Skip to content

Revert "feat: 将换行更换为双换行、配置全局常量 (#320)" #321

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

Merged
yogacc33 merged 1 commit into from
Mar 20, 2025
Merged

Revert "feat: 将换行更换为双换行、配置全局常量 (#320)" #321

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
3 changes: 0 additions & 3 deletions llm_web_kit/extractor/html/recognizer/constant.py
View file
Open in desktop

This file was deleted.

8 changes: 3 additions & 5 deletions llm_web_kit/extractor/html/recognizer/text.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,8 +11,6 @@
from llm_web_kit.libs.doc_element_type import DocElementType, ParagraphTextType
from llm_web_kit.libs.html_utils import element_to_html

from .constant import LINE_BREAK_UNIX, LINE_BREAK_WINDOWS, PARAGRAPH_SEPARATOR

special_symbols = [ # TODO 从文件读取
'®', # 注册商标符号
'™', # 商标符号
Expand Down Expand Up @@ -114,11 +112,11 @@ def __combine_text(self, text1:str, text2:str, lang='en') -> str:
text2 = text2.strip(' ') if text2 else ''
if lang == 'zh':
txt = text1 + text2
return txt.strip().replace(LINE_BREAK_WINDOWS, PARAGRAPH_SEPARATOR).replace(LINE_BREAK_UNIX, PARAGRAPH_SEPARATOR)
return txt.strip().replace('\\r\\n', '\n').replace('\\n', '\n')
else:
words_sep = '' if text2[0] in string.punctuation or text2[0] in special_symbols else ' '
txt = text1 + words_sep + text2
return txt.strip().replace(LINE_BREAK_WINDOWS, PARAGRAPH_SEPARATOR).replace(LINE_BREAK_UNIX, PARAGRAPH_SEPARATOR)
return txt.strip().replace('\\r\\n', '\n').replace('\\n', '\n')

def __get_paragraph_text(self, root: HtmlElement) -> List[dict]:
"""
Expand Down Expand Up @@ -147,7 +145,7 @@ def __get_paragraph_text_recusive(el: HtmlElement, text: str) -> str:
text = ''
para_text.append({'c': el.text, 't': ParagraphTextType.CODE_INLINE})
elif el.tag in ['br']:
text += PARAGRAPH_SEPARATOR
text += '\n'
else:
if el.text and el.text.strip():
text = self.__combine_text(text, el.text.strip())
Expand Down
Loading