Fix "endpoint seems conditional" determination in workers-doc-to-yaml.awk"

This prevented us from keeping our workers reverse-proxying definitions
updated since Synapse v1.54.0.

The last `workers.md` file we could parse is at commit
02632b3504ad4512c5f5a4f859b3fe326b19c788.
Parsing regressed at commit c56bfb08bc071368db23f3b1c593724eb4f205f0,
because the introduction message for `synapse.app.generic_worker` said
"If":

> If a worker is set up to handle a..

.. which made the AWK script think that definitions below were
conditional (which they're not in this case).

This patch fixes up the regex for determining if a line is conditional
or not, so that it doesn't trip up. Hopefully, it doesn't miss something
important.

roles/matrix-synapse/files/workers-doc-to-yaml.awk

@@ -120,7 +120,7 @@ enable_parsing {
                 worker_stanza_append("  # " line linefeed)
 
                 # and take note of words hinting at additional conditions to be met
-                if (line ~ /(^| )[Ii]f |(^| )[Ff]or /) {
+                if (line ~ /(^[Ii]f|care must be taken|can be handled for)/) {
                     endpoints_seem_conditional = 1
                 }
             }

roles/matrix-synapse/vars/workers.yml

@@ -1,12 +1,15 @@
 ---
 
 matrix_synapse_workers_generic_worker_endpoints:
-  # This worker can handle API requests matching the following regular
+  # This worker can handle API requests matching the following regular expressions.
-  # expressions:
+  # These endpoints can be routed to any worker. If a worker is set up to handle a
+  # stream then, for maximum efficiency, additional endpoints should be routed to that
+  # worker: refer to the [stream writers](#stream-writers) section below for further
+  # information.
 
   # Sync requests
-  - ^/_matrix/client/(v2_alpha|r0|v3)/sync$
+  - ^/_matrix/client/(r0|v3)/sync$
-  - ^/_matrix/client/(api/v1|v2_alpha|r0|v3)/events$
+  - ^/_matrix/client/(api/v1|r0|v3)/events$
   - ^/_matrix/client/(api/v1|r0|v3)/initialSync$
   - ^/_matrix/client/(api/v1|r0|v3)/rooms/[^/]+/initialSync$
 
@@ -20,19 +23,14 @@ matrix_synapse_workers_generic_worker_endpoints:
   - ^/_matrix/federation/v1/query/
   - ^/_matrix/federation/v1/make_join/
   - ^/_matrix/federation/v1/make_leave/
-  - ^/_matrix/federation/v1/send_join/
+  - ^/_matrix/federation/(v1|v2)/send_join/
-  - ^/_matrix/federation/v2/send_join/
+  - ^/_matrix/federation/(v1|v2)/send_leave/
-  - ^/_matrix/federation/v1/send_leave/
+  - ^/_matrix/federation/(v1|v2)/invite/
-  - ^/_matrix/federation/v2/send_leave/
-  - ^/_matrix/federation/v1/invite/
-  - ^/_matrix/federation/v2/invite/
-  - ^/_matrix/federation/v1/query_auth/
   - ^/_matrix/federation/v1/event_auth/
   - ^/_matrix/federation/v1/exchange_third_party_invite/
   - ^/_matrix/federation/v1/user/devices/
   - ^/_matrix/federation/v1/get_groups_publicised$
   - ^/_matrix/key/v2/query
-  - ^/_matrix/federation/unstable/org.matrix.msc2946/spaces/
   - ^/_matrix/federation/(v1|unstable/org.matrix.msc2946)/hierarchy/
 
   # Inbound federation transaction request
@@ -45,22 +43,25 @@ matrix_synapse_workers_generic_worker_endpoints:
   - ^/_matrix/client/(api/v1|r0|v3|unstable)/rooms/.*/context/.*$
   - ^/_matrix/client/(api/v1|r0|v3|unstable)/rooms/.*/members$
   - ^/_matrix/client/(api/v1|r0|v3|unstable)/rooms/.*/state$
-  - ^/_matrix/client/unstable/org.matrix.msc2946/rooms/.*/spaces$
   - ^/_matrix/client/(v1|unstable/org.matrix.msc2946)/rooms/.*/hierarchy$
   - ^/_matrix/client/unstable/im.nheko.summary/rooms/.*/summary$
-  - ^/_matrix/client/(api/v1|r0|v3|unstable)/account/3pid$
+  - ^/_matrix/client/(r0|v3|unstable)/account/3pid$
-  - ^/_matrix/client/(api/v1|r0|v3|unstable)/devices$
+  - ^/_matrix/client/(r0|v3|unstable)/devices$
-  - ^/_matrix/client/(api/v1|r0|v3|unstable)/keys/query$
-  - ^/_matrix/client/(api/v1|r0|v3|unstable)/keys/changes$
   - ^/_matrix/client/versions$
   - ^/_matrix/client/(api/v1|r0|v3|unstable)/voip/turnServer$
-  - ^/_matrix/client/(api/v1|r0|v3|unstable)/joined_groups$
+  - ^/_matrix/client/(r0|v3|unstable)/joined_groups$
-  - ^/_matrix/client/(api/v1|r0|v3|unstable)/publicised_groups$
+  - ^/_matrix/client/(r0|v3|unstable)/publicised_groups$
-  - ^/_matrix/client/(api/v1|r0|v3|unstable)/publicised_groups/
+  - ^/_matrix/client/(r0|v3|unstable)/publicised_groups/
   - ^/_matrix/client/(api/v1|r0|v3|unstable)/rooms/.*/event/
   - ^/_matrix/client/(api/v1|r0|v3|unstable)/joined_rooms$
   - ^/_matrix/client/(api/v1|r0|v3|unstable)/search$
 
