Refactor documentation for content/media repository

Fixes https://github.com/matrix-org/matrix-doc/issues/2060
Fixes https://github.com/matrix-org/matrix-doc/issues/772
Fixes https://github.com/matrix-org/matrix-doc/issues/888

api/client-server/content-repo.yaml

@@ -1,4 +1,5 @@
 # Copyright 2016 OpenMarket Ltd
+# Copyright 2019 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.
@@ -58,66 +59,41 @@ paths:
             format: byte
       responses:
         200:
-          description: The MXC URI for the uploaded content.
+          description: The `MXC URI`_ for the uploaded content.
           schema:
             type: object
             required: ["content_uri"]
             properties:
               content_uri:
                 type: string
-                description: "The MXC URI to the uploaded content."
+                description: "The `MXC URI`_ to the uploaded content."
           examples:
             application/json: {
-                "content_uri": "mxc://example.com/AQwafuaFswefuhsfAFAgsw"
+              "content_uri": "mxc://example.com/AQwafuaFswefuhsfAFAgsw"
-              }
+            }
-        429:
+        403:
-          description: This request was rate-limited.
+          description: |-
+            The user does not have permission to upload the content. Some reasons for this error include:
+
+            - The server does not permit the file type.
+            - The user has reached a quota for uploaded content.
+          examples:
+            application/json: {
+              "errcode": "M_FORBIDDEN",
+              "error": "Cannot upload this content"
+            }
           schema:
-            "$ref": "definitions/errors/rate_limited.yaml"
+            "$ref": "definitions/errors/error.yaml"
-      tags:
+        413:
-        - Media
+          description: |-
-  "/download/{serverName}/{mediaId}":
+            The uploaded content is too large for the server.
-    get:
+          examples:
-      summary: "Download content from the content repository."
+            application/json: {
-      operationId: getContent
+              "errcode": "M_TOO_LARGE",
-      produces: ["*/*"]
+              "error": "Cannot upload files larger than 100mb"
-      parameters:
+            }
-        - in: path
-          type: string
-          name: serverName
-          x-example: matrix.org
-          required: true
-          description: |
-            The server name from the ``mxc://`` URI (the authoritory component)
-        - in: path
-          type: string
-          name: mediaId
-          x-example: ascERGshawAWawugaAcauga
-          required: true
-          description: |
-            The media ID from the ``mxc://`` URI (the path component)
-        - in: query
-          type: boolean
-          name: allow_remote
-          x-example: false
-          required: false
-          default: true
-          description: |
-            Indicates to the server that it should not attempt to fetch the media if it is deemed
-            remote. This is to prevent routing loops where the server contacts itself. Defaults to
-            true if not provided.
-      responses:
-        200:
-          description: "The content that was previously uploaded."
-          headers:
-            Content-Type:
-              description: "The content type of the file that was previously uploaded."
-              type: "string"
-            Content-Disposition:
-              description: "The name of the file that was previously uploaded, if set."
-              type: "string"
           schema:
-            type: file
+            "$ref": "definitions/errors/error.yaml"
         429:
           description: This request was rate-limited.
           schema:
@@ -126,8 +102,8 @@ paths:
         - Media
   "/download/{serverName}/{mediaId}/{fileName}":
     get:
-      summary: "Download content from the content repository as a given filename."
+      summary: "Download content from the content repository."
-      operationId: getContentOverrideName
+      operationId: getContent
       produces: ["*/*"]
       parameters:
         - in: path
@@ -148,9 +124,7 @@ paths:
           type: string
           name: fileName
           x-example: filename.jpg
-          required: true
+          description: An optional filename to give in the ``Content-Disposition`` header.
-          description: |
-            The filename to give in the Content-Disposition
         - in: query
           type: boolean
           name: allow_remote
@@ -169,10 +143,24 @@ paths:
               description: "The content type of the file that was previously uploaded."
               type: "string"
             Content-Disposition:
-              description: "The name of file given in the request"
+              description: |-
+                The ``fileName`` requested or the name of the file that was previously
+                uploaded, if set.
               type: "string"
           schema:
             type: file
+            # This is a workaround for us not being able to say the response is required.
+            description: "**Required.** The bytes for the uploaded file."
+        502:
+          description: |-
+            The content is too large for the server to serve.
+          examples:
+            application/json: {
+              "errcode": "M_TOO_LARGE",
+              "error": "Content is too large to serve"
+            }
+          schema:
+            "$ref": "definitions/errors/error.yaml"
         429:
           description: This request was rate-limited.
           schema:
@@ -181,7 +169,9 @@ paths:
         - Media
   "/thumbnail/{serverName}/{mediaId}":
     get:
-      summary: "Download a thumbnail of the content from the content repository."
+      summary: |-
+        Download a thumbnail of content from the content repository. See the `thumbnailing <#thumbnails>`_
+        section for more information.
       operationId: getContentThumbnail
       produces: ["image/jpeg", "image/png"]
       parameters:
@@ -189,7 +179,7 @@ paths:
           type: string
           name: serverName
           required: true
-          x-example: matrix.org
+          x-example: example.org
           description: |
             The server name from the ``mxc://`` URI (the authoritory component)
         - in: path
@@ -205,22 +195,24 @@ paths:
           name: width
           required: true
           description: |-
-            The *desired* width of the thumbnail. The actual thumbnail may not
+            The *desired* width of the thumbnail. The actual thumbnail may be
-            match the size specified.
+            larger than the size specified.
         - in: query
           type: integer
           x-example: 64
           name: height
           required: true
           description: |-
-            The *desired* height of the thumbnail. The actual thumbnail may not
+            The *desired* height of the thumbnail. The actual thumbnail may be
-            match the size specified.
+            larger than the size specified.
         - in: query
           type: string
           enum: ["crop", "scale"]
           name: method
           x-example: "scale"
-          description: The desired resizing method.
+          description: |-
+            The desired resizing method. See the `thumbnailing <#thumbnails>`_
+            section for more information.
         - in: query
           type: boolean
           name: allow_remote
@@ -241,6 +233,40 @@ paths:
               enum: ["image/jpeg", "image/png"]
           schema:
             type: file
+            # This is a workaround for us not being able to say the response is required.
+            description: "**Required.** The bytes for the thumbnail."
+        400:
+          description: |-
+            The request does not make sense to the server, or the server cannot thumbnail
+            the content. For example, the client requested non-integer dimensions or asked
+            for negatively-sized images.
+          examples:
+            application/json: {
+              "errcode": "M_UNKNOWN",
+              "error": "Cannot generate thumbnails for the requested content"
+            }
+          schema:
+            "$ref": "definitions/errors/error.yaml"
+        413:
+          description: |-
+            The local content is too large for the server to thumbnail.
+          examples:
+            application/json: {
+              "errcode": "M_TOO_LARGE",
+              "error": "Content is too large to thumbnail"
+            }
+          schema:
+            "$ref": "definitions/errors/error.yaml"
+        502:
+          description: |-
+            The remote content is too large for the server to thumbnail.
+          examples:
+            application/json: {
+              "errcode": "M_TOO_LARGE",
+              "error": "Content is too large to thumbnail"
+            }
+          schema:
+            "$ref": "definitions/errors/error.yaml"
         429:
           description: This request was rate-limited.
           schema:
@@ -259,7 +285,7 @@ paths:
           type: string
           x-example: "https://matrix.org"
           name: url
-          description: "The URL to get a preview of"
+          description: "The URL to get a preview of."
           required: true
         - in: query
           type: integer
@@ -287,7 +313,7 @@ paths:
               "og:image":
                 type: string
                 description: |-
-                  An MXC URI to the image. Omitted if there is no image.
+                  An `MXC URI`_ to the image. Omitted if there is no image.
           examples:
             application/json: {
                 "og:title": "Matrix Blog Post",

