diff options
author | Richard van der Hoff <1389908+richvdh@users.noreply.github.com> | 2021-01-18 14:52:49 +0000 |
---|---|---|
committer | GitHub <noreply@github.com> | 2021-01-18 14:52:49 +0000 |
commit | 02070c69faa47bf6aef280939c2d5f32cbcb9f25 (patch) | |
tree | 9815f932175ae1ddfb3acb5b6d8f811f5848bbf0 /tests/test_utils/html_parsers.py | |
parent | Fix the Python 3.5 old-deps build. (#9146) (diff) | |
download | synapse-02070c69faa47bf6aef280939c2d5f32cbcb9f25.tar.xz |
Fix bugs in handling clientRedirectUrl, and improve OIDC tests (#9127, #9128)
* Factor out a common TestHtmlParser Looks like I'm doing this in a few different places. * Improve OIDC login test Complete the OIDC login flow, rather than giving up halfway through. * Ensure that OIDC login works with multiple OIDC providers * Fix bugs in handling clientRedirectUrl - don't drop duplicate query-params, or params with no value - allow utf-8 in query-params
Diffstat (limited to 'tests/test_utils/html_parsers.py')
-rw-r--r-- | tests/test_utils/html_parsers.py | 53 |
1 files changed, 53 insertions, 0 deletions
diff --git a/tests/test_utils/html_parsers.py b/tests/test_utils/html_parsers.py new file mode 100644 index 0000000000..ad563eb3f0 --- /dev/null +++ b/tests/test_utils/html_parsers.py @@ -0,0 +1,53 @@ +# -*- coding: utf-8 -*- +# Copyright 2021 The Matrix.org Foundation C.I.C. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +from html.parser import HTMLParser +from typing import Dict, Iterable, List, Optional, Tuple + + +class TestHtmlParser(HTMLParser): + """A generic HTML page parser which extracts useful things from the HTML""" + + def __init__(self): + super().__init__() + + # a list of links found in the doc + self.links = [] # type: List[str] + + # the values of any hidden <input>s: map from name to value + self.hiddens = {} # type: Dict[str, Optional[str]] + + # the values of any radio buttons: map from name to list of values + self.radios = {} # type: Dict[str, List[Optional[str]]] + + def handle_starttag( + self, tag: str, attrs: Iterable[Tuple[str, Optional[str]]] + ) -> None: + attr_dict = dict(attrs) + if tag == "a": + href = attr_dict["href"] + if href: + self.links.append(href) + elif tag == "input": + input_name = attr_dict.get("name") + if attr_dict["type"] == "radio": + assert input_name + self.radios.setdefault(input_name, []).append(attr_dict["value"]) + elif attr_dict["type"] == "hidden": + assert input_name + self.hiddens[input_name] = attr_dict["value"] + + def error(_, message): + raise AssertionError(message) |