test: unit tests for send_step_failure_notification AttributeError regression

Verifies that the module-level _check_cascading_vars is called correctly
(not as self._check_cascading_vars) and that a notification is queued
when step failure occurs.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

changedetectionio/blueprint/backups/templates/backup_restore.html

@@ -20,8 +20,7 @@
                 <p>{{ _('Restore a backup. Must be a .zip backup file created on/after v0.53.1 (new database layout).') }}</p>
                 <p>{{ _('Note: This does not override the main application settings, only watches and groups.') }}</p>
                 <p class="pure-form-message">
-                    {{ _('Max upload size: %(upload)s MB &nbsp;·&nbsp; Max decompressed size: %(decomp)s MB',
-                         upload=max_upload_mb, decomp=max_decompressed_mb) }}
+                    {{ _('Max upload size: %(upload)s MB, Max decompressed size: %(decomp)s MB', upload=max_upload_mb, decomp=max_decompressed_mb) }}
                 </p>
 
                 <form class="pure-form pure-form-stacked settings"

changedetectionio/blueprint/imports/templates/import.html

@@ -9,6 +9,7 @@
             <li class="tab" id=""><a href="#url-list">{{ _('URL List') }}</a></li>
             <li class="tab"><a href="#distill-io">{{ _('Distill.io') }}</a></li>
             <li class="tab"><a href="#xlsx">{{ _('.XLSX & Wachete') }}</a></li>
+            <li class="tab"><a href="{{url_for('backups.restore.restore')}}">{{ _('Backup Restore') }}</a></li>
         </ul>
     </div>
 

changedetectionio/blueprint/tags/__init__.py

@@ -22,10 +22,12 @@ def construct_blueprint(datastore: ChangeDetectionStore):
 
         tag_count = Counter(tag for watch in datastore.data['watching'].values() if watch.get('tags') for tag in watch['tags'])
 
+        from changedetectionio import processors
         output = render_template("groups-overview.html",
                                  app_rss_token=datastore.data['settings']['application'].get('rss_access_token'),
                                  available_tags=sorted_tags,
                                  form=add_form,
+                                 generate_tag_colors=processors.generate_processor_badge_colors,
                                  tag_count=tag_count,
                                  )
 
@@ -208,9 +210,17 @@ def construct_blueprint(datastore: ChangeDetectionStore):
             template = env.from_string(template_str)
             included_content = template.render(**template_args)
 
+        # Watches whose URL currently matches this tag's pattern
+        matching_watches = {
+            w_uuid: watch
+            for w_uuid, watch in datastore.data['watching'].items()
+            if default.matches_url(watch.get('url', ''))
+        }
+
         output = render_template("edit-tag.html",
                                  extra_form_content=included_content,
                                  extra_tab_content=form.extra_tab_content() if form.extra_tab_content() else None,
+                                 matching_watches=matching_watches,
                                  settings_application=datastore.data['settings']['application'],
                                  **template_args
                                  )

changedetectionio/blueprint/tags/form.py

@@ -10,6 +10,8 @@ from changedetectionio.processors.restock_diff.forms import processor_settings_f
 
 class group_restock_settings_form(restock_settings_form):
     overrides_watch = BooleanField('Activate for individual watches in this tag/group?', default=False)
+    url_match_pattern = StringField('Auto-apply to watches with URLs matching',
+                                    render_kw={"placeholder": "e.g. *://example.com/* or github.com/myorg"})
 
 class SingleTag(Form):
 

changedetectionio/blueprint/tags/templates/edit-tag.html

@@ -43,6 +43,20 @@
                     <div class="pure-control-group">
                         {{ render_field(form.title, placeholder="https://...", required=true, class="m-d") }}
                     </div>
+                    <div class="pure-control-group">
+                        {{ render_field(form.url_match_pattern, class="m-d") }}
+                        <span class="pure-form-message-inline">{{ _('Automatically applies this tag to any watch whose URL matches. Supports wildcards: <code>*example.com*</code> or plain substring: <code>github.com/myorg</code>')|safe }}</span>
+                    </div>
+                    {% if matching_watches %}
+                    <div class="pure-control-group">
+                        <label>{{ _('Currently matching watches') }} ({{ matching_watches|length }})</label>
+                        <ul class="tag-url-match-list">
+                            {% for w_uuid, w in matching_watches.items() %}
+                            <li><a href="{{ url_for('ui.ui_edit.edit_page', uuid=w_uuid) }}">{{ w.label }}</a></li>
+                            {% endfor %}
+                        </ul>
+                    </div>
+                    {% endif %}
                 </fieldset>
             </div>
 

changedetectionio/blueprint/tags/templates/groups-overview.html

@@ -3,6 +3,22 @@
 {% from '_helpers.html' import render_simple_field, render_field %}
 <script src="{{url_for('static_content', group='js', filename='jquery-3.6.0.min.js')}}"></script>
 <script src="{{url_for('static_content', group='js', filename='modal.js')}}"></script>
+<style>
+{%- for uuid, tag in available_tags -%}
+{%- if tag and tag.title -%}
+{%- set class_name = tag.title|sanitize_tag_class -%}
+{%- set colors = generate_tag_colors(tag.title) -%}
+.watch-tag-list.tag-{{ class_name }} {
+  background-color: {{ colors['light']['bg'] }};
+  color: {{ colors['light']['color'] }};
+}
+html[data-darkmode="true"] .watch-tag-list.tag-{{ class_name }} {
+  background-color: {{ colors['dark']['bg'] }};
+  color: {{ colors['dark']['color'] }};
+}
+{%- endif -%}
+{%- endfor -%}
+</style>
 
