mirror of
https://github.com/dgtlmoon/changedetection.io.git
synced 2026-01-25 00:20:33 +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
254 lines
6.7 KiB
Python
254 lines
6.7 KiB
Python
#!/usr/bin/env python3
|
|
|
|
import time
|
|
import os
|
|
|
|
from flask import url_for
|
|
|
|
from ..html_tools import *
|
|
from .util import live_server_setup, wait_for_all_checks, delete_all_watches
|
|
|
|
|
|
|
|
|
|
def set_response_with_multiple_index(datastore_path):
|
|
data= """<!DOCTYPE html>
|
|
<html>
|
|
<body>
|
|
|
|
<!-- NOTE!! CHROME WILL ADD TBODY HERE IF ITS NOT THERE!! -->
|
|
<table style="width:100%">
|
|
<tr>
|
|
<th>Person 1</th>
|
|
<th>Person 2</th>
|
|
<th>Person 3</th>
|
|
</tr>
|
|
<tr>
|
|
<td>Emil</td>
|
|
<td>Tobias</td>
|
|
<td>Linus</td>
|
|
</tr>
|
|
<tr>
|
|
<td>16</td>
|
|
<td>14</td>
|
|
<td>10</td>
|
|
</tr>
|
|
</table>
|
|
</body>
|
|
</html>
|
|
"""
|
|
with open(os.path.join(datastore_path, "endpoint-content.txt"), "w") as f:
|
|
f.write(data)
|
|
|
|
|
|
def set_original_response(datastore_path):
|
|
test_return_data = """<html>
|
|
<header>
|
|
<h2>Header</h2>
|
|
</header>
|
|
<nav>
|
|
<ul>
|
|
<li><a href="#">A</a></li>
|
|
<li><a href="#">B</a></li>
|
|
<li><a href="#">C</a></li>
|
|
</ul>
|
|
</nav>
|
|
<body>
|
|
Some initial text<br>
|
|
<p>Which is across multiple lines</p>
|
|
<br>
|
|
So let's see what happens. <br>
|
|
<div id="changetext">Some text that will change</div>
|
|
</body>
|
|
<footer>
|
|
<p>Footer</p>
|
|
</footer>
|
|
</html>
|
|
"""
|
|
|
|
with open(os.path.join(datastore_path, "endpoint-content.txt"), "w") as f:
|
|
f.write(test_return_data)
|
|
|
|
|
|
def set_modified_response(datastore_path):
|
|
test_return_data = """<html>
|
|
<header>
|
|
<h2>Header changed</h2>
|
|
</header>
|
|
<nav>
|
|
<ul>
|
|
<li><a href="#">A changed</a></li>
|
|
<li><a href="#">B</a></li>
|
|
<li><a href="#">C</a></li>
|
|
</ul>
|
|
</nav>
|
|
<body>
|
|
Some initial text<br>
|
|
<p>Which is across multiple lines</p>
|
|
<br>
|
|
So let's see what happens. <br>
|
|
<div id="changetext">Some text that changes</div>
|
|
</body>
|
|
<footer>
|
|
<p>Footer changed</p>
|
|
</footer>
|
|
</html>
|
|
"""
|
|
|
|
with open(os.path.join(datastore_path, "endpoint-content.txt"), "w") as f:
|
|
f.write(test_return_data)
|
|
|
|
|
|
def test_element_removal_output():
|
|
from inscriptis import get_text
|
|
|
|
# Check text with sub-parts renders correctly
|
|
content = """<html>
|
|
<header>
|
|
<h2>Header</h2>
|
|
</header>
|
|
<nav>
|
|
<ul>
|
|
<li><a href="#">A</a></li>
|
|
</ul>
|
|
</nav>
|
|
<body>
|
|
Some initial text<br>
|
|
<p>across multiple lines</p>
|
|
<div id="changetext">Some text that changes</div>
|
|
<div>Some text should be matched by xPath // selector</div>
|
|
<div>Some text should be matched by xPath selector</div>
|
|
<div>Some text should be matched by xPath1 selector</div>
|
|
</body>
|
|
<footer>
|
|
<p>Footer</p>
|
|
</footer>
|
|
</html>
|
|
"""
|
|
html_blob = element_removal(
|
|
[
|
|
"header",
|
|
"footer",
|
|
"nav",
|
|
"#changetext",
|
|
"//*[contains(text(), 'xPath // selector')]",
|
|
"xpath://*[contains(text(), 'xPath selector')]",
|
|
"xpath1://*[contains(text(), 'xPath1 selector')]"
|
|
],
|
|
html_content=content
|
|
)
|
|
text = get_text(html_blob)
|
|
assert (
|
|
text
|
|
== """Some initial text
|
|
|
|
across multiple lines
|
|
"""
|
|
)
|
|
|
|
|
|
def test_element_removal_full(client, live_server, measure_memory_usage, datastore_path):
