keboss/opencode
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix _run_rapidocr: rapidocr API

Browse Source
This commit is contained in:
keboss-m 2026-06-01 13:24:49 +03:00
parent 1a72168f98
commit b344ef6f59
1 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
process_any_pdf.py
View File

@ -157,13 +157,12 @@ def process_pdf(pdf_path: Path, out_dir: Path, use_qwen: bool = False, use_tilin
def _run_rapidocr(img_path: Path): def _run_rapidocr(img_path: Path):
res = engine(img_path) res = engine(img_path)
ocr_lines = [] ocr_lines = []
if res and res[0] is not None: if res and res.txts is not None:
for item in res[0]: for txt, box, score in zip(res.txts, res.boxes, res.scores):
box, txt, score = item
ocr_lines.append({ ocr_lines.append({
"text": txt, "text": txt,
"confidence": float(score), "confidence": float(score),
"bbox": box "bbox": box.tolist() if hasattr(box, "tolist") else box
}) })
return ocr_lines return ocr_lines