Allow specifying the value of Accept-Language header for URL previews (#7265)

2 files changed, 35 insertions, 2 deletions

diff --git a/synapse/config/repository.py b/synapse/config/repository.py
index 7d2dd27fd0..7193ea1114 100644
--- a/synapse/config/repository.py
+++ b/synapse/config/repository.py
@@ -192,6 +192,10 @@ class ContentRepositoryConfig(Config):
 
             self.url_preview_url_blacklist = config.get("url_preview_url_blacklist", ())
 
+            self.url_preview_accept_language = config.get(
+                "url_preview_accept_language"
+            ) or ["en"]
+
     def generate_config_section(self, data_dir_path, **kwargs):
         media_store = os.path.join(data_dir_path, "media_store")
         uploads_path = os.path.join(data_dir_path, "uploads")
@@ -329,6 +333,31 @@ class ContentRepositoryConfig(Config):
         # The largest allowed URL preview spidering size in bytes
         #
         #max_spider_size: 10M
+
+        # A list of values for the Accept-Language HTTP header used when
+        # downloading webpages during URL preview generation. This allows
+        # Synapse to specify the preferred languages that URL previews should
+        # be in when communicating with remote servers.
+        #
+        # Each value is a IETF language tag; a 2-3 letter identifier for a
+        # language, optionally followed by subtags separated by '-', specifying
+        # a country or region variant.
+        #
+        # Multiple values can be provided, and a weight can be added to each by
+        # using quality value syntax (;q=). '*' translates to any language.
+        #
+        # Defaults to "en".
+        #
+        # Example:
+        #
+        # url_preview_accept_language:
+        #   - en-UK
+        #   - en-US;q=0.9
+        #   - fr;q=0.8
+        #   - *;q=0.7
+        #
+        url_preview_accept_language:
+        #   - en
         """
             % locals()
         )
diff --git a/synapse/rest/media/v1/preview_url_resource.py b/synapse/rest/media/v1/preview_url_resource.py
index c46676f8fc..f68e18ea8a 100644
--- a/synapse/rest/media/v1/preview_url_resource.py
+++ b/synapse/rest/media/v1/preview_url_resource.py
@@ -86,6 +86,7 @@ class PreviewUrlResource(DirectServeResource):
         self.media_storage = media_storage
 
         self.url_preview_url_blacklist = hs.config.url_preview_url_blacklist
+        self.url_preview_accept_language = hs.config.url_preview_accept_language
 
         # memory cache mapping urls to an ObservableDeferred returning
         # JSON-encoded OG metadata
@@ -315,9 +316,12 @@ class PreviewUrlResource(DirectServeResource):
 
         with self.media_storage.store_into_file(file_info) as (f, fname, finish):
             try:
-                logger.debug("Trying to get url '%s'", url)
+                logger.debug("Trying to get preview for url '%s'", url)
                 length, headers, uri, code = await self.client.get_file(
-                    url, output_stream=f, max_size=self.max_spider_size
+                    url,
+                    output_stream=f,
+                    max_size=self.max_spider_size,
+                    headers={"Accept-Language": self.url_preview_accept_language},
                 )
             except SynapseError:
                 # Pass SynapseErrors through directly, so that the servlet