feat: add paddleocr parser (#12513)

### What problem does this PR solve?

Add PaddleOCR as a new PDF parser.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Lin Manhui
2026-01-09 17:48:45 +08:00
committed by GitHub
parent 6abf55c048
commit 2e09db02f3
34 changed files with 1510 additions and 453 deletions

View File

@ -26,5 +26,8 @@ def normalize_layout_recognizer(layout_recognizer_raw: Any) -> tuple[Any, str |
if lowered.endswith("@mineru"):
parser_model_name = layout_recognizer_raw.rsplit("@", 1)[0]
layout_recognizer = "MinerU"
elif lowered.endswith("@paddleocr"):
parser_model_name = layout_recognizer_raw.rsplit("@", 1)[0]
layout_recognizer = "PaddleOCR"
return layout_recognizer, parser_model_name