Fix broken export-data admin command and add a test for it to CI

.ci/scripts/test_export_data_command.sh

@@ -0,0 +1,49 @@
+#!/usr/bin/env bash
+
+# Test for the export-data admin command
+
+set -xe
+cd `dirname $0`/../..
+
+echo "--- Install dependencies"
+
+# Install dependencies for this test.
+pip install psycopg2 coverage coverage-enable-subprocess
+
+# Install Synapse itself. This won't update any libraries.
+pip install -e .
+
+echo "--- Generate the signing key"
+
+# Generate the server's signing key.
+python -m synapse.app.homeserver --generate-keys -c .ci/sqlite-config.yaml
+
+echo "--- Prepare test database"
+
+# Make sure the SQLite3 database is using the latest schema and has no pending background update.
+scripts-dev/update_database --database-config .ci/sqlite-config.yaml
+
+# Create the PostgreSQL database.
+.ci/scripts/postgres_exec.py "CREATE DATABASE synapse"
+
+# Port the SQLite databse to postgres so we can check command works against both
+echo "+++ Port SQLite3 databse to postgres"
+scripts/synapse_port_db --sqlite-database .ci/test_db.db --postgres-config .ci/postgres-config.yaml
+
+# Run the export-data command on the sqlite test database
+python -m synapse.app.admin_cmd -c .ci/sqlite-config.yaml  export-data @anon-20191002_181700-832:localhost:8800 \
+--output-directory /tmp/export_data
+
+# Run the export-data command on postgres database
+python -m synapse.app.admin_cmd -c .ci/postgres-config.yaml  export-data @anon-20191002_181700-832:localhost:8800 \
+--output-directory /tmp/export_data2
+
+# Test that the output directories exist and contain the rooms directory
+dir="/tmp/export_data/rooms"
+dir2="/tmp/export_data2/rooms"
+if [ -d "$dir" ] && [ -d "$dir2" ]; then
+  echo "Command successful, this test passes"
+else
+  echo "No output directories found, this test fails"
+  exit 1
+fi

.github/workflows/tests.yml

@@ -243,6 +243,42 @@ jobs:
           path: |
             /logs/results.tap
             /logs/**/*.log*
+  export-data:
+    if: ${{ !failure() && !cancelled() }} # Allow previous steps to be skipped, but not fail
+    needs: linting-done
+    runs-on: ubuntu-latest
+    env:
+      TOP: ${{ github.workspace }}
+    strategy:
+      matrix:
+        include:
+          - python-version: "3.6"
+            postgres-version: "9.6"
+
+          - python-version: "3.9"
+            postgres-version: "13"
+
+    services:
+      postgres:
+        image: postgres:${{ matrix.postgres-version }}
+        ports:
+          - 5432:5432
+        env:
+          POSTGRES_PASSWORD: "postgres"
+          POSTGRES_INITDB_ARGS: "--lc-collate C --lc-ctype C --encoding UTF8"
+        options: >-
+          --health-cmd pg_isready
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 5
+
+    steps:
+      - uses: actions/checkout@v2
+      - run: sudo apt-get -qq install xmlsec1
+      - uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+      - run: .ci/scripts/test_export_data_command.sh
 
   portdb:
     if: ${{ !failure() && !cancelled() }} # Allow previous steps to be skipped, but not fail

changelog.d/11078.bugfix

@@ -0,0 +1 @@
+Fix broken export-data admin command and add test script checking the command to CI.

synapse/app/admin_cmd.py

@@ -185,11 +185,7 @@ def start(config_options):
     # a full worker config.
     config.worker.worker_app = "synapse.app.admin_cmd"
 
-    if (
-        not config.worker.worker_daemonize
-        and not config.worker.worker_log_file
-        and not config.worker.worker_log_config
-    ):
+    if not config.worker.worker_daemonize and not config.worker.worker_log_config:
         # Since we're meant to be run as a "command" let's not redirect stdio
         # unless we've actually set log config.
         config.logging.no_redirect_stdio = True
@@ -221,7 +217,7 @@ def start(config_options):
 
     async def run():
         with LoggingContext("command"):
-            _base.start(ss)
+            await _base.start(ss)
             await args.func(ss, args)
 
     _base.start_worker_reactor(

synapse/handlers/admin.py

@@ -166,7 +166,9 @@ async def export_user_data(self, user_id: str, writer: "ExfiltrationWriter") ->
 
                 from_key = events[-1].internal_metadata.after
 
-                events = await filter_events_for_client(self.storage, user_id, events)
+                events = await filter_events_for_client(
+                    self.storage, user_id, events, filter_send_to_client=False
+                )
 
                 writer.write_events(room_id, events)