fix: remove padding from GLMOCREndToEndService and clean up ruff violations

- Drop image padding in GLMOCREndToEndService.recognize(); use raw image directly
- Fix F821 undefined `padded` references replaced with `image`
- Fix F601 duplicate dict key "≠" in converter
- Fix F841 unused `image_cls_ids` variable in layout_postprocess
- Fix E702 semicolon-separated statements in layout_postprocess
- Fix UP031 percent-format replaced with f-string in logging_config
- Auto-fix 44 additional ruff violations (import order, UP035/UP045/UP006, F401, F541)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
liuyuanchuang
2026-03-10 19:52:22 +08:00
parent f8173f7c0a
commit 30d2c2f45b
16 changed files with 162 additions and 140 deletions

View File

@@ -1,12 +1,11 @@
"""PP-DocLayoutV3 wrapper for document layout detection."""
import numpy as np
from app.schemas.image import LayoutInfo, LayoutRegion
from app.core.config import get_settings
from app.services.layout_postprocess import apply_layout_postprocess
from paddleocr import LayoutDetection
from typing import Optional
from app.core.config import get_settings
from app.schemas.image import LayoutInfo, LayoutRegion
from app.services.layout_postprocess import apply_layout_postprocess
settings = get_settings()
@@ -14,7 +13,7 @@ settings = get_settings()
class LayoutDetector:
"""Layout detector for PP-DocLayoutV2."""
_layout_detector: Optional[LayoutDetection] = None
_layout_detector: LayoutDetection | None = None
# PP-DocLayoutV2 class ID to label mapping
CLS_ID_TO_LABEL: dict[int, str] = {
@@ -156,10 +155,11 @@ class LayoutDetector:
if __name__ == "__main__":
import cv2
from app.core.config import get_settings
from app.services.image_processor import ImageProcessor
from app.services.converter import Converter
from app.services.ocr_service import OCRService
from app.services.image_processor import ImageProcessor
from app.services.ocr_service import GLMOCREndToEndService
settings = get_settings()
@@ -169,15 +169,15 @@ if __name__ == "__main__":
converter = Converter()
# Initialize OCR service
ocr_service = OCRService(
vl_server_url=settings.paddleocr_vl_url,
ocr_service = GLMOCREndToEndService(
vl_server_url=settings.glm_ocr_url,
layout_detector=layout_detector,
image_processor=image_processor,
converter=converter,
)
# Load test image
image_path = "test/timeout.jpg"
image_path = "test/image2.png"
image = cv2.imread(image_path)
if image is None: