Benjamin_Boenisch/breakpilot-lehrer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
ed7fc99fc4f5db149555c1d1c5ca051540e8a1b7
breakpilot-lehrer/klausur-service/backend
T
History
Benjamin Admin ed7fc99fc4 Improve syllable divider insertion for dictionary pages 
Rewrite cv_syllable_detect.py with pyphen-first approach:
- Remove unreliable CV gate (morphological pipe detection)
- Strip existing pipes and re-syllabify via pyphen (DE then EN)
- Merge pipe-gap spaces where OCR split words at divider positions
- Guard merges with function word blacklist and punctuation checks

Add false-positive prevention:
- Pre-check: skip if <5% of cells have existing | from OCR
- Call-site check: require article_col_index (der/die/das column)
- Prevents syllabification of synonym dictionaries and word lists

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-24 19:44:29 +01:00
..
data
feat(ocr-pipeline): British/American IPA pronunciation choice
2026-03-01 11:08:52 +01:00
mail
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
migrations
feat: Sprint 1 — IPA hardening, regression framework, ground-truth review
2026-03-23 09:21:27 +01:00
models
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
policies
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
routes
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
services
feat: Sprint 2 — TrOCR ONNX, PP-DocLayout, Model Management
2026-03-23 09:53:02 +01:00
tests
fix(ocr-pipeline): improve page crop spine detection and cell assignment
2026-03-24 09:23:30 +01:00
admin_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
config.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
country_metadata.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
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 bullet overlap disambiguation + raise red threshold to 90
2026-03-20 18:21:00 +01:00
cv_doclayout_detect.py
feat: Sprint 2 — TrOCR ONNX, PP-DocLayout, Model Management
2026-03-23 09:53:02 +01:00
cv_graphic_detect.py
feat: Sprint 2 — TrOCR ONNX, PP-DocLayout, Model Management
2026-03-23 09:53:02 +01:00
cv_layout.py
feat: ImageLayoutEditor, arrow-key nav, multi-select bold, wider columns
2026-03-24 07:45:39 +01:00
cv_ocr_engines.py
fix: preserve pipe syllable dividers + detect alphabet sidebar columns
2026-03-24 13:52:11 +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_syllable_detect.py
Improve syllable divider insertion for dictionary pages
2026-03-24 19:44:29 +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: ImageLayoutEditor, arrow-key nav, multi-select bold, wider columns
2026-03-24 07:45:39 +01:00
cv_words_first.py
fix(ocr-pipeline): improve page crop spine detection and cell assignment
2026-03-24 09:23:30 +01:00
dsfa_corpus_ingestion.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
dsfa_rag_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
eh_pipeline.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
eh_templates.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
embedding_client.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
full_compliance_pipeline.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
full_reingestion.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
github_crawler.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
grid_editor_api.py
Improve syllable divider insertion for dictionary pages
2026-03-24 19:44:29 +01:00
grid_editor_helpers.py
Fix NameError: _text_has_garbled_ipa not imported in grid_editor_helpers
2026-03-24 15:11:29 +01:00
handwriting_htr_api.py
feat(klausur): Handschrift entfernen + Klausur-HTR implementiert
2026-03-03 12:04:26 +01:00
hybrid_search.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
hybrid_vocab_extractor.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
hyde.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
legal_corpus_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
legal_corpus_ingestion.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
legal_corpus_robust.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
legal_templates_ingestion.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
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
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
migrate_rag_chunks.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
minio_storage.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
nibis_ingestion.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
nru_worksheet_generator.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
ocr_labeling_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
ocr_pipeline_api.py
Add Ground Truth regression test system for OCR pipeline
2026-03-18 13:46:48 +01:00
ocr_pipeline_auto.py
refactor: split ocr_pipeline_api.py (5426 lines) into 8 modules
2026-03-18 08:42:00 +01:00
ocr_pipeline_common.py
feat: add Woerterbuch category + column add/delete in grid editor
2026-03-23 16:27:12 +01:00
ocr_pipeline_geometry.py
Invalidate grid_editor_result when exclude regions change
2026-03-19 09:19:09 +01:00
ocr_pipeline_ocr_merge.py
refactor: split ocr_pipeline_api.py (5426 lines) into 8 modules
2026-03-18 08:42:00 +01:00
ocr_pipeline_overlays.py
Preserve alphabetic marker columns, broaden junk filter, enable IPA in grid
2026-03-18 11:08:23 +01:00
ocr_pipeline_postprocess.py
refactor: split ocr_pipeline_api.py (5426 lines) into 8 modules
2026-03-18 08:42:00 +01:00
ocr_pipeline_regression.py
feat: save automatic grid snapshot before manual edits for GT comparison
2026-03-24 13:16:44 +01:00
ocr_pipeline_rows.py
refactor: split ocr_pipeline_api.py (5426 lines) into 8 modules
2026-03-18 08:42:00 +01:00
ocr_pipeline_session_store.py
refactor: independent sessions for page-split + URL-based pipeline navigation
2026-03-24 17:05:33 +01:00
ocr_pipeline_sessions.py
refactor: independent sessions for page-split + URL-based pipeline navigation
2026-03-24 17:05:33 +01:00
ocr_pipeline_words.py
refactor: split ocr_pipeline_api.py (5426 lines) into 8 modules
2026-03-18 08:42:00 +01:00
orientation_crop_api.py
refactor: independent sessions for page-split + URL-based pipeline navigation
2026-03-24 17:05:33 +01:00
page_crop.py
fix(ocr-pipeline): improve page crop spine detection and cell assignment
2026-03-24 09:23:30 +01:00
pdf_export.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
pdf_extraction.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
pipeline_checkpoints.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
pyproject.toml
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
qdrant_service.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
rag_evaluation.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
rbac.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
requirements.txt
feat: auto-insert syllable dividers via pyphen on dictionary pages
2026-03-24 14:17:26 +01:00
reranker.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
self_rag.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
storage.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
template_sources.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
tesseract_vocab_extractor.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
training_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
training_export_service.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
trocr_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
upload_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
vocab_session_store.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
vocab_worksheet_api.py
fix: Edge-Gaps in _split_broad_columns ignorieren + return-Tuple bei leerem Ergebnis
2026-03-07 22:16:29 +01:00
worksheet_cleanup_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
worksheet_editor_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
zeugnis_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
zeugnis_crawler.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
zeugnis_models.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
zeugnis_seed_data.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00