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

resolve the issue of naive parser (#87)

Browse Source
This commit is contained in:
KevinHuSh
2024-02-29 18:53:02 +08:00
committed by GitHub
parent 28531fc73d
commit 3d4315c42a
7 changed files with 41 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
deepdoc/parser/pdf_parser.py
View File

@ -24,9 +24,10 @@ logging.getLogger("pdfminer").setLevel(logging.WARNING)
class HuParser:
def __init__(self):
self.ocr = OCR()
if not hasattr(self, "model_speciess"):
self.model_speciess = ParserType.NAIVE.value
self.layouter = LayoutRecognizer("layout."+self.model_speciess)
if hasattr(self, "model_speciess"):
self.layouter = LayoutRecognizer("layout."+self.model_speciess)
else:
self.layouter = LayoutRecognizer("layout")
self.tbl_det = TableStructureRecognizer()
self.updown_cnt_mdl = xgb.Booster()