mirror of
https://github.com/dgtlmoon/changedetection.io.git
synced 2026-01-22 07:00:27 +00:00
3d14df6a11
Multi-language / Translations Support (#3696) - Complete internationalization system implemented - Support for 7 languages: Czech (cs), German (de), French (fr), Italian (it), Korean (ko), Chinese Simplified (zh), Chinese Traditional (zh_TW) - Language selector with localized flags and theming - Flash message translations - Multiple translation fixes and improvements across all languages - Language setting preserved across redirects Pluggable Content Fetchers (#3653) - New architecture for extensible content fetcher system - Allows custom fetcher implementations Image / Screenshot Comparison Processor (#3680) - New processor for visual change detection (disabled for this release) - Supporting CSS/JS infrastructure added UI Improvements Design & Layout - Auto-generated tag color schemes - Simplified login form styling - Removed hard-coded CSS, moved to SCSS variables - Tag UI cleanup and improvements - Automatic tab wrapper functionality - Menu refactoring for better organization - Cleanup of offset settings - Hide sticky tabs on narrow viewports - Improved responsive layout (#3702) User Experience - Modal alerts/confirmations on delete/clear operations (#3693, #3598, #3382) - Auto-add https:// to URLs in quickwatch form if not present - Better redirect handling on login (#3699) - 'Recheck all' now returns to correct group/tag (#3673) - Language set redirect keeps hash fragment - More friendly human-readable text throughout UI Performance & Reliability Scheduler & Processing - Soft delays instead of blocking time.sleep() calls (#3710) - More resilient handling of same UUID being processed (#3700) - Better Puppeteer timeout handling - Improved Puppeteer shutdown/cleanup (#3692) - Requests cleanup now properly async History & Rendering - Faster server-side "difference" rendering on History page (#3442) - Show ignored/triggered rows in history - API: Retry watch data if watch dict changed (more reliable) API Improvements - Watch get endpoint: retry mechanism for changed watch data - WatchHistoryDiff API endpoint includes extra format args (#3703) Testing Improvements - Replace time.sleep with wait_for_notification_endpoint_output (#3716) - Test for mode switching (#3701) - Test for #3720 added (#3725) - Extract-text difference test fixes - Improved dev workflow Bug Fixes - Notification error text output (#3672, #3669, #3280) - HTML validation fixes (#3704) - Template discovery path fixes - Notification debug log now uses system locale for dates/times - Puppeteer spelling mistake in log output - Recalculation on anchor change - Queue bubble update disabled temporarily Dependency Updates - beautifulsoup4 updated (#3724) - psutil 7.1.0 → 7.2.1 (#3723) - python-engineio ~=4.12.3 → ~=4.13.0 (#3707) - python-socketio ~=5.14.3 → ~=5.16.0 (#3706) - flask-socketio ~=5.5.1 → ~=5.6.0 (#3691) - brotli ~=1.1 → ~=1.2 (#3687) - lxml updated (#3590) - pytest ~=7.2 → ~=9.0 (#3676) - jsonschema ~=4.0 → ~=4.25 (#3618) - pluggy ~=1.5 → ~=1.6 (#3616) - cryptography 44.0.1 → 46.0.3 (security) (#3589) Documentation - README updated with viewport size setup information Development Infrastructure - Dev container only built on dev branch - Improved dev workflow tooling
85 lines
3.5 KiB
Python
85 lines
3.5 KiB
Python
#!/usr/bin/env python3
|
|
|
|
import time
|
|
from flask import url_for
|
|
from .util import set_original_response, set_modified_response, live_server_setup, wait_for_all_checks
|
|
import os
|
|
|
|
|
|
# `subtractive_selectors` should still work in `source:` type requests
|
|
def test_fetch_pdf(client, live_server, measure_memory_usage, datastore_path):
|
|
import shutil
|
|
import os
|
|
|
|
shutil.copy("tests/test.pdf", os.path.join(datastore_path, "endpoint-test.pdf"))
|
|
first_version_size = os.path.getsize(os.path.join(datastore_path, "endpoint-test.pdf"))
|
|
|
|
test_url = url_for('test_pdf_endpoint', _external=True)
|
|
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
|
|
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
|
|
|
|
wait_for_all_checks(client)
|
|
|
|
watch = live_server.app.config['DATASTORE'].data['watching'][uuid]
|
|
dates = list(watch.history.keys())
|
|
snapshot_contents = watch.get_history_snapshot(timestamp=dates[0])
|
|
|
|
# PDF header should not be there (it was converted to text)
|
|
assert 'PDF' not in snapshot_contents
|
|
# Was converted away from HTML
|
|
assert 'pdftohtml' not in snapshot_contents.lower() # Generator tag shouldnt be there
|
|
assert f'Original file size - {first_version_size}' in snapshot_contents
|
|
assert 'html' not in snapshot_contents.lower() # is converted from html
|
|
assert 'body' not in snapshot_contents.lower() # is converted from html
|
|
# And our text content was there
|
|
assert 'hello world' in snapshot_contents
|
|
|
|
# So we know if the file changes in other ways
|
|
import hashlib
|
|
original_md5 = hashlib.md5(open(os.path.join(datastore_path, "endpoint-test.pdf"), 'rb').read()).hexdigest().upper()
|
|
# We should have one
|
|
assert len(original_md5) >0
|
|
# And it's going to be in the document
|
|
assert f'Document checksum - {original_md5}' in snapshot_contents
|
|
|
|
shutil.copy("tests/test2.pdf", os.path.join(datastore_path, "endpoint-test.pdf"))
|
|
changed_md5 = hashlib.md5(open(os.path.join(datastore_path, "endpoint-test.pdf"), 'rb').read()).hexdigest().upper()
|
|
res = client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
|
|
assert b'Queued 1 watch for rechecking.' in res.data
|
|
|
|
wait_for_all_checks(client)
|
|
|
|
# Now something should be ready, indicated by having a 'has-unread-changes' class
|
|
res = client.get(url_for("watchlist.index"))
|
|
assert b'has-unread-changes' in res.data
|
|
|
|
# The original checksum should be not be here anymore (cdio adds it to the bottom of the text)
|
|
|
|
res = client.get(
|
|
url_for("ui.ui_preview.preview_page", uuid="first"),
|
|
follow_redirects=True
|
|
)
|
|
|
|
assert original_md5.encode('utf-8') not in res.data
|
|
assert changed_md5.encode('utf-8') in res.data
|
|
|
|
res = client.get(
|
|
url_for("ui.ui_diff.diff_history_page", uuid="first"),
|
|
follow_redirects=True
|
|
)
|
|
|
|
assert original_md5.encode('utf-8') in res.data
|
|
assert changed_md5.encode('utf-8') in res.data
|
|
assert b'here is a change' in res.data
|
|
|
|
|
|
dates = list(watch.history.keys())
|
|
# new snapshot was also OK, no HTML
|
|
snapshot_contents = watch.get_history_snapshot(timestamp=dates[1])
|
|
assert 'html' not in snapshot_contents.lower()
|
|
assert f'Original file size - {os.path.getsize(os.path.join(datastore_path, "endpoint-test.pdf"))}' in snapshot_contents
|
|
assert f'here is a change' in snapshot_contents
|
|
assert os.path.getsize(os.path.join(datastore_path, "endpoint-test.pdf")) != first_version_size # And the disk change worked
|
|
|
|
|
|
|