+  # Encryption requests
+  - ^/_matrix/client/(r0|v3|unstable)/keys/query$
+  - ^/_matrix/client/(r0|v3|unstable)/keys/changes$
+  - ^/_matrix/client/(r0|v3|unstable)/keys/claim$
+  - ^/_matrix/client/(r0|v3|unstable)/room_keys/
+
   # Registration/login requests
   - ^/_matrix/client/(api/v1|r0|v3|unstable)/login$
   - ^/_matrix/client/(r0|v3|unstable)/register$
@@ -74,11 +75,27 @@ matrix_synapse_workers_generic_worker_endpoints:
   - ^/_matrix/client/(api/v1|r0|v3|unstable)/join/
   - ^/_matrix/client/(api/v1|r0|v3|unstable)/profile/
 
+  # Device requests
+  - ^/_matrix/client/(r0|v3|unstable)/sendToDevice/
+
+  # Account data requests
+  - ^/_matrix/client/(r0|v3|unstable)/.*/tags
+  - ^/_matrix/client/(r0|v3|unstable)/.*/account_data
+
+  # Receipts requests
+  - ^/_matrix/client/(r0|v3|unstable)/rooms/.*/receipt
+  - ^/_matrix/client/(r0|v3|unstable)/rooms/.*/read_markers
+
+  # Presence requests
+  - ^/_matrix/client/(api/v1|r0|v3|unstable)/presence/
+
 
   # Additionally, the following REST endpoints can be handled for GET requests:
 
   # FIXME: ADDITIONAL CONDITIONS REQUIRED: to be enabled manually
   # ^/_matrix/federation/v1/groups/
+  # ^/_matrix/client/(api/v1|r0|v3|unstable)/pushrules/
+  # ^/_matrix/client/(r0|v3|unstable)/groups/
 
   # Pagination requests can also be handled, but all requests for a given
   # room must be routed to the same instance. Additionally, care must be taken to
@@ -155,16 +172,17 @@ matrix_synapse_workers_generic_worker_endpoints:
 
   # #### Stream writers
 
-  # Additionally, there is *experimental* support for moving writing of specific
+  # Additionally, the writing of specific streams (such as events) can be moved off
-  # streams (such as events) off of the main process to a particular worker. (This
+  # of the main process to a particular worker.
-  # is only supported with Redis-based replication.)
+  # (This is only supported with Redis-based replication.)
-
-  # Currently supported streams are `events` and `typing`.
 
   # To enable this, the worker must have a HTTP replication listener configured,
-  # have a `worker_name` and be listed in the `instance_map` config. For example to
+  # have a `worker_name` and be listed in the `instance_map` config. The same worker
-  # move event persistence off to a dedicated worker, the shared configuration would
+  # can handle multiple streams, but unless otherwise documented, each stream can only
-  # include:
+  # have a single writer.
+
+  # For example, to move event persistence off to a dedicated worker, the shared
+  # configuration would include:
 
   # ```yaml
   # instance_map:
@@ -176,8 +194,20 @@ matrix_synapse_workers_generic_worker_endpoints:
   #     events: event_persister1
   # ```
 
-  # The `events` stream also experimentally supports having multiple writers, where
+  # An example for a stream writer instance:
-  # work is sharded between them by room ID. Note that you *must* restart all worker
+
+  # ```yaml
+  # {{#include systemd-with-workers/workers/event_persister.yaml}}
+  # ```
+
+  # Some of the streams have associated endpoints which, for maximum efficiency, should
+  # be routed to the workers handling that stream. See below for the currently supported
+  # streams and the endpoints associated with them:
+
+  # ##### The `events` stream
+
+  # The `events` stream experimentally supports having multiple writers, where work
+  # is sharded between them by room ID. Note that you *must* restart all worker
   # instances when adding or removing event persisters. An example `stream_writers`
   # configuration with multiple writers:
 
@@ -188,9 +218,51 @@ matrix_synapse_workers_generic_worker_endpoints:
   #         - event_persister2
   # ```
 
+  # ##### The `typing` stream
+
+  # The following endpoints should be routed directly to the worker configured as
+  # the stream writer for the `typing` stream:
+
+  # FIXME: ADDITIONAL CONDITIONS REQUIRED: to be enabled manually
+  # ^/_matrix/client/(api/v1|r0|v3|unstable)/rooms/.*/typing
+
+  # ##### The `to_device` stream
+
+  # The following endpoints should be routed directly to the worker configured as
+  # the stream writer for the `to_device` stream:
+
+  # FIXME: ADDITIONAL CONDITIONS REQUIRED: to be enabled manually
+  # ^/_matrix/client/(r0|v3|unstable)/sendToDevice/
+
+  # ##### The `account_data` stream
+
+  # The following endpoints should be routed directly to the worker configured as
+  # the stream writer for the `account_data` stream:
+
+  # FIXME: ADDITIONAL CONDITIONS REQUIRED: to be enabled manually
+  # ^/_matrix/client/(r0|v3|unstable)/.*/tags
+  # ^/_matrix/client/(r0|v3|unstable)/.*/account_data
+
+  # ##### The `receipts` stream
+
+  # The following endpoints should be routed directly to the worker configured as
+  # the stream writer for the `receipts` stream:
+
+  # FIXME: ADDITIONAL CONDITIONS REQUIRED: to be enabled manually
+  # ^/_matrix/client/(r0|v3|unstable)/rooms/.*/receipt
+  # ^/_matrix/client/(r0|v3|unstable)/rooms/.*/read_markers
+
+  # ##### The `presence` stream
+
+  # The following endpoints should be routed directly to the worker configured as
+  # the stream writer for the `presence` stream:
+
+  # FIXME: ADDITIONAL CONDITIONS REQUIRED: to be enabled manually
+  # ^/_matrix/client/(api/v1|r0|v3|unstable)/presence/
+
   # #### Background tasks
 
-  # There is also *experimental* support for moving background tasks to a separate
+  # There is also support for moving background tasks to a separate
   # worker. Background tasks are run periodically or started via replication. Exactly
   # which tasks are configured to run depends on your Synapse configuration (e.g. if
   # stats is enabled).
@@ -206,6 +278,12 @@ matrix_synapse_workers_generic_worker_endpoints:
   # You might also wish to investigate the `update_user_directory` and
   # `media_instance_running_background_jobs` settings.
 
+  # An example for a dedicated background worker instance:
+
+  # ```yaml
+  # {{#include systemd-with-workers/workers/background_worker.yaml}}
+  # ```
+
 # pusher worker (no API endpoints) [
   # Handles sending push notifications to sygnal and email. Doesn't handle any
   # REST endpoints itself, but you should set `start_pushers: False` in the
@@ -292,18 +370,27 @@ matrix_synapse_workers_user_dir_endpoints:
   # Handles searches in the user directory. It can handle REST endpoints matching
   # the following regular expressions:
 
-  - ^/_matrix/client/(api/v1|r0|v3|unstable)/user_directory/search$
+  - ^/_matrix/client/(r0|v3|unstable)/user_directory/search$
 
-  # When using this worker you must also set `update_user_directory: False` in the
+  # When using this worker you must also set `update_user_directory: false` in the
   # shared configuration file to stop the main synapse running background
   # jobs related to updating the user directory.
 
+  # Above endpoint is not *required* to be routed to this worker. By default,
+  # `update_user_directory` is set to `true`, which means the main process
+  # will handle updates. All workers configured with `client` can handle the above
+  # endpoint as long as either this worker or the main process are configured to
+  # handle it, and are online.
+
+  # If `update_user_directory` is set to `false`, and this worker is not running,
+  # the above endpoint may give outdated results.
+
 matrix_synapse_workers_frontend_proxy_endpoints:
   # Proxies some frequently-requested client endpoints to add caching and remove
   # load from the main synapse. It can handle REST endpoints matching the following
   # regular expressions:
 
-  - ^/_matrix/client/(api/v1|r0|v3|unstable)/keys/upload
+  - ^/_matrix/client/(r0|v3|unstable)/keys/upload
 
   # If `use_presence` is False in the homeserver config, it can also handle REST
   # endpoints matching the following regular expressions: