pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-31 17:15:32 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix IDE warnings (#12281)

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

As title

### Type of change

- [x] Refactoring

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
This commit is contained in:
Jin Hai
2025-12-29 12:01:18 +08:00
committed by GitHub
parent 647fb115a0
commit 01f0ced1e6
43 changed files with 817 additions and 637 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
rag/app/paper.py
View File

@ -20,7 +20,8 @@ import re
from deepdoc.parser.figure_parser import vision_figure_parser_pdf_wrapper
from common.constants import ParserType
from rag.nlp import rag_tokenizer, tokenize, tokenize_table, add_positions, bullets_category, title_frequency, tokenize_chunks, attach_media_context
from rag.nlp import rag_tokenizer, tokenize, tokenize_table, add_positions, bullets_category, title_frequency, \
tokenize_chunks, attach_media_context
from deepdoc.parser import PdfParser
import numpy as np
from rag.app.naive import by_plaintext, PARSERS
@ -66,7 +67,7 @@ class Pdf(PdfParser):
# clean mess
if column_width < self.page_images[0].size[0] / zoomin / 2:
logging.debug("two_column................... {} {}".format(column_width,
self.page_images[0].size[0] / zoomin / 2))
self.page_images[0].size[0] / zoomin / 2))
self.boxes = self.sort_X_by_page(self.boxes, column_width / 2)
for b in self.boxes:
b["text"] = re.sub(r"([\t 　]|\u3000){2,}", " ", b["text"].strip())
@ -89,7 +90,7 @@ class Pdf(PdfParser):
title = ""
authors = []
i = 0
while i < min(32, len(self.boxes)-1):
while i < min(32, len(self.boxes) - 1):
b = self.boxes[i]
i += 1
if b.get("layoutno", "").find("title") >= 0:
@ -190,8 +191,8 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
"tables": tables
}
tbls=paper["tables"]
tbls=vision_figure_parser_pdf_wrapper(tbls=tbls,callback=callback,**kwargs)
tbls = paper["tables"]
tbls = vision_figure_parser_pdf_wrapper(tbls=tbls, callback=callback, **kwargs)
paper["tables"] = tbls
else:
raise NotImplementedError("file type not supported yet(pdf supported)")
@ -329,6 +330,9 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
if __name__ == "__main__":
import sys
def dummy(prog=None, msg=""):
pass
chunk(sys.argv[1], callback=dummy)