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
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: kreuzberg
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 4.0.0.
|
|
4
|
+
version: 4.0.0.rc2
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Na'aman Hirschfeld
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: exe
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2025-
|
|
11
|
+
date: 2025-12-09 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: bundler
|
|
@@ -16,14 +16,14 @@ dependencies:
|
|
|
16
16
|
requirements:
|
|
17
17
|
- - "~>"
|
|
18
18
|
- !ruby/object:Gem::Version
|
|
19
|
-
version: '
|
|
19
|
+
version: '4.0'
|
|
20
20
|
type: :development
|
|
21
21
|
prerelease: false
|
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
|
23
23
|
requirements:
|
|
24
24
|
- - "~>"
|
|
25
25
|
- !ruby/object:Gem::Version
|
|
26
|
-
version: '
|
|
26
|
+
version: '4.0'
|
|
27
27
|
- !ruby/object:Gem::Dependency
|
|
28
28
|
name: rake
|
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
|
@@ -58,14 +58,14 @@ dependencies:
|
|
|
58
58
|
requirements:
|
|
59
59
|
- - "~>"
|
|
60
60
|
- !ruby/object:Gem::Version
|
|
61
|
-
version:
|
|
61
|
+
version: 0.9.119
|
|
62
62
|
type: :development
|
|
63
63
|
prerelease: false
|
|
64
64
|
version_requirements: !ruby/object:Gem::Requirement
|
|
65
65
|
requirements:
|
|
66
66
|
- - "~>"
|
|
67
67
|
- !ruby/object:Gem::Version
|
|
68
|
-
version:
|
|
68
|
+
version: 0.9.119
|
|
69
69
|
- !ruby/object:Gem::Dependency
|
|
70
70
|
name: rspec
|
|
71
71
|
requirement: !ruby/object:Gem::Requirement
|
|
@@ -80,76 +80,6 @@ dependencies:
|
|
|
80
80
|
- - "~>"
|
|
81
81
|
- !ruby/object:Gem::Version
|
|
82
82
|
version: '3.12'
|
|
83
|
-
- !ruby/object:Gem::Dependency
|
|
84
|
-
name: rbs
|
|
85
|
-
requirement: !ruby/object:Gem::Requirement
|
|
86
|
-
requirements:
|
|
87
|
-
- - "~>"
|
|
88
|
-
- !ruby/object:Gem::Version
|
|
89
|
-
version: '3.0'
|
|
90
|
-
type: :development
|
|
91
|
-
prerelease: false
|
|
92
|
-
version_requirements: !ruby/object:Gem::Requirement
|
|
93
|
-
requirements:
|
|
94
|
-
- - "~>"
|
|
95
|
-
- !ruby/object:Gem::Version
|
|
96
|
-
version: '3.0'
|
|
97
|
-
- !ruby/object:Gem::Dependency
|
|
98
|
-
name: rubocop
|
|
99
|
-
requirement: !ruby/object:Gem::Requirement
|
|
100
|
-
requirements:
|
|
101
|
-
- - "~>"
|
|
102
|
-
- !ruby/object:Gem::Version
|
|
103
|
-
version: '1.66'
|
|
104
|
-
type: :development
|
|
105
|
-
prerelease: false
|
|
106
|
-
version_requirements: !ruby/object:Gem::Requirement
|
|
107
|
-
requirements:
|
|
108
|
-
- - "~>"
|
|
109
|
-
- !ruby/object:Gem::Version
|
|
110
|
-
version: '1.66'
|
|
111
|
-
- !ruby/object:Gem::Dependency
|
|
112
|
-
name: rubocop-performance
|
|
113
|
-
requirement: !ruby/object:Gem::Requirement
|
|
114
|
-
requirements:
|
|
115
|
-
- - "~>"
|
|
116
|
-
- !ruby/object:Gem::Version
|
|
117
|
-
version: '1.21'
|
|
118
|
-
type: :development
|
|
119
|
-
prerelease: false
|
|
120
|
-
version_requirements: !ruby/object:Gem::Requirement
|
|
121
|
-
requirements:
|
|
122
|
-
- - "~>"
|
|
123
|
-
- !ruby/object:Gem::Version
|
|
124
|
-
version: '1.21'
|
|
125
|
-
- !ruby/object:Gem::Dependency
|
|
126
|
-
name: rubocop-rspec
|
|
127
|
-
requirement: !ruby/object:Gem::Requirement
|
|
128
|
-
