LICENSE
MANIFEST.in
README.md
pyproject.toml
configs/communications-vdl.yaml
configs/full-run.yaml
src/eurlex_builder/__init__.py
src/eurlex_builder/checkpoint.py
src/eurlex_builder/cli.py
src/eurlex_builder/config.py
src/eurlex_builder/constants.py
src/eurlex_builder/enrich.py
src/eurlex_builder/errors.py
src/eurlex_builder/eurovoc_review.py
src/eurlex_builder/html_parser.py
src/eurlex_builder/multilingual.py
src/eurlex_builder/pipeline.py
src/eurlex_builder/protocols.py
src/eurlex_builder/py.typed
src/eurlex_builder/translate.py
src/eurlex_builder/utils.py
src/eurlex_builder/validate.py
src/eurlex_builder.egg-info/PKG-INFO
src/eurlex_builder.egg-info/SOURCES.txt
src/eurlex_builder.egg-info/dependency_links.txt
src/eurlex_builder.egg-info/entry_points.txt
src/eurlex_builder.egg-info/requires.txt
src/eurlex_builder.egg-info/top_level.txt
src/eurlex_builder/extractors/__init__.py
src/eurlex_builder/extractors/docling_process.py
src/eurlex_builder/extractors/html.py
src/eurlex_builder/extractors/pdf.py
src/eurlex_builder/extractors/pdf_headings.py
src/eurlex_builder/extractors/pdf_languages.py
src/eurlex_builder/extractors/pdf_layout.py
src/eurlex_builder/extractors/splitter.py
src/eurlex_builder/sources/__init__.py
src/eurlex_builder/sources/cellar.py
src/eurlex_builder/storage/__init__.py
src/eurlex_builder/storage/duckdb.py
src/eurlex_builder/storage/export.py
tests/__init__.py
tests/conftest.py
tests/docling_startup_error_stub.py
tests/docling_worker_stub.py
tests/test_cellar.py
tests/test_checkpoint.py
tests/test_cli.py
tests/test_config.py
tests/test_discovery_query.py
tests/test_enrich.py
tests/test_extractors.py
tests/test_html_fidelity.py
tests/test_multilingual.py
tests/test_pdf_headings.py
tests/test_pdf_languages.py
tests/test_pdf_preambles.py
tests/test_pdf_repair.py
tests/test_pipeline.py
tests/test_quality_repair.py
tests/test_run_outcomes.py
tests/test_splitter.py
tests/test_storage.py
tests/test_translate.py
tests/test_utils.py
tests/test_validate.py
tests/fixtures/html/README.md
tests/fixtures/html/consolidated-copyright-article-6.xhtml
tests/fixtures/html/consolidated-gdpr-article-99.xhtml
tests/fixtures/html/consolidated-safety-article-8.xhtml
tests/fixtures/html/copyright-directive-article-24.xhtml
tests/fixtures/html/provenance.json
tests/fixtures/multilingual/README.md
tests/fixtures/multilingual/consolidated-gdpr-article-7-deu.xhtml
tests/fixtures/multilingual/consolidated-gdpr-article-7-eng.xhtml
tests/fixtures/multilingual/dora-article-60-eng.xhtml
tests/fixtures/multilingual/gdpr-article-7-deu.xhtml
tests/fixtures/multilingual/gdpr-article-7-ell.xhtml
tests/fixtures/multilingual/gdpr-article-7-eng.xhtml
tests/fixtures/multilingual/provenance.json
tests/fixtures/pdf/31982D0809-spa.md
tests/fixtures/pdf/README.md
tests/fixtures/pdf/gdpr-articles-1-2.json
tests/fixtures/pdf/gdpr-displaced-headings.json
tests/fixtures/pdf/preamble-layout-pages.json
tests/fixtures/pdf/provenance.json