RubyGems - kreuzberg - Versions diffs - 4.0.0.rc1 → 4.0.0.rc2 - Mend

kreuzberg 4.0.0.rc1 → 4.0.0.rc2

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 (342) hide show

checksums.yaml +4 -4
data/.gitignore +14 -8
data/.rspec +3 -3
data/.rubocop.yaml +1 -534
data/.rubocop.yml +538 -0
data/Gemfile +8 -9
data/Gemfile.lock +9 -109
data/README.md +426 -421
data/Rakefile +25 -25
data/Steepfile +47 -47
data/examples/async_patterns.rb +341 -340
data/ext/kreuzberg_rb/extconf.rb +45 -35
data/ext/kreuzberg_rb/native/Cargo.lock +6535 -0
data/ext/kreuzberg_rb/native/Cargo.toml +44 -36
data/ext/kreuzberg_rb/native/README.md +425 -425
data/ext/kreuzberg_rb/native/build.rs +15 -17
data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -11
data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -14
data/ext/kreuzberg_rb/native/include/strings.h +20 -20
data/ext/kreuzberg_rb/native/include/unistd.h +47 -47
data/ext/kreuzberg_rb/native/src/lib.rs +2998 -2939
data/extconf.rb +28 -28
data/kreuzberg.gemspec +148 -105
data/lib/kreuzberg/api_proxy.rb +142 -142
data/lib/kreuzberg/cache_api.rb +46 -45
data/lib/kreuzberg/cli.rb +55 -55
data/lib/kreuzberg/cli_proxy.rb +127 -127
data/lib/kreuzberg/config.rb +691 -684
data/lib/kreuzberg/error_context.rb +32 -0
data/lib/kreuzberg/errors.rb +118 -50
data/lib/kreuzberg/extraction_api.rb +85 -84
data/lib/kreuzberg/mcp_proxy.rb +186 -186
data/lib/kreuzberg/ocr_backend_protocol.rb +113 -113
data/lib/kreuzberg/post_processor_protocol.rb +86 -86
data/lib/kreuzberg/result.rb +216 -216
data/lib/kreuzberg/setup_lib_path.rb +80 -79
data/lib/kreuzberg/validator_protocol.rb +89 -89
data/lib/kreuzberg/version.rb +5 -5
data/lib/kreuzberg.rb +103 -82
data/sig/kreuzberg/internal.rbs +184 -184
data/sig/kreuzberg.rbs +520 -468
data/spec/binding/cache_spec.rb +227 -227
data/spec/binding/cli_proxy_spec.rb +85 -87
data/spec/binding/cli_spec.rb +55 -54
data/spec/binding/config_spec.rb +345 -345
data/spec/binding/config_validation_spec.rb +283 -283
data/spec/binding/error_handling_spec.rb +213 -213
data/spec/binding/errors_spec.rb +66 -66
data/spec/binding/plugins/ocr_backend_spec.rb +307 -307
data/spec/binding/plugins/postprocessor_spec.rb +269 -269
data/spec/binding/plugins/validator_spec.rb +274 -274
data/spec/fixtures/config.toml +39 -39
data/spec/fixtures/config.yaml +41 -42
data/spec/fixtures/invalid_config.toml +4 -4
data/spec/smoke/package_spec.rb +178 -178
data/spec/spec_helper.rb +42 -42
data/vendor/kreuzberg/Cargo.toml +204 -134
data/vendor/kreuzberg/README.md +175 -175
data/vendor/kreuzberg/benches/otel_overhead.rs +48 -0
data/vendor/kreuzberg/build.rs +474 -460
data/vendor/kreuzberg/src/api/error.rs +81 -81
data/vendor/kreuzberg/src/api/handlers.rs +199 -199
data/vendor/kreuzberg/src/api/mod.rs +79 -79
data/vendor/kreuzberg/src/api/server.rs +353 -353
data/vendor/kreuzberg/src/api/types.rs +170 -170
data/vendor/kreuzberg/src/cache/mod.rs +1167 -1143
data/vendor/kreuzberg/src/chunking/mod.rs +677 -677
data/vendor/kreuzberg/src/core/batch_mode.rs +95 -35
data/vendor/kreuzberg/src/core/config.rs +1032 -1032
data/vendor/kreuzberg/src/core/extractor.rs +1024 -903
data/vendor/kreuzberg/src/core/io.rs +329 -327
data/vendor/kreuzberg/src/core/mime.rs +605 -615
data/vendor/kreuzberg/src/core/mod.rs +45 -42
data/vendor/kreuzberg/src/core/pipeline.rs +984 -906
data/vendor/kreuzberg/src/embeddings.rs +432 -323
data/vendor/kreuzberg/src/error.rs +431 -431
data/vendor/kreuzberg/src/extraction/archive.rs +954 -954
data/vendor/kreuzberg/src/extraction/docx.rs +40 -40
data/vendor/kreuzberg/src/extraction/email.rs +854 -854
data/vendor/kreuzberg/src/extraction/excel.rs +688 -688
data/vendor/kreuzberg/src/extraction/html.rs +553 -553
data/vendor/kreuzberg/src/extraction/image.rs +368 -368
data/vendor/kreuzberg/src/extraction/libreoffice.rs +563 -564
data/vendor/kreuzberg/src/extraction/markdown.rs +213 -0
data/vendor/kreuzberg/src/extraction/mod.rs +81 -77
data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -398
data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -247
data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -240
data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -128
data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +287 -0
data/vendor/kreuzberg/src/extraction/pptx.rs +3000 -3000
data/vendor/kreuzberg/src/extraction/structured.rs +490 -490
data/vendor/kreuzberg/src/extraction/table.rs +328 -328
data/vendor/kreuzberg/src/extraction/text.rs +269 -269
data/vendor/kreuzberg/src/extraction/xml.rs +333 -333
data/vendor/kreuzberg/src/extractors/archive.rs +446 -425
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 -479
data/vendor/kreuzberg/src/extractors/email.rs +143 -129
data/vendor/kreuzberg/src/extractors/epub.rs +707 -0
data/vendor/kreuzberg/src/extractors/excel.rs +343 -344
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 -410
data/vendor/kreuzberg/src/extractors/image.rs +198 -195
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 -268
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 -496
data/vendor/kreuzberg/src/extractors/pptx.rs +248 -234
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 -126
data/vendor/kreuzberg/src/extractors/text.rs +260 -242
data/vendor/kreuzberg/src/extractors/typst.rs +650 -0
data/vendor/kreuzberg/src/extractors/xml.rs +135 -128
data/vendor/kreuzberg/src/image/dpi.rs +164 -164
data/vendor/kreuzberg/src/image/mod.rs +6 -6
data/vendor/kreuzberg/src/image/preprocessing.rs +417 -417
data/vendor/kreuzberg/src/image/resize.rs +89 -89
data/vendor/kreuzberg/src/keywords/config.rs +154 -154
data/vendor/kreuzberg/src/keywords/mod.rs +237 -237
data/vendor/kreuzberg/src/keywords/processor.rs +267 -267
data/vendor/kreuzberg/src/keywords/rake.rs +293 -294
data/vendor/kreuzberg/src/keywords/types.rs +68 -68
data/vendor/kreuzberg/src/keywords/yake.rs +163 -163
data/vendor/kreuzberg/src/language_detection/mod.rs +942 -942
data/vendor/kreuzberg/src/lib.rs +105 -102
data/vendor/kreuzberg/src/mcp/mod.rs +32 -32
data/vendor/kreuzberg/src/mcp/server.rs +1968 -1966
data/vendor/kreuzberg/src/ocr/cache.rs +469 -469
data/vendor/kreuzberg/src/ocr/error.rs +37 -37
data/vendor/kreuzberg/src/ocr/hocr.rs +216 -216
data/vendor/kreuzberg/src/ocr/mod.rs +58 -58
data/vendor/kreuzberg/src/ocr/processor.rs +863 -847
data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -4
data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -144
data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +450 -450
data/vendor/kreuzberg/src/ocr/types.rs +393 -393
data/vendor/kreuzberg/src/ocr/utils.rs +47 -47
data/vendor/kreuzberg/src/ocr/validation.rs +206 -206
data/vendor/kreuzberg/src/panic_context.rs +154 -0
data/vendor/kreuzberg/src/pdf/error.rs +122 -122
data/vendor/kreuzberg/src/pdf/images.rs +139 -139
data/vendor/kreuzberg/src/pdf/metadata.rs +346 -346
data/vendor/kreuzberg/src/pdf/mod.rs +50 -50
data/vendor/kreuzberg/src/pdf/rendering.rs +369 -369
data/vendor/kreuzberg/src/pdf/table.rs +393 -420
data/vendor/kreuzberg/src/pdf/text.rs +158 -161
data/vendor/kreuzberg/src/plugins/extractor.rs +1013 -1010
data/vendor/kreuzberg/src/plugins/mod.rs +209 -209
data/vendor/kreuzberg/src/plugins/ocr.rs +620 -629
data/vendor/kreuzberg/src/plugins/processor.rs +642 -641
data/vendor/kreuzberg/src/plugins/registry.rs +1337 -1324
data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
data/vendor/kreuzberg/src/plugins/validator.rs +956 -955
data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
data/vendor/kreuzberg/src/text/mod.rs +19 -19
data/vendor/kreuzberg/src/text/quality.rs +697 -697
data/vendor/kreuzberg/src/text/string_utils.rs +217 -217
data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -164
data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -100
data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -796
data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -902
data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -160
data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -619
data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -147
data/vendor/kreuzberg/src/types.rs +903 -873
data/vendor/kreuzberg/src/utils/mod.rs +17 -17
data/vendor/kreuzberg/src/utils/quality.rs +959 -959
data/vendor/kreuzberg/src/utils/string_utils.rs +381 -381
data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -53
data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -482
data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -261
data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -400
data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -1205
data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -280
data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -425
data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -172
data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -622
data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -849
data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -1300
data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -175
data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -734
data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -37
data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -100
data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -801
data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -849
data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -693
data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -111
data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -162
data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -226
data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -41
data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -196
data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -227
data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -181
data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -791
data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -47
data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -760
data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -634
data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -136
data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -84
data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -681
data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -64
data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -51
data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -476
data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -163
data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -1
data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -101
data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -477
data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -490
data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -415
data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -223
data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -331
data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -562
data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -436
data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -561
data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -193
data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -420
data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -448
data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -32
data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -33
data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -420
data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -76
data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -129
data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -54
data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -118
data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -149
data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -506
data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -75
data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -519
data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -647
data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -62
data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -796
data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -31
data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -0
data/vendor/kreuzberg/tests/api_tests.rs +966 -966
data/vendor/kreuzberg/tests/archive_integration.rs +543 -543
data/vendor/kreuzberg/tests/batch_orchestration.rs +556 -542
data/vendor/kreuzberg/tests/batch_processing.rs +316 -304
data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -0
data/vendor/kreuzberg/tests/concurrency_stress.rs +525 -509
data/vendor/kreuzberg/tests/config_features.rs +598 -580
data/vendor/kreuzberg/tests/config_loading_tests.rs +415 -439
data/vendor/kreuzberg/tests/core_integration.rs +510 -493
data/vendor/kreuzberg/tests/csv_integration.rs +414 -424
data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +498 -0
data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -124
data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -0
data/vendor/kreuzberg/tests/email_integration.rs +325 -325
data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -0
data/vendor/kreuzberg/tests/error_handling.rs +393 -393
data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -0
data/vendor/kreuzberg/tests/format_integration.rs +159 -159
data/vendor/kreuzberg/tests/helpers/mod.rs +142 -142
data/vendor/kreuzberg/tests/html_table_test.rs +551 -0
data/vendor/kreuzberg/tests/image_integration.rs +253 -253
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 -479
data/vendor/kreuzberg/tests/keywords_quality.rs +509 -509
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 -428
data/vendor/kreuzberg/tests/ocr_configuration.rs +510 -510
data/vendor/kreuzberg/tests/ocr_errors.rs +676 -676
data/vendor/kreuzberg/tests/ocr_quality.rs +627 -627
data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
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 -43
data/vendor/kreuzberg/tests/pipeline_integration.rs +1411 -1412
data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +771 -771
data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +560 -561
data/vendor/kreuzberg/tests/plugin_system.rs +921 -921
data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
data/vendor/kreuzberg/tests/registry_integration_tests.rs +586 -607
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 -404
data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
data/vendor/kreuzberg/tests/test_fastembed.rs +609 -609
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 -87
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 +90 -95
data/pkg/kreuzberg-4.0.0.rc1.gem +0 -0
data/spec/examples.txt +0 -104
data/vendor/kreuzberg/src/bin/profile_extract.rs +0 -455
data/vendor/kreuzberg/src/extraction/pandoc/batch.rs +0 -275
data/vendor/kreuzberg/src/extraction/pandoc/mime_types.rs +0 -178
data/vendor/kreuzberg/src/extraction/pandoc/mod.rs +0 -491
data/vendor/kreuzberg/src/extraction/pandoc/server.rs +0 -496
data/vendor/kreuzberg/src/extraction/pandoc/subprocess.rs +0 -1188
data/vendor/kreuzberg/src/extraction/pandoc/version.rs +0 -162
data/vendor/kreuzberg/src/extractors/pandoc.rs +0 -201
data/vendor/kreuzberg/tests/chunking_offset_demo.rs +0 -92
data/vendor/kreuzberg/tests/pandoc_integration.rs +0 -503

data/vendor/kreuzberg/src/extractors/opml.rs ADDED Viewed

@@ -0,0 +1,634 @@
+//! Native OPML (Outline Processor Markup Language) extractor using the `roxmltree` library.
+//!
+//! This extractor provides native Rust-based OPML extraction, parsing outline structures
+//! commonly used for RSS feed lists, podcast directories, and general outlines.
+//!
+//! Extracts:
+//! - Metadata from `<head>`: title, dateCreated, dateModified, ownerName, ownerEmail
+//! - Content from `<body><outline>` hierarchy using text attributes
+//! - Outline hierarchy structure preserved in plain text format with indentation
+//! - Note: URLs (xmlUrl, htmlUrl) are extracted from attributes but not included in main content
+//!
+//! Example OPML structure:
+//! ```xml
+//! <opml version="2.0">
+//!   <head>
+//!     <title>My Feeds</title>
+//!     <ownerName>John</ownerName>
+//!   </head>
+//!   <body>
+//!     <outline text="Tech" type="folder">
+//!       <outline text="Hacker News" type="rss" xmlUrl="https://..." />
+//!     </outline>
+//!   </body>
+//! </opml>
+//! ```
+use crate::Result;
+use crate::core::config::ExtractionConfig;
+use crate::plugins::{DocumentExtractor, Plugin};
+use crate::types::{ExtractionResult, Metadata};
+use async_trait::async_trait;
+use std::collections::HashMap;
+#[cfg(feature = "office")]
+use roxmltree::Node;
+/// OPML format extractor.
+///
+/// Extracts outline structure and metadata from OPML documents using native Rust parsing.
+pub struct OpmlExtractor;
+impl OpmlExtractor {
+    /// Create a new OPML extractor.
+    pub fn new() -> Self {
+        Self
+    }
+    /// Extract OPML content and structure
+    #[cfg(feature = "office")]
+    fn extract_content_and_metadata(content: &[u8]) -> Result<(String, HashMap<String, serde_json::Value>)> {
+        let doc = roxmltree::Document::parse(
+            std::str::from_utf8(content)
+                .map_err(|e| crate::KreuzbergError::Other(format!("Invalid UTF-8 in OPML: {}", e)))?,
+        )
+        .map_err(|e| crate::KreuzbergError::Other(format!("Failed to parse OPML: {}", e)))?;
+        let mut extracted_content = String::new();
+        let mut metadata = HashMap::new();
+        if let Some(opml) = doc.root().children().find(|n| n.tag_name().name() == "opml") {
+            if let Some(head) = opml.children().find(|n| n.tag_name().name() == "head") {
+                for child in head.children().filter(|n| n.is_element()) {
+                    let tag = child.tag_name().name();
+                    let text = child.text().unwrap_or("").trim();
+                    match tag {
+                        "title" => {
+                            if !text.is_empty() {
+                                metadata.insert("title".to_string(), serde_json::json!(text));
+                            }
+                        }
+                        "dateCreated" => {
+                            if !text.is_empty() {
+                                metadata.insert("dateCreated".to_string(), serde_json::json!(text));
+                            }
+                        }
+                        "dateModified" => {
+                            if !text.is_empty() {
+                                metadata.insert("dateModified".to_string(), serde_json::json!(text));
+                            }
+                        }
+                        "ownerName" => {
+                            if !text.is_empty() {
+                                metadata.insert("ownerName".to_string(), serde_json::json!(text));
+                            }
+                        }
+                        "ownerEmail" => {
+                            if !text.is_empty() {
+                                metadata.insert("ownerEmail".to_string(), serde_json::json!(text));
+                            }
+                        }
+                        _ => {}
+                    }
+                }
+            }
+            if let Some(body) = opml.children().find(|n| n.tag_name().name() == "body") {
+                if let Some(title) = metadata.get("title").and_then(|v| v.as_str()) {
+                    extracted_content.push_str(title);
+                    extracted_content.push('\n');
+                    extracted_content.push('\n');
+                }
+                for outline in body.children().filter(|n| n.tag_name().name() == "outline") {
+                    Self::process_outline(outline, 0, &mut extracted_content);
+                }
+            }
+        }
+        Ok((extracted_content.trim().to_string(), metadata))
+    }
+    /// Process outline elements recursively
+    ///
+    /// Extracts text content from outline hierarchy while preserving nesting depth
+    /// through indentation. URL attributes are excluded from the main content.
+    #[cfg(feature = "office")]
+    fn process_outline(node: Node, depth: usize, output: &mut String) {
+        let text = node.attribute("text").unwrap_or("").trim();
+        if !text.is_empty() {
+            let indent = "  ".repeat(depth);
+            output.push_str(&indent);
+            output.push_str(text);
+            output.push('\n');
+        }
+        for child in node.children().filter(|n| n.tag_name().name() == "outline") {
+            Self::process_outline(child, depth + 1, output);
+        }
+    }
+}
+impl Default for OpmlExtractor {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+impl Plugin for OpmlExtractor {
+    fn name(&self) -> &str {
+        "opml-extractor"
+    }
+    fn version(&self) -> String {
+        env!("CARGO_PKG_VERSION").to_string()
+    }
+    fn initialize(&self) -> Result<()> {
+        Ok(())
+    }
+    fn shutdown(&self) -> Result<()> {
+        Ok(())
+    }
+    fn description(&self) -> &str {
+        "Extracts content and metadata from OPML (Outline Processor Markup Language) documents"
+    }
+    fn author(&self) -> &str {
+        "Kreuzberg Team"
+    }
+}
+#[cfg(feature = "office")]
+#[async_trait]
+impl DocumentExtractor for OpmlExtractor {
+    #[cfg_attr(
+        feature = "otel",
+        tracing::instrument(
+            skip(self, content, _config),
+            fields(
+                extractor.name = self.name(),
+                content.size_bytes = content.len(),
+            )
+        )
+    )]
+    async fn extract_bytes(
+        &self,
+        content: &[u8],
+        mime_type: &str,
+        _config: &ExtractionConfig,
+    ) -> Result<ExtractionResult> {
+        let (extracted_content, metadata_map) = Self::extract_content_and_metadata(content)?;
+        Ok(ExtractionResult {
+            content: extracted_content,
+            mime_type: mime_type.to_string(),
+            metadata: Metadata {
+                additional: metadata_map,
+                ..Default::default()
+            },
+            tables: vec![],
+            detected_languages: None,
+            chunks: None,
+            images: None,
+        })
+    }
+    fn supported_mime_types(&self) -> &[&str] {
+        &["text/x-opml", "application/xml+opml"]
+    }
+    fn priority(&self) -> i32 {
+        55
+    }
+}
+#[cfg(all(test, feature = "office"))]
+mod tests {
+    use super::*;
+    #[test]
+    fn test_opml_extractor_plugin_interface() {
+        let extractor = OpmlExtractor::new();
+        assert_eq!(extractor.name(), "opml-extractor");
+        assert_eq!(extractor.version(), env!("CARGO_PKG_VERSION"));
+        assert_eq!(extractor.priority(), 55);
+        assert!(!extractor.supported_mime_types().is_empty());
+    }
+    #[test]
+    fn test_opml_extractor_default() {
+        let extractor = OpmlExtractor;
+        assert_eq!(extractor.name(), "opml-extractor");
+    }
+    #[tokio::test]
+    async fn test_opml_extractor_initialize_shutdown() {
+        let extractor = OpmlExtractor::new();
+        assert!(extractor.initialize().is_ok());
+        assert!(extractor.shutdown().is_ok());
+    }
+    #[test]
+    fn test_opml_simple_outline_parsing() {
+        let opml = br#"<?xml version="1.0"?>
+<opml version="2.0">
+  <head>
+    <title>Test</title>
+  </head>
+  <body>
+    <outline text="Item 1" />
+    <outline text="Item 2" />
+  </body>
+</opml>"#;
+        let (content, metadata) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should parse simple OPML");
+        assert!(content.contains("Item 1"), "Should extract first item");
+        assert!(content.contains("Item 2"), "Should extract second item");
+        assert_eq!(
+            metadata.get("title").and_then(|v| v.as_str()),
+            Some("Test"),
+            "Should extract title"
+        );
+    }
+    #[test]
+    fn test_opml_nested_hierarchy() {
+        let opml = br#"<?xml version="1.0"?>
+<opml version="2.0">
+  <head>
+    <title>Hierarchy Test</title>
+  </head>
+  <body>
+    <outline text="Category">
+      <outline text="Subcategory">
+        <outline text="Item" />
+      </outline>
+    </outline>
+  </body>
+</opml>"#;
+        let (content, _) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should parse nested OPML");
+        assert!(content.contains("Category"), "Should contain top level");
+        assert!(content.contains("Subcategory"), "Should contain nested level");
+        assert!(content.contains("Item"), "Should contain deep item");
+        assert!(content.contains("  "), "Should have indentation for nested items");
+    }
+    #[test]
+    fn test_opml_rss_feeds() {
+        let opml = br#"<?xml version="1.0"?>
+<opml version="2.0">
+  <head>
+    <title>Feeds</title>
+  </head>
+  <body>
+    <outline text="Tech">
+      <outline text="Hacker News" type="rss" xmlUrl="https://news.ycombinator.com/rss" htmlUrl="https://news.ycombinator.com/" />
+      <outline text="TechCrunch" type="rss" xmlUrl="https://techcrunch.com/feed/" />
+    </outline>
+  </body>
+</opml>"#;
+        let (content, _) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should parse RSS OPML");
+        assert!(content.contains("Hacker News"), "Should extract feed title");
+        assert!(
+            !content.contains("https://"),
+            "Should NOT extract feed URLs (text-only extraction)"
+        );
+        assert!(content.contains("TechCrunch"), "Should extract multiple feeds");
+    }
+    #[test]
+    fn test_opml_metadata_extraction() {
+        let opml = br#"<?xml version="1.0"?>
+<opml version="2.0">
+  <head>
+    <title>My Feeds</title>
+    <dateCreated>Mon, 06 Nov 2023 00:00:00 GMT</dateCreated>
+    <dateModified>Fri, 01 Dec 2023 12:00:00 GMT</dateModified>
+    <ownerName>John Doe</ownerName>
+    <ownerEmail>john@example.com</ownerEmail>
+  </head>
+  <body>
+    <outline text="Item" />
+  </body>
+</opml>"#;
+        let (_content, metadata) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should extract metadata");
+        assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("My Feeds"));
+        assert_eq!(metadata.get("ownerName").and_then(|v| v.as_str()), Some("John Doe"));
+        assert_eq!(
+            metadata.get("ownerEmail").and_then(|v| v.as_str()),
+            Some("john@example.com")
+        );
+        assert!(metadata.contains_key("dateCreated"));
+        assert!(metadata.contains_key("dateModified"));
+    }
+    #[test]
+    fn test_opml_supported_mime_types() {
+        let extractor = OpmlExtractor::new();
+        let supported = extractor.supported_mime_types();
+        assert!(supported.contains(&"text/x-opml"));
+        assert!(supported.contains(&"application/xml+opml"));
+    }
+    #[test]
+    fn test_opml_with_special_characters() {
+        let opml = br#"<?xml version="1.0"?>
+<opml version="2.0">
+  <head>
+    <title>Test &amp; Special</title>
+  </head>
+  <body>
+    <outline text="Business &amp; Startups" />
+    <outline text="Science &lt;Advanced&gt;" />
+  </body>
+</opml>"#;
+        let (content, metadata) =
+            OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle special characters");
+        assert!(
+            content.contains("Business") && content.contains("Startups"),
+            "Should decode HTML entities"
+        );
+        let title = metadata.get("title").and_then(|v| v.as_str()).unwrap_or("");
+        assert!(!title.is_empty(), "Should extract title");
+    }
+    #[test]
+    fn test_opml_empty_body() {
+        let opml = br#"<?xml version="1.0"?>
+<opml version="2.0">
+  <head>
+    <title>Empty</title>
+  </head>
+  <body>
+  </body>
+</opml>"#;
+        let (_content, metadata) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle empty body");
+        assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("Empty"));
+    }
+    #[tokio::test]
+    async fn test_opml_extractor_async_extraction() {
+        let extractor = OpmlExtractor::new();
+        let opml = br#"<?xml version="1.0"?>
+<opml version="2.0">
+  <head>
+    <title>Async Test</title>
+  </head>
+  <body>
+    <outline text="Item" />
+  </body>
+</opml>"#;
+        let result = extractor
+            .extract_bytes(opml, "text/x-opml", &ExtractionConfig::default())
+            .await
+            .expect("Should extract OPML asynchronously");
+        assert_eq!(result.mime_type, "text/x-opml");
+        assert!(result.content.contains("Item"));
+        assert_eq!(
+            result.metadata.additional.get("title").and_then(|v| v.as_str()),
+            Some("Async Test")
+        );
+    }
+    #[test]
+    fn test_opml_malformed_missing_closing_tag() {
+        let opml = br#"<?xml version="1.0"?>
+<opml version="2.0">
+  <head>
+    <title>Broken</title>
+  </head>
+  <body>
+    <outline text="Unclosed"
+  </body>
+</opml>"#;
+        let result = OpmlExtractor::extract_content_and_metadata(opml);
+        assert!(result.is_err(), "Should fail to parse OPML with missing closing tags");
+    }
+    #[test]
+    fn test_opml_malformed_invalid_nesting() {
+        let opml = br#"<?xml version="1.0"?>
+<opml version="2.0">
+  <head>
+    <title>Invalid Nesting</title>
+  <body>
+    <outline text="Item" />
+  </body>
+</opml>"#;
+        let result = OpmlExtractor::extract_content_and_metadata(opml);
+        assert!(result.is_err(), "Should fail to parse OPML with invalid nesting");
+    }
+    #[test]
+    fn test_opml_empty_outline_elements() {
+        let opml = br#"<?xml version="1.0"?>
+<opml version="2.0">
+  <head>
+    <title>Empty Outlines</title>
+  </head>
+  <body>
+    <outline text="" />
+    <outline />
+    <outline text="Valid Item">
+      <outline text="" />
+      <outline text="Another Valid" />
+    </outline>
+  </body>
+</opml>"#;
+        let (content, metadata) =
+            OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle empty outline elements");
+        assert!(content.contains("Valid Item"), "Should extract valid items");
+        assert!(content.contains("Another Valid"), "Should extract nested valid items");
+        let empty_count = content.matches("\n\n").count();
+        assert!(empty_count < 3, "Should skip empty outline elements");
+        assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("Empty Outlines"));
+    }
+    #[test]
+    fn test_opml_deeply_nested_empty_nodes() {
+        let opml = br#"<?xml version="1.0"?>
+<opml version="2.0">
+  <head>
+    <title>Deep Nesting</title>
+  </head>
+  <body>
+    <outline text="Level 1">
+      <outline text="">
+        <outline text="">
+          <outline text="Deep Item">
+            <outline text="" />
+          </outline>
+        </outline>
+      </outline>
+      <outline text="Level 1 Sibling" />
+    </outline>
+  </body>
+</opml>"#;
+        let (content, _) =
+            OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle deeply nested structures");
+        assert!(content.contains("Level 1"), "Should extract top-level item");
+        assert!(content.contains("Deep Item"), "Should extract deeply nested item");
+        assert!(content.contains("Level 1 Sibling"), "Should extract sibling items");
+    }
+    #[test]
+    fn test_opml_outline_with_missing_text_attribute() {
+        let opml = br#"<?xml version="1.0"?>
+<opml version="2.0">
+  <head>
+    <title>Missing Attributes</title>
+  </head>
+  <body>
+    <outline type="folder" />
+    <outline text="Valid Item" type="rss" />
+    <outline type="rss" xmlUrl="https://example.com/feed" />
+  </body>
+</opml>"#;
+        let (content, metadata) = OpmlExtractor::extract_content_and_metadata(opml)
+            .expect("Should handle outline with missing text attribute");
+        assert!(content.contains("Valid Item"), "Should extract item with text");
+        assert!(!content.contains("https://"), "Should not extract URLs");
+        assert_eq!(
+            metadata.get("title").and_then(|v| v.as_str()),
+            Some("Missing Attributes")
+        );
+    }
+    #[test]
+    fn test_opml_whitespace_only_text_attribute() {
+        let opml = br#"<?xml version="1.0"?>
+<opml version="2.0">
+  <head>
+    <title>Whitespace Test</title>
+  </head>
+  <body>
+    <outline text="   " />
+    <outline text="
+" />
+    <outline text="Real Content" />
+  </body>
+</opml>"#;
+        let (content, _) =
+            OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle whitespace-only text");
+        assert!(
+            content.contains("Real Content"),
+            "Should extract non-whitespace content"
+        );
+        let trimmed = content.trim();
+        assert!(trimmed.contains("Whitespace Test"), "Should have title");
+        assert!(trimmed.contains("Real Content"), "Should have real content");
+    }
+    #[test]
+    fn test_opml_html_entity_in_nested_structure() {
+        let opml = br#"<?xml version="1.0"?>
+<opml version="2.0">
+  <head>
+    <title>Entities &amp; Nesting</title>
+  </head>
+  <body>
+    <outline text="News &amp; Updates">
+      <outline text="Tech &lt; Science" />
+      <outline text="Health &gt; Wealth" />
+    </outline>
+  </body>
+</opml>"#;
+        let (content, metadata) =
+            OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle HTML entities");
+        assert!(
+            content.contains("News") && content.contains("Updates"),
+            "Should decode &amp; entity"
+        );
+        assert!(content.contains("Tech"), "Should handle &lt; entity");
+        assert!(content.contains("Science"), "Should decode entity properly");
+        let title = metadata.get("title").and_then(|v| v.as_str()).unwrap_or("");
+        assert!(
+            title.contains("&") && title.contains("Nesting"),
+            "Title should have decoded entity"
+        );
+    }
+    #[test]
+    fn test_opml_single_outline_no_children() {
+        let opml = br#"<?xml version="1.0"?>
+<opml version="2.0">
+  <head>
+    <title>Single</title>
+  </head>
+  <body>
+    <outline text="Only Item" />
+  </body>
+</opml>"#;
+        let (content, metadata) =
+            OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle single outline");
+        assert!(content.contains("Only Item"), "Should extract single item");
+        assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("Single"));
+    }
+    #[test]
+    fn test_opml_head_without_body() {
+        let opml = br#"<?xml version="1.0"?>
+<opml version="2.0">
+  <head>
+    <title>No Body</title>
+  </head>
+</opml>"#;
+        let (content, metadata) =
+            OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle OPML without body");
+        assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("No Body"));
+        assert!(content.is_empty() || content.trim() == "No Body");
+    }
+    #[test]
+    fn test_opml_body_without_head() {
+        let opml = br#"<?xml version="1.0"?>
+<opml version="2.0">
+  <body>
+    <outline text="Item" />
+  </body>
+</opml>"#;
+        let (content, metadata) =
+            OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle OPML without head");
+        assert!(content.contains("Item"), "Should extract body content");
+        assert!(metadata.is_empty(), "Should have no metadata without head");
+    }
+}