improve re efficiency

This commit is contained in:
binary-husky 2023-07-24 18:50:29 +08:00 committed by GitHub
parent c2701c9ce5
commit 56bb8b6498
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -22,7 +22,8 @@ def split_subprocess(txt, project_folder, return_dict, opts):
mask = np.zeros(len(txt), dtype=np.uint8) + TRANSFORM mask = np.zeros(len(txt), dtype=np.uint8) + TRANSFORM
# 吸收title与作者以上的部分 # 吸收title与作者以上的部分
text, mask = set_forbidden_text(text, mask, r"(.*?)\\maketitle", re.DOTALL) text, mask = set_forbidden_text(text, mask, r"^(.*?)\\maketitle", re.DOTALL)
text, mask = set_forbidden_text(text, mask, r"^(.*?)\\begin{document}", re.DOTALL)
# 吸收iffalse注释 # 吸收iffalse注释
text, mask = set_forbidden_text(text, mask, r"\\iffalse(.*?)\\fi", re.DOTALL) text, mask = set_forbidden_text(text, mask, r"\\iffalse(.*?)\\fi", re.DOTALL)
# 吸收在42行以内的begin-end组合 # 吸收在42行以内的begin-end组合