RubyGems - kreuzberg - Versions diffs - 4.0.0.pre.rc.6 - Mend

kreuzberg 4.0.0.pre.rc.6

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 (330) hide show

checksums.yaml +7 -0
data/.gitignore +14 -0
data/.rspec +3 -0
data/.rubocop.yaml +1 -0
data/.rubocop.yml +538 -0
data/Gemfile +8 -0
data/Gemfile.lock +157 -0
data/README.md +426 -0
data/Rakefile +25 -0
data/Steepfile +47 -0
data/examples/async_patterns.rb +341 -0
data/ext/kreuzberg_rb/extconf.rb +45 -0
data/ext/kreuzberg_rb/native/Cargo.lock +6535 -0
data/ext/kreuzberg_rb/native/Cargo.toml +44 -0
data/ext/kreuzberg_rb/native/README.md +425 -0
data/ext/kreuzberg_rb/native/build.rs +15 -0
data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -0
data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -0
data/ext/kreuzberg_rb/native/include/strings.h +20 -0
data/ext/kreuzberg_rb/native/include/unistd.h +47 -0
data/ext/kreuzberg_rb/native/src/lib.rs +2998 -0
data/extconf.rb +28 -0
data/kreuzberg.gemspec +148 -0
data/lib/kreuzberg/api_proxy.rb +142 -0
data/lib/kreuzberg/cache_api.rb +46 -0
data/lib/kreuzberg/cli.rb +55 -0
data/lib/kreuzberg/cli_proxy.rb +127 -0
data/lib/kreuzberg/config.rb +691 -0
data/lib/kreuzberg/error_context.rb +32 -0
data/lib/kreuzberg/errors.rb +118 -0
data/lib/kreuzberg/extraction_api.rb +85 -0
data/lib/kreuzberg/mcp_proxy.rb +186 -0
data/lib/kreuzberg/ocr_backend_protocol.rb +113 -0
data/lib/kreuzberg/post_processor_protocol.rb +86 -0
data/lib/kreuzberg/result.rb +216 -0
data/lib/kreuzberg/setup_lib_path.rb +80 -0
data/lib/kreuzberg/validator_protocol.rb +89 -0
data/lib/kreuzberg/version.rb +5 -0
data/lib/kreuzberg.rb +103 -0
data/sig/kreuzberg/internal.rbs +184 -0
data/sig/kreuzberg.rbs +520 -0
data/spec/binding/cache_spec.rb +227 -0
data/spec/binding/cli_proxy_spec.rb +85 -0
data/spec/binding/cli_spec.rb +55 -0
data/spec/binding/config_spec.rb +345 -0
data/spec/binding/config_validation_spec.rb +283 -0
data/spec/binding/error_handling_spec.rb +213 -0
data/spec/binding/errors_spec.rb +66 -0
data/spec/binding/plugins/ocr_backend_spec.rb +307 -0
data/spec/binding/plugins/postprocessor_spec.rb +269 -0
data/spec/binding/plugins/validator_spec.rb +274 -0
data/spec/fixtures/config.toml +39 -0
data/spec/fixtures/config.yaml +41 -0
data/spec/fixtures/invalid_config.toml +4 -0
data/spec/smoke/package_spec.rb +178 -0
data/spec/spec_helper.rb +42 -0
data/vendor/kreuzberg/Cargo.toml +204 -0
data/vendor/kreuzberg/README.md +175 -0
data/vendor/kreuzberg/benches/otel_overhead.rs +48 -0
data/vendor/kreuzberg/build.rs +474 -0
data/vendor/kreuzberg/src/api/error.rs +81 -0
data/vendor/kreuzberg/src/api/handlers.rs +199 -0
data/vendor/kreuzberg/src/api/mod.rs +79 -0
data/vendor/kreuzberg/src/api/server.rs +353 -0
data/vendor/kreuzberg/src/api/types.rs +170 -0
data/vendor/kreuzberg/src/cache/mod.rs +1167 -0
data/vendor/kreuzberg/src/chunking/mod.rs +677 -0
data/vendor/kreuzberg/src/core/batch_mode.rs +95 -0
data/vendor/kreuzberg/src/core/config.rs +1032 -0
data/vendor/kreuzberg/src/core/extractor.rs +1024 -0
data/vendor/kreuzberg/src/core/io.rs +329 -0
data/vendor/kreuzberg/src/core/mime.rs +605 -0
data/vendor/kreuzberg/src/core/mod.rs +45 -0
data/vendor/kreuzberg/src/core/pipeline.rs +984 -0
data/vendor/kreuzberg/src/embeddings.rs +432 -0
data/vendor/kreuzberg/src/error.rs +431 -0
data/vendor/kreuzberg/src/extraction/archive.rs +954 -0
data/vendor/kreuzberg/src/extraction/docx.rs +40 -0
data/vendor/kreuzberg/src/extraction/email.rs +854 -0
data/vendor/kreuzberg/src/extraction/excel.rs +688 -0
data/vendor/kreuzberg/src/extraction/html.rs +553 -0
data/vendor/kreuzberg/src/extraction/image.rs +368 -0
data/vendor/kreuzberg/src/extraction/libreoffice.rs +563 -0
data/vendor/kreuzberg/src/extraction/markdown.rs +213 -0
data/vendor/kreuzberg/src/extraction/mod.rs +81 -0
data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -0
data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -0
data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -0
data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -0
data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +287 -0
data/vendor/kreuzberg/src/extraction/pptx.rs +3000 -0
data/vendor/kreuzberg/src/extraction/structured.rs +490 -0
data/vendor/kreuzberg/src/extraction/table.rs +328 -0
data/vendor/kreuzberg/src/extraction/text.rs +269 -0
data/vendor/kreuzberg/src/extraction/xml.rs +333 -0
data/vendor/kreuzberg/src/extractors/archive.rs +446 -0
data/vendor/kreuzberg/src/extractors/bibtex.rs +469 -0
data/vendor/kreuzberg/src/extractors/docbook.rs +502 -0
data/vendor/kreuzberg/src/extractors/docx.rs +367 -0
data/vendor/kreuzberg/src/extractors/email.rs +143 -0
data/vendor/kreuzberg/src/extractors/epub.rs +707 -0
data/vendor/kreuzberg/src/extractors/excel.rs +343 -0
data/vendor/kreuzberg/src/extractors/fictionbook.rs +491 -0
data/vendor/kreuzberg/src/extractors/fictionbook.rs.backup2 +738 -0
data/vendor/kreuzberg/src/extractors/html.rs +393 -0
data/vendor/kreuzberg/src/extractors/image.rs +198 -0
data/vendor/kreuzberg/src/extractors/jats.rs +1051 -0
data/vendor/kreuzberg/src/extractors/jupyter.rs +367 -0
data/vendor/kreuzberg/src/extractors/latex.rs +652 -0
data/vendor/kreuzberg/src/extractors/markdown.rs +700 -0
data/vendor/kreuzberg/src/extractors/mod.rs +365 -0
data/vendor/kreuzberg/src/extractors/odt.rs +628 -0
data/vendor/kreuzberg/src/extractors/opml.rs +634 -0
data/vendor/kreuzberg/src/extractors/orgmode.rs +528 -0
data/vendor/kreuzberg/src/extractors/pdf.rs +493 -0
data/vendor/kreuzberg/src/extractors/pptx.rs +248 -0
data/vendor/kreuzberg/src/extractors/rst.rs +576 -0
data/vendor/kreuzberg/src/extractors/rtf.rs +810 -0
data/vendor/kreuzberg/src/extractors/security.rs +484 -0
data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -0
data/vendor/kreuzberg/src/extractors/structured.rs +140 -0
data/vendor/kreuzberg/src/extractors/text.rs +260 -0
data/vendor/kreuzberg/src/extractors/typst.rs +650 -0
data/vendor/kreuzberg/src/extractors/xml.rs +135 -0
data/vendor/kreuzberg/src/image/dpi.rs +164 -0
data/vendor/kreuzberg/src/image/mod.rs +6 -0
data/vendor/kreuzberg/src/image/preprocessing.rs +417 -0
data/vendor/kreuzberg/src/image/resize.rs +89 -0
data/vendor/kreuzberg/src/keywords/config.rs +154 -0
data/vendor/kreuzberg/src/keywords/mod.rs +237 -0
data/vendor/kreuzberg/src/keywords/processor.rs +267 -0
data/vendor/kreuzberg/src/keywords/rake.rs +293 -0
data/vendor/kreuzberg/src/keywords/types.rs +68 -0
data/vendor/kreuzberg/src/keywords/yake.rs +163 -0
data/vendor/kreuzberg/src/language_detection/mod.rs +942 -0
data/vendor/kreuzberg/src/lib.rs +105 -0
data/vendor/kreuzberg/src/mcp/mod.rs +32 -0
data/vendor/kreuzberg/src/mcp/server.rs +1968 -0
data/vendor/kreuzberg/src/ocr/cache.rs +469 -0
data/vendor/kreuzberg/src/ocr/error.rs +37 -0
data/vendor/kreuzberg/src/ocr/hocr.rs +216 -0
data/vendor/kreuzberg/src/ocr/mod.rs +58 -0
data/vendor/kreuzberg/src/ocr/processor.rs +863 -0
data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -0
data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -0
data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +450 -0
data/vendor/kreuzberg/src/ocr/types.rs +393 -0
data/vendor/kreuzberg/src/ocr/utils.rs +47 -0
data/vendor/kreuzberg/src/ocr/validation.rs +206 -0
data/vendor/kreuzberg/src/panic_context.rs +154 -0
data/vendor/kreuzberg/src/pdf/error.rs +122 -0
data/vendor/kreuzberg/src/pdf/images.rs +139 -0
data/vendor/kreuzberg/src/pdf/metadata.rs +346 -0
data/vendor/kreuzberg/src/pdf/mod.rs +50 -0
data/vendor/kreuzberg/src/pdf/rendering.rs +369 -0
data/vendor/kreuzberg/src/pdf/table.rs +393 -0
data/vendor/kreuzberg/src/pdf/text.rs +158 -0
data/vendor/kreuzberg/src/plugins/extractor.rs +1013 -0
data/vendor/kreuzberg/src/plugins/mod.rs +209 -0
data/vendor/kreuzberg/src/plugins/ocr.rs +620 -0
data/vendor/kreuzberg/src/plugins/processor.rs +642 -0
data/vendor/kreuzberg/src/plugins/registry.rs +1337 -0
data/vendor/kreuzberg/src/plugins/traits.rs +258 -0
data/vendor/kreuzberg/src/plugins/validator.rs +956 -0
data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -0
data/vendor/kreuzberg/src/text/mod.rs +19 -0
data/vendor/kreuzberg/src/text/quality.rs +697 -0
data/vendor/kreuzberg/src/text/string_utils.rs +217 -0
data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -0
data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -0
data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -0
data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -0
data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -0
data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -0
data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -0
data/vendor/kreuzberg/src/types.rs +903 -0
data/vendor/kreuzberg/src/utils/mod.rs +17 -0
data/vendor/kreuzberg/src/utils/quality.rs +959 -0
data/vendor/kreuzberg/src/utils/string_utils.rs +381 -0
data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -0
data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -0
data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -0
data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -0
data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -0
data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -0
data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -0
data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -0
data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -0
data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -0
data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -0
data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -0
data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -0
data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -0
data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -0
data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -0
data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -0
data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -0
data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -0
data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -0
data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -0
data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -0
data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -0
data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -0
data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -0
data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -0
data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -0
data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -0
data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -0
data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -0
data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -0
data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -0
data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -0
data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -0
data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -0
data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -0
data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -0
data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -0
data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -0
data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -0
data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -0
data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -0
data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -0
data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -0
data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -0
data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -0
data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -0
data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -0
data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -0
data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -0
data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -0
data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -0
data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -0
data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -0
data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -0
data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -0
data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -0
data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -0
data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -0
data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -0
data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -0
data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -0
data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -0
data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -0
data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -0
data/vendor/kreuzberg/tests/api_tests.rs +966 -0
data/vendor/kreuzberg/tests/archive_integration.rs +543 -0
data/vendor/kreuzberg/tests/batch_orchestration.rs +556 -0
data/vendor/kreuzberg/tests/batch_processing.rs +316 -0
data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -0
data/vendor/kreuzberg/tests/concurrency_stress.rs +525 -0
data/vendor/kreuzberg/tests/config_features.rs +598 -0
data/vendor/kreuzberg/tests/config_loading_tests.rs +415 -0
data/vendor/kreuzberg/tests/core_integration.rs +510 -0
data/vendor/kreuzberg/tests/csv_integration.rs +414 -0
data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +498 -0
data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -0
data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -0
data/vendor/kreuzberg/tests/email_integration.rs +325 -0
data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -0
data/vendor/kreuzberg/tests/error_handling.rs +393 -0
data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -0
data/vendor/kreuzberg/tests/format_integration.rs +159 -0
data/vendor/kreuzberg/tests/helpers/mod.rs +142 -0
data/vendor/kreuzberg/tests/html_table_test.rs +551 -0
data/vendor/kreuzberg/tests/image_integration.rs +253 -0
data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -0
data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -0
data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -0
data/vendor/kreuzberg/tests/keywords_integration.rs +479 -0
data/vendor/kreuzberg/tests/keywords_quality.rs +509 -0
data/vendor/kreuzberg/tests/latex_extractor_tests.rs +496 -0
data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -0
data/vendor/kreuzberg/tests/mime_detection.rs +428 -0
data/vendor/kreuzberg/tests/ocr_configuration.rs +510 -0
data/vendor/kreuzberg/tests/ocr_errors.rs +676 -0
data/vendor/kreuzberg/tests/ocr_quality.rs +627 -0
data/vendor/kreuzberg/tests/ocr_stress.rs +469 -0
data/vendor/kreuzberg/tests/odt_extractor_tests.rs +695 -0
data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -0
data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -0
data/vendor/kreuzberg/tests/pdf_integration.rs +43 -0
data/vendor/kreuzberg/tests/pipeline_integration.rs +1411 -0
data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +771 -0
data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +560 -0
data/vendor/kreuzberg/tests/plugin_system.rs +921 -0
data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -0
data/vendor/kreuzberg/tests/registry_integration_tests.rs +586 -0
data/vendor/kreuzberg/tests/rst_extractor_tests.rs +692 -0
data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +776 -0
data/vendor/kreuzberg/tests/security_validation.rs +415 -0
data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -0
data/vendor/kreuzberg/tests/test_fastembed.rs +609 -0
data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1259 -0
data/vendor/kreuzberg/tests/typst_extractor_tests.rs +647 -0
data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -0
data/vendor/rb-sys/.cargo-ok +1 -0
data/vendor/rb-sys/.cargo_vcs_info.json +6 -0
data/vendor/rb-sys/Cargo.lock +393 -0
data/vendor/rb-sys/Cargo.toml +70 -0
data/vendor/rb-sys/Cargo.toml.orig +57 -0
data/vendor/rb-sys/LICENSE-APACHE +190 -0
data/vendor/rb-sys/LICENSE-MIT +21 -0
data/vendor/rb-sys/bin/release.sh +21 -0
data/vendor/rb-sys/build/features.rs +108 -0
data/vendor/rb-sys/build/main.rs +246 -0
data/vendor/rb-sys/build/stable_api_config.rs +153 -0
data/vendor/rb-sys/build/version.rs +48 -0
data/vendor/rb-sys/readme.md +36 -0
data/vendor/rb-sys/src/bindings.rs +21 -0
data/vendor/rb-sys/src/hidden.rs +11 -0
data/vendor/rb-sys/src/lib.rs +34 -0
data/vendor/rb-sys/src/macros.rs +371 -0
data/vendor/rb-sys/src/memory.rs +53 -0
data/vendor/rb-sys/src/ruby_abi_version.rs +38 -0
data/vendor/rb-sys/src/special_consts.rs +31 -0
data/vendor/rb-sys/src/stable_api/compiled.c +179 -0
data/vendor/rb-sys/src/stable_api/compiled.rs +257 -0
data/vendor/rb-sys/src/stable_api/ruby_2_6.rs +316 -0
data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +316 -0
data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +324 -0
data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +317 -0
data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +315 -0
data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +326 -0
data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +327 -0
data/vendor/rb-sys/src/stable_api.rs +261 -0
data/vendor/rb-sys/src/symbol.rs +31 -0
data/vendor/rb-sys/src/tracking_allocator.rs +332 -0
data/vendor/rb-sys/src/utils.rs +89 -0
data/vendor/rb-sys/src/value_type.rs +7 -0
metadata +536 -0

data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs ADDED Viewed

@@ -0,0 +1,87 @@
+//! End-to-end integration test for XLSX metadata extraction
+#![cfg(feature = "excel")]
+use kreuzberg::extraction::excel::read_excel_file;
+#[test]
+fn test_xlsx_full_metadata_extraction() {
+    let workspace_root = std::path::Path::new(env!("CARGO_MANIFEST_DIR"))
+        .parent()
+        .unwrap()
+        .parent()
+        .unwrap();
+    let test_file = workspace_root.join("test_documents/office/excel.xlsx");
+    if !test_file.exists() {
+        println!("Skipping test: Test file not found at {:?}", test_file);
+        return;
+    }
+    let result = read_excel_file(test_file.to_str().unwrap()).expect("Should extract XLSX successfully");
+    assert!(!result.sheets.is_empty(), "Should have at least one sheet");
+    assert!(result.metadata.contains_key("sheet_count"), "Should have sheet count");
+    println!("✅ XLSX metadata extraction test passed!");
+    println!("   Found {} metadata fields", result.metadata.len());
+    for (key, value) in &result.metadata {
+        println!("   {}: {}", key, value);
+    }
+}
+#[test]
+fn test_xlsx_multi_sheet_metadata() {
+    let workspace_root = std::path::Path::new(env!("CARGO_MANIFEST_DIR"))
+        .parent()
+        .unwrap()
+        .parent()
+        .unwrap();
+    let test_file = workspace_root.join("test_documents/spreadsheets/excel_multi_sheet.xlsx");
+    if !test_file.exists() {
+        println!("Skipping test: Test file not found at {:?}", test_file);
+        return;
+    }
+    let result = read_excel_file(test_file.to_str().unwrap()).expect("Should extract multi-sheet XLSX successfully");
+    assert!(
+        result.sheets.len() > 1,
+        "Should have multiple sheets, got {}",
+        result.sheets.len()
+    );
+    assert!(
+        result.metadata.contains_key("sheet_names"),
+        "Should have sheet_names metadata"
+    );
+    println!("✅ XLSX multi-sheet metadata extraction test passed!");
+    println!("   Found {} sheets", result.sheets.len());
+}
+#[test]
+fn test_xlsx_minimal_metadata_extraction() {
+    let workspace_root = std::path::Path::new(env!("CARGO_MANIFEST_DIR"))
+        .parent()
+        .unwrap()
+        .parent()
+        .unwrap();
+    let test_file = workspace_root.join("test_documents/spreadsheets/test_01.xlsx");
+    if !test_file.exists() {
+        println!("Skipping test: Test file not found at {:?}", test_file);
+        return;
+    }
+    let result = read_excel_file(test_file.to_str().unwrap()).expect("Should extract XLSX successfully");
+    assert!(!result.sheets.is_empty(), "Content should not be empty");
+    assert!(
+        result.metadata.contains_key("sheet_count"),
+        "Should have basic sheet metadata"
+    );
+    println!("✅ XLSX minimal metadata extraction test passed!");
+}

data/vendor/rb-sys/.cargo-ok ADDED Viewed

	@@ -0,0 +1 @@
1	+ {"v":1}

data/vendor/rb-sys/.cargo_vcs_info.json ADDED Viewed

@@ -0,0 +1,6 @@
+{
+  "git": {
+    "sha1": "99078677bdd36b9e84828518792e13e8e8e5c114"
+  },
+  "path_in_vcs": "crates/rb-sys"
+}

data/vendor/rb-sys/Cargo.lock ADDED Viewed

@@ -0,0 +1,393 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 3
+[[package]]
+name = "aho-corasick"
+version = "1.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e60d3430d3a69478ad0993f19238d2df97c507009a52b3c10addcd7f6bcb916"
+dependencies = [
+ "memchr",
+]
+[[package]]
+name = "bindgen"
+version = "0.69.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a00dc851838a2120612785d195287475a3ac45514741da670b735818822129a0"
+dependencies = [
+ "bitflags",
+ "cexpr",
+ "clang-sys",
+ "itertools",
+ "lazy_static",
+ "lazycell",
+ "proc-macro2",
+ "quote",
+ "regex",
+ "rustc-hash",
+ "shlex",
+ "syn",
+]
+[[package]]
+name = "bitflags"
+version = "2.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b048fb63fd8b5923fc5aa7b340d8e156aec7ec02f0c78fa8a6ddc2613f6f71de"
+[[package]]
+name = "cexpr"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6fac387a98bb7c37292057cffc56d62ecb629900026402633ae9160df93a8766"
+dependencies = [
+ "nom",
+]
+[[package]]
+name = "cfg-if"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
+[[package]]
+name = "clang-sys"
+version = "1.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b023947811758c97c59bf9d1c188fd619ad4718dcaa767947df1cadb14f39f4"
+dependencies = [
+ "glob",
+ "libc",
+ "libloading",
+]
+[[package]]
+name = "either"
+version = "1.13.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "60b1af1c220855b6ceac025d3f6ecdd2b7c4894bfe9cd9bda4fbb4bc7c0d4cf0"
+[[package]]
+name = "errno"
+version = "0.3.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "534c5cf6194dfab3db3242765c03bbe257cf92f22b38f6bc0c58d59108a820ba"
+dependencies = [
+ "libc",
+ "windows-sys",
+]
+[[package]]
+name = "fastrand"
+version = "2.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9fc0510504f03c51ada170672ac806f1f105a88aa97a5281117e1ddc3368e51a"
+[[package]]
+name = "fnv"
+version = "1.0.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
+[[package]]
+name = "glob"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d2fabcfbdc87f4758337ca535fb41a6d701b65693ce38287d856d1674551ec9b"
+[[package]]
+name = "itertools"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba291022dbbd398a455acf126c1e341954079855bc60dfdda641363bd6922569"
+dependencies = [
+ "either",
+]
+[[package]]
+name = "lazy_static"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
+[[package]]
+name = "lazycell"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "830d08ce1d1d941e6b30645f1a0eb5643013d835ce3779a5fc208261dbe10f55"
+[[package]]
+name = "libc"
+version = "0.2.155"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "97b3888a4aecf77e811145cadf6eef5901f4782c53886191b2f693f24761847c"
+[[package]]
+name = "libloading"
+version = "0.8.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4979f22fdb869068da03c9f7528f8297c6fd2606bc3a4affe42e6a823fdb8da4"
+dependencies = [
+ "cfg-if",
+ "windows-targets",
+]
+[[package]]
+name = "linux-raw-sys"
+version = "0.4.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "78b3ae25bc7c8c38cec158d1f2757ee79e9b3740fbc7ccf0e59e4b08d793fa89"
+[[package]]
+name = "memchr"
+version = "2.7.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3"
+[[package]]
+name = "minimal-lexical"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
+[[package]]
+name = "nom"
+version = "7.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d273983c5a657a70a3e8f2a01329822f3b8c8172b73826411a55751e404a0a4a"
+dependencies = [
+ "memchr",
+ "minimal-lexical",
+]
+[[package]]
+name = "proc-macro2"
+version = "1.0.95"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "02b3e5e68a3a1a02aad3ec490a98007cbc13c37cbe84a3cd7b8e406d76e7f778"
+dependencies = [
+ "unicode-ident",
+]
+[[package]]
+name = "quick-error"
+version = "1.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a1d01941d82fa2ab50be1e79e6714289dd7cde78eba4c074bc5a4374f650dfe0"
+[[package]]
+name = "quote"
+version = "1.0.38"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0e4dccaaaf89514f546c693ddc140f729f958c247918a13380cccc6078391acc"
+dependencies = [
+ "proc-macro2",
+]
+[[package]]
+name = "rb-sys"
+version = "0.9.117"
+dependencies = [
+ "rb-sys-build",
+ "rusty-fork",
+]
+[[package]]
+name = "rb-sys-build"
+version = "0.9.117"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ef1e9c857028f631056bcd6d88cec390c751e343ce2223ddb26d23eb4a151d59"
+dependencies = [
+ "bindgen",
+ "lazy_static",
+ "proc-macro2",
+ "quote",
+ "regex",
+ "shell-words",
+ "syn",
+]
+[[package]]
+name = "regex"
+version = "1.11.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b544ef1b4eac5dc2db33ea63606ae9ffcfac26c1416a2806ae0bf5f56b201191"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-automata",
+ "regex-syntax",
+]
+[[package]]
+name = "regex-automata"
+version = "0.4.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "368758f23274712b504848e9d5a6f010445cc8b87a7cdb4d7cbee666c1288da3"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+[[package]]
+name = "regex-syntax"
+version = "0.8.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2b15c43186be67a4fd63bee50d0303afffcef381492ebe2c5d87f324e1b8815c"
+[[package]]
+name = "rustc-hash"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
+[[package]]
+name = "rustix"
+version = "0.38.34"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "70dc5ec042f7a43c4a73241207cecc9873a06d45debb38b329f8541d85c2730f"
+dependencies = [
+ "bitflags",
+ "errno",
+ "libc",
+ "linux-raw-sys",
+ "windows-sys",
+]
+[[package]]
+name = "rusty-fork"
+version = "0.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cb3dcc6e454c328bb824492db107ab7c0ae8fcffe4ad210136ef014458c1bc4f"
+dependencies = [
+ "fnv",
+ "quick-error",
+ "tempfile",
+ "wait-timeout",
+]
+[[package]]
+name = "shell-words"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "24188a676b6ae68c3b2cb3a01be17fbf7240ce009799bb56d5b1409051e78fde"
+[[package]]
+name = "shlex"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
+[[package]]
+name = "syn"
+version = "2.0.104"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "17b6f705963418cdb9927482fa304bc562ece2fdd4f616084c50b7023b435a40"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+[[package]]
+name = "tempfile"
+version = "3.10.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "85b77fafb263dd9d05cbeac119526425676db3784113aa9295c88498cbf8bff1"
+dependencies = [
+ "cfg-if",
+ "fastrand",
+ "rustix",
+ "windows-sys",
+]
+[[package]]
+name = "unicode-ident"
+version = "1.0.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
+[[package]]
+name = "wait-timeout"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9f200f5b12eb75f8c1ed65abd4b2db8a6e1b138a20de009dacee265a2498f3f6"
+dependencies = [
+ "libc",
+]
+[[package]]
+name = "windows-sys"
+version = "0.52.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
+dependencies = [
+ "windows-targets",
+]
+[[package]]
+name = "windows-targets"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
+dependencies = [
+ "windows_aarch64_gnullvm",
+ "windows_aarch64_msvc",
+ "windows_i686_gnu",
+ "windows_i686_gnullvm",
+ "windows_i686_msvc",
+ "windows_x86_64_gnu",
+ "windows_x86_64_gnullvm",
+ "windows_x86_64_msvc",
+]
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
+[[package]]
+name = "windows_i686_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b"
+[[package]]
+name = "windows_i686_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
+[[package]]
+name = "windows_i686_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"

data/vendor/rb-sys/Cargo.toml ADDED Viewed

@@ -0,0 +1,70 @@
+# THIS FILE IS AUTOMATICALLY GENERATED BY CARGO
+#
+# When uploading crates to the registry Cargo will automatically
+# "normalize" Cargo.toml files for maximal compatibility
+# with all versions of Cargo and also rewrite `path` dependencies
+# to registry (e.g., crates.io) dependencies.
+#
+# If you are reading this file be aware that the original Cargo.toml
+# will likely look very different (and much more reasonable).
+# See Cargo.toml.orig for the original contents.
+[package]
+edition = "2018"
+rust-version = "1.65"
+name = "rb-sys"
+version = "4.0.0-rc.6"
+build = "build/main.rs"
+links = "rb"
+autolib = false
+autobins = false
+autoexamples = false
+autotests = false
+autobenches = false
+description = "Rust bindings for the CRuby API"
+homepage = "https://github.com/oxidize-rb/rb-sys"
+documentation = "https://docs.rs/rb-sys"
+readme = "readme.md"
+categories = ["external-ffi-bindings"]
+license = "MIT OR Apache-2.0"
+repository = "https://github.com/oxidize-rb/rb-sys"
+[features]
+bindgen-deprecated-types = ["rb-sys-build/bindgen-deprecated-types"]
+bindgen-enable-function-attribute-detection = ["rb-sys-build/bindgen-enable-function-attribute-detection"]
+bindgen-impl-debug = ["rb-sys-build/bindgen-impl-debug"]
+bindgen-layout-tests = ["rb-sys-build/bindgen-layout-tests"]
+bindgen-rbimpls = ["rb-sys-build/bindgen-rbimpls"]
+bindgen-return-const-encoding-pointers = ["rb-sys-build/bindgen-return-const-encoding-pointers"]
+bindgen-sizet-is-usize = ["rb-sys-build/bindgen-sizet-is-usize"]
+default = ["stable-api-compiled-fallback"]
+fuzz = []
+global-allocator = []
+link-ruby = []
+no-link-ruby = []
+ruby-macros = ["stable-api"]
+ruby-static = []
+stable-api = []
+stable-api-compiled-fallback = ["stable-api"]
+stable-api-compiled-force = []
+stable-api-compiled-testing = ["stable-api-compiled-fallback"]
+[lib]
+name = "rb_sys"
+path = "src/lib.rs"
+doctest = false
+[dev-dependencies.rusty-fork]
+version = "0.3.0"
+[build-dependencies.rb-sys-build]
+version = "0.9.117"
+[lints.rust.unexpected_cfgs]
+level = "warn"
+priority = 0
+check-cfg = [
+    "cfg(rb_sys_gem)",
+    "cfg(rb_sys_use_stable_api_compiled_fallback)",
+    "cfg(rb_sys_force_stable_api_compiled)",
+]

data/vendor/rb-sys/Cargo.toml.orig ADDED Viewed

@@ -0,0 +1,57 @@
+[package]
+build = "build/main.rs"
+name = "rb-sys"
+version = "0.9.117"
+edition = "2018"
+readme = "readme.md"
+categories = ["external-ffi-bindings"]
+description = "Rust bindings for the CRuby API"
+documentation = "https://docs.rs/rb-sys"
+homepage = "https://github.com/oxidize-rb/rb-sys"
+license = "MIT OR Apache-2.0"
+links = "rb"
+repository = "https://github.com/oxidize-rb/rb-sys"
+rust-version = "1.65"
+[build-dependencies]
+rb-sys-build = { version = "0.9.117", path = "../rb-sys-build" }
+[dev-dependencies]
+rb-sys = { path = ".", features = ["link-ruby"] }
+rusty-fork = "0.3.0"
+[features]
+default = ["stable-api-compiled-fallback"]
+link-ruby = []
+fuzz = []
+no-link-ruby = []
+ruby-static = []
+global-allocator = []
+stable-api = []
+stable-api-compiled-fallback = ["stable-api"] # Fallback to compiled C API
+stable-api-compiled-testing = [
+  "stable-api-compiled-fallback",
+] # For testing the fallback in rb-sys (internal)
+stable-api-compiled-force = [] # Always use the compiled C API
+ruby-macros = ["stable-api"] # deprecated
+bindgen-rbimpls = ["rb-sys-build/bindgen-rbimpls"]
+bindgen-deprecated-types = ["rb-sys-build/bindgen-deprecated-types"]
+bindgen-layout-tests = ["rb-sys-build/bindgen-layout-tests"]
+bindgen-impl-debug = ["rb-sys-build/bindgen-impl-debug"]
+bindgen-sizet-is-usize = ["rb-sys-build/bindgen-sizet-is-usize"]
+bindgen-return-const-encoding-pointers = [
+  "rb-sys-build/bindgen-return-const-encoding-pointers",
+]
+bindgen-enable-function-attribute-detection = [
+  "rb-sys-build/bindgen-enable-function-attribute-detection",
+]
+[lib]
+doctest = false
+[lints.rust]
+unexpected_cfgs = { level = "warn", check-cfg = [
+  "cfg(rb_sys_gem)",
+  "cfg(rb_sys_use_stable_api_compiled_fallback)",
+  "cfg(rb_sys_force_stable_api_compiled)",
+] }