553,5 +575,396 @@ class SyncRestServlet(RestServlet): return result +class SlidingSyncE2eeRestServlet(RestServlet): + """ + API endpoint for MSC3575 Sliding Sync `/sync/e2ee`. This is being introduced as part + of Sliding Sync but doesn't have any sliding window component. It's just a way to + get E2EE events without having to sit through a big initial sync (`/sync` v2). And + we can avoid encryption events being backed up by the main sync response. + + Having To-Device messages split out to this sync endpoint also helps when clients + need to have 2 or more sync streams open at a time, e.g a push notification process + and a main process. This can cause the two processes to race to fetch the To-Device + events, resulting in the need for complex synchronisation rules to ensure the token + is correctly and atomically exchanged between processes. + + GET parameters:: + timeout(int): How long to wait for new events in milliseconds. + since(batch_token): Batch token when asking for incremental deltas. + + Response JSON:: + { + "next_batch": // batch token for the next /sync + "to_device": { + // list of to-device events + "events": [ + { + "content: { "algorithm": "m.olm.v1.curve25519-aes-sha2", "ciphertext": { ... }, "org.matrix.msgid": "abcd", "session_id": "abcd" }, + "type": "m.room.encrypted", + "sender": "@alice:example.com", + } + // ... + ] + }, + "device_lists": { + "changed": ["@alice:example.com"], + "left": ["@bob:example.com"] + }, + "device_one_time_keys_count": { + "signed_curve25519": 50 + }, + "device_unused_fallback_key_types": [ + "signed_curve25519" + ] + } + """ + + PATTERNS = client_patterns( + "/org.matrix.msc3575/sync/e2ee$", releases=[], v1=False, unstable=True + ) + + def __init__(self, hs: "HomeServer"): + super().__init__() + self.hs = hs + self.auth = hs.get_auth() + self.store = hs.get_datastores().main + self.sync_handler = hs.get_sync_handler() + + # Filtering only matters for the `device_lists` because it requires a bunch of + # derived information from rooms (see how `_generate_sync_entry_for_rooms()` + # prepares a bunch of data for `_generate_sync_entry_for_device_list()`). + self.only_member_events_filter_collection = FilterCollection( + self.hs, + { + "room": { + # We only care about membership events for the `device_lists`. + # Membership will tell us whether a user has joined/left a room and + # if there are new devices to encrypt for. + "timeline": { + "types": ["m.room.member"], + }, + "state": { + "types": ["m.room.member"], + }, + # We don't want any extra account_data generated because it's not + # returned by this endpoint. This helps us avoid work in + # `_generate_sync_entry_for_rooms()` + "account_data": { + "not_types": ["*"], + }, + # We don't want any extra ephemeral data generated because it's not + # returned by this endpoint. This helps us avoid work in + # `_generate_sync_entry_for_rooms()` + "ephemeral": { + "not_types": ["*"], + }, + }, + # We don't want any extra account_data generated because it's not + # returned by this endpoint. (This is just here for good measure) + "account_data": { + "not_types": ["*"], + }, + # We don't want any extra presence data generated because it's not + # returned by this endpoint. (This is just here for good measure) + "presence": { + "not_types": ["*"], + }, + }, + ) + + async def on_GET(self, request: SynapseRequest) -> Tuple[int, JsonDict]: + requester = await self.auth.get_user_by_req(request, allow_guest=True) + user = requester.user + device_id = requester.device_id + + timeout = parse_integer(request, "timeout", default=0) + since = parse_string(request, "since") + + sync_config = SyncConfig( + user=user, + filter_collection=self.only_member_events_filter_collection, + is_guest=requester.is_guest, + device_id=device_id, + ) + + since_token = None + if since is not None: + since_token = await StreamToken.from_string(self.store, since) + + # Request cache key + request_key = ( + SyncVersion.E2EE_SYNC, + user, + timeout, + since, + ) + + # Gather data for the response + sync_result = await self.sync_handler.wait_for_sync_for_user( + requester, + sync_config, + SyncVersion.E2EE_SYNC, + request_key, + since_token=since_token, + timeout=timeout, + full_state=False, + ) + + # The client may have disconnected by now; don't bother to serialize the + # response if so. + if request._disconnected: + logger.info("Client has disconnected; not serializing response.") + return 200, {} + + response: JsonDict = defaultdict(dict) + response["next_batch"] = await sync_result.next_batch.to_string(self.store) + + if sync_result.to_device: + response["to_device"] = {"events": sync_result.to_device} + + if sync_result.device_lists.changed: + response["device_lists"]["changed"] = list(sync_result.device_lists.changed) + if sync_result.device_lists.left: + response["device_lists"]["left"] = list(sync_result.device_lists.left) + + # We always include this because https://github.com/vector-im/element-android/issues/3725 + # The spec isn't terribly clear on when this can be omitted and how a client would tell + # the difference between "no keys present" and "nothing changed" in terms of whole field + # absent / individual key type entry absent + # Corresponding synapse issue: https://github.com/matrix-org/synapse/issues/10456 + response["device_one_time_keys_count"] = sync_result.device_one_time_keys_count + + # https://github.com/matrix-org/matrix-doc/blob/54255851f642f84a4f1aaf7bc063eebe3d76752b/proposals/2732-olm-fallback-keys.md + # states that this field should always be included, as long as the server supports the feature. + response["device_unused_fallback_key_types"] = ( + sync_result.device_unused_fallback_key_types + ) + + return 200, response + + +class SlidingSyncRestServlet(RestServlet): + """ + API endpoint for MSC3575 Sliding Sync `/sync`. Allows for clients to request a + subset (sliding window) of rooms, state, and timeline events (just what they need) + in order to bootstrap quickly and subscribe to only what the client cares about. + Because the client can specify what it cares about, we can respond quickly and skip + all of the work we would normally have to do with a sync v2 response. + + Request query parameters: + timeout: How long to wait for new events in milliseconds. + pos: Stream position token when asking for incremental deltas. + + Request body:: + { + // Sliding Window API + "lists": { + "foo-list": { + "ranges": [ [0, 99] ], + "sort": [ "by_notification_level", "by_recency", "by_name" ], + "required_state": [ + ["m.room.join_rules", ""], + ["m.room.history_visibility", ""], + ["m.space.child", "*"] + ], + "timeline_limit": 10, + "filters": { + "is_dm": true + }, + "bump_event_types": [ "m.room.message", "m.room.encrypted" ], + } + }, + // Room Subscriptions API + "room_subscriptions": { + "!sub1:bar": { + "required_state": [ ["*","*"] ], + "timeline_limit": 10, + "include_old_rooms": { + "timeline_limit": 1, + "required_state": [ ["m.room.tombstone", ""], ["m.room.create", ""] ], + } + } + }, + // Extensions API + "extensions": {} + } + + Response JSON:: + { + "next_pos": "s58_224_0_13_10_1_1_16_0_1", + "lists": { + "foo-list": { + "count": 1337, + "ops": [{ + "op": "SYNC", + "range": [0, 99], + "room_ids": [ + "!foo:bar", + // ... 99 more room IDs + ] + }] + } + }, + // Aggregated rooms from lists and room subscriptions + "rooms": { + // Room from room subscription + "!sub1:bar": { + "name": "Alice and Bob", + "avatar": "mxc://...", + "initial": true, + "required_state": [ + {"sender":"@alice:example.com","type":"m.room.create", "state_key":"", "content":{"creator":"@alice:example.com"}}, + {"sender":"@alice:example.com","type":"m.room.join_rules", "state_key":"", "content":{"join_rule":"invite"}}, + {"sender":"@alice:example.com","type":"m.room.history_visibility", "state_key":"", "content":{"history_visibility":"joined"}}, + {"sender":"@alice:example.com","type":"m.room.member", "state_key":"@alice:example.com", "content":{"membership":"join"}} + ], + "timeline": [ + {"sender":"@alice:example.com","type":"m.room.create", "state_key":"", "content":{"creator":"@alice:example.com"}}, + {"sender":"@alice:example.com","type":"m.room.join_rules", "state_key":"", "content":{"join_rule":"invite"}}, + {"sender":"@alice:example.com","type":"m.room.history_visibility", "state_key":"", "content":{"history_visibility":"joined"}}, + {"sender":"@alice:example.com","type":"m.room.member", "state_key":"@alice:example.com", "content":{"membership":"join"}}, + {"sender":"@alice:example.com","type":"m.room.message", "content":{"body":"A"}}, + {"sender":"@alice:example.com","type":"m.room.message", "content":{"body":"B"}}, + ], + "prev_batch": "t111_222_333", + "joined_count": 41, + "invited_count": 1, + "notification_count": 1, + "highlight_count": 0 + }, + // rooms from list + "!foo:bar": { + "name": "The calculated room name", + "avatar": "mxc://...", + "initial": true, + "required_state": [ + {"sender":"@alice:example.com","type":"m.room.join_rules", "state_key":"", "content":{"join_rule":"invite"}}, + {"sender":"@alice:example.com","type":"m.room.history_visibility", "state_key":"", "content":{"history_visibility":"joined"}}, + {"sender":"@alice:example.com","type":"m.space.child", "state_key":"!foo:example.com", "content":{"via":["example.com"]}}, + {"sender":"@alice:example.com","type":"m.space.child", "state_key":"!bar:example.com", "content":{"via":["example.com"]}}, + {"sender":"@alice:example.com","type":"m.space.child", "state_key":"!baz:example.com", "content":{"via":["example.com"]}} + ], + "timeline": [ + {"sender":"@alice:example.com","type":"m.room.join_rules", "state_key":"", "content":{"join_rule":"invite"}}, + {"sender":"@alice:example.com","type":"m.room.message", "content":{"body":"A"}}, + {"sender":"@alice:example.com","type":"m.room.message", "content":{"body":"B"}}, + {"sender":"@alice:example.com","type":"m.room.message", "content":{"body":"C"}}, + {"sender":"@alice:example.com","type":"m.room.message", "content":{"body":"D"}}, + ], + "prev_batch": "t111_222_333", + "joined_count": 4, + "invited_count": 0, + "notification_count": 54, + "highlight_count": 3 + }, + // ... 99 more items + }, + "extensions": {} + } + """ + + PATTERNS = client_patterns( + "/org.matrix.simplified_msc3575/sync$", releases=[], v1=False, unstable=True + ) + + def __init__(self, hs: "HomeServer"): + super().__init__() + self.auth = hs.get_auth() + self.store = hs.get_datastores().main + self.filtering = hs.get_filtering() + self.sliding_sync_handler = hs.get_sliding_sync_handler() + + # TODO: Update this to `on_GET` once we figure out how we want to handle params + async def on_POST(self, request: SynapseRequest) -> Tuple[int, JsonDict]: + requester = await self.auth.get_user_by_req(request, allow_guest=True) + user = requester.user + device_id = requester.device_id + + timeout = parse_integer(request, "timeout", default=0) + # Position in the stream + from_token_string = parse_string(request, "pos") + + from_token = None + if from_token_string is not None: + from_token = await StreamToken.from_string(self.store, from_token_string) + + # TODO: We currently don't know whether we're going to use sticky params or + # maybe some filters like sync v2 where they are built up once and referenced + # by filter ID. For now, we will just prototype with always passing everything + # in. + body = parse_and_validate_json_object_from_request(request, SlidingSyncBody) + logger.info("Sliding sync request: %r", body) + + sync_config = SlidingSyncConfig( + user=user, + device_id=device_id, + # FIXME: Currently, we're just manually copying the fields from the + # `SlidingSyncBody` into the config. How can we gurantee into the future + # that we don't forget any? I would like something more structured like + # `copy_attributes(from=body, to=config)` + lists=body.lists, + room_subscriptions=body.room_subscriptions, + extensions=body.extensions, + ) + + sliding_sync_results = await self.sliding_sync_handler.wait_for_sync_for_user( + requester, + sync_config, + from_token, + timeout, + ) + + # The client may have disconnected by now; don't bother to serialize the + # response if so. + if request._disconnected: + logger.info("Client has disconnected; not serializing response.") + return 200, {} + + response_content = await self.encode_response(sliding_sync_results) + + return 200, response_content + + # TODO: Is there a better way to encode things? + async def encode_response( + self, + sliding_sync_result: SlidingSyncResult, + ) -> JsonDict: + response: JsonDict = defaultdict(dict) + + response["next_pos"] = await sliding_sync_result.next_pos.to_string(self.store) + serialized_lists = self.encode_lists(sliding_sync_result.lists) + if serialized_lists: + response["lists"] = serialized_lists + response["rooms"] = {} # TODO: sliding_sync_result.rooms + response["extensions"] = {} # TODO: sliding_sync_result.extensions + + return response + + def encode_lists( + self, lists: Dict[str, SlidingSyncResult.SlidingWindowList] + ) -> JsonDict: + def encode_operation( + operation: SlidingSyncResult.SlidingWindowList.Operation, + ) -> JsonDict: + return { + "op": operation.op.value, + "range": operation.range, + "room_ids": operation.room_ids, + } + + serialized_lists = {} + for list_key, list_result in lists.items(): + serialized_lists[list_key] = { + "count": list_result.count, + "ops": [encode_operation(op) for op in list_result.ops], + } + + return serialized_lists + + def register_servlets(hs: "HomeServer", http_server: HttpServer) -> None: SyncRestServlet(hs).register(http_server) + + if hs.config.experimental.msc3575_enabled: + SlidingSyncRestServlet(hs).register(http_server) + SlidingSyncE2eeRestServlet(hs).register(http_server) diff --git a/synapse/rest/client/versions.py b/synapse/rest/client/versions.py index 56de6906d0..f428158139 100644 --- a/synapse/rest/client/versions.py +++ b/synapse/rest/client/versions.py @@ -149,6 +149,8 @@ class VersionsRestServlet(RestServlet): is not None ) ), + # MSC4151: Report room API (Client-Server API) + "org.matrix.msc4151": self.config.experimental.msc4151_enabled, }, }, ) diff --git a/synapse/rest/key/v2/remote_key_resource.py b/synapse/rest/key/v2/remote_key_resource.py index dc7325fc57..a411ed614e 100644 --- a/synapse/rest/key/v2/remote_key_resource.py +++ b/synapse/rest/key/v2/remote_key_resource.py @@ -41,9 +41,9 @@ from synapse.http.servlet import ( parse_and_validate_json_object_from_request, parse_integer, ) -from synapse.rest.models import RequestBodyModel from synapse.storage.keys import FetchKeyResultForRemote from synapse.types import JsonDict +from synapse.types.rest import RequestBodyModel from synapse.util import json_decoder from synapse.util.async_helpers import yieldable_gather_results diff --git a/synapse/rest/media/download_resource.py b/synapse/rest/media/download_resource.py index 8ba723c8d4..1628d58926 100644 --- a/synapse/rest/media/download_resource.py +++ b/synapse/rest/media/download_resource.py @@ -97,6 +97,12 @@ class DownloadResource(RestServlet): respond_404(request) return + ip_address = request.getClientAddress().host await self.media_repo.get_remote_media( - request, server_name, media_id, file_name, max_timeout_ms + request, + server_name, + media_id, + file_name, + max_timeout_ms, + ip_address, ) diff --git a/synapse/rest/media/thumbnail_resource.py b/synapse/rest/media/thumbnail_resource.py index 7cb335c7c3..ce511c6dce 100644 --- a/synapse/rest/media/thumbnail_resource.py +++ b/synapse/rest/media/thumbnail_resource.py @@ -22,23 +22,18 @@ import logging import re -from typing import TYPE_CHECKING, List, Optional, Tuple +from typing import TYPE_CHECKING -from synapse.api.errors import Codes, SynapseError, cs_error -from synapse.config.repository import THUMBNAIL_SUPPORTED_MEDIA_FORMAT_MAP -from synapse.http.server import respond_with_json, set_corp_headers, set_cors_headers +from synapse.http.server import set_corp_headers, set_cors_headers from synapse.http.servlet import RestServlet, parse_integer, parse_string from synapse.http.site import SynapseRequest from synapse.media._base import ( DEFAULT_MAX_TIMEOUT_MS, MAXIMUM_ALLOWED_MAX_TIMEOUT_MS, - FileInfo, - ThumbnailInfo, respond_404, - respond_with_file, - respond_with_responder, ) from synapse.media.media_storage import MediaStorage +from synapse.media.thumbnailer import ThumbnailProvider from synapse.util.stringutils import parse_and_validate_server_name if TYPE_CHECKING: @@ -66,10 +61,11 @@ class ThumbnailResource(RestServlet): self.store = hs.get_datastores().main self.media_repo = media_repo self.media_storage = media_storage - self.dynamic_thumbnails = hs.config.media.dynamic_thumbnails self._is_mine_server_name = hs.is_mine_server_name self._server_name = hs.hostname self.prevent_media_downloads_from = hs.config.media.prevent_media_downloads_from + self.dynamic_thumbnails = hs.config.media.dynamic_thumbnails + self.thumbnail_provider = ThumbnailProvider(hs, media_repo, media_storage) async def on_GET( self, request: SynapseRequest, server_name: str, media_id: str @@ -91,11 +87,11 @@ class ThumbnailResource(RestServlet): if self._is_mine_server_name(server_name): if self.dynamic_thumbnails: - await self._select_or_generate_local_thumbnail( + await self.thumbnail_provider.select_or_generate_local_thumbnail( request, media_id, width, height, method, m_type, max_timeout_ms ) else: - await self._respond_local_thumbnail( + await self.thumbnail_provider.respond_local_thumbnail( request, media_id, width, height, method, m_type, max_timeout_ms ) self.media_repo.mark_recently_accessed(None, media_id) @@ -108,10 +104,11 @@ class ThumbnailResource(RestServlet): respond_404(request) return + ip_address = request.getClientAddress().host remote_resp_function = ( - self._select_or_generate_remote_thumbnail + self.thumbnail_provider.select_or_generate_remote_thumbnail if self.dynamic_thumbnails - else self._respond_remote_thumbnail + else self.thumbnail_provider.respond_remote_thumbnail ) await remote_resp_function( request, @@ -122,459 +119,6 @@ class ThumbnailResource(RestServlet): method, m_type, max_timeout_ms, + ip_address, ) self.media_repo.mark_recently_accessed(server_name, media_id) - - async def _respond_local_thumbnail( - self, - request: SynapseRequest, - media_id: str, - width: int, - height: int, - method: str, - m_type: str, - max_timeout_ms: int, - ) -> None: - media_info = await self.media_repo.get_local_media_info( - request, media_id, max_timeout_ms - ) - if not media_info: - return - - thumbnail_infos = await self.store.get_local_media_thumbnails(media_id) - await self._select_and_respond_with_thumbnail( - request, - width, - height, - method, - m_type, - thumbnail_infos, - media_id, - media_id, - url_cache=bool(media_info.url_cache), - server_name=None, - ) - - async def _select_or_generate_local_thumbnail( - self, - request: SynapseRequest, - media_id: str, - desired_width: int, - desired_height: int, - desired_method: str, - desired_type: str, - max_timeout_ms: int, - ) -> None: - media_info = await self.media_repo.get_local_media_info( - request, media_id, max_timeout_ms - ) - - if not media_info: - return - - thumbnail_infos = await self.store.get_local_media_thumbnails(media_id) - for info in thumbnail_infos: - t_w = info.width == desired_width - t_h = info.height == desired_height - t_method = info.method == desired_method - t_type = info.type == desired_type - - if t_w and t_h and t_method and t_type: - file_info = FileInfo( - server_name=None, - file_id=media_id, - url_cache=bool(media_info.url_cache), - thumbnail=info, - ) - - responder = await self.media_storage.fetch_media(file_info) - if responder: - await respond_with_responder( - request, responder, info.type, info.length - ) - return - - logger.debug("We don't have a thumbnail of that size. Generating") - - # Okay, so we generate one. - file_path = await self.media_repo.generate_local_exact_thumbnail( - media_id, - desired_width, - desired_height, - desired_method, - desired_type, - url_cache=bool(media_info.url_cache), - ) - - if file_path: - await respond_with_file(request, desired_type, file_path) - else: - logger.warning("Failed to generate thumbnail") - raise SynapseError(400, "Failed to generate thumbnail.") - - async def _select_or_generate_remote_thumbnail( - self, - request: SynapseRequest, - server_name: str, - media_id: str, - desired_width: int, - desired_height: int, - desired_method: str, - desired_type: str, - max_timeout_ms: int, - ) -> None: - media_info = await self.media_repo.get_remote_media_info( - server_name, media_id, max_timeout_ms - ) - if not media_info: - respond_404(request) - return - - thumbnail_infos = await self.store.get_remote_media_thumbnails( - server_name, media_id - ) - - file_id = media_info.filesystem_id - - for info in thumbnail_infos: - t_w = info.width == desired_width - t_h = info.height == desired_height - t_method = info.method == desired_method - t_type = info.type == desired_type - - if t_w and t_h and t_method and t_type: - file_info = FileInfo( - server_name=server_name, - file_id=file_id, - thumbnail=info, - ) - - responder = await self.media_storage.fetch_media(file_info) - if responder: - await respond_with_responder( - request, responder, info.type, info.length - ) - return - - logger.debug("We don't have a thumbnail of that size. Generating") - - # Okay, so we generate one. - file_path = await self.media_repo.generate_remote_exact_thumbnail( - server_name, - file_id, - media_id, - desired_width, - desired_height, - desired_method, - desired_type, - ) - - if file_path: - await respond_with_file(request, desired_type, file_path) - else: - logger.warning("Failed to generate thumbnail") - raise SynapseError(400, "Failed to generate thumbnail.") - - async def _respond_remote_thumbnail( - self, - request: SynapseRequest, - server_name: str, - media_id: str, - width: int, - height: int, - method: str, - m_type: str, - max_timeout_ms: int, - ) -> None: - # TODO: Don't download the whole remote file - # We should proxy the thumbnail from the remote server instead of - # downloading the remote file and generating our own thumbnails. - media_info = await self.media_repo.get_remote_media_info( - server_name, media_id, max_timeout_ms - ) - if not media_info: - return - - thumbnail_infos = await self.store.get_remote_media_thumbnails( - server_name, media_id - ) - await self._select_and_respond_with_thumbnail( - request, - width, - height, - method, - m_type, - thumbnail_infos, - media_id, - media_info.filesystem_id, - url_cache=False, - server_name=server_name, - ) - - async def _select_and_respond_with_thumbnail( - self, - request: SynapseRequest, - desired_width: int, - desired_height: int, - desired_method: str, - desired_type: str, - thumbnail_infos: List[ThumbnailInfo], - media_id: str, - file_id: str, - url_cache: bool, - server_name: Optional[str] = None, - ) -> None: - """ - Respond to a request with an appropriate thumbnail from the previously generated thumbnails. - - Args: - request: The incoming request. - desired_width: The desired width, the returned thumbnail may be larger than this. - desired_height: The desired height, the returned thumbnail may be larger than this. - desired_method: The desired method used to generate the thumbnail. - desired_type: The desired content-type of the thumbnail. - thumbnail_infos: A list of thumbnail info of candidate thumbnails. - file_id: The ID of the media that a thumbnail is being requested for. - url_cache: True if this is from a URL cache. - server_name: The server name, if this is a remote thumbnail. - """ - logger.debug( - "_select_and_respond_with_thumbnail: media_id=%s desired=%sx%s (%s) thumbnail_infos=%s", - media_id, - desired_width, - desired_height, - desired_method, - thumbnail_infos, - ) - - # If `dynamic_thumbnails` is enabled, we expect Synapse to go down a - # different code path to handle it. - assert not self.dynamic_thumbnails - - if thumbnail_infos: - file_info = self._select_thumbnail( - desired_width, - desired_height, - desired_method, - desired_type, - thumbnail_infos, - file_id, - url_cache, - server_name, - ) - if not file_info: - logger.info("Couldn't find a thumbnail matching the desired inputs") - respond_404(request) - return - - # The thumbnail property must exist. - assert file_info.thumbnail is not None - - responder = await self.media_storage.fetch_media(file_info) - if responder: - await respond_with_responder( - request, - responder, - file_info.thumbnail.type, - file_info.thumbnail.length, - ) - return - - # If we can't find the thumbnail we regenerate it. This can happen - # if e.g. we've deleted the thumbnails but still have the original - # image somewhere. - # - # Since we have an entry for the thumbnail in the DB we a) know we - # have have successfully generated the thumbnail in the past (so we - # don't need to worry about repeatedly failing to generate - # thumbnails), and b) have already calculated that appropriate - # width/height/method so we can just call the "generate exact" - # methods. - - # First let's check that we do actually have the original image - # still. This will throw a 404 if we don't. - # TODO: We should refetch the thumbnails for remote media. - await self.media_storage.ensure_media_is_in_local_cache( - FileInfo(server_name, file_id, url_cache=url_cache) - ) - - if server_name: - await self.media_repo.generate_remote_exact_thumbnail( - server_name, - file_id=file_id, - media_id=media_id, - t_width=file_info.thumbnail.width, - t_height=file_info.thumbnail.height, - t_method=file_info.thumbnail.method, - t_type=file_info.thumbnail.type, - ) - else: - await self.media_repo.generate_local_exact_thumbnail( - media_id=media_id, - t_width=file_info.thumbnail.width, - t_height=file_info.thumbnail.height, - t_method=file_info.thumbnail.method, - t_type=file_info.thumbnail.type, - url_cache=url_cache, - ) - - responder = await self.media_storage.fetch_media(file_info) - await respond_with_responder( - request, - responder, - file_info.thumbnail.type, - file_info.thumbnail.length, - ) - else: - # This might be because: - # 1. We can't create thumbnails for the given media (corrupted or - # unsupported file type), or - # 2. The thumbnailing process never ran or errored out initially - # when the media was first uploaded (these bugs should be - # reported and fixed). - # Note that we don't attempt to generate a thumbnail now because - # `dynamic_thumbnails` is disabled. - logger.info("Failed to find any generated thumbnails") - - assert request.path is not None - respond_with_json( - request, - 400, - cs_error( - "Cannot find any thumbnails for the requested media ('%s'). This might mean the media is not a supported_media_format=(%s) or that thumbnailing failed for some other reason. (Dynamic thumbnails are disabled on this server.)" - % ( - request.path.decode(), - ", ".join(THUMBNAIL_SUPPORTED_MEDIA_FORMAT_MAP.keys()), - ), - code=Codes.UNKNOWN, - ), - send_cors=True, - ) - - def _select_thumbnail( - self, - desired_width: int, - desired_height: int, - desired_method: str, - desired_type: str, - thumbnail_infos: List[ThumbnailInfo], - file_id: str, - url_cache: bool, - server_name: Optional[str], - ) -> Optional[FileInfo]: - """ - Choose an appropriate thumbnail from the previously generated thumbnails. - - Args: - desired_width: The desired width, the returned thumbnail may be larger than this. - desired_height: The desired height, the returned thumbnail may be larger than this. - desired_method: The desired method used to generate the thumbnail. - desired_type: The desired content-type of the thumbnail. - thumbnail_infos: A list of thumbnail infos of candidate thumbnails. - file_id: The ID of the media that a thumbnail is being requested for. - url_cache: True if this is from a URL cache. - server_name: The server name, if this is a remote thumbnail. - - Returns: - The thumbnail which best matches the desired parameters. - """ - desired_method = desired_method.lower() - - # The chosen thumbnail. - thumbnail_info = None - - d_w = desired_width - d_h = desired_height - - if desired_method == "crop": - # Thumbnails that match equal or larger sizes of desired width/height. - crop_info_list: List[ - Tuple[int, int, int, bool, Optional[int], ThumbnailInfo] - ] = [] - # Other thumbnails. - crop_info_list2: List[ - Tuple[int, int, int, bool, Optional[int], ThumbnailInfo] - ] = [] - for info in thumbnail_infos: - # Skip thumbnails generated with different methods. - if info.method != "crop": - continue - - t_w = info.width - t_h = info.height - aspect_quality = abs(d_w * t_h - d_h * t_w) - min_quality = 0 if d_w <= t_w and d_h <= t_h else 1 - size_quality = abs((d_w - t_w) * (d_h - t_h)) - type_quality = desired_type != info.type - length_quality = info.length - if t_w >= d_w or t_h >= d_h: - crop_info_list.append( - ( - aspect_quality, - min_quality, - size_quality, - type_quality, - length_quality, - info, - ) - ) - else: - crop_info_list2.append( - ( - aspect_quality, - min_quality, - size_quality, - type_quality, - length_quality, - info, - ) - ) - # Pick the most appropriate thumbnail. Some values of `desired_width` and - # `desired_height` may result in a tie, in which case we avoid comparing on - # the thumbnail info and pick the thumbnail that appears earlier - # in the list of candidates. - if crop_info_list: - thumbnail_info = min(crop_info_list, key=lambda t: t[:-1])[-1] - elif crop_info_list2: - thumbnail_info = min(crop_info_list2, key=lambda t: t[:-1])[-1] - elif desired_method == "scale": - # Thumbnails that match equal or larger sizes of desired width/height. - info_list: List[Tuple[int, bool, int, ThumbnailInfo]] = [] - # Other thumbnails. - info_list2: List[Tuple[int, bool, int, ThumbnailInfo]] = [] - - for info in thumbnail_infos: - # Skip thumbnails generated with different methods. - if info.method != "scale": - continue - - t_w = info.width - t_h = info.height - size_quality = abs((d_w - t_w) * (d_h - t_h)) - type_quality = desired_type != info.type - length_quality = info.length - if t_w >= d_w or t_h >= d_h: - info_list.append((size_quality, type_quality, length_quality, info)) - else: - info_list2.append( - (size_quality, type_quality, length_quality, info) - ) - # Pick the most appropriate thumbnail. Some values of `desired_width` and - # `desired_height` may result in a tie, in which case we avoid comparing on - # the thumbnail info and pick the thumbnail that appears earlier - # in the list of candidates. - if info_list: - thumbnail_info = min(info_list, key=lambda t: t[:-1])[-1] - elif info_list2: - thumbnail_info = min(info_list2, key=lambda t: t[:-1])[-1] - - if thumbnail_info: - return FileInfo( - file_id=file_id, - url_cache=url_cache, - server_name=server_name, - thumbnail=thumbnail_info, - ) - - # No matching thumbnail was found. - return None diff --git a/synapse/rest/synapse/client/__init__.py b/synapse/rest/synapse/client/__init__.py index ba6576d4db..7b5bfc0421 100644 --- a/synapse/rest/synapse/client/__init__.py +++ b/synapse/rest/synapse/client/__init__.py @@ -23,6 +23,7 @@ from typing import TYPE_CHECKING, Mapping from twisted.web.resource import Resource +from synapse.rest.synapse.client.federation_whitelist import FederationWhitelistResource from synapse.rest.synapse.client.new_user_consent import NewUserConsentResource from synapse.rest.synapse.client.pick_idp import PickIdpResource from synapse.rest.synapse.client.pick_username import pick_username_resource @@ -77,6 +78,9 @@ def build_synapse_client_resource_tree(hs: "HomeServer") -> Mapping[str, Resourc # To be removed in Synapse v1.32.0. resources["/_matrix/saml2"] = res + if hs.config.federation.federation_whitelist_endpoint_enabled: + resources[FederationWhitelistResource.PATH] = FederationWhitelistResource(hs) + if hs.config.experimental.msc4108_enabled: resources["/_synapse/client/rendezvous"] = MSC4108RendezvousSessionResource(hs) diff --git a/synapse/rest/synapse/client/federation_whitelist.py b/synapse/rest/synapse/client/federation_whitelist.py new file mode 100644 index 0000000000..2b8f0320e0 --- /dev/null +++ b/synapse/rest/synapse/client/federation_whitelist.py @@ -0,0 +1,66 @@ +# +# This file is licensed under the Affero General Public License (AGPL) version 3. +# +# Copyright (C) 2024 New Vector, Ltd +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as +# published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# See the GNU Affero General Public License for more details: +# <https://www.gnu.org/licenses/agpl-3.0.html>. +# + +import logging +from typing import TYPE_CHECKING, Tuple + +from synapse.http.server import DirectServeJsonResource +from synapse.http.site import SynapseRequest +from synapse.types import JsonDict + +if TYPE_CHECKING: + from synapse.server import HomeServer + +logger = logging.getLogger(__name__) + + +class FederationWhitelistResource(DirectServeJsonResource): + """Custom endpoint (disabled by default) to fetch the federation whitelist + config. + + Only enabled if `federation_whitelist_endpoint_enabled` feature is enabled. + + Response format: + + { + "whitelist_enabled": true, // Whether the federation whitelist is being enforced + "whitelist": [ // Which server names are allowed by the whitelist + "example.com" + ] + } + """ + + PATH = "/_synapse/client/v1/config/federation_whitelist" + + def __init__(self, hs: "HomeServer"): + super().__init__() + + self._federation_whitelist = hs.config.federation.federation_domain_whitelist + + self._auth = hs.get_auth() + + async def _async_render_GET(self, request: SynapseRequest) -> Tuple[int, JsonDict]: + await self._auth.get_user_by_req(request) + + whitelist = [] + if self._federation_whitelist: + # federation_whitelist is actually a dict, not a list + whitelist = list(self._federation_whitelist) + + return_dict: JsonDict = { + "whitelist_enabled": self._federation_whitelist is not None, + "whitelist": whitelist, + } + + return 200, return_dict diff --git a/synapse/server.py b/synapse/server.py index 95e319d2e6..ae927c3904 100644 --- a/synapse/server.py +++ b/synapse/server.py @@ -109,6 +109,7 @@ from synapse.handlers.room_summary import RoomSummaryHandler from synapse.handlers.search import SearchHandler from synapse.handlers.send_email import SendEmailHandler from synapse.handlers.set_password import SetPasswordHandler +from synapse.handlers.sliding_sync import SlidingSyncHandler from synapse.handlers.sso import SsoHandler from synapse.handlers.stats import StatsHandler from synapse.handlers.sync import SyncHandler @@ -554,6 +555,9 @@ class HomeServer(metaclass=abc.ABCMeta): def get_sync_handler(self) -> SyncHandler: return SyncHandler(self) + def get_sliding_sync_handler(self) -> SlidingSyncHandler: + return SlidingSyncHandler(self) + @cache_in_self def get_room_list_handler(self) -> RoomListHandler: return RoomListHandler(self) diff --git a/synapse/storage/controllers/persist_events.py b/synapse/storage/controllers/persist_events.py index 84699a2ee1..d0e015bf19 100644 --- a/synapse/storage/controllers/persist_events.py +++ b/synapse/storage/controllers/persist_events.py @@ -617,6 +617,17 @@ class EventsPersistenceStorageController: room_id, chunk ) + with Measure(self._clock, "calculate_chain_cover_index_for_events"): + # We now calculate chain ID/sequence numbers for any state events we're + # persisting. We ignore out of band memberships as we're not in the room + # and won't have their auth chain (we'll fix it up later if we join the + # room). + # + # See: docs/auth_chain_difference_algorithm.md + new_event_links = await self.persist_events_store.calculate_chain_cover_index_for_events( + room_id, [e for e, _ in chunk] + ) + await self.persist_events_store._persist_events_and_state_updates( room_id, chunk, @@ -624,6 +635,7 @@ class EventsPersistenceStorageController: new_forward_extremities=new_forward_extremities, use_negative_stream_ordering=backfilled, inhibit_local_membership_updates=backfilled, + new_event_links=new_event_links, ) return replaced_events diff --git a/synapse/storage/controllers/state.py b/synapse/storage/controllers/state.py index f9eced23bf..cc9b162ae4 100644 --- a/synapse/storage/controllers/state.py +++ b/synapse/storage/controllers/state.py @@ -45,7 +45,7 @@ from synapse.storage.util.partial_state_events_tracker import ( PartialStateEventsTracker, ) from synapse.synapse_rust.acl import ServerAclEvaluator -from synapse.types import MutableStateMap, StateMap, get_domain_from_id +from synapse.types import MutableStateMap, StateMap, StreamToken, get_domain_from_id from synapse.types.state import StateFilter from synapse.util.async_helpers import Linearizer from synapse.util.caches import intern_string @@ -372,6 +372,91 @@ class StateStorageController: ) return state_map[event_id] + async def get_state_after_event( + self, + event_id: str, + state_filter: Optional[StateFilter] = None, + await_full_state: bool = True, + ) -> StateMap[str]: + """ + Get the room state after the given event + + Args: + event_id: event of interest + state_filter: The state filter used to fetch state from the database. + await_full_state: if `True`, will block if we do not yet have complete state + at the event and `state_filter` is not satisfied by partial state. + Defaults to `True`. + """ + state_ids = await self.get_state_ids_for_event( + event_id, + state_filter=state_filter or StateFilter.all(), + await_full_state=await_full_state, + ) + + # using get_metadata_for_events here (instead of get_event) sidesteps an issue + # with redactions: if `event_id` is a redaction event, and we don't have the + # original (possibly because it got purged), get_event will refuse to return + # the redaction event, which isn't terribly helpful here. + # + # (To be fair, in that case we could assume it's *not* a state event, and + # therefore we don't need to worry about it. But still, it seems cleaner just + # to pull the metadata.) + m = (await self.stores.main.get_metadata_for_events([event_id]))[event_id] + if m.state_key is not None and m.rejection_reason is None: + state_ids = dict(state_ids) + state_ids[(m.event_type, m.state_key)] = event_id + + return state_ids + + async def get_state_at( + self, + room_id: str, + stream_position: StreamToken, + state_filter: Optional[StateFilter] = None, + await_full_state: bool = True, + ) -> StateMap[str]: + """Get the room state at a particular stream position + + Args: + room_id: room for which to get state + stream_position: point at which to get state + state_filter: The state filter used to fetch state from the database. + await_full_state: if `True`, will block if we do not yet have complete state + at the last event in the room before `stream_position` and + `state_filter` is not satisfied by partial state. Defaults to `True`. + """ + # FIXME: This gets the state at the latest event before the stream ordering, + # which might not be the same as the "current state" of the room at the time + # of the stream token if there were multiple forward extremities at the time. + last_event_id = ( + await self.stores.main.get_last_event_id_in_room_before_stream_ordering( + room_id, + end_token=stream_position.room_key, + ) + ) + + if last_event_id: + state = await self.get_state_after_event( + last_event_id, + state_filter=state_filter or StateFilter.all(), + await_full_state=await_full_state, + ) + + else: + # no events in this room - so presumably no state + state = {} + + # (erikj) This should be rarely hit, but we've had some reports that + # we get more state down gappy syncs than we should, so let's add + # some logging. + logger.info( + "Failed to find any events in room %s at %s", + room_id, + stream_position.room_key, + ) + return state + @trace @tag_args async def get_state_for_groups( diff --git a/synapse/storage/database.py b/synapse/storage/database.py index d9c85e411e..569f618193 100644 --- a/synapse/storage/database.py +++ b/synapse/storage/database.py @@ -2461,7 +2461,11 @@ class DatabasePool: def make_in_list_sql_clause( - database_engine: BaseDatabaseEngine, column: str, iterable: Collection[Any] + database_engine: BaseDatabaseEngine, + column: str, + iterable: Collection[Any], + *, + negative: bool = False, ) -> Tuple[str, list]: """Returns an SQL clause that checks the given column is in the iterable. @@ -2474,6 +2478,7 @@ def make_in_list_sql_clause( database_engine column: Name of the column iterable: The values to check the column against. + negative: Whether we should check for inequality, i.e. `NOT IN` Returns: A tuple of SQL query and the args @@ -2482,9 +2487,19 @@ def make_in_list_sql_clause( if database_engine.supports_using_any_list: # This should hopefully be faster, but also makes postgres query # stats easier to understand. - return "%s = ANY(?)" % (column,), [list(iterable)] + if not negative: + clause = f"{column} = ANY(?)" + else: + clause = f"{column} != ALL(?)" + + return clause, [list(iterable)] else: - return "%s IN (%s)" % (column, ",".join("?" for _ in iterable)), list(iterable) + params = ",".join("?" for _ in iterable) + if not negative: + clause = f"{column} IN ({params})" + else: + clause = f"{column} NOT IN ({params})" + return clause, list(iterable) # These overloads ensure that `columns` and `iterable` values have the same length. diff --git a/synapse/storage/databases/main/account_data.py b/synapse/storage/databases/main/account_data.py index 563450a97e..9611a84932 100644 --- a/synapse/storage/databases/main/account_data.py +++ b/synapse/storage/databases/main/account_data.py @@ -43,11 +43,9 @@ from synapse.storage.database import ( ) from synapse.storage.databases.main.cache import CacheInvalidationWorkerStore from synapse.storage.databases.main.push_rule import PushRulesWorkerStore -from synapse.storage.engines import PostgresEngine from synapse.storage.util.id_generators import ( AbstractStreamIdGenerator, MultiWriterIdGenerator, - StreamIdGenerator, ) from synapse.types import JsonDict, JsonMapping from synapse.util import json_encoder @@ -75,37 +73,20 @@ class AccountDataWorkerStore(PushRulesWorkerStore, CacheInvalidationWorkerStore) self._account_data_id_gen: AbstractStreamIdGenerator - if isinstance(database.engine, PostgresEngine): - self._account_data_id_gen = MultiWriterIdGenerator( - db_conn=db_conn, - db=database, - notifier=hs.get_replication_notifier(), - stream_name="account_data", - instance_name=self._instance_name, - tables=[ - ("room_account_data", "instance_name", "stream_id"), - ("room_tags_revisions", "instance_name", "stream_id"), - ("account_data", "instance_name", "stream_id"), - ], - sequence_name="account_data_sequence", - writers=hs.config.worker.writers.account_data, - ) - else: - # Multiple writers are not supported for SQLite. - # - # We shouldn't be running in worker mode with SQLite, but its useful - # to support it for unit tests. - self._account_data_id_gen = StreamIdGenerator( - db_conn, - hs.get_replication_notifier(), - "room_account_data", - "stream_id", - extra_tables=[ - ("account_data", "stream_id"), - ("room_tags_revisions", "stream_id"), - ], - is_writer=self._instance_name in hs.config.worker.writers.account_data, - ) + self._account_data_id_gen = MultiWriterIdGenerator( + db_conn=db_conn, + db=database, + notifier=hs.get_replication_notifier(), + stream_name="account_data", + instance_name=self._instance_name, + tables=[ + ("room_account_data", "instance_name", "stream_id"), + ("room_tags_revisions", "instance_name", "stream_id"), + ("account_data", "instance_name", "stream_id"), + ], + sequence_name="account_data_sequence", + writers=hs.config.worker.writers.account_data, + ) account_max = self.get_max_account_data_stream_id() self._account_data_stream_cache = StreamChangeCache( diff --git a/synapse/storage/databases/main/cache.py b/synapse/storage/databases/main/cache.py index bfd492d95d..c6787faea0 100644 --- a/synapse/storage/databases/main/cache.py +++ b/synapse/storage/databases/main/cache.py @@ -318,7 +318,13 @@ class CacheInvalidationWorkerStore(SQLBaseStore): self._invalidate_local_get_event_cache(redacts) # type: ignore[attr-defined] # Caches which might leak edits must be invalidated for the event being # redacted. - self._attempt_to_invalidate_cache("get_relations_for_event", (redacts,)) + self._attempt_to_invalidate_cache( + "get_relations_for_event", + ( + room_id, + redacts, + ), + ) self._attempt_to_invalidate_cache("get_applicable_edit", (redacts,)) self._attempt_to_invalidate_cache("get_thread_id", (redacts,)) self._attempt_to_invalidate_cache("get_thread_id_for_receipts", (redacts,)) @@ -345,7 +351,13 @@ class CacheInvalidationWorkerStore(SQLBaseStore): ) if relates_to: - self._attempt_to_invalidate_cache("get_relations_for_event", (relates_to,)) + self._attempt_to_invalidate_cache( + "get_relations_for_event", + ( + room_id, + relates_to, + ), + ) self._attempt_to_invalidate_cache("get_references_for_event", (relates_to,)) self._attempt_to_invalidate_cache("get_applicable_edit", (relates_to,)) self._attempt_to_invalidate_cache("get_thread_summary", (relates_to,)) @@ -380,9 +392,9 @@ class CacheInvalidationWorkerStore(SQLBaseStore): self._attempt_to_invalidate_cache( "get_unread_event_push_actions_by_room_for_user", (room_id,) ) + self._attempt_to_invalidate_cache("get_relations_for_event", (room_id,)) self._attempt_to_invalidate_cache("_get_membership_from_event_id", None) - self._attempt_to_invalidate_cache("get_relations_for_event", None) self._attempt_to_invalidate_cache("get_applicable_edit", None) self._attempt_to_invalidate_cache("get_thread_id", None) self._attempt_to_invalidate_cache("get_thread_id_for_receipts", None) diff --git a/synapse/storage/databases/main/deviceinbox.py b/synapse/storage/databases/main/deviceinbox.py index e17821ff6e..07333efff8 100644 --- a/synapse/storage/databases/main/deviceinbox.py +++ b/synapse/storage/databases/main/deviceinbox.py @@ -50,16 +50,15 @@ from synapse.storage.database import ( LoggingTransaction, make_in_list_sql_clause, ) -from synapse.storage.engines import PostgresEngine from synapse.storage.util.id_generators import ( AbstractStreamIdGenerator, MultiWriterIdGenerator, - StreamIdGenerator, ) from synapse.types import JsonDict from synapse.util import json_encoder from synapse.util.caches.expiringcache import ExpiringCache from synapse.util.caches.stream_change_cache import StreamChangeCache +from synapse.util.stringutils import parse_and_validate_server_name if TYPE_CHECKING: from synapse.server import HomeServer @@ -89,35 +88,23 @@ class DeviceInboxWorkerStore(SQLBaseStore): expiry_ms=30 * 60 * 1000, ) - if isinstance(database.engine, PostgresEngine): - self._can_write_to_device = ( - self._instance_name in hs.config.worker.writers.to_device - ) + self._can_write_to_device = ( + self._instance_name in hs.config.worker.writers.to_device + ) - self._to_device_msg_id_gen: AbstractStreamIdGenerator = ( - MultiWriterIdGenerator( - db_conn=db_conn, - db=database, - notifier=hs.get_replication_notifier(), - stream_name="to_device", - instance_name=self._instance_name, - tables=[ - ("device_inbox", "instance_name", "stream_id"), - ("device_federation_outbox", "instance_name", "stream_id"), - ], - sequence_name="device_inbox_sequence", - writers=hs.config.worker.writers.to_device, - ) - ) - else: - self._can_write_to_device = True - self._to_device_msg_id_gen = StreamIdGenerator( - db_conn, - hs.get_replication_notifier(), - "device_inbox", - "stream_id", - extra_tables=[("device_federation_outbox", "stream_id")], - ) + self._to_device_msg_id_gen: AbstractStreamIdGenerator = MultiWriterIdGenerator( + db_conn=db_conn, + db=database, + notifier=hs.get_replication_notifier(), + stream_name="to_device", + instance_name=self._instance_name, + tables=[ + ("device_inbox", "instance_name", "stream_id"), + ("device_federation_outbox", "instance_name", "stream_id"), + ], + sequence_name="device_inbox_sequence", + writers=hs.config.worker.writers.to_device, + ) max_device_inbox_id = self._to_device_msg_id_gen.get_current_token() device_inbox_prefill, min_device_inbox_id = self.db_pool.get_cache_dict( @@ -978,6 +965,7 @@ class DeviceInboxWorkerStore(SQLBaseStore): class DeviceInboxBackgroundUpdateStore(SQLBaseStore): DEVICE_INBOX_STREAM_ID = "device_inbox_stream_drop" REMOVE_DEAD_DEVICES_FROM_INBOX = "remove_dead_devices_from_device_inbox" + CLEANUP_DEVICE_FEDERATION_OUTBOX = "cleanup_device_federation_outbox" def __init__( self, @@ -1003,6 +991,11 @@ class DeviceInboxBackgroundUpdateStore(SQLBaseStore): self._remove_dead_devices_from_device_inbox, ) + self.db_pool.updates.register_background_update_handler( + self.CLEANUP_DEVICE_FEDERATION_OUTBOX, + self._cleanup_device_federation_outbox, + ) + async def _background_drop_index_device_inbox( self, progress: JsonDict, batch_size: int ) -> int: @@ -1094,6 +1087,75 @@ class DeviceInboxBackgroundUpdateStore(SQLBaseStore): return batch_size + async def _cleanup_device_federation_outbox( + self, + progress: JsonDict, + batch_size: int, + ) -> int: + def _cleanup_device_federation_outbox_txn( + txn: LoggingTransaction, + ) -> bool: + if "max_stream_id" in progress: + max_stream_id = progress["max_stream_id"] + else: + txn.execute("SELECT max(stream_id) FROM device_federation_outbox") + res = cast(Tuple[Optional[int]], txn.fetchone()) + if res[0] is None: + # this can only happen if the `device_inbox` table is empty, in which + # case we have no work to do. + return True + else: + max_stream_id = res[0] + + start = progress.get("stream_id", 0) + stop = start + batch_size + + sql = """ + SELECT destination FROM device_federation_outbox + WHERE ? < stream_id AND stream_id <= ? + """ + + txn.execute(sql, (start, stop)) + + destinations = {d for d, in txn} + to_remove = set() + for d in destinations: + try: + parse_and_validate_server_name(d) + except ValueError: + to_remove.add(d) + + self.db_pool.simple_delete_many_txn( + txn, + table="device_federation_outbox", + column="destination", + values=to_remove, + keyvalues={}, + ) + + self.db_pool.updates._background_update_progress_txn( + txn, + self.CLEANUP_DEVICE_FEDERATION_OUTBOX, + { + "stream_id": stop, + "max_stream_id": max_stream_id, + }, + ) + + return stop >= max_stream_id + + finished = await self.db_pool.runInteraction( + "_cleanup_device_federation_outbox", + _cleanup_device_federation_outbox_txn, + ) + + if finished: + await self.db_pool.updates._end_background_update( + self.CLEANUP_DEVICE_FEDERATION_OUTBOX, + ) + + return batch_size + class DeviceInboxStore(DeviceInboxWorkerStore, DeviceInboxBackgroundUpdateStore): pass diff --git a/synapse/storage/databases/main/devices.py b/synapse/storage/databases/main/devices.py index 8dbcb3f5a0..59a035dd62 100644 --- a/synapse/storage/databases/main/devices.py +++ b/synapse/storage/databases/main/devices.py @@ -57,10 +57,7 @@ from synapse.storage.database import ( from synapse.storage.databases.main.end_to_end_keys import EndToEndKeyWorkerStore from synapse.storage.databases.main.roommember import RoomMemberWorkerStore from synapse.storage.types import Cursor -from synapse.storage.util.id_generators import ( - AbstractStreamIdGenerator, - StreamIdGenerator, -) +from synapse.storage.util.id_generators import MultiWriterIdGenerator from synapse.types import ( JsonDict, JsonMapping, @@ -70,10 +67,7 @@ from synapse.types import ( from synapse.util import json_decoder, json_encoder from synapse.util.caches.descriptors import cached, cachedList from synapse.util.caches.lrucache import LruCache -from synapse.util.caches.stream_change_cache import ( - AllEntitiesChangedResult, - StreamChangeCache, -) +from synapse.util.caches.stream_change_cache import StreamChangeCache from synapse.util.cancellation import cancellable from synapse.util.iterutils import batch_iter from synapse.util.stringutils import shortstr @@ -102,19 +96,26 @@ class DeviceWorkerStore(RoomMemberWorkerStore, EndToEndKeyWorkerStore): # In the worker store this is an ID tracker which we overwrite in the non-worker # class below that is used on the main process. - self._device_list_id_gen = StreamIdGenerator( - db_conn, - hs.get_replication_notifier(), - "device_lists_stream", - "stream_id", - extra_tables=[ - ("user_signature_stream", "stream_id"), - ("device_lists_outbound_pokes", "stream_id"), - ("device_lists_changes_in_room", "stream_id"), - ("device_lists_remote_pending", "stream_id"), - ("device_lists_changes_converted_stream_position", "stream_id"), + self._device_list_id_gen = MultiWriterIdGenerator( + db_conn=db_conn, + db=database, + notifier=hs.get_replication_notifier(), + stream_name="device_lists_stream", + instance_name=self._instance_name, + tables=[ + ("device_lists_stream", "instance_name", "stream_id"), + ("user_signature_stream", "instance_name", "stream_id"), + ("device_lists_outbound_pokes", "instance_name", "stream_id"), + ("device_lists_changes_in_room", "instance_name", "stream_id"), + ("device_lists_remote_pending", "instance_name", "stream_id"), + ( + "device_lists_changes_converted_stream_position", + "instance_name", + "stream_id", + ), ], - is_writer=hs.config.worker.worker_app is None, + sequence_name="device_lists_sequence", + writers=["master"], ) device_list_max = self._device_list_id_gen.get_current_token() @@ -132,6 +133,20 @@ class DeviceWorkerStore(RoomMemberWorkerStore, EndToEndKeyWorkerStore): prefilled_cache=device_list_prefill, ) + device_list_room_prefill, min_device_list_room_id = self.db_pool.get_cache_dict( + db_conn, + "device_lists_changes_in_room", + entity_column="room_id", + stream_column="stream_id", + max_value=device_list_max, + limit=10000, + ) + self._device_list_room_stream_cache = StreamChangeCache( + "DeviceListRoomStreamChangeCache", + min_device_list_room_id, + prefilled_cache=device_list_room_prefill, + ) + ( user_signature_stream_prefill, user_signature_stream_list_id, @@ -149,22 +164,24 @@ class DeviceWorkerStore(RoomMemberWorkerStore, EndToEndKeyWorkerStore): prefilled_cache=user_signature_stream_prefill, ) - ( - device_list_federation_prefill, - device_list_federation_list_id, - ) = self.db_pool.get_cache_dict( - db_conn, - "device_lists_outbound_pokes", - entity_column="destination", - stream_column="stream_id", - max_value=device_list_max, - limit=10000, - ) - self._device_list_federation_stream_cache = StreamChangeCache( - "DeviceListFederationStreamChangeCache", - device_list_federation_list_id, - prefilled_cache=device_list_federation_prefill, - ) + self._device_list_federation_stream_cache = None + if hs.should_send_federation(): + ( + device_list_federation_prefill, + device_list_federation_list_id, + ) = self.db_pool.get_cache_dict( + db_conn, + "device_lists_outbound_pokes", + entity_column="destination", + stream_column="stream_id", + max_value=device_list_max, + limit=10000, + ) + self._device_list_federation_stream_cache = StreamChangeCache( + "DeviceListFederationStreamChangeCache", + device_list_federation_list_id, + prefilled_cache=device_list_federation_prefill, + ) if hs.config.worker.run_background_tasks: self._clock.looping_call( @@ -192,23 +209,37 @@ class DeviceWorkerStore(RoomMemberWorkerStore, EndToEndKeyWorkerStore): ) -> None: for row in rows: if row.is_signature: - self._user_signature_stream_cache.entity_has_changed(row.entity, token) + self._user_signature_stream_cache.entity_has_changed(row.user_id, token) continue # The entities are either user IDs (starting with '@') whose devices # have changed, or remote servers that we need to tell about # changes. - if row.entity.startswith("@"): - self._device_list_stream_cache.entity_has_changed(row.entity, token) - self.get_cached_devices_for_user.invalidate((row.entity,)) - self._get_cached_user_device.invalidate((row.entity,)) - self.get_device_list_last_stream_id_for_remote.invalidate((row.entity,)) - - else: - self._device_list_federation_stream_cache.entity_has_changed( - row.entity, token + if not row.hosts_calculated: + self._device_list_stream_cache.entity_has_changed(row.user_id, token) + self.get_cached_devices_for_user.invalidate((row.user_id,)) + self._get_cached_user_device.invalidate((row.user_id,)) + self.get_device_list_last_stream_id_for_remote.invalidate( + (row.user_id,) ) + def device_lists_outbound_pokes_have_changed( + self, destinations: StrCollection, token: int + ) -> None: + assert self._device_list_federation_stream_cache is not None + + for destination in destinations: + self._device_list_federation_stream_cache.entity_has_changed( + destination, token + ) + + def device_lists_in_rooms_have_changed( + self, room_ids: StrCollection, token: int + ) -> None: + "Record that device lists have changed in rooms" + for room_id in room_ids: + self._device_list_room_stream_cache.entity_has_changed(room_id, token) + def get_device_stream_token(self) -> int: return self._device_list_id_gen.get_current_token() @@ -341,6 +372,11 @@ class DeviceWorkerStore(RoomMemberWorkerStore, EndToEndKeyWorkerStore): EDU contents. """ now_stream_id = self.get_device_stream_token() + if from_stream_id == now_stream_id: + return now_stream_id, [] + + if self._device_list_federation_stream_cache is None: + raise Exception("Func can only be used on federation senders") has_changed = self._device_list_federation_stream_cache.has_entity_changed( destination, int(from_stream_id) @@ -744,6 +780,7 @@ class DeviceWorkerStore(RoomMemberWorkerStore, EndToEndKeyWorkerStore): "stream_id": stream_id, "from_user_id": from_user_id, "user_ids": json_encoder.encode(user_ids), + "instance_name": self._instance_name, }, ) @@ -832,16 +869,6 @@ class DeviceWorkerStore(RoomMemberWorkerStore, EndToEndKeyWorkerStore): ) return {device[0]: db_to_json(device[1]) for device in devices} - def get_cached_device_list_changes( - self, - from_key: int, - ) -> AllEntitiesChangedResult: - """Get set of users whose devices have changed since `from_key`, or None - if that information is not in our cache. - """ - - return self._device_list_stream_cache.get_all_entities_changed(from_key) - @cancellable async def get_all_devices_changed( self, @@ -1005,10 +1032,10 @@ class DeviceWorkerStore(RoomMemberWorkerStore, EndToEndKeyWorkerStore): # This query Does The Right Thing where it'll correctly apply the # bounds to the inner queries. sql = """ - SELECT stream_id, entity FROM ( - SELECT stream_id, user_id AS entity FROM device_lists_stream + SELECT stream_id, user_id, hosts FROM ( + SELECT stream_id, user_id, false AS hosts FROM device_lists_stream UNION ALL - SELECT stream_id, destination AS entity FROM device_lists_outbound_pokes + SELECT DISTINCT stream_id, user_id, true AS hosts FROM device_lists_outbound_pokes ) AS e WHERE ? < stream_id AND stream_id <= ? ORDER BY stream_id ASC @@ -1457,7 +1484,7 @@ class DeviceWorkerStore(RoomMemberWorkerStore, EndToEndKeyWorkerStore): @cancellable async def get_device_list_changes_in_rooms( - self, room_ids: Collection[str], from_id: int + self, room_ids: Collection[str], from_id: int, to_id: int ) -> Optional[Set[str]]: """Return the set of users whose devices have changed in the given rooms since the given stream ID. @@ -1473,9 +1500,15 @@ class DeviceWorkerStore(RoomMemberWorkerStore, EndToEndKeyWorkerStore): if min_stream_id > from_id: return None + changed_room_ids = self._device_list_room_stream_cache.get_entities_changed( + room_ids, from_id + ) + if not changed_room_ids: + return set() + sql = """ SELECT DISTINCT user_id FROM device_lists_changes_in_room - WHERE {clause} AND stream_id >= ? + WHERE {clause} AND stream_id > ? AND stream_id <= ? """ def _get_device_list_changes_in_rooms_txn( @@ -1487,11 +1520,12 @@ class DeviceWorkerStore(RoomMemberWorkerStore, EndToEndKeyWorkerStore): return {user_id for user_id, in txn} changes = set() - for chunk in batch_iter(room_ids, 1000): + for chunk in batch_iter(changed_room_ids, 1000): clause, args = make_in_list_sql_clause( self.database_engine, "room_id", chunk ) args.append(from_id) + args.append(to_id) changes |= await self.db_pool.runInteraction( "get_device_list_changes_in_rooms", @@ -1502,6 +1536,34 @@ class DeviceWorkerStore(RoomMemberWorkerStore, EndToEndKeyWorkerStore): return changes + async def get_all_device_list_changes(self, from_id: int, to_id: int) -> Set[str]: + """Return the set of rooms where devices have changed since the given + stream ID. + + Will raise an exception if the given stream ID is too old. + """ + + min_stream_id = await self._get_min_device_lists_changes_in_room() + + if min_stream_id > from_id: + raise Exception("stream ID is too old") + + sql = """ + SELECT DISTINCT room_id FROM device_lists_changes_in_room + WHERE stream_id > ? AND stream_id <= ? + """ + + def _get_all_device_list_changes_txn( + txn: LoggingTransaction, + ) -> Set[str]: + txn.execute(sql, (from_id, to_id)) + return {room_id for room_id, in txn} + + return await self.db_pool.runInteraction( + "get_all_device_list_changes", + _get_all_device_list_changes_txn, + ) + async def get_device_list_changes_in_room( self, room_id: str, min_stream_id: int ) -> Collection[Tuple[str, str]]: @@ -1529,6 +1591,14 @@ class DeviceWorkerStore(RoomMemberWorkerStore, EndToEndKeyWorkerStore): get_device_list_changes_in_room_txn, ) + async def get_destinations_for_device(self, stream_id: int) -> StrCollection: + return await self.db_pool.simple_select_onecol( + table="device_lists_outbound_pokes", + keyvalues={"stream_id": stream_id}, + retcol="destination", + desc="get_destinations_for_device", + ) + class DeviceBackgroundUpdateStore(SQLBaseStore): def __init__( @@ -1539,6 +1609,8 @@ class DeviceBackgroundUpdateStore(SQLBaseStore): ): super().__init__(database, db_conn, hs) + self._instance_name = hs.get_instance_name() + self.db_pool.updates.register_background_index_update( "device_lists_stream_idx", index_name="device_lists_stream_user_id", @@ -1651,6 +1723,7 @@ class DeviceBackgroundUpdateStore(SQLBaseStore): "device_lists_outbound_pokes", { "stream_id": stream_id, + "instance_name": self._instance_name, "destination": destination, "user_id": user_id, "device_id": device_id, @@ -1687,10 +1760,6 @@ class DeviceBackgroundUpdateStore(SQLBaseStore): class DeviceStore(DeviceWorkerStore, DeviceBackgroundUpdateStore): - # Because we have write access, this will be a StreamIdGenerator - # (see DeviceWorkerStore.__init__) - _device_list_id_gen: AbstractStreamIdGenerator - def __init__( self, database: DatabasePool, @@ -1962,8 +2031,8 @@ class DeviceStore(DeviceWorkerStore, DeviceBackgroundUpdateStore): async def add_device_change_to_streams( self, user_id: str, - device_ids: Collection[str], - room_ids: Collection[str], + device_ids: StrCollection, + room_ids: StrCollection, ) -> Optional[int]: """Persist that a user's devices have been updated, and which hosts (if any) should be poked. @@ -2049,9 +2118,9 @@ class DeviceStore(DeviceWorkerStore, DeviceBackgroundUpdateStore): self.db_pool.simple_insert_many_txn( txn, table="device_lists_stream", - keys=("stream_id", "user_id", "device_id"), + keys=("instance_name", "stream_id", "user_id", "device_id"), values=[ - (stream_id, user_id, device_id) + (self._instance_name, stream_id, user_id, device_id) for stream_id, device_id in zip(stream_ids, device_ids) ], ) @@ -2062,18 +2131,18 @@ class DeviceStore(DeviceWorkerStore, DeviceBackgroundUpdateStore): user_id: str, device_id: str, hosts: Collection[str], - stream_ids: List[int], + stream_id: int, context: Optional[Dict[str, str]], ) -> None: - for host in hosts: - txn.call_after( - self._device_list_federation_stream_cache.entity_has_changed, - host, - stream_ids[-1], - ) + if self._device_list_federation_stream_cache: + for host in hosts: + txn.call_after( + self._device_list_federation_stream_cache.entity_has_changed, + host, + stream_id, + ) now = self._clock.time_msec() - stream_id_iterator = iter(stream_ids) encoded_context = json_encoder.encode(context) mark_sent = not self.hs.is_mine_id(user_id) @@ -2081,7 +2150,8 @@ class DeviceStore(DeviceWorkerStore, DeviceBackgroundUpdateStore): values = [ ( destination, - next(stream_id_iterator), + self._instance_name, + stream_id, user_id, device_id, mark_sent, @@ -2096,6 +2166,7 @@ class DeviceStore(DeviceWorkerStore, DeviceBackgroundUpdateStore): table="device_lists_outbound_pokes", keys=( "destination", + "instance_name", "stream_id", "user_id", "device_id", @@ -2114,16 +2185,40 @@ class DeviceStore(DeviceWorkerStore, DeviceBackgroundUpdateStore): device_id, { stream_id: destination - for (destination, stream_id, _, _, _, _, _) in values + for (destination, _, stream_id, _, _, _, _, _) in values }, ) + async def mark_redundant_device_lists_pokes( + self, + user_id: str, + device_id: str, + room_id: str, + converted_upto_stream_id: int, + ) -> None: + """If we've calculated the outbound pokes for a given room/device list + update, mark any subsequent changes as already converted""" + + sql = """ + UPDATE device_lists_changes_in_room + SET converted_to_destinations = true + WHERE stream_id > ? AND user_id = ? AND device_id = ? + AND room_id = ? AND NOT converted_to_destinations + """ + + def mark_redundant_device_lists_pokes_txn(txn: LoggingTransaction) -> None: + txn.execute(sql, (converted_upto_stream_id, user_id, device_id, room_id)) + + return await self.db_pool.runInteraction( + "mark_redundant_device_lists_pokes", mark_redundant_device_lists_pokes_txn + ) + def _add_device_outbound_room_poke_txn( self, txn: LoggingTransaction, user_id: str, - device_ids: Iterable[str], - room_ids: Collection[str], + device_ids: StrCollection, + room_ids: StrCollection, stream_ids: List[int], context: Dict[str, str], ) -> None: @@ -2143,6 +2238,7 @@ class DeviceStore(DeviceWorkerStore, DeviceBackgroundUpdateStore): "device_id", "room_id", "stream_id", + "instance_name", "converted_to_destinations", "opentracing_context", ), @@ -2152,6 +2248,7 @@ class DeviceStore(DeviceWorkerStore, DeviceBackgroundUpdateStore): device_id, room_id, stream_id, + self._instance_name, # We only need to calculate outbound pokes for local users not self.hs.is_mine_id(user_id), encoded_context, @@ -2161,6 +2258,10 @@ class DeviceStore(DeviceWorkerStore, DeviceBackgroundUpdateStore): ], ) + txn.call_after( + self.device_lists_in_rooms_have_changed, room_ids, max(stream_ids) + ) + async def get_uncoverted_outbound_room_pokes( self, start_stream_id: int, start_room_id: str, limit: int = 10 ) -> List[Tuple[str, str, str, int, Optional[Dict[str, str]]]]: @@ -2235,22 +2336,22 @@ class DeviceStore(DeviceWorkerStore, DeviceBackgroundUpdateStore): return def add_device_list_outbound_pokes_txn( - txn: LoggingTransaction, stream_ids: List[int] + txn: LoggingTransaction, stream_id: int ) -> None: self._add_device_outbound_poke_to_stream_txn( txn, user_id=user_id, device_id=device_id, hosts=hosts, - stream_ids=stream_ids, + stream_id=stream_id, context=context, ) - async with self._device_list_id_gen.get_next_mult(len(hosts)) as stream_ids: + async with self._device_list_id_gen.get_next() as stream_id: return await self.db_pool.runInteraction( "add_device_list_outbound_pokes", add_device_list_outbound_pokes_txn, - stream_ids, + stream_id, ) async def add_remote_device_list_to_pending( @@ -2267,7 +2368,10 @@ class DeviceStore(DeviceWorkerStore, DeviceBackgroundUpdateStore): "user_id": user_id, "device_id": device_id, }, - values={"stream_id": stream_id}, + values={ + "stream_id": stream_id, + "instance_name": self._instance_name, + }, desc="add_remote_device_list_to_pending", ) @@ -2317,15 +2421,16 @@ class DeviceStore(DeviceWorkerStore, DeviceBackgroundUpdateStore): `FALSE` have not been converted. """ - return cast( - Tuple[int, str], - await self.db_pool.simple_select_one( - table="device_lists_changes_converted_stream_position", - keyvalues={}, - retcols=["stream_id", "room_id"], - desc="get_device_change_last_converted_pos", - ), + # There should be only one row in this table, though we want to + # future-proof ourselves for when we have multiple rows (one for each + # instance). So to handle that case we take the minimum of all rows. + rows = await self.db_pool.simple_select_list( + table="device_lists_changes_converted_stream_position", + keyvalues={}, + retcols=["stream_id", "room_id"], + desc="get_device_change_last_converted_pos", ) + return cast(Tuple[int, str], min(rows)) async def set_device_change_last_converted_pos( self, @@ -2340,6 +2445,10 @@ class DeviceStore(DeviceWorkerStore, DeviceBackgroundUpdateStore): await self.db_pool.simple_update_one( table="device_lists_changes_converted_stream_position", keyvalues={}, - updatevalues={"stream_id": stream_id, "room_id": room_id}, + updatevalues={ + "stream_id": stream_id, + "instance_name": self._instance_name, + "room_id": room_id, + }, desc="set_device_change_last_converted_pos", ) diff --git a/synapse/storage/databases/main/end_to_end_keys.py b/synapse/storage/databases/main/end_to_end_keys.py index b219ea70ee..9e6c9561ae 100644 --- a/synapse/storage/databases/main/end_to_end_keys.py +++ b/synapse/storage/databases/main/end_to_end_keys.py @@ -58,7 +58,7 @@ from synapse.storage.database import ( ) from synapse.storage.databases.main.cache import CacheInvalidationWorkerStore from synapse.storage.engines import PostgresEngine -from synapse.storage.util.id_generators import StreamIdGenerator +from synapse.storage.util.id_generators import MultiWriterIdGenerator from synapse.types import JsonDict, JsonMapping from synapse.util import json_decoder, json_encoder from synapse.util.caches.descriptors import cached, cachedList @@ -123,9 +123,9 @@ class EndToEndKeyWorkerStore(EndToEndKeyBackgroundStore, CacheInvalidationWorker if stream_name == DeviceListsStream.NAME: for row in rows: assert isinstance(row, DeviceListsStream.DeviceListsStreamRow) - if row.entity.startswith("@"): + if not row.hosts_calculated: self._get_e2e_device_keys_for_federation_query_inner.invalidate( - (row.entity,) + (row.user_id,) ) super().process_replication_rows(stream_name, instance_name, token, rows) @@ -1448,11 +1448,17 @@ class EndToEndKeyStore(EndToEndKeyWorkerStore, SQLBaseStore): ): super().__init__(database, db_conn, hs) - self._cross_signing_id_gen = StreamIdGenerator( - db_conn, - hs.get_replication_notifier(), - "e2e_cross_signing_keys", - "stream_id", + self._cross_signing_id_gen = MultiWriterIdGenerator( + db_conn=db_conn, + db=database, + notifier=hs.get_replication_notifier(), + stream_name="e2e_cross_signing_keys", + instance_name=self._instance_name, + tables=[ + ("e2e_cross_signing_keys", "instance_name", "stream_id"), + ], + sequence_name="e2e_cross_signing_keys_sequence", + writers=["master"], ) async def set_e2e_device_keys( @@ -1627,6 +1633,7 @@ class EndToEndKeyStore(EndToEndKeyWorkerStore, SQLBaseStore): "keytype": key_type, "keydata": json_encoder.encode(key), "stream_id": stream_id, + "instance_name": self._instance_name, }, ) diff --git a/synapse/storage/databases/main/event_federation.py b/synapse/storage/databases/main/event_federation.py index 9b3ced9edb..9da9723674 100644 --- a/synapse/storage/databases/main/event_federation.py +++ b/synapse/storage/databases/main/event_federation.py @@ -159,6 +159,10 @@ class EventFederationWorkerStore(SignatureWorkerStore, EventsWorkerStore, SQLBas 500000, "_event_auth_cache", size_callback=len ) + # Flag used by unit tests to disable fallback when there is no chain cover + # index. + self.tests_allow_no_chain_cover_index = True + self._clock.looping_call(self._get_stats_for_federation_staging, 30 * 1000) if isinstance(self.database_engine, PostgresEngine): @@ -231,8 +235,10 @@ class EventFederationWorkerStore(SignatureWorkerStore, EventsWorkerStore, SQLBas ) except _NoChainCoverIndex: # For whatever reason we don't actually have a chain cover index - # for the events in question, so we fall back to the old method. - pass + # for the events in question, so we fall back to the old method + # (except in tests) + if not self.tests_allow_no_chain_cover_index: + raise return await self.db_pool.runInteraction( "get_auth_chain_ids", @@ -282,7 +288,7 @@ class EventFederationWorkerStore(SignatureWorkerStore, EventsWorkerStore, SQLBas if events_missing_chain_info: # This can happen due to e.g. downgrade/upgrade of the server. We # raise an exception and fall back to the previous algorithm. - logger.info( + logger.error( "Unexpectedly found that events don't have chain IDs in room %s: %s", room_id, events_missing_chain_info, @@ -579,8 +585,10 @@ class EventFederationWorkerStore(SignatureWorkerStore, EventsWorkerStore, SQLBas ) except _NoChainCoverIndex: # For whatever reason we don't actually have a chain cover index - # for the events in question, so we fall back to the old method. - pass + # for the events in question, so we fall back to the old method + # (except in tests) + if not self.tests_allow_no_chain_cover_index: + raise return await self.db_pool.runInteraction( "get_auth_chain_difference", @@ -807,7 +815,7 @@ class EventFederationWorkerStore(SignatureWorkerStore, EventsWorkerStore, SQLBas if events_missing_chain_info - event_to_auth_ids.keys(): # Uh oh, we somehow haven't correctly done the chain cover index, # bail and fall back to the old method. - logger.info( + logger.error( "Unexpectedly found that events don't have chain IDs in room %s: %s", room_id, events_missing_chain_info - event_to_auth_ids.keys(), diff --git a/synapse/storage/databases/main/event_push_actions.py b/synapse/storage/databases/main/event_push_actions.py index bdd0781c48..0ebf5b53d5 100644 --- a/synapse/storage/databases/main/event_push_actions.py +++ b/synapse/storage/databases/main/event_push_actions.py @@ -1829,7 +1829,7 @@ class EventPushActionsWorkerStore(ReceiptsWorkerStore, StreamWorkerStore, SQLBas async def get_push_actions_for_user( self, user_id: str, - before: Optional[str] = None, + before: Optional[int] = None, limit: int = 50, only_highlight: bool = False, ) -> List[UserPushAction]: diff --git a/synapse/storage/databases/main/events.py b/synapse/storage/databases/main/events.py index 990698aa5c..1f7acdb859 100644 --- a/synapse/storage/databases/main/events.py +++ b/synapse/storage/databases/main/events.py @@ -34,7 +34,6 @@ from typing import ( Optional, Set, Tuple, - Union, cast, ) @@ -95,6 +94,27 @@ class DeltaState: to_insert: StateMap[str] no_longer_in_room: bool = False + def is_noop(self) -> bool: + """Whether this state delta is actually empty""" + return not self.to_delete and not self.to_insert and not self.no_longer_in_room + + +@attr.s(slots=True, auto_attribs=True) +class NewEventChainLinks: + """Information about new auth chain links that need to be added to the DB. + + Attributes: + chain_id, sequence_number: the IDs corresponding to the event being + inserted, and the starting point of the links + links: Lists the links that need to be added, 2-tuple of the chain + ID/sequence number of the end point of the link. + """ + + chain_id: int + sequence_number: int + + links: List[Tuple[int, int]] = attr.Factory(list) + class PersistEventsStore: """Contains all the functions for writing events to the database. @@ -144,6 +164,7 @@ class PersistEventsStore: *, state_delta_for_room: Optional[DeltaState], new_forward_extremities: Optional[Set[str]], + new_event_links: Dict[str, NewEventChainLinks], use_negative_stream_ordering: bool = False, inhibit_local_membership_updates: bool = False, ) -> None: @@ -203,6 +224,7 @@ class PersistEventsStore: async with stream_ordering_manager as stream_orderings: for (event, _), stream in zip(events_and_contexts, stream_orderings): event.internal_metadata.stream_ordering = stream + event.internal_metadata.instance_name = self._instance_name await self.db_pool.runInteraction( "persist_events", @@ -212,6 +234,7 @@ class PersistEventsStore: inhibit_local_membership_updates=inhibit_local_membership_updates, state_delta_for_room=state_delta_for_room, new_forward_extremities=new_forward_extremities, + new_event_links=new_event_links, ) persist_event_counter.inc(len(events_and_contexts)) @@ -238,6 +261,87 @@ class PersistEventsStore: (room_id,), frozenset(new_forward_extremities) ) + async def calculate_chain_cover_index_for_events( + self, room_id: str, events: Collection[EventBase] + ) -> Dict[str, NewEventChainLinks]: + # Filter to state events, and ensure there are no duplicates. + state_events = [] + seen_events = set() + for event in events: + if not event.is_state() or event.event_id in seen_events: + continue + + state_events.append(event) + seen_events.add(event.event_id) + + if not state_events: + return {} + + return await self.db_pool.runInteraction( + "_calculate_chain_cover_index_for_events", + self.calculate_chain_cover_index_for_events_txn, + room_id, + state_events, + ) + + def calculate_chain_cover_index_for_events_txn( + self, txn: LoggingTransaction, room_id: str, state_events: Collection[EventBase] + ) -> Dict[str, NewEventChainLinks]: + # We now calculate chain ID/sequence numbers for any state events we're + # persisting. We ignore out of band memberships as we're not in the room + # and won't have their auth chain (we'll fix it up later if we join the + # room). + # + # See: docs/auth_chain_difference_algorithm.md + + # We ignore legacy rooms that we aren't filling the chain cover index + # for. + row = self.db_pool.simple_select_one_txn( + txn, + table="rooms", + keyvalues={"room_id": room_id}, + retcols=("room_id", "has_auth_chain_index"), + allow_none=True, + ) + if row is None or row[1] is False: + return {} + + # Filter out events that we've already calculated. + rows = self.db_pool.simple_select_many_txn( + txn, + table="event_auth_chains", + column="event_id", + iterable=[e.event_id for e in state_events], + keyvalues={}, + retcols=("event_id",), + ) + already_persisted_events = {event_id for event_id, in rows} + state_events = [ + event + for event in state_events + if event.event_id not in already_persisted_events + ] + + if not state_events: + return {} + + # We need to know the type/state_key and auth events of the events we're + # calculating chain IDs for. We don't rely on having the full Event + # instances as we'll potentially be pulling more events from the DB and + # we don't need the overhead of fetching/parsing the full event JSON. + event_to_types = {e.event_id: (e.type, e.state_key) for e in state_events} + event_to_auth_chain = {e.event_id: e.auth_event_ids() for e in state_events} + event_to_room_id = {e.event_id: e.room_id for e in state_events} + + return self._calculate_chain_cover_index( + txn, + self.db_pool, + self.store.event_chain_id_gen, + event_to_room_id, + event_to_types, + event_to_auth_chain, + ) + async def _get_events_which_are_prevs(self, event_ids: Iterable[str]) -> List[str]: """Filter the supplied list of event_ids to get those which are prev_events of existing (non-outlier/rejected) events. @@ -353,6 +457,7 @@ class PersistEventsStore: inhibit_local_membership_updates: bool, state_delta_for_room: Optional[DeltaState], new_forward_extremities: Optional[Set[str]], + new_event_links: Dict[str, NewEventChainLinks], ) -> None: """Insert some number of room events into the necessary database tables. @@ -461,7 +566,9 @@ class PersistEventsStore: # Insert into event_to_state_groups. self._store_event_state_mappings_txn(txn, events_and_contexts) - self._persist_event_auth_chain_txn(txn, [e for e, _ in events_and_contexts]) + self._persist_event_auth_chain_txn( + txn, [e for e, _ in events_and_contexts], new_event_links + ) # _store_rejected_events_txn filters out any events which were # rejected, and returns the filtered list. @@ -491,7 +598,11 @@ class PersistEventsStore: self, txn: LoggingTransaction, events: List[EventBase], + new_event_links: Dict[str, NewEventChainLinks], ) -> None: + if new_event_links: + self._persist_chain_cover_index(txn, self.db_pool, new_event_links) + # We only care about state events, so this if there are no state events. if not any(e.is_state() for e in events): return @@ -514,62 +625,37 @@ class PersistEventsStore: ], ) - # We now calculate chain ID/sequence numbers for any state events we're - # persisting. We ignore out of band memberships as we're not in the room - # and won't have their auth chain (we'll fix it up later if we join the - # room). - # - # See: docs/auth_chain_difference_algorithm.md - - # We ignore legacy rooms that we aren't filling the chain cover index - # for. - rows = cast( - List[Tuple[str, Optional[Union[int, bool]]]], - self.db_pool.simple_select_many_txn( - txn, - table="rooms", - column="room_id", - iterable={event.room_id for event in events if event.is_state()}, - keyvalues={}, - retcols=("room_id", "has_auth_chain_index"), - ), - ) - rooms_using_chain_index = { - room_id for room_id, has_auth_chain_index in rows if has_auth_chain_index - } - - state_events = { - event.event_id: event - for event in events - if event.is_state() and event.room_id in rooms_using_chain_index - } - - if not state_events: - return + @classmethod + def _add_chain_cover_index( + cls, + txn: LoggingTransaction, + db_pool: DatabasePool, + event_chain_id_gen: SequenceGenerator, + event_to_room_id: Dict[str, str], + event_to_types: Dict[str, Tuple[str, str]], + event_to_auth_chain: Dict[str, StrCollection], + ) -> None: + """Calculate and persist the chain cover index for the given events. - # We need to know the type/state_key and auth events of the events we're - # calculating chain IDs for. We don't rely on having the full Event - # instances as we'll potentially be pulling more events from the DB and - # we don't need the overhead of fetching/parsing the full event JSON. - event_to_types = { - e.event_id: (e.type, e.state_key) for e in state_events.values() - } - event_to_auth_chain = { - e.event_id: e.auth_event_ids() for e in state_events.values() - } - event_to_room_id = {e.event_id: e.room_id for e in state_events.values()} + Args: + event_to_room_id: Event ID to the room ID of the event + event_to_types: Event ID to type and state_key of the event + event_to_auth_chain: Event ID to list of auth event IDs of the + event (events with no auth events can be excluded). + """ - self._add_chain_cover_index( + new_event_links = cls._calculate_chain_cover_index( txn, - self.db_pool, - self.store.event_chain_id_gen, + db_pool, + event_chain_id_gen, event_to_room_id, event_to_types, event_to_auth_chain, ) + cls._persist_chain_cover_index(txn, db_pool, new_event_links) @classmethod - def _add_chain_cover_index( + def _calculate_chain_cover_index( cls, txn: LoggingTransaction, db_pool: DatabasePool, @@ -577,7 +663,7 @@ class PersistEventsStore: event_to_room_id: Dict[str, str], event_to_types: Dict[str, Tuple[str, str]], event_to_auth_chain: Dict[str, StrCollection], - ) -> None: + ) -> Dict[str, NewEventChainLinks]: """Calculate the chain cover index for the given events. Args: @@ -585,6 +671,10 @@ class PersistEventsStore: event_to_types: Event ID to type and state_key of the event event_to_auth_chain: Event ID to list of auth event IDs of the event (events with no auth events can be excluded). + + Returns: + A mapping with any new auth chain links we need to add, keyed by + event ID. """ # Map from event ID to chain ID/sequence number. @@ -703,11 +793,11 @@ class PersistEventsStore: room_id = event_to_room_id.get(event_id) if room_id: e_type, state_key = event_to_types[event_id] - db_pool.simple_insert_txn( + db_pool.simple_upsert_txn( txn, table="event_auth_chain_to_calculate", + keyvalues={"event_id": event_id}, values={ - "event_id": event_id, "room_id": room_id, "type": e_type, "state_key": state_key, @@ -719,7 +809,7 @@ class PersistEventsStore: break if not events_to_calc_chain_id_for: - return + return {} # Allocate chain ID/sequence numbers to each new event. new_chain_tuples = cls._allocate_chain_ids( @@ -734,23 +824,10 @@ class PersistEventsStore: ) chain_map.update(new_chain_tuples) - db_pool.simple_insert_many_txn( - txn, - table="event_auth_chains", - keys=("event_id", "chain_id", "sequence_number"), - values=[ - (event_id, c_id, seq) - for event_id, (c_id, seq) in new_chain_tuples.items() - ], - ) - - db_pool.simple_delete_many_txn( - txn, - table="event_auth_chain_to_calculate", - keyvalues={}, - column="event_id", - values=new_chain_tuples, - ) + to_return = { + event_id: NewEventChainLinks(chain_id, sequence_number) + for event_id, (chain_id, sequence_number) in new_chain_tuples.items() + } # Now we need to calculate any new links between chains caused by # the new events. @@ -820,10 +897,38 @@ class PersistEventsStore: auth_chain_id, auth_sequence_number = chain_map[auth_id] # Step 2a, add link between the event and auth event + to_return[event_id].links.append((auth_chain_id, auth_sequence_number)) chain_links.add_link( (chain_id, sequence_number), (auth_chain_id, auth_sequence_number) ) + return to_return + + @classmethod + def _persist_chain_cover_index( + cls, + txn: LoggingTransaction, + db_pool: DatabasePool, + new_event_links: Dict[str, NewEventChainLinks], + ) -> None: + db_pool.simple_insert_many_txn( + txn, + table="event_auth_chains", + keys=("event_id", "chain_id", "sequence_number"), + values=[ + (event_id, new_links.chain_id, new_links.sequence_number) + for event_id, new_links in new_event_links.items() + ], + ) + + db_pool.simple_delete_many_txn( + txn, + table="event_auth_chain_to_calculate", + keyvalues={}, + column="event_id", + values=new_event_links, + ) + db_pool.simple_insert_many_txn( txn, table="event_auth_chain_links", @@ -833,7 +938,16 @@ class PersistEventsStore: "target_chain_id", "target_sequence_number", ), - values=list(chain_links.get_additions()), + values=[ + ( + new_links.chain_id, + new_links.sequence_number, + target_chain_id, + target_sequence_number, + ) + for new_links in new_event_links.values() + for (target_chain_id, target_sequence_number) in new_links.links + ], ) @staticmethod @@ -1017,6 +1131,9 @@ class PersistEventsStore: ) -> None: """Update the current state stored in the datatabase for the given room""" + if state_delta.is_noop(): + return + async with self._stream_id_gen.get_next() as stream_ordering: await self.db_pool.runInteraction( "update_current_state", @@ -1923,7 +2040,12 @@ class PersistEventsStore: # Any relation information for the related event must be cleared. self.store._invalidate_cache_and_stream( - txn, self.store.get_relations_for_event, (redacted_relates_to,) + txn, + self.store.get_relations_for_event, + ( + room_id, + redacted_relates_to, + ), ) if rel_type == RelationTypes.REFERENCE: self.store._invalidate_cache_and_stream( diff --git a/synapse/storage/databases/main/events_bg_updates.py b/synapse/storage/databases/main/events_bg_updates.py index 6c979f9f2c..64d303e330 100644 --- a/synapse/storage/databases/main/events_bg_updates.py +++ b/synapse/storage/databases/main/events_bg_updates.py @@ -1181,7 +1181,7 @@ class EventsBackgroundUpdatesStore(SQLBaseStore): results = list(txn) # (event_id, parent_id, rel_type) for each relation - relations_to_insert: List[Tuple[str, str, str]] = [] + relations_to_insert: List[Tuple[str, str, str, str]] = [] for event_id, event_json_raw in results: try: event_json = db_to_json(event_json_raw) @@ -1214,7 +1214,8 @@ class EventsBackgroundUpdatesStore(SQLBaseStore): if not isinstance(parent_id, str): continue - relations_to_insert.append((event_id, parent_id, rel_type)) + room_id = event_json["room_id"] + relations_to_insert.append((room_id, event_id, parent_id, rel_type)) # Insert the missing data, note that we upsert here in case the event # has already been processed. @@ -1223,18 +1224,27 @@ class EventsBackgroundUpdatesStore(SQLBaseStore): txn=txn, table="event_relations", key_names=("event_id",), - key_values=[(r[0],) for r in relations_to_insert], + key_values=[(r[1],) for r in relations_to_insert], value_names=("relates_to_id", "relation_type"), - value_values=[r[1:] for r in relations_to_insert], + value_values=[r[2:] for r in relations_to_insert], ) # Iterate the parent IDs and invalidate caches. - cache_tuples = {(r[1],) for r in relations_to_insert} self._invalidate_cache_and_stream_bulk( # type: ignore[attr-defined] - txn, self.get_relations_for_event, cache_tuples # type: ignore[attr-defined] + txn, + self.get_relations_for_event, # type: ignore[attr-defined] + { + ( + r[0], # room_id + r[2], # parent_id + ) + for r in relations_to_insert + }, ) self._invalidate_cache_and_stream_bulk( # type: ignore[attr-defined] - txn, self.get_thread_summary, cache_tuples # type: ignore[attr-defined] + txn, + self.get_thread_summary, # type: ignore[attr-defined] + {(r[1],) for r in relations_to_insert}, ) if results: diff --git a/synapse/storage/databases/main/events_worker.py b/synapse/storage/databases/main/events_worker.py index e39d4b9624..e264d36f02 100644 --- a/synapse/storage/databases/main/events_worker.py +++ b/synapse/storage/databases/main/events_worker.py @@ -75,12 +75,10 @@ from synapse.storage.database import ( LoggingDatabaseConnection, LoggingTransaction, ) -from synapse.storage.engines import PostgresEngine from synapse.storage.types import Cursor from synapse.storage.util.id_generators import ( AbstractStreamIdGenerator, MultiWriterIdGenerator, - StreamIdGenerator, ) from synapse.storage.util.sequence import build_sequence_generator from synapse.types import JsonDict, get_domain_from_id @@ -158,6 +156,7 @@ class _EventRow: event_id: str stream_ordering: int + instance_name: str json: str internal_metadata: str format_version: Optional[int] @@ -195,51 +194,35 @@ class EventsWorkerStore(SQLBaseStore): self._stream_id_gen: AbstractStreamIdGenerator self._backfill_id_gen: AbstractStreamIdGenerator - if isinstance(database.engine, PostgresEngine): - # If we're using Postgres than we can use `MultiWriterIdGenerator` - # regardless of whether this process writes to the streams or not. - self._stream_id_gen = MultiWriterIdGenerator( - db_conn=db_conn, - db=database, - notifier=hs.get_replication_notifier(), - stream_name="events", - instance_name=hs.get_instance_name(), - tables=[("events", "instance_name", "stream_ordering")], - sequence_name="events_stream_seq", - writers=hs.config.worker.writers.events, - ) - self._backfill_id_gen = MultiWriterIdGenerator( - db_conn=db_conn, - db=database, - notifier=hs.get_replication_notifier(), - stream_name="backfill", - instance_name=hs.get_instance_name(), - tables=[("events", "instance_name", "stream_ordering")], - sequence_name="events_backfill_stream_seq", - positive=False, - writers=hs.config.worker.writers.events, - ) - else: - # Multiple writers are not supported for SQLite. - # - # We shouldn't be running in worker mode with SQLite, but its useful - # to support it for unit tests. - self._stream_id_gen = StreamIdGenerator( - db_conn, - hs.get_replication_notifier(), - "events", - "stream_ordering", - is_writer=hs.get_instance_name() in hs.config.worker.writers.events, - ) - self._backfill_id_gen = StreamIdGenerator( - db_conn, - hs.get_replication_notifier(), - "events", - "stream_ordering", - step=-1, - extra_tables=[("ex_outlier_stream", "event_stream_ordering")], - is_writer=hs.get_instance_name() in hs.config.worker.writers.events, - ) + + self._stream_id_gen = MultiWriterIdGenerator( + db_conn=db_conn, + db=database, + notifier=hs.get_replication_notifier(), + stream_name="events", + instance_name=hs.get_instance_name(), + tables=[ + ("events", "instance_name", "stream_ordering"), + ("current_state_delta_stream", "instance_name", "stream_id"), + ("ex_outlier_stream", "instance_name", "event_stream_ordering"), + ], + sequence_name="events_stream_seq", + writers=hs.config.worker.writers.events, + ) + self._backfill_id_gen = MultiWriterIdGenerator( + db_conn=db_conn, + db=database, + notifier=hs.get_replication_notifier(), + stream_name="backfill", + instance_name=hs.get_instance_name(), + tables=[ + ("events", "instance_name", "stream_ordering"), + ("ex_outlier_stream", "instance_name", "event_stream_ordering"), + ], + sequence_name="events_backfill_stream_seq", + positive=False, + writers=hs.config.worker.writers.events, + ) events_max = self._stream_id_gen.get_current_token() curr_state_delta_prefill, min_curr_state_delta_id = self.db_pool.get_cache_dict( @@ -309,27 +292,17 @@ class EventsWorkerStore(SQLBaseStore): self._un_partial_stated_events_stream_id_gen: AbstractStreamIdGenerator - if isinstance(database.engine, PostgresEngine): - self._un_partial_stated_events_stream_id_gen = MultiWriterIdGenerator( - db_conn=db_conn, - db=database, - notifier=hs.get_replication_notifier(), - stream_name="un_partial_stated_event_stream", - instance_name=hs.get_instance_name(), - tables=[ - ("un_partial_stated_event_stream", "instance_name", "stream_id") - ], - sequence_name="un_partial_stated_event_stream_sequence", - # TODO(faster_joins, multiple writers) Support multiple writers. - writers=["master"], - ) - else: - self._un_partial_stated_events_stream_id_gen = StreamIdGenerator( - db_conn, - hs.get_replication_notifier(), - "un_partial_stated_event_stream", - "stream_id", - ) + self._un_partial_stated_events_stream_id_gen = MultiWriterIdGenerator( + db_conn=db_conn, + db=database, + notifier=hs.get_replication_notifier(), + stream_name="un_partial_stated_event_stream", + instance_name=hs.get_instance_name(), + tables=[("un_partial_stated_event_stream", "instance_name", "stream_id")], + sequence_name="un_partial_stated_event_stream_sequence", + # TODO(faster_joins, multiple writers) Support multiple writers. + writers=["master"], + ) def get_un_partial_stated_events_token(self, instance_name: str) -> int: return ( @@ -1382,6 +1355,7 @@ class EventsWorkerStore(SQLBaseStore): rejected_reason=rejected_reason, ) original_ev.internal_metadata.stream_ordering = row.stream_ordering + original_ev.internal_metadata.instance_name = row.instance_name original_ev.internal_metadata.outlier = row.outlier # Consistency check: if the content of the event has been modified in the @@ -1467,6 +1441,7 @@ class EventsWorkerStore(SQLBaseStore): SELECT e.event_id, e.stream_ordering, + e.instance_name, ej.internal_metadata, ej.json, ej.format_version, @@ -1490,13 +1465,14 @@ class EventsWorkerStore(SQLBaseStore): event_dict[event_id] = _EventRow( event_id=event_id, stream_ordering=row[1], - internal_metadata=row[2], - json=row[3], - format_version=row[4], - room_version_id=row[5], - rejected_reason=row[6], + instance_name=row[2], + internal_metadata=row[3], + json=row[4], + format_version=row[5], + room_version_id=row[6], + rejected_reason=row[7], redactions=[], - outlier=bool(row[7]), # This is an int in SQLite3 + outlier=bool(row[8]), # This is an int in SQLite3 ) # check for redactions diff --git a/synapse/storage/databases/main/presence.py b/synapse/storage/databases/main/presence.py index 567c2d30bd..923e764491 100644 --- a/synapse/storage/databases/main/presence.py +++ b/synapse/storage/databases/main/presence.py @@ -40,13 +40,11 @@ from synapse.storage.database import ( LoggingTransaction, ) from synapse.storage.databases.main.cache import CacheInvalidationWorkerStore -from synapse.storage.engines import PostgresEngine from synapse.storage.engines._base import IsolationLevel from synapse.storage.types import Connection from synapse.storage.util.id_generators import ( AbstractStreamIdGenerator, MultiWriterIdGenerator, - StreamIdGenerator, ) from synapse.util.caches.descriptors import cached, cachedList from synapse.util.caches.stream_change_cache import StreamChangeCache @@ -91,21 +89,16 @@ class PresenceStore(PresenceBackgroundUpdateStore, CacheInvalidationWorkerStore) self._instance_name in hs.config.worker.writers.presence ) - if isinstance(database.engine, PostgresEngine): - self._presence_id_gen = MultiWriterIdGenerator( - db_conn=db_conn, - db=database, - notifier=hs.get_replication_notifier(), - stream_name="presence_stream", - instance_name=self._instance_name, - tables=[("presence_stream", "instance_name", "stream_id")], - sequence_name="presence_stream_sequence", - writers=hs.config.worker.writers.presence, - ) - else: - self._presence_id_gen = StreamIdGenerator( - db_conn, hs.get_replication_notifier(), "presence_stream", "stream_id" - ) + self._presence_id_gen = MultiWriterIdGenerator( + db_conn=db_conn, + db=database, + notifier=hs.get_replication_notifier(), + stream_name="presence_stream", + instance_name=self._instance_name, + tables=[("presence_stream", "instance_name", "stream_id")], + sequence_name="presence_stream_sequence", + writers=hs.config.worker.writers.presence, + ) self.hs = hs self._presence_on_startup = self._get_active_presence(db_conn) diff --git a/synapse/storage/databases/main/push_rule.py b/synapse/storage/databases/main/push_rule.py index 660c834518..2a39dc9f90 100644 --- a/synapse/storage/databases/main/push_rule.py +++ b/synapse/storage/databases/main/push_rule.py @@ -53,7 +53,7 @@ from synapse.storage.databases.main.receipts import ReceiptsWorkerStore from synapse.storage.databases.main.roommember import RoomMemberWorkerStore from synapse.storage.engines import PostgresEngine, Sqlite3Engine from synapse.storage.push_rule import InconsistentRuleException, RuleNotFoundException -from synapse.storage.util.id_generators import IdGenerator, StreamIdGenerator +from synapse.storage.util.id_generators import IdGenerator, MultiWriterIdGenerator from synapse.synapse_rust.push import FilteredPushRules, PushRule, PushRules from synapse.types import JsonDict from synapse.util import json_encoder, unwrapFirstError @@ -126,7 +126,7 @@ class PushRulesWorkerStore( `get_max_push_rules_stream_id` which can be called in the initializer. """ - _push_rules_stream_id_gen: StreamIdGenerator + _push_rules_stream_id_gen: MultiWriterIdGenerator def __init__( self, @@ -140,14 +140,17 @@ class PushRulesWorkerStore( hs.get_instance_name() in hs.config.worker.writers.push_rules ) - # In the worker store this is an ID tracker which we overwrite in the non-worker - # class below that is used on the main process. - self._push_rules_stream_id_gen = StreamIdGenerator( - db_conn, - hs.get_replication_notifier(), - "push_rules_stream", - "stream_id", - is_writer=self._is_push_writer, + self._push_rules_stream_id_gen = MultiWriterIdGenerator( + db_conn=db_conn, + db=database, + notifier=hs.get_replication_notifier(), + stream_name="push_rules_stream", + instance_name=self._instance_name, + tables=[ + ("push_rules_stream", "instance_name", "stream_id"), + ], + sequence_name="push_rules_stream_sequence", + writers=hs.config.worker.writers.push_rules, ) push_rules_prefill, push_rules_id = self.db_pool.get_cache_dict( @@ -880,6 +883,7 @@ class PushRulesWorkerStore( raise Exception("Not a push writer") values = { + "instance_name": self._instance_name, "stream_id": stream_id, "event_stream_ordering": event_stream_ordering, "user_id": user_id, diff --git a/synapse/storage/databases/main/pusher.py b/synapse/storage/databases/main/pusher.py index 39e22d3b43..a8a37b6c85 100644 --- a/synapse/storage/databases/main/pusher.py +++ b/synapse/storage/databases/main/pusher.py @@ -40,10 +40,7 @@ from synapse.storage.database import ( LoggingDatabaseConnection, LoggingTransaction, ) -from synapse.storage.util.id_generators import ( - AbstractStreamIdGenerator, - StreamIdGenerator, -) +from synapse.storage.util.id_generators import MultiWriterIdGenerator from synapse.types import JsonDict from synapse.util import json_encoder from synapse.util.caches.descriptors import cached @@ -84,15 +81,20 @@ class PusherWorkerStore(SQLBaseStore): ): super().__init__(database, db_conn, hs) - # In the worker store this is an ID tracker which we overwrite in the non-worker - # class below that is used on the main process. - self._pushers_id_gen = StreamIdGenerator( - db_conn, - hs.get_replication_notifier(), - "pushers", - "id", - extra_tables=[("deleted_pushers", "stream_id")], - is_writer=hs.config.worker.worker_app is None, + self._instance_name = hs.get_instance_name() + + self._pushers_id_gen = MultiWriterIdGenerator( + db_conn=db_conn, + db=database, + notifier=hs.get_replication_notifier(), + stream_name="pushers", + instance_name=self._instance_name, + tables=[ + ("pushers", "instance_name", "id"), + ("deleted_pushers", "instance_name", "stream_id"), + ], + sequence_name="pushers_sequence", + writers=["master"], ) self.db_pool.updates.register_background_update_handler( @@ -655,7 +657,7 @@ class PusherBackgroundUpdatesStore(SQLBaseStore): class PusherStore(PusherWorkerStore, PusherBackgroundUpdatesStore): # Because we have write access, this will be a StreamIdGenerator # (see PusherWorkerStore.__init__) - _pushers_id_gen: AbstractStreamIdGenerator + _pushers_id_gen: MultiWriterIdGenerator async def add_pusher( self, @@ -688,6 +690,7 @@ class PusherStore(PusherWorkerStore, PusherBackgroundUpdatesStore): "last_stream_ordering": last_stream_ordering, "profile_tag": profile_tag, "id": stream_id, + "instance_name": self._instance_name, "enabled": enabled, "device_id": device_id, # XXX(quenting): We're only really persisting the access token ID @@ -735,6 +738,7 @@ class PusherStore(PusherWorkerStore, PusherBackgroundUpdatesStore): table="deleted_pushers", values={ "stream_id": stream_id, + "instance_name": self._instance_name, "app_id": app_id, "pushkey": pushkey, "user_id": user_id, @@ -773,9 +777,15 @@ class PusherStore(PusherWorkerStore, PusherBackgroundUpdatesStore): self.db_pool.simple_insert_many_txn( txn, table="deleted_pushers", - keys=("stream_id", "app_id", "pushkey", "user_id"), + keys=("stream_id", "instance_name", "app_id", "pushkey", "user_id"), values=[ - (stream_id, pusher.app_id, pusher.pushkey, user_id) + ( + stream_id, + self._instance_name, + pusher.app_id, + pusher.pushkey, + user_id, + ) for stream_id, pusher in zip(stream_ids, pushers) ], ) diff --git a/synapse/storage/databases/main/receipts.py b/synapse/storage/databases/main/receipts.py index 13387a3839..8432560a89 100644 --- a/synapse/storage/databases/main/receipts.py +++ b/synapse/storage/databases/main/receipts.py @@ -44,12 +44,10 @@ from synapse.storage.database import ( LoggingDatabaseConnection, LoggingTransaction, ) -from synapse.storage.engines import PostgresEngine from synapse.storage.engines._base import IsolationLevel from synapse.storage.util.id_generators import ( AbstractStreamIdGenerator, MultiWriterIdGenerator, - StreamIdGenerator, ) from synapse.types import ( JsonDict, @@ -80,35 +78,20 @@ class ReceiptsWorkerStore(SQLBaseStore): # class below that is used on the main process. self._receipts_id_gen: AbstractStreamIdGenerator - if isinstance(database.engine, PostgresEngine): - self._can_write_to_receipts = ( - self._instance_name in hs.config.worker.writers.receipts - ) + self._can_write_to_receipts = ( + self._instance_name in hs.config.worker.writers.receipts + ) - self._receipts_id_gen = MultiWriterIdGenerator( - db_conn=db_conn, - db=database, - notifier=hs.get_replication_notifier(), - stream_name="receipts", - instance_name=self._instance_name, - tables=[("receipts_linearized", "instance_name", "stream_id")], - sequence_name="receipts_sequence", - writers=hs.config.worker.writers.receipts, - ) - else: - self._can_write_to_receipts = True - - # Multiple writers are not supported for SQLite. - # - # We shouldn't be running in worker mode with SQLite, but its useful - # to support it for unit tests. - self._receipts_id_gen = StreamIdGenerator( - db_conn, - hs.get_replication_notifier(), - "receipts_linearized", - "stream_id", - is_writer=hs.get_instance_name() in hs.config.worker.writers.receipts, - ) + self._receipts_id_gen = MultiWriterIdGenerator( + db_conn=db_conn, + db=database, + notifier=hs.get_replication_notifier(), + stream_name="receipts", + instance_name=self._instance_name, + tables=[("receipts_linearized", "instance_name", "stream_id")], + sequence_name="receipts_sequence", + writers=hs.config.worker.writers.receipts, + ) super().__init__(database, db_conn, hs) diff --git a/synapse/storage/databases/main/relations.py b/synapse/storage/databases/main/relations.py index 77f3641525..29a001ff92 100644 --- a/synapse/storage/databases/main/relations.py +++ b/synapse/storage/databases/main/relations.py @@ -169,9 +169,9 @@ class RelationsWorkerStore(SQLBaseStore): @cached(uncached_args=("event",), tree=True) async def get_relations_for_event( self, + room_id: str, event_id: str, event: EventBase, - room_id: str, relation_type: Optional[str] = None, event_type: Optional[str] = None, limit: int = 5, diff --git a/synapse/storage/databases/main/room.py b/synapse/storage/databases/main/room.py index 81c7bf3712..d5627b1d6e 100644 --- a/synapse/storage/databases/main/room.py +++ b/synapse/storage/databases/main/room.py @@ -21,13 +21,11 @@ # import logging -from abc import abstractmethod from enum import Enum from typing import ( TYPE_CHECKING, AbstractSet, Any, - Awaitable, Collection, Dict, List, @@ -53,20 +51,18 @@ from synapse.api.room_versions import RoomVersion, RoomVersions from synapse.config.homeserver import HomeServerConfig from synapse.events import EventBase from synapse.replication.tcp.streams.partial_state import UnPartialStatedRoomStream -from synapse.storage._base import SQLBaseStore, db_to_json, make_in_list_sql_clause +from synapse.storage._base import db_to_json, make_in_list_sql_clause from synapse.storage.database import ( DatabasePool, LoggingDatabaseConnection, LoggingTransaction, ) from synapse.storage.databases.main.cache import CacheInvalidationWorkerStore -from synapse.storage.engines import PostgresEngine from synapse.storage.types import Cursor from synapse.storage.util.id_generators import ( AbstractStreamIdGenerator, IdGenerator, MultiWriterIdGenerator, - StreamIdGenerator, ) from synapse.types import JsonDict, RetentionPolicy, StrCollection, ThirdPartyInstanceID from synapse.util import json_encoder @@ -157,27 +153,17 @@ class RoomWorkerStore(CacheInvalidationWorkerStore): self._un_partial_stated_rooms_stream_id_gen: AbstractStreamIdGenerator - if isinstance(database.engine, PostgresEngine): - self._un_partial_stated_rooms_stream_id_gen = MultiWriterIdGenerator( - db_conn=db_conn, - db=database, - notifier=hs.get_replication_notifier(), - stream_name="un_partial_stated_room_stream", - instance_name=self._instance_name, - tables=[ - ("un_partial_stated_room_stream", "instance_name", "stream_id") - ], - sequence_name="un_partial_stated_room_stream_sequence", - # TODO(faster_joins, multiple writers) Support multiple writers. - writers=["master"], - ) - else: - self._un_partial_stated_rooms_stream_id_gen = StreamIdGenerator( - db_conn, - hs.get_replication_notifier(), - "un_partial_stated_room_stream", - "stream_id", - ) + self._un_partial_stated_rooms_stream_id_gen = MultiWriterIdGenerator( + db_conn=db_conn, + db=database, + notifier=hs.get_replication_notifier(), + stream_name="un_partial_stated_room_stream", + instance_name=self._instance_name, + tables=[("un_partial_stated_room_stream", "instance_name", "stream_id")], + sequence_name="un_partial_stated_room_stream_sequence", + # TODO(faster_joins, multiple writers) Support multiple writers. + writers=["master"], + ) def process_replication_position( self, stream_name: str, instance_name: str, token: int @@ -620,6 +606,8 @@ class RoomWorkerStore(CacheInvalidationWorkerStore): order_by: str, reverse_order: bool, search_term: Optional[str], + public_rooms: Optional[bool], + empty_rooms: Optional[bool], ) -> Tuple[List[Dict[str, Any]], int]: """Function to retrieve a paginated list of rooms as json. @@ -631,30 +619,49 @@ class RoomWorkerStore(CacheInvalidationWorkerStore): search_term: a string to filter room names, canonical alias and room ids by. Room ID must match exactly. Canonical alias must match a substring of the local part. + public_rooms: Optional flag to filter public and non-public rooms. If true, public rooms are queried. + if false, public rooms are excluded from the query. When it is + none (the default), both public rooms and none-public-rooms are queried. + empty_rooms: Optional flag to filter empty and non-empty rooms. + A room is empty if joined_members is zero. + If true, empty rooms are queried. + if false, empty rooms are excluded from the query. When it is + none (the default), both empty rooms and none-empty rooms are queried. Returns: A list of room dicts and an integer representing the total number of rooms that exist given this query """ # Filter room names by a string - where_statement = "" - search_pattern: List[object] = [] + filter_ = [] + where_args = [] if search_term: - where_statement = """ - WHERE LOWER(state.name) LIKE ? - OR LOWER(state.canonical_alias) LIKE ? - OR state.room_id = ? - """ + filter_ = [ + "LOWER(state.name) LIKE ? OR " + "LOWER(state.canonical_alias) LIKE ? OR " + "state.room_id = ?" + ] # Our postgres db driver converts ? -> %s in SQL strings as that's the # placeholder for postgres. # HOWEVER, if you put a % into your SQL then everything goes wibbly. # To get around this, we're going to surround search_term with %'s # before giving it to the database in python instead - search_pattern = [ - "%" + search_term.lower() + "%", - "#%" + search_term.lower() + "%:%", + where_args = [ + f"%{search_term.lower()}%", + f"#%{search_term.lower()}%:%", search_term, ] + if public_rooms is not None: + filter_arg = "1" if public_rooms else "0" + filter_.append(f"rooms.is_public = '{filter_arg}'") + + if empty_rooms is not None: + if empty_rooms: + filter_.append("curr.joined_members = 0") + else: + filter_.append("curr.joined_members <> 0") + + where_clause = "WHERE " + " AND ".join(filter_) if len(filter_) > 0 else "" # Set ordering if RoomSortOrder(order_by) == RoomSortOrder.SIZE: @@ -731,7 +738,7 @@ class RoomWorkerStore(CacheInvalidationWorkerStore): LIMIT ? OFFSET ? """.format( - where=where_statement, + where=where_clause, order_by=order_by_column, direction="ASC" if order_by_asc else "DESC", ) @@ -740,10 +747,12 @@ class RoomWorkerStore(CacheInvalidationWorkerStore): count_sql = """ SELECT count(*) FROM ( SELECT room_id FROM room_stats_state state + INNER JOIN room_stats_current curr USING (room_id) + INNER JOIN rooms USING (room_id) {where} ) AS get_room_ids """.format( - where=where_statement, + where=where_clause, ) def _get_rooms_paginate_txn( @@ -751,7 +760,7 @@ class RoomWorkerStore(CacheInvalidationWorkerStore): ) -> Tuple[List[Dict[str, Any]], int]: # Add the search term into the WHERE clause # and execute the data query - txn.execute(info_sql, search_pattern + [limit, start]) + txn.execute(info_sql, where_args + [limit, start]) # Refactor room query data into a structured dictionary rooms = [] @@ -781,7 +790,7 @@ class RoomWorkerStore(CacheInvalidationWorkerStore): # Execute the count query # Add the search term into the WHERE clause if present - txn.execute(count_sql, search_pattern) + txn.execute(count_sql, where_args) room_count = cast(Tuple[int], txn.fetchone()) return rooms, room_count[0] @@ -1684,6 +1693,58 @@ class RoomWorkerStore(CacheInvalidationWorkerStore): return True + async def set_room_is_public(self, room_id: str, is_public: bool) -> None: + await self.db_pool.simple_update_one( + table="rooms", + keyvalues={"room_id": room_id}, + updatevalues={"is_public": is_public}, + desc="set_room_is_public", + ) + + async def set_room_is_public_appservice( + self, room_id: str, appservice_id: str, network_id: str, is_public: bool + ) -> None: + """Edit the appservice/network specific public room list. + + Each appservice can have a number of published room lists associated + with them, keyed off of an appservice defined `network_id`, which + basically represents a single instance of a bridge to a third party + network. + + Args: + room_id + appservice_id + network_id + is_public: Whether to publish or unpublish the room from the list. + """ + + if is_public: + await self.db_pool.simple_upsert( + table="appservice_room_list", + keyvalues={ + "appservice_id": appservice_id, + "network_id": network_id, + "room_id": room_id, + }, + values={}, + insertion_values={ + "appservice_id": appservice_id, + "network_id": network_id, + "room_id": room_id, + }, + desc="set_room_is_public_appservice_true", + ) + else: + await self.db_pool.simple_delete( + table="appservice_room_list", + keyvalues={ + "appservice_id": appservice_id, + "network_id": network_id, + "room_id": room_id, + }, + desc="set_room_is_public_appservice_false", + ) + class _BackgroundUpdates: REMOVE_TOMESTONED_ROOMS_BG_UPDATE = "remove_tombstoned_rooms_from_directory" @@ -1702,7 +1763,7 @@ _REPLACE_ROOM_DEPTH_SQL_COMMANDS = ( ) -class RoomBackgroundUpdateStore(SQLBaseStore): +class RoomBackgroundUpdateStore(RoomWorkerStore): def __init__( self, database: DatabasePool, @@ -1935,14 +1996,6 @@ class RoomBackgroundUpdateStore(SQLBaseStore): return len(rooms) - @abstractmethod - def set_room_is_public(self, room_id: str, is_public: bool) -> Awaitable[None]: - # this will need to be implemented if a background update is performed with - # existing (tombstoned, public) rooms in the database. - # - # It's overridden by RoomStore for the synapse master. - raise NotImplementedError() - async def has_auth_chain_index(self, room_id: str) -> bool: """Check if the room has (or can have) a chain cover index. @@ -2177,6 +2230,7 @@ class RoomStore(RoomBackgroundUpdateStore, RoomWorkerStore): super().