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

fix plainPdf bugs (#152)

Browse Source
This commit is contained in:
KevinHuSh
2024-03-26 15:11:07 +08:00
committed by GitHub
parent 75f7c6da2f
commit da21320b88
13 changed files with 36 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
rag/app/laws.py
View File

@ -68,7 +68,7 @@ class Pdf(PdfParser):
callback(0.8, "Text extraction finished")
return [(b["text"], self._line_tag(b, zoomin)) for b in self.boxes]
return [(b["text"], self._line_tag(b, zoomin)) for b in self.boxes], None
def chunk(filename, binary=None, from_page=0, to_page=100000, lang="Chinese", callback=None, **kwargs):
@ -91,7 +91,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000, lang="Chinese", ca
elif re.search(r"\.pdf$", filename, re.IGNORECASE):
pdf_parser = Pdf() if kwargs.get("parser_config",{}).get("layout_recognize", True) else PlainParser()
for txt, poss in pdf_parser(filename if not binary else binary,
from_page=from_page, to_page=to_page, callback=callback):
from_page=from_page, to_page=to_page, callback=callback)[0]:
sections.append(txt + poss)
elif re.search(r"\.txt$", filename, re.IGNORECASE):

2
rag/app/paper.py
View File

@ -136,7 +136,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000, lang="Chinese", ca
"title": filename,
"authors": " ",
"abstract": "",
"sections": pdf_parser(filename if not binary else binary, from_page=from_page, to_page=to_page),
"sections": pdf_parser(filename if not binary else binary, from_page=from_page, to_page=to_page)[0],
"tables": []
}
else:

2
rag/app/presentation.py
View File

@ -66,7 +66,7 @@ class Pdf(PdfParser):
class PlainPdf(PlainParser):
def __call__(self, filename, binary=None, from_page=0, to_page=100000, callback=None, **kwargs):
self.pdf = pdf2_read(filename if not binary else BytesIO(filename))
self.pdf = pdf2_read(filename if not binary else BytesIO(binary))
page_txt = []
for page in self.pdf.pages[from_page: to_page]:
page_txt.append(page.extract_text())

2
rag/app/resume.py
View File

@ -40,7 +40,7 @@ def remote_call(filename, binary):
"encrypt_type": "base64",
"filename": filename,
"langtype": '',
"fileori": base64.b64encode(binary.stream.read()).decode('utf-8')
"fileori": base64.b64encode(binary).decode('utf-8')
},
"c": "resume_parse_module",
"m": "resume_parse"