Skip to content

GitLab

Unverified Commit 30be5017 authored by Xiaomeng Zhao's avatar Xiaomeng Zhao Committed by GitHub
Browse files

Merge pull request #1065 from opendatalab/dev 

fix(pdf_parse): improve OCR result handling
parents 809bf479 b936cb0c
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
magic_pdf/pdf_parse_union_core_v2.py
View file @ 30be5017
...@@ -222,7 +222,7 @@ def txt_spans_extract_v2(pdf_page, spans, all_bboxes, all_discarded_blocks, lang ...@@ -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) ocr_res = ocr_model.ocr(span_img, det=False)
# logger.info(f"ocr_res: {ocr_res}") # logger.info(f"ocr_res: {ocr_res}")
# logger.info(f"empty_span: {span}") # 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: if len(ocr_res[0]) > 0:
ocr_text, ocr_score = ocr_res[0][0] ocr_text, ocr_score = ocr_res[0][0]
if ocr_score > 0.5 and len(ocr_text) > 0: if ocr_score > 0.5 and len(ocr_text) > 0:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment