.gitignore
.pre-commit-config.yaml
LICENSE
README.md
docker-compose.yml
justfile
mkdocs.yml
pyproject.toml
uv.lock
.github/pull_request_template.md
.github/workflows/deploy-package-to-pypi.yml
.github/workflows/docs-build-and-deploy.yml
.github/workflows/docs-build.yml
.github/workflows/pytest.yml
.github/workflows/ruff.yml
.vscode/launch.json
.vscode/settings.json
docs/contributing.md
docs/index.md
docs/use-cases.md
docs/api/client/clean.md
docs/api/client/dags.md
docs/api/client/extract.md
docs/api/client/helpers.md
docs/api/client/index.md
docs/api/client/models.md
docs/api/client/results.md
docs/api/client/visualisation.md
docs/api/common/arrow.md
docs/api/common/db.md
docs/api/common/dtos.md
docs/api/common/exceptions.md
docs/api/common/graph.md
docs/api/common/hash.md
docs/api/common/index.md
docs/api/common/logging.md
docs/api/common/sources.md
docs/api/common/transform.md
docs/api/common/factories/entities.md
docs/api/common/factories/index.md
docs/api/common/factories/models.md
docs/api/common/factories/sources.md
docs/api/server/api.md
docs/api/server/index.md
docs/api/server/backends/postgresql.md
docs/assets/matchbox-icon-dark.png
docs/assets/matchbox-icon.svg
docs/assets/matchbox-logo-dark.svg
docs/assets/matchbox-logo-light.svg
docs/client/explore_resolutions.md
docs/client/install.md
docs/client/link-data.md
docs/client/query-data.md
docs/server/deploy.md
docs/server/install.md
docs/stylesheets/extra.css
environments/datadog-agent-private-sample.env
environments/datadog-agent-public.env
environments/development.env
environments/sample.env
environments/server.env
references/.gitkeep
references/README_aspitational.md
references/classdiagram.png
references/design.md
references/devnotes.md
references/erdiagram.png
references/hybrid_additive.drawio
references/hybridadditive_links.png
src/matchbox/__init__.py
src/matchbox/client/__init__.py
src/matchbox/client/_handler.py
src/matchbox/client/_settings.py
src/matchbox/client/dags.py
src/matchbox/client/extract.py
src/matchbox/client/results.py
src/matchbox/client/visualisation.py
src/matchbox/client/clean/__init__.py
src/matchbox/client/clean/lib.py
src/matchbox/client/clean/utils.py
src/matchbox/client/clean/steps/__init__.py
src/matchbox/client/clean/steps/clean_basic.py
src/matchbox/client/clean/steps/clean_basic_original.py
src/matchbox/client/helpers/__init__.py
src/matchbox/client/helpers/cleaner.py
src/matchbox/client/helpers/comparison.py
src/matchbox/client/helpers/index.py
src/matchbox/client/helpers/selector.py
src/matchbox/client/models/__init__.py
src/matchbox/client/models/models.py
src/matchbox/client/models/dedupers/__init__.py
src/matchbox/client/models/dedupers/base.py
src/matchbox/client/models/dedupers/naive.py
src/matchbox/client/models/linkers/__init__.py
src/matchbox/client/models/linkers/base.py
src/matchbox/client/models/linkers/deterministic.py
src/matchbox/client/models/linkers/splinklinker.py
src/matchbox/client/models/linkers/weighteddeterministic.py
src/matchbox/common/__init__.py
src/matchbox/common/arrow.py
src/matchbox/common/db.py
src/matchbox/common/dtos.py
src/matchbox/common/exceptions.py
src/matchbox/common/graph.py
src/matchbox/common/hash.py
src/matchbox/common/logging.py
src/matchbox/common/sources.py
src/matchbox/common/transform.py
src/matchbox/common/factories/__init__.py
src/matchbox/common/factories/dags.py
src/matchbox/common/factories/entities.py
src/matchbox/common/factories/models.py
src/matchbox/common/factories/sources.py
src/matchbox/server/Dockerfile
src/matchbox/server/__init__.py
src/matchbox/server/base.py
src/matchbox/server/api/__init__.py
src/matchbox/server/api/arrow.py
src/matchbox/server/api/cache.py
src/matchbox/server/api/routes.py
src/matchbox/server/postgresql/.gitkeep
src/matchbox/server/postgresql/__init__.py
src/matchbox/server/postgresql/adapter.py
src/matchbox/server/postgresql/alembic.ini
src/matchbox/server/postgresql/db.py
src/matchbox/server/postgresql/mixin.py
src/matchbox/server/postgresql/orm.py
src/matchbox/server/postgresql/alembic/env.py
src/matchbox/server/postgresql/alembic/script.py.mako
src/matchbox/server/postgresql/alembic/versions/1907c34cfa1f_create_tables_given_schema.py
src/matchbox/server/postgresql/alembic/versions/40a8e5ed48f2_create_schema_without_tables.py
src/matchbox/server/postgresql/alembic/versions/b694eb292dea_add_an_index_to_the_probabilities_.py
src/matchbox/server/postgresql/alembic/versions/f3c9279437f4_add_content_hash_to_resolutions.py
src/matchbox/server/postgresql/benchmark/__init__.py
src/matchbox/server/postgresql/benchmark/cluster_pipeline.py
src/matchbox/server/postgresql/benchmark/generate_tables.py
src/matchbox/server/postgresql/benchmark/query.py
src/matchbox/server/postgresql/utils/__init__.py
src/matchbox/server/postgresql/utils/db.py
src/matchbox/server/postgresql/utils/insert.py
src/matchbox/server/postgresql/utils/query.py
src/matchbox/server/postgresql/utils/results.py
src/matchbox_db.egg-info/PKG-INFO
src/matchbox_db.egg-info/SOURCES.txt
src/matchbox_db.egg-info/dependency_links.txt
src/matchbox_db.egg-info/requires.txt
src/matchbox_db.egg-info/top_level.txt
test/__init__.py
test/conftest.py
test/client/__init__.py
test/client/test_cleaning.py
test/client/test_dags.py
test/client/test_extract.py
test/client/test_helpers.py
test/client/test_model.py
test/client/test_utils.py
test/client/test_visualisation.py
test/client/cleaning/alias/clean.csv
test/client/cleaning/alias/dirty.csv
test/client/cleaning/clean_punctuation/clean.csv
test/client/cleaning/clean_punctuation/clean_punctuation.md
test/client/cleaning/clean_punctuation/dirty.csv
test/client/cleaning/cleaning_function/duckdb_cleaning_factory.md
test/client/cleaning/cleaning_function/clean_comp_names/clean.csv
test/client/cleaning/cleaning_function/clean_comp_names/dirty.csv
test/client/cleaning/cleaning_function/pass/clean.csv
test/client/cleaning/cleaning_function/pass/dirty.csv
test/client/cleaning/cleaning_function/tokenise/clean.csv
test/client/cleaning/cleaning_function/tokenise/dirty.csv
test/client/cleaning/expand_abbreviations/clean.csv
test/client/cleaning/expand_abbreviations/dirty.csv
test/client/cleaning/expand_abbreviations/expand_abbreviations.md
test/client/cleaning/list_join_to_string/clean.csv
test/client/cleaning/list_join_to_string/dirty.csv
test/client/cleaning/list_join_to_string/list_join_to_string.md
test/client/cleaning/remove_stopwords/clean.csv
test/client/cleaning/remove_stopwords/dirty.csv
test/client/cleaning/remove_stopwords/remove_stopwords.md
test/client/cleaning/tokenise/clean.csv
test/client/cleaning/tokenise/dirty.csv
test/client/cleaning/tokenise/tokenise.md
test/client/cleaning/unnest_renest/unnest_renest.md
test/client/cleaning/unnest_renest/expand_abbreviations/clean.csv
test/client/cleaning/unnest_renest/expand_abbreviations/dirty.csv
test/client/cleaning/unnest_renest/pass/clean.csv
test/client/cleaning/unnest_renest/pass/dirty.csv
test/client/methodologies/__init__.py
test/client/methodologies/test_dedupers_deterministic.py
test/client/methodologies/test_linkers_deterministic.py
test/client/methodologies/test_linkers_probabilistic.py
test/common/__init__.py
test/common/test_graph.py
test/common/test_hash.py
test/common/test_results.py
test/common/test_sources.py
test/common/test_transform.py
test/common/factories/__init__.py
test/common/factories/test_entity_factory.py
test/common/factories/test_linked_factory.py
test/common/factories/test_model_factory.py
test/common/factories/test_probability_generation.py
test/common/factories/test_source_factory.py
test/common/factories/test_testkit_dag.py
test/data/all_companies.csv
test/e2e/test_e2e.py
test/fixtures/__init__.py
test/fixtures/client.py
test/fixtures/db.py
test/fixtures/graph.py
test/server/__init__.py
test/server/test_adapter.py
test/server/api/__init__.py
test/server/api/test_routes.py
test/server/api/test_utilities.py
test/server/postgresql/__init__.py
test/server/postgresql/test_pg_core.py
test/server/postgresql/test_pg_migrations.py