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: fix pdf_parser ignored in rag/app/naive.py (#11065)

Browse Source 
### What problem does this PR solve?

Fix: fix pdf_parser ignored in rag/app/naive.py #11000

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Billy Bao
2025-11-06 15:20:35 +08:00
committed by GitHub
parent ca30ef83bf
commit 4b8ce08050
6 changed files with 26 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
rag/app/one.py
View File

@ -23,7 +23,7 @@ from rag.app import naive
from rag.nlp import rag_tokenizer, tokenize
from deepdoc.parser import PdfParser, ExcelParser, HtmlParser
from deepdoc.parser.figure_parser import vision_figure_parser_docx_wrapper
from rag.app.naive import plaintext_parser, PARSERS
from rag.app.naive import by_plaintext, PARSERS
class Pdf(PdfParser):
def __call__(self, filename, binary=None, from_page=0,
@ -88,10 +88,10 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
layout_recognizer = "DeepDOC" if layout_recognizer else "Plain Text"
name = layout_recognizer.strip().lower()
parser = PARSERS.get(name, plaintext_parser)
parser = PARSERS.get(name, by_plaintext)
callback(0.1, "Start to parse.")
sections, tbls, _ = parser(
sections, tbls, pdf_parser = parser(
filename = filename,
binary = binary,
from_page = from_page,