Benjamin Admin 5359a4cc2b fix: cache word_result in paddle_kombi/rapid_kombi for detect-structure ...

Both kombi OCR functions wrote word_result to DB but not to the
in-memory cache. When detect-structure ran next, it found no words
and passed an empty list to graphic detection, making all word-overlap
heuristics ineffective. This caused green text words to be wrongly
classified as graphic regions.

Also adds a fallback in detect-structure to use raw OCR word lists
if cell word_boxes are empty.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-18 07:29:02 +01:00

..

data

…

mail

…

migrations

feat: add Excel-like grid editor for OCR overlay (Kombi mode step 6)

2026-03-14 23:41:03 +01:00

models

…

policies

…

routes

…

services

fix: increase PaddleOCR remote timeout to 120s for large scans

2026-03-12 13:41:39 +01:00

tests

feat: box-aware column detection — exclude box content from global columns

2026-03-16 18:42:46 +01:00

admin_api.py

…

config.py

…

country_metadata.py

…

cv_box_detect.py

feat: run shading-based box detection alongside line detection

2026-03-16 08:12:52 +01:00

cv_cell_grid.py

fix: word_boxes auch fuer breite Spalten (Full-Page OCR) speichern

2026-03-11 20:41:29 +01:00

cv_color_detect.py

fix: filter words and color recoveries inside graphic/image regions

2026-03-17 11:20:07 +01:00

cv_graphic_detect.py

fix: robust colored-text detection in graphic filter

2026-03-17 18:09:16 +01:00

cv_layout.py

feat: box-aware column detection — exclude box content from global columns

2026-03-16 18:42:46 +01:00

cv_ocr_engines.py

feat: use local RapidOCR as default in ocr_region_paddle(), remote as fallback

2026-03-14 08:26:04 +01:00

cv_preprocessing.py

fix: swap 90°/270° rotation direction in orientation detection

2026-03-17 16:39:15 +01:00

cv_review.py

fix: _group_words_into_lines nach cv_ocr_engines.py verschieben

2026-03-09 15:24:56 +01:00

cv_vocab_pipeline.py

feat: Words-First Grid Builder (bottom-up alternative zu cell_grid_v2)

2026-03-12 06:46:05 +01:00

cv_vocab_types.py

feat: generische Box-Erkennung fuer zonenbasierte Spaltenerkennung

2026-03-09 15:06:23 +01:00

cv_words_first.py

fix: sort word_boxes in reading order (Y-grouped, then X-sorted)

2026-03-17 10:41:30 +01:00

dsfa_corpus_ingestion.py

…

dsfa_rag_api.py

…

eh_pipeline.py

…

eh_templates.py

…

embedding_client.py

…

full_compliance_pipeline.py

…

full_reingestion.py

…

github_crawler.py

…

grid_editor_api.py

fix: conservative column detection + smart graphic word filter

2026-03-17 18:19:25 +01:00

handwriting_htr_api.py

…

hybrid_search.py

…

hybrid_vocab_extractor.py

…

hyde.py

…

legal_corpus_api.py

…

legal_corpus_ingestion.py

…

legal_corpus_robust.py

…

legal_templates_ingestion.py

…

main.py

feat: add Excel-like grid editor for OCR overlay (Kombi mode step 6)

2026-03-14 23:41:03 +01:00

metrics_db.py

…

migrate_rag_chunks.py

…

minio_storage.py

…

nibis_ingestion.py

…

nru_worksheet_generator.py

…

ocr_labeling_api.py

…

ocr_pipeline_api.py

fix: cache word_result in paddle_kombi/rapid_kombi for detect-structure

2026-03-18 07:29:02 +01:00

ocr_pipeline_session_store.py

feat: add Structure Detection step to OCR pipeline

2026-03-16 12:31:09 +01:00

orientation_crop_api.py

feat: auto-detect multi-page spreads and split into sub-sessions

2026-03-17 16:34:06 +01:00

page_crop.py

fix: NameError in detect_page_splits — 'gaps' var removed in rewrite

2026-03-17 17:01:34 +01:00

pdf_export.py

…

pdf_extraction.py

…

pipeline_checkpoints.py

…

pyproject.toml

…

qdrant_service.py

…

rag_evaluation.py

…

rbac.py

…

requirements.txt

…

reranker.py

…

self_rag.py

…

storage.py

…

template_sources.py

…

tesseract_vocab_extractor.py

…

training_api.py

…

training_export_service.py

…

trocr_api.py

…

upload_api.py

…

vocab_session_store.py

…

vocab_worksheet_api.py

…

worksheet_cleanup_api.py

…

worksheet_editor_api.py

…

zeugnis_api.py

…

zeugnis_crawler.py

…

zeugnis_models.py

…

zeugnis_seed_data.py

…