mirror of
https://github.com/dgtlmoon/changedetection.io.git
synced 2026-01-23 07:30:21 +00:00
Compare commits
19 Commits
translatio
...
0.52.9
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
c22335ed01 | ||
|
|
0042f0c36a | ||
|
|
55e14cf394 | ||
|
|
308ccb5841 | ||
|
|
978e17acf6 | ||
|
|
73c29d1fa0 | ||
|
|
b3eb88b6d2 | ||
|
|
aa73ce2ee6 | ||
|
|
0cbf345e84 | ||
|
|
d65e08e7c8 | ||
|
|
10f233a939 | ||
|
|
52911d699f | ||
|
|
7e886e0c56 | ||
|
|
151e603af7 | ||
|
|
7311af4b58 | ||
|
|
af193e8d7a | ||
|
|
9e2acadb7e | ||
|
|
48da93b4ec | ||
|
|
0c1adc8906 |
21
.github/workflows/containers.yml
vendored
21
.github/workflows/containers.yml
vendored
@@ -15,7 +15,6 @@ on:
|
||||
push:
|
||||
branches:
|
||||
- master
|
||||
- dev
|
||||
|
||||
jobs:
|
||||
metadata:
|
||||
@@ -93,17 +92,28 @@ jobs:
|
||||
version: latest
|
||||
driver-opts: image=moby/buildkit:master
|
||||
|
||||
# dev branch -> :dev container tag
|
||||
# master branch -> :dev container tag
|
||||
- name: Docker meta :dev
|
||||
if: ${{ github.ref == 'refs/heads/master' && github.event_name != 'release' }}
|
||||
uses: docker/metadata-action@v5
|
||||
id: meta_dev
|
||||
with:
|
||||
images: |
|
||||
${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io
|
||||
ghcr.io/${{ github.repository }}
|
||||
tags: |
|
||||
type=raw,value=dev
|
||||
|
||||
- name: Build and push :dev
|
||||
id: docker_build
|
||||
if: ${{ github.ref == 'refs/heads/dev' }}
|
||||
if: ${{ github.ref == 'refs/heads/master' && github.event_name != 'release' }}
|
||||
uses: docker/build-push-action@v6
|
||||
with:
|
||||
context: ./
|
||||
file: ./Dockerfile
|
||||
push: true
|
||||
tags: |
|
||||
${{ secrets.DOCKER_HUB_USERNAME }}/changedetection.io:dev,ghcr.io/${{ github.repository }}:dev
|
||||
tags: ${{ steps.meta_dev.outputs.tags }}
|
||||
labels: ${{ steps.meta_dev.outputs.labels }}
|
||||
platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8
|
||||
cache-from: type=gha
|
||||
cache-to: type=gha,mode=max
|
||||
@@ -142,6 +152,7 @@ jobs:
|
||||
file: ./Dockerfile
|
||||
push: true
|
||||
tags: ${{ steps.meta.outputs.tags }}
|
||||
labels: ${{ steps.meta.outputs.labels }}
|
||||
platforms: linux/amd64,linux/arm64,linux/arm/v7,linux/arm/v8
|
||||
cache-from: type=gha
|
||||
cache-to: type=gha,mode=max
|
||||
|
||||
@@ -78,6 +78,12 @@ RUN --mount=type=cache,id=pip,sharing=locked,target=/tmp/pip-cache \
|
||||
# Final image stage
|
||||
FROM python:${PYTHON_VERSION}-slim-bookworm
|
||||
LABEL org.opencontainers.image.source="https://github.com/dgtlmoon/changedetection.io"
|
||||
LABEL org.opencontainers.image.url="https://changedetection.io"
|
||||
LABEL org.opencontainers.image.documentation="https://changedetection.io/tutorials"
|
||||
LABEL org.opencontainers.image.title="changedetection.io"
|
||||
LABEL org.opencontainers.image.description="Self-hosted web page change monitoring and notification service"
|
||||
LABEL org.opencontainers.image.licenses="Apache-2.0"
|
||||
LABEL org.opencontainers.image.vendor="changedetection.io"
|
||||
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends \
|
||||
libxslt1.1 \
|
||||
|
||||
@@ -16,6 +16,7 @@ recursive-include changedetectionio/widgets *
|
||||
prune changedetectionio/static/package-lock.json
|
||||
prune changedetectionio/static/styles/node_modules
|
||||
prune changedetectionio/static/styles/package-lock.json
|
||||
include changedetectionio/favicon_utils.py
|
||||
include changedetection.py
|
||||
include requirements.txt
|
||||
include README-pip.md
|
||||
|
||||
5
babel.cfg
Normal file
5
babel.cfg
Normal file
@@ -0,0 +1,5 @@
|
||||
[python: **.py]
|
||||
keywords = _:1,_l:1,gettext:1
|
||||
|
||||
[jinja2: **/templates/**.html]
|
||||
encoding = utf-8
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
# Read more https://github.com/dgtlmoon/changedetection.io/wiki
|
||||
# Semver means never use .01, or 00. Should be .1.
|
||||
__version__ = '0.52.6'
|
||||
__version__ = '0.52.9'
|
||||
|
||||
from changedetectionio.strtobool import strtobool
|
||||
from json.decoder import JSONDecodeError
|
||||
|
||||
@@ -2,6 +2,7 @@ import os
|
||||
import threading
|
||||
|
||||
from changedetectionio.validate_url import is_safe_valid_url
|
||||
from changedetectionio.favicon_utils import get_favicon_mime_type
|
||||
|
||||
from . import auth
|
||||
from changedetectionio import queuedWatchMetaData, strtobool
|
||||
@@ -68,13 +69,17 @@ class Watch(Resource):
|
||||
import time
|
||||
from copy import deepcopy
|
||||
watch = None
|
||||
for _ in range(20):
|
||||
# Retry up to 20 times if dict is being modified
|
||||
# With sleep(0), this is fast: ~200µs best case, ~20ms worst case under heavy load
|
||||
for attempt in range(20):
|
||||
try:
|
||||
watch = deepcopy(self.datastore.data['watching'].get(uuid))
|
||||
break
|
||||
except RuntimeError:
|
||||
# Incase dict changed, try again
|
||||
time.sleep(0.01)
|
||||
# Dict changed during deepcopy, retry after yielding to scheduler
|
||||
# sleep(0) releases GIL and yields - no fixed delay, just lets other threads run
|
||||
if attempt < 19: # Don't yield on last attempt
|
||||
time.sleep(0) # Yield to scheduler (microseconds, not milliseconds)
|
||||
|
||||
if not watch:
|
||||
abort(404, message='No watch exists with the UUID of {}'.format(uuid))
|
||||
@@ -126,17 +131,31 @@ class Watch(Resource):
|
||||
|
||||
if request.json.get('proxy'):
|
||||
plist = self.datastore.proxy_list
|
||||
if not request.json.get('proxy') in plist:
|
||||
return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
|
||||
if not plist or request.json.get('proxy') not in plist:
|
||||
proxy_list_str = ', '.join(plist) if plist else 'none configured'
|
||||
return f"Invalid proxy choice, currently supported proxies are '{proxy_list_str}'", 400
|
||||
|
||||
# Validate time_between_check when not using defaults
|
||||
validation_error = validate_time_between_check_required(request.json)
|
||||
if validation_error:
|
||||
return validation_error, 400
|
||||
|
||||
# XSS etc protection
|
||||
if request.json.get('url') and not is_safe_valid_url(request.json.get('url')):
|
||||
return "Invalid URL", 400
|
||||
# XSS etc protection - validate URL if it's being updated
|
||||
if 'url' in request.json:
|
||||
new_url = request.json.get('url')
|
||||
|
||||
# URL must be a non-empty string
|
||||
if new_url is None:
|
||||
return "URL cannot be null", 400
|
||||
|
||||
if not isinstance(new_url, str):
|
||||
return "URL must be a string", 400
|
||||
|
||||
if not new_url.strip():
|
||||
return "URL cannot be empty or whitespace only", 400
|
||||
|
||||
if not is_safe_valid_url(new_url.strip()):
|
||||
return "Invalid or unsupported URL format. URL must use http://, https://, or ftp:// protocol", 400
|
||||
|
||||
# Handle processor-config-* fields separately (save to JSON, not datastore)
|
||||
from changedetectionio import processors
|
||||
@@ -232,6 +251,10 @@ class WatchSingleHistory(Resource):
|
||||
if timestamp == 'latest':
|
||||
timestamp = list(watch.history.keys())[-1]
|
||||
|
||||
# Validate that the timestamp exists in history
|
||||
if timestamp not in watch.history:
|
||||
abort(404, message=f"No history snapshot found for timestamp '{timestamp}'")
|
||||
|
||||
if request.args.get('html'):
|
||||
content = watch.get_fetched_html(timestamp)
|
||||
if content:
|
||||
@@ -380,16 +403,9 @@ class WatchFavicon(Resource):
|
||||
|
||||
favicon_filename = watch.get_favicon_filename()
|
||||
if favicon_filename:
|
||||
try:
|
||||
import magic
|
||||
mime = magic.from_file(
|
||||
os.path.join(watch.watch_data_dir, favicon_filename),
|
||||
mime=True
|
||||
)
|
||||
except ImportError:
|
||||
# Fallback, no python-magic
|
||||
import mimetypes
|
||||
mime, encoding = mimetypes.guess_type(favicon_filename)
|
||||
# Use cached MIME type detection
|
||||
filepath = os.path.join(watch.watch_data_dir, favicon_filename)
|
||||
mime = get_favicon_mime_type(filepath)
|
||||
|
||||
response = make_response(send_from_directory(watch.watch_data_dir, favicon_filename))
|
||||
response.headers['Content-type'] = mime
|
||||
@@ -419,8 +435,9 @@ class CreateWatch(Resource):
|
||||
|
||||
if json_data.get('proxy'):
|
||||
plist = self.datastore.proxy_list
|
||||
if not json_data.get('proxy') in plist:
|
||||
return "Invalid proxy choice, currently supported proxies are '{}'".format(', '.join(plist)), 400
|
||||
if not plist or json_data.get('proxy') not in plist:
|
||||
proxy_list_str = ', '.join(plist) if plist else 'none configured'
|
||||
return f"Invalid proxy choice, currently supported proxies are '{proxy_list_str}'", 400
|
||||
|
||||
# Validate time_between_check when not using defaults
|
||||
validation_error = validate_time_between_check_required(json_data)
|
||||
|
||||
@@ -30,13 +30,23 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
|
||||
app: Flask application instance
|
||||
datastore: Application datastore
|
||||
executor: ThreadPoolExecutor for queue operations (optional)
|
||||
|
||||
Returns:
|
||||
"restart" if worker should restart, "shutdown" for clean exit
|
||||
"""
|
||||
# Set a descriptive name for this task
|
||||
task = asyncio.current_task()
|
||||
if task:
|
||||
task.set_name(f"async-worker-{worker_id}")
|
||||
|
||||
logger.info(f"Starting async worker {worker_id}")
|
||||
# Read restart policy from environment
|
||||
max_jobs = int(os.getenv("WORKER_MAX_JOBS", "10"))
|
||||
max_runtime_seconds = int(os.getenv("WORKER_MAX_RUNTIME", "3600")) # 1 hour default
|
||||
|
||||
jobs_processed = 0
|
||||
start_time = time.time()
|
||||
|
||||
logger.info(f"Starting async worker {worker_id} (max_jobs={max_jobs}, max_runtime={max_runtime_seconds}s)")
|
||||
|
||||
while not app.config.exit.is_set():
|
||||
update_handler = None
|
||||
@@ -51,7 +61,11 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
|
||||
)
|
||||
|
||||
except asyncio.TimeoutError:
|
||||
# No jobs available, continue loop
|
||||
# No jobs available - check if we should restart based on time while idle
|
||||
runtime = time.time() - start_time
|
||||
if runtime >= max_runtime_seconds:
|
||||
logger.info(f"Worker {worker_id} idle and reached max runtime ({runtime:.0f}s), restarting")
|
||||
return "restart"
|
||||
continue
|
||||
except Exception as e:
|
||||
# Handle expected Empty exception from queue timeout
|
||||
@@ -149,8 +163,10 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
|
||||
except ProcessorException as e:
|
||||
if e.screenshot:
|
||||
watch.save_screenshot(screenshot=e.screenshot)
|
||||
e.screenshot = None # Free memory immediately
|
||||
if e.xpath_data:
|
||||
watch.save_xpath_data(data=e.xpath_data)
|
||||
e.xpath_data = None # Free memory immediately
|
||||
datastore.update_watch(uuid=uuid, update_obj={'last_error': e.message})
|
||||
process_changedetection_results = False
|
||||
|
||||
@@ -170,9 +186,11 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
|
||||
|
||||
if e.screenshot:
|
||||
watch.save_screenshot(screenshot=e.screenshot, as_error=True)
|
||||
e.screenshot = None # Free memory immediately
|
||||
|
||||
if e.xpath_data:
|
||||
watch.save_xpath_data(data=e.xpath_data)
|
||||
e.xpath_data = None # Free memory immediately
|
||||
|
||||
process_changedetection_results = False
|
||||
|
||||
@@ -191,8 +209,10 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
|
||||
|
||||
if e.screenshot:
|
||||
watch.save_screenshot(screenshot=e.screenshot, as_error=True)
|
||||
e.screenshot = None # Free memory immediately
|
||||
if e.xpath_data:
|
||||
watch.save_xpath_data(data=e.xpath_data, as_error=True)
|
||||
e.xpath_data = None # Free memory immediately
|
||||
if e.page_text:
|
||||
watch.save_error_text(contents=e.page_text)
|
||||
|
||||
@@ -209,9 +229,11 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
|
||||
# Filter wasnt found, but we should still update the visual selector so that they can have a chance to set it up again
|
||||
if e.screenshot:
|
||||
watch.save_screenshot(screenshot=e.screenshot)
|
||||
e.screenshot = None # Free memory immediately
|
||||
|
||||
if e.xpath_data:
|
||||
watch.save_xpath_data(data=e.xpath_data)
|
||||
e.xpath_data = None # Free memory immediately
|
||||
|
||||
# Only when enabled, send the notification
|
||||
if watch.get('filter_failure_notification_send', False):
|
||||
@@ -303,6 +325,7 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
|
||||
err_text = "Error running JS Actions - Page request - "+e.message
|
||||
if e.screenshot:
|
||||
watch.save_screenshot(screenshot=e.screenshot, as_error=True)
|
||||
e.screenshot = None # Free memory immediately
|
||||
datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
|
||||
'last_check_status': e.status_code})
|
||||
process_changedetection_results = False
|
||||
@@ -314,6 +337,7 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
|
||||
|
||||
if e.screenshot:
|
||||
watch.save_screenshot(screenshot=e.screenshot, as_error=True)
|
||||
e.screenshot = None # Free memory immediately
|
||||
|
||||
datastore.update_watch(uuid=uuid, update_obj={'last_error': err_text,
|
||||
'last_check_status': e.status_code,
|
||||
@@ -355,9 +379,17 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
|
||||
if changed_detected or not watch.history_n:
|
||||
if update_handler.screenshot:
|
||||
watch.save_screenshot(screenshot=update_handler.screenshot)
|
||||
# Free screenshot memory immediately after saving
|
||||
update_handler.screenshot = None
|
||||
if hasattr(update_handler, 'fetcher') and hasattr(update_handler.fetcher, 'screenshot'):
|
||||
update_handler.fetcher.screenshot = None
|
||||
|
||||
if update_handler.xpath_data:
|
||||
watch.save_xpath_data(data=update_handler.xpath_data)
|
||||
# Free xpath data memory
|
||||
update_handler.xpath_data = None
|
||||
if hasattr(update_handler, 'fetcher') and hasattr(update_handler.fetcher, 'xpath_data'):
|
||||
update_handler.fetcher.xpath_data = None
|
||||
|
||||
# Ensure unique timestamp for history
|
||||
if watch.newest_history_key and int(fetch_start_time) == int(watch.newest_history_key):
|
||||
@@ -424,6 +456,20 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
|
||||
update_handler.fetcher.clear_content()
|
||||
logger.debug(f"Cleared fetcher content for UUID {uuid}")
|
||||
|
||||
# Explicitly delete update_handler to free all references
|
||||
if update_handler:
|
||||
del update_handler
|
||||
update_handler = None
|
||||
|
||||
# Force aggressive memory cleanup after clearing
|
||||
import gc
|
||||
gc.collect()
|
||||
try:
|
||||
import ctypes
|
||||
ctypes.CDLL('libc.so.6').malloc_trim(0)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Worker {worker_id} unexpected error processing {uuid}: {e}")
|
||||
logger.error(f"Worker {worker_id} traceback:", exc_info=True)
|
||||
@@ -488,6 +534,19 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
|
||||
# Small yield for normal completion
|
||||
await asyncio.sleep(0.01)
|
||||
|
||||
# Job completed - increment counter and check restart conditions
|
||||
jobs_processed += 1
|
||||
runtime = time.time() - start_time
|
||||
|
||||
# Check if we should restart (only when idle, between jobs)
|
||||
should_restart_jobs = jobs_processed >= max_jobs
|
||||
should_restart_time = runtime >= max_runtime_seconds
|
||||
|
||||
if should_restart_jobs or should_restart_time:
|
||||
reason = f"{jobs_processed} jobs" if should_restart_jobs else f"{runtime:.0f}s runtime"
|
||||
logger.info(f"Worker {worker_id} restarting after {reason} ({jobs_processed} jobs, {runtime:.0f}s runtime)")
|
||||
return "restart"
|
||||
|
||||
# Check if we should exit
|
||||
if app.config.exit.is_set():
|
||||
break
|
||||
@@ -495,10 +554,12 @@ async def async_update_worker(worker_id, q, notification_q, app, datastore, exec
|
||||
# Check if we're in pytest environment - if so, be more gentle with logging
|
||||
import sys
|
||||
in_pytest = "pytest" in sys.modules or "PYTEST_CURRENT_TEST" in os.environ
|
||||
|
||||
|
||||
if not in_pytest:
|
||||
logger.info(f"Worker {worker_id} shutting down")
|
||||
|
||||
return "shutdown"
|
||||
|
||||
|
||||
def cleanup_error_artifacts(uuid, datastore):
|
||||
"""Helper function to clean up error artifacts"""
|
||||
|
||||
@@ -25,9 +25,7 @@
|
||||
<li class="tab"><a href="#ui-options">{{ _('UI Options') }}</a></li>
|
||||
<li class="tab"><a href="#api">{{ _('API') }}</a></li>
|
||||
<li class="tab"><a href="#rss">{{ _('RSS') }}</a></li>
|
||||
<li class="pure-menu-item menu-collapsible {% if request.endpoint.startswith('backups.') %}active{% endif %}">
|
||||
<a href="{{ url_for('backups.index') }}" class="pure-menu-link">{{ _('Backups') }}</a>
|
||||
</li>
|
||||
<li class="tab"><a href="{{ url_for('backups.index') }}" class="pure-menu-link">{{ _('Backups') }}</a></li>
|
||||
<li class="tab"><a href="#timedate">{{ _('Time & Date') }}</a></li>
|
||||
<li class="tab"><a href="#proxies">{{ _('CAPTCHA & Proxies') }}</a></li>
|
||||
{% if plugin_tabs %}
|
||||
@@ -56,9 +54,9 @@
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
{{ render_field(form.application.form.filter_failure_notification_threshold_attempts, class="filter_failure_notification_threshold_attempts") }}
|
||||
<span class="pure-form-message-inline">After this many consecutive times that the CSS/xPath filter is missing, send a notification
|
||||
<span class="pure-form-message-inline">{{ _('After this many consecutive times that the CSS/xPath filter is missing, send a notification') }}
|
||||
<br>
|
||||
Set to <strong>0</strong> to disable
|
||||
{{ _('Set to') }} <strong>0</strong> {{ _('to disable') }}
|
||||
</span>
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
@@ -67,21 +65,20 @@
|
||||
{{ render_button(form.application.form.removepassword_button) }}
|
||||
{% else %}
|
||||
{{ render_field(form.application.form.password) }}
|
||||
<span class="pure-form-message-inline">Password protection for your changedetection.io application.</span>
|
||||
<span class="pure-form-message-inline">{{ _('Password protection for your changedetection.io application.') }}</span>
|
||||
{% endif %}
|
||||
{% else %}
|
||||
<span class="pure-form-message-inline">Password is locked.</span>
|
||||
<span class="pure-form-message-inline">{{ _('Password is locked.') }}</span>
|
||||
{% endif %}
|
||||
</div>
|
||||
|
||||
<div class="pure-control-group">
|
||||
{{ render_checkbox_field(form.application.form.shared_diff_access, class="shared_diff_access") }}
|
||||
<span class="pure-form-message-inline">Allow access to the watch change history page when password is enabled (Good for sharing the diff page)
|
||||
</span>
|
||||
<span class="pure-form-message-inline">{{ _('Allow access to the watch change history page when password is enabled (Good for sharing the diff page)') }}</span>
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
{{ render_checkbox_field(form.application.form.empty_pages_are_a_change) }}
|
||||
<span class="pure-form-message-inline">When a request returns no content, or the HTML does not contain any text, is this considered a change?</span>
|
||||
<span class="pure-form-message-inline">{{ _('When a request returns no content, or the HTML does not contain any text, is this considered a change?') }}</span>
|
||||
</div>
|
||||
</fieldset>
|
||||
</div>
|
||||
@@ -93,8 +90,8 @@
|
||||
<div class="pure-control-group" id="notification-base-url">
|
||||
{{ render_field(form.application.form.base_url, class="m-d") }}
|
||||
<span class="pure-form-message-inline">
|
||||
Base URL used for the <code>{{ '{{ base_url }}' }}</code> token in notification links.<br>
|
||||
Default value is the system environment variable '<code>BASE_URL</code>' - <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Configurable-BASE_URL-setting">read more here</a>.
|
||||
{{ _('Base URL used for the') }} <code>{{ '{{ base_url }}' }}</code> {{ _('token in notification links.') }}<br>
|
||||
{{ _('Default value is the system environment variable') }} '<code>BASE_URL</code>' - <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Configurable-BASE_URL-setting">{{ _('read more here') }}</a>.
|
||||
</span>
|
||||
</div>
|
||||
</div>
|
||||
@@ -103,15 +100,15 @@
|
||||
<div class="pure-control-group inline-radio">
|
||||
{{ render_field(form.application.form.fetch_backend, class="fetch-backend") }}
|
||||
<span class="pure-form-message-inline">
|
||||
<p>Use the <strong>Basic</strong> method (default) where your watched sites don't need Javascript to render.</p>
|
||||
<p>The <strong>Chrome/Javascript</strong> method requires a network connection to a running WebDriver+Chrome server, set by the ENV var 'WEBDRIVER_URL'. </p>
|
||||
<p>{{ _('Use the') }} <strong>{{ _('Basic') }}</strong> {{ _('method (default) where your watched sites don\'t need Javascript to render.') }}</p>
|
||||
<p>{{ _('The') }} <strong>{{ _('Chrome/Javascript') }}</strong> {{ _('method requires a network connection to a running WebDriver+Chrome server, set by the ENV var') }} 'WEBDRIVER_URL'. </p>
|
||||
</span>
|
||||
</div>
|
||||
<fieldset class="pure-group" id="webdriver-override-options" data-visible-for="application-fetch_backend=html_webdriver">
|
||||
<div class="pure-form-message-inline">
|
||||
<strong>If you're having trouble waiting for the page to be fully rendered (text missing etc), try increasing the 'wait' time here.</strong>
|
||||
<strong>{{ _('If you\'re having trouble waiting for the page to be fully rendered (text missing etc), try increasing the \'wait\' time here.') }}</strong>
|
||||
<br>
|
||||
This will wait <i>n</i> seconds before extracting the text.
|
||||
{{ _('This will wait') }} <i>n</i> {{ _('seconds before extracting the text.') }}
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
{{ render_field(form.application.form.webdriver_delay) }}
|
||||
@@ -120,27 +117,27 @@
|
||||
<div class="pure-control-group">
|
||||
{{ render_field(form.requests.form.workers) }}
|
||||
{% set worker_info = get_worker_status_info() %}
|
||||
<span class="pure-form-message-inline">Number of concurrent workers to process watches. More workers = faster processing but higher memory usage.<br>
|
||||
Currently running: <strong>{{ worker_info.count }}</strong> operational {{ worker_info.type }} workers{% if worker_info.active_workers > 0 %} ({{ worker_info.active_workers }} actively processing){% endif %}.</span>
|
||||
<span class="pure-form-message-inline">{{ _('Number of concurrent workers to process watches. More workers = faster processing but higher memory usage.') }}<br>
|
||||
{{ _('Currently running:') }} <strong>{{ worker_info.count }}</strong> {{ _('operational') }} {{ worker_info.type }} {{ _('workers') }}{% if worker_info.active_workers > 0 %} ({{ worker_info.active_workers }} {{ _('actively processing') }}){% endif %}.</span>
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
{{ render_field(form.requests.form.jitter_seconds, class="jitter_seconds") }}
|
||||
<span class="pure-form-message-inline">Example - 3 seconds random jitter could trigger up to 3 seconds earlier or up to 3 seconds later</span>
|
||||
<span class="pure-form-message-inline">{{ _('Example - 3 seconds random jitter could trigger up to 3 seconds earlier or up to 3 seconds later') }}</span>
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
{{ render_field(form.requests.form.timeout) }}
|
||||
<span class="pure-form-message-inline">For regular plain requests (not chrome based), maximum number of seconds until timeout, 1-999.</span><br>
|
||||
<span class="pure-form-message-inline">{{ _('For regular plain requests (not chrome based), maximum number of seconds until timeout, 1-999.') }}</span><br>
|
||||
</div>
|
||||
<div class="pure-control-group inline-radio">
|
||||
{{ render_field(form.requests.form.default_ua) }}
|
||||
<span class="pure-form-message-inline">
|
||||
Applied to all requests.<br><br>
|
||||
Note: Simply changing the User-Agent often does not defeat anti-robot technologies, it's important to consider <a href="https://changedetection.io/tutorial/what-are-main-types-anti-robot-mechanisms">all of the ways that the browser is detected</a>.
|
||||
{{ _('Applied to all requests.') }}<br><br>
|
||||
{{ _('Note: Simply changing the User-Agent often does not defeat anti-robot technologies, it\'s important to consider') }} <a href="https://changedetection.io/tutorial/what-are-main-types-anti-robot-mechanisms">{{ _('all of the ways that the browser is detected') }}</a>.
|
||||
</span>
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
<br>
|
||||
Tip: <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">Connect using Bright Data and Oxylabs Proxies, find out more here.</a>
|
||||
{{ _('Tip:') }} <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Proxy-configuration#brightdata-proxy-support">{{ _('Connect using Bright Data and Oxylabs Proxies, find out more here.') }}</a>
|
||||
|
||||
</div>
|
||||
</div>
|
||||
@@ -149,15 +146,15 @@
|
||||
|
||||
<fieldset class="pure-group">
|
||||
{{ render_checkbox_field(form.application.form.ignore_whitespace) }}
|
||||
<span class="pure-form-message-inline">Ignore whitespace, tabs and new-lines/line-feeds when considering if a change was detected.<br>
|
||||
<i>Note:</i> Changing this will change the status of your existing watches, possibly trigger alerts etc.
|
||||
<span class="pure-form-message-inline">{{ _('Ignore whitespace, tabs and new-lines/line-feeds when considering if a change was detected.') }}<br>
|
||||
<i>{{ _('Note:') }}</i> {{ _('Changing this will change the status of your existing watches, possibly trigger alerts etc.') }}
|
||||
</span>
|
||||
</fieldset>
|
||||
<fieldset class="pure-group">
|
||||
{{ render_checkbox_field(form.application.form.render_anchor_tag_content) }}
|
||||
<span class="pure-form-message-inline">Render anchor tag content, default disabled, when enabled renders links as <code>(link text)[https://somesite.com]</code>
|
||||
<span class="pure-form-message-inline">{{ _('Render anchor tag content, default disabled, when enabled renders links as') }} <code>(link text)[https://somesite.com]</code>
|
||||
<br>
|
||||
<i>Note:</i> Changing this could affect the content of your existing watches, possibly trigger alerts etc.
|
||||
<i>{{ _('Note:') }}</i> {{ _('Changing this could affect the content of your existing watches, possibly trigger alerts etc.') }}
|
||||
</span>
|
||||
</fieldset>
|
||||
<fieldset class="pure-group">
|
||||
@@ -168,9 +165,9 @@ nav
|
||||
//*[contains(text(), 'Advertisement')]") }}
|
||||
<span class="pure-form-message-inline">
|
||||
<ul>
|
||||
<li> Remove HTML element(s) by CSS and XPath selectors before text conversion. </li>
|
||||
<li> Don't paste HTML here, use only CSS and XPath selectors </li>
|
||||
<li> Add multiple elements, CSS or XPath selectors per line to ignore multiple parts of the HTML. </li>
|
||||
<li> {{ _('Remove HTML element(s) by CSS and XPath selectors before text conversion.') }} </li>
|
||||
<li> {{ _('Don\'t paste HTML here, use only CSS and XPath selectors') }} </li>
|
||||
<li> {{ _('Add multiple elements, CSS or XPath selectors per line to ignore multiple parts of the HTML.') }} </li>
|
||||
</ul>
|
||||
</span>
|
||||
</fieldset>
|
||||
@@ -178,50 +175,50 @@ nav
|
||||
{{ render_field(form.application.form.global_ignore_text, rows=5, placeholder="Some text to ignore in a line
|
||||
/some.regex\d{2}/ for case-INsensitive regex
|
||||
") }}
|
||||
<span class="pure-form-message-inline">Note: This is applied globally in addition to the per-watch rules.</span><br>
|
||||
<span class="pure-form-message-inline">{{ _('Note: This is applied globally in addition to the per-watch rules.') }}</span><br>
|
||||
<span class="pure-form-message-inline">
|
||||
<ul>
|
||||
<li>Matching text will be <strong>ignored</strong> in the text snapshot (you can still see it but it wont trigger a change)</li>
|
||||
<li>Note: This is applied globally in addition to the per-watch rules.</li>
|
||||
<li>Each line processed separately, any line matching will be ignored (removed before creating the checksum)</li>
|
||||
<li>Regular Expression support, wrap the entire line in forward slash <code>/regex/</code></li>
|
||||
<li>Changing this will affect the comparison checksum which may trigger an alert</li>
|
||||
<li>{{ _('Matching text will be') }} <strong>{{ _('ignored') }}</strong> {{ _('in the text snapshot (you can still see it but it wont trigger a change)') }}</li>
|
||||
<li>{{ _('Note: This is applied globally in addition to the per-watch rules.') }}</li>
|
||||
<li>{{ _('Each line processed separately, any line matching will be ignored (removed before creating the checksum)') }}</li>
|
||||
<li>{{ _('Regular Expression support, wrap the entire line in forward slash') }} <code>/regex/</code></li>
|
||||
<li>{{ _('Changing this will affect the comparison checksum which may trigger an alert') }}</li>
|
||||
</ul>
|
||||
</span>
|
||||
</fieldset>
|
||||
<fieldset class="pure-group">
|
||||
{{ render_checkbox_field(form.application.form.strip_ignored_lines) }}
|
||||
<span class="pure-form-message-inline">Remove any text that appears in the "Ignore text" from the output (otherwise its just ignored for change-detection)<br>
|
||||
<i>Note:</i> Changing this will change the status of your existing watches, possibly trigger alerts etc.
|
||||
<span class="pure-form-message-inline">{{ _('Remove any text that appears in the "Ignore text" from the output (otherwise its just ignored for change-detection)') }}<br>
|
||||
<i>{{ _('Note:') }}</i> {{ _('Changing this will change the status of your existing watches, possibly trigger alerts etc.') }}
|
||||
</span>
|
||||
</fieldset>
|
||||
</div>
|
||||
|
||||
<div class="tab-pane-inner" id="api">
|
||||
<h4>API Access</h4>
|
||||
<p>Drive your changedetection.io via API, More about <a href="https://changedetection.io/docs/api_v1/index.html">API access and examples here</a>.</p>
|
||||
<h4>{{ _('API Access') }}</h4>
|
||||
<p>{{ _('Drive your changedetection.io via API, More about') }} <a href="https://changedetection.io/docs/api_v1/index.html">{{ _('API access and examples here') }}</a>.</p>
|
||||
|
||||
<div class="pure-control-group">
|
||||
{{ render_checkbox_field(form.application.form.api_access_token_enabled) }}
|
||||
<div class="pure-form-message-inline">Restrict API access limit by using <code>x-api-key</code> header - required for the Chrome Extension to work</div><br>
|
||||
<div class="pure-form-message-inline"><br>API Key <span id="api-key">{{api_key}}</span>
|
||||
<span style="display:none;" id="api-key-copy" >copy</span>
|
||||
<div class="pure-form-message-inline">{{ _('Restrict API access limit by using') }} <code>x-api-key</code> {{ _('header - required for the Chrome Extension to work') }}</div><br>
|
||||
<div class="pure-form-message-inline"><br>{{ _('API Key') }} <span id="api-key">{{api_key}}</span>
|
||||
<span style="display:none;" id="api-key-copy" >{{ _('copy') }}</span>
|
||||
</div>
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
<a href="{{url_for('settings.settings_reset_api_key')}}" class="pure-button button-small button-cancel">Regenerate API key</a>
|
||||
<a href="{{url_for('settings.settings_reset_api_key')}}" class="pure-button button-small button-cancel">{{ _('Regenerate API key') }}</a>
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
<h4>Chrome Extension</h4>
|
||||
<p>Easily add any web-page to your changedetection.io installation from within Chrome.</p>
|
||||
<strong>Step 1</strong> Install the extension, <strong>Step 2</strong> Navigate to this page,
|
||||
<strong>Step 3</strong> Open the extension from the toolbar and click "<i>Sync API Access</i>"
|
||||
<h4>{{ _('Chrome Extension') }}</h4>
|
||||
<p>{{ _('Easily add any web-page to your changedetection.io installation from within Chrome.') }}</p>
|
||||
<strong>{{ _('Step 1') }}</strong> {{ _('Install the extension,') }} <strong>{{ _('Step 2') }}</strong> {{ _('Navigate to this page,') }}
|
||||
<strong>{{ _('Step 3') }}</strong> {{ _('Open the extension from the toolbar and click') }} "<i>{{ _('Sync API Access') }}</i>"
|
||||
<p>
|
||||
<a id="chrome-extension-link"
|
||||
title="Try our new Chrome Extension!"
|
||||
title="{{ _('Try our new Chrome Extension!') }}"
|
||||
href="https://chromewebstore.google.com/detail/changedetectionio-website/kefcfmgmlhmankjmnbijimhofdjekbop">
|
||||
<img alt="Chrome store icon" src="{{ url_for('static_content', group='images', filename='google-chrome-icon.png') }}" >
|
||||
Chrome Webstore
|
||||
<img alt="{{ _('Chrome store icon') }}" src="{{ url_for('static_content', group='images', filename='google-chrome-icon.png') }}" >
|
||||
{{ _('Chrome Webstore') }}
|
||||
</a>
|
||||
</p>
|
||||
</div>
|
||||
@@ -232,20 +229,20 @@ nav
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
{{ render_field(form.application.form.rss_diff_length) }}
|
||||
<span class="pure-form-message-inline">Maximum number of history snapshots to include in the watch specific RSS feed.</span>
|
||||
<span class="pure-form-message-inline">{{ _('Maximum number of history snapshots to include in the watch specific RSS feed.') }}</span>
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
{{ render_checkbox_field(form.application.form.rss_reader_mode) }}
|
||||
<span class="pure-form-message-inline">For watching other RSS feeds - When watching RSS/Atom feeds, convert them into clean text for better change detection.</span>
|
||||
<span class="pure-form-message-inline">{{ _('For watching other RSS feeds - When watching RSS/Atom feeds, convert them into clean text for better change detection.') }}</span>
|
||||
</div>
|
||||
<div class="pure-control-group grey-form-border">
|
||||
<div class="pure-control-group">
|
||||
{{ render_field(form.application.form.rss_content_format) }}
|
||||
<span class="pure-form-message-inline">Does your reader support HTML? Set it here</span>
|
||||
<span class="pure-form-message-inline">{{ _('Does your reader support HTML? Set it here') }}</span>
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
{{ render_field(form.application.form.rss_template_type) }}
|
||||
<span class="pure-form-message-inline">'System default' for the same template for all items, or re-use your "Notification Body" as the template.</span>
|
||||
<span class="pure-form-message-inline">{{ _('\'System default\' for the same template for all items, or re-use your "Notification Body" as the template.') }}</span>
|
||||
</div>
|
||||
<div>
|
||||
{{ render_field(form.application.form.rss_template_override) }}
|
||||
@@ -258,11 +255,11 @@ nav
|
||||
</div>
|
||||
<div class="tab-pane-inner" id="timedate">
|
||||
<div class="pure-control-group">
|
||||
Ensure the settings below are correct, they are used to manage the time schedule for checking your web page watches.
|
||||
{{ _('Ensure the settings below are correct, they are used to manage the time schedule for checking your web page watches.') }}
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
<p><strong>UTC Time & Date from Server:</strong> <span id="utc-time" >{{ utc_time }}</span></p>
|
||||
<p><strong>Local Time & Date in Browser:</strong> <span class="local-time" data-utc="{{ utc_time }}"></span></p>
|
||||
<p><strong>{{ _('UTC Time & Date from Server:') }}</strong> <span id="utc-time" >{{ utc_time }}</span></p>
|
||||
<p><strong>{{ _('Local Time & Date in Browser:') }}</strong> <span class="local-time" data-utc="{{ utc_time }}"></span></p>
|
||||
<div>
|
||||
{{ render_field(form.application.form.scheduler_timezone_default) }}
|
||||
<datalist id="timezones" style="display: none;">
|
||||
@@ -274,22 +271,22 @@ nav
|
||||
<div class="tab-pane-inner" id="ui-options">
|
||||
<div class="pure-control-group">
|
||||
{{ render_checkbox_field(form.application.form.ui.form.open_diff_in_new_tab, class="open_diff_in_new_tab") }}
|
||||
<span class="pure-form-message-inline">Enable this setting to open the diff page in a new tab. If disabled, the diff page will open in the current tab.</span>
|
||||
<span class="pure-form-message-inline">{{ _('Enable this setting to open the diff page in a new tab. If disabled, the diff page will open in the current tab.') }}</span>
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
{{ render_checkbox_field(form.application.form.ui.form.socket_io_enabled, class="socket_io_enabled") }}
|
||||
<span class="pure-form-message-inline">Realtime UI Updates Enabled - (Restart required if this is changed)</span>
|
||||
<span class="pure-form-message-inline">{{ _('Realtime UI Updates Enabled - (Restart required if this is changed)') }}</span>
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
{{ render_checkbox_field(form.application.form.ui.form.favicons_enabled, class="") }}
|
||||
<span class="pure-form-message-inline">Enable or Disable Favicons next to the watch list</span>
|
||||
<span class="pure-form-message-inline">{{ _('Enable or Disable Favicons next to the watch list') }}</span>
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
{{ render_checkbox_field(form.application.form.ui.use_page_title_in_list) }}
|
||||
</div>
|
||||
<div class="pure-control-group">
|
||||
{{ render_field(form.application.form.pager_size) }}
|
||||
<span class="pure-form-message-inline">Number of items per page in the watch overview list, 0 to disable.</span>
|
||||
<span class="pure-form-message-inline">{{ _('Number of items per page in the watch overview list, 0 to disable.') }}</span>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
@@ -337,18 +334,18 @@ nav
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<p><strong>Tip</strong>: "Residential" and "Mobile" proxy type can be more successfull than "Data Center" for blocked websites.</p>
|
||||
<p><strong>{{ _('Tip') }}</strong>: {{ _('"Residential" and "Mobile" proxy type can be more successfull than "Data Center" for blocked websites.') }}</p>
|
||||
|
||||
<div class="pure-control-group" id="extra-proxies-setting">
|
||||
{{ render_fieldlist_with_inline_errors(form.requests.form.extra_proxies) }}
|
||||
<span class="pure-form-message-inline">"Name" will be used for selecting the proxy in the Watch Edit settings</span><br>
|
||||
<span class="pure-form-message-inline">SOCKS5 proxies with authentication are only supported with 'plain requests' fetcher, for other fetchers you should whitelist the IP access instead</span>
|
||||
<span class="pure-form-message-inline">{{ _('"Name" will be used for selecting the proxy in the Watch Edit settings') }}</span><br>
|
||||
<span class="pure-form-message-inline">{{ _('SOCKS5 proxies with authentication are only supported with \'plain requests\' fetcher, for other fetchers you should whitelist the IP access instead') }}</span>
|
||||
{% if form.requests.proxy %}
|
||||
<div>
|
||||
<br>
|
||||
<div class="inline-radio">
|
||||
{{ render_field(form.requests.form.proxy, class="fetch-backend-proxy") }}
|
||||
<span class="pure-form-message-inline">Choose a default proxy for all watches</span>
|
||||
<span class="pure-form-message-inline">{{ _('Choose a default proxy for all watches') }}</span>
|
||||
</div>
|
||||
</div>
|
||||
{% endif %}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import time
|
||||
import threading
|
||||
from flask import Blueprint, request, redirect, url_for, flash, render_template, session
|
||||
from flask import Blueprint, request, redirect, url_for, flash, render_template, session, current_app
|
||||
from flask_babel import gettext
|
||||
from loguru import logger
|
||||
|
||||
@@ -404,4 +404,25 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, worker_handle
|
||||
|
||||
return redirect(url_for('watchlist.index'))
|
||||
|
||||
@ui_blueprint.route("/language/auto-detect", methods=['GET'])
|
||||
def delete_locale_language_session_var_if_it_exists():
|
||||
"""Clear the session locale preference to auto-detect from browser Accept-Language header"""
|
||||
if 'locale' in session:
|
||||
session.pop('locale', None)
|
||||
# Refresh Flask-Babel to clear cached locale
|
||||
from flask_babel import refresh
|
||||
refresh()
|
||||
flash(gettext("Language set to auto-detect from browser"))
|
||||
|
||||
# Check if there's a redirect parameter to return to the same page
|
||||
redirect_url = request.args.get('redirect')
|
||||
|
||||
# If redirect is provided and safe, use it
|
||||
from changedetectionio.is_safe_url import is_safe_url
|
||||
if redirect_url and is_safe_url(redirect_url, current_app):
|
||||
return redirect(redirect_url)
|
||||
|
||||
# Otherwise redirect to watchlist
|
||||
return redirect(url_for('watchlist.index'))
|
||||
|
||||
return ui_blueprint
|
||||
@@ -3,6 +3,7 @@ import time
|
||||
|
||||
from flask import Blueprint, request, make_response, render_template, redirect, url_for, flash, session
|
||||
from flask_paginate import Pagination, get_page_parameter
|
||||
from flask_babel import gettext as _
|
||||
|
||||
from changedetectionio import forms
|
||||
from changedetectionio import processors
|
||||
@@ -73,7 +74,10 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
|
||||
|
||||
pagination = Pagination(page=page,
|
||||
total=total_count,
|
||||
per_page=datastore.data['settings']['application'].get('pager_size', 50), css_framework="semantic")
|
||||
per_page=datastore.data['settings']['application'].get('pager_size', 50),
|
||||
css_framework="semantic",
|
||||
display_msg=_('displaying <b>{start} - {end}</b> {record_name} in total <b>{total}</b>'),
|
||||
record_name=_('records'))
|
||||
|
||||
sorted_tags = sorted(datastore.data['settings']['application'].get('tags').items(), key=lambda x: x[1]['title'])
|
||||
|
||||
|
||||
@@ -62,7 +62,7 @@ html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
|
||||
{{ render_nolabel_field(form.edit_and_watch_submit_button, title=_("Edit first then Watch") ) }}
|
||||
</div>
|
||||
<div id="watch-group-tag">
|
||||
{{ render_field(form.tags, value=active_tag.title if active_tag_uuid else '', placeholder="Watch group / tag", class="transparent-field") }}
|
||||
{{ render_field(form.tags, value=active_tag.title if active_tag_uuid else '', placeholder=_("Watch group / tag"), class="transparent-field") }}
|
||||
</div>
|
||||
<div id="quick-watch-processor-type">
|
||||
{{ render_simple_field(form.processor) }}
|
||||
|
||||
@@ -71,10 +71,19 @@ class Fetcher():
|
||||
supports_screenshots = False # Can capture page screenshots
|
||||
supports_xpath_element_data = False # Can extract xpath element positions/data for visual selector
|
||||
|
||||
# Screenshot element locking - prevents layout shifts during screenshot capture
|
||||
# Only needed for visual comparison (image_ssim_diff processor)
|
||||
# Locks element dimensions in the first viewport to prevent headers/ads from resizing
|
||||
lock_viewport_elements = False # Default: disabled for performance
|
||||
|
||||
def __init__(self, **kwargs):
|
||||
if kwargs and 'screenshot_format' in kwargs:
|
||||
self.screenshot_format = kwargs.get('screenshot_format')
|
||||
|
||||
# Allow lock_viewport_elements to be set via kwargs
|
||||
if kwargs and 'lock_viewport_elements' in kwargs:
|
||||
self.lock_viewport_elements = kwargs.get('lock_viewport_elements')
|
||||
|
||||
|
||||
@classmethod
|
||||
def get_status_icon_data(cls):
|
||||
|
||||
@@ -10,18 +10,20 @@ from changedetectionio.content_fetchers import SCREENSHOT_MAX_HEIGHT_DEFAULT, vi
|
||||
from changedetectionio.content_fetchers.base import Fetcher, manage_user_agent
|
||||
from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200ErrorCodeReceived, EmptyReply, ScreenshotUnavailable
|
||||
|
||||
async def capture_full_page_async(page, screenshot_format='JPEG'):
|
||||
async def capture_full_page_async(page, screenshot_format='JPEG', watch_uuid=None, lock_viewport_elements=False):
|
||||
import os
|
||||
import time
|
||||
import multiprocessing
|
||||
|
||||
start = time.time()
|
||||
watch_info = f"[{watch_uuid}] " if watch_uuid else ""
|
||||
|
||||
setup_start = time.time()
|
||||
page_height = await page.evaluate("document.documentElement.scrollHeight")
|
||||
page_width = await page.evaluate("document.documentElement.scrollWidth")
|
||||
original_viewport = page.viewport_size
|
||||
dimensions_time = time.time() - setup_start
|
||||
|
||||
logger.debug(f"Playwright viewport size {page.viewport_size} page height {page_height} page width {page_width}")
|
||||
logger.debug(f"{watch_info}Playwright viewport size {page.viewport_size} page height {page_height} page width {page_width} (got dimensions in {dimensions_time:.2f}s)")
|
||||
|
||||
# Use an approach similar to puppeteer: set a larger viewport and take screenshots in chunks
|
||||
step_size = SCREENSHOT_SIZE_STITCH_THRESHOLD # Size that won't cause GPU to overflow
|
||||
@@ -29,25 +31,31 @@ async def capture_full_page_async(page, screenshot_format='JPEG'):
|
||||
y = 0
|
||||
elements_locked = False
|
||||
|
||||
if page_height > page.viewport_size['height']:
|
||||
|
||||
# Lock all element dimensions BEFORE screenshot to prevent CSS media queries from resizing
|
||||
# capture_full_page_async() changes viewport height which triggers @media (min-height) rules
|
||||
# Only lock viewport elements if explicitly enabled (for image_ssim_diff processor)
|
||||
# This prevents headers/ads from resizing when viewport changes
|
||||
if lock_viewport_elements and page_height > page.viewport_size['height']:
|
||||
lock_start = time.time()
|
||||
lock_elements_js_path = os.path.join(os.path.dirname(__file__), 'res', 'lock-elements-sizing.js')
|
||||
with open(lock_elements_js_path, 'r') as f:
|
||||
lock_elements_js = f.read()
|
||||
await page.evaluate(lock_elements_js)
|
||||
elements_locked = True
|
||||
lock_time = time.time() - lock_start
|
||||
logger.debug(f"{watch_info}Viewport element locking enabled (took {lock_time:.2f}s)")
|
||||
|
||||
logger.debug("Element dimensions locked before screenshot capture")
|
||||
|
||||
if page_height > page.viewport_size['height']:
|
||||
if page_height < step_size:
|
||||
step_size = page_height # Incase page is bigger than default viewport but smaller than proposed step size
|
||||
logger.debug(f"Setting bigger viewport to step through large page width W{page.viewport_size['width']}xH{step_size} because page_height > viewport_size")
|
||||
viewport_start = time.time()
|
||||
logger.debug(f"{watch_info}Setting bigger viewport to step through large page width W{page.viewport_size['width']}xH{step_size} because page_height > viewport_size")
|
||||
# Set viewport to a larger size to capture more content at once
|
||||
await page.set_viewport_size({'width': page.viewport_size['width'], 'height': step_size})
|
||||
viewport_time = time.time() - viewport_start
|
||||
logger.debug(f"{watch_info}Viewport changed to {page.viewport_size['width']}x{step_size} (took {viewport_time:.2f}s)")
|
||||
|
||||
# Capture screenshots in chunks up to the max total height
|
||||
capture_start = time.time()
|
||||
chunk_times = []
|
||||
# Use PNG for better quality (no compression artifacts), JPEG for smaller size
|
||||
screenshot_type = screenshot_format.lower() if screenshot_format else 'jpeg'
|
||||
# PNG should use quality 100, JPEG uses configurable quality
|
||||
@@ -69,7 +77,11 @@ async def capture_full_page_async(page, screenshot_format='JPEG'):
|
||||
if screenshot_type == 'jpeg':
|
||||
screenshot_kwargs['quality'] = screenshot_quality
|
||||
|
||||
chunk_start = time.time()
|
||||
screenshot_chunks.append(await page.screenshot(**screenshot_kwargs))
|
||||
chunk_time = time.time() - chunk_start
|
||||
chunk_times.append(chunk_time)
|
||||
logger.debug(f"{watch_info}Chunk {len(screenshot_chunks)} captured in {chunk_time:.2f}s")
|
||||
y += step_size
|
||||
|
||||
# Restore original viewport size
|
||||
@@ -81,40 +93,54 @@ async def capture_full_page_async(page, screenshot_format='JPEG'):
|
||||
with open(unlock_elements_js_path, 'r') as f:
|
||||
unlock_elements_js = f.read()
|
||||
await page.evaluate(unlock_elements_js)
|
||||
logger.debug("Element dimensions unlocked after screenshot capture")
|
||||
logger.debug(f"{watch_info}Element dimensions unlocked after screenshot capture")
|
||||
|
||||
capture_time = time.time() - capture_start
|
||||
total_capture_time = sum(chunk_times)
|
||||
logger.debug(f"{watch_info}All {len(screenshot_chunks)} chunks captured in {capture_time:.2f}s (total chunk time: {total_capture_time:.2f}s)")
|
||||
|
||||
# If we have multiple chunks, stitch them together
|
||||
if len(screenshot_chunks) > 1:
|
||||
logger.debug(f"Screenshot stitching {len(screenshot_chunks)} chunks together")
|
||||
stitch_start = time.time()
|
||||
logger.debug(f"{watch_info}Starting stitching of {len(screenshot_chunks)} chunks")
|
||||
|
||||
# For small number of chunks (2-3), stitch inline to avoid multiprocessing overhead
|
||||
# Only use separate process for many chunks (4+) to avoid blocking the event loop
|
||||
if len(screenshot_chunks) <= 3:
|
||||
from changedetectionio.content_fetchers.screenshot_handler import stitch_images_inline
|
||||
screenshot = stitch_images_inline(screenshot_chunks, page_height, SCREENSHOT_MAX_TOTAL_HEIGHT)
|
||||
else:
|
||||
# Use separate process for many chunks to avoid blocking
|
||||
# Always use spawn for thread safety - consistent behavior in tests and production
|
||||
from changedetectionio.content_fetchers.screenshot_handler import stitch_images_worker
|
||||
ctx = multiprocessing.get_context('spawn')
|
||||
parent_conn, child_conn = ctx.Pipe()
|
||||
p = ctx.Process(target=stitch_images_worker, args=(child_conn, screenshot_chunks, page_height, SCREENSHOT_MAX_TOTAL_HEIGHT))
|
||||
p.start()
|
||||
screenshot = parent_conn.recv_bytes()
|
||||
p.join()
|
||||
# Explicit cleanup
|
||||
del p
|
||||
del parent_conn, child_conn
|
||||
# Always use spawn subprocess for ANY stitching (2+ chunks)
|
||||
# PIL allocates at C level and Python GC never releases it - subprocess exit forces OS to reclaim
|
||||
# Trade-off: 35MB resource_tracker vs 500MB+ PIL leak in main process
|
||||
from changedetectionio.content_fetchers.screenshot_handler import stitch_images_worker_raw_bytes
|
||||
import multiprocessing
|
||||
import struct
|
||||
|
||||
ctx = multiprocessing.get_context('spawn')
|
||||
parent_conn, child_conn = ctx.Pipe()
|
||||
p = ctx.Process(target=stitch_images_worker_raw_bytes, args=(child_conn, page_height, SCREENSHOT_MAX_TOTAL_HEIGHT))
|
||||
p.start()
|
||||
|
||||
# Send via raw bytes (no pickle)
|
||||
parent_conn.send_bytes(struct.pack('I', len(screenshot_chunks)))
|
||||
for chunk in screenshot_chunks:
|
||||
parent_conn.send_bytes(chunk)
|
||||
|
||||
screenshot = parent_conn.recv_bytes()
|
||||
p.join()
|
||||
|
||||
parent_conn.close()
|
||||
child_conn.close()
|
||||
del p, parent_conn, child_conn
|
||||
|
||||
stitch_time = time.time() - stitch_start
|
||||
total_time = time.time() - start
|
||||
setup_time = total_time - capture_time - stitch_time
|
||||
logger.debug(
|
||||
f"Screenshot (chunked/stitched) - Page height: {page_height} Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT} - Stitched together in {time.time() - start:.2f}s")
|
||||
# Explicit cleanup
|
||||
del screenshot_chunks
|
||||
screenshot_chunks = None
|
||||
f"{watch_info}Screenshot complete - Page height: {page_height}px, Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT}px | "
|
||||
f"Setup: {setup_time:.2f}s, Capture: {capture_time:.2f}s, Stitching: {stitch_time:.2f}s, Total: {total_time:.2f}s")
|
||||
return screenshot
|
||||
|
||||
total_time = time.time() - start
|
||||
setup_time = total_time - capture_time
|
||||
logger.debug(
|
||||
f"Screenshot Page height: {page_height} Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT} - Stitched together in {time.time() - start:.2f}s")
|
||||
f"{watch_info}Screenshot complete - Page height: {page_height}px, Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT}px | "
|
||||
f"Setup: {setup_time:.2f}s, Single chunk: {capture_time:.2f}s, Total: {total_time:.2f}s")
|
||||
|
||||
return screenshot_chunks[0]
|
||||
|
||||
@@ -184,7 +210,8 @@ class fetcher(Fetcher):
|
||||
|
||||
async def screenshot_step(self, step_n=''):
|
||||
super().screenshot_step(step_n=step_n)
|
||||
screenshot = await capture_full_page_async(page=self.page, screenshot_format=self.screenshot_format)
|
||||
watch_uuid = getattr(self, 'watch_uuid', None)
|
||||
screenshot = await capture_full_page_async(page=self.page, screenshot_format=self.screenshot_format, watch_uuid=watch_uuid, lock_viewport_elements=self.lock_viewport_elements)
|
||||
|
||||
# Request GC immediately after screenshot to free memory
|
||||
# Screenshots can be large and browser steps take many of them
|
||||
@@ -233,6 +260,7 @@ class fetcher(Fetcher):
|
||||
import playwright._impl._errors
|
||||
import time
|
||||
self.delete_browser_steps_screenshots()
|
||||
self.watch_uuid = watch_uuid # Store for use in screenshot_step
|
||||
response = None
|
||||
|
||||
async with async_playwright() as p:
|
||||
@@ -318,7 +346,7 @@ class fetcher(Fetcher):
|
||||
logger.error(f"Error fetching FavIcon info {str(e)}, continuing.")
|
||||
|
||||
if self.status_code != 200 and not ignore_status_codes:
|
||||
screenshot = await capture_full_page_async(self.page, screenshot_format=self.screenshot_format)
|
||||
screenshot = await capture_full_page_async(self.page, screenshot_format=self.screenshot_format, watch_uuid=watch_uuid, lock_viewport_elements=self.lock_viewport_elements)
|
||||
# Cleanup before raising to prevent memory leak
|
||||
await self.page.close()
|
||||
await context.close()
|
||||
@@ -374,7 +402,17 @@ class fetcher(Fetcher):
|
||||
# which will significantly increase the IO size between the server and client, it's recommended to use the lowest
|
||||
# acceptable screenshot quality here
|
||||
# The actual screenshot - this always base64 and needs decoding! horrible! huge CPU usage
|
||||
self.screenshot = await capture_full_page_async(page=self.page, screenshot_format=self.screenshot_format)
|
||||
self.screenshot = await capture_full_page_async(page=self.page, screenshot_format=self.screenshot_format, watch_uuid=watch_uuid, lock_viewport_elements=self.lock_viewport_elements)
|
||||
|
||||
# Force aggressive memory cleanup - screenshots are large and base64 decode creates temporary buffers
|
||||
await self.page.request_gc()
|
||||
gc.collect()
|
||||
# Release C-level memory from base64 decode back to OS
|
||||
try:
|
||||
import ctypes
|
||||
ctypes.CDLL('libc.so.6').malloc_trim(0)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
except ScreenshotUnavailable:
|
||||
# Re-raise screenshot unavailable exceptions
|
||||
|
||||
@@ -20,18 +20,20 @@ from changedetectionio.content_fetchers.exceptions import PageUnloadable, Non200
|
||||
# Screenshots also travel via the ws:// (websocket) meaning that the binary data is base64 encoded
|
||||
# which will significantly increase the IO size between the server and client, it's recommended to use the lowest
|
||||
# acceptable screenshot quality here
|
||||
async def capture_full_page(page, screenshot_format='JPEG'):
|
||||
async def capture_full_page(page, screenshot_format='JPEG', watch_uuid=None, lock_viewport_elements=False):
|
||||
import os
|
||||
import time
|
||||
import multiprocessing
|
||||
|
||||
start = time.time()
|
||||
watch_info = f"[{watch_uuid}] " if watch_uuid else ""
|
||||
|
||||
setup_start = time.time()
|
||||
page_height = await page.evaluate("document.documentElement.scrollHeight")
|
||||
page_width = await page.evaluate("document.documentElement.scrollWidth")
|
||||
original_viewport = page.viewport
|
||||
dimensions_time = time.time() - setup_start
|
||||
|
||||
logger.debug(f"Puppeteer viewport size {page.viewport} page height {page_height} page width {page_width}")
|
||||
logger.debug(f"{watch_info}Puppeteer viewport size {page.viewport} page height {page_height} page width {page_width} (got dimensions in {dimensions_time:.2f}s)")
|
||||
|
||||
# Bug 3 in Playwright screenshot handling
|
||||
# Some bug where it gives the wrong screenshot size, but making a request with the clip set first seems to solve it
|
||||
@@ -50,20 +52,35 @@ async def capture_full_page(page, screenshot_format='JPEG'):
|
||||
screenshot_chunks = []
|
||||
y = 0
|
||||
elements_locked = False
|
||||
if page_height > page.viewport['height']:
|
||||
# Lock all element dimensions BEFORE screenshot to prevent CSS media queries from resizing
|
||||
# capture_full_page() changes viewport height which triggers @media (min-height) rules
|
||||
|
||||
# Only lock viewport elements if explicitly enabled (for image_ssim_diff processor)
|
||||
# This prevents headers/ads from resizing when viewport changes
|
||||
if lock_viewport_elements and page_height > page.viewport['height']:
|
||||
lock_start = time.time()
|
||||
lock_elements_js_path = os.path.join(os.path.dirname(__file__), 'res', 'lock-elements-sizing.js')
|
||||
file_read_start = time.time()
|
||||
with open(lock_elements_js_path, 'r') as f:
|
||||
lock_elements_js = f.read()
|
||||
await page.evaluate(lock_elements_js)
|
||||
elements_locked = True
|
||||
logger.debug("Element dimensions locked before screenshot capture")
|
||||
file_read_time = time.time() - file_read_start
|
||||
|
||||
evaluate_start = time.time()
|
||||
await page.evaluate(lock_elements_js)
|
||||
evaluate_time = time.time() - evaluate_start
|
||||
|
||||
elements_locked = True
|
||||
lock_time = time.time() - lock_start
|
||||
logger.debug(f"{watch_info}Viewport element locking enabled - File read: {file_read_time:.3f}s, Browser evaluate: {evaluate_time:.2f}s, Total: {lock_time:.2f}s")
|
||||
|
||||
if page_height > page.viewport['height']:
|
||||
if page_height < step_size:
|
||||
step_size = page_height # Incase page is bigger than default viewport but smaller than proposed step size
|
||||
viewport_start = time.time()
|
||||
await page.setViewport({'width': page.viewport['width'], 'height': step_size})
|
||||
viewport_time = time.time() - viewport_start
|
||||
logger.debug(f"{watch_info}Viewport changed to {page.viewport['width']}x{step_size} (took {viewport_time:.2f}s)")
|
||||
|
||||
capture_start = time.time()
|
||||
chunk_times = []
|
||||
while y < min(page_height, SCREENSHOT_MAX_TOTAL_HEIGHT):
|
||||
# better than scrollTo incase they override it in the page
|
||||
await page.evaluate(
|
||||
@@ -82,7 +99,11 @@ async def capture_full_page(page, screenshot_format='JPEG'):
|
||||
if screenshot_type == 'jpeg':
|
||||
screenshot_kwargs['quality'] = screenshot_quality
|
||||
|
||||
chunk_start = time.time()
|
||||
screenshot_chunks.append(await page.screenshot(**screenshot_kwargs))
|
||||
chunk_time = time.time() - chunk_start
|
||||
chunk_times.append(chunk_time)
|
||||
logger.debug(f"{watch_info}Chunk {len(screenshot_chunks)} captured in {chunk_time:.2f}s")
|
||||
y += step_size
|
||||
|
||||
await page.setViewport({'width': original_viewport['width'], 'height': original_viewport['height']})
|
||||
@@ -93,26 +114,53 @@ async def capture_full_page(page, screenshot_format='JPEG'):
|
||||
with open(unlock_elements_js_path, 'r') as f:
|
||||
unlock_elements_js = f.read()
|
||||
await page.evaluate(unlock_elements_js)
|
||||
logger.debug("Element dimensions unlocked after screenshot capture")
|
||||
logger.debug(f"{watch_info}Element dimensions unlocked after screenshot capture")
|
||||
|
||||
capture_time = time.time() - capture_start
|
||||
total_capture_time = sum(chunk_times)
|
||||
logger.debug(f"{watch_info}All {len(screenshot_chunks)} chunks captured in {capture_time:.2f}s (total chunk time: {total_capture_time:.2f}s)")
|
||||
|
||||
if len(screenshot_chunks) > 1:
|
||||
# Always use spawn for thread safety - consistent behavior in tests and production
|
||||
from changedetectionio.content_fetchers.screenshot_handler import stitch_images_worker
|
||||
logger.debug(f"Screenshot stitching {len(screenshot_chunks)} chunks together")
|
||||
stitch_start = time.time()
|
||||
logger.debug(f"{watch_info}Starting stitching of {len(screenshot_chunks)} chunks")
|
||||
|
||||
# Always use spawn subprocess for ANY stitching (2+ chunks)
|
||||
# PIL allocates at C level and Python GC never releases it - subprocess exit forces OS to reclaim
|
||||
# Trade-off: 35MB resource_tracker vs 500MB+ PIL leak in main process
|
||||
from changedetectionio.content_fetchers.screenshot_handler import stitch_images_worker_raw_bytes
|
||||
import multiprocessing
|
||||
import struct
|
||||
|
||||
ctx = multiprocessing.get_context('spawn')
|
||||
parent_conn, child_conn = ctx.Pipe()
|
||||
p = ctx.Process(target=stitch_images_worker, args=(child_conn, screenshot_chunks, page_height, SCREENSHOT_MAX_TOTAL_HEIGHT))
|
||||
p = ctx.Process(target=stitch_images_worker_raw_bytes, args=(child_conn, page_height, SCREENSHOT_MAX_TOTAL_HEIGHT))
|
||||
p.start()
|
||||
|
||||
# Send via raw bytes (no pickle)
|
||||
parent_conn.send_bytes(struct.pack('I', len(screenshot_chunks)))
|
||||
for chunk in screenshot_chunks:
|
||||
parent_conn.send_bytes(chunk)
|
||||
|
||||
screenshot = parent_conn.recv_bytes()
|
||||
p.join()
|
||||
logger.debug(
|
||||
f"Screenshot (chunked/stitched) - Page height: {page_height} Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT} - Stitched together in {time.time() - start:.2f}s")
|
||||
|
||||
screenshot_chunks = None
|
||||
parent_conn.close()
|
||||
child_conn.close()
|
||||
del p, parent_conn, child_conn
|
||||
|
||||
stitch_time = time.time() - stitch_start
|
||||
total_time = time.time() - start
|
||||
setup_time = total_time - capture_time - stitch_time
|
||||
logger.debug(
|
||||
f"{watch_info}Screenshot complete - Page height: {page_height}px, Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT}px | "
|
||||
f"Setup: {setup_time:.2f}s, Capture: {capture_time:.2f}s, Stitching: {stitch_time:.2f}s, Total: {total_time:.2f}s")
|
||||
return screenshot
|
||||
|
||||
total_time = time.time() - start
|
||||
setup_time = total_time - capture_time
|
||||
logger.debug(
|
||||
f"Screenshot Page height: {page_height} Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT} - Stitched together in {time.time() - start:.2f}s")
|
||||
f"{watch_info}Screenshot complete - Page height: {page_height}px, Capture height: {SCREENSHOT_MAX_TOTAL_HEIGHT}px | "
|
||||
f"Setup: {setup_time:.2f}s, Single chunk: {capture_time:.2f}s, Total: {total_time:.2f}s")
|
||||
return screenshot_chunks[0]
|
||||
|
||||
|
||||
@@ -357,7 +405,7 @@ class fetcher(Fetcher):
|
||||
logger.error(f"Error fetching FavIcon info {str(e)}, continuing.")
|
||||
|
||||
if self.status_code != 200 and not ignore_status_codes:
|
||||
screenshot = await capture_full_page(page=self.page, screenshot_format=self.screenshot_format)
|
||||
screenshot = await capture_full_page(page=self.page, screenshot_format=self.screenshot_format, watch_uuid=watch_uuid, lock_viewport_elements=self.lock_viewport_elements)
|
||||
|
||||
raise Non200ErrorCodeReceived(url=url, status_code=self.status_code, screenshot=screenshot)
|
||||
|
||||
@@ -387,7 +435,17 @@ class fetcher(Fetcher):
|
||||
|
||||
# Now take screenshot (scrolling may trigger layout changes, but measurements are already captured)
|
||||
logger.debug(f"Screenshot format {self.screenshot_format}")
|
||||
self.screenshot = await capture_full_page(page=self.page, screenshot_format=self.screenshot_format)
|
||||
self.screenshot = await capture_full_page(page=self.page, screenshot_format=self.screenshot_format, watch_uuid=watch_uuid, lock_viewport_elements=self.lock_viewport_elements)
|
||||
|
||||
# Force aggressive memory cleanup - pyppeteer base64 decode creates temporary buffers
|
||||
import gc
|
||||
gc.collect()
|
||||
# Release C-level memory from base64 decode back to OS
|
||||
try:
|
||||
import ctypes
|
||||
ctypes.CDLL('libc.so.6').malloc_trim(0)
|
||||
except Exception:
|
||||
pass
|
||||
self.xpath_data = await self.page.evaluate(XPATH_ELEMENT_JS, {
|
||||
"visualselector_xpath_selectors": visualselector_xpath_selectors,
|
||||
"max_height": MAX_TOTAL_HEIGHT
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
/**
|
||||
* Lock Element Dimensions for Screenshot Capture
|
||||
* Lock Element Dimensions for Screenshot Capture (First Viewport Only)
|
||||
*
|
||||
* THE PROBLEM:
|
||||
* When taking full-page screenshots of tall pages, Chrome/Puppeteer/Playwright need to:
|
||||
@@ -10,40 +10,31 @@
|
||||
* However, changing the viewport height triggers CSS media queries like:
|
||||
* @media (min-height: 860px) { .ad { height: 250px; } }
|
||||
*
|
||||
* This causes elements (especially ads) to resize during screenshot capture, creating a mismatch:
|
||||
* - Screenshot shows element at NEW size (after media query triggered)
|
||||
* - xpath element coordinates measured at OLD size (before viewport change)
|
||||
* - Visual selector overlays don't align with screenshot
|
||||
*
|
||||
* EXAMPLE BUG:
|
||||
* - Initial viewport: 1280x800, ad height: 138px, article position: 279px ✓
|
||||
* - Viewport changes to 1280x3809 for screenshot
|
||||
* - Media query triggers: ad expands to 250px
|
||||
* - All content below shifts down by 112px (250-138)
|
||||
* - Article now at position: 391px (279+112)
|
||||
* - But xpath data says 279px → 112px mismatch! ✗
|
||||
* This causes elements (especially ads/headers) to resize during screenshot capture.
|
||||
*
|
||||
* THE SOLUTION:
|
||||
* Before changing viewport, lock ALL element dimensions with !important inline styles.
|
||||
* Inline styles with !important override media query CSS, preventing layout changes.
|
||||
* Lock element dimensions in the FIRST VIEWPORT ONLY with !important inline styles.
|
||||
* This prevents headers, navigation, and top ads from resizing when viewport changes.
|
||||
* We only lock the visible portion because:
|
||||
* - Most layout shifts happen in headers/navbars/top ads
|
||||
* - Locking only visible elements is 100x+ faster (100-200 elements vs 10,000+)
|
||||
* - Below-fold content shifts don't affect visual comparison accuracy
|
||||
*
|
||||
* WHAT THIS SCRIPT DOES:
|
||||
* 1. Iterates through every element on the page
|
||||
* 2. Captures current computed dimensions (width, height)
|
||||
* 3. Sets inline styles with !important to freeze those dimensions
|
||||
* 1. Gets current viewport height
|
||||
* 2. Finds elements within first viewport (top of page to bottom of screen)
|
||||
* 3. Locks their dimensions with !important inline styles
|
||||
* 4. Disables ResizeObserver API (for JS-based resizing)
|
||||
* 5. When viewport changes for screenshot, media queries can't resize anything
|
||||
* 6. Layout remains consistent → xpath coordinates match screenshot ✓
|
||||
*
|
||||
* USAGE:
|
||||
* Execute this script BEFORE calling capture_full_page() / screenshot functions.
|
||||
* The page must be fully loaded and settled at its initial viewport size.
|
||||
* No need to restore state afterward - page is closed after screenshot.
|
||||
* Only enabled for image_ssim_diff processor (visual comparison).
|
||||
* Default: OFF for performance.
|
||||
*
|
||||
* PERFORMANCE:
|
||||
* - Iterates all DOM elements (can be 1000s on complex pages)
|
||||
* - Typically completes in 50-200ms
|
||||
* - One-time cost before screenshot, well worth it for coordinate accuracy
|
||||
* - Only processes 100-300 elements (first viewport) vs 10,000+ (entire page)
|
||||
* - Typically completes in 10-50ms
|
||||
* - 100x+ faster than locking entire page
|
||||
*
|
||||
* @see https://github.com/dgtlmoon/changedetection.io/issues/XXXX
|
||||
*/
|
||||
@@ -52,11 +43,34 @@
|
||||
// Store original styles in a global WeakMap for later restoration
|
||||
window.__elementSizingRestore = new WeakMap();
|
||||
|
||||
// Lock ALL element dimensions to prevent media query layout changes
|
||||
document.querySelectorAll('*').forEach(el => {
|
||||
const computed = window.getComputedStyle(el);
|
||||
const rect = el.getBoundingClientRect();
|
||||
const start = performance.now();
|
||||
|
||||
// Get current viewport height (visible portion of page)
|
||||
const viewportHeight = window.innerHeight;
|
||||
|
||||
// Get all elements and filter to FIRST VIEWPORT ONLY
|
||||
// This dramatically reduces elements to process (100-300 vs 10,000+)
|
||||
const allElements = Array.from(document.querySelectorAll('*'));
|
||||
|
||||
// BATCH READ PHASE: Get bounding rects and filter to viewport
|
||||
const measurements = allElements.map(el => {
|
||||
const rect = el.getBoundingClientRect();
|
||||
const computed = window.getComputedStyle(el);
|
||||
|
||||
// Only lock elements in the first viewport (visible on initial page load)
|
||||
// rect.top < viewportHeight means element starts within visible area
|
||||
const inViewport = rect.top < viewportHeight && rect.top >= 0;
|
||||
const hasSize = rect.height > 0 && rect.width > 0;
|
||||
|
||||
return inViewport && hasSize ? { el, computed, rect } : null;
|
||||
}).filter(Boolean); // Remove null entries
|
||||
|
||||
const elapsed = performance.now() - start;
|
||||
console.log(`Locked first viewport elements: ${measurements.length} of ${allElements.length} total elements (viewport height: ${viewportHeight}px, took ${elapsed.toFixed(0)}ms)`);
|
||||
|
||||
// BATCH WRITE PHASE: Apply all inline styles without triggering layout
|
||||
// No interleaved reads means browser can optimize style application
|
||||
measurements.forEach(({el, computed, rect}) => {
|
||||
// Save original inline style values BEFORE locking
|
||||
const properties = ['height', 'min-height', 'max-height', 'width', 'min-width', 'max-width'];
|
||||
const originalStyles = {};
|
||||
@@ -89,5 +103,5 @@
|
||||
disconnect() {}
|
||||
};
|
||||
|
||||
console.log('✓ Element dimensions locked to prevent media query changes during screenshot');
|
||||
console.log(`✓ Element dimensions locked (${measurements.length} elements) to prevent media query changes during screenshot`);
|
||||
})();
|
||||
|
||||
@@ -8,92 +8,42 @@ from loguru import logger
|
||||
|
||||
from changedetectionio.content_fetchers import SCREENSHOT_MAX_HEIGHT_DEFAULT, SCREENSHOT_DEFAULT_QUALITY
|
||||
|
||||
# Cache font to avoid loading on every stitch
|
||||
_cached_font = None
|
||||
|
||||
def _get_caption_font():
|
||||
"""Get or create cached font for caption text."""
|
||||
global _cached_font
|
||||
if _cached_font is None:
|
||||
from PIL import ImageFont
|
||||
try:
|
||||
_cached_font = ImageFont.truetype("arial.ttf", 35)
|
||||
except IOError:
|
||||
_cached_font = ImageFont.load_default()
|
||||
return _cached_font
|
||||
|
||||
|
||||
def stitch_images_inline(chunks_bytes, original_page_height, capture_height):
|
||||
"""
|
||||
Stitch image chunks together inline (no multiprocessing).
|
||||
Optimized for small number of chunks (2-3) to avoid process creation overhead.
|
||||
|
||||
Args:
|
||||
chunks_bytes: List of JPEG image bytes
|
||||
original_page_height: Original page height in pixels
|
||||
capture_height: Maximum capture height
|
||||
|
||||
Returns:
|
||||
bytes: Stitched JPEG image
|
||||
"""
|
||||
import os
|
||||
import io
|
||||
from PIL import Image, ImageDraw
|
||||
|
||||
# Load images from byte chunks
|
||||
images = [Image.open(io.BytesIO(b)) for b in chunks_bytes]
|
||||
total_height = sum(im.height for im in images)
|
||||
max_width = max(im.width for im in images)
|
||||
|
||||
# Create stitched image
|
||||
stitched = Image.new('RGB', (max_width, total_height))
|
||||
y_offset = 0
|
||||
for im in images:
|
||||
stitched.paste(im, (0, y_offset))
|
||||
y_offset += im.height
|
||||
im.close() # Close immediately after pasting
|
||||
|
||||
# Draw caption only if page was trimmed
|
||||
if original_page_height > capture_height:
|
||||
draw = ImageDraw.Draw(stitched)
|
||||
caption_text = f"WARNING: Screenshot was {original_page_height}px but trimmed to {capture_height}px because it was too long"
|
||||
padding = 10
|
||||
font = _get_caption_font()
|
||||
|
||||
bbox = draw.textbbox((0, 0), caption_text, font=font)
|
||||
text_width = bbox[2] - bbox[0]
|
||||
text_height = bbox[3] - bbox[1]
|
||||
|
||||
# Draw white background rectangle
|
||||
draw.rectangle([(0, 0), (max_width, text_height + 2 * padding)], fill=(255, 255, 255))
|
||||
|
||||
# Draw text centered
|
||||
text_x = (max_width - text_width) // 2
|
||||
draw.text((text_x, padding), caption_text, font=font, fill=(255, 0, 0))
|
||||
|
||||
# Encode to JPEG
|
||||
output = io.BytesIO()
|
||||
stitched.save(output, format="JPEG", quality=int(os.getenv("SCREENSHOT_QUALITY", SCREENSHOT_DEFAULT_QUALITY)), optimize=True)
|
||||
result = output.getvalue()
|
||||
|
||||
# Cleanup
|
||||
stitched.close()
|
||||
|
||||
return result
|
||||
|
||||
|
||||
def stitch_images_worker(pipe_conn, chunks_bytes, original_page_height, capture_height):
|
||||
def stitch_images_worker_raw_bytes(pipe_conn, original_page_height, capture_height):
|
||||
"""
|
||||
Stitch image chunks together in a separate process.
|
||||
Used for large number of chunks (4+) to avoid blocking the main event loop.
|
||||
|
||||
Uses spawn multiprocessing to isolate PIL's C-level memory allocation.
|
||||
When the subprocess exits, the OS reclaims ALL memory including C-level allocations
|
||||
that Python's GC cannot release. This prevents the ~50MB per stitch from accumulating
|
||||
in the main process.
|
||||
|
||||
Trade-off: Adds 35MB resource_tracker subprocess, but prevents 500MB+ memory leak
|
||||
in main process (much better at scale: 35GB vs 500GB for 1000 instances).
|
||||
|
||||
Args:
|
||||
pipe_conn: Pipe connection to receive data and send result
|
||||
original_page_height: Original page height in pixels
|
||||
capture_height: Maximum capture height
|
||||
"""
|
||||
import os
|
||||
import io
|
||||
import struct
|
||||
from PIL import Image, ImageDraw, ImageFont
|
||||
|
||||
try:
|
||||
# Receive chunk count as 4-byte integer (no pickle!)
|
||||
count_bytes = pipe_conn.recv_bytes()
|
||||
chunk_count = struct.unpack('I', count_bytes)[0]
|
||||
|
||||
# Receive each chunk as raw bytes (no pickle!)
|
||||
chunks_bytes = []
|
||||
for _ in range(chunk_count):
|
||||
chunks_bytes.append(pipe_conn.recv_bytes())
|
||||
|
||||
# Load images from byte chunks
|
||||
images = [Image.open(io.BytesIO(b)) for b in chunks_bytes]
|
||||
del chunks_bytes
|
||||
|
||||
total_height = sum(im.height for im in images)
|
||||
max_width = max(im.width for im in images)
|
||||
|
||||
@@ -103,15 +53,14 @@ def stitch_images_worker(pipe_conn, chunks_bytes, original_page_height, capture_
|
||||
for im in images:
|
||||
stitched.paste(im, (0, y_offset))
|
||||
y_offset += im.height
|
||||
im.close() # Close immediately after pasting
|
||||
im.close()
|
||||
del images
|
||||
|
||||
# Draw caption only if page was trimmed
|
||||
if original_page_height > capture_height:
|
||||
draw = ImageDraw.Draw(stitched)
|
||||
caption_text = f"WARNING: Screenshot was {original_page_height}px but trimmed to {capture_height}px because it was too long"
|
||||
padding = 10
|
||||
|
||||
# Try to load font
|
||||
try:
|
||||
font = ImageFont.truetype("arial.ttf", 35)
|
||||
except IOError:
|
||||
@@ -120,23 +69,26 @@ def stitch_images_worker(pipe_conn, chunks_bytes, original_page_height, capture_
|
||||
bbox = draw.textbbox((0, 0), caption_text, font=font)
|
||||
text_width = bbox[2] - bbox[0]
|
||||
text_height = bbox[3] - bbox[1]
|
||||
|
||||
# Draw white background rectangle
|
||||
draw.rectangle([(0, 0), (max_width, text_height + 2 * padding)], fill=(255, 255, 255))
|
||||
|
||||
# Draw text centered
|
||||
text_x = (max_width - text_width) // 2
|
||||
draw.text((text_x, padding), caption_text, font=font, fill=(255, 0, 0))
|
||||
|
||||
# Encode and send image with optimization
|
||||
# Encode and send
|
||||
output = io.BytesIO()
|
||||
stitched.save(output, format="JPEG", quality=int(os.getenv("SCREENSHOT_QUALITY", SCREENSHOT_DEFAULT_QUALITY)), optimize=True)
|
||||
pipe_conn.send_bytes(output.getvalue())
|
||||
result_bytes = output.getvalue()
|
||||
|
||||
stitched.close()
|
||||
del stitched
|
||||
output.close()
|
||||
del output
|
||||
|
||||
pipe_conn.send_bytes(result_bytes)
|
||||
del result_bytes
|
||||
|
||||
except Exception as e:
|
||||
pipe_conn.send(f"error:{e}")
|
||||
logger.error(f"Error in stitch_images_worker_raw_bytes: {e}")
|
||||
error_msg = f"error:{e}".encode('utf-8')
|
||||
pipe_conn.send_bytes(error_msg)
|
||||
finally:
|
||||
pipe_conn.close()
|
||||
|
||||
|
||||
|
||||
43
changedetectionio/favicon_utils.py
Normal file
43
changedetectionio/favicon_utils.py
Normal file
@@ -0,0 +1,43 @@
|
||||
"""
|
||||
Favicon utilities for changedetection.io
|
||||
Handles favicon MIME type detection with caching
|
||||
"""
|
||||
|
||||
from functools import lru_cache
|
||||
|
||||
|
||||
@lru_cache(maxsize=1000)
|
||||
def get_favicon_mime_type(filepath):
|
||||
"""
|
||||
Detect MIME type of favicon by reading file content using puremagic.
|
||||
Results are cached to avoid repeatedly reading the same files.
|
||||
|
||||
Args:
|
||||
filepath: Full path to the favicon file
|
||||
|
||||
Returns:
|
||||
MIME type string (e.g., 'image/png')
|
||||
"""
|
||||
mime = None
|
||||
|
||||
try:
|
||||
import puremagic
|
||||
with open(filepath, 'rb') as f:
|
||||
content_bytes = f.read(200) # Read first 200 bytes
|
||||
|
||||
detections = puremagic.magic_string(content_bytes)
|
||||
if detections:
|
||||
mime = detections[0].mime_type
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Fallback to mimetypes if puremagic fails
|
||||
if not mime:
|
||||
import mimetypes
|
||||
mime, _ = mimetypes.guess_type(filepath)
|
||||
|
||||
# Final fallback based on extension
|
||||
if not mime:
|
||||
mime = 'image/x-icon' if filepath.endswith('.ico') else 'image/png'
|
||||
|
||||
return mime
|
||||
@@ -44,6 +44,8 @@ from changedetectionio.api import Watch, WatchHistory, WatchSingleHistory, Watch
|
||||
from changedetectionio.api.Search import Search
|
||||
from .time_handler import is_within_schedule
|
||||
from changedetectionio.languages import get_available_languages, get_language_codes, get_flag_for_locale, get_timeago_locale
|
||||
from changedetectionio.favicon_utils import get_favicon_mime_type
|
||||
|
||||
IN_PYTEST = "pytest" in sys.modules or "PYTEST_CURRENT_TEST" in os.environ
|
||||
|
||||
datastore = None
|
||||
@@ -69,9 +71,13 @@ socketio_server = None
|
||||
CORS(app)
|
||||
|
||||
# Super handy for compressing large BrowserSteps responses and others
|
||||
FlaskCompress(app)
|
||||
app.config['COMPRESS_MIN_SIZE'] = 4096
|
||||
# Flask-Compress handles HTTP compression, Socket.IO compression disabled to prevent memory leak
|
||||
compress = FlaskCompress()
|
||||
app.config['COMPRESS_MIN_SIZE'] = 2096
|
||||
app.config['COMPRESS_MIMETYPES'] = ['text/html', 'text/css', 'text/javascript', 'application/json', 'application/javascript', 'image/svg+xml']
|
||||
# Use gzip only - smaller memory footprint than zstd/brotli (4-8KB vs 200-500KB contexts)
|
||||
app.config['COMPRESS_ALGORITHM'] = ['gzip']
|
||||
compress.init_app(app)
|
||||
app.config['TEMPLATES_AUTO_RELOAD'] = False
|
||||
|
||||
|
||||
@@ -88,6 +94,14 @@ if os.getenv('FLASK_SERVER_NAME'):
|
||||
app.config['BABEL_TRANSLATION_DIRECTORIES'] = str(Path(__file__).parent / 'translations')
|
||||
app.config['BABEL_DEFAULT_LOCALE'] = 'en_GB'
|
||||
|
||||
# Session configuration
|
||||
# NOTE: Flask session (for locale, etc.) is separate from Flask-Login's remember-me cookie
|
||||
# - Flask session stores data like session['locale'] in a signed cookie
|
||||
# - Flask-Login's remember=True creates a separate authentication cookie
|
||||
# - Setting PERMANENT_SESSION_LIFETIME controls how long the Flask session cookie lasts
|
||||
from datetime import timedelta
|
||||
app.config['PERMANENT_SESSION_LIFETIME'] = timedelta(days=3650) # ~10 years (effectively unlimited)
|
||||
|
||||
#app.config["EXPLAIN_TEMPLATE_LOADING"] = True
|
||||
|
||||
|
||||
@@ -400,11 +414,27 @@ def changedetection_app(config=None, datastore_o=None):
|
||||
language_codes = get_language_codes()
|
||||
|
||||
def get_locale():
|
||||
# Locale aliases: map browser language codes to translation directory names
|
||||
# This handles cases where browsers send standard codes (e.g., zh-TW)
|
||||
# but our translations use more specific codes (e.g., zh_Hant_TW)
|
||||
locale_aliases = {
|
||||
'zh-TW': 'zh_Hant_TW', # Traditional Chinese: browser sends zh-TW, we use zh_Hant_TW
|
||||
'zh_TW': 'zh_Hant_TW', # Also handle underscore variant
|
||||
}
|
||||
|
||||
# 1. Try to get locale from session (user explicitly selected)
|
||||
if 'locale' in session:
|
||||
return session['locale']
|
||||
|
||||
# 2. Fall back to Accept-Language header
|
||||
return request.accept_languages.best_match(language_codes)
|
||||
# Get the best match from browser's Accept-Language header
|
||||
browser_locale = request.accept_languages.best_match(language_codes + list(locale_aliases.keys()))
|
||||
|
||||
# 3. Check if we need to map the browser locale to our internal locale
|
||||
if browser_locale in locale_aliases:
|
||||
return locale_aliases[browser_locale]
|
||||
|
||||
return browser_locale
|
||||
|
||||
# Initialize Babel with locale selector
|
||||
babel = Babel(app, locale_selector=get_locale)
|
||||
@@ -528,6 +558,9 @@ def changedetection_app(config=None, datastore_o=None):
|
||||
|
||||
# Validate the locale against available languages
|
||||
if locale in language_codes:
|
||||
# Make session permanent so language preference persists across browser sessions
|
||||
# NOTE: This is the Flask session cookie (separate from Flask-Login's remember-me auth cookie)
|
||||
session.permanent = True
|
||||
session['locale'] = locale
|
||||
|
||||
# CRITICAL: Flask-Babel caches the locale in the request context (ctx.babel_locale)
|
||||
@@ -666,16 +699,9 @@ def changedetection_app(config=None, datastore_o=None):
|
||||
|
||||
favicon_filename = watch.get_favicon_filename()
|
||||
if favicon_filename:
|
||||
try:
|
||||
import magic
|
||||
mime = magic.from_file(
|
||||
os.path.join(watch.watch_data_dir, favicon_filename),
|
||||
mime=True
|
||||
)
|
||||
except ImportError:
|
||||
# Fallback, no python-magic
|
||||
import mimetypes
|
||||
mime, encoding = mimetypes.guess_type(favicon_filename)
|
||||
# Use cached MIME type detection
|
||||
filepath = os.path.join(watch.watch_data_dir, favicon_filename)
|
||||
mime = get_favicon_mime_type(filepath)
|
||||
|
||||
response = make_response(send_from_directory(watch.watch_data_dir, favicon_filename))
|
||||
response.headers['Content-type'] = mime
|
||||
|
||||
@@ -727,8 +727,8 @@ class ValidateStartsWithRegex(object):
|
||||
raise ValidationError(self.message or _l("Invalid value."))
|
||||
|
||||
class quickWatchForm(Form):
|
||||
url = fields.URLField('URL', validators=[validateURL()])
|
||||
tags = StringTagUUID('Group tag', [validators.Optional()])
|
||||
url = fields.URLField(_l('URL'), validators=[validateURL()])
|
||||
tags = StringTagUUID(_l('Group tag'), validators=[validators.Optional()])
|
||||
watch_submit_button = SubmitField(_l('Watch'), render_kw={"class": "pure-button pure-button-primary"})
|
||||
processor = RadioField(_l('Processor'), choices=lambda: processors.available_processors(), default="text_json_diff")
|
||||
edit_and_watch_submit_button = SubmitField(_l('Edit > Watch'), render_kw={"class": "pure-button pure-button-primary"})
|
||||
@@ -786,6 +786,7 @@ class processor_text_json_diff_form(commonSettingsForm):
|
||||
|
||||
time_between_check = EnhancedFormField(
|
||||
TimeBetweenCheckForm,
|
||||
label=_l('Time Between Check'),
|
||||
conditional_field='time_between_check_use_default',
|
||||
conditional_message=REQUIRE_ATLEAST_ONE_TIME_PART_WHEN_NOT_GLOBAL_DEFAULT,
|
||||
conditional_test_function=validate_time_between_check_has_values
|
||||
@@ -947,7 +948,7 @@ class DefaultUAInputForm(Form):
|
||||
|
||||
# datastore.data['settings']['requests']..
|
||||
class globalSettingsRequestForm(Form):
|
||||
time_between_check = RequiredFormField(TimeBetweenCheckForm)
|
||||
time_between_check = RequiredFormField(TimeBetweenCheckForm, label=_l('Time Between Check'))
|
||||
time_schedule_limit = FormField(ScheduleLimitForm)
|
||||
proxy = RadioField(_l('Default proxy'))
|
||||
jitter_seconds = IntegerField(_l('Random jitter seconds ± check'),
|
||||
@@ -1007,7 +1008,7 @@ class globalSettingsApplicationForm(commonSettingsForm):
|
||||
render_kw={"placeholder": "0.1", "style": "width: 8em;"}
|
||||
)
|
||||
|
||||
password = SaltyPasswordField()
|
||||
password = SaltyPasswordField(_l('Password'))
|
||||
pager_size = IntegerField(_l('Pager size'),
|
||||
render_kw={"style": "width: 5em;"},
|
||||
validators=[validators.NumberRange(min=0,
|
||||
|
||||
@@ -20,8 +20,9 @@ mtable = {'seconds': 1, 'minutes': 60, 'hours': 3600, 'days': 86400, 'weeks': 86
|
||||
|
||||
def _brotli_save(contents, filepath, mode=None, fallback_uncompressed=False):
|
||||
"""
|
||||
Save compressed data using native brotli.
|
||||
Testing shows no memory leak when using gc.collect() after compression.
|
||||
Save compressed data using native brotli with streaming compression.
|
||||
Uses chunked compression to minimize peak memory usage and malloc_trim()
|
||||
to force release of C-level memory back to the OS.
|
||||
|
||||
Args:
|
||||
contents: data to compress (str or bytes)
|
||||
@@ -37,27 +38,52 @@ def _brotli_save(contents, filepath, mode=None, fallback_uncompressed=False):
|
||||
"""
|
||||
import brotli
|
||||
import gc
|
||||
import ctypes
|
||||
|
||||
# Ensure contents are bytes
|
||||
if isinstance(contents, str):
|
||||
contents = contents.encode('utf-8')
|
||||
|
||||
try:
|
||||
logger.debug(f"Starting brotli compression of {len(contents)} bytes.")
|
||||
original_size = len(contents)
|
||||
logger.debug(f"Starting brotli streaming compression of {original_size} bytes.")
