README.md
pyproject.toml
setup.py
src/ocr_pipeline/__init__.py
src/ocr_pipeline/cli.py
src/ocr_pipeline/config.py
src/ocr_pipeline/doctor.py
src/ocr_pipeline/pipeline.py
src/ocr_pipeline/watch.py
src/ocr_pipeline.egg-info/PKG-INFO
src/ocr_pipeline.egg-info/SOURCES.txt
src/ocr_pipeline.egg-info/dependency_links.txt
src/ocr_pipeline.egg-info/entry_points.txt
src/ocr_pipeline.egg-info/requires.txt
src/ocr_pipeline.egg-info/top_level.txt
src/ocr_pipeline/citations/__init__.py
src/ocr_pipeline/citations/extractor.py
src/ocr_pipeline/citations/regex_extractor.py
src/ocr_pipeline/detectors/__init__.py
src/ocr_pipeline/detectors/figures.py
src/ocr_pipeline/detectors/tables.py
src/ocr_pipeline/ocr/__init__.py
src/ocr_pipeline/ocr/engine.py
src/ocr_pipeline/ocr/parallel.py
src/ocr_pipeline/ocr/preprocess.py
src/ocr_pipeline/output/__init__.py
src/ocr_pipeline/output/markdown.py
src/ocr_pipeline/postprocess/__init__.py
src/ocr_pipeline/postprocess/chunk.py
src/ocr_pipeline/postprocess/clean.py
src/ocr_pipeline/postprocess/entities.py
src/ocr_pipeline/utils/__init__.py
src/ocr_pipeline/utils/db.py
src/ocr_pipeline/utils/logging.py
src/ocr_pipeline/utils/migrate.py
src/ocr_pipeline/watch/__init__.py
src/ocr_pipeline/watch/watcher.py
tests/test_graph.py
tests/test_indexer.py
tests/test_ocr.py
tests/test_output.py
tests/test_postprocess.py
tests/test_profiles.py