paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-11-21 04:36:53 -06:00
Code Issues Packages Projects Releases Wiki Activity

Chore: replace test image URLs to our own files (#11390)

Browse Source
This commit is contained in:
shamoon
2025-11-17 10:22:54 -08:00
committed by GitHub
parent b3d6359afc
commit 533b64cb70
3 changed files with 6 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/paperless_mail/tests/samples/html.eml
View File

@@ -55,7 +55,7 @@ Content-Transfer-Encoding: 7bit
<p>Some Text</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.">
<img src="https://docs.paperless-ngx.com/assets/logo_full_white.svg" alt="This image should not be shown.">
</p>
<p>and an embedded image.<br>

2
src/paperless_mail/tests/samples/sample.html
View File

@@ -6,7 +6,7 @@
<p>Some Text</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.">
<img src="https://docs.paperless-ngx.com/assets/logo_full_white.svg" alt="This image should not be shown.">
</p>
<p>and an embedded image.<br>

37
src/paperless_mail/tests/test_parsers_live.py
View File

@@ -2,7 +2,6 @@ import os
import shutil
import subprocess
import tempfile
import time
from pathlib import Path
import httpx
@@ -54,34 +53,6 @@ class TestUrlCanary:
Verify certain URLs are still available so testing is valid still
"""
@classmethod
def _fetch_wikimedia(cls, url: str) -> httpx.Response:
"""
Wikimedia occasionally throttles automated requests (HTTP 429). Retry a few
times with a short backoff so the tests stay stable, and skip if throttling
persists.
"""
last_resp: httpx.Response | None = None
# Wikimedia rejects requests without a browser-like User-Agent header and returns 403.
headers = {
"User-Agent": (
"Mozilla/5.0 (X11; Linux x86_64) "
"AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/123.0.0.0 Safari/537.36"
),
}
for delay in (0, 1, 2):
resp = httpx.get(url, headers=headers, timeout=30.0)
if resp.status_code != httpx.codes.TOO_MANY_REQUESTS:
return resp
last_resp = resp
time.sleep(delay)
pytest.skip(
"Wikimedia throttled the canary request with HTTP 429; try rerunning later.",
)
return last_resp # pragma: no cover
def test_online_image_exception_on_not_available(self):
"""
GIVEN:
@@ -96,8 +67,8 @@ class TestUrlCanary:
whether this image stays online forever, so here we check if we can detect if is not
available anymore.
"""
resp = self._fetch_wikimedia(
"https://upload.wikimedia.org/wikipedia/en/f/f7/nonexistent.png",
resp = httpx.get(
"https://docs.paperless-ngx.com/assets/non-existent.png",
)
with pytest.raises(httpx.HTTPStatusError) as exec_info:
resp.raise_for_status()
@@ -119,8 +90,8 @@ class TestUrlCanary:
"""
# Now check the URL used in samples/sample.html
resp = self._fetch_wikimedia(
"https://upload.wikimedia.org/wikipedia/en/f/f7/RickRoll.png",
resp = httpx.get(
"https://docs.paperless-ngx.com/assets/logo_full_white.svg",
)
resp.raise_for_status()