ソースを参照

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

### What problem does this PR solve?

#3598

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Performance Improvement
tags/v0.14.0
Kevin Hu 11ヶ月前
コミット
609236f5c1
コミッターのメールアドレスに関連付けられたアカウントが存在しません
1個のファイルの変更5行の追加2行の削除
  1. 5
    2
      rag/app/one.py

+ 5
- 2
rag/app/one.py ファイルの表示

@@ -16,7 +16,7 @@ from io import BytesIO
import re

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 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):
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.")

elif re.search(r"\.pdf$", filename, re.IGNORECASE):

読み込み中…
キャンセル
保存