Compare commits

...

8 Commits

Author SHA1 Message Date
dgtlmoon
11dd28b115 Fixes for image 2026-01-15 13:44:40 +01:00
dgtlmoon
109bbaf144 Revert sub-process brotli saving because it could fork-bomb/use up too many system resources 2026-01-15 13:41:10 +01:00
dgtlmoon
4643082c5b i18n: Recompile zh_Hant_TW/LC_MESSAGES/messages.mo 2026-01-15 13:21:49 +01:00
滅ü
3b2b74e62d i18n: Update zh_Hant_TW translations (#3745) 2026-01-15 13:12:25 +01:00
dependabot[bot]
68354cf53d Update jsonschema requirement from ~=4.25 to ~=4.26 (#3743) 2026-01-15 13:03:16 +01:00
dgtlmoon
3e364e0eba Translations - ZH_Hant_TW - Fixing timeago string handling #3737
Some checks failed
Build and push containers / metadata (push) Has been cancelled
Build and push containers / build-push-containers (push) Has been cancelled
Publish Python 🐍distribution 📦 to PyPI and TestPyPI / Build distribution 📦 (push) Has been cancelled
Publish Python 🐍distribution 📦 to PyPI and TestPyPI / Test the built package works basically. (push) Has been cancelled
Publish Python 🐍distribution 📦 to PyPI and TestPyPI / Publish Python 🐍 distribution 📦 to PyPI (push) Has been cancelled
ChangeDetection.io Container Build Test / Build linux/amd64 (alpine) (push) Has been cancelled
ChangeDetection.io Container Build Test / Build linux/arm64 (alpine) (push) Has been cancelled
ChangeDetection.io Container Build Test / Build linux/amd64 (main) (push) Has been cancelled
ChangeDetection.io Container Build Test / Build linux/arm/v7 (main) (push) Has been cancelled
ChangeDetection.io Container Build Test / Build linux/arm/v8 (main) (push) Has been cancelled
ChangeDetection.io Container Build Test / Build linux/arm64 (main) (push) Has been cancelled
ChangeDetection.io App Test / lint-code (push) Has been cancelled
ChangeDetection.io App Test / test-application-3-10 (push) Has been cancelled
ChangeDetection.io App Test / test-application-3-11 (push) Has been cancelled
ChangeDetection.io App Test / test-application-3-12 (push) Has been cancelled
ChangeDetection.io App Test / test-application-3-13 (push) Has been cancelled
2026-01-15 12:24:53 +01:00
dgtlmoon
06ea29bfc7 Translations - Fixing zh_TW to zh_Hant_TW , adding tests #3737 (#3744) 2026-01-15 12:01:12 +01:00
dependabot[bot]
f4e178955c Bump pyppeteer-ng from 2.0.0rc10 to 2.0.0rc11 (#3742) 2026-01-15 10:31:42 +01:00
11 changed files with 614 additions and 1072 deletions

View File

@@ -41,9 +41,10 @@ from loguru import logger
#
# IMPLEMENTATION:
# 1. Explicit contexts everywhere (primary protection):
# - Watch.py: ctx = multiprocessing.get_context('spawn')
# - playwright.py: ctx = multiprocessing.get_context('spawn')
# - puppeteer.py: ctx = multiprocessing.get_context('spawn')
# - isolated_opencv.py: ctx = multiprocessing.get_context('spawn')
# - isolated_libvips.py: ctx = multiprocessing.get_context('spawn')
#
# 2. Global default (defense-in-depth, below):
# - Safety net if future code forgets explicit context