requirements:
|
|
129
|
-
- - "~>"
|
|
130
|
-
- !ruby/object:Gem::Version
|
|
131
|
-
version: '3.0'
|
|
132
|
-
type: :development
|
|
133
|
-
prerelease: false
|
|
134
|
-
version_requirements: !ruby/object:Gem::Requirement
|
|
135
|
-
requirements:
|
|
136
|
-
- - "~>"
|
|
137
|
-
- !ruby/object:Gem::Version
|
|
138
|
-
version: '3.0'
|
|
139
|
-
- !ruby/object:Gem::Dependency
|
|
140
|
-
name: steep
|
|
141
|
-
requirement: !ruby/object:Gem::Requirement
|
|
142
|
-
requirements:
|
|
143
|
-
- - "~>"
|
|
144
|
-
- !ruby/object:Gem::Version
|
|
145
|
-
version: '1.8'
|
|
146
|
-
type: :development
|
|
147
|
-
prerelease: false
|
|
148
|
-
version_requirements: !ruby/object:Gem::Requirement
|
|
149
|
-
requirements:
|
|
150
|
-
- - "~>"
|
|
151
|
-
- !ruby/object:Gem::Version
|
|
152
|
-
version: '1.8'
|
|
153
83
|
- !ruby/object:Gem::Dependency
|
|
154
84
|
name: yard
|
|
155
85
|
requirement: !ruby/object:Gem::Requirement
|
|
@@ -178,6 +108,7 @@ files:
|
|
|
178
108
|
- ".gitignore"
|
|
179
109
|
- ".rspec"
|
|
180
110
|
- ".rubocop.yaml"
|
|
111
|
+
- ".rubocop.yml"
|
|
181
112
|
- Gemfile
|
|
182
113
|
- Gemfile.lock
|
|
183
114
|
- README.md
|
|
@@ -185,6 +116,7 @@ files:
|
|
|
185
116
|
- Steepfile
|
|
186
117
|
- examples/async_patterns.rb
|
|
187
118
|
- ext/kreuzberg_rb/extconf.rb
|
|
119
|
+
- ext/kreuzberg_rb/native/Cargo.lock
|
|
188
120
|
- ext/kreuzberg_rb/native/Cargo.toml
|
|
189
121
|
- ext/kreuzberg_rb/native/README.md
|
|
190
122
|
- ext/kreuzberg_rb/native/build.rs
|
|
@@ -201,6 +133,7 @@ files:
|
|
|
201
133
|
- lib/kreuzberg/cli.rb
|
|
202
134
|
- lib/kreuzberg/cli_proxy.rb
|
|
203
135
|
- lib/kreuzberg/config.rb
|
|
136
|
+
- lib/kreuzberg/error_context.rb
|
|
204
137
|
- lib/kreuzberg/errors.rb
|
|
205
138
|
- lib/kreuzberg/extraction_api.rb
|
|
206
139
|
- lib/kreuzberg/mcp_proxy.rb
|
|
@@ -210,7 +143,6 @@ files:
|
|
|
210
143
|
- lib/kreuzberg/setup_lib_path.rb
|
|
211
144
|
- lib/kreuzberg/validator_protocol.rb
|
|
212
145
|
- lib/kreuzberg/version.rb
|
|
213
|
-
- pkg/kreuzberg-4.0.0.rc1.gem
|
|
214
146
|
- sig/kreuzberg.rbs
|
|
215
147
|
- sig/kreuzberg/internal.rbs
|
|
216
148
|
- spec/binding/cache_spec.rb
|
|
@@ -223,7 +155,6 @@ files:
|
|
|
223
155
|
- spec/binding/plugins/ocr_backend_spec.rb
|
|
224
156
|
- spec/binding/plugins/postprocessor_spec.rb
|
|
225
157
|
- spec/binding/plugins/validator_spec.rb
|
|
226
|
-
- spec/examples.txt
|
|
227
158
|
- spec/fixtures/config.toml
|
|
228
159
|
- spec/fixtures/config.yaml
|
|
229
160
|
- spec/fixtures/invalid_config.toml
|
|
@@ -231,13 +162,13 @@ files:
|
|
|
231
162
|
- spec/spec_helper.rb
|
|
232
163
|
- vendor/kreuzberg/Cargo.toml
|
|
233
164
|
- vendor/kreuzberg/README.md
|
|
165
|
+
- vendor/kreuzberg/benches/otel_overhead.rs
|
|
234
166
|
- vendor/kreuzberg/build.rs
|
|
235
167
|
- vendor/kreuzberg/src/api/error.rs
|
|
236
168
|
- vendor/kreuzberg/src/api/handlers.rs
|
|
237
169
|
- vendor/kreuzberg/src/api/mod.rs
|
|
238
170
|
- vendor/kreuzberg/src/api/server.rs
|
|
239
171
|
- vendor/kreuzberg/src/api/types.rs
|
|
240
|
-
- vendor/kreuzberg/src/bin/profile_extract.rs
|
|
241
172
|
- vendor/kreuzberg/src/cache/mod.rs
|
|
242
173
|
- vendor/kreuzberg/src/chunking/mod.rs
|
|
243
174
|
- vendor/kreuzberg/src/core/batch_mode.rs
|
|
@@ -256,34 +187,46 @@ files:
