pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

refine presentation parser (#110)

Browse Source
This commit is contained in:
KevinHuSh
2024-03-07 17:21:38 +08:00
committed by GitHub
parent 2d7c9080f4
commit 436c52bbc5
3 changed files with 15 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
rag/app/presentation.py
View File

@ -88,20 +88,25 @@ def chunk(filename, binary=None, from_page=0, to_page=100000, lang="Chinese", ca
res = []
if re.search(r"\.pptx?$", filename, re.IGNORECASE):
ppt_parser = Ppt()
for txt,img in ppt_parser(filename if not binary else binary, from_page, 1000000, callback):
for pn, (txt,img) in enumerate(ppt_parser(filename if not binary else binary, from_page, 1000000, callback)):
d = copy.deepcopy(doc)
pn += from_page
d["image"] = img
tokenize(d, txt, ppt_parser.is_english)
d["page_num_int"] = [pn+1]
d["top_int"] = [0]
d["position_int"] = [(pn + 1, 0, img.size[0], 0, img.size[1])]
tokenize(d, txt, eng)
res.append(d)
return res
elif re.search(r"\.pdf$", filename, re.IGNORECASE):
pdf_parser = Pdf()
for pn, (txt,img) in enumerate(pdf_parser(filename if not binary else binary, from_page=from_page, to_page=to_page, callback=callback)):
d = copy.deepcopy(doc)
pn += from_page
d["image"] = img
d["page_num_int"] = [pn+1]
d["top_int"] = [0]
d["position_int"].append((pn + 1, 0, img.size[0], 0, img.size[1]))
d["position_int"] = [(pn + 1, 0, img.size[0], 0, img.size[1])]
tokenize(d, txt, eng)
res.append(d)
return res