api/client-server/room_state.yaml

@@ -70,7 +70,7 @@ paths:
             type: object
             example: {
                 "membership": "join",
-                "avatar_url": "mxc://localhost/SEsfnsuifSDFSSEF#auto",
+                "avatar_url": "mxc://localhost/SEsfnsuifSDFSSEF",
                 "displayname": "Alice Margatroid"
               }
       responses:

changelogs/client_server/newsfragments/2068.clarification

@@ -0,0 +1 @@
+Clarify how the content repository works, and what it is used for.

event-schemas/examples/m.room.member

@@ -4,7 +4,7 @@
   "type": "m.room.member",
   "content": {
     "membership": "join",
-    "avatar_url": "mxc://example.org/SEsfnsuifSDFSSEF#auto",
+    "avatar_url": "mxc://example.org/SEsfnsuifSDFSSEF",
     "displayname": "Alice Margatroid"
   }
 }

event-schemas/examples/m.room.member$invite_room_state

@@ -2,7 +2,7 @@
   "$ref": "m.room.member",
   "content": {
     "membership": "invite",
-    "avatar_url": "mxc://example.org/SEsfnsuifSDFSSEF#auto",
+    "avatar_url": "mxc://example.org/SEsfnsuifSDFSSEF",
     "displayname": "Alice Margatroid"
   },
   "unsigned": {

event-schemas/examples/m.room.member$third_party_invite

@@ -2,7 +2,7 @@
   "$ref": "m.room.member",
   "content": {
     "membership": "invite",
-    "avatar_url": "mxc://example.org/SEsfnsuifSDFSSEF#auto",
+    "avatar_url": "mxc://example.org/SEsfnsuifSDFSSEF",
     "displayname": "Alice Margatroid",
     "third_party_invite": {
       "display_name": "alice",

event-schemas/schema/core-event-schema/msgtype_infos/image_info.yaml

@@ -19,7 +19,7 @@ properties:
     type: integer
   thumbnail_url:
     description: |-
-      The URL to a thumbnail of the image. Only present if the
+      The `MXC URI`_ to a thumbnail of the image. Only present if the
       thumbnail is unencrypted.
     type: string
   thumbnail_file:

event-schemas/schema/m.room.message$m.audio

@@ -27,7 +27,7 @@ properties:
           - m.audio
         type: string
       url:
-        description: Required if the file is not encrypted. The URL to the audio clip.
+        description: Required if the file is not encrypted. The `MXC URI`_ to the audio clip.
         type: string
       file:
         description: |-

event-schemas/schema/m.room.message$m.file

@@ -42,7 +42,7 @@ properties:
           - m.file
         type: string
       url:
-        description: Required if the file is unencrypted. The URL to the file.
+        description: Required if the file is unencrypted. The `MXC URI`_ to the file.
         type: string
       file:
         description: |-

event-schemas/schema/m.room.message$m.image

@@ -17,7 +17,7 @@ properties:
           - m.image
         type: string
       url:
-        description: Required if the file is unencrypted. The URL to the image.
+        description: Required if the file is unencrypted. The `MXC URI`_ to the image.
         type: string
       file:
         description: |-

event-schemas/schema/m.room.message$m.video

@@ -28,7 +28,7 @@ properties:
             type: integer
           thumbnail_url:
             description: |-
-              The URL to an image thumbnail of the video clip. Only present if the
+              The `MXC URI`_ to an image thumbnail of the video clip. Only present if the
               thumbnail is unencrypted.
             type: string
           thumbnail_file:
@@ -48,7 +48,7 @@ properties:
           - m.video
         type: string
       url:
-        description: Required if the file is unencrypted. The URL to the video clip.
+        description: Required if the file is unencrypted. The `MXC URI`_ to the video clip.
         type: string
       file:
         description: |-

specification/modules/content_repo.rst

@@ -1,4 +1,5 @@
 .. Copyright 2016 OpenMarket Ltd
+.. Copyright 2019 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.
@@ -17,27 +18,38 @@ Content repository
 
 .. _module:content:
 
-This module allows users to upload content to their homeserver which is
+The content repository (or "media repository") allows users to upload
-retrievable from other homeservers. Its' purpose is to allow users to share
+files to their homeserver for later user. For example, files which the
-attachments in a room. Content locations are represented as Matrix Content (MXC)
+user wants to send to a room would be uploaded here, as would an avatar
-URIs. They look like::
+the user wants to use.
 
-  mxc://<server-name>/<media-id>
+Uploads are POSTed to a resource on the user's local homeserver which
-
+returns a MXC URI which can later be used to GET the download. Content
-  <server-name> : The name of the homeserver where this content originated, e.g. matrix.org
+is downloaded from the recipient's local homeserver, which must first
-  <media-id> : An opaque ID which identifies the content.
+transfer the content from the origin homeserver using the same API
-
+(unless the origin and destination homeservers are the same).
-Uploads are POSTed to a resource on the user's local homeserver which returns a
-token which is used to GET the download. Content is downloaded from the
-recipient's local homeserver, which must first transfer the content from the
-origin homeserver using the same API (unless the origin and destination
-homeservers are the same).
 
