AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-08-18 07:25:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

Let 'One' applicable for tables in docx (#3619)

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

#3598

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Performance Improvement
This commit is contained in:
Kevin Hu 2024-11-25 09:57:54 +08:00 committed by GitHub
parent 6a3f9bc32a
commit 609236f5c1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
rag/app/one.py
View File

@ -16,7 +16,7 @@ from io import BytesIO
import re import re
from deepdoc.parser.utils import get_text from deepdoc.parser.utils import get_text
from rag.app import laws from rag.app import naive
from rag.nlp import rag_tokenizer, tokenize from rag.nlp import rag_tokenizer, tokenize
from deepdoc.parser import PdfParser, ExcelParser, PlainParser, HtmlParser from deepdoc.parser import PdfParser, ExcelParser, PlainParser, HtmlParser
@ -67,7 +67,10 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
if re.search(r"\.docx$", filename, re.IGNORECASE): if re.search(r"\.docx$", filename, re.IGNORECASE):
callback(0.1, "Start to parse.") callback(0.1, "Start to parse.")
sections = [txt for txt in laws.Docx()(filename, binary) if txt] sections, tbls = naive.Docx()(filename, binary)
sections = [s for s, _ in sections if s]
for (_, html), _ in tbls:
sections.append(html)
callback(0.8, "Finish parsing.") callback(0.8, "Finish parsing.")
elif re.search(r"\.pdf$", filename, re.IGNORECASE): elif re.search(r"\.pdf$", filename, re.IGNORECASE):