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

Remove truncated links

main
bashrc 2026-01-08 11:55:51 +00:00
parent 98c770347f
commit 3e42a977b1
2 changed files with 45 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
content.py
View File

@ -1108,6 +1108,28 @@ def remove_text_formatting(content: str, bold_reading: bool) -> str:
return content return content
def _remove_truncated_link(content: str) -> str:
"""Removes any truncated links.
Sometimes very long links get truncated due to character limits
on some instances.
"""
if '<a href' not in content:
return content
sections = content.split('<a href')
ctr = 0
remove_strings = []
for section in sections:
if ctr == 0:
ctr = 1
continue
if '</a>' not in section:
remove_strings.append('<a href' + section)
ctr += 1
for removal_text in remove_strings:
content = content.replace(removal_text, '')
return content
def remove_long_words(content: str, max_word_length: int, def remove_long_words(content: str, max_word_length: int,
long_words_list: []) -> str: long_words_list: []) -> str:
"""Breaks up long words so that on mobile screens this doesn't """Breaks up long words so that on mobile screens this doesn't
@ -1116,6 +1138,7 @@ def remove_long_words(content: str, max_word_length: int,
if is_pgp_encrypted(content) or contains_pgp_public_key(content): if is_pgp_encrypted(content) or contains_pgp_public_key(content):
return content return content
content = replace_content_duplicates(content) content = replace_content_duplicates(content)
content = _remove_truncated_link(content)
non_html_list = False non_html_list = False
if '\n\n' in content and '<p>' not in content: if '\n\n' in content and '<p>' not in content:

22
tests.py
View File

@ -4125,6 +4125,28 @@ def _test_web_links():
result_text = remove_long_words(test_fn_str, 40, []) result_text = remove_long_words(test_fn_str, 40, [])
assert result_text == example_text assert result_text == example_text
example_text = \
"<p>Malformed link</p><p><a href=\"" + \
"https://some.crap.domain/cos-osf-prod-files-us-east1/" + \
"46238446746346949566326576231358356756535656956256?" + \
"response-content-disposition=attachment%3B%20filename%3D%22" + \
"CN_IS_jfoewyffnmviwyudrw_in%20thing.pdf%22%3B%20filename%2A%3D" + \
"UTF-8%27%27CN_IS_37492fbhfbhvgbwhvbwv_in%2520thing.pdf&amp;" + \
"BigTechAccessId=files-us%40cos-osf-prod.iam.sillyaccount." + \
"whatever&amp;Expires=1261814358&amp;Signature=bnhvsdbyfef2h2he2" + \
"8756254hthvifbebvWi6psszq7mLUQpB0Zrrbj7VU93k8GsUnHjidJFNWCIg2%2" + \
"FztCupUxXwtBXg%2FZP1uSCeVu3Nv09y9y6mszhXOqlsBuXIROMTYYQzCUN%2Bz" + \
"ZaffzUfbnwhebwufbwewyvvwvbiOlpeI7gG2lIku23vy2m%2Fk2PHf9I5Z0Nt1n" + \
"Lv3%2Beb%2FR8avLECuCIJjhbMkiBWvDarY0l5Hl%2F%2BQ9QCbRnRRLIC1vjJo" + \
"PyjK%2FzyShPVz%2B4ztVMF6MYOnMTxFQC4POa4ovxoo1%2B1QdixwmAI9sIK4U" + \
"%2BOKYiV%2FEZdw%3D%3D"
result_text = remove_long_words(example_text, 40, [])
expected_text = "<p>Malformed link</p><p></p>"
if result_text != expected_text:
print("Expected: " + expected_text)
print("Result: " + result_text)
assert result_text == expected_text
def _test_addemoji(base_dir: str): def _test_addemoji(base_dir: str):
print('test_addemoji') print('test_addemoji')