kreuzberg 4.0.0.pre.rc.8 → 4.0.0.pre.rc.13
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 -14
- data/.rspec +3 -3
- data/.rubocop.yaml +1 -1
- data/.rubocop.yml +538 -538
- data/Gemfile +8 -8
- data/Gemfile.lock +4 -104
- data/README.md +454 -432
- data/Rakefile +25 -25
- data/Steepfile +47 -47
- data/examples/async_patterns.rb +341 -341
- data/ext/kreuzberg_rb/extconf.rb +45 -45
- data/ext/kreuzberg_rb/native/.cargo/config.toml +2 -2
- data/ext/kreuzberg_rb/native/Cargo.lock +6941 -6721
- data/ext/kreuzberg_rb/native/Cargo.toml +54 -54
- data/ext/kreuzberg_rb/native/README.md +425 -425
- data/ext/kreuzberg_rb/native/build.rs +15 -15
- 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 +3158 -3135
- data/extconf.rb +28 -28
- data/kreuzberg.gemspec +214 -182
- data/lib/kreuzberg/api_proxy.rb +142 -142
- data/lib/kreuzberg/cache_api.rb +81 -46
- data/lib/kreuzberg/cli.rb +55 -55
- data/lib/kreuzberg/cli_proxy.rb +127 -127
- data/lib/kreuzberg/config.rb +724 -724
- data/lib/kreuzberg/error_context.rb +80 -32
- data/lib/kreuzberg/errors.rb +118 -118
- data/lib/kreuzberg/extraction_api.rb +340 -85
- 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 +279 -279
- data/lib/kreuzberg/setup_lib_path.rb +80 -80
- data/lib/kreuzberg/validator_protocol.rb +89 -89
- data/lib/kreuzberg/version.rb +5 -5
- data/lib/kreuzberg.rb +109 -103
- data/lib/pdfium.dll +0 -0
- data/sig/kreuzberg/internal.rbs +184 -184
- data/sig/kreuzberg.rbs +546 -537
- data/spec/binding/cache_spec.rb +227 -227
- data/spec/binding/cli_proxy_spec.rb +85 -85
- data/spec/binding/cli_spec.rb +55 -55
- 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 -41
- 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/Cargo.toml +45 -0
- data/vendor/kreuzberg/Cargo.toml +61 -38
- data/vendor/kreuzberg/README.md +230 -221
- data/vendor/kreuzberg/benches/otel_overhead.rs +48 -48
- data/vendor/kreuzberg/build.rs +843 -891
- 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 -1167
- data/vendor/kreuzberg/src/chunking/mod.rs +1877 -1877
- data/vendor/kreuzberg/src/chunking/processor.rs +220 -220
- data/vendor/kreuzberg/src/core/batch_mode.rs +95 -95
- data/vendor/kreuzberg/src/core/config.rs +1080 -1080
- data/vendor/kreuzberg/src/core/extractor.rs +1156 -1156
- data/vendor/kreuzberg/src/core/io.rs +329 -329
- data/vendor/kreuzberg/src/core/mime.rs +605 -605
- data/vendor/kreuzberg/src/core/mod.rs +47 -47
- data/vendor/kreuzberg/src/core/pipeline.rs +1184 -1171
- data/vendor/kreuzberg/src/embeddings.rs +500 -432
- data/vendor/kreuzberg/src/error.rs +431 -431
- data/vendor/kreuzberg/src/extraction/archive.rs +954 -954
- data/vendor/kreuzberg/src/extraction/docx.rs +398 -398
- 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 +601 -569
- data/vendor/kreuzberg/src/extraction/image.rs +491 -491
- data/vendor/kreuzberg/src/extraction/libreoffice.rs +574 -562
- data/vendor/kreuzberg/src/extraction/markdown.rs +213 -213
- data/vendor/kreuzberg/src/extraction/mod.rs +81 -81
- 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 -130
- data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +284 -284
- data/vendor/kreuzberg/src/extraction/pptx.rs +3100 -3100
- 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 +447 -447
- data/vendor/kreuzberg/src/extractors/bibtex.rs +470 -470
- data/vendor/kreuzberg/src/extractors/docbook.rs +504 -504
- data/vendor/kreuzberg/src/extractors/docx.rs +400 -400
- data/vendor/kreuzberg/src/extractors/email.rs +157 -157
- data/vendor/kreuzberg/src/extractors/epub.rs +708 -708
- data/vendor/kreuzberg/src/extractors/excel.rs +345 -345
- data/vendor/kreuzberg/src/extractors/fictionbook.rs +492 -492
- data/vendor/kreuzberg/src/extractors/html.rs +407 -407
- data/vendor/kreuzberg/src/extractors/image.rs +219 -219
- data/vendor/kreuzberg/src/extractors/jats.rs +1054 -1054
- data/vendor/kreuzberg/src/extractors/jupyter.rs +368 -368
- data/vendor/kreuzberg/src/extractors/latex.rs +653 -653
- data/vendor/kreuzberg/src/extractors/markdown.rs +701 -701
- data/vendor/kreuzberg/src/extractors/mod.rs +429 -429
- data/vendor/kreuzberg/src/extractors/odt.rs +628 -628
- data/vendor/kreuzberg/src/extractors/opml.rs +635 -635
- data/vendor/kreuzberg/src/extractors/orgmode.rs +529 -529
- data/vendor/kreuzberg/src/extractors/pdf.rs +749 -673
- data/vendor/kreuzberg/src/extractors/pptx.rs +267 -267
- data/vendor/kreuzberg/src/extractors/rst.rs +577 -577
- data/vendor/kreuzberg/src/extractors/rtf.rs +809 -809
- data/vendor/kreuzberg/src/extractors/security.rs +484 -484
- data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -367
- data/vendor/kreuzberg/src/extractors/structured.rs +142 -142
- data/vendor/kreuzberg/src/extractors/text.rs +265 -265
- data/vendor/kreuzberg/src/extractors/typst.rs +651 -651
- data/vendor/kreuzberg/src/extractors/xml.rs +147 -147
- 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 +275 -275
- data/vendor/kreuzberg/src/keywords/rake.rs +293 -293
- 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 +985 -985
- data/vendor/kreuzberg/src/language_detection/processor.rs +219 -219
- data/vendor/kreuzberg/src/lib.rs +113 -113
- data/vendor/kreuzberg/src/mcp/mod.rs +35 -35
- data/vendor/kreuzberg/src/mcp/server.rs +2076 -2076
- 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 -863
- 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 +452 -452
- 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 -154
- data/vendor/kreuzberg/src/pdf/bindings.rs +44 -0
- data/vendor/kreuzberg/src/pdf/bundled.rs +346 -328
- data/vendor/kreuzberg/src/pdf/error.rs +130 -130
- data/vendor/kreuzberg/src/pdf/images.rs +139 -139
- data/vendor/kreuzberg/src/pdf/metadata.rs +489 -489
- data/vendor/kreuzberg/src/pdf/mod.rs +68 -66
- data/vendor/kreuzberg/src/pdf/rendering.rs +368 -368
- data/vendor/kreuzberg/src/pdf/table.rs +420 -417
- data/vendor/kreuzberg/src/pdf/text.rs +240 -240
- data/vendor/kreuzberg/src/plugins/extractor.rs +1044 -1044
- data/vendor/kreuzberg/src/plugins/mod.rs +212 -212
- data/vendor/kreuzberg/src/plugins/ocr.rs +639 -639
- data/vendor/kreuzberg/src/plugins/processor.rs +650 -650
- data/vendor/kreuzberg/src/plugins/registry.rs +1339 -1339
- data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
- data/vendor/kreuzberg/src/plugins/validator.rs +967 -967
- data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
- data/vendor/kreuzberg/src/text/mod.rs +25 -25
- data/vendor/kreuzberg/src/text/quality.rs +697 -697
- data/vendor/kreuzberg/src/text/quality_processor.rs +219 -219
- 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 +1055 -1055
- 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 -52
- data/vendor/kreuzberg/tests/api_tests.rs +966 -966
- data/vendor/kreuzberg/tests/archive_integration.rs +545 -545
- data/vendor/kreuzberg/tests/batch_orchestration.rs +556 -556
- data/vendor/kreuzberg/tests/batch_processing.rs +318 -318
- data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -421
- data/vendor/kreuzberg/tests/concurrency_stress.rs +533 -533
- data/vendor/kreuzberg/tests/config_features.rs +612 -612
- data/vendor/kreuzberg/tests/config_loading_tests.rs +416 -416
- data/vendor/kreuzberg/tests/core_integration.rs +510 -510
- data/vendor/kreuzberg/tests/csv_integration.rs +414 -414
- data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +500 -500
- data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -122
- data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -370
- data/vendor/kreuzberg/tests/email_integration.rs +327 -327
- data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -275
- data/vendor/kreuzberg/tests/error_handling.rs +402 -402
- data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -228
- data/vendor/kreuzberg/tests/format_integration.rs +164 -161
- data/vendor/kreuzberg/tests/helpers/mod.rs +142 -142
- data/vendor/kreuzberg/tests/html_table_test.rs +551 -551
- data/vendor/kreuzberg/tests/image_integration.rs +255 -255
- data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -139
- data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -639
- data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -704
- 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 -496
- data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -490
- data/vendor/kreuzberg/tests/mime_detection.rs +429 -429
- data/vendor/kreuzberg/tests/ocr_configuration.rs +514 -514
- data/vendor/kreuzberg/tests/ocr_errors.rs +698 -698
- data/vendor/kreuzberg/tests/ocr_quality.rs +629 -629
- data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
- data/vendor/kreuzberg/tests/odt_extractor_tests.rs +674 -674
- data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -616
- data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -822
- data/vendor/kreuzberg/tests/pdf_integration.rs +45 -45
- data/vendor/kreuzberg/tests/pdfium_linking.rs +374 -374
- data/vendor/kreuzberg/tests/pipeline_integration.rs +1436 -1436
- data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +776 -776
- data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +560 -560
- data/vendor/kreuzberg/tests/plugin_system.rs +927 -927
- data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
- data/vendor/kreuzberg/tests/registry_integration_tests.rs +587 -587
- data/vendor/kreuzberg/tests/rst_extractor_tests.rs +694 -694
- data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +775 -775
- data/vendor/kreuzberg/tests/security_validation.rs +416 -416
- data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
- data/vendor/kreuzberg/tests/test_fastembed.rs +631 -631
- data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1260 -1260
- data/vendor/kreuzberg/tests/typst_extractor_tests.rs +648 -648
- data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -87
- data/vendor/kreuzberg-ffi/Cargo.toml +63 -0
- data/vendor/kreuzberg-ffi/README.md +851 -0
- data/vendor/kreuzberg-ffi/build.rs +176 -0
- data/vendor/kreuzberg-ffi/cbindgen.toml +27 -0
- data/vendor/kreuzberg-ffi/kreuzberg-ffi-install.pc +12 -0
- data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +12 -0
- data/vendor/kreuzberg-ffi/kreuzberg.h +1087 -0
- data/vendor/kreuzberg-ffi/src/lib.rs +3616 -0
- data/vendor/kreuzberg-ffi/src/panic_shield.rs +247 -0
- data/vendor/kreuzberg-ffi/tests.disabled/README.md +48 -0
- data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +299 -0
- data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +346 -0
- data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +232 -0
- data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +470 -0
- data/vendor/kreuzberg-tesseract/.commitlintrc.json +13 -0
- data/vendor/kreuzberg-tesseract/.crate-ignore +2 -0
- data/vendor/kreuzberg-tesseract/Cargo.lock +2933 -0
- data/vendor/kreuzberg-tesseract/Cargo.toml +48 -0
- data/vendor/kreuzberg-tesseract/LICENSE +22 -0
- data/vendor/kreuzberg-tesseract/README.md +399 -0
- data/vendor/kreuzberg-tesseract/build.rs +1354 -0
- data/vendor/kreuzberg-tesseract/patches/README.md +71 -0
- data/vendor/kreuzberg-tesseract/patches/tesseract.diff +199 -0
- data/vendor/kreuzberg-tesseract/src/api.rs +1371 -0
- data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +77 -0
- data/vendor/kreuzberg-tesseract/src/enums.rs +297 -0
- data/vendor/kreuzberg-tesseract/src/error.rs +81 -0
- data/vendor/kreuzberg-tesseract/src/lib.rs +145 -0
- data/vendor/kreuzberg-tesseract/src/monitor.rs +57 -0
- data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +197 -0
- data/vendor/kreuzberg-tesseract/src/page_iterator.rs +253 -0
- data/vendor/kreuzberg-tesseract/src/result_iterator.rs +286 -0
- data/vendor/kreuzberg-tesseract/src/result_renderer.rs +183 -0
- data/vendor/kreuzberg-tesseract/tests/integration_test.rs +211 -0
- data/vendor/rb-sys/.cargo_vcs_info.json +5 -5
- data/vendor/rb-sys/Cargo.lock +393 -393
- data/vendor/rb-sys/Cargo.toml +70 -70
- data/vendor/rb-sys/Cargo.toml.orig +57 -57
- data/vendor/rb-sys/LICENSE-APACHE +190 -190
- data/vendor/rb-sys/LICENSE-MIT +21 -21
- data/vendor/rb-sys/build/features.rs +111 -111
- data/vendor/rb-sys/build/main.rs +286 -286
- data/vendor/rb-sys/build/stable_api_config.rs +155 -155
- data/vendor/rb-sys/build/version.rs +50 -50
- data/vendor/rb-sys/readme.md +36 -36
- data/vendor/rb-sys/src/bindings.rs +21 -21
- data/vendor/rb-sys/src/hidden.rs +11 -11
- data/vendor/rb-sys/src/lib.rs +35 -35
- data/vendor/rb-sys/src/macros.rs +371 -371
- data/vendor/rb-sys/src/memory.rs +53 -53
- data/vendor/rb-sys/src/ruby_abi_version.rs +38 -38
- data/vendor/rb-sys/src/special_consts.rs +31 -31
- data/vendor/rb-sys/src/stable_api/compiled.c +179 -179
- data/vendor/rb-sys/src/stable_api/compiled.rs +257 -257
- data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +324 -324
- data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +332 -332
- data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +325 -325
- data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +323 -323
- data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +339 -339
- data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +339 -339
- data/vendor/rb-sys/src/stable_api.rs +260 -260
- data/vendor/rb-sys/src/symbol.rs +31 -31
- data/vendor/rb-sys/src/tracking_allocator.rs +330 -330
- data/vendor/rb-sys/src/utils.rs +89 -89
- data/vendor/rb-sys/src/value_type.rs +7 -7
- metadata +44 -81
- data/vendor/rb-sys/bin/release.sh +0 -21
|
@@ -1,139 +1,139 @@
|
|
|
1
|
-
#![cfg(feature = "otel")]
|
|
2
|
-
|
|
3
|
-
use std::sync::{Arc, Mutex};
|
|
4
|
-
use tracing::Subscriber;
|
|
5
|
-
use tracing::span::{Attributes, Id};
|
|
6
|
-
use tracing_subscriber::Layer;
|
|
7
|
-
use tracing_subscriber::layer::{Context, SubscriberExt};
|
|
8
|
-
use tracing_subscriber::registry::LookupSpan;
|
|
9
|
-
|
|
10
|
-
/// Simple span name collector for testing.
|
|
11
|
-
///
|
|
12
|
-
/// This layer collects span names as they are created to verify
|
|
13
|
-
/// that instrumentation is working correctly.
|
|
14
|
-
struct SpanCollector {
|
|
15
|
-
spans: Arc<Mutex<Vec<String>>>,
|
|
16
|
-
}
|
|
17
|
-
|
|
18
|
-
impl<S: Subscriber + for<'a> LookupSpan<'a>> Layer<S> for SpanCollector {
|
|
19
|
-
fn on_new_span(&self, attrs: &Attributes<'_>, _id: &Id, _ctx: Context<'_, S>) {
|
|
20
|
-
self.spans.lock().unwrap().push(attrs.metadata().name().to_string());
|
|
21
|
-
}
|
|
22
|
-
}
|
|
23
|
-
|
|
24
|
-
#[tokio::test]
|
|
25
|
-
async fn test_cache_instrumentation() {
|
|
26
|
-
use kreuzberg::cache::GenericCache;
|
|
27
|
-
use tempfile::tempdir;
|
|
28
|
-
|
|
29
|
-
let spans = Arc::new(Mutex::new(Vec::new()));
|
|
30
|
-
let collector = SpanCollector { spans: spans.clone() };
|
|
31
|
-
|
|
32
|
-
let subscriber = tracing_subscriber::registry().with(collector);
|
|
33
|
-
let _guard = tracing::subscriber::set_default(subscriber);
|
|
34
|
-
|
|
35
|
-
let temp_dir = tempdir().unwrap();
|
|
36
|
-
let cache = GenericCache::new(
|
|
37
|
-
"test".to_string(),
|
|
38
|
-
Some(temp_dir.path().to_str().unwrap().to_string()),
|
|
39
|
-
30.0,
|
|
40
|
-
500.0,
|
|
41
|
-
1000.0,
|
|
42
|
-
)
|
|
43
|
-
.unwrap();
|
|
44
|
-
|
|
45
|
-
cache.set("test_key", b"test data".to_vec(), None).unwrap();
|
|
46
|
-
|
|
47
|
-
let _ = cache.get("test_key", None).unwrap();
|
|
48
|
-
|
|
49
|
-
let span_names = spans.lock().unwrap();
|
|
50
|
-
assert!(span_names.contains(&"set".to_string()), "Expected 'set' span");
|
|
51
|
-
assert!(span_names.contains(&"get".to_string()), "Expected 'get' span");
|
|
52
|
-
}
|
|
53
|
-
|
|
54
|
-
#[cfg(feature = "ocr")]
|
|
55
|
-
#[tokio::test]
|
|
56
|
-
async fn test_ocr_instrumentation() {
|
|
57
|
-
use kreuzberg::ocr::processor::OcrProcessor;
|
|
58
|
-
use kreuzberg::ocr::types::TesseractConfig;
|
|
59
|
-
use tempfile::tempdir;
|
|
60
|
-
|
|
61
|
-
let spans = Arc::new(Mutex::new(Vec::new()));
|
|
62
|
-
let collector = SpanCollector { spans: spans.clone() };
|
|
63
|
-
|
|
64
|
-
let subscriber = tracing_subscriber::registry().with(collector);
|
|
65
|
-
let _guard = tracing::subscriber::set_default(subscriber);
|
|
66
|
-
|
|
67
|
-
let temp_dir = tempdir().unwrap();
|
|
68
|
-
let processor = OcrProcessor::new(Some(temp_dir.path().to_path_buf())).unwrap();
|
|
69
|
-
|
|
70
|
-
let mut test_image = Vec::new();
|
|
71
|
-
let img = image::ImageBuffer::from_fn(1, 1, |_, _| image::Rgb([255u8, 255u8, 255u8]));
|
|
72
|
-
img.write_to(&mut std::io::Cursor::new(&mut test_image), image::ImageFormat::Png)
|
|
73
|
-
.unwrap();
|
|
74
|
-
|
|
75
|
-
let config = TesseractConfig {
|
|
76
|
-
output_format: "text".to_string(),
|
|
77
|
-
use_cache: false,
|
|
78
|
-
..TesseractConfig::default()
|
|
79
|
-
};
|
|
80
|
-
|
|
81
|
-
let _ = processor.process_image(&test_image, &config);
|
|
82
|
-
|
|
83
|
-
let span_names = spans.lock().unwrap();
|
|
84
|
-
assert!(
|
|
85
|
-
span_names.contains(&"process_image".to_string()),
|
|
86
|
-
"Expected 'process_image' span"
|
|
87
|
-
);
|
|
88
|
-
}
|
|
89
|
-
|
|
90
|
-
#[tokio::test]
|
|
91
|
-
async fn test_registry_instrumentation() {
|
|
92
|
-
use kreuzberg::plugins::registry::DocumentExtractorRegistry;
|
|
93
|
-
|
|
94
|
-
let spans = Arc::new(Mutex::new(Vec::new()));
|
|
95
|
-
let collector = SpanCollector { spans: spans.clone() };
|
|
96
|
-
|
|
97
|
-
let subscriber = tracing_subscriber::registry().with(collector);
|
|
98
|
-
let _guard = tracing::subscriber::set_default(subscriber);
|
|
99
|
-
|
|
100
|
-
let registry = DocumentExtractorRegistry::new();
|
|
101
|
-
|
|
102
|
-
let _ = registry.get("application/pdf");
|
|
103
|
-
|
|
104
|
-
let span_names = spans.lock().unwrap();
|
|
105
|
-
assert!(
|
|
106
|
-
span_names.contains(&"get".to_string()),
|
|
107
|
-
"Expected 'get' span from registry"
|
|
108
|
-
);
|
|
109
|
-
}
|
|
110
|
-
|
|
111
|
-
#[cfg(all(feature = "pdf", feature = "office"))]
|
|
112
|
-
#[tokio::test]
|
|
113
|
-
async fn test_span_hierarchy() {
|
|
114
|
-
use kreuzberg::core::config::ExtractionConfig;
|
|
115
|
-
use kreuzberg::core::extractor::extract_bytes;
|
|
116
|
-
|
|
117
|
-
let spans = Arc::new(Mutex::new(Vec::new()));
|
|
118
|
-
let collector = SpanCollector { spans: spans.clone() };
|
|
119
|
-
|
|
120
|
-
let subscriber = tracing_subscriber::registry().with(collector);
|
|
121
|
-
let _guard = tracing::subscriber::set_default(subscriber);
|
|
122
|
-
|
|
123
|
-
let test_content = b"Hello, World!";
|
|
124
|
-
let config = ExtractionConfig::default();
|
|
125
|
-
|
|
126
|
-
let _ = extract_bytes(test_content, "text/plain", &config).await;
|
|
127
|
-
|
|
128
|
-
let span_names = spans.lock().unwrap();
|
|
129
|
-
assert!(
|
|
130
|
-
span_names.contains(&"extract_bytes".to_string()),
|
|
131
|
-
"Expected 'extract_bytes' span"
|
|
132
|
-
);
|
|
133
|
-
}
|
|
134
|
-
|
|
135
|
-
#[test]
|
|
136
|
-
fn test_span_collector_creation() {
|
|
137
|
-
let spans = Arc::new(Mutex::new(Vec::new()));
|
|
138
|
-
let _collector = SpanCollector { spans };
|
|
139
|
-
}
|
|
1
|
+
#![cfg(feature = "otel")]
|
|
2
|
+
|
|
3
|
+
use std::sync::{Arc, Mutex};
|
|
4
|
+
use tracing::Subscriber;
|
|
5
|
+
use tracing::span::{Attributes, Id};
|
|
6
|
+
use tracing_subscriber::Layer;
|
|
7
|
+
use tracing_subscriber::layer::{Context, SubscriberExt};
|
|
8
|
+
use tracing_subscriber::registry::LookupSpan;
|
|
9
|
+
|
|
10
|
+
/// Simple span name collector for testing.
|
|
11
|
+
///
|
|
12
|
+
/// This layer collects span names as they are created to verify
|
|
13
|
+
/// that instrumentation is working correctly.
|
|
14
|
+
struct SpanCollector {
|
|
15
|
+
spans: Arc<Mutex<Vec<String>>>,
|
|
16
|
+
}
|
|
17
|
+
|
|
18
|
+
impl<S: Subscriber + for<'a> LookupSpan<'a>> Layer<S> for SpanCollector {
|
|
19
|
+
fn on_new_span(&self, attrs: &Attributes<'_>, _id: &Id, _ctx: Context<'_, S>) {
|
|
20
|
+
self.spans.lock().unwrap().push(attrs.metadata().name().to_string());
|
|
21
|
+
}
|
|
22
|
+
}
|
|
23
|
+
|
|
24
|
+
#[tokio::test]
|
|
25
|
+
async fn test_cache_instrumentation() {
|
|
26
|
+
use kreuzberg::cache::GenericCache;
|
|
27
|
+
use tempfile::tempdir;
|
|
28
|
+
|
|
29
|
+
let spans = Arc::new(Mutex::new(Vec::new()));
|
|
30
|
+
let collector = SpanCollector { spans: spans.clone() };
|
|
31
|
+
|
|
32
|
+
let subscriber = tracing_subscriber::registry().with(collector);
|
|
33
|
+
let _guard = tracing::subscriber::set_default(subscriber);
|
|
34
|
+
|
|
35
|
+
let temp_dir = tempdir().unwrap();
|
|
36
|
+
let cache = GenericCache::new(
|
|
37
|
+
"test".to_string(),
|
|
38
|
+
Some(temp_dir.path().to_str().unwrap().to_string()),
|
|
39
|
+
30.0,
|
|
40
|
+
500.0,
|
|
41
|
+
1000.0,
|
|
42
|
+
)
|
|
43
|
+
.unwrap();
|
|
44
|
+
|
|
45
|
+
cache.set("test_key", b"test data".to_vec(), None).unwrap();
|
|
46
|
+
|
|
47
|
+
let _ = cache.get("test_key", None).unwrap();
|
|
48
|
+
|
|
49
|
+
let span_names = spans.lock().unwrap();
|
|
50
|
+
assert!(span_names.contains(&"set".to_string()), "Expected 'set' span");
|
|
51
|
+
assert!(span_names.contains(&"get".to_string()), "Expected 'get' span");
|
|
52
|
+
}
|
|
53
|
+
|
|
54
|
+
#[cfg(feature = "ocr")]
|
|
55
|
+
#[tokio::test]
|
|
56
|
+
async fn test_ocr_instrumentation() {
|
|
57
|
+
use kreuzberg::ocr::processor::OcrProcessor;
|
|
58
|
+
use kreuzberg::ocr::types::TesseractConfig;
|
|
59
|
+
use tempfile::tempdir;
|
|
60
|
+
|
|
61
|
+
let spans = Arc::new(Mutex::new(Vec::new()));
|
|
62
|
+
let collector = SpanCollector { spans: spans.clone() };
|
|
63
|
+
|
|
64
|
+
let subscriber = tracing_subscriber::registry().with(collector);
|
|
65
|
+
let _guard = tracing::subscriber::set_default(subscriber);
|
|
66
|
+
|
|
67
|
+
let temp_dir = tempdir().unwrap();
|
|
68
|
+
let processor = OcrProcessor::new(Some(temp_dir.path().to_path_buf())).unwrap();
|
|
69
|
+
|
|
70
|
+
let mut test_image = Vec::new();
|
|
71
|
+
let img = image::ImageBuffer::from_fn(1, 1, |_, _| image::Rgb([255u8, 255u8, 255u8]));
|
|
72
|
+
img.write_to(&mut std::io::Cursor::new(&mut test_image), image::ImageFormat::Png)
|
|
73
|
+
.unwrap();
|
|
74
|
+
|
|
75
|
+
let config = TesseractConfig {
|
|
76
|
+
output_format: "text".to_string(),
|
|
77
|
+
use_cache: false,
|
|
78
|
+
..TesseractConfig::default()
|
|
79
|
+
};
|
|
80
|
+
|
|
81
|
+
let _ = processor.process_image(&test_image, &config);
|
|
82
|
+
|
|
83
|
+
let span_names = spans.lock().unwrap();
|
|
84
|
+
assert!(
|
|
85
|
+
span_names.contains(&"process_image".to_string()),
|
|
86
|
+
"Expected 'process_image' span"
|
|
87
|
+
);
|
|
88
|
+
}
|
|
89
|
+
|
|
90
|
+
#[tokio::test]
|
|
91
|
+
async fn test_registry_instrumentation() {
|
|
92
|
+
use kreuzberg::plugins::registry::DocumentExtractorRegistry;
|
|
93
|
+
|
|
94
|
+
let spans = Arc::new(Mutex::new(Vec::new()));
|
|
95
|
+
let collector = SpanCollector { spans: spans.clone() };
|
|
96
|
+
|
|
97
|
+
let subscriber = tracing_subscriber::registry().with(collector);
|
|
98
|
+
let _guard = tracing::subscriber::set_default(subscriber);
|
|
99
|
+
|
|
100
|
+
let registry = DocumentExtractorRegistry::new();
|
|
101
|
+
|
|
102
|
+
let _ = registry.get("application/pdf");
|
|
103
|
+
|
|
104
|
+
let span_names = spans.lock().unwrap();
|
|
105
|
+
assert!(
|
|
106
|
+
span_names.contains(&"get".to_string()),
|
|
107
|
+
"Expected 'get' span from registry"
|
|
108
|
+
);
|
|
109
|
+
}
|
|
110
|
+
|
|
111
|
+
#[cfg(all(feature = "pdf", feature = "office"))]
|
|
112
|
+
#[tokio::test]
|
|
113
|
+
async fn test_span_hierarchy() {
|
|
114
|
+
use kreuzberg::core::config::ExtractionConfig;
|
|
115
|
+
use kreuzberg::core::extractor::extract_bytes;
|
|
116
|
+
|
|
117
|
+
let spans = Arc::new(Mutex::new(Vec::new()));
|
|
118
|
+
let collector = SpanCollector { spans: spans.clone() };
|
|
119
|
+
|
|
120
|
+
let subscriber = tracing_subscriber::registry().with(collector);
|
|
121
|
+
let _guard = tracing::subscriber::set_default(subscriber);
|
|
122
|
+
|
|
123
|
+
let test_content = b"Hello, World!";
|
|
124
|
+
let config = ExtractionConfig::default();
|
|
125
|
+
|
|
126
|
+
let _ = extract_bytes(test_content, "text/plain", &config).await;
|
|
127
|
+
|
|
128
|
+
let span_names = spans.lock().unwrap();
|
|
129
|
+
assert!(
|
|
130
|
+
span_names.contains(&"extract_bytes".to_string()),
|
|
131
|
+
"Expected 'extract_bytes' span"
|
|
132
|
+
);
|
|
133
|
+
}
|
|
134
|
+
|
|
135
|
+
#[test]
|
|
136
|
+
fn test_span_collector_creation() {
|
|
137
|
+
let spans = Arc::new(Mutex::new(Vec::new()));
|
|
138
|
+
let _collector = SpanCollector { spans };
|
|
139
|
+
}
|