lee/changedetection.io
1
0
Fork 0
mirror of https://github.com/dgtlmoon/changedetection.io.git synced 2025-12-13 11:35:45 +00:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

New text filter - Sort text alphabetically filter (#2153)

Browse Source
This commit is contained in:
dgtlmoon
2024-02-02 11:36:58 +01:00
committed by GitHub
parent c90b27823a
commit 616c0b3f65
5 changed files with 87 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
changedetectionio/processors/text_json_diff.py
View File

@@ -204,6 +204,12 @@ class perform_site_check(difference_detection_processor):
is_rss=is_rss # #1874 activate the <title workaround hack
)
if watch.get('sort_text_alphabetically') and stripped_text_from_html:
# Note: Because a <p>something</p> will add an extra line feed to signify the paragraph gap
# we end up with 'Some text\n\n', sorting will add all those extra \n at the start, so we remove them here.
stripped_text_from_html = stripped_text_from_html.replace('\n\n', '\n')
stripped_text_from_html = '\n'.join( sorted(stripped_text_from_html.splitlines(), key=lambda x: x.lower() ))
# Re #340 - return the content before the 'ignore text' was applied
text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')