paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-27 10:59:27 -05:00
Code Issues Packages Projects Releases Wiki Activity

add unittest for external images

Browse Source
This commit is contained in:
phail 2022-10-22 00:44:32 +02:00
parent 09b5bd17f2
commit f1f5227ccd
7 changed files with 52 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
docker/compose/docker-compose.postgres-tika.yml
View File

@ -80,6 +80,13 @@ services:
image: docker.io/gotenberg/gotenberg:7.4
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.
command:
- "gotenberg"
- "--chromium-disable-javascript=true"
- "--chromium-allow-list=file:///tmp/.*"
tika:
image: ghcr.io/paperless-ngx/tika:latest
restart: unless-stopped

7
docker/compose/docker-compose.sqlite-tika.yml
View File

@ -68,6 +68,13 @@ services:
image: docker.io/gotenberg/gotenberg:7.4
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.
command:
- "gotenberg"
- "--chromium-disable-javascript=true"
- "--chromium-allow-list=file:///tmp/.*"
tika:
image: ghcr.io/paperless-ngx/tika:latest
restart: unless-stopped

7
docs/configuration.rst
View File

@ -515,6 +515,13 @@ requires are as follows:
image: gotenberg/gotenberg:7.4
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.
command:
- "gotenberg"
- "--chromium-disable-javascript=true"
- "--chromium-allow-list=file:///tmp/.*"
tika:
image: ghcr.io/paperless-ngx/tika:latest
restart: unless-stopped

9
docs/troubleshooting.rst
View File

@ -127,9 +127,14 @@ If using docker-compose, this is achieved by the following configuration change
gotenberg:
image: gotenberg/gotenberg:7.4
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.
command:
- "gotenberg"
- "--api-timeout=60"
- "gotenberg"
- "--chromium-disable-javascript=true"
- "--chromium-allow-list=file:///tmp/.*"
- "--api-timeout=60"
Permission denied errors in the consumption directory
#####################################################

2
scripts/start_services.sh
View File

@ -2,5 +2,5 @@
docker run -p 5432:5432 -e POSTGRES_PASSWORD=password -v paperless_pgdata:/var/lib/postgresql/data -d postgres:13
docker run -d -p 6379:6379 redis:latest
docker run -p 3000:3000 -d gotenberg/gotenberg:7.4
docker run -p 3000:3000 -d gotenberg/gotenberg:7.4 gotenberg --chromium-disable-javascript=true --chromium-allow-list=file:///tmp/.*
docker run -p 9998:9998 -d ghcr.io/paperless-ngx/tika:latest

6
src/paperless_mail/tests/samples/sample.html
View File

@ -4,7 +4,11 @@
</head>
<body>
<p>Some Text</p>
<p><img src="cid:part1.pNdUSz0s.D3NqVtPg@example.de" alt=""></p>
<p>
<img src="cid:part1.pNdUSz0s.D3NqVtPg@example.de" alt="Has to be rewritten to work..">
<img src="https://upload.wikimedia.org/wikipedia/en/f/f7/RickRoll.png" alt="This image should not be shown.">
</p>
<p>and an embedded image.<br>
</p>
<p id="changeme">Paragraph unchanged.</p>

20
src/paperless_mail/tests/test_eml.py
View File

@ -2,6 +2,8 @@ import datetime
import hashlib
import os
from unittest import mock
from urllib.error import HTTPError
from urllib.request import urlopen
import pytest
from django.test import TestCase
@ -350,10 +352,24 @@ class TestParser(TestCase):
# The created pdf is not reproducible. But the converted image should always look the same.
expected_hash = (
"88dee024ec77b1139b77913547717bd7e94f53651d489c54a7084d30a82e389e"
"267d61f0ab8f128a037002a424b2cb4bfe18a81e17f0b70f15d241688ed47d1a"
)
self.assertEqual(
thumb_hash,
expected_hash,
"PDF looks different.",
f"PDF looks different. Check if {converted} looks weird. "
f"If Rick Astley is shown, Gotenberg loads from web which is bad for Mail content.",
)
def test_is_online_image_still_available(self):
"""
A public image is used in the html sample file. We have no control
whether this image stays online forever, so here we check if it is still there
"""
# Start by Testing if nonexistent URL really throws an Exception
with pytest.raises(HTTPError):
urlopen("https://upload.wikimedia.org/wikipedia/en/f/f7/nonexistent.png")
# Now check the URL used in samples/sample.html
urlopen("https://upload.wikimedia.org/wikipedia/en/f/f7/RickRoll.png")