Chore: Raise Gotenberg container version (#4815)

* Updates the Gotenberg version to use 7.10 and gotenberg-client to match
* Fixes a long standing bug in this test where a whole page was missing from the expected

diff --git a/Pipfile.lock b/Pipfile.lock
index c0afbeea74474976e298327c1e3dbddaa65ed263..d1627e63ec68eaea384a91954899936784a7d39d 100644 (file)
--- a/Pipfile.lock
+++ b/Pipfile.lock
@@ -24,11 +24,11 @@
         },
         "anyio": {
             "hashes": [
-                "sha256:cfdb2b588b9fc25ede96d8db56ed50848b0b649dca3dd1df0b11f683bb9e0b5f",
-                "sha256:f7ed51751b2c2add651e5747c891b47e26d2a21be5d32d9311dfe9692f3e5d7a"
+                "sha256:56a415fbc462291813a94528a779597226619c8e78af7de0507333f700011e5f",
+                "sha256:5a0bec7085176715be77df87fc66d6c9d70626bd752fcc85f57cdbee5b3760da"
             ],
             "markers": "python_version >= '3.8'",
-            "version": "==4.0.0"
+            "version": "==4.1.0"
         },
         "asgiref": {
             "hashes": [
@@ -164,11 +164,11 @@
         },
         "certifi": {
             "hashes": [
-                "sha256:539cc1d13202e33ca466e88b2807e29f4c13049d6d87031a3c110744495cb082",
-                "sha256:92d6037539857d8206b8f6ae472e8b77db8058fec5937a1ef3f54304089edbb9"
+                "sha256:9b469f3a900bf28dc19b8cfbf8019bf47f7fdd1a65a1d4ffb98fc14166beb4d1",
+                "sha256:e036ab49d5b79556f99cfc2d9320b34cfbe5be05c5871b51de9329f0603b0474"
             ],
             "markers": "python_version >= '3.6'",
-            "version": "==2023.7.22"
+            "version": "==2023.11.17"
         },
         "cffi": {
             "hashes": [
@@ -540,11 +540,11 @@
         },
         "exceptiongroup": {
             "hashes": [
-                "sha256:097acd85d473d75af5bb98e41b61ff7fe35efe6675e4f9370ec6ec5126d160e9",
-                "sha256:343280667a4585d195ca1cf9cef84a4e178c4b6cf2274caef9859782b567d5e3"
+                "sha256:4bfd3996ac73b41e9b9628b04e079f193850720ea5945fc96a08633c66912f14",
+                "sha256:91f5c769735f051a4290d52edd0858999b57e5876e9f85937691bd4c9fa3ed68"
             ],
             "markers": "python_version < '3.11'",
-            "version": "==1.1.3"
+            "version": "==1.2.0"
         },
         "filelock": {
             "hashes": [
@@ -566,12 +566,12 @@
         },
         "gotenberg-client": {
             "hashes": [
-                "sha256:4508ecb913ef2d553dd2ceb78e32cee001000ba08c910ba1f9ace38350d1589e",
-                "sha256:7a3f8a02caee768391373b3610c6ec25a853cccf391ed6b5d5a1292c3ed15e7e"
+                "sha256:3026726d1a47f41e9d43f18c95e530ff64f506e2ec436f116a088da27c7430da",
+                "sha256:c2555f7401faa48213a7cbe29c5e4a68316a003a6953753bc58d1e2b19873771"
             ],
             "index": "pypi",
             "markers": "python_version >= '3.8'",
-            "version": "==0.3.0"
+            "version": "==0.4.0"
         },
         "gunicorn": {
             "hashes": [
@@ -753,11 +753,11 @@
                 "http2"
             ],
             "hashes": [
-                "sha256:fec7d6cc5c27c578a391f7e87b9aa7d3d8fbcd034f6399f9f79b45bcc12a866a",
-                "sha256:ffd96d5cf901e63863d9f1b4b6807861dbea4d301613415d9e6e57ead15fc5d0"
+                "sha256:8b8fcaa0c8ea7b05edd69a094e63a2094c4efcb48129fb757361bc423c0ad9e8",
+                "sha256:a05d3d052d9b2dfce0e3896636467f8a5342fb2b902c819428e1ac65413ca118"
             ],
             "markers": "python_version >= '3.9'",
-            "version": "==0.25.1"
+            "version": "==0.25.2"
         },
         "humanize": {
             "hashes": [
@@ -777,11 +777,11 @@
         },
         "idna": {
             "hashes": [
-                "sha256:814f528e8dead7d329833b91c5faa87d60bf71824cd12a7530b5526063d02cb4",
-                "sha256:90b77e79eaa3eba6de819a0c442c0b4ceefc341a7a2ab77d7562bf49f425c5c2"
+                "sha256:9ecdbbd083b06798ae1e86adcbfe8ab1479cf864e4ee30fe4e46a003d12491ca",
+                "sha256:c05567e9c24a6b9faaa835c4821bad0590fbb9d5779e7caa6e1cc4978e7eb24f"
             ],
             "markers": "python_version >= '3.5'",
-            "version": "==3.4"
+            "version": "==3.6"
         },
         "imap-tools": {
             "hashes": [
@@ -1849,7 +1849,7 @@
                 "sha256:8f92fc8806f9a6b641eaa5318da32b44d401efaac0f6678c9bc448ba3605faa0",
                 "sha256:df8e4339e9cb77357558cbdbceca33c303714cf861d1eef15e1070055ae8b7ef"
             ],
-            "markers": "python_version < '3.11'",
+            "markers": "python_version < '3.10'",
             "version": "==4.8.0"
         },
         "tzdata": {

