RubyGems - kreuzberg - Versions diffs - 4.0.0.pre.rc.29 → 4.0.0.rc1 - Mend

kreuzberg 4.0.0.pre.rc.29 → 4.0.0.rc1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (321) hide show

checksums.yaml +4 -4
data/.gitignore +0 -6
data/.rubocop.yaml +534 -1
data/Gemfile +2 -1
data/Gemfile.lock +28 -116
data/README.md +269 -629
data/Rakefile +0 -9
data/Steepfile +4 -8
data/examples/async_patterns.rb +58 -1
data/ext/kreuzberg_rb/extconf.rb +5 -35
data/ext/kreuzberg_rb/native/Cargo.toml +16 -55
data/ext/kreuzberg_rb/native/build.rs +14 -12
data/ext/kreuzberg_rb/native/include/ieeefp.h +1 -1
data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +1 -1
data/ext/kreuzberg_rb/native/include/strings.h +2 -2
data/ext/kreuzberg_rb/native/include/unistd.h +1 -1
data/ext/kreuzberg_rb/native/src/lib.rs +34 -897
data/extconf.rb +6 -38
data/kreuzberg.gemspec +20 -114
data/lib/kreuzberg/api_proxy.rb +18 -2
data/lib/kreuzberg/cache_api.rb +0 -22
data/lib/kreuzberg/cli.rb +10 -2
data/lib/kreuzberg/cli_proxy.rb +10 -0
data/lib/kreuzberg/config.rb +22 -274
data/lib/kreuzberg/errors.rb +7 -73
data/lib/kreuzberg/extraction_api.rb +8 -237
data/lib/kreuzberg/mcp_proxy.rb +11 -2
data/lib/kreuzberg/ocr_backend_protocol.rb +73 -0
data/lib/kreuzberg/post_processor_protocol.rb +71 -0
data/lib/kreuzberg/result.rb +33 -151
data/lib/kreuzberg/setup_lib_path.rb +2 -22
data/lib/kreuzberg/validator_protocol.rb +73 -0
data/lib/kreuzberg/version.rb +1 -1
data/lib/kreuzberg.rb +13 -27
data/pkg/kreuzberg-4.0.0.rc1.gem +0 -0
data/sig/kreuzberg.rbs +12 -105
data/spec/binding/cache_spec.rb +22 -22
data/spec/binding/cli_proxy_spec.rb +4 -2
data/spec/binding/cli_spec.rb +11 -12
data/spec/binding/config_spec.rb +0 -74
data/spec/binding/config_validation_spec.rb +6 -100
data/spec/binding/error_handling_spec.rb +97 -283
data/spec/binding/plugins/ocr_backend_spec.rb +8 -8
data/spec/binding/plugins/postprocessor_spec.rb +11 -11
data/spec/binding/plugins/validator_spec.rb +13 -12
data/spec/examples.txt +104 -0
data/spec/fixtures/config.toml +1 -0
data/spec/fixtures/config.yaml +1 -0
data/spec/fixtures/invalid_config.toml +1 -0
data/spec/smoke/package_spec.rb +3 -2
data/spec/spec_helper.rb +3 -1
data/vendor/kreuzberg/Cargo.toml +67 -192
data/vendor/kreuzberg/README.md +9 -97
data/vendor/kreuzberg/build.rs +194 -516
data/vendor/kreuzberg/src/api/handlers.rs +9 -130
data/vendor/kreuzberg/src/api/mod.rs +3 -18
data/vendor/kreuzberg/src/api/server.rs +71 -236
data/vendor/kreuzberg/src/api/types.rs +7 -43
data/vendor/kreuzberg/src/bin/profile_extract.rs +455 -0
data/vendor/kreuzberg/src/cache/mod.rs +3 -27
data/vendor/kreuzberg/src/chunking/mod.rs +79 -1705
data/vendor/kreuzberg/src/core/batch_mode.rs +0 -60
data/vendor/kreuzberg/src/core/config.rs +23 -905
data/vendor/kreuzberg/src/core/extractor.rs +106 -403
data/vendor/kreuzberg/src/core/io.rs +2 -4
data/vendor/kreuzberg/src/core/mime.rs +12 -2
data/vendor/kreuzberg/src/core/mod.rs +3 -22
data/vendor/kreuzberg/src/core/pipeline.rs +78 -395
data/vendor/kreuzberg/src/embeddings.rs +21 -169
data/vendor/kreuzberg/src/error.rs +2 -2
data/vendor/kreuzberg/src/extraction/archive.rs +31 -36
data/vendor/kreuzberg/src/extraction/docx.rs +1 -365
data/vendor/kreuzberg/src/extraction/email.rs +11 -12
data/vendor/kreuzberg/src/extraction/excel.rs +129 -138
data/vendor/kreuzberg/src/extraction/html.rs +170 -1447
data/vendor/kreuzberg/src/extraction/image.rs +14 -138
data/vendor/kreuzberg/src/extraction/libreoffice.rs +3 -13
data/vendor/kreuzberg/src/extraction/mod.rs +5 -21
data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +0 -2
data/vendor/kreuzberg/src/extraction/pandoc/batch.rs +275 -0
data/vendor/kreuzberg/src/extraction/pandoc/mime_types.rs +178 -0
data/vendor/kreuzberg/src/extraction/pandoc/mod.rs +491 -0
data/vendor/kreuzberg/src/extraction/pandoc/server.rs +496 -0
data/vendor/kreuzberg/src/extraction/pandoc/subprocess.rs +1188 -0
data/vendor/kreuzberg/src/extraction/pandoc/version.rs +162 -0
data/vendor/kreuzberg/src/extraction/pptx.rs +94 -196
data/vendor/kreuzberg/src/extraction/structured.rs +4 -5
data/vendor/kreuzberg/src/extraction/table.rs +1 -2
data/vendor/kreuzberg/src/extraction/text.rs +10 -18
data/vendor/kreuzberg/src/extractors/archive.rs +0 -22
data/vendor/kreuzberg/src/extractors/docx.rs +148 -69
data/vendor/kreuzberg/src/extractors/email.rs +9 -37
data/vendor/kreuzberg/src/extractors/excel.rs +40 -81
data/vendor/kreuzberg/src/extractors/html.rs +173 -182
data/vendor/kreuzberg/src/extractors/image.rs +8 -32
data/vendor/kreuzberg/src/extractors/mod.rs +10 -171
data/vendor/kreuzberg/src/extractors/pandoc.rs +201 -0
data/vendor/kreuzberg/src/extractors/pdf.rs +64 -329
data/vendor/kreuzberg/src/extractors/pptx.rs +34 -79
data/vendor/kreuzberg/src/extractors/structured.rs +0 -16
data/vendor/kreuzberg/src/extractors/text.rs +7 -30
data/vendor/kreuzberg/src/extractors/xml.rs +8 -27
data/vendor/kreuzberg/src/keywords/processor.rs +1 -9
data/vendor/kreuzberg/src/keywords/rake.rs +1 -0
data/vendor/kreuzberg/src/language_detection/mod.rs +51 -94
data/vendor/kreuzberg/src/lib.rs +5 -17
data/vendor/kreuzberg/src/mcp/mod.rs +1 -4
data/vendor/kreuzberg/src/mcp/server.rs +21 -145
data/vendor/kreuzberg/src/ocr/mod.rs +0 -2
data/vendor/kreuzberg/src/ocr/processor.rs +8 -19
data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +0 -2
data/vendor/kreuzberg/src/pdf/error.rs +1 -93
data/vendor/kreuzberg/src/pdf/metadata.rs +100 -263
data/vendor/kreuzberg/src/pdf/mod.rs +2 -33
data/vendor/kreuzberg/src/pdf/rendering.rs +12 -12
data/vendor/kreuzberg/src/pdf/table.rs +64 -61
data/vendor/kreuzberg/src/pdf/text.rs +24 -416
data/vendor/kreuzberg/src/plugins/extractor.rs +8 -40
data/vendor/kreuzberg/src/plugins/mod.rs +0 -3
data/vendor/kreuzberg/src/plugins/ocr.rs +14 -22
data/vendor/kreuzberg/src/plugins/processor.rs +1 -10
data/vendor/kreuzberg/src/plugins/registry.rs +0 -15
data/vendor/kreuzberg/src/plugins/validator.rs +8 -20
data/vendor/kreuzberg/src/stopwords/mod.rs +2 -2
data/vendor/kreuzberg/src/text/mod.rs +0 -8
data/vendor/kreuzberg/src/text/quality.rs +15 -28
data/vendor/kreuzberg/src/text/string_utils.rs +10 -22
data/vendor/kreuzberg/src/text/token_reduction/core.rs +50 -86
data/vendor/kreuzberg/src/text/token_reduction/filters.rs +16 -37
data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +1 -2
data/vendor/kreuzberg/src/types.rs +67 -907
data/vendor/kreuzberg/src/utils/mod.rs +0 -14
data/vendor/kreuzberg/src/utils/quality.rs +3 -12
data/vendor/kreuzberg/tests/api_tests.rs +0 -506
data/vendor/kreuzberg/tests/archive_integration.rs +0 -2
data/vendor/kreuzberg/tests/batch_orchestration.rs +12 -57
data/vendor/kreuzberg/tests/batch_processing.rs +8 -32
data/vendor/kreuzberg/tests/chunking_offset_demo.rs +92 -0
data/vendor/kreuzberg/tests/concurrency_stress.rs +8 -40
data/vendor/kreuzberg/tests/config_features.rs +1 -33
data/vendor/kreuzberg/tests/config_loading_tests.rs +39 -16
data/vendor/kreuzberg/tests/core_integration.rs +9 -35
data/vendor/kreuzberg/tests/csv_integration.rs +81 -71
data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +25 -23
data/vendor/kreuzberg/tests/email_integration.rs +1 -3
data/vendor/kreuzberg/tests/error_handling.rs +34 -43
data/vendor/kreuzberg/tests/format_integration.rs +1 -7
data/vendor/kreuzberg/tests/helpers/mod.rs +0 -60
data/vendor/kreuzberg/tests/image_integration.rs +0 -2
data/vendor/kreuzberg/tests/mime_detection.rs +16 -17
data/vendor/kreuzberg/tests/ocr_configuration.rs +0 -4
data/vendor/kreuzberg/tests/ocr_errors.rs +0 -22
data/vendor/kreuzberg/tests/ocr_quality.rs +0 -2
data/vendor/kreuzberg/tests/pandoc_integration.rs +503 -0
data/vendor/kreuzberg/tests/pdf_integration.rs +0 -2
data/vendor/kreuzberg/tests/pipeline_integration.rs +2 -36
data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +0 -5
data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +1 -17
data/vendor/kreuzberg/tests/plugin_system.rs +0 -6
data/vendor/kreuzberg/tests/registry_integration_tests.rs +22 -2
data/vendor/kreuzberg/tests/security_validation.rs +1 -13
data/vendor/kreuzberg/tests/test_fastembed.rs +23 -45
metadata +25 -171
data/.rubocop.yml +0 -543
data/ext/kreuzberg_rb/native/.cargo/config.toml +0 -23
data/ext/kreuzberg_rb/native/Cargo.lock +0 -7619
data/lib/kreuzberg/error_context.rb +0 -136
data/lib/kreuzberg/types.rb +0 -170
data/lib/libpdfium.so +0 -0
data/spec/binding/async_operations_spec.rb +0 -473
data/spec/binding/batch_operations_spec.rb +0 -595
data/spec/binding/batch_spec.rb +0 -359
