Benjamin Admin 7ffa4c90f9 Lower word-split threshold from 7 to 4 chars ...

Short merged words like "anew" (a new), "Imadea" (I made a),
"makeadecision" (make a decision) were missed because the split
threshold was too high. Now processes tokens >= 4 chars.

English single-letter words (a, I) are already handled by the DP
algorithm which allows them as valid split points.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-12 08:59:02 +02:00

..

__init__.py

…

conftest.py

…

test_advanced_rag.py

…

test_border_ghost_filter.py

feat: add border ghost filter + graphic detection tests + structure overlay

2026-03-16 18:28:53 +01:00

test_box_column_awareness.py

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

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

test_byoeh.py

…

test_cell_phonetics.py

feat: Sprint 1 — IPA hardening, regression framework, ground-truth review

2026-03-23 09:21:27 +01:00

test_cv_box_detect.py

feat: generische Box-Erkennung fuer zonenbasierte Spaltenerkennung

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

test_cv_graphic_detect.py

feat: add border ghost filter + graphic detection tests + structure overlay

2026-03-16 18:28:53 +01:00

test_cv_vocab_pipeline.py

feat: cell-first OCR + document type detection + dynamic pipeline steps

2026-03-04 13:52:38 +01:00

test_cv_words_first.py

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

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

test_doclayout_detect.py

feat: Sprint 2 — TrOCR ONNX, PP-DocLayout, Model Management

2026-03-23 09:53:02 +01:00

test_grid_detection.py

…

test_grid_editor_api.py

fix: border strip pre-filter + 3-column detection for vocabulary tables

2026-03-21 21:01:43 +01:00

test_gutter_repair.py

Fix hyphen-join: preserve next row + skip valid hyphenations

2026-04-10 19:49:07 +02:00

test_legal_templates.py

…

test_mail_service.py

…

test_ocr_labeling.py

…

test_paddle_kombi.py

feat: add Kombi-Vergleich mode for side-by-side Paddle vs RapidOCR comparison

2026-03-14 07:59:06 +01:00

test_paddleocr_remote.py

feat: PaddleOCR Remote-Engine (PP-OCRv5 Latin auf Hetzner x86_64)

2026-03-12 09:31:22 +01:00

test_page_crop.py

Add camera gutter detection via vertical continuity analysis

2026-04-11 13:58:14 +02:00

test_rag_admin.py

…

test_rbac.py

…

test_trocr_onnx.py

feat: Sprint 2 — TrOCR ONNX, PP-DocLayout, Model Management

2026-03-23 09:53:02 +01:00

test_vocab_worksheet.py

feat: use OCR pipeline instead of LLM vision for vocab worksheet extraction

2026-03-05 15:35:44 +01:00

test_word_split.py

Lower word-split threshold from 7 to 4 chars

2026-04-12 08:59:02 +02:00

test_worksheet_editor.py

…