kreuzberg 4.0.0.pre.rc.8 → 4.0.0.pre.rc.13

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 (370) hide show
  1. checksums.yaml +4 -4
  2. data/.gitignore +14 -14
  3. data/.rspec +3 -3
  4. data/.rubocop.yaml +1 -1
  5. data/.rubocop.yml +538 -538
  6. data/Gemfile +8 -8
  7. data/Gemfile.lock +4 -104
  8. data/README.md +454 -432
  9. data/Rakefile +25 -25
  10. data/Steepfile +47 -47
  11. data/examples/async_patterns.rb +341 -341
  12. data/ext/kreuzberg_rb/extconf.rb +45 -45
  13. data/ext/kreuzberg_rb/native/.cargo/config.toml +2 -2
  14. data/ext/kreuzberg_rb/native/Cargo.lock +6941 -6721
  15. data/ext/kreuzberg_rb/native/Cargo.toml +54 -54
  16. data/ext/kreuzberg_rb/native/README.md +425 -425
  17. data/ext/kreuzberg_rb/native/build.rs +15 -15
  18. data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -11
  19. data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -14
  20. data/ext/kreuzberg_rb/native/include/strings.h +20 -20
  21. data/ext/kreuzberg_rb/native/include/unistd.h +47 -47
  22. data/ext/kreuzberg_rb/native/src/lib.rs +3158 -3135
  23. data/extconf.rb +28 -28
  24. data/kreuzberg.gemspec +214 -182
  25. data/lib/kreuzberg/api_proxy.rb +142 -142
  26. data/lib/kreuzberg/cache_api.rb +81 -46
  27. data/lib/kreuzberg/cli.rb +55 -55
  28. data/lib/kreuzberg/cli_proxy.rb +127 -127
  29. data/lib/kreuzberg/config.rb +724 -724
  30. data/lib/kreuzberg/error_context.rb +80 -32
  31. data/lib/kreuzberg/errors.rb +118 -118
  32. data/lib/kreuzberg/extraction_api.rb +340 -85
  33. data/lib/kreuzberg/mcp_proxy.rb +186 -186
  34. data/lib/kreuzberg/ocr_backend_protocol.rb +113 -113
  35. data/lib/kreuzberg/post_processor_protocol.rb +86 -86
  36. data/lib/kreuzberg/result.rb +279 -279
  37. data/lib/kreuzberg/setup_lib_path.rb +80 -80
  38. data/lib/kreuzberg/validator_protocol.rb +89 -89
  39. data/lib/kreuzberg/version.rb +5 -5
  40. data/lib/kreuzberg.rb +109 -103
  41. data/lib/pdfium.dll +0 -0
  42. data/sig/kreuzberg/internal.rbs +184 -184
  43. data/sig/kreuzberg.rbs +546 -537
  44. data/spec/binding/cache_spec.rb +227 -227
  45. data/spec/binding/cli_proxy_spec.rb +85 -85
  46. data/spec/binding/cli_spec.rb +55 -55
  47. data/spec/binding/config_spec.rb +345 -345
  48. data/spec/binding/config_validation_spec.rb +283 -283
  49. data/spec/binding/error_handling_spec.rb +213 -213
  50. data/spec/binding/errors_spec.rb +66 -66
  51. data/spec/binding/plugins/ocr_backend_spec.rb +307 -307
  52. data/spec/binding/plugins/postprocessor_spec.rb +269 -269
  53. data/spec/binding/plugins/validator_spec.rb +274 -274
  54. data/spec/fixtures/config.toml +39 -39
  55. data/spec/fixtures/config.yaml +41 -41
  56. data/spec/fixtures/invalid_config.toml +4 -4
  57. data/spec/smoke/package_spec.rb +178 -178
  58. data/spec/spec_helper.rb +42 -42
  59. data/vendor/Cargo.toml +45 -0
  60. data/vendor/kreuzberg/Cargo.toml +61 -38
  61. data/vendor/kreuzberg/README.md +230 -221
  62. data/vendor/kreuzberg/benches/otel_overhead.rs +48 -48
  63. data/vendor/kreuzberg/build.rs +843 -891
  64. data/vendor/kreuzberg/src/api/error.rs +81 -81
  65. data/vendor/kreuzberg/src/api/handlers.rs +199 -199
  66. data/vendor/kreuzberg/src/api/mod.rs +79 -79
  67. data/vendor/kreuzberg/src/api/server.rs +353 -353
  68. data/vendor/kreuzberg/src/api/types.rs +170 -170
  69. data/vendor/kreuzberg/src/cache/mod.rs +1167 -1167
  70. data/vendor/kreuzberg/src/chunking/mod.rs +1877 -1877
  71. data/vendor/kreuzberg/src/chunking/processor.rs +220 -220
  72. data/vendor/kreuzberg/src/core/batch_mode.rs +95 -95
  73. data/vendor/kreuzberg/src/core/config.rs +1080 -1080
  74. data/vendor/kreuzberg/src/core/extractor.rs +1156 -1156
  75. data/vendor/kreuzberg/src/core/io.rs +329 -329
  76. data/vendor/kreuzberg/src/core/mime.rs +605 -605
  77. data/vendor/kreuzberg/src/core/mod.rs +47 -47
  78. data/vendor/kreuzberg/src/core/pipeline.rs +1184 -1171
  79. data/vendor/kreuzberg/src/embeddings.rs +500 -432
  80. data/vendor/kreuzberg/src/error.rs +431 -431
  81. data/vendor/kreuzberg/src/extraction/archive.rs +954 -954
  82. data/vendor/kreuzberg/src/extraction/docx.rs +398 -398
  83. data/vendor/kreuzberg/src/extraction/email.rs +854 -854
  84. data/vendor/kreuzberg/src/extraction/excel.rs +688 -688
  85. data/vendor/kreuzberg/src/extraction/html.rs +601 -569
  86. data/vendor/kreuzberg/src/extraction/image.rs +491 -491
  87. data/vendor/kreuzberg/src/extraction/libreoffice.rs +574 -562
  88. data/vendor/kreuzberg/src/extraction/markdown.rs +213 -213
  89. data/vendor/kreuzberg/src/extraction/mod.rs +81 -81
  90. data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -398
  91. data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -247
  92. data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -240
  93. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -130
  94. data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +284 -284
  95. data/vendor/kreuzberg/src/extraction/pptx.rs +3100 -3100
  96. data/vendor/kreuzberg/src/extraction/structured.rs +490 -490
  97. data/vendor/kreuzberg/src/extraction/table.rs +328 -328
  98. data/vendor/kreuzberg/src/extraction/text.rs +269 -269
  99. data/vendor/kreuzberg/src/extraction/xml.rs +333 -333
  100. data/vendor/kreuzberg/src/extractors/archive.rs +447 -447
  101. data/vendor/kreuzberg/src/extractors/bibtex.rs +470 -470
  102. data/vendor/kreuzberg/src/extractors/docbook.rs +504 -504
  103. data/vendor/kreuzberg/src/extractors/docx.rs +400 -400
  104. data/vendor/kreuzberg/src/extractors/email.rs +157 -157
  105. data/vendor/kreuzberg/src/extractors/epub.rs +708 -708
  106. data/vendor/kreuzberg/src/extractors/excel.rs +345 -345
  107. data/vendor/kreuzberg/src/extractors/fictionbook.rs +492 -492
  108. data/vendor/kreuzberg/src/extractors/html.rs +407 -407
  109. data/vendor/kreuzberg/src/extractors/image.rs +219 -219
  110. data/vendor/kreuzberg/src/extractors/jats.rs +1054 -1054
  111. data/vendor/kreuzberg/src/extractors/jupyter.rs +368 -368
  112. data/vendor/kreuzberg/src/extractors/latex.rs +653 -653
  113. data/vendor/kreuzberg/src/extractors/markdown.rs +701 -701
  114. data/vendor/kreuzberg/src/extractors/mod.rs +429 -429
  115. data/vendor/kreuzberg/src/extractors/odt.rs +628 -628
  116. data/vendor/kreuzberg/src/extractors/opml.rs +635 -635
  117. data/vendor/kreuzberg/src/extractors/orgmode.rs +529 -529
  118. data/vendor/kreuzberg/src/extractors/pdf.rs +749 -673
  119. data/vendor/kreuzberg/src/extractors/pptx.rs +267 -267
  120. data/vendor/kreuzberg/src/extractors/rst.rs +577 -577
  121. data/vendor/kreuzberg/src/extractors/rtf.rs +809 -809
  122. data/vendor/kreuzberg/src/extractors/security.rs +484 -484
  123. data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -367
  124. data/vendor/kreuzberg/src/extractors/structured.rs +142 -142
  125. data/vendor/kreuzberg/src/extractors/text.rs +265 -265
  126. data/vendor/kreuzberg/src/extractors/typst.rs +651 -651
  127. data/vendor/kreuzberg/src/extractors/xml.rs +147 -147
  128. data/vendor/kreuzberg/src/image/dpi.rs +164 -164
  129. data/vendor/kreuzberg/src/image/mod.rs +6 -6
  130. data/vendor/kreuzberg/src/image/preprocessing.rs +417 -417
  131. data/vendor/kreuzberg/src/image/resize.rs +89 -89
  132. data/vendor/kreuzberg/src/keywords/config.rs +154 -154
  133. data/vendor/kreuzberg/src/keywords/mod.rs +237 -237
  134. data/vendor/kreuzberg/src/keywords/processor.rs +275 -275
  135. data/vendor/kreuzberg/src/keywords/rake.rs +293 -293
  136. data/vendor/kreuzberg/src/keywords/types.rs +68 -68
  137. data/vendor/kreuzberg/src/keywords/yake.rs +163 -163
  138. data/vendor/kreuzberg/src/language_detection/mod.rs +985 -985
  139. data/vendor/kreuzberg/src/language_detection/processor.rs +219 -219
  140. data/vendor/kreuzberg/src/lib.rs +113 -113
  141. data/vendor/kreuzberg/src/mcp/mod.rs +35 -35
  142. data/vendor/kreuzberg/src/mcp/server.rs +2076 -2076
  143. data/vendor/kreuzberg/src/ocr/cache.rs +469 -469
  144. data/vendor/kreuzberg/src/ocr/error.rs +37 -37
  145. data/vendor/kreuzberg/src/ocr/hocr.rs +216 -216
  146. data/vendor/kreuzberg/src/ocr/mod.rs +58 -58
  147. data/vendor/kreuzberg/src/ocr/processor.rs +863 -863
  148. data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -4
  149. data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -144
  150. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +452 -452
  151. data/vendor/kreuzberg/src/ocr/types.rs +393 -393
  152. data/vendor/kreuzberg/src/ocr/utils.rs +47 -47
  153. data/vendor/kreuzberg/src/ocr/validation.rs +206 -206
  154. data/vendor/kreuzberg/src/panic_context.rs +154 -154
  155. data/vendor/kreuzberg/src/pdf/bindings.rs +44 -0
  156. data/vendor/kreuzberg/src/pdf/bundled.rs +346 -328
  157. data/vendor/kreuzberg/src/pdf/error.rs +130 -130
  158. data/vendor/kreuzberg/src/pdf/images.rs +139 -139
  159. data/vendor/kreuzberg/src/pdf/metadata.rs +489 -489
  160. data/vendor/kreuzberg/src/pdf/mod.rs +68 -66
  161. data/vendor/kreuzberg/src/pdf/rendering.rs +368 -368
  162. data/vendor/kreuzberg/src/pdf/table.rs +420 -417
  163. data/vendor/kreuzberg/src/pdf/text.rs +240 -240
  164. data/vendor/kreuzberg/src/plugins/extractor.rs +1044 -1044
  165. data/vendor/kreuzberg/src/plugins/mod.rs +212 -212
  166. data/vendor/kreuzberg/src/plugins/ocr.rs +639 -639
  167. data/vendor/kreuzberg/src/plugins/processor.rs +650 -650
  168. data/vendor/kreuzberg/src/plugins/registry.rs +1339 -1339
  169. data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
  170. data/vendor/kreuzberg/src/plugins/validator.rs +967 -967
  171. data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
  172. data/vendor/kreuzberg/src/text/mod.rs +25 -25
  173. data/vendor/kreuzberg/src/text/quality.rs +697 -697
  174. data/vendor/kreuzberg/src/text/quality_processor.rs +219 -219
  175. data/vendor/kreuzberg/src/text/string_utils.rs +217 -217
  176. data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -164
  177. data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -100
  178. data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -796
  179. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -902
  180. data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -160
  181. data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -619
  182. data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -147
  183. data/vendor/kreuzberg/src/types.rs +1055 -1055
  184. data/vendor/kreuzberg/src/utils/mod.rs +17 -17
  185. data/vendor/kreuzberg/src/utils/quality.rs +959 -959
  186. data/vendor/kreuzberg/src/utils/string_utils.rs +381 -381
  187. data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -53
  188. data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -482
  189. data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -261
  190. data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -400
  191. data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -1205
  192. data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -280
  193. data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -425
  194. data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -172
  195. data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -622
  196. data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -849
  197. data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -1300
  198. data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -175
  199. data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -734
  200. data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -37
  201. data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -100
  202. data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -801
  203. data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -849
  204. data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -693
  205. data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -111
  206. data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -162
  207. data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -226
  208. data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -41
  209. data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -196
  210. data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -227
  211. data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -181
  212. data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -791
  213. data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -47
  214. data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -760
  215. data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -634
  216. data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -136
  217. data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -84
  218. data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -681
  219. data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -64
  220. data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -51
  221. data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -476
  222. data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -163
  223. data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -1
  224. data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -101
  225. data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -477
  226. data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -490
  227. data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -415
  228. data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -223
  229. data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -331
  230. data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -562
  231. data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -436
  232. data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -561
  233. data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -193
  234. data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -420
  235. data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -448
  236. data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -32
  237. data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -33
  238. data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -420
  239. data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -76
  240. data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -129
  241. data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -54
  242. data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -118
  243. data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -149
  244. data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -506
  245. data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -75
  246. data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -519
  247. data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -647
  248. data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -62
  249. data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -796
  250. data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -31
  251. data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -52
  252. data/vendor/kreuzberg/tests/api_tests.rs +966 -966
  253. data/vendor/kreuzberg/tests/archive_integration.rs +545 -545
  254. data/vendor/kreuzberg/tests/batch_orchestration.rs +556 -556
  255. data/vendor/kreuzberg/tests/batch_processing.rs +318 -318
  256. data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -421
  257. data/vendor/kreuzberg/tests/concurrency_stress.rs +533 -533
  258. data/vendor/kreuzberg/tests/config_features.rs +612 -612
  259. data/vendor/kreuzberg/tests/config_loading_tests.rs +416 -416
  260. data/vendor/kreuzberg/tests/core_integration.rs +510 -510
  261. data/vendor/kreuzberg/tests/csv_integration.rs +414 -414
  262. data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +500 -500
  263. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -122
  264. data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -370
  265. data/vendor/kreuzberg/tests/email_integration.rs +327 -327
  266. data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -275
  267. data/vendor/kreuzberg/tests/error_handling.rs +402 -402
  268. data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -228
  269. data/vendor/kreuzberg/tests/format_integration.rs +164 -161
  270. data/vendor/kreuzberg/tests/helpers/mod.rs +142 -142
  271. data/vendor/kreuzberg/tests/html_table_test.rs +551 -551
  272. data/vendor/kreuzberg/tests/image_integration.rs +255 -255
  273. data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -139
  274. data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -639
  275. data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -704
  276. data/vendor/kreuzberg/tests/keywords_integration.rs +479 -479
  277. data/vendor/kreuzberg/tests/keywords_quality.rs +509 -509
  278. data/vendor/kreuzberg/tests/latex_extractor_tests.rs +496 -496
  279. data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -490
  280. data/vendor/kreuzberg/tests/mime_detection.rs +429 -429
  281. data/vendor/kreuzberg/tests/ocr_configuration.rs +514 -514
  282. data/vendor/kreuzberg/tests/ocr_errors.rs +698 -698
  283. data/vendor/kreuzberg/tests/ocr_quality.rs +629 -629
  284. data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
  285. data/vendor/kreuzberg/tests/odt_extractor_tests.rs +674 -674
  286. data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -616
  287. data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -822
  288. data/vendor/kreuzberg/tests/pdf_integration.rs +45 -45
  289. data/vendor/kreuzberg/tests/pdfium_linking.rs +374 -374
  290. data/vendor/kreuzberg/tests/pipeline_integration.rs +1436 -1436
  291. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +776 -776
  292. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +560 -560
  293. data/vendor/kreuzberg/tests/plugin_system.rs +927 -927
  294. data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
  295. data/vendor/kreuzberg/tests/registry_integration_tests.rs +587 -587
  296. data/vendor/kreuzberg/tests/rst_extractor_tests.rs +694 -694
  297. data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +775 -775
  298. data/vendor/kreuzberg/tests/security_validation.rs +416 -416
  299. data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
  300. data/vendor/kreuzberg/tests/test_fastembed.rs +631 -631
  301. data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1260 -1260
  302. data/vendor/kreuzberg/tests/typst_extractor_tests.rs +648 -648
  303. data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -87
  304. data/vendor/kreuzberg-ffi/Cargo.toml +63 -0
  305. data/vendor/kreuzberg-ffi/README.md +851 -0
  306. data/vendor/kreuzberg-ffi/build.rs +176 -0
  307. data/vendor/kreuzberg-ffi/cbindgen.toml +27 -0
  308. data/vendor/kreuzberg-ffi/kreuzberg-ffi-install.pc +12 -0
  309. data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +12 -0
  310. data/vendor/kreuzberg-ffi/kreuzberg.h +1087 -0
  311. data/vendor/kreuzberg-ffi/src/lib.rs +3616 -0
  312. data/vendor/kreuzberg-ffi/src/panic_shield.rs +247 -0
  313. data/vendor/kreuzberg-ffi/tests.disabled/README.md +48 -0
  314. data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +299 -0
  315. data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +346 -0
  316. data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +232 -0
  317. data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +470 -0
  318. data/vendor/kreuzberg-tesseract/.commitlintrc.json +13 -0
  319. data/vendor/kreuzberg-tesseract/.crate-ignore +2 -0
  320. data/vendor/kreuzberg-tesseract/Cargo.lock +2933 -0
  321. data/vendor/kreuzberg-tesseract/Cargo.toml +48 -0
  322. data/vendor/kreuzberg-tesseract/LICENSE +22 -0
  323. data/vendor/kreuzberg-tesseract/README.md +399 -0
  324. data/vendor/kreuzberg-tesseract/build.rs +1354 -0
  325. data/vendor/kreuzberg-tesseract/patches/README.md +71 -0
  326. data/vendor/kreuzberg-tesseract/patches/tesseract.diff +199 -0
  327. data/vendor/kreuzberg-tesseract/src/api.rs +1371 -0
  328. data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +77 -0
  329. data/vendor/kreuzberg-tesseract/src/enums.rs +297 -0
  330. data/vendor/kreuzberg-tesseract/src/error.rs +81 -0
  331. data/vendor/kreuzberg-tesseract/src/lib.rs +145 -0
  332. data/vendor/kreuzberg-tesseract/src/monitor.rs +57 -0
  333. data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +197 -0
  334. data/vendor/kreuzberg-tesseract/src/page_iterator.rs +253 -0
  335. data/vendor/kreuzberg-tesseract/src/result_iterator.rs +286 -0
  336. data/vendor/kreuzberg-tesseract/src/result_renderer.rs +183 -0
  337. data/vendor/kreuzberg-tesseract/tests/integration_test.rs +211 -0
  338. data/vendor/rb-sys/.cargo_vcs_info.json +5 -5
  339. data/vendor/rb-sys/Cargo.lock +393 -393
  340. data/vendor/rb-sys/Cargo.toml +70 -70
  341. data/vendor/rb-sys/Cargo.toml.orig +57 -57
  342. data/vendor/rb-sys/LICENSE-APACHE +190 -190
  343. data/vendor/rb-sys/LICENSE-MIT +21 -21
  344. data/vendor/rb-sys/build/features.rs +111 -111
  345. data/vendor/rb-sys/build/main.rs +286 -286
  346. data/vendor/rb-sys/build/stable_api_config.rs +155 -155
  347. data/vendor/rb-sys/build/version.rs +50 -50
  348. data/vendor/rb-sys/readme.md +36 -36
  349. data/vendor/rb-sys/src/bindings.rs +21 -21
  350. data/vendor/rb-sys/src/hidden.rs +11 -11
  351. data/vendor/rb-sys/src/lib.rs +35 -35
  352. data/vendor/rb-sys/src/macros.rs +371 -371
  353. data/vendor/rb-sys/src/memory.rs +53 -53
  354. data/vendor/rb-sys/src/ruby_abi_version.rs +38 -38
  355. data/vendor/rb-sys/src/special_consts.rs +31 -31
  356. data/vendor/rb-sys/src/stable_api/compiled.c +179 -179
  357. data/vendor/rb-sys/src/stable_api/compiled.rs +257 -257
  358. data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +324 -324
  359. data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +332 -332
  360. data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +325 -325
  361. data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +323 -323
  362. data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +339 -339
  363. data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +339 -339
  364. data/vendor/rb-sys/src/stable_api.rs +260 -260
  365. data/vendor/rb-sys/src/symbol.rs +31 -31
  366. data/vendor/rb-sys/src/tracking_allocator.rs +330 -330
  367. data/vendor/rb-sys/src/utils.rs +89 -89
  368. data/vendor/rb-sys/src/value_type.rs +7 -7
  369. metadata +44 -81
  370. data/vendor/rb-sys/bin/release.sh +0 -21
@@ -1,796 +1,796 @@
1
- [
2
- "、",
3
- "。",
4
- "〈",
5
- "〉",
6
- "《",
7
- "》",
8
- "一",
9
- "一个",
10
- "一些",
11
- "一何",
12
- "一切",
13
- "一则",
14
- "一方面",
15
- "一旦",
16
- "一来",
17
- "一样",
18
- "一种",
19
- "一般",
20
- "一转眼",
21
- "七",
22
- "万一",
23
- "三",
24
- "上",
25
- "上下",
26
- "下",
27
- "不",
28
- "不仅",
29
- "不但",
30
- "不光",
31
- "不单",
32
- "不只",
33
- "不外乎",
34
- "不如",
35
- "不妨",
36
- "不尽",
37
- "不尽然",
38
- "不得",
39
- "不怕",
40
- "不惟",
41
- "不成",
42
- "不拘",
43
- "不料",
44
- "不是",
45
- "不比",
46
- "不然",
47
- "不特",
48
- "不独",
49
- "不管",
50
- "不至于",
51
- "不若",
52
- "不论",
53
- "不过",
54
- "不问",
55
- "与",
56
- "与其",
57
- "与其说",
58
- "与否",
59
- "与此同时",
60
- "且",
61
- "且不说",
62
- "且说",
63
- "两者",
64
- "个",
65
- "个别",
66
- "中",
67
- "临",
68
- "为",
69
- "为了",
70
- "为什么",
71
- "为何",
72
- "为止",
73
- "为此",
74
- "为着",
75
- "乃",
76
- "乃至",
77
- "乃至于",
78
- "么",
79
- "之",
80
- "之一",
81
- "之所以",
82
- "之类",
83
- "乌乎",
84
- "乎",
85
- "乘",
86
- "九",
87
- "也",
88
- "也好",
89
- "也罢",
90
- "了",
91
- "二",
92
- "二来",
93
- "于",
94
- "于是",
95
- "于是乎",
96
- "云云",
97
- "云尔",
98
- "五",
99
- "些",
100
- "亦",
101
- "人",
102
- "人们",
103
- "人家",
104
- "什",
105
- "什么",
106
- "什么样",
107
- "今",
108
- "介于",
109
- "仍",
110
- "仍旧",
111
- "从",
112
- "从此",
113
- "从而",
114
- "他",
115
- "他人",
116
- "他们",
117
- "他们们",
118
- "以",
119
- "以上",
120
- "以为",
121
- "以便",
122
- "以免",
123
- "以及",
124
- "以故",
125
- "以期",
126
- "以来",
127
- "以至",
128
- "以至于",
129
- "以致",
130
- "们",
131
- "任",
132
- "任何",
133
- "任凭",
134
- "会",
135
- "似的",
136
- "但",
137
- "但凡",
138
- "但是",
139
- "何",
140
- "何以",
141
- "何况",
142
- "何处",
143
- "何时",
144
- "余外",
145
- "作为",
146
- "你",
147
- "你们",
148
- "使",
149
- "使得",
150
- "例如",
151
- "依",
152
- "依据",
153
- "依照",
154
- "便于",
155
- "俺",
156
- "俺们",
157
- "倘",
158
- "倘使",
159
- "倘或",
160
- "倘然",
161
- "倘若",
162
- "借",
163
- "借傥然",
164
- "假使",
165
- "假如",
166
- "假若",
167
- "做",
168
- "像",
169
- "儿",
170
- "先不先",
171
- "光",
172
- "光是",
173
- "全体",
174
- "全部",
175
- "八",
176
- "六",
177
- "兮",
178
- "共",
179
- "关于",
180
- "关于具体地说",
181
- "其",
182
- "其一",
183
- "其中",
184
- "其二",
185
- "其他",
186
- "其余",
187
- "其它",
188
- "其次",
189
- "具体地说",
190
- "具体说来",
191
- "兼之",
192
- "内",
193
- "再",
194
- "再其次",
195
- "再则",
196
- "再有",
197
- "再者",
198
- "再者说",
199
- "再说",
200
- "冒",
201
- "冲",
202
- "况且",
203
- "几",
204
- "几时",
205
- "凡",
206
- "凡是",
207
- "凭",
208
- "凭借",
209
- "出于",
210
- "出来",
211
- "分",
212
- "分别",
213
- "则",
214
- "则甚",
215
- "别",
216
- "别人",
217
- "别处",
218
- "别是",
219
- "别的",
220
- "别管",
221
- "别说",
222
- "到",
223
- "前后",
224
- "前此",
225
- "前者",
226
- "加之",
227
- "加以",
228
- "区",
229
- "即",
230
- "即令",
231
- "即使",
232
- "即便",
233
- "即如",
234
- "即或",
235
- "即若",
236
- "却",
237
- "去",
238
- "又",
239
- "又及",
240
- "及",
241
- "及其",
242
- "及至",
243
- "反之",
244
- "反而",
245
- "反过来",
246
- "反过来说",
247
- "受到",
248
- "另",
249
- "另一方面",
250
- "另外",
251
- "另悉",
252
- "只",
253
- "只当",
254
- "只怕",
255
- "只是",
256
- "只有",
257
- "只消",
258
- "只要",
259
- "只限",
260
- "叫",
261
- "叮咚",
262
- "可",
263
- "可以",
264
- "可是",
265
- "可见",
266
- "各",
267
- "各个",
268
- "各位",
269
- "各种",
270
- "各自",
271
- "同",
272
- "同时",
273
- "后",
274
- "后者",
275
- "向",
276
- "向使",
277
- "向着",
278
- "吓",
279
- "吗",
280
- "否则",
281
- "吧",
282
- "吧哒",
283
- "含",
284
- "吱",
285
- "呀",
286
- "呃",
287
- "呕",
288
- "呗",
289
- "呜",
290
- "呜呼",
291
- "呢",
292
- "呵",
293
- "呵呵",
294
- "呸",
295
- "呼哧",
296
- "咋",
297
- "和",
298
- "咚",
299
- "咦",
300
- "咧",
301
- "咱",
302
- "咱们",
303
- "咳",
304
- "哇",
305
- "哈",
306
- "哈哈",
307
- "哉",
308
- "哎",
309
- "哎呀",
310
- "哎哟",
311
- "哗",
312
- "哟",
313
- "哦",
314
- "哩",
315
- "哪",
316
- "哪个",
317
- "哪些",
318
- "哪儿",
319
- "哪天",
320
- "哪年",
321
- "哪怕",
322
- "哪样",
323
- "哪边",
324
- "哪里",
325
- "哼",
326
- "哼唷",
327
- "唉",
328
- "唯有",
329
- "啊",
330
- "啐",
331
- "啥",
332
- "啦",
333
- "啪达",
334
- "啷当",
335
- "喂",
336
- "喏",
337
- "喔唷",
338
- "喽",
339
- "嗡",
340
- "嗡嗡",
341
- "嗬",
342
- "嗯",
343
- "嗳",
344
- "嘎",
345
- "嘎登",
346
- "嘘",
347
- "嘛",
348
- "嘻",
349
- "嘿",
350
- "嘿嘿",
351
- "四",
352
- "因",
353
- "因为",
354
- "因了",
355
- "因此",
356
- "因着",
357
- "因而",
358
- "固然",
359
- "在",
360
- "在下",
361
- "在于",
362
- "地",
363
- "基于",
364
- "处在",
365
- "多",
366
- "多么",
367
- "多少",
368
- "大",
369
- "大家",
370
- "她",
371
- "她们",
372
- "好",
373
- "如",
374
- "如上",
375
- "如上所述",
376
- "如下",
377
- "如何",
378
- "如其",
379
- "如同",
380
- "如是",
381
- "如果",
382
- "如此",
383
- "如若",
384
- "始而",
385
- "孰料",
386
- "孰知",
387
- "宁",
388
- "宁可",
389
- "宁愿",
390
- "宁肯",
391
- "它",
392
- "它们",
393
- "对",
394
- "对于",
395
- "对待",
396
- "对方",
397
- "对比",
398
- "将",
399
- "小",
400
- "尔",
401
- "尔后",
402
- "尔尔",
403
- "尚且",
404
- "就",
405
- "就是",
406
- "就是了",
407
- "就是说",
408
- "就算",
409
- "就要",
410
- "尽",
411
- "尽管",
412
- "尽管如此",
413
- "岂但",
414
- "己",
415
- "已",
416
- "已矣",
417
- "巴",
418
- "巴巴",
419
- "年",
420
- "并",
421
- "并且",
422
- "庶乎",
423
- "庶几",
424
- "开外",
425
- "开始",
426
- "归",
427
- "归齐",
428
- "当",
429
- "当地",
430
- "当然",
431
- "当着",
432
- "彼",
433
- "彼时",
434
- "彼此",
435
- "往",
436
- "待",
437
- "很",
438
- "得",
439
- "得了",
440
- "怎",
441
- "怎么",
442
- "怎么办",
443
- "怎么样",
444
- "怎奈",
445
- "怎样",
446
- "总之",
447
- "总的来看",
448
- "总的来说",
449
- "总的说来",
450
- "总而言之",
451
- "恰恰相反",
452
- "您",
453
- "惟其",
454
- "慢说",
455
- "我",
456
- "我们",
457
- "或",
458
- "或则",
459
- "或是",
460
- "或曰",
461
- "或者",
462
- "截至",
463
- "所",
464
- "所以",
465
- "所在",
466
- "所幸",
467
- "所有",
468
- "才",
469
- "才能",
470
- "打",
471
- "打从",
472
- "把",
473
- "抑或",
474
- "拿",
475
- "按",
476
- "按照",
477
- "换句话说",
478
- "换言之",
479
- "据",
480
- "据此",
481
- "接着",
482
- "故",
483
- "故此",
484
- "故而",
485
- "旁人",
486
- "无",
487
- "无宁",
488
- "无论",
489
- "既",
490
- "既往",
491
- "既是",
492
- "既然",
493
- "日",
494
- "时",
495
- "时候",
496
- "是",
497
- "是以",
498
- "是的",
499
- "更",
500
- "曾",
501
- "替",
502
- "替代",
503
- "最",
504
- "月",
505
- "有",
506
- "有些",
507
- "有关",
508
- "有及",
509
- "有时",
510
- "有的",
511
- "望",
512
- "朝",
513
- "朝着",
514
- "本",
515
- "本人",
516
- "本地",
517
- "本着",
518
- "本身",
519
- "来",
520
- "来着",
521
- "来自",
522
- "来说",
523
- "极了",
524
- "果然",
525
- "果真",
526
- "某",
527
- "某个",
528
- "某些",
529
- "某某",
530
- "根据",
531
- "欤",
532
- "正值",
533
- "正如",
534
- "正巧",
535
- "正是",
536
- "此",
537
- "此地",
538
- "此处",
539
- "此外",
540
- "此时",
541
- "此次",
542
- "此间",
543
- "毋宁",
544
- "每",
545
- "每当",
546
- "比",
547
- "比及",
548
- "比如",
549
- "比方",
550
- "没奈何",
551
- "沿",
552
- "沿着",
553
- "漫说",
554
- "点",
555
- "焉",
556
- "然则",
557
- "然后",
558
- "然而",
559
- "照",
560
- "照着",
561
- "犹且",
562
- "犹自",
563
- "甚且",
564
- "甚么",
565
- "甚或",
566
- "甚而",
567
- "甚至",
568
- "甚至于",
569
- "用",
570
- "用来",
571
- "由",
572
- "由于",
573
- "由是",
574
- "由此",
575
- "由此可见",
576
- "的",
577
- "的确",
578
- "的话",
579
- "直到",
580
- "相对而言",
581
- "省得",
582
- "看",
583
- "眨眼",
584
- "着",
585
- "着呢",
586
- "矣",
587
- "矣乎",
588
- "矣哉",
589
- "离",
590
- "秒",
591
- "称",
592
- "竟而",
593
- "第",
594
- "等",
595
- "等到",
596
- "等等",
597
- "简言之",
598
- "管",
599
- "类如",
600
- "紧接着",
601
- "纵",
602
- "纵令",
603
- "纵使",
604
- "纵然",
605
- "经",
606
- "经过",
607
- "结果",
608
- "给",
609
- "继之",
610
- "继后",
611
- "继而",
612
- "综上所述",
613
- "罢了",
614
- "者",
615
- "而",
616
- "而且",
617
- "而况",
618
- "而后",
619
- "而外",
620
- "而已",
621
- "而是",
622
- "而言",
623
- "能",
624
- "能否",
625
- "腾",
626
- "自",
627
- "自个儿",
628
- "自从",
629
- "自各儿",
630
- "自后",
631
- "自家",
632
- "自己",
633
- "自打",
634
- "自身",
635
- "至",
636
- "至于",
637
- "至今",
638
- "至若",
639
- "致",
640
- "般的",
641
- "若",
642
- "若夫",
643
- "若是",
644
- "若果",
645
- "若非",
646
- "莫不然",
647
- "莫如",
648
- "莫若",
649
- "虽",
650
- "虽则",
651
- "虽然",
652
- "虽说",
653
- "被",
654
- "要",
655
- "要不",
656
- "要不是",
657
- "要不然",
658
- "要么",
659
- "要是",
660
- "譬喻",
661
- "譬如",
662
- "让",
663
- "许多",
664
- "论",
665
- "设使",
666
- "设或",
667
- "设若",
668
- "诚如",
669
- "诚然",
670
- "该",
671
- "说",
672
- "说来",
673
- "请",
674
- "诸",
675
- "诸位",
676
- "诸如",
677
- "谁",
678
- "谁人",
679
- "谁料",
680
- "谁知",
681
- "贼死",
682
- "赖以",
683
- "赶",
684
- "起",
685
- "起见",
686
- "趁",
687
- "趁着",
688
- "越是",
689
- "距",
690
- "跟",
691
- "较",
692
- "较之",
693
- "边",
694
- "过",
695
- "还",
696
- "还是",
697
- "还有",
698
- "还要",
699
- "这",
700
- "这一来",
701
- "这个",
702
- "这么",
703
- "这么些",
704
- "这么样",
705
- "这么点儿",
706
- "这些",
707
- "这会儿",
708
- "这儿",
709
- "这就是说",
710
- "这时",
711
- "这样",
712
- "这次",
713
- "这般",
714
- "这边",
715
- "这里",
716
- "进而",
717
- "连",
718
- "连同",
719
- "逐步",
720
- "通过",
721
- "遵循",
722
- "遵照",
723
- "那",
724
- "那个",
725
- "那么",
726
- "那么些",
727
- "那么样",
728
- "那些",
729
- "那会儿",
730
- "那儿",
731
- "那时",
732
- "那样",
733
- "那般",
734
- "那边",
735
- "那里",
736
- "都",
737
- "鄙人",
738
- "鉴于",
739
- "针对",
740
- "阿",
741
- "除",
742
- "除了",
743
- "除外",
744
- "除开",
745
- "除此之外",
746
- "除非",
747
- "随",
748
- "随后",
749
- "随时",
750
- "随着",
751
- "难道说",
752
- "零",
753
- "非",
754
- "非但",
755
- "非徒",
756
- "非特",
757
- "非独",
758
- "靠",
759
- "顺",
760
- "顺着",
761
- "首先",
762
- "︿",
763
- "!",
764
- "#",
765
- "$",
766
- "%",
767
- "&",
768
- "(",
769
- ")",
770
- "*",
771
- "+",
772
- ",",
773
- "0",
774
- "1",
775
- "2",
776
- "3",
777
- "4",
778
- "5",
779
- "6",
780
- "7",
781
- "8",
782
- "9",
783
- ":",
784
- ";",
785
- "<",
786
- ">",
787
- "?",
788
- "@",
789
- "[",
790
- "]",
791
- "{",
792
- "|",
793
- "}",
794
- "~",
795
- "¥"
796
- ]
1
+ [
2
+ "、",
3
+ "。",
4
+ "〈",
5
+ "〉",
6
+ "《",
7
+ "》",
8
+ "一",
9
+ "一个",
10
+ "一些",
11
+ "一何",
12
+ "一切",
13
+ "一则",
14
+ "一方面",
15
+ "一旦",
16
+ "一来",
17
+ "一样",
18
+ "一种",
19
+ "一般",
20
+ "一转眼",
21
+ "七",
22
+ "万一",
23
+ "三",
24
+ "上",
25
+ "上下",
26
+ "下",
27
+ "不",
28
+ "不仅",
29
+ "不但",
30
+ "不光",
31
+ "不单",
32
+ "不只",
33
+ "不外乎",
34
+ "不如",
35
+ "不妨",
36
+ "不尽",
37
+ "不尽然",
38
+ "不得",
39
+ "不怕",
40
+ "不惟",
41
+ "不成",
42
+ "不拘",
43
+ "不料",
44
+ "不是",
45
+ "不比",
46
+ "不然",
47
+ "不特",
48
+ "不独",
49
+ "不管",
50
+ "不至于",
51
+ "不若",
52
+ "不论",
53
+ "不过",
54
+ "不问",
55
+ "与",
56
+ "与其",
57
+ "与其说",
58
+ "与否",
59
+ "与此同时",
60
+ "且",
61
+ "且不说",
62
+ "且说",
63
+ "两者",
64
+ "个",
65
+ "个别",
66
+ "中",
67
+ "临",
68
+ "为",
69
+ "为了",
70
+ "为什么",
71
+ "为何",
72
+ "为止",
73
+ "为此",
74
+ "为着",
75
+ "乃",
76
+ "乃至",
77
+ "乃至于",
78
+ "么",
79
+ "之",
80
+ "之一",
81
+ "之所以",
82
+ "之类",
83
+ "乌乎",
84
+ "乎",
85
+ "乘",
86
+ "九",
87
+ "也",
88
+ "也好",
89
+ "也罢",
90
+ "了",
91
+ "二",
92
+ "二来",
93
+ "于",
94
+ "于是",
95
+ "于是乎",
96
+ "云云",
97
+ "云尔",
98
+ "五",
99
+ "些",
100
+ "亦",
101
+ "人",
102
+ "人们",
103
+ "人家",
104
+ "什",
105
+ "什么",
106
+ "什么样",
107
+ "今",
108
+ "介于",
109
+ "仍",
110
+ "仍旧",
111
+ "从",
112
+ "从此",
113
+ "从而",
114
+ "他",
115
+ "他人",
116
+ "他们",
117
+ "他们们",
118
+ "以",
119
+ "以上",
120
+ "以为",
121
+ "以便",
122
+ "以免",
123
+ "以及",
124
+ "以故",
125
+ "以期",
126
+ "以来",
127
+ "以至",
128
+ "以至于",
129
+ "以致",
130
+ "们",
131
+ "任",
132
+ "任何",
133
+ "任凭",
134
+ "会",
135
+ "似的",
136
+ "但",
137
+ "但凡",
138
+ "但是",
139
+ "何",
140
+ "何以",
141
+ "何况",
142
+ "何处",
143
+ "何时",
144
+ "余外",
145
+ "作为",
146
+ "你",
147
+ "你们",
148
+ "使",
149
+ "使得",
150
+ "例如",
151
+ "依",
152
+ "依据",
153
+ "依照",
154
+ "便于",
155
+ "俺",
156
+ "俺们",
157
+ "倘",
158
+ "倘使",
159
+ "倘或",
160
+ "倘然",
161
+ "倘若",
162
+ "借",
163
+ "借傥然",
164
+ "假使",
165
+ "假如",
166
+ "假若",
167
+ "做",
168
+ "像",
169
+ "儿",
170
+ "先不先",
171
+ "光",
172
+ "光是",
173
+ "全体",
174
+ "全部",
175
+ "八",
176
+ "六",
177
+ "兮",
178
+ "共",
179
+ "关于",
180
+ "关于具体地说",
181
+ "其",
182
+ "其一",
183
+ "其中",
184
+ "其二",
185
+ "其他",
186
+ "其余",
187
+ "其它",
188
+ "其次",
189
+ "具体地说",
190
+ "具体说来",
191
+ "兼之",
192
+ "内",
193
+ "再",
194
+ "再其次",
195
+ "再则",
196
+ "再有",
197
+ "再者",
198
+ "再者说",
199
+ "再说",
200
+ "冒",
201
+ "冲",
202
+ "况且",
203
+ "几",
204
+ "几时",
205
+ "凡",
206
+ "凡是",
207
+ "凭",
208
+ "凭借",
209
+ "出于",
210
+ "出来",
211
+ "分",
212
+ "分别",
213
+ "则",
214
+ "则甚",
215
+ "别",
216
+ "别人",
217
+ "别处",
218
+ "别是",
219
+ "别的",
220
+ "别管",
221
+ "别说",
222
+ "到",
223
+ "前后",
224
+ "前此",
225
+ "前者",
226
+ "加之",
227
+ "加以",
228
+ "区",
229
+ "即",
230
+ "即令",
231
+ "即使",
232
+ "即便",
233
+ "即如",
234
+ "即或",
235
+ "即若",
236
+ "却",
237
+ "去",
238
+ "又",
239
+ "又及",
240
+ "及",
241
+ "及其",
242
+ "及至",
243
+ "反之",
244
+ "反而",
245
+ "反过来",
246
+ "反过来说",
247
+ "受到",
248
+ "另",
249
+ "另一方面",
250
+ "另外",
251
+ "另悉",
252
+ "只",
253
+ "只当",
254
+ "只怕",
255
+ "只是",
256
+ "只有",
257
+ "只消",
258
+ "只要",
259
+ "只限",
260
+ "叫",
261
+ "叮咚",
262
+ "可",
263
+ "可以",
264
+ "可是",
265
+ "可见",
266
+ "各",
267
+ "各个",
268
+ "各位",
269
+ "各种",
270
+ "各自",
271
+ "同",
272
+ "同时",
273
+ "后",
274
+ "后者",
275
+ "向",
276
+ "向使",
277
+ "向着",
278
+ "吓",
279
+ "吗",
280
+ "否则",
281
+ "吧",
282
+ "吧哒",
283
+ "含",
284
+ "吱",
285
+ "呀",
286
+ "呃",
287
+ "呕",
288
+ "呗",
289
+ "呜",
290
+ "呜呼",
291
+ "呢",
292
+ "呵",
293
+ "呵呵",
294
+ "呸",
295
+ "呼哧",
296
+ "咋",
297
+ "和",
298
+ "咚",
299
+ "咦",
300
+ "咧",
301
+ "咱",
302
+ "咱们",
303
+ "咳",
304
+ "哇",
305
+ "哈",
306
+ "哈哈",
307
+ "哉",
308
+ "哎",
309
+ "哎呀",
310
+ "哎哟",
311
+ "哗",
312
+ "哟",
313
+ "哦",
314
+ "哩",
315
+ "哪",
316
+ "哪个",
317
+ "哪些",
318
+ "哪儿",
319
+ "哪天",
320
+ "哪年",
321
+ "哪怕",
322
+ "哪样",
323
+ "哪边",
324
+ "哪里",
325
+ "哼",
326
+ "哼唷",
327
+ "唉",
328
+ "唯有",
329
+ "啊",
330
+ "啐",
331
+ "啥",
332
+ "啦",
333
+ "啪达",
334
+ "啷当",
335
+ "喂",
336
+ "喏",
337
+ "喔唷",
338
+ "喽",
339
+ "嗡",
340
+ "嗡嗡",
341
+ "嗬",
342
+ "嗯",
343
+ "嗳",
344
+ "嘎",
345
+ "嘎登",
346
+ "嘘",
347
+ "嘛",
348
+ "嘻",
349
+ "嘿",
350
+ "嘿嘿",
351
+ "四",
352
+ "因",
353
+ "因为",
354
+ "因了",
355
+ "因此",
356
+ "因着",
357
+ "因而",
358
+ "固然",
359
+ "在",
360
+ "在下",
361
+ "在于",
362
+ "地",
363
+ "基于",
364
+ "处在",
365
+ "多",
366
+ "多么",
367
+ "多少",
368
+ "大",
369
+ "大家",
370
+ "她",
371
+ "她们",
372
+ "好",
373
+ "如",
374
+ "如上",
375
+ "如上所述",
376
+ "如下",
377
+ "如何",
378
+ "如其",
379
+ "如同",
380
+ "如是",
381
+ "如果",
382
+ "如此",
383
+ "如若",
384
+ "始而",
385
+ "孰料",
386
+ "孰知",
387
+ "宁",
388
+ "宁可",
389
+ "宁愿",
390
+ "宁肯",
391
+ "它",
392
+ "它们",
393
+ "对",
394
+ "对于",
395
+ "对待",
396
+ "对方",
397
+ "对比",
398
+ "将",
399
+ "小",
400
+ "尔",
401
+ "尔后",
402
+ "尔尔",
403
+ "尚且",
404
+ "就",
405
+ "就是",
406
+ "就是了",
407
+ "就是说",
408
+ "就算",
409
+ "就要",
410
+ "尽",
411
+ "尽管",
412
+ "尽管如此",
413
+ "岂但",
414
+ "己",
415
+ "已",
416
+ "已矣",
417
+ "巴",
418
+ "巴巴",
419
+ "年",
420
+ "并",
421
+ "并且",
422
+ "庶乎",
423
+ "庶几",
424
+ "开外",
425
+ "开始",
426
+ "归",
427
+ "归齐",
428
+ "当",
429
+ "当地",
430
+ "当然",
431
+ "当着",
432
+ "彼",
433
+ "彼时",
434
+ "彼此",
435
+ "往",
436
+ "待",
437
+ "很",
438
+ "得",
439
+ "得了",
440
+ "怎",
441
+ "怎么",
442
+ "怎么办",
443
+ "怎么样",
444
+ "怎奈",
445
+ "怎样",
446
+ "总之",
447
+ "总的来看",
448
+ "总的来说",
449
+ "总的说来",
450
+ "总而言之",
451
+ "恰恰相反",
452
+ "您",
453
+ "惟其",
454
+ "慢说",
455
+ "我",
456
+ "我们",
457
+ "或",
458
+ "或则",
459
+ "或是",
460
+ "或曰",
461
+ "或者",
462
+ "截至",
463
+ "所",
464
+ "所以",
465
+ "所在",
466
+ "所幸",
467
+ "所有",
468
+ "才",
469
+ "才能",
470
+ "打",
471
+ "打从",
472
+ "把",
473
+ "抑或",
474
+ "拿",
475
+ "按",
476
+ "按照",
477
+ "换句话说",
478
+ "换言之",
479
+ "据",
480
+ "据此",
481
+ "接着",
482
+ "故",
483
+ "故此",
484
+ "故而",
485
+ "旁人",
486
+ "无",
487
+ "无宁",
488
+ "无论",
489
+ "既",
490
+ "既往",
491
+ "既是",
492
+ "既然",
493
+ "日",
494
+ "时",
495
+ "时候",
496
+ "是",
497
+ "是以",
498
+ "是的",
499
+ "更",
500
+ "曾",
501
+ "替",
502
+ "替代",
503
+ "最",
504
+ "月",
505
+ "有",
506
+ "有些",
507
+ "有关",
508
+ "有及",
509
+ "有时",
510
+ "有的",
511
+ "望",
512
+ "朝",
513
+ "朝着",
514
+ "本",
515
+ "本人",
516
+ "本地",
517
+ "本着",
518
+ "本身",
519
+ "来",
520
+ "来着",
521
+ "来自",
522
+ "来说",
523
+ "极了",
524
+ "果然",
525
+ "果真",
526
+ "某",
527
+ "某个",
528
+ "某些",
529
+ "某某",
530
+ "根据",
531
+ "欤",
532
+ "正值",
533
+ "正如",
534
+ "正巧",
535
+ "正是",
536
+ "此",
537
+ "此地",
538
+ "此处",
539
+ "此外",
540
+ "此时",
541
+ "此次",
542
+ "此间",
543
+ "毋宁",
544
+ "每",
545
+ "每当",
546
+ "比",
547
+ "比及",
548
+ "比如",
549
+ "比方",
550
+ "没奈何",
551
+ "沿",
552
+ "沿着",
553
+ "漫说",
554
+ "点",
555
+ "焉",
556
+ "然则",
557
+ "然后",
558
+ "然而",
559
+ "照",
560
+ "照着",
561
+ "犹且",
562
+ "犹自",
563
+ "甚且",
564
+ "甚么",
565
+ "甚或",
566
+ "甚而",
567
+ "甚至",
568
+ "甚至于",
569
+ "用",
570
+ "用来",
571
+ "由",
572
+ "由于",
573
+ "由是",
574
+ "由此",
575
+ "由此可见",
576
+ "的",
577
+ "的确",
578
+ "的话",
579
+ "直到",
580
+ "相对而言",
581
+ "省得",
582
+ "看",
583
+ "眨眼",
584
+ "着",
585
+ "着呢",
586
+ "矣",
587
+ "矣乎",
588
+ "矣哉",
589
+ "离",
590
+ "秒",
591
+ "称",
592
+ "竟而",
593
+ "第",
594
+ "等",
595
+ "等到",
596
+ "等等",
597
+ "简言之",
598
+ "管",
599
+ "类如",
600
+ "紧接着",
601
+ "纵",
602
+ "纵令",
603
+ "纵使",
604
+ "纵然",
605
+ "经",
606
+ "经过",
607
+ "结果",
608
+ "给",
609
+ "继之",
610
+ "继后",
611
+ "继而",
612
+ "综上所述",
613
+ "罢了",
614
+ "者",
615
+ "而",
616
+ "而且",
617
+ "而况",
618
+ "而后",
619
+ "而外",
620
+ "而已",
621
+ "而是",
622
+ "而言",
623
+ "能",
624
+ "能否",
625
+ "腾",
626
+ "自",
627
+ "自个儿",
628
+ "自从",
629
+ "自各儿",
630
+ "自后",
631
+ "自家",
632
+ "自己",
633
+ "自打",
634
+ "自身",
635
+ "至",
636
+ "至于",
637
+ "至今",
638
+ "至若",
639
+ "致",
640
+ "般的",
641
+ "若",
642
+ "若夫",
643
+ "若是",
644
+ "若果",
645
+ "若非",
646
+ "莫不然",
647
+ "莫如",
648
+ "莫若",
649
+ "虽",
650
+ "虽则",
651
+ "虽然",
652
+ "虽说",
653
+ "被",
654
+ "要",
655
+ "要不",
656
+ "要不是",
657
+ "要不然",
658
+ "要么",
659
+ "要是",
660
+ "譬喻",
661
+ "譬如",
662
+ "让",
663
+ "许多",
664
+ "论",
665
+ "设使",
666
+ "设或",
667
+ "设若",
668
+ "诚如",
669
+ "诚然",
670
+ "该",
671
+ "说",
672
+ "说来",
673
+ "请",
674
+ "诸",
675
+ "诸位",
676
+ "诸如",
677
+ "谁",
678
+ "谁人",
679
+ "谁料",
680
+ "谁知",
681
+ "贼死",
682
+ "赖以",
683
+ "赶",
684
+ "起",
685
+ "起见",
686
+ "趁",
687
+ "趁着",
688
+ "越是",
689
+ "距",
690
+ "跟",
691
+ "较",
692
+ "较之",
693
+ "边",
694
+ "过",
695
+ "还",
696
+ "还是",
697
+ "还有",
698
+ "还要",
699
+ "这",
700
+ "这一来",
701
+ "这个",
702
+ "这么",
703
+ "这么些",
704
+ "这么样",
705
+ "这么点儿",
706
+ "这些",
707
+ "这会儿",
708
+ "这儿",
709
+ "这就是说",
710
+ "这时",
711
+ "这样",
712
+ "这次",
713
+ "这般",
714
+ "这边",
715
+ "这里",
716
+ "进而",
717
+ "连",
718
+ "连同",
719
+ "逐步",
720
+ "通过",
721
+ "遵循",
722
+ "遵照",
723
+ "那",
724
+ "那个",
725
+ "那么",
726
+ "那么些",
727
+ "那么样",
728
+ "那些",
729
+ "那会儿",
730
+ "那儿",
731
+ "那时",
732
+ "那样",
733
+ "那般",
734
+ "那边",
735
+ "那里",
736
+ "都",
737
+ "鄙人",
738
+ "鉴于",
739
+ "针对",
740
+ "阿",
741
+ "除",
742
+ "除了",
743
+ "除外",
744
+ "除开",
745
+ "除此之外",
746
+ "除非",
747
+ "随",
748
+ "随后",
749
+ "随时",
750
+ "随着",
751
+ "难道说",
752
+ "零",
753
+ "非",
754
+ "非但",
755
+ "非徒",
756
+ "非特",
757
+ "非独",
758
+ "靠",
759
+ "顺",
760
+ "顺着",
761
+ "首先",
762
+ "︿",
763
+ "!",
764
+ "#",
765
+ "$",
766
+ "%",
767
+ "&",
768
+ "(",
769
+ ")",
770
+ "*",
771
+ "+",
772
+ ",",
773
+ "0",
774
+ "1",
775
+ "2",
776
+ "3",
777
+ "4",
778
+ "5",
779
+ "6",
780
+ "7",
781
+ "8",
782
+ "9",
783
+ ":",
784
+ ";",
785
+ "<",
786
+ ">",
787
+ "?",
788
+ "@",
789
+ "[",
790
+ "]",
791
+ "{",
792
+ "|",
793
+ "}",
794
+ "~",
795
+ "¥"
796
+ ]