diff --git a/docker/compose/docker-compose.ci-test.yml b/docker/compose/docker-compose.ci-test.yml
index e9ff1d29eae9445f04a78a85f2f46bf548feec0f..7987b8798bc2e85232e7ae0f314908b9c99686c9 100644 (file)
--- a/docker/compose/docker-compose.ci-test.yml
+++ b/docker/compose/docker-compose.ci-test.yml
@@ -6,7 +6,7 @@
 version: "3.7"
 services:
   gotenberg:
-    image: docker.io/gotenberg/gotenberg:7.8
+    image: docker.io/gotenberg/gotenberg:7.10
     hostname: gotenberg
     container_name: gotenberg
     network_mode: host
@@ -17,6 +17,8 @@ services:
       - "gotenberg"
       - "--chromium-disable-javascript=true"
       - "--chromium-allow-list=file:///tmp/.*"
+      - "--log-level=warn"
+      - "--log-format=text"
   tika:
     image: ghcr.io/paperless-ngx/tika:latest
     hostname: tika

diff --git a/docker/compose/docker-compose.mariadb-tika.yml b/docker/compose/docker-compose.mariadb-tika.yml
index 7513655d0323127c09b43c87f7803d8c48203886..10d0e61a226b66428994ad53f29e62488bc947a0 100644 (file)
--- a/docker/compose/docker-compose.mariadb-tika.yml
+++ b/docker/compose/docker-compose.mariadb-tika.yml
@@ -83,7 +83,7 @@ services:
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998
 
   gotenberg:
-    image: docker.io/gotenberg/gotenberg:7.8
+    image: docker.io/gotenberg/gotenberg:7.10
     restart: unless-stopped
     # The gotenberg chromium route is used to convert .eml files. We do not
     # want to allow external content like tracking pixels or even javascript.

diff --git a/docker/compose/docker-compose.postgres-tika.yml b/docker/compose/docker-compose.postgres-tika.yml
index d040b307c08a245fc5b2e91430c1286713a0205c..5ec2595c169c65e08995511c9f0991a685124232 100644 (file)
--- a/docker/compose/docker-compose.postgres-tika.yml
+++ b/docker/compose/docker-compose.postgres-tika.yml
@@ -77,7 +77,7 @@ services:
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998
 
   gotenberg:
-    image: docker.io/gotenberg/gotenberg:7.8
+    image: docker.io/gotenberg/gotenberg:7.10
     restart: unless-stopped
 
     # The gotenberg chromium route is used to convert .eml files. We do not

diff --git a/docker/compose/docker-compose.sqlite-tika.yml b/docker/compose/docker-compose.sqlite-tika.yml
index 37f619c178378a27928bd632ee235d2c502c4128..ed3842224957066871943b90c64a4ce96dc3dcc6 100644 (file)
--- a/docker/compose/docker-compose.sqlite-tika.yml
+++ b/docker/compose/docker-compose.sqlite-tika.yml
@@ -65,7 +65,7 @@ services:
       PAPERLESS_TIKA_ENDPOINT: http://tika:9998
 
   gotenberg:
-    image: docker.io/gotenberg/gotenberg:7.8
+    image: docker.io/gotenberg/gotenberg:7.10
     restart: unless-stopped
 
     # The gotenberg chromium route is used to convert .eml files. We do not

diff --git a/src/paperless_mail/parsers.py b/src/paperless_mail/parsers.py
index 4b3e5686eb530326e9f2be38be4c748fde22985c..9bc7081d69c6a1ec63207f610a0cd7a6529e52f1 100644 (file)
--- a/src/paperless_mail/parsers.py
+++ b/src/paperless_mail/parsers.py
@@ -215,6 +215,8 @@ class MailDocumentParser(DocumentParser):
                 mail_message.attachments,
             )
 
+            self.log.debug("Merging email text and HTML content into single PDF")
+
             with GotenbergClient(
                 host=settings.TIKA_GOTENBERG_ENDPOINT,
                 timeout=settings.CELERY_TASK_TIME_LIMIT,
@@ -348,7 +350,7 @@ class MailDocumentParser(DocumentParser):
             text = compiled_close.sub("</div", text)
             return text
 
-        self.log.info("Converting html to PDF")
+        self.log.info("Converting message html to PDF")
 
         tempdir = Path(self.tempdir)
 

diff --git a/src/paperless_mail/tests/samples/html.eml.pdf b/src/paperless_mail/tests/samples/html.eml.pdf
index d2de2cb8e35e4fd75e5b5a1dca1a45372404053d..6916e2ea7c0238741667455e4ab1fda4165eb9c8 100644 (file)
Binary files a/src/paperless_mail/tests/samples/html.eml.pdf and b/src/paperless_mail/tests/samples/html.eml.pdf differ