indymedia
/
epicyon
mirror of https://gitlab.com/bashrc2/epicyon
7
4
Fork 1
Code Issues 14 Releases Wiki Activity

Tidying

merge-requests/30/head
Bob Mottram 2024-05-08 11:22:38 +01:00
parent 4b04f1ce17
commit ff221fabfe
1 changed files with 66 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

110
cwlists.py
View File

@ -42,6 +42,68 @@ def load_cw_lists(base_dir: str, verbose: bool) -> {}:
return result return result
def _add_cw_match_tags(item: {}, post_tags: {}, cw_text: str,
warning: str) -> (bool, str):
"""Updates content warning text using hashtags from within
the post content
"""
matched = False
for tag in item['hashtags']:
tag = tag.strip()
if not tag:
continue
if not tag.startswith('#'):
tag = '#' + tag
tag = tag.lower()
for tag_dict in post_tags:
if not isinstance(tag_dict, dict):
continue
if not tag_dict.get('Hashtag'):
continue
if not tag_dict.get('name'):
continue
if tag_dict['name'].lower() == tag:
if cw_text:
cw_text = warning + ' / ' + cw_text
else:
cw_text = warning
matched = True
break
if matched:
break
return matched, cw_text
def _add_cw_match_domains(item: {}, content: str, cw_text: str,
warning: str) -> (bool, str):
"""Updates content warning text using domains from within
the post content
"""
matched = False
for domain in item['domains']:
if '.' in domain:
first_section = domain.split('.')[0]
if len(first_section) < 4:
if '.' + domain in content or \
'/' + domain in content:
if cw_text:
cw_text = warning + ' / ' + cw_text
else:
cw_text = warning
matched = True
break
continue
if domain in content:
if cw_text:
cw_text = warning + ' / ' + cw_text
else:
cw_text = warning
matched = True
break
return matched, cw_text
def add_cw_from_lists(post_json_object: {}, cw_lists: {}, translate: {}, def add_cw_from_lists(post_json_object: {}, cw_lists: {}, translate: {},
lists_enabled: str, system_language: str, lists_enabled: str, system_language: str,
languages_understood: []) -> None: languages_understood: []) -> None:
@ -86,56 +148,16 @@ def add_cw_from_lists(post_json_object: {}, cw_lists: {}, translate: {},
# match hashtags within the post # match hashtags within the post
if post_tags and item.get('hashtags'): if post_tags and item.get('hashtags'):
for tag in item['hashtags']: matched, cw_text = \
tag = tag.strip() _add_cw_match_tags(item, post_tags, cw_text, warning)
if not tag:
continue
if not tag.startswith('#'):
tag = '#' + tag
tag = tag.lower()
for tag_dict in post_tags:
if not isinstance(tag_dict, dict):
continue
if not tag_dict.get('Hashtag'):
continue
if not tag_dict.get('name'):
continue
if tag_dict['name'].lower() == tag:
if cw_text:
cw_text = warning + ' / ' + cw_text
else:
cw_text = warning
matched = True
break
if matched:
break
if matched: if matched:
continue continue
# match domains within the content # match domains within the content
if item.get('domains'): if item.get('domains'):
for domain in item['domains']: matched, cw_text = \
if '.' in domain: _add_cw_match_domains(item, content, cw_text, warning)
first_section = domain.split('.')[0]
if len(first_section) < 4:
if '.' + domain in content or \
'/' + domain in content:
if cw_text:
cw_text = warning + ' / ' + cw_text
else:
cw_text = warning
matched = True
break
continue
if domain in content:
if cw_text:
cw_text = warning + ' / ' + cw_text
else:
cw_text = warning
matched = True
break
if matched: if matched:
continue continue