 When serving content, the server SHOULD provide a ``Content-Security-Policy``
 header. The recommended policy is ``sandbox; default-src 'none'; script-src
 'none'; plugin-types application/pdf; style-src 'unsafe-inline'; object-src
 'self';``.
 
+Content in the repository should be treated as bytes as it may be encrypted.
+
+Matrix Content (MXC) URIs
+-------------------------
+
+.. _`MXC URI`:
+
+Content locations are represented as Matrix Content (MXC) URIs. They look
+like::
+
+  mxc://<server-name>/<media-id>
+
+  <server-name> : The name of the homeserver where this content originated, e.g. matrix.org
+  <media-id> : An opaque ID which identifies the content.
+
+
 Client behaviour
 ----------------
 
@@ -47,6 +59,11 @@ Clients can upload and download content using the following HTTP APIs.
 
 Thumbnails
 ~~~~~~~~~~
+The homeserver SHOULD be able to supply thumbnails for uploaded images and
+videos. The exact file types which can be thumbnailed are not currently
+specified - see `Issue #1938 <https://github.com/matrix-org/matrix-doc/issues/1938>`_
+for more information.
+
 The thumbnail methods are "crop" and "scale". "scale" tries to return an
 image where either the width or the height is smaller than the requested
 size. The client should then scale and letterbox the image if it needs to
@@ -55,18 +72,32 @@ width and height are close to the requested size and the aspect matches
 the requested size. The client should scale the image if it needs to fit
 within a given rectangle.
 
+The dimensions given to the thumbnail API are the minimum size the client
+would prefer. Servers must never return thumbnails smaller than the client's
+requested dimensions, unless the content being thumbnailed is smaller than
+the dimensions. When the content is smaller than the requested dimensions,
+servers should return the original content rather than thumbnail it.
+
+Servers SHOULD pre-calculate or have a list of set dimensions for which they
+will thumbnail content at. For example, the server may choose that it will
+only create thumbnails sized 96x96 or 512x512. When the client requests a
+thumbnail, the server will pick the size which is larger than the requested
+dimensions. Servers SHOULD pre-calculate the following thumbnails for uploaded
+content, and limit thumbnails to the same sizes:
+
+* 32x32, crop
+* 96x96, crop
+* 320x240, scale
+* 640x480, scale
+* 800x600, scale
+
 In summary:
  * "scale" maintains the original aspect ratio of the image
  * "crop" provides an image in the aspect ratio of the sizes given in the request
+ * The server will return an image larger than or equal to the dimensions requested
+   where possible.
 
-Server behaviour
+Servers MUST NOT upscale thumbnails under any circumstance.
-----------------
-
-Homeservers may generate thumbnails for content uploaded to remote
-homeservers themselves or may rely on the remote homeserver to thumbnail
-the content. Homeservers may return thumbnails of a different size to that
-requested. However homeservers should provide exact matches where reasonable.
-Homeservers must never upscale images.
 
 Security considerations
 -----------------------
@@ -88,16 +119,20 @@ UTF-8 encoded traversals, etc).
 Homeservers have additional content-specific concerns:
 
 - Clients may try to upload very large files. Homeservers should not store files
-  that are too large and should not serve them to clients.
+  that are too large and should not serve them to clients, returning a HTTP 413
+  error with the ``M_TOO_LARGE`` code.
 
 - Clients may try to upload very large images. Homeservers should not attempt to
-  generate thumbnails for images that are too large.
+  generate thumbnails for images that are too large, returning a HTTP 413 error
+  with the ``M_TOO_LARGE`` code.
 
 - Remote homeservers may host very large files or images. Homeservers should not
-  proxy or thumbnail large files or images from remote homeservers.
+  proxy or thumbnail large files or images from remote homeservers, returning a
+  HTTP 502 error with the ``M_TOO_LARGE`` code.
 
 - Clients may try to upload a large number of files. Homeservers should limit the
-  number and total size of media that can be uploaded by clients.
+  number and total size of media that can be uploaded by clients, returning a
+  HTTP 403 error with the ``M_FORBIDDEN`` code.
 
 - Clients may try to access a large number of remote files through a homeserver.
   Homeservers should restrict the number and size of remote files that it caches.