__init__(database, db_conn, hs) self._event_reports_id_gen = IdGenerator(db_conn, "event_reports", "id") + self._room_reports_id_gen = IdGenerator(db_conn, "room_reports", "id") self._instance_name = hs.get_instance_name() @@ -2349,62 +2403,6 @@ class RoomStore(RoomBackgroundUpdateStore, RoomWorkerStore): }, ) - async def set_room_is_public(self, room_id: str, is_public: bool) -> None: - await self.db_pool.simple_update_one( - table="rooms", - keyvalues={"room_id": room_id}, - updatevalues={"is_public": is_public}, - desc="set_room_is_public", - ) - - self.hs.get_notifier().on_new_replication_data() - - async def set_room_is_public_appservice( - self, room_id: str, appservice_id: str, network_id: str, is_public: bool - ) -> None: - """Edit the appservice/network specific public room list. - - Each appservice can have a number of published room lists associated - with them, keyed off of an appservice defined `network_id`, which - basically represents a single instance of a bridge to a third party - network. - - Args: - room_id - appservice_id - network_id - is_public: Whether to publish or unpublish the room from the list. - """ - - if is_public: - await self.db_pool.simple_upsert( - table="appservice_room_list", - keyvalues={ - "appservice_id": appservice_id, - "network_id": network_id, - "room_id": room_id, - }, - values={}, - insertion_values={ - "appservice_id": appservice_id, - "network_id": network_id, - "room_id": room_id, - }, - desc="set_room_is_public_appservice_true", - ) - else: - await self.db_pool.simple_delete( - table="appservice_room_list", - keyvalues={ - "appservice_id": appservice_id, - "network_id": network_id, - "room_id": room_id, - }, - desc="set_room_is_public_appservice_false", - ) - - self.hs.get_notifier().on_new_replication_data() - async def add_event_report( self, room_id: str, @@ -2442,6 +2440,37 @@ class RoomStore(RoomBackgroundUpdateStore, RoomWorkerStore): ) return next_id + async def add_room_report( + self, + room_id: str, + user_id: str, + reason: str, + received_ts: int, + ) -> int: + """Add a room report + + Args: + room_id: The room ID being reported. + user_id: User who reports the room. + reason: Description that the user specifies. + received_ts: Time when the user submitted the report (milliseconds). + Returns: + Id of the room report. + """ + next_id = self._room_reports_id_gen.get_next() + await self.db_pool.simple_insert( + table="room_reports", + values={ + "id": next_id, + "received_ts": received_ts, + "room_id": room_id, + "user_id": user_id, + "reason": reason, + }, + desc="add_room_report", + ) + return next_id + async def block_room(self, room_id: str, user_id: str) -> None: """Marks the room as blocked. diff --git a/synapse/storage/databases/main/roommember.py b/synapse/storage/databases/main/roommember.py index 9fddbb2caf..d8b54dc4e3 100644 --- a/synapse/storage/databases/main/roommember.py +++ b/synapse/storage/databases/main/roommember.py @@ -476,7 +476,7 @@ class RoomMemberWorkerStore(EventsWorkerStore, CacheInvalidationWorkerStore): ) sql = """ - SELECT room_id, e.sender, c.membership, event_id, e.stream_ordering, r.room_version + SELECT room_id, e.sender, c.membership, event_id, e.instance_name, e.stream_ordering, r.room_version FROM local_current_membership AS c INNER JOIN events AS e USING (room_id, event_id) INNER JOIN rooms AS r USING (room_id) @@ -488,7 +488,17 @@ class RoomMemberWorkerStore(EventsWorkerStore, CacheInvalidationWorkerStore): ) txn.execute(sql, (user_id, *args)) - results = [RoomsForUser(*r) for r in txn] + results = [ + RoomsForUser( + room_id=room_id, + sender=sender, + membership=membership, + event_id=event_id, + event_pos=PersistedEventPosition(instance_name, stream_ordering), + room_version_id=room_version, + ) + for room_id, sender, membership, event_id, instance_name, stream_ordering, room_version in txn + ] return results diff --git a/synapse/storage/databases/main/stream.py b/synapse/storage/databases/main/stream.py index 7ab6003f61..ff0d723684 100644 --- a/synapse/storage/databases/main/stream.py +++ b/synapse/storage/databases/main/stream.py @@ -895,7 +895,7 @@ class StreamWorkerStore(EventsWorkerStore, SQLBaseStore): "get_room_event_before_stream_ordering", _f ) - async def get_last_event_in_room_before_stream_ordering( + async def get_last_event_id_in_room_before_stream_ordering( self, room_id: str, end_token: RoomStreamToken, @@ -910,16 +910,55 @@ class StreamWorkerStore(EventsWorkerStore, SQLBaseStore): The ID of the most recent event, or None if there are no events in the room before this stream ordering. """ + last_event_result = ( + await self.get_last_event_pos_in_room_before_stream_ordering( + room_id, end_token + ) + ) - def get_last_event_in_room_before_stream_ordering_txn( - txn: LoggingTransaction, - ) -> Optional[str]: - # We need to handle the fact that the stream tokens can be vector - # clocks. We do this by getting all rows between the minimum and - # maximum stream ordering in the token, plus one row less than the - # minimum stream ordering. We then filter the results against the - # token and return the first row that matches. + if last_event_result: + return last_event_result[0] + + return None + + async def get_last_event_pos_in_room_before_stream_ordering( + self, + room_id: str, + end_token: RoomStreamToken, + ) -> Optional[Tuple[str, PersistedEventPosition]]: + """ + Returns the ID and event position of the last event in a room at or before a + stream ordering. + Args: + room_id + end_token: The token used to stream from + + Returns: + The ID of the most recent event and it's position, or None if there are no + events in the room before this stream ordering. + """ + + def get_last_event_pos_in_room_before_stream_ordering_txn( + txn: LoggingTransaction, + ) -> Optional[Tuple[str, PersistedEventPosition]]: + # We're looking for the closest event at or before the token. We need to + # handle the fact that the stream token can be a vector clock (with an + # `instance_map`) and events can be persisted on different instances + # (sharded event persisters). The first subquery handles the events that + # would be within the vector clock and gets all rows between the minimum and + # maximum stream ordering in the token which need to be filtered against the + # `instance_map`. The second subquery handles the "before" case and finds + # the first row before the token. We then filter out any results past the + # token's vector clock and return the first row that matches. + min_stream = end_token.stream + max_stream = end_token.get_max_stream_pos() + + # We use `union all` because we don't need any of the deduplication logic + # (`union` is really a union + distinct). `UNION ALL` does preserve the + # ordering of the operand queries but there is no actual gurantee that it + # has this behavior in all scenarios so we need the extra `ORDER BY` at the + # bottom. sql = """ SELECT * FROM ( SELECT instance_name, stream_ordering, topological_ordering, event_id @@ -931,7 +970,7 @@ class StreamWorkerStore(EventsWorkerStore, SQLBaseStore): AND rejections.event_id IS NULL ORDER BY stream_ordering DESC ) AS a - UNION + UNION ALL SELECT * FROM ( SELECT instance_name, stream_ordering, topological_ordering, event_id FROM events @@ -943,15 +982,16 @@ class StreamWorkerStore(EventsWorkerStore, SQLBaseStore): ORDER BY stream_ordering DESC LIMIT 1 ) AS b + ORDER BY stream_ordering DESC """ txn.execute( sql, ( room_id, - end_token.stream, - end_token.get_max_stream_pos(), + min_stream, + max_stream, room_id, - end_token.stream, + min_stream, ), ) @@ -963,13 +1003,15 @@ class StreamWorkerStore(EventsWorkerStore, SQLBaseStore): topological_ordering=topological_ordering, stream_ordering=stream_ordering, ): - return event_id + return event_id, PersistedEventPosition( + instance_name, stream_ordering + ) return None return await self.db_pool.runInteraction( - "get_last_event_in_room_before_stream_ordering", - get_last_event_in_room_before_stream_ordering_txn, + "get_last_event_pos_in_room_before_stream_ordering", + get_last_event_pos_in_room_before_stream_ordering_txn, ) async def get_current_room_stream_token_for_room_id( diff --git a/synapse/storage/databases/main/user_directory.py b/synapse/storage/databases/main/user_directory.py index 0513e7dc06..6e18f714d7 100644 --- a/synapse/storage/databases/main/user_directory.py +++ b/synapse/storage/databases/main/user_directory.py @@ -1281,7 +1281,7 @@ def _parse_words_with_regex(search_term: str) -> List[str]: Break down search term into words, when we don't have ICU available. See: `_parse_words` """ - return re.findall(r"([\w\-]+)", search_term, re.UNICODE) + return re.findall(r"([\w-]+)", search_term, re.UNICODE) def _parse_words_with_icu(search_term: str) -> List[str]: @@ -1303,15 +1303,69 @@ def _parse_words_with_icu(search_term: str) -> List[str]: if j < 0: break - result = search_term[i:j] + # We want to make sure that we split on `@` and `:` specifically, as + # they occur in user IDs. + for result in re.split(r"[@:]+", search_term[i:j]): + results.append(result.strip()) + + i = j + + # libicu will break up words that have punctuation in them, but to handle + # cases where user IDs have '-', '.' and '_' in them we want to *not* break + # those into words and instead allow the DB to tokenise them how it wants. + # + # In particular, user-71 in postgres gets tokenised to "user, -71", and this + # will not match a query for "user, 71". + new_results: List[str] = [] + i = 0 + while i < len(results): + curr = results[i] + + prev = None + next = None + if i > 0: + prev = results[i - 1] + if i + 1 < len(results): + next = results[i + 1] + + i += 1 # libicu considers spaces and punctuation between words as words, but we don't # want to include those in results as they would result in syntax errors in SQL # queries (e.g. "foo bar" would result in the search query including "foo & & # bar"). - if len(re.findall(r"([\w\-]+)", result, re.UNICODE)): - results.append(result) + if not curr: + continue + + if curr in ["-", ".", "_"]: + prefix = "" + suffix = "" + + # Check if the next item is a word, and if so use it as the suffix. + # We check for if its a word as we don't want to concatenate + # multiple punctuation marks. + if next is not None and re.match(r"\w", next): + suffix = next + i += 1 # We're using next, so we skip it in the outer loop. + else: + # We want to avoid creating terms like "user-", as we should + # strip trailing punctuation. + continue - i = j + if prev and re.match(r"\w", prev) and new_results: + prefix = new_results[-1] + new_results.pop() + + # We might not have a prefix here, but that's fine as we want to + # ensure that we don't strip preceding punctuation e.g. '-71' + # shouldn't be converted to '71'. + + new_results.append(f"{prefix}{curr}{suffix}") + continue + elif not re.match(r"\w", curr): + # Ignore other punctuation + continue + + new_results.append(curr) - return results + return new_results diff --git a/synapse/storage/engines/postgres.py b/synapse/storage/engines/postgres.py index b9168ee074..90641d5a18 100644 --- a/synapse/storage/engines/postgres.py +++ b/synapse/storage/engines/postgres.py @@ -142,6 +142,10 @@ class PostgresEngine( apply stricter checks on new databases versus existing database. """ + allow_unsafe_locale = self.config.get("allow_unsafe_locale", False) + if allow_unsafe_locale: + return + collation, ctype = self.get_db_locale(txn) errors = [] @@ -155,7 +159,9 @@ class PostgresEngine( if errors: raise IncorrectDatabaseSetup( "Database is incorrectly configured:\n\n%s\n\n" - "See docs/postgres.md for more information." % ("\n".join(errors)) + "See docs/postgres.md for more information. You can override this check by" + "setting 'allow_unsafe_locale' to true in the database config.", + "\n".join(errors), ) def convert_param_style(self, sql: str) -> str: diff --git a/synapse/storage/roommember.py b/synapse/storage/roommember.py index 7471f81a19..80c9630867 100644 --- a/synapse/storage/roommember.py +++ b/synapse/storage/roommember.py @@ -35,7 +35,7 @@ class RoomsForUser: sender: str membership: str event_id: str - stream_ordering: int + event_pos: PersistedEventPosition room_version_id: str diff --git a/synapse/storage/schema/main/delta/85/02_add_instance_names.sql b/synapse/storage/schema/main/delta/85/02_add_instance_names.sql new file mode 100644 index 0000000000..d604595f73 --- /dev/null +++ b/synapse/storage/schema/main/delta/85/02_add_instance_names.sql @@ -0,0 +1,27 @@ +-- +-- This file is licensed under the Affero General Public License (AGPL) version 3. +-- +-- Copyright (C) 2024 New Vector, Ltd +-- +-- This program is free software: you can redistribute it and/or modify +-- it under the terms of the GNU Affero General Public License as +-- published by the Free Software Foundation, either version 3 of the +-- License, or (at your option) any later version. +-- +-- See the GNU Affero General Public License for more details: +-- <https://www.gnu.org/licenses/agpl-3.0.html>. + +-- Add `instance_name` columns to stream tables to allow them to be used with +-- `MultiWriterIdGenerator` +ALTER TABLE device_lists_stream ADD COLUMN instance_name TEXT; +ALTER TABLE user_signature_stream ADD COLUMN instance_name TEXT; +ALTER TABLE device_lists_outbound_pokes ADD COLUMN instance_name TEXT; +ALTER TABLE device_lists_changes_in_room ADD COLUMN instance_name TEXT; +ALTER TABLE device_lists_remote_pending ADD COLUMN instance_name TEXT; + +ALTER TABLE e2e_cross_signing_keys ADD COLUMN instance_name TEXT; + +ALTER TABLE push_rules_stream ADD COLUMN instance_name TEXT; + +ALTER TABLE pushers ADD COLUMN instance_name TEXT; +ALTER TABLE deleted_pushers ADD COLUMN instance_name TEXT; diff --git a/synapse/storage/schema/main/delta/85/03_new_sequences.sql.postgres b/synapse/storage/schema/main/delta/85/03_new_sequences.sql.postgres new file mode 100644 index 0000000000..9d34066bf5 --- /dev/null +++ b/synapse/storage/schema/main/delta/85/03_new_sequences.sql.postgres @@ -0,0 +1,54 @@ +-- +-- This file is licensed under the Affero General Public License (AGPL) version 3. +-- +-- Copyright (C) 2024 New Vector, Ltd +-- +-- This program is free software: you can redistribute it and/or modify +-- it under the terms of the GNU Affero General Public License as +-- published by the Free Software Foundation, either version 3 of the +-- License, or (at your option) any later version. +-- +-- See the GNU Affero General Public License for more details: +-- <https://www.gnu.org/licenses/agpl-3.0.html>. + +-- Add squences for stream tables to allow them to be used with +-- `MultiWriterIdGenerator` +CREATE SEQUENCE IF NOT EXISTS device_lists_sequence; + +-- We need to take the max across all the device lists tables as they share the +-- ID generator +SELECT setval('device_lists_sequence', ( + SELECT GREATEST( + (SELECT COALESCE(MAX(stream_id), 1) FROM device_lists_stream), + (SELECT COALESCE(MAX(stream_id), 1) FROM user_signature_stream), + (SELECT COALESCE(MAX(stream_id), 1) FROM device_lists_outbound_pokes), + (SELECT COALESCE(MAX(stream_id), 1) FROM device_lists_changes_in_room), + (SELECT COALESCE(MAX(stream_id), 1) FROM device_lists_remote_pending), + (SELECT COALESCE(MAX(stream_id), 1) FROM device_lists_changes_converted_stream_position) + ) +)); + +CREATE SEQUENCE IF NOT EXISTS e2e_cross_signing_keys_sequence; + +SELECT setval('e2e_cross_signing_keys_sequence', ( + SELECT COALESCE(MAX(stream_id), 1) FROM e2e_cross_signing_keys +)); + + +CREATE SEQUENCE IF NOT EXISTS push_rules_stream_sequence; + +SELECT setval('push_rules_stream_sequence', ( + SELECT COALESCE(MAX(stream_id), 1) FROM push_rules_stream +)); + + +CREATE SEQUENCE IF NOT EXISTS pushers_sequence; + +-- We need to take the max across all the pusher tables as they share the +-- ID generator +SELECT setval('pushers_sequence', ( + SELECT GREATEST( + (SELECT COALESCE(MAX(id), 1) FROM pushers), + (SELECT COALESCE(MAX(stream_id), 1) FROM deleted_pushers) + ) +)); diff --git a/synapse/storage/schema/main/delta/85/04_cleanup_device_federation_outbox.sql b/synapse/storage/schema/main/delta/85/04_cleanup_device_federation_outbox.sql new file mode 100644 index 0000000000..041b17b0ee --- /dev/null +++ b/synapse/storage/schema/main/delta/85/04_cleanup_device_federation_outbox.sql @@ -0,0 +1,15 @@ +-- +-- This file is licensed under the Affero General Public License (AGPL) version 3. +-- +-- Copyright (C) 2024 New Vector, Ltd +-- +-- This program is free software: you can redistribute it and/or modify +-- it under the terms of the GNU Affero General Public License as +-- published by the Free Software Foundation, either version 3 of the +-- License, or (at your option) any later version. +-- +-- See the GNU Affero General Public License for more details: +-- <https://www.gnu.org/licenses/agpl-3.0.html>. + +INSERT INTO background_updates (ordering, update_name, progress_json) VALUES + (8504, 'cleanup_device_federation_outbox', '{}'); diff --git a/synapse/storage/schema/main/delta/85/05_add_instance_names_converted_pos.sql b/synapse/storage/schema/main/delta/85/05_add_instance_names_converted_pos.sql new file mode 100644 index 0000000000..c3f2b6a1dd --- /dev/null +++ b/synapse/storage/schema/main/delta/85/05_add_instance_names_converted_pos.sql @@ -0,0 +1,16 @@ +-- +-- This file is licensed under the Affero General Public License (AGPL) version 3. +-- +-- Copyright (C) 2024 New Vector, Ltd +-- +-- This program is free software: you can redistribute it and/or modify +-- it under the terms of the GNU Affero General Public License as +-- published by the Free Software Foundation, either version 3 of the +-- License, or (at your option) any later version. +-- +-- See the GNU Affero General Public License for more details: +-- <https://www.gnu.org/licenses/agpl-3.0.html>. + +-- Add `instance_name` columns to stream tables to allow them to be used with +-- `MultiWriterIdGenerator` +ALTER TABLE device_lists_changes_converted_stream_position ADD COLUMN instance_name TEXT; diff --git a/synapse/storage/schema/main/delta/85/06_add_room_reports.sql b/synapse/storage/schema/main/delta/85/06_add_room_reports.sql new file mode 100644 index 0000000000..f7b45276cf --- /dev/null +++ b/synapse/storage/schema/main/delta/85/06_add_room_reports.sql @@ -0,0 +1,20 @@ +-- +-- This file is licensed under the Affero General Public License (AGPL) version 3. +-- +-- Copyright (C) 2024 New Vector, Ltd +-- +-- This program is free software: you can redistribute it and/or modify +-- it under the terms of the GNU Affero General Public License as +-- published by the Free Software Foundation, either version 3 of the +-- License, or (at your option) any later version. +-- +-- See the GNU Affero General Public License for more details: +-- <https://www.gnu.org/licenses/agpl-3.0.html>. + +CREATE TABLE room_reports ( + id BIGINT NOT NULL PRIMARY KEY, + received_ts BIGINT NOT NULL, + room_id TEXT NOT NULL, + user_id TEXT NOT NULL, + reason TEXT NOT NULL +); diff --git a/synapse/storage/util/id_generators.py b/synapse/storage/util/id_generators.py index fadc75cc80..48f88a6f8a 100644 --- a/synapse/storage/util/id_generators.py +++ b/synapse/storage/util/id_generators.py @@ -23,15 +23,12 @@ import abc import heapq import logging import threading -from collections import OrderedDict -from contextlib import contextmanager from types import TracebackType from typing import ( TYPE_CHECKING, AsyncContextManager, ContextManager, Dict, - Generator, Generic, Iterable, List, @@ -53,9 +50,11 @@ from synapse.storage.database import ( DatabasePool, LoggingDatabaseConnection, LoggingTransaction, + make_in_list_sql_clause, ) +from synapse.storage.engines import PostgresEngine from synapse.storage.types import Cursor -from synapse.storage.util.sequence import PostgresSequenceGenerator +from synapse.storage.util.sequence import build_sequence_generator if TYPE_CHECKING: from synapse.notifier import ReplicationNotifier @@ -177,161 +176,6 @@ class AbstractStreamIdGenerator(metaclass=abc.ABCMeta): raise NotImplementedError() -class StreamIdGenerator(AbstractStreamIdGenerator): - """Generates and tracks stream IDs for a stream with a single writer. - - This class must only be used when the current Synapse process is the sole - writer for a stream. - - Args: - db_conn(connection): A database connection to use to fetch the - initial value of the generator from. - table(str): A database table to read the initial value of the id - generator from. - column(str): The column of the database table to read the initial - value from the id generator from. - extra_tables(list): List of pairs of database tables and columns to - use to source the initial value of the generator from. The value - with the largest magnitude is used. - step(int): which direction the stream ids grow in. +1 to grow - upwards, -1 to grow downwards. - - Usage: - async with stream_id_gen.get_next() as stream_id: - # ... persist event ... - """ - - def __init__( - self, - db_conn: LoggingDatabaseConnection, - notifier: "ReplicationNotifier", - table: str, - column: str, - extra_tables: Iterable[Tuple[str, str]] = (), - step: int = 1, - is_writer: bool = True, - ) -> None: - assert step != 0 - self._lock = threading.Lock() - self._step: int = step - self._current: int = _load_current_id(db_conn, table, column, step) - self._is_writer = is_writer - for table, column in extra_tables: - self._current = (max if step > 0 else min)( - self._current, _load_current_id(db_conn, table, column, step) - ) - - # We use this as an ordered set, as we want to efficiently append items, - # remove items and get the first item. Since we insert IDs in order, the - # insertion ordering will ensure its in the correct ordering. - # - # The key and values are the same, but we never look at the values. - self._unfinished_ids: OrderedDict[int, int] = OrderedDict() - - self._notifier = notifier - - def advance(self, instance_name: str, new_id: int) -> None: - # Advance should never be called on a writer instance, only over replication - if self._is_writer: - raise Exception("Replication is not supported by writer StreamIdGenerator") - - self._current = (max if self._step > 0 else min)(self._current, new_id) - - def get_next(self) -> AsyncContextManager[int]: - with self._lock: - self._current += self._step - next_id = self._current - - self._unfinished_ids[next_id] = next_id - - @contextmanager - def manager() -> Generator[int, None, None]: - try: - yield next_id - finally: - with self._lock: - self._unfinished_ids.pop(next_id) - - self._notifier.notify_replication() - - return _AsyncCtxManagerWrapper(manager()) - - def get_next_mult(self, n: int) -> AsyncContextManager[Sequence[int]]: - with self._lock: - next_ids = range( - self._current + self._step, - self._current + self._step * (n + 1), - self._step, - ) - self._current += n * self._step - - for next_id in next_ids: - self._unfinished_ids[next_id] = next_id - - @contextmanager - def manager() -> Generator[Sequence[int], None, None]: - try: - yield next_ids - finally: - with self._lock: - for next_id in next_ids: - self._unfinished_ids.pop(next_id) - - self._notifier.notify_replication() - - return _AsyncCtxManagerWrapper(manager()) - - def get_next_txn(self, txn: LoggingTransaction) -> int: - """ - Retrieve the next stream ID from within a database transaction. - - Clean-up functions will be called when the transaction finishes. - - Args: - txn: The database transaction object. - - Returns: - The next stream ID. - """ - if not self._is_writer: - raise Exception("Tried to allocate stream ID on non-writer") - - # Get the next stream ID. - with self._lock: - self._current += self._step - next_id = self._current - - self._unfinished_ids[next_id] = next_id - - def clear_unfinished_id(id_to_clear: int) -> None: - """A function to mark processing this ID as finished""" - with self._lock: - self._unfinished_ids.pop(id_to_clear) - - # Mark this ID as finished once the database transaction itself finishes. - txn.call_after(clear_unfinished_id, next_id) - txn.call_on_exception(clear_unfinished_id, next_id) - - # Return the new ID. - return next_id - - def get_current_token(self) -> int: - if not self._is_writer: - return self._current - - with self._lock: - if self._unfinished_ids: - return next(iter(self._unfinished_ids)) - self._step - - return self._current - - def get_current_token_for_writer(self, instance_name: str) -> int: - return self.get_current_token() - - def get_minimal_local_current_token(self) -> int: - return self.get_current_token() - - class MultiWriterIdGenerator(AbstractStreamIdGenerator): """Generates and tracks stream IDs for a stream with multiple writers. @@ -432,7 +276,19 @@ class MultiWriterIdGenerator(AbstractStreamIdGenerator): # no active writes in progress. self._max_position_of_local_instance = self._max_seen_allocated_stream_id - self._sequence_gen = PostgresSequenceGenerator(sequence_name) + self._sequence_gen = build_sequence_generator( + db_conn=db_conn, + database_engine=db.engine, + get_first_callback=lambda _: self._persisted_upto_position, + sequence_name=sequence_name, + # We only need to set the below if we want it to call + # `check_consistency`, but we do that ourselves below so we can + # leave them blank. + table=None, + id_column=None, + stream_name=None, + positive=positive, + ) # We check that the table and sequence haven't diverged. for table, _, id_column in tables: @@ -445,7 +301,11 @@ class MultiWriterIdGenerator(AbstractStreamIdGenerator): ) # This goes and fills out the above state from the database. - self._load_current_ids(db_conn, tables) + # This may read on the PostgreSQL sequence, and + # SequenceGenerator.check_consistency might have fixed up the sequence, which + # means the SequenceGenerator needs to be setup before we read the value from + # the sequence. + self._load_current_ids(db_conn, tables, sequence_name) self._max_seen_allocated_stream_id = max( self._current_positions.values(), default=1 @@ -471,6 +331,7 @@ class MultiWriterIdGenerator(AbstractStreamIdGenerator): self, db_conn: LoggingDatabaseConnection, tables: List[Tuple[str, str, str]], + sequence_name: str, ) -> None: cur = db_conn.cursor(txn_name="_load_current_ids") @@ -480,13 +341,17 @@ class MultiWriterIdGenerator(AbstractStreamIdGenerator): # important if we add back a writer after a long time; we want to # consider that a "new" writer, rather than using the old stale # entry here. - sql = """ + clause, args = make_in_list_sql_clause( + self._db.engine, "instance_name", self._writers, negative=True + ) + + sql = f""" DELETE FROM stream_positions WHERE stream_name = ? - AND instance_name != ALL(?) + AND {clause} """ - cur.execute(sql, (self._stream_name, self._writers)) + cur.execute(sql, [self._stream_name] + args) sql = """ SELECT instance_name, stream_id FROM stream_positions @@ -500,6 +365,18 @@ class MultiWriterIdGenerator(AbstractStreamIdGenerator): if instance in self._writers } + # If we're a writer, we can assume we're at the end of the stream + # Usually, we would get that from the stream_positions, but in some cases, + # like if we rolled back Synapse, the stream_positions table might not be up to + # date. If we're using Postgres for the sequences, we can just use the current + # sequence value as our own position. + if self._instance_name in self._writers: + if isinstance(self._db.engine, PostgresEngine): + cur.execute(f"SELECT last_value FROM {sequence_name}") + row = cur.fetchone() + assert row is not None + self._current_positions[self._instance_name] = row[0] + # We set the `_persisted_upto_position` to be the minimum of all current # positions. If empty we use the max stream ID from the DB table. min_stream_id = min(self._current_positions.values(), default=None) @@ -508,12 +385,16 @@ class MultiWriterIdGenerator(AbstractStreamIdGenerator): # We add a GREATEST here to ensure that the result is always # positive. (This can be a problem for e.g. backfill streams where # the server has never backfilled). + greatest_func = ( + "GREATEST" if isinstance(self._db.engine, PostgresEngine) else "MAX" + ) max_stream_id = 1 for table, _, id_column in tables: sql = """ - SELECT GREATEST(COALESCE(%(agg)s(%(id)s), 1), 1) + SELECT %(greatest_func)s(COALESCE(%(agg)s(%(id)s), 1), 1) FROM %(table)s """ % { + "greatest_func": greatest_func, "id": id_column, "table": table, "agg": "MAX" if self._positive else "-MIN", @@ -913,6 +794,11 @@ class MultiWriterIdGenerator(AbstractStreamIdGenerator): # We upsert the value, ensuring on conflict that we always increase the # value (or decrease if stream goes backwards). + if isinstance(self._db.engine, PostgresEngine): + agg = "GREATEST" if self._positive else "LEAST" + else: + agg = "MAX" if self._positive else "MIN" + sql = """ INSERT INTO stream_positions (stream_name, instance_name, stream_id) VALUES (?, ?, ?) @@ -920,10 +806,10 @@ class MultiWriterIdGenerator(AbstractStreamIdGenerator): DO UPDATE SET stream_id = %(agg)s(stream_positions.stream_id, EXCLUDED.stream_id) """ % { - "agg": "GREATEST" if self._positive else "LEAST", + "agg": agg, } - pos = (self.get_current_token_for_writer(self._instance_name),) + pos = self.get_current_token_for_writer(self._instance_name) txn.execute(sql, (self._stream_name, self._instance_name, pos)) diff --git a/synapse/storage/util/sequence.py b/synapse/storage/util/sequence.py index f57e7ec41c..c4c0602b28 100644 --- a/synapse/storage/util/sequence.py +++ b/synapse/storage/util/sequence.py @@ -36,21 +36,6 @@ if TYPE_CHECKING: logger = logging.getLogger(__name__) -_INCONSISTENT_SEQUENCE_ERROR = """ -Postgres sequence '%(seq)s' is inconsistent with associated -table '%(table)s'. This can happen if Synapse has been downgraded and -then upgraded again, or due to a bad migration. - -To fix this error, shut down Synapse (including any and all workers) -and run the following SQL: - - SELECT setval('%(seq)s', ( - %(max_id_sql)s - )); - -See docs/postgres.md for more information. -""" - _INCONSISTENT_STREAM_ERROR = """ Postgres sequence '%(seq)s' is inconsistent with associated stream position of '%(stream_name)s' in the 'stream_positions' table. @@ -169,25 +154,33 @@ class PostgresSequenceGenerator(SequenceGenerator): if row: max_in_stream_positions = row[0] - txn.close() - # If `is_called` is False then `last_value` is actually the value that # will be generated next, so we decrement to get the true "last value". if not is_called: last_value -= 1 if max_stream_id > last_value: + # The sequence is lagging behind the tables. This is probably due to + # rolling back to a version before the sequence was used and then + # forwards again. We resolve this by setting the sequence to the + # right value. logger.warning( - "Postgres sequence %s is behind table %s: %d < %d", + "Postgres sequence %s is behind table %s: %d < %d. Updating sequence.", self._sequence_name, table, last_value, max_stream_id, ) - raise IncorrectDatabaseSetup( - _INCONSISTENT_SEQUENCE_ERROR - % {"seq": self._sequence_name, "table": table, "max_id_sql": table_sql} - ) + + sql = f""" + SELECT setval('{self._sequence_name}', GREATEST( + (SELECT last_value FROM {self._sequence_name}), + ({table_sql}) + )); + """ + txn.execute(sql) + + txn.close() # If we have values in the stream positions table then they have to be # less than or equal to `last_value` diff --git a/synapse/streams/config.py b/synapse/streams/config.py index eeafe889de..9fee5bfb92 100644 --- a/synapse/streams/config.py +++ b/synapse/streams/config.py @@ -75,9 +75,6 @@ class PaginationConfig: raise SynapseError(400, "'to' parameter is invalid") limit = parse_integer(request, "limit", default=default_limit) - if limit < 0: - raise SynapseError(400, "Limit must be 0 or above") - limit = min(limit, MAX_LIMIT) try: diff --git a/synapse/synapse_rust/events.pyi b/synapse/synapse_rust/events.pyi index 69837617f5..1682d0d151 100644 --- a/synapse/synapse_rust/events.pyi +++ b/synapse/synapse_rust/events.pyi @@ -19,6 +19,8 @@ class EventInternalMetadata: stream_ordering: Optional[int] """the stream ordering of this event. None, until it has been persisted.""" + instance_name: Optional[str] + """the instance name of the server that persisted this event. None, until it has been persisted.""" outlier: bool """whether this event is an outlier (ie, whether we have the state at that diff --git a/synapse/types/__init__.py b/synapse/types/__init__.py index 509a2d3a0f..151658df53 100644 --- a/synapse/types/__init__.py +++ b/synapse/types/__init__.py @@ -48,7 +48,7 @@ import attr from immutabledict import immutabledict from signedjson.key import decode_verify_key_bytes from signedjson.types import VerifyKey -from typing_extensions import TypedDict +from typing_extensions import Self, TypedDict from unpaddedbase64 import decode_base64 from zope.interface import Interface @@ -515,6 +515,27 @@ class AbstractMultiWriterStreamToken(metaclass=abc.ABCMeta): # at `self.stream`. return self.instance_map.get(instance_name, self.stream) + def is_before_or_eq(self, other_token: Self) -> bool: + """Wether this token is before the other token, i.e. every constituent + part is before the other. + + Essentially it is `self <= other`. + + Note: if `self.is_before_or_eq(other_token) is False` then that does not + imply that the reverse is True. + """ + if self.stream > other_token.stream: + return False + + instances = self.instance_map.keys() | other_token.instance_map.keys() + for instance in instances: + if self.instance_map.get( + instance, self.stream + ) > other_token.instance_map.get(instance, other_token.stream): + return False + + return True + @attr.s(frozen=True, slots=True, order=False) class RoomStreamToken(AbstractMultiWriterStreamToken): @@ -1008,6 +1029,41 @@ class StreamToken: """Returns the stream ID for the given key.""" return getattr(self, key.value) + def is_before_or_eq(self, other_token: "StreamToken") -> bool: + """Wether this token is before the other token, i.e. every constituent + part is before the other. + + Essentially it is `self <= other`. + + Note: if `self.is_before_or_eq(other_token) is False` then that does not + imply that the reverse is True. + """ + + for _, key in StreamKeyType.__members__.items(): + if key == StreamKeyType.TYPING: + # Typing stream is allowed to "reset", and so comparisons don't + # really make sense as is. + # TODO: Figure out a better way of tracking resets. + continue + + self_value = self.get_field(key) + other_value = other_token.get_field(key) + + if isinstance(self_value, RoomStreamToken): + assert isinstance(other_value, RoomStreamToken) + if not self_value.is_before_or_eq(other_value): + return False + elif isinstance(self_value, MultiWriterStreamToken): + assert isinstance(other_value, MultiWriterStreamToken) + if not self_value.is_before_or_eq(other_value): + return False + else: + assert isinstance(other_value, int) + if self_value > other_value: + return False + + return True + StreamToken.START = StreamToken( RoomStreamToken(stream=0), 0, 0, MultiWriterStreamToken(stream=0), 0, 0, 0, 0, 0, 0 diff --git a/synapse/types/handlers/__init__.py b/synapse/types/handlers/__init__.py new file mode 100644 index 0000000000..1d65551d5b --- /dev/null +++ b/synapse/types/handlers/__init__.py @@ -0,0 +1,252 @@ +# +# This file is licensed under the Affero General Public License (AGPL) version 3. +# +# Copyright (C) 2024 New Vector, Ltd +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as +# published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# See the GNU Affero General Public License for more details: +# <https://www.gnu.org/licenses/agpl-3.0.html>. +# +# Originally licensed under the Apache License, Version 2.0: +# <http://www.apache.org/licenses/LICENSE-2.0>. +# +# [This file includes modifications made by New Vector Limited] +# +# +from enum import Enum +from typing import TYPE_CHECKING, Dict, Final, List, Optional, Tuple + +import attr +from typing_extensions import TypedDict + +from synapse._pydantic_compat import HAS_PYDANTIC_V2 + +if TYPE_CHECKING or HAS_PYDANTIC_V2: + from pydantic.v1 import Extra +else: + from pydantic import Extra + +from synapse.events import EventBase +from synapse.types import JsonMapping, StreamToken, UserID +from synapse.types.rest.client import SlidingSyncBody + + +class ShutdownRoomParams(TypedDict): + """ + Attributes: + requester_user_id: + User who requested the action. Will be recorded as putting the room on the + blocking list. + new_room_user_id: + If set, a new room will be created with this user ID + as the creator and admin, and all users in the old room will be + moved into that room. If not set, no new room will be created + and the users will just be removed from the old room. + new_room_name: + A string representing the name of the room that new users will + be invited to. Defaults to `Content Violation Notification` + message: + A string containing the first message that will be sent as + `new_room_user_id` in the new room. Ideally this will clearly + convey why the original room was shut down. + Defaults to `Sharing illegal content on this server is not + permitted and rooms in violation will be blocked.` + block: + If set to `true`, this room will be added to a blocking list, + preventing future attempts to join the room. Defaults to `false`. + purge: + If set to `true`, purge the given room from the database. + force_purge: + If set to `true`, the room will be purged from database + even if there are still users joined to the room. + """ + + requester_user_id: Optional[str] + new_room_user_id: Optional[str] + new_room_name: Optional[str] + message: Optional[str] + block: bool + purge: bool + force_purge: bool + + +class ShutdownRoomResponse(TypedDict): + """ + Attributes: + kicked_users: An array of users (`user_id`) that were kicked. + failed_to_kick_users: + An array of users (`user_id`) that that were not kicked. + local_aliases: + An array of strings representing the local aliases that were + migrated from the old room to the new. + new_room_id: A string representing the room ID of the new room. + """ + + kicked_users: List[str] + failed_to_kick_users: List[str] + local_aliases: List[str] + new_room_id: Optional[str] + + +class SlidingSyncConfig(SlidingSyncBody): + """ + Inherit from `SlidingSyncBody` since we need all of the same fields and add a few + extra fields that we need in the handler + """ + + user: UserID + device_id: Optional[str] + + # Pydantic config + class Config: + # By default, ignore fields that we don't recognise. + extra = Extra.ignore + # By default, don't allow fields to be reassigned after parsing. + allow_mutation = False + # Allow custom types like `UserID` to be used in the model + arbitrary_types_allowed = True + + +class OperationType(Enum): + """ + Represents the operation types in a Sliding Sync window. + + Attributes: + SYNC: Sets a range of entries. Clients SHOULD discard what they previous knew about + entries in this range. + INSERT: Sets a single entry. If the position is not empty then clients MUST move + entries to the left or the right depending on where the closest empty space is. + DELETE: Remove a single entry. Often comes before an INSERT to allow entries to move + places. + INVALIDATE: Remove a range of entries. Clients MAY persist the invalidated range for + offline support, but they should be treated as empty when additional operations + which concern indexes in the range arrive from the server. + """ + + SYNC: Final = "SYNC" + INSERT: Final = "INSERT" + DELETE: Final = "DELETE" + INVALIDATE: Final = "INVALIDATE" + + +@attr.s(slots=True, frozen=True, auto_attribs=True) +class SlidingSyncResult: + """ + The Sliding Sync result to be serialized to JSON for a response. + + Attributes: + next_pos: The next position token in the sliding window to request (next_batch). + lists: Sliding window API. A map of list key to list results. + rooms: Room subscription API. A map of room ID to room subscription to room results. + extensions: Extensions API. A map of extension key to extension results. + """ + + @attr.s(slots=True, frozen=True, auto_attribs=True) + class RoomResult: + """ + Attributes: + name: Room name or calculated room name. + avatar: Room avatar + heroes: List of stripped membership events (containing `user_id` and optionally + `avatar_url` and `displayname`) for the users used to calculate the room name. + initial: Flag which is set when this is the first time the server is sending this + data on this connection. Clients can use this flag to replace or update + their local state. When there is an update, servers MUST omit this flag + entirely and NOT send "initial":false as this is wasteful on bandwidth. The + absence of this flag means 'false'. + required_state: The current state of the room + timeline: Latest events in the room. The last event is the most recent + is_dm: Flag to specify whether the room is a direct-message room (most likely + between two people). + invite_state: Stripped state events. Same as `rooms.invite.$room_id.invite_state` + in sync v2, absent on joined/left rooms + prev_batch: A token that can be passed as a start parameter to the + `/rooms/<room_id>/messages` API to retrieve earlier messages. + limited: True if their are more events than fit between the given position and now. + Sync again to get more. + joined_count: The number of users with membership of join, including the client's + own user ID. (same as sync `v2 m.joined_member_count`) + invited_count: The number of users with membership of invite. (same as sync v2 + `m.invited_member_count`) + notification_count: The total number of unread notifications for this room. (same + as sync v2) + highlight_count: The number of unread notifications for this room with the highlight + flag set. (same as sync v2) + num_live: The number of timeline events which have just occurred and are not historical. + The last N events are 'live' and should be treated as such. This is mostly + useful to determine whether a given @mention event should make a noise or not. + Clients cannot rely solely on the absence of `initial: true` to determine live + events because if a room not in the sliding window bumps into the window because + of an @mention it will have `initial: true` yet contain a single live event + (with potentially other old events in the timeline). + """ + + name: str + avatar: Optional[str] + heroes: Optional[List[EventBase]] + initial: bool + required_state: List[EventBase] + timeline: List[EventBase] + is_dm: bool + invite_state: List[EventBase] + prev_batch: StreamToken + limited: bool + joined_count: int + invited_count: int + notification_count: int + highlight_count: int + num_live: int + + @attr.s(slots=True, frozen=True, auto_attribs=True) + class SlidingWindowList: + """ + Attributes: + count: The total number of entries in the list. Always present if this list + is. + ops: The sliding list operations to perform. + """ + + @attr.s(slots=True, frozen=True, auto_attribs=True) + class Operation: + """ + Attributes: + op: The operation type to perform. + range: Which index positions are affected by this operation. These are + both inclusive. + room_ids: Which room IDs are affected by this operation. These IDs match + up to the positions in the `range`, so the last room ID in this list + matches the 9th index. The room data is held in a separate object. + """ + + op: OperationType + range: Tuple[int, int] + room_ids: List[str] + + count: int + ops: List[Operation] + + next_pos: StreamToken + lists: Dict[str, SlidingWindowList] + rooms: Dict[str, RoomResult] + extensions: JsonMapping + + def __bool__(self) -> bool: + """Make the result appear empty if there are no updates. This is used + to tell if the notifier needs to wait for more events when polling for + events. + """ + return bool(self.lists or self.rooms or self.extensions) + + @staticmethod + def empty(next_pos: StreamToken) -> "SlidingSyncResult": + "Return a new empty result" + return SlidingSyncResult( + next_pos=next_pos, + lists={}, + rooms={}, + extensions={}, + ) diff --git a/synapse/rest/models.py b/synapse/types/rest/__init__.py index 2b6f5ed35a..2b6f5ed35a 100644 --- a/synapse/rest/models.py +++ b/synapse/types/rest/__init__.py diff --git a/synapse/types/rest/client/__init__.py b/synapse/types/rest/client/__init__.py new file mode 100644 index 0000000000..e2c79c4106 --- /dev/null +++ b/synapse/types/rest/client/__init__.py @@ -0,0 +1,309 @@ +# +# This file is licensed under the Affero General Public License (AGPL) version 3. +# +# Copyright 2022 The Matrix.org Foundation C.I.C. +# Copyright (C) 2023 New Vector, Ltd +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as +# published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# See the GNU Affero General Public License for more details: +# <https://www.gnu.org/licenses/agpl-3.0.html>. +# +# Originally licensed under the Apache License, Version 2.0: +# <http://www.apache.org/licenses/LICENSE-2.0>. +# +# [This file includes modifications made by New Vector Limited] +# +# +from typing import TYPE_CHECKING, Dict, List, Optional, Tuple, Union + +from synapse._pydantic_compat import HAS_PYDANTIC_V2 + +if TYPE_CHECKING or HAS_PYDANTIC_V2: + from pydantic.v1 import ( + Extra, + StrictBool, + StrictInt, + StrictStr, + conint, + constr, + validator, + ) +else: + from pydantic import ( + Extra, + StrictBool, + StrictInt, + StrictStr, + conint, + constr, + validator, + ) + +from synapse.types.rest import RequestBodyModel +from synapse.util.threepids import validate_email + + +class AuthenticationData(RequestBodyModel): + """ + Data used during user-interactive authentication. + + (The name "Authentication Data" is taken directly from the spec.) + + Additional keys will be present, depending on the `type` field. Use + `.dict(exclude_unset=True)` to access them. + """ + + class Config: + extra = Extra.allow + + session: Optional[StrictStr] = None + type: Optional[StrictStr] = None + + +if TYPE_CHECKING: + ClientSecretStr = StrictStr +else: + # See also assert_valid_client_secret() + ClientSecretStr = constr( + regex="[0-9a-zA-Z.=_-]", # noqa: F722 + min_length=1, + max_length=255, + strict=True, + ) + + +class ThreepidRequestTokenBody(RequestBodyModel): + client_secret: ClientSecretStr + id_server: Optional[StrictStr] + id_access_token: Optional[StrictStr] + next_link: Optional[StrictStr] + send_attempt: StrictInt + + @validator("id_access_token", always=True) + def token_required_for_identity_server( + cls, token: Optional[str], values: Dict[str, object] + ) -> Optional[str]: + if values.get("id_server") is not None and token is None: + raise ValueError("id_access_token is required if an id_server is supplied.") + return token + + +class EmailRequestTokenBody(ThreepidRequestTokenBody): + email: StrictStr + + # Canonicalise the email address. The addresses are all stored canonicalised + # in the database. This allows the user to reset his password without having to + # know the exact spelling (eg. upper and lower case) of address in the database. + # Without this, an email stored in the database as "foo@bar.com" would cause + # user requests for "FOO@bar.com" to raise a Not Found error. + _email_validator = validator("email", allow_reuse=True)(validate_email) + + +if TYPE_CHECKING: + ISO3116_1_Alpha_2 = StrictStr +else: + # Per spec: two-letter uppercase ISO-3166-1-alpha-2 + ISO3116_1_Alpha_2 = constr(regex="[A-Z]{2}", strict=True) + + +class MsisdnRequestTokenBody(ThreepidRequestTokenBody): + country: ISO3116_1_Alpha_2 + phone_number: StrictStr + + +class SlidingSyncBody(RequestBodyModel): + """ + Sliding Sync API request body. + + Attributes: + lists: Sliding window API. A map of list key to list information + (:class:`SlidingSyncList`). Max lists: 100. The list keys should be + arbitrary strings which the client is using to refer to the list. Keep this + small as it needs to be sent a lot. Max length: 64 bytes. + room_subscriptions: Room subscription API. A map of room ID to room subscription + information. Used to subscribe to a specific room. Sometimes clients know + exactly which room they want to get information about e.g by following a + permalink or by refreshing a webapp currently viewing a specific room. The + sliding window API alone is insufficient for this use case because there's + no way to say "please track this room explicitly". + extensions: Extensions API. A map of extension key to extension config. + """ + + class CommonRoomParameters(RequestBodyModel): + """ + Common parameters shared between the sliding window and room subscription APIs. + + Attributes: + required_state: Required state for each room returned. An array of event + type and state key tuples. Elements in this array are ORd together to + produce the final set of state events to return. One unique exception is + when you request all state events via `["*", "*"]`. When used, all state + events are returned by default, and additional entries FILTER OUT the + returned set of state events. These additional entries cannot use `*` + themselves. For example, `["*", "*"], ["m.room.member", + "@alice:example.com"]` will *exclude* every `m.room.member` event + *except* for `@alice:example.com`, and include every other state event. + In addition, `["*", "*"], ["m.space.child", "*"]` is an error, the + `m.space.child` filter is not required as it would have been returned + anyway. + timeline_limit: The maximum number of timeline events to return per response. + (Max 1000 messages) + include_old_rooms: Determines if `predecessor` rooms are included in the + `rooms` response. The user MUST be joined to old rooms for them to show up + in the response. + """ + + class IncludeOldRooms(RequestBodyModel): + timeline_limit: StrictInt + required_state: List[Tuple[StrictStr, StrictStr]] + + required_state: List[Tuple[StrictStr, StrictStr]] + # mypy workaround via https://github.com/pydantic/pydantic/issues/156#issuecomment-1130883884 + if TYPE_CHECKING: + timeline_limit: int + else: + timeline_limit: conint(le=1000, strict=True) # type: ignore[valid-type] + include_old_rooms: Optional[IncludeOldRooms] = None + + class SlidingSyncList(CommonRoomParameters): + """ + Attributes: + ranges: Sliding window ranges. If this field is missing, no sliding window + is used and all rooms are returned in this list. Integers are + *inclusive*. + slow_get_all_rooms: Just get all rooms (for clients that don't want to deal with + sliding windows). When true, the `ranges` field is ignored. + required_state: Required state for each room returned. An array of event + type and state key tuples. Elements in this array are ORd together to + produce the final set of state events to return. + + One unique exception is when you request all state events via `["*", + "*"]`. When used, all state events are returned by default, and + additional entries FILTER OUT the returned set of state events. These + additional entries cannot use `*` themselves. For example, `["*", "*"], + ["m.room.member", "@alice:example.com"]` will *exclude* every + `m.room.member` event *except* for `@alice:example.com`, and include + every other state event. In addition, `["*", "*"], ["m.space.child", + "*"]` is an error, the `m.space.child` filter is not required as it + would have been returned anyway. + + Room members can be lazily-loaded by using the special `$LAZY` state key + (`["m.room.member", "$LAZY"]`). Typically, when you view a room, you + want to retrieve all state events except for m.room.member events which + you want to lazily load. To get this behaviour, clients can send the + following:: + + { + "required_state": [ + // activate lazy loading + ["m.room.member", "$LAZY"], + // request all state events _except_ for m.room.member + events which are lazily loaded + ["*", "*"] + ] + } + + timeline_limit: The maximum number of timeline events to return per response. + include_old_rooms: Determines if `predecessor` rooms are included in the + `rooms` response. The user MUST be joined to old rooms for them to show up + in the response. + include_heroes: Return a stripped variant of membership events (containing + `user_id` and optionally `avatar_url` and `displayname`) for the users used + to calculate the room name. + filters: Filters to apply to the list before sorting. + """ + + class Filters(RequestBodyModel): + """ + All fields are applied with AND operators, hence if `is_dm: True` and + `is_encrypted: True` then only Encrypted DM rooms will be returned. The + absence of fields implies no filter on that criteria: it does NOT imply + `False`. These fields may be expanded through use of extensions. + + Attributes: + is_dm: Flag which only returns rooms present (or not) in the DM section + of account data. If unset, both DM rooms and non-DM rooms are returned. + If False, only non-DM rooms are returned. If True, only DM rooms are + returned. + spaces: Filter the room based on the space they belong to according to + `m.space.child` state events. If multiple spaces are present, a room can + be part of any one of the listed spaces (OR'd). The server will inspect + the `m.space.child` state events for the JOINED space room IDs given. + Servers MUST NOT navigate subspaces. It is up to the client to give a + complete list of spaces to navigate. Only rooms directly mentioned as + `m.space.child` events in these spaces will be returned. Unknown spaces + or spaces the user is not joined to will be ignored. + is_encrypted: Flag which only returns rooms which have an + `m.room.encryption` state event. If unset, both encrypted and + unencrypted rooms are returned. If `False`, only unencrypted rooms are + returned. If `True`, only encrypted rooms are returned. + is_invite: Flag which only returns rooms the user is currently invited + to. If unset, both invited and joined rooms are returned. If `False`, no + invited rooms are returned. If `True`, only invited rooms are returned. + room_types: If specified, only rooms where the `m.room.create` event has + a `type` matching one of the strings in this array will be returned. If + this field is unset, all rooms are returned regardless of type. This can + be used to get the initial set of spaces for an account. For rooms which + do not have a room type, use `null`/`None` to include them. + not_room_types: Same as `room_types` but inverted. This can be used to + filter out spaces from the room list. If a type is in both `room_types` + and `not_room_types`, then `not_room_types` wins and they are not included + in the result. + room_name_like: Filter the room name. Case-insensitive partial matching + e.g 'foo' matches 'abFooab'. The term 'like' is inspired by SQL 'LIKE', + and the text here is similar to '%foo%'. + tags: Filter the room based on its room tags. If multiple tags are + present, a room can have any one of the listed tags (OR'd). + not_tags: Filter the room based on its room tags. Takes priority over + `tags`. For example, a room with tags A and B with filters `tags: [A]` + `not_tags: [B]` would NOT be included because `not_tags` takes priority over + `tags`. This filter is useful if your rooms list does NOT include the + list of favourite rooms again. + """ + + is_dm: Optional[StrictBool] = None + spaces: Optional[List[StrictStr]] = None + is_encrypted: Optional[StrictBool] = None + is_invite: Optional[StrictBool] = None + room_types: Optional[List[Union[StrictStr, None]]] = None + not_room_types: Optional[List[StrictStr]] = None + room_name_like: Optional[StrictStr] = None + tags: Optional[List[StrictStr]] = None + not_tags: Optional[List[StrictStr]] = None + + # mypy workaround via https://github.com/pydantic/pydantic/issues/156#issuecomment-1130883884 + if TYPE_CHECKING: + ranges: Optional[List[Tuple[int, int]]] = None + else: + ranges: Optional[List[Tuple[conint(ge=0, strict=True), conint(ge=0, strict=True)]]] = None # type: ignore[valid-type] + slow_get_all_rooms: Optional[StrictBool] = False + include_heroes: Optional[StrictBool] = False + filters: Optional[Filters] = None + + class RoomSubscription(CommonRoomParameters): + pass + + class Extension(RequestBodyModel): + enabled: Optional[StrictBool] = False + lists: Optional[List[StrictStr]] = None + rooms: Optional[List[StrictStr]] = None + + # mypy workaround via https://github.com/pydantic/pydantic/issues/156#issuecomment-1130883884 + if TYPE_CHECKING: + lists: Optional[Dict[str, SlidingSyncList]] = None + else: + lists: Optional[Dict[constr(max_length=64, strict=True), SlidingSyncList]] = None # type: ignore[valid-type] + room_subscriptions: Optional[Dict[StrictStr, RoomSubscription]] = None + extensions: Optional[Dict[StrictStr, Extension]] = None + + @validator("lists") + def lists_length_check( + cls, value: Optional[Dict[str, SlidingSyncList]] + ) -> Optional[Dict[str, SlidingSyncList]]: + if value is not None: + assert len(value) <= 100, f"Max lists: 100 but saw {len(value)}" + return value diff --git a/synapse/util/task_scheduler.py b/synapse/util/task_scheduler.py index 01d05c9ed6..448960b297 100644 --- a/synapse/util/task_scheduler.py +++ b/synapse/util/task_scheduler.py @@ -24,7 +24,12 @@ from typing import TYPE_CHECKING, Awaitable, Callable, Dict, List, Optional, Set from twisted.python.failure import Failure -from synapse.logging.context import nested_logging_context +from synapse.logging.context import ( + ContextResourceUsage, + LoggingContext, + nested_logging_context, + set_current_context, +) from synapse.metrics import LaterGauge from synapse.metrics.background_process_metrics import ( run_as_background_process, @@ -81,6 +86,8 @@ class TaskScheduler: MAX_CONCURRENT_RUNNING_TASKS = 5 # Time from the last task update after which we will log a warning LAST_UPDATE_BEFORE_WARNING_MS = 24 * 60 * 60 * 1000 # 24hrs + # Report a running task's status and usage every so often. + OCCASIONAL_REPORT_INTERVAL_MS = 5 * 60 * 1000 # 5 minutes def __init__(self, hs: "HomeServer"): self._hs = hs @@ -346,6 +353,33 @@ class TaskScheduler: assert task.id not in self._running_tasks await self._store.delete_scheduled_task(task.id) + @staticmethod + def _log_task_usage( + state: str, task: ScheduledTask, usage: ContextResourceUsage, active_time: float + ) -> None: + """ + Log a line describing the state and usage of a task. + The log line is inspired by / a copy of the request log line format, + but with irrelevant fields removed. + + active_time: Time that the task has been running for, in seconds. + """ + + logger.info( + "Task %s: %.3fsec (%.3fsec, %.3fsec) (%.3fsec/%.3fsec/%d)" + " [%d dbevts] %r, %r", + state, + active_time, + usage.ru_utime, + usage.ru_stime, + usage.db_sched_duration_sec, + usage.db_txn_duration_sec, + int(usage.db_txn_count), + usage.evt_db_fetch_count, + task.resource_id, + task.params, + ) + async def _launch_task(self, task: ScheduledTask) -> None: """Launch a scheduled task now. @@ -360,8 +394,32 @@ class TaskScheduler: ) function = self._actions[task.action] + def _occasional_report( + task_log_context: LoggingContext, start_time: float + ) -> None: + """ + Helper to log a 'Task continuing' line every so often. + """ + + current_time = self._clock.time() + calling_context = set_current_context(task_log_context) + try: + usage = task_log_context.get_resource_usage() + TaskScheduler._log_task_usage( + "continuing", task, usage, current_time - start_time + ) + finally: + set_current_context(calling_context) + async def wrapper() -> None: - with nested_logging_context(task.id): + with nested_logging_context(task.id) as log_context: + start_time = self._clock.time() + occasional_status_call = self._clock.looping_call( + _occasional_report, + TaskScheduler.OCCASIONAL_REPORT_INTERVAL_MS, + log_context, + start_time, + ) try: (status, result, error) = await function(task) except Exception: @@ -383,6 +441,13 @@ class TaskScheduler: ) self._running_tasks.remove(task.id) + current_time = self._clock.time() + usage = log_context.get_resource_usage() + TaskScheduler._log_task_usage( + status.value, task, usage, current_time - start_time + ) + occasional_status_call.stop() + # Try launch a new task since we've finished with this one. self._clock.call_later(0.1, self._launch_scheduled_tasks) diff --git a/synapse/visibility.py b/synapse/visibility.py index 09a947ef15..128413c8aa 100644 --- a/synapse/visibility.py +++ b/synapse/visibility.py @@ -82,7 +82,6 @@ async def filter_events_for_client( is_peeking: bool = False, always_include_ids: FrozenSet[str] = frozenset(), filter_send_to_client: bool = True, - msc4115_membership_on_events: bool = False, ) -> List[EventBase]: """ Check which events a user is allowed to see. If the user can see the event but its @@ -101,12 +100,10 @@ async def filter_events_for_client( filter_send_to_client: Whether we're checking an event that's going to be sent to a client. This might not always be the case since this function can also be called to check whether a user can see the state at a given point. - msc4115_membership_on_events: Whether to include the requesting user's - membership in the "unsigned" data, per MSC4115. Returns: - The filtered events. If `msc4115_membership_on_events` is true, the `unsigned` - data is annotated with the membership state of `user_id` at each event. + The filtered events. The `unsigned` data is annotated with the membership state + of `user_id` at each event. """ # Filter out events that have been soft failed so that we don't relay them # to clients. @@ -151,7 +148,7 @@ async def filter_events_for_client( filter_send_to_client=filter_send_to_client, sender_ignored=event.sender in ignore_list, always_include_ids=always_include_ids, - retention_policy=retention_policies[room_id], + retention_policy=retention_policies[event.room_id], state=state_after_event, is_peeking=is_peeking, sender_erased=erased_senders.get(event.sender, False), @@ -159,9 +156,6 @@ async def filter_events_for_client( if filtered is None: return None - if not msc4115_membership_on_events: - return filtered - # Annotate the event with the user's membership after the event. # # Normally we just look in `state_after_event`, but if the event is an outlier @@ -186,7 +180,7 @@ async def filter_events_for_client( # Copy the event before updating the unsigned data: this shouldn't be persisted # to the cache! cloned = clone_event(filtered) - cloned.unsigned[EventUnsignedContentFields.MSC4115_MEMBERSHIP] = user_membership + cloned.unsigned[EventUnsignedContentFields.MEMBERSHIP] = user_membership return cloned diff --git a/tests/api/test_ratelimiting.py b/tests/api/test_ratelimiting.py index a24638c9ef..a59e168db1 100644 --- a/tests/api/test_ratelimiting.py +++ b/tests/api/test_ratelimiting.py @@ -116,8 +116,9 @@ class TestRatelimiter(unittest.HomeserverTestCase): # Should raise with self.assertRaises(LimitExceededError) as context: self.get_success_or_raise( - limiter.ratelimit(None, key="test_id", _time_now_s=5) + limiter.ratelimit(None, key="test_id", _time_now_s=5), by=0.5 ) + self.assertEqual(context.exception.retry_after_ms, 5000) # Shouldn't raise @@ -192,7 +193,7 @@ class TestRatelimiter(unittest.HomeserverTestCase): # Second attempt, 1s later, will fail with self.assertRaises(LimitExceededError) as context: self.get_success_or_raise( - limiter.ratelimit(None, key=("test_id",), _time_now_s=1) + limiter.ratelimit(None, key=("test_id",), _time_now_s=1), by=0.5 ) self.assertEqual(context.exception.retry_after_ms, 9000) diff --git a/tests/events/test_auto_accept_invites.py b/tests/events/test_auto_accept_invites.py new file mode 100644 index 0000000000..7fb4d4fa90 --- /dev/null +++ b/tests/events/test_auto_accept_invites.py @@ -0,0 +1,657 @@ +# +# This file is licensed under the Affero General Public License (AGPL) version 3. +# +# Copyright 2021 The Matrix.org Foundation C.I.C +# Copyright (C) 2024 New Vector, Ltd +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as +# published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# See the GNU Affero General Public License for more details: +# <https://www.gnu.org/licenses/agpl-3.0.html>. +# +# Originally licensed under the Apache License, Version 2.0: +# <http://www.apache.org/licenses/LICENSE-2.0>. +# +# [This file includes modifications made by New Vector Limited] +# +# +import asyncio +from asyncio import Future +from http import HTTPStatus +from typing import Any, Awaitable, Dict, List, Optional, Tuple, TypeVar, cast +from unittest.mock import Mock + +import attr +from parameterized import parameterized + +from twisted.test.proto_helpers import MemoryReactor + +from synapse.api.constants import EventTypes +from synapse.api.errors import SynapseError +from synapse.config.auto_accept_invites import AutoAcceptInvitesConfig +from synapse.events.auto_accept_invites import InviteAutoAccepter +from synapse.federation.federation_base import event_from_pdu_json +from synapse.handlers.sync import JoinedSyncResult, SyncRequestKey, SyncVersion +from synapse.module_api import ModuleApi +from synapse.rest import admin +from synapse.rest.client import login, room +from synapse.server import HomeServer +from synapse.types import StreamToken, create_requester +from synapse.util import Clock + +from tests.handlers.test_sync import generate_sync_config +from tests.unittest import ( + FederatingHomeserverTestCase, + HomeserverTestCase, + TestCase, + override_config, +) + + +class AutoAcceptInvitesTestCase(FederatingHomeserverTestCase): + """ + Integration test cases for auto-accepting invites. + """ + + servlets = [ + admin.register_servlets, + login.register_servlets, + room.register_servlets, + ] + + def make_homeserver(self, reactor: MemoryReactor, clock: Clock) -> HomeServer: + hs = self.setup_test_homeserver() + self.handler = hs.get_federation_handler() + self.store = hs.get_datastores().main + return hs + + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: + self.sync_handler = self.hs.get_sync_handler() + self.module_api = hs.get_module_api() + + @parameterized.expand( + [ + [False], + [True], + ] + ) + @override_config( + { + "auto_accept_invites": { + "enabled": True, + }, + } + ) + def test_auto_accept_invites(self, direct_room: bool) -> None: + """Test that a user automatically joins a room when invited, if the + module is enabled. + """ + # A local user who sends an invite + inviting_user_id = self.register_user("inviter", "pass") + inviting_user_tok = self.login("inviter", "pass") + + # A local user who receives an invite + invited_user_id = self.register_user("invitee", "pass") + self.login("invitee", "pass") + + # Create a room and send an invite to the other user + room_id = self.helper.create_room_as( + inviting_user_id, + is_public=False, + tok=inviting_user_tok, + ) + + self.helper.invite( + room_id, + inviting_user_id, + invited_user_id, + tok=inviting_user_tok, + extra_data={"is_direct": direct_room}, + ) + + # Check that the invite receiving user has automatically joined the room when syncing + join_updates, _ = sync_join(self, invited_user_id) + self.assertEqual(len(join_updates), 1) + + join_update: JoinedSyncResult = join_updates[0] + self.assertEqual(join_update.room_id, room_id) + + @override_config( + { + "auto_accept_invites": { + "enabled": False, + }, + } + ) + def test_module_not_enabled(self) -> None: + """Test that a user does not automatically join a room when invited, + if the module is not enabled. + """ + # A local user who sends an invite + inviting_user_id = self.register_user("inviter", "pass") + inviting_user_tok = self.login("inviter", "pass") + + # A local user who receives an invite + invited_user_id = self.register_user("invitee", "pass") + self.login("invitee", "pass") + + # Create a room and send an invite to the other user + room_id = self.helper.create_room_as( + inviting_user_id, is_public=False, tok=inviting_user_tok + ) + + self.helper.invite( + room_id, + inviting_user_id, + invited_user_id, + tok=inviting_user_tok, + ) + + # Check that the invite receiving user has not automatically joined the room when syncing + join_updates, _ = sync_join(self, invited_user_id) + self.assertEqual(len(join_updates), 0) + + @override_config( + { + "auto_accept_invites": { + "enabled": True, + }, + } + ) + def test_invite_from_remote_user(self) -> None: + """Test that an invite from a remote user results in the invited user + automatically joining the room. + """ + # A remote user who sends the invite + remote_server = "otherserver" + remote_user = "@otheruser:" + remote_server + + # A local user who creates the room + creator_user_id = self.register_user("creator", "pass") + creator_user_tok = self.login("creator", "pass") + + # A local user who receives an invite + invited_user_id = self.register_user("invitee", "pass") + self.login("invitee", "pass") + + room_id = self.helper.create_room_as( + room_creator=creator_user_id, tok=creator_user_tok + ) + room_version = self.get_success(self.store.get_room_version(room_id)) + + invite_event = event_from_pdu_json( + { + "type": EventTypes.Member, + "content": {"membership": "invite"}, + "room_id": room_id, + "sender": remote_user, + "state_key": invited_user_id, + "depth": 32, + "prev_events": [], + "auth_events": [], + "origin_server_ts": self.clock.time_msec(), + }, + room_version, + ) + self.get_success( + self.handler.on_invite_request( + remote_server, + invite_event, + invite_event.room_version, + ) + ) + + # Check that the invite receiving user has automatically joined the room when syncing + join_updates, _ = sync_join(self, invited_user_id) + self.assertEqual(len(join_updates), 1) + + join_update: JoinedSyncResult = join_updates[0] + self.assertEqual(join_update.room_id, room_id) + + @parameterized.expand( + [ + [False, False], + [True, True], + ] + ) + @override_config( + { + "auto_accept_invites": { + "enabled": True, + "only_for_direct_messages": True, + }, + } + ) + def test_accept_invite_direct_message( + self, + direct_room: bool, + expect_auto_join: bool, + ) -> None: + """Tests that, if the module is configured to only accept DM invites, invites to DM rooms are still + automatically accepted. Otherwise they are rejected. + """ + # A local user who sends an invite + inviting_user_id = self.register_user("inviter", "pass") + inviting_user_tok = self.login("inviter", "pass") + + # A local user who receives an invite + invited_user_id = self.register_user("invitee", "pass") + self.login("invitee", "pass") + + # Create a room and send an invite to the other user + room_id = self.helper.create_room_as( + inviting_user_id, + is_public=False, + tok=inviting_user_tok, + ) + + self.helper.invite( + room_id, + inviting_user_id, + invited_user_id, + tok=inviting_user_tok, + extra_data={"is_direct": direct_room}, + ) + + if expect_auto_join: + # Check that the invite receiving user has automatically joined the room when syncing + join_updates, _ = sync_join(self, invited_user_id) + self.assertEqual(len(join_updates), 1) + + join_update: JoinedSyncResult = join_updates[0] + self.assertEqual(join_update.room_id, room_id) + else: + # Check that the invite receiving user has not automatically joined the room when syncing + join_updates, _ = sync_join(self, invited_user_id) + self.assertEqual(len(join_updates), 0) + + @parameterized.expand( + [ + [False, True], + [True, False], + ] + ) + @override_config( + { + "auto_accept_invites": { + "enabled": True, + "only_from_local_users": True, + }, + } + ) + def test_accept_invite_local_user( + self, remote_inviter: bool, expect_auto_join: bool + ) -> None: + """Tests that, if the module is configured to only accept invites from local users, invites + from local users are still automatically accepted. Otherwise they are rejected. + """ + # A local user who sends an invite + creator_user_id = self.register_user("inviter", "pass") + creator_user_tok = self.login("inviter", "pass") + + # A local user who receives an invite + invited_user_id = self.register_user("invitee", "pass") + self.login("invitee", "pass") + + # Create a room and send an invite to the other user + room_id = self.helper.create_room_as( + creator_user_id, is_public=False, tok=creator_user_tok + ) + + if remote_inviter: + room_version = self.get_success(self.store.get_room_version(room_id)) + + # A remote user who sends the invite + remote_server = "otherserver" + remote_user = "@otheruser:" + remote_server + + invite_event = event_from_pdu_json( + { + "type": EventTypes.Member, + "content": {"membership": "invite"}, + "room_id": room_id, + "sender": remote_user, + "state_key": invited_user_id, + "depth": 32, + "prev_events": [], + "auth_events": [], + "origin_server_ts": self.clock.time_msec(), + }, + room_version, + ) + self.get_success( + self.handler.on_invite_request( + remote_server, + invite_event, + invite_event.room_version, + ) + ) + else: + self.helper.invite( + room_id, + creator_user_id, + invited_user_id, + tok=creator_user_tok, + ) + + if expect_auto_join: + # Check that the invite receiving user has automatically joined the room when syncing + join_updates, _ = sync_join(self, invited_user_id) + self.assertEqual(len(join_updates), 1) + + join_update: JoinedSyncResult = join_updates[0] + self.assertEqual(join_update.room_id, room_id) + else: + # Check that the invite receiving user has not automatically joined the room when syncing + join_updates, _ = sync_join(self, invited_user_id) + self.assertEqual(len(join_updates), 0) + + +_request_key = 0 + + +def generate_request_key() -> SyncRequestKey: + global _request_key + _request_key += 1 + return ("request_key", _request_key) + + +def sync_join( + testcase: HomeserverTestCase, + user_id: str, + since_token: Optional[StreamToken] = None, +) -> Tuple[List[JoinedSyncResult], StreamToken]: + """Perform a sync request for the given user and return the user join updates + they've received, as well as the next_batch token. + + This method assumes testcase.sync_handler points to the homeserver's sync handler. + + Args: + testcase: The testcase that is currently being run. + user_id: The ID of the user to generate a sync response for. + since_token: An optional token to indicate from at what point to sync from. + + Returns: + A tuple containing a list of join updates, and the sync response's + next_batch token. + """ + requester = create_requester(user_id) + sync_config = generate_sync_config(requester.user.to_string()) + sync_result = testcase.get_success( + testcase.hs.get_sync_handler().wait_for_sync_for_user( + requester, + sync_config, + SyncVersion.SYNC_V2, + generate_request_key(), + since_token, + ) + ) + + return sync_result.joined, sync_result.next_batch + + +class InviteAutoAccepterInternalTestCase(TestCase): + """ + Test cases which exercise the internals of the InviteAutoAccepter. + """ + + def setUp(self) -> None: + self.module = create_module() + self.user_id = "@peter:test" + self.invitee = "@lesley:test" + self.remote_invitee = "@thomas:remote" + + # We know our module API is a mock, but mypy doesn't. + self.mocked_update_membership: Mock = self.module._api.update_room_membership # type: ignore[assignment] + + async def test_accept_invite_with_failures(self) -> None: + """Tests that receiving an invite for a local user makes the module attempt to + make the invitee join the room. This test verifies that it works if the call to + update membership returns exceptions before successfully completing and returning an event. + """ + invite = MockEvent( + sender="@inviter:test", + state_key="@invitee:test", + type="m.room.member", + content={"membership": "invite"}, + ) + + join_event = MockEvent( + sender="someone", + state_key="someone", + type="m.room.member", + content={"membership": "join"}, + ) + # the first two calls raise an exception while the third call is successful + self.mocked_update_membership.side_effect = [ + SynapseError(HTTPStatus.FORBIDDEN, "Forbidden"), + SynapseError(HTTPStatus.FORBIDDEN, "Forbidden"), + make_awaitable(join_event), + ] + + # Stop mypy from complaining that we give on_new_event a MockEvent rather than an + # EventBase. + await self.module.on_new_event(event=invite) # type: ignore[arg-type] + + await self.retry_assertions( + self.mocked_update_membership, + 3, + sender=invite.state_key, + target=invite.state_key, + room_id=invite.room_id, + new_membership="join", + ) + + async def test_accept_invite_failures(self) -> None: + """Tests that receiving an invite for a local user makes the module attempt to + make the invitee join the room. This test verifies that if the update_membership call + fails consistently, _retry_make_join will break the loop after the set number of retries and + execution will continue. + """ + invite = MockEvent( + sender=self.user_id, + state_key=self.invitee, + type="m.room.member", + content={"membership": "invite"}, + ) + self.mocked_update_membership.side_effect = SynapseError( + HTTPStatus.FORBIDDEN, "Forbidden" + ) + + # Stop mypy from complaining that we give on_new_event a MockEvent rather than an + # EventBase. + await self.module.on_new_event(event=invite) # type: ignore[arg-type] + + await self.retry_assertions( + self.mocked_update_membership, + 5, + sender=invite.state_key, + target=invite.state_key, + room_id=invite.room_id, + new_membership="join", + ) + + async def test_not_state(self) -> None: + """Tests that receiving an invite that's not a state event does nothing.""" + invite = MockEvent( + sender=self.user_id, type="m.room.member", content={"membership": "invite"} + ) + + # Stop mypy from complaining that we give on_new_event a MockEvent rather than an + # EventBase. + await self.module.on_new_event(event=invite) # type: ignore[arg-type] + + self.mocked_update_membership.assert_not_called() + + async def test_not_invite(self) -> None: + """Tests that receiving a membership update that's not an invite does nothing.""" + invite = MockEvent( + sender=self.user_id, + state_key=self.user_id, + type="m.room.member", + content={"membership": "join"}, + ) + + # Stop mypy from complaining that we give on_new_event a MockEvent rather than an + # EventBase. + await self.module.on_new_event(event=invite) # type: ignore[arg-type] + + self.mocked_update_membership.assert_not_called() + + async def test_not_membership(self) -> None: + """Tests that receiving a state event that's not a membership update does + nothing. + """ + invite = MockEvent( + sender=self.user_id, + state_key=self.user_id, + type="org.matrix.test", + content={"foo": "bar"}, + ) + + # Stop mypy from complaining that we give on_new_event a MockEvent rather than an + # EventBase. + await self.module.on_new_event(event=invite) # type: ignore[arg-type] + + self.mocked_update_membership.assert_not_called() + + def test_config_parse(self) -> None: + """Tests that a correct configuration parses.""" + config = { + "auto_accept_invites": { + "enabled": True, + "only_for_direct_messages": True, + "only_from_local_users": True, + } + } + parsed_config = AutoAcceptInvitesConfig() + parsed_config.read_config(config) + + self.assertTrue(parsed_config.enabled) + self.assertTrue(parsed_config.accept_invites_only_for_direct_messages) + self.assertTrue(parsed_config.accept_invites_only_from_local_users) + + def test_runs_on_only_one_worker(self) -> None: + """ + Tests that the module only runs on the specified worker. + """ + # By default, we run on the main process... + main_module = create_module( + config_override={"auto_accept_invites": {"enabled": True}}, worker_name=None + ) + cast( + Mock, main_module._api.register_third_party_rules_callbacks + ).assert_called_once() + + # ...and not on other workers (like synchrotrons)... + sync_module = create_module(worker_name="synchrotron42") + cast( + Mock, sync_module._api.register_third_party_rules_callbacks + ).assert_not_called() + + # ...unless we configured them to be the designated worker. + specified_module = create_module( + config_override={ + "auto_accept_invites": { + "enabled": True, + "worker_to_run_on": "account_data1", + } + }, + worker_name="account_data1", + ) + cast( + Mock, specified_module._api.register_third_party_rules_callbacks + ).assert_called_once() + + async def retry_assertions( + self, mock: Mock, call_count: int, **kwargs: Any + ) -> None: + """ + This is a hacky way to ensure that the assertions are not called before the other coroutine + has a chance to call `update_room_membership`. It catches the exception caused by a failure, + and sleeps the thread before retrying, up until 5 tries. + + Args: + call_count: the number of times the mock should have been called + mock: the mocked function we want to assert on + kwargs: keyword arguments to assert that the mock was called with + """ + + i = 0 + while i < 5: + try: + # Check that the mocked method is called the expected amount of times and with the right + # arguments to attempt to make the user join the room. + mock.assert_called_with(**kwargs) + self.assertEqual(call_count, mock.call_count) + break + except AssertionError as e: + i += 1 + if i == 5: + # we've used up the tries, force the test to fail as we've already caught the exception + self.fail(e) + await asyncio.sleep(1) + + +@attr.s(auto_attribs=True) +class MockEvent: + """Mocks an event. Only exposes properties the module uses.""" + + sender: str + type: str + content: Dict[str, Any] + room_id: str = "!someroom" + state_key: Optional[str] = None + + def is_state(self) -> bool: + """Checks if the event is a state event by checking if it has a state key.""" + return self.state_key is not None + + @property + def membership(self) -> str: + """Extracts the membership from the event. Should only be called on an event + that's a membership event, and will raise a KeyError otherwise. + """ + membership: str = self.content["membership"] + return membership + + +T = TypeVar("T") +TV = TypeVar("TV") + + +async def make_awaitable(value: T) -> T: + return value + + +def make_multiple_awaitable(result: TV) -> Awaitable[TV]: + """ + Makes an awaitable, suitable for mocking an `async` function. + This uses Futures as they can be awaited multiple times so can be returned + to multiple callers. + """ + future: Future[TV] = Future() + future.set_result(result) + return future + + +def create_module( + config_override: Optional[Dict[str, Any]] = None, worker_name: Optional[str] = None +) -> InviteAutoAccepter: + # Create a mock based on the ModuleApi spec, but override some mocked functions + # because some capabilities are needed for running the tests. + module_api = Mock(spec=ModuleApi) + module_api.is_mine.side_effect = lambda a: a.split(":")[1] == "test" + module_api.worker_name = worker_name + module_api.sleep.return_value = make_multiple_awaitable(None) + + if config_override is None: + config_override = {} + + config = AutoAcceptInvitesConfig() + config.read_config(config_override) + + return InviteAutoAccepter(config, module_api) diff --git a/tests/events/test_presence_router.py b/tests/events/test_presence_router.py index e51cdf01ab..e48983ddfe 100644 --- a/tests/events/test_presence_router.py +++ b/tests/events/test_presence_router.py @@ -36,7 +36,7 @@ from synapse.server import HomeServer from synapse.types import JsonDict, StreamToken, create_requester from synapse.util import Clock -from tests.handlers.test_sync import generate_sync_config +from tests.handlers.test_sync import SyncRequestKey, SyncVersion, generate_sync_config from tests.unittest import ( FederatingHomeserverTestCase, HomeserverTestCase, @@ -498,6 +498,15 @@ def send_presence_update( return channel.json_body +_request_key = 0 + + +def generate_request_key() -> SyncRequestKey: + global _request_key + _request_key += 1 + return ("request_key", _request_key) + + def sync_presence( testcase: HomeserverTestCase, user_id: str, @@ -521,7 +530,11 @@ def sync_presence( sync_config = generate_sync_config(requester.user.to_string()) sync_result = testcase.get_success( testcase.hs.get_sync_handler().wait_for_sync_for_user( - requester, sync_config, since_token + requester, + sync_config, + SyncVersion.SYNC_V2, + generate_request_key(), + since_token, ) ) diff --git a/tests/events/test_utils.py b/tests/events/test_utils.py index d5ac66a6ed..30f8787758 100644 --- a/tests/events/test_utils.py +++ b/tests/events/test_utils.py @@ -625,6 +625,8 @@ class CloneEventTestCase(stdlib_unittest.TestCase): ) original.internal_metadata.stream_ordering = 1234 self.assertEqual(original.internal_metadata.stream_ordering, 1234) + original.internal_metadata.instance_name = "worker1" + self.assertEqual(original.internal_metadata.instance_name, "worker1") cloned = clone_event(original) cloned.unsigned["b"] = 3 @@ -632,6 +634,7 @@ class CloneEventTestCase(stdlib_unittest.TestCase): self.assertEqual(original.unsigned, {"a": 1, "b": 2}) self.assertEqual(cloned.unsigned, {"a": 1, "b": 3}) self.assertEqual(cloned.internal_metadata.stream_ordering, 1234) + self.assertEqual(cloned.internal_metadata.instance_name, "worker1") self.assertEqual(cloned.internal_metadata.txn_id, "txn") diff --git a/tests/federation/test_federation_media.py b/tests/federation/test_federation_media.py new file mode 100644 index 0000000000..2c396adbe3 --- /dev/null +++ b/tests/federation/test_federation_media.py @@ -0,0 +1,173 @@ +# +# This file is licensed under the Affero General Public License (AGPL) version 3. +# +# Copyright (C) 2024 New Vector, Ltd +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as +# published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# See the GNU Affero General Public License for more details: +# <https://www.gnu.org/licenses/agpl-3.0.html>. +# +# Originally licensed under the Apache License, Version 2.0: +# <http://www.apache.org/licenses/LICENSE-2.0>. +# +# [This file includes modifications made by New Vector Limited] +# +# +import io +import os +import shutil +import tempfile + +from twisted.test.proto_helpers import MemoryReactor + +from synapse.media.filepath import MediaFilePaths +from synapse.media.media_storage import MediaStorage +from synapse.media.storage_provider import ( + FileStorageProviderBackend, + StorageProviderWrapper, +) +from synapse.server import HomeServer +from synapse.types import UserID +from synapse.util import Clock + +from tests import unittest +from tests.test_utils import SMALL_PNG +from tests.unittest import override_config + + +class FederationUnstableMediaDownloadsTest(unittest.FederatingHomeserverTestCase): + + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: + super().prepare(reactor, clock, hs) + self.test_dir = tempfile.mkdtemp(prefix="synapse-tests-") + self.addCleanup(shutil.rmtree, self.test_dir) + self.primary_base_path = os.path.join(self.test_dir, "primary") + self.secondary_base_path = os.path.join(self.test_dir, "secondary") + + hs.config.media.media_store_path = self.primary_base_path + + storage_providers = [ + StorageProviderWrapper( + FileStorageProviderBackend(hs, self.secondary_base_path), + store_local=True, + store_remote=False, + store_synchronous=True, + ) + ] + + self.filepaths = MediaFilePaths(self.primary_base_path) + self.media_storage = MediaStorage( + hs, self.primary_base_path, self.filepaths, storage_providers + ) + self.media_repo = hs.get_media_repository() + + @override_config( + {"experimental_features": {"msc3916_authenticated_media_enabled": True}} + ) + def test_file_download(self) -> None: + content = io.BytesIO(b"file_to_stream") + content_uri = self.get_success( + self.media_repo.create_content( + "text/plain", + "test_upload", + content, + 46, + UserID.from_string("@user_id:whatever.org"), + ) + ) + # test with a text file + channel = self.make_signed_federation_request( + "GET", + f"/_matrix/federation/unstable/org.matrix.msc3916/media/download/{content_uri.media_id}", + ) + self.pump() + self.assertEqual(200, channel.code) + + content_type = channel.headers.getRawHeaders("content-type") + assert content_type is not None + assert "multipart/mixed" in content_type[0] + assert "boundary" in content_type[0] + + # extract boundary + boundary = content_type[0].split("boundary=")[1] + # split on boundary and check that json field and expected value exist + stripped = channel.text_body.split("\r\n" + "--" + boundary) + # TODO: the json object expected will change once MSC3911 is implemented, currently + # {} is returned for all requests as a placeholder (per MSC3196) + found_json = any( + "\r\nContent-Type: application/json\r\n\r\n{}" in field + for field in stripped + ) + self.assertTrue(found_json) + + # check that the text file and expected value exist + found_file = any( + "\r\nContent-Type: text/plain\r\n\r\nfile_to_stream" in field + for field in stripped + ) + self.assertTrue(found_file) + + content = io.BytesIO(SMALL_PNG) + content_uri = self.get_success( + self.media_repo.create_content( + "image/png", + "test_png_upload", + content, + 67, + UserID.from_string("@user_id:whatever.org"), + ) + ) + # test with an image file + channel = self.make_signed_federation_request( + "GET", + f"/_matrix/federation/unstable/org.matrix.msc3916/media/download/{content_uri.media_id}", + ) + self.pump() + self.assertEqual(200, channel.code) + + content_type = channel.headers.getRawHeaders("content-type") + assert content_type is not None + assert "multipart/mixed" in content_type[0] + assert "boundary" in content_type[0] + + # extract boundary + boundary = content_type[0].split("boundary=")[1] + # split on boundary and check that json field and expected value exist + body = channel.result.get("body") + assert body is not None + stripped_bytes = body.split(b"\r\n" + b"--" + boundary.encode("utf-8")) + found_json = any( + b"\r\nContent-Type: application/json\r\n\r\n{}" in field + for field in stripped_bytes + ) + self.assertTrue(found_json) + + # check that the png file exists and matches what was uploaded + found_file = any(SMALL_PNG in field for field in stripped_bytes) + self.assertTrue(found_file) + + @override_config( + {"experimental_features": {"msc3916_authenticated_media_enabled": False}} + ) + def test_disable_config(self) -> None: + content = io.BytesIO(b"file_to_stream") + content_uri = self.get_success( + self.media_repo.create_content( + "text/plain", + "test_upload", + content, + 46, + UserID.from_string("@user_id:whatever.org"), + ) + ) + channel = self.make_signed_federation_request( + "GET", + f"/_matrix/federation/unstable/org.matrix.msc3916/media/download/{content_uri.media_id}", + ) + self.pump() + self.assertEqual(404, channel.code) + self.assertEqual(channel.json_body.get("errcode"), "M_UNRECOGNIZED") diff --git a/tests/handlers/test_federation.py b/tests/handlers/test_federation.py index b819b60c5d..3fe5b0a1b4 100644 --- a/tests/handlers/test_federation.py +++ b/tests/handlers/test_federation.py @@ -483,6 +483,7 @@ class FederationTestCase(unittest.FederatingHomeserverTestCase): event.room_version, ), exc=LimitExceededError, + by=0.5, ) def _build_and_send_join_event( diff --git a/tests/handlers/test_oauth_delegation.py b/tests/handlers/test_oauth_delegation.py index 9387d07de8..036c539db2 100644 --- a/tests/handlers/test_oauth_delegation.py +++ b/tests/handlers/test_oauth_delegation.py @@ -541,6 +541,8 @@ class MSC3861OAuthDelegation(HomeserverTestCase): self.assertEqual(channel.code, 200, channel.json_body) + # Try uploading *different* keys; it should cause a 501 error. + keys_upload_body = self.make_device_keys(USER_ID, DEVICE) channel = self.make_request( "POST", "/_matrix/client/v3/keys/device_signing/upload", diff --git a/tests/handlers/test_room_member.py b/tests/handlers/test_room_member.py index 3e28117e2c..213a66ed1a 100644 --- a/tests/handlers/test_room_member.py +++ b/tests/handlers/test_room_member.py @@ -70,6 +70,7 @@ class TestJoinsLimitedByPerRoomRateLimiter(FederatingHomeserverTestCase): action=Membership.JOIN, ), LimitExceededError, + by=0.5, ) @override_config({"rc_joins_per_room": {"per_second": 0, "burst_count": 2}}) @@ -206,6 +207,7 @@ class TestJoinsLimitedByPerRoomRateLimiter(FederatingHomeserverTestCase): remote_room_hosts=[self.OTHER_SERVER_NAME], ), LimitExceededError, + by=0.5, ) # TODO: test that remote joins to a room are rate limited. @@ -273,6 +275,7 @@ class TestReplicatedJoinsLimitedByPerRoomRateLimiter(BaseMultiWorkerStreamTestCa action=Membership.JOIN, ), LimitExceededError, + by=0.5, ) # Try to join as Chris on the original worker. Should get denied because Alice @@ -285,6 +288,7 @@ class TestReplicatedJoinsLimitedByPerRoomRateLimiter(BaseMultiWorkerStreamTestCa action=Membership.JOIN, ), LimitExceededError, + by=0.5, ) @@ -403,3 +407,24 @@ class RoomMemberMasterHandlerTestCase(HomeserverTestCase): self.assertFalse( self.get_success(self.store.did_forget(self.alice, self.room_id)) ) + + def test_deduplicate_joins(self) -> None: + """ + Test that calling /join multiple times does not store a new state group. + """ + + self.helper.join(self.room_id, user=self.bob, tok=self.bob_token) + + sql = "SELECT COUNT(*) FROM state_groups WHERE room_id = ?" + rows = self.get_success( + self.store.db_pool.execute("test_deduplicate_joins", sql, self.room_id) + ) + initial_count = rows[0][0] + + self.helper.join(self.room_id, user=self.bob, tok=self.bob_token) + rows = self.get_success( + self.store.db_pool.execute("test_deduplicate_joins", sql, self.room_id) + ) + new_count = rows[0][0] + + self.assertEqual(initial_count, new_count) diff --git a/tests/handlers/test_sliding_sync.py b/tests/handlers/test_sliding_sync.py new file mode 100644 index 0000000000..8dd4521b18 --- /dev/null +++ b/tests/handlers/test_sliding_sync.py @@ -0,0 +1,1520 @@ +# +# This file is licensed under the Affero General Public License (AGPL) version 3. +# +# Copyright (C) 2024 New Vector, Ltd +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as +# published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# See the GNU Affero General Public License for more details: +# <https://www.gnu.org/licenses/agpl-3.0.html>. +# +# Originally licensed under the Apache License, Version 2.0: +# <http://www.apache.org/licenses/LICENSE-2.0>. +# +# [This file includes modifications made by New Vector Limited] +# +# +import logging +from unittest.mock import patch + +from parameterized import parameterized + +from twisted.test.proto_helpers import MemoryReactor + +from synapse.api.constants import AccountDataTypes, EventTypes, JoinRules, Membership +from synapse.api.room_versions import RoomVersions +from synapse.handlers.sliding_sync import SlidingSyncConfig +from synapse.rest import admin +from synapse.rest.client import knock, login, room +from synapse.server import HomeServer +from synapse.storage.util.id_generators import MultiWriterIdGenerator +from synapse.types import JsonDict, UserID +from synapse.util import Clock + +from tests.replication._base import BaseMultiWorkerStreamTestCase +from tests.unittest import HomeserverTestCase + +logger = logging.getLogger(__name__) + + +class GetSyncRoomIdsForUserTestCase(HomeserverTestCase): + """ + Tests Sliding Sync handler `get_sync_room_ids_for_user()` to make sure it returns + the correct list of rooms IDs. + """ + + servlets = [ + admin.register_servlets, + knock.register_servlets, + login.register_servlets, + room.register_servlets, + ] + + def default_config(self) -> JsonDict: + config = super().default_config() + # Enable sliding sync + config["experimental_features"] = {"msc3575_enabled": True} + return config + + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: + self.sliding_sync_handler = self.hs.get_sliding_sync_handler() + self.store = self.hs.get_datastores().main + self.event_sources = hs.get_event_sources() + + def test_no_rooms(self) -> None: + """ + Test when the user has never joined any rooms before + """ + user1_id = self.register_user("user1", "pass") + # user1_tok = self.login(user1_id, "pass") + + now_token = self.event_sources.get_current_token() + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=now_token, + to_token=now_token, + ) + ) + + self.assertEqual(room_id_results.keys(), set()) + + def test_get_newly_joined_room(self) -> None: + """ + Test that rooms that the user has newly_joined show up. newly_joined is when you + join after the `from_token` and <= `to_token`. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + + before_room_token = self.event_sources.get_current_token() + + room_id = self.helper.create_room_as(user1_id, tok=user1_tok, is_public=True) + + after_room_token = self.event_sources.get_current_token() + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=before_room_token, + to_token=after_room_token, + ) + ) + + self.assertEqual(room_id_results.keys(), {room_id}) + + def test_get_already_joined_room(self) -> None: + """ + Test that rooms that the user is already joined show up. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + + room_id = self.helper.create_room_as(user1_id, tok=user1_tok, is_public=True) + + after_room_token = self.event_sources.get_current_token() + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=after_room_token, + to_token=after_room_token, + ) + ) + + self.assertEqual(room_id_results.keys(), {room_id}) + + def test_get_invited_banned_knocked_room(self) -> None: + """ + Test that rooms that the user is invited to, banned from, and knocked on show + up. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + before_room_token = self.event_sources.get_current_token() + + # Setup the invited room (user2 invites user1 to the room) + invited_room_id = self.helper.create_room_as(user2_id, tok=user2_tok) + self.helper.invite(invited_room_id, targ=user1_id, tok=user2_tok) + + # Setup the ban room (user2 bans user1 from the room) + ban_room_id = self.helper.create_room_as( + user2_id, tok=user2_tok, is_public=True + ) + self.helper.join(ban_room_id, user1_id, tok=user1_tok) + self.helper.ban(ban_room_id, src=user2_id, targ=user1_id, tok=user2_tok) + + # Setup the knock room (user1 knocks on the room) + knock_room_id = self.helper.create_room_as( + user2_id, tok=user2_tok, room_version=RoomVersions.V7.identifier + ) + self.helper.send_state( + knock_room_id, + EventTypes.JoinRules, + {"join_rule": JoinRules.KNOCK}, + tok=user2_tok, + ) + # User1 knocks on the room + channel = self.make_request( + "POST", + "/_matrix/client/r0/knock/%s" % (knock_room_id,), + b"{}", + user1_tok, + ) + self.assertEqual(channel.code, 200, channel.result) + + after_room_token = self.event_sources.get_current_token() + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=before_room_token, + to_token=after_room_token, + ) + ) + + # Ensure that the invited, ban, and knock rooms show up + self.assertEqual( + room_id_results.keys(), + { + invited_room_id, + ban_room_id, + knock_room_id, + }, + ) + + def test_get_kicked_room(self) -> None: + """ + Test that a room that the user was kicked from still shows up. When the user + comes back to their client, they should see that they were kicked. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + # Setup the kick room (user2 kicks user1 from the room) + kick_room_id = self.helper.create_room_as( + user2_id, tok=user2_tok, is_public=True + ) + self.helper.join(kick_room_id, user1_id, tok=user1_tok) + # Kick user1 from the room + self.helper.change_membership( + room=kick_room_id, + src=user2_id, + targ=user1_id, + tok=user2_tok, + membership=Membership.LEAVE, + extra_data={ + "reason": "Bad manners", + }, + ) + + after_kick_token = self.event_sources.get_current_token() + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=after_kick_token, + to_token=after_kick_token, + ) + ) + + # The kicked room should show up + self.assertEqual(room_id_results.keys(), {kick_room_id}) + + def test_forgotten_rooms(self) -> None: + """ + Forgotten rooms do not show up even if we forget after the from/to range. + + Ideally, we would be able to track when the `/forget` happens and apply it + accordingly in the token range but the forgotten flag is only an extra bool in + the `room_memberships` table. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + # Setup a normal room that we leave. This won't show up in the sync response + # because we left it before our token but is good to check anyway. + leave_room_id = self.helper.create_room_as( + user2_id, tok=user2_tok, is_public=True + ) + self.helper.join(leave_room_id, user1_id, tok=user1_tok) + self.helper.leave(leave_room_id, user1_id, tok=user1_tok) + + # Setup the ban room (user2 bans user1 from the room) + ban_room_id = self.helper.create_room_as( + user2_id, tok=user2_tok, is_public=True + ) + self.helper.join(ban_room_id, user1_id, tok=user1_tok) + self.helper.ban(ban_room_id, src=user2_id, targ=user1_id, tok=user2_tok) + + # Setup the kick room (user2 kicks user1 from the room) + kick_room_id = self.helper.create_room_as( + user2_id, tok=user2_tok, is_public=True + ) + self.helper.join(kick_room_id, user1_id, tok=user1_tok) + # Kick user1 from the room + self.helper.change_membership( + room=kick_room_id, + src=user2_id, + targ=user1_id, + tok=user2_tok, + membership=Membership.LEAVE, + extra_data={ + "reason": "Bad manners", + }, + ) + + before_room_forgets = self.event_sources.get_current_token() + + # Forget the room after we already have our tokens. This doesn't change + # the membership event itself but will mark it internally in Synapse + channel = self.make_request( + "POST", + f"/_matrix/client/r0/rooms/{leave_room_id}/forget", + content={}, + access_token=user1_tok, + ) + self.assertEqual(channel.code, 200, channel.result) + channel = self.make_request( + "POST", + f"/_matrix/client/r0/rooms/{ban_room_id}/forget", + content={}, + access_token=user1_tok, + ) + self.assertEqual(channel.code, 200, channel.result) + channel = self.make_request( + "POST", + f"/_matrix/client/r0/rooms/{kick_room_id}/forget", + content={}, + access_token=user1_tok, + ) + self.assertEqual(channel.code, 200, channel.result) + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=before_room_forgets, + to_token=before_room_forgets, + ) + ) + + # We shouldn't see the room because it was forgotten + self.assertEqual(room_id_results.keys(), set()) + + def test_only_newly_left_rooms_show_up(self) -> None: + """ + Test that newly_left rooms still show up in the sync response but rooms that + were left before the `from_token` don't show up. See condition "2)" comments in + the `get_sync_room_ids_for_user` method. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + + # Leave before we calculate the `from_token` + room_id1 = self.helper.create_room_as(user1_id, tok=user1_tok) + self.helper.leave(room_id1, user1_id, tok=user1_tok) + + after_room1_token = self.event_sources.get_current_token() + + # Leave during the from_token/to_token range (newly_left) + room_id2 = self.helper.create_room_as(user1_id, tok=user1_tok) + self.helper.leave(room_id2, user1_id, tok=user1_tok) + + after_room2_token = self.event_sources.get_current_token() + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=after_room1_token, + to_token=after_room2_token, + ) + ) + + # Only the newly_left room should show up + self.assertEqual(room_id_results.keys(), {room_id2}) + + def test_no_joins_after_to_token(self) -> None: + """ + Rooms we join after the `to_token` should *not* show up. See condition "1b)" + comments in the `get_sync_room_ids_for_user()` method. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + + before_room1_token = self.event_sources.get_current_token() + + room_id1 = self.helper.create_room_as(user1_id, tok=user1_tok) + + after_room1_token = self.event_sources.get_current_token() + + # Room join after after our `to_token` shouldn't show up + room_id2 = self.helper.create_room_as(user1_id, tok=user1_tok) + _ = room_id2 + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=before_room1_token, + to_token=after_room1_token, + ) + ) + + self.assertEqual(room_id_results.keys(), {room_id1}) + + def test_join_during_range_and_left_room_after_to_token(self) -> None: + """ + Room still shows up if we left the room but were joined during the + from_token/to_token. See condition "1a)" comments in the + `get_sync_room_ids_for_user()` method. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + + before_room1_token = self.event_sources.get_current_token() + + room_id1 = self.helper.create_room_as(user1_id, tok=user1_tok) + + after_room1_token = self.event_sources.get_current_token() + + # Leave the room after we already have our tokens + self.helper.leave(room_id1, user1_id, tok=user1_tok) + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=before_room1_token, + to_token=after_room1_token, + ) + ) + + # We should still see the room because we were joined during the + # from_token/to_token time period. + self.assertEqual(room_id_results.keys(), {room_id1}) + + def test_join_before_range_and_left_room_after_to_token(self) -> None: + """ + Room still shows up if we left the room but were joined before the `from_token` + so it should show up. See condition "1a)" comments in the + `get_sync_room_ids_for_user()` method. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + + room_id1 = self.helper.create_room_as(user1_id, tok=user1_tok) + + after_room1_token = self.event_sources.get_current_token() + + # Leave the room after we already have our tokens + self.helper.leave(room_id1, user1_id, tok=user1_tok) + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=after_room1_token, + to_token=after_room1_token, + ) + ) + + # We should still see the room because we were joined before the `from_token` + self.assertEqual(room_id_results.keys(), {room_id1}) + + def test_kicked_before_range_and_left_after_to_token(self) -> None: + """ + Room still shows up if we left the room but were kicked before the `from_token` + so it should show up. See condition "1a)" comments in the + `get_sync_room_ids_for_user()` method. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + # Setup the kick room (user2 kicks user1 from the room) + kick_room_id = self.helper.create_room_as( + user2_id, tok=user2_tok, is_public=True + ) + self.helper.join(kick_room_id, user1_id, tok=user1_tok) + # Kick user1 from the room + self.helper.change_membership( + room=kick_room_id, + src=user2_id, + targ=user1_id, + tok=user2_tok, + membership=Membership.LEAVE, + extra_data={ + "reason": "Bad manners", + }, + ) + + after_kick_token = self.event_sources.get_current_token() + + # Leave the room after we already have our tokens + # + # We have to join before we can leave (leave -> leave isn't a valid transition + # or at least it doesn't work in Synapse, 403 forbidden) + self.helper.join(kick_room_id, user1_id, tok=user1_tok) + self.helper.leave(kick_room_id, user1_id, tok=user1_tok) + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=after_kick_token, + to_token=after_kick_token, + ) + ) + + # We shouldn't see the room because it was forgotten + self.assertEqual(room_id_results.keys(), {kick_room_id}) + + def test_newly_left_during_range_and_join_leave_after_to_token(self) -> None: + """ + Newly left room should show up. But we're also testing that joining and leaving + after the `to_token` doesn't mess with the results. See condition "2)" and "1a)" + comments in the `get_sync_room_ids_for_user()` method. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + before_room1_token = self.event_sources.get_current_token() + + # We create the room with user2 so the room isn't left with no members when we + # leave and can still re-join. + room_id1 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + # Join and leave the room during the from/to range + self.helper.join(room_id1, user1_id, tok=user1_tok) + self.helper.leave(room_id1, user1_id, tok=user1_tok) + + after_room1_token = self.event_sources.get_current_token() + + # Join and leave the room after we already have our tokens + self.helper.join(room_id1, user1_id, tok=user1_tok) + self.helper.leave(room_id1, user1_id, tok=user1_tok) + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=before_room1_token, + to_token=after_room1_token, + ) + ) + + # Room should still show up because it's newly_left during the from/to range + self.assertEqual(room_id_results.keys(), {room_id1}) + + def test_newly_left_during_range_and_join_after_to_token(self) -> None: + """ + Newly left room should show up. But we're also testing that joining after the + `to_token` doesn't mess with the results. See condition "2)" and "1b)" comments + in the `get_sync_room_ids_for_user()` method. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + before_room1_token = self.event_sources.get_current_token() + + # We create the room with user2 so the room isn't left with no members when we + # leave and can still re-join. + room_id1 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + # Join and leave the room during the from/to range + self.helper.join(room_id1, user1_id, tok=user1_tok) + self.helper.leave(room_id1, user1_id, tok=user1_tok) + + after_room1_token = self.event_sources.get_current_token() + + # Join the room after we already have our tokens + self.helper.join(room_id1, user1_id, tok=user1_tok) + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=before_room1_token, + to_token=after_room1_token, + ) + ) + + # Room should still show up because it's newly_left during the from/to range + self.assertEqual(room_id_results.keys(), {room_id1}) + + def test_no_from_token(self) -> None: + """ + Test that if we don't provide a `from_token`, we get all the rooms that we we're + joined to up to the `to_token`. + + Providing `from_token` only really has the effect that it adds `newly_left` + rooms to the response. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + # We create the room with user2 so the room isn't left with no members when we + # leave and can still re-join. + room_id1 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + room_id2 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + + # Join room1 + self.helper.join(room_id1, user1_id, tok=user1_tok) + + # Join and leave the room2 before the `to_token` + self.helper.join(room_id2, user1_id, tok=user1_tok) + self.helper.leave(room_id2, user1_id, tok=user1_tok) + + after_room1_token = self.event_sources.get_current_token() + + # Join the room2 after we already have our tokens + self.helper.join(room_id2, user1_id, tok=user1_tok) + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=None, + to_token=after_room1_token, + ) + ) + + # Only rooms we were joined to before the `to_token` should show up + self.assertEqual(room_id_results.keys(), {room_id1}) + + def test_from_token_ahead_of_to_token(self) -> None: + """ + Test when the provided `from_token` comes after the `to_token`. We should + basically expect the same result as having no `from_token`. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + # We create the room with user2 so the room isn't left with no members when we + # leave and can still re-join. + room_id1 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + room_id2 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + room_id3 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + room_id4 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + + # Join room1 before `before_room_token` + self.helper.join(room_id1, user1_id, tok=user1_tok) + + # Join and leave the room2 before `before_room_token` + self.helper.join(room_id2, user1_id, tok=user1_tok) + self.helper.leave(room_id2, user1_id, tok=user1_tok) + + # Note: These are purposely swapped. The `from_token` should come after + # the `to_token` in this test + to_token = self.event_sources.get_current_token() + + # Join room2 after `before_room_token` + self.helper.join(room_id2, user1_id, tok=user1_tok) + + # -------- + + # Join room3 after `before_room_token` + self.helper.join(room_id3, user1_id, tok=user1_tok) + + # Join and leave the room4 after `before_room_token` + self.helper.join(room_id4, user1_id, tok=user1_tok) + self.helper.leave(room_id4, user1_id, tok=user1_tok) + + # Note: These are purposely swapped. The `from_token` should come after the + # `to_token` in this test + from_token = self.event_sources.get_current_token() + + # Join the room4 after we already have our tokens + self.helper.join(room_id4, user1_id, tok=user1_tok) + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=from_token, + to_token=to_token, + ) + ) + + # Only rooms we were joined to before the `to_token` should show up + # + # There won't be any newly_left rooms because the `from_token` is ahead of the + # `to_token` and that range will give no membership changes to check. + self.assertEqual(room_id_results.keys(), {room_id1}) + + def test_leave_before_range_and_join_leave_after_to_token(self) -> None: + """ + Old left room shouldn't show up. But we're also testing that joining and leaving + after the `to_token` doesn't mess with the results. See condition "1a)" comments + in the `get_sync_room_ids_for_user()` method. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + # We create the room with user2 so the room isn't left with no members when we + # leave and can still re-join. + room_id1 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + # Join and leave the room before the from/to range + self.helper.join(room_id1, user1_id, tok=user1_tok) + self.helper.leave(room_id1, user1_id, tok=user1_tok) + + after_room1_token = self.event_sources.get_current_token() + + # Join and leave the room after we already have our tokens + self.helper.join(room_id1, user1_id, tok=user1_tok) + self.helper.leave(room_id1, user1_id, tok=user1_tok) + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=after_room1_token, + to_token=after_room1_token, + ) + ) + + # Room shouldn't show up because it was left before the `from_token` + self.assertEqual(room_id_results.keys(), set()) + + def test_leave_before_range_and_join_after_to_token(self) -> None: + """ + Old left room shouldn't show up. But we're also testing that joining after the + `to_token` doesn't mess with the results. See condition "1b)" comments in the + `get_sync_room_ids_for_user()` method. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + # We create the room with user2 so the room isn't left with no members when we + # leave and can still re-join. + room_id1 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + # Join and leave the room before the from/to range + self.helper.join(room_id1, user1_id, tok=user1_tok) + self.helper.leave(room_id1, user1_id, tok=user1_tok) + + after_room1_token = self.event_sources.get_current_token() + + # Join the room after we already have our tokens + self.helper.join(room_id1, user1_id, tok=user1_tok) + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=after_room1_token, + to_token=after_room1_token, + ) + ) + + # Room shouldn't show up because it was left before the `from_token` + self.assertEqual(room_id_results.keys(), set()) + + def test_join_leave_multiple_times_during_range_and_after_to_token( + self, + ) -> None: + """ + Join and leave multiple times shouldn't affect rooms from showing up. It just + matters that we were joined or newly_left in the from/to range. But we're also + testing that joining and leaving after the `to_token` doesn't mess with the + results. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + before_room1_token = self.event_sources.get_current_token() + + # We create the room with user2 so the room isn't left with no members when we + # leave and can still re-join. + room_id1 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + # Join, leave, join back to the room before the from/to range + self.helper.join(room_id1, user1_id, tok=user1_tok) + self.helper.leave(room_id1, user1_id, tok=user1_tok) + self.helper.join(room_id1, user1_id, tok=user1_tok) + + after_room1_token = self.event_sources.get_current_token() + + # Leave and Join the room multiple times after we already have our tokens + self.helper.leave(room_id1, user1_id, tok=user1_tok) + self.helper.join(room_id1, user1_id, tok=user1_tok) + self.helper.leave(room_id1, user1_id, tok=user1_tok) + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=before_room1_token, + to_token=after_room1_token, + ) + ) + + # Room should show up because it was newly_left and joined during the from/to range + self.assertEqual(room_id_results.keys(), {room_id1}) + + def test_join_leave_multiple_times_before_range_and_after_to_token( + self, + ) -> None: + """ + Join and leave multiple times before the from/to range shouldn't affect rooms + from showing up. It just matters that we were joined or newly_left in the + from/to range. But we're also testing that joining and leaving after the + `to_token` doesn't mess with the results. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + # We create the room with user2 so the room isn't left with no members when we + # leave and can still re-join. + room_id1 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + # Join, leave, join back to the room before the from/to range + self.helper.join(room_id1, user1_id, tok=user1_tok) + self.helper.leave(room_id1, user1_id, tok=user1_tok) + self.helper.join(room_id1, user1_id, tok=user1_tok) + + after_room1_token = self.event_sources.get_current_token() + + # Leave and Join the room multiple times after we already have our tokens + self.helper.leave(room_id1, user1_id, tok=user1_tok) + self.helper.join(room_id1, user1_id, tok=user1_tok) + self.helper.leave(room_id1, user1_id, tok=user1_tok) + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=after_room1_token, + to_token=after_room1_token, + ) + ) + + # Room should show up because we were joined before the from/to range + self.assertEqual(room_id_results.keys(), {room_id1}) + + def test_invite_before_range_and_join_leave_after_to_token( + self, + ) -> None: + """ + Make it look like we joined after the token range but we were invited before the + from/to range so the room should still show up. See condition "1a)" comments in + the `get_sync_room_ids_for_user()` method. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + # We create the room with user2 so the room isn't left with no members when we + # leave and can still re-join. + room_id1 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + + # Invited to the room before the token + self.helper.invite(room_id1, src=user2_id, targ=user1_id, tok=user2_tok) + + after_room1_token = self.event_sources.get_current_token() + + # Join and leave the room after we already have our tokens + self.helper.join(room_id1, user1_id, tok=user1_tok) + self.helper.leave(room_id1, user1_id, tok=user1_tok) + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=after_room1_token, + to_token=after_room1_token, + ) + ) + + # Room should show up because we were invited before the from/to range + self.assertEqual(room_id_results.keys(), {room_id1}) + + def test_multiple_rooms_are_not_confused( + self, + ) -> None: + """ + Test that multiple rooms are not confused as we fixup the list. This test is + spawning from a real world bug in the code where I was accidentally using + `event.room_id` in one of the fix-up loops but the `event` being referenced was + actually from a different loop. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + # We create the room with user2 so the room isn't left with no members when we + # leave and can still re-join. + room_id1 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + room_id2 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + + # Invited and left the room before the token + self.helper.invite(room_id1, src=user2_id, targ=user1_id, tok=user2_tok) + self.helper.leave(room_id1, user1_id, tok=user1_tok) + # Invited to room2 + self.helper.invite(room_id2, src=user2_id, targ=user1_id, tok=user2_tok) + + before_room3_token = self.event_sources.get_current_token() + + # Invited and left room3 during the from/to range + room_id3 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + self.helper.invite(room_id3, src=user2_id, targ=user1_id, tok=user2_tok) + self.helper.leave(room_id3, user1_id, tok=user1_tok) + + after_room3_token = self.event_sources.get_current_token() + + # Join and leave the room after we already have our tokens + self.helper.join(room_id1, user1_id, tok=user1_tok) + self.helper.leave(room_id1, user1_id, tok=user1_tok) + # Leave room2 + self.helper.leave(room_id2, user1_id, tok=user1_tok) + # Leave room3 + self.helper.leave(room_id3, user1_id, tok=user1_tok) + + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=before_room3_token, + to_token=after_room3_token, + ) + ) + + self.assertEqual( + room_id_results.keys(), + { + # `room_id1` shouldn't show up because we left before the from/to range + # + # Room should show up because we were invited before the from/to range + room_id2, + # Room should show up because it was newly_left during the from/to range + room_id3, + }, + ) + + +class GetSyncRoomIdsForUserEventShardTestCase(BaseMultiWorkerStreamTestCase): + """ + Tests Sliding Sync handler `get_sync_room_ids_for_user()` to make sure it works with + sharded event stream_writers enabled + """ + + servlets = [ + admin.register_servlets_for_client_rest_resource, + room.register_servlets, + login.register_servlets, + ] + + def default_config(self) -> dict: + config = super().default_config() + # Enable sliding sync + config["experimental_features"] = {"msc3575_enabled": True} + + # Enable shared event stream_writers + config["stream_writers"] = {"events": ["worker1", "worker2", "worker3"]} + config["instance_map"] = { + "main": {"host": "testserv", "port": 8765}, + "worker1": {"host": "testserv", "port": 1001}, + "worker2": {"host": "testserv", "port": 1002}, + "worker3": {"host": "testserv", "port": 1003}, + } + return config + + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: + self.sliding_sync_handler = self.hs.get_sliding_sync_handler() + self.store = self.hs.get_datastores().main + self.event_sources = hs.get_event_sources() + + def _create_room(self, room_id: str, user_id: str, tok: str) -> None: + """ + Create a room with a specific room_id. We use this so that that we have a + consistent room_id across test runs that hashes to the same value and will be + sharded to a known worker in the tests. + """ + + # We control the room ID generation by patching out the + # `_generate_room_id` method + with patch( + "synapse.handlers.room.RoomCreationHandler._generate_room_id" + ) as mock: + mock.side_effect = lambda: room_id + self.helper.create_room_as(user_id, tok=tok) + + def test_sharded_event_persisters(self) -> None: + """ + This test should catch bugs that would come from flawed stream position + (`stream_ordering`) comparisons or making `RoomStreamToken`'s naively. To + compare event positions properly, you need to consider both the `instance_name` + and `stream_ordering` together. + + The test creates three event persister workers and a room that is sharded to + each worker. On worker2, we make the event stream position stuck so that it lags + behind the other workers and we start getting `RoomStreamToken` that have an + `instance_map` component (i.e. q`m{min_pos}~{writer1}.{pos1}~{writer2}.{pos2}`). + + We then send some events to advance the stream positions of worker1 and worker3 + but worker2 is lagging behind because it's stuck. We are specifically testing + that `get_sync_room_ids_for_user(from_token=xxx, to_token=xxx)` should work + correctly in these adverse conditions. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + self.make_worker_hs( + "synapse.app.generic_worker", + {"worker_name": "worker1"}, + ) + + worker_hs2 = self.make_worker_hs( + "synapse.app.generic_worker", + {"worker_name": "worker2"}, + ) + + self.make_worker_hs( + "synapse.app.generic_worker", + {"worker_name": "worker3"}, + ) + + # Specially crafted room IDs that get persisted on different workers. + # + # Sharded to worker1 + room_id1 = "!fooo:test" + # Sharded to worker2 + room_id2 = "!bar:test" + # Sharded to worker3 + room_id3 = "!quux:test" + + # Create rooms on the different workers. + self._create_room(room_id1, user2_id, user2_tok) + self._create_room(room_id2, user2_id, user2_tok) + self._create_room(room_id3, user2_id, user2_tok) + join_response1 = self.helper.join(room_id1, user1_id, tok=user1_tok) + join_response2 = self.helper.join(room_id2, user1_id, tok=user1_tok) + # Leave room2 + self.helper.leave(room_id2, user1_id, tok=user1_tok) + join_response3 = self.helper.join(room_id3, user1_id, tok=user1_tok) + # Leave room3 + self.helper.leave(room_id3, user1_id, tok=user1_tok) + + # Ensure that the events were sharded to different workers. + pos1 = self.get_success( + self.store.get_position_for_event(join_response1["event_id"]) + ) + self.assertEqual(pos1.instance_name, "worker1") + pos2 = self.get_success( + self.store.get_position_for_event(join_response2["event_id"]) + ) + self.assertEqual(pos2.instance_name, "worker2") + pos3 = self.get_success( + self.store.get_position_for_event(join_response3["event_id"]) + ) + self.assertEqual(pos3.instance_name, "worker3") + + before_stuck_activity_token = self.event_sources.get_current_token() + + # We now gut wrench into the events stream `MultiWriterIdGenerator` on worker2 to + # mimic it getting stuck persisting an event. This ensures that when we send an + # event on worker1/worker3 we end up in a state where worker2 events stream + # position lags that on worker1/worker3, resulting in a RoomStreamToken with a + # non-empty `instance_map` component. + # + # Worker2's event stream position will not advance until we call `__aexit__` + # again. + worker_store2 = worker_hs2.get_datastores().main + assert isinstance(worker_store2._stream_id_gen, MultiWriterIdGenerator) + actx = worker_store2._stream_id_gen.get_next() + self.get_success(actx.__aenter__()) + + # For room_id1/worker1: leave and join the room to advance the stream position + # and generate membership changes. + self.helper.leave(room_id1, user1_id, tok=user1_tok) + self.helper.join(room_id1, user1_id, tok=user1_tok) + # For room_id2/worker2: which is currently stuck, join the room. + join_on_worker2_response = self.helper.join(room_id2, user1_id, tok=user1_tok) + # For room_id3/worker3: leave and join the room to advance the stream position + # and generate membership changes. + self.helper.leave(room_id3, user1_id, tok=user1_tok) + join_on_worker3_response = self.helper.join(room_id3, user1_id, tok=user1_tok) + + # Get a token while things are stuck after our activity + stuck_activity_token = self.event_sources.get_current_token() + # Let's make sure we're working with a token that has an `instance_map` + self.assertNotEqual(len(stuck_activity_token.room_key.instance_map), 0) + + # Just double check that the join event on worker2 (that is stuck) happened + # after the position recorded for worker2 in the token but before the max + # position in the token. This is crucial for the behavior we're trying to test. + join_on_worker2_pos = self.get_success( + self.store.get_position_for_event(join_on_worker2_response["event_id"]) + ) + # Ensure the join technially came after our token + self.assertGreater( + join_on_worker2_pos.stream, + stuck_activity_token.room_key.get_stream_pos_for_instance("worker2"), + ) + # But less than the max stream position of some other worker + self.assertLess( + join_on_worker2_pos.stream, + # max + stuck_activity_token.room_key.get_max_stream_pos(), + ) + + # Just double check that the join event on worker3 happened after the min stream + # value in the token but still within the position recorded for worker3. This is + # crucial for the behavior we're trying to test. + join_on_worker3_pos = self.get_success( + self.store.get_position_for_event(join_on_worker3_response["event_id"]) + ) + # Ensure the join came after the min but still encapsulated by the token + self.assertGreaterEqual( + join_on_worker3_pos.stream, + # min + stuck_activity_token.room_key.stream, + ) + self.assertLessEqual( + join_on_worker3_pos.stream, + stuck_activity_token.room_key.get_stream_pos_for_instance("worker3"), + ) + + # We finish the fake persisting an event we started above and advance worker2's + # event stream position (unstuck worker2). + self.get_success(actx.__aexit__(None, None, None)) + + # The function under test + room_id_results = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=before_stuck_activity_token, + to_token=stuck_activity_token, + ) + ) + + self.assertEqual( + room_id_results.keys(), + { + room_id1, + # room_id2 shouldn't show up because we left before the from/to range + # and the join event during the range happened while worker2 was stuck. + # This means that from the perspective of the master, where the + # `stuck_activity_token` is generated, the stream position for worker2 + # wasn't advanced to the join yet. Looking at the `instance_map`, the + # join technically comes after `stuck_activity_token``. + # + # room_id2, + room_id3, + }, + ) + + +class FilterRoomsTestCase(HomeserverTestCase): + """ + Tests Sliding Sync handler `filter_rooms()` to make sure it includes/excludes rooms + correctly. + """ + + servlets = [ + admin.register_servlets, + knock.register_servlets, + login.register_servlets, + room.register_servlets, + ] + + def default_config(self) -> JsonDict: + config = super().default_config() + # Enable sliding sync + config["experimental_features"] = {"msc3575_enabled": True} + return config + + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: + self.sliding_sync_handler = self.hs.get_sliding_sync_handler() + self.store = self.hs.get_datastores().main + self.event_sources = hs.get_event_sources() + + def _create_dm_room( + self, + inviter_user_id: str, + inviter_tok: str, + invitee_user_id: str, + invitee_tok: str, + ) -> str: + """ + Helper to create a DM room as the "inviter" and invite the "invitee" user to the room. The + "invitee" user also will join the room. The `m.direct` account data will be set + for both users. + """ + + # Create a room and send an invite the other user + room_id = self.helper.create_room_as( + inviter_user_id, + is_public=False, + tok=inviter_tok, + ) + self.helper.invite( + room_id, + src=inviter_user_id, + targ=invitee_user_id, + tok=inviter_tok, + extra_data={"is_direct": True}, + ) + # Person that was invited joins the room + self.helper.join(room_id, invitee_user_id, tok=invitee_tok) + + # Mimic the client setting the room as a direct message in the global account + # data + self.get_success( + self.store.add_account_data_for_user( + invitee_user_id, + AccountDataTypes.DIRECT, + {inviter_user_id: [room_id]}, + ) + ) + self.get_success( + self.store.add_account_data_for_user( + inviter_user_id, + AccountDataTypes.DIRECT, + {invitee_user_id: [room_id]}, + ) + ) + + return room_id + + def test_filter_dm_rooms(self) -> None: + """ + Test `filter.is_dm` for DM rooms + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + # Create a normal room + room_id = self.helper.create_room_as(user1_id, tok=user1_tok) + + # Create a DM room + dm_room_id = self._create_dm_room( + inviter_user_id=user1_id, + inviter_tok=user1_tok, + invitee_user_id=user2_id, + invitee_tok=user2_tok, + ) + + after_rooms_token = self.event_sources.get_current_token() + + # Get the rooms the user should be syncing with + sync_room_map = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=None, + to_token=after_rooms_token, + ) + ) + + # Try with `is_dm=True` + truthy_filtered_room_map = self.get_success( + self.sliding_sync_handler.filter_rooms( + UserID.from_string(user1_id), + sync_room_map, + SlidingSyncConfig.SlidingSyncList.Filters( + is_dm=True, + ), + after_rooms_token, + ) + ) + + self.assertEqual(truthy_filtered_room_map.keys(), {dm_room_id}) + + # Try with `is_dm=False` + falsy_filtered_room_map = self.get_success( + self.sliding_sync_handler.filter_rooms( + UserID.from_string(user1_id), + sync_room_map, + SlidingSyncConfig.SlidingSyncList.Filters( + is_dm=False, + ), + after_rooms_token, + ) + ) + + self.assertEqual(falsy_filtered_room_map.keys(), {room_id}) + + def test_filter_encrypted_rooms(self) -> None: + """ + Test `filter.is_encrypted` for encrypted rooms + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + + # Create a normal room + room_id = self.helper.create_room_as(user1_id, tok=user1_tok) + + # Create an encrypted room + encrypted_room_id = self.helper.create_room_as(user1_id, tok=user1_tok) + self.helper.send_state( + encrypted_room_id, + EventTypes.RoomEncryption, + {"algorithm": "m.megolm.v1.aes-sha2"}, + tok=user1_tok, + ) + + after_rooms_token = self.event_sources.get_current_token() + + # Get the rooms the user should be syncing with + sync_room_map = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=None, + to_token=after_rooms_token, + ) + ) + + # Try with `is_encrypted=True` + truthy_filtered_room_map = self.get_success( + self.sliding_sync_handler.filter_rooms( + UserID.from_string(user1_id), + sync_room_map, + SlidingSyncConfig.SlidingSyncList.Filters( + is_encrypted=True, + ), + after_rooms_token, + ) + ) + + self.assertEqual(truthy_filtered_room_map.keys(), {encrypted_room_id}) + + # Try with `is_encrypted=False` + falsy_filtered_room_map = self.get_success( + self.sliding_sync_handler.filter_rooms( + UserID.from_string(user1_id), + sync_room_map, + SlidingSyncConfig.SlidingSyncList.Filters( + is_encrypted=False, + ), + after_rooms_token, + ) + ) + + self.assertEqual(falsy_filtered_room_map.keys(), {room_id}) + + def test_filter_invite_rooms(self) -> None: + """ + Test `filter.is_invite` for rooms that the user has been invited to + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + # Create a normal room + room_id = self.helper.create_room_as(user2_id, tok=user2_tok) + self.helper.join(room_id, user1_id, tok=user1_tok) + + # Create a room that user1 is invited to + invite_room_id = self.helper.create_room_as(user2_id, tok=user2_tok) + self.helper.invite(invite_room_id, src=user2_id, targ=user1_id, tok=user2_tok) + + after_rooms_token = self.event_sources.get_current_token() + + # Get the rooms the user should be syncing with + sync_room_map = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=None, + to_token=after_rooms_token, + ) + ) + + # Try with `is_invite=True` + truthy_filtered_room_map = self.get_success( + self.sliding_sync_handler.filter_rooms( + UserID.from_string(user1_id), + sync_room_map, + SlidingSyncConfig.SlidingSyncList.Filters( + is_invite=True, + ), + after_rooms_token, + ) + ) + + self.assertEqual(truthy_filtered_room_map.keys(), {invite_room_id}) + + # Try with `is_invite=False` + falsy_filtered_room_map = self.get_success( + self.sliding_sync_handler.filter_rooms( + UserID.from_string(user1_id), + sync_room_map, + SlidingSyncConfig.SlidingSyncList.Filters( + is_invite=False, + ), + after_rooms_token, + ) + ) + + self.assertEqual(falsy_filtered_room_map.keys(), {room_id}) + + +class SortRoomsTestCase(HomeserverTestCase): + """ + Tests Sliding Sync handler `sort_rooms()` to make sure it sorts/orders rooms + correctly. + """ + + servlets = [ + admin.register_servlets, + knock.register_servlets, + login.register_servlets, + room.register_servlets, + ] + + def default_config(self) -> JsonDict: + config = super().default_config() + # Enable sliding sync + config["experimental_features"] = {"msc3575_enabled": True} + return config + + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: + self.sliding_sync_handler = self.hs.get_sliding_sync_handler() + self.store = self.hs.get_datastores().main + self.event_sources = hs.get_event_sources() + + def test_sort_activity_basic(self) -> None: + """ + Rooms with newer activity are sorted first. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + + room_id1 = self.helper.create_room_as( + user1_id, + tok=user1_tok, + ) + room_id2 = self.helper.create_room_as( + user1_id, + tok=user1_tok, + ) + + after_rooms_token = self.event_sources.get_current_token() + + # Get the rooms the user should be syncing with + sync_room_map = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=None, + to_token=after_rooms_token, + ) + ) + + # Sort the rooms (what we're testing) + sorted_room_info = self.get_success( + self.sliding_sync_handler.sort_rooms( + sync_room_map=sync_room_map, + to_token=after_rooms_token, + ) + ) + + self.assertEqual( + [room_id for room_id, _ in sorted_room_info], + [room_id2, room_id1], + ) + + @parameterized.expand( + [ + (Membership.LEAVE,), + (Membership.INVITE,), + (Membership.KNOCK,), + (Membership.BAN,), + ] + ) + def test_activity_after_xxx(self, room1_membership: str) -> None: + """ + When someone has left/been invited/knocked/been banned from a room, they + shouldn't take anything into account after that membership event. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + before_rooms_token = self.event_sources.get_current_token() + + # Create the rooms as user2 so we can have user1 with a clean slate to work from + # and join in whatever order we need for the tests. + room_id1 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + # If we're testing knocks, set the room to knock + if room1_membership == Membership.KNOCK: + self.helper.send_state( + room_id1, + EventTypes.JoinRules, + {"join_rule": JoinRules.KNOCK}, + tok=user2_tok, + ) + room_id2 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + room_id3 = self.helper.create_room_as(user2_id, tok=user2_tok, is_public=True) + + # Here is the activity with user1 that will determine the sort of the rooms + # (room2, room1, room3) + self.helper.join(room_id3, user1_id, tok=user1_tok) + if room1_membership == Membership.LEAVE: + self.helper.join(room_id1, user1_id, tok=user1_tok) + self.helper.leave(room_id1, user1_id, tok=user1_tok) + elif room1_membership == Membership.INVITE: + self.helper.invite(room_id1, src=user2_id, targ=user1_id, tok=user2_tok) + elif room1_membership == Membership.KNOCK: + self.helper.knock(room_id1, user1_id, tok=user1_tok) + elif room1_membership == Membership.BAN: + self.helper.ban(room_id1, src=user2_id, targ=user1_id, tok=user2_tok) + self.helper.join(room_id2, user1_id, tok=user1_tok) + + # Activity before the token but the user is only been xxx to this room so it + # shouldn't be taken into account + self.helper.send(room_id1, "activity in room1", tok=user2_tok) + + after_rooms_token = self.event_sources.get_current_token() + + # Activity after the token. Just make it in a different order than what we + # expect to make sure we're not taking the activity after the token into + # account. + self.helper.send(room_id1, "activity in room1", tok=user2_tok) + self.helper.send(room_id2, "activity in room2", tok=user2_tok) + self.helper.send(room_id3, "activity in room3", tok=user2_tok) + + # Get the rooms the user should be syncing with + sync_room_map = self.get_success( + self.sliding_sync_handler.get_sync_room_ids_for_user( + UserID.from_string(user1_id), + from_token=before_rooms_token, + to_token=after_rooms_token, + ) + ) + + # Sort the rooms (what we're testing) + sorted_room_info = self.get_success( + self.sliding_sync_handler.sort_rooms( + sync_room_map=sync_room_map, + to_token=after_rooms_token, + ) + ) + + self.assertEqual( + [room_id for room_id, _ in sorted_room_info], + [room_id2, room_id1, room_id3], + "Corresponding map to disambiguate the opaque room IDs: " + + str( + { + "room_id1": room_id1, + "room_id2": room_id2, + "room_id3": room_id3, + } + ), + ) diff --git a/tests/handlers/test_sync.py b/tests/handlers/test_sync.py index 2780d29cad..02371ce724 100644 --- a/tests/handlers/test_sync.py +++ b/tests/handlers/test_sync.py @@ -24,14 +24,14 @@ from parameterized import parameterized from twisted.test.proto_helpers import MemoryReactor -from synapse.api.constants import EventTypes, JoinRules +from synapse.api.constants import AccountDataTypes, EventTypes, JoinRules from synapse.api.errors import Codes, ResourceLimitError from synapse.api.filtering import FilterCollection, Filtering from synapse.api.room_versions import RoomVersion, RoomVersions from synapse.events import EventBase from synapse.events.snapshot import EventContext from synapse.federation.federation_base import event_from_pdu_json -from synapse.handlers.sync import SyncConfig, SyncResult +from synapse.handlers.sync import SyncConfig, SyncRequestKey, SyncResult, SyncVersion from synapse.rest import admin from synapse.rest.client import knock, login, room from synapse.server import HomeServer @@ -41,6 +41,14 @@ from synapse.util import Clock import tests.unittest import tests.utils +_request_key = 0 + + +def generate_request_key() -> SyncRequestKey: + global _request_key + _request_key += 1 + return ("request_key", _request_key) + class SyncTestCase(tests.unittest.HomeserverTestCase): """Tests Sync Handler.""" @@ -73,13 +81,23 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): # Check that the happy case does not throw errors self.get_success(self.store.upsert_monthly_active_user(user_id1)) self.get_success( - self.sync_handler.wait_for_sync_for_user(requester, sync_config) + self.sync_handler.wait_for_sync_for_user( + requester, + sync_config, + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), + ) ) # Test that global lock works self.auth_blocking._hs_disabled = True e = self.get_failure( - self.sync_handler.wait_for_sync_for_user(requester, sync_config), + self.sync_handler.wait_for_sync_for_user( + requester, + sync_config, + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), + ), ResourceLimitError, ) self.assertEqual(e.value.errcode, Codes.RESOURCE_LIMIT_EXCEEDED) @@ -90,7 +108,12 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): requester = create_requester(user_id2) e = self.get_failure( - self.sync_handler.wait_for_sync_for_user(requester, sync_config), + self.sync_handler.wait_for_sync_for_user( + requester, + sync_config, + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), + ), ResourceLimitError, ) self.assertEqual(e.value.errcode, Codes.RESOURCE_LIMIT_EXCEEDED) @@ -109,7 +132,10 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): requester = create_requester(user) initial_result = self.get_success( self.sync_handler.wait_for_sync_for_user( - requester, sync_config=generate_sync_config(user, device_id="dev") + requester, + sync_config=generate_sync_config(user, device_id="dev"), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), ) ) @@ -140,7 +166,10 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): # The rooms should appear in the sync response. result = self.get_success( self.sync_handler.wait_for_sync_for_user( - requester, sync_config=generate_sync_config(user) + requester, + sync_config=generate_sync_config(user), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), ) ) self.assertIn(joined_room, [r.room_id for r in result.joined]) @@ -152,6 +181,8 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): self.sync_handler.wait_for_sync_for_user( requester, sync_config=generate_sync_config(user, device_id="dev"), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), since_token=initial_result.next_batch, ) ) @@ -180,7 +211,10 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): # Get a new request key. result = self.get_success( self.sync_handler.wait_for_sync_for_user( - requester, sync_config=generate_sync_config(user) + requester, + sync_config=generate_sync_config(user), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), ) ) self.assertNotIn(joined_room, [r.room_id for r in result.joined]) @@ -192,6 +226,8 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): self.sync_handler.wait_for_sync_for_user( requester, sync_config=generate_sync_config(user, device_id="dev"), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), since_token=initial_result.next_batch, ) ) @@ -231,7 +267,10 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): # Do a sync as Alice to get the latest event in the room. alice_sync_result: SyncResult = self.get_success( self.sync_handler.wait_for_sync_for_user( - create_requester(owner), generate_sync_config(owner) + create_requester(owner), + generate_sync_config(owner), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), ) ) self.assertEqual(len(alice_sync_result.joined), 1) @@ -251,7 +290,12 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): eve_requester = create_requester(eve) eve_sync_config = generate_sync_config(eve) eve_sync_after_ban: SyncResult = self.get_success( - self.sync_handler.wait_for_sync_for_user(eve_requester, eve_sync_config) + self.sync_handler.wait_for_sync_for_user( + eve_requester, + eve_sync_config, + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), + ) ) # Sanity check this sync result. We shouldn't be joined to the room. @@ -268,6 +312,8 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): self.sync_handler.wait_for_sync_for_user( eve_requester, eve_sync_config, + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), since_token=eve_sync_after_ban.next_batch, ) ) @@ -279,6 +325,8 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): self.sync_handler.wait_for_sync_for_user( eve_requester, eve_sync_config, + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), since_token=None, ) ) @@ -310,7 +358,10 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): # Do an initial sync as Alice to get a known starting point. initial_sync_result = self.get_success( self.sync_handler.wait_for_sync_for_user( - alice_requester, generate_sync_config(alice) + alice_requester, + generate_sync_config(alice), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), ) ) last_room_creation_event_id = ( @@ -338,6 +389,8 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): self.hs, {"room": {"timeline": {"limit": 2}}} ), ), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), since_token=initial_sync_result.next_batch, ) ) @@ -380,7 +433,10 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): # Do an initial sync as Alice to get a known starting point. initial_sync_result = self.get_success( self.sync_handler.wait_for_sync_for_user( - alice_requester, generate_sync_config(alice) + alice_requester, + generate_sync_config(alice), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), ) ) last_room_creation_event_id = ( @@ -418,6 +474,8 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): }, ), ), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), since_token=initial_sync_result.next_batch, ) ) @@ -461,7 +519,10 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): # Do an initial sync as Alice to get a known starting point. initial_sync_result = self.get_success( self.sync_handler.wait_for_sync_for_user( - alice_requester, generate_sync_config(alice) + alice_requester, + generate_sync_config(alice), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), ) ) last_room_creation_event_id = ( @@ -486,6 +547,8 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): self.hs, {"room": {"timeline": {"limit": 1}}} ), ), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), since_token=initial_sync_result.next_batch, ) ) @@ -515,6 +578,8 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): self.hs, {"room": {"timeline": {"limit": 1}}} ), ), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), since_token=incremental_sync.next_batch, ) ) @@ -574,7 +639,10 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): # Do an initial sync to get a known starting point. initial_sync_result = self.get_success( self.sync_handler.wait_for_sync_for_user( - alice_requester, generate_sync_config(alice) + alice_requester, + generate_sync_config(alice), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), ) ) last_room_creation_event_id = ( @@ -598,6 +666,8 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): self.hs, {"room": {"timeline": {"limit": 1}}} ), ), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), ) ) room_sync = initial_sync_result.joined[0] @@ -618,6 +688,8 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): self.sync_handler.wait_for_sync_for_user( alice_requester, generate_sync_config(alice), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), since_token=initial_sync_result.next_batch, ) ) @@ -668,7 +740,10 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): initial_sync_result = self.get_success( self.sync_handler.wait_for_sync_for_user( - bob_requester, generate_sync_config(bob) + bob_requester, + generate_sync_config(bob), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), ) ) @@ -699,6 +774,8 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): generate_sync_config( bob, filter_collection=FilterCollection(self.hs, filter_dict) ), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), since_token=None if initial_sync else initial_sync_result.next_batch, ) ).archived[0] @@ -791,7 +868,10 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): # but that it does not come down /sync in public room sync_result: SyncResult = self.get_success( self.sync_handler.wait_for_sync_for_user( - create_requester(user), generate_sync_config(user) + create_requester(user), + generate_sync_config(user), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), ) ) event_ids = [] @@ -837,7 +917,10 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): private_sync_result: SyncResult = self.get_success( self.sync_handler.wait_for_sync_for_user( - create_requester(user2), generate_sync_config(user2) + create_requester(user2), + generate_sync_config(user2), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), ) ) priv_event_ids = [] @@ -846,8 +929,35 @@ class SyncTestCase(tests.unittest.HomeserverTestCase): self.assertIn(private_call_event.event_id, priv_event_ids) + def test_push_rules_with_bad_account_data(self) -> None: + """Some old accounts have managed to set a `m.push_rules` account data, + which we should ignore in /sync response. + """ -_request_key = 0 + user = self.register_user("alice", "password") + + # Insert the bad account data. + self.get_success( + self.store.add_account_data_for_user(user, AccountDataTypes.PUSH_RULES, {}) + ) + + sync_result: SyncResult = self.get_success( + self.sync_handler.wait_for_sync_for_user( + create_requester(user), + generate_sync_config(user), + sync_version=SyncVersion.SYNC_V2, + request_key=generate_request_key(), + ) + ) + + for account_dict in sync_result.account_data: + if account_dict["type"] == AccountDataTypes.PUSH_RULES: + # We should have lots of push rules here, rather than the bad + # empty data. + self.assertNotEqual(account_dict["content"], {}) + return + + self.fail("No push rules found") def generate_sync_config( @@ -866,12 +976,9 @@ def generate_sync_config( if filter_collection is None: filter_collection = Filtering(Mock()).DEFAULT_FILTER_COLLECTION - global _request_key - _request_key += 1 return SyncConfig( user=UserID.from_string(user_id), filter_collection=filter_collection, is_guest=False, - request_key=("request_key", _request_key), device_id=device_id, ) diff --git a/tests/handlers/test_typing.py b/tests/handlers/test_typing.py index c754083967..9d8960315f 100644 --- a/tests/handlers/test_typing.py +++ b/tests/handlers/test_typing.py @@ -32,7 +32,7 @@ from twisted.web.resource import Resource from synapse.api.constants import EduTypes from synapse.api.errors import AuthError from synapse.federation.transport.server import TransportLayerServer -from synapse.handlers.typing import TypingWriterHandler +from synapse.handlers.typing import FORGET_TIMEOUT, TypingWriterHandler from synapse.http.federation.matrix_federation_agent import MatrixFederationAgent from synapse.server import HomeServer from synapse.types import JsonDict, Requester, StreamKeyType, UserID, create_requester @@ -501,3 +501,54 @@ class TypingNotificationsTestCase(unittest.HomeserverTestCase): } ], ) + + def test_prune_typing_replication(self) -> None: + """Regression test for `get_all_typing_updates` breaking when we prune + old updates + """ + self.room_members = [U_APPLE, U_BANANA] + + instance_name = self.hs.get_instance_name() + + self.get_success( + self.handler.started_typing( + target_user=U_APPLE, + requester=create_requester(U_APPLE), + room_id=ROOM_ID, + timeout=10000, + ) + ) + + rows, _, _ = self.get_success( + self.handler.get_all_typing_updates( + instance_name=instance_name, + last_id=0, + current_id=self.handler.get_current_token(), + limit=100, + ) + ) + self.assertEqual(rows, [(1, [ROOM_ID, [U_APPLE.to_string()]])]) + + self.reactor.advance(20000) + + rows, _, _ = self.get_success( + self.handler.get_all_typing_updates( + instance_name=instance_name, + last_id=1, + current_id=self.handler.get_current_token(), + limit=100, + ) + ) + self.assertEqual(rows, [(2, [ROOM_ID, []])]) + + self.reactor.advance(FORGET_TIMEOUT) + + rows, _, _ = self.get_success( + self.handler.get_all_typing_updates( + instance_name=instance_name, + last_id=1, + current_id=self.handler.get_current_token(), + limit=100, + ) + ) + self.assertEqual(rows, []) diff --git a/tests/handlers/test_user_directory.py b/tests/handlers/test_user_directory.py index 77c6cac449..878d9683b6 100644 --- a/tests/handlers/test_user_directory.py +++ b/tests/handlers/test_user_directory.py @@ -1061,6 +1061,45 @@ class UserDirectoryTestCase(unittest.HomeserverTestCase): {alice: ProfileInfo(display_name=None, avatar_url=MXC_DUMMY)}, ) + def test_search_punctuation(self) -> None: + """Test that you can search for a user that includes punctuation""" + + searching_user = self.register_user("searcher", "password") + searching_user_tok = self.login("searcher", "password") + + room_id = self.helper.create_room_as( + searching_user, + room_version=RoomVersions.V1.identifier, + tok=searching_user_tok, + ) + + # We want to test searching for users of the form e.g. "user-1", with + # various punctuation. We also test both where the prefix is numeric and + # alphanumeric, as e.g. postgres tokenises "user-1" as "user" and "-1". + i = 1 + for char in ["-", ".", "_"]: + for use_numeric in [False, True]: + if use_numeric: + prefix1 = f"{i}" + prefix2 = f"{i+1}" + else: + prefix1 = f"a{i}" + prefix2 = f"a{i+1}" + + local_user_1 = self.register_user(f"user{char}{prefix1}", "password") + local_user_2 = self.register_user(f"user{char}{prefix2}", "password") + + self._add_user_to_room(room_id, RoomVersions.V1, local_user_1) + self._add_user_to_room(room_id, RoomVersions.V1, local_user_2) + + results = self.get_success( + self.handler.search_users(searching_user, local_user_1, 20) + )["results"] + received_user_id_ordering = [result["user_id"] for result in results] + self.assertSequenceEqual(received_user_id_ordering[:1], [local_user_1]) + + i += 2 + class TestUserDirSearchDisabled(unittest.HomeserverTestCase): servlets = [ diff --git a/tests/media/test_media_storage.py b/tests/media/test_media_storage.py index cae67e11c8..46d20ce775 100644 --- a/tests/media/test_media_storage.py +++ b/tests/media/test_media_storage.py @@ -18,13 +18,14 @@ # [This file includes modifications made by New Vector Limited] # # +import itertools import os import shutil import tempfile from binascii import unhexlify from io import BytesIO from typing import Any, BinaryIO, ClassVar, Dict, List, Optional, Tuple, Union -from unittest.mock import Mock +from unittest.mock import MagicMock, Mock, patch from urllib import parse import attr @@ -36,9 +37,12 @@ from twisted.internet import defer from twisted.internet.defer import Deferred from twisted.python.failure import Failure from twisted.test.proto_helpers import MemoryReactor +from twisted.web.http_headers import Headers +from twisted.web.iweb import UNKNOWN_LENGTH, IResponse from twisted.web.resource import Resource from synapse.api.errors import Codes, HttpResponseException +from synapse.api.ratelimiting import Ratelimiter from synapse.events import EventBase from synapse.http.types import QueryParams from synapse.logging.context import make_deferred_yieldable @@ -46,11 +50,11 @@ from synapse.media._base import FileInfo, ThumbnailInfo from synapse.media.filepath import MediaFilePaths from synapse.media.media_storage import MediaStorage, ReadableFileWrapper from synapse.media.storage_provider import FileStorageProviderBackend +from synapse.media.thumbnailer import ThumbnailProvider from synapse.module_api import ModuleApi from synapse.module_api.callbacks.spamchecker_callbacks import load_legacy_spam_checkers from synapse.rest import admin -from synapse.rest.client import login -from synapse.rest.media.thumbnail_resource import ThumbnailResource +from synapse.rest.client import login, media from synapse.server import HomeServer from synapse.types import JsonDict, RoomAlias from synapse.util import Clock @@ -58,6 +62,7 @@ from synapse.util import Clock from tests import unittest from tests.server import FakeChannel from tests.test_utils import SMALL_PNG +from tests.unittest import override_config from tests.utils import default_config @@ -153,68 +158,54 @@ class _TestImage: is_inline: bool = True -@parameterized_class( - ("test_image",), - [ - # small png - ( - _TestImage( - SMALL_PNG, - b"image/png", - b".png", - unhexlify( - b"89504e470d0a1a0a0000000d4948445200000020000000200806" - b"000000737a7af40000001a49444154789cedc101010000008220" - b"ffaf6e484001000000ef0610200001194334ee0000000049454e" - b"44ae426082" - ), - unhexlify( - b"89504e470d0a1a0a0000000d4948445200000001000000010806" - b"0000001f15c4890000000d49444154789c636060606000000005" - b"0001a5f645400000000049454e44ae426082" - ), - ), - ), - # small png with transparency. - ( - _TestImage( - unhexlify( - b"89504e470d0a1a0a0000000d49484452000000010000000101000" - b"00000376ef9240000000274524e5300010194fdae0000000a4944" - b"4154789c636800000082008177cd72b60000000049454e44ae426" - b"082" - ), - b"image/png", - b".png", - # Note that we don't check the output since it varies across - # different versions of Pillow. - ), - ), - # small lossless webp - ( - _TestImage( - unhexlify( - b"524946461a000000574542505650384c0d0000002f0000001007" - b"1011118888fe0700" - ), - b"image/webp", - b".webp", - ), - ), - # an empty file - ( - _TestImage( - b"", - b"image/gif", - b".gif", - expected_found=False, - unable_to_thumbnail=True, - ), - ), - # An SVG. - ( - _TestImage( - b"""<?xml version="1.0"?> +small_png = _TestImage( + SMALL_PNG, + b"image/png", + b".png", + unhexlify( + b"89504e470d0a1a0a0000000d4948445200000020000000200806" + b"000000737a7af40000001a49444154789cedc101010000008220" + b"ffaf6e484001000000ef0610200001194334ee0000000049454e" + b"44ae426082" + ), + unhexlify( + b"89504e470d0a1a0a0000000d4948445200000001000000010806" + b"0000001f15c4890000000d49444154789c636060606000000005" + b"0001a5f645400000000049454e44ae426082" + ), +) + +small_png_with_transparency = _TestImage( + unhexlify( + b"89504e470d0a1a0a0000000d49484452000000010000000101000" + b"00000376ef9240000000274524e5300010194fdae0000000a4944" + b"4154789c636800000082008177cd72b60000000049454e44ae426" + b"082" + ), + b"image/png", + b".png", + # Note that we don't check the output since it varies across + # different versions of Pillow. +) + +small_lossless_webp = _TestImage( + unhexlify( + b"524946461a000000574542505650384c0d0000002f0000001007" b"1011118888fe0700" + ), + b"image/webp", + b".webp", +) + +empty_file = _TestImage( + b"", + b"image/gif", + b".gif", + expected_found=False, + unable_to_thumbnail=True, +) + +SVG = _TestImage( + b"""<?xml version="1.0"?> <!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd"> @@ -223,19 +214,32 @@ class _TestImage: <circle cx="100" cy="100" r="50" stroke="black" stroke-width="5" fill="red" /> </svg>""", - b"image/svg", - b".svg", - expected_found=False, - unable_to_thumbnail=True, - is_inline=False, - ), - ), - ], + b"image/svg", + b".svg", + expected_found=False, + unable_to_thumbnail=True, + is_inline=False, ) +test_images = [ + small_png, + small_png_with_transparency, + small_lossless_webp, + empty_file, + SVG, +] +urls = [ + "_matrix/media/r0/thumbnail", + "_matrix/client/unstable/org.matrix.msc3916/media/thumbnail", +] + + +@parameterized_class(("test_image", "url"), itertools.product(test_images, urls)) class MediaRepoTests(unittest.HomeserverTestCase): + servlets = [media.register_servlets] test_image: ClassVar[_TestImage] hijack_auth = True user_id = "@test:user" + url: ClassVar[str] def make_homeserver(self, reactor: MemoryReactor, clock: Clock) -> HomeServer: self.fetches: List[ @@ -251,9 +255,11 @@ class MediaRepoTests(unittest.HomeserverTestCase): destination: str, path: str, output_stream: BinaryIO, + download_ratelimiter: Ratelimiter, + ip_address: Any, + max_size: int, args: Optional[QueryParams] = None, retry_on_dns_fail: bool = True, - max_size: Optional[int] = None, ignore_backoff: bool = False, follow_redirects: bool = False, ) -> "Deferred[Tuple[int, Dict[bytes, List[bytes]]]]": @@ -298,6 +304,7 @@ class MediaRepoTests(unittest.HomeserverTestCase): "config": {"directory": self.storage_path}, } config["media_storage_providers"] = [provider_config] + config["experimental_features"] = {"msc3916_authenticated_media_enabled": True} hs = self.setup_test_homeserver(config=config, federation_http_client=client) @@ -502,7 +509,7 @@ class MediaRepoTests(unittest.HomeserverTestCase): params = "?width=32&height=32&method=scale" channel = self.make_request( "GET", - f"/_matrix/media/v3/thumbnail/{self.media_id}{params}", + f"/{self.url}/{self.media_id}{params}", shorthand=False, await_result=False, ) @@ -530,7 +537,7 @@ class MediaRepoTests(unittest.HomeserverTestCase): channel = self.make_request( "GET", - f"/_matrix/media/v3/thumbnail/{self.media_id}{params}", + f"/{self.url}/{self.media_id}{params}", shorthand=False, await_result=False, ) @@ -566,12 +573,11 @@ class MediaRepoTests(unittest.HomeserverTestCase): params = "?width=32&height=32&method=" + method channel = self.make_request( "GET", - f"/_matrix/media/r0/thumbnail/{self.media_id}{params}", + f"/{self.url}/{self.media_id}{params}", shorthand=False, await_result=False, ) self.pump() - headers = { b"Content-Length": [b"%d" % (len(self.test_image.data))], b"Content-Type": [self.test_image.content_type], @@ -580,7 +586,6 @@ class MediaRepoTests(unittest.HomeserverTestCase): (self.test_image.data, (len(self.test_image.data), headers)) ) self.pump() - if expected_found: self.assertEqual(channel.code, 200) @@ -603,7 +608,7 @@ class MediaRepoTests(unittest.HomeserverTestCase): channel.json_body, { "errcode": "M_UNKNOWN", - "error": "Cannot find any thumbnails for the requested media ('/_matrix/media/r0/thumbnail/example.com/12345'). This might mean the media is not a supported_media_format=(image/jpeg, image/jpg, image/webp, image/gif, image/png) or that thumbnailing failed for some other reason. (Dynamic thumbnails are disabled on this server.)", + "error": f"Cannot find any thumbnails for the requested media ('/{self.url}/example.com/12345'). This might mean the media is not a supported_media_format=(image/jpeg, image/jpg, image/webp, image/gif, image/png) or that thumbnailing failed for some other reason. (Dynamic thumbnails are disabled on this server.)", }, ) else: @@ -613,7 +618,7 @@ class MediaRepoTests(unittest.HomeserverTestCase): channel.json_body, { "errcode": "M_NOT_FOUND", - "error": "Not found '/_matrix/media/r0/thumbnail/example.com/12345'", + "error": f"Not found '/{self.url}/example.com/12345'", }, ) @@ -625,12 +630,12 @@ class MediaRepoTests(unittest.HomeserverTestCase): content_type = self.test_image.content_type.decode() media_repo = self.hs.get_media_repository() - thumbnail_resouce = ThumbnailResource( + thumbnail_provider = ThumbnailProvider( self.hs, media_repo, media_repo.media_storage ) self.assertIsNotNone( - thumbnail_resouce._select_thumbnail( + thumbnail_provider._select_thumbnail( desired_width=desired_size, desired_height=desired_size, desired_method=method, @@ -879,3 +884,218 @@ class SpamCheckerTestCase(unittest.HomeserverTestCase): tok=self.tok, expect_code=400, ) + + +class RemoteDownloadLimiterTestCase(unittest.HomeserverTestCase): + def make_homeserver(self, reactor: MemoryReactor, clock: Clock) -> HomeServer: + config = self.default_config() + + self.storage_path = self.mktemp() + self.media_store_path = self.mktemp() + os.mkdir(self.storage_path) + os.mkdir(self.media_store_path) + config["media_store_path"] = self.media_store_path + + provider_config = { + "module": "synapse.media.storage_provider.FileStorageProviderBackend", + "store_local": True, + "store_synchronous": False, + "store_remote": True, + "config": {"directory": self.storage_path}, + } + + config["media_storage_providers"] = [provider_config] + + return self.setup_test_homeserver(config=config) + + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: + self.repo = hs.get_media_repository() + self.client = hs.get_federation_http_client() + self.store = hs.get_datastores().main + + def create_resource_dict(self) -> Dict[str, Resource]: + # We need to manually set the resource tree to include media, the + # default only does `/_matrix/client` APIs. + return {"/_matrix/media": self.hs.get_media_repository_resource()} + + # mock actually reading file body + def read_body_with_max_size_30MiB(*args: Any, **kwargs: Any) -> Deferred: + d: Deferred = defer.Deferred() + d.callback(31457280) + return d + + def read_body_with_max_size_50MiB(*args: Any, **kwargs: Any) -> Deferred: + d: Deferred = defer.Deferred() + d.callback(52428800) + return d + + @patch( + "synapse.http.matrixfederationclient.read_body_with_max_size", + read_body_with_max_size_30MiB, + ) + def test_download_ratelimit_default(self) -> None: + """ + Test remote media download ratelimiting against default configuration - 500MB bucket + and 87kb/second drain rate + """ + + # mock out actually sending the request, returns a 30MiB response + async def _send_request(*args: Any, **kwargs: Any) -> IResponse: + resp = MagicMock(spec=IResponse) + resp.code = 200 + resp.length = 31457280 + resp.headers = Headers({"Content-Type": ["application/octet-stream"]}) + resp.phrase = b"OK" + return resp + + self.client._send_request = _send_request # type: ignore + + # first request should go through + channel = self.make_request( + "GET", + "/_matrix/media/v3/download/remote.org/abcdefghijklmnopqrstuvwxyz", + shorthand=False, + ) + assert channel.code == 200 + + # next 15 should go through + for i in range(15): + channel2 = self.make_request( + "GET", + f"/_matrix/media/v3/download/remote.org/abcdefghijklmnopqrstuvwxy{i}", + shorthand=False, + ) + assert channel2.code == 200 + + # 17th will hit ratelimit + channel3 = self.make_request( + "GET", + "/_matrix/media/v3/download/remote.org/abcdefghijklmnopqrstuvwxyx", + shorthand=False, + ) + assert channel3.code == 429 + + # however, a request from a different IP will go through + channel4 = self.make_request( + "GET", + "/_matrix/media/v3/download/remote.org/abcdefghijklmnopqrstuvwxyz", + shorthand=False, + client_ip="187.233.230.159", + ) + assert channel4.code == 200 + + # at 87Kib/s it should take about 2 minutes for enough to drain from bucket that another + # 30MiB download is authorized - The last download was blocked at 503,316,480. + # The next download will be authorized when bucket hits 492,830,720 + # (524,288,000 total capacity - 31,457,280 download size) so 503,316,480 - 492,830,720 ~= 10,485,760 + # needs to drain before another download will be authorized, that will take ~= + # 2 minutes (10,485,760/89,088/60) + self.reactor.pump([2.0 * 60.0]) + + # enough has drained and next request goes through + channel5 = self.make_request( + "GET", + "/_matrix/media/v3/download/remote.org/abcdefghijklmnopqrstuvwxyb", + shorthand=False, + ) + assert channel5.code == 200 + + @override_config( + { + "remote_media_download_per_second": "50M", + "remote_media_download_burst_count": "50M", + } + ) + @patch( + "synapse.http.matrixfederationclient.read_body_with_max_size", + read_body_with_max_size_50MiB, + ) + def test_download_rate_limit_config(self) -> None: + """ + Test that download rate limit config options are correctly picked up and applied + """ + + async def _send_request(*args: Any, **kwargs: Any) -> IResponse: + resp = MagicMock(spec=IResponse) + resp.code = 200 + resp.length = 52428800 + resp.headers = Headers({"Content-Type": ["application/octet-stream"]}) + resp.phrase = b"OK" + return resp + + self.client._send_request = _send_request # type: ignore + + # first request should go through + channel = self.make_request( + "GET", + "/_matrix/media/v3/download/remote.org/abcdefghijklmnopqrstuvwxyz", + shorthand=False, + ) + assert