|
|
|
256
187
|
- vendor/kreuzberg/src/extraction/html.rs
|
|
257
188
|
- vendor/kreuzberg/src/extraction/image.rs
|
|
258
189
|
- vendor/kreuzberg/src/extraction/libreoffice.rs
|
|
190
|
+
- vendor/kreuzberg/src/extraction/markdown.rs
|
|
259
191
|
- vendor/kreuzberg/src/extraction/mod.rs
|
|
260
192
|
- vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs
|
|
261
193
|
- vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs
|
|
262
194
|
- vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs
|
|
263
195
|
- vendor/kreuzberg/src/extraction/office_metadata/mod.rs
|
|
264
|
-
- vendor/kreuzberg/src/extraction/
|
|
265
|
-
- vendor/kreuzberg/src/extraction/pandoc/mime_types.rs
|
|
266
|
-
- vendor/kreuzberg/src/extraction/pandoc/mod.rs
|
|
267
|
-
- vendor/kreuzberg/src/extraction/pandoc/server.rs
|
|
268
|
-
- vendor/kreuzberg/src/extraction/pandoc/subprocess.rs
|
|
269
|
-
- vendor/kreuzberg/src/extraction/pandoc/version.rs
|
|
196
|
+
- vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs
|
|
270
197
|
- vendor/kreuzberg/src/extraction/pptx.rs
|
|
271
198
|
- vendor/kreuzberg/src/extraction/structured.rs
|
|
272
199
|
- vendor/kreuzberg/src/extraction/table.rs
|
|
273
200
|
- vendor/kreuzberg/src/extraction/text.rs
|
|
274
201
|
- vendor/kreuzberg/src/extraction/xml.rs
|
|
275
202
|
- vendor/kreuzberg/src/extractors/archive.rs
|
|
203
|
+
- vendor/kreuzberg/src/extractors/bibtex.rs
|
|
204
|
+
- vendor/kreuzberg/src/extractors/docbook.rs
|
|
276
205
|
- vendor/kreuzberg/src/extractors/docx.rs
|
|
277
206
|
- vendor/kreuzberg/src/extractors/email.rs
|
|
207
|
+
- vendor/kreuzberg/src/extractors/epub.rs
|
|
278
208
|
- vendor/kreuzberg/src/extractors/excel.rs
|
|
209
|
+
- vendor/kreuzberg/src/extractors/fictionbook.rs
|
|
210
|
+
- vendor/kreuzberg/src/extractors/fictionbook.rs.backup2
|
|
279
211
|
- vendor/kreuzberg/src/extractors/html.rs
|
|
280
212
|
- vendor/kreuzberg/src/extractors/image.rs
|
|
213
|
+
- vendor/kreuzberg/src/extractors/jats.rs
|
|
214
|
+
- vendor/kreuzberg/src/extractors/jupyter.rs
|
|
215
|
+
- vendor/kreuzberg/src/extractors/latex.rs
|
|
216
|
+
- vendor/kreuzberg/src/extractors/markdown.rs
|
|
281
217
|
- vendor/kreuzberg/src/extractors/mod.rs
|
|
282
|
-
- vendor/kreuzberg/src/extractors/
|
|
218
|
+
- vendor/kreuzberg/src/extractors/odt.rs
|
|
219
|
+
- vendor/kreuzberg/src/extractors/opml.rs
|
|
220
|
+
- vendor/kreuzberg/src/extractors/orgmode.rs
|
|
283
221
|
- vendor/kreuzberg/src/extractors/pdf.rs
|
|
284
222
|
- vendor/kreuzberg/src/extractors/pptx.rs
|
|
223
|
+
- vendor/kreuzberg/src/extractors/rst.rs
|
|
224
|
+
- vendor/kreuzberg/src/extractors/rtf.rs
|
|
225
|
+
- vendor/kreuzberg/src/extractors/security.rs
|
|
226
|
+
- vendor/kreuzberg/src/extractors/security_tests.rs
|
|
285
227
|
- vendor/kreuzberg/src/extractors/structured.rs
|
|
286
228
|
- vendor/kreuzberg/src/extractors/text.rs
|
|
229
|
+
- vendor/kreuzberg/src/extractors/typst.rs
|
|
287
230
|
- vendor/kreuzberg/src/extractors/xml.rs
|
|
288
231
|
- vendor/kreuzberg/src/image/dpi.rs
|
|
289
232
|
- vendor/kreuzberg/src/image/mod.rs
|
|
@@ -310,6 +253,7 @@ files:
|
|
|
310
253
|
- vendor/kreuzberg/src/ocr/types.rs
|
|
311
254
|
- vendor/kreuzberg/src/ocr/utils.rs
|
|
312
255
|
- vendor/kreuzberg/src/ocr/validation.rs
|
|
256
|
+
- vendor/kreuzberg/src/panic_context.rs
|
|
313
257
|
- vendor/kreuzberg/src/pdf/error.rs
|
|
314
258
|
- vendor/kreuzberg/src/pdf/images.rs
|
|
315
259
|
- vendor/kreuzberg/src/pdf/metadata.rs
|
|
@@ -403,30 +347,43 @@ files:
|
|
|
403
347
|
- vendor/kreuzberg/stopwords/yo_stopwords.json
|
|
404
348
|
- vendor/kreuzberg/stopwords/zh_stopwords.json
|
|
405
349
|
- vendor/kreuzberg/stopwords/zu_stopwords.json
|
|
350
|
+
- vendor/kreuzberg/tests/api_extract_multipart.rs
|
|
406
351
|
- vendor/kreuzberg/tests/api_tests.rs
|
|
407
352
|
- vendor/kreuzberg/tests/archive_integration.rs
|
|
408
353
|
- vendor/kreuzberg/tests/batch_orchestration.rs
|
|
409
354
|
- vendor/kreuzberg/tests/batch_processing.rs
|
|
410
|
-
- vendor/kreuzberg/tests/
|
|
355
|
+
- vendor/kreuzberg/tests/bibtex_parity_test.rs
|
|
411
356
|
- vendor/kreuzberg/tests/concurrency_stress.rs
|
|
412
357
|
- vendor/kreuzberg/tests/config_features.rs
|
|
413
358
|
- vendor/kreuzberg/tests/config_loading_tests.rs
|
|
414
359
|
- vendor/kreuzberg/tests/core_integration.rs
|
|
415
360
|
- vendor/kreuzberg/tests/csv_integration.rs
|
|
361
|
+
- vendor/kreuzberg/tests/docbook_extractor_tests.rs
|
|
416
362
|
- vendor/kreuzberg/tests/docx_metadata_extraction_test.rs
|
|
363
|
+
- vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs
|
|
417
364
|
- vendor/kreuzberg/tests/email_integration.rs
|
|
365
|
+
- vendor/kreuzberg/tests/epub_native_extractor_tests.rs
|
|
418
366
|
- vendor/kreuzberg/tests/error_handling.rs
|
|
367
|
+
- vendor/kreuzberg/tests/fictionbook_extractor_tests.rs
|
|
419
368
|
- vendor/kreuzberg/tests/format_integration.rs
|
|
420
369
|
- vendor/kreuzberg/tests/helpers/mod.rs
|
|
370
|
+
- vendor/kreuzberg/tests/html_table_test.rs
|
|
421
371
|
- vendor/kreuzberg/tests/image_integration.rs
|
|
372
|
+
- vendor/kreuzberg/tests/instrumentation_test.rs
|
|
373
|
+
- vendor/kreuzberg/tests/jats_extractor_tests.rs
|
|
374
|
+
- vendor/kreuzberg/tests/jupyter_extractor_tests.rs
|
|
422
375
|
- vendor/kreuzberg/tests/keywords_integration.rs
|
|
423
376
|
- vendor/kreuzberg/tests/keywords_quality.rs
|
|
377
|
+
- vendor/kreuzberg/tests/latex_extractor_tests.rs
|
|
378
|
+
- vendor/kreuzberg/tests/markdown_extractor_tests.rs
|
|
424
379
|
- vendor/kreuzberg/tests/mime_detection.rs
|
|
425
380
|
- vendor/kreuzberg/tests/ocr_configuration.rs
|
|
426
381
|
- vendor/kreuzberg/tests/ocr_errors.rs
|
|
427
382
|
- vendor/kreuzberg/tests/ocr_quality.rs
|
|
428
383
|
- vendor/kreuzberg/tests/ocr_stress.rs
|
|
429
|
-
- vendor/kreuzberg/tests/
|
|
384
|
+
- vendor/kreuzberg/tests/odt_extractor_tests.rs
|
|
385
|
+
- vendor/kreuzberg/tests/opml_extractor_tests.rs
|
|
386
|
+
- vendor/kreuzberg/tests/orgmode_extractor_tests.rs
|
|
430
387
|
- vendor/kreuzberg/tests/pdf_integration.rs
|
|
431
388
|
- vendor/kreuzberg/tests/pipeline_integration.rs
|
|
432
389
|
- vendor/kreuzberg/tests/plugin_ocr_backend_test.rs
|
|
@@ -434,21 +391,59 @@ files:
|
|
|
434
391
|
- vendor/kreuzberg/tests/plugin_system.rs
|
|
435
392
|
- vendor/kreuzberg/tests/plugin_validator_test.rs
|
|
436
393
|
- vendor/kreuzberg/tests/registry_integration_tests.rs
|
|
394
|
+
- vendor/kreuzberg/tests/rst_extractor_tests.rs
|
|
395
|
+
- vendor/kreuzberg/tests/rtf_extractor_tests.rs
|
|
437
396
|
- vendor/kreuzberg/tests/security_validation.rs
|
|
438
397
|
- vendor/kreuzberg/tests/stopwords_integration_test.rs
|
|
439
398
|
- vendor/kreuzberg/tests/test_fastembed.rs
|
|
399
|
+
- vendor/kreuzberg/tests/typst_behavioral_tests.rs
|
|
400
|
+
- vendor/kreuzberg/tests/typst_extractor_tests.rs
|
|
440
401
|
- vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs
|
|
441
|
-
|
|
402
|
+
- vendor/rb-sys/.cargo-ok
|
|
403
|
+
- vendor/rb-sys/.cargo_vcs_info.json
|
|
404
|
+
- vendor/rb-sys/Cargo.lock
|
|
405
|
+
- vendor/rb-sys/Cargo.toml
|
|
406
|
+
- vendor/rb-sys/Cargo.toml.orig
|
|
407
|
+
- vendor/rb-sys/LICENSE-APACHE
|
|
408
|
+
- vendor/rb-sys/LICENSE-MIT
|
|
409
|
+
- vendor/rb-sys/bin/release.sh
|
|
410
|
+
- vendor/rb-sys/build/features.rs
|
|
411
|
+
- vendor/rb-sys/build/main.rs
|
|
412
|
+
- vendor/rb-sys/build/stable_api_config.rs
|
|
413
|
+
- vendor/rb-sys/build/version.rs
|
|
414
|
+
- vendor/rb-sys/readme.md
|
|
415
|
+
- vendor/rb-sys/src/bindings.rs
|
|
416
|
+
- vendor/rb-sys/src/hidden.rs
|
|
417
|
+
- vendor/rb-sys/src/lib.rs
|
|
418
|
+
- vendor/rb-sys/src/macros.rs
|
|
419
|
+
- vendor/rb-sys/src/memory.rs
|
|
420
|
+
- vendor/rb-sys/src/ruby_abi_version.rs
|
|
421
|
+
- vendor/rb-sys/src/special_consts.rs
|
|
422
|
+
- vendor/rb-sys/src/stable_api.rs
|
|
423
|
+
- vendor/rb-sys/src/stable_api/compiled.c
|
|
424
|
+
- vendor/rb-sys/src/stable_api/compiled.rs
|
|
425
|
+
- vendor/rb-sys/src/stable_api/ruby_2_6.rs
|
|
426
|
+
- vendor/rb-sys/src/stable_api/ruby_2_7.rs
|
|
427
|
+
- vendor/rb-sys/src/stable_api/ruby_3_0.rs
|
|
428
|
+
- vendor/rb-sys/src/stable_api/ruby_3_1.rs
|
|
429
|
+
- vendor/rb-sys/src/stable_api/ruby_3_2.rs
|
|
430
|
+
- vendor/rb-sys/src/stable_api/ruby_3_3.rs
|
|
431
|
+
- vendor/rb-sys/src/stable_api/ruby_3_4.rs
|
|
432
|
+
- vendor/rb-sys/src/symbol.rs
|
|
433
|
+
- vendor/rb-sys/src/tracking_allocator.rs
|
|
434
|
+
- vendor/rb-sys/src/utils.rs
|
|
435
|
+
- vendor/rb-sys/src/value_type.rs
|
|
436
|
+
homepage: https://github.com/kreuzberg-dev/kreuzberg
|
|
442
437
|
licenses:
|
|
443
438
|
- MIT
|
|
444
439
|
metadata:
|
|
445
|
-
|
|
446
|
-
|
|
447
|
-
changelog_uri: https://github.com/Goldziher/kreuzberg/blob/main/CHANGELOG.md
|
|
440
|
+
bug_tracker_uri: https://github.com/kreuzberg-dev/kreuzberg/issues
|
|
441
|
+
changelog_uri: https://github.com/kreuzberg-dev/kreuzberg/blob/main/CHANGELOG.md
|
|
448
442
|
documentation_uri: https://docs.kreuzberg.dev
|
|
449
|
-
|
|
450
|
-
rubygems_mfa_required: 'true'
|
|
443
|
+
homepage_uri: https://github.com/kreuzberg-dev/kreuzberg
|
|
451
444
|
keywords: document-intelligence,document-extraction,ocr,rust,bindings
|
|
445
|
+
rubygems_mfa_required: 'true'
|
|
446
|
+
source_code_uri: https://github.com/kreuzberg-dev/kreuzberg
|
|
452
447
|
post_install_message:
|
|
453
448
|
rdoc_options: []
|
|
454
449
|
require_paths:
|
|
@@ -464,7 +459,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
464
459
|
- !ruby/object:Gem::Version
|
|
465
460
|
version: '0'
|
|
466
461
|
requirements: []
|
|
467
|
-
rubygems_version: 3.
|
|
462
|
+
rubygems_version: 3.4.20
|
|
468
463
|
signing_key:
|
|
469
464
|
specification_version: 4
|
|
470
465
|
summary: High-performance document intelligence framework
|
data/pkg/kreuzberg-4.0.0.rc1.gem
DELETED
