Merge pull request #4 from CocoRoF/main

feat: Add OCR engine module with support for multiple providers

Author: CocoRoF

libs/__init__.py contextifier/__init__.pylibs/__init__.py renamed to contextifier/__init__.py

@@ -1,4 +1,4 @@
-# libs/__init__.py
+# contextifier/__init__.py
 """
 Contextifier Library
 
@@ -23,14 +23,14 @@
     result = processor.extract_chunks("document.pdf", chunk_size=1000)
 """
 
-__version__ = "0.1.0"
+__version__ = "0.1.2"
 
 # Expose core classes at top level
-from libs.core import DocumentProcessor
+from contextifier.core import DocumentProcessor
 
 # Explicit subpackages
-from libs import core
-from libs import chunking
+from contextifier import core
+from contextifier import chunking
 
 __all__ = [
     "__version__",

libs/chunking/__init__.py contextifier/chunking/__init__.pylibs/chunking/__init__.py renamed to contextifier/chunking/__init__.py

@@ -20,7 +20,7 @@
 """
 
 # === Main Chunking Functions (chunking.py) ===
-from libs.chunking.chunking import (
+from contextifier.chunking.chunking import (
     # Primary API
     create_chunks,
     # Backward compatibility (deprecated)
@@ -30,7 +30,7 @@
 )
 
 # constants
-from libs.chunking.constants import (
+from contextifier.chunking.constants import (
     # Constants
     LANGCHAIN_CODE_LANGUAGE_MAP,
     HTML_TABLE_PATTERN,
@@ -48,15 +48,15 @@
 )
 
 # table_parser
-from libs.chunking.table_parser import (
+from contextifier.chunking.table_parser import (
     parse_html_table,
     extract_cell_spans,
     extract_cell_spans_with_positions,
     has_complex_spans,
 )
 
 # table_chunker
-from libs.chunking.table_chunker import (
+from contextifier.chunking.table_chunker import (
     calculate_available_space,
     adjust_rowspan_in_chunk,
     build_table_chunk,
@@ -67,7 +67,7 @@
 )
 
 # protected_regions
-from libs.chunking.protected_regions import (
+from contextifier.chunking.protected_regions import (
     find_protected_regions,
     get_protected_region_positions,
     ensure_protected_region_integrity,
@@ -79,15 +79,15 @@
 )
 
 # page_chunker
-from libs.chunking.page_chunker import (
+from contextifier.chunking.page_chunker import (
     split_into_pages,
     merge_pages,
     get_overlap_content,
     chunk_by_pages,
 )
 
 # text_chunker
-from libs.chunking.text_chunker import (
+from contextifier.chunking.text_chunker import (
     chunk_plain_text,
     chunk_text_without_tables,
     chunk_with_row_protection,
@@ -100,7 +100,7 @@
 )
 
 # sheet_processor
-from libs.chunking.sheet_processor import (
+from contextifier.chunking.sheet_processor import (
     extract_document_metadata,
     prepend_metadata_to_chunks,
     extract_sheet_sections,

libs/chunking/chunking.py contextifier/chunking/chunking.pylibs/chunking/chunking.py renamed to contextifier/chunking/chunking.py

@@ -25,7 +25,7 @@
 from typing import Any, Dict, List, Optional, Union
 
 # Import from individual modules
-from libs.chunking.constants import (
+from contextifier.chunking.constants import (
     LANGCHAIN_CODE_LANGUAGE_MAP,
     HTML_TABLE_PATTERN,
     CHART_BLOCK_PATTERN,
@@ -40,14 +40,14 @@
     ParsedTable,
 )
 
-from libs.chunking.table_parser import (
+from contextifier.chunking.table_parser import (
     parse_html_table as _parse_html_table,
     extract_cell_spans as _extract_cell_spans,
     extract_cell_spans_with_positions as _extract_cell_spans_with_positions,
     has_complex_spans as _has_complex_spans,
 )
 
-from libs.chunking.table_chunker import (
+from contextifier.chunking.table_chunker import (
     calculate_available_space as _calculate_available_space,
     adjust_rowspan_in_chunk as _adjust_rowspan_in_chunk,
     build_table_chunk as _build_table_chunk,
@@ -57,7 +57,7 @@
     chunk_large_table as _chunk_large_table,
 )
 
-from libs.chunking.protected_regions import (
+from contextifier.chunking.protected_regions import (
     find_protected_regions as _find_protected_regions,
     get_protected_region_positions as _get_protected_region_positions,
     ensure_protected_region_integrity as _ensure_protected_region_integrity,
@@ -67,14 +67,14 @@
     split_large_chunk_with_table_protection as _split_large_chunk_with_table_protection,
 )
 
