LICENSE
README.md
pyproject.toml
setup.py
doc2mark/__init__.py
doc2mark/__main__.py
doc2mark/cli.py
doc2mark/py.typed
doc2mark.egg-info/PKG-INFO
doc2mark.egg-info/SOURCES.txt
doc2mark.egg-info/dependency_links.txt
doc2mark.egg-info/entry_points.txt
doc2mark.egg-info/requires.txt
doc2mark.egg-info/top_level.txt
doc2mark/core/__init__.py
doc2mark/core/base.py
doc2mark/core/chunker.py
doc2mark/core/loader.py
doc2mark/core/mime_mapper.py
doc2mark/core/strategy.py
doc2mark/core/table.py
doc2mark/core/types.py
doc2mark/formats/__init__.py
doc2mark/formats/email.py
doc2mark/formats/image.py
doc2mark/formats/legacy.py
doc2mark/formats/markup.py
doc2mark/formats/office.py
doc2mark/formats/pdf.py
doc2mark/formats/text.py
doc2mark/ocr/__init__.py
doc2mark/ocr/base.py
doc2mark/ocr/cache.py
doc2mark/ocr/openai.py
doc2mark/ocr/prompts.py
doc2mark/ocr/schema.py
doc2mark/ocr/tesseract.py
doc2mark/ocr/vertex_ai.py
doc2mark/pipelines/__init__.py
doc2mark/pipelines/office_advanced_pipeline.py
doc2mark/pipelines/pymupdf_advanced_pipeline.py
doc2mark/utils/__init__.py
doc2mark/utils/image_utils.py
doc2mark/utils/libreoffice.py
tests/test_basic.py
tests/test_batch_parallel.py
tests/test_chunker.py
tests/test_cli.py
tests/test_edge_cases.py
tests/test_email_format.py
tests/test_footnotes.py
tests/test_image_downscale.py
tests/test_image_formats.py
tests/test_image_pdf_ocr.py
tests/test_image_utils.py
tests/test_legacy_conversion.py
tests/test_mime_mapper.py
tests/test_ocr.py
tests/test_ocr_cache.py
tests/test_ocr_concurrency.py
tests/test_ocr_context_pdf.py
tests/test_ocr_facade.py
tests/test_ocr_fallback.py
tests/test_ocr_router.py
tests/test_ocr_schema.py
tests/test_ocr_structured_e2e.py
tests/test_office_route.py
tests/test_page_markers.py
tests/test_pdf_heading_heuristics.py
tests/test_pipeline_golden.py
tests/test_pipelines.py
tests/test_rag_e2e.py
tests/test_simple.py
tests/test_strategy.py
tests/test_table_models.py
tests/test_text_formats.py
tests/test_token_chunking.py