centersl/MinerU
1
0
Fork 0
mirror of https://github.com/opendatalab/MinerU.git synced 2026-03-27 11:08:32 +07:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1065 from opendatalab/dev

Browse Source 
fix(pdf_parse): improve OCR result handling
This commit is contained in:
Xiaomeng Zhao
2024-11-22 17:48:07 +08:00
committed by GitHub
parent 809bf4793a b936cb0c25
commit 30be501728
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
magic_pdf/pdf_parse_union_core_v2.py
View File

@@ -222,7 +222,7 @@ def txt_spans_extract_v2(pdf_page, spans, all_bboxes, all_discarded_blocks, lang
ocr_res = ocr_model.ocr(span_img, det=False)
# logger.info(f"ocr_res: {ocr_res}")
# logger.info(f"empty_span: {span}")
if len(ocr_res) > 0:
if ocr_res and len(ocr_res) > 0:
if len(ocr_res[0]) > 0:
ocr_text, ocr_score = ocr_res[0][0]
if ocr_score > 0.5 and len(ocr_text) > 0: