[split-required] Split 500-850 LOC files (batch 2)
backend-lehrer (10 files): - game/database.py (785 → 5), correction_api.py (683 → 4) - classroom_engine/antizipation.py (676 → 5) - llm_gateway schools/edu_search already done in prior batch klausur-service (12 files): - orientation_crop_api.py (694 → 5), pdf_export.py (677 → 4) - zeugnis_crawler.py (676 → 5), grid_editor_api.py (671 → 5) - eh_templates.py (658 → 5), mail/api.py (651 → 5) - qdrant_service.py (638 → 5), training_api.py (625 → 4) website (6 pages): - middleware (696 → 8), mail (733 → 6), consent (628 → 8) - compliance/risks (622 → 5), export (502 → 5), brandbook (629 → 7) studio-v2 (3 components): - B2BMigrationWizard (848 → 3), CleanupPanel (765 → 2) - dashboard-experimental (739 → 2) admin-lehrer (4 files): - uebersetzungen (769 → 4), manager (670 → 2) - ChunkBrowserQA (675 → 6), dsfa/page (674 → 5) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
290
klausur-service/backend/crop_api.py
Normal file
290
klausur-service/backend/crop_api.py
Normal file
@@ -0,0 +1,290 @@
|
||||
"""
|
||||
Crop API endpoints (Step 4 / UI index 3 of OCR Pipeline).
|
||||
|
||||
Auto-crop, manual crop, and skip-crop for scanner/book borders.
|
||||
"""
|
||||
|
||||
import logging
|
||||
import time
|
||||
from typing import Any, Dict
|
||||
|
||||
import cv2
|
||||
from fastapi import APIRouter, HTTPException
|
||||
from pydantic import BaseModel
|
||||
|
||||
from page_crop import detect_and_crop_page, detect_page_splits
|
||||
from ocr_pipeline_session_store import get_sub_sessions, update_session_db
|
||||
|
||||
from orientation_crop_helpers import ensure_cached, append_pipeline_log
|
||||
from page_sub_sessions import create_page_sub_sessions
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter(prefix="/api/v1/ocr-pipeline", tags=["ocr-pipeline"])
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Step 4 (UI index 3): Crop — runs after deskew + dewarp
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
@router.post("/sessions/{session_id}/crop")
|
||||
async def auto_crop(session_id: str):
|
||||
"""Auto-detect and crop scanner/book borders.
|
||||
|
||||
Reads the dewarped image (post-deskew + dewarp, so the page is straight).
|
||||
Falls back to oriented -> original if earlier steps were skipped.
|
||||
|
||||
If the image is a multi-page spread (e.g. book on scanner), it will
|
||||
automatically split into separate sub-sessions per page, crop each
|
||||
individually, and return the split info.
|
||||
"""
|
||||
cached = await ensure_cached(session_id)
|
||||
|
||||
# Use dewarped (preferred), fall back to oriented, then original
|
||||
img_bgr = next(
|
||||
(v for k in ("dewarped_bgr", "oriented_bgr", "original_bgr")
|
||||
if (v := cached.get(k)) is not None),
|
||||
None,
|
||||
)
|
||||
if img_bgr is None:
|
||||
raise HTTPException(status_code=400, detail="No image available for cropping")
|
||||
|
||||
t0 = time.time()
