kreuzberg 4.0.0.pre.rc.6 → 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 (175) hide show
  1. checksums.yaml +4 -4
  2. data/.gitignore +0 -6
  3. data/.rubocop.yaml +534 -1
  4. data/Gemfile +2 -1
  5. data/Gemfile.lock +11 -11
  6. data/README.md +5 -10
  7. data/examples/async_patterns.rb +0 -1
  8. data/ext/kreuzberg_rb/extconf.rb +0 -10
  9. data/ext/kreuzberg_rb/native/Cargo.toml +15 -23
  10. data/ext/kreuzberg_rb/native/build.rs +2 -0
  11. data/ext/kreuzberg_rb/native/include/ieeefp.h +1 -1
  12. data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +1 -1
  13. data/ext/kreuzberg_rb/native/include/strings.h +2 -2
  14. data/ext/kreuzberg_rb/native/include/unistd.h +1 -1
  15. data/ext/kreuzberg_rb/native/src/lib.rs +16 -75
  16. data/kreuzberg.gemspec +14 -57
  17. data/lib/kreuzberg/cache_api.rb +0 -1
  18. data/lib/kreuzberg/cli.rb +2 -2
  19. data/lib/kreuzberg/config.rb +2 -9
  20. data/lib/kreuzberg/errors.rb +7 -75
  21. data/lib/kreuzberg/extraction_api.rb +0 -1
  22. data/lib/kreuzberg/setup_lib_path.rb +0 -1
  23. data/lib/kreuzberg/version.rb +1 -1
  24. data/lib/kreuzberg.rb +0 -21
  25. data/pkg/kreuzberg-4.0.0.rc1.gem +0 -0
  26. data/sig/kreuzberg.rbs +3 -55
  27. data/spec/binding/cli_proxy_spec.rb +4 -2
  28. data/spec/binding/cli_spec.rb +11 -12
  29. data/spec/examples.txt +104 -0
  30. data/spec/fixtures/config.yaml +1 -0
  31. data/spec/spec_helper.rb +1 -1
  32. data/vendor/kreuzberg/Cargo.toml +42 -112
  33. data/vendor/kreuzberg/README.md +2 -2
  34. data/vendor/kreuzberg/build.rs +4 -18
  35. data/vendor/kreuzberg/src/bin/profile_extract.rs +455 -0
  36. data/vendor/kreuzberg/src/cache/mod.rs +3 -27
  37. data/vendor/kreuzberg/src/core/batch_mode.rs +0 -60
  38. data/vendor/kreuzberg/src/core/extractor.rs +81 -202
  39. data/vendor/kreuzberg/src/core/io.rs +2 -4
  40. data/vendor/kreuzberg/src/core/mime.rs +12 -2
  41. data/vendor/kreuzberg/src/core/mod.rs +1 -4
  42. data/vendor/kreuzberg/src/core/pipeline.rs +33 -111
  43. data/vendor/kreuzberg/src/embeddings.rs +16 -125
  44. data/vendor/kreuzberg/src/error.rs +1 -1
  45. data/vendor/kreuzberg/src/extraction/docx.rs +1 -1
  46. data/vendor/kreuzberg/src/extraction/image.rs +13 -13
  47. data/vendor/kreuzberg/src/extraction/libreoffice.rs +1 -0
  48. data/vendor/kreuzberg/src/extraction/mod.rs +5 -9
  49. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +0 -2
  50. data/vendor/kreuzberg/src/extraction/pandoc/batch.rs +275 -0
  51. data/vendor/kreuzberg/src/extraction/pandoc/mime_types.rs +178 -0
  52. data/vendor/kreuzberg/src/extraction/pandoc/mod.rs +491 -0
  53. data/vendor/kreuzberg/src/extraction/pandoc/server.rs +496 -0
  54. data/vendor/kreuzberg/src/extraction/pandoc/subprocess.rs +1188 -0
  55. data/vendor/kreuzberg/src/extraction/pandoc/version.rs +162 -0
  56. data/vendor/kreuzberg/src/extractors/archive.rs +0 -21
  57. data/vendor/kreuzberg/src/extractors/docx.rs +128 -16
  58. data/vendor/kreuzberg/src/extractors/email.rs +0 -14
  59. data/vendor/kreuzberg/src/extractors/excel.rs +20 -19
  60. data/vendor/kreuzberg/src/extractors/html.rs +154 -137
  61. data/vendor/kreuzberg/src/extractors/image.rs +4 -7
  62. data/vendor/kreuzberg/src/extractors/mod.rs +9 -106
  63. data/vendor/kreuzberg/src/extractors/pandoc.rs +201 -0
  64. data/vendor/kreuzberg/src/extractors/pdf.rs +15 -12
  65. data/vendor/kreuzberg/src/extractors/pptx.rs +3 -17
  66. data/vendor/kreuzberg/src/extractors/structured.rs +0 -14
  67. data/vendor/kreuzberg/src/extractors/text.rs +5 -23
  68. data/vendor/kreuzberg/src/extractors/xml.rs +0 -7
  69. data/vendor/kreuzberg/src/keywords/rake.rs +1 -0
  70. data/vendor/kreuzberg/src/lib.rs +1 -4
  71. data/vendor/kreuzberg/src/mcp/mod.rs +1 -1
  72. data/vendor/kreuzberg/src/mcp/server.rs +3 -5
  73. data/vendor/kreuzberg/src/ocr/processor.rs +2 -18
  74. data/vendor/kreuzberg/src/pdf/error.rs +1 -1
  75. data/vendor/kreuzberg/src/pdf/table.rs +44 -17
  76. data/vendor/kreuzberg/src/pdf/text.rs +3 -0
  77. data/vendor/kreuzberg/src/plugins/extractor.rs +5 -8
  78. data/vendor/kreuzberg/src/plugins/ocr.rs +11 -2
  79. data/vendor/kreuzberg/src/plugins/processor.rs +1 -2
  80. data/vendor/kreuzberg/src/plugins/registry.rs +0 -13
  81. data/vendor/kreuzberg/src/plugins/validator.rs +8 -9
  82. data/vendor/kreuzberg/src/stopwords/mod.rs +2 -2
  83. data/vendor/kreuzberg/src/types.rs +12 -42
  84. data/vendor/kreuzberg/tests/batch_orchestration.rs +5 -19
  85. data/vendor/kreuzberg/tests/batch_processing.rs +3 -15
  86. data/vendor/kreuzberg/tests/chunking_offset_demo.rs +92 -0
  87. data/vendor/kreuzberg/tests/concurrency_stress.rs +1 -17
  88. data/vendor/kreuzberg/tests/config_features.rs +0 -18
  89. data/vendor/kreuzberg/tests/config_loading_tests.rs +39 -15
  90. data/vendor/kreuzberg/tests/core_integration.rs +7 -24
  91. data/vendor/kreuzberg/tests/csv_integration.rs +81 -71
  92. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +25 -23
  93. data/vendor/kreuzberg/tests/pandoc_integration.rs +503 -0
  94. data/vendor/kreuzberg/tests/pipeline_integration.rs +1 -0
  95. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +1 -0
  96. data/vendor/kreuzberg/tests/registry_integration_tests.rs +22 -1
  97. data/vendor/kreuzberg/tests/security_validation.rs +1 -12
  98. metadata +25 -90
  99. data/.rubocop.yml +0 -538
  100. data/ext/kreuzberg_rb/native/Cargo.lock +0 -6535
  101. data/lib/kreuzberg/error_context.rb +0 -32
  102. data/vendor/kreuzberg/benches/otel_overhead.rs +0 -48
  103. data/vendor/kreuzberg/src/extraction/markdown.rs +0 -213
  104. data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +0 -287
  105. data/vendor/kreuzberg/src/extractors/bibtex.rs +0 -469
  106. data/vendor/kreuzberg/src/extractors/docbook.rs +0 -502
  107. data/vendor/kreuzberg/src/extractors/epub.rs +0 -707
  108. data/vendor/kreuzberg/src/extractors/fictionbook.rs +0 -491
  109. data/vendor/kreuzberg/src/extractors/fictionbook.rs.backup2 +0 -738
  110. data/vendor/kreuzberg/src/extractors/jats.rs +0 -1051
  111. data/vendor/kreuzberg/src/extractors/jupyter.rs +0 -367
  112. data/vendor/kreuzberg/src/extractors/latex.rs +0 -652
  113. data/vendor/kreuzberg/src/extractors/markdown.rs +0 -700
  114. data/vendor/kreuzberg/src/extractors/odt.rs +0 -628
  115. data/vendor/kreuzberg/src/extractors/opml.rs +0 -634
  116. data/vendor/kreuzberg/src/extractors/orgmode.rs +0 -528
  117. data/vendor/kreuzberg/src/extractors/rst.rs +0 -576
  118. data/vendor/kreuzberg/src/extractors/rtf.rs +0 -810
  119. data/vendor/kreuzberg/src/extractors/security.rs +0 -484
  120. data/vendor/kreuzberg/src/extractors/security_tests.rs +0 -367
  121. data/vendor/kreuzberg/src/extractors/typst.rs +0 -650
  122. data/vendor/kreuzberg/src/panic_context.rs +0 -154
  123. data/vendor/kreuzberg/tests/api_extract_multipart.rs +0 -52
  124. data/vendor/kreuzberg/tests/bibtex_parity_test.rs +0 -421
  125. data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +0 -498
  126. data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +0 -370
  127. data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +0 -275
  128. data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +0 -228
  129. data/vendor/kreuzberg/tests/html_table_test.rs +0 -551
  130. data/vendor/kreuzberg/tests/instrumentation_test.rs +0 -139
  131. data/vendor/kreuzberg/tests/jats_extractor_tests.rs +0 -639
  132. data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +0 -704
  133. data/vendor/kreuzberg/tests/latex_extractor_tests.rs +0 -496
  134. data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +0 -490
  135. data/vendor/kreuzberg/tests/odt_extractor_tests.rs +0 -695
  136. data/vendor/kreuzberg/tests/opml_extractor_tests.rs +0 -616
  137. data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +0 -822
  138. data/vendor/kreuzberg/tests/rst_extractor_tests.rs +0 -692
  139. data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +0 -776
  140. data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +0 -1259
  141. data/vendor/kreuzberg/tests/typst_extractor_tests.rs +0 -647
  142. data/vendor/rb-sys/.cargo-ok +0 -1
  143. data/vendor/rb-sys/.cargo_vcs_info.json +0 -6
  144. data/vendor/rb-sys/Cargo.lock +0 -393
  145. data/vendor/rb-sys/Cargo.toml +0 -70
  146. data/vendor/rb-sys/Cargo.toml.orig +0 -57
  147. data/vendor/rb-sys/LICENSE-APACHE +0 -190
  148. data/vendor/rb-sys/LICENSE-MIT +0 -21
  149. data/vendor/rb-sys/bin/release.sh +0 -21
  150. data/vendor/rb-sys/build/features.rs +0 -108
  151. data/vendor/rb-sys/build/main.rs +0 -246
  152. data/vendor/rb-sys/build/stable_api_config.rs +0 -153
  153. data/vendor/rb-sys/build/version.rs +0 -48
  154. data/vendor/rb-sys/readme.md +0 -36
  155. data/vendor/rb-sys/src/bindings.rs +0 -21
  156. data/vendor/rb-sys/src/hidden.rs +0 -11
  157. data/vendor/rb-sys/src/lib.rs +0 -34
  158. data/vendor/rb-sys/src/macros.rs +0 -371
  159. data/vendor/rb-sys/src/memory.rs +0 -53
  160. data/vendor/rb-sys/src/ruby_abi_version.rs +0 -38
  161. data/vendor/rb-sys/src/special_consts.rs +0 -31
  162. data/vendor/rb-sys/src/stable_api/compiled.c +0 -179
  163. data/vendor/rb-sys/src/stable_api/compiled.rs +0 -257
  164. data/vendor/rb-sys/src/stable_api/ruby_2_6.rs +0 -316
  165. data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +0 -316
  166. data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +0 -324
  167. data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +0 -317
  168. data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +0 -315
  169. data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +0 -326
  170. data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +0 -327
  171. data/vendor/rb-sys/src/stable_api.rs +0 -261
  172. data/vendor/rb-sys/src/symbol.rs +0 -31
  173. data/vendor/rb-sys/src/tracking_allocator.rs +0 -332
  174. data/vendor/rb-sys/src/utils.rs +0 -89
  175. data/vendor/rb-sys/src/value_type.rs +0 -7
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.pre.rc.6
4
+ version: 4.0.0.rc1
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: 2025-12-10 00:00:00.000000000 Z
11
+ date: 2025-11-23 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: '4.0'
19
+ version: '2.0'
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: '4.0'
26
+ version: '2.0'
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: 0.9.119
61
+ version: '0.9'
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: 0.9.119
68
+ version: '0.9'
69
69
  - !ruby/object:Gem::Dependency
70
70
  name: rspec
71
71
  requirement: !ruby/object:Gem::Requirement
@@ -178,7 +178,6 @@ files:
178
178
  - ".gitignore"
179
179
  - ".rspec"
180
180
  - ".rubocop.yaml"
181
- - ".rubocop.yml"
182
181
  - Gemfile
183
182
  - Gemfile.lock
184
183
  - README.md
@@ -186,7 +185,6 @@ files:
186
185
  - Steepfile
187
186
  - examples/async_patterns.rb
188
187
  - ext/kreuzberg_rb/extconf.rb
189
- - ext/kreuzberg_rb/native/Cargo.lock
190
188
  - ext/kreuzberg_rb/native/Cargo.toml
191
189
  - ext/kreuzberg_rb/native/README.md
192
190
  - ext/kreuzberg_rb/native/build.rs
@@ -203,7 +201,6 @@ files:
203
201
  - lib/kreuzberg/cli.rb
204
202
  - lib/kreuzberg/cli_proxy.rb
205
203
  - lib/kreuzberg/config.rb
206
- - lib/kreuzberg/error_context.rb
207
204
  - lib/kreuzberg/errors.rb
208
205
  - lib/kreuzberg/extraction_api.rb
209
206
  - lib/kreuzberg/mcp_proxy.rb
@@ -213,6 +210,7 @@ files:
213
210
  - lib/kreuzberg/setup_lib_path.rb
214
211
  - lib/kreuzberg/validator_protocol.rb
215
212
  - lib/kreuzberg/version.rb
213
+ - pkg/kreuzberg-4.0.0.rc1.gem
216
214
  - sig/kreuzberg.rbs
217
215
  - sig/kreuzberg/internal.rbs
218
216
  - spec/binding/cache_spec.rb
@@ -225,6 +223,7 @@ files:
225
223
  - spec/binding/plugins/ocr_backend_spec.rb
226
224
  - spec/binding/plugins/postprocessor_spec.rb
227
225
  - spec/binding/plugins/validator_spec.rb
226
+ - spec/examples.txt
228
227
  - spec/fixtures/config.toml
229
228
  - spec/fixtures/config.yaml
230
229
  - spec/fixtures/invalid_config.toml
@@ -232,13 +231,13 @@ files:
232
231
  - spec/spec_helper.rb
233
232
  - vendor/kreuzberg/Cargo.toml
234
233
  - vendor/kreuzberg/README.md
235
- - vendor/kreuzberg/benches/otel_overhead.rs
236
234
  - vendor/kreuzberg/build.rs
237
235
  - vendor/kreuzberg/src/api/error.rs
238
236
  - vendor/kreuzberg/src/api/handlers.rs
239
237
  - vendor/kreuzberg/src/api/mod.rs
240
238
  - vendor/kreuzberg/src/api/server.rs
241
239
  - vendor/kreuzberg/src/api/types.rs
240
+ - vendor/kreuzberg/src/bin/profile_extract.rs
242
241
  - vendor/kreuzberg/src/cache/mod.rs
243
242
  - vendor/kreuzberg/src/chunking/mod.rs
244
243
  - vendor/kreuzberg/src/core/batch_mode.rs
@@ -257,46 +256,34 @@ files:
257
256
  - vendor/kreuzberg/src/extraction/html.rs
258
257
  - vendor/kreuzberg/src/extraction/image.rs
259
258
  - vendor/kreuzberg/src/extraction/libreoffice.rs
260
- - vendor/kreuzberg/src/extraction/markdown.rs
261
259
  - vendor/kreuzberg/src/extraction/mod.rs
262
260
  - vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs
263
261
  - vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs
264
262
  - vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs
265
263
  - vendor/kreuzberg/src/extraction/office_metadata/mod.rs
266
- - vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs
264
+ - vendor/kreuzberg/src/extraction/pandoc/batch.rs
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
267
270
  - vendor/kreuzberg/src/extraction/pptx.rs
268
271
  - vendor/kreuzberg/src/extraction/structured.rs
269
272
  - vendor/kreuzberg/src/extraction/table.rs
270
273
  - vendor/kreuzberg/src/extraction/text.rs
271
274
  - vendor/kreuzberg/src/extraction/xml.rs
272
275
  - vendor/kreuzberg/src/extractors/archive.rs
273
- - vendor/kreuzberg/src/extractors/bibtex.rs
274
- - vendor/kreuzberg/src/extractors/docbook.rs
275
276
  - vendor/kreuzberg/src/extractors/docx.rs
276
277
  - vendor/kreuzberg/src/extractors/email.rs
277
- - vendor/kreuzberg/src/extractors/epub.rs
278
278
  - vendor/kreuzberg/src/extractors/excel.rs
279
- - vendor/kreuzberg/src/extractors/fictionbook.rs
280
- - vendor/kreuzberg/src/extractors/fictionbook.rs.backup2
281
279
  - vendor/kreuzberg/src/extractors/html.rs
282
280
  - vendor/kreuzberg/src/extractors/image.rs
283
- - vendor/kreuzberg/src/extractors/jats.rs
284
- - vendor/kreuzberg/src/extractors/jupyter.rs
285
- - vendor/kreuzberg/src/extractors/latex.rs
286
- - vendor/kreuzberg/src/extractors/markdown.rs
287
281
  - vendor/kreuzberg/src/extractors/mod.rs
288
- - vendor/kreuzberg/src/extractors/odt.rs
289
- - vendor/kreuzberg/src/extractors/opml.rs
290
- - vendor/kreuzberg/src/extractors/orgmode.rs
282
+ - vendor/kreuzberg/src/extractors/pandoc.rs
291
283
  - vendor/kreuzberg/src/extractors/pdf.rs
292
284
  - vendor/kreuzberg/src/extractors/pptx.rs
293
- - vendor/kreuzberg/src/extractors/rst.rs
294
- - vendor/kreuzberg/src/extractors/rtf.rs
295
- - vendor/kreuzberg/src/extractors/security.rs
296
- - vendor/kreuzberg/src/extractors/security_tests.rs
297
285
  - vendor/kreuzberg/src/extractors/structured.rs
298
286
  - vendor/kreuzberg/src/extractors/text.rs
299
- - vendor/kreuzberg/src/extractors/typst.rs
300
287
  - vendor/kreuzberg/src/extractors/xml.rs
301
288
  - vendor/kreuzberg/src/image/dpi.rs
302
289
  - vendor/kreuzberg/src/image/mod.rs
@@ -323,7 +310,6 @@ files:
323
310
  - vendor/kreuzberg/src/ocr/types.rs
324
311
  - vendor/kreuzberg/src/ocr/utils.rs
325
312
  - vendor/kreuzberg/src/ocr/validation.rs
326
- - vendor/kreuzberg/src/panic_context.rs
327
313
  - vendor/kreuzberg/src/pdf/error.rs
328
314
  - vendor/kreuzberg/src/pdf/images.rs
329
315
  - vendor/kreuzberg/src/pdf/metadata.rs
@@ -417,43 +403,30 @@ files:
417
403
  - vendor/kreuzberg/stopwords/yo_stopwords.json
418
404
  - vendor/kreuzberg/stopwords/zh_stopwords.json
419
405
  - vendor/kreuzberg/stopwords/zu_stopwords.json
420
- - vendor/kreuzberg/tests/api_extract_multipart.rs
421
406
  - vendor/kreuzberg/tests/api_tests.rs
422
407
  - vendor/kreuzberg/tests/archive_integration.rs
423
408
  - vendor/kreuzberg/tests/batch_orchestration.rs
424
409
  - vendor/kreuzberg/tests/batch_processing.rs
425
- - vendor/kreuzberg/tests/bibtex_parity_test.rs
410
+ - vendor/kreuzberg/tests/chunking_offset_demo.rs
426
411
  - vendor/kreuzberg/tests/concurrency_stress.rs
427
412
  - vendor/kreuzberg/tests/config_features.rs
428
413
  - vendor/kreuzberg/tests/config_loading_tests.rs
429
414
  - vendor/kreuzberg/tests/core_integration.rs
430
415
  - vendor/kreuzberg/tests/csv_integration.rs
431
- - vendor/kreuzberg/tests/docbook_extractor_tests.rs
432
416
  - vendor/kreuzberg/tests/docx_metadata_extraction_test.rs
433
- - vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs
434
417
  - vendor/kreuzberg/tests/email_integration.rs
435
- - vendor/kreuzberg/tests/epub_native_extractor_tests.rs
436
418
  - vendor/kreuzberg/tests/error_handling.rs
437
- - vendor/kreuzberg/tests/fictionbook_extractor_tests.rs
438
419
  - vendor/kreuzberg/tests/format_integration.rs
439
420
  - vendor/kreuzberg/tests/helpers/mod.rs
440
- - vendor/kreuzberg/tests/html_table_test.rs
441
421
  - vendor/kreuzberg/tests/image_integration.rs
442
- - vendor/kreuzberg/tests/instrumentation_test.rs
443
- - vendor/kreuzberg/tests/jats_extractor_tests.rs
444
- - vendor/kreuzberg/tests/jupyter_extractor_tests.rs
445
422
  - vendor/kreuzberg/tests/keywords_integration.rs
446
423
  - vendor/kreuzberg/tests/keywords_quality.rs
447
- - vendor/kreuzberg/tests/latex_extractor_tests.rs
448
- - vendor/kreuzberg/tests/markdown_extractor_tests.rs
449
424
  - vendor/kreuzberg/tests/mime_detection.rs
450
425
  - vendor/kreuzberg/tests/ocr_configuration.rs
451
426
  - vendor/kreuzberg/tests/ocr_errors.rs
452
427
  - vendor/kreuzberg/tests/ocr_quality.rs
453
428
  - vendor/kreuzberg/tests/ocr_stress.rs
454
- - vendor/kreuzberg/tests/odt_extractor_tests.rs
455
- - vendor/kreuzberg/tests/opml_extractor_tests.rs
456
- - vendor/kreuzberg/tests/orgmode_extractor_tests.rs
429
+ - vendor/kreuzberg/tests/pandoc_integration.rs
457
430
  - vendor/kreuzberg/tests/pdf_integration.rs
458
431
  - vendor/kreuzberg/tests/pipeline_integration.rs
459
432
  - vendor/kreuzberg/tests/plugin_ocr_backend_test.rs
@@ -461,59 +434,21 @@ files:
461
434
  - vendor/kreuzberg/tests/plugin_system.rs
462
435
  - vendor/kreuzberg/tests/plugin_validator_test.rs
463
436
  - vendor/kreuzberg/tests/registry_integration_tests.rs
464
- - vendor/kreuzberg/tests/rst_extractor_tests.rs
465
- - vendor/kreuzberg/tests/rtf_extractor_tests.rs
466
437
  - vendor/kreuzberg/tests/security_validation.rs
467
438
  - vendor/kreuzberg/tests/stopwords_integration_test.rs
468
439
  - vendor/kreuzberg/tests/test_fastembed.rs
469
- - vendor/kreuzberg/tests/typst_behavioral_tests.rs
470
- - vendor/kreuzberg/tests/typst_extractor_tests.rs
471
440
  - vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs
472
- - vendor/rb-sys/.cargo-ok
473
- - vendor/rb-sys/.cargo_vcs_info.json
474
- - vendor/rb-sys/Cargo.lock
475
- - vendor/rb-sys/Cargo.toml
476
- - vendor/rb-sys/Cargo.toml.orig
477
- - vendor/rb-sys/LICENSE-APACHE
478
- - vendor/rb-sys/LICENSE-MIT
479
- - vendor/rb-sys/bin/release.sh
480
- - vendor/rb-sys/build/features.rs
481
- - vendor/rb-sys/build/main.rs
482
- - vendor/rb-sys/build/stable_api_config.rs
483
- - vendor/rb-sys/build/version.rs
484
- - vendor/rb-sys/readme.md
485
- - vendor/rb-sys/src/bindings.rs
486
- - vendor/rb-sys/src/hidden.rs
487
- - vendor/rb-sys/src/lib.rs
488
- - vendor/rb-sys/src/macros.rs
489
- - vendor/rb-sys/src/memory.rs
490
- - vendor/rb-sys/src/ruby_abi_version.rs
491
- - vendor/rb-sys/src/special_consts.rs
492
- - vendor/rb-sys/src/stable_api.rs
493
- - vendor/rb-sys/src/stable_api/compiled.c
494
- - vendor/rb-sys/src/stable_api/compiled.rs
495
- - vendor/rb-sys/src/stable_api/ruby_2_6.rs
496
- - vendor/rb-sys/src/stable_api/ruby_2_7.rs
497
- - vendor/rb-sys/src/stable_api/ruby_3_0.rs
498
- - vendor/rb-sys/src/stable_api/ruby_3_1.rs
499
- - vendor/rb-sys/src/stable_api/ruby_3_2.rs
500
- - vendor/rb-sys/src/stable_api/ruby_3_3.rs
501
- - vendor/rb-sys/src/stable_api/ruby_3_4.rs
502
- - vendor/rb-sys/src/symbol.rs
503
- - vendor/rb-sys/src/tracking_allocator.rs
504
- - vendor/rb-sys/src/utils.rs
505
- - vendor/rb-sys/src/value_type.rs
506
- homepage: https://github.com/kreuzberg-dev/kreuzberg
441
+ homepage: https://github.com/Goldziher/kreuzberg
507
442
  licenses:
508
443
  - MIT
509
444
  metadata:
510
- bug_tracker_uri: https://github.com/kreuzberg-dev/kreuzberg/issues
511
- changelog_uri: https://github.com/kreuzberg-dev/kreuzberg/blob/main/CHANGELOG.md
445
+ homepage_uri: https://github.com/Goldziher/kreuzberg
446
+ source_code_uri: https://github.com/Goldziher/kreuzberg
447
+ changelog_uri: https://github.com/Goldziher/kreuzberg/blob/main/CHANGELOG.md
512
448
  documentation_uri: https://docs.kreuzberg.dev
513
- homepage_uri: https://github.com/kreuzberg-dev/kreuzberg
514
- keywords: document-intelligence,document-extraction,ocr,rust,bindings
449
+ bug_tracker_uri: https://github.com/Goldziher/kreuzberg/issues
515
450
  rubygems_mfa_required: 'true'
516
- source_code_uri: https://github.com/kreuzberg-dev/kreuzberg
451
+ keywords: document-intelligence,document-extraction,ocr,rust,bindings
517
452
  post_install_message:
518
453
  rdoc_options: []
519
454
  require_paths:
@@ -529,7 +464,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
529
464
  - !ruby/object:Gem::Version
530
465
  version: '0'
531
466
  requirements: []
532
- rubygems_version: 3.4.20
467
+ rubygems_version: 3.5.22
533
468
  signing_key:
534
469
  specification_version: 4
535
470
  summary: High-performance document intelligence framework