egg/OCR
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: pass preprocessing parameters from start_task to OCR service

Browse Source 
The preprocessing_mode and preprocessing_config parameters were not
being passed from the start_task endpoint through to the OCR service:
- Add preprocessing_mode and preprocessing_config to process_task_ocr()
- Extract preprocessing options from ProcessingOptions in start_task()
- Convert string/dict to proper PreprocessingModeEnum/PreprocessingConfig
- Pass converted parameters to ocr_service.process() and process_image()

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
egg
2025-11-27 16:13:32 +08:00
parent 19cb80460f
commit f6d2957592
1 changed files with 40 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
backend/app/routers/tasks.py
View File

@@ -73,7 +73,9 @@ def process_task_ocr(
use_dual_track: bool = True,
force_track: Optional[str] = None,
language: str = 'ch',
layout_model: Optional[str] = "chinese"
layout_model: Optional[str] = "chinese",
preprocessing_mode: Optional[str] = "auto",
preprocessing_config: Optional[dict] = None
):
"""
Background task to process OCR for a task with dual-track support.
@@ -90,6 +92,8 @@ def process_task_ocr(
force_track: Force specific track ('ocr' or 'direct')
language: OCR language code
layout_model: Layout detection model ('chinese', 'default', 'cdla')
preprocessing_mode: Preprocessing mode ('auto', 'manual', 'disabled')
preprocessing_config: Manual preprocessing config dict (contrast, sharpen, binarize)
"""
from app.core.database import SessionLocal
from app.models.task import Task
@@ -101,6 +105,20 @@ def process_task_ocr(
try:
logger.info(f"Starting OCR processing for task {task_id}, file: {filename}")
logger.info(f"Processing options: dual_track={use_dual_track}, force_track={force_track}, lang={language}")
logger.info(f"Preprocessing options: mode={preprocessing_mode}, config={preprocessing_config}")
# Convert preprocessing parameters to proper types
preprocess_mode_enum = None
preprocess_config_obj = None
if preprocessing_mode:
preprocess_mode_enum = PreprocessingModeEnum(preprocessing_mode)
if preprocessing_config:
from app.schemas.task import PreprocessingContrastEnum
preprocess_config_obj = PreprocessingConfig(
contrast=PreprocessingContrastEnum(preprocessing_config.get("contrast", "clahe")),
sharpen=preprocessing_config.get("sharpen", True),
binarize=preprocessing_config.get("binarize", False)
)
# Get task directly by database ID (bypass user isolation for background task)
task = db.query(Task).filter(Task.id == task_db_id).first()
@@ -148,7 +166,9 @@ def process_task_ocr(
output_dir=result_dir,
use_dual_track=use_dual_track,
force_track=force_track,
layout_model=layout_model
layout_model=layout_model,
preprocessing_mode=preprocess_mode_enum,
preprocessing_config=preprocess_config_obj
)
else:
# Fall back to traditional processing (no force_track support)
@@ -157,7 +177,9 @@ def process_task_ocr(
lang=language,
detect_layout=True,
output_dir=result_dir,
layout_model=layout_model
layout_model=layout_model,
preprocessing_mode=preprocess_mode_enum,
preprocessing_config=preprocess_config_obj
)
# Calculate processing time
@@ -744,6 +766,17 @@ async def start_task(
layout_model = options.layout_model.value if options.layout_model else "chinese"
logger.info(f"Using layout model: {layout_model}")
# Extract preprocessing options
preprocessing_mode = options.preprocessing_mode.value if options.preprocessing_mode else "auto"
preprocessing_config = None
if options.preprocessing_config:
preprocessing_config = {
"contrast": options.preprocessing_config.contrast.value,
"sharpen": options.preprocessing_config.sharpen,
"binarize": options.preprocessing_config.binarize
}
logger.info(f"Preprocessing: mode={preprocessing_mode}, config={preprocessing_config}")
# Get task details
task = task_service.get_task_by_id(
db=db,
@@ -790,11 +823,13 @@ async def start_task(
use_dual_track=use_dual_track,
force_track=force_track,
language=language,
layout_model=layout_model
layout_model=layout_model,
preprocessing_mode=preprocessing_mode,
preprocessing_config=preprocessing_config
)
logger.info(f"Started OCR processing task {task_id} for user {current_user.email}")
logger.info(f"Options: dual_track={use_dual_track}, force_track={force_track}, lang={language}, layout_model={layout_model}")
logger.info(f"Options: dual_track={use_dual_track}, force_track={force_track}, lang={language}, layout_model={layout_model}, preprocessing={preprocessing_mode}")
return task
except HTTPException: