Benjamin_Boenisch/breakpilot-lehrer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

debug: add diagnostic logging to _ocr_cell_crop for empty cell investigation

Browse Source 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-03-04 16:35:33 +01:00
parent d0e7966925
commit e4bdb3cc24
1 changed files with 11 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
klausur-service/backend/cv_vocab_pipeline.py
View File

@@ -4727,6 +4727,7 @@ def _ocr_cell_crop(
}
if cw <= 0 or ch <= 0:
logger.debug("_ocr_cell_crop R%02d_C%d: zero-size crop (%dx%d)", row_idx, col_idx, cw, ch)
return empty_cell
# --- Pixel-density check: skip truly empty cells ---
@@ -4735,6 +4736,8 @@ def _ocr_cell_crop(
if crop.size > 0:
dark_ratio = float(np.count_nonzero(crop < 180)) / crop.size
if dark_ratio < 0.005:
logger.debug("_ocr_cell_crop R%02d_C%d: skip empty (dark_ratio=%.4f, crop=%dx%d)",
row_idx, col_idx, dark_ratio, cw, ch)
return empty_cell
# --- Prepare crop for OCR ---
@@ -4787,6 +4790,11 @@ def _ocr_cell_crop(
y_tol = max(15, ch)
text = _words_to_reading_order_text(words, y_tolerance_px=y_tol)
avg_conf = round(sum(w['conf'] for w in words) / len(words), 1)
logger.debug("_ocr_cell_crop R%02d_C%d: OCR raw text=%r conf=%.1f nwords=%d crop=%dx%d psm=%s engine=%s",
row_idx, col_idx, text, avg_conf, len(words), cw, ch, psm, engine_name)
else:
logger.debug("_ocr_cell_crop R%02d_C%d: OCR returned NO words (crop=%dx%d psm=%s engine=%s)",
row_idx, col_idx, cw, ch, psm, engine_name)
# --- PSM 7 fallback for still-empty Tesseract cells ---
if not text.strip() and engine_name == "tesseract" and ocr_img is not None:
@@ -4808,8 +4816,11 @@ def _ocr_cell_crop(
# --- Noise filter ---
if text.strip():
pre_filter = text
text = _clean_cell_text_lite(text)
if not text:
logger.debug("_ocr_cell_crop R%02d_C%d: _clean_cell_text_lite REMOVED %r",
row_idx, col_idx, pre_filter)
avg_conf = 0.0
result = dict(empty_cell)