|
||||
|
||||
if mode is not None:
|
||||
compressed_data = brotli.compress(contents, mode=mode)
|
||||
else:
|
||||
compressed_data = brotli.compress(contents)
|
||||
# Create streaming compressor
|
||||
compressor = brotli.Compressor(quality=6, mode=mode if mode is not None else brotli.MODE_GENERIC)
|
||||
|
||||
# Stream compress in chunks to minimize memory usage
|
||||
chunk_size = 65536 # 64KB chunks
|
||||
total_compressed_size = 0
|
||||
|
||||
with open(filepath, 'wb') as f:
|
||||
f.write(compressed_data)
|
||||
# Process data in chunks
|
||||
offset = 0
|
||||
while offset < len(contents):
|
||||
chunk = contents[offset:offset + chunk_size]
|
||||
compressed_chunk = compressor.process(chunk)
|
||||
if compressed_chunk:
|
||||
f.write(compressed_chunk)
|
||||
total_compressed_size += len(compressed_chunk)
|
||||
offset += chunk_size
|
||||
|
||||
logger.debug(f"Finished brotli compression - From {len(contents)} to {len(compressed_data)} bytes.")
|
||||
# Finalize compression - critical for proper cleanup
|
||||
final_chunk = compressor.finish()
|
||||
if final_chunk:
|
||||
f.write(final_chunk)
|
||||
total_compressed_size += len(final_chunk)
|
||||
|
||||
# Force garbage collection to prevent memory buildup
|
||||
logger.debug(f"Finished brotli compression - From {original_size} to {total_compressed_size} bytes.")
|
||||
|
||||
# Cleanup: Delete compressor, force Python GC, then force C-level memory release
|
||||
del compressor
|
||||
gc.collect()
|
||||
|
||||
# Force release of C-level memory back to OS (since brotli is a C library)
|
||||
try:
|
||||
ctypes.CDLL('libc.so.6').malloc_trim(0)
|
||||
except Exception:
|
||||
pass # malloc_trim not available on all systems (e.g., macOS)
|
||||
|
||||
return filepath
|
||||
|
||||
except Exception as e:
|
||||
|
||||
@@ -69,7 +69,7 @@ class RecheckPriorityQueue:
|
||||
# Emit signals
|
||||
self._emit_put_signals(item)
|
||||
|
||||
logger.debug(f"Successfully queued item: {self._get_item_uuid(item)}")
|
||||
logger.trace(f"Successfully queued item: {self._get_item_uuid(item)}")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
|
||||
@@ -240,7 +240,10 @@ def init_socketio(app, datastore):
|
||||
async_mode=async_mode,
|
||||
cors_allowed_origins=cors_origins, # None means same-origin only
|
||||
logger=strtobool(os.getenv('SOCKETIO_LOGGING', 'False')),
|
||||
engineio_logger=strtobool(os.getenv('SOCKETIO_LOGGING', 'False')))
|
||||
engineio_logger=strtobool(os.getenv('SOCKETIO_LOGGING', 'False')),
|
||||
# Disable WebSocket compression to prevent memory accumulation
|
||||
# Flask-Compress already handles HTTP response compression
|
||||
engineio_options={'http_compression': False, 'compression_threshold': 0})
|
||||
|
||||
# Set up event handlers
|
||||
logger.info("Socket.IO: Registering connect event handler")
|
||||
|
||||
@@ -91,8 +91,8 @@ REMOVE_REQUESTS_OLD_SCREENSHOTS=false pytest -vv -s --maxfail=1 tests/test_notif
|
||||
# And again with brotli+screenshot attachment
|
||||
SNAPSHOT_BROTLI_COMPRESSION_THRESHOLD=5 REMOVE_REQUESTS_OLD_SCREENSHOTS=false pytest -vv -s --maxfail=1 --dist=load tests/test_backend.py tests/test_rss.py tests/test_unique_lines.py tests/test_notification.py tests/test_access_control.py
|
||||
|
||||
# Try high concurrency
|
||||
FETCH_WORKERS=50 pytest tests/test_history_consistency.py -vv -l -s
|
||||
# Try high concurrency with aggressive worker restarts
|
||||
FETCH_WORKERS=50 WORKER_MAX_RUNTIME=2 WORKER_MAX_JOBS=1 pytest tests/test_history_consistency.py -vv -l -s
|
||||
|
||||
# Check file:// will pickup a file when enabled
|
||||
echo "Hello world" > /tmp/test-file.txt
|
||||
|
||||
@@ -1,19 +1,25 @@
|
||||
{
|
||||
"name": "",
|
||||
"short_name": "",
|
||||
"name": "ChangeDetection.io",
|
||||
"short_name": "ChangeDetect",
|
||||
"description": "Self-hosted website change detection and monitoring",
|
||||
"icons": [
|
||||
{
|
||||
"src": "android-chrome-192x192.png",
|
||||
"sizes": "192x192",
|
||||
"type": "image/png"
|
||||
"type": "image/png",
|
||||
"purpose": "any maskable"
|
||||
},
|
||||
{
|
||||
"src": "android-chrome-256x256.png",
|
||||
"sizes": "256x256",
|
||||
"type": "image/png"
|
||||
"type": "image/png",
|
||||
"purpose": "any maskable"
|
||||
}
|
||||
],
|
||||
"theme_color": "#ffffff",
|
||||
"start_url": "/",
|
||||
"theme_color": "#5bbad5",
|
||||
"background_color": "#ffffff",
|
||||
"display": "standalone"
|
||||
"display": "standalone",
|
||||
"categories": ["utilities", "productivity"],
|
||||
"orientation": "any"
|
||||
}
|
||||
|
||||
@@ -69,6 +69,19 @@
|
||||
}
|
||||
});
|
||||
|
||||
// Handle Enter key in search input
|
||||
if (searchInput) {
|
||||
searchInput.addEventListener('keydown', function(e) {
|
||||
if (e.key === 'Enter') {
|
||||
e.preventDefault();
|
||||
if (searchForm) {
|
||||
// Trigger form submission programmatically
|
||||
searchForm.dispatchEvent(new Event('submit'));
|
||||
}
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
// Handle form submission
|
||||
if (searchForm) {
|
||||
searchForm.addEventListener('submit', function(e) {
|
||||
@@ -88,8 +101,8 @@
|
||||
params.append('tags', tags);
|
||||
}
|
||||
|
||||
// Navigate to search results
|
||||
window.location.href = '?' + params.toString();
|
||||
// Navigate to search results (always redirect to watchlist home)
|
||||
window.location.href = '/?' + params.toString();
|
||||
});
|
||||
}
|
||||
});
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import gc
|
||||
import shutil
|
||||
|
||||
from changedetectionio.strtobool import strtobool
|
||||
@@ -125,6 +126,10 @@ class ChangeDetectionStore:
|
||||
if 'application' in from_disk['settings']:
|
||||
self.__data['settings']['application'].update(from_disk['settings']['application'])
|
||||
|
||||
# from_disk no longer needed - free memory immediately
|
||||
del from_disk
|
||||
gc.collect()
|
||||
|
||||
# Convert each existing watch back to the Watch.model object
|
||||
for uuid, watch in self.__data['watching'].items():
|
||||
self.__data['watching'][uuid] = self.rehydrate_entity(uuid, watch)
|
||||
@@ -348,7 +353,8 @@ class ChangeDetectionStore:
|
||||
r = requests.request(method="GET",
|
||||
url=url,
|
||||
# So we know to return the JSON instead of the human-friendly "help" page
|
||||
headers={'App-Guid': self.__data['app_guid']})
|
||||
headers={'App-Guid': self.__data['app_guid']},
|
||||
timeout=5.0) # 5 second timeout to prevent blocking
|
||||
res = r.json()
|
||||
|
||||
# List of permissible attributes we accept from the wild internet
|
||||
@@ -449,7 +455,7 @@ class ChangeDetectionStore:
|
||||
data = deepcopy(self.__data)
|
||||
except RuntimeError as e:
|
||||
# Try again in 15 seconds
|
||||
time.sleep(15)
|
||||
time.sleep(1)
|
||||
logger.error(f"! Data changed when writing to JSON, trying again.. {str(e)}")
|
||||
self.sync_to_json()
|
||||
return
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
|
||||
<div class="pure-controls">
|
||||
<span class="pure-form-message-inline">
|
||||
Body for all notifications ‐ You can use <a target="newwindow" href="https://jinja.palletsprojects.com/en/3.0.x/templates/">Jinja2</a> templating in the notification title, body and URL, and tokens from below.
|
||||
{{ _('Body for all notifications — You can use') }} <a target="newwindow" href="https://jinja.palletsprojects.com/en/3.0.x/templates/">Jinja2</a> {{ _('templating in the notification title, body and URL, and tokens from below.') }}
|
||||
</span><br>
|
||||
<div data-target="#notification-tokens-info{{ suffix }}" class="toggle-show pure-button button-tag button-xsmall">{{ _('Show token/placeholders') }}
|
||||
</div>
|
||||
@@ -22,77 +22,77 @@
|
||||
<tbody>
|
||||
<tr>
|
||||
<td><code>{{ '{{base_url}}' }}</code></td>
|
||||
<td>The URL of the changedetection.io instance you are running.</td>
|
||||
<td>{{ _('The URL of the changedetection.io instance you are running.') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{watch_url}}' }}</code></td>
|
||||
<td>The URL being watched.</td>
|
||||
<td>{{ _('The URL being watched.') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{watch_uuid}}' }}</code></td>
|
||||
<td>The UUID of the watch.</td>
|
||||
<td>{{ _('The UUID of the watch.') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{watch_title}}' }}</code></td>
|
||||
<td>The page title of the watch, uses <title> if not set, falls back to URL</td>
|
||||
<td>{{ _('The page title of the watch, uses <title> if not set, falls back to URL') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{watch_tag}}' }}</code></td>
|
||||
<td>The watch group / tag</td>
|
||||
<td>{{ _('The watch group / tag') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{preview_url}}' }}</code></td>
|
||||
<td>The URL of the preview page generated by changedetection.io.</td>
|
||||
<td>{{ _('The URL of the preview page generated by changedetection.io.') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{diff_url}}' }}</code></td>
|
||||
<td>The URL of the diff output for the watch.</td>
|
||||
<td>{{ _('The URL of the diff output for the watch.') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{diff}}' }}</code></td>
|
||||
<td>The diff output - only changes, additions, and removals</td>
|
||||
<td>{{ _('The diff output - only changes, additions, and removals') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{diff_clean}}' }}</code></td>
|
||||
<td>The diff output - only changes, additions, and removals ‐ <i>Without (added) prefix or colors</i>
|
||||
<td>{{ _('The diff output - only changes, additions, and removals —') }} <i>{{ _('Without (added) prefix or colors') }}</i>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{diff_added}}' }}</code></td>
|
||||
<td>The diff output - only changes and additions</td>
|
||||
<td>{{ _('The diff output - only changes and additions') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{diff_added_clean}}' }}</code></td>
|
||||
<td>The diff output - only changes and additions ‐ <i>Without (added) prefix or colors</i></td>
|
||||
<td>{{ _('The diff output - only changes and additions —') }} <i>{{ _('Without (added) prefix or colors') }}</i></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{diff_removed}}' }}</code></td>
|
||||
<td>The diff output - only changes and removals</td>
|
||||
<td>{{ _('The diff output - only changes and removals') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{diff_removed_clean}}' }}</code></td>
|
||||
<td>The diff output - only changes and removals ‐ <i>Without (added) prefix or colors</i></td>
|
||||
<td>{{ _('The diff output - only changes and removals —') }} <i>{{ _('Without (added) prefix or colors') }}</i></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{diff_full}}' }}</code></td>
|
||||
<td>The diff output - full difference output</td>
|
||||
<td>{{ _('The diff output - full difference output') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{diff_full_clean}}' }}</code></td>
|
||||
<td>The diff output - full difference output ‐ <i>Without (added) prefix or colors</i></td>
|
||||
<td>{{ _('The diff output - full difference output —') }} <i>{{ _('Without (added) prefix or colors') }}</i></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{diff_patch}}' }}</code></td>
|
||||
<td>The diff output - patch in unified format</td>
|
||||
<td>{{ _('The diff output - patch in unified format') }}</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{current_snapshot}}' }}</code></td>
|
||||
<td>The current snapshot text contents value, useful when combined with JSON or CSS filters
|
||||
<td>{{ _('The current snapshot text contents value, useful when combined with JSON or CSS filters') }}
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><code>{{ '{{triggered_text}}' }}</code></td>
|
||||
<td>Text that tripped the trigger from filters</td>
|
||||
<td>{{ _('Text that tripped the trigger from filters') }}</td>
|
||||
|
||||
{% if extra_notification_token_placeholder_info %}
|
||||
{% for token in extra_notification_token_placeholder_info %}
|
||||
@@ -106,8 +106,8 @@
|
||||
</table>
|
||||
|
||||
<span class="pure-form-message-inline">
|
||||
Warning: Contents of <code>{{ '{{diff}}' }}</code>, <code>{{ '{{diff_removed}}' }}</code>, and <code>{{ '{{diff_added}}' }}</code> depend on how the difference algorithm perceives the change. <br>
|
||||
For example, an addition or removal could be perceived as a change in some cases. <a target="newwindow" href="https://github.com/dgtlmoon/changedetection.io/wiki/Using-the-%7B%7Bdiff%7D%7D,-%7B%7Bdiff_added%7D%7D,-and-%7B%7Bdiff_removed%7D%7D-notification-tokens">More Here</a> <br>
|
||||
{{ _('Warning: Contents of') }} <code>{{ '{{diff}}' }}</code>, <code>{{ '{{diff_removed}}' }}</code>, {{ _('and') }} <code>{{ '{{diff_added}}' }}</code> {{ _('depend on how the difference algorithm perceives the change.') }} <br>
|
||||
{{ _('For example, an addition or removal could be perceived as a change in some cases.') }} <a target="newwindow" href="https://github.com/dgtlmoon/changedetection.io/wiki/Using-the-%7B%7Bdiff%7D%7D,-%7B%7Bdiff_added%7D%7D,-and-%7B%7Bdiff_removed%7D%7D-notification-tokens">{{ _('More Here') }}</a> <br>
|
||||
</span>
|
||||
</div>
|
||||
{% endmacro %}
|
||||
@@ -123,15 +123,15 @@
|
||||
}}
|
||||
<div class="pure-form-message-inline">
|
||||
<p>
|
||||
<strong>Tip:</strong> Use <a target="newwindow" href="https://github.com/caronc/apprise">AppRise Notification URLs</a> for notification to just about any service! <i><a target="newwindow" href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes">Please read the notification services wiki here for important configuration notes</a></i>.<br>
|
||||
<strong>{{ _('Tip:') }}</strong> {{ _('Use') }} <a target="newwindow" href="https://github.com/caronc/apprise">{{ _('AppRise Notification URLs') }}</a> {{ _('for notification to just about any service!') }} <i><a target="newwindow" href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes">{{ _('Please read the notification services wiki here for important configuration notes') }}</a></i>.<br>
|
||||
</p>
|
||||
<div data-target="#advanced-help-notifications" class="toggle-show pure-button button-tag button-xsmall">{{ _('Show advanced help and tips') }}</div>
|
||||
<ul style="display: none" id="advanced-help-notifications">
|
||||
<li><code><a target="newwindow" href="https://github.com/caronc/apprise/wiki/Notify_discord">discord://</a></code> (or <code>https://discord.com/api/webhooks...</code>)) only supports a maximum <strong>2,000 characters</strong> of notification text, including the title.</li>
|
||||
<li><code><a target="newwindow" href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> bots can't send messages to other bots, so you should specify chat ID of non-bot user.</li>
|
||||
<li><code><a target="newwindow" href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> only supports very limited HTML and can fail when extra tags are sent, <a href="https://core.telegram.org/bots/api#html-style">read more here</a> (or use plaintext/markdown format)</li>
|
||||
<li><code>gets://</code>, <code>posts://</code>, <code>puts://</code>, <code>deletes://</code> for direct API calls (or omit the "<code>s</code>" for non-SSL ie <code>get://</code>) <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes#postposts">more help here</a></li>
|
||||
<li>Accepts the <code>{{ '{{token}}' }}</code> placeholders listed below</li>
|
||||
<li><code><a target="newwindow" href="https://github.com/caronc/apprise/wiki/Notify_discord">discord://</a></code> {{ _('(or') }} <code>https://discord.com/api/webhooks...</code>)) {{ _('only supports a maximum') }} <strong>{{ _('2,000 characters') }}</strong> {{ _('of notification text, including the title.') }}</li>
|
||||
<li><code><a target="newwindow" href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> {{ _('bots can\'t send messages to other bots, so you should specify chat ID of non-bot user.') }}</li>
|
||||
<li><code><a target="newwindow" href="https://github.com/caronc/apprise/wiki/Notify_telegram">tgram://</a></code> {{ _('only supports very limited HTML and can fail when extra tags are sent,') }} <a href="https://core.telegram.org/bots/api#html-style">{{ _('read more here') }}</a> {{ _('(or use plaintext/markdown format)') }}</li>
|
||||
<li><code>gets://</code>, <code>posts://</code>, <code>puts://</code>, <code>deletes://</code> {{ _('for direct API calls (or omit the') }} "<code>s</code>" {{ _('for non-SSL ie') }} <code>get://</code>) <a href="https://github.com/dgtlmoon/changedetection.io/wiki/Notification-configuration-notes#postposts">{{ _('more help here') }}</a></li>
|
||||
<li>{{ _('Accepts the') }} <code>{{ '{{token}}' }}</code> {{ _('placeholders listed below') }}</li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="notifications-wrapper">
|
||||
@@ -156,16 +156,16 @@
|
||||
<div class="pure-form-message-inline">
|
||||
<ul>
|
||||
<li><span class="pure-form-message-inline">
|
||||
For JSON payloads, use <strong>|tojson</strong> without quotes for automatic escaping, for example - <code>{ "name": {{ '{{ watch_title|tojson }}' }} }</code>
|
||||
{{ _('For JSON payloads, use') }} <strong>|tojson</strong> {{ _('without quotes for automatic escaping, for example -') }} <code>{ "name": {{ '{{ watch_title|tojson }}' }} }</code>
|
||||
</span></li>
|
||||
<li><span class="pure-form-message-inline">
|
||||
URL encoding, use <strong>|urlencode</strong>, for example - <code>gets://hook-website.com/test.php?title={{ '{{ watch_title|urlencode }}' }}</code>
|
||||
{{ _('URL encoding, use') }} <strong>|urlencode</strong>, {{ _('for example -') }} <code>gets://hook-website.com/test.php?title={{ '{{ watch_title|urlencode }}' }}</code>
|
||||
</span></li>
|
||||
<li><span class="pure-form-message-inline">
|
||||
Regular-expression replace, use <strong>|regex_replace</strong>, for example - <code>{{ "{{ \"hello world 123\" | regex_replace('[0-9]+', 'no-more-numbers') }}" }}</code>
|
||||
{{ _('Regular-expression replace, use') }} <strong>|regex_replace</strong>, {{ _('for example -') }} <code>{{ "{{ \"hello world 123\" | regex_replace('[0-9]+', 'no-more-numbers') }}" }}</code>
|
||||
</span></li>
|
||||
<li><span class="pure-form-message-inline">
|
||||
For a complete reference of all Jinja2 built-in filters, users can refer to the <a href="https://jinja.palletsprojects.com/en/3.1.x/templates/#builtin-filters">https://jinja.palletsprojects.com/en/3.1.x/templates/#builtin-filters</a>
|
||||
{{ _('For a complete reference of all Jinja2 built-in filters, users can refer to the') }} <a href="https://jinja.palletsprojects.com/en/3.1.x/templates/#builtin-filters">https://jinja.palletsprojects.com/en/3.1.x/templates/#builtin-filters</a>
|
||||
</span></li>
|
||||
</ul>
|
||||
<br>
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{% macro render_field(field) %}
|
||||
<div {% if field.errors or field.top_errors %} class="error" {% endif %}><label for="{{ field.id }}">{{ field.label.text | string | forceescape }}</label></div>
|
||||
<div {% if field.errors or field.top_errors %} class="error" {% endif %}>{{ field.label }}</div>
|
||||
<div {% if field.errors or field.top_errors %} class="error" {% endif %}>{{ field(**kwargs)|safe }}
|
||||
{% if field.top_errors %}
|
||||
top
|
||||
@@ -59,7 +59,7 @@
|
||||
|
||||
{% macro render_ternary_field(field, BooleanField=false) %}
|
||||
{% if BooleanField %}
|
||||
{% set _ = field.__setattr__('boolean_mode', true) %}
|
||||
{% set dummy = field.__setattr__('boolean_mode', true) %}
|
||||
{% endif %}
|
||||
<div class="ternary-field {% if field.errors %} error {% endif %}">
|
||||
<div class="ternary-field-label"><label for="{{ field.id }}">{{ field.label.text | string | forceescape }}</label></div>
|
||||
@@ -113,17 +113,17 @@
|
||||
|
||||
{% macro render_fieldlist_with_inline_errors(fieldlist) %}
|
||||
{# Specialized macro for FieldList(FormField(...)) that renders errors inline with each field #}
|
||||
<div {% if fieldlist.errors %} class="error" {% endif %}>{{ fieldlist.label }}</div>
|
||||
<div {% if fieldlist.errors %} class="error" {% endif %}>{{ _(fieldlist.label.text | string) }}</div>
|
||||
<div {% if fieldlist.errors %} class="error" {% endif %}>
|
||||
<ul id="{{ fieldlist.id }}">
|
||||
{% for entry in fieldlist %}
|
||||
<li {% if entry.errors %} class="error" {% endif %}>
|
||||
<label for="{{ entry.id }}" {% if entry.errors %} class="error" {% endif %}>{{ fieldlist.label.text }}-{{ loop.index0 }}</label>
|
||||
<label for="{{ entry.id }}" {% if entry.errors %} class="error" {% endif %}>{{ _(fieldlist.label.text | string) }}-{{ loop.index0 }}</label>
|
||||
<table id="{{ entry.id }}" {% if entry.errors %} class="error" {% endif %}>
|
||||
<tbody>
|
||||
{% for subfield in entry %}
|
||||
<tr {% if subfield.errors %} class="error" {% endif %}>
|
||||
<th {% if subfield.errors %} class="error" {% endif %}><label for="{{ subfield.id }}" {% if subfield.errors %} class="error" {% endif %}>{{ subfield.label.text }}</label></th>
|
||||
<th {% if subfield.errors %} class="error" {% endif %}><label for="{{ subfield.id }}" {% if subfield.errors %} class="error" {% endif %}>{{ subfield.label.text | string }}</label></th>
|
||||
<td {% if subfield.errors %} class="error" {% endif %}>
|
||||
{{ subfield(**kwargs)|safe }}
|
||||
{% if subfield.errors %}
|
||||
@@ -148,7 +148,7 @@
|
||||
<div class="fieldlist_formfields" id="{{ table_id }}">
|
||||
<div class="fieldlist-header">
|
||||
{% for subfield in fieldlist[0] %}
|
||||
<div class="fieldlist-header-cell">{{ subfield.label }}</div>
|
||||
<div class="fieldlist-header-cell">{{ subfield.label.text | string }}</div>
|
||||
{% endfor %}
|
||||
<div class="fieldlist-header-cell">{{ _('Actions') }}</div>
|
||||
</div>
|
||||
|
||||
@@ -27,7 +27,7 @@
|
||||
<link rel="apple-touch-icon" sizes="180x180" href="{{url_for('static_content', group='favicons', filename='apple-touch-icon.png')}}">
|
||||
<link rel="icon" type="image/png" sizes="32x32" href="{{url_for('static_content', group='favicons', filename='favicon-32x32.png')}}">
|
||||
<link rel="icon" type="image/png" sizes="16x16" href="{{url_for('static_content', group='favicons', filename='favicon-16x16.png')}}">
|
||||
<link rel="manifest" href="{{url_for('static_content', group='favicons', filename='site.webmanifest')}}">
|
||||
<link rel="manifest" href="{{url_for('static_content', group='favicons', filename='site.webmanifest')}}" crossorigin="use-credentials">
|
||||
<link rel="mask-icon" href="{{url_for('static_content', group='favicons', filename='safari-pinned-tab.svg')}}" color="#5bbad5">
|
||||
<link rel="shortcut icon" href="{{url_for('static_content', group='favicons', filename='favicon.ico')}}">
|
||||
<meta name="msapplication-TileColor" content="#da532c">
|
||||
@@ -265,6 +265,9 @@
|
||||
</a>
|
||||
{% endfor %}
|
||||
</div>
|
||||
<div>
|
||||
<a href="{{ url_for('ui.delete_locale_language_session_var_if_it_exists', redirect=request.path) }}" >{{ _('Auto-detect from browser') }}</a>
|
||||
</div>
|
||||
<div>
|
||||
{{ _('Language support is in beta, please help us improve by opening a PR on GitHub with any updates.') }}
|
||||
</div>
|
||||
|
||||
@@ -14,10 +14,10 @@
|
||||
<a href="{{ url_for('imports.import_page') }}" class="pure-menu-link">{{ _('IMPORT') }}</a>
|
||||
</li>
|
||||
<li class="pure-menu-item" id="menu-pause">
|
||||
<a href="{{ url_for('settings.toggle_all_paused') }}" ><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="{% if all_paused %}Resume automatic scheduling{% else %}Pause auto-queue scheduling of watches{% endif %}" title="{% if all_paused %}Scheduling is paused - click to resume{% else %}Pause auto-queue scheduling of watches{% endif %}" class="icon icon-pause"{% if not all_paused %} style="opacity: 0.3"{% endif %}></a>
|
||||
<a href="{{ url_for('settings.toggle_all_paused') }}" ><img src="{{url_for('static_content', group='images', filename='pause.svg')}}" alt="{% if all_paused %}{{ _('Resume automatic scheduling') }}{% else %}{{ _('Pause auto-queue scheduling of watches') }}{% endif %}" title="{% if all_paused %}{{ _('Scheduling is paused - click to resume') }}{% else %}{{ _('Pause auto-queue scheduling of watches') }}{% endif %}" class="icon icon-pause"{% if not all_paused %} style="opacity: 0.3"{% endif %}></a>
|
||||
</li>
|
||||
<li class="pure-menu-item " id="menu-mute">
|
||||
<a href="{{ url_for('settings.toggle_all_muted') }}" ><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="{% if all_muted %}Unmute notifications{% else %}Mute notifications{% endif %}" title="{% if all_muted %}Notifications are muted - click to unmute{% else %}Mute notifications{% endif %}" class="icon icon-mute"{% if not all_muted %} style="opacity: 0.3"{% endif %}></a>
|
||||
<a href="{{ url_for('settings.toggle_all_muted') }}" ><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="{% if all_muted %}{{ _('Unmute notifications') }}{% else %}{{ _('Mute notifications') }}{% endif %}" title="{% if all_muted %}{{ _('Notifications are muted - click to unmute') }}{% else %}{{ _('Mute notifications') }}{% endif %}" class="icon icon-mute"{% if not all_muted %} style="opacity: 0.3"{% endif %}></a>
|
||||
</li>
|
||||
{% else %}
|
||||
<li class="pure-menu-item menu-collapsible">
|
||||
@@ -33,7 +33,7 @@
|
||||
|
||||
{% else %}
|
||||
<li class="pure-menu-item menu-collapsible">
|
||||
<a class="pure-menu-link" href="https://changedetection.io">Website Change Detection and Notification.</a>
|
||||
<a class="pure-menu-link" href="https://changedetection.io">{{ _('Website Change Detection and Notification.') }}</a>
|
||||
</li>
|
||||
{% endif %}
|
||||
<li class="pure-menu-item menu-collapsible" id="inline-menu-extras-group">
|
||||
@@ -50,7 +50,9 @@
|
||||
<span class="visually-hidden">{{ _('Change language') }}</span>
|
||||
<span class="{{ get_flag_for_locale(get_locale()) }}" id="language-selector-flag"></span>
|
||||
</button>
|
||||
<a class="github-link" href="https://github.com/dgtlmoon/changedetection.io">
|
||||
<a class="github-link" href="https://github.com/dgtlmoon/changedetection.io"
|
||||
target="_blank"
|
||||
rel="noopener" >
|
||||
{% include "svgs/github.svg" %}
|
||||
</a>
|
||||
</li>
|
||||
|
||||
@@ -58,7 +58,7 @@ def is_valid_uuid(val):
|
||||
|
||||
|
||||
def test_api_simple(client, live_server, measure_memory_usage, datastore_path):
|
||||
|
||||
|
||||
|
||||
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
|
||||
|
||||
@@ -506,7 +506,7 @@ def test_api_import(client, live_server, measure_memory_usage, datastore_path):
|
||||
|
||||
def test_api_conflict_UI_password(client, live_server, measure_memory_usage, datastore_path):
|
||||
|
||||
|
||||
|
||||
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
|
||||
|
||||
# Enable password check and diff page access bypass
|
||||
@@ -548,3 +548,172 @@ def test_api_conflict_UI_password(client, live_server, measure_memory_usage, dat
|
||||
assert len(res.json)
|
||||
|
||||
|
||||
def test_api_url_validation(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test URL validation for edge cases in both CREATE and UPDATE endpoints.
|
||||
Addresses security issues where empty/null/invalid URLs could bypass validation.
|
||||
|
||||
This test ensures that:
|
||||
- CREATE endpoint rejects null, empty, and invalid URLs
|
||||
- UPDATE endpoint rejects attempts to change URL to null, empty, or invalid
|
||||
- UPDATE endpoint allows updating other fields without touching URL
|
||||
- URL validation properly checks protocol, format, and safety
|
||||
"""
|
||||
|
||||
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
|
||||
set_original_response(datastore_path=datastore_path)
|
||||
test_url = url_for('test_endpoint', _external=True)
|
||||
|
||||
# Test 1: CREATE with null URL should fail
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({"url": None}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert res.status_code == 400, "Creating watch with null URL should fail"
|
||||
|
||||
# Test 2: CREATE with empty string URL should fail
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({"url": ""}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert res.status_code == 400, "Creating watch with empty string URL should fail"
|
||||
assert b'Invalid or unsupported URL' in res.data or b'required' in res.data.lower()
|
||||
|
||||
# Test 3: CREATE with whitespace-only URL should fail
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({"url": " "}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert res.status_code == 400, "Creating watch with whitespace-only URL should fail"
|
||||
|
||||
# Test 4: CREATE with invalid protocol should fail
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({"url": "javascript:alert(1)"}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert res.status_code == 400, "Creating watch with javascript: protocol should fail"
|
||||
|
||||
# Test 5: CREATE with missing protocol should fail
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({"url": "example.com"}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert res.status_code == 400, "Creating watch without protocol should fail"
|
||||
|
||||
# Test 6: CREATE with valid URL should succeed (baseline)
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({"url": test_url, "title": "Valid URL test"}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
follow_redirects=True
|
||||
)
|
||||
assert res.status_code == 201, "Creating watch with valid URL should succeed"
|
||||
assert is_valid_uuid(res.json.get('uuid'))
|
||||
watch_uuid = res.json.get('uuid')
|
||||
wait_for_all_checks(client)
|
||||
|
||||
# Test 7: UPDATE to null URL should fail
|
||||
res = client.put(
|
||||
url_for("watch", uuid=watch_uuid),
|
||||
headers={'x-api-key': api_key, 'content-type': 'application/json'},
|
||||
data=json.dumps({"url": None}),
|
||||
)
|
||||
assert res.status_code == 400, "Updating watch URL to null should fail"
|
||||
# Accept either OpenAPI validation error or our custom validation error
|
||||
assert b'URL cannot be null' in res.data or b'OpenAPI validation failed' in res.data or b'validation error' in res.data.lower()
|
||||
|
||||
# Test 8: UPDATE to empty string URL should fail
|
||||
res = client.put(
|
||||
url_for("watch", uuid=watch_uuid),
|
||||
headers={'x-api-key': api_key, 'content-type': 'application/json'},
|
||||
data=json.dumps({"url": ""}),
|
||||
)
|
||||
assert res.status_code == 400, "Updating watch URL to empty string should fail"
|
||||
# Accept either our custom validation error or OpenAPI/schema validation error
|
||||
assert b'URL cannot be empty' in res.data or b'OpenAPI validation' in res.data or b'Invalid or unsupported URL' in res.data
|
||||
|
||||
# Test 9: UPDATE to whitespace-only URL should fail
|
||||
res = client.put(
|
||||
url_for("watch", uuid=watch_uuid),
|
||||
headers={'x-api-key': api_key, 'content-type': 'application/json'},
|
||||
data=json.dumps({"url": " \t\n "}),
|
||||
)
|
||||
assert res.status_code == 400, "Updating watch URL to whitespace should fail"
|
||||
# Accept either our custom validation error or generic validation error
|
||||
assert b'URL cannot be empty' in res.data or b'Invalid or unsupported URL' in res.data or b'validation' in res.data.lower()
|
||||
|
||||
# Test 10: UPDATE to invalid protocol should fail (javascript:)
|
||||
res = client.put(
|
||||
url_for("watch", uuid=watch_uuid),
|
||||
headers={'x-api-key': api_key, 'content-type': 'application/json'},
|
||||
data=json.dumps({"url": "javascript:alert(document.domain)"}),
|
||||
)
|
||||
assert res.status_code == 400, "Updating watch URL to XSS attempt should fail"
|
||||
assert b'Invalid or unsupported URL' in res.data or b'protocol' in res.data.lower()
|
||||
|
||||
# Test 11: UPDATE to file:// protocol should fail (unless ALLOW_FILE_URI is set)
|
||||
res = client.put(
|
||||
url_for("watch", uuid=watch_uuid),
|
||||
headers={'x-api-key': api_key, 'content-type': 'application/json'},
|
||||
data=json.dumps({"url": "file:///etc/passwd"}),
|
||||
)
|
||||
assert res.status_code == 400, "Updating watch URL to file:// should fail by default"
|
||||
|
||||
# Test 12: UPDATE other fields without URL should succeed
|
||||
res = client.put(
|
||||
url_for("watch", uuid=watch_uuid),
|
||||
headers={'x-api-key': api_key, 'content-type': 'application/json'},
|
||||
data=json.dumps({"title": "Updated title without URL change"}),
|
||||
)
|
||||
assert res.status_code == 200, "Updating other fields without URL should succeed"
|
||||
|
||||
# Test 13: Verify URL is still valid after non-URL update
|
||||
res = client.get(
|
||||
url_for("watch", uuid=watch_uuid),
|
||||
headers={'x-api-key': api_key}
|
||||
)
|
||||
assert res.json.get('url') == test_url, "URL should remain unchanged"
|
||||
assert res.json.get('title') == "Updated title without URL change"
|
||||
|
||||
# Test 14: UPDATE to valid different URL should succeed
|
||||
new_valid_url = test_url + "?new=param"
|
||||
res = client.put(
|
||||
url_for("watch", uuid=watch_uuid),
|
||||
headers={'x-api-key': api_key, 'content-type': 'application/json'},
|
||||
data=json.dumps({"url": new_valid_url}),
|
||||
)
|
||||
assert res.status_code == 200, "Updating to valid different URL should succeed"
|
||||
|
||||
# Test 15: Verify URL was actually updated
|
||||
res = client.get(
|
||||
url_for("watch", uuid=watch_uuid),
|
||||
headers={'x-api-key': api_key}
|
||||
)
|
||||
assert res.json.get('url') == new_valid_url, "URL should be updated to new valid URL"
|
||||
|
||||
# Test 16: CREATE with XSS in URL parameters should fail
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({"url": "http://example.com?xss=<script>alert(1)</script>"}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
follow_redirects=True
|
||||
)
|
||||
# This should fail because of suspicious characters check
|
||||
assert res.status_code == 400, "Creating watch with XSS in URL params should fail"
|
||||
|
||||
# Cleanup
|
||||
client.delete(
|
||||
url_for("watch", uuid=watch_uuid),
|
||||
headers={'x-api-key': api_key},
|
||||
)
|
||||
delete_all_watches(client)
|
||||
|
||||
805
changedetectionio/tests/test_api_security.py
Normal file
805
changedetectionio/tests/test_api_security.py
Normal file
@@ -0,0 +1,805 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Comprehensive security and edge case tests for the API.
|
||||
Tests critical areas that were identified as gaps in the existing test suite.
|
||||
"""
|
||||
|
||||
import time
|
||||
import json
|
||||
import threading
|
||||
import uuid as uuid_module
|
||||
from flask import url_for
|
||||
from .util import live_server_setup, wait_for_all_checks, delete_all_watches
|
||||
import os
|
||||
|
||||
|
||||
def set_original_response(datastore_path):
|
||||
test_return_data = """<html>
|
||||
<body>
|
||||
Some initial text<br>
|
||||
<p>Which is across multiple lines</p>
|
||||
</body>
|
||||
</html>
|
||||
"""
|
||||
with open(os.path.join(datastore_path, "endpoint-content.txt"), "w") as f:
|
||||
f.write(test_return_data)
|
||||
return None
|
||||
|
||||
|
||||
def is_valid_uuid(val):
|
||||
try:
|
||||
uuid_module.UUID(str(val))
|
||||
return True
|
||||
except ValueError:
|
||||
return False
|
||||
|
||||
|
||||
# ============================================================================
|
||||
# TIER 1: CRITICAL SECURITY TESTS
|
||||
# ============================================================================
|
||||
|
||||
def test_api_path_traversal_in_uuids(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test that path traversal attacks via UUID parameter are blocked.
|
||||
Addresses CVE-like vulnerabilities where ../../../ in UUID could access arbitrary files.
|
||||
"""
|
||||
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
|
||||
set_original_response(datastore_path=datastore_path)
|
||||
test_url = url_for('test_endpoint', _external=True)
|
||||
|
||||
# Create a valid watch first
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({"url": test_url, "title": "Valid watch"}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
assert res.status_code == 201
|
||||
valid_uuid = res.json.get('uuid')
|
||||
|
||||
# Test 1: Path traversal with ../../../
|
||||
res = client.get(
|
||||
f"/api/v1/watch/../../etc/passwd",
|
||||
headers={'x-api-key': api_key}
|
||||
)
|
||||
assert res.status_code in [400, 404], "Path traversal should be rejected"
|
||||
|
||||
# Test 2: Encoded path traversal
|
||||
res = client.get(
|
||||
"/api/v1/watch/..%2F..%2F..%2Fetc%2Fpasswd",
|
||||
headers={'x-api-key': api_key}
|
||||
)
|
||||
assert res.status_code in [400, 404], "Encoded path traversal should be rejected"
|
||||
|
||||
# Test 3: Double-encoded path traversal
|
||||
res = client.get(
|
||||
"/api/v1/watch/%2e%2e%2f%2e%2e%2f%2e%2e%2f",
|
||||
headers={'x-api-key': api_key}
|
||||
)
|
||||
assert res.status_code in [400, 404], "Double-encoded traversal should be rejected"
|
||||
|
||||
# Test 4: Try to access datastore file
|
||||
res = client.get(
|
||||
"/api/v1/watch/../url-watches.json",
|
||||
headers={'x-api-key': api_key}
|
||||
)
|
||||
assert res.status_code in [400, 404], "Access to datastore should be blocked"
|
||||
|
||||
# Test 5: Null byte injection
|
||||
res = client.get(
|
||||
f"/api/v1/watch/{valid_uuid}%00.json",
|
||||
headers={'x-api-key': api_key}
|
||||
)
|
||||
# Should either work (ignoring null byte) or reject - but not crash
|
||||
assert res.status_code in [200, 400, 404]
|
||||
|
||||
# Test 6: DELETE with path traversal
|
||||
res = client.delete(
|
||||
"/api/v1/watch/../../datastore/url-watches.json",
|
||||
headers={'x-api-key': api_key}
|
||||
)
|
||||
assert res.status_code in [400, 404, 405], "DELETE with traversal should be blocked (405=method not allowed is also acceptable)"
|
||||
|
||||
# Cleanup
|
||||
client.delete(url_for("watch", uuid=valid_uuid), headers={'x-api-key': api_key})
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
def test_api_injection_via_headers_and_proxy(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test that injection attacks via headers and proxy fields are properly sanitized.
|
||||
Addresses XSS and injection vulnerabilities.
|
||||
"""
|
||||
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
|
||||
set_original_response(datastore_path=datastore_path)
|
||||
test_url = url_for('test_endpoint', _external=True)
|
||||
|
||||
# Test 1: XSS in headers
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"headers": {
|
||||
"User-Agent": "<script>alert(1)</script>",
|
||||
"X-Custom": "'; DROP TABLE watches; --"
|
||||
}
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Headers are metadata used for HTTP requests, not HTML rendering
|
||||
# Storing them as-is is expected behavior
|
||||
assert res.status_code in [201, 400]
|
||||
if res.status_code == 201:
|
||||
watch_uuid = res.json.get('uuid')
|
||||
# Verify headers are stored (API returns JSON, not HTML, so no XSS risk)
|
||||
res = client.get(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
assert res.status_code == 200
|
||||
client.delete(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
|
||||
# Test 2: Null bytes in headers
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"headers": {"X-Test": "value\x00null"}
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should handle null bytes gracefully (reject or sanitize)
|
||||
assert res.status_code in [201, 400]
|
||||
|
||||
# Test 3: Malformed proxy string
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"proxy": "http://evil.com:8080@victim.com"
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should reject invalid proxy format
|
||||
assert res.status_code == 400
|
||||
|
||||
# Test 4: Control characters in notification title
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"notification_title": "Test\r\nInjected-Header: value"
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should accept but sanitize control characters
|
||||
if res.status_code == 201:
|
||||
watch_uuid = res.json.get('uuid')
|
||||
client.delete(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
def test_api_large_payload_dos(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test that excessively large payloads are rejected to prevent DoS.
|
||||
Addresses memory leak issues found in changelog.
|
||||
"""
|
||||
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
|
||||
set_original_response(datastore_path=datastore_path)
|
||||
test_url = url_for('test_endpoint', _external=True)
|
||||
|
||||
# Test 1: Huge ignore_text array
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"ignore_text": ["a" * 10000] * 100 # 1MB of data
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should either accept (with limits) or reject
|
||||
if res.status_code == 201:
|
||||
watch_uuid = res.json.get('uuid')
|
||||
client.delete(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
|
||||
# Test 2: Massive headers object
|
||||
huge_headers = {f"X-Header-{i}": "x" * 1000 for i in range(100)}
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"headers": huge_headers
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should reject or truncate
|
||||
assert res.status_code in [201, 400, 413]
|
||||
if res.status_code == 201:
|
||||
watch_uuid = res.json.get('uuid')
|
||||
client.delete(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
|
||||
# Test 3: Huge browser_steps array
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"browser_steps": [
|
||||
{"operation": "click", "selector": "#test" * 1000, "optional_value": ""}
|
||||
] * 100
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should reject or limit
|
||||
assert res.status_code in [201, 400, 413]
|
||||
if res.status_code == 201:
|
||||
watch_uuid = res.json.get('uuid')
|
||||
client.delete(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
|
||||
# Test 4: Extremely long title
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"title": "x" * 100000 # 100KB title
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should reject (exceeds maxLength: 5000)
|
||||
assert res.status_code == 400
|
||||
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
def test_api_utf8_encoding_edge_cases(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test UTF-8 encoding edge cases that have caused bugs on Windows.
|
||||
Addresses 18+ encoding bugs from changelog.
|
||||
"""
|
||||
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
|
||||
set_original_response(datastore_path=datastore_path)
|
||||
test_url = url_for('test_endpoint', _external=True)
|
||||
|
||||
# Test 1: Unicode in title (should work)
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"title": "Test 中文 Ελληνικά 日本語 🔥"
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
assert res.status_code == 201
|
||||
watch_uuid = res.json.get('uuid')
|
||||
|
||||
# Verify it round-trips correctly
|
||||
res = client.get(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
assert res.status_code == 200
|
||||
assert "中文" in res.json.get('title')
|
||||
|
||||
client.delete(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
|
||||
# Test 2: Unicode in URL query parameters
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url + "?search=日本語"
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should handle URL encoding properly
|
||||
assert res.status_code in [201, 400]
|
||||
if res.status_code == 201:
|
||||
watch_uuid = res.json.get('uuid')
|
||||
client.delete(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
|
||||
# Test 3: Null byte in title (should be rejected or sanitized)
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"title": "Test\x00Title"
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should handle gracefully
|
||||
assert res.status_code in [201, 400]
|
||||
if res.status_code == 201:
|
||||
watch_uuid = res.json.get('uuid')
|
||||
client.delete(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
|
||||
# Test 4: BOM (Byte Order Mark) in title
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"title": "\ufeffTest with BOM"
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
assert res.status_code in [201, 400]
|
||||
if res.status_code == 201:
|
||||
watch_uuid = res.json.get('uuid')
|
||||
client.delete(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
def test_api_concurrency_race_conditions(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test concurrent API requests to detect race conditions.
|
||||
Addresses 20+ concurrency bugs from changelog.
|
||||
"""
|
||||
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
|
||||
set_original_response(datastore_path=datastore_path)
|
||||
test_url = url_for('test_endpoint', _external=True)
|
||||
|
||||
# Create a watch
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({"url": test_url, "title": "Concurrency test"}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
assert res.status_code == 201
|
||||
watch_uuid = res.json.get('uuid')
|
||||
wait_for_all_checks(client)
|
||||
|
||||
# Test 1: Concurrent updates to same watch
|
||||
# Note: Flask test client is not thread-safe, so we test sequential updates instead
|
||||
# Real concurrency issues would be caught in integration tests with actual HTTP requests
|
||||
results = []
|
||||
for i in range(10):
|
||||
try:
|
||||
r = client.put(
|
||||
url_for("watch", uuid=watch_uuid),
|
||||
data=json.dumps({"title": f"Title {i}"}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
results.append(r.status_code)
|
||||
except Exception as e:
|
||||
results.append(str(e))
|
||||
|
||||
# All updates should succeed (200) without crashes
|
||||
assert all(r == 200 for r in results), f"Some updates failed: {results}"
|
||||
|
||||
# Test 2: Update while watch is being checked
|
||||
# Queue a recheck
|
||||
client.get(
|
||||
url_for("watch", uuid=watch_uuid, recheck=True),
|
||||
headers={'x-api-key': api_key}
|
||||
)
|
||||
|
||||
# Immediately update it
|
||||
res = client.put(
|
||||
url_for("watch", uuid=watch_uuid),
|
||||
data=json.dumps({"title": "Updated during check"}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should succeed without error
|
||||
assert res.status_code == 200
|
||||
|
||||
# Test 3: Delete watch that's being processed
|
||||
# Create another watch
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({"url": test_url}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
watch_uuid2 = res.json.get('uuid')
|
||||
|
||||
# Queue it for checking
|
||||
client.get(url_for("watch", uuid=watch_uuid2, recheck=True), headers={'x-api-key': api_key})
|
||||
|
||||
# Immediately delete it
|
||||
res = client.delete(url_for("watch", uuid=watch_uuid2), headers={'x-api-key': api_key})
|
||||
# Should succeed or return appropriate error
|
||||
assert res.status_code in [204, 404, 400]
|
||||
|
||||
# Cleanup
|
||||
client.delete(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
# ============================================================================
|
||||
# TIER 2: IMPORTANT FUNCTIONALITY TESTS
|
||||
# ============================================================================
|
||||
|
||||
def test_api_time_validation_edge_cases(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test time_between_check validation edge cases.
|
||||
"""
|
||||
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
|
||||
set_original_response(datastore_path=datastore_path)
|
||||
test_url = url_for('test_endpoint', _external=True)
|
||||
|
||||
# Test 1: Zero interval
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"time_between_check_use_default": False,
|
||||
"time_between_check": {"seconds": 0}
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
assert res.status_code == 400, "Zero interval should be rejected"
|
||||
|
||||
# Test 2: Negative interval
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"time_between_check_use_default": False,
|
||||
"time_between_check": {"seconds": -100}
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
assert res.status_code == 400, "Negative interval should be rejected"
|
||||
|
||||
# Test 3: All fields null with use_default=false
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"time_between_check_use_default": False,
|
||||
"time_between_check": {"weeks": None, "days": None, "hours": None, "minutes": None, "seconds": None}
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
assert res.status_code == 400, "All null intervals should be rejected when not using default"
|
||||
|
||||
# Test 4: Extremely large interval (overflow risk)
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"time_between_check_use_default": False,
|
||||
"time_between_check": {"weeks": 999999999}
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should either accept (with limits) or reject
|
||||
assert res.status_code in [201, 400]
|
||||
if res.status_code == 201:
|
||||
watch_uuid = res.json.get('uuid')
|
||||
client.delete(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
|
||||
# Test 5: Valid minimal interval (should work)
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"time_between_check_use_default": False,
|
||||
"time_between_check": {"seconds": 60}
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
assert res.status_code == 201
|
||||
watch_uuid = res.json.get('uuid')
|
||||
client.delete(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
def test_api_browser_steps_validation(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test browser_steps validation for invalid operations and structures.
|
||||
"""
|
||||
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
|
||||
set_original_response(datastore_path=datastore_path)
|
||||
test_url = url_for('test_endpoint', _external=True)
|
||||
|
||||
# Test 1: Empty browser step
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"browser_steps": [
|
||||
{"operation": "", "selector": "", "optional_value": ""}
|
||||
]
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should accept (empty is valid as null)
|
||||
assert res.status_code in [201, 400]
|
||||
if res.status_code == 201:
|
||||
watch_uuid = res.json.get('uuid')
|
||||
client.delete(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
|
||||
# Test 2: Invalid operation type
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"browser_steps": [
|
||||
{"operation": "invalid_operation", "selector": "#test", "optional_value": ""}
|
||||
]
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should accept (validation happens at runtime) or reject
|
||||
assert res.status_code in [201, 400]
|
||||
if res.status_code == 201:
|
||||
watch_uuid = res.json.get('uuid')
|
||||
client.delete(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
|
||||
# Test 3: Missing required fields in browser step
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"browser_steps": [
|
||||
{"operation": "click"} # Missing selector and optional_value
|
||||
]
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should be rejected due to schema validation
|
||||
assert res.status_code == 400
|
||||
|
||||
# Test 4: Extra fields in browser step
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"browser_steps": [
|
||||
{"operation": "click", "selector": "#test", "optional_value": "", "extra_field": "value"}
|
||||
]
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should be rejected due to additionalProperties: false
|
||||
assert res.status_code == 400
|
||||
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
def test_api_queue_manipulation(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test queue behavior under stress and edge cases.
|
||||
"""
|
||||
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
|
||||
set_original_response(datastore_path=datastore_path)
|
||||
test_url = url_for('test_endpoint', _external=True)
|
||||
|
||||
# Test 1: Create many watches rapidly
|
||||
watch_uuids = []
|
||||
for i in range(20):
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({"url": test_url, "title": f"Watch {i}"}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
if res.status_code == 201:
|
||||
watch_uuids.append(res.json.get('uuid'))
|
||||
|
||||
assert len(watch_uuids) == 20, "Should be able to create 20 watches"
|
||||
|
||||
# Test 2: Recheck all when watches exist
|
||||
res = client.get(
|
||||
url_for("createwatch", recheck_all='1'),
|
||||
headers={'x-api-key': api_key},
|
||||
)
|
||||
# Should return success (200 or 202 for background processing)
|
||||
assert res.status_code in [200, 202]
|
||||
|
||||
# Test 3: Verify queue doesn't overflow with moderate load
|
||||
# The app has MAX_QUEUE_SIZE = 5000, we're well below that
|
||||
wait_for_all_checks(client)
|
||||
|
||||
# Cleanup
|
||||
for uuid in watch_uuids:
|
||||
client.delete(url_for("watch", uuid=uuid), headers={'x-api-key': api_key})
|
||||
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
# ============================================================================
|
||||
# TIER 3: EDGE CASES & POLISH
|
||||
# ============================================================================
|
||||
|
||||
def test_api_history_edge_cases(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test history API with invalid timestamps and edge cases.
|
||||
"""
|
||||
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
|
||||
set_original_response(datastore_path=datastore_path)
|
||||
test_url = url_for('test_endpoint', _external=True)
|
||||
|
||||
# Create watch and generate history
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({"url": test_url}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
watch_uuid = res.json.get('uuid')
|
||||
wait_for_all_checks(client)
|
||||
|
||||
# Test 1: Get history with invalid timestamp
|
||||
res = client.get(
|
||||
url_for("watchsinglehistory", uuid=watch_uuid, timestamp="invalid"),
|
||||
headers={'x-api-key': api_key}
|
||||
)
|
||||
assert res.status_code == 404, "Invalid timestamp should return 404"
|
||||
|
||||
# Test 2: Future timestamp
|
||||
res = client.get(
|
||||
url_for("watchsinglehistory", uuid=watch_uuid, timestamp="9999999999"),
|
||||
headers={'x-api-key': api_key}
|
||||
)
|
||||
assert res.status_code == 404, "Future timestamp should return 404"
|
||||
|
||||
# Test 3: Negative timestamp
|
||||
res = client.get(
|
||||
url_for("watchsinglehistory", uuid=watch_uuid, timestamp="-1"),
|
||||
headers={'x-api-key': api_key}
|
||||
)
|
||||
assert res.status_code == 404, "Negative timestamp should return 404"
|
||||
|
||||
# Test 4: Diff with reversed timestamps (from > to)
|
||||
# First get actual timestamps
|
||||
res = client.get(
|
||||
url_for("watchhistory", uuid=watch_uuid),
|
||||
headers={'x-api-key': api_key}
|
||||
)
|
||||
if len(res.json) >= 2:
|
||||
timestamps = sorted(res.json.keys())
|
||||
# Try reversed order
|
||||
res = client.get(
|
||||
url_for("watchhistorydiff", uuid=watch_uuid, from_timestamp=timestamps[-1], to_timestamp=timestamps[0]),
|
||||
headers={'x-api-key': api_key}
|
||||
)
|
||||
# Should either work (show reverse diff) or return error
|
||||
assert res.status_code in [200, 400]
|
||||
|
||||
# Cleanup
|
||||
client.delete(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
def test_api_notification_edge_cases(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test notification configuration edge cases.
|
||||
"""
|
||||
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
|
||||
set_original_response(datastore_path=datastore_path)
|
||||
test_url = url_for('test_endpoint', _external=True)
|
||||
|
||||
# Test 1: Invalid notification URL
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"notification_urls": ["invalid://url", "ftp://test.com"]
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should accept (apprise validates at runtime) or reject
|
||||
assert res.status_code in [201, 400]
|
||||
if res.status_code == 201:
|
||||
watch_uuid = res.json.get('uuid')
|
||||
client.delete(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
|
||||
# Test 2: Invalid notification format
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"notification_format": "invalid_format"
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should be rejected by schema
|
||||
assert res.status_code == 400
|
||||
|
||||
# Test 3: Empty notification arrays
|
||||
res = client.post(
|
||||
url_for("createwatch"),
|
||||
data=json.dumps({
|
||||
"url": test_url,
|
||||
"notification_urls": []
|
||||
}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should accept (empty is valid)
|
||||
assert res.status_code == 201
|
||||
watch_uuid = res.json.get('uuid')
|
||||
client.delete(url_for("watch", uuid=watch_uuid), headers={'x-api-key': api_key})
|
||||
|
||||
delete_all_watches(client)
|
||||
|
||||
|
||||
def test_api_tag_edge_cases(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test tag/group API edge cases including XSS and path traversal.
|
||||
"""
|
||||
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
|
||||
|
||||
# Test 1: Empty tag title
|
||||
res = client.post(
|
||||
url_for("tag"),
|
||||
data=json.dumps({"title": ""}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should be rejected (empty title)
|
||||
assert res.status_code == 400
|
||||
|
||||
# Test 2: XSS in tag title
|
||||
res = client.post(
|
||||
url_for("tag"),
|
||||
data=json.dumps({"title": "<script>alert(1)</script>"}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should accept but sanitize
|
||||
if res.status_code == 201:
|
||||
tag_uuid = res.json.get('uuid')
|
||||
# Verify title is stored safely
|
||||
res = client.get(url_for("tag", uuid=tag_uuid), headers={'x-api-key': api_key})
|
||||
# Should be escaped or sanitized
|
||||
client.delete(url_for("tag", uuid=tag_uuid), headers={'x-api-key': api_key})
|
||||
|
||||
# Test 3: Path traversal in tag title
|
||||
res = client.post(
|
||||
url_for("tag"),
|
||||
data=json.dumps({"title": "../../etc/passwd"}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should accept (it's just a string, not a path)
|
||||
if res.status_code == 201:
|
||||
tag_uuid = res.json.get('uuid')
|
||||
client.delete(url_for("tag", uuid=tag_uuid), headers={'x-api-key': api_key})
|
||||
|
||||
# Test 4: Very long tag title
|
||||
res = client.post(
|
||||
url_for("tag"),
|
||||
data=json.dumps({"title": "x" * 10000}),
|
||||
headers={'content-type': 'application/json', 'x-api-key': api_key},
|
||||
)
|
||||
# Should be rejected (exceeds maxLength)
|
||||
assert res.status_code == 400
|
||||
|
||||
|
||||
def test_api_authentication_edge_cases(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test API authentication edge cases.
|
||||
"""
|
||||
api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
|
||||
set_original_response(datastore_path=datastore_path)
|
||||
test_url = url_for('test_endpoint', _external=True)
|
||||
|
||||
# Test 1: Missing API key
|
||||
res = client.get(url_for("createwatch"))
|
||||
assert res.status_code == 403, "Missing API key should be forbidden"
|
||||
|
||||
# Test 2: Invalid API key
|
||||
res = client.get(
|
||||
url_for("createwatch"),
|
||||
headers={'x-api-key': "invalid_key_12345"}
|
||||
)
|
||||
assert res.status_code == 403, "Invalid API key should be forbidden"
|
||||
|
||||
# Test 3: API key with special characters
|
||||
res = client.get(
|
||||
url_for("createwatch"),
|
||||
headers={'x-api-key': "key<script>alert(1)</script>"}
|
||||
)
|
||||
assert res.status_code == 403, "Invalid API key should be forbidden"
|
||||
|
||||
# Test 4: Very long API key
|
||||
res = client.get(
|
||||
url_for("createwatch"),
|
||||
headers={'x-api-key': "x" * 10000}
|
||||
)
|
||||
assert res.status_code == 403, "Invalid API key should be forbidden"
|
||||
|
||||
# Test 5: Case sensitivity of API key
|
||||
wrong_case_key = api_key.upper() if api_key.islower() else api_key.lower()
|
||||
res = client.get(
|
||||
url_for("createwatch"),
|
||||
headers={'x-api-key': wrong_case_key}
|
||||
)
|
||||
# Should be forbidden (keys are case-sensitive)
|
||||
assert res.status_code == 403, "Wrong case API key should be forbidden"
|
||||
|
||||
# Test 6: Valid API key should work
|
||||
res = client.get(
|
||||
url_for("createwatch"),
|
||||
headers={'x-api-key': api_key}
|
||||
)
|
||||
assert res.status_code == 200, "Valid API key should work"
|
||||
@@ -160,7 +160,7 @@ def test_invalid_locale(client, live_server, measure_memory_usage, datastore_pat
|
||||
def test_language_persistence_in_session(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test that the language preference persists across multiple requests
|
||||
within the same session.
|
||||
within the same session, and that auto-detect properly clears the preference.
|
||||
"""
|
||||
|
||||
# Establish session cookie
|
||||
@@ -184,6 +184,34 @@ def test_language_persistence_in_session(client, live_server, measure_memory_usa
|
||||
assert res.status_code == 200
|
||||
assert b"Annulla" in res.data, "Italian text should persist across requests"
|
||||
|
||||
# Verify locale is in session
|
||||
with client.session_transaction() as sess:
|
||||
assert sess.get('locale') == 'it', "Locale should be set in session"
|
||||
|
||||
# Call auto-detect to clear the locale
|
||||
res = client.get(
|
||||
url_for("ui.delete_locale_language_session_var_if_it_exists"),
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
assert res.status_code == 200
|
||||
# Verify the flash message appears (in English since we cleared the locale)
|
||||
assert b"Language set to auto-detect from browser" in res.data, "Should show flash message"
|
||||
|
||||
# Verify locale was removed from session
|
||||
with client.session_transaction() as sess:
|
||||
assert 'locale' not in sess, "Locale should be removed from session after auto-detect"
|
||||
|
||||
# Now requests should use browser default (English in test environment)
|
||||
res = client.get(
|
||||
url_for("watchlist.index"),
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
assert res.status_code == 200
|
||||
assert b"Cancel" in res.data, "Should show English after auto-detect clears Italian"
|
||||
assert b"Annulla" not in res.data, "Should not show Italian after auto-detect"
|
||||
|
||||
|
||||
def test_set_language_with_redirect(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
@@ -225,3 +253,374 @@ def test_set_language_with_redirect(client, live_server, measure_memory_usage, d
|
||||
assert res.status_code in [302, 303]
|
||||
# Should not redirect to evil.com
|
||||
assert 'evil.com' not in res.location
|
||||
|
||||
|
||||
def test_time_unit_translations(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test that time unit labels (Hours, Minutes, Seconds) and Chrome Extension
|
||||
are correctly translated on the settings page for all supported languages.
|
||||
"""
|
||||
from flask import url_for
|
||||
|
||||
# Establish session cookie
|
||||
client.get(url_for("watchlist.index"), follow_redirects=True)
|
||||
|
||||
# Test Italian translations
|
||||
res = client.get(url_for("set_language", locale="it"), follow_redirects=True)
|
||||
assert res.status_code == 200
|
||||
|
||||
res = client.get(url_for("settings.settings_page"), follow_redirects=True)
|
||||
assert res.status_code == 200
|
||||
|
||||
# Check that Italian translations are present (not English)
|
||||
assert b"Minutes" not in res.data or b"Minuti" in res.data, "Expected Italian 'Minuti' not English 'Minutes'"
|
||||
assert b"Ore" in res.data, "Expected Italian 'Ore' for Hours"
|
||||
assert b"Minuti" in res.data, "Expected Italian 'Minuti' for Minutes"
|
||||
assert b"Secondi" in res.data, "Expected Italian 'Secondi' for Seconds"
|
||||
assert b"Estensione Chrome" in res.data, "Expected Italian 'Estensione Chrome' for Chrome Extension"
|
||||
assert b"Intervallo tra controlli" in res.data, "Expected Italian 'Intervallo tra controlli' for Time Between Check"
|
||||
assert b"Time Between Check" not in res.data, "Should not have English 'Time Between Check'"
|
||||
|
||||
# Test Korean translations
|
||||
res = client.get(url_for("set_language", locale="ko"), follow_redirects=True)
|
||||
assert res.status_code == 200
|
||||
|
||||
res = client.get(url_for("settings.settings_page"), follow_redirects=True)
|
||||
assert res.status_code == 200
|
||||
|
||||
# Check that Korean translations are present (not English)
|
||||
# Korean: Hours=시간, Minutes=분, Seconds=초, Chrome Extension=Chrome 확장 프로그램, Time Between Check=확인 간격
|
||||
assert "시간".encode() in res.data, "Expected Korean '시간' for Hours"
|
||||
assert "분".encode() in res.data, "Expected Korean '분' for Minutes"
|
||||
assert "초".encode() in res.data, "Expected Korean '초' for Seconds"
|
||||
assert "Chrome 확장 프로그램".encode() in res.data, "Expected Korean 'Chrome 확장 프로그램' for Chrome Extension"
|
||||
assert "확인 간격".encode() in res.data, "Expected Korean '확인 간격' for Time Between Check"
|
||||
# Make sure we don't have the incorrect translations
|
||||
assert "목요일".encode() not in res.data, "Should not have '목요일' (Thursday) for Hours"
|
||||
assert "무음".encode() not in res.data, "Should not have '무음' (Mute) for Minutes"
|
||||
assert "Chrome 요청".encode() not in res.data, "Should not have 'Chrome 요청' (Chrome requests) for Chrome Extension"
|
||||
assert b"Time Between Check" not in res.data, "Should not have English 'Time Between Check'"
|
||||
|
||||
# Test Chinese Simplified translations
|
||||
res = client.get(url_for("set_language", locale="zh"), follow_redirects=True)
|
||||
assert res.status_code == 200
|
||||
|
||||
res = client.get(url_for("settings.settings_page"), follow_redirects=True)
|
||||
assert res.status_code == 200
|
||||
|
||||
# Check that Chinese translations are present
|
||||
# Chinese: Hours=小时, Minutes=分钟, Seconds=秒, Chrome Extension=Chrome 扩展程序, Time Between Check=检查间隔
|
||||
assert "小时".encode() in res.data, "Expected Chinese '小时' for Hours"
|
||||
assert "分钟".encode() in res.data, "Expected Chinese '分钟' for Minutes"
|
||||
assert "秒".encode() in res.data, "Expected Chinese '秒' for Seconds"
|
||||
assert "Chrome 扩展程序".encode() in res.data, "Expected Chinese 'Chrome 扩展程序' for Chrome Extension"
|
||||
assert "检查间隔".encode() in res.data, "Expected Chinese '检查间隔' for Time Between Check"
|
||||
assert b"Time Between Check" not in res.data, "Should not have English 'Time Between Check'"
|
||||
|
||||
# Test German translations
|
||||
res = client.get(url_for("set_language", locale="de"), follow_redirects=True)
|
||||
assert res.status_code == 200
|
||||
|
||||
res = client.get(url_for("settings.settings_page"), follow_redirects=True)
|
||||
assert res.status_code == 200
|
||||
|
||||
# Check that German translations are present
|
||||
# German: Hours=Stunden, Minutes=Minuten, Seconds=Sekunden, Chrome Extension=Chrome-Erweiterung, Time Between Check=Prüfintervall
|
||||
assert b"Stunden" in res.data, "Expected German 'Stunden' for Hours"
|
||||
assert b"Minuten" in res.data, "Expected German 'Minuten' for Minutes"
|
||||
assert b"Sekunden" in res.data, "Expected German 'Sekunden' for Seconds"
|
||||
assert b"Chrome-Erweiterung" in res.data, "Expected German 'Chrome-Erweiterung' for Chrome Extension"
|
||||
assert b"Time Between Check" not in res.data, "Should not have English 'Time Between Check'"
|
||||
|
||||
# Test Traditional Chinese (zh_Hant_TW) translations
|
||||
res = client.get(url_for("set_language", locale="zh_Hant_TW"), follow_redirects=True)
|
||||
assert res.status_code == 200
|
||||
|
||||
res = client.get(url_for("settings.settings_page"), follow_redirects=True)
|
||||
assert res.status_code == 200
|
||||
|
||||
# Check that Traditional Chinese translations are present (not English)
|
||||
# Traditional Chinese: Hours=小時, Minutes=分鐘, Seconds=秒, Chrome Extension=Chrome 擴充功能, Time Between Check=檢查間隔
|
||||
assert "小時".encode() in res.data, "Expected Traditional Chinese '小時' for Hours"
|
||||
assert "分鐘".encode() in res.data, "Expected Traditional Chinese '分鐘' for Minutes"
|
||||
assert "秒".encode() in res.data, "Expected Traditional Chinese '秒' for Seconds"
|
||||
assert "Chrome 擴充功能".encode() in res.data, "Expected Traditional Chinese 'Chrome 擴充功能' for Chrome Extension"
|
||||
assert "發送測試通知".encode() in res.data, "Expected Traditional Chinese '發送測試通知' for Send test notification"
|
||||
assert "通知除錯記錄".encode() in res.data, "Expected Traditional Chinese '通知除錯記錄' for Notification debug logs"
|
||||
assert "檢查間隔".encode() in res.data, "Expected Traditional Chinese '檢查間隔' for Time Between Check"
|
||||
# Make sure we don't have incorrect English text or wrong translations
|
||||
assert b"Send test notification" not in res.data, "Should not have English 'Send test notification'"
|
||||
assert b"Time Between Check" not in res.data, "Should not have English 'Time Between Check'"
|
||||
assert "Chrome 請求".encode() not in res.data, "Should not have incorrect 'Chrome 請求' (Chrome requests)"
|
||||
assert "使用預設通知".encode() not in res.data, "Should not have incorrect '使用預設通知' (Use default notification)"
|
||||
|
||||
|
||||
def test_accept_language_header_zh_tw(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test that browsers sending zh-TW in Accept-Language header get Traditional Chinese.
|
||||
This tests the locale alias mapping for issue #3779.
|
||||
"""
|
||||
from flask import url_for
|
||||
|
||||
# Clear any session data to simulate a fresh visitor
|
||||
with client.session_transaction() as sess:
|
||||
sess.clear()
|
||||
|
||||
# Request the index page with zh-TW in Accept-Language header (what browsers send)
|
||||
res = client.get(
|
||||
url_for("watchlist.index"),
|
||||
headers={'Accept-Language': 'zh-TW,zh;q=0.9,en;q=0.8'},
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
assert res.status_code == 200
|
||||
|
||||
# Should get Traditional Chinese content, not Simplified Chinese
|
||||
# Traditional: 選擇語言, Simplified: 选择语言
|
||||
assert '選擇語言'.encode() in res.data, "Expected Traditional Chinese '選擇語言' (Select Language)"
|
||||
assert '选择语言'.encode() not in res.data, "Should not get Simplified Chinese '选择语言'"
|
||||
|
||||
# Check HTML lang attribute uses BCP 47 format
|
||||
assert b'<html lang="zh-Hant-TW"' in res.data, "Expected BCP 47 language tag zh-Hant-TW in HTML"
|
||||
|
||||
# Check that the correct flag icon is shown (Taiwan flag for Traditional Chinese)
|
||||
assert b'<span class="fi fi-tw fis" id="language-selector-flag">' in res.data, \
|
||||
"Expected Taiwan flag 'fi fi-tw' for Traditional Chinese"
|
||||
assert b'<span class="fi fi-cn fis" id="language-selector-flag">' not in res.data, \
|
||||
"Should not show China flag 'fi fi-cn' for Traditional Chinese"
|
||||
|
||||
# Verify we're getting Traditional Chinese text throughout the page
|
||||
res = client.get(
|
||||
url_for("settings.settings_page"),
|
||||
headers={'Accept-Language': 'zh-TW,zh;q=0.9,en;q=0.8'},
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
assert res.status_code == 200
|
||||
|
||||
# Check Traditional Chinese translations (not English)
|
||||
assert "小時".encode() in res.data, "Expected Traditional Chinese '小時' for Hours"
|
||||
assert "分鐘".encode() in res.data, "Expected Traditional Chinese '分鐘' for Minutes"
|
||||
assert b"Hours" not in res.data or "小時".encode() in res.data, "Should have Traditional Chinese, not English"
|
||||
|
||||
|
||||
def test_accept_language_header_en_variants(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test that browsers sending en-GB and en-US in Accept-Language header get the correct English variant.
|
||||
This ensures the locale selector works properly for English variants.
|
||||
"""
|
||||
from flask import url_for
|
||||
|
||||
# Test 1: British English (en-GB)
|
||||
with client.session_transaction() as sess:
|
||||
sess.clear()
|
||||
|
||||
res = client.get(
|
||||
url_for("watchlist.index"),
|
||||
headers={'Accept-Language': 'en-GB,en;q=0.9'},
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
assert res.status_code == 200
|
||||
|
||||
# Should get English content
|
||||
assert b"Select Language" in res.data, "Expected English text 'Select Language'"
|
||||
|
||||
# Check HTML lang attribute uses BCP 47 format with hyphen
|
||||
assert b'<html lang="en-GB"' in res.data, "Expected BCP 47 language tag en-GB in HTML"
|
||||
|
||||
# Check that the correct flag icon is shown (UK flag for en-GB)
|
||||
assert b'<span class="fi fi-gb fis" id="language-selector-flag">' in res.data, \
|
||||
"Expected UK flag 'fi fi-gb' for British English"
|
||||
|
||||
# Test 2: American English (en-US)
|
||||
with client.session_transaction() as sess:
|
||||
sess.clear()
|
||||
|
||||
res = client.get(
|
||||
url_for("watchlist.index"),
|
||||
headers={'Accept-Language': 'en-US,en;q=0.9'},
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
assert res.status_code == 200
|
||||
|
||||
# Should get English content
|
||||
assert b"Select Language" in res.data, "Expected English text 'Select Language'"
|
||||
|
||||
# Check HTML lang attribute uses BCP 47 format with hyphen
|
||||
assert b'<html lang="en-US"' in res.data, "Expected BCP 47 language tag en-US in HTML"
|
||||
|
||||
# Check that the correct flag icon is shown (US flag for en-US)
|
||||
assert b'<span class="fi fi-us fis" id="language-selector-flag">' in res.data, \
|
||||
"Expected US flag 'fi fi-us' for American English"
|
||||
|
||||
# Test 3: Generic 'en' should fall back to one of the English variants
|
||||
with client.session_transaction() as sess:
|
||||
sess.clear()
|
||||
|
||||
res = client.get(
|
||||
url_for("watchlist.index"),
|
||||
headers={'Accept-Language': 'en'},
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
assert res.status_code == 200
|
||||
|
||||
# Should get English content (either variant is fine)
|
||||
assert b"Select Language" in res.data, "Expected English text 'Select Language'"
|
||||
|
||||
|
||||
def test_accept_language_header_zh_simplified(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test that browsers sending zh or zh-CN in Accept-Language header get Simplified Chinese.
|
||||
This ensures Simplified Chinese still works correctly and doesn't get confused with Traditional.
|
||||
"""
|
||||
from flask import url_for
|
||||
|
||||
# Test 1: Generic 'zh' should get Simplified Chinese
|
||||
with client.session_transaction() as sess:
|
||||
sess.clear()
|
||||
|
||||
res = client.get(
|
||||
url_for("watchlist.index"),
|
||||
headers={'Accept-Language': 'zh,en;q=0.9'},
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
assert res.status_code == 200
|
||||
|
||||
# Should get Simplified Chinese content, not Traditional Chinese
|
||||
# Simplified: 选择语言, Traditional: 選擇語言
|
||||
assert '选择语言'.encode() in res.data, "Expected Simplified Chinese '选择语言' (Select Language)"
|
||||
assert '選擇語言'.encode() not in res.data, "Should not get Traditional Chinese '選擇語言'"
|
||||
|
||||
# Check HTML lang attribute
|
||||
assert b'<html lang="zh"' in res.data, "Expected language tag zh in HTML"
|
||||
|
||||
# Check that the correct flag icon is shown (China flag for Simplified Chinese)
|
||||
assert b'<span class="fi fi-cn fis" id="language-selector-flag">' in res.data, \
|
||||
"Expected China flag 'fi fi-cn' for Simplified Chinese"
|
||||
assert b'<span class="fi fi-tw fis" id="language-selector-flag">' not in res.data, \
|
||||
"Should not show Taiwan flag 'fi fi-tw' for Simplified Chinese"
|
||||
|
||||
# Test 2: 'zh-CN' should also get Simplified Chinese
|
||||
with client.session_transaction() as sess:
|
||||
sess.clear()
|
||||
|
||||
res = client.get(
|
||||
url_for("watchlist.index"),
|
||||
headers={'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8'},
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
assert res.status_code == 200
|
||||
|
||||
# Should get Simplified Chinese content
|
||||
assert '选择语言'.encode() in res.data, "Expected Simplified Chinese '选择语言' with zh-CN header"
|
||||
assert '選擇語言'.encode() not in res.data, "Should not get Traditional Chinese with zh-CN header"
|
||||
|
||||
# Check that the correct flag icon is shown (China flag for zh-CN)
|
||||
assert b'<span class="fi fi-cn fis" id="language-selector-flag">' in res.data, \
|
||||
"Expected China flag 'fi fi-cn' for zh-CN header"
|
||||
|
||||
# Verify Simplified Chinese in settings page
|
||||
res = client.get(
|
||||
url_for("settings.settings_page"),
|
||||
headers={'Accept-Language': 'zh,en;q=0.9'},
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
assert res.status_code == 200
|
||||
|
||||
# Check Simplified Chinese translations (not Traditional or English)
|
||||
# Simplified: 小时, Traditional: 小時
|
||||
assert "小时".encode() in res.data, "Expected Simplified Chinese '小时' for Hours"
|
||||
assert "分钟".encode() in res.data, "Expected Simplified Chinese '分钟' for Minutes"
|
||||
assert "秒".encode() in res.data, "Expected Simplified Chinese '秒' for Seconds"
|
||||
# Make sure it's not Traditional Chinese
|
||||
assert "小時".encode() not in res.data, "Should not have Traditional Chinese '小時'"
|
||||
assert "分鐘".encode() not in res.data, "Should not have Traditional Chinese '分鐘'"
|
||||
|
||||
|
||||
def test_session_locale_overrides_accept_language(client, live_server, measure_memory_usage, datastore_path):
|
||||
"""
|
||||
Test that session locale preference overrides browser Accept-Language header.
|
||||
|
||||
Scenario:
|
||||
1. Browser auto-detects zh-TW (Traditional Chinese) from Accept-Language header
|
||||
2. User explicitly selects Korean language
|
||||
3. On subsequent page loads, Korean should be shown (not Traditional Chinese)
|
||||
even though the Accept-Language header still says zh-TW
|
||||
|
||||
This tests the session override behavior for issue #3779.
|
||||
"""
|
||||
from flask import url_for
|
||||
|
||||
# Step 1: Clear session and make first request with zh-TW header (auto-detect)
|
||||
with client.session_transaction() as sess:
|
||||
sess.clear()
|
||||
|
||||
res = client.get(
|
||||
url_for("watchlist.index"),
|
||||
headers={'Accept-Language': 'zh-TW,zh;q=0.9,en;q=0.8'},
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
assert res.status_code == 200
|
||||
|
||||
# Should initially get Traditional Chinese from auto-detect
|
||||
assert '選擇語言'.encode() in res.data, "Expected Traditional Chinese '選擇語言' from auto-detect"
|
||||
assert b'<html lang="zh-Hant-TW"' in res.data, "Expected zh-Hant-TW language tag"
|
||||
assert b'<span class="fi fi-tw fis" id="language-selector-flag">' in res.data, \
|
||||
"Expected Taiwan flag 'fi fi-tw' from auto-detect"
|
||||
|
||||
# Step 2: User explicitly selects Korean language
|
||||
res = client.get(
|
||||
url_for("set_language", locale="ko"),
|
||||
headers={'Accept-Language': 'zh-TW,zh;q=0.9,en;q=0.8'}, # Browser still sends zh-TW
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
assert res.status_code == 200
|
||||
|
||||
# Step 3: Make another request with same zh-TW header
|
||||
# Session should override the Accept-Language header
|
||||
res = client.get(
|
||||
url_for("watchlist.index"),
|
||||
headers={'Accept-Language': 'zh-TW,zh;q=0.9,en;q=0.8'}, # Still sending zh-TW!
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
assert res.status_code == 200
|
||||
|
||||
# Should now get Korean (session overrides auto-detect)
|
||||
# Korean: 언어 선택, Traditional Chinese: 選擇語言
|
||||
assert '언어 선택'.encode() in res.data, "Expected Korean '언어 선택' (Select Language) from session"
|
||||
assert '選擇語言'.encode() not in res.data, "Should not get Traditional Chinese when Korean is set in session"
|
||||
|
||||
# Check HTML lang attribute is Korean
|
||||
assert b'<html lang="ko"' in res.data, "Expected Korean language tag 'ko' in HTML"
|
||||
|
||||
# Check that Korean flag is shown (not Taiwan flag)
|
||||
assert b'<span class="fi fi-kr fis" id="language-selector-flag">' in res.data, \
|
||||
"Expected Korean flag 'fi fi-kr' from session preference"
|
||||
assert b'<span class="fi fi-tw fis" id="language-selector-flag">' not in res.data, \
|
||||
"Should not show Taiwan flag when Korean is set in session"
|
||||
|
||||
# Verify Korean text on settings page as well
|
||||
res = client.get(
|
||||
url_for("settings.settings_page"),
|
||||
headers={'Accept-Language': 'zh-TW,zh;q=0.9,en;q=0.8'}, # Still zh-TW!
|
||||
follow_redirects=True
|
||||
)
|
||||
|
||||
assert res.status_code == 200
|
||||
|
||||
# Check Korean translations (not Traditional Chinese or English)
|
||||
# Korean: 시간 (Hours), 분 (Minutes), 초 (Seconds)
|
||||
# Traditional Chinese: 小時, 分鐘, 秒
|
||||
assert "시간".encode() in res.data, "Expected Korean '시간' for Hours"
|
||||
assert "분".encode() in res.data, "Expected Korean '분' for Minutes"
|
||||
assert "小時".encode() not in res.data, "Should not have Traditional Chinese '小時' when Korean is set"
|
||||
assert "分鐘".encode() not in res.data, "Should not have Traditional Chinese '分鐘' when Korean is set"
|
||||
|
||||
@@ -22,14 +22,13 @@ something to trigger<br>
|
||||
def test_content_filter_live_preview(client, live_server, measure_memory_usage, datastore_path):
|
||||
# live_server_setup(live_server) # Setup on conftest per function
|
||||
set_response(datastore_path=datastore_path)
|
||||
|
||||
import time
|
||||
test_url = url_for('test_endpoint', _external=True)
|
||||
|
||||
|
||||
uuid = client.application.config.get('DATASTORE').add_watch(url=test_url)
|
||||
res = client.get(url_for("ui.form_watch_checknow"), follow_redirects=True)
|
||||
assert b'Queued 1 watch for rechecking.' in res.data
|
||||
|
||||
time.sleep(0.5)
|
||||
wait_for_all_checks(client)
|
||||
|
||||
res = client.post(
|
||||
|
||||
@@ -42,6 +42,9 @@ def test_check_notification_error_handling(client, live_server, measure_memory_u
|
||||
)
|
||||
assert b"Updated watch." in res.data
|
||||
|
||||
|
||||
wait_for_all_checks(client)
|
||||
|
||||
found=False
|
||||
for i in range(1, 10):
|
||||
|
||||
|
||||
101
changedetectionio/translations/README.md
Normal file
101
changedetectionio/translations/README.md
Normal file
@@ -0,0 +1,101 @@
|
||||
# Translation Guide
|
||||
|
||||
## Updating Translations
|
||||
|
||||
To maintain consistency and minimize unnecessary changes in translation files, run these commands:
|
||||
|
||||
```bash
|
||||
python setup.py extract_messages # Extract translatable strings
|
||||
python setup.py update_catalog # Update all language files
|
||||
python setup.py compile_catalog # Compile to binary .mo files
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
All translation settings are configured in **`../../setup.cfg`** (single source of truth).
|
||||
|
||||
The configuration below is shown for reference - **edit `setup.cfg` to change settings**:
|
||||
|
||||
```ini
|
||||
[extract_messages]
|
||||
# Extract translatable strings from source code
|
||||
mapping_file = babel.cfg
|
||||
output_file = changedetectionio/translations/messages.pot
|
||||
input_paths = changedetectionio
|
||||
keywords = _ _l gettext
|
||||
# Options to reduce unnecessary changes in .pot files
|
||||
sort_by_file = true # Keeps entries ordered by file path
|
||||
width = 120 # Consistent line width (prevents rewrapping)
|
||||
add_location = file # Show file path only (not line numbers)
|
||||
|
||||
[update_catalog]
|
||||
# Update existing .po files with new strings from .pot
|
||||
# Note: 'locale' is omitted - Babel auto-discovers all catalogs in output_dir
|
||||
input_file = changedetectionio/translations/messages.pot
|
||||
output_dir = changedetectionio/translations
|
||||
domain = messages
|
||||
# Options for consistent formatting
|
||||
width = 120 # Consistent line width
|
||||
no_fuzzy_matching = true # Avoids incorrect automatic matches
|
||||
|
||||
[compile_catalog]
|
||||
# Compile .po files to .mo binary format
|
||||
directory = changedetectionio/translations
|
||||
domain = messages
|
||||
```
|
||||
|
||||
**Key formatting options:**
|
||||
- `sort_by_file = true` - Orders entries by file path (consistent ordering)
|
||||
- `width = 120` - Fixed line width prevents text rewrapping
|
||||
- `add_location = file` - Shows file path only, not line numbers (reduces git churn)
|
||||
- `no_fuzzy_matching = true` - Prevents incorrect automatic fuzzy matches
|
||||
|
||||
## Why Use These Commands?
|
||||
|
||||
Running pybabel commands directly without consistent options causes:
|
||||
- ❌ Entries get reordered differently each time
|
||||
- ❌ Text gets rewrapped at different widths
|
||||
- ❌ Line numbers change every edit (if not configured)
|
||||
- ❌ Large diffs that make code review difficult
|
||||
|
||||
Using `python setup.py` commands ensures:
|
||||
- ✅ Consistent ordering (by file path, not alphabetically)
|
||||
- ✅ Consistent line width (120 characters, no rewrapping)
|
||||
- ✅ File-only locations (no line number churn)
|
||||
- ✅ No fuzzy matching (prevents incorrect auto-translations)
|
||||
- ✅ Minimal diffs (only actual changes show up)
|
||||
- ✅ Easier code review and git history
|
||||
|
||||
These commands read settings from `../../setup.cfg` automatically.
|
||||
|
||||
## Supported Languages
|
||||
|
||||
- `cs` - Czech (Čeština)
|
||||
- `de` - German (Deutsch)
|
||||
- `en_GB` - English (UK)
|
||||
- `en_US` - English (US)
|
||||
- `fr` - French (Français)
|
||||
- `it` - Italian (Italiano)
|
||||
- `ko` - Korean (한국어)
|
||||
- `zh` - Chinese Simplified (中文简体)
|
||||
- `zh_Hant_TW` - Chinese Traditional (繁體中文)
|
||||
|
||||
## Adding a New Language
|
||||
|
||||
1. Initialize the new language catalog:
|
||||
```bash
|
||||
pybabel init -i changedetectionio/translations/messages.pot -d changedetectionio/translations -l NEW_LANG_CODE
|
||||
```
|
||||
2. Compile it:
|
||||
```bash
|
||||
python setup.py compile_catalog
|
||||
```
|
||||
|
||||
Babel will auto-discover the new language on subsequent translation updates.
|
||||
|
||||
## Translation Notes
|
||||
|
||||
From CLAUDE.md:
|
||||
- Always use "monitor" or "watcher" terminology (not "clock")
|
||||
- Use the most brief wording suitable
|
||||
- When finding issues in one language, check ALL languages for the same issue
|
||||
Binary file not shown.
File diff suppressed because it is too large
Load Diff
Binary file not shown.
File diff suppressed because it is too large
Load Diff
Binary file not shown.
File diff suppressed because it is too large
Load Diff
Binary file not shown.
File diff suppressed because it is too large
Load Diff
Binary file not shown.
File diff suppressed because it is too large
Load Diff
Binary file not shown.
File diff suppressed because it is too large
Load Diff
Binary file not shown.
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Binary file not shown.
File diff suppressed because it is too large
Load Diff
Binary file not shown.
File diff suppressed because it is too large
Load Diff
@@ -64,6 +64,19 @@ def is_safe_valid_url(test_url):
|
||||
import re
|
||||
import validators
|
||||
|
||||
# Validate input type first - must be a non-empty string
|
||||
if test_url is None:
|
||||
logger.warning('URL validation failed: URL is None')
|
||||
return False
|
||||
|
||||
if not isinstance(test_url, str):
|
||||
logger.warning(f'URL validation failed: URL must be a string, got {type(test_url).__name__}')
|
||||
return False
|
||||
|
||||
if not test_url.strip():
|
||||
logger.warning('URL validation failed: URL is empty or whitespace only')
|
||||
return False
|
||||
|
||||
allow_file_access = strtobool(os.getenv('ALLOW_FILE_URI', 'false'))
|
||||
safe_protocol_regex = '^(http|https|ftp|file):' if allow_file_access else '^(http|https|ftp):'
|
||||
|
||||
|
||||
@@ -132,11 +132,19 @@ async def start_single_async_worker(worker_id, update_q, notification_q, app, da
|
||||
|
||||
while not app.config.exit.is_set():
|
||||
try:
|
||||
await async_update_worker(worker_id, update_q, notification_q, app, datastore, executor)
|
||||
# If we reach here, worker exited cleanly
|
||||
if not in_pytest:
|
||||
logger.info(f"Async worker {worker_id} exited cleanly")
|
||||
break
|
||||
result = await async_update_worker(worker_id, update_q, notification_q, app, datastore, executor)
|
||||
|
||||
if result == "restart":
|
||||
# Worker requested restart - immediately loop back and restart
|
||||
if not in_pytest:
|
||||
logger.debug(f"Async worker {worker_id} restarting")
|
||||
continue
|
||||
else:
|
||||
# Worker exited cleanly (shutdown)
|
||||
if not in_pytest:
|
||||
logger.info(f"Async worker {worker_id} exited cleanly")
|
||||
break
|
||||
|
||||
except asyncio.CancelledError:
|
||||
# Task was cancelled (normal shutdown)
|
||||
if not in_pytest:
|
||||
@@ -147,7 +155,7 @@ async def start_single_async_worker(worker_id, update_q, notification_q, app, da
|
||||
if not in_pytest:
|
||||
logger.info(f"Restarting async worker {worker_id} in 5 seconds...")
|
||||
await asyncio.sleep(5)
|
||||
|
||||
|
||||
if not in_pytest:
|
||||
logger.info(f"Async worker {worker_id} shutdown complete")
|
||||
|
||||
@@ -161,7 +169,11 @@ def add_worker(update_q, notification_q, app, datastore):
|
||||
"""Add a new async worker (for dynamic scaling)"""
|
||||
global worker_threads
|
||||
|
||||
worker_id = len(worker_threads)
|
||||
# Reuse lowest available ID to prevent unbounded growth over time
|
||||
used_ids = {w.worker_id for w in worker_threads}
|
||||
worker_id = 0
|
||||
while worker_id in used_ids:
|
||||
worker_id += 1
|
||||
logger.info(f"Adding async worker {worker_id}")
|
||||
|
||||
try:
|
||||
@@ -251,7 +263,7 @@ def queue_item_async_safe(update_q, item, silent=False):
|
||||
return False
|
||||
|
||||
if not silent:
|
||||
logger.debug(f"Successfully queued item: {item_uuid}")
|
||||
logger.trace(f"Successfully queued item: {item_uuid}")
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
|
||||
@@ -183,15 +183,30 @@ components:
|
||||
properties:
|
||||
weeks:
|
||||
type: integer
|
||||
minimum: 0
|
||||
maximum: 52000
|
||||
nullable: true
|
||||
days:
|
||||
type: integer
|
||||
minimum: 0
|
||||
maximum: 365000
|
||||
nullable: true
|
||||
hours:
|
||||
type: integer
|
||||
minimum: 0
|
||||
maximum: 8760000
|
||||
nullable: true
|
||||
minutes:
|
||||
type: integer
|
||||
minimum: 0
|
||||
maximum: 525600000
|
||||
nullable: true
|
||||
seconds:
|
||||
type: integer
|
||||
description: Time intervals between checks
|
||||
minimum: 0
|
||||
maximum: 31536000000
|
||||
nullable: true
|
||||
description: Time intervals between checks. All fields must be non-negative. At least one non-zero value required when not using default settings.
|
||||
time_between_check_use_default:
|
||||
type: boolean
|
||||
default: true
|
||||
@@ -200,7 +215,9 @@ components:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
description: Notification URLs for this web page change monitor (watch)
|
||||
maxLength: 1000
|
||||
maxItems: 100
|
||||
description: Notification URLs for this web page change monitor (watch). Maximum 100 URLs.
|
||||
notification_title:
|
||||
type: string
|
||||
description: Custom notification title
|
||||
@@ -224,14 +241,19 @@ components:
|
||||
operation:
|
||||
type: string
|
||||
maxLength: 5000
|
||||
nullable: true
|
||||
selector:
|
||||
type: string
|
||||
maxLength: 5000
|
||||
nullable: true
|
||||
optional_value:
|
||||
type: string
|
||||
maxLength: 5000
|
||||
nullable: true
|
||||
required: [operation, selector, optional_value]
|
||||
description: Browser automation steps
|
||||
additionalProperties: false
|
||||
maxItems: 100
|
||||
description: Browser automation steps. Maximum 100 steps allowed.
|
||||
processor:
|
||||
type: string
|
||||
enum: [restock_diff, text_json_diff]
|
||||
|
||||
@@ -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==2.0.0rc11
|
||||
pyppeteer-ng==2.0.0rc12
|
||||
pyppeteerstealth>=0.0.4
|
||||
|
||||
# Include pytest, so if theres a support issue we can ask them to run these tests on their setup
|
||||
|
||||
28
setup.cfg
Normal file
28
setup.cfg
Normal file
@@ -0,0 +1,28 @@
|
||||
# Translation configuration for changedetection.io
|
||||
# See changedetectionio/translations/README.md for full documentation on updating translations
|
||||
|
||||
[extract_messages]
|
||||
# Extract translatable strings from source code
|
||||
mapping_file = babel.cfg
|
||||
output_file = changedetectionio/translations/messages.pot
|
||||
input_paths = changedetectionio
|
||||
keywords = _ _l gettext
|
||||
# Options to reduce unnecessary changes in .pot files
|
||||
sort_by_file = true
|
||||
width = 120
|
||||
add_location = file
|
||||
|
||||
[update_catalog]
|
||||
# Update existing .po files with new strings from .pot
|
||||
# Note: Omitting 'locale' makes Babel auto-discover all catalogs in output_dir
|
||||
input_file = changedetectionio/translations/messages.pot
|
||||
output_dir = changedetectionio/translations
|
||||
domain = messages
|
||||
# Options for consistent formatting
|
||||
width = 120
|
||||
no_fuzzy_matching = true
|
||||
|
||||
[compile_catalog]
|
||||
# Compile .po files to .mo binary format
|
||||
directory = changedetectionio/translations
|
||||
domain = messages
|
||||
Reference in New Issue
Block a user