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
|
@@ -1,111 +1,111 @@
|
|
|
1
|
-
[
|
|
2
|
-
"a",
|
|
3
|
-
"ach",
|
|
4
|
-
"ag",
|
|
5
|
-
"agus",
|
|
6
|
-
"an",
|
|
7
|
-
"aon",
|
|
8
|
-
"ar",
|
|
9
|
-
"arna",
|
|
10
|
-
"as",
|
|
11
|
-
"b'",
|
|
12
|
-
"ba",
|
|
13
|
-
"beirt",
|
|
14
|
-
"bhúr",
|
|
15
|
-
"caoga",
|
|
16
|
-
"ceathair",
|
|
17
|
-
"ceathrar",
|
|
18
|
-
"chomh",
|
|
19
|
-
"chtó",
|
|
20
|
-
"chuig",
|
|
21
|
-
"chun",
|
|
22
|
-
"cois",
|
|
23
|
-
"céad",
|
|
24
|
-
"cúig",
|
|
25
|
-
"cúigear",
|
|
26
|
-
"d'",
|
|
27
|
-
"daichead",
|
|
28
|
-
"dar",
|
|
29
|
-
"de",
|
|
30
|
-
"deich",
|
|
31
|
-
"deichniúr",
|
|
32
|
-
"den",
|
|
33
|
-
"dhá",
|
|
34
|
-
"do",
|
|
35
|
-
"don",
|
|
36
|
-
"dtí",
|
|
37
|
-
"dá",
|
|
38
|
-
"dár",
|
|
39
|
-
"dó",
|
|
40
|
-
"faoi",
|
|
41
|
-
"faoin",
|
|
42
|
-
"faoina",
|
|
43
|
-
"faoinár",
|
|
44
|
-
"fara",
|
|
45
|
-
"fiche",
|
|
46
|
-
"gach",
|
|
47
|
-
"gan",
|
|
48
|
-
"go",
|
|
49
|
-
"gur",
|
|
50
|
-
"haon",
|
|
51
|
-
"hocht",
|
|
52
|
-
"i",
|
|
53
|
-
"iad",
|
|
54
|
-
"idir",
|
|
55
|
-
"in",
|
|
56
|
-
"ina",
|
|
57
|
-
"ins",
|
|
58
|
-
"inár",
|
|
59
|
-
"is",
|
|
60
|
-
"le",
|
|
61
|
-
"leis",
|
|
62
|
-
"lena",
|
|
63
|
-
"lenár",
|
|
64
|
-
"m'",
|
|
65
|
-
"mar",
|
|
66
|
-
"mo",
|
|
67
|
-
"mé",
|
|
68
|
-
"na",
|
|
69
|
-
"nach",
|
|
70
|
-
"naoi",
|
|
71
|
-
"naonúr",
|
|
72
|
-
"ná",
|
|
73
|
-
"ní",
|
|
74
|
-
"níor",
|
|
75
|
-
"nó",
|
|
76
|
-
"nócha",
|
|
77
|
-
"ocht",
|
|
78
|
-
"ochtar",
|
|
79
|
-
"os",
|
|
80
|
-
"roimh",
|
|
81
|
-
"sa",
|
|
82
|
-
"seacht",
|
|
83
|
-
"seachtar",
|
|
84
|
-
"seachtó",
|
|
85
|
-
"seasca",
|
|
86
|
-
"seisear",
|
|
87
|
-
"siad",
|
|
88
|
-
"sibh",
|
|
89
|
-
"sinn",
|
|
90
|
-
"sna",
|
|
91
|
-
"sé",
|
|
92
|
-
"sí",
|
|
93
|
-
"tar",
|
|
94
|
-
"thar",
|
|
95
|
-
"thú",
|
|
96
|
-
"triúr",
|
|
97
|
-
"trí",
|
|
98
|
-
"trína",
|
|
99
|
-
"trínár",
|
|
100
|
-
"tríocha",
|
|
101
|
-
"tú",
|
|
102
|
-
"um",
|
|
103
|
-
"ár",
|
|
104
|
-
"é",
|
|
105
|
-
"éis",
|
|
106
|
-
"í",
|
|
107
|
-
"ó",
|
|
108
|
-
"ón",
|
|
109
|
-
"óna",
|
|
110
|
-
"ónár"
|
|
111
|
-
]
|
|
1
|
+
[
|
|
2
|
+
"a",
|
|
3
|
+
"ach",
|
|
4
|
+
"ag",
|
|
5
|
+
"agus",
|
|
6
|
+
"an",
|
|
7
|
+
"aon",
|
|
8
|
+
"ar",
|
|
9
|
+
"arna",
|
|
10
|
+
"as",
|
|
11
|
+
"b'",
|
|
12
|
+
"ba",
|
|
13
|
+
"beirt",
|
|
14
|
+
"bhúr",
|
|
15
|
+
"caoga",
|
|
16
|
+
"ceathair",
|
|
17
|
+
"ceathrar",
|
|
18
|
+
"chomh",
|
|
19
|
+
"chtó",
|
|
20
|
+
"chuig",
|
|
21
|
+
"chun",
|
|
22
|
+
"cois",
|
|
23
|
+
"céad",
|
|
24
|
+
"cúig",
|
|
25
|
+
"cúigear",
|
|
26
|
+
"d'",
|
|
27
|
+
"daichead",
|
|
28
|
+
"dar",
|
|
29
|
+
"de",
|
|
30
|
+
"deich",
|
|
31
|
+
"deichniúr",
|
|
32
|
+
"den",
|
|
33
|
+
"dhá",
|
|
34
|
+
"do",
|
|
35
|
+
"don",
|
|
36
|
+
"dtí",
|
|
37
|
+
"dá",
|
|
38
|
+
"dár",
|
|
39
|
+
"dó",
|
|
40
|
+
"faoi",
|
|
41
|
+
"faoin",
|
|
42
|
+
"faoina",
|
|
43
|
+
"faoinár",
|
|
44
|
+
"fara",
|
|
45
|
+
"fiche",
|
|
46
|
+
"gach",
|
|
47
|
+
"gan",
|
|
48
|
+
"go",
|
|
49
|
+
"gur",
|
|
50
|
+
"haon",
|
|
51
|
+
"hocht",
|
|
52
|
+
"i",
|
|
53
|
+
"iad",
|
|
54
|
+
"idir",
|
|
55
|
+
"in",
|
|
56
|
+
"ina",
|
|
57
|
+
"ins",
|
|
58
|
+
"inár",
|
|
59
|
+
"is",
|
|
60
|
+
"le",
|
|
61
|
+
"leis",
|
|
62
|
+
"lena",
|
|
63
|
+
"lenár",
|
|
64
|
+
"m'",
|
|
65
|
+
"mar",
|
|
66
|
+
"mo",
|
|
67
|
+
"mé",
|
|
68
|
+
"na",
|
|
69
|
+
"nach",
|
|
70
|
+
"naoi",
|
|
71
|
+
"naonúr",
|
|
72
|
+
"ná",
|
|
73
|
+
"ní",
|
|
74
|
+
"níor",
|
|
75
|
+
"nó",
|
|
76
|
+
"nócha",
|
|
77
|
+
"ocht",
|
|
78
|
+
"ochtar",
|
|
79
|
+
"os",
|
|
80
|
+
"roimh",
|
|
81
|
+
"sa",
|
|
82
|
+
"seacht",
|
|
83
|
+
"seachtar",
|
|
84
|
+
"seachtó",
|
|
85
|
+
"seasca",
|
|
86
|
+
"seisear",
|
|
87
|
+
"siad",
|
|
88
|
+
"sibh",
|
|
89
|
+
"sinn",
|
|
90
|
+
"sna",
|
|
91
|
+
"sé",
|
|
92
|
+
"sí",
|
|
93
|
+
"tar",
|
|
94
|
+
"thar",
|
|
95
|
+
"thú",
|
|
96
|
+
"triúr",
|
|
97
|
+
"trí",
|
|
98
|
+
"trína",
|
|
99
|
+
"trínár",
|
|
100
|
+
"tríocha",
|
|
101
|
+
"tú",
|
|
102
|
+
"um",
|
|
103
|
+
"ár",
|
|
104
|
+
"é",
|
|
105
|
+
"éis",
|
|
106
|
+
"í",
|
|
107
|
+
"ó",
|
|
108
|
+
"ón",
|
|
109
|
+
"óna",
|
|
110
|
+
"ónár"
|
|
111
|
+
]
|
|
@@ -1,162 +1,162 @@
|
|
|
1
|
-
[
|
|
2
|
-
"a",
|
|
3
|
-
"alí",
|
|
4
|
-
"ao",
|
|
5
|
-
"aos",
|
|
6
|
-
"aquel",
|
|
7
|
-
"aquela",
|
|
8
|
-
"aquelas",
|
|
9
|
-
"aqueles",
|
|
10
|
-
"aquilo",
|
|
11
|
-
"aquí",
|
|
12
|
-
"as",
|
|
13
|
-
"así",
|
|
14
|
-
"aínda",
|
|
15
|
-
"ben",
|
|
16
|
-
"cando",
|
|
17
|
-
"che",
|
|
18
|
-
"co",
|
|
19
|
-
"coa",
|
|
20
|
-
"coas",
|
|
21
|
-
"comigo",
|
|
22
|
-
"con",
|
|
23
|
-
"connosco",
|
|
24
|
-
"contigo",
|
|
25
|
-
"convosco",
|
|
26
|
-
"cos",
|
|
27
|
-
"cun",
|
|
28
|
-
"cunha",
|
|
29
|
-
"cunhas",
|
|
30
|
-
"cuns",
|
|
31
|
-
"da",
|
|
32
|
-
"dalgunha",
|
|
33
|
-
"dalgunhas",
|
|
34
|
-
"dalgún",
|
|
35
|
-
"dalgúns",
|
|
36
|
-
"das",
|
|
37
|
-
"de",
|
|
38
|
-
"del",
|
|
39
|
-
"dela",
|
|
40
|
-
"delas",
|
|
41
|
-
"deles",
|
|
42
|
-
"desde",
|
|
43
|
-
"deste",
|
|
44
|
-
"do",
|
|
45
|
-
"dos",
|
|
46
|
-
"dun",
|
|
47
|
-
"dunha",
|
|
48
|
-
"dunhas",
|
|
49
|
-
"duns",
|
|
50
|
-
"e",
|
|
51
|
-
"el",
|
|
52
|
-
"ela",
|
|
53
|
-
"elas",
|
|
54
|
-
"eles",
|
|
55
|
-
"en",
|
|
56
|
-
"era",
|
|
57
|
-
"eran",
|
|
58
|
-
"esa",
|
|
59
|
-
"esas",
|
|
60
|
-
"ese",
|
|
61
|
-
"eses",
|
|
62
|
-
"esta",
|
|
63
|
-
"estaba",
|
|
64
|
-
"estar",
|
|
65
|
-
"este",
|
|
66
|
-
"estes",
|
|
67
|
-
"estiven",
|
|
68
|
-
"estou",
|
|
69
|
-
"está",
|
|
70
|
-
"están",
|
|
71
|
-
"eu",
|
|
72
|
-
"facer",
|
|
73
|
-
"foi",
|
|
74
|
-
"foron",
|
|
75
|
-
"fun",
|
|
76
|
-
"había",
|
|
77
|
-
"hai",
|
|
78
|
-
"iso",
|
|
79
|
-
"isto",
|
|
80
|
-
"la",
|
|
81
|
-
"las",
|
|
82
|
-
"lle",
|
|
83
|
-
"lles",
|
|
84
|
-
"lo",
|
|
85
|
-
"los",
|
|
86
|
-
"mais",
|
|
87
|
-
"me",
|
|
88
|
-
"meu",
|
|
89
|
-
"meus",
|
|
90
|
-
"min",
|
|
91
|
-
"miña",
|
|
92
|
-
"miñas",
|
|
93
|
-
"moi",
|
|
94
|
-
"na",
|
|
95
|
-
"nas",
|
|
96
|
-
"neste",
|
|
97
|
-
"nin",
|
|
98
|
-
"no",
|
|
99
|
-
"non",
|
|
100
|
-
"nos",
|
|
101
|
-
"nosa",
|
|
102
|
-
"nosas",
|
|
103
|
-
"noso",
|
|
104
|
-
"nosos",
|
|
105
|
-
"nun",
|
|
106
|
-
"nunha",
|
|
107
|
-
"nunhas",
|
|
108
|
-
"nuns",
|
|
109
|
-
"nós",
|
|
110
|
-
"o",
|
|
111
|
-
"os",
|
|
112
|
-
"ou",
|
|
113
|
-
"para",
|
|
114
|
-
"pero",
|
|
115
|
-
"pode",
|
|
116
|
-
"pois",
|
|
117
|
-
"pola",
|
|
118
|
-
"polas",
|
|
119
|
-
"polo",
|
|
120
|
-
"polos",
|
|
121
|
-
"por",
|
|
122
|
-
"que",
|
|
123
|
-
"se",
|
|
124
|
-
"senón",
|
|
125
|
-
"ser",
|
|
126
|
-
"seu",
|
|
127
|
-
"seus",
|
|
128
|
-
"sexa",
|
|
129
|
-
"sido",
|
|
130
|
-
"sobre",
|
|
131
|
-
"súa",
|
|
132
|
-
"súas",
|
|
133
|
-
"tamén",
|
|
134
|
-
"tan",
|
|
135
|
-
"te",
|
|
136
|
-
"ten",
|
|
137
|
-
"ter",
|
|
138
|
-
"teu",
|
|
139
|
-
"teus",
|
|
140
|
-
"teñen",
|
|
141
|
-
"teño",
|
|
142
|
-
"ti",
|
|
143
|
-
"tido",
|
|
144
|
-
"tiven",
|
|
145
|
-
"tiña",
|
|
146
|
-
"túa",
|
|
147
|
-
"túas",
|
|
148
|
-
"un",
|
|
149
|
-
"unha",
|
|
150
|
-
"unhas",
|
|
151
|
-
"uns",
|
|
152
|
-
"vos",
|
|
153
|
-
"vosa",
|
|
154
|
-
"vosas",
|
|
155
|
-
"voso",
|
|
156
|
-
"vosos",
|
|
157
|
-
"vós",
|
|
158
|
-
"á",
|
|
159
|
-
"é",
|
|
160
|
-
"ó",
|
|
161
|
-
"ós"
|
|
162
|
-
]
|
|
1
|
+
[
|
|
2
|
+
"a",
|
|
3
|
+
"alí",
|
|
4
|
+
"ao",
|
|
5
|
+
"aos",
|
|
6
|
+
"aquel",
|
|
7
|
+
"aquela",
|
|
8
|
+
"aquelas",
|
|
9
|
+
"aqueles",
|
|
10
|
+
"aquilo",
|
|
11
|
+
"aquí",
|
|
12
|
+
"as",
|
|
13
|
+
"así",
|
|
14
|
+
"aínda",
|
|
15
|
+
"ben",
|
|
16
|
+
"cando",
|
|
17
|
+
"che",
|
|
18
|
+
"co",
|
|
19
|
+
"coa",
|
|
20
|
+
"coas",
|
|
21
|
+
"comigo",
|
|
22
|
+
"con",
|
|
23
|
+
"connosco",
|
|
24
|
+
"contigo",
|
|
25
|
+
"convosco",
|
|
26
|
+
"cos",
|
|
27
|
+
"cun",
|
|
28
|
+
"cunha",
|
|
29
|
+
"cunhas",
|
|
30
|
+
"cuns",
|
|
31
|
+
"da",
|
|
32
|
+
"dalgunha",
|
|
33
|
+
"dalgunhas",
|
|
34
|
+
"dalgún",
|
|
35
|
+
"dalgúns",
|
|
36
|
+
"das",
|
|
37
|
+
"de",
|
|
38
|
+
"del",
|
|
39
|
+
"dela",
|
|
40
|
+
"delas",
|
|
41
|
+
"deles",
|
|
42
|
+
"desde",
|
|
43
|
+
"deste",
|
|
44
|
+
"do",
|
|
45
|
+
"dos",
|
|
46
|
+
"dun",
|
|
47
|
+
"dunha",
|
|
48
|
+
"dunhas",
|
|
49
|
+
"duns",
|
|
50
|
+
"e",
|
|
51
|
+
"el",
|
|
52
|
+
"ela",
|
|
53
|
+
"elas",
|
