kreuzberg 4.0.0.pre.rc.13 → 4.0.0.pre.rc.15

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 (369) 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 +104 -2
  8. data/README.md +454 -454
  9. data/Rakefile +33 -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 +6750 -6941
  15. data/ext/kreuzberg_rb/native/Cargo.toml +53 -54
  16. data/ext/kreuzberg_rb/native/README.md +425 -425
  17. data/ext/kreuzberg_rb/native/build.rs +52 -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 -3158
  23. data/extconf.rb +28 -28
  24. data/kreuzberg.gemspec +214 -214
  25. data/lib/kreuzberg/api_proxy.rb +142 -142
  26. data/lib/kreuzberg/cache_api.rb +81 -81
  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 -80
  31. data/lib/kreuzberg/errors.rb +118 -118
  32. data/lib/kreuzberg/extraction_api.rb +340 -340
  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 -109
  41. data/lib/{pdfium.dll → libpdfium.so} +0 -0
  42. data/sig/kreuzberg/internal.rbs +184 -184
  43. data/sig/kreuzberg.rbs +546 -546
  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 +2 -2
  60. data/vendor/kreuzberg/Cargo.toml +5 -5
  61. data/vendor/kreuzberg/README.md +230 -230
  62. data/vendor/kreuzberg/benches/otel_overhead.rs +48 -48
  63. data/vendor/kreuzberg/build.rs +887 -843
  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 +87 -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 -1184
  79. data/vendor/kreuzberg/src/embeddings.rs +500 -500
  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 +634 -601
  86. data/vendor/kreuzberg/src/extraction/image.rs +491 -491
  87. data/vendor/kreuzberg/src/extraction/libreoffice.rs +574 -574
  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 -749
  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 -44
  156. data/vendor/kreuzberg/src/pdf/bundled.rs +452 -346
  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 -68
  161. data/vendor/kreuzberg/src/pdf/rendering.rs +368 -368
  162. data/vendor/kreuzberg/src/pdf/table.rs +420 -420
  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 +165 -164
  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-tesseract/.commitlintrc.json +13 -13
  305. data/vendor/kreuzberg-tesseract/.crate-ignore +2 -2
  306. data/vendor/kreuzberg-tesseract/Cargo.lock +2933 -2933
  307. data/vendor/kreuzberg-tesseract/Cargo.toml +2 -2
  308. data/vendor/kreuzberg-tesseract/LICENSE +22 -22
  309. data/vendor/kreuzberg-tesseract/README.md +399 -399
  310. data/vendor/kreuzberg-tesseract/build.rs +1354 -1354
  311. data/vendor/kreuzberg-tesseract/patches/README.md +71 -71
  312. data/vendor/kreuzberg-tesseract/patches/tesseract.diff +199 -199
  313. data/vendor/kreuzberg-tesseract/src/api.rs +1371 -1371
  314. data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +77 -77
  315. data/vendor/kreuzberg-tesseract/src/enums.rs +297 -297
  316. data/vendor/kreuzberg-tesseract/src/error.rs +81 -81
  317. data/vendor/kreuzberg-tesseract/src/lib.rs +145 -145
  318. data/vendor/kreuzberg-tesseract/src/monitor.rs +57 -57
  319. data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +197 -197
  320. data/vendor/kreuzberg-tesseract/src/page_iterator.rs +253 -253
  321. data/vendor/kreuzberg-tesseract/src/result_iterator.rs +286 -286
  322. data/vendor/kreuzberg-tesseract/src/result_renderer.rs +183 -183
  323. data/vendor/kreuzberg-tesseract/tests/integration_test.rs +211 -211
  324. data/vendor/rb-sys/.cargo_vcs_info.json +5 -5
  325. data/vendor/rb-sys/Cargo.lock +393 -393
  326. data/vendor/rb-sys/Cargo.toml +70 -70
  327. data/vendor/rb-sys/Cargo.toml.orig +57 -57
  328. data/vendor/rb-sys/LICENSE-APACHE +190 -190
  329. data/vendor/rb-sys/LICENSE-MIT +21 -21
  330. data/vendor/rb-sys/build/features.rs +111 -111
  331. data/vendor/rb-sys/build/main.rs +286 -286
  332. data/vendor/rb-sys/build/stable_api_config.rs +155 -155
  333. data/vendor/rb-sys/build/version.rs +50 -50
  334. data/vendor/rb-sys/readme.md +36 -36
  335. data/vendor/rb-sys/src/bindings.rs +21 -21
  336. data/vendor/rb-sys/src/hidden.rs +11 -11
  337. data/vendor/rb-sys/src/lib.rs +35 -35
  338. data/vendor/rb-sys/src/macros.rs +371 -371
  339. data/vendor/rb-sys/src/memory.rs +53 -53
  340. data/vendor/rb-sys/src/ruby_abi_version.rs +38 -38
  341. data/vendor/rb-sys/src/special_consts.rs +31 -31
  342. data/vendor/rb-sys/src/stable_api/compiled.c +179 -179
  343. data/vendor/rb-sys/src/stable_api/compiled.rs +257 -257
  344. data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +324 -324
  345. data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +332 -332
  346. data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +325 -325
  347. data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +323 -323
  348. data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +339 -339
  349. data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +339 -339
  350. data/vendor/rb-sys/src/stable_api.rs +260 -260
  351. data/vendor/rb-sys/src/symbol.rs +31 -31
  352. data/vendor/rb-sys/src/tracking_allocator.rs +330 -330
  353. data/vendor/rb-sys/src/utils.rs +89 -89
  354. data/vendor/rb-sys/src/value_type.rs +7 -7
  355. metadata +81 -22
  356. data/vendor/kreuzberg-ffi/Cargo.toml +0 -63
  357. data/vendor/kreuzberg-ffi/README.md +0 -851
  358. data/vendor/kreuzberg-ffi/build.rs +0 -176
  359. data/vendor/kreuzberg-ffi/cbindgen.toml +0 -27
  360. data/vendor/kreuzberg-ffi/kreuzberg-ffi-install.pc +0 -12
  361. data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +0 -12
  362. data/vendor/kreuzberg-ffi/kreuzberg.h +0 -1087
  363. data/vendor/kreuzberg-ffi/src/lib.rs +0 -3616
  364. data/vendor/kreuzberg-ffi/src/panic_shield.rs +0 -247
  365. data/vendor/kreuzberg-ffi/tests.disabled/README.md +0 -48
  366. data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +0 -299
  367. data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +0 -346
  368. data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +0 -232
  369. data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +0 -470
@@ -1,477 +1,477 @@
1
- [
2
- "abdul",
3
- "abdullah",
4
- "acara",
5
- "ada",
6
- "adalah",
7
- "ahmad",
8
- "air",
9
- "akan",
10
- "akhbar",
11
- "akhir",
12
- "aktiviti",
13
- "alam",
14
- "amat",
15
- "amerika",
16
- "anak",
17
- "anggota",
18
- "antara",
19
- "antarabangsa",
20
- "apa",
21
- "apabila",
22
- "april",
23
- "as",
24
- "asas",
25
- "asean",
26
- "asia",
27
- "asing",
28
- "atas",
29
- "atau",
30
- "australia",
31
- "awal",
32
- "awam",
33
- "bagaimanapun",
34
- "bagi",
35
- "bahagian",
36
- "bahan",
37
- "baharu",
38
- "bahawa",
39
- "baik",
40
- "bandar",
41
- "bank",
42
- "banyak",
43
- "barangan",
44
- "baru",
45
- "baru-baru",
46
- "bawah",
47
- "beberapa",
48
- "bekas",
49
- "beliau",
50
- "belum",
51
- "berada",
52
- "berakhir",
53
- "berbanding",
54
- "berdasarkan",
55
- "berharap",
56
- "berikutan",
57
- "berjaya",
58
- "berjumlah",
59
- "berkaitan",
60
- "berkata",
61
- "berkenaan",
62
- "berlaku",
63
- "bermula",
64
- "bernama",
65
- "bernilai",
66
- "bersama",
67
- "berubah",
68
- "besar",
69
- "bhd",
70
- "bidang",
71
- "bilion",
72
- "bn",
73
- "boleh",
74
- "bukan",
75
- "bulan",
76
- "bursa",
77
- "cadangan",
78
- "china",
79
- "dagangan",
80
- "dalam",
81
- "dan",
82
- "dana",
83
- "dapat",
84
- "dari",
85
- "daripada",
86
- "dasar",
87
- "datang",
88
- "datuk",
89
- "demikian",
90
- "dengan",
91
- "depan",
92
- "derivatives",
93
- "dewan",
94
- "di",
95
- "diadakan",
96
- "dibuka",
97
- "dicatatkan",
98
- "dijangka",
99
- "diniagakan",
100
- "dis",
101
- "disember",
102
- "ditutup",
103
- "dolar",
104
- "dr",
105
- "dua",
106
- "dunia",
107
- "ekonomi",
108
- "eksekutif",
109
- "eksport",
110
- "empat",
111
- "enam",
112
- "faedah",
113
- "feb",
114
- "global",
115
- "hadapan",
116
- "hanya",
117
- "harga",
118
- "hari",
119
- "hasil",
120
- "hingga",
121
- "hubungan",
122
- "ia",
123
- "iaitu",
124
- "ialah",
125
- "indeks",
126
- "india",
127
- "indonesia",
128
- "industri",
129
- "ini",
130
- "islam",
131
- "isnin",
132
- "isu",
133
- "itu",
134
- "jabatan",
135
- "jalan",
136
- "jan",
137
- "jawatan",
138
- "jawatankuasa",
139
- "jepun",
140
- "jika",
141
- "jualan",
142
- "juga",
143
- "julai",
144
- "jumaat",
145
- "jumlah",
146
- "jun",
147
- "juta",
148
- "kadar",
149
- "kalangan",
150
- "kali",
151
- "kami",
152
- "kata",
153
- "katanya",
154
- "kaunter",
155
- "kawasan",
156
- "ke",
157
- "keadaan",
158
- "kecil",
159
- "kedua",
160
- "kedua-dua",
161
- "kedudukan",
162
- "kekal",
163
- "kementerian",
164
- "kemudahan",
165
- "kenaikan",
166
- "kenyataan",
167
- "kepada",
168
- "kepentingan",
169
- "keputusan",
170
- "kerajaan",
171
- "kerana",
172
- "kereta",
173
- "kerja",
174
- "kerjasama",
175
- "kes",
176
- "keselamatan",
177
- "keseluruhan",
178
- "kesihatan",
179
- "ketika",
180
- "ketua",
181
- "keuntungan",
182
- "kewangan",
183
- "khamis",
184
- "kini",
185
- "kira-kira",
186
- "kita",
187
- "klci",
188
- "klibor",
189
- "komposit",
190
- "kontrak",
191
- "kos",
192
- "kuala",
193
- "kuasa",
194
- "kukuh",
195
- "kumpulan",
196
- "lagi",
197
- "lain",
198
- "langkah",
199
- "laporan",
200
- "lebih",
201
- "lepas",
202
- "lima",
203
- "lot",
204
- "luar",
205
- "lumpur",
206
- "mac",
207
- "mahkamah",
208
- "mahu",
209
- "majlis",
210
- "makanan",
211
- "maklumat",
212
- "malam",
213
- "malaysia",
214
- "mana",
215
- "manakala",
216
- "masa",
217
- "masalah",
218
- "masih",
219
- "masing-masing",
220
- "masyarakat",
221
- "mata",
222
- "media",
223
- "mei",
224
- "melalui",
225
- "melihat",
226
- "memandangkan",
227
- "memastikan",
228
- "membantu",
229
- "membawa",
230
- "memberi",
231
- "memberikan",
232
- "membolehkan",
233
- "membuat",
234
- "mempunyai",
235
- "menambah",
236
- "menarik",
237
- "menawarkan",
238
- "mencapai",
239
- "mencatatkan",
240
- "mendapat",
241
- "mendapatkan",
242
- "menerima",
243
- "menerusi",
244
- "mengadakan",
245
- "mengambil",
246
- "mengenai",
247
- "menggalakkan",
248
- "menggunakan",
249
- "mengikut",
250
- "mengumumkan",
251
- "mengurangkan",
252
- "meningkat",
253
- "meningkatkan",
254
- "menjadi",
255
- "menjelang",
256
- "menokok",
257
- "menteri",
258
- "menunjukkan",
259
- "menurut",
260
- "menyaksikan",
261
- "menyediakan",
262
- "mereka",
263
- "merosot",
264
- "merupakan",
265
- "mesyuarat",
266
- "minat",
267
- "minggu",
268
- "minyak",
269
- "modal",
270
- "mohd",
271
- "mudah",
272
- "mungkin",
273
- "naik",
274
- "najib",
275
- "nasional",
276
- "negara",
277
- "negara-negara",
278
- "negeri",
279
- "niaga",
280
- "nilai",
281
- "nov",
282
- "ogos",
283
- "okt",
284
- "oleh",
285
- "operasi",
286
- "orang",
287
- "pada",
288
- "pagi",
289
- "paling",
290
- "pameran",
291
- "papan",
292
- "para",
293
- "paras",
294
- "parlimen",
295
- "parti",
296
- "pasaran",
297
- "pasukan",
298
- "pegawai",
299
- "pejabat",
300
- "pekerja",
301
- "pelabur",
302
- "pelaburan",
303
- "pelancongan",
304
- "pelanggan",
305
- "pelbagai",
306
- "peluang",
307
- "pembangunan",
308
- "pemberita",
309
- "pembinaan",
310
- "pemimpin",
311
- "pendapatan",
312
- "pendidikan",
313
- "penduduk",
314
- "penerbangan",
315
- "pengarah",
316
- "pengeluaran",
317
- "pengerusi",
318
- "pengguna",
319
- "pengurusan",
320
- "peniaga",
321
- "peningkatan",
322
- "penting",
323
- "peratus",
324
- "perdagangan",
325
- "perdana",
326
- "peringkat",
327
- "perjanjian",
328
- "perkara",
329
- "perkhidmatan",
330
- "perladangan",
331
- "perlu",
332
- "permintaan",
333
- "perniagaan",
334
- "persekutuan",
335
- "persidangan",
336
- "pertama",
337
- "pertubuhan",
338
- "pertumbuhan",
339
- "perusahaan",
340
- "peserta",
341
- "petang",
342
- "pihak",
343
- "pilihan",
344
- "pinjaman",
345
- "polis",
346
- "politik",
347
- "presiden",
348
- "prestasi",
349
- "produk",
350
- "program",
351
- "projek",
352
- "proses",
353
- "proton",
354
- "pukul",
355
- "pula",
356
- "pusat",
357
- "rabu",
358
- "rakan",
359
- "rakyat",
360
- "ramai",
361
- "rantau",
362
- "raya",
363
- "rendah",
364
- "ringgit",
365
- "rumah",
366
- "sabah",
367
- "sahaja",
368
- "saham",
369
- "sama",
370
- "sarawak",
371
- "satu",
372
- "sawit",
373
- "saya",
374
- "sdn",
375
- "sebagai",
376
- "sebahagian",
377
- "sebanyak",
378
- "sebarang",
379
- "sebelum",
380
- "sebelumnya",
381
- "sebuah",
382
- "secara",
383
- "sedang",
384
- "segi",
385
- "sehingga",
386
- "sejak",
387
- "sekarang",
388
- "sektor",
389
- "sekuriti",
390
- "selain",
391
- "selama",
392
- "selasa",
393
- "selatan",
394
- "selepas",
395
- "seluruh",
396
- "semakin",
397
- "semalam",
398
- "semasa",
399
- "sementara",
400
- "semua",
401
- "semula",
402
- "sen",
403
- "sendiri",
404
- "seorang",
405
- "sepanjang",
406
- "seperti",
407
- "sept",
408
- "september",
409
- "serantau",
410
- "seri",
411
- "serta",
412
- "sesi",
413
- "setiap",
414
- "setiausaha",
415
- "sidang",
416
- "singapura",
417
- "sini",
418
- "sistem",
419
- "sokongan",
420
- "sri",
421
- "sudah",
422
- "sukan",
423
- "suku",
424
- "sumber",
425
- "supaya",
426
- "susut",
427
- "syarikat",
428
- "syed",
429
- "tahap",
430
- "tahun",
431
- "tan",
432
- "tanah",
433
- "tanpa",
434
- "tawaran",
435
- "teknologi",
436
- "telah",
437
- "tempat",
438
- "tempatan",
439
- "tempoh",
440
- "tenaga",
441
- "tengah",
442
- "tentang",
443
- "terbaik",
444
- "terbang",
445
- "terbesar",
446
- "terbuka",
447
- "terdapat",
448
- "terhadap",
449
- "termasuk",
450
- "tersebut",
451
- "terus",
452
- "tetapi",
453
- "thailand",
454
- "tiada",
455
- "tidak",
456
- "tiga",
457
- "timbalan",
458
- "timur",
459
- "tindakan",
460
- "tinggi",
461
- "tun",
462
- "tunai",
463
- "turun",
464
- "turut",
465
- "umno",
466
- "unit",
467
- "untuk",
468
- "untung",
469
- "urus",
470
- "usaha",
471
- "utama",
472
- "walaupun",
473
- "wang",
474
- "wanita",
475
- "wilayah",
476
- "yang"
477
- ]
1
+ [
2
+ "abdul",
3
+ "abdullah",
4
+ "acara",
5
+ "ada",
6
+ "adalah",
7
+ "ahmad",
8
+ "air",
9
+ "akan",
10
+ "akhbar",
11
+ "akhir",
12
+ "aktiviti",
13
+ "alam",
14
+ "amat",
15
+ "amerika",
16
+ "anak",
17
+ "anggota",
18
+ "antara",
19
+ "antarabangsa",
20
+ "apa",
21
+ "apabila",
22
+ "april",
23
+ "as",
24
+ "asas",
25
+ "asean",
26
+ "asia",
27
+ "asing",
28
+ "atas",
29
+ "atau",
30
+ "australia",
31
+ "awal",
32
+ "awam",
33
+ "bagaimanapun",
34
+ "bagi",
35
+ "bahagian",
36
+ "bahan",
37
+ "baharu",
38
+ "bahawa",
39
+ "baik",
40
+ "bandar",
41
+ "bank",
42
+ "banyak",
43
+ "barangan",
44
+ "baru",
45
+ "baru-baru",
46
+ "bawah",
47
+ "beberapa",
48
+ "bekas",
49
+ "beliau",
50
+ "belum",
51
+ "berada",
52
+ "berakhir",
53
+ "berbanding",
54
+ "berdasarkan",
55
+ "berharap",
56
+ "berikutan",
57
+ "berjaya",
58
+ "berjumlah",
59
+ "berkaitan",
60
+ "berkata",
61
+ "berkenaan",
62
+ "berlaku",
63
+ "bermula",
64
+ "bernama",
65
+ "bernilai",
66
+ "bersama",
67
+ "berubah",
68
+ "besar",
69
+ "bhd",
70
+ "bidang",
71
+ "bilion",
72
+ "bn",
73
+ "boleh",
74
+ "bukan",
75
+ "bulan",
76
+ "bursa",
77
+ "cadangan",
78
+ "china",
79
+ "dagangan",
80
+ "dalam",
81
+ "dan",
82
+ "dana",
83
+ "dapat",
84
+ "dari",
85
+ "daripada",
86
+ "dasar",
87
+ "datang",
88
+ "datuk",
89
+ "demikian",
90
+ "dengan",
91
+ "depan",
92
+ "derivatives",
93
+ "dewan",
94
+ "di",
95
+ "diadakan",
96
+ "dibuka",
97
+ "dicatatkan",
98
+ "dijangka",
99
+ "diniagakan",
100
+ "dis",
101
+ "disember",
102
+ "ditutup",
103
+ "dolar",
104
+ "dr",
105
+ "dua",
106
+ "dunia",
107
+ "ekonomi",
108
+ "eksekutif",
109
+ "eksport",
110
+ "empat",
111
+ "enam",
112
+ "faedah",
113
+ "feb",
114
+ "global",
115
+ "hadapan",
116
+ "hanya",
117
+ "harga",
118
+ "hari",
119
+ "hasil",
120
+ "hingga",
121
+ "hubungan",
122
+ "ia",
123
+ "iaitu",
124
+ "ialah",
125
+ "indeks",
126
+ "india",
127
+ "indonesia",
128
+ "industri",
129
+ "ini",
130
+ "islam",
131
+ "isnin",
132
+ "isu",
133
+ "itu",
134
+ "jabatan",
135
+ "jalan",
136
+ "jan",
137
+ "jawatan",
138
+ "jawatankuasa",
139
+ "jepun",
140
+ "jika",
141
+ "jualan",
142
+ "juga",
143
+ "julai",
144
+ "jumaat",
145
+ "jumlah",
146
+ "jun",
147
+ "juta",
148
+ "kadar",
149
+ "kalangan",
150
+ "kali",
151
+ "kami",
152
+ "kata",
153
+ "katanya",
154
+ "kaunter",
155
+ "kawasan",
156
+ "ke",
157
+ "keadaan",
158
+ "kecil",
159
+ "kedua",
160
+ "kedua-dua",
161
+ "kedudukan",
162
+ "kekal",
163
+ "kementerian",
164
+ "kemudahan",
165
+ "kenaikan",
166
+ "kenyataan",
167
+ "kepada",
168
+ "kepentingan",
169
+ "keputusan",
170
+ "kerajaan",
171
+ "kerana",
172
+ "kereta",
173
+ "kerja",
174
+ "kerjasama",
175
+ "kes",
176
+ "keselamatan",
177
+ "keseluruhan",
178
+ "kesihatan",
179
+ "ketika",
180
+ "ketua",
181
+ "keuntungan",
182
+ "kewangan",
183
+ "khamis",
184
+ "kini",
185
+ "kira-kira",
186
+ "kita",
187
+ "klci",
188
+ "klibor",
189
+ "komposit",
190
+ "kontrak",
191
+ "kos",
192
+ "kuala",
193
+ "kuasa",
194
+ "kukuh",
195
+ "kumpulan",
196
+ "lagi",
197
+ "lain",
198
+ "langkah",
199
+ "laporan",
200
+ "lebih",
201
+ "lepas",
202
+ "lima",
203
+ "lot",
204
+ "luar",
205
+ "lumpur",
206
+ "mac",
207
+ "mahkamah",
208
+ "mahu",
209
+ "majlis",
210
+ "makanan",
211
+ "maklumat",
212
+ "malam",
213
+ "malaysia",
214
+ "mana",
215
+ "manakala",
216
+ "masa",
217
+ "masalah",
218
+ "masih",
219
+ "masing-masing",
220
+ "masyarakat",
221
+ "mata",
222
+ "media",
223
+ "mei",
224
+ "melalui",
225
+ "melihat",
226
+ "memandangkan",
227
+ "memastikan",
228
+ "membantu",
229
+ "membawa",
230
+ "memberi",
231
+ "memberikan",
232
+ "membolehkan",
233
+ "membuat",
234
+ "mempunyai",
235
+ "menambah",
236
+ "menarik",
237
+ "menawarkan",
238
+ "mencapai",
239
+ "mencatatkan",
240
+ "mendapat",
241
+ "mendapatkan",
242
+ "menerima",
243
+ "menerusi",
244
+ "mengadakan",
245
+ "mengambil",
246
+ "mengenai",
247
+ "menggalakkan",
248
+ "menggunakan",
249
+ "mengikut",
250
+ "mengumumkan",
251
+ "mengurangkan",
252
+ "meningkat",
253
+ "meningkatkan",
254
+ "menjadi",
255
+ "menjelang",
256
+ "menokok",
257
+ "menteri",
258
+ "menunjukkan",
259
+ "menurut",
260
+ "menyaksikan",
261
+ "menyediakan",
262
+ "mereka",
263
+ "merosot",
264
+ "merupakan",
265
+ "mesyuarat",
266
+ "minat",
267
+ "minggu",
268
+ "minyak",
269
+ "modal",
270
+ "mohd",
271
+ "mudah",
272
+ "mungkin",
273
+ "naik",
274
+ "najib",
275
+ "nasional",
276
+ "negara",
277
+ "negara-negara",
278
+ "negeri",
279
+ "niaga",
280
+ "nilai",
281
+ "nov",
282
+ "ogos",
283
+ "okt",
284
+ "oleh",
285
+ "operasi",
286
+ "orang",
287
+ "pada",
288
+ "pagi",
289
+ "paling",
290
+ "pameran",
291
+ "papan",
292
+ "para",
293