channel.code == 200 + + # immediate second request should fail + channel = self.make_request( + "GET", + "/_matrix/media/v3/download/remote.org/abcdefghijklmnopqrstuvwxy1", + shorthand=False, + ) + assert channel.code == 429 + + # advance half a second + self.reactor.pump([0.5]) + + # request still fails + channel = self.make_request( + "GET", + "/_matrix/media/v3/download/remote.org/abcdefghijklmnopqrstuvwxy2", + shorthand=False, + ) + assert channel.code == 429 + + # advance another half second + self.reactor.pump([0.5]) + + # enough has drained from bucket and request is successful + channel = self.make_request( + "GET", + "/_matrix/media/v3/download/remote.org/abcdefghijklmnopqrstuvwxy3", + shorthand=False, + ) + assert channel.code == 200 + + @patch( + "synapse.http.matrixfederationclient.read_body_with_max_size", + read_body_with_max_size_30MiB, + ) + def test_download_ratelimit_max_size_sub(self) -> None: + """ + Test that if no content-length is provided, the default max size is applied instead + """ + + # mock out actually sending the request + async def _send_request(*args: Any, **kwargs: Any) -> IResponse: + resp = MagicMock(spec=IResponse) + resp.code = 200 + resp.length = UNKNOWN_LENGTH + resp.headers = Headers({"Content-Type": ["application/octet-stream"]}) + resp.phrase = b"OK" + return resp + + self.client._send_request = _send_request # type: ignore + + # ten requests should go through using the max size (500MB/50MB) + for i in range(10): + channel2 = self.make_request( + "GET", + f"/_matrix/media/v3/download/remote.org/abcdefghijklmnopqrstuvwxy{i}", + shorthand=False, + ) + assert channel2.code == 200 + + # eleventh will hit ratelimit + channel3 = self.make_request( + "GET", + "/_matrix/media/v3/download/remote.org/abcdefghijklmnopqrstuvwxyx", + shorthand=False, + ) + assert channel3.code == 429 diff --git a/tests/module_api/test_api.py b/tests/module_api/test_api.py index 5eb1406a06..b6ba472d7d 100644 --- a/tests/module_api/test_api.py +++ b/tests/module_api/test_api.py @@ -688,7 +688,7 @@ class ModuleApiTestCase(BaseModuleApiTestCase): channel = self.make_request( "GET", - "/notifications?from=", + "/notifications", access_token=tok, ) self.assertEqual(channel.code, 200, channel.result) diff --git a/tests/push/test_email.py b/tests/push/test_email.py index c927a73fa6..e0aab1c046 100644 --- a/tests/push/test_email.py +++ b/tests/push/test_email.py @@ -205,8 +205,24 @@ class EmailPusherTests(HomeserverTestCase): # Multipart: plain text, base 64 encoded; html, base 64 encoded multipart_msg = email.message_from_bytes(msg) - txt = multipart_msg.get_payload()[0].get_payload(decode=True).decode() - html = multipart_msg.get_payload()[1].get_payload(decode=True).decode() + + # Extract the text (non-HTML) portion of the multipart Message, + # as a Message. + txt_message = multipart_msg.get_payload(i=0) + assert isinstance(txt_message, email.message.Message) + + # Extract the actual bytes from the Message object, and decode them to a `str`. + txt_bytes = txt_message.get_payload(decode=True) + assert isinstance(txt_bytes, bytes) + txt = txt_bytes.decode() + + # Do the same for the HTML portion of the multipart Message. + html_message = multipart_msg.get_payload(i=1) + assert isinstance(html_message, email.message.Message) + html_bytes = html_message.get_payload(decode=True) + assert isinstance(html_bytes, bytes) + html = html_bytes.decode() + self.assertIn("/_synapse/client/unsubscribe", txt) self.assertIn("/_synapse/client/unsubscribe", html) @@ -347,12 +363,17 @@ class EmailPusherTests(HomeserverTestCase): # That email should contain the room's avatar msg: bytes = args[5] # Multipart: plain text, base 64 encoded; html, base 64 encoded - html = ( - email.message_from_bytes(msg) - .get_payload()[1] - .get_payload(decode=True) - .decode() - ) + + # Extract the html Message object from the Multipart Message. + # We need the asserts to convince mypy that this is OK. + html_message = email.message_from_bytes(msg).get_payload(i=1) + assert isinstance(html_message, email.message.Message) + + # Extract the `bytes` from the html Message object, and decode to a `str`. + html = html_message.get_payload(decode=True) + assert isinstance(html, bytes) + html = html.decode() + self.assertIn("_matrix/media/v1/thumbnail/DUMMY_MEDIA_ID", html) def test_empty_room(self) -> None: diff --git a/tests/replication/storage/test_events.py b/tests/replication/storage/test_events.py index 86c8f14d1b..a56f1e2d5d 100644 --- a/tests/replication/storage/test_events.py +++ b/tests/replication/storage/test_events.py @@ -141,6 +141,7 @@ class EventsWorkerStoreTestCase(BaseWorkerStoreTestCase): self.persist(type="m.room.create", key="", creator=USER_ID) self.check("get_invited_rooms_for_local_user", [USER_ID_2], []) event = self.persist(type="m.room.member", key=USER_ID_2, membership="invite") + assert event.internal_metadata.instance_name is not None assert event.internal_metadata.stream_ordering is not None self.replicate() @@ -154,7 +155,10 @@ class EventsWorkerStoreTestCase(BaseWorkerStoreTestCase): USER_ID, "invite", event.event_id, - event.internal_metadata.stream_ordering, + PersistedEventPosition( + event.internal_metadata.instance_name, + event.internal_metadata.stream_ordering, + ), RoomVersions.V1.identifier, ) ], @@ -229,11 +233,12 @@ class EventsWorkerStoreTestCase(BaseWorkerStoreTestCase): j2 = self.persist( type="m.room.member", sender=USER_ID_2, key=USER_ID_2, membership="join" ) + assert j2.internal_metadata.instance_name is not None assert j2.internal_metadata.stream_ordering is not None self.replicate() expected_pos = PersistedEventPosition( - "master", j2.internal_metadata.stream_ordering + j2.internal_metadata.instance_name, j2.internal_metadata.stream_ordering ) self.check( "get_rooms_for_user_with_stream_ordering", @@ -285,6 +290,7 @@ class EventsWorkerStoreTestCase(BaseWorkerStoreTestCase): msg, msgctx = self.build_event() self.get_success(self.persistance.persist_events([(j2, j2ctx), (msg, msgctx)])) self.replicate() + assert j2.internal_metadata.instance_name is not None assert j2.internal_metadata.stream_ordering is not None event_source = RoomEventSource(self.hs) @@ -326,7 +332,8 @@ class EventsWorkerStoreTestCase(BaseWorkerStoreTestCase): # joined_rooms list. if membership_changes: expected_pos = PersistedEventPosition( - "master", j2.internal_metadata.stream_ordering + j2.internal_metadata.instance_name, + j2.internal_metadata.stream_ordering, ) self.assertEqual( joined_rooms, diff --git a/tests/rest/admin/test_admin.py b/tests/rest/admin/test_admin.py index 22106eb786..5f6f7213b3 100644 --- a/tests/rest/admin/test_admin.py +++ b/tests/rest/admin/test_admin.py @@ -435,10 +435,6 @@ class ExperimentalFeaturesTestCase(unittest.HomeserverTestCase): True, channel.json_body["features"]["msc3881"], ) - self.assertEqual( - False, - channel.json_body["features"]["msc3967"], - ) # test nothing blows up if you try to disable a feature that isn't already enabled url = f"{self.url}/{self.other_user}" diff --git a/tests/rest/admin/test_event_reports.py b/tests/rest/admin/test_event_reports.py index a0f978911a..feb410a11d 100644 --- a/tests/rest/admin/test_event_reports.py +++ b/tests/rest/admin/test_event_reports.py @@ -24,7 +24,7 @@ from twisted.test.proto_helpers import MemoryReactor import synapse.rest.admin from synapse.api.errors import Codes -from synapse.rest.client import login, report_event, room +from synapse.rest.client import login, reporting, room from synapse.server import HomeServer from synapse.types import JsonDict from synapse.util import Clock @@ -37,7 +37,7 @@ class EventReportsTestCase(unittest.HomeserverTestCase): synapse.rest.admin.register_servlets, login.register_servlets, room.register_servlets, - report_event.register_servlets, + reporting.register_servlets, ] def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: @@ -453,7 +453,7 @@ class EventReportDetailTestCase(unittest.HomeserverTestCase): synapse.rest.admin.register_servlets, login.register_servlets, room.register_servlets, - report_event.register_servlets, + reporting.register_servlets, ] def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: diff --git a/tests/rest/admin/test_room.py b/tests/rest/admin/test_room.py index 7562747260..95ed736451 100644 --- a/tests/rest/admin/test_room.py +++ b/tests/rest/admin/test_room.py @@ -1795,6 +1795,83 @@ class RoomTestCase(unittest.HomeserverTestCase): self.assertEqual(room_id, channel.json_body["rooms"][0].get("room_id")) self.assertEqual("ж", channel.json_body["rooms"][0].get("name")) + def test_filter_public_rooms(self) -> None: + self.helper.create_room_as( + self.admin_user, tok=self.admin_user_tok, is_public=True + ) + self.helper.create_room_as( + self.admin_user, tok=self.admin_user_tok, is_public=True + ) + self.helper.create_room_as( + self.admin_user, tok=self.admin_user_tok, is_public=False + ) + + response = self.make_request( + "GET", + "/_synapse/admin/v1/rooms", + access_token=self.admin_user_tok, + ) + self.assertEqual(200, response.code, msg=response.json_body) + self.assertEqual(3, response.json_body["total_rooms"]) + self.assertEqual(3, len(response.json_body["rooms"])) + + response = self.make_request( + "GET", + "/_synapse/admin/v1/rooms?public_rooms=true", + access_token=self.admin_user_tok, + ) + self.assertEqual(200, response.code, msg=response.json_body) + self.assertEqual(2, response.json_body["total_rooms"]) + self.assertEqual(2, len(response.json_body["rooms"])) + + response = self.make_request( + "GET", + "/_synapse/admin/v1/rooms?public_rooms=false", + access_token=self.admin_user_tok, + ) + self.assertEqual(200, response.code, msg=response.json_body) + self.assertEqual(1, response.json_body["total_rooms"]) + self.assertEqual(1, len(response.json_body["rooms"])) + + def test_filter_empty_rooms(self) -> None: + self.helper.create_room_as( + self.admin_user, tok=self.admin_user_tok, is_public=True + ) + self.helper.create_room_as( + self.admin_user, tok=self.admin_user_tok, is_public=True + ) + room_id = self.helper.create_room_as( + self.admin_user, tok=self.admin_user_tok, is_public=False + ) + self.helper.leave(room_id, self.admin_user, tok=self.admin_user_tok) + + response = self.make_request( + "GET", + "/_synapse/admin/v1/rooms", + access_token=self.admin_user_tok, + ) + self.assertEqual(200, response.code, msg=response.json_body) + self.assertEqual(3, response.json_body["total_rooms"]) + self.assertEqual(3, len(response.json_body["rooms"])) + + response = self.make_request( + "GET", + "/_synapse/admin/v1/rooms?empty_rooms=false", + access_token=self.admin_user_tok, + ) + self.assertEqual(200, response.code, msg=response.json_body) + self.assertEqual(2, response.json_body["total_rooms"]) + self.assertEqual(2, len(response.json_body["rooms"])) + + response = self.make_request( + "GET", + "/_synapse/admin/v1/rooms?empty_rooms=true", + access_token=self.admin_user_tok, + ) + self.assertEqual(200, response.code, msg=response.json_body) + self.assertEqual(1, response.json_body["total_rooms"]) + self.assertEqual(1, len(response.json_body["rooms"])) + def test_single_room(self) -> None: """Test that a single room can be requested correctly""" # Create two test rooms diff --git a/tests/rest/admin/test_user.py b/tests/rest/admin/test_user.py index c5da1e9686..16bb4349f5 100644 --- a/tests/rest/admin/test_user.py +++ b/tests/rest/admin/test_user.py @@ -37,6 +37,7 @@ from synapse.api.constants import ApprovalNoticeMedium, LoginType, UserTypes from synapse.api.errors import Codes, HttpResponseException, ResourceLimitError from synapse.api.room_versions import RoomVersions from synapse.media.filepath import MediaFilePaths +from synapse.rest import admin from synapse.rest.client import ( devices, login, @@ -5005,3 +5006,86 @@ class AllowCrossSigningReplacementTestCase(unittest.HomeserverTestCase): ) assert timestamp is not None self.assertGreater(timestamp, self.clock.time_msec()) + + +class UserSuspensionTestCase(unittest.HomeserverTestCase): + servlets = [ + synapse.rest.admin.register_servlets, + login.register_servlets, + admin.register_servlets, + ] + + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: + self.admin = self.register_user("thomas", "hackme", True) + self.admin_tok = self.login("thomas", "hackme") + + self.bad_user = self.register_user("teresa", "hackme") + self.bad_user_tok = self.login("teresa", "hackme") + + self.store = hs.get_datastores().main + + @override_config({"experimental_features": {"msc3823_account_suspension": True}}) + def test_suspend_user(self) -> None: + # test that suspending user works + channel = self.make_request( + "PUT", + f"/_synapse/admin/v1/suspend/{self.bad_user}", + {"suspend": True}, + access_token=self.admin_tok, + ) + self.assertEqual(channel.code, 200) + self.assertEqual(channel.json_body, {f"user_{self.bad_user}_suspended": True}) + + res = self.get_success(self.store.get_user_suspended_status(self.bad_user)) + self.assertEqual(True, res) + + # test that un-suspending user works + channel2 = self.make_request( + "PUT", + f"/_synapse/admin/v1/suspend/{self.bad_user}", + {"suspend": False}, + access_token=self.admin_tok, + ) + self.assertEqual(channel2.code, 200) + self.assertEqual(channel2.json_body, {f"user_{self.bad_user}_suspended": False}) + + res2 = self.get_success(self.store.get_user_suspended_status(self.bad_user)) + self.assertEqual(False, res2) + + # test that trying to un-suspend user who isn't suspended doesn't cause problems + channel3 = self.make_request( + "PUT", + f"/_synapse/admin/v1/suspend/{self.bad_user}", + {"suspend": False}, + access_token=self.admin_tok, + ) + self.assertEqual(channel3.code, 200) + self.assertEqual(channel3.json_body, {f"user_{self.bad_user}_suspended": False}) + + res3 = self.get_success(self.store.get_user_suspended_status(self.bad_user)) + self.assertEqual(False, res3) + + # test that trying to suspend user who is already suspended doesn't cause problems + channel4 = self.make_request( + "PUT", + f"/_synapse/admin/v1/suspend/{self.bad_user}", + {"suspend": True}, + access_token=self.admin_tok, + ) + self.assertEqual(channel4.code, 200) + self.assertEqual(channel4.json_body, {f"user_{self.bad_user}_suspended": True}) + + res4 = self.get_success(self.store.get_user_suspended_status(self.bad_user)) + self.assertEqual(True, res4) + + channel5 = self.make_request( + "PUT", + f"/_synapse/admin/v1/suspend/{self.bad_user}", + {"suspend": True}, + access_token=self.admin_tok, + ) + self.assertEqual(channel5.code, 200) + self.assertEqual(channel5.json_body, {f"user_{self.bad_user}_suspended": True}) + + res5 = self.get_success(self.store.get_user_suspended_status(self.bad_user)) + self.assertEqual(True, res5) diff --git a/tests/rest/client/test_account.py b/tests/rest/client/test_account.py index 992421ffe2..a85ea994de 100644 --- a/tests/rest/client/test_account.py +++ b/tests/rest/client/test_account.py @@ -427,13 +427,23 @@ class PasswordResetTestCase(unittest.HomeserverTestCase): text = None for part in mail.walk(): if part.get_content_type() == "text/plain": - text = part.get_payload(decode=True).decode("UTF-8") + text = part.get_payload(decode=True) + if text is not None: + # According to the logic table in `get_payload`, we know that + # the result of `get_payload` will be `bytes`, but mypy doesn't + # know this and complains. Thus, we assert the type. + assert isinstance(text, bytes) + text = text.decode("UTF-8") + break if not text: self.fail("Could not find text portion of email to parse") - assert text is not None + # `text` must be a `str`, after being decoded and determined just above + # to not be `None` or an empty `str`. + assert isinstance(text, str) + match = re.search(r"https://example.com\S+", text) assert match, "Could not find link in email" @@ -1209,13 +1219,23 @@ class ThreepidEmailRestTestCase(unittest.HomeserverTestCase): text = None for part in mail.walk(): if part.get_content_type() == "text/plain": - text = part.get_payload(decode=True).decode("UTF-8") + text = part.get_payload(decode=True) + if text is not None: + # According to the logic table in `get_payload`, we know that + # the result of `get_payload` will be `bytes`, but mypy doesn't + # know this and complains. Thus, we assert the type. + assert isinstance(text, bytes) + text = text.decode("UTF-8") + break if not text: self.fail("Could not find text portion of email to parse") - assert text is not None + # `text` must be a `str`, after being decoded and determined just above + # to not be `None` or an empty `str`. + assert isinstance(text, str) + match = re.search(r"https://example.com\S+", text) assert match, "Could not find link in email" diff --git a/tests/rest/client/test_devices.py b/tests/rest/client/test_devices.py index 2b360732ac..a3ed12a38f 100644 --- a/tests/rest/client/test_devices.py +++ b/tests/rest/client/test_devices.py @@ -24,8 +24,8 @@ from twisted.internet.defer import ensureDeferred from twisted.test.proto_helpers import MemoryReactor from synapse.api.errors import NotFoundError -from synapse.rest import admin, devices, room, sync -from synapse.rest.client import account, keys, login, register +from synapse.rest import admin, devices, sync +from synapse.rest.client import keys, login, register from synapse.server import HomeServer from synapse.types import JsonDict, UserID, create_requester from synapse.util import Clock @@ -33,146 +33,6 @@ from synapse.util import Clock from tests import unittest -class DeviceListsTestCase(unittest.HomeserverTestCase): - """Tests regarding device list changes.""" - - servlets = [ - admin.register_servlets_for_client_rest_resource, - login.register_servlets, - register.register_servlets, - account.register_servlets, - room.register_servlets, - sync.register_servlets, - devices.register_servlets, - ] - - def test_receiving_local_device_list_changes(self) -> None: - """Tests that a local users that share a room receive each other's device list - changes. - """ - # Register two users - test_device_id = "TESTDEVICE" - alice_user_id = self.register_user("alice", "correcthorse") - alice_access_token = self.login( - alice_user_id, "correcthorse", device_id=test_device_id - ) - - bob_user_id = self.register_user("bob", "ponyponypony") - bob_access_token = self.login(bob_user_id, "ponyponypony") - - # Create a room for them to coexist peacefully in - new_room_id = self.helper.create_room_as( - alice_user_id, is_public=True, tok=alice_access_token - ) - self.assertIsNotNone(new_room_id) - - # Have Bob join the room - self.helper.invite( - new_room_id, alice_user_id, bob_user_id, tok=alice_access_token - ) - self.helper.join(new_room_id, bob_user_id, tok=bob_access_token) - - # Now have Bob initiate an initial sync (in order to get a since token) - channel = self.make_request( - "GET", - "/sync", - access_token=bob_access_token, - ) - self.assertEqual(channel.code, 200, channel.json_body) - next_batch_token = channel.json_body["next_batch"] - - # ...and then an incremental sync. This should block until the sync stream is woken up, - # which we hope will happen as a result of Alice updating their device list. - bob_sync_channel = self.make_request( - "GET", - f"/sync?since={next_batch_token}&timeout=30000", - access_token=bob_access_token, - # Start the request, then continue on. - await_result=False, - ) - - # Have alice update their device list - channel = self.make_request( - "PUT", - f"/devices/{test_device_id}", - { - "display_name": "New Device Name", - }, - access_token=alice_access_token, - ) - self.assertEqual(channel.code, HTTPStatus.OK, channel.json_body) - - # Check that bob's incremental sync contains the updated device list. - # If not, the client would only receive the device list update on the - # *next* sync. - bob_sync_channel.await_result() - self.assertEqual(bob_sync_channel.code, 200, bob_sync_channel.json_body) - - changed_device_lists = bob_sync_channel.json_body.get("device_lists", {}).get( - "changed", [] - ) - self.assertIn(alice_user_id, changed_device_lists, bob_sync_channel.json_body) - - def test_not_receiving_local_device_list_changes(self) -> None: - """Tests a local users DO NOT receive device updates from each other if they do not - share a room. - """ - # Register two users - test_device_id = "TESTDEVICE" - alice_user_id = self.register_user("alice", "correcthorse") - alice_access_token = self.login( - alice_user_id, "correcthorse", device_id=test_device_id - ) - - bob_user_id = self.register_user("bob", "ponyponypony") - bob_access_token = self.login(bob_user_id, "ponyponypony") - - # These users do not share a room. They are lonely. - - # Have Bob initiate an initial sync (in order to get a since token) - channel = self.make_request( - "GET", - "/sync", - access_token=bob_access_token, - ) - self.assertEqual(channel.code, HTTPStatus.OK, channel.json_body) - next_batch_token = channel.json_body["next_batch"] - - # ...and then an incremental sync. This should block until the sync stream is woken up, - # which we hope will happen as a result of Alice updating their device list. - bob_sync_channel = self.make_request( - "GET", - f"/sync?since={next_batch_token}&timeout=1000", - access_token=bob_access_token, - # Start the request, then continue on. - await_result=False, - ) - - # Have alice update their device list - channel = self.make_request( - "PUT", - f"/devices/{test_device_id}", - { - "display_name": "New Device Name", - }, - access_token=alice_access_token, - ) - self.assertEqual(channel.code, HTTPStatus.OK, channel.json_body) - - # Check that bob's incremental sync does not contain the updated device list. - bob_sync_channel.await_result() - self.assertEqual( - bob_sync_channel.code, HTTPStatus.OK, bob_sync_channel.json_body - ) - - changed_device_lists = bob_sync_channel.json_body.get("device_lists", {}).get( - "changed", [] - ) - self.assertNotIn( - alice_user_id, changed_device_lists, bob_sync_channel.json_body - ) - - class DevicesTestCase(unittest.HomeserverTestCase): servlets = [ admin.register_servlets, diff --git a/tests/rest/client/test_keys.py b/tests/rest/client/test_keys.py index 5f0c005576..8bbd109092 100644 --- a/tests/rest/client/test_keys.py +++ b/tests/rest/client/test_keys.py @@ -155,71 +155,6 @@ class KeyQueryTestCase(unittest.HomeserverTestCase): } def test_device_signing_with_uia(self) -> None: - """Device signing key upload requires UIA.""" - password = "wonderland" - device_id = "ABCDEFGHI" - alice_id = self.register_user("alice", password) - alice_token = self.login("alice", password, device_id=device_id) - - content = self.make_device_keys(alice_id, device_id) - - channel = self.make_request( - "POST", - "/_matrix/client/v3/keys/device_signing/upload", - content, - alice_token, - ) - - self.assertEqual(channel.code, HTTPStatus.UNAUTHORIZED, channel.result) - # Grab the session - session = channel.json_body["session"] - # Ensure that flows are what is expected. - self.assertIn({"stages": ["m.login.password"]}, channel.json_body["flows"]) - - # add UI auth - content["auth"] = { - "type": "m.login.password", - "identifier": {"type": "m.id.user", "user": alice_id}, - "password": password, - "session": session, - } - - channel = self.make_request( - "POST", - "/_matrix/client/v3/keys/device_signing/upload", - content, - alice_token, - ) - - self.assertEqual(channel.code, HTTPStatus.OK, channel.result) - - @override_config({"ui_auth": {"session_timeout": "15m"}}) - def test_device_signing_with_uia_session_timeout(self) -> None: - """Device signing key upload requires UIA buy passes with grace period.""" - password = "wonderland" - device_id = "ABCDEFGHI" - alice_id = self.register_user("alice", password) - alice_token = self.login("alice", password, device_id=device_id) - - content = self.make_device_keys(alice_id, device_id) - - channel = self.make_request( - "POST", - "/_matrix/client/v3/keys/device_signing/upload", - content, - alice_token, - ) - - self.assertEqual(channel.code, HTTPStatus.OK, channel.result) - - @override_config( - { - "experimental_features": {"msc3967_enabled": True}, - "ui_auth": {"session_timeout": "15s"}, - } - ) - def test_device_signing_with_msc3967(self) -> None: - """Device signing key follows MSC3967 behaviour when enabled.""" password = "wonderland" device_id = "ABCDEFGHI" alice_id = self.register_user("alice", password) diff --git a/tests/rest/client/test_media.py b/tests/rest/client/test_media.py new file mode 100644 index 0000000000..be4a289ec1 --- /dev/null +++ b/tests/rest/client/test_media.py @@ -0,0 +1,1609 @@ +# +# This file is licensed under the Affero General Public License (AGPL) version 3. +# +# Copyright 2022 The Matrix.org Foundation C.I.C. +# Copyright (C) 2024 New Vector, Ltd +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as +# published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# See the GNU Affero General Public License for more details: +# <https://www.gnu.org/licenses/agpl-3.0.html>. +# +# Originally licensed under the Apache License, Version 2.0: +# <http://www.apache.org/licenses/LICENSE-2.0>. +# +# [This file includes modifications made by New Vector Limited] +# +# +import base64 +import json +import os +import re +from typing import Any, Dict, Optional, Sequence, Tuple, Type +from urllib.parse import quote, urlencode + +from twisted.internet._resolver import HostResolution +from twisted.internet.address import IPv4Address, IPv6Address +from twisted.internet.error import DNSLookupError +from twisted.internet.interfaces import IAddress, IResolutionReceiver +from twisted.test.proto_helpers import AccumulatingProtocol, MemoryReactor +from twisted.web.resource import Resource + +from synapse.config.oembed import OEmbedEndpointConfig +from synapse.media._base import FileInfo +from synapse.media.url_previewer import IMAGE_CACHE_EXPIRY_MS +from synapse.rest import admin +from synapse.rest.client import login, media +from synapse.server import HomeServer +from synapse.types import JsonDict +from synapse.util import Clock +from synapse.util.stringutils import parse_and_validate_mxc_uri + +from tests import unittest +from tests.server import FakeTransport, ThreadedMemoryReactorClock +from tests.test_utils import SMALL_PNG +from tests.unittest import override_config + +try: + import lxml +except ImportError: + lxml = None # type: ignore[assignment] + + +class UnstableMediaDomainBlockingTests(unittest.HomeserverTestCase): + remote_media_id = "doesnotmatter" + remote_server_name = "evil.com" + servlets = [ + media.register_servlets, + admin.register_servlets, + login.register_servlets, + ] + + def make_homeserver( + self, reactor: ThreadedMemoryReactorClock, clock: Clock + ) -> HomeServer: + config = self.default_config() + + self.storage_path = self.mktemp() + self.media_store_path = self.mktemp() + os.mkdir(self.storage_path) + os.mkdir(self.media_store_path) + config["media_store_path"] = self.media_store_path + + provider_config = { + "module": "synapse.media.storage_provider.FileStorageProviderBackend", + "store_local": True, + "store_synchronous": False, + "store_remote": True, + "config": {"directory": self.storage_path}, + } + + config["media_storage_providers"] = [provider_config] + + return self.setup_test_homeserver(config=config) + + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: + self.store = hs.get_datastores().main + + # Inject a piece of media. We'll use this to ensure we're returning a sane + # response when we're not supposed to block it, distinguishing a media block + # from a regular 404. + file_id = "abcdefg12345" + file_info = FileInfo(server_name=self.remote_server_name, file_id=file_id) + + media_storage = hs.get_media_repository().media_storage + + ctx = media_storage.store_into_file(file_info) + (f, fname) = self.get_success(ctx.__aenter__()) + f.write(SMALL_PNG) + self.get_success(ctx.__aexit__(None, None, None)) + + self.get_success( + self.store.store_cached_remote_media( + origin=self.remote_server_name, + media_id=self.remote_media_id, + media_type="image/png", + media_length=1, + time_now_ms=clock.time_msec(), + upload_name="test.png", + filesystem_id=file_id, + ) + ) + self.register_user("user", "password") + self.tok = self.login("user", "password") + + @override_config( + { + # Disable downloads from the domain we'll be trying to download from. + # Should result in a 404. + "prevent_media_downloads_from": ["evil.com"], + "dynamic_thumbnails": True, + "experimental_features": {"msc3916_authenticated_media_enabled": True}, + } + ) + def test_cannot_download_blocked_media_thumbnail(self) -> None: + """ + Same test as test_cannot_download_blocked_media but for thumbnails. + """ + response = self.make_request( + "GET", + f"/_matrix/client/unstable/org.matrix.msc3916/media/thumbnail/evil.com/{self.remote_media_id}?width=100&height=100", + shorthand=False, + content={"width": 100, "height": 100}, + access_token=self.tok, + ) + self.assertEqual(response.code, 404) + + @override_config( + { + # Disable downloads from a domain we won't be requesting downloads from. + # This proves we haven't broken anything. + "prevent_media_downloads_from": ["not-listed.com"], + "dynamic_thumbnails": True, + "experimental_features": {"msc3916_authenticated_media_enabled": True}, + } + ) + def test_remote_media_thumbnail_normally_unblocked(self) -> None: + """ + Same test as test_remote_media_normally_unblocked but for thumbnails. + """ + response = self.make_request( + "GET", + f"/_matrix/client/unstable/org.matrix.msc3916/media/thumbnail/evil.com/{self.remote_media_id}?width=100&height=100", + shorthand=False, + access_token=self.tok, + ) + self.assertEqual(response.code, 200) + + +class UnstableURLPreviewTests(unittest.HomeserverTestCase): + if not lxml: + skip = "url preview feature requires lxml" + + servlets = [media.register_servlets] + hijack_auth = True + user_id = "@test:user" + end_content = ( + b"<html><head>" + b'<meta property="og:title" content="~matrix~" />' + b'<meta property="og:description" content="hi" />' + b"</head></html>" + ) + + def make_homeserver(self, reactor: MemoryReactor, clock: Clock) -> HomeServer: + config = self.default_config() + config["experimental_features"] = {"msc3916_authenticated_media_enabled": True} + config["url_preview_enabled"] = True + config["max_spider_size"] = 9999999 + config["url_preview_ip_range_blacklist"] = ( + "192.168.1.1", + "1.0.0.0/8", + "3fff:ffff:ffff:ffff:ffff:ffff:ffff:ffff", + "2001:800::/21", + ) + config["url_preview_ip_range_whitelist"] = ("1.1.1.1",) + config["url_preview_accept_language"] = [ + "en-UK", + "en-US;q=0.9", + "fr;q=0.8", + "*;q=0.7", + ] + + self.storage_path = self.mktemp() + self.media_store_path = self.mktemp() + os.mkdir(self.storage_path) + os.mkdir(self.media_store_path) + config["media_store_path"] = self.media_store_path + + provider_config = { + "module": "synapse.media.storage_provider.FileStorageProviderBackend", + "store_local": True, + "store_synchronous": False, + "store_remote": True, + "config": {"directory": self.storage_path}, + } + + config["media_storage_providers"] = [provider_config] + + hs = self.setup_test_homeserver(config=config) + + # After the hs is created, modify the parsed oEmbed config (to avoid + # messing with files). + # + # Note that HTTP URLs are used to avoid having to deal with TLS in tests. + hs.config.oembed.oembed_patterns = [ + OEmbedEndpointConfig( + api_endpoint="http://publish.twitter.com/oembed", + url_patterns=[ + re.compile(r"http://twitter\.com/.+/status/.+"), + ], + formats=None, + ), + OEmbedEndpointConfig( + api_endpoint="http://www.hulu.com/api/oembed.{format}", + url_patterns=[ + re.compile(r"http://www\.hulu\.com/watch/.+"), + ], + formats=["json"], + ), + ] + + return hs + + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: + self.media_repo = hs.get_media_repository() + assert self.media_repo.url_previewer is not None + self.url_previewer = self.media_repo.url_previewer + + self.lookups: Dict[str, Any] = {} + + class Resolver: + def resolveHostName( + _self, + resolutionReceiver: IResolutionReceiver, + hostName: str, + portNumber: int = 0, + addressTypes: Optional[Sequence[Type[IAddress]]] = None, + transportSemantics: str = "TCP", + ) -> IResolutionReceiver: + resolution = HostResolution(hostName) + resolutionReceiver.resolutionBegan(resolution) + if hostName not in self.lookups: + raise DNSLookupError("OH NO") + + for i in self.lookups[hostName]: + resolutionReceiver.addressResolved(i[0]("TCP", i[1], portNumber)) + resolutionReceiver.resolutionComplete() + return resolutionReceiver + + self.reactor.nameResolver = Resolver() # type: ignore[assignment] + + def create_resource_dict(self) -> Dict[str, Resource]: + """Create a resource tree for the test server + + A resource tree is a mapping from path to twisted.web.resource. + + The default implementation creates a JsonResource and calls each function in + `servlets` to register servlets against it. + """ + resources = super().create_resource_dict() + resources["/_matrix/media"] = self.hs.get_media_repository_resource() + return resources + + def _assert_small_png(self, json_body: JsonDict) -> None: + """Assert properties from the SMALL_PNG test image.""" + self.assertTrue(json_body["og:image"].startswith("mxc://")) + self.assertEqual(json_body["og:image:height"], 1) + self.assertEqual(json_body["og:image:width"], 1) + self.assertEqual(json_body["og:image:type"], "image/png") + self.assertEqual(json_body["matrix:image:size"], 67) + + def test_cache_returns_correct_type(self) -> None: + self.lookups["matrix.org"] = [(IPv4Address, "10.1.2.3")] + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://matrix.org", + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\nContent-Type: text/html\r\n\r\n" + % (len(self.end_content),) + + self.end_content + ) + + self.pump() + self.assertEqual(channel.code, 200) + self.assertEqual( + channel.json_body, {"og:title": "~matrix~", "og:description": "hi"} + ) + + # Check the cache returns the correct response + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://matrix.org", + shorthand=False, + ) + + # Check the cache response has the same content + self.assertEqual(channel.code, 200) + self.assertEqual( + channel.json_body, {"og:title": "~matrix~", "og:description": "hi"} + ) + + # Clear the in-memory cache + self.assertIn("http://matrix.org", self.url_previewer._cache) + self.url_previewer._cache.pop("http://matrix.org") + self.assertNotIn("http://matrix.org", self.url_previewer._cache) + + # Check the database cache returns the correct response + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://matrix.org", + shorthand=False, + ) + + # Check the cache response has the same content + self.assertEqual(channel.code, 200) + self.assertEqual( + channel.json_body, {"og:title": "~matrix~", "og:description": "hi"} + ) + + def test_non_ascii_preview_httpequiv(self) -> None: + self.lookups["matrix.org"] = [(IPv4Address, "10.1.2.3")] + + end_content = ( + b"<html><head>" + b'<meta http-equiv="Content-Type" content="text/html; charset=windows-1251"/>' + b'<meta property="og:title" content="\xe4\xea\xe0" />' + b'<meta property="og:description" content="hi" />' + b"</head></html>" + ) + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://matrix.org", + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b'Content-Type: text/html; charset="utf8"\r\n\r\n' + ) + % (len(end_content),) + + end_content + ) + + self.pump() + self.assertEqual(channel.code, 200) + self.assertEqual(channel.json_body["og:title"], "\u0434\u043a\u0430") + + def test_video_rejected(self) -> None: + self.lookups["matrix.org"] = [(IPv4Address, "10.1.2.3")] + + end_content = b"anything" + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://matrix.org", + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b"Content-Type: video/mp4\r\n\r\n" + ) + % (len(end_content)) + + end_content + ) + + self.pump() + self.assertEqual(channel.code, 502) + self.assertEqual( + channel.json_body, + { + "errcode": "M_UNKNOWN", + "error": "Requested file's content type not allowed for this operation: video/mp4", + }, + ) + + def test_audio_rejected(self) -> None: + self.lookups["matrix.org"] = [(IPv4Address, "10.1.2.3")] + + end_content = b"anything" + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://matrix.org", + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b"Content-Type: audio/aac\r\n\r\n" + ) + % (len(end_content)) + + end_content + ) + + self.pump() + self.assertEqual(channel.code, 502) + self.assertEqual( + channel.json_body, + { + "errcode": "M_UNKNOWN", + "error": "Requested file's content type not allowed for this operation: audio/aac", + }, + ) + + def test_non_ascii_preview_content_type(self) -> None: + self.lookups["matrix.org"] = [(IPv4Address, "10.1.2.3")] + + end_content = ( + b"<html><head>" + b'<meta property="og:title" content="\xe4\xea\xe0" />' + b'<meta property="og:description" content="hi" />' + b"</head></html>" + ) + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://matrix.org", + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b'Content-Type: text/html; charset="windows-1251"\r\n\r\n' + ) + % (len(end_content),) + + end_content + ) + + self.pump() + self.assertEqual(channel.code, 200) + self.assertEqual(channel.json_body["og:title"], "\u0434\u043a\u0430") + + def test_overlong_title(self) -> None: + self.lookups["matrix.org"] = [(IPv4Address, "10.1.2.3")] + + end_content = ( + b"<html><head>" + b"<title>" + b"x" * 2000 + b"</title>" + b'<meta property="og:description" content="hi" />' + b"</head></html>" + ) + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://matrix.org", + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b'Content-Type: text/html; charset="windows-1251"\r\n\r\n' + ) + % (len(end_content),) + + end_content + ) + + self.pump() + self.assertEqual(channel.code, 200) + res = channel.json_body + # We should only see the `og:description` field, as `title` is too long and should be stripped out + self.assertCountEqual(["og:description"], res.keys()) + + def test_ipaddr(self) -> None: + """ + IP addresses can be previewed directly. + """ + self.lookups["example.com"] = [(IPv4Address, "10.1.2.3")] + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://example.com", + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\nContent-Type: text/html\r\n\r\n" + % (len(self.end_content),) + + self.end_content + ) + + self.pump() + self.assertEqual(channel.code, 200) + self.assertEqual( + channel.json_body, {"og:title": "~matrix~", "og:description": "hi"} + ) + + def test_blocked_ip_specific(self) -> None: + """ + Blocked IP addresses, found via DNS, are not spidered. + """ + self.lookups["example.com"] = [(IPv4Address, "192.168.1.1")] + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://example.com", + shorthand=False, + ) + + # No requests made. + self.assertEqual(len(self.reactor.tcpClients), 0) + self.assertEqual(channel.code, 502) + self.assertEqual( + channel.json_body, + { + "errcode": "M_UNKNOWN", + "error": "DNS resolution failure during URL preview generation", + }, + ) + + def test_blocked_ip_range(self) -> None: + """ + Blocked IP ranges, IPs found over DNS, are not spidered. + """ + self.lookups["example.com"] = [(IPv4Address, "1.1.1.2")] + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://example.com", + shorthand=False, + ) + + self.assertEqual(channel.code, 502) + self.assertEqual( + channel.json_body, + { + "errcode": "M_UNKNOWN", + "error": "DNS resolution failure during URL preview generation", + }, + ) + + def test_blocked_ip_specific_direct(self) -> None: + """ + Blocked IP addresses, accessed directly, are not spidered. + """ + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://192.168.1.1", + shorthand=False, + ) + + # No requests made. + self.assertEqual(len(self.reactor.tcpClients), 0) + self.assertEqual( + channel.json_body, + {"errcode": "M_UNKNOWN", "error": "IP address blocked"}, + ) + self.assertEqual(channel.code, 403) + + def test_blocked_ip_range_direct(self) -> None: + """ + Blocked IP ranges, accessed directly, are not spidered. + """ + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://1.1.1.2", + shorthand=False, + ) + + self.assertEqual(channel.code, 403) + self.assertEqual( + channel.json_body, + {"errcode": "M_UNKNOWN", "error": "IP address blocked"}, + ) + + def test_blocked_ip_range_whitelisted_ip(self) -> None: + """ + Blocked but then subsequently whitelisted IP addresses can be + spidered. + """ + self.lookups["example.com"] = [(IPv4Address, "1.1.1.1")] + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://example.com", + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + + client.dataReceived( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\nContent-Type: text/html\r\n\r\n" + % (len(self.end_content),) + + self.end_content + ) + + self.pump() + self.assertEqual(channel.code, 200) + self.assertEqual( + channel.json_body, {"og:title": "~matrix~", "og:description": "hi"} + ) + + def test_blocked_ip_with_external_ip(self) -> None: + """ + If a hostname resolves a blocked IP, even if there's a non-blocked one, + it will be rejected. + """ + # Hardcode the URL resolving to the IP we want. + self.lookups["example.com"] = [ + (IPv4Address, "1.1.1.2"), + (IPv4Address, "10.1.2.3"), + ] + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://example.com", + shorthand=False, + ) + self.assertEqual(channel.code, 502) + self.assertEqual( + channel.json_body, + { + "errcode": "M_UNKNOWN", + "error": "DNS resolution failure during URL preview generation", + }, + ) + + def test_blocked_ipv6_specific(self) -> None: + """ + Blocked IP addresses, found via DNS, are not spidered. + """ + self.lookups["example.com"] = [ + (IPv6Address, "3fff:ffff:ffff:ffff:ffff:ffff:ffff:ffff") + ] + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://example.com", + shorthand=False, + ) + + # No requests made. + self.assertEqual(len(self.reactor.tcpClients), 0) + self.assertEqual(channel.code, 502) + self.assertEqual( + channel.json_body, + { + "errcode": "M_UNKNOWN", + "error": "DNS resolution failure during URL preview generation", + }, + ) + + def test_blocked_ipv6_range(self) -> None: + """ + Blocked IP ranges, IPs found over DNS, are not spidered. + """ + self.lookups["example.com"] = [(IPv6Address, "2001:800::1")] + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://example.com", + shorthand=False, + ) + + self.assertEqual(channel.code, 502) + self.assertEqual( + channel.json_body, + { + "errcode": "M_UNKNOWN", + "error": "DNS resolution failure during URL preview generation", + }, + ) + + def test_OPTIONS(self) -> None: + """ + OPTIONS returns the OPTIONS. + """ + channel = self.make_request( + "OPTIONS", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://example.com", + shorthand=False, + ) + self.assertEqual(channel.code, 204) + + def test_accept_language_config_option(self) -> None: + """ + Accept-Language header is sent to the remote server + """ + self.lookups["example.com"] = [(IPv4Address, "10.1.2.3")] + + # Build and make a request to the server + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://example.com", + shorthand=False, + await_result=False, + ) + self.pump() + + # Extract Synapse's tcp client + client = self.reactor.tcpClients[0][2].buildProtocol(None) + + # Build a fake remote server to reply with + server = AccumulatingProtocol() + + # Connect the two together + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + + # Tell Synapse that it has received some data from the remote server + client.dataReceived( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\nContent-Type: text/html\r\n\r\n" + % (len(self.end_content),) + + self.end_content + ) + + # Move the reactor along until we get a response on our original channel + self.pump() + self.assertEqual(channel.code, 200) + self.assertEqual( + channel.json_body, {"og:title": "~matrix~", "og:description": "hi"} + ) + + # Check that the server received the Accept-Language header as part + # of the request from Synapse + self.assertIn( + ( + b"Accept-Language: en-UK\r\n" + b"Accept-Language: en-US;q=0.9\r\n" + b"Accept-Language: fr;q=0.8\r\n" + b"Accept-Language: *;q=0.7" + ), + server.data, + ) + + def test_image(self) -> None: + """An image should be precached if mentioned in the HTML.""" + self.lookups["matrix.org"] = [(IPv4Address, "10.1.2.3")] + self.lookups["cdn.matrix.org"] = [(IPv4Address, "10.1.2.4")] + + result = ( + b"""<html><body><img src="http://cdn.matrix.org/foo.png"></body></html>""" + ) + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://matrix.org", + shorthand=False, + await_result=False, + ) + self.pump() + + # Respond with the HTML. + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b'Content-Type: text/html; charset="utf8"\r\n\r\n' + ) + % (len(result),) + + result + ) + self.pump() + + # Respond with the photo. + client = self.reactor.tcpClients[1][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b"Content-Type: image/png\r\n\r\n" + ) + % (len(SMALL_PNG),) + + SMALL_PNG + ) + self.pump() + + # The image should be in the result. + self.assertEqual(channel.code, 200) + self._assert_small_png(channel.json_body) + + def test_nonexistent_image(self) -> None: + """If the preview image doesn't exist, ensure some data is returned.""" + self.lookups["matrix.org"] = [(IPv4Address, "10.1.2.3")] + + result = ( + b"""<html><body><img src="http://cdn.matrix.org/foo.jpg"></body></html>""" + ) + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://matrix.org", + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b'Content-Type: text/html; charset="utf8"\r\n\r\n' + ) + % (len(result),) + + result + ) + + self.pump() + + # There should not be a second connection. + self.assertEqual(len(self.reactor.tcpClients), 1) + + # The image should not be in the result. + self.assertEqual(channel.code, 200) + self.assertNotIn("og:image", channel.json_body) + + @unittest.override_config( + {"url_preview_url_blacklist": [{"netloc": "cdn.matrix.org"}]} + ) + def test_image_blocked(self) -> None: + """If the preview image doesn't exist, ensure some data is returned.""" + self.lookups["matrix.org"] = [(IPv4Address, "10.1.2.3")] + self.lookups["cdn.matrix.org"] = [(IPv4Address, "10.1.2.4")] + + result = ( + b"""<html><body><img src="http://cdn.matrix.org/foo.jpg"></body></html>""" + ) + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://matrix.org", + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b'Content-Type: text/html; charset="utf8"\r\n\r\n' + ) + % (len(result),) + + result + ) + self.pump() + + # There should not be a second connection. + self.assertEqual(len(self.reactor.tcpClients), 1) + + # The image should not be in the result. + self.assertEqual(channel.code, 200) + self.assertNotIn("og:image", channel.json_body) + + def test_oembed_failure(self) -> None: + """If the autodiscovered oEmbed URL fails, ensure some data is returned.""" + self.lookups["matrix.org"] = [(IPv4Address, "10.1.2.3")] + + result = b""" + <title>oEmbed Autodiscovery Fail</title> + <link rel="alternate" type="application/json+oembed" + href="http://example.com/oembed?url=http%3A%2F%2Fmatrix.org&format=json" + title="matrixdotorg" /> + """ + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://matrix.org", + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b'Content-Type: text/html; charset="utf8"\r\n\r\n' + ) + % (len(result),) + + result + ) + + self.pump() + self.assertEqual(channel.code, 200) + + # The image should not be in the result. + self.assertEqual(channel.json_body["og:title"], "oEmbed Autodiscovery Fail") + + def test_data_url(self) -> None: + """ + Requesting to preview a data URL is not supported. + """ + self.lookups["matrix.org"] = [(IPv4Address, "10.1.2.3")] + + data = base64.b64encode(SMALL_PNG).decode() + + query_params = urlencode( + { + "url": f'<html><head><img src="data:image/png;base64,{data}" /></head></html>' + } + ) + + channel = self.make_request( + "GET", + f"/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?