-from libs.chunking.page_chunker import (
+from contextifier.chunking.page_chunker import (
     split_into_pages as _split_into_pages,
     merge_pages as _merge_pages,
     get_overlap_content as _get_overlap_content,
     chunk_by_pages as _chunk_by_pages,
 )
 
-from libs.chunking.text_chunker import (
+from contextifier.chunking.text_chunker import (
     chunk_plain_text as _chunk_plain_text,
     chunk_text_without_tables,
     chunk_with_row_protection,
@@ -86,7 +86,7 @@
     estimate_chunks_count,
 )
 
-from libs.chunking.sheet_processor import (
+from contextifier.chunking.sheet_processor import (
     extract_document_metadata as _extract_document_metadata,
     prepend_metadata_to_chunks as _prepend_metadata_to_chunks,
     extract_sheet_sections as _extract_sheet_sections,
@@ -120,7 +120,7 @@ def _get_page_marker_patterns(page_tag_processor: Optional[Any] = None) -> List[
         ]
         # Add slide pattern if different prefix
         if config.slide_prefix != config.tag_prefix:
-            from libs.core.functions.page_tag_processor import PageTagType
+            from contextifier.core.functions.page_tag_processor import PageTagType
             patterns.append(page_tag_processor.get_pattern_string(PageTagType.SLIDE))
         return patterns
     else:
@@ -142,7 +142,7 @@ def _get_sheet_marker_pattern(page_tag_processor: Optional[Any] = None) -> str:
         Regex pattern for sheet markers
     """
     if page_tag_processor is not None:
-        from libs.core.functions.page_tag_processor import PageTagType
+        from contextifier.core.functions.page_tag_processor import PageTagType
         return page_tag_processor.get_pattern_string(PageTagType.SHEET)
     else:
         return r'\[Sheet:\s*([^\]]+)\]'

libs/chunking/constants.py contextifier/chunking/constants.pylibs/chunking/constants.py renamed to contextifier/chunking/constants.py

@@ -11,7 +11,7 @@
 import re
 from typing import List, Tuple
 
-from libs.chunking.protected_regions import (
+from contextifier.chunking.protected_regions import (
     find_protected_regions, get_protected_region_positions,
     ensure_protected_region_integrity, split_large_chunk_with_protected_regions
 )
@@ -125,7 +125,7 @@ def chunk_by_pages(
         ]
         config = page_tag_processor.config
         if config.slide_prefix != config.tag_prefix:
-            from libs.core.functions.page_tag_processor import PageTagType
+            from contextifier.core.functions.page_tag_processor import PageTagType
             page_marker_patterns.append(page_tag_processor.get_pattern_string(PageTagType.SLIDE))
     else:
         page_marker_patterns = [

libs/chunking/page_chunker.py contextifier/chunking/page_chunker.pylibs/chunking/page_chunker.py renamed to contextifier/chunking/page_chunker.py

@@ -11,7 +11,7 @@
 import re
 from typing import List, Tuple
 
-from libs.chunking.constants import (
+from contextifier.chunking.constants import (
     HTML_TABLE_PATTERN, CHART_BLOCK_PATTERN, TEXTBOX_BLOCK_PATTERN,
     IMAGE_TAG_PATTERN, MARKDOWN_TABLE_PATTERN
 )

libs/chunking/protected_regions.py …ntextifier/chunking/protected_regions.pylibs/chunking/protected_regions.py renamed to contextifier/chunking/protected_regions.py libs/chunking/protected_regions.py renamed to contextifier/chunking/protected_regions.py

@@ -12,11 +12,11 @@
 import re
 from typing import Dict, List
 
-from libs.chunking.constants import (
+from contextifier.chunking.constants import (
     ParsedTable, TableRow,
     TABLE_WRAPPER_OVERHEAD, CHUNK_INDEX_OVERHEAD
 )
-from libs.chunking.table_parser import (
+from contextifier.chunking.table_parser import (
     parse_html_table, extract_cell_spans_with_positions, has_complex_spans
 )
 

libs/chunking/sheet_processor.py contextifier/chunking/sheet_processor.pylibs/chunking/sheet_processor.py renamed to contextifier/chunking/sheet_processor.py

@@ -11,7 +11,7 @@
 import re
 from typing import Dict, List, Optional, Tuple
 
-from libs.chunking.constants import ParsedTable, TableRow
+from contextifier.chunking.constants import ParsedTable, TableRow
 
 logger = logging.getLogger("document-processor")
 

libs/chunking/table_chunker.py contextifier/chunking/table_chunker.pylibs/chunking/table_chunker.py renamed to contextifier/chunking/table_chunker.py

@@ -14,7 +14,7 @@
 
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 
-from libs.chunking.constants import LANGCHAIN_CODE_LANGUAGE_MAP
+from contextifier.chunking.constants import LANGCHAIN_CODE_LANGUAGE_MAP
 
 logger = logging.getLogger("document-processor")