+ "paras",
294
+ "parlimen",
295
+ "parti",
296
+ "pasaran",
297
+ "pasukan",
298
+ "pegawai",
299
+ "pejabat",
300
+ "pekerja",
301
+ "pelabur",
302
+ "pelaburan",
303
+ "pelancongan",
304
+ "pelanggan",
305
+ "pelbagai",
306
+ "peluang",
307
+ "pembangunan",
308
+ "pemberita",
309
+ "pembinaan",
310
+ "pemimpin",
311
+ "pendapatan",
312
+ "pendidikan",
313
+ "penduduk",
314
+ "penerbangan",
315
+ "pengarah",
316
+ "pengeluaran",
317
+ "pengerusi",
318
+ "pengguna",
319
+ "pengurusan",
320
+ "peniaga",
321
+ "peningkatan",
322
+ "penting",
323
+ "peratus",
324
+ "perdagangan",
325
+ "perdana",
326
+ "peringkat",
327
+ "perjanjian",
328
+ "perkara",
329
+ "perkhidmatan",
330
+ "perladangan",
331
+ "perlu",
332
+ "permintaan",
333
+ "perniagaan",
334
+ "persekutuan",
335
+ "persidangan",
336
+ "pertama",
337
+ "pertubuhan",
338
+ "pertumbuhan",
339
+ "perusahaan",
340
+ "peserta",
341
+ "petang",
342
+ "pihak",
343
+ "pilihan",
344
+ "pinjaman",
345
+ "polis",
346
+ "politik",
347
+ "presiden",
348
+ "prestasi",
349
+ "produk",
350
+ "program",
351
+ "projek",
352
+ "proses",
353
+ "proton",
354
+ "pukul",
355
+ "pula",
356
+ "pusat",
357
+ "rabu",
358
+ "rakan",
359
+ "rakyat",
360
+ "ramai",
361
+ "rantau",
362
+ "raya",
363
+ "rendah",
364
+ "ringgit",
365
+ "rumah",
366
+ "sabah",
367
+ "sahaja",
368
+ "saham",
369
+ "sama",
370
+ "sarawak",
371
+ "satu",
372
+ "sawit",
373
+ "saya",
374
+ "sdn",
375
+ "sebagai",
376
+ "sebahagian",
377
+ "sebanyak",
378
+ "sebarang",
379
+ "sebelum",
380
+ "sebelumnya",
381
+ "sebuah",
382
+ "secara",
383
+ "sedang",
384
+ "segi",
385
+ "sehingga",
386
+ "sejak",
387
+ "sekarang",
388
+ "sektor",
389
+ "sekuriti",
390
+ "selain",
391
+ "selama",
392
+ "selasa",
393
+ "selatan",
394
+ "selepas",
395
+ "seluruh",
396
+ "semakin",
397
+ "semalam",
398
+ "semasa",
399
+ "sementara",
400
+ "semua",
401
+ "semula",
402
+ "sen",
403
+ "sendiri",
404
+ "seorang",
405
+ "sepanjang",
406
+ "seperti",
407
+ "sept",
408
+ "september",
409
+ "serantau",
410
+ "seri",
411
+ "serta",
412
+ "sesi",
413
+ "setiap",
414
+ "setiausaha",
415
+ "sidang",
416
+ "singapura",
417
+ "sini",
418
+ "sistem",
419
+ "sokongan",
420
+ "sri",
421
+ "sudah",
422
+ "sukan",
423
+ "suku",
424
+ "sumber",
425
+ "supaya",
426
+ "susut",
427
+ "syarikat",
428
+ "syed",
429
+ "tahap",
430
+ "tahun",
431
+ "tan",
432
+ "tanah",
433
+ "tanpa",
434
+ "tawaran",
435
+ "teknologi",
436
+ "telah",
437
+ "tempat",
438
+ "tempatan",
439
+ "tempoh",
440
+ "tenaga",
441
+ "tengah",
442
+ "tentang",
443
+ "terbaik",
444
+ "terbang",
445
+ "terbesar",
446
+ "terbuka",
447
+ "terdapat",
448
+ "terhadap",
449
+ "termasuk",
450
+ "tersebut",
451
+ "terus",
452
+ "tetapi",
453
+ "thailand",
454
+ "tiada",
455
+ "tidak",
456
+ "tiga",
457
+ "timbalan",
458
+ "timur",
459
+ "tindakan",
460
+ "tinggi",
461
+ "tun",
462
+ "tunai",
463
+ "turun",
464
+ "turut",
465
+ "umno",
466
+ "unit",
467
+ "untuk",
468
+ "untung",
469
+ "urus",
470
+ "usaha",
471
+ "utama",
472
+ "walaupun",
473
+ "wang",
474
+ "wanita",
475
+ "wilayah",
476
+ "yang"
477
+ ]