View File

@@ -9,6 +9,7 @@ import threading
import time
import timeago
from blinker import signal
from pathlib import Path
from changedetectionio.strtobool import strtobool
from threading import Event
@@ -84,6 +85,10 @@ app.config['NEW_VERSION_AVAILABLE'] = False
if os.getenv('FLASK_SERVER_NAME'):
app.config['SERVER_NAME'] = os.getenv('FLASK_SERVER_NAME')
# Babel/i18n configuration
app.config['BABEL_TRANSLATION_DIRECTORIES'] = str(Path(__file__).parent / 'translations')
app.config['BABEL_DEFAULT_LOCALE'] = 'en_GB'
#app.config["EXPLAIN_TEMPLATE_LOADING"] = True
@@ -395,13 +400,9 @@ def changedetection_app(config=None, datastore_o=None):
def get_locale():
# 1. Try to get locale from session (user explicitly selected)
if 'locale' in session:
locale = session['locale']
logger.trace(f"DEBUG: get_locale() returning from session: {locale}")
return locale
return session['locale']
# 2. Fall back to Accept-Language header
locale = request.accept_languages.best_match(language_codes)
logger.trace(f"DEBUG: get_locale() returning from Accept-Language: {locale}")
return locale
return request.accept_languages.best_match(language_codes)
# Initialize Babel with locale selector
babel = Babel(app, locale_selector=get_locale)
@@ -518,9 +519,20 @@ def changedetection_app(config=None, datastore_o=None):
@app.route('/set-language/<locale>')
def set_language(locale):
"""Set the user's preferred language in the session"""
if not request.cookies:
logger.error("Cannot set language without session cookie")
flash("Cannot set language without session cookie", 'error')
return redirect(url_for('watchlist.index'))
# Validate the locale against available languages
if locale in language_codes:
session['locale'] = locale
# CRITICAL: Flask-Babel caches the locale in the request context (ctx.babel_locale)
# We must refresh to clear this cache so the new locale takes effect immediately
# This is especially important for tests where multiple requests happen rapidly
from flask_babel import refresh
refresh()
else:
logger.error(f"Invalid locale {locale}, available: {language_codes}")

View File

@@ -29,7 +29,9 @@ def get_timeago_locale(flask_locale):
"""
locale_map = {
'zh': 'zh_CN', # Chinese Simplified
'zh_Hant_TW': 'zh_TW', # Flask-Babel normalizes zh_TW to zh_Hant_TW
# timeago library just hasn't been updated to use the more modern locale naming convention, before BCP 47 / RFC 5646.
'zh_TW': 'zh_TW', # Chinese Traditional (timeago uses zh_TW)
'zh_Hant_TW': 'zh_TW', # Flask-Babel normalizes zh_TW to zh_Hant_TW, map back to timeago's zh_TW
'pt': 'pt_PT', # Portuguese (Portugal)
'sv': 'sv_SE', # Swedish
'no': 'nb_NO', # Norwegian Bokmål
@@ -54,7 +56,7 @@ LANGUAGE_DATA = {
'it': {'flag': 'fi fi-it fis', 'name': 'Italiano'},
'ja': {'flag': 'fi fi-jp fis', 'name': '日本語'},
'zh': {'flag': 'fi fi-cn fis', 'name': '中文 (简体)'},
'zh_TW': {'flag': 'fi fi-tw fis', 'name': '繁體中文'},
'zh_Hant_TW': {'flag': 'fi fi-tw fis', 'name': '繁體中文'},
'ru': {'flag': 'fi fi-ru fis', 'name': 'Русский'},
'pl': {'flag': 'fi fi-pl fis', 'name': 'Polski'},
'nl': {'flag': 'fi fi-nl fis', 'name': 'Nederlands'},

View File

@@ -18,21 +18,31 @@ BROTLI_COMPRESS_SIZE_THRESHOLD = int(os.getenv('SNAPSHOT_BROTLI_COMPRESSION_THRE
minimum_seconds_recheck_time = int(os.getenv('MINIMUM_SECONDS_RECHECK_TIME', 3))
mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86400 * 7}
def _brotli_compress_worker(conn, filepath, mode=None):
def _brotli_save(contents, filepath, mode=None, fallback_uncompressed=False):
"""
Worker function to compress data with brotli in a separate process.
This isolates memory - when process exits, OS reclaims all memory.
Save compressed data using native brotli.
Testing shows no memory leak when using gc.collect() after compression.
Args:
conn: multiprocessing.Pipe connection to receive data
contents: data to compress (str or bytes)
filepath: destination file path
mode: brotli compression mode (e.g., brotli.MODE_TEXT)
fallback_uncompressed: if True, save uncompressed on failure; if False, raise exception
Returns:
str: actual filepath saved (may differ from input if fallback used)
Raises:
Exception: if compression fails and fallback_uncompressed is False
"""
import brotli
import gc
# Ensure contents are bytes
if isinstance(contents, str):
contents = contents.encode('utf-8')
try:
# Receive data from parent process via pipe (avoids pickle overhead)
contents = conn.recv()
logger.debug(f"Starting brotli compression of {len(contents)} bytes.")
if mode is not None:
@@ -43,111 +53,25 @@ def _brotli_compress_worker(conn, filepath, mode=None):
with open(filepath, 'wb') as f:
f.write(compressed_data)
# Send success status back
conn.send(True)
logger.debug(f"Finished brotli compression - From {len(contents)} to {len(compressed_data)} bytes.")
# No need for explicit cleanup - process exit frees all memory
except Exception as e:
logger.critical(f"Brotli compression worker failed: {e}")
conn.send(False)
finally:
conn.close()
# Force garbage collection to prevent memory buildup
gc.collect()
def _brotli_subprocess_save(contents, filepath, mode=None, timeout=30, fallback_uncompressed=False):
"""
Save compressed data using subprocess to isolate memory.
Uses Pipe to avoid pickle overhead for large data.
Args:
contents: data to compress (str or bytes)
filepath: destination file path
mode: brotli compression mode (e.g., brotli.MODE_TEXT)
timeout: subprocess timeout in seconds
fallback_uncompressed: if True, save uncompressed on failure; if False, raise exception
Returns:
str: actual filepath saved (may differ from input if fallback used)
Raises:
Exception: if compression fails and fallback_uncompressed is False
"""
import multiprocessing
import sys
# Ensure contents are bytes
if isinstance(contents, str):
contents = contents.encode('utf-8')
# Use explicit spawn context for thread safety (avoids fork() with multi-threaded parent)
# Always use spawn - consistent behavior in tests and production
ctx = multiprocessing.get_context('spawn')
parent_conn, child_conn = ctx.Pipe()
# Run compression in subprocess using spawn (not fork)
proc = ctx.Process(target=_brotli_compress_worker, args=(child_conn, filepath, mode))
# Windows-safe: Set daemon=False explicitly to avoid issues with process cleanup
proc.daemon = False
proc.start()
try:
# Send data to subprocess via pipe (avoids pickle)
parent_conn.send(contents)
# Wait for result with timeout
if parent_conn.poll(timeout):
success = parent_conn.recv()
else:
success = False
logger.warning(f"Brotli compression subprocess timed out after {timeout}s")
# Graceful termination with platform-aware cleanup
try:
proc.terminate()
except Exception as term_error:
logger.debug(f"Process termination issue (may be normal on Windows): {term_error}")
parent_conn.close()
proc.join(timeout=5)
# Force kill if still alive after graceful termination
if proc.is_alive():
try:
if sys.platform == 'win32':
# Windows: use kill() which is more forceful
proc.kill()
else:
# Unix: terminate() already sent SIGTERM, now try SIGKILL
proc.kill()
proc.join(timeout=2)
except Exception as kill_error:
logger.warning(f"Failed to kill brotli compression process: {kill_error}")
# Check if file was created successfully
if success and os.path.exists(filepath):
return filepath
return filepath
except Exception as e:
logger.error(f"Brotli compression error: {e}")
try:
parent_conn.close()
except:
pass
try:
proc.terminate()
proc.join(timeout=2)
except:
pass
# Compression failed
if fallback_uncompressed:
logger.warning(f"Brotli compression failed for {filepath}, saving uncompressed")
fallback_path = filepath.replace('.br', '')
with open(fallback_path, 'wb') as f:
f.write(contents)
return fallback_path
else:
raise Exception(f"Brotli compression subprocess failed for {filepath}")
# Compression failed
if fallback_uncompressed:
logger.warning(f"Brotli compression failed for {filepath}, saving uncompressed")
fallback_path = filepath.replace('.br', '')
with open(fallback_path, 'wb') as f:
f.write(contents)
return fallback_path
else:
raise Exception(f"Brotli compression failed for {filepath}: {e}")
class model(watch_base):
@@ -523,7 +447,7 @@ class model(watch_base):
if not os.path.exists(dest):
try:
actual_dest = _brotli_subprocess_save(contents, dest, mode=brotli.MODE_TEXT, fallback_uncompressed=True)
actual_dest = _brotli_save(contents, dest, mode=brotli.MODE_TEXT, fallback_uncompressed=True)
if actual_dest != dest:
snapshot_fname = os.path.basename(actual_dest)
except Exception as e:
@@ -949,13 +873,13 @@ class model(watch_base):
def save_last_text_fetched_before_filters(self, contents):
import brotli
filepath = os.path.join(self.watch_data_dir, 'last-fetched.br')
_brotli_subprocess_save(contents, filepath, mode=brotli.MODE_TEXT, fallback_uncompressed=False)
_brotli_save(contents, filepath, mode=brotli.MODE_TEXT, fallback_uncompressed=False)
def save_last_fetched_html(self, timestamp, contents):
self.ensure_data_dir_exists()
snapshot_fname = f"{timestamp}.html.br"
filepath = os.path.join(self.watch_data_dir, snapshot_fname)
_brotli_subprocess_save(contents, filepath, mode=None, fallback_uncompressed=True)
_brotli_save(contents, filepath, mode=None, fallback_uncompressed=True)
self._prune_last_fetched_html_snapshots()
def get_fetched_html(self, timestamp):

View File

@@ -13,14 +13,9 @@ Research: https://github.com/libvips/pyvips/issues/234
import multiprocessing
# CRITICAL: Use 'spawn' instead of 'fork' to avoid inheriting parent's
# CRITICAL: Use 'spawn' context instead of 'fork' to avoid inheriting parent's
# LibVIPS threading state which can cause hangs in gaussblur operations
# https://docs.python.org/3/library/multiprocessing.html#contexts-and-start-methods
try:
multiprocessing.set_start_method('spawn', force=False)
except RuntimeError:
# Already set, ignore
pass
def _worker_generate_diff(conn, img_bytes_from, img_bytes_to, threshold, blur_sigma, max_width, max_height):
@@ -95,9 +90,10 @@ def generate_diff_isolated(img_bytes_from, img_bytes_to, threshold, blur_sigma,
Returns:
bytes: JPEG diff image or None on failure
"""
parent_conn, child_conn = multiprocessing.Pipe()
ctx = multiprocessing.get_context('spawn')
parent_conn, child_conn = ctx.Pipe()
p = multiprocessing.Process(
p = ctx.Process(
target=_worker_generate_diff,
args=(child_conn, img_bytes_from, img_bytes_to, threshold, blur_sigma, max_width, max_height)
)
@@ -140,7 +136,8 @@ def calculate_change_percentage_isolated(img_bytes_from, img_bytes_to, threshold
Returns:
float: Change percentage
"""
parent_conn, child_conn = multiprocessing.Pipe()
ctx = multiprocessing.get_context('spawn')
parent_conn, child_conn = ctx.Pipe()
def _worker_calculate(conn):
try:
@@ -185,7 +182,7 @@ def calculate_change_percentage_isolated(img_bytes_from, img_bytes_to, threshold
finally:
conn.close()
p = multiprocessing.Process(target=_worker_calculate, args=(child_conn,))
p = ctx.Process(target=_worker_calculate, args=(child_conn,))
p.start()
result = 0.0
@@ -233,7 +230,8 @@ def compare_images_isolated(img_bytes_from, img_bytes_to, threshold, blur_sigma,
tuple: (changed_detected, change_percentage)
"""
print(f"[Parent] Starting compare_images_isolated subprocess", flush=True)
parent_conn, child_conn = multiprocessing.Pipe()
ctx = multiprocessing.get_context('spawn')
parent_conn, child_conn = ctx.Pipe()
def _worker_compare(conn):
try:
@@ -301,7 +299,7 @@ def compare_images_isolated(img_bytes_from, img_bytes_to, threshold, blur_sigma,
finally:
conn.close()
p = multiprocessing.Process(target=_worker_compare, args=(child_conn,))
p = ctx.Process(target=_worker_compare, args=(child_conn,))
print(f"[Parent] Starting subprocess (pid will be assigned)", flush=True)
p.start()
print(f"[Parent] Subprocess started (pid={p.pid}), waiting for result (30s timeout)", flush=True)

View File

@@ -1,5 +1,5 @@
<!DOCTYPE html>
<html lang="{{ get_locale() }}" data-darkmode="{{ get_darkmode_state() }}">
<html lang="{{ get_locale()|replace('_', '-') }}" data-darkmode="{{ get_darkmode_state() }}">
<head>
<meta charset="utf-8" >

