cphipps/changedetection.io
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Adding form.remove_duplicate_lines

Browse Source
This commit is contained in:
dgtlmoon
2024-09-09 22:16:16 +02:00
parent 0506c01c07
commit f032a1b1b3
3 changed files with 9 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
changedetectionio/forms.py
View File

@@ -480,6 +480,7 @@ class processor_text_json_diff_form(commonSettingsForm):
method = SelectField('Request method', choices=valid_method, default=default_method)
ignore_status_codes = BooleanField('Ignore status codes (process non-2xx status codes as normal)', default=False)
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)
trim_text_whitespace = BooleanField('Trim whitespace before and after text', default=False)

3
changedetectionio/processors/text_json_diff/processor.py
View File

@@ -213,6 +213,9 @@ class perform_site_check(difference_detection_processor):
if watch.get('trim_text_whitespace') and stripped_text_from_html:
stripped_text_from_html = '\n'.join(line.strip() for line in stripped_text_from_html.splitlines())
if watch.get('remove_duplicate_lines') and stripped_text_from_html:
stripped_text_from_html = '\n'.join(dict.fromkeys(line for line in stripped_text_from_html.splitlines()))
# Re #340 - return the content before the 'ignore text' was applied
text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')

6
changedetectionio/templates/edit.html
View File

@@ -341,8 +341,12 @@ nav
<fieldset class="pure-control-group">
{{ render_checkbox_field(form.trim_text_whitespace) }}
<span class="pure-form-message-inline">Remove any whitespace before and after each line of text</span>
</fieldset>
<fieldset class="pure-control-group">
{{ render_checkbox_field(form.remove_duplicate_lines) }}
<span class="pure-form-message-inline">Remove duplicate lines of text</span>
</fieldset>
<fieldset class="pure-control-group">
{{ render_checkbox_field(form.check_unique_lines) }}
<span class="pure-form-message-inline">Good for websites that just move the content around, and you want to know when NEW content is added, compares new lines against all history for this watch.</span>