opensource/MinerU
3
0
Fork 0
mirror of https://github.com/opendatalab/MinerU.git synced 2026-09-24 23:10:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(pdf_parse): improve OCR result handling

Browse Source 
- Add null check for OCR results to prevent errors on empty lists
- Enhance robustness of OCR text processing in the magic-pdf project
This commit is contained in:
myhloli
2024-11-22 17:45:14 +08:00
parent f1e2f08467
commit 6b296ee2b5
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
magic_pdf/pdf_parse_union_core_v2.py
+1 -1
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: