remove doc from supported processing types (#488)

### What problem does this PR solve?
#474 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
KevinHuSh
2024-04-22 15:46:09 +08:00
committed by GitHub
parent 3610e1e5b4
commit a38e163035
4 changed files with 4 additions and 4 deletions

View File

@ -60,7 +60,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
eng = lang.lower() == "english" # is_english(cks)
if re.search(r"\.docx?$", filename, re.IGNORECASE):
if re.search(r"\.docx$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.")
sections = [txt for txt in laws.Docx()(filename, binary) if txt]
callback(0.8, "Finish parsing.")