|
54
|
+
"eles",
|
|
55
|
+
"en",
|
|
56
|
+
"era",
|
|
57
|
+
"eran",
|
|
58
|
+
"esa",
|
|
59
|
+
"esas",
|
|
60
|
+
"ese",
|
|
61
|
+
"eses",
|
|
62
|
+
"esta",
|
|
63
|
+
"estaba",
|
|
64
|
+
"estar",
|
|
65
|
+
"este",
|
|
66
|
+
"estes",
|
|
67
|
+
"estiven",
|
|
68
|
+
"estou",
|
|
69
|
+
"está",
|
|
70
|
+
"están",
|
|
71
|
+
"eu",
|
|
72
|
+
"facer",
|
|
73
|
+
"foi",
|
|
74
|
+
"foron",
|
|
75
|
+
"fun",
|
|
76
|
+
"había",
|
|
77
|
+
"hai",
|
|
78
|
+
"iso",
|
|
79
|
+
"isto",
|
|
80
|
+
"la",
|
|
81
|
+
"las",
|
|
82
|
+
"lle",
|
|
83
|
+
"lles",
|
|
84
|
+
"lo",
|
|
85
|
+
"los",
|
|
86
|
+
"mais",
|
|
87
|
+
"me",
|
|
88
|
+
"meu",
|
|
89
|
+
"meus",
|
|
90
|
+
"min",
|
|
91
|
+
"miña",
|
|
92
|
+
"miñas",
|
|
93
|
+
"moi",
|
|
94
|
+
"na",
|
|
95
|
+
"nas",
|
|
96
|
+
"neste",
|
|
97
|
+
"nin",
|
|
98
|
+
"no",
|
|
99
|
+
"non",
|
|
100
|
+
"nos",
|
|
101
|
+
"nosa",
|
|
102
|
+
"nosas",
|
|
103
|
+
"noso",
|
|
104
|
+
"nosos",
|
|
105
|
+
"nun",
|
|
106
|
+
"nunha",
|
|
107
|
+
"nunhas",
|
|
108
|
+
"nuns",
|
|
109
|
+
"nós",
|
|
110
|
+
"o",
|
|
111
|
+
"os",
|
|
112
|
+
"ou",
|
|
113
|
+
"para",
|
|
114
|
+
"pero",
|
|
115
|
+
"pode",
|
|
116
|
+
"pois",
|
|
117
|
+
"pola",
|
|
118
|
+
"polas",
|
|
119
|
+
"polo",
|
|
120
|
+
"polos",
|
|
121
|
+
"por",
|
|
122
|
+
"que",
|
|
123
|
+
"se",
|
|
124
|
+
"senón",
|
|
125
|
+
"ser",
|
|
126
|
+
"seu",
|
|
127
|
+
"seus",
|
|
128
|
+
"sexa",
|
|
129
|
+
"sido",
|
|
130
|
+
"sobre",
|
|
131
|
+
"súa",
|
|
132
|
+
"súas",
|
|
133
|
+
"tamén",
|
|
134
|
+
"tan",
|
|
135
|
+
"te",
|
|
136
|
+
"ten",
|
|
137
|
+
"ter",
|
|
138
|
+
"teu",
|
|
139
|
+
"teus",
|
|
140
|
+
"teñen",
|
|
141
|
+
"teño",
|
|
142
|
+
"ti",
|
|
143
|
+
"tido",
|
|
144
|
+
"tiven",
|
|
145
|
+
"tiña",
|
|
146
|
+
"túa",
|
|
147
|
+
"túas",
|
|
148
|
+
"un",
|
|
149
|
+
"unha",
|
|
150
|
+
"unhas",
|
|
151
|
+
"uns",
|
|
152
|
+
"vos",
|
|
153
|
+
"vosa",
|
|
154
|
+
"vosas",
|
|
155
|
+
"voso",
|
|
156
|
+
"vosos",
|
|
157
|
+
"vós",
|
|
158
|
+
"á",
|
|
159
|
+
"é",
|
|
160
|
+
"ó",
|
|
161
|
+
"ós"
|
|
162
|
+
]
|