View File

@@ -1,7 +1,71 @@
#!/usr/bin/env python3
from flask import url_for
from .util import live_server_setup
from .util import live_server_setup, wait_for_all_checks
def test_zh_TW(client, live_server, measure_memory_usage, datastore_path):
import time
test_url = url_for('test_endpoint', _external=True)
# Be sure we got a session cookie
res = client.get(url_for("watchlist.index"), follow_redirects=True)
res = client.get(
url_for("set_language", locale="zh_Hant_TW"), # Traditional
follow_redirects=True
)
# HTML follows BCP 47 language tag rules, not underscore-based locale formats.
assert b'<html lang="zh-Hant-TW"' in res.data
assert b'Cannot set language without session cookie' not in res.data
assert '選擇語言'.encode() in res.data
# Check second set works
res = client.get(
url_for("set_language", locale="en_GB"),
follow_redirects=True
)
assert b'Cannot set language without session cookie' not in res.data
res = client.get(url_for("watchlist.index"), follow_redirects=True)
assert b"Select Language" in res.data, "Second set of language worked"
# Check arbitration between zh_Hant_TW<->zh
res = client.get(
url_for("set_language", locale="zh"), # Simplified chinese
follow_redirects=True
)
res = client.get(url_for("watchlist.index"), follow_redirects=True)
assert "选择语言".encode() in res.data, "Simplified chinese worked and it means the flask-babel cache worked"
# timeago library just hasn't been updated to use the more modern locale naming convention, before BCP 47 / RFC 5646.
# The Python timeago library (https://github.com/hustcc/timeago) supports 48 locales but uses different naming conventions than Flask-Babel.
def test_zh_Hant_TW_timeago_integration():
"""Test that zh_Hant_TW mapping works and timeago renders Traditional Chinese correctly"""
import timeago
from datetime import datetime, timedelta
from changedetectionio.languages import get_timeago_locale
# 1. Test the mapping
mapped_locale = get_timeago_locale('zh_Hant_TW')
assert mapped_locale == 'zh_TW', "zh_Hant_TW should map to timeago's zh_TW"
assert get_timeago_locale('zh_TW') == 'zh_TW', "zh_TW should also map to zh_TW"
# 2. Test timeago library renders Traditional Chinese with the mapped locale
now = datetime.now()
# Test various time periods with Traditional Chinese strings
result_15s = timeago.format(now - timedelta(seconds=15), now, mapped_locale)
assert '秒前' in result_15s, f"Expected '秒前' in '{result_15s}'"
result_5m = timeago.format(now - timedelta(minutes=5), now, mapped_locale)
assert '分鐘前' in result_5m, f"Expected '分鐘前' in '{result_5m}'"
result_2h = timeago.format(now - timedelta(hours=2), now, mapped_locale)
assert '小時前' in result_2h, f"Expected '小時前' in '{result_2h}'"
result_3d = timeago.format(now - timedelta(days=3), now, mapped_locale)
assert '天前' in result_3d, f"Expected '天前' in '{result_3d}'"
def test_language_switching(client, live_server, measure_memory_usage, datastore_path):
@@ -13,6 +77,9 @@ def test_language_switching(client, live_server, measure_memory_usage, datastore
3. Switch back to English and verify English text appears
"""
# Establish session cookie
client.get(url_for("watchlist.index"), follow_redirects=True)
# Step 1: Set the language to Italian using the /set-language endpoint
res = client.get(
url_for("set_language", locale="it"),
@@ -61,6 +128,9 @@ def test_invalid_locale(client, live_server, measure_memory_usage, datastore_pat
The app should ignore invalid locales and continue working.
"""
# Establish session cookie
client.get(url_for("watchlist.index"), follow_redirects=True)
# First set to English
res = client.get(
url_for("set_language", locale="en"),
@@ -93,6 +163,9 @@ def test_language_persistence_in_session(client, live_server, measure_memory_usa
within the same session.
"""
# Establish session cookie
client.get(url_for("watchlist.index"), follow_redirects=True)
# Set language to Italian
res = client.get(
url_for("set_language", locale="it"),
@@ -119,6 +192,9 @@ def test_set_language_with_redirect(client, live_server, measure_memory_usage, d
"""
from flask import url_for
# Establish session cookie
client.get(url_for("watchlist.index"), follow_redirects=True)
# Set language with a redirect parameter (simulating language change from /settings)
res = client.get(
url_for("set_language", locale="de", redirect="/settings"),

View File

@@ -91,7 +91,7 @@ jq~=1.3; python_version >= "3.8" and sys_platform == "linux"
# playwright is installed at Dockerfile build time because it's not available on all platforms
pyppeteer-ng==2.0.0rc10
pyppeteer-ng==2.0.0rc11
pyppeteerstealth>=0.0.4
# Include pytest, so if theres a support issue we can ask them to run these tests on their setup
@@ -100,7 +100,7 @@ pytest-flask ~=1.3
pytest-mock ~=3.15
# Anything 4.0 and up but not 5.0
jsonschema ~= 4.25
jsonschema ~= 4.26
# OpenAPI validation support
openapi-core[flask] >= 0.19.0