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.
- 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
|
@@ -1,87 +1,87 @@
|
|
|
1
|
-
//! End-to-end integration test for XLSX metadata extraction
|
|
2
|
-
#![cfg(feature = "excel")]
|
|
3
|
-
|
|
4
|
-
use kreuzberg::extraction::excel::read_excel_file;
|
|
5
|
-
|
|
6
|
-
#[test]
|
|
7
|
-
fn test_xlsx_full_metadata_extraction() {
|
|
8
|
-
let workspace_root = std::path::Path::new(env!("CARGO_MANIFEST_DIR"))
|
|
9
|
-
.parent()
|
|
10
|
-
.unwrap()
|
|
11
|
-
.parent()
|
|
12
|
-
.unwrap();
|
|
13
|
-
let test_file = workspace_root.join("test_documents/office/excel.xlsx");
|
|
14
|
-
|
|
15
|
-
if !test_file.exists() {
|
|
16
|
-
println!("Skipping test: Test file not found at {:?}", test_file);
|
|
17
|
-
return;
|
|
18
|
-
}
|
|
19
|
-
|
|
20
|
-
let result = read_excel_file(test_file.to_str().unwrap()).expect("Should extract XLSX successfully");
|
|
21
|
-
|
|
22
|
-
assert!(!result.sheets.is_empty(), "Should have at least one sheet");
|
|
23
|
-
|
|
24
|
-
assert!(result.metadata.contains_key("sheet_count"), "Should have sheet count");
|
|
25
|
-
|
|
26
|
-
println!("✅ XLSX metadata extraction test passed!");
|
|
27
|
-
println!(" Found {} metadata fields", result.metadata.len());
|
|
28
|
-
for (key, value) in &result.metadata {
|
|
29
|
-
println!(" {}: {}", key, value);
|
|
30
|
-
}
|
|
31
|
-
}
|
|
32
|
-
|
|
33
|
-
#[test]
|
|
34
|
-
fn test_xlsx_multi_sheet_metadata() {
|
|
35
|
-
let workspace_root = std::path::Path::new(env!("CARGO_MANIFEST_DIR"))
|
|
36
|
-
.parent()
|
|
37
|
-
.unwrap()
|
|
38
|
-
.parent()
|
|
39
|
-
.unwrap();
|
|
40
|
-
let test_file = workspace_root.join("test_documents/spreadsheets/excel_multi_sheet.xlsx");
|
|
41
|
-
|
|
42
|
-
if !test_file.exists() {
|
|
43
|
-
println!("Skipping test: Test file not found at {:?}", test_file);
|
|
44
|
-
return;
|
|
45
|
-
}
|
|
46
|
-
|
|
47
|
-
let result = read_excel_file(test_file.to_str().unwrap()).expect("Should extract multi-sheet XLSX successfully");
|
|
48
|
-
|
|
49
|
-
assert!(
|
|
50
|
-
result.sheets.len() > 1,
|
|
51
|
-
"Should have multiple sheets, got {}",
|
|
52
|
-
result.sheets.len()
|
|
53
|
-
);
|
|
54
|
-
|
|
55
|
-
assert!(
|
|
56
|
-
result.metadata.contains_key("sheet_names"),
|
|
57
|
-
"Should have sheet_names metadata"
|
|
58
|
-
);
|
|
59
|
-
|
|
60
|
-
println!("✅ XLSX multi-sheet metadata extraction test passed!");
|
|
61
|
-
println!(" Found {} sheets", result.sheets.len());
|
|
62
|
-
}
|
|
63
|
-
|
|
64
|
-
#[test]
|
|
65
|
-
fn test_xlsx_minimal_metadata_extraction() {
|
|
66
|
-
let workspace_root = std::path::Path::new(env!("CARGO_MANIFEST_DIR"))
|
|
67
|
-
.parent()
|
|
68
|
-
.unwrap()
|
|
69
|
-
.parent()
|
|
70
|
-
.unwrap();
|
|
71
|
-
let test_file = workspace_root.join("test_documents/spreadsheets/test_01.xlsx");
|
|
72
|
-
|
|
73
|
-
if !test_file.exists() {
|
|
74
|
-
println!("Skipping test: Test file not found at {:?}", test_file);
|
|
75
|
-
return;
|
|
76
|
-
}
|
|
77
|
-
|
|
78
|
-
let result = read_excel_file(test_file.to_str().unwrap()).expect("Should extract XLSX successfully");
|
|
79
|
-
|
|
80
|
-
assert!(!result.sheets.is_empty(), "Content should not be empty");
|
|
81
|
-
assert!(
|
|
82
|
-
result.metadata.contains_key("sheet_count"),
|
|
83
|
-
"Should have basic sheet metadata"
|
|
84
|
-
);
|
|
85
|
-
|
|
86
|
-
println!("✅ XLSX minimal metadata extraction test passed!");
|
|
87
|
-
}
|
|
1
|
+
//! End-to-end integration test for XLSX metadata extraction
|
|
2
|
+
#![cfg(feature = "excel")]
|
|
3
|
+
|
|
4
|
+
use kreuzberg::extraction::excel::read_excel_file;
|
|
5
|
+
|
|
6
|
+
#[test]
|
|
7
|
+
fn test_xlsx_full_metadata_extraction() {
|
|
8
|
+
let workspace_root = std::path::Path::new(env!("CARGO_MANIFEST_DIR"))
|
|
9
|
+
.parent()
|
|
10
|
+
.unwrap()
|
|
11
|
+
.parent()
|
|
12
|
+
.unwrap();
|
|
13
|
+
let test_file = workspace_root.join("test_documents/office/excel.xlsx");
|
|
14
|
+
|
|
15
|
+
if !test_file.exists() {
|
|
16
|
+
println!("Skipping test: Test file not found at {:?}", test_file);
|
|
17
|
+
return;
|
|
18
|
+
}
|
|
19
|
+
|
|
20
|
+
let result = read_excel_file(test_file.to_str().unwrap()).expect("Should extract XLSX successfully");
|
|
21
|
+
|
|
22
|
+
assert!(!result.sheets.is_empty(), "Should have at least one sheet");
|
|
23
|
+
|
|
24
|
+
assert!(result.metadata.contains_key("sheet_count"), "Should have sheet count");
|
|
25
|
+
|
|
26
|
+
println!("✅ XLSX metadata extraction test passed!");
|
|
27
|
+
println!(" Found {} metadata fields", result.metadata.len());
|
|
28
|
+
for (key, value) in &result.metadata {
|
|
29
|
+
println!(" {}: {}", key, value);
|
|
30
|
+
}
|
|
31
|
+
}
|
|
32
|
+
|
|
33
|
+
#[test]
|
|
34
|
+
fn test_xlsx_multi_sheet_metadata() {
|
|
35
|
+
let workspace_root = std::path::Path::new(env!("CARGO_MANIFEST_DIR"))
|
|
36
|
+
.parent()
|
|
37
|
+
.unwrap()
|
|
38
|
+
.parent()
|
|
39
|
+
.unwrap();
|
|
40
|
+
let test_file = workspace_root.join("test_documents/spreadsheets/excel_multi_sheet.xlsx");
|
|
41
|
+
|
|
42
|
+
if !test_file.exists() {
|
|
43
|
+
println!("Skipping test: Test file not found at {:?}", test_file);
|
|
44
|
+
return;
|
|
45
|
+
}
|
|
46
|
+
|
|
47
|
+
let result = read_excel_file(test_file.to_str().unwrap()).expect("Should extract multi-sheet XLSX successfully");
|
|
48
|
+
|
|
49
|
+
assert!(
|
|
50
|
+
result.sheets.len() > 1,
|
|
51
|
+
"Should have multiple sheets, got {}",
|
|
52
|
+
result.sheets.len()
|
|
53
|
+
);
|
|
54
|
+
|
|
55
|
+
assert!(
|
|
56
|
+
result.metadata.contains_key("sheet_names"),
|
|
57
|
+
"Should have sheet_names metadata"
|
|
58
|
+
);
|
|
59
|
+
|
|
60
|
+
println!("✅ XLSX multi-sheet metadata extraction test passed!");
|
|
61
|
+
println!(" Found {} sheets", result.sheets.len());
|
|
62
|
+
}
|
|
63
|
+
|
|
64
|
+
#[test]
|
|
65
|
+
fn test_xlsx_minimal_metadata_extraction() {
|
|
66
|
+
let workspace_root = std::path::Path::new(env!("CARGO_MANIFEST_DIR"))
|
|
67
|
+
.parent()
|
|
68
|
+
.unwrap()
|
|
69
|
+
.parent()
|
|
70
|
+
.unwrap();
|
|
71
|
+
let test_file = workspace_root.join("test_documents/spreadsheets/test_01.xlsx");
|
|
72
|
+
|
|
73
|
+
if !test_file.exists() {
|
|
74
|
+
println!("Skipping test: Test file not found at {:?}", test_file);
|
|
75
|
+
return;
|
|
76
|
+
}
|
|
77
|
+
|
|
78
|
+
let result = read_excel_file(test_file.to_str().unwrap()).expect("Should extract XLSX successfully");
|
|
79
|
+
|
|
80
|
+
assert!(!result.sheets.is_empty(), "Content should not be empty");
|
|
81
|
+
assert!(
|
|
82
|
+
result.metadata.contains_key("sheet_count"),
|
|
83
|
+
"Should have basic sheet metadata"
|
|
84
|
+
);
|
|
85
|
+
|
|
86
|
+
println!("✅ XLSX minimal metadata extraction test passed!");
|
|
87
|
+
}
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"v":1}
|
|
@@ -0,0 +1,393 @@
|
|
|
1
|
+
# This file is automatically @generated by Cargo.
|
|
2
|
+
# It is not intended for manual editing.
|
|
3
|
+
version = 3
|
|
4
|
+
|
|
5
|
+
[[package]]
|
|
6
|
+
name = "aho-corasick"
|
|
7
|
+
version = "1.1.3"
|
|
8
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
9
|
+
checksum = "8e60d3430d3a69478ad0993f19238d2df97c507009a52b3c10addcd7f6bcb916"
|
|
10
|
+
dependencies = [
|
|
11
|
+
"memchr",
|
|
12
|
+
]
|
|
13
|
+
|
|
14
|
+
[[package]]
|
|
15
|
+
name = "bindgen"
|
|
16
|
+
version = "0.69.4"
|
|
17
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
18
|
+
checksum = "a00dc851838a2120612785d195287475a3ac45514741da670b735818822129a0"
|
|
19
|
+
dependencies = [
|
|
20
|
+
"bitflags",
|
|
21
|
+
"cexpr",
|
|
22
|
+
"clang-sys",
|
|
23
|
+
"itertools",
|
|
24
|
+
"lazy_static",
|
|
25
|
+
"lazycell",
|
|
26
|
+
"proc-macro2",
|
|
27
|
+
"quote",
|
|
28
|
+
"regex",
|
|
29
|
+
"rustc-hash",
|
|
30
|
+
"shlex",
|
|
31
|
+
"syn",
|
|
32
|
+
]
|
|
33
|
+
|
|
34
|
+
[[package]]
|
|
35
|
+
name = "bitflags"
|
|
36
|
+
version = "2.6.0"
|
|
37
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
38
|
+
checksum = "b048fb63fd8b5923fc5aa7b340d8e156aec7ec02f0c78fa8a6ddc2613f6f71de"
|
|
39
|
+
|
|
40
|
+
[[package]]
|
|
41
|
+
name = "cexpr"
|
|
42
|
+
version = "0.6.0"
|
|
43
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
44
|
+
checksum = "6fac387a98bb7c37292057cffc56d62ecb629900026402633ae9160df93a8766"
|
|
45
|
+
dependencies = [
|
|
46
|
+
"nom",
|
|
47
|
+
]
|
|
48
|
+
|
|
49
|
+
[[package]]
|
|
50
|
+
name = "cfg-if"
|
|
51
|
+
version = "1.0.0"
|
|
52
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
53
|
+
checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
|
|
54
|
+
|
|
55
|
+
[[package]]
|
|
56
|
+
name = "clang-sys"
|
|
57
|
+
version = "1.8.1"
|
|
58
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
59
|
+
checksum = "0b023947811758c97c59bf9d1c188fd619ad4718dcaa767947df1cadb14f39f4"
|
|
60
|
+
dependencies = [
|
|
61
|
+
"glob",
|
|
62
|
+
"libc",
|
|
63
|
+
"libloading",
|
|
64
|
+
]
|
|
65
|
+
|
|
66
|
+
[[package]]
|
|
67
|
+
name = "either"
|
|
68
|
+
version = "1.13.0"
|
|
69
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
70
|
+
checksum = "60b1af1c220855b6ceac025d3f6ecdd2b7c4894bfe9cd9bda4fbb4bc7c0d4cf0"
|
|
71
|
+
|
|
72
|
+
[[package]]
|
|
73
|
+
name = "errno"
|
|
74
|
+
version = "0.3.9"
|
|
75
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
76
|
+
checksum = "534c5cf6194dfab3db3242765c03bbe257cf92f22b38f6bc0c58d59108a820ba"
|
|
77
|
+
dependencies = [
|
|
78
|
+
"libc",
|
|
79
|
+
"windows-sys",
|
|
80
|
+
]
|
|
81
|
+
|
|
82
|
+
[[package]]
|
|
83
|
+
name = "fastrand"
|
|
84
|
+
version = "2.1.0"
|
|
85
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
86
|
+
checksum = "9fc0510504f03c51ada170672ac806f1f105a88aa97a5281117e1ddc3368e51a"
|
|
87
|
+
|
|
88
|
+
[[package]]
|
|
89
|
+
name = "fnv"
|
|
90
|
+
version = "1.0.7"
|
|
91
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
92
|
+
checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
|
|
93
|
+
|
|
94
|
+
[[package]]
|
|
95
|
+
name = "glob"
|
|
96
|
+
version = "0.3.1"
|
|
97
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
98
|
+
checksum = "d2fabcfbdc87f4758337ca535fb41a6d701b65693ce38287d856d1674551ec9b"
|
|
99
|
+
|
|
100
|
+
[[package]]
|
|
101
|
+
name = "itertools"
|
|
102
|
+
version = "0.12.1"
|
|
103
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
104
|
+
checksum = "ba291022dbbd398a455acf126c1e341954079855bc60dfdda641363bd6922569"
|
|
105
|
+
dependencies = [
|
|
106
|
+
"either",
|
|
107
|
+
]
|
|
108
|
+
|
|
109
|
+
[[package]]
|
|
110
|
+
name = "lazy_static"
|
|
111
|
+
version = "1.5.0"
|
|
112
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
113
|
+
checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
|
|
114
|
+
|
|
115
|
+
[[package]]
|
|
116
|
+
name = "lazycell"
|
|
117
|
+
version = "1.3.0"
|
|
118
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
119
|
+
checksum = "830d08ce1d1d941e6b30645f1a0eb5643013d835ce3779a5fc208261dbe10f55"
|
|
120
|
+
|
|
121
|
+
[[package]]
|
|
122
|
+
name = "libc"
|
|
123
|
+
version = "0.2.155"
|
|
124
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
125
|
+
checksum = "97b3888a4aecf77e811145cadf6eef5901f4782c53886191b2f693f24761847c"
|
|
126
|
+
|
|
127
|
+
[[package]]
|
|
128
|
+
name = "libloading"
|
|
129
|
+
version = "0.8.5"
|
|
130
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
131
|
+
checksum = "4979f22fdb869068da03c9f7528f8297c6fd2606bc3a4affe42e6a823fdb8da4"
|
|
132
|
+
dependencies = [
|
|
133
|
+
"cfg-if",
|
|
134
|
+
"windows-targets",
|
|
135
|
+
]
|
|
136
|
+
|
|
137
|
+
[[package]]
|
|
138
|
+
name = "linux-raw-sys"
|
|
139
|
+
version = "0.4.14"
|
|
140
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
141
|
+
checksum = "78b3ae25bc7c8c38cec158d1f2757ee79e9b3740fbc7ccf0e59e4b08d793fa89"
|
|
142
|
+
|
|
143
|
+
[[package]]
|
|
144
|
+
name = "memchr"
|
|
145
|
+
version = "2.7.4"
|
|
146
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
147
|
+
checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3"
|
|
148
|
+
|
|
149
|
+
[[package]]
|
|
150
|
+
name = "minimal-lexical"
|
|
151
|
+
version = "0.2.1"
|
|
152
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
153
|
+
checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
|
|
154
|
+
|
|
155
|
+
[[package]]
|
|
156
|
+
name = "nom"
|
|
157
|
+
version = "7.1.3"
|
|
158
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
159
|
+
checksum = "d273983c5a657a70a3e8f2a01329822f3b8c8172b73826411a55751e404a0a4a"
|
|
160
|
+
dependencies = [
|
|
161
|
+
"memchr",
|
|
162
|
+
"minimal-lexical",
|
|
163
|
+
]
|
|
164
|
+
|
|
165
|
+
[[package]]
|
|
166
|
+
name = "proc-macro2"
|
|
167
|
+
version = "1.0.95"
|
|
168
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
169
|
+
checksum = "02b3e5e68a3a1a02aad3ec490a98007cbc13c37cbe84a3cd7b8e406d76e7f778"
|
|
170
|
+
dependencies = [
|
|
171
|
+
"unicode-ident",
|
|
172
|
+
]
|
|
173
|
+
|
|
174
|
+
[[package]]
|
|
175
|
+
name = "quick-error"
|
|
176
|
+
version = "1.2.3"
|
|
177
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
178
|
+
checksum = "a1d01941d82fa2ab50be1e79e6714289dd7cde78eba4c074bc5a4374f650dfe0"
|
|
179
|
+
|
|
180
|
+
[[package]]
|
|
181
|
+
name = "quote"
|
|
182
|
+
version = "1.0.38"
|
|
183
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
184
|
+
checksum = "0e4dccaaaf89514f546c693ddc140f729f958c247918a13380cccc6078391acc"
|
|
185
|
+
dependencies = [
|
|
186
|
+
"proc-macro2",
|
|
187
|
+
]
|
|
188
|
+
|
|
189
|
+
[[package]]
|
|
190
|
+
name = "rb-sys"
|
|
191
|
+
version = "0.9.117"
|
|
192
|
+
dependencies = [
|
|
193
|
+
"rb-sys-build",
|
|
194
|
+
"rusty-fork",
|
|
195
|
+
]
|
|
196
|
+
|
|
197
|
+
[[package]]
|
|
198
|
+
name = "rb-sys-build"
|
|
199
|
+
version = "0.9.117"
|
|
200
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
201
|
+
checksum = "ef1e9c857028f631056bcd6d88cec390c751e343ce2223ddb26d23eb4a151d59"
|
|
202
|
+
dependencies = [
|
|
203
|
+
"bindgen",
|
|
204
|
+
"lazy_static",
|
|
205
|
+
"proc-macro2",
|
|
206
|
+
"quote",
|
|
207
|
+
"regex",
|
|
208
|
+
"shell-words",
|
|
209
|
+
"syn",
|
|
210
|
+
]
|
|
211
|
+
|
|
212
|
+
[[package]]
|
|
213
|
+
name = "regex"
|
|
214
|
+
version = "1.11.1"
|
|
215
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
216
|
+
checksum = "b544ef1b4eac5dc2db33ea63606ae9ffcfac26c1416a2806ae0bf5f56b201191"
|
|
217
|
+
dependencies = [
|
|
218
|
+
"aho-corasick",
|
|
219
|
+
"memchr",
|
|
220
|
+
"regex-automata",
|
|
221
|
+
"regex-syntax",
|
|
222
|
+
]
|
|
223
|
+
|
|
224
|
+
[[package]]
|
|
225
|
+
name = "regex-automata"
|
|
226
|
+
version = "0.4.8"
|
|
227
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
228
|
+
checksum = "368758f23274712b504848e9d5a6f010445cc8b87a7cdb4d7cbee666c1288da3"
|
|
229
|
+
dependencies = [
|
|
230
|
+
"aho-corasick",
|
|
231
|
+
"memchr",
|
|
232
|
+
"regex-syntax",
|
|
233
|
+
]
|
|
234
|
+
|
|
235
|
+
[[package]]
|
|
236
|
+
name = "regex-syntax"
|
|
237
|
+
version = "0.8.5"
|
|
238
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
239
|
+
checksum = "2b15c43186be67a4fd63bee50d0303afffcef381492ebe2c5d87f324e1b8815c"
|
|
240
|
+
|
|
241
|
+
[[package]]
|
|
242
|
+
name = "rustc-hash"
|
|
243
|
+
version = "1.1.0"
|
|
244
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
245
|
+
checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
|
|
246
|
+
|
|
247
|
+
[[package]]
|
|
248
|
+
name = "rustix"
|
|
249
|
+
version = "0.38.34"
|
|
250
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
251
|
+
checksum = "70dc5ec042f7a43c4a73241207cecc9873a06d45debb38b329f8541d85c2730f"
|
|
252
|
+
dependencies = [
|
|
253
|
+
"bitflags",
|
|
254
|
+
"errno",
|
|
255
|
+
"libc",
|
|
256
|
+
"linux-raw-sys",
|
|
257
|
+
"windows-sys",
|
|
258
|
+
]
|
|
259
|
+
|
|
260
|
+
[[package]]
|
|
261
|
+
name = "rusty-fork"
|
|
262
|
+
version = "0.3.0"
|
|
263
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
264
|
+
checksum = "cb3dcc6e454c328bb824492db107ab7c0ae8fcffe4ad210136ef014458c1bc4f"
|
|
265
|
+
dependencies = [
|
|
266
|
+
"fnv",
|
|
267
|
+
"quick-error",
|
|
268
|
+
"tempfile",
|
|
269
|
+
"wait-timeout",
|
|
270
|
+
]
|
|
271
|
+
|
|
272
|
+
[[package]]
|
|
273
|
+
name = "shell-words"
|
|
274
|
+
version = "1.1.0"
|
|
275
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
276
|
+
checksum = "24188a676b6ae68c3b2cb3a01be17fbf7240ce009799bb56d5b1409051e78fde"
|
|
277
|
+
|
|
278
|
+
[[package]]
|
|
279
|
+
name = "shlex"
|
|
280
|
+
version = "1.3.0"
|
|
281
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
282
|
+
checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
|
|
283
|
+
|
|
284
|
+
[[package]]
|
|
285
|
+
name = "syn"
|
|
286
|
+
version = "2.0.104"
|
|
287
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
288
|
+
checksum = "17b6f705963418cdb9927482fa304bc562ece2fdd4f616084c50b7023b435a40"
|
|
289
|
+
dependencies = [
|
|
290
|
+
"proc-macro2",
|
|
291
|
+
"quote",
|
|
292
|
+
"unicode-ident",
|
|
293
|
+
]
|
|
294
|
+
|
|
295
|
+
[[package]]
|
|
296
|
+
name = "tempfile"
|
|
297
|
+
version = "3.10.1"
|
|
298
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
299
|
+
checksum = "85b77fafb263dd9d05cbeac119526425676db3784113aa9295c88498cbf8bff1"
|
|
300
|
+
dependencies = [
|
|
301
|
+
"cfg-if",
|
|
302
|
+
"fastrand",
|
|
303
|
+
"rustix",
|
|
304
|
+
"windows-sys",
|
|
305
|
+
]
|
|
306
|
+
|
|
307
|
+
[[package]]
|
|
308
|
+
name = "unicode-ident"
|
|
309
|
+
version = "1.0.12"
|
|
310
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
311
|
+
checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
|
|
312
|
+
|
|
313
|
+
[[package]]
|
|
314
|
+
name = "wait-timeout"
|
|
315
|
+
version = "0.2.0"
|
|
316
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
317
|
+
checksum = "9f200f5b12eb75f8c1ed65abd4b2db8a6e1b138a20de009dacee265a2498f3f6"
|
|
318
|
+
dependencies = [
|
|
319
|
+
"libc",
|
|
320
|
+
]
|
|
321
|
+
|
|
322
|
+
[[package]]
|
|
323
|
+
name = "windows-sys"
|
|
324
|
+
version = "0.52.0"
|
|
325
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
326
|
+
checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
|
|
327
|
+
dependencies = [
|
|
328
|
+
"windows-targets",
|
|
329
|
+
]
|
|
330
|
+
|
|
331
|
+
[[package]]
|
|
332
|
+
name = "windows-targets"
|
|
333
|
+
version = "0.52.6"
|
|
334
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
335
|
+
checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
|
|
336
|
+
dependencies = [
|
|
337
|
+
"windows_aarch64_gnullvm",
|
|
338
|
+
"windows_aarch64_msvc",
|
|
339
|
+
"windows_i686_gnu",
|
|
340
|
+
"windows_i686_gnullvm",
|
|
341
|
+
"windows_i686_msvc",
|
|
342
|
+
"windows_x86_64_gnu",
|
|
343
|
+
"windows_x86_64_gnullvm",
|
|
344
|
+
"windows_x86_64_msvc",
|
|
345
|
+
]
|
|
346
|
+
|
|
347
|
+
[[package]]
|
|
348
|
+
name = "windows_aarch64_gnullvm"
|
|
349
|
+
version = "0.52.6"
|
|
350
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
351
|
+
checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
|
|
352
|
+
|
|
353
|
+
[[package]]
|
|
354
|
+
name = "windows_aarch64_msvc"
|
|
355
|
+
version = "0.52.6"
|
|
356
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
357
|
+
checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
|
|
358
|
+
|
|
359
|
+
[[package]]
|
|
360
|
+
name = "windows_i686_gnu"
|
|
361
|
+
version = "0.52.6"
|
|
362
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
363
|
+
checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b"
|
|
364
|
+
|
|
365
|
+
[[package]]
|
|
366
|
+
name = "windows_i686_gnullvm"
|
|
367
|
+
version = "0.52.6"
|
|
368
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
369
|
+
checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
|
|
370
|
+
|
|
371
|
+
[[package]]
|
|
372
|
+
name = "windows_i686_msvc"
|
|
373
|
+
version = "0.52.6"
|
|
374
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
375
|
+
checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
|
|
376
|
+
|
|
377
|
+
[[package]]
|
|
378
|
+
name = "windows_x86_64_gnu"
|
|
379
|
+
version = "0.52.6"
|
|
380
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
381
|
+
checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
|
|
382
|
+
|
|
383
|
+
[[package]]
|
|
384
|
+
name = "windows_x86_64_gnullvm"
|
|
385
|
+
version = "0.52.6"
|
|
386
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
387
|
+
checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
|
|
388
|
+
|
|
389
|
+
[[package]]
|
|
390
|
+
name = "windows_x86_64_msvc"
|
|
391
|
+
version = "0.52.6"
|
|
392
|
+
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
393
|
+
checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
|
|
@@ -0,0 +1,70 @@
|
|
|
1
|
+
# THIS FILE IS AUTOMATICALLY GENERATED BY CARGO
|
|
2
|
+
#
|
|
3
|
+
# When uploading crates to the registry Cargo will automatically
|
|
4
|
+
# "normalize" Cargo.toml files for maximal compatibility
|
|
5
|
+
# with all versions of Cargo and also rewrite `path` dependencies
|
|
6
|
+
# to registry (e.g., crates.io) dependencies.
|
|
7
|
+
#
|
|
8
|
+
# If you are reading this file be aware that the original Cargo.toml
|
|
9
|
+
# will likely look very different (and much more reasonable).
|
|
10
|
+
# See Cargo.toml.orig for the original contents.
|
|
11
|
+
|
|
12
|
+
[package]
|
|
13
|
+
edition = "2018"
|
|
14
|
+
rust-version = "1.65"
|
|
15
|
+
name = "rb-sys"
|
|
16
|
+
version = "4.0.0-rc.6"
|
|
17
|
+
build = "build/main.rs"
|
|
18
|
+
links = "rb"
|
|
19
|
+
autolib = false
|
|
20
|
+
autobins = false
|
|
21
|
+
autoexamples = false
|
|
22
|
+
autotests = false
|
|
23
|
+
autobenches = false
|
|
24
|
+
description = "Rust bindings for the CRuby API"
|
|
25
|
+
homepage = "https://github.com/oxidize-rb/rb-sys"
|
|
26
|
+
documentation = "https://docs.rs/rb-sys"
|
|
27
|
+
readme = "readme.md"
|
|
28
|
+
categories = ["external-ffi-bindings"]
|
|
29
|
+
license = "MIT OR Apache-2.0"
|
|
30
|
+
repository = "https://github.com/oxidize-rb/rb-sys"
|
|
31
|
+
|
|
32
|
+
[features]
|
|
33
|
+
bindgen-deprecated-types = ["rb-sys-build/bindgen-deprecated-types"]
|
|
34
|
+
bindgen-enable-function-attribute-detection = ["rb-sys-build/bindgen-enable-function-attribute-detection"]
|
|
35
|
+
bindgen-impl-debug = ["rb-sys-build/bindgen-impl-debug"]
|
|
36
|
+
bindgen-layout-tests = ["rb-sys-build/bindgen-layout-tests"]
|
|
37
|
+
bindgen-rbimpls = ["rb-sys-build/bindgen-rbimpls"]
|
|
38
|
+
bindgen-return-const-encoding-pointers = ["rb-sys-build/bindgen-return-const-encoding-pointers"]
|
|
39
|
+
bindgen-sizet-is-usize = ["rb-sys-build/bindgen-sizet-is-usize"]
|
|
40
|
+
default = ["stable-api-compiled-fallback"]
|
|
41
|
+
fuzz = []
|
|
42
|
+
global-allocator = []
|
|
43
|
+
link-ruby = []
|
|
44
|
+
no-link-ruby = []
|
|
45
|
+
ruby-macros = ["stable-api"]
|
|
46
|
+
ruby-static = []
|
|
47
|
+
stable-api = []
|
|
48
|
+
stable-api-compiled-fallback = ["stable-api"]
|
|
49
|
+
stable-api-compiled-force = []
|
|
50
|
+
stable-api-compiled-testing = ["stable-api-compiled-fallback"]
|
|
51
|
+
|
|
52
|
+
[lib]
|
|
53
|
+
name = "rb_sys"
|
|
54
|
+
path = "src/lib.rs"
|
|
55
|
+
doctest = false
|
|
56
|
+
|
|
57
|
+
[dev-dependencies.rusty-fork]
|
|
58
|
+
version = "0.3.0"
|
|
59
|
+
|
|
60
|
+
[build-dependencies.rb-sys-build]
|
|
61
|
+
version = "0.9.117"
|
|
62
|
+
|
|
63
|
+
[lints.rust.unexpected_cfgs]
|
|
64
|
+
level = "warn"
|
|
65
|
+
priority = 0
|
|
66
|
+
check-cfg = [
|
|
67
|
+
"cfg(rb_sys_gem)",
|
|
68
|
+
"cfg(rb_sys_use_stable_api_compiled_fallback)",
|
|
69
|
+
"cfg(rb_sys_force_stable_api_compiled)",
|
|
70
|
+
]
|