adjust hierarchical_merge strategy (#100)

This commit is contained in:
KevinHuSh
2024-03-06 09:09:16 +08:00
committed by GitHub
parent 8b2bbd79e4
commit d7c362f237
3 changed files with 77 additions and 45 deletions

View File

@ -103,7 +103,6 @@ def chunk(filename, binary=None, from_page=0, to_page=100000, lang="Chinese", ca
if not l:break
txt += l
sections = txt.split("\n")
sections = txt.split("\n")
sections = [l for l in sections if l]
callback(0.8, "Finish parsing.")
else: raise NotImplementedError("file type not supported yet(docx, pdf, txt supported)")