Skip to content

fix: support replacing URLs mixed with CJK characters (#15) #41

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
stellarissss wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: support replacing URLs mixed with CJK characters (#15) #41

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions cleantext/clean.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -127,6 +127,14 @@ def replace_urls(text, replace_with="<URL>"):
"""
Replace all URLs in ``text`` str with ``replace_with`` str.
"""
CJK = r'[\u4e00-\u9fff\u3040-\u30ff]' # CJK Unicode ranges: \u4e00-\u9fff (Chinese/Japanese Kanji), \u3040-\u30ff (Hiragana/Katakana)
B = r'[^\s，。？！；：、（）【】「」“”‘’\)\]\}]'
text = re.sub(
r'(' + B + r'*?' + CJK + B + r'*?https?://' + B + r'*|' +
B + r'*?https?://' + B + r'*?' + CJK + B + r'*)',
lambda m: ''.join(re.findall(CJK, m.group(1))) + replace_with,
text
)
return constants.URL_REGEX.sub(replace_with, text)


Expand Down
24 changes: 24 additions & 0 deletions tests/test_clean.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,30 @@ def test_replace_urls():
assert cleantext.replace_urls(text, "*URL*") == proc_text


def test_replace_CJK_urls():
texts = [
[
"请点击http://www.example.com查看内容",
"请点击查看内容*URL*",
],
[
"http://www.tie你好ba.com",
"你好*URL*",
],
[
"こんにちはhttp://example.com/テスト",
"こんにちはテスト*URL*",
],
[
"前部http://leetcode.com後ろにある",
"前部後ろにある*URL*",
],
]

for text, proc_text in texts:
assert cleantext.replace_urls(text, "*URL*") == proc_text


email_addresses = [
"mustermann@fh-aachen.de",
"mustermann(at)fh-aachen.de",
Expand Down