Filters - Adding "Strip ignored lines" in output option to filters (#3449)

fix-build-test
dgtlmoon 2025-10-01 12:39:57 +02:00 zatwierdzone przez GitHub
rodzic c8caa0662d
commit 4b9ae5a97c
Nie znaleziono w bazie danych klucza dla tego podpisu
ID klucza GPG: B5690EEEBB952194
9 zmienionych plików z 56 dodań i 3 usunięć

Wyświetl plik

@ -191,6 +191,12 @@ nav
</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>
</fieldset>
</div>
<div class="tab-pane-inner" id="api">

Wyświetl plik

@ -759,6 +759,7 @@ class processor_text_json_diff_form(commonSettingsForm):
check_unique_lines = BooleanField('Only trigger when unique lines appear in all history', default=False)
remove_duplicate_lines = BooleanField('Remove duplicate lines of text', default=False)
sort_text_alphabetically = BooleanField('Sort text alphabetically', default=False)
strip_ignored_lines = TernaryNoneBooleanField('Strip ignored lines', default=None)
trim_text_whitespace = BooleanField('Trim whitespace before and after text', default=False)
filter_text_added = BooleanField('Added lines', default=True)
@ -936,6 +937,7 @@ class globalSettingsApplicationForm(commonSettingsForm):
removepassword_button = SubmitField('Remove password', render_kw={"class": "pure-button pure-button-primary"})
render_anchor_tag_content = BooleanField('Render anchor tag content', default=False)
shared_diff_access = BooleanField('Allow anonymous access to watch history page when password is enabled', default=False, validators=[validators.Optional()])
strip_ignored_lines = BooleanField('Strip ignored lines')
rss_hide_muted_watches = BooleanField('Hide muted watches from RSS feed', default=True,
validators=[validators.Optional()])
filter_failure_notification_threshold_attempts = IntegerField('Number of times the filter can be missing before sending a notification',

Wyświetl plik

@ -57,6 +57,7 @@ class model(dict):
'rss_hide_muted_watches': True,
'schema_version' : 0,
'shared_diff_access': False,
'strip_ignored_lines': False,
'tags': {}, #@todo use Tag.model initialisers
'timezone': None, # Default IANA timezone name
'webdriver_delay': None , # Extra delay in seconds before extracting text

Wyświetl plik

@ -58,6 +58,7 @@ class watch_base(dict):
'proxy': None, # Preferred proxy connection
'remote_server_reply': None, # From 'server' reply header
'sort_text_alphabetically': False,
'strip_ignored_lines': None,
'subtractive_selectors': [],
'tag': '', # Old system of text name for a tag, to be removed
'tags': [], # list of UUIDs to App.Tags

Wyświetl plik

@ -315,6 +315,11 @@ class perform_site_check(difference_detection_processor):
text_for_checksuming = stripped_text_from_html
if text_to_ignore:
text_for_checksuming = html_tools.strip_ignore_text(stripped_text_from_html, text_to_ignore)
# Some people prefer to also completely remove it
strip_ignored_lines = watch.get('strip_ignored_lines') if watch.get('strip_ignored_lines') is not None else self.datastore.data['settings']['application'].get('strip_ignored_lines')
if strip_ignored_lines:
# @todo add test in the 'preview' mode, check the widget works? compare to datastruct
stripped_text_from_html = text_for_checksuming
# Re #133 - if we should strip whitespaces from triggering the change detected comparison
if text_for_checksuming and self.datastore.data['settings']['application'].get('ignore_whitespace', False):

Wyświetl plik

@ -34,7 +34,6 @@
transition: all 0.2s ease;
cursor: pointer;
display: block;
min-width: 60px;
text-align: center;
}

File diff suppressed because one or more lines are too long

Wyświetl plik

@ -26,7 +26,10 @@
<li>Changing this will affect the comparison checksum which may trigger an alert</li>
</ul>
</span>
<br><br>
<div class="pure-control-group">
{{ render_ternary_field(form.strip_ignored_lines) }}
</div>
</fieldset>
<fieldset>

Wyświetl plik

@ -58,3 +58,39 @@ def test_ignore(client, live_server, measure_memory_usage):
# Should be in base.html
assert b'csrftoken' in res.data
def test_strip_ignore_lines(client, live_server, measure_memory_usage):
# live_server_setup(live_server) # Setup on conftest per function
set_original_ignore_response()
# Goto the settings page, add our ignore text
res = client.post(
url_for("settings.settings_page"),
data={
"requests-time_between_check-minutes": 180,
"application-ignore_whitespace": "y",
"application-strip_ignored_lines": "y",
"application-global_ignore_text": "Which is across multiple",
'application-fetch_backend': "html_requests"
},
follow_redirects=True
)
assert b"Settings updated." in res.data
test_url = url_for('test_endpoint', _external=True)
res = client.post(
url_for("imports.import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
# Give the thread time to pick it up
wait_for_all_checks(client)
uuid = next(iter(live_server.app.config['DATASTORE'].data['watching']))
# It should not be in the preview anymore
res = client.get(url_for("ui.ui_views.preview_page", uuid=uuid))
assert b'<div class="ignored">' not in res.data
assert b'Which is across multiple' not in res.data