|
|
|
|
|
|
set_original_response(datastore_path=datastore_path)
|
|
|
|
|
|
# Add our URL to the import page
|
|
test_url = url_for("test_endpoint", _external=True)
|
|
res = client.post(
|
|
url_for("imports.import_page"), data={"urls": test_url}, follow_redirects=True
|
|
)
|
|
assert b"1 Imported" in res.data
|
|
wait_for_all_checks(client)
|
|
|
|
# Goto the edit page, add the filter data
|
|
# Not sure why \r needs to be added - absent of the #changetext this is not necessary
|
|
subtractive_selectors_data = "header\r\nfooter\r\nnav\r\n#changetext"
|
|
res = client.post(
|
|
url_for("ui.ui_edit.edit_page", uuid="first"),
|
|
data={
|
|
"subtractive_selectors": subtractive_selectors_data,
|
|
"url": test_url,
|
|
"tags": "",
|
|
"headers": "",
|
|
"fetch_backend": "html_requests",
|
|
"time_between_check_use_default": "y",
|
|
},
|
|
follow_redirects=True,
|
|
)
|
|
assert b"Updated watch." in res.data
|
|
wait_for_all_checks(client)
|
|
|
|
# Check it saved
|
|
res = client.get(
|
|
url_for("ui.ui_edit.edit_page", uuid="first"),
|
|
)
|
|
assert bytes(subtractive_selectors_data.encode("utf-8")) in res.data
|
|
|
|
# Trigger a check
|
|
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)
|
|
|
|
# so that we set the state to 'has-unread-changes' after all the edits
|
|
client.get(url_for("ui.ui_diff.diff_history_page", uuid="first"))
|
|
|
|
# Make a change to header/footer/nav
|
|
set_modified_response(datastore_path=datastore_path)
|
|
|
|
# Trigger a check
|
|
res = client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
|
|
assert b'Queued 1 watch for rechecking.' in res.data
|
|
|
|
# Give the thread time to pick it up
|
|
wait_for_all_checks(client)
|
|
|
|
# There should not be an unviewed change, as changes should be removed
|
|
res = client.get(url_for("watchlist.index"))
|
|
assert b"unviewed" not in res.data
|
|
|
|
# Re #2752
|
|
def test_element_removal_nth_offset_no_shift(client, live_server, measure_memory_usage, datastore_path):
|
|
|
|
set_response_with_multiple_index(datastore_path=datastore_path)
|
|
subtractive_selectors_data = [
|
|
### css style ###
|
|
"""body > table > tr:nth-child(1) > th:nth-child(2)
|
|
body > table > tr:nth-child(2) > td:nth-child(2)
|
|
body > table > tr:nth-child(3) > td:nth-child(2)
|
|
body > table > tr:nth-child(1) > th:nth-child(3)
|
|
body > table > tr:nth-child(2) > td:nth-child(3)
|
|
body > table > tr:nth-child(3) > td:nth-child(3)""",
|
|
### second type, xpath ###
|
|
"""//body/table/tr[1]/th[2]
|
|
//body/table/tr[2]/td[2]
|
|
//body/table/tr[3]/td[2]
|
|
//body/table/tr[1]/th[3]
|
|
//body/table/tr[2]/td[3]
|
|
//body/table/tr[3]/td[3]"""]
|
|
|
|
test_url = url_for("test_endpoint", _external=True)
|
|
|
|
for selector_list in subtractive_selectors_data:
|
|
|
|
delete_all_watches(client)
|
|
|
|
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url, extras={"subtractive_selectors": selector_list.splitlines()})
|
|
client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
|
|
wait_for_all_checks(client)
|
|
|
|
res = client.get(
|
|
url_for("ui.ui_preview.preview_page", uuid="first"),
|
|
follow_redirects=True
|
|
)
|
|
|
|
# the filters above should have removed this but they never say to remove the "emil" column
|
|
assert b"Tobias" not in res.data
|
|
assert b"Linus" not in res.data
|
|
assert b"Person 2" not in res.data
|
|
assert b"Person 3" not in res.data
|
|
# First column should exist
|
|
assert b"Emil" in res.data
|
|
|