|
Binary file
|
data/spec/examples.txt
DELETED
|
@@ -1,104 +0,0 @@
|
|
|
1
|
-
example_id | status | run_time |
|
|
2
|
-
---------------------------------------------------------------------------------- | ------ | --------------- |
|
|
3
|
-
./spec/binding/plugins/ocr_backend_spec.rb[1:1:1] | failed | 0.00173 seconds |
|
|
4
|
-
./spec/binding/plugins/ocr_backend_spec.rb[1:1:2] | failed | 0.0018 seconds |
|
|
5
|
-
./spec/binding/plugins/ocr_backend_spec.rb[1:2:1] | failed | 0.00192 seconds |
|
|
6
|
-
./spec/binding/plugins/ocr_backend_spec.rb[1:2:2] | failed | 0.00581 seconds |
|
|
7
|
-
./spec/binding/plugins/ocr_backend_spec.rb[1:3:1] | failed | 0.00184 seconds |
|
|
8
|
-
./spec/binding/plugins/ocr_backend_spec.rb[1:4:1] | passed | 0.00088 seconds |
|
|
9
|
-
./spec/binding/plugins/ocr_backend_spec.rb[1:4:2] | passed | 0.00045 seconds |
|
|
10
|
-
./spec/binding/plugins/ocr_backend_spec.rb[1:5:1] | passed | 0.00007 seconds |
|
|
11
|
-
./spec/binding/plugins/ocr_backend_spec.rb[1:5:2] | passed | 0.00052 seconds |
|
|
12
|
-
./spec/binding/plugins/ocr_backend_spec.rb[1:6:1:1] | passed | 0.00012 seconds |
|
|
13
|
-
./spec/binding/plugins/ocr_backend_spec.rb[1:6:1:2] | passed | 0.00079 seconds |
|
|
14
|
-
./spec/binding/plugins/ocr_backend_spec.rb[1:6:2:1] | passed | 0.00004 seconds |
|
|
15
|
-
./spec/binding/plugins/ocr_backend_spec.rb[1:6:2:2] | passed | 0.00029 seconds |
|
|
16
|
-
./spec/binding/plugins/postprocessor_spec.rb[1:1:1] | failed | 0.00139 seconds |
|
|
17
|
-
./spec/binding/plugins/postprocessor_spec.rb[1:1:2] | failed | 0.00153 seconds |
|
|
18
|
-
./spec/binding/plugins/postprocessor_spec.rb[1:1:3] | failed | 0.0014 seconds |
|
|
19
|
-
./spec/binding/plugins/postprocessor_spec.rb[1:2:1] | failed | 0.00182 seconds |
|
|
20
|
-
./spec/binding/plugins/postprocessor_spec.rb[1:2:2] | failed | 0.00209 seconds |
|
|
21
|
-
./spec/binding/plugins/postprocessor_spec.rb[1:3:1] | failed | 0.00165 seconds |
|
|
22
|
-
./spec/binding/plugins/postprocessor_spec.rb[1:4:1] | failed | 0.00142 seconds |
|
|
23
|
-
./spec/binding/plugins/postprocessor_spec.rb[1:4:2] | failed | 0.00148 seconds |
|
|
24
|
-
./spec/binding/plugins/postprocessor_spec.rb[1:5:1] | failed | 0.00148 seconds |
|
|
25
|
-
./spec/binding/plugins/postprocessor_spec.rb[1:6:1] | passed | 0.0001 seconds |
|
|
26
|
-
./spec/binding/plugins/postprocessor_spec.rb[1:6:2] | passed | 0.00011 seconds |
|
|
27
|
-
./spec/binding/plugins/postprocessor_spec.rb[1:7:1] | passed | 0.00003 seconds |
|
|
28
|
-
./spec/binding/plugins/postprocessor_spec.rb[1:7:2] | passed | 0.00002 seconds |
|
|
29
|
-
./spec/binding/plugins/postprocessor_spec.rb[1:7:3] | passed | 0.00003 seconds |
|
|
30
|
-
./spec/binding/plugins/postprocessor_spec.rb[1:7:4] | passed | 0.00006 seconds |
|
|
31
|
-
./spec/binding/plugins/validator_spec.rb[1:1:1] | failed | 0.00154 seconds |
|
|
32
|
-
./spec/binding/plugins/validator_spec.rb[1:1:2] | failed | 0.00171 seconds |
|
|
33
|
-
./spec/binding/plugins/validator_spec.rb[1:1:3] | passed | 0.00099 seconds |
|
|
34
|
-
./spec/binding/plugins/validator_spec.rb[1:2:1] | failed | 0.00186 seconds |
|
|
35
|
-
./spec/binding/plugins/validator_spec.rb[1:2:2] | failed | 0.0016 seconds |
|
|
36
|
-
./spec/binding/plugins/validator_spec.rb[1:3:1] | failed | 0.00182 seconds |
|
|
37
|
-
./spec/binding/plugins/validator_spec.rb[1:3:2] | failed | 0.0128 seconds |
|
|
38
|
-
./spec/binding/plugins/validator_spec.rb[1:4:1] | failed | 0.00156 seconds |
|
|
39
|
-
./spec/binding/plugins/validator_spec.rb[1:4:2] | passed | 0.0001 seconds |
|
|
40
|
-
./spec/binding/plugins/validator_spec.rb[1:5:1] | failed | 0.00445 seconds |
|
|
41
|
-
./spec/binding/plugins/validator_spec.rb[1:5:2] | failed | 0.00198 seconds |
|
|
42
|
-
./spec/binding/plugins/validator_spec.rb[1:6:1] | failed | 0.00179 seconds |
|
|
43
|
-
./spec/binding/plugins/validator_spec.rb[1:7:1] | passed | 0.00068 seconds |
|
|
44
|
-
./spec/binding/plugins/validator_spec.rb[1:7:2] | passed | 0.00088 seconds |
|
|
45
|
-
./spec/binding/plugins/validator_spec.rb[1:7:3] | passed | 0.00045 seconds |
|
|
46
|
-
./spec/binding/plugins/validator_spec.rb[1:7:4] | passed | 0.00004 seconds |
|
|
47
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/email_spec.rb[1:1] | passed | 0.01048 seconds |
|
|
48
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/html_spec.rb[1:1] | passed | 1.95 seconds |
|
|
49
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/html_spec.rb[1:2] | passed | 0.00031 seconds |
|
|
50
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/image_spec.rb[1:1] | passed | 0.0027 seconds |
|
|
51
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/ocr_spec.rb[1:1] | passed | 0.04721 seconds |
|
|
52
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/ocr_spec.rb[1:2] | passed | 0.04402 seconds |
|
|
53
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/ocr_spec.rb[1:3] | passed | 3.41 seconds |
|
|
54
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/ocr_spec.rb[1:4] | passed | 0.34493 seconds |
|
|
55
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/ocr_spec.rb[1:5] | passed | 0.33223 seconds |
|
|
56
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:1] | passed | 2.74 seconds |
|
|
57
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:2] | passed | 0.00021 seconds |
|
|
58
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:3] | passed | 0.00035 seconds |
|
|
59
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:4] | passed | 0.00021 seconds |
|
|
60
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:5] | passed | 0.0003 seconds |
|
|
61
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:6] | passed | 0.00027 seconds |
|
|
62
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:7] | passed | 0.00023 seconds |
|
|
63
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:8] | passed | 0.00016 seconds |
|
|
64
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:9] | passed | 2.65 seconds |
|
|
65
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:10] | passed | 0.0003 seconds |
|
|
66
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:11] | passed | 0.0002 seconds |
|
|
67
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:12] | passed | 0.00984 seconds |
|
|
68
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:13] | passed | 0.00096 seconds |
|
|
69
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:14] | passed | 0.00115 seconds |
|
|
70
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:15] | passed | 0.00038 seconds |
|
|
71
