LICENSE
README.md
pyproject.toml
pdf_auto_tagger.egg-info/PKG-INFO
pdf_auto_tagger.egg-info/SOURCES.txt
pdf_auto_tagger.egg-info/dependency_links.txt
pdf_auto_tagger.egg-info/entry_points.txt
pdf_auto_tagger.egg-info/requires.txt
pdf_auto_tagger.egg-info/top_level.txt
tagger/__init__.py
tagger/__main__.py
tagger/api.py
tagger/cli.py
tagger/config.py
tagger/docmodel_adapter.py
tagger/page_cache.py
tagger/pipeline.py
tagger/preflight.py
tagger/text_norm.py
tagger/audit/__init__.py
tagger/audit/act_rules.py
tagger/audit/alt_text_quality.py
tagger/audit/matterhorn.py
tagger/audit/screen_reader.py
tagger/audit/semantic_judge.py
tagger/audit/text_coverage.py
tagger/audit/verapdf.py
tagger/benchmark/__init__.py
tagger/benchmark/gemma_quality.py
tagger/benchmark/harness.py
tagger/benchmark/loader.py
tagger/benchmark/report.py
tagger/benchmark/struct_utils.py
tagger/benchmark/dpbench/__init__.py
tagger/benchmark/dpbench/adapter.py
tagger/benchmark/dpbench/converter.py
tagger/benchmark/dpbench/harness.py
tagger/benchmark/dpbench/heading.py
tagger/benchmark/dpbench/reading_order.py
tagger/benchmark/dpbench/report.py
tagger/benchmark/dpbench/score.py
tagger/benchmark/dpbench/table.py
tagger/benchmark/verdicts/__init__.py
tagger/benchmark/verdicts/alt_text.py
tagger/benchmark/verdicts/base.py
tagger/benchmark/verdicts/font_embedding.py
tagger/benchmark/verdicts/functional_hyperlinks.py
tagger/benchmark/verdicts/logical_reading_order.py
tagger/benchmark/verdicts/semantic_tagging.py
tagger/benchmark/verdicts/table_structure.py
tagger/benchmark/verdicts/unicode_mapping.py
tagger/models/__init__.py
tagger/models/confidence.py
tagger/models/data_types.py
tagger/packages/__init__.py
tagger/packages/structure/__init__.py
tagger/qa/__init__.py
tagger/qa/modal_gemma_vllm.py
tagger/qa/rules_db.py
tagger/qa/table_header_rules.py
tagger/qa/tableheader_pass.py
tagger/stage0_classifier/__init__.py
tagger/stage0_classifier/page_classifier.py
tagger/stage10_writeback/__init__.py
tagger/stage10_writeback/content_stream_writer.py
tagger/stage10_writeback/repair_gate.py
tagger/stage10_writeback/splice.py
tagger/stage10_writeback/struct_tree_writer.py
tagger/stage1_extraction/__init__.py
tagger/stage1_extraction/coord_transformer.py
tagger/stage1_extraction/native_extractor.py
tagger/stage1_extraction/scanned_extractor.py
tagger/stage2_merger/__init__.py
tagger/stage2_merger/text_merger.py
tagger/stage3_layout/__init__.py
tagger/stage3_layout/cpu_layout_detector.py
tagger/stage3_layout/layout_detector.py
tagger/stage3_layout/mineru_worker.py
tagger/stage3_layout/model_adapter.py
tagger/stage3_layout/picodet_layout.py
tagger/stage4_router/__init__.py
tagger/stage4_router/content_router.py
tagger/stage5_specialists/__init__.py
tagger/stage5_specialists/docling_table_extractor.py
tagger/stage5_specialists/figure_handler.py
tagger/stage5_specialists/formula_extractor.py
tagger/stage5_specialists/mathml_emitter.py
tagger/stage5_specialists/slanet_table_extractor.py
tagger/stage5_specialists/table_extractor.py
tagger/stage5_specialists/tableformerv2_table_extractor.py
tagger/stage5_specialists/tatr_table_extractor.py
tagger/stage5_specialists/text_handler.py
tagger/stage6_validator/__init__.py
tagger/stage6_validator/consistency_validator.py
tagger/stage7_cross_page/__init__.py
tagger/stage7_cross_page/cross_page_merger.py
tagger/stage8_semantic/__init__.py
tagger/stage8_semantic/artifact_detector.py
tagger/stage8_semantic/caption_detector.py
tagger/stage8_semantic/heading_hierarchy_enforcer.py
tagger/stage8_semantic/heading_ranker.py
tagger/stage8_semantic/list_builder.py
tagger/stage8_semantic/pdfua_structural_enforcer.py
tagger/stage8_semantic/toc_detector.py
tagger/stage9_alttext/__init__.py
tagger/stage9_alttext/alt_text_generator.py
tagger/stage9_alttext/siglip_figure_classifier.py
tests/test_act_rules.py
tests/test_alt_endpoint_consolidation.py
tests/test_alt_text_backend.py
tests/test_alt_text_labels.py
tests/test_alt_text_quality.py
tests/test_artifact_wrap.py
tests/test_benchmark_alt_font.py
tests/test_benchmark_harness.py
tests/test_benchmark_loader.py
tests/test_benchmark_report.py
tests/test_benchmark_struct_utils.py
tests/test_benchmark_verdicts.py
tests/test_conformance_gate.py
tests/test_coords.py
tests/test_cross_page.py
tests/test_docmodel_adapter.py
tests/test_dpbench_adapter.py
tests/test_dpbench_gate.py
tests/test_dpbench_harness.py
tests/test_dpbench_score.py
tests/test_figure_tagging.py
tests/test_heading_hierarchy_enforcer.py
tests/test_mathml_formula.py
tests/test_matterhorn.py
tests/test_mixed_pages.py
tests/test_pdfua_structural_enforcer.py
tests/test_picodet_backend.py
tests/test_pipeline.py
tests/test_preflight.py
tests/test_reading_order.py
tests/test_repair_gate.py
tests/test_screen_reader.py
tests/test_semantic_judge.py
tests/test_slanet_table.py
tests/test_splice.py
tests/test_stage0.py
tests/test_stage2.py
tests/test_stage5.py
tests/test_stage6.py
tests/test_stage8.py
tests/test_structure_facade.py
tests/test_table_header.py
tests/test_tableheader_pass.py
tests/test_text_coverage.py
tests/test_text_norm.py
tests/test_unicode_mapping.py
tests/test_verapdf_primitive.py
tests/test_writeback.py