Merge pull request #2767 from matrix-org/erikj/media_storage_refactor

Refactor MediaRepository to separate out storage

synapse/rest/media/v1/_base.py

@@ -70,38 +70,11 @@ def respond_with_file(request, media_type, file_path,
     logger.debug("Responding with %r", file_path)
 
     if os.path.isfile(file_path):
-        request.setHeader(b"Content-Type", media_type.encode("UTF-8"))
-        if upload_name:
-            if is_ascii(upload_name):
-                request.setHeader(
-                    b"Content-Disposition",
-                    b"inline; filename=%s" % (
-                        urllib.quote(upload_name.encode("utf-8")),
-                    ),
-                )
-            else:
-                request.setHeader(
-                    b"Content-Disposition",
-                    b"inline; filename*=utf-8''%s" % (
-                        urllib.quote(upload_name.encode("utf-8")),
-                    ),
-                )
-
-        # cache for at least a day.
-        # XXX: we might want to turn this off for data we don't want to
-        # recommend caching as it's sensitive or private - or at least
-        # select private. don't bother setting Expires as all our
-        # clients are smart enough to be happy with Cache-Control
-        request.setHeader(
-            b"Cache-Control", b"public,max-age=86400,s-maxage=86400"
-        )
         if file_size is None:
             stat = os.stat(file_path)
             file_size = stat.st_size
 
-        request.setHeader(
-            b"Content-Length", b"%d" % (file_size,)
-        )
+        add_file_headers(request, media_type, file_size, upload_name)
 
         with open(file_path, "rb") as f:
             yield logcontext.make_deferred_yieldable(
@@ -111,3 +84,118 @@ def respond_with_file(request, media_type, file_path,
         finish_request(request)
     else:
         respond_404(request)
+
+
+def add_file_headers(request, media_type, file_size, upload_name):
+    """Adds the correct response headers in preparation for responding with the
+    media.
+
+    Args:
+        request (twisted.web.http.Request)
+        media_type (str): The media/content type.
+        file_size (int): Size in bytes of the media, if known.
+        upload_name (str): The name of the requested file, if any.
+    """
+    request.setHeader(b"Content-Type", media_type.encode("UTF-8"))
+    if upload_name:
+        if is_ascii(upload_name):
+            request.setHeader(
+                b"Content-Disposition",
+                b"inline; filename=%s" % (
+                    urllib.quote(upload_name.encode("utf-8")),
+                ),
+            )
+        else:
+            request.setHeader(
+                b"Content-Disposition",
+                b"inline; filename*=utf-8''%s" % (
+                    urllib.quote(upload_name.encode("utf-8")),
+                ),
+            )
+
+    # cache for at least a day.
+    # XXX: we might want to turn this off for data we don't want to
+    # recommend caching as it's sensitive or private - or at least
+    # select private. don't bother setting Expires as all our
+    # clients are smart enough to be happy with Cache-Control
+    request.setHeader(
+        b"Cache-Control", b"public,max-age=86400,s-maxage=86400"
+    )
+
+    request.setHeader(
+        b"Content-Length", b"%d" % (file_size,)
+    )
+
+
+@defer.inlineCallbacks
+def respond_with_responder(request, responder, media_type, file_size, upload_name=None):
+    """Responds to the request with given responder. If responder is None then
+    returns 404.
+
+    Args:
+        request (twisted.web.http.Request)
+        responder (Responder|None)
+        media_type (str): The media/content type.
+        file_size (int|None): Size in bytes of the media. If not known it should be None
+        upload_name (str|None): The name of the requested file, if any.
+    """
+    if not responder:
+        respond_404(request)
+        return
+
+    add_file_headers(request, media_type, file_size, upload_name)
+    with responder:
+        yield responder.write_to_consumer(request)
+    finish_request(request)
+
+
+class Responder(object):
+    """Represents a response that can be streamed to the requester.
+
+    Responder is a context manager which *must* be used, so that any resources
+    held can be cleaned up.
+    """
+    def write_to_consumer(self, consumer):
+        """Stream response into consumer
+
+        Args:
+            consumer (IConsumer)
+
+        Returns:
+            Deferred: Resolves once the response has finished being written
+        """
+        pass
+
+    def __enter__(self):
+        pass
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        pass
+
+
+class FileInfo(object):
+    """Details about a requested/uploaded file.
+
+    Attributes:
+        server_name (str): The server name where the media originated from,
+            or None if local.
+        file_id (str): The local ID of the file. For local files this is the
+            same as the media_id
+        url_cache (bool): If the file is for the url preview cache
+        thumbnail (bool): Whether the file is a thumbnail or not.
+        thumbnail_width (int)
+        thumbnail_height (int)
+        thumbnail_method (str)
+        thumbnail_type (str): Content type of thumbnail, e.g. image/png
+    """
+    def __init__(self, server_name, file_id, url_cache=False,
+                 thumbnail=False, thumbnail_width=None, thumbnail_height=None,
+                 thumbnail_method=None, thumbnail_type=None):
+        self.server_name = server_name
+        self.file_id = file_id
+        self.url_cache = url_cache
+        self.thumbnail = thumbnail
+        self.thumbnail_width = thumbnail_width
+        self.thumbnail_height = thumbnail_height
+        self.thumbnail_method = thumbnail_method
+        self.thumbnail_type = thumbnail_type

synapse/rest/media/v1/download_resource.py

@@ -14,7 +14,7 @@
 # limitations under the License.
 import synapse.http.servlet
 
-from ._base import parse_media_id, respond_with_file, respond_404
+from ._base import parse_media_id, respond_404
 from twisted.web.resource import Resource
 from synapse.http.server import request_handler, set_cors_headers
 
@@ -32,12 +32,12 @@ class DownloadResource(Resource):
     def __init__(self, hs, media_repo):
         Resource.__init__(self)
 
-        self.filepaths = media_repo.filepaths
         self.media_repo = media_repo
         self.server_name = hs.hostname
-        self.store = hs.get_datastore()
-        self.version_string = hs.version_string
+
+        # Both of these are expected by @request_handler()
         self.clock = hs.get_clock()
+        self.version_string = hs.version_string
 
     def render_GET(self, request):
         self._async_render_GET(request)
@@ -57,59 +57,16 @@ def _async_render_GET(self, request):
         )
         server_name, media_id, name = parse_media_id(request)
         if server_name == self.server_name:
-            yield self._respond_local_file(request, media_id, name)
+            yield self.media_repo.get_local_media(request, media_id, name)
         else:
-            yield self._respond_remote_file(
-                request, server_name, media_id, name
-            )
-
-    @defer.inlineCallbacks
-    def _respond_local_file(self, request, media_id, name):
-        media_info = yield self.store.get_local_media(media_id)
-        if not media_info or media_info["quarantined_by"]:
-            respond_404(request)
-            return
-
-        media_type = media_info["media_type"]
-        media_length = media_info["media_length"]
-        upload_name = name if name else media_info["upload_name"]
-        if media_info["url_cache"]:
-            # TODO: Check the file still exists, if it doesn't we can redownload
-            # it from the url `media_info["url_cache"]`
-            file_path = self.filepaths.url_cache_filepath(media_id)
-        else:
-            file_path = self.filepaths.local_media_filepath(media_id)
-
-        yield respond_with_file(
-            request, media_type, file_path, media_length,
-            upload_name=upload_name,
-        )
-
-    @defer.inlineCallbacks
-    def _respond_remote_file(self, request, server_name, media_id, name):
-        # don't forward requests for remote media if allow_remote is false
-        allow_remote = synapse.http.servlet.parse_boolean(
-            request, "allow_remote", default=True)
-        if not allow_remote:
-            logger.info(
-                "Rejecting request for remote media %s/%s due to allow_remote",
-                server_name, media_id,
-            )
-            respond_404(request)
-            return
-
-        media_info = yield self.media_repo.get_remote_media(server_name, media_id)
-
-        media_type = media_info["media_type"]
-        media_length = media_info["media_length"]
-        filesystem_id = media_info["filesystem_id"]
-        upload_name = name if name else media_info["upload_name"]
-
-        file_path = self.filepaths.remote_media_filepath(
-            server_name, filesystem_id
-        )
-
-        yield respond_with_file(
-            request, media_type, file_path, media_length,
-            upload_name=upload_name,
-        )
+            allow_remote = synapse.http.servlet.parse_boolean(
+                request, "allow_remote", default=True)
+            if not allow_remote:
+                logger.info(
+                    "Rejecting request for remote media %s/%s due to allow_remote",
+                    server_name, media_id,
+                )
+                respond_404(request)
+                return
+
+            yield self.media_repo.get_remote_media(request, server_name, media_id, name)