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

refine code (#595)

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

### Type of change

- [x] Refactoring
This commit is contained in:
KevinHuSh
2024-04-28 19:13:33 +08:00
committed by GitHub
parent aee8b48d2f
commit 8c07992b6c
24 changed files with 538 additions and 116 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
deepdoc/vision/table_structure_recognizer.py
View File

@ -19,7 +19,7 @@ import numpy as np
from huggingface_hub import snapshot_download
from api.utils.file_utils import get_project_base_directory
from rag.nlp import huqie
from rag.nlp import rag_tokenizer
from .recognizer import Recognizer
@ -117,14 +117,14 @@ class TableStructureRecognizer(Recognizer):
for p, n in patt:
if re.search(p, b["text"].strip()):
return n
tks = [t for t in huqie.qie(b["text"]).split(" ") if len(t) > 1]
tks = [t for t in rag_tokenizer.tokenize(b["text"]).split(" ") if len(t) > 1]
if len(tks) > 3:
if len(tks) < 12:
return "Tx"
else:
return "Lx"
if len(tks) == 1 and huqie.tag(tks[0]) == "nr":
if len(tks) == 1 and rag_tokenizer.tag(tks[0]) == "nr":
return "Nr"
return "Ot"