LICENSE
README.md
pyproject.toml
setup.py
tests/test_boilerplate.py
tests/test_cli.py
tests/test_dedup.py
tests/test_embed.py
tests/test_normalize.py
tests/test_pipeline.py
tests/test_quality.py
tests/test_writers.py
websieve/__init__.py
websieve/cli.py
websieve/models.py
websieve/pipeline.py
websieve.egg-info/PKG-INFO
websieve.egg-info/SOURCES.txt
websieve.egg-info/dependency_links.txt
websieve.egg-info/entry_points.txt
websieve.egg-info/requires.txt
websieve.egg-info/top_level.txt
websieve/clean/__init__.py
websieve/clean/boilerplate.py
websieve/clean/normalize.py
websieve/dedup/__init__.py
websieve/dedup/exact.py
websieve/dedup/minhash.py
websieve/embed/__init__.py
websieve/embed/encoder.py
websieve/export/__init__.py
websieve/export/writers.py
websieve/quality/__init__.py
websieve/quality/heuristics.py