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/office_spec.rb[1:16] | passed | 0.00448 seconds |
|
|
72
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:1] | passed | 0.99668 seconds |
|
|
73
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:2] | passed | 4.11 seconds |
|
|
74
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:3] | passed | 0.00451 seconds |
|
|
75
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:4] | passed | 0.07588 seconds |
|
|
76
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:5] | passed | 0.00339 seconds |
|
|
77
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:6] | passed | 0.00238 seconds |
|
|
78
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:7] | passed | 0.24683 seconds |
|
|
79
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:8] | passed | 0.07999 seconds |
|
|
80
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:9] | passed | 0.01214 seconds |
|
|
81
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:10] | passed | 0.00095 seconds |
|
|
82
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:11] | passed | 0.03728 seconds |
|
|
83
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:12] | passed | 0.01741 seconds |
|
|
84
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:13] | passed | 0.0036 seconds |
|
|
85
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/pdf_spec.rb[1:14] | passed | 0.89424 seconds |
|
|
86
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[1:1] | passed | 0.00228 seconds |
|
|
87
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[1:2] | passed | 0.0012 seconds |
|
|
88
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[2:1] | passed | 0.0008 seconds |
|
|
89
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[2:2] | passed | 0.00119 seconds |
|
|
90
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[2:3] | passed | 0.0013 seconds |
|
|
91
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[3:1] | passed | 0.00184 seconds |
|
|
92
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[3:2] | passed | 0.00053 seconds |
|
|
93
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[3:3] | passed | 0.00004 seconds |
|
|
94
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[4:1] | passed | 0.00049 seconds |
|
|
95
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[4:2] | passed | 0.00006 seconds |
|
|
96
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[4:3] | passed | 0.00005 seconds |
|
|
97
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[5:1] | passed | 0.00007 seconds |
|
|
98
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[5:2] | passed | 0.00011 seconds |
|
|
99
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[6:1] | passed | 0.00003 seconds |
|
|
100
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/plugin_apis_spec.rb[6:2] | passed | 0.00002 seconds |
|
|
101
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/structured_spec.rb[1:1] | passed | 0.00101 seconds |
|
|
102
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/structured_spec.rb[1:2] | passed | 0.00041 seconds |
|
|
103
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/structured_spec.rb[1:3] | passed | 0.00035 seconds |
|
|
104
|
-
/Users/naamanhirschfeld/workspace/kreuzberg/e2e/ruby/spec/xml_spec.rb[1:1] | passed | 0.00078 seconds |
|