data/spec/binding/config_result_spec.rb +0 -377
data/spec/binding/embeddings_spec.rb +0 -816
data/spec/binding/error_recovery_spec.rb +0 -488
data/spec/binding/font_config_spec.rb +0 -220
data/spec/binding/images_spec.rb +0 -738
data/spec/binding/keywords_extraction_spec.rb +0 -600
data/spec/binding/metadata_types_spec.rb +0 -1228
data/spec/binding/pages_extraction_spec.rb +0 -471
data/spec/binding/tables_spec.rb +0 -641
data/spec/unit/config/chunking_config_spec.rb +0 -213
data/spec/unit/config/embedding_config_spec.rb +0 -343
data/spec/unit/config/extraction_config_spec.rb +0 -438
data/spec/unit/config/font_config_spec.rb +0 -285
data/spec/unit/config/hierarchy_config_spec.rb +0 -314
data/spec/unit/config/image_extraction_config_spec.rb +0 -209
data/spec/unit/config/image_preprocessing_config_spec.rb +0 -249
data/spec/unit/config/keyword_config_spec.rb +0 -229
data/spec/unit/config/language_detection_config_spec.rb +0 -258
data/spec/unit/config/ocr_config_spec.rb +0 -171
data/spec/unit/config/page_config_spec.rb +0 -221
data/spec/unit/config/pdf_config_spec.rb +0 -267
data/spec/unit/config/postprocessor_config_spec.rb +0 -290
data/spec/unit/config/tesseract_config_spec.rb +0 -181
data/spec/unit/config/token_reduction_config_spec.rb +0 -251
data/test/metadata_types_test.rb +0 -959
data/vendor/Cargo.toml +0 -61
data/vendor/kreuzberg/examples/bench_fixes.rs +0 -71
data/vendor/kreuzberg/examples/test_pdfium_fork.rs +0 -62
data/vendor/kreuzberg/src/chunking/processor.rs +0 -219
data/vendor/kreuzberg/src/core/batch_optimizations.rs +0 -385
data/vendor/kreuzberg/src/core/config_validation.rs +0 -949
data/vendor/kreuzberg/src/core/formats.rs +0 -235
data/vendor/kreuzberg/src/core/server_config.rs +0 -1220
data/vendor/kreuzberg/src/extraction/capacity.rs +0 -263
data/vendor/kreuzberg/src/extraction/markdown.rs +0 -216
data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +0 -284
data/vendor/kreuzberg/src/extractors/bibtex.rs +0 -470
data/vendor/kreuzberg/src/extractors/docbook.rs +0 -504
data/vendor/kreuzberg/src/extractors/epub.rs +0 -696
data/vendor/kreuzberg/src/extractors/fictionbook.rs +0 -492
data/vendor/kreuzberg/src/extractors/jats.rs +0 -1054
data/vendor/kreuzberg/src/extractors/jupyter.rs +0 -368
data/vendor/kreuzberg/src/extractors/latex.rs +0 -653
data/vendor/kreuzberg/src/extractors/markdown.rs +0 -701
data/vendor/kreuzberg/src/extractors/odt.rs +0 -628
data/vendor/kreuzberg/src/extractors/opml.rs +0 -635
data/vendor/kreuzberg/src/extractors/orgmode.rs +0 -529
data/vendor/kreuzberg/src/extractors/rst.rs +0 -577
data/vendor/kreuzberg/src/extractors/rtf.rs +0 -809
data/vendor/kreuzberg/src/extractors/security.rs +0 -484
data/vendor/kreuzberg/src/extractors/security_tests.rs +0 -367
data/vendor/kreuzberg/src/extractors/typst.rs +0 -651
data/vendor/kreuzberg/src/language_detection/processor.rs +0 -218
data/vendor/kreuzberg/src/ocr/language_registry.rs +0 -520
data/vendor/kreuzberg/src/panic_context.rs +0 -154
data/vendor/kreuzberg/src/pdf/bindings.rs +0 -306
data/vendor/kreuzberg/src/pdf/bundled.rs +0 -408
data/vendor/kreuzberg/src/pdf/fonts.rs +0 -358
data/vendor/kreuzberg/src/pdf/hierarchy.rs +0 -903
data/vendor/kreuzberg/src/text/quality_processor.rs +0 -231
data/vendor/kreuzberg/src/text/utf8_validation.rs +0 -193
data/vendor/kreuzberg/src/utils/pool.rs +0 -503
data/vendor/kreuzberg/src/utils/pool_sizing.rs +0 -364
data/vendor/kreuzberg/src/utils/string_pool.rs +0 -761
data/vendor/kreuzberg/tests/api_embed.rs +0 -360
data/vendor/kreuzberg/tests/api_extract_multipart.rs +0 -52
data/vendor/kreuzberg/tests/api_large_pdf_extraction.rs +0 -471
data/vendor/kreuzberg/tests/api_large_pdf_extraction_diagnostics.rs +0 -289
data/vendor/kreuzberg/tests/batch_pooling_benchmark.rs +0 -154
data/vendor/kreuzberg/tests/bibtex_parity_test.rs +0 -421
data/vendor/kreuzberg/tests/config_integration_test.rs +0 -753
data/vendor/kreuzberg/tests/data/hierarchy_ground_truth.json +0 -294
data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +0 -500
data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +0 -370
data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +0 -275
data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +0 -228
data/vendor/kreuzberg/tests/html_table_test.rs +0 -551
data/vendor/kreuzberg/tests/instrumentation_test.rs +0 -139
data/vendor/kreuzberg/tests/jats_extractor_tests.rs +0 -639
data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +0 -704
data/vendor/kreuzberg/tests/latex_extractor_tests.rs +0 -496
data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +0 -490
data/vendor/kreuzberg/tests/ocr_language_registry.rs +0 -191
data/vendor/kreuzberg/tests/odt_extractor_tests.rs +0 -674
data/vendor/kreuzberg/tests/opml_extractor_tests.rs +0 -616
data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +0 -822
data/vendor/kreuzberg/tests/page_markers.rs +0 -297
data/vendor/kreuzberg/tests/pdf_hierarchy_detection.rs +0 -301
data/vendor/kreuzberg/tests/pdf_hierarchy_quality.rs +0 -589
data/vendor/kreuzberg/tests/pdf_ocr_triggering.rs +0 -301
data/vendor/kreuzberg/tests/pdf_text_merging.rs +0 -475
data/vendor/kreuzberg/tests/pdfium_linking.rs +0 -340
data/vendor/kreuzberg/tests/rst_extractor_tests.rs +0 -694
data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +0 -775
data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +0 -1260
data/vendor/kreuzberg/tests/typst_extractor_tests.rs +0 -648
data/vendor/kreuzberg-ffi/Cargo.toml +0 -67
data/vendor/kreuzberg-ffi/README.md +0 -851
data/vendor/kreuzberg-ffi/benches/result_view_benchmark.rs +0 -227
data/vendor/kreuzberg-ffi/build.rs +0 -168
data/vendor/kreuzberg-ffi/cbindgen.toml +0 -37
data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +0 -12
data/vendor/kreuzberg-ffi/kreuzberg.h +0 -3012
data/vendor/kreuzberg-ffi/src/batch_streaming.rs +0 -588
data/vendor/kreuzberg-ffi/src/config.rs +0 -1341
data/vendor/kreuzberg-ffi/src/error.rs +0 -901
data/vendor/kreuzberg-ffi/src/extraction.rs +0 -555
data/vendor/kreuzberg-ffi/src/helpers.rs +0 -879
data/vendor/kreuzberg-ffi/src/lib.rs +0 -977
data/vendor/kreuzberg-ffi/src/memory.rs +0 -493
data/vendor/kreuzberg-ffi/src/mime.rs +0 -329
data/vendor/kreuzberg-ffi/src/panic_shield.rs +0 -265
data/vendor/kreuzberg-ffi/src/plugins/document_extractor.rs +0 -442
data/vendor/kreuzberg-ffi/src/plugins/mod.rs +0 -14
data/vendor/kreuzberg-ffi/src/plugins/ocr_backend.rs +0 -628
data/vendor/kreuzberg-ffi/src/plugins/post_processor.rs +0 -438
data/vendor/kreuzberg-ffi/src/plugins/validator.rs +0 -329
data/vendor/kreuzberg-ffi/src/result.rs +0 -510
data/vendor/kreuzberg-ffi/src/result_pool.rs +0 -639
data/vendor/kreuzberg-ffi/src/result_view.rs +0 -773
data/vendor/kreuzberg-ffi/src/string_intern.rs +0 -568
data/vendor/kreuzberg-ffi/src/types.rs +0 -363
data/vendor/kreuzberg-ffi/src/util.rs +0 -210
data/vendor/kreuzberg-ffi/src/validation.rs +0 -848
data/vendor/kreuzberg-ffi/tests.disabled/README.md +0 -48
data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +0 -299
data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +0 -346
data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +0 -232
data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +0 -470
data/vendor/kreuzberg-tesseract/.commitlintrc.json +0 -13
data/vendor/kreuzberg-tesseract/.crate-ignore +0 -2
data/vendor/kreuzberg-tesseract/Cargo.lock +0 -2933
data/vendor/kreuzberg-tesseract/Cargo.toml +0 -57
data/vendor/kreuzberg-tesseract/LICENSE +0 -22
data/vendor/kreuzberg-tesseract/README.md +0 -399
data/vendor/kreuzberg-tesseract/build.rs +0 -1127
data/vendor/kreuzberg-tesseract/patches/README.md +0 -71
data/vendor/kreuzberg-tesseract/patches/tesseract.diff +0 -199
data/vendor/kreuzberg-tesseract/src/api.rs +0 -1371
data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +0 -77
data/vendor/kreuzberg-tesseract/src/enums.rs +0 -297
data/vendor/kreuzberg-tesseract/src/error.rs +0 -81
data/vendor/kreuzberg-tesseract/src/lib.rs +0 -145
data/vendor/kreuzberg-tesseract/src/monitor.rs +0 -57
data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +0 -197
data/vendor/kreuzberg-tesseract/src/page_iterator.rs +0 -253
data/vendor/kreuzberg-tesseract/src/result_iterator.rs +0 -286
data/vendor/kreuzberg-tesseract/src/result_renderer.rs +0 -183
data/vendor/kreuzberg-tesseract/tests/integration_test.rs +0 -211

data/vendor/kreuzberg/tests/jats_extractor_tests.rs DELETED Viewed

@@ -1,639 +0,0 @@
-//! Comprehensive test suite for the JATS (Journal Article Tag Suite) extractor.
-//!
-//! This test suite validates all aspects of the JATS extractor including:
-//! - Metadata extraction (title, authors, affiliations, DOI, keywords, dates)
-//! - Article content extraction (sections, paragraphs)
-//! - Table extraction with proper structure
-//! - Citation handling
-//! - Edge cases and error handling
-#[cfg(all(test, feature = "xml"))]
-mod jats_extractor_tests {
-    use kreuzberg::core::config::ExtractionConfig;
-    use kreuzberg::extractors::JatsExtractor;
-    use kreuzberg::plugins::{DocumentExtractor, Plugin};
-    use std::path::PathBuf;
-    fn jats_fixture(name: &str) -> PathBuf {
-        PathBuf::from(env!("CARGO_MANIFEST_DIR"))
-            .join("../../test_documents/jats")
-            .join(name)
-    }
-    /// Test basic JATS article extraction with all key metadata fields
-    #[tokio::test]
-    async fn test_extract_complete_jats_article() {
-        let jats_content = r#"<?xml version="1.0" encoding="UTF-8"?>
-<article xmlns:xlink="http://www.w3.org/1999/xlink" article-type="research-article">
-  <front>
-    <article-meta>
-      <article-title>Effects of Caffeine on Human Health</article-title>
-      <subtitle>A Systematic Review and Meta-Analysis</subtitle>
-      <contrib-group>
-        <contrib contrib-type="author">
-          <name>
-            <surname>Smith</surname>
-            <given-names>John A.</given-names>
-          </name>
-        </contrib>
-        <contrib contrib-type="author">
-          <name>
-            <surname>Johnson</surname>
-            <given-names>Jane B.</given-names>
-          </name>
-        </contrib>
-      </contrib-group>
-      <aff id="aff1">Department of Medicine, Harvard University, Cambridge, MA</aff>
-      <article-id pub-id-type="doi">10.1371/journal.pmed.0020124</article-id>
-      <article-id pub-id-type="pii">05-PLME-RA-0071R2</article-id>
-      <pub-date pub-type="epub">
-        <day>18</day>
-        <month>04</month>
-        <year>2005</year>
-      </pub-date>
-      <volume>2</volume>
-      <issue>4</issue>
-      <fpage>e124</fpage>
-      <lpage>e132</lpage>
-      <kwd-group>
-        <kwd>caffeine</kwd>
-        <kwd>meta-analysis</kwd>
-        <kwd>systematic review</kwd>
-      </kwd-group>
-      <abstract>
-        <sec>
-          <title>Background</title>
-          <p>Caffeine is one of the most widely consumed psychoactive substances.</p>
-        </sec>
-      </abstract>
-    </article-meta>
-  </front>
-  <body>
-    <sec id="s1">
-      <title>Introduction</title>
-      <p>This review examines the evidence for effects of caffeine.</p>
-    </sec>
-  </body>
-</article>"#;
-        let extractor = JatsExtractor::new();
-        let config = ExtractionConfig::default();
-        let result = extractor
-            .extract_bytes(jats_content.as_bytes(), "application/x-jats+xml", &config)
-            .await;
-        assert!(result.is_ok());
-        let extraction = result.unwrap();
-        assert!(extraction.content.contains("Effects of Caffeine"));
-        assert!(extraction.content.contains("Introduction"));
-        assert!(extraction.metadata.subject.is_some());
-        let subject = extraction.metadata.subject.unwrap();
-        assert!(subject.contains("Effects of Caffeine"));
-        assert!(subject.contains("10.1371"));
-        assert!(subject.contains("caffeine") || subject.contains("Keywords"));
-    }
-    /// Test extraction of rich metadata including all author and affiliation data
-    #[tokio::test]
-    async fn test_extract_rich_author_affiliation_metadata() {
-        let jats_content = r#"<?xml version="1.0" encoding="UTF-8"?>
-<article>
-  <front>
-    <article-meta>
-      <article-title>Advanced Study</article-title>
-      <contrib-group>
-        <contrib contrib-type="author">
-          <name>
-            <surname>Alpha</surname>
-            <given-names>First</given-names>
-          </name>
-          <xref ref-type="aff" rid="aff1">1</xref>
-          <xref ref-type="aff" rid="aff2">2</xref>
-        </contrib>
-        <contrib contrib-type="author">
-          <name>
-            <surname>Beta</surname>
-            <given-names>Second</given-names>
-          </name>
-          <xref ref-type="aff" rid="aff1">1</xref>
-        </contrib>
-        <contrib contrib-type="author">
-          <name>
-            <surname>Gamma</surname>
-            <given-names>Third</given-names>
-          </name>
-          <xref ref-type="aff" rid="aff3">3</xref>
-          <role>Correspondence</role>
-        </contrib>
-      </contrib-group>
-      <aff id="aff1"><label>1</label>Department of Science, University A, City A</aff>
-      <aff id="aff2"><label>2</label>Research Institute, City B</aff>
-      <aff id="aff3"><label>3</label>Medical Center, City C</aff>
-    </article-meta>
-  </front>
-</article>"#;
-        let extractor = JatsExtractor::new();
-        let config = ExtractionConfig::default();
-        let result = extractor
-            .extract_bytes(jats_content.as_bytes(), "application/x-jats+xml", &config)
-            .await;
-        assert!(result.is_ok());
-        let extraction = result.unwrap();
-        let subject = extraction.metadata.subject.unwrap();
-        assert!(subject.contains("Alpha"));
-        assert!(subject.contains("Beta"));
-        assert!(subject.contains("Gamma"));
-        assert!(subject.contains("Department of Science"));
-    }
-    /// Test section hierarchy extraction in article body
-    #[tokio::test]
-    async fn test_extract_section_hierarchy() {
-        let jats_content = r#"<?xml version="1.0" encoding="UTF-8"?>
-<article>
-  <front>
-    <article-meta>
-      <article-title>Research Article</article-title>
-    </article-meta>
-  </front>
-  <body>
-    <sec id="s1">
-      <title>Introduction</title>
-      <p>Introduction content here.</p>
-    </sec>
-    <sec id="s2">
-      <title>Methods</title>
-      <sec id="s2a">
-        <title>Study Design</title>
-        <p>Design content here.</p>
-      </sec>
-      <sec id="s2b">
-        <title>Participants</title>
-        <p>Participant content here.</p>
-      </sec>
-    </sec>
-    <sec id="s3">
-      <title>Results</title>
-      <p>Results content here.</p>
-    </sec>
-    <sec id="s4">
-      <title>Discussion</title>
-      <p>Discussion content here.</p>
-    </sec>
-    <sec id="s5">
-      <title>Conclusions</title>
-      <p>Conclusion content here.</p>
-    </sec>
-  </body>
-</article>"#;
-        let extractor = JatsExtractor::new();
-        let config = ExtractionConfig::default();
-        let result = extractor
-            .extract_bytes(jats_content.as_bytes(), "application/x-jats+xml", &config)
-            .await;
-        assert!(result.is_ok());
-        let extraction = result.unwrap();
-        assert!(extraction.content.contains("Introduction"));
-        assert!(extraction.content.contains("Methods"));
-        assert!(extraction.content.contains("Results"));
-        assert!(extraction.content.contains("Discussion"));
-        assert!(extraction.content.contains("Conclusions"));
-        assert!(extraction.content.contains("Study Design"));
-        assert!(extraction.content.contains("Participants"));
-    }
-    /// Test table extraction with headers and data rows
-    #[tokio::test]
-    async fn test_extract_tables_with_captions() {
-        let jats_content = r#"<?xml version="1.0" encoding="UTF-8"?>
-<article>
-  <front>
-    <article-meta>
-      <article-title>Study Results</article-title>
-    </article-meta>
-  </front>
-  <body>
-    <sec id="s1">
-      <title>Results</title>
-      <table-wrap id="tbl1">
-        <label>Table 1</label>
-        <caption>
-          <title>Characteristics of Study Population</title>
-          <p>Baseline characteristics of enrolled subjects.</p>
-        </caption>
-        <table>
-          <thead>
-            <tr>
-              <th>Parameter</th>
-              <th>Group A (n=50)</th>
-              <th>Group B (n=50)</th>
-              <th>P-value</th>
-            </tr>
-          </thead>
-          <tbody>
-            <tr>
-              <td>Age (years)</td>
-              <td>45.3 ± 8.2</td>
-              <td>44.9 ± 7.8</td>
-              <td>0.45</td>
-            </tr>
-            <tr>
-              <td>Sex (M/F)</td>
-              <td>28/22</td>
-              <td>26/24</td>
-              <td>0.58</td>
-            </tr>
-            <tr>
-              <td>BMI (kg/m²)</td>
-              <td>25.1 ± 3.2</td>
-              <td>24.8 ± 2.9</td>
-              <td>0.62</td>
-            </tr>
-          </tbody>
-        </table>
-      </table-wrap>
-    </sec>
-  </body>
-</article>"#;
-        let extractor = JatsExtractor::new();
-        let config = ExtractionConfig::default();
-        let result = extractor
-            .extract_bytes(jats_content.as_bytes(), "application/x-jats+xml", &config)
-            .await;
-        assert!(result.is_ok());
-        let extraction = result.unwrap();
-        assert_eq!(extraction.tables.len(), 1);
-        let table = &extraction.tables[0];
-        assert!(table.cells.len() >= 3);
-        assert_eq!(table.cells[0].len(), 4);
-        assert!(table.cells[0][0].contains("Parameter"));
-        assert!(table.cells[1][0].contains("Age"));
-        assert!(table.cells[2][0].contains("Sex"));
-    }
-    /// Test multiple tables extraction
-    #[tokio::test]
-    async fn test_extract_multiple_tables() {
-        let jats_content = r#"<?xml version="1.0" encoding="UTF-8"?>
-<article>
-  <front>
-    <article-meta>
-      <article-title>Multi-Table Article</article-title>
-    </article-meta>
-  </front>
-  <body>
-    <table-wrap id="tbl1">
-      <table>
-        <thead>
-          <tr><th>A</th><th>B</th></tr>
-        </thead>
-        <tbody>
-          <tr><td>1</td><td>2</td></tr>
-        </tbody>
-      </table>
-    </table-wrap>
-    <table-wrap id="tbl2">
-      <table>
-        <thead>
-          <tr><th>X</th><th>Y</th><th>Z</th></tr>
-        </thead>
-        <tbody>
-          <tr><td>a</td><td>b</td><td>c</td></tr>
-        </tbody>
-      </table>
-    </table-wrap>
-  </body>
-</article>"#;
-        let extractor = JatsExtractor::new();
-        let config = ExtractionConfig::default();
-        let result = extractor
-            .extract_bytes(jats_content.as_bytes(), "application/x-jats+xml", &config)
-            .await;
-        assert!(result.is_ok());
-        let extraction = result.unwrap();
-        assert_eq!(extraction.tables.len(), 2);
-        assert_eq!(extraction.tables[0].cells[0].len(), 2);
-        assert_eq!(extraction.tables[1].cells[0].len(), 3);
-    }
-    /// Test citation extraction in text with xref elements
-    #[tokio::test]
-    async fn test_extract_citations_in_text() {
-        let jats_content = r#"<?xml version="1.0" encoding="UTF-8"?>
-<article>
-  <front>
-    <article-meta>
-      <article-title>Citation Study</article-title>
-    </article-meta>
-  </front>
-  <body>
-    <sec id="s1">
-      <title>Introduction</title>
-      <p>Previous research has shown effectiveness <xref ref-type="bibr" rid="ref1">1</xref>.
-         Other studies confirm this finding <xref ref-type="bibr" rid="ref2">2</xref>.</p>
-    </sec>
-  </body>
-  <back>
-    <ref-list>
-      <ref id="ref1">
-        <element-citation publication-type="journal">
-          <person-group person-group-type="author">
-            <name>
-              <surname>Author</surname>
-              <given-names>First</given-names>
-            </name>
-          </person-group>
-          <article-title>Original Research</article-title>
-          <source>Journal Name</source>
-          <year>2020</year>
-        </element-citation>
-      </ref>
-      <ref id="ref2">
-        <element-citation publication-type="journal">
-          <person-group person-group-type="author">
-            <name>
-              <surname>Researcher</surname>
-              <given-names>Second</given-names>
-            </name>
-          </person-group>
-          <article-title>Confirmatory Study</article-title>
-          <source>Other Journal</source>
-          <year>2021</year>
-        </element-citation>
-      </ref>
-    </ref-list>
-  </back>
-</article>"#;
-        let extractor = JatsExtractor::new();
-        let config = ExtractionConfig::default();
-        let result = extractor
-            .extract_bytes(jats_content.as_bytes(), "application/x-jats+xml", &config)
-            .await;
-        assert!(result.is_ok());
-        let extraction = result.unwrap();
-        assert!(extraction.content.contains("Previous research"));
-        assert!(extraction.content.contains("Other studies"));
-    }
-    /// Test abstract extraction with structured sections
-    #[tokio::test]
-    async fn test_extract_structured_abstract() {
-        let jats_content = r#"<?xml version="1.0" encoding="UTF-8"?>
-<article>
-  <front>
-    <article-meta>
-      <article-title>Abstract Study</article-title>
-      <abstract>
-        <sec>
-          <title>Background</title>
-          <p>This is the background information of the study.</p>
-        </sec>
-        <sec>
-          <title>Methods and Findings</title>
-          <p>We used quantitative analysis to evaluate the hypothesis.</p>
-        </sec>
-        <sec>
-          <title>Conclusions</title>
-          <p>The study provides evidence that the hypothesis is correct.</p>
-        </sec>
-      </abstract>
-    </article-meta>
-  </front>
-</article>"#;
-        let extractor = JatsExtractor::new();
-        let config = ExtractionConfig::default();
-        let result = extractor
-            .extract_bytes(jats_content.as_bytes(), "application/x-jats+xml", &config)
-            .await;
-        assert!(result.is_ok());
-        let extraction = result.unwrap();
-        let subject = extraction.metadata.subject.unwrap();
-        assert!(subject.contains("background") || subject.contains("Background") || subject.contains("Abstract"));
-    }
-    /// Test corresponding author extraction
-    #[tokio::test]
-    async fn test_extract_corresponding_author() {
-        let jats_content = r#"<?xml version="1.0" encoding="UTF-8"?>
-<article>
-  <front>
-    <article-meta>
-      <article-title>Study</article-title>
-      <author-notes>
-        <corresp id="cor1"><label>*</label>Corresponding author. E-mail: john.smith@example.com</corresp>
-      </author-notes>
-    </article-meta>
-  </front>
-</article>"#;
-        let extractor = JatsExtractor::new();
-        let config = ExtractionConfig::default();
-        let result = extractor
-            .extract_bytes(jats_content.as_bytes(), "application/x-jats+xml", &config)
-            .await;
-        assert!(result.is_ok());
-        let extraction = result.unwrap();
-        assert!(extraction.metadata.subject.is_some());
-    }
-    /// Test publication date extraction in various formats
-    #[tokio::test]
-    async fn test_extract_publication_date() {
-        let jats_content = r#"<?xml version="1.0" encoding="UTF-8"?>
-<article>
-  <front>
-    <article-meta>
-      <article-title>Publication Test</article-title>
-      <pub-date pub-type="epub">
-        <day>15</day>
-        <month>06</month>
-        <year>2023</year>
-      </pub-date>
-    </article-meta>
-  </front>
-</article>"#;
-        let extractor = JatsExtractor::new();
-        let config = ExtractionConfig::default();
-        let result = extractor
-            .extract_bytes(jats_content.as_bytes(), "application/x-jats+xml", &config)
-            .await;
-        assert!(result.is_ok());
-        let extraction = result.unwrap();
-        assert!(extraction.metadata.created_at.is_some());
-    }
-    /// Test handling of empty/minimal JATS documents
-    #[tokio::test]
-    async fn test_extract_minimal_jats() {
-        let jats_content = r#"<?xml version="1.0" encoding="UTF-8"?>
-<article>
-  <front>
-    <article-meta>
-    </article-meta>
-  </front>
-  <body>
-  </body>
-</article>"#;
-        let extractor = JatsExtractor::new();
-        let config = ExtractionConfig::default();
-        let result = extractor
-            .extract_bytes(jats_content.as_bytes(), "application/x-jats+xml", &config)
-            .await;
-        assert!(result.is_ok());
-        let extraction = result.unwrap();
-        assert!(extraction.content.is_empty() || extraction.content.trim().is_empty());
-    }
-    /// Test MIME type support
-    #[test]
-    fn test_jats_supported_mime_types() {
-        let extractor = JatsExtractor::new();
-        let mime_types = extractor.supported_mime_types();
-        assert!(mime_types.contains(&"application/x-jats+xml"));
-        assert!(mime_types.contains(&"text/jats"));
-    }
-    /// Test extractor priority value
-    #[test]
-    fn test_jats_extractor_priority() {
-        let extractor = JatsExtractor::new();
-        assert_eq!(extractor.priority(), 50);
-    }
-    /// Test plugin interface compliance
-    #[test]
-    fn test_jats_plugin_interface() {
-        let extractor = JatsExtractor::new();
-        assert_eq!(extractor.name(), "jats-extractor");
-        assert!(!extractor.version().is_empty());
-        assert!(extractor.initialize().is_ok());
-        assert!(extractor.shutdown().is_ok());
-    }
-    /// Test mixed content with tables and paragraphs
-    #[tokio::test]
-    async fn test_extract_mixed_content() {
-        let jats_content = r#"<?xml version="1.0" encoding="UTF-8"?>
-<article>
-  <front>
-    <article-meta>
-      <article-title>Mixed Content</article-title>
-    </article-meta>
-  </front>
-  <body>
-    <sec id="s1">
-      <title>Analysis</title>
-      <p>First paragraph with data.</p>
-      <table-wrap id="tbl1">
-        <table>
-          <thead>
-            <tr><th>Data</th><th>Value</th></tr>
-          </thead>
-          <tbody>
-            <tr><td>Sample</td><td>100</td></tr>
-          </tbody>
-        </table>
-      </table-wrap>
-      <p>Second paragraph after table.</p>
-    </sec>
-  </body>
-</article>"#;
-        let extractor = JatsExtractor::new();
-        let config = ExtractionConfig::default();
-        let result = extractor
-            .extract_bytes(jats_content.as_bytes(), "application/x-jats+xml", &config)
-            .await;
-        assert!(result.is_ok());
-        let extraction = result.unwrap();
-        assert!(extraction.content.contains("First paragraph"));
-        assert!(extraction.content.contains("Second paragraph"));
-        assert_eq!(extraction.tables.len(), 1);
-    }
-    /// Test extraction with multiple keyword groups
-    #[tokio::test]
-    async fn test_extract_multiple_keywords() {
-        let jats_content = r#"<?xml version="1.0" encoding="UTF-8"?>
-<article>
-  <front>
-    <article-meta>
-      <article-title>Keyword Test</article-title>
-      <kwd-group xml:lang="en">
-        <kwd>primary keyword</kwd>
-        <kwd>secondary keyword</kwd>
-      </kwd-group>
-      <kwd-group xml:lang="es">
-        <kwd>palabra clave</kwd>
-      </kwd-group>
-    </article-meta>
-  </front>
-</article>"#;
-        let extractor = JatsExtractor::new();
-        let config = ExtractionConfig::default();
-        let result = extractor
-            .extract_bytes(jats_content.as_bytes(), "application/x-jats+xml", &config)
-            .await;
-        assert!(result.is_ok());
-        let extraction = result.unwrap();
-        let subject = extraction.metadata.subject.unwrap();
-        assert!(subject.contains("keyword") || subject.contains("Keyword"));
-    }
-    /// Test full extraction workflow on file
-    #[tokio::test]
-    async fn test_extract_jats_file() {
-        let extractor = JatsExtractor::new();
-        let config = ExtractionConfig::default();
-        let test_file = jats_fixture("sample_article.jats");
-        if test_file.exists() {
-            let result = extractor
-                .extract_file(&test_file, "application/x-jats+xml", &config)
-                .await;
-            assert!(result.is_ok());
-            let extraction = result.unwrap();
-            assert!(!extraction.content.is_empty());
-            assert!(extraction.metadata.subject.is_some());
-        }
-    }
-}