|
||||
|
||||
# --- Check for existing sub-sessions (from page-split step) ---
|
||||
# If page-split already created sub-sessions, skip multi-page detection
|
||||
# in the crop step. Each sub-session runs its own crop independently.
|
||||
existing_subs = await get_sub_sessions(session_id)
|
||||
if existing_subs:
|
||||
crop_result = cached.get("crop_result") or {}
|
||||
if crop_result.get("multi_page"):
|
||||
# Already split -- just return the existing info
|
||||
duration = time.time() - t0
|
||||
h, w = img_bgr.shape[:2]
|
||||
return {
|
||||
"session_id": session_id,
|
||||
**crop_result,
|
||||
"image_width": w,
|
||||
"image_height": h,
|
||||
"sub_sessions": [
|
||||
{"id": s["id"], "name": s.get("name"), "page_index": s.get("box_index", i)}
|
||||
for i, s in enumerate(existing_subs)
|
||||
],
|
||||
"note": "Page split was already performed; each sub-session runs its own crop.",
|
||||
}
|
||||
|
||||
# --- Multi-page detection (fallback for sessions that skipped page-split) ---
|
||||
page_splits = detect_page_splits(img_bgr)
|
||||
|
||||
if page_splits and len(page_splits) >= 2:
|
||||
# Multi-page spread detected -- create sub-sessions
|
||||
sub_sessions = await create_page_sub_sessions(
|
||||
session_id, cached, img_bgr, page_splits,
|
||||
)
|
||||
duration = time.time() - t0
|
||||
|
||||
crop_info: Dict[str, Any] = {
|
||||
"crop_applied": True,
|
||||
"multi_page": True,
|
||||
"page_count": len(page_splits),
|
||||
"page_splits": page_splits,
|
||||
"duration_seconds": round(duration, 2),
|
||||
}
|
||||
cached["crop_result"] = crop_info
|
||||
|
||||
# Store the first page as the main cropped image for backward compat
|
||||
first_page = page_splits[0]
|
||||
first_bgr = img_bgr[
|
||||
first_page["y"]:first_page["y"] + first_page["height"],
|
||||
first_page["x"]:first_page["x"] + first_page["width"],
|
||||
].copy()
|
||||
first_cropped, _ = detect_and_crop_page(first_bgr)
|
||||
cached["cropped_bgr"] = first_cropped
|
||||
|
||||
ok, png_buf = cv2.imencode(".png", first_cropped)
|
||||
await update_session_db(
|
||||
session_id,
|
||||
cropped_png=png_buf.tobytes() if ok else b"",
|
||||
crop_result=crop_info,
|
||||
current_step=5,
|
||||
status='split',
|
||||
)
|
||||
|
||||
logger.info(
|
||||
"OCR Pipeline: crop session %s: multi-page split into %d pages in %.2fs",
|
||||
session_id, len(page_splits), duration,
|
||||
)
|
||||
|
||||
await append_pipeline_log(session_id, "crop", {
|
||||
"multi_page": True,
|
||||
"page_count": len(page_splits),
|
||||
}, duration_ms=int(duration * 1000))
|
||||
|
||||
h, w = first_cropped.shape[:2]
|
||||
return {
|
||||
"session_id": session_id,
|
||||
**crop_info,
|
||||
"image_width": w,
|
||||
"image_height": h,
|
||||
"cropped_image_url": f"/api/v1/ocr-pipeline/sessions/{session_id}/image/cropped",
|
||||
"sub_sessions": sub_sessions,
|
||||
}
|
||||
|
||||
# --- Single page (normal) ---
|
||||
cropped_bgr, crop_info = detect_and_crop_page(img_bgr)
|
||||
|
||||
duration = time.time() - t0
|
||||
crop_info["duration_seconds"] = round(duration, 2)
|
||||
crop_info["multi_page"] = False
|
||||
|
||||
# Encode cropped image
|
||||
success, png_buf = cv2.imencode(".png", cropped_bgr)
|
||||
cropped_png = png_buf.tobytes() if success else b""
|
||||
|
||||
# Update cache
|
||||
cached["cropped_bgr"] = cropped_bgr
|
||||
cached["crop_result"] = crop_info
|
||||
|
||||
# Persist to DB
|
||||
await update_session_db(
|
||||
session_id,
|
||||
cropped_png=cropped_png,
|
||||
crop_result=crop_info,
|
||||
current_step=5,
|
||||
)
|
||||
|
||||
logger.info(
|
||||
"OCR Pipeline: crop session %s: applied=%s format=%s in %.2fs",
|
||||
session_id, crop_info["crop_applied"],
|
||||
crop_info.get("detected_format", "?"),
|
||||
duration,
|
||||
)
|
||||
|
||||
await append_pipeline_log(session_id, "crop", {
|
||||
"crop_applied": crop_info["crop_applied"],
|
||||
"detected_format": crop_info.get("detected_format"),
|
||||
"format_confidence": crop_info.get("format_confidence"),
|
||||
}, duration_ms=int(duration * 1000))
|
||||
|
||||
h, w = cropped_bgr.shape[:2]
|
||||
return {
|
||||
"session_id": session_id,
|
||||
**crop_info,
|
||||
"image_width": w,
|
||||
"image_height": h,
|
||||
"cropped_image_url": f"/api/v1/ocr-pipeline/sessions/{session_id}/image/cropped",
|
||||
}
|
||||
|
||||
|
||||
class ManualCropRequest(BaseModel):
|
||||
x: float # percentage 0-100
|
||||
y: float # percentage 0-100
|
||||
width: float # percentage 0-100
|
||||
height: float # percentage 0-100
|
||||
|
||||
|
||||
@router.post("/sessions/{session_id}/crop/manual")
|
||||
async def manual_crop(session_id: str, req: ManualCropRequest):
|
||||
"""Manually crop using percentage coordinates."""
|
||||
cached = await ensure_cached(session_id)
|
||||
|
||||
img_bgr = next(
|
||||
(v for k in ("dewarped_bgr", "oriented_bgr", "original_bgr")
|
||||
if (v := cached.get(k)) is not None),
|
||||
None,
|
||||
)
|
||||
if img_bgr is None:
|
||||
raise HTTPException(status_code=400, detail="No image available for cropping")
|
||||
|
||||
h, w = img_bgr.shape[:2]
|
||||
|
||||
# Convert percentages to pixels
|
||||
px_x = int(w * req.x / 100.0)
|
||||
px_y = int(h * req.y / 100.0)
|
||||
px_w = int(w * req.width / 100.0)
|
||||
px_h = int(h * req.height / 100.0)
|
||||
|
||||
# Clamp
|
||||
px_x = max(0, min(px_x, w - 1))
|
||||
px_y = max(0, min(px_y, h - 1))
|
||||
px_w = max(1, min(px_w, w - px_x))
|
||||
px_h = max(1, min(px_h, h - px_y))
|
||||
|
||||
cropped_bgr = img_bgr[px_y:px_y + px_h, px_x:px_x + px_w].copy()
|
||||
|
||||
success, png_buf = cv2.imencode(".png", cropped_bgr)
|
||||
cropped_png = png_buf.tobytes() if success else b""
|
||||
|
||||
crop_result = {
|
||||
"crop_applied": True,
|
||||
"crop_rect": {"x": px_x, "y": px_y, "width": px_w, "height": px_h},
|
||||
"crop_rect_pct": {"x": round(req.x, 2), "y": round(req.y, 2),
|
||||
"width": round(req.width, 2), "height": round(req.height, 2)},
|
||||
"original_size": {"width": w, "height": h},
|
||||
"cropped_size": {"width": px_w, "height": px_h},
|
||||
"method": "manual",
|
||||
}
|
||||
|
||||
cached["cropped_bgr"] = cropped_bgr
|
||||
cached["crop_result"] = crop_result
|
||||
|
||||
await update_session_db(
|
||||
session_id,
|
||||
cropped_png=cropped_png,
|
||||
crop_result=crop_result,
|
||||
current_step=5,
|
||||
)
|
||||
|
||||
ch, cw = cropped_bgr.shape[:2]
|
||||
return {
|
||||
"session_id": session_id,
|
||||
**crop_result,
|
||||
"image_width": cw,
|
||||
"image_height": ch,
|
||||
"cropped_image_url": f"/api/v1/ocr-pipeline/sessions/{session_id}/image/cropped",
|
||||
}
|
||||
|
||||
|
||||
@router.post("/sessions/{session_id}/crop/skip")
|
||||
async def skip_crop(session_id: str):
|
||||
"""Skip cropping -- use dewarped (or oriented/original) image as-is."""
|
||||
cached = await ensure_cached(session_id)
|
||||
|
||||
img_bgr = next(
|
||||
(v for k in ("dewarped_bgr", "oriented_bgr", "original_bgr")
|
||||
if (v := cached.get(k)) is not None),
|
||||
None,
|
||||
)
|
||||
if img_bgr is None:
|
||||
raise HTTPException(status_code=400, detail="No image available")
|
||||
|
||||
h, w = img_bgr.shape[:2]
|
||||
|
||||
# Store the dewarped image as cropped (identity crop)
|
||||
success, png_buf = cv2.imencode(".png", img_bgr)
|
||||
cropped_png = png_buf.tobytes() if success else b""
|
||||
|
||||
crop_result = {
|
||||
"crop_applied": False,
|
||||
"skipped": True,
|
||||
"original_size": {"width": w, "height": h},
|
||||
"cropped_size": {"width": w, "height": h},
|
||||
}
|
||||
|
||||
cached["cropped_bgr"] = img_bgr
|
||||
cached["crop_result"] = crop_result
|
||||
|
||||
await update_session_db(
|
||||
session_id,
|
||||
cropped_png=cropped_png,
|
||||
crop_result=crop_result,
|
||||
current_step=5,
|
||||
)
|
||||
|
||||
return {
|
||||
"session_id": session_id,
|
||||
**crop_result,
|
||||
"image_width": w,
|
||||
"image_height": h,
|
||||
"cropped_image_url": f"/api/v1/ocr-pipeline/sessions/{session_id}/image/cropped",
|
||||
}
|
||||
Reference in New Issue
Block a user