 <div class="box">
     <form class="pure-form" action="{{ url_for('tags.form_tag_add') }}" method="POST" id="new-watch-form">
@@ -48,7 +64,7 @@
                     <a class="link-mute state-{{'on' if tag.notification_muted else 'off'}}" href="{{url_for('tags.mute', uuid=tag.uuid)}}"><img src="{{url_for('static_content', group='images', filename='bell-off.svg')}}" alt="Mute notifications" title="Mute notifications" class="icon icon-mute" ></a>
                 </td>
                 <td>{{ "{:,}".format(tag_count[uuid]) if uuid in tag_count else 0 }}</td>
-                <td class="title-col inline"> <a href="{{url_for('watchlist.index', tag=uuid) }}">{{ tag.title }}</a></td>
+                <td class="title-col inline"> <a href="{{url_for('watchlist.index', tag=uuid) }}" class="watch-tag-list tag-{{ tag.title|sanitize_tag_class }}">{{ tag.title }}</a></td>
                 <td>
                     <a class="pure-button pure-button-primary" href="{{ url_for('tags.form_tag_edit', uuid=uuid) }}">{{ _('Edit') }}</a>
                     <a href="{{ url_for('ui.form_watch_checknow', tag=uuid) }}" class="pure-button pure-button-primary" >{{ _('Recheck') }}</a>

changedetectionio/blueprint/ui/edit.py

@@ -320,7 +320,12 @@ def construct_blueprint(datastore: ChangeDetectionStore, update_q, queuedWatchMe
                 'using_global_webdriver_wait': not default['webdriver_delay'],
                 'uuid': uuid,
                 'watch': watch,
-                'capabilities': capabilities
+                'capabilities': capabilities,
+                'auto_applied_tags': {
+                    tag_uuid: tag
+                    for tag_uuid, tag in datastore.data['settings']['application']['tags'].items()
+                    if tag_uuid not in watch.get('tags', []) and tag.matches_url(watch.get('url', ''))
+                },
             }
 
             included_content = None

changedetectionio/blueprint/ui/templates/edit.html

@@ -81,6 +81,14 @@
                     <div class="pure-control-group">
                         {{ render_field(form.tags) }}
                         <span class="pure-form-message-inline">{{ _('Organisational tag/group name used in the main listing page') }}</span>
+                        {% if auto_applied_tags %}
+                        <span class="pure-form-message-inline">
+                            {{ _('Also automatically applied by URL pattern:') }}
+                            {% for tag_uuid, tag in auto_applied_tags.items() %}
+                            <a href="{{ url_for('tags.form_tag_edit', uuid=tag_uuid) }}" class="watch-tag-list tag-{{ tag.title|sanitize_tag_class }}">{{ tag.title }}</a>
+                            {% endfor %}
+                        </span>
+                        {% endif %}
                     </div>
                     <div class="pure-control-group inline-radio">
                         {{ render_field(form.processor) }}

changedetectionio/content_fetchers/playwright.py

@@ -49,6 +49,9 @@ async def capture_full_page_async(page, screenshot_format='JPEG', watch_uuid=Non
     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
+        # Never set viewport taller than our max capture height - otherwise one screenshot chunk
+        # captures the whole (e.g. 8098px) page even when SCREENSHOT_MAX_HEIGHT=1000
+        step_size = min(step_size, SCREENSHOT_MAX_TOTAL_HEIGHT)
         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

changedetectionio/content_fetchers/puppeteer.py

@@ -75,6 +75,9 @@ async def capture_full_page(page, screenshot_format='JPEG', watch_uuid=None, loc
     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
+        # Never set viewport taller than our max capture height - otherwise one screenshot chunk
+        # captures the whole page even when SCREENSHOT_MAX_HEIGHT is set smaller
+        step_size = min(step_size, SCREENSHOT_MAX_TOTAL_HEIGHT)
         viewport_start = time.time()
         await page.setViewport({'width': page.viewport['width'], 'height': step_size})
         viewport_time = time.time() - viewport_start

changedetectionio/content_fetchers/screenshot_handler.py

@@ -56,6 +56,10 @@ def stitch_images_worker_raw_bytes(pipe_conn, original_page_height, capture_heig
             im.close()
         del images
 
+        # Clip stitched image to capture_height (chunks may overshoot by up to step_size-1 px)
+        if total_height > capture_height:
+            stitched = stitched.crop((0, 0, max_width, capture_height))
+
         # Draw caption only if page was trimmed
         if original_page_height > capture_height:
             draw = ImageDraw.Draw(stitched)

changedetectionio/content_fetchers/webdriver_selenium.py

@@ -104,15 +104,17 @@ class fetcher(Fetcher):
 
             from selenium.webdriver.remote.remote_connection import RemoteConnection
             from selenium.webdriver.remote.webdriver import WebDriver as RemoteWebDriver
+            from selenium.webdriver.remote.client_config import ClientConfig
+            from urllib3.util import Timeout
             driver = None
             try:
-                # Create the RemoteConnection and set timeout (e.g., 30 seconds)
-                remote_connection = RemoteConnection(
-                    self.browser_connection_url,
+                connection_timeout = int(os.getenv("WEBDRIVER_CONNECTION_TIMEOUT", 90))
+                client_config = ClientConfig(
+                    remote_server_addr=self.browser_connection_url,
+                    timeout=Timeout(connect=connection_timeout, total=connection_timeout)
                 )
-                remote_connection.set_timeout(30)  # seconds
+                remote_connection = RemoteConnection(client_config=client_config)
 
-                # Now create the driver with the RemoteConnection
                 driver = RemoteWebDriver(
                     command_executor=remote_connection,
                     options=options

changedetectionio/diff/__init__.py

@@ -45,6 +45,36 @@ CHANGED_INTO_PLACEMARKER_CLOSED = '@changed_into_PLACEMARKER_CLOSED'
 # Compiled regex patterns for performance
 WHITESPACE_NORMALIZE_RE = re.compile(r'\s+')
 
+# Regexes built from the constants above — no brittle hardcoded strings
+_EXTRACT_REMOVED_RE = re.compile(
+    re.escape(REMOVED_PLACEMARKER_OPEN) + r'(.*?)' + re.escape(REMOVED_PLACEMARKER_CLOSED)
+    + r'|' +
+    re.escape(CHANGED_PLACEMARKER_OPEN) + r'(.*?)' + re.escape(CHANGED_PLACEMARKER_CLOSED)
+)
+_EXTRACT_ADDED_RE = re.compile(
+    re.escape(ADDED_PLACEMARKER_OPEN) + r'(.*?)' + re.escape(ADDED_PLACEMARKER_CLOSED)
+    + r'|' +
+    re.escape(CHANGED_INTO_PLACEMARKER_OPEN) + r'(.*?)' + re.escape(CHANGED_INTO_PLACEMARKER_CLOSED)
+)
+
+
+def extract_changed_from(raw_diff: str) -> str:
+    """Extract only the removed/changed-from fragments from a raw diff string.
+
+    Useful for {{diff_changed_from}} — gives just the old value (e.g. old price),
+    not the full surrounding line. Multiple fragments joined with newlines.
+    """
+    return '\n'.join(m.group(1) or m.group(2) for m in _EXTRACT_REMOVED_RE.finditer(raw_diff))
+
+
+def extract_changed_to(raw_diff: str) -> str:
+    """Extract only the added/changed-into fragments from a raw diff string.
+
+    Useful for {{diff_changed_to}} — gives just the new value (e.g. new price),
+    not the full surrounding line. Multiple fragments joined with newlines.
+    """
+    return '\n'.join(m.group(1) or m.group(2) for m in _EXTRACT_ADDED_RE.finditer(raw_diff))
+
 
 def render_inline_word_diff(before_line: str, after_line: str, ignore_junk: bool = False, markdown_style: str = None, tokenizer: str = 'words_and_html') -> tuple[str, bool]:
     """

changedetectionio/languages.py

@@ -28,18 +28,20 @@ def get_timeago_locale(flask_locale):
         str: timeago library locale code (e.g., 'en', 'zh_CN', 'pt_PT')
     """
     locale_map = {
-        'zh': 'zh_CN',      # Chinese Simplified
+        'zh': 'zh_CN',          # Chinese Simplified
         # timeago library just hasn't been updated to use the more modern locale naming convention, before BCP 47 / RFC 5646.
-        'zh_TW': 'zh_TW',   # Chinese Traditional (timeago uses zh_TW)
+        'zh_TW': 'zh_TW',       # Chinese Traditional (timeago uses zh_TW)
         'zh_Hant_TW': 'zh_TW',  # Flask-Babel normalizes zh_TW to zh_Hant_TW, map back to timeago's zh_TW
-        'pt': 'pt_PT',      # Portuguese (Portugal)
-        'sv': 'sv_SE',      # Swedish
-        'no': 'nb_NO',      # Norwegian Bokmål
-        'hi': 'in_HI',      # Hindi
-        'cs': 'en',         # Czech not supported by timeago, fallback to English
-        'uk': 'uk',         # Ukrainian
-        'en_GB': 'en',      # British English - timeago uses 'en'
-        'en_US': 'en',      # American English - timeago uses 'en'
+        'pt': 'pt_PT',          # Portuguese (Portugal)
+        'pt_BR': 'pt_BR',       # Portuguese (Brasil)
+        'sv': 'sv_SE',          # Swedish
+        'no': 'nb_NO',          # Norwegian Bokmål
+        'hi': 'in_HI',          # Hindi
+        'cs': 'en',             # Czech not supported by timeago, fallback to English
+        'ja': 'ja',             # Japanese
+        'uk': 'uk',             # Ukrainian
+        'en_GB': 'en',          # British English - timeago uses 'en'
+        'en_US': 'en',          # American English - timeago uses 'en'
     }
     return locale_map.get(flask_locale, flask_locale)
 
@@ -53,7 +55,8 @@ LANGUAGE_DATA = {
     'ko': {'flag': 'fi fi-kr fis', 'name': '한국어'},
     'cs': {'flag': 'fi fi-cz fis', 'name': 'Čeština'},
     'es': {'flag': 'fi fi-es fis', 'name': 'Español'},
-    'pt': {'flag': 'fi fi-pt fis', 'name': 'Português'},
+    'pt': {'flag': 'fi fi-pt fis', 'name': 'Português (Portugal)'},
+    'pt_BR': {'flag': 'fi fi-br fis', 'name': 'Português (Brasil)'},
     'it': {'flag': 'fi fi-it fis', 'name': 'Italiano'},
     'ja': {'flag': 'fi fi-jp fis', 'name': '日本語'},
     'zh': {'flag': 'fi fi-cn fis', 'name': '中文 (简体)'},

changedetectionio/model/Tag.py

@@ -46,11 +46,26 @@ class model(EntityPersistenceMixin, watch_base):
         super(model, self).__init__(*arg, **kw)
 
         self['overrides_watch'] = kw.get('default', {}).get('overrides_watch')
+        self['url_match_pattern'] = kw.get('default', {}).get('url_match_pattern', '')
 
         if kw.get('default'):
             self.update(kw['default'])
             del kw['default']
 
+    def matches_url(self, url: str) -> bool:
+        """Return True if this tag should be auto-applied to the given watch URL.
+
+        Wildcard patterns (*,?,[ ) use fnmatch; anything else is a case-insensitive
+        substring match. Returns False if no pattern is configured.
+        """
+        import fnmatch
+        pattern = self.get('url_match_pattern', '').strip()
+        if not pattern or not url:
+            return False
+        if any(c in pattern for c in ('*', '?', '[')):
+            return fnmatch.fnmatch(url.lower(), pattern.lower())
+        return pattern.lower() in url.lower()
+
     # _save_to_disk() method provided by EntityPersistenceMixin
     # commit() and _get_commit_data() methods inherited from watch_base
     # Tag uses default _get_commit_data() (includes all keys)

changedetectionio/notification_service.py

@@ -88,6 +88,28 @@ class FormattableTimestamp(str):
             return self._dt.isoformat()
 
 
+class FormattableExtract(str):
+    """
+    A str subclass that holds only the extracted changed fragments from a diff.
+    Used for {{diff_changed_from}} and {{diff_changed_to}} tokens.
+
+        {{ diff_changed_from }}   → old value(s) only, e.g. "$99.99"
+        {{ diff_changed_to }}     → new value(s) only, e.g. "$109.99"
+
+    Multiple changed fragments are joined with newlines.
+    Being a str subclass means it is natively JSON serializable.
+    """
+    def __new__(cls, prev_snapshot, current_snapshot, extract_fn):
+        if prev_snapshot or current_snapshot:
+            from changedetectionio import diff as diff_module
+            raw = diff_module.render_diff(prev_snapshot, current_snapshot, word_diff=True)
+            extracted = extract_fn(raw)
+        else:
+            extracted = ''
+        instance = super().__new__(cls, extracted)
+        return instance
+
+
 class FormattableDiff(str):
     """
     A str subclass representing a rendered diff. As a plain string it renders
@@ -161,6 +183,8 @@ class NotificationContextData(dict):
             'diff_patch': FormattableDiff('', '', patch_format=True),
             'diff_removed': FormattableDiff('', '', include_added=False),
             'diff_removed_clean': FormattableDiff('', '', include_added=False, include_change_type_prefix=False),
+            'diff_changed_from': FormattableExtract('', '', extract_fn=lambda x: x),
+            'diff_changed_to': FormattableExtract('', '', extract_fn=lambda x: x),
             'diff_url': None,
             'markup_text_links_to_html_links': False, # If automatic conversion of plaintext to HTML should happen
             'notification_timestamp': time.time(),
@@ -244,16 +268,27 @@ def add_rendered_diff_to_notification_vars(notification_scan_text:str, prev_snap
         'diff_removed_clean': {'word_diff': word_diff, 'include_added': False, 'include_change_type_prefix': False},
     }
 
+    from changedetectionio.diff import extract_changed_from, extract_changed_to
+    extract_specs = {
+        'diff_changed_from': extract_changed_from,
+        'diff_changed_to':   extract_changed_to,
+    }
+
     ret = {}
     rendered_count = 0
-    # Only create FormattableDiff objects for diff keys actually used in the notification text
+    # Only create FormattableDiff/FormattableExtract objects for diff keys actually used in the notification text
     for key in NotificationContextData().keys():
-        if key.startswith('diff') and key in diff_specs:
-            # Check if this placeholder is actually used in the notification text
-            pattern = rf"(?<![A-Za-z0-9_]){re.escape(key)}(?![A-Za-z0-9_])"
-            if re.search(pattern, notification_scan_text, re.IGNORECASE):
-                ret[key] = FormattableDiff(prev_snapshot, current_snapshot, **diff_specs[key])
-                rendered_count += 1
+        if not key.startswith('diff'):
+            continue
+        pattern = rf"(?<![A-Za-z0-9_]){re.escape(key)}(?![A-Za-z0-9_])"
+        if not re.search(pattern, notification_scan_text, re.IGNORECASE):
+            continue
+        if key in diff_specs:
+            ret[key] = FormattableDiff(prev_snapshot, current_snapshot, **diff_specs[key])
+            rendered_count += 1
+        elif key in extract_specs:
+            ret[key] = FormattableExtract(prev_snapshot, current_snapshot, extract_fn=extract_specs[key])
+            rendered_count += 1
 
     if rendered_count:
         logger.trace(f"Rendered {rendered_count} diff placeholder(s) {sorted(ret.keys())} in {time.time() - now:.3f}s")
@@ -461,7 +496,7 @@ Thanks - Your omniscient changedetection.io installation.
         n_object = NotificationContextData({
             'notification_title': f"Changedetection.io - Alert - Browser step at position {step} could not be run",
             'notification_body': body,
-            'notification_format': self._check_cascading_vars('notification_format', watch),
+            'notification_format': _check_cascading_vars(self.datastore, 'notification_format', watch),
         })
         n_object['markup_text_links_to_html_links'] = n_object.get('notification_format').startswith('html')
 

changedetectionio/store/__init__.py

@@ -980,12 +980,20 @@ class ChangeDetectionStore(DatastoreUpdatesMixin, FileSavingDataStore):
     def get_all_tags_for_watch(self, uuid):
         """This should be in Watch model but Watch doesn't have access to datastore, not sure how to solve that yet"""
         watch = self.data['watching'].get(uuid)
+        if not watch:
+            return {}
 
-        # Should return a dict of full tag info linked by UUID
-        if watch:
-            return dictfilt(self.__data['settings']['application']['tags'], watch.get('tags', []))
+        # Start with manually assigned tags
+        result = dictfilt(self.__data['settings']['application']['tags'], watch.get('tags', []))
 
-        return {}
+        # Additionally include any tag whose url_match_pattern matches this watch's URL
+        watch_url = watch.get('url', '')
+        if watch_url:
+            for tag_uuid, tag in self.__data['settings']['application']['tags'].items():
+                if tag_uuid not in result and tag.matches_url(watch_url):
+                    result[tag_uuid] = tag
+
+        return result
 
     @property
     def extra_browsers(self):

changedetectionio/templates/_common_fields.html

@@ -98,6 +98,14 @@
                 <td><code>{{ '{{diff_patch}}' }}</code></td>
                 <td>{{ _('The diff output - patch in unified format') }}</td>
             </tr>
+            <tr>
+                <td><code>{{ '{{diff_changed_from}}' }}</code></td>
+                <td>{{ _('Only the changed words/values from the previous version — e.g. the old price. Best when a single value changes per line; multiple changed fragments are joined by newline.') }}</td>
+            </tr>
+            <tr>
+                <td><code>{{ '{{diff_changed_to}}' }}</code></td>
+                <td>{{ _('Only the changed words/values from the new version — e.g. the new price. Best when a single value changes per line; multiple changed fragments are joined by newline.') }}</td>
+            </tr>
             <tr>
                 <td><code>{{ '{{current_snapshot}}' }}</code></td>
                 <td>{{ _('The current snapshot text contents value, useful when combined with JSON or CSS filters') }}

changedetectionio/tests/smtp/test_notification_smtp.py

@@ -11,10 +11,10 @@ from changedetectionio.tests.util import set_original_response, set_modified_res
     set_longer_modified_response, delete_all_watches
 
 import logging
-
+import os
 
 # NOTE - RELIES ON mailserver as hostname running, see github build recipes
-smtp_test_server = 'mailserver'
+smtp_test_server = os.getenv('SMTP_TEST_MAILSERVER', 'mailserver')
 
 ALL_MARKUP_TOKENS = ''.join(f"TOKEN: '{t}'\n{{{{{t}}}}}\n" for t in NotificationContextData().keys())
 

changedetectionio/tests/test_tag_url_match.py

@@ -0,0 +1,144 @@
+#!/usr/bin/env python3
+"""
+Integration tests for auto-applying tags to watches by URL pattern matching.
+
+Verifies:
+ - A tag with url_match_pattern shows on the watch overview list (via get_all_tags_for_watch)
+ - The auto-applied tag appears on the watch edit page
+ - A watch whose URL does NOT match the pattern does not get the tag
+"""
+
+import json
+from flask import url_for
+from .util import set_original_response, live_server_setup
+
+
+def test_tag_url_pattern_shows_in_overview(client, live_server, measure_memory_usage, datastore_path):
+    """Tag with a matching url_match_pattern must appear in the watch overview row."""
+    set_original_response(datastore_path=datastore_path)
+
+    api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
+
+    # Create a tag with a URL match pattern
+    res = client.post(
+        url_for("tag"),
+        data=json.dumps({"title": "Auto GitHub", "url_match_pattern": "*github.com*"}),
+        headers={'content-type': 'application/json', 'x-api-key': api_key},
+    )
+    assert res.status_code == 201, res.data
+    tag_uuid = res.json['uuid']
+
+    # Add a watch that matches the pattern
+    res = client.post(
+        url_for("createwatch"),
+        data=json.dumps({"url": "https://github.com/someuser/repo"}),
+        headers={'content-type': 'application/json', 'x-api-key': api_key},
+    )
+    assert res.status_code == 201, res.data
+    matching_watch_uuid = res.json['uuid']
+
+    # Add a watch that does NOT match
+    res = client.post(
+        url_for("createwatch"),
+        data=json.dumps({"url": "https://example.com/page"}),
+        headers={'content-type': 'application/json', 'x-api-key': api_key},
+    )
+    assert res.status_code == 201, res.data
+    non_matching_watch_uuid = res.json['uuid']
+
+    # Watch overview — the tag label must appear in the matching watch's row
+    res = client.get(url_for("watchlist.index"))
+    assert res.status_code == 200
+    html = res.get_data(as_text=True)
+
+    # The tag title should appear somewhere on the page (it's rendered per-watch via get_all_tags_for_watch)
+    assert "Auto GitHub" in html, "Auto-matched tag title must appear in watch overview"
+
+    # Verify via the datastore directly that get_all_tags_for_watch returns the pattern-matched tag
+    datastore = live_server.app.config['DATASTORE']
+
+    matching_tags = datastore.get_all_tags_for_watch(matching_watch_uuid)
+    assert tag_uuid in matching_tags, "Pattern-matched tag must be returned for matching watch"
+
+    non_matching_tags = datastore.get_all_tags_for_watch(non_matching_watch_uuid)
+    assert tag_uuid not in non_matching_tags, "Pattern-matched tag must NOT appear for non-matching watch"
+
+
+def test_auto_applied_tag_shows_on_watch_edit(client, live_server, measure_memory_usage, datastore_path):
+    """The watch edit page must show auto-applied tags (from URL pattern) separately."""
+    set_original_response(datastore_path=datastore_path)
+
+    api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
+
+    res = client.post(
+        url_for("tag"),
+        data=json.dumps({"title": "Auto Docs", "url_match_pattern": "*docs.example.com*"}),
+        headers={'content-type': 'application/json', 'x-api-key': api_key},
+    )
+    assert res.status_code == 201, res.data
+
+    res = client.post(
+        url_for("createwatch"),
+        data=json.dumps({"url": "https://docs.example.com/guide"}),
+        headers={'content-type': 'application/json', 'x-api-key': api_key},
+    )
+    assert res.status_code == 201, res.data
+    watch_uuid = res.json['uuid']
+
+    # Watch edit page must mention the auto-applied tag
+    res = client.get(url_for("ui.ui_edit.edit_page", uuid=watch_uuid))
+    assert res.status_code == 200
+    html = res.get_data(as_text=True)
+
+    assert "Auto Docs" in html, "Auto-applied tag name must appear on watch edit page"
+    assert "automatically applied" in html.lower() or "auto" in html.lower(), \
+        "Watch edit page must indicate the tag is auto-applied by pattern"
+
+
+def test_multiple_pattern_tags_all_applied(client, live_server, measure_memory_usage, datastore_path):
+    """A watch matching multiple tag patterns must receive all of them, not just the first."""
+    set_original_response(datastore_path=datastore_path)
+
+    api_key = live_server.app.config['DATASTORE'].data['settings']['application'].get('api_access_token')
+
+    # Two tags with different patterns that both match the same URL
+    res = client.post(
+        url_for("tag"),
+        data=json.dumps({"title": "Org Docs", "url_match_pattern": "*docs.*"}),
+        headers={'content-type': 'application/json', 'x-api-key': api_key},
+    )
+    assert res.status_code == 201, res.data
+    tag_docs_uuid = res.json['uuid']
+
+    res = client.post(
+        url_for("tag"),
+        data=json.dumps({"title": "Org Python", "url_match_pattern": "*python*"}),
+        headers={'content-type': 'application/json', 'x-api-key': api_key},
+    )
+    assert res.status_code == 201, res.data
+    tag_python_uuid = res.json['uuid']
+
+    # A third tag whose pattern does NOT match
+    res = client.post(
+        url_for("tag"),
+        data=json.dumps({"title": "Org Rust", "url_match_pattern": "*rust-lang*"}),
+        headers={'content-type': 'application/json', 'x-api-key': api_key},
+    )
+    assert res.status_code == 201, res.data
+    tag_rust_uuid = res.json['uuid']
+
+    # Watch URL matches both "docs" and "python" patterns but not "rust"
+    res = client.post(
+        url_for("createwatch"),
+        data=json.dumps({"url": "https://docs.python.org/3/library/fnmatch.html"}),
+        headers={'content-type': 'application/json', 'x-api-key': api_key},
+    )
+    assert res.status_code == 201, res.data
+    watch_uuid = res.json['uuid']
+
+    datastore = live_server.app.config['DATASTORE']
+    resolved = datastore.get_all_tags_for_watch(watch_uuid)
+
+    assert tag_docs_uuid in resolved, "First matching tag must be included"
+    assert tag_python_uuid in resolved, "Second matching tag must be included"
+    assert tag_rust_uuid not in resolved, "Non-matching tag must NOT be included"

changedetectionio/tests/unit/test_notification_diff.py

@@ -15,7 +15,9 @@ from changedetectionio.diff import (
     CHANGED_PLACEMARKER_OPEN,
     CHANGED_PLACEMARKER_CLOSED,
     CHANGED_INTO_PLACEMARKER_OPEN,
-    CHANGED_INTO_PLACEMARKER_CLOSED
+    CHANGED_INTO_PLACEMARKER_CLOSED,
+    extract_changed_from,
+    extract_changed_to,
 )
 
 
@@ -381,5 +383,84 @@ Line 3 with tabs and spaces"""
         self.assertNotIn('[-Line 2-]', output)
         self.assertNotIn('[+Line 2+]', output)
 
+    def test_diff_changed_from_to_word_level(self):
+        """Primary use case: extract just the old/new value from a changed line (e.g. price monitoring)"""
+        before = "Widget costs $99.99 per month"
+        after  = "Widget costs $109.99 per month"
+
+        raw = diff.render_diff(before, after, word_diff=True)
+
+        self.assertEqual(extract_changed_from(raw), "$99.99")
+        self.assertEqual(extract_changed_to(raw),   "$109.99")
+
+    def test_diff_changed_from_to_multiple_changes(self):
+        """Multiple changed fragments on different lines are joined with newline.
+        An unchanged line between the two changes ensures each is a 1-to-1 replace,
+        so word_diff fires per line rather than falling back to multi-line block mode."""
+        before = "Price $99\nunchanged\nTax $5"
+        after  = "Price $149\nunchanged\nTax $12"
+
+        raw = diff.render_diff(before, after, word_diff=True)
+
+        self.assertEqual(extract_changed_from(raw), "$99\n$5")
+        self.assertEqual(extract_changed_to(raw),   "$149\n$12")
+
+    def test_diff_changed_from_to_pure_insert_delete(self):
+        """Pure line additions/deletions (no inline word diff) are also captured"""
+        before = "old line"
+        after  = "new line"
+
+        # word_diff=False forces line-level CHANGED markers
+        raw = diff.render_diff(before, after, word_diff=False)
+
+        self.assertEqual(extract_changed_from(raw), "old line")
+        self.assertEqual(extract_changed_to(raw),   "new line")
+
+    def test_diff_changed_from_to_similar_numbers(self):
+        """$90.00 → $9.00 must not produce a partial match like '0.00'.
+        The tokenizer splits on whitespace only, so '$90.00' and '$9.00' are
+        each a single atomic token — diff never sees their internal characters."""
+        before = "for sale $90.00"
+        after  = "for sale $9.00"
+
+        raw = diff.render_diff(before, after, word_diff=True)
+
+        self.assertEqual(extract_changed_from(raw), "$90.00")
+        self.assertEqual(extract_changed_to(raw),   "$9.00")
+
+    def test_diff_changed_from_to_whole_line_replaced(self):
+        """When every token on the line changed (no common tokens), render_inline_word_diff
+        takes the whole_line_replaced path using CHANGED/CHANGED_INTO markers instead of
+        REMOVED/ADDED. Extraction must still work via the alternation in the regex."""
+        before = "$99"
+        after  = "$109"
+
+        raw = diff.render_diff(before, after, word_diff=True)
+
+        self.assertEqual(extract_changed_from(raw), "$99")
+        self.assertEqual(extract_changed_to(raw),   "$109")
+
+    def test_diff_changed_from_to_multiple_words_same_line(self):
+        """When multiple words change on the same line all fragments are joined with newline.
+        'quick brown fox jumps' -> 'slow brown fox hops' gives 'quick\njumps' / 'slow\nhops'.
+        These tokens work best when a single value changes per line."""
+        before = "quick brown fox jumps"
+        after  = "slow brown fox hops"
+
+        raw = diff.render_diff(before, after, word_diff=True)
+
+        self.assertEqual(extract_changed_from(raw), "quick\njumps")
+        self.assertEqual(extract_changed_to(raw),   "slow\nhops")
+
+    def test_diff_changed_from_to_no_change(self):
+        """No changes → empty string"""
+        content = "nothing changed here"
+
+        raw = diff.render_diff(content, content, word_diff=True)
+
+        self.assertEqual(extract_changed_from(raw), "")
+        self.assertEqual(extract_changed_to(raw),   "")
+
+
 if __name__ == '__main__':
     unittest.main()

changedetectionio/tests/unit/test_step_failure_notification.py

@@ -0,0 +1,68 @@
+"""
+Unit test for send_step_failure_notification regression.
+
+Before the fix, line 499 called self._check_cascading_vars('notification_format', watch)
+which raises AttributeError because _check_cascading_vars is a module-level function,
+not a method of NotificationService.
+"""
+
+import queue
+from unittest.mock import MagicMock
+
+
+def _make_datastore(watch_uuid, notification_url):
+    """Minimal datastore mock that NotificationService and _check_cascading_vars need."""
+    watch = MagicMock()
+    watch.get = lambda key, default=None: {
+        'uuid': watch_uuid,
+        'url': 'https://example.com',
+        'notification_urls': [notification_url],
+        'notification_format': '',
+        'notification_muted': False,
+    }.get(key, default)
+    watch.__getitem__ = lambda self, key: watch.get(key)
+
+    datastore = MagicMock()
+    datastore.data = {
+        'watching': {watch_uuid: watch},
+        'settings': {
+            'application': {
+                'notification_urls': [],
+                'notification_format': 'text',
+                'filter_failure_notification_threshold_attempts': 3,
+            }
+        }
+    }
+    datastore.get_all_tags_for_watch.return_value = {}
+    return datastore, watch
+
+
+def test_send_step_failure_notification_does_not_raise():
+    """send_step_failure_notification must not raise AttributeError (wrong self. prefix on module-level function)."""
+    from changedetectionio.notification_service import NotificationService
+
+    watch_uuid = 'test-uuid-1234'
+    notification_q = queue.Queue()
+    datastore, _ = _make_datastore(watch_uuid, 'post://localhost/test')
+    service = NotificationService(datastore=datastore, notification_q=notification_q)
+
+    # Before the fix this raised:
+    # AttributeError: 'NotificationService' object has no attribute '_check_cascading_vars'
+    service.send_step_failure_notification(watch_uuid=watch_uuid, step_n=0)
+
+
+def test_send_step_failure_notification_queues_item():
+    """A notification object should be placed on the queue when URLs are configured."""
+    from changedetectionio.notification_service import NotificationService
+
+    watch_uuid = 'test-uuid-5678'
+    notification_q = queue.Queue()
+    datastore, _ = _make_datastore(watch_uuid, 'post://localhost/test')
+    service = NotificationService(datastore=datastore, notification_q=notification_q)
+
+    service.send_step_failure_notification(watch_uuid=watch_uuid, step_n=1)
+
+    assert not notification_q.empty(), "Expected a notification to be queued"
+    item = notification_q.get_nowait()
+    assert 'notification_title' in item
+    assert 'position 2' in item['notification_title']

changedetectionio/tests/unit/test_tag_url_match.py

@@ -0,0 +1,68 @@
+#!/usr/bin/env python3
+
+# run from dir above changedetectionio/ dir
+# python3 -m unittest changedetectionio.tests.unit.test_tag_url_match
+
+import unittest
+from changedetectionio.model.Tag import model as TagModel
+
+
+def make_tag(pattern):
+    """Minimal Tag instance for testing matches_url — skips datastore wiring."""
+    tag = TagModel.__new__(TagModel)
+    dict.__init__(tag)
+    tag['url_match_pattern'] = pattern
+    return tag
+
+
+class TestTagUrlMatch(unittest.TestCase):
+
+    def test_wildcard_matches(self):
+        tag = make_tag('*example.com*')
+        self.assertTrue(tag.matches_url('https://example.com/page'))
+        self.assertTrue(tag.matches_url('https://www.example.com/shop/item'))
+        self.assertFalse(tag.matches_url('https://other.com/page'))
+
+    def test_wildcard_case_insensitive(self):
+        tag = make_tag('*EXAMPLE.COM*')
+        self.assertTrue(tag.matches_url('https://example.com/page'))
+
+    def test_substring_match(self):
+        tag = make_tag('github.com/myorg')
+        self.assertTrue(tag.matches_url('https://github.com/myorg/repo'))
+        self.assertFalse(tag.matches_url('https://github.com/otherorg/repo'))
+
+    def test_substring_case_insensitive(self):
+        tag = make_tag('GitHub.com/MyOrg')
+        self.assertTrue(tag.matches_url('https://github.com/myorg/repo'))
+
+    def test_empty_pattern_never_matches(self):
+        tag = make_tag('')
+        self.assertFalse(tag.matches_url('https://example.com'))
+
+    def test_empty_url_never_matches(self):
+        tag = make_tag('*example.com*')
+        self.assertFalse(tag.matches_url(''))
+
+    def test_question_mark_wildcard(self):
+        tag = make_tag('https://example.com/item-?')
+        self.assertTrue(tag.matches_url('https://example.com/item-1'))
+        self.assertFalse(tag.matches_url('https://example.com/item-12'))
+
+    def test_substring_is_broad(self):
+        """Plain substring matching is intentionally broad — 'evil.com' matches anywhere
+        in the URL string, including 'notevil.com'. Users who need precise domain matching
+        should use a wildcard pattern like '*://evil.com/*' instead."""
+        tag = make_tag('evil.com')
+        self.assertTrue(tag.matches_url('https://evil.com/page'))
+        self.assertTrue(tag.matches_url('https://notevil.com'))  # substring match — expected
+
+    def test_precise_domain_match_with_wildcard(self):
+        """Use wildcard pattern for precise domain matching to avoid substring surprises."""
+        tag = make_tag('*://evil.com/*')
+        self.assertTrue(tag.matches_url('https://evil.com/page'))
+        self.assertFalse(tag.matches_url('https://notevil.com/page'))
+
+
+if __name__ == '__main__':
+    unittest.main()

changedetectionio/translations/README.md

@@ -76,7 +76,9 @@ These commands read settings from `../../setup.cfg` automatically.
 - `en_US` - English (US)
 - `fr` - French (Français)
 - `it` - Italian (Italiano)
+- `ja` - Japanese (日本語)
 - `ko` - Korean (한국어)
+- `pt_BR` - Portuguese (Brasil)
 - `zh` - Chinese Simplified (中文简体)
 - `zh_Hant_TW` - Chinese Traditional (繁體中文)
 

changedetectionio/translations/de/LC_MESSAGES/messages.po

@@ -1617,7 +1617,7 @@ msgstr "Bereich zeichnen"
 
 #: changedetectionio/blueprint/ui/templates/edit.html
 msgid "Clear selection"
-msgstr "Klare Auswahl"
+msgstr "Auswahl löschen"
 
 #: changedetectionio/blueprint/ui/templates/edit.html
 msgid "One moment, fetching screenshot and element information.."

docs/api-spec.yaml

@@ -725,6 +725,13 @@ components:
                 - true: Tag settings override watch settings
                 - false: Tag settings do not override (watches use their own settings)
                 - null: Not decided yet / inherit default behavior
+            url_match_pattern:
+              type: string
+              description: |
+                Automatically apply this tag to any watch whose URL matches this pattern.
+                Supports fnmatch wildcards (* and ?): e.g. *://example.com/* or github.com/myorg.
+                Plain strings are matched as case-insensitive substrings.
+                Leave empty to disable auto-matching.
             # Future: Aggregated statistics from all watches with this tag
             # check_count:
             #   type: integer