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

There are too many changes on this page to be displayed.


The amount of changes on this page would crash your brower.

You can still verify the content by downloading the gem file manually.