Fix: preserve document fields during Gotenberg conversion

Gotenberg's LibreOffice route enables updateIndexes by default, which
refreshes dynamic fields (e.g. auto-dates) to the current date. Disable
it so field values are preserved as authored.

Dockerfile

@@ -37,9 +37,7 @@ WORKDIR /usr/src/s6
 # https://github.com/just-containers/s6-overlay#customizing-s6-overlay-behaviour
 ENV \
     S6_BEHAVIOUR_IF_STAGE2_FAILS=2 \
-    S6_CMD_WAIT_FOR_SERVICES_MAXTIME=60000 \
-    S6_KILL_GRACETIME=30000 \
-    S6_SERVICES_GRACETIME=30000 \
+    S6_CMD_WAIT_FOR_SERVICES_MAXTIME=0 \
     S6_VERBOSITY=1 \
     PATH=/command:$PATH
 

docker/rootfs/etc/s6-overlay/s6-rc.d/svc-consumer/finish

@@ -1,16 +0,0 @@
-#!/command/with-contenv /usr/bin/bash
-# shellcheck shell=bash
-
-if [[ -n "${PAPERLESS_CONSUMER_DISABLE}" ]]; then
-	if [[ $1 -eq 0 ]]; then
-		echo "[svc-consumer] Consumer is disabled, service did not run"
-	else
-		echo "[svc-consumer] Consumer is disabled, but service exited with error (exit code: $1, signal: $2)" >&2
-	fi
-else
-	if [[ $1 -eq 0 ]]; then
-		echo "[svc-consumer] Service stopped cleanly (exit code: $1, signal: $2)"
-	else
-		echo "[svc-consumer] Service exited with error (exit code: $1, signal: $2)" >&2
-	fi
-fi

docker/rootfs/etc/s6-overlay/s6-rc.d/svc-flower/finish

@@ -1,16 +0,0 @@
-#!/command/with-contenv /usr/bin/bash
-# shellcheck shell=bash
-
-if [[ -z "${PAPERLESS_ENABLE_FLOWER}" ]]; then
-	if [[ $1 -eq 0 ]]; then
-		echo "[svc-flower] Flower is disabled, service did not run"
-	else
-		echo "[svc-flower] Flower is disabled, but service exited with error (exit code: $1, signal: $2)" >&2
-	fi
-else
-	if [[ $1 -eq 0 ]]; then
-		echo "[svc-flower] Service stopped cleanly (exit code: $1, signal: $2)"
-	else
-		echo "[svc-flower] Service exited with error (exit code: $1, signal: $2)" >&2
-	fi
-fi

docker/rootfs/etc/s6-overlay/s6-rc.d/svc-flower/run

@@ -6,6 +6,9 @@ declare -r log_prefix="[svc-flower]"
 echo "${log_prefix} Checking if we should start flower..."
 
 if [[ -n "${PAPERLESS_ENABLE_FLOWER}" ]]; then
+	# Small delay to allow celery to be up first
+	echo "${log_prefix} Starting flower in 5s"
+	sleep 5
 	cd ${PAPERLESS_SRC_DIR}
 
 	if [[ -n "${USER_IS_NON_ROOT}" ]]; then

docker/rootfs/etc/s6-overlay/s6-rc.d/svc-scheduler/finish

@@ -1,8 +0,0 @@
-#!/command/with-contenv /usr/bin/bash
-# shellcheck shell=bash
-
-if [[ $1 -eq 0 ]]; then
-	echo "[svc-scheduler] Service stopped cleanly (exit code: $1, signal: $2)"
-else
-	echo "[svc-scheduler] Service exited with error (exit code: $1, signal: $2)" >&2
-fi

docker/rootfs/etc/s6-overlay/s6-rc.d/svc-webserver/finish

@@ -1,8 +0,0 @@
-#!/command/with-contenv /usr/bin/bash
-# shellcheck shell=bash
-
-if [[ $1 -eq 0 ]]; then
-	echo "[svc-webserver] Service stopped cleanly (exit code: $1, signal: $2)"
-else
-	echo "[svc-webserver] Service exited with error (exit code: $1, signal: $2)" >&2
-fi

docker/rootfs/etc/s6-overlay/s6-rc.d/svc-webserver/notification-fd

@@ -1 +0,0 @@
-3

docker/rootfs/etc/s6-overlay/s6-rc.d/svc-webserver/run

@@ -14,7 +14,7 @@ if [[ -n "${PAPERLESS_FORCE_SCRIPT_NAME}" ]]; then
 fi
 
 if [[ -n "${USER_IS_NON_ROOT}" ]]; then
-	exec s6-notifyoncheck -d -w 1000 -- curl -sf "http://localhost:${GRANIAN_PORT}/" -- granian --interface asginl --ws --loop uvloop "paperless.asgi:application"
+	exec granian --interface asginl --ws --loop uvloop "paperless.asgi:application"
 else
-	exec s6-notifyoncheck -d -w 1000 -- curl -sf "http://localhost:${GRANIAN_PORT}/" -- s6-setuidgid paperless granian --interface asginl --ws --loop uvloop "paperless.asgi:application"
+	exec s6-setuidgid paperless granian --interface asginl --ws --loop uvloop "paperless.asgi:application"
 fi

docker/rootfs/etc/s6-overlay/s6-rc.d/svc-worker/finish

@@ -1,8 +0,0 @@
-#!/command/with-contenv /usr/bin/bash
-# shellcheck shell=bash
-
-if [[ $1 -eq 0 ]]; then
-	echo "[svc-worker] Service stopped cleanly (exit code: $1, signal: $2)"
-else
-	echo "[svc-worker] Service exited with error (exit code: $1, signal: $2)" >&2
-fi

docker/rootfs/etc/s6-overlay/s6-rc.d/svc-worker/notification-fd

@@ -1 +0,0 @@
-3

docker/rootfs/etc/s6-overlay/s6-rc.d/svc-worker/run

@@ -4,7 +4,7 @@
 cd ${PAPERLESS_SRC_DIR}
 
 if [[ -n "${USER_IS_NON_ROOT}" ]]; then
-	exec s6-notifyoncheck -d -w 1000 -- sh -c 'celery --app paperless inspect ping --timeout 1' -- /usr/local/bin/celery --app paperless worker --loglevel INFO --without-mingle --without-gossip
+	exec /usr/local/bin/celery --app paperless worker --loglevel INFO --without-mingle --without-gossip
 else
-	exec s6-notifyoncheck -d -w 1000 -- sh -c 'celery --app paperless inspect ping --timeout 1' -- s6-setuidgid paperless /usr/local/bin/celery --app paperless worker --loglevel INFO --without-mingle --without-gossip
+	exec s6-setuidgid paperless /usr/local/bin/celery --app paperless worker --loglevel INFO --without-mingle --without-gossip
 fi

src/paperless/parsers/tika.py

@@ -423,6 +423,11 @@ class TikaDocumentParser:
         logger.info("Converting %s to PDF as %s", document_path, pdf_path)
 
         with self._gotenberg_client.libre_office.to_pdf() as route:
+            # Preserve document fields as authored. updateIndexes (Gotenberg's
+            # default) triggers a refresh() that rewrites dynamic fields like
+            # auto-dates to the current date.
+            route.update_indexes(update_indexes=False)
+
             # Set the output format of the resulting PDF.
             # OutputTypeConfig reads the database-stored ApplicationConfiguration
             # first, then falls back to the PAPERLESS_OCR_OUTPUT_TYPE env var.

src/paperless/tests/parsers/test_tika_parser.py

@@ -223,4 +223,11 @@ class TestTikaParser:
 
         assert form_field_found
 
+        # Field updates must be disabled so LibreOffice preserves document
+        # fields (e.g. auto-date fields) as authored rather than refreshing
+        # them to the current date.
+        assert any(
+            b'name="updateIndexes"' in part and b"false" in part for part in parts
+        )
+
         httpx_mock.reset()