kreuzberg 4.0.0.rc1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (265) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +8 -0
  3. data/.rspec +3 -0
  4. data/.rubocop.yaml +534 -0
  5. data/Gemfile +9 -0
  6. data/Gemfile.lock +157 -0
  7. data/README.md +421 -0
  8. data/Rakefile +25 -0
  9. data/Steepfile +47 -0
  10. data/examples/async_patterns.rb +340 -0
  11. data/ext/kreuzberg_rb/extconf.rb +35 -0
  12. data/ext/kreuzberg_rb/native/Cargo.toml +36 -0
  13. data/ext/kreuzberg_rb/native/README.md +425 -0
  14. data/ext/kreuzberg_rb/native/build.rs +17 -0
  15. data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -0
  16. data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -0
  17. data/ext/kreuzberg_rb/native/include/strings.h +20 -0
  18. data/ext/kreuzberg_rb/native/include/unistd.h +47 -0
  19. data/ext/kreuzberg_rb/native/src/lib.rs +2939 -0
  20. data/extconf.rb +28 -0
  21. data/kreuzberg.gemspec +105 -0
  22. data/lib/kreuzberg/api_proxy.rb +142 -0
  23. data/lib/kreuzberg/cache_api.rb +45 -0
  24. data/lib/kreuzberg/cli.rb +55 -0
  25. data/lib/kreuzberg/cli_proxy.rb +127 -0
  26. data/lib/kreuzberg/config.rb +684 -0
  27. data/lib/kreuzberg/errors.rb +50 -0
  28. data/lib/kreuzberg/extraction_api.rb +84 -0
  29. data/lib/kreuzberg/mcp_proxy.rb +186 -0
  30. data/lib/kreuzberg/ocr_backend_protocol.rb +113 -0
  31. data/lib/kreuzberg/post_processor_protocol.rb +86 -0
  32. data/lib/kreuzberg/result.rb +216 -0
  33. data/lib/kreuzberg/setup_lib_path.rb +79 -0
  34. data/lib/kreuzberg/validator_protocol.rb +89 -0
  35. data/lib/kreuzberg/version.rb +5 -0
  36. data/lib/kreuzberg.rb +82 -0
  37. data/pkg/kreuzberg-4.0.0.rc1.gem +0 -0
  38. data/sig/kreuzberg/internal.rbs +184 -0
  39. data/sig/kreuzberg.rbs +468 -0
  40. data/spec/binding/cache_spec.rb +227 -0
  41. data/spec/binding/cli_proxy_spec.rb +87 -0
  42. data/spec/binding/cli_spec.rb +54 -0
  43. data/spec/binding/config_spec.rb +345 -0
  44. data/spec/binding/config_validation_spec.rb +283 -0
  45. data/spec/binding/error_handling_spec.rb +213 -0
  46. data/spec/binding/errors_spec.rb +66 -0
  47. data/spec/binding/plugins/ocr_backend_spec.rb +307 -0
  48. data/spec/binding/plugins/postprocessor_spec.rb +269 -0
  49. data/spec/binding/plugins/validator_spec.rb +274 -0
  50. data/spec/examples.txt +104 -0
  51. data/spec/fixtures/config.toml +39 -0
  52. data/spec/fixtures/config.yaml +42 -0
  53. data/spec/fixtures/invalid_config.toml +4 -0
  54. data/spec/smoke/package_spec.rb +178 -0
  55. data/spec/spec_helper.rb +42 -0
  56. data/vendor/kreuzberg/Cargo.toml +134 -0
  57. data/vendor/kreuzberg/README.md +175 -0
  58. data/vendor/kreuzberg/build.rs +460 -0
  59. data/vendor/kreuzberg/src/api/error.rs +81 -0
  60. data/vendor/kreuzberg/src/api/handlers.rs +199 -0
  61. data/vendor/kreuzberg/src/api/mod.rs +79 -0
  62. data/vendor/kreuzberg/src/api/server.rs +353 -0
  63. data/vendor/kreuzberg/src/api/types.rs +170 -0
  64. data/vendor/kreuzberg/src/bin/profile_extract.rs +455 -0
  65. data/vendor/kreuzberg/src/cache/mod.rs +1143 -0
  66. data/vendor/kreuzberg/src/chunking/mod.rs +677 -0
  67. data/vendor/kreuzberg/src/core/batch_mode.rs +35 -0
  68. data/vendor/kreuzberg/src/core/config.rs +1032 -0
  69. data/vendor/kreuzberg/src/core/extractor.rs +903 -0
  70. data/vendor/kreuzberg/src/core/io.rs +327 -0
  71. data/vendor/kreuzberg/src/core/mime.rs +615 -0
  72. data/vendor/kreuzberg/src/core/mod.rs +42 -0
  73. data/vendor/kreuzberg/src/core/pipeline.rs +906 -0
  74. data/vendor/kreuzberg/src/embeddings.rs +323 -0
  75. data/vendor/kreuzberg/src/error.rs +431 -0
  76. data/vendor/kreuzberg/src/extraction/archive.rs +954 -0
  77. data/vendor/kreuzberg/src/extraction/docx.rs +40 -0
  78. data/vendor/kreuzberg/src/extraction/email.rs +854 -0
  79. data/vendor/kreuzberg/src/extraction/excel.rs +688 -0
  80. data/vendor/kreuzberg/src/extraction/html.rs +553 -0
  81. data/vendor/kreuzberg/src/extraction/image.rs +368 -0
  82. data/vendor/kreuzberg/src/extraction/libreoffice.rs +564 -0
  83. data/vendor/kreuzberg/src/extraction/mod.rs +77 -0
  84. data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -0
  85. data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -0
  86. data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -0
  87. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +128 -0
  88. data/vendor/kreuzberg/src/extraction/pandoc/batch.rs +275 -0
  89. data/vendor/kreuzberg/src/extraction/pandoc/mime_types.rs +178 -0
  90. data/vendor/kreuzberg/src/extraction/pandoc/mod.rs +491 -0
  91. data/vendor/kreuzberg/src/extraction/pandoc/server.rs +496 -0
  92. data/vendor/kreuzberg/src/extraction/pandoc/subprocess.rs +1188 -0
  93. data/vendor/kreuzberg/src/extraction/pandoc/version.rs +162 -0
  94. data/vendor/kreuzberg/src/extraction/pptx.rs +3000 -0
  95. data/vendor/kreuzberg/src/extraction/structured.rs +490 -0
  96. data/vendor/kreuzberg/src/extraction/table.rs +328 -0
  97. data/vendor/kreuzberg/src/extraction/text.rs +269 -0
  98. data/vendor/kreuzberg/src/extraction/xml.rs +333 -0
  99. data/vendor/kreuzberg/src/extractors/archive.rs +425 -0
  100. data/vendor/kreuzberg/src/extractors/docx.rs +479 -0
  101. data/vendor/kreuzberg/src/extractors/email.rs +129 -0
  102. data/vendor/kreuzberg/src/extractors/excel.rs +344 -0
  103. data/vendor/kreuzberg/src/extractors/html.rs +410 -0
  104. data/vendor/kreuzberg/src/extractors/image.rs +195 -0
  105. data/vendor/kreuzberg/src/extractors/mod.rs +268 -0
  106. data/vendor/kreuzberg/src/extractors/pandoc.rs +201 -0
  107. data/vendor/kreuzberg/src/extractors/pdf.rs +496 -0
  108. data/vendor/kreuzberg/src/extractors/pptx.rs +234 -0
  109. data/vendor/kreuzberg/src/extractors/structured.rs +126 -0
  110. data/vendor/kreuzberg/src/extractors/text.rs +242 -0
  111. data/vendor/kreuzberg/src/extractors/xml.rs +128 -0
  112. data/vendor/kreuzberg/src/image/dpi.rs +164 -0
  113. data/vendor/kreuzberg/src/image/mod.rs +6 -0
  114. data/vendor/kreuzberg/src/image/preprocessing.rs +417 -0
  115. data/vendor/kreuzberg/src/image/resize.rs +89 -0
  116. data/vendor/kreuzberg/src/keywords/config.rs +154 -0
  117. data/vendor/kreuzberg/src/keywords/mod.rs +237 -0
  118. data/vendor/kreuzberg/src/keywords/processor.rs +267 -0
  119. data/vendor/kreuzberg/src/keywords/rake.rs +294 -0
  120. data/vendor/kreuzberg/src/keywords/types.rs +68 -0
  121. data/vendor/kreuzberg/src/keywords/yake.rs +163 -0
  122. data/vendor/kreuzberg/src/language_detection/mod.rs +942 -0
  123. data/vendor/kreuzberg/src/lib.rs +102 -0
  124. data/vendor/kreuzberg/src/mcp/mod.rs +32 -0
  125. data/vendor/kreuzberg/src/mcp/server.rs +1966 -0
  126. data/vendor/kreuzberg/src/ocr/cache.rs +469 -0
  127. data/vendor/kreuzberg/src/ocr/error.rs +37 -0
  128. data/vendor/kreuzberg/src/ocr/hocr.rs +216 -0
  129. data/vendor/kreuzberg/src/ocr/mod.rs +58 -0
  130. data/vendor/kreuzberg/src/ocr/processor.rs +847 -0
  131. data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -0
  132. data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -0
  133. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +450 -0
  134. data/vendor/kreuzberg/src/ocr/types.rs +393 -0
  135. data/vendor/kreuzberg/src/ocr/utils.rs +47 -0
  136. data/vendor/kreuzberg/src/ocr/validation.rs +206 -0
  137. data/vendor/kreuzberg/src/pdf/error.rs +122 -0
  138. data/vendor/kreuzberg/src/pdf/images.rs +139 -0
  139. data/vendor/kreuzberg/src/pdf/metadata.rs +346 -0
  140. data/vendor/kreuzberg/src/pdf/mod.rs +50 -0
  141. data/vendor/kreuzberg/src/pdf/rendering.rs +369 -0
  142. data/vendor/kreuzberg/src/pdf/table.rs +420 -0
  143. data/vendor/kreuzberg/src/pdf/text.rs +161 -0
  144. data/vendor/kreuzberg/src/plugins/extractor.rs +1010 -0
  145. data/vendor/kreuzberg/src/plugins/mod.rs +209 -0
  146. data/vendor/kreuzberg/src/plugins/ocr.rs +629 -0
  147. data/vendor/kreuzberg/src/plugins/processor.rs +641 -0
  148. data/vendor/kreuzberg/src/plugins/registry.rs +1324 -0
  149. data/vendor/kreuzberg/src/plugins/traits.rs +258 -0
  150. data/vendor/kreuzberg/src/plugins/validator.rs +955 -0
  151. data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -0
  152. data/vendor/kreuzberg/src/text/mod.rs +19 -0
  153. data/vendor/kreuzberg/src/text/quality.rs +697 -0
  154. data/vendor/kreuzberg/src/text/string_utils.rs +217 -0
  155. data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -0
  156. data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -0
  157. data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -0
  158. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -0
  159. data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -0
  160. data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -0
  161. data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -0
  162. data/vendor/kreuzberg/src/types.rs +873 -0
  163. data/vendor/kreuzberg/src/utils/mod.rs +17 -0
  164. data/vendor/kreuzberg/src/utils/quality.rs +959 -0
  165. data/vendor/kreuzberg/src/utils/string_utils.rs +381 -0
  166. data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -0
  167. data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -0
  168. data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -0
  169. data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -0
  170. data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -0
  171. data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -0
  172. data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -0
  173. data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -0
  174. data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -0
  175. data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -0
  176. data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -0
  177. data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -0
  178. data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -0
  179. data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -0
  180. data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -0
  181. data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -0
  182. data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -0
  183. data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -0
  184. data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -0
  185. data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -0
  186. data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -0
  187. data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -0
  188. data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -0
  189. data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -0
  190. data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -0
  191. data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -0
  192. data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -0
  193. data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -0
  194. data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -0
  195. data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -0
  196. data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -0
  197. data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -0
  198. data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -0
  199. data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -0
  200. data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -0
  201. data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -0
  202. data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -0
  203. data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -0
  204. data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -0
  205. data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -0
  206. data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -0
  207. data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -0
  208. data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -0
  209. data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -0
  210. data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -0
  211. data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -0
  212. data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -0
  213. data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -0
  214. data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -0
  215. data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -0
  216. data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -0
  217. data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -0
  218. data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -0
  219. data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -0
  220. data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -0
  221. data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -0
  222. data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -0
  223. data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -0
  224. data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -0
  225. data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -0
  226. data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -0
  227. data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -0
  228. data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -0
  229. data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -0
  230. data/vendor/kreuzberg/tests/api_tests.rs +966 -0
  231. data/vendor/kreuzberg/tests/archive_integration.rs +543 -0
  232. data/vendor/kreuzberg/tests/batch_orchestration.rs +542 -0
  233. data/vendor/kreuzberg/tests/batch_processing.rs +304 -0
  234. data/vendor/kreuzberg/tests/chunking_offset_demo.rs +92 -0
  235. data/vendor/kreuzberg/tests/concurrency_stress.rs +509 -0
  236. data/vendor/kreuzberg/tests/config_features.rs +580 -0
  237. data/vendor/kreuzberg/tests/config_loading_tests.rs +439 -0
  238. data/vendor/kreuzberg/tests/core_integration.rs +493 -0
  239. data/vendor/kreuzberg/tests/csv_integration.rs +424 -0
  240. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +124 -0
  241. data/vendor/kreuzberg/tests/email_integration.rs +325 -0
  242. data/vendor/kreuzberg/tests/error_handling.rs +393 -0
  243. data/vendor/kreuzberg/tests/format_integration.rs +159 -0
  244. data/vendor/kreuzberg/tests/helpers/mod.rs +142 -0
  245. data/vendor/kreuzberg/tests/image_integration.rs +253 -0
  246. data/vendor/kreuzberg/tests/keywords_integration.rs +479 -0
  247. data/vendor/kreuzberg/tests/keywords_quality.rs +509 -0
  248. data/vendor/kreuzberg/tests/mime_detection.rs +428 -0
  249. data/vendor/kreuzberg/tests/ocr_configuration.rs +510 -0
  250. data/vendor/kreuzberg/tests/ocr_errors.rs +676 -0
  251. data/vendor/kreuzberg/tests/ocr_quality.rs +627 -0
  252. data/vendor/kreuzberg/tests/ocr_stress.rs +469 -0
  253. data/vendor/kreuzberg/tests/pandoc_integration.rs +503 -0
  254. data/vendor/kreuzberg/tests/pdf_integration.rs +43 -0
  255. data/vendor/kreuzberg/tests/pipeline_integration.rs +1412 -0
  256. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +771 -0
  257. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +561 -0
  258. data/vendor/kreuzberg/tests/plugin_system.rs +921 -0
  259. data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -0
  260. data/vendor/kreuzberg/tests/registry_integration_tests.rs +607 -0
  261. data/vendor/kreuzberg/tests/security_validation.rs +404 -0
  262. data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -0
  263. data/vendor/kreuzberg/tests/test_fastembed.rs +609 -0
  264. data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -0
  265. metadata +471 -0
checksums.yaml ADDED
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA256:
3
+ metadata.gz: bfb7dc6c3685285b053af795140387ad8292c698cbba4cfda3411390dfe3cd48
4
+ data.tar.gz: 7688722b9a8d99564044a8bca31c6fadf107208aabaa336d450069b636a02726
5
+ SHA512:
6
+ metadata.gz: 3c5b66fc2c0457f670c39e53f038a5fa040760ac3f36b8731c35210d2ca98b1cf65ae41411bd6788411f18090ffd269878cf814d4b93b4201098f5e5950782e0
7
+ data.tar.gz: 1a02c5c0ffb830454e20e03e937aa4d80e73d9e6a6ae4913ed9d35d6cdb84ffbb2141711fa3b2ce5fcd821b109613f5ec01cbfdcface5615071727b26c772347
data/.gitignore ADDED
@@ -0,0 +1,8 @@
1
+ tmp/
2
+ lib/*.bundle
3
+ lib/*.dylib
4
+ lib/*.so
5
+ lib/*.dll
6
+ lib/*.dylib
7
+ lib/*.so
8
+ lib/*.dll
data/.rspec ADDED
@@ -0,0 +1,3 @@
1
+ --require spec_helper
2
+ --format documentation
3
+ --color
data/.rubocop.yaml ADDED
@@ -0,0 +1,534 @@
1
+
2
+ plugins:
3
+ - rubocop-performance
4
+ - rubocop-rspec
5
+
6
+ AllCops:
7
+ TargetRubyVersion: 3.2
8
+ NewCops: enable
9
+ SuggestExtensions: false
10
+ Exclude:
11
+ - 'vendor/**/*'
12
+ - 'tmp/**/*'
13
+ - 'lib/**/*.bundle'
14
+ - 'ext/**/*'
15
+
16
+ Style/StringLiterals:
17
+ Enabled: true
18
+ EnforcedStyle: single_quotes
19
+
20
+ Style/StringLiteralsInInterpolation:
21
+ Enabled: true
22
+ EnforcedStyle: single_quotes
23
+
24
+ Style/FrozenStringLiteralComment:
25
+ Enabled: true
26
+ EnforcedStyle: always
27
+
28
+ Style/Documentation:
29
+ Enabled: false
30
+
31
+ Layout/LineLength:
32
+ Max: 120
33
+ AllowedPatterns:
34
+ - '\A\s*#'
35
+ Exclude:
36
+ - 'spec/**/*'
37
+
38
+ Metrics/BlockLength:
39
+ Max: 350
40
+ Exclude:
41
+ - '*.gemspec'
42
+ - 'examples/**/*'
43
+
44
+ Metrics/MethodLength:
45
+ Max: 18
46
+ Exclude:
47
+ - 'spec/**/*'
48
+ - 'examples/**/*'
49
+
50
+ Metrics/AbcSize:
51
+ Max: 20
52
+ Exclude:
53
+ - 'spec/**/*'
54
+ - 'examples/**/*'
55
+
56
+ Naming/FileName:
57
+ Enabled: true
58
+ Exclude:
59
+ - 'Gemfile'
60
+ - 'Rakefile'
61
+
62
+ RSpec/SpecFilePathFormat:
63
+ Enabled: false
64
+ RSpec/SpecFilePathSuffix:
65
+ Enabled: false
66
+
67
+ RSpec/PendingWithoutReason:
68
+ Enabled: false
69
+
70
+ RSpec/LeakyConstantDeclaration:
71
+ Enabled: false
72
+
73
+ RSpec/UnspecifiedException:
74
+ Enabled: false
75
+
76
+ Lint/ConstantDefinitionInBlock:
77
+ Exclude:
78
+ - 'spec/**/*'
79
+
80
+ RSpec/InstanceVariable:
81
+ Enabled: false
82
+
83
+ Gemspec/DevelopmentDependencies:
84
+ Enabled: false
85
+
86
+ Metrics/ParameterLists:
87
+ Max: 7
88
+ Exclude:
89
+ - 'lib/kreuzberg/config.rb'
90
+
91
+ Metrics/CyclomaticComplexity:
92
+ Max: 7
93
+ Exclude:
94
+ - 'lib/kreuzberg/config.rb'
95
+
96
+ RSpec/RepeatedExampleGroupBody:
97
+ Enabled: false
98
+
99
+ RSpec/DescribeClass:
100
+ Enabled: false
101
+
102
+ RSpec/PredicateMatcher:
103
+ Enabled: false
104
+
105
+ # New cops from RuboCop 1.65+
106
+ Gemspec/AddRuntimeDependency:
107
+ Enabled: true
108
+
109
+ Gemspec/AttributeAssignment:
110
+ Enabled: true
111
+
112
+ Gemspec/DeprecatedAttributeAssignment:
113
+ Enabled: true
114
+
115
+ Gemspec/RequireMFA:
116
+ Enabled: false
117
+
118
+ Layout/EmptyLinesAfterModuleInclusion:
119
+ Enabled: true
120
+
121
+ Layout/LineContinuationLeadingSpace:
122
+ Enabled: true
123
+
124
+ Layout/LineContinuationSpacing:
125
+ Enabled: true
126
+
127
+ Layout/LineEndStringConcatenationIndentation:
128
+ Enabled: true
129
+
130
+ Layout/SpaceBeforeBrackets:
131
+ Enabled: true
132
+
133
+ Lint/AmbiguousAssignment:
134
+ Enabled: true
135
+
136
+ Lint/AmbiguousOperatorPrecedence:
137
+ Enabled: true
138
+
139
+ Lint/AmbiguousRange:
140
+ Enabled: true
141
+
142
+ Lint/ArrayLiteralInRegexp:
143
+ Enabled: true
144
+
145
+ Lint/ConstantOverwrittenInRescue:
146
+ Enabled: true
147
+
148
+ Lint/ConstantReassignment:
149
+ Enabled: true
150
+
151
+ Lint/CopDirectiveSyntax:
152
+ Enabled: true
153
+
154
+ Lint/DeprecatedConstants:
155
+ Enabled: true
156
+
157
+ Lint/DuplicateBranch:
158
+ Enabled: true
159
+
160
+ Lint/DuplicateMagicComment:
161
+ Enabled: true
162
+
163
+ Lint/DuplicateMatchPattern:
164
+ Enabled: true
165
+
166
+ Lint/DuplicateRegexpCharacterClassElement:
167
+ Enabled: true
168
+
169
+ Lint/DuplicateSetElement:
170
+ Enabled: true
171
+
172
+ Lint/EmptyBlock:
173
+ Enabled: true
174
+
175
+ Lint/EmptyClass:
176
+ Enabled: true
177
+
178
+ Lint/EmptyInPattern:
179
+ Enabled: true
180
+
181
+ Lint/HashNewWithKeywordArgumentsAsDefault:
182
+ Enabled: true
183
+
184
+ Lint/IncompatibleIoSelectWithFiberScheduler:
185
+ Enabled: true
186
+
187
+ Lint/ItWithoutArgumentsInBlock:
188
+ Enabled: true
189
+
190
+ Lint/LambdaWithoutLiteralBlock:
191
+ Enabled: true
192
+
193
+ Lint/LiteralAssignmentInCondition:
194
+ Enabled: true
195
+
196
+ Lint/MixedCaseRange:
197
+ Enabled: true
198
+
199
+ Lint/NoReturnInBeginEndBlocks:
200
+ Enabled: true
201
+
202
+ Lint/NonAtomicFileOperation:
203
+ Enabled: true
204
+
205
+ Lint/NumberedParameterAssignment:
206
+ Enabled: true
207
+
208
+ Lint/NumericOperationWithConstantResult:
209
+ Enabled: true
210
+
211
+ Lint/OrAssignmentToConstant:
212
+ Enabled: true
213
+
214
+ Lint/RedundantDirGlobSort:
215
+ Enabled: true
216
+
217
+ Lint/RedundantRegexpQuantifiers:
218
+ Enabled: true
219
+
220
+ Lint/RedundantTypeConversion:
221
+ Enabled: true
222
+
223
+ Lint/RefinementImportMethods:
224
+ Enabled: true
225
+
226
+ Lint/RequireRangeParentheses:
227
+ Enabled: true
228
+
229
+ Lint/RequireRelativeSelfPath:
230
+ Enabled: true
231
+
232
+ Lint/SharedMutableDefault:
233
+ Enabled: true
234
+
235
+ Lint/SuppressedExceptionInNumberConversion:
236
+ Enabled: true
237
+
238
+ Lint/SymbolConversion:
239
+ Enabled: true
240
+
241
+ Lint/ToEnumArguments:
242
+ Enabled: true
243
+
244
+ Lint/TripleQuotes:
245
+ Enabled: true
246
+
247
+ Lint/UnescapedBracketInRegexp:
248
+ Enabled: true
249
+
250
+ Lint/UnexpectedBlockArity:
251
+ Enabled: true
252
+
253
+ Lint/UnmodifiedReduceAccumulator:
254
+ Enabled: true
255
+
256
+ Lint/UselessConstantScoping:
257
+ Enabled: true
258
+
259
+ Lint/UselessDefaultValueArgument:
260
+ Enabled: true
261
+
262
+ Lint/UselessDefined:
263
+ Enabled: true
264
+
265
+ Lint/UselessNumericOperation:
266
+ Enabled: true
267
+
268
+ Lint/UselessOr:
269
+ Enabled: true
270
+
271
+ Lint/UselessRescue:
272
+ Enabled: true
273
+
274
+ Lint/UselessRuby2Keywords:
275
+ Enabled: true
276
+
277
+ Metrics/CollectionLiteralLength:
278
+ Enabled: true
279
+
280
+ Naming/BlockForwarding:
281
+ Enabled: true
282
+
283
+ Naming/PredicateMethod:
284
+ Enabled: true
285
+
286
+ Security/CompoundHash:
287
+ Enabled: true
288
+
289
+ Security/IoMethods:
290
+ Enabled: true
291
+
292
+ Style/AmbiguousEndlessMethodDefinition:
293
+ Enabled: true
294
+
295
+ Style/ArgumentsForwarding:
296
+ Enabled: true
297
+
298
+ Style/ArrayIntersect:
299
+ Enabled: true
300
+
301
+ Style/ArrayIntersectWithSingleElement:
302
+ Enabled: true
303
+
304
+ Style/BitwisePredicate:
305
+ Enabled: true
306
+
307
+ Style/CollectionCompact:
308
+ Enabled: true
309
+
310
+ Style/CollectionQuerying:
311
+ Enabled: true
312
+
313
+ Style/CombinableDefined:
314
+ Enabled: true
315
+
316
+ Style/ComparableBetween:
317
+ Enabled: true
318
+
319
+ Style/ComparableClamp:
320
+ Enabled: true
321
+
322
+ Style/ConcatArrayLiterals:
323
+ Enabled: true
324
+
325
+ Style/DataInheritance:
326
+ Enabled: true
327
+
328
+ Style/DigChain:
329
+ Enabled: true
330
+
331
+ Style/DirEmpty:
332
+ Enabled: true
333
+
334
+ Style/DocumentDynamicEvalDefinition:
335
+ Enabled: true
336
+
337
+ Style/EmptyHeredoc:
338
+ Enabled: true
339
+
340
+ Style/EmptyStringInsideInterpolation:
341
+ Enabled: true
342
+
343
+ Style/EndlessMethod:
344
+ Enabled: true
345
+
346
+ Style/EnvHome:
347
+ Enabled: true
348
+
349
+ Style/ExactRegexpMatch:
350
+ Enabled: true
351
+
352
+ Style/FetchEnvVar:
353
+ Enabled: true
354
+
355
+ Style/FileEmpty:
356
+ Enabled: true
357
+
358
+ Style/FileNull:
359
+ Enabled: true
360
+
361
+ Style/FileRead:
362
+ Enabled: true
363
+
364
+ Style/FileTouch:
365
+ Enabled: true
366
+
367
+ Style/FileWrite:
368
+ Enabled: true
369
+
370
+ Style/HashConversion:
371
+ Enabled: true
372
+
373
+ Style/HashExcept:
374
+ Enabled: true
375
+
376
+ Style/HashFetchChain:
377
+ Enabled: true
378
+
379
+ Style/HashSlice:
380
+ Enabled: true
381
+
382
+ Style/IfWithBooleanLiteralBranches:
383
+ Enabled: true
384
+
385
+ Style/InPatternThen:
386
+ Enabled: true
387
+
388
+ Style/ItAssignment:
389
+ Enabled: true
390
+
391
+ Style/ItBlockParameter:
392
+ Enabled: true
393
+
394
+ Style/KeywordArgumentsMerging:
395
+ Enabled: true
396
+
397
+ Style/MagicCommentFormat:
398
+ Enabled: true
399
+
400
+ Style/MapCompactWithConditionalBlock:
401
+ Enabled: true
402
+
403
+ Style/MapIntoArray:
404
+ Enabled: true
405
+
406
+ Style/MapToHash:
407
+ Enabled: true
408
+
409
+ Style/MapToSet:
410
+ Enabled: true
411
+
412
+ Style/MinMaxComparison:
413
+ Enabled: true
414
+
415
+ Style/MultilineInPatternThen:
416
+ Enabled: true
417
+
418
+ Style/NegatedIfElseCondition:
419
+ Enabled: true
420
+
421
+ Style/NestedFileDirname:
422
+ Enabled: true
423
+
424
+ Style/NilLambda:
425
+ Enabled: true
426
+
427
+ Style/NumberedParameters:
428
+ Enabled: true
429
+
430
+ Style/NumberedParametersLimit:
431
+ Enabled: true
432
+
433
+ Style/ObjectThen:
434
+ Enabled: true
435
+
436
+ Style/OpenStructUse:
437
+ Enabled: true
438
+
439
+ Style/OperatorMethodCall:
440
+ Enabled: true
441
+
442
+ Style/QuotedSymbols:
443
+ Enabled: true
444
+
445
+ Style/RedundantArgument:
446
+ Enabled: true
447
+
448
+ Style/RedundantArrayConstructor:
449
+ Enabled: true
450
+
451
+ Style/RedundantArrayFlatten:
452
+ Enabled: true
453
+
454
+ Style/RedundantConstantBase:
455
+ Enabled: true
456
+
457
+ Style/RedundantCurrentDirectoryInPath:
458
+ Enabled: true
459
+
460
+ Style/RedundantDoubleSplatHashBraces:
461
+ Enabled: true
462
+
463
+ Style/RedundantEach:
464
+ Enabled: true
465
+
466
+ Style/RedundantFilterChain:
467
+ Enabled: true
468
+
469
+ Style/RedundantFormat:
470
+ Enabled: true
471
+
472
+ Style/RedundantHeredocDelimiterQuotes:
473
+ Enabled: true
474
+
475
+ Style/RedundantInitialize:
476
+ Enabled: true
477
+
478
+ Style/RedundantInterpolationUnfreeze:
479
+ Enabled: true
480
+
481
+ Style/RedundantLineContinuation:
482
+ Enabled: true
483
+
484
+ Style/RedundantRegexpArgument:
485
+ Enabled: true
486
+
487
+ Style/RedundantRegexpConstructor:
488
+ Enabled: true
489
+
490
+ Style/RedundantSelfAssignmentBranch:
491
+ Enabled: true
492
+
493
+ Style/RedundantStringEscape:
494
+ Enabled: true
495
+
496
+ Style/ReturnNilInPredicateMethodDefinition:
497
+ Enabled: true
498
+
499
+ Style/SafeNavigationChainLength:
500
+ Enabled: true
501
+
502
+ Style/SelectByRegexp:
503
+ Enabled: true
504
+
505
+ Style/SendWithLiteralMethodName:
506
+ Enabled: true
507
+
508
+ Style/SingleLineDoEndBlock:
509
+ Enabled: true
510
+
511
+ Style/StringChars:
512
+ Enabled: true
513
+
514
+ Style/SuperArguments:
515
+ Enabled: true
516
+
517
+ Style/SuperWithArgsParentheses:
518
+ Enabled: true
519
+
520
+ Style/SwapValues:
521
+ Enabled: true
522
+
523
+ Style/YAMLFileRead:
524
+ Enabled: true
525
+
526
+ # Adjust RSpec metrics for test blocks
527
+ RSpec/ExampleLength:
528
+ Max: 35
529
+
530
+ RSpec/MultipleExpectations:
531
+ Max: 15
532
+
533
+ RSpec/NestedGroups:
534
+ Max: 6
data/Gemfile ADDED
@@ -0,0 +1,9 @@
1
+ # frozen_string_literal: true
2
+
3
+ source 'https://rubygems.org'
4
+
5
+ gemspec
6
+
7
+ gem 'pry', '~> 0.14', group: :development
8
+
9
+ gem 'pry-byebug', '~> 3.10', group: :development unless Gem.win_platform?
data/Gemfile.lock ADDED
@@ -0,0 +1,157 @@
1
+ PATH
2
+ remote: .
3
+ specs:
4
+ kreuzberg (4.0.0.rc1)
5
+
6
+ GEM
7
+ remote: https://rubygems.org/
8
+ specs:
9
+ activesupport (8.1.1)
10
+ base64
11
+ bigdecimal
12
+ concurrent-ruby (~> 1.0, >= 1.3.1)
13
+ connection_pool (>= 2.2.5)
14
+ drb
15
+ i18n (>= 1.6, < 2)
16
+ json
17
+ logger (>= 1.4.2)
18
+ minitest (>= 5.1)
19
+ securerandom (>= 0.3)
20
+ tzinfo (~> 2.0, >= 2.0.5)
21
+ uri (>= 0.13.1)
22
+ ast (2.4.3)
23
+ base64 (0.3.0)
24
+ bigdecimal (3.3.1)
25
+ byebug (12.0.0)
26
+ coderay (1.1.3)
27
+ concurrent-ruby (1.3.5)
28
+ connection_pool (2.5.4)
29
+ csv (3.3.5)
30
+ diff-lcs (1.6.2)
31
+ drb (2.2.3)
32
+ ffi (1.17.2)
33
+ ffi (1.17.2-arm64-darwin)
34
+ fileutils (1.8.0)
35
+ i18n (1.14.7)
36
+ concurrent-ruby (~> 1.0)
37
+ json (2.16.0)
38
+ language_server-protocol (3.17.0.5)
39
+ lint_roller (1.1.0)
40
+ listen (3.9.0)
41
+ rb-fsevent (~> 0.10, >= 0.10.3)
42
+ rb-inotify (~> 0.9, >= 0.9.10)
43
+ logger (1.7.0)
44
+ method_source (1.1.0)
45
+ minitest (5.26.2)
46
+ mutex_m (0.3.0)
47
+ parallel (1.27.0)
48
+ parser (3.3.10.0)
49
+ ast (~> 2.4.1)
50
+ racc
51
+ prism (1.6.0)
52
+ pry (0.15.2)
53
+ coderay (~> 1.1)
54
+ method_source (~> 1.0)
55
+ pry-byebug (3.11.0)
56
+ byebug (~> 12.0)
57
+ pry (>= 0.13, < 0.16)
58
+ racc (1.8.1)
59
+ rainbow (3.1.1)
60
+ rake (13.3.1)
61
+ rake-compiler (1.3.0)
62
+ rake
63
+ rake-compiler-dock (1.9.1)
64
+ rb-fsevent (0.11.2)
65
+ rb-inotify (0.11.1)
66
+ ffi (~> 1.0)
67
+ rb_sys (0.9.117)
68
+ rake-compiler-dock (= 1.9.1)
69
+ rbs (3.9.5)
70
+ logger
71
+ regexp_parser (2.11.3)
72
+ rspec (3.13.2)
73
+ rspec-core (~> 3.13.0)
74
+ rspec-expectations (~> 3.13.0)
75
+ rspec-mocks (~> 3.13.0)
76
+ rspec-core (3.13.6)
77
+ rspec-support (~> 3.13.0)
78
+ rspec-expectations (3.13.5)
79
+ diff-lcs (>= 1.2.0, < 2.0)
80
+ rspec-support (~> 3.13.0)
81
+ rspec-mocks (3.13.7)
82
+ diff-lcs (>= 1.2.0, < 2.0)
83
+ rspec-support (~> 3.13.0)
84
+ rspec-support (3.13.6)
85
+ rubocop (1.81.7)
86
+ json (~> 2.3)
87
+ language_server-protocol (~> 3.17.0.2)
88
+ lint_roller (~> 1.1.0)
89
+ parallel (~> 1.10)
90
+ parser (>= 3.3.0.2)
91
+ rainbow (>= 2.2.2, < 4.0)
92
+ regexp_parser (>= 2.9.3, < 3.0)
93
+ rubocop-ast (>= 1.47.1, < 2.0)
94
+ ruby-progressbar (~> 1.7)
95
+ unicode-display_width (>= 2.4.0, < 4.0)
96
+ rubocop-ast (1.48.0)
97
+ parser (>= 3.3.7.2)
98
+ prism (~> 1.4)
99
+ rubocop-performance (1.26.1)
100
+ lint_roller (~> 1.1)
101
+ rubocop (>= 1.75.0, < 2.0)
102
+ rubocop-ast (>= 1.47.1, < 2.0)
103
+ rubocop-rspec (3.8.0)
104
+ lint_roller (~> 1.1)
105
+ rubocop (~> 1.81)
106
+ ruby-progressbar (1.13.0)
107
+ securerandom (0.4.1)
108
+ steep (1.10.0)
109
+ activesupport (>= 5.1)
110
+ concurrent-ruby (>= 1.1.10)
111
+ csv (>= 3.0.9)
112
+ fileutils (>= 1.1.0)
113
+ json (>= 2.1.0)
114
+ language_server-protocol (>= 3.17.0.4, < 4.0)
115
+ listen (~> 3.0)
116
+ logger (>= 1.3.0)
117
+ mutex_m (>= 0.3.0)
118
+ parser (>= 3.1)
119
+ rainbow (>= 2.2.2, < 4.0)
120
+ rbs (~> 3.9)
121
+ securerandom (>= 0.1)
122
+ strscan (>= 1.0.0)
123
+ terminal-table (>= 2, < 5)
124
+ uri (>= 0.12.0)
125
+ strscan (3.1.5)
126
+ terminal-table (4.0.0)
127
+ unicode-display_width (>= 1.1.1, < 4)
128
+ tzinfo (2.0.6)
129
+ concurrent-ruby (~> 1.0)
130
+ unicode-display_width (3.2.0)
131
+ unicode-emoji (~> 4.1)
132
+ unicode-emoji (4.1.0)
133
+ uri (1.1.1)
134
+ yard (0.9.37)
135
+
136
+ PLATFORMS
137
+ arm64-darwin-24
138
+ ruby
139
+
140
+ DEPENDENCIES
141
+ bundler (~> 2.0)
142
+ kreuzberg!
143
+ pry (~> 0.14)
144
+ pry-byebug (~> 3.10)
145
+ rake (~> 13.0)
146
+ rake-compiler (~> 1.2)
147
+ rb_sys (~> 0.9)
148
+ rbs (~> 3.0)
149
+ rspec (~> 3.12)
150
+ rubocop (~> 1.66)
151
+ rubocop-performance (~> 1.21)
152
+ rubocop-rspec (~> 3.0)
153
+ steep (~> 1.8)
154
+ yard (~> 0.9)
155
+
156
+ BUNDLED WITH
157
+ 2.7.2