Restructure: Move 47 cv_* files into ocr/ package

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

klausur-service/backend/ocr/layout/__init__.py

@@ -0,0 +1,2 @@
+"""Layout analysis sub-package."""
+from .layout import *  # noqa: F401,F403

klausur-service/backend/ocr/layout/analyze.py

@@ -13,8 +13,8 @@ from typing import List
 
 import numpy as np
 
-from cv_vocab_types import PageRegion
-from cv_layout_detection import _find_content_bounds
+from ..types import PageRegion
+from .detection import _find_content_bounds
 
 logger = logging.getLogger(__name__)
 
@@ -246,7 +246,7 @@ def analyze_layout(layout_img: np.ndarray, ocr_img: np.ndarray) -> List[PageRegi
 
     # Add header/footer info (gap-based detection with fallback)
     # Lazy import to avoid circular dependency with cv_layout.py
-    from cv_layout_detection import _add_header_footer
+    from .detection import _add_header_footer
     _add_header_footer(regions, top_y, bottom_y, w, h, inv=inv)
 
     top_region = next((r.type for r in regions if r.type in ('header', 'margin_top')), 'none')

klausur-service/backend/ocr/layout/classify.py

@@ -11,16 +11,16 @@ from typing import Dict, List, Optional
 
 import numpy as np
 
-from cv_vocab_types import ColumnGeometry, PageRegion
+from ..types import ColumnGeometry, PageRegion
 
-from cv_layout_scoring import (
+from .scoring import (
     _score_language,
     _score_role,
     _score_dictionary_signals,
     _classify_dictionary_columns,
 )
 
-from cv_layout_classify_position import (
+from .classify_position import (
     _classify_by_position_enhanced,
     _classify_by_position_fallback,
 )
@@ -211,7 +211,7 @@ def classify_column_types(geometries: List[ColumnGeometry],
     # _add_header_footer lives in cv_layout (avoids circular import at module
     # level).  Lazy-import here so the module can be tested independently when
     # cv_layout hasn't been modified yet.
-    from cv_layout_detection import _add_header_footer  # noqa: E402
+    from .detection import _add_header_footer  # noqa: E402
 
     content_h = bottom_y - top_y
 

klausur-service/backend/ocr/layout/classify_position.py

@@ -11,7 +11,7 @@ Extracted from cv_layout_classify.py during file-size split.
 import logging
 from typing import Dict, List, Optional
 
-from cv_vocab_types import ColumnGeometry, PageRegion
+from ..types import ColumnGeometry, PageRegion
 
 logger = logging.getLogger(__name__)
 

klausur-service/backend/ocr/layout/column_refine.py

@@ -16,7 +16,7 @@ from typing import Dict, List, Optional, Tuple
 
 import numpy as np
 
-from cv_vocab_types import ColumnGeometry
+from ..types import ColumnGeometry
 
 logger = logging.getLogger(__name__)
 

klausur-service/backend/ocr/layout/columns.py

@@ -19,8 +19,8 @@ from typing import Dict, List, Optional, Tuple
 
 import numpy as np
 
-from cv_vocab_types import ColumnGeometry
-from cv_layout_detection import _find_content_bounds
+from ..types import ColumnGeometry
+from .detection import _find_content_bounds
 
 logger = logging.getLogger(__name__)
 

klausur-service/backend/ocr/layout/detection.py

@@ -13,7 +13,7 @@ from typing import List, Optional, Tuple
 
 import numpy as np
 
-from cv_vocab_types import (
+from ..types import (
     DocumentTypeResult,
     PageRegion,
 )

klausur-service/backend/ocr/layout/layout.py

@@ -21,14 +21,14 @@ from typing import Any, Dict, List, Optional, Tuple
 
 import numpy as np
 
-from cv_vocab_types import ColumnGeometry, DetectedBox, PageRegion
+from ..types import ColumnGeometry, DetectedBox, PageRegion
 
 logger = logging.getLogger(__name__)
 
 
 # ── Re-exports (backward compatibility) ───────────────────────────────────
 
-from cv_layout_detection import (  # noqa: F401
+from .detection import (  # noqa: F401
     detect_document_type,
     create_ocr_image,
     create_layout_image,
@@ -39,46 +39,46 @@ from cv_layout_detection import (  # noqa: F401
     _add_header_footer,
 )
 
-from cv_layout_analyze import (  # noqa: F401
+from .analyze import (  # noqa: F401
     analyze_layout,
 )
 
-from cv_layout_columns import (  # noqa: F401
+from .columns import (  # noqa: F401
     detect_column_geometry,
     _detect_columns_by_clustering,
     _build_geometries_from_starts,
 )
 
-from cv_layout_column_refine import (  # noqa: F401
+from .column_refine import (  # noqa: F401
     _detect_sub_columns,
     _split_broad_columns,
     expand_narrow_columns,
 )
 
-from cv_layout_rows import (  # noqa: F401
+from .rows import (  # noqa: F401
     detect_row_geometry,
     _build_rows_from_word_grouping,
 )
 
-from cv_layout_row_regularize import (  # noqa: F401
+from .row_regularize import (  # noqa: F401
     _regularize_row_grid,
 )
 
-from cv_layout_scoring import (  # noqa: F401
+from .scoring import (  # noqa: F401
     _score_language,
     _score_role,
     _score_dictionary_signals,
     _classify_dictionary_columns,
 )
 
-from cv_layout_classify import (  # noqa: F401
+from .classify import (  # noqa: F401
     _build_margin_regions,
     positional_column_regions,
     classify_column_types,
     _classify_by_content,
 )
 
-from cv_layout_classify_position import (  # noqa: F401
+from .classify_position import (  # noqa: F401
     _classify_by_position_enhanced,
     _classify_by_position_fallback,
 )
@@ -143,7 +143,7 @@ def detect_column_geometry_zoned(
        per content zone on the corresponding sub-image.
     4. If no boxes: delegates entirely to detect_column_geometry().
     """
-    from cv_box_detect import detect_boxes, split_page_into_zones
+    from ..detect.box_detect import detect_boxes, split_page_into_zones
 
     geo_result = detect_column_geometry(ocr_img, dewarped_bgr)
     if geo_result is None:

klausur-service/backend/ocr/layout/row_regularize.py

@@ -13,7 +13,7 @@ from typing import Dict, List
 
 import numpy as np
 
-from cv_vocab_types import RowGeometry
+from ..types import RowGeometry
 
 logger = logging.getLogger(__name__)
 

klausur-service/backend/ocr/layout/rows.py

@@ -20,9 +20,9 @@ try:
 except ImportError:
     cv2 = None  # type: ignore[assignment]
 
-from cv_vocab_types import RowGeometry
-from cv_ocr_word_assembly import _group_words_into_lines
-from cv_layout_row_regularize import _regularize_row_grid
+from ..types import RowGeometry
+from ..engines.word_assembly import _group_words_into_lines
+from .row_regularize import _regularize_row_grid
 
 logger = logging.getLogger(__name__)
 

klausur-service/backend/ocr/layout/scoring.py

@@ -11,7 +11,7 @@ import logging
 from collections import Counter
 from typing import Any, Dict, List, Optional
 
-from cv_vocab_types import (
+from ..types import (
     ColumnGeometry,
     ENGLISH_FUNCTION_WORDS,
     GERMAN_FUNCTION_WORDS,