{query_params}", + shorthand=False, + ) + self.pump() + + self.assertEqual(channel.code, 500) + + def test_inline_data_url(self) -> None: + """ + An inline image (as a data URL) should be parsed properly. + """ + self.lookups["matrix.org"] = [(IPv4Address, "10.1.2.3")] + + data = base64.b64encode(SMALL_PNG) + + end_content = ( + b"<html><head>" b'<img src="data:image/png;base64,%s" />' b"</head></html>" + ) % (data,) + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://matrix.org", + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b'Content-Type: text/html; charset="utf8"\r\n\r\n' + ) + % (len(end_content),) + + end_content + ) + + self.pump() + self.assertEqual(channel.code, 200) + self._assert_small_png(channel.json_body) + + def test_oembed_photo(self) -> None: + """Test an oEmbed endpoint which returns a 'photo' type which redirects the preview to a new URL.""" + self.lookups["publish.twitter.com"] = [(IPv4Address, "10.1.2.3")] + self.lookups["cdn.twitter.com"] = [(IPv4Address, "10.1.2.3")] + + result = { + "version": "1.0", + "type": "photo", + "url": "http://cdn.twitter.com/matrixdotorg", + } + oembed_content = json.dumps(result).encode("utf-8") + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://twitter.com/matrixdotorg/status/12345", + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b'Content-Type: application/json; charset="utf8"\r\n\r\n' + ) + % (len(oembed_content),) + + oembed_content + ) + + self.pump() + + # Ensure a second request is made to the photo URL. + client = self.reactor.tcpClients[1][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b"Content-Type: image/png\r\n\r\n" + ) + % (len(SMALL_PNG),) + + SMALL_PNG + ) + + self.pump() + + # Ensure the URL is what was requested. + self.assertIn(b"/matrixdotorg", server.data) + + self.assertEqual(channel.code, 200) + body = channel.json_body + self.assertEqual(body["og:url"], "http://twitter.com/matrixdotorg/status/12345") + self._assert_small_png(body) + + def test_oembed_rich(self) -> None: + """Test an oEmbed endpoint which returns HTML content via the 'rich' type.""" + self.lookups["publish.twitter.com"] = [(IPv4Address, "10.1.2.3")] + + result = { + "version": "1.0", + "type": "rich", + # Note that this provides the author, not the title. + "author_name": "Alice", + "html": "<div>Content Preview</div>", + } + end_content = json.dumps(result).encode("utf-8") + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://twitter.com/matrixdotorg/status/12345", + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b'Content-Type: application/json; charset="utf8"\r\n\r\n' + ) + % (len(end_content),) + + end_content + ) + + self.pump() + + # Double check that the proper host is being connected to. (Note that + # twitter.com can't be resolved so this is already implicitly checked.) + self.assertIn(b"\r\nHost: publish.twitter.com\r\n", server.data) + + self.assertEqual(channel.code, 200) + body = channel.json_body + self.assertEqual( + body, + { + "og:url": "http://twitter.com/matrixdotorg/status/12345", + "og:title": "Alice", + "og:description": "Content Preview", + }, + ) + + def test_oembed_format(self) -> None: + """Test an oEmbed endpoint which requires the format in the URL.""" + self.lookups["www.hulu.com"] = [(IPv4Address, "10.1.2.3")] + + result = { + "version": "1.0", + "type": "rich", + "html": "<div>Content Preview</div>", + } + end_content = json.dumps(result).encode("utf-8") + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://www.hulu.com/watch/12345", + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b'Content-Type: application/json; charset="utf8"\r\n\r\n' + ) + % (len(end_content),) + + end_content + ) + + self.pump() + + # The {format} should have been turned into json. + self.assertIn(b"/api/oembed.json", server.data) + # A URL parameter of format=json should be provided. + self.assertIn(b"format=json", server.data) + + self.assertEqual(channel.code, 200) + body = channel.json_body + self.assertEqual( + body, + { + "og:url": "http://www.hulu.com/watch/12345", + "og:description": "Content Preview", + }, + ) + + @unittest.override_config( + {"url_preview_url_blacklist": [{"netloc": "publish.twitter.com"}]} + ) + def test_oembed_blocked(self) -> None: + """The oEmbed URL should not be downloaded if the oEmbed URL is blocked.""" + self.lookups["twitter.com"] = [(IPv4Address, "10.1.2.3")] + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://twitter.com/matrixdotorg/status/12345", + shorthand=False, + await_result=False, + ) + self.pump() + self.assertEqual(channel.code, 403, channel.result) + + def test_oembed_autodiscovery(self) -> None: + """ + Autodiscovery works by finding the link in the HTML response and then requesting an oEmbed URL. + 1. Request a preview of a URL which is not known to the oEmbed code. + 2. It returns HTML including a link to an oEmbed preview. + 3. The oEmbed preview is requested and returns a URL for an image. + 4. The image is requested for thumbnailing. + """ + # This is a little cheesy in that we use the www subdomain (which isn't the + # list of oEmbed patterns) to get "raw" HTML response. + self.lookups["www.twitter.com"] = [(IPv4Address, "10.1.2.3")] + self.lookups["publish.twitter.com"] = [(IPv4Address, "10.1.2.3")] + self.lookups["cdn.twitter.com"] = [(IPv4Address, "10.1.2.3")] + + result = b""" + <link rel="alternate" type="application/json+oembed" + href="http://publish.twitter.com/oembed?url=http%3A%2F%2Fcdn.twitter.com%2Fmatrixdotorg%2Fstatus%2F12345&format=json" + title="matrixdotorg" /> + """ + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://www.twitter.com/matrixdotorg/status/12345", + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b'Content-Type: text/html; charset="utf8"\r\n\r\n' + ) + % (len(result),) + + result + ) + self.pump() + + # The oEmbed response. + result2 = { + "version": "1.0", + "type": "photo", + "url": "http://cdn.twitter.com/matrixdotorg", + } + oembed_content = json.dumps(result2).encode("utf-8") + + # Ensure a second request is made to the oEmbed URL. + client = self.reactor.tcpClients[1][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b'Content-Type: application/json; charset="utf8"\r\n\r\n' + ) + % (len(oembed_content),) + + oembed_content + ) + self.pump() + + # Ensure the URL is what was requested. + self.assertIn(b"/oembed?", server.data) + + # Ensure a third request is made to the photo URL. + client = self.reactor.tcpClients[2][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b"Content-Type: image/png\r\n\r\n" + ) + % (len(SMALL_PNG),) + + SMALL_PNG + ) + self.pump() + + # Ensure the URL is what was requested. + self.assertIn(b"/matrixdotorg", server.data) + + self.assertEqual(channel.code, 200) + body = channel.json_body + self.assertEqual( + body["og:url"], "http://www.twitter.com/matrixdotorg/status/12345" + ) + self._assert_small_png(body) + + @unittest.override_config( + {"url_preview_url_blacklist": [{"netloc": "publish.twitter.com"}]} + ) + def test_oembed_autodiscovery_blocked(self) -> None: + """ + If the discovered oEmbed URL is blocked, it should be discarded. + """ + # This is a little cheesy in that we use the www subdomain (which isn't the + # list of oEmbed patterns) to get "raw" HTML response. + self.lookups["www.twitter.com"] = [(IPv4Address, "10.1.2.3")] + self.lookups["publish.twitter.com"] = [(IPv4Address, "10.1.2.4")] + + result = b""" + <title>Test</title> + <link rel="alternate" type="application/json+oembed" + href="http://publish.twitter.com/oembed?url=http%3A%2F%2Fcdn.twitter.com%2Fmatrixdotorg%2Fstatus%2F12345&format=json" + title="matrixdotorg" /> + """ + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://www.twitter.com/matrixdotorg/status/12345", + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + ( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\n" + b'Content-Type: text/html; charset="utf8"\r\n\r\n' + ) + % (len(result),) + + result + ) + + self.pump() + + # Ensure there's no additional connections. + self.assertEqual(len(self.reactor.tcpClients), 1) + + # Ensure the URL is what was requested. + self.assertIn(b"\r\nHost: www.twitter.com\r\n", server.data) + + self.assertEqual(channel.code, 200) + body = channel.json_body + self.assertEqual(body["og:title"], "Test") + self.assertNotIn("og:image", body) + + def _download_image(self) -> Tuple[str, str]: + """Downloads an image into the URL cache. + Returns: + A (host, media_id) tuple representing the MXC URI of the image. + """ + self.lookups["cdn.twitter.com"] = [(IPv4Address, "10.1.2.3")] + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=http://cdn.twitter.com/matrixdotorg", + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\nContent-Type: image/png\r\n\r\n" + % (len(SMALL_PNG),) + + SMALL_PNG + ) + + self.pump() + self.assertEqual(channel.code, 200) + body = channel.json_body + mxc_uri = body["og:image"] + host, _port, media_id = parse_and_validate_mxc_uri(mxc_uri) + self.assertIsNone(_port) + return host, media_id + + def test_storage_providers_exclude_files(self) -> None: + """Test that files are not stored in or fetched from storage providers.""" + host, media_id = self._download_image() + + rel_file_path = self.media_repo.filepaths.url_cache_filepath_rel(media_id) + media_store_path = os.path.join(self.media_store_path, rel_file_path) + storage_provider_path = os.path.join(self.storage_path, rel_file_path) + + # Check storage + self.assertTrue(os.path.isfile(media_store_path)) + self.assertFalse( + os.path.isfile(storage_provider_path), + "URL cache file was unexpectedly stored in a storage provider", + ) + + # Check fetching + channel = self.make_request( + "GET", + f"/_matrix/media/v3/download/{host}/{media_id}", + shorthand=False, + await_result=False, + ) + self.pump() + self.assertEqual(channel.code, 200) + + # Move cached file into the storage provider + os.makedirs(os.path.dirname(storage_provider_path), exist_ok=True) + os.rename(media_store_path, storage_provider_path) + + channel = self.make_request( + "GET", + f"/_matrix/media/v3/download/{host}/{media_id}", + shorthand=False, + await_result=False, + ) + self.pump() + self.assertEqual( + channel.code, + 404, + "URL cache file was unexpectedly retrieved from a storage provider", + ) + + def test_storage_providers_exclude_thumbnails(self) -> None: + """Test that thumbnails are not stored in or fetched from storage providers.""" + host, media_id = self._download_image() + + rel_thumbnail_path = ( + self.media_repo.filepaths.url_cache_thumbnail_directory_rel(media_id) + ) + media_store_thumbnail_path = os.path.join( + self.media_store_path, rel_thumbnail_path + ) + storage_provider_thumbnail_path = os.path.join( + self.storage_path, rel_thumbnail_path + ) + + # Check storage + self.assertTrue(os.path.isdir(media_store_thumbnail_path)) + self.assertFalse( + os.path.isdir(storage_provider_thumbnail_path), + "URL cache thumbnails were unexpectedly stored in a storage provider", + ) + + # Check fetching + channel = self.make_request( + "GET", + f"/_matrix/client/unstable/org.matrix.msc3916/media/thumbnail/{host}/{media_id}?width=32&height=32&method=scale", + shorthand=False, + await_result=False, + ) + self.pump() + self.assertEqual(channel.code, 200) + + # Remove the original, otherwise thumbnails will regenerate + rel_file_path = self.media_repo.filepaths.url_cache_filepath_rel(media_id) + media_store_path = os.path.join(self.media_store_path, rel_file_path) + os.remove(media_store_path) + + # Move cached thumbnails into the storage provider + os.makedirs(os.path.dirname(storage_provider_thumbnail_path), exist_ok=True) + os.rename(media_store_thumbnail_path, storage_provider_thumbnail_path) + + channel = self.make_request( + "GET", + f"/_matrix/client/unstable/org.matrix.msc3916/media/thumbnail/{host}/{media_id}?width=32&height=32&method=scale", + shorthand=False, + await_result=False, + ) + self.pump() + self.assertEqual( + channel.code, + 404, + "URL cache thumbnail was unexpectedly retrieved from a storage provider", + ) + + def test_cache_expiry(self) -> None: + """Test that URL cache files and thumbnails are cleaned up properly on expiry.""" + _host, media_id = self._download_image() + + file_path = self.media_repo.filepaths.url_cache_filepath(media_id) + file_dirs = self.media_repo.filepaths.url_cache_filepath_dirs_to_delete( + media_id + ) + thumbnail_dir = self.media_repo.filepaths.url_cache_thumbnail_directory( + media_id + ) + thumbnail_dirs = self.media_repo.filepaths.url_cache_thumbnail_dirs_to_delete( + media_id + ) + + self.assertTrue(os.path.isfile(file_path)) + self.assertTrue(os.path.isdir(thumbnail_dir)) + + self.reactor.advance(IMAGE_CACHE_EXPIRY_MS * 1000 + 1) + self.get_success(self.url_previewer._expire_url_cache_data()) + + for path in [file_path] + file_dirs + [thumbnail_dir] + thumbnail_dirs: + self.assertFalse( + os.path.exists(path), + f"{os.path.relpath(path, self.media_store_path)} was not deleted", + ) + + @unittest.override_config({"url_preview_url_blacklist": [{"port": "*"}]}) + def test_blocked_port(self) -> None: + """Tests that blocking URLs with a port makes previewing such URLs + fail with a 403 error and doesn't impact other previews. + """ + self.lookups["matrix.org"] = [(IPv4Address, "10.1.2.3")] + + bad_url = quote("http://matrix.org:8888/foo") + good_url = quote("http://matrix.org/foo") + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=" + + bad_url, + shorthand=False, + await_result=False, + ) + self.pump() + self.assertEqual(channel.code, 403, channel.result) + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=" + + good_url, + shorthand=False, + await_result=False, + ) + self.pump() + + client = self.reactor.tcpClients[0][2].buildProtocol(None) + server = AccumulatingProtocol() + server.makeConnection(FakeTransport(client, self.reactor)) + client.makeConnection(FakeTransport(server, self.reactor)) + client.dataReceived( + b"HTTP/1.0 200 OK\r\nContent-Length: %d\r\nContent-Type: text/html\r\n\r\n" + % (len(self.end_content),) + + self.end_content + ) + + self.pump() + self.assertEqual(channel.code, 200) + + @unittest.override_config( + {"url_preview_url_blacklist": [{"netloc": "example.com"}]} + ) + def test_blocked_url(self) -> None: + """Tests that blocking URLs with a host makes previewing such URLs + fail with a 403 error. + """ + self.lookups["example.com"] = [(IPv4Address, "10.1.2.3")] + + bad_url = quote("http://example.com/foo") + + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/preview_url?url=" + + bad_url, + shorthand=False, + await_result=False, + ) + self.pump() + self.assertEqual(channel.code, 403, channel.result) + + +class UnstableMediaConfigTest(unittest.HomeserverTestCase): + servlets = [ + media.register_servlets, + admin.register_servlets, + login.register_servlets, + ] + + def make_homeserver( + self, reactor: ThreadedMemoryReactorClock, clock: Clock + ) -> HomeServer: + config = self.default_config() + config["experimental_features"] = {"msc3916_authenticated_media_enabled": True} + + self.storage_path = self.mktemp() + self.media_store_path = self.mktemp() + os.mkdir(self.storage_path) + os.mkdir(self.media_store_path) + config["media_store_path"] = self.media_store_path + + provider_config = { + "module": "synapse.media.storage_provider.FileStorageProviderBackend", + "store_local": True, + "store_synchronous": False, + "store_remote": True, + "config": {"directory": self.storage_path}, + } + + config["media_storage_providers"] = [provider_config] + + return self.setup_test_homeserver(config=config) + + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: + self.register_user("user", "password") + self.tok = self.login("user", "password") + + def test_media_config(self) -> None: + channel = self.make_request( + "GET", + "/_matrix/client/unstable/org.matrix.msc3916/media/config", + shorthand=False, + access_token=self.tok, + ) + self.assertEqual(channel.code, 200) + self.assertEqual( + channel.json_body["m.upload.size"], self.hs.config.media.max_upload_size + ) diff --git a/tests/rest/client/test_models.py b/tests/rest/client/test_models.py index 534dd7bcf4..f8a56c80ca 100644 --- a/tests/rest/client/test_models.py +++ b/tests/rest/client/test_models.py @@ -24,7 +24,7 @@ from typing import TYPE_CHECKING from typing_extensions import Literal from synapse._pydantic_compat import HAS_PYDANTIC_V2 -from synapse.rest.client.models import EmailRequestTokenBody +from synapse.types.rest.client import EmailRequestTokenBody if TYPE_CHECKING or HAS_PYDANTIC_V2: from pydantic.v1 import BaseModel, ValidationError diff --git a/tests/rest/client/test_notifications.py b/tests/rest/client/test_notifications.py index e9aa2e450e..e4b0455ce8 100644 --- a/tests/rest/client/test_notifications.py +++ b/tests/rest/client/test_notifications.py @@ -18,6 +18,7 @@ # [This file includes modifications made by New Vector Limited] # # +from typing import List, Optional, Tuple from unittest.mock import AsyncMock, Mock from twisted.test.proto_helpers import MemoryReactor @@ -48,6 +49,14 @@ class HTTPPusherTests(HomeserverTestCase): self.sync_handler = homeserver.get_sync_handler() self.auth_handler = homeserver.get_auth_handler() + self.user_id = self.register_user("user", "pass") + self.access_token = self.login("user", "pass") + self.other_user_id = self.register_user("otheruser", "pass") + self.other_access_token = self.login("otheruser", "pass") + + # Create a room + self.room_id = self.helper.create_room_as(self.user_id, tok=self.access_token) + def make_homeserver(self, reactor: MemoryReactor, clock: Clock) -> HomeServer: # Mock out the calls over federation. fed_transport_client = Mock(spec=["send_transaction"]) @@ -61,32 +70,22 @@ class HTTPPusherTests(HomeserverTestCase): """ Local users will get notified for invites """ - - user_id = self.register_user("user", "pass") - access_token = self.login("user", "pass") - other_user_id = self.register_user("otheruser", "pass") - other_access_token = self.login("otheruser", "pass") - - # Create a room - room = self.helper.create_room_as(user_id, tok=access_token) - # Check we start with no pushes - channel = self.make_request( - "GET", - "/notifications", - access_token=other_access_token, - ) - self.assertEqual(channel.code, 200, channel.result) - self.assertEqual(len(channel.json_body["notifications"]), 0, channel.json_body) + self._request_notifications(from_token=None, limit=1, expected_count=0) # Send an invite - self.helper.invite(room=room, src=user_id, targ=other_user_id, tok=access_token) + self.helper.invite( + room=self.room_id, + src=self.user_id, + targ=self.other_user_id, + tok=self.access_token, + ) # We should have a notification now channel = self.make_request( "GET", "/notifications", - access_token=other_access_token, + access_token=self.other_access_token, ) self.assertEqual(channel.code, 200) self.assertEqual(len(channel.json_body["notifications"]), 1, channel.json_body) @@ -95,3 +94,139 @@ class HTTPPusherTests(HomeserverTestCase): "invite", channel.json_body, ) + + def test_pagination_of_notifications(self) -> None: + """ + Check that pagination of notifications works. + """ + # Check we start with no pushes + self._request_notifications(from_token=None, limit=1, expected_count=0) + + # Send an invite and have the other user join the room. + self.helper.invite( + room=self.room_id, + src=self.user_id, + targ=self.other_user_id, + tok=self.access_token, + ) + self.helper.join(self.room_id, self.other_user_id, tok=self.other_access_token) + + # Send 5 messages in the room and note down their event IDs. + sent_event_ids = [] + for _ in range(5): + resp = self.helper.send_event( + self.room_id, + "m.room.message", + {"body": "honk", "msgtype": "m.text"}, + tok=self.access_token, + ) + sent_event_ids.append(resp["event_id"]) + + # We expect to get notifications for messages in reverse order. + # So reverse this list of event IDs to make it easier to compare + # against later. + sent_event_ids.reverse() + + # We should have a few notifications now. Let's try and fetch the first 2. + notification_event_ids, _ = self._request_notifications( + from_token=None, limit=2, expected_count=2 + ) + + # Check we got the expected event IDs back. + self.assertEqual(notification_event_ids, sent_event_ids[:2]) + + # Try requesting again without a 'from' query parameter. We should get the + # same two notifications back. + notification_event_ids, next_token = self._request_notifications( + from_token=None, limit=2, expected_count=2 + ) + self.assertEqual(notification_event_ids, sent_event_ids[:2]) + + # Ask for the next 5 notifications, though there should only be + # 4 remaining; the next 3 messages and the invite. + # + # We need to use the "next_token" from the response as the "from" + # query parameter in the next request in order to paginate. + notification_event_ids, next_token = self._request_notifications( + from_token=next_token, limit=5, expected_count=4 + ) + # Ensure we chop off the invite on the end. + notification_event_ids = notification_event_ids[:-1] + self.assertEqual(notification_event_ids, sent_event_ids[2:]) + + def _request_notifications( + self, from_token: Optional[str], limit: int, expected_count: int + ) -> Tuple[List[str], str]: + """ + Make a request to /notifications to get the latest events to be notified about. + + Only the event IDs are returned. The request is made by the "other user". + + Args: + from_token: An optional starting parameter. + limit: The maximum number of results to return. + expected_count: The number of events to expect in the response. + + Returns: + A list of event IDs that the client should be notified about. + Events are returned newest-first. + """ + # Construct the request path. + path = f"/notifications?limit={limit}" + if from_token is not None: + path += f"&from={from_token}" + + channel = self.make_request( + "GET", + path, + access_token=self.other_access_token, + ) + + self.assertEqual(channel.code, 200) + self.assertEqual( + len(channel.json_body["notifications"]), expected_count, channel.json_body + ) + + # Extract the necessary data from the response. + next_token = channel.json_body["next_token"] + event_ids = [ + event["event"]["event_id"] for event in channel.json_body["notifications"] + ] + + return event_ids, next_token + + def test_parameters(self) -> None: + """ + Test that appropriate errors are returned when query parameters are malformed. + """ + # Test that no parameters are required. + channel = self.make_request( + "GET", + "/notifications", + access_token=self.other_access_token, + ) + self.assertEqual(channel.code, 200) + + # Test that limit cannot be negative + channel = self.make_request( + "GET", + "/notifications?limit=-1", + access_token=self.other_access_token, + ) + self.assertEqual(channel.code, 400) + + # Test that the 'limit' parameter must be an integer. + channel = self.make_request( + "GET", + "/notifications?limit=foobar", + access_token=self.other_access_token, + ) + self.assertEqual(channel.code, 400) + + # Test that the 'from' parameter must be an integer. + channel = self.make_request( + "GET", + "/notifications?from=osborne", + access_token=self.other_access_token, + ) + self.assertEqual(channel.code, 400) diff --git a/tests/rest/client/test_report_event.py b/tests/rest/client/test_reporting.py index 5903771e52..009deb9cb0 100644 --- a/tests/rest/client/test_report_event.py +++ b/tests/rest/client/test_reporting.py @@ -22,7 +22,7 @@ from twisted.test.proto_helpers import MemoryReactor import synapse.rest.admin -from synapse.rest.client import login, report_event, room +from synapse.rest.client import login, reporting, room from synapse.server import HomeServer from synapse.types import JsonDict from synapse.util import Clock @@ -35,7 +35,7 @@ class ReportEventTestCase(unittest.HomeserverTestCase): synapse.rest.admin.register_servlets, login.register_servlets, room.register_servlets, - report_event.register_servlets, + reporting.register_servlets, ] def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: @@ -139,3 +139,92 @@ class ReportEventTestCase(unittest.HomeserverTestCase): "POST", self.report_path, data, access_token=self.other_user_tok ) self.assertEqual(response_status, channel.code, msg=channel.result["body"]) + + +class ReportRoomTestCase(unittest.HomeserverTestCase): + servlets = [ + synapse.rest.admin.register_servlets, + login.register_servlets, + room.register_servlets, + reporting.register_servlets, + ] + + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: + self.other_user = self.register_user("user", "pass") + self.other_user_tok = self.login("user", "pass") + + self.room_id = self.helper.create_room_as( + self.other_user, tok=self.other_user_tok, is_public=True + ) + self.report_path = ( + f"/_matrix/client/unstable/org.matrix.msc4151/rooms/{self.room_id}/report" + ) + + @unittest.override_config( + { + "experimental_features": {"msc4151_enabled": True}, + } + ) + def test_reason_str(self) -> None: + data = {"reason": "this makes me sad"} + self._assert_status(200, data) + + @unittest.override_config( + { + "experimental_features": {"msc4151_enabled": True}, + } + ) + def test_no_reason(self) -> None: + data = {"not_reason": "for typechecking"} + self._assert_status(400, data) + + @unittest.override_config( + { + "experimental_features": {"msc4151_enabled": True}, + } + ) + def test_reason_nonstring(self) -> None: + data = {"reason": 42} + self._assert_status(400, data) + + @unittest.override_config( + { + "experimental_features": {"msc4151_enabled": True}, + } + ) + def test_reason_null(self) -> None: + data = {"reason": None} + self._assert_status(400, data) + + @unittest.override_config( + { + "experimental_features": {"msc4151_enabled": True}, + } + ) + def test_cannot_report_nonexistent_room(self) -> None: + """ + Tests that we don't accept event reports for rooms which do not exist. + """ + channel = self.make_request( + "POST", + "/_matrix/client/unstable/org.matrix.msc4151/rooms/!bloop:example.org/report", + {"reason": "i am very sad"}, + access_token=self.other_user_tok, + shorthand=False, + ) + self.assertEqual(404, channel.code, msg=channel.result["body"]) + self.assertEqual( + "Room does not exist", + channel.json_body["error"], + msg=channel.result["body"], + ) + + def _assert_status(self, response_status: int, data: JsonDict) -> None: + channel = self.make_request( + "POST", + self.report_path, + data, + access_token=self.other_user_tok, + shorthand=False, + ) + self.assertEqual(response_status, channel.code, msg=channel.result["body"]) diff --git a/tests/rest/client/test_retention.py b/tests/rest/client/test_retention.py index ceae40498e..1e5a1b0a4d 100644 --- a/tests/rest/client/test_retention.py +++ b/tests/rest/client/test_retention.py @@ -167,7 +167,6 @@ class RetentionTestCase(unittest.HomeserverTestCase): storage_controllers, self.user_id, events, - msc4115_membership_on_events=True, ) ) diff --git a/tests/rest/client/test_rooms.py b/tests/rest/client/test_rooms.py index d398cead1c..c559dfda83 100644 --- a/tests/rest/client/test_rooms.py +++ b/tests/rest/client/test_rooms.py @@ -3819,3 +3819,108 @@ class TimestampLookupTestCase(unittest.HomeserverTestCase): # Make sure the outlier event is not returned self.assertNotEqual(channel.json_body["event_id"], outlier_event.event_id) + + +class UserSuspensionTests(unittest.HomeserverTestCase): + servlets = [ + admin.register_servlets, + login.register_servlets, + room.register_servlets, + profile.register_servlets, + ] + + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: + self.user1 = self.register_user("thomas", "hackme") + self.tok1 = self.login("thomas", "hackme") + + self.user2 = self.register_user("teresa", "hackme") + self.tok2 = self.login("teresa", "hackme") + + self.room1 = self.helper.create_room_as(room_creator=self.user1, tok=self.tok1) + self.store = hs.get_datastores().main + + def test_suspended_user_cannot_send_message_to_room(self) -> None: + # set the user as suspended + self.get_success(self.store.set_user_suspended_status(self.user1, True)) + + channel = self.make_request( + "PUT", + f"/rooms/{self.room1}/send/m.room.message/1", + access_token=self.tok1, + content={"body": "hello", "msgtype": "m.text"}, + ) + self.assertEqual( + channel.json_body["errcode"], "ORG.MATRIX.MSC3823.USER_ACCOUNT_SUSPENDED" + ) + + def test_suspended_user_cannot_change_profile_data(self) -> None: + # set the user as suspended + self.get_success(self.store.set_user_suspended_status(self.user1, True)) + + channel = self.make_request( + "PUT", + f"/_matrix/client/v3/profile/{self.user1}/avatar_url", + access_token=self.tok1, + content={"avatar_url": "mxc://matrix.org/wefh34uihSDRGhw34"}, + shorthand=False, + ) + self.assertEqual( + channel.json_body["errcode"], "ORG.MATRIX.MSC3823.USER_ACCOUNT_SUSPENDED" + ) + + channel2 = self.make_request( + "PUT", + f"/_matrix/client/v3/profile/{self.user1}/displayname", + access_token=self.tok1, + content={"displayname": "something offensive"}, + shorthand=False, + ) + self.assertEqual( + channel2.json_body["errcode"], "ORG.MATRIX.MSC3823.USER_ACCOUNT_SUSPENDED" + ) + + def test_suspended_user_cannot_redact_messages_other_than_their_own(self) -> None: + # first user sends message + self.make_request("POST", f"/rooms/{self.room1}/join", access_token=self.tok2) + res = self.helper.send_event( + self.room1, + "m.room.message", + {"body": "hello", "msgtype": "m.text"}, + tok=self.tok2, + ) + event_id = res["event_id"] + + # second user sends message + self.make_request("POST", f"/rooms/{self.room1}/join", access_token=self.tok1) + res2 = self.helper.send_event( + self.room1, + "m.room.message", + {"body": "bad_message", "msgtype": "m.text"}, + tok=self.tok1, + ) + event_id2 = res2["event_id"] + + # set the second user as suspended + self.get_success(self.store.set_user_suspended_status(self.user1, True)) + + # second user can't redact first user's message + channel = self.make_request( + "PUT", + f"/_matrix/client/v3/rooms/{self.room1}/redact/{event_id}/1", + access_token=self.tok1, + content={"reason": "bogus"}, + shorthand=False, + ) + self.assertEqual( + channel.json_body["errcode"], "ORG.MATRIX.MSC3823.USER_ACCOUNT_SUSPENDED" + ) + + # but can redact their own + channel = self.make_request( + "PUT", + f"/_matrix/client/v3/rooms/{self.room1}/redact/{event_id2}/1", + access_token=self.tok1, + content={"reason": "bogus"}, + shorthand=False, + ) + self.assertEqual(channel.code, 200) diff --git a/tests/rest/client/test_sendtodevice.py b/tests/rest/client/test_sendtodevice.py index 2f994ad553..5ef501c6d5 100644 --- a/tests/rest/client/test_sendtodevice.py +++ b/tests/rest/client/test_sendtodevice.py @@ -18,15 +18,39 @@ # [This file includes modifications made by New Vector Limited] # # +from parameterized import parameterized_class from synapse.api.constants import EduTypes from synapse.rest import admin from synapse.rest.client import login, sendtodevice, sync +from synapse.types import JsonDict from tests.unittest import HomeserverTestCase, override_config +@parameterized_class( + ("sync_endpoint", "experimental_features"), + [ + ("/sync", {}), + ( + "/_matrix/client/unstable/org.matrix.msc3575/sync/e2ee", + # Enable sliding sync + {"msc3575_enabled": True}, + ), + ], +) class SendToDeviceTestCase(HomeserverTestCase): + """ + Test `/sendToDevice` will deliver messages across to people receiving them over `/sync`. + + Attributes: + sync_endpoint: The endpoint under test to use for syncing. + experimental_features: The experimental features homeserver config to use. + """ + + sync_endpoint: str + experimental_features: JsonDict + servlets = [ admin.register_servlets, login.register_servlets, @@ -34,6 +58,11 @@ class SendToDeviceTestCase(HomeserverTestCase): sync.register_servlets, ] + def default_config(self) -> JsonDict: + config = super().default_config() + config["experimental_features"] = self.experimental_features + return config + def test_user_to_user(self) -> None: """A to-device message from one user to another should get delivered""" @@ -54,7 +83,7 @@ class SendToDeviceTestCase(HomeserverTestCase): self.assertEqual(chan.code, 200, chan.result) # check it appears - channel = self.make_request("GET", "/sync", access_token=user2_tok) + channel = self.make_request("GET", self.sync_endpoint, access_token=user2_tok) self.assertEqual(channel.code, 200, channel.result) expected_result = { "events": [ @@ -67,15 +96,19 @@ class SendToDeviceTestCase(HomeserverTestCase): } self.assertEqual(channel.json_body["to_device"], expected_result) - # it should re-appear if we do another sync - channel = self.make_request("GET", "/sync", access_token=user2_tok) + # it should re-appear if we do another sync because the to-device message is not + # deleted until we acknowledge it by sending a `?since=...` parameter in the + # next sync request corresponding to the `next_batch` value from the response. + channel = self.make_request("GET", self.sync_endpoint, access_token=user2_tok) self.assertEqual(channel.code, 200, channel.result) self.assertEqual(channel.json_body["to_device"], expected_result) # it should *not* appear if we do an incremental sync sync_token = channel.json_body["next_batch"] channel = self.make_request( - "GET", f"/sync?since={sync_token}", access_token=user2_tok + "GET", + f"{self.sync_endpoint}?since={sync_token}", + access_token=user2_tok, ) self.assertEqual(channel.code, 200, channel.result) self.assertEqual(channel.json_body.get("to_device", {}).get("events", []), []) @@ -99,15 +132,19 @@ class SendToDeviceTestCase(HomeserverTestCase): ) self.assertEqual(chan.code, 200, chan.result) - # now sync: we should get two of the three - channel = self.make_request("GET", "/sync", access_token=user2_tok) + # now sync: we should get two of the three (because burst_count=2) + channel = self.make_request("GET", self.sync_endpoint, access_token=user2_tok) self.assertEqual(channel.code, 200, channel.result) msgs = channel.json_body["to_device"]["events"] self.assertEqual(len(msgs), 2) for i in range(2): self.assertEqual( msgs[i], - {"sender": user1, "type": "m.room_key_request", "content": {"idx": i}}, + { + "sender": user1, + "type": "m.room_key_request", + "content": {"idx": i}, + }, ) sync_token = channel.json_body["next_batch"] @@ -125,7 +162,9 @@ class SendToDeviceTestCase(HomeserverTestCase): # ... which should arrive channel = self.make_request( - "GET", f"/sync?since={sync_token}", access_token=user2_tok + "GET", + f"{self.sync_endpoint}?since={sync_token}", + access_token=user2_tok, ) self.assertEqual(channel.code, 200, channel.result) msgs = channel.json_body["to_device"]["events"] @@ -159,7 +198,7 @@ class SendToDeviceTestCase(HomeserverTestCase): ) # now sync: we should get two of the three - channel = self.make_request("GET", "/sync", access_token=user2_tok) + channel = self.make_request("GET", self.sync_endpoint, access_token=user2_tok) self.assertEqual(channel.code, 200, channel.result) msgs = channel.json_body["to_device"]["events"] self.assertEqual(len(msgs), 2) @@ -193,7 +232,9 @@ class SendToDeviceTestCase(HomeserverTestCase): # ... which should arrive channel = self.make_request( - "GET", f"/sync?since={sync_token}", access_token=user2_tok + "GET", + f"{self.sync_endpoint}?since={sync_token}", + access_token=user2_tok, ) self.assertEqual(channel.code, 200, channel.result) msgs = channel.json_body["to_device"]["events"] @@ -217,7 +258,7 @@ class SendToDeviceTestCase(HomeserverTestCase): user2_tok = self.login("u2", "pass", "d2") # Do an initial sync - channel = self.make_request("GET", "/sync", access_token=user2_tok) + channel = self.make_request("GET", self.sync_endpoint, access_token=user2_tok) self.assertEqual(channel.code, 200, channel.result) sync_token = channel.json_body["next_batch"] @@ -233,7 +274,9 @@ class SendToDeviceTestCase(HomeserverTestCase): self.assertEqual(chan.code, 200, chan.result) channel = self.make_request( - "GET", f"/sync?since={sync_token}&timeout=300000", access_token=user2_tok + "GET", + f"{self.sync_endpoint}?since={sync_token}&timeout=300000", + access_token=user2_tok, ) self.assertEqual(channel.code, 200, channel.result) messages = channel.json_body.get("to_device", {}).get("events", []) @@ -241,7 +284,9 @@ class SendToDeviceTestCase(HomeserverTestCase): sync_token = channel.json_body["next_batch"] channel = self.make_request( - "GET", f"/sync?since={sync_token}&timeout=300000", access_token=user2_tok + "GET", + f"{self.sync_endpoint}?since={sync_token}&timeout=300000", + access_token=user2_tok, ) self.assertEqual(channel.code, 200, channel.result) messages = channel.json_body.get("to_device", {}).get("events", []) diff --git a/tests/rest/client/test_sync.py b/tests/rest/client/test_sync.py index 417a87feb2..bfb26139d3 100644 --- a/tests/rest/client/test_sync.py +++ b/tests/rest/client/test_sync.py @@ -19,14 +19,16 @@ # # import json -from typing import List +import logging +from typing import Dict, List -from parameterized import parameterized +from parameterized import parameterized, parameterized_class from twisted.test.proto_helpers import MemoryReactor import synapse.rest.admin from synapse.api.constants import ( + AccountDataTypes, EventContentFields, EventTypes, ReceiptTypes, @@ -34,7 +36,7 @@ from synapse.api.constants import ( ) from synapse.rest.client import devices, knock, login, read_marker, receipts, room, sync from synapse.server import HomeServer -from synapse.types import JsonDict +from synapse.types import JsonDict, RoomStreamToken, StreamKeyType from synapse.util import Clock from tests import unittest @@ -43,6 +45,8 @@ from tests.federation.transport.test_knocking import ( ) from tests.server import TimedOutException +logger = logging.getLogger(__name__) + class FilterTestCase(unittest.HomeserverTestCase): user_id = "@apple:test" @@ -688,24 +692,180 @@ class SyncCacheTestCase(unittest.HomeserverTestCase): self.assertEqual(channel.code, 200, channel.json_body) +@parameterized_class( + ("sync_endpoint", "experimental_features"), + [ + ("/sync", {}), + ( + "/_matrix/client/unstable/org.matrix.msc3575/sync/e2ee", + # Enable sliding sync + {"msc3575_enabled": True}, + ), + ], +) class DeviceListSyncTestCase(unittest.HomeserverTestCase): + """ + Tests regarding device list (`device_lists`) changes. + + Attributes: + sync_endpoint: The endpoint under test to use for syncing. + experimental_features: The experimental features homeserver config to use. + """ + + sync_endpoint: str + experimental_features: JsonDict + servlets = [ synapse.rest.admin.register_servlets, login.register_servlets, + room.register_servlets, sync.register_servlets, devices.register_servlets, ] + def default_config(self) -> JsonDict: + config = super().default_config() + config["experimental_features"] = self.experimental_features + return config + + def test_receiving_local_device_list_changes(self) -> None: + """Tests that a local users that share a room receive each other's device list + changes. + """ + # Register two users + test_device_id = "TESTDEVICE" + alice_user_id = self.register_user("alice", "correcthorse") + alice_access_token = self.login( + alice_user_id, "correcthorse", device_id=test_device_id + ) + + bob_user_id = self.register_user("bob", "ponyponypony") + bob_access_token = self.login(bob_user_id, "ponyponypony") + + # Create a room for them to coexist peacefully in + new_room_id = self.helper.create_room_as( + alice_user_id, is_public=True, tok=alice_access_token + ) + self.assertIsNotNone(new_room_id) + + # Have Bob join the room + self.helper.invite( + new_room_id, alice_user_id, bob_user_id, tok=alice_access_token + ) + self.helper.join(new_room_id, bob_user_id, tok=bob_access_token) + + # Now have Bob initiate an initial sync (in order to get a since token) + channel = self.make_request( + "GET", + self.sync_endpoint, + access_token=bob_access_token, + ) + self.assertEqual(channel.code, 200, channel.json_body) + next_batch_token = channel.json_body["next_batch"] + + # ...and then an incremental sync. This should block until the sync stream is woken up, + # which we hope will happen as a result of Alice updating their device list. + bob_sync_channel = self.make_request( + "GET", + f"{self.sync_endpoint}?since={next_batch_token}&timeout=30000", + access_token=bob_access_token, + # Start the request, then continue on. + await_result=False, + ) + + # Have alice update their device list + channel = self.make_request( + "PUT", + f"/devices/{test_device_id}", + { + "display_name": "New Device Name", + }, + access_token=alice_access_token, + ) + self.assertEqual(channel.code, 200, channel.json_body) + + # Check that bob's incremental sync contains the updated device list. + # If not, the client would only receive the device list update on the + # *next* sync. + bob_sync_channel.await_result() + self.assertEqual(bob_sync_channel.code, 200, bob_sync_channel.json_body) + + changed_device_lists = bob_sync_channel.json_body.get("device_lists", {}).get( + "changed", [] + ) + self.assertIn(alice_user_id, changed_device_lists, bob_sync_channel.json_body) + + def test_not_receiving_local_device_list_changes(self) -> None: + """Tests a local users DO NOT receive device updates from each other if they do not + share a room. + """ + # Register two users + test_device_id = "TESTDEVICE" + alice_user_id = self.register_user("alice", "correcthorse") + alice_access_token = self.login( + alice_user_id, "correcthorse", device_id=test_device_id + ) + + bob_user_id = self.register_user("bob", "ponyponypony") + bob_access_token = self.login(bob_user_id, "ponyponypony") + + # These users do not share a room. They are lonely. + + # Have Bob initiate an initial sync (in order to get a since token) + channel = self.make_request( + "GET", + self.sync_endpoint, + access_token=bob_access_token, + ) + self.assertEqual(channel.code, 200, channel.json_body) + next_batch_token = channel.json_body["next_batch"] + + # ...and then an incremental sync. This should block until the sync stream is woken up, + # which we hope will happen as a result of Alice updating their device list. + bob_sync_channel = self.make_request( + "GET", + f"{self.sync_endpoint}?since={next_batch_token}&timeout=1000", + access_token=bob_access_token, + # Start the request, then continue on. + await_result=False, + ) + + # Have alice update their device list + channel = self.make_request( + "PUT", + f"/devices/{test_device_id}", + { + "display_name": "New Device Name", + }, + access_token=alice_access_token, + ) + self.assertEqual(channel.code, 200, channel.json_body) + + # Check that bob's incremental sync does not contain the updated device list. + bob_sync_channel.await_result() + self.assertEqual(bob_sync_channel.code, 200, bob_sync_channel.json_body) + + changed_device_lists = bob_sync_channel.json_body.get("device_lists", {}).get( + "changed", [] + ) + self.assertNotIn( + alice_user_id, changed_device_lists, bob_sync_channel.json_body + ) + def test_user_with_no_rooms_receives_self_device_list_updates(self) -> None: """Tests that a user with no rooms still receives their own device list updates""" - device_id = "TESTDEVICE" + test_device_id = "TESTDEVICE" # Register a user and login, creating a device - self.user_id = self.register_user("kermit", "monkey") - self.tok = self.login("kermit", "monkey", device_id=device_id) + alice_user_id = self.register_user("alice", "correcthorse") + alice_access_token = self.login( + alice_user_id, "correcthorse", device_id=test_device_id + ) # Request an initial sync - channel = self.make_request("GET", "/sync", access_token=self.tok) + channel = self.make_request( + "GET", self.sync_endpoint, access_token=alice_access_token + ) self.assertEqual(channel.code, 200, channel.json_body) next_batch = channel.json_body["next_batch"] @@ -713,19 +873,19 @@ class DeviceListSyncTestCase(unittest.HomeserverTestCase): # It won't return until something has happened incremental_sync_channel = self.make_request( "GET", - f"/sync?since={next_batch}&timeout=30000", - access_token=self.tok, + f"{self.sync_endpoint}?since={next_batch}&timeout=30000", + access_token=alice_access_token, await_result=False, ) # Change our device's display name channel = self.make_request( "PUT", - f"devices/{device_id}", + f"devices/{test_device_id}", { "display_name": "freeze ray", }, - access_token=self.tok, + access_token=alice_access_token, ) self.assertEqual(channel.code, 200, channel.json_body) @@ -739,7 +899,230 @@ class DeviceListSyncTestCase(unittest.HomeserverTestCase): ).get("changed", []) self.assertIn( - self.user_id, device_list_changes, incremental_sync_channel.json_body + alice_user_id, device_list_changes, incremental_sync_channel.json_body + ) + + +@parameterized_class( + ("sync_endpoint", "experimental_features"), + [ + ("/sync", {}), + ( + "/_matrix/client/unstable/org.matrix.msc3575/sync/e2ee", + # Enable sliding sync + {"msc3575_enabled": True}, + ), + ], +) +class DeviceOneTimeKeysSyncTestCase(unittest.HomeserverTestCase): + """ + Tests regarding device one time keys (`device_one_time_keys_count`) changes. + + Attributes: + sync_endpoint: The endpoint under test to use for syncing. + experimental_features: The experimental features homeserver config to use. + """ + + sync_endpoint: str + experimental_features: JsonDict + + servlets = [ + synapse.rest.admin.register_servlets, + login.register_servlets, + sync.register_servlets, + devices.register_servlets, + ] + + def default_config(self) -> JsonDict: + config = super().default_config() + config["experimental_features"] = self.experimental_features + return config + + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: + self.e2e_keys_handler = hs.get_e2e_keys_handler() + + def test_no_device_one_time_keys(self) -> None: + """ + Tests when no one time keys set, it still has the default `signed_curve25519` in + `device_one_time_keys_count` + """ + test_device_id = "TESTDEVICE" + + alice_user_id = self.register_user("alice", "correcthorse") + alice_access_token = self.login( + alice_user_id, "correcthorse", device_id=test_device_id + ) + + # Request an initial sync + channel = self.make_request( + "GET", self.sync_endpoint, access_token=alice_access_token + ) + self.assertEqual(channel.code, 200, channel.json_body) + + # Check for those one time key counts + self.assertDictEqual( + channel.json_body["device_one_time_keys_count"], + # Note that "signed_curve25519" is always returned in key count responses + # regardless of whether we uploaded any keys for it. This is necessary until + # https://github.com/matrix-org/matrix-doc/issues/3298 is fixed. + {"signed_curve25519": 0}, + channel.json_body["device_one_time_keys_count"], + ) + + def test_returns_device_one_time_keys(self) -> None: + """ + Tests that one time keys for the device/user are counted correctly in the `/sync` + response + """ + test_device_id = "TESTDEVICE" + + alice_user_id = self.register_user("alice", "correcthorse") + alice_access_token = self.login( + alice_user_id, "correcthorse", device_id=test_device_id + ) + + # Upload one time keys for the user/device + keys: JsonDict = { + "alg1:k1": "key1", + "alg2:k2": {"key": "key2", "signatures": {"k1": "sig1"}}, + "alg2:k3": {"key": "key3"}, + } + res = self.get_success( + self.e2e_keys_handler.upload_keys_for_user( + alice_user_id, test_device_id, {"one_time_keys": keys} + ) + ) + # Note that "signed_curve25519" is always returned in key count responses + # regardless of whether we uploaded any keys for it. This is necessary until + # https://github.com/matrix-org/matrix-doc/issues/3298 is fixed. + self.assertDictEqual( + res, + {"one_time_key_counts": {"alg1": 1, "alg2": 2, "signed_curve25519": 0}}, + ) + + # Request an initial sync + channel = self.make_request( + "GET", self.sync_endpoint, access_token=alice_access_token + ) + self.assertEqual(channel.code, 200, channel.json_body) + + # Check for those one time key counts + self.assertDictEqual( + channel.json_body["device_one_time_keys_count"], + {"alg1": 1, "alg2": 2, "signed_curve25519": 0}, + channel.json_body["device_one_time_keys_count"], + ) + + +@parameterized_class( + ("sync_endpoint", "experimental_features"), + [ + ("/sync", {}), + ( + "/_matrix/client/unstable/org.matrix.msc3575/sync/e2ee", + # Enable sliding sync + {"msc3575_enabled": True}, + ), + ], +) +class DeviceUnusedFallbackKeySyncTestCase(unittest.HomeserverTestCase): + """ + Tests regarding device one time keys (`device_unused_fallback_key_types`) changes. + + Attributes: + sync_endpoint: The endpoint under test to use for syncing. + experimental_features: The experimental features homeserver config to use. + """ + + sync_endpoint: str + experimental_features: JsonDict + + servlets = [ + synapse.rest.admin.register_servlets, + login.register_servlets, + sync.register_servlets, + devices.register_servlets, + ] + + def default_config(self) -> JsonDict: + config = super().default_config() + config["experimental_features"] = self.experimental_features + return config + + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: + self.store = self.hs.get_datastores().main + self.e2e_keys_handler = hs.get_e2e_keys_handler() + + def test_no_device_unused_fallback_key(self) -> None: + """ + Test when no unused fallback key is set, it just returns an empty list. The MSC + says "The device_unused_fallback_key_types parameter must be present if the + server supports fallback keys.", + https://github.com/matrix-org/matrix-spec-proposals/blob/54255851f642f84a4f1aaf7bc063eebe3d76752b/proposals/2732-olm-fallback-keys.md + """ + test_device_id = "TESTDEVICE" + + alice_user_id = self.register_user("alice", "correcthorse") + alice_access_token = self.login( + alice_user_id, "correcthorse", device_id=test_device_id + ) + + # Request an initial sync + channel = self.make_request( + "GET", self.sync_endpoint, access_token=alice_access_token + ) + self.assertEqual(channel.code, 200, channel.json_body) + + # Check for those one time key counts + self.assertListEqual( + channel.json_body["device_unused_fallback_key_types"], + [], + channel.json_body["device_unused_fallback_key_types"], + ) + + def test_returns_device_one_time_keys(self) -> None: + """ + Tests that device unused fallback key type is returned correctly in the `/sync` + """ + test_device_id = "TESTDEVICE" + + alice_user_id = self.register_user("alice", "correcthorse") + alice_access_token = self.login( + alice_user_id, "correcthorse", device_id=test_device_id + ) + + # We shouldn't have any unused fallback keys yet + res = self.get_success( + self.store.get_e2e_unused_fallback_key_types(alice_user_id, test_device_id) + ) + self.assertEqual(res, []) + + # Upload a fallback key for the user/device + fallback_key = {"alg1:k1": "fallback_key1"} + self.get_success( + self.e2e_keys_handler.upload_keys_for_user( + alice_user_id, + test_device_id, + {"fallback_keys": fallback_key}, + ) + ) + # We should now have an unused alg1 key + fallback_res = self.get_success( + self.store.get_e2e_unused_fallback_key_types(alice_user_id, test_device_id) + ) + self.assertEqual(fallback_res, ["alg1"], fallback_res) + + # Request an initial sync + channel = self.make_request( + "GET", self.sync_endpoint, access_token=alice_access_token + ) + self.assertEqual(channel.code, 200, channel.json_body) + + # Check for the unused fallback key types + self.assertListEqual( + channel.json_body["device_unused_fallback_key_types"], + ["alg1"], + channel.json_body["device_unused_fallback_key_types"], ) @@ -825,3 +1208,411 @@ class ExcludeRoomTestCase(unittest.HomeserverTestCase): self.assertNotIn(self.excluded_room_id, channel.json_body["rooms"]["join"]) self.assertIn(self.included_room_id, channel.json_body["rooms"]["join"]) + + +class SlidingSyncTestCase(unittest.HomeserverTestCase): + """ + Tests regarding MSC3575 Sliding Sync `/sync` endpoint. + """ + + servlets = [ + synapse.rest.admin.register_servlets, + login.register_servlets, + room.register_servlets, + sync.register_servlets, + devices.register_servlets, + ] + + def default_config(self) -> JsonDict: + config = super().default_config() + # Enable sliding sync + config["experimental_features"] = {"msc3575_enabled": True} + return config + + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: + self.store = hs.get_datastores().main + self.sync_endpoint = ( + "/_matrix/client/unstable/org.matrix.simplified_msc3575/sync" + ) + self.store = hs.get_datastores().main + self.event_sources = hs.get_event_sources() + + def _add_new_dm_to_global_account_data( + self, source_user_id: str, target_user_id: str, target_room_id: str + ) -> None: + """ + Helper to handle inserting a new DM for the source user into global account data + (handles all of the list merging). + + Args: + source_user_id: The user ID of the DM mapping we're going to update + target_user_id: User ID of the person the DM is with + target_room_id: Room ID of the DM + """ + + # Get the current DM map + existing_dm_map = self.get_success( + self.store.get_global_account_data_by_type_for_user( + source_user_id, AccountDataTypes.DIRECT + ) + ) + # Scrutinize the account data since it has no concrete type. We're just copying + # everything into a known type. It should be a mapping from user ID to a list of + # room IDs. Ignore anything else. + new_dm_map: Dict[str, List[str]] = {} + if isinstance(existing_dm_map, dict): + for user_id, room_ids in existing_dm_map.items(): + if isinstance(user_id, str) and isinstance(room_ids, list): + for room_id in room_ids: + if isinstance(room_id, str): + new_dm_map[user_id] = new_dm_map.get(user_id, []) + [ + room_id + ] + + # Add the new DM to the map + new_dm_map[target_user_id] = new_dm_map.get(target_user_id, []) + [ + target_room_id + ] + # Save the DM map to global account data + self.get_success( + self.store.add_account_data_for_user( + source_user_id, + AccountDataTypes.DIRECT, + new_dm_map, + ) + ) + + def _create_dm_room( + self, + inviter_user_id: str, + inviter_tok: str, + invitee_user_id: str, + invitee_tok: str, + should_join_room: bool = True, + ) -> str: + """ + Helper to create a DM room as the "inviter" and invite the "invitee" user to the + room. The "invitee" user also will join the room. The `m.direct` account data + will be set for both users. + """ + + # Create a room and send an invite the other user + room_id = self.helper.create_room_as( + inviter_user_id, + is_public=False, + tok=inviter_tok, + ) + self.helper.invite( + room_id, + src=inviter_user_id, + targ=invitee_user_id, + tok=inviter_tok, + extra_data={"is_direct": True}, + ) + if should_join_room: + # Person that was invited joins the room + self.helper.join(room_id, invitee_user_id, tok=invitee_tok) + + # Mimic the client setting the room as a direct message in the global account + # data for both users. + self._add_new_dm_to_global_account_data( + invitee_user_id, inviter_user_id, room_id + ) + self._add_new_dm_to_global_account_data( + inviter_user_id, invitee_user_id, room_id + ) + + return room_id + + def test_sync_list(self) -> None: + """ + Test that room IDs show up in the Sliding Sync lists + """ + alice_user_id = self.register_user("alice", "correcthorse") + alice_access_token = self.login(alice_user_id, "correcthorse") + + room_id = self.helper.create_room_as( + alice_user_id, tok=alice_access_token, is_public=True + ) + + # Make the Sliding Sync request + channel = self.make_request( + "POST", + self.sync_endpoint, + { + "lists": { + "foo-list": { + "ranges": [[0, 99]], + "required_state": [ + ["m.room.join_rules", ""], + ["m.room.history_visibility", ""], + ["m.space.child", "*"], + ], + "timeline_limit": 1, + } + } + }, + access_token=alice_access_token, + ) + self.assertEqual(channel.code, 200, channel.json_body) + + # Make sure it has the foo-list we requested + self.assertListEqual( + list(channel.json_body["lists"].keys()), + ["foo-list"], + channel.json_body["lists"].keys(), + ) + + # Make sure the list includes the room we are joined to + self.assertListEqual( + list(channel.json_body["lists"]["foo-list"]["ops"]), + [ + { + "op": "SYNC", + "range": [0, 99], + "room_ids": [room_id], + } + ], + channel.json_body["lists"]["foo-list"], + ) + + def test_wait_for_sync_token(self) -> None: + """ + Test that worker will wait until it catches up to the given token + """ + alice_user_id = self.register_user("alice", "correcthorse") + alice_access_token = self.login(alice_user_id, "correcthorse") + + # Create a future token that will cause us to wait. Since we never send a new + # event to reach that future stream_ordering, the worker will wait until the + # full timeout. + current_token = self.event_sources.get_current_token() + future_position_token = current_token.copy_and_replace( + StreamKeyType.ROOM, + RoomStreamToken(stream=current_token.room_key.stream + 1), + ) + + future_position_token_serialized = self.get_success( + future_position_token.to_string(self.store) + ) + + # Make the Sliding Sync request + channel = self.make_request( + "POST", + self.sync_endpoint + f"?pos={future_position_token_serialized}", + { + "lists": { + "foo-list": { + "ranges": [[0, 99]], + "required_state": [ + ["m.room.join_rules", ""], + ["m.room.history_visibility", ""], + ["m.space.child", "*"], + ], + "timeline_limit": 1, + } + } + }, + access_token=alice_access_token, + await_result=False, + ) + # Block for 10 seconds to make `notifier.wait_for_stream_token(from_token)` + # timeout + with self.assertRaises(TimedOutException): + channel.await_result(timeout_ms=9900) + channel.await_result(timeout_ms=200) + self.assertEqual(channel.code, 200, channel.json_body) + + # We expect the `next_pos` in the result to be the same as what we requested + # with because we weren't able to find anything new yet. + self.assertEqual( + channel.json_body["next_pos"], future_position_token_serialized + ) + + def test_filter_list(self) -> None: + """ + Test that filters apply to lists + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + user2_id = self.register_user("user2", "pass") + user2_tok = self.login(user2_id, "pass") + + # Create a DM room + joined_dm_room_id = self._create_dm_room( + inviter_user_id=user1_id, + inviter_tok=user1_tok, + invitee_user_id=user2_id, + invitee_tok=user2_tok, + should_join_room=True, + ) + invited_dm_room_id = self._create_dm_room( + inviter_user_id=user1_id, + inviter_tok=user1_tok, + invitee_user_id=user2_id, + invitee_tok=user2_tok, + should_join_room=False, + ) + + # Create a normal room + room_id = self.helper.create_room_as(user1_id, tok=user2_tok) + self.helper.join(room_id, user1_id, tok=user1_tok) + + # Create a room that user1 is invited to + invite_room_id = self.helper.create_room_as(user1_id, tok=user2_tok) + self.helper.invite(invite_room_id, src=user2_id, targ=user1_id, tok=user2_tok) + + # Make the Sliding Sync request + channel = self.make_request( + "POST", + self.sync_endpoint, + { + "lists": { + # Absense of filters does not imply "False" values + "all": { + "ranges": [[0, 99]], + "required_state": [], + "timeline_limit": 1, + "filters": {}, + }, + # Test single truthy filter + "dms": { + "ranges": [[0, 99]], + "required_state": [], + "timeline_limit": 1, + "filters": {"is_dm": True}, + }, + # Test single falsy filter + "non-dms": { + "ranges": [[0, 99]], + "required_state": [], + "timeline_limit": 1, + "filters": {"is_dm": False}, + }, + # Test how multiple filters should stack (AND'd together) + "room-invites": { + "ranges": [[0, 99]], + "required_state": [], + "timeline_limit": 1, + "filters": {"is_dm": False, "is_invite": True}, + }, + } + }, + access_token=user1_tok, + ) + self.assertEqual(channel.code, 200, channel.json_body) + + # Make sure it has the foo-list we requested + self.assertListEqual( + list(channel.json_body["lists"].keys()), + ["all", "dms", "non-dms", "room-invites"], + channel.json_body["lists"].keys(), + ) + + # Make sure the lists have the correct rooms + self.assertListEqual( + list(channel.json_body["lists"]["all"]["ops"]), + [ + { + "op": "SYNC", + "range": [0, 99], + "room_ids": [ + invite_room_id, + room_id, + invited_dm_room_id, + joined_dm_room_id, + ], + } + ], + list(channel.json_body["lists"]["all"]), + ) + self.assertListEqual( + list(channel.json_body["lists"]["dms"]["ops"]), + [ + { + "op": "SYNC", + "range": [0, 99], + "room_ids": [invited_dm_room_id, joined_dm_room_id], + } + ], + list(channel.json_body["lists"]["dms"]), + ) + self.assertListEqual( + list(channel.json_body["lists"]["non-dms"]["ops"]), + [ + { + "op": "SYNC", + "range": [0, 99], + "room_ids": [invite_room_id, room_id], + } + ], + list(channel.json_body["lists"]["non-dms"]), + ) + self.assertListEqual( + list(channel.json_body["lists"]["room-invites"]["ops"]), + [ + { + "op": "SYNC", + "range": [0, 99], + "room_ids": [invite_room_id], + } + ], + list(channel.json_body["lists"]["room-invites"]), + ) + + def test_sort_list(self) -> None: + """ + Test that the lists are sorted by `stream_ordering` + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + + room_id1 = self.helper.create_room_as(user1_id, tok=user1_tok, is_public=True) + room_id2 = self.helper.create_room_as(user1_id, tok=user1_tok, is_public=True) + room_id3 = self.helper.create_room_as(user1_id, tok=user1_tok, is_public=True) + + # Activity that will order the rooms + self.helper.send(room_id3, "activity in room3", tok=user1_tok) + self.helper.send(room_id1, "activity in room1", tok=user1_tok) + self.helper.send(room_id2, "activity in room2", tok=user1_tok) + + # Make the Sliding Sync request + channel = self.make_request( + "POST", + self.sync_endpoint, + { + "lists": { + "foo-list": { + "ranges": [[0, 99]], + "required_state": [ + ["m.room.join_rules", ""], + ["m.room.history_visibility", ""], + ["m.space.child", "*"], + ], + "timeline_limit": 1, + } + } + }, + access_token=user1_tok, + ) + self.assertEqual(channel.code, 200, channel.json_body) + + # Make sure it has the foo-list we requested + self.assertListEqual( + list(channel.json_body["lists"].keys()), + ["foo-list"], + channel.json_body["lists"].keys(), + ) + + # Make sure the list is sorted in the way we expect + self.assertListEqual( + list(channel.json_body["lists"]["foo-list"]["ops"]), + [ + { + "op": "SYNC", + "range": [0, 99], + "room_ids": [room_id2, room_id1, room_id3], + } + ], + channel.json_body["lists"]["foo-list"], + ) diff --git a/tests/rest/client/utils.py b/tests/rest/client/utils.py index fe00afe198..f0ba40a1f1 100644 --- a/tests/rest/client/utils.py +++ b/tests/rest/client/utils.py @@ -170,6 +170,7 @@ class RestHelper: targ: Optional[str] = None, expect_code: int = HTTPStatus.OK, tok: Optional[str] = None, + extra_data: Optional[dict] = None, ) -> JsonDict: return self.change_membership( room=room, @@ -178,6 +179,7 @@ class RestHelper: tok=tok, membership=Membership.INVITE, expect_code=expect_code, + extra_data=extra_data, ) def join( @@ -328,9 +330,12 @@ class RestHelper: data, ) - assert channel.code == expect_code, "Expected: %d, got: %d, resp: %r" % ( + assert ( + channel.code == expect_code + ), "Expected: %d, got: %d, PUT %s -> resp: %r" % ( expect_code, channel.code, + path, channel.result["body"], ) diff --git a/tests/rest/media/test_domain_blocking.py b/tests/rest/media/test_domain_blocking.py index 88988f3a22..72205c6bb3 100644 --- a/tests/rest/media/test_domain_blocking.py +++ b/tests/rest/media/test_domain_blocking.py @@ -44,13 +44,13 @@ class MediaDomainBlockingTests(unittest.HomeserverTestCase): # from a regular 404. file_id = "abcdefg12345" file_info = FileInfo(server_name=self.remote_server_name, file_id=file_id) - with hs.get_media_repository().media_storage.store_into_file(file_info) as ( - f, - fname, - finish, - ): - f.write(SMALL_PNG) - self.get_success(finish()) + + media_storage = hs.get_media_repository().media_storage + + ctx = media_storage.store_into_file(file_info) + (f, fname) = self.get_success(ctx.__aenter__()) + f.write(SMALL_PNG) + self.get_success(ctx.__aexit__(None, None, None)) self.get_success( self.store.store_cached_remote_media( diff --git a/tests/rest/synapse/__init__.py b/tests/rest/synapse/__init__.py new file mode 100644 index 0000000000..e5138f67e1 --- /dev/null +++ b/tests/rest/synapse/__init__.py @@ -0,0 +1,12 @@ +# +# This file is licensed under the Affero General Public License (AGPL) version 3. +# +# Copyright (C) 2024 New Vector, Ltd +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as +# published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# See the GNU Affero General Public License for more details: +# <https://www.gnu.org/licenses/agpl-3.0.html>. diff --git a/tests/rest/synapse/client/__init__.py b/tests/rest/synapse/client/__init__.py new file mode 100644 index 0000000000..e5138f67e1 --- /dev/null +++ b/tests/rest/synapse/client/__init__.py @@ -0,0 +1,12 @@ +# +# This file is licensed under the Affero General Public License (AGPL) version 3. +# +# Copyright (C) 2024 New Vector, Ltd +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as +# published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# See the GNU Affero General Public License for more details: +# <https://www.gnu.org/licenses/agpl-3.0.html>. diff --git a/tests/rest/synapse/client/test_federation_whitelist.py b/tests/rest/synapse/client/test_federation_whitelist.py new file mode 100644 index 0000000000..f0067a8f2b --- /dev/null +++ b/tests/rest/synapse/client/test_federation_whitelist.py @@ -0,0 +1,119 @@ +# +# This file is licensed under the Affero General Public License (AGPL) version 3. +# +# Copyright (C) 2024 New Vector, Ltd +# +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU Affero General Public License as +# published by the Free Software Foundation, either version 3 of the +# License, or (at your option) any later version. +# +# See the GNU Affero General Public License for more details: +# <https://www.gnu.org/licenses/agpl-3.0.html>. + +from typing import Dict + +from twisted.web.resource import Resource + +from synapse.rest import admin +from synapse.rest.client import login +from synapse.rest.synapse.client import build_synapse_client_resource_tree + +from tests import unittest + + +class FederationWhitelistTests(unittest.HomeserverTestCase): + servlets = [ + admin.register_servlets_for_client_rest_resource, + login.register_servlets, + ] + + def create_resource_dict(self) -> Dict[str, Resource]: + base = super().create_resource_dict() + base.update(build_synapse_client_resource_tree(self.hs)) + return base + + def test_default(self) -> None: + "If the config option is not enabled, the endpoint should 404" + channel = self.make_request( + "GET", "/_synapse/client/v1/config/federation_whitelist", shorthand=False + ) + + self.assertEqual(channel.code, 404) + + @unittest.override_config({"federation_whitelist_endpoint_enabled": True}) + def test_no_auth(self) -> None: + "Endpoint requires auth when enabled" + + channel = self.make_request( + "GET", "/_synapse/client/v1/config/federation_whitelist", shorthand=False + ) + + self.assertEqual(channel.code, 401) + + @unittest.override_config({"federation_whitelist_endpoint_enabled": True}) + def test_no_whitelist(self) -> None: + "Test when there is no whitelist configured" + + self.register_user("user", "password") + tok = self.login("user", "password") + + channel = self.make_request( + "GET", + "/_synapse/client/v1/config/federation_whitelist", + shorthand=False, + access_token=tok, + ) + + self.assertEqual(channel.code, 200) + self.assertEqual( + channel.json_body, {"whitelist_enabled": False, "whitelist": []} + ) + + @unittest.override_config( + { + "federation_whitelist_endpoint_enabled": True, + "federation_domain_whitelist": ["example.com"], + } + ) + def test_whitelist(self) -> None: + "Test when there is a whitelist configured" + + self.register_user("user", "password") + tok = self.login("user", "password") + + channel = self.make_request( + "GET", + "/_synapse/client/v1/config/federation_whitelist", + shorthand=False, + access_token=tok, + ) + + self.assertEqual(channel.code, 200) + self.assertEqual( + channel.json_body, {"whitelist_enabled": True, "whitelist": ["example.com"]} + ) + + @unittest.override_config( + { + "federation_whitelist_endpoint_enabled": True, + "federation_domain_whitelist": ["example.com", "example.com"], + } + ) + def test_whitelist_no_duplicates(self) -> None: + "Test when there is a whitelist configured with duplicates, no duplicates are returned" + + self.register_user("user", "password") + tok = self.login("user", "password") + + channel = self.make_request( + "GET", + "/_synapse/client/v1/config/federation_whitelist", + shorthand=False, + access_token=tok, + ) + + self.assertEqual(channel.code, 200) + self.assertEqual( + channel.json_body, {"whitelist_enabled": True, "whitelist": ["example.com"]} + ) diff --git a/tests/server.py b/tests/server.py index 434be3d22c..f3a917f835 100644 --- a/tests/server.py +++ b/tests/server.py @@ -85,6 +85,7 @@ from twisted.web.server import Request, Site from synapse.config.database import DatabaseConnectionConfig from synapse.config.homeserver import HomeServerConfig +from synapse.events.auto_accept_invites import InviteAutoAccepter from synapse.events.presence_router import load_legacy_presence_router from synapse.handlers.auth import load_legacy_password_auth_providers from synapse.http.site import SynapseRequest @@ -1156,6 +1157,11 @@ def setup_test_homeserver( for module, module_config in hs.config.modules.loaded_modules: module(config=module_config, api=module_api) + if hs.config.auto_accept_invites.enabled: + # Start the local auto_accept_invites module. + m = InviteAutoAccepter(hs.config.auto_accept_invites, module_api) + logger.info("Loaded local module %s", m) + load_legacy_spam_checkers(hs) load_legacy_third_party_event_rules(hs) load_legacy_presence_router(hs) diff --git a/tests/storage/test_devices.py b/tests/storage/test_devices.py index 7f975d04ff..ba01b038ab 100644 --- a/tests/storage/test_devices.py +++ b/tests/storage/test_devices.py @@ -36,6 +36,14 @@ class DeviceStoreTestCase(HomeserverTestCase): def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: self.store = hs.get_datastores().main + def default_config(self) -> JsonDict: + config = super().default_config() + + # We 'enable' federation otherwise `get_device_updates_by_remote` will + # throw an exception. + config["federation_sender_instances"] = ["master"] + return config + def add_device_change(self, user_id: str, device_ids: List[str], host: str) -> None: """Add a device list change for the given device to `device_lists_outbound_pokes` table. diff --git a/tests/storage/test_event_chain.py b/tests/storage/test_event_chain.py index 27d5b0125f..c4e216c308 100644 --- a/tests/storage/test_event_chain.py +++ b/tests/storage/test_event_chain.py @@ -431,6 +431,7 @@ class EventChainStoreTestCase(HomeserverTestCase): for e in events: e.internal_metadata.stream_ordering = self._next_stream_ordering + e.internal_metadata.instance_name = self.hs.get_instance_name() self._next_stream_ordering += 1 def _persist(txn: LoggingTransaction) -> None: @@ -446,7 +447,14 @@ class EventChainStoreTestCase(HomeserverTestCase): ) # Actually call the function that calculates the auth chain stuff. - persist_events_store._persist_event_auth_chain_txn(txn, events) + new_event_links = ( + persist_events_store.calculate_chain_cover_index_for_events_txn( + txn, events[0].room_id, [e for e in events if e.is_state()] + ) + ) + persist_events_store._persist_event_auth_chain_txn( + txn, events, new_event_links + ) self.get_success( persist_events_store.db_pool.runInteraction( diff --git a/tests/storage/test_event_federation.py b/tests/storage/test_event_federation.py index 0a6253e22c..088f0d24f9 100644 --- a/tests/storage/test_event_federation.py +++ b/tests/storage/test_event_federation.py @@ -365,12 +365,19 @@ class EventFederationWorkerStoreTestCase(tests.unittest.HomeserverTestCase): }, ) + events = [ + cast(EventBase, FakeEvent(event_id, room_id, AUTH_GRAPH[event_id])) + for event_id in AUTH_GRAPH + ] + new_event_links = ( + self.persist_events.calculate_chain_cover_index_for_events_txn( + txn, room_id, [e for e in events if e.is_state()] + ) + ) self.persist_events._persist_event_auth_chain_txn( txn, - [ - cast(EventBase, FakeEvent(event_id, room_id, AUTH_GRAPH[event_id])) - for event_id in AUTH_GRAPH - ], + events, + new_event_links, ) self.get_success( @@ -544,6 +551,9 @@ class EventFederationWorkerStoreTestCase(tests.unittest.HomeserverTestCase): rooms. """ + # We allow partial covers for this test + self.hs.get_datastores().main.tests_allow_no_chain_cover_index = True + room_id = "@ROOM:local" # The silly auth graph we use to test the auth difference algorithm, @@ -628,13 +638,20 @@ class EventFederationWorkerStoreTestCase(tests.unittest.HomeserverTestCase): ) # Insert all events apart from 'B' + events = [ + cast(EventBase, FakeEvent(event_id, room_id, auth_graph[event_id])) + for event_id in auth_graph + if event_id != "b" + ] + new_event_links = ( + self.persist_events.calculate_chain_cover_index_for_events_txn( + txn, room_id, [e for e in events if e.is_state()] + ) + ) self.persist_events._persist_event_auth_chain_txn( txn, - [ - cast(EventBase, FakeEvent(event_id, room_id, auth_graph[event_id])) - for event_id in auth_graph - if event_id != "b" - ], + events, + new_event_links, ) # Now we insert the event 'B' without a chain cover, by temporarily @@ -647,9 +664,14 @@ class EventFederationWorkerStoreTestCase(tests.unittest.HomeserverTestCase): updatevalues={"has_auth_chain_index": False}, ) + events = [cast(EventBase, FakeEvent("b", room_id, auth_graph["b"]))] + new_event_links = ( + self.persist_events.calculate_chain_cover_index_for_events_txn( + txn, room_id, [e for e in events if e.is_state()] + ) + ) self.persist_events._persist_event_auth_chain_txn( - txn, - [cast(EventBase, FakeEvent("b", room_id, auth_graph["b"]))], + txn, events, new_event_links ) self.store.db_pool.simple_update_txn( diff --git a/tests/storage/test_id_generators.py b/tests/storage/test_id_generators.py index 409d856ab9..12b89cecb6 100644 --- a/tests/storage/test_id_generators.py +++ b/tests/storage/test_id_generators.py @@ -18,7 +18,7 @@ # [This file includes modifications made by New Vector Limited] # # -from typing import List, Optional +from typing import Dict, List, Optional from twisted.test.proto_helpers import MemoryReactor @@ -28,177 +28,55 @@ from synapse.storage.database import ( LoggingDatabaseConnection, LoggingTransaction, ) -from synapse.storage.engines import IncorrectDatabaseSetup from synapse.storage.types import Cursor -from synapse.storage.util.id_generators import MultiWriterIdGenerator, StreamIdGenerator +from synapse.storage.util.id_generators import MultiWriterIdGenerator +from synapse.storage.util.sequence import ( + LocalSequenceGenerator, + PostgresSequenceGenerator, + SequenceGenerator, +) from synapse.util import Clock from tests.unittest import HomeserverTestCase from tests.utils import USE_POSTGRES_FOR_TESTS -class StreamIdGeneratorTestCase(HomeserverTestCase): +class MultiWriterIdGeneratorBase(HomeserverTestCase): + positive: bool = True + tables: List[str] = ["foobar"] + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: self.store = hs.get_datastores().main self.db_pool: DatabasePool = self.store.db_pool + self.instances: Dict[str, MultiWriterIdGenerator] = {} self.get_success(self.db_pool.runInteraction("_setup_db", self._setup_db)) + if USE_POSTGRES_FOR_TESTS: + self.seq_gen: SequenceGenerator = PostgresSequenceGenerator("foobar_seq") + else: + self.seq_gen = LocalSequenceGenerator(lambda _: 0) + def _setup_db(self, txn: LoggingTransaction) -> None: - txn.execute( - """ - CREATE TABLE foobar ( - stream_id BIGINT NOT NULL, - data TEXT - ); - """ - ) - txn.execute("INSERT INTO foobar VALUES (123, 'hello world');") + if USE_POSTGRES_FOR_TESTS: + txn.execute("CREATE SEQUENCE foobar_seq") - def _create_id_generator(self) -> StreamIdGenerator: - def _create(conn: LoggingDatabaseConnection) -> StreamIdGenerator: - return StreamIdGenerator( - db_conn=conn, - notifier=self.hs.get_replication_notifier(), - table="foobar", - column="stream_id", + for table in self.tables: + txn.execute( + """ + CREATE TABLE %s ( + stream_id BIGINT NOT NULL, + instance_name TEXT NOT NULL, + data TEXT + ); + """ + % (table,) ) - return self.get_success_or_raise(self.db_pool.runWithConnection(_create)) - - def test_initial_value(self) -> None: - """Check that we read the current token from the DB.""" - id_gen = self._create_id_generator() - self.assertEqual(id_gen.get_current_token(), 123) - - def test_single_gen_next(self) -> None: - """Check that we correctly increment the current token from the DB.""" - id_gen = self._create_id_generator() - - async def test_gen_next() -> None: - async with id_gen.get_next() as next_id: - # We haven't persisted `next_id` yet; current token is still 123 - self.assertEqual(id_gen.get_current_token(), 123) - # But we did learn what the next value is - self.assertEqual(next_id, 124) - - # Once the context manager closes we assume that the `next_id` has been - # written to the DB. - self.assertEqual(id_gen.get_current_token(), 124) - - self.get_success(test_gen_next()) - - def test_multiple_gen_nexts(self) -> None: - """Check that we handle overlapping calls to gen_next sensibly.""" - id_gen = self._create_id_generator() - - async def test_gen_next() -> None: - ctx1 = id_gen.get_next() - ctx2 = id_gen.get_next() - ctx3 = id_gen.get_next() - - # Request three new stream IDs. - self.assertEqual(await ctx1.__aenter__(), 124) - self.assertEqual(await ctx2.__aenter__(), 125) - self.assertEqual(await ctx3.__aenter__(), 126) - - # None are persisted: current token unchanged. - self.assertEqual(id_gen.get_current_token(), 123) - - # Persist each in turn. - await ctx1.__aexit__(None, None, None) - self.assertEqual(id_gen.get_current_token(), 124) - await ctx2.__aexit__(None, None, None) - self.assertEqual(id_gen.get_current_token(), 125) - await ctx3.__aexit__(None, None, None) - self.assertEqual(id_gen.get_current_token(), 126) - - self.get_success(test_gen_next()) - - def test_multiple_gen_nexts_closed_in_different_order(self) -> None: - """Check that we handle overlapping calls to gen_next, even when their IDs - created and persisted in different orders.""" - id_gen = self._create_id_generator() - - async def test_gen_next() -> None: - ctx1 = id_gen.get_next() - ctx2 = id_gen.get_next() - ctx3 = id_gen.get_next() - - # Request three new stream IDs. - self.assertEqual(await ctx1.__aenter__(), 124) - self.assertEqual(await ctx2.__aenter__(), 125) - self.assertEqual(await ctx3.__aenter__(), 126) - - # None are persisted: current token unchanged. - self.assertEqual(id_gen.get_current_token(), 123) - - # Persist them in a different order, starting with 126 from ctx3. - await ctx3.__aexit__(None, None, None) - # We haven't persisted 124 from ctx1 yet---current token is still 123. - self.assertEqual(id_gen.get_current_token(), 123) - - # Now persist 124 from ctx1. - await ctx1.__aexit__(None, None, None) - # Current token is then 124, waiting for 125 to be persisted. - self.assertEqual(id_gen.get_current_token(), 124) - - # Finally persist 125 from ctx2. - await ctx2.__aexit__(None, None, None) - # Current token is then 126 (skipping over 125). - self.assertEqual(id_gen.get_current_token(), 126) - - self.get_success(test_gen_next()) - - def test_gen_next_while_still_waiting_for_persistence(self) -> None: - """Check that we handle overlapping calls to gen_next.""" - id_gen = self._create_id_generator() - - async def test_gen_next() -> None: - ctx1 = id_gen.get_next() - ctx2 = id_gen.get_next() - ctx3 = id_gen.get_next() - - # Request two new stream IDs. - self.assertEqual(await ctx1.__aenter__(), 124) - self.assertEqual(await ctx2.__aenter__(), 125) - - # Persist ctx2 first. - await ctx2.__aexit__(None, None, None) - # Still waiting on ctx1's ID to be persisted. - self.assertEqual(id_gen.get_current_token(), 123) - - # Now request a third stream ID. It should be 126 (the smallest ID that - # we've not yet handed out.) - self.assertEqual(await ctx3.__aenter__(), 126) - - self.get_success(test_gen_next()) - - -class MultiWriterIdGeneratorTestCase(HomeserverTestCase): - if not USE_POSTGRES_FOR_TESTS: - skip = "Requires Postgres" - - def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: - self.store = hs.get_datastores().main - self.db_pool: DatabasePool = self.store.db_pool - - self.get_success(self.db_pool.runInteraction("_setup_db", self._setup_db)) - - def _setup_db(self, txn: LoggingTransaction) -> None: - txn.execute("CREATE SEQUENCE foobar_seq") - txn.execute( - """ - CREATE TABLE foobar ( - stream_id BIGINT NOT NULL, - instance_name TEXT NOT NULL, - data TEXT - ); - """ - ) - def _create_id_generator( - self, instance_name: str = "master", writers: Optional[List[str]] = None + self, + instance_name: str = "master", + writers: Optional[List[str]] = None, ) -> MultiWriterIdGenerator: def _create(conn: LoggingDatabaseConnection) -> MultiWriterIdGenerator: return MultiWriterIdGenerator( @@ -207,58 +85,98 @@ class MultiWriterIdGeneratorTestCase(HomeserverTestCase): notifier=self.hs.get_replication_notifier(), stream_name="test_stream", instance_name=instance_name, - tables=[("foobar", "instance_name", "stream_id")], + tables=[(table, "instance_name", "stream_id") for table in self.tables], sequence_name="foobar_seq", writers=writers or ["master"], + positive=self.positive, ) - return self.get_success_or_raise(self.db_pool.runWithConnection(_create)) + self.instances[instance_name] = self.get_success_or_raise( + self.db_pool.runWithConnection(_create) + ) + return self.instances[instance_name] - def _insert_rows(self, instance_name: str, number: int) -> None: - """Insert N rows as the given instance, inserting with stream IDs pulled - from the postgres sequence. - """ + def _replicate(self, instance_name: str) -> None: + """Similate a replication event for the given instance.""" - def _insert(txn: LoggingTransaction) -> None: - for _ in range(number): - txn.execute( - "INSERT INTO foobar VALUES (nextval('foobar_seq'), ?)", - (instance_name,), - ) - txn.execute( - """ - INSERT INTO stream_positions VALUES ('test_stream', ?, lastval()) - ON CONFLICT (stream_name, instance_name) DO UPDATE SET stream_id = lastval() - """, - (instance_name,), - ) + writer = self.instances[instance_name] + token = writer.get_current_token_for_writer(instance_name) + for generator in self.instances.values(): + if writer != generator: + generator.advance(instance_name, token) - self.get_success(self.db_pool.runInteraction("_insert_rows", _insert)) + def _replicate_all(self) -> None: + """Similate a replication event for all instances.""" - def _insert_row_with_id(self, instance_name: str, stream_id: int) -> None: - """Insert one row as the given instance with given stream_id, updating - the postgres sequence position to match. - """ + for instance_name in self.instances: + self._replicate(instance_name) + + def _insert_row( + self, instance_name: str, stream_id: int, table: Optional[str] = None + ) -> None: + """Insert one row as the given instance with given stream_id.""" + + if table is None: + table = self.tables[0] + + factor = 1 if self.positive else -1 def _insert(txn: LoggingTransaction) -> None: txn.execute( - "INSERT INTO foobar VALUES (?, ?)", + "INSERT INTO %s VALUES (?, ?)" % (table,), ( stream_id, instance_name, ), ) - txn.execute("SELECT setval('foobar_seq', ?)", (stream_id,)) txn.execute( """ INSERT INTO stream_positions VALUES ('test_stream', ?, ?) ON CONFLICT (stream_name, instance_name) DO UPDATE SET stream_id = ? """, - (instance_name, stream_id, stream_id), + (instance_name, stream_id * factor, stream_id * factor), ) - self.get_success(self.db_pool.runInteraction("_insert_row_with_id", _insert)) + self.get_success(self.db_pool.runInteraction("_insert_row", _insert)) + + def _insert_rows( + self, + instance_name: str, + number: int, + table: Optional[str] = None, + update_stream_table: bool = True, + ) -> None: + """Insert N rows as the given instance, inserting with stream IDs pulled + from the postgres sequence. + """ + + if table is None: + table = self.tables[0] + factor = 1 if self.positive else -1 + + def _insert(txn: LoggingTransaction) -> None: + for _ in range(number): + next_val = self.seq_gen.get_next_id_txn(txn) + txn.execute( + "INSERT INTO %s (stream_id, instance_name) VALUES (?, ?)" + % (table,), + (next_val, instance_name), + ) + + if update_stream_table: + txn.execute( + """ + INSERT INTO stream_positions VALUES ('test_stream', ?, ?) + ON CONFLICT (stream_name, instance_name) DO UPDATE SET stream_id = ? + """, + (instance_name, next_val * factor, next_val * factor), + ) + + self.get_success(self.db_pool.runInteraction("_insert_rows", _insert)) + + +class MultiWriterIdGeneratorTestCase(MultiWriterIdGeneratorBase): def test_empty(self) -> None: """Test an ID generator against an empty database gives sensible current positions. @@ -347,137 +265,106 @@ class MultiWriterIdGeneratorTestCase(HomeserverTestCase): self.assertEqual(id_gen.get_positions(), {"master": 11}) self.assertEqual(id_gen.get_current_token_for_writer("master"), 11) - def test_multi_instance(self) -> None: - """Test that reads and writes from multiple processes are handled - correctly. - """ - self._insert_rows("first", 3) - self._insert_rows("second", 4) + def test_get_next_txn(self) -> None: + """Test that the `get_next_txn` function works correctly.""" - first_id_gen = self._create_id_generator("first", writers=["first", "second"]) - second_id_gen = self._create_id_generator("second", writers=["first", "second"]) + # Prefill table with 7 rows written by 'master' + self._insert_rows("master", 7) - self.assertEqual(first_id_gen.get_positions(), {"first": 3, "second": 7}) - self.assertEqual(first_id_gen.get_current_token_for_writer("first"), 7) - self.assertEqual(first_id_gen.get_current_token_for_writer("second"), 7) + id_gen = self._create_id_generator() - self.assertEqual(second_id_gen.get_positions(), {"first": 3, "second": 7}) - self.assertEqual(second_id_gen.get_current_token_for_writer("first"), 7) - self.assertEqual(second_id_gen.get_current_token_for_writer("second"), 7) + self.assertEqual(id_gen.get_positions(), {"master": 7}) + self.assertEqual(id_gen.get_current_token_for_writer("master"), 7) # Try allocating a new ID gen and check that we only see position # advanced after we leave the context manager. - async def _get_next_async() -> None: - async with first_id_gen.get_next() as stream_id: - self.assertEqual(stream_id, 8) - - self.assertEqual( - first_id_gen.get_positions(), {"first": 3, "second": 7} - ) - self.assertEqual(first_id_gen.get_persisted_upto_position(), 7) - - self.get_success(_get_next_async()) - - self.assertEqual(first_id_gen.get_positions(), {"first": 8, "second": 7}) - - # However the ID gen on the second instance won't have seen the update - self.assertEqual(second_id_gen.get_positions(), {"first": 3, "second": 7}) - - # ... but calling `get_next` on the second instance should give a unique - # stream ID + def _get_next_txn(txn: LoggingTransaction) -> None: + stream_id = id_gen.get_next_txn(txn) + self.assertEqual(stream_id, 8) - async def _get_next_async2() -> None: - async with second_id_gen.get_next() as stream_id: - self.assertEqual(stream_id, 9) + self.assertEqual(id_gen.get_positions(), {"master": 7}) + self.assertEqual(id_gen.get_current_token_for_writer("master"), 7) - self.assertEqual( - second_id_gen.get_positions(), {"first": 3, "second": 7} - ) + self.get_success(self.db_pool.runInteraction("test", _get_next_txn)) - self.get_success(_get_next_async2()) + self.assertEqual(id_gen.get_positions(), {"master": 8}) + self.assertEqual(id_gen.get_current_token_for_writer("master"), 8) - self.assertEqual(second_id_gen.get_positions(), {"first": 3, "second": 9}) + def test_restart_during_out_of_order_persistence(self) -> None: + """Test that restarting a process while another process is writing out + of order updates are handled correctly. + """ - # If the second ID gen gets told about the first, it correctly updates - second_id_gen.advance("first", 8) - self.assertEqual(second_id_gen.get_positions(), {"first": 8, "second": 9}) + # Prefill table with 7 rows written by 'master' + self._insert_rows("master", 7) - def test_multi_instance_empty_row(self) -> None: - """Test that reads and writes from multiple processes are handled - correctly, when one of the writers starts without any rows. - """ - # Insert some rows for two out of three of the ID gens. - self._insert_rows("first", 3) - self._insert_rows("second", 4) + id_gen = self._create_id_generator() - first_id_gen = self._create_id_generator( - "first", writers=["first", "second", "third"] - ) - second_id_gen = self._create_id_generator( - "second", writers=["first", "second", "third"] - ) - third_id_gen = self._create_id_generator( - "third", writers=["first", "second", "third"] - ) + self.assertEqual(id_gen.get_positions(), {"master": 7}) + self.assertEqual(id_gen.get_current_token_for_writer("master"), 7) - self.assertEqual( - first_id_gen.get_positions(), {"first": 3, "second": 7, "third": 7} - ) - self.assertEqual(first_id_gen.get_current_token_for_writer("first"), 7) - self.assertEqual(first_id_gen.get_current_token_for_writer("second"), 7) - self.assertEqual(first_id_gen.get_current_token_for_writer("third"), 7) + # Persist two rows at once + ctx1 = id_gen.get_next() + ctx2 = id_gen.get_next() - self.assertEqual( - second_id_gen.get_positions(), {"first": 3, "second": 7, "third": 7} - ) - self.assertEqual(second_id_gen.get_current_token_for_writer("first"), 7) - self.assertEqual(second_id_gen.get_current_token_for_writer("second"), 7) - self.assertEqual(second_id_gen.get_current_token_for_writer("third"), 7) + s1 = self.get_success(ctx1.__aenter__()) + s2 = self.get_success(ctx2.__aenter__()) - # Try allocating a new ID gen and check that we only see position - # advanced after we leave the context manager. + self.assertEqual(s1, 8) + self.assertEqual(s2, 9) - async def _get_next_async() -> None: - async with third_id_gen.get_next() as stream_id: - self.assertEqual(stream_id, 8) + self.assertEqual(id_gen.get_positions(), {"master": 7}) + self.assertEqual(id_gen.get_current_token_for_writer("master"), 7) - self.assertEqual( - third_id_gen.get_positions(), {"first": 3, "second": 7, "third": 7} - ) - self.assertEqual(third_id_gen.get_persisted_upto_position(), 7) + # We finish persisting the second row before restart + self.get_success(ctx2.__aexit__(None, None, None)) - self.get_success(_get_next_async()) + # We simulate a restart of another worker by just creating a new ID gen. + id_gen_worker = self._create_id_generator("worker") - self.assertEqual( - third_id_gen.get_positions(), {"first": 3, "second": 7, "third": 8} - ) + # Restarted worker should not see the second persisted row + self.assertEqual(id_gen_worker.get_positions(), {"master": 7}) + self.assertEqual(id_gen_worker.get_current_token_for_writer("master"), 7) - def test_get_next_txn(self) -> None: - """Test that the `get_next_txn` function works correctly.""" + # Now if we persist the first row then both instances should jump ahead + # correctly. + self.get_success(ctx1.__aexit__(None, None, None)) - # Prefill table with 7 rows written by 'master' - self._insert_rows("master", 7) + self.assertEqual(id_gen.get_positions(), {"master": 9}) + id_gen_worker.advance("master", 9) + self.assertEqual(id_gen_worker.get_positions(), {"master": 9}) - id_gen = self._create_id_generator() - self.assertEqual(id_gen.get_positions(), {"master": 7}) - self.assertEqual(id_gen.get_current_token_for_writer("master"), 7) +class WorkerMultiWriterIdGeneratorTestCase(MultiWriterIdGeneratorBase): + if not USE_POSTGRES_FOR_TESTS: + skip = "Requires Postgres" - # Try allocating a new ID gen and check that we only see position - # advanced after we leave the context manager. + def _insert_row_with_id(self, instance_name: str, stream_id: int) -> None: + """Insert one row as the given instance with given stream_id, updating + the postgres sequence position to match. + """ - def _get_next_txn(txn: LoggingTransaction) -> None: - stream_id = id_gen.get_next_txn(txn) - self.assertEqual(stream_id, 8) + def _insert(txn: LoggingTransaction) -> None: + txn.execute( + "INSERT INTO foobar (stream_id, instance_name) VALUES (?, ?)", + ( + stream_id, + instance_name, + ), + ) - self.assertEqual(id_gen.get_positions(), {"master": 7}) - self.assertEqual(id_gen.get_current_token_for_writer("master"), 7) + txn.execute("SELECT setval('foobar_seq', ?)", (stream_id,)) - self.get_success(self.db_pool.runInteraction("test", _get_next_txn)) + txn.execute( + """ + INSERT INTO stream_positions VALUES ('test_stream', ?, ?) + ON CONFLICT (stream_name, instance_name) DO UPDATE SET stream_id = ? + """, + (instance_name, stream_id, stream_id), + ) - self.assertEqual(id_gen.get_positions(), {"master": 8}) - self.assertEqual(id_gen.get_current_token_for_writer("master"), 8) + self.get_success(self.db_pool.runInteraction("_insert_row_with_id", _insert)) def test_get_persisted_upto_position(self) -> None: """Test that `get_persisted_upto_position` correctly tracks updates to @@ -531,7 +418,9 @@ class MultiWriterIdGeneratorTestCase(HomeserverTestCase): id_gen = self._create_id_generator("first", writers=["first", "second"]) - self.assertEqual(id_gen.get_positions(), {"first": 3, "second": 5}) + # When the writer is created, it assumes its own position is the current head of + # the sequence + self.assertEqual(id_gen.get_positions(), {"first": 5, "second": 5}) self.assertEqual(id_gen.get_persisted_upto_position(), 5) @@ -548,49 +437,118 @@ class MultiWriterIdGeneratorTestCase(HomeserverTestCase): # `persisted_upto_position` in this case, then it will be correct in the # other cases that are tested above (since they'll hit the same code). - def test_restart_during_out_of_order_persistence(self) -> None: - """Test that restarting a process while another process is writing out - of order updates are handled correctly. + def test_multi_instance(self) -> None: + """Test that reads and writes from multiple processes are handled + correctly. """ + self._insert_rows("first", 3) + first_id_gen = self._create_id_generator("first", writers=["first", "second"]) - # Prefill table with 7 rows written by 'master' - self._insert_rows("master", 7) + self._insert_rows("second", 4) + second_id_gen = self._create_id_generator("second", writers=["first", "second"]) - id_gen = self._create_id_generator() + self._replicate_all() - self.assertEqual(id_gen.get_positions(), {"master": 7}) - self.assertEqual(id_gen.get_current_token_for_writer("master"), 7) + self.assertEqual(first_id_gen.get_positions(), {"first": 3, "second": 7}) + self.assertEqual(first_id_gen.get_current_token_for_writer("first"), 7) + self.assertEqual(first_id_gen.get_current_token_for_writer("second"), 7) - # Persist two rows at once - ctx1 = id_gen.get_next() - ctx2 = id_gen.get_next() + self.assertEqual(second_id_gen.get_positions(), {"first": 3, "second": 7}) + self.assertEqual(second_id_gen.get_current_token_for_writer("first"), 7) + self.assertEqual(second_id_gen.get_current_token_for_writer("second"), 7) - s1 = self.get_success(ctx1.__aenter__()) - s2 = self.get_success(ctx2.__aenter__()) + # Try allocating a new ID gen and check that we only see position + # advanced after we leave the context manager. - self.assertEqual(s1, 8) - self.assertEqual(s2, 9) + async def _get_next_async() -> None: + async with first_id_gen.get_next() as stream_id: + self.assertEqual(stream_id, 8) - self.assertEqual(id_gen.get_positions(), {"master": 7}) - self.assertEqual(id_gen.get_current_token_for_writer("master"), 7) + self.assertEqual( + first_id_gen.get_positions(), {"first": 3, "second": 7} + ) + self.assertEqual( + second_id_gen.get_positions(), {"first": 3, "second": 7} + ) + self.assertEqual(first_id_gen.get_persisted_upto_position(), 7) - # We finish persisting the second row before restart - self.get_success(ctx2.__aexit__(None, None, None)) + self.get_success(_get_next_async()) - # We simulate a restart of another worker by just creating a new ID gen. - id_gen_worker = self._create_id_generator("worker") + self.assertEqual(first_id_gen.get_positions(), {"first": 8, "second": 7}) - # Restarted worker should not see the second persisted row - self.assertEqual(id_gen_worker.get_positions(), {"master": 7}) - self.assertEqual(id_gen_worker.get_current_token_for_writer("master"), 7) + # However the ID gen on the second instance won't have seen the update + self.assertEqual(second_id_gen.get_positions(), {"first": 3, "second": 7}) - # Now if we persist the first row then both instances should jump ahead - # correctly. - self.get_success(ctx1.__aexit__(None, None, None)) + # ... but calling `get_next` on the second instance should give a unique + # stream ID - self.assertEqual(id_gen.get_positions(), {"master": 9}) - id_gen_worker.advance("master", 9) - self.assertEqual(id_gen_worker.get_positions(), {"master": 9}) + async def _get_next_async2() -> None: + async with second_id_gen.get_next() as stream_id: + self.assertEqual(stream_id, 9) + + self.assertEqual( + second_id_gen.get_positions(), {"first": 3, "second": 7} + ) + + self.get_success(_get_next_async2()) + + self.assertEqual(second_id_gen.get_positions(), {"first": 3, "second": 9}) + + # If the second ID gen gets told about the first, it correctly updates + second_id_gen.advance("first", 8) + self.assertEqual(second_id_gen.get_positions(), {"first": 8, "second": 9}) + + def test_multi_instance_empty_row(self) -> None: + """Test that reads and writes from multiple processes are handled + correctly, when one of the writers starts without any rows. + """ + # Insert some rows for two out of three of the ID gens. + self._insert_rows("first", 3) + first_id_gen = self._create_id_generator( + "first", writers=["first", "second", "third"] + ) + + self._insert_rows("second", 4) + second_id_gen = self._create_id_generator( + "second", writers=["first", "second", "third"] + ) + third_id_gen = self._create_id_generator( + "third", writers=["first", "second", "third"] + ) + + self._replicate_all() + + self.assertEqual( + first_id_gen.get_positions(), {"first": 3, "second": 7, "third": 7} + ) + self.assertEqual(first_id_gen.get_current_token_for_writer("first"), 7) + self.assertEqual(first_id_gen.get_current_token_for_writer("second"), 7) + self.assertEqual(first_id_gen.get_current_token_for_writer("third"), 7) + + self.assertEqual( + second_id_gen.get_positions(), {"first": 3, "second": 7, "third": 7} + ) + self.assertEqual(second_id_gen.get_current_token_for_writer("first"), 7) + self.assertEqual(second_id_gen.get_current_token_for_writer("second"), 7) + self.assertEqual(second_id_gen.get_current_token_for_writer("third"), 7) + + # Try allocating a new ID gen and check that we only see position + # advanced after we leave the context manager. + + async def _get_next_async() -> None: + async with third_id_gen.get_next() as stream_id: + self.assertEqual(stream_id, 8) + + self.assertEqual( + third_id_gen.get_positions(), {"first": 3, "second": 7, "third": 7} + ) + self.assertEqual(third_id_gen.get_persisted_upto_position(), 7) + + self.get_success(_get_next_async()) + + self.assertEqual( + third_id_gen.get_positions(), {"first": 3, "second": 7, "third": 8} + ) def test_writer_config_change(self) -> None: """Test that changing the writer config correctly works.""" @@ -640,7 +598,7 @@ class MultiWriterIdGeneratorTestCase(HomeserverTestCase): self.assertEqual(id_gen_5.get_current_token_for_writer("third"), 6) def test_sequence_consistency(self) -> None: - """Test that we error out if the table and sequence diverges.""" + """Test that we correct the sequence if the table and sequence diverges.""" # Prefill with some rows self._insert_row_with_id("master", 3) @@ -651,17 +609,24 @@ class MultiWriterIdGeneratorTestCase(HomeserverTestCase): self.get_success(self.db_pool.runInteraction("_insert", _insert)) - # Creating the ID gen should error - with self.assertRaises(IncorrectDatabaseSetup): - self._create_id_generator("first") + # Creating the ID gen should now fix the inconsistency + id_gen = self._create_id_generator() + + async def _get_next_async() -> None: + async with id_gen.get_next() as stream_id: + self.assertEqual(stream_id, 27) + + self.get_success(_get_next_async()) def test_minimal_local_token(self) -> None: self._insert_rows("first", 3) - self._insert_rows("second", 4) - first_id_gen = self._create_id_generator("first", writers=["first", "second"]) + + self._insert_rows("second", 4) second_id_gen = self._create_id_generator("second", writers=["first", "second"]) + self._replicate_all() + self.assertEqual(first_id_gen.get_positions(), {"first": 3, "second": 7}) self.assertEqual(first_id_gen.get_minimal_local_current_token(), 3) @@ -673,15 +638,17 @@ class MultiWriterIdGeneratorTestCase(HomeserverTestCase): token when there are no writes. """ self._insert_rows("first", 3) - self._insert_rows("second", 4) - first_id_gen = self._create_id_generator( "first", writers=["first", "second", "third"] ) + + self._insert_rows("second", 4) second_id_gen = self._create_id_generator( "second", writers=["first", "second", "third"] ) + self._replicate_all() + self.assertEqual(second_id_gen.get_current_token_for_writer("first"), 7) self.assertEqual(second_id_gen.get_current_token_for_writer("second"), 7) self.assertEqual(second_id_gen.get_current_token(), 7) @@ -720,68 +687,13 @@ class MultiWriterIdGeneratorTestCase(HomeserverTestCase): self.assertEqual(second_id_gen.get_current_token(), 7) -class BackwardsMultiWriterIdGeneratorTestCase(HomeserverTestCase): +class BackwardsMultiWriterIdGeneratorTestCase(MultiWriterIdGeneratorBase): """Tests MultiWriterIdGenerator that produce *negative* stream IDs.""" if not USE_POSTGRES_FOR_TESTS: skip = "Requires Postgres" - def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: - self.store = hs.get_datastores().main - self.db_pool: DatabasePool = self.store.db_pool - - self.get_success(self.db_pool.runInteraction("_setup_db", self._setup_db)) - - def _setup_db(self, txn: LoggingTransaction) -> None: - txn.execute("CREATE SEQUENCE foobar_seq") - txn.execute( - """ - CREATE TABLE foobar ( - stream_id BIGINT NOT NULL, - instance_name TEXT NOT NULL, - data TEXT - ); - """ - ) - - def _create_id_generator( - self, instance_name: str = "master", writers: Optional[List[str]] = None - ) -> MultiWriterIdGenerator: - def _create(conn: LoggingDatabaseConnection) -> MultiWriterIdGenerator: - return MultiWriterIdGenerator( - conn, - self.db_pool, - notifier=self.hs.get_replication_notifier(), - stream_name="test_stream", - instance_name=instance_name, - tables=[("foobar", "instance_name", "stream_id")], - sequence_name="foobar_seq", - writers=writers or ["master"], - positive=False, - ) - - return self.get_success(self.db_pool.runWithConnection(_create)) - - def _insert_row(self, instance_name: str, stream_id: int) -> None: - """Insert one row as the given instance with given stream_id.""" - - def _insert(txn: LoggingTransaction) -> None: - txn.execute( - "INSERT INTO foobar VALUES (?, ?)", - ( - stream_id, - instance_name, - ), - ) - txn.execute( - """ - INSERT INTO stream_positions VALUES ('test_stream', ?, ?) - ON CONFLICT (stream_name, instance_name) DO UPDATE SET stream_id = ? - """, - (instance_name, -stream_id, -stream_id), - ) - - self.get_success(self.db_pool.runInteraction("_insert_row", _insert)) + positive = False def test_single_instance(self) -> None: """Test that reads and writes from a single process are handled @@ -827,7 +739,7 @@ class BackwardsMultiWriterIdGeneratorTestCase(HomeserverTestCase): async def _get_next_async() -> None: async with id_gen_1.get_next() as stream_id: self._insert_row("first", stream_id) - id_gen_2.advance("first", stream_id) + self._replicate("first") self.get_success(_get_next_async()) @@ -839,7 +751,7 @@ class BackwardsMultiWriterIdGeneratorTestCase(HomeserverTestCase): async def _get_next_async2() -> None: async with id_gen_2.get_next() as stream_id: self._insert_row("second", stream_id) - id_gen_1.advance("second", stream_id) + self._replicate("second") self.get_success(_get_next_async2()) @@ -849,98 +761,26 @@ class BackwardsMultiWriterIdGeneratorTestCase(HomeserverTestCase): self.assertEqual(id_gen_2.get_persisted_upto_position(), -2) -class MultiTableMultiWriterIdGeneratorTestCase(HomeserverTestCase): +class MultiTableMultiWriterIdGeneratorTestCase(MultiWriterIdGeneratorBase): if not USE_POSTGRES_FOR_TESTS: skip = "Requires Postgres" - def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: - self.store = hs.get_datastores().main - self.db_pool: DatabasePool = self.store.db_pool - - self.get_success(self.db_pool.runInteraction("_setup_db", self._setup_db)) - - def _setup_db(self, txn: LoggingTransaction) -> None: - txn.execute("CREATE SEQUENCE foobar_seq") - txn.execute( - """ - CREATE TABLE foobar1 ( - stream_id BIGINT NOT NULL, - instance_name TEXT NOT NULL, - data TEXT - ); - """ - ) - - txn.execute( - """ - CREATE TABLE foobar2 ( - stream_id BIGINT NOT NULL, - instance_name TEXT NOT NULL, - data TEXT - ); - """ - ) - - def _create_id_generator( - self, instance_name: str = "master", writers: Optional[List[str]] = None - ) -> MultiWriterIdGenerator: - def _create(conn: LoggingDatabaseConnection) -> MultiWriterIdGenerator: - return MultiWriterIdGenerator( - conn, - self.db_pool, - notifier=self.hs.get_replication_notifier(), - stream_name="test_stream", - instance_name=instance_name, - tables=[ - ("foobar1", "instance_name", "stream_id"), - ("foobar2", "instance_name", "stream_id"), - ], - sequence_name="foobar_seq", - writers=writers or ["master"], - ) - - return self.get_success_or_raise(self.db_pool.runWithConnection(_create)) - - def _insert_rows( - self, - table: str, - instance_name: str, - number: int, - update_stream_table: bool = True, - ) -> None: - """Insert N rows as the given instance, inserting with stream IDs pulled - from the postgres sequence. - """ - - def _insert(txn: LoggingTransaction) -> None: - for _ in range(number): - txn.execute( - "INSERT INTO %s VALUES (nextval('foobar_seq'), ?)" % (table,), - (instance_name,), - ) - if update_stream_table: - txn.execute( - """ - INSERT INTO stream_positions VALUES ('test_stream', ?, lastval()) - ON CONFLICT (stream_name, instance_name) DO UPDATE SET stream_id = lastval() - """, - (instance_name,), - ) - - self.get_success(self.db_pool.runInteraction("_insert_rows", _insert)) + tables = ["foobar1", "foobar2"] def test_load_existing_stream(self) -> None: """Test creating ID gens with multiple tables that have rows from after the position in `stream_positions` table. """ - self._insert_rows("foobar1", "first", 3) - self._insert_rows("foobar2", "second", 3) - self._insert_rows("foobar2", "second", 1, update_stream_table=False) - + self._insert_rows("first", 3, table="foobar1") first_id_gen = self._create_id_generator("first", writers=["first", "second"]) + + self._insert_rows("second", 3, table="foobar2") + self._insert_rows("second", 1, table="foobar2", update_stream_table=False) second_id_gen = self._create_id_generator("second", writers=["first", "second"]) - self.assertEqual(first_id_gen.get_positions(), {"first": 3, "second": 6}) + self._replicate_all() + + self.assertEqual(first_id_gen.get_positions(), {"first": 3, "second": 7}) self.assertEqual(first_id_gen.get_current_token_for_writer("first"), 7) self.assertEqual(first_id_gen.get_current_token_for_writer("second"), 7) self.assertEqual(first_id_gen.get_persisted_upto_position(), 7) diff --git a/tests/storage/test_stream.py b/tests/storage/test_stream.py index 2029cd9c68..fe1e873e15 100644 --- a/tests/storage/test_stream.py +++ b/tests/storage/test_stream.py @@ -19,7 +19,10 @@ # # -from typing import List +import logging +from typing import List, Tuple + +from immutabledict import immutabledict from twisted.test.proto_helpers import MemoryReactor @@ -28,11 +31,13 @@ from synapse.api.filtering import Filter from synapse.rest import admin from synapse.rest.client import login, room from synapse.server import HomeServer -from synapse.types import JsonDict +from synapse.types import JsonDict, PersistedEventPosition, RoomStreamToken from synapse.util import Clock from tests.unittest import HomeserverTestCase +logger = logging.getLogger(__name__) + class PaginationTestCase(HomeserverTestCase): """ @@ -268,3 +273,273 @@ class PaginationTestCase(HomeserverTestCase): } chunk = self._filter_messages(filter) self.assertEqual(chunk, [self.event_id_1, self.event_id_2, self.event_id_none]) + + +class GetLastEventInRoomBeforeStreamOrderingTestCase(HomeserverTestCase): + """ + Test `get_last_event_pos_in_room_before_stream_ordering(...)` + """ + + servlets = [ + admin.register_servlets, + room.register_servlets, + login.register_servlets, + ] + + def prepare(self, reactor: MemoryReactor, clock: Clock, hs: HomeServer) -> None: + self.store = hs.get_datastores().main + self.event_sources = hs.get_event_sources() + + def _update_persisted_instance_name_for_event( + self, event_id: str, instance_name: str + ) -> None: + """ + Update the `instance_name` that persisted the the event in the database. + """ + return self.get_success( + self.store.db_pool.simple_update_one( + "events", + keyvalues={"event_id": event_id}, + updatevalues={"instance_name": instance_name}, + ) + ) + + def _send_event_on_instance( + self, instance_name: str, room_id: str, access_token: str + ) -> Tuple[JsonDict, PersistedEventPosition]: + """ + Send an event in a room and mimic that it was persisted by a specific + instance/worker. + """ + event_response = self.helper.send( + room_id, f"{instance_name} message", tok=access_token + ) + + self._update_persisted_instance_name_for_event( + event_response["event_id"], instance_name + ) + + event_pos = self.get_success( + self.store.get_position_for_event(event_response["event_id"]) + ) + + return event_response, event_pos + + def test_before_room_created(self) -> None: + """ + Test that no event is returned if we are using a token before the room was even created + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + + before_room_token = self.event_sources.get_current_token() + + room_id = self.helper.create_room_as(user1_id, tok=user1_tok, is_public=True) + + last_event_result = self.get_success( + self.store.get_last_event_pos_in_room_before_stream_ordering( + room_id=room_id, + end_token=before_room_token.room_key, + ) + ) + + self.assertIsNone(last_event_result) + + def test_after_room_created(self) -> None: + """ + Test that an event is returned if we are using a token after the room was created + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + + room_id = self.helper.create_room_as(user1_id, tok=user1_tok, is_public=True) + + after_room_token = self.event_sources.get_current_token() + + last_event_result = self.get_success( + self.store.get_last_event_pos_in_room_before_stream_ordering( + room_id=room_id, + end_token=after_room_token.room_key, + ) + ) + assert last_event_result is not None + last_event_id, _ = last_event_result + + self.assertIsNotNone(last_event_id) + + def test_activity_in_other_rooms(self) -> None: + """ + Test to make sure that the last event in the room is returned even if the + `stream_ordering` has advanced from activity in other rooms. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + + room_id1 = self.helper.create_room_as(user1_id, tok=user1_tok, is_public=True) + event_response = self.helper.send(room_id1, "target!", tok=user1_tok) + # Create another room to advance the stream_ordering + self.helper.create_room_as(user1_id, tok=user1_tok, is_public=True) + + after_room_token = self.event_sources.get_current_token() + + last_event_result = self.get_success( + self.store.get_last_event_pos_in_room_before_stream_ordering( + room_id=room_id1, + end_token=after_room_token.room_key, + ) + ) + assert last_event_result is not None + last_event_id, _ = last_event_result + + # Make sure it's the event we expect (which also means we know it's from the + # correct room) + self.assertEqual(last_event_id, event_response["event_id"]) + + def test_activity_after_token_has_no_effect(self) -> None: + """ + Test to make sure we return the last event before the token even if there is + activity after it. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + + room_id1 = self.helper.create_room_as(user1_id, tok=user1_tok, is_public=True) + event_response = self.helper.send(room_id1, "target!", tok=user1_tok) + + after_room_token = self.event_sources.get_current_token() + + # Send some events after the token + self.helper.send(room_id1, "after1", tok=user1_tok) + self.helper.send(room_id1, "after2", tok=user1_tok) + + last_event_result = self.get_success( + self.store.get_last_event_pos_in_room_before_stream_ordering( + room_id=room_id1, + end_token=after_room_token.room_key, + ) + ) + assert last_event_result is not None + last_event_id, _ = last_event_result + + # Make sure it's the last event before the token + self.assertEqual(last_event_id, event_response["event_id"]) + + def test_last_event_within_sharded_token(self) -> None: + """ + Test to make sure we can find the last event that that is *within* the sharded + token (a token that has an `instance_map` and looks like + `m{min_pos}~{writer1}.{pos1}~{writer2}.{pos2}`). We are specifically testing + that we can find an event within the tokens minimum and instance + `stream_ordering`. + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + + room_id1 = self.helper.create_room_as(user1_id, tok=user1_tok, is_public=True) + event_response1, event_pos1 = self._send_event_on_instance( + "worker1", room_id1, user1_tok + ) + event_response2, event_pos2 = self._send_event_on_instance( + "worker1", room_id1, user1_tok + ) + event_response3, event_pos3 = self._send_event_on_instance( + "worker1", room_id1, user1_tok + ) + + # Create another room to advance the `stream_ordering` on the same worker + # so we can sandwich event3 in the middle of the token + room_id2 = self.helper.create_room_as(user1_id, tok=user1_tok, is_public=True) + event_response4, event_pos4 = self._send_event_on_instance( + "worker1", room_id2, user1_tok + ) + + # Assemble a token that encompasses event1 -> event4 on worker1 + end_token = RoomStreamToken( + stream=event_pos2.stream, + instance_map=immutabledict({"worker1": event_pos4.stream}), + ) + + # Send some events after the token + self.helper.send(room_id1, "after1", tok=user1_tok) + self.helper.send(room_id1, "after2", tok=user1_tok) + + last_event_result = self.get_success( + self.store.get_last_event_pos_in_room_before_stream_ordering( + room_id=room_id1, + end_token=end_token, + ) + ) + assert last_event_result is not None + last_event_id, _ = last_event_result + + # Should find closest event before the token in room1 + self.assertEqual( + last_event_id, + event_response3["event_id"], + f"We expected {event_response3['event_id']} but saw {last_event_id} which corresponds to " + + str( + { + "event1": event_response1["event_id"], + "event2": event_response2["event_id"], + "event3": event_response3["event_id"], + } + ), + ) + + def test_last_event_before_sharded_token(self) -> None: + """ + Test to make sure we can find the last event that is *before* the sharded token + (a token that has an `instance_map` and looks like + `m{min_pos}~{writer1}.{pos1}~{writer2}.{pos2}`). + """ + user1_id = self.register_user("user1", "pass") + user1_tok = self.login(user1_id, "pass") + + room_id1 = self.helper.create_room_as(user1_id, tok=user1_tok, is_public=True) + event_response1, event_pos1 = self._send_event_on_instance( + "worker1", room_id1, user1_tok + ) + event_response2, event_pos2 = self._send_event_on_instance( + "worker1", room_id1, user1_tok + ) + + # Create another room to advance the `stream_ordering` on the same worker + room_id2 = self.helper.create_room_as(user1_id, tok=user1_tok, is_public=True) + event_response3, event_pos3 = self._send_event_on_instance( + "worker1", room_id2, user1_tok + ) + event_response4, event_pos4 = self._send_event_on_instance( + "worker1", room_id2, user1_tok + ) + + # Assemble a token that encompasses event3 -> event4 on worker1 + end_token = RoomStreamToken( + stream=event_pos3.stream, + instance_map=immutabledict({"worker1": event_pos4.stream}), + ) + + # Send some events after the token + self.helper.send(room_id1, "after1", tok=user1_tok) + self.helper.send(room_id1, "after2", tok=user1_tok) + + last_event_result = self.get_success( + self.store.get_last_event_pos_in_room_before_stream_ordering( + room_id=room_id1, + end_token=end_token, + ) + ) + assert last_event_result is not None + last_event_id, _ = last_event_result + + # Should find closest event before the token in room1 + self.assertEqual( + last_event_id, + event_response2["event_id"], + f"We expected {event_response2['event_id']} but saw {last_event_id} which corresponds to " + + str( + { + "event1": event_response1["event_id"], + "event2": event_response2["event_id"], + } + ), + ) diff --git a/tests/storage/test_user_directory.py b/tests/storage/test_user_directory.py index 156a610faa..c26932069f 100644 --- a/tests/storage/test_user_directory.py +++ b/tests/storage/test_user_directory.py @@ -711,6 +711,10 @@ class UserDirectoryICUTestCase(HomeserverTestCase): ), ) + self.assertEqual(_parse_words_with_icu("user-1"), ["user-1"]) + self.assertEqual(_parse_words_with_icu("user-ab"), ["user-ab"]) + self.assertEqual(_parse_words_with_icu("user.--1"), ["user", "-1"]) + def test_regex_word_boundary_punctuation(self) -> None: """ Tests the behaviour of punctuation with the non-ICU tokeniser diff --git a/tests/test_visibility.py b/tests/test_visibility.py index 3e2100eab4..89cbe4e54b 100644 --- a/tests/test_visibility.py +++ b/tests/test_visibility.py @@ -336,7 +336,6 @@ class FilterEventsForClientTestCase(HomeserverTestCase): self.hs.get_storage_controllers(), "@joiner:test", events_to_filter, - msc4115_membership_on_events=True, ) ) resident_filtered_events = self.get_success( @@ -344,7 +343,6 @@ class FilterEventsForClientTestCase(HomeserverTestCase): self.hs.get_storage_controllers(), "@resident:test", events_to_filter, - msc4115_membership_on_events=True, ) ) @@ -357,7 +355,7 @@ class FilterEventsForClientTestCase(HomeserverTestCase): self.assertEqual( ["join", "join", "leave"], [ - e.unsigned[EventUnsignedContentFields.MSC4115_MEMBERSHIP] + e.unsigned[EventUnsignedContentFields.MEMBERSHIP] for e in joiner_filtered_events ], ) @@ -379,7 +377,7 @@ class FilterEventsForClientTestCase(HomeserverTestCase): self.assertEqual( ["join", "join", "join", "join", "join"], [ - e.unsigned[EventUnsignedContentFields.MSC4115_MEMBERSHIP] + e.unsigned[EventUnsignedContentFields.MEMBERSHIP] for e in resident_filtered_events ], ) @@ -441,7 +439,6 @@ class FilterEventsOutOfBandEventsForClientTestCase( self.hs.get_storage_controllers(), "@user:test", [invite_event, reject_event], - msc4115_membership_on_events=True, ) ) self.assertEqual( @@ -451,7 +448,7 @@ class FilterEventsOutOfBandEventsForClientTestCase( self.assertEqual( ["invite", "leave"], [ - e.unsigned[EventUnsignedContentFields.MSC4115_MEMBERSHIP] + e.unsigned[EventUnsignedContentFields.MEMBERSHIP] for e in filtered_events ], ) @@ -463,7 +460,6 @@ class FilterEventsOutOfBandEventsForClientTestCase( self.hs.get_storage_controllers(), "@other:test", [invite_event, reject_event], - msc4115_membership_on_events=True, ) ), [], diff --git a/tests/unittest.py b/tests/unittest.py index e6aad9ed40..a7c20556a0 100644 --- a/tests/unittest.py +++ b/tests/unittest.py @@ -344,6 +344,8 @@ class HomeserverTestCase(TestCase): self._hs_args = {"clock": self.clock, "reactor": self.reactor} self.hs = self.make_homeserver(self.reactor, self.clock) + self.hs.get_datastores().main.tests_allow_no_chain_cover_index = False + # Honour the `use_frozen_dicts` config option. We have to do this # manually because this is taken care of in the app `start` code, which # we don't run. Plus we want to reset it on tearDown. @@ -637,13 +639,13 @@ class HomeserverTestCase(TestCase): return self.successResultOf(deferred) def get_failure( - self, d: Awaitable[Any], exc: Type[_ExcType] + self, d: Awaitable[Any], exc: Type[_ExcType], by: float = 0.0 ) -> _TypedFailure[_ExcType]: """ Run a Deferred and get a Failure from it. The failure must be of the type `exc`. """ deferred: Deferred[Any] = ensureDeferred(d) # type: ignore[arg-type] - self.pump() + self.pump(by) return self.failureResultOf(deferred, exc) def get_success_or_raise(self, d: Awaitable[TV], by: float = 0.0) -> TV: |