@wanshi-kg/wanshi 0.1.0

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 (443) hide show
  1. package/LICENSE +21 -0
  2. package/README.md +458 -0
  3. package/dist/__tests__/helpers.js +27 -0
  4. package/dist/__tests__/helpers.js.map +1 -0
  5. package/dist/cli/commands/export.command.js +99 -0
  6. package/dist/cli/commands/export.command.js.map +1 -0
  7. package/dist/cli/commands/index.js +22 -0
  8. package/dist/cli/commands/index.js.map +1 -0
  9. package/dist/cli/commands/inspectMerges.command.js +84 -0
  10. package/dist/cli/commands/inspectMerges.command.js.map +1 -0
  11. package/dist/cli/commands/metrics.command.js +196 -0
  12. package/dist/cli/commands/metrics.command.js.map +1 -0
  13. package/dist/cli/commands/process.command.js +82 -0
  14. package/dist/cli/commands/process.command.js.map +1 -0
  15. package/dist/cli/commands/watch.command.js +91 -0
  16. package/dist/cli/commands/watch.command.js.map +1 -0
  17. package/dist/cli/index.js +269 -0
  18. package/dist/cli/index.js.map +1 -0
  19. package/dist/cli/optionsToConfig.js +160 -0
  20. package/dist/cli/optionsToConfig.js.map +1 -0
  21. package/dist/config/index.js +59 -0
  22. package/dist/config/index.js.map +1 -0
  23. package/dist/config/legacyHints.js +113 -0
  24. package/dist/config/legacyHints.js.map +1 -0
  25. package/dist/config/schema.js +803 -0
  26. package/dist/config/schema.js.map +1 -0
  27. package/dist/config/ui.js +221 -0
  28. package/dist/config/ui.js.map +1 -0
  29. package/dist/core/DirectoryProcessor.js +725 -0
  30. package/dist/core/DirectoryProcessor.js.map +1 -0
  31. package/dist/core/adapters/IStructuredAdapter.js +3 -0
  32. package/dist/core/adapters/IStructuredAdapter.js.map +1 -0
  33. package/dist/core/adapters/SqliteAdapter.js +267 -0
  34. package/dist/core/adapters/SqliteAdapter.js.map +1 -0
  35. package/dist/core/adapters/StructuredAdapterRegistry.js +31 -0
  36. package/dist/core/adapters/StructuredAdapterRegistry.js.map +1 -0
  37. package/dist/core/adapters/index.js +20 -0
  38. package/dist/core/adapters/index.js.map +1 -0
  39. package/dist/core/checkpoint/CheckpointService.js +188 -0
  40. package/dist/core/checkpoint/CheckpointService.js.map +1 -0
  41. package/dist/core/checkpoint/index.js +18 -0
  42. package/dist/core/checkpoint/index.js.map +1 -0
  43. package/dist/core/corpus/CorpusAnalyzer.js +266 -0
  44. package/dist/core/corpus/CorpusAnalyzer.js.map +1 -0
  45. package/dist/core/corpus/CorpusProfileStore.js +92 -0
  46. package/dist/core/corpus/CorpusProfileStore.js.map +1 -0
  47. package/dist/core/corpus/index.js +21 -0
  48. package/dist/core/corpus/index.js.map +1 -0
  49. package/dist/core/corpus/normalizeGlossary.js +60 -0
  50. package/dist/core/corpus/normalizeGlossary.js.map +1 -0
  51. package/dist/core/corpus/relPath.js +52 -0
  52. package/dist/core/corpus/relPath.js.map +1 -0
  53. package/dist/core/corpus/termFrequency.js +86 -0
  54. package/dist/core/corpus/termFrequency.js.map +1 -0
  55. package/dist/core/cost/CostMeter.js +235 -0
  56. package/dist/core/cost/CostMeter.js.map +1 -0
  57. package/dist/core/cost/index.js +19 -0
  58. package/dist/core/cost/index.js.map +1 -0
  59. package/dist/core/cost/prices.js +38 -0
  60. package/dist/core/cost/prices.js.map +1 -0
  61. package/dist/core/cv/ObjectDetectionService.js +119 -0
  62. package/dist/core/cv/ObjectDetectionService.js.map +1 -0
  63. package/dist/core/di/ContainerFactory.js +670 -0
  64. package/dist/core/di/ContainerFactory.js.map +1 -0
  65. package/dist/core/di/DIContainer.js +103 -0
  66. package/dist/core/di/DIContainer.js.map +1 -0
  67. package/dist/core/di/index.js +19 -0
  68. package/dist/core/di/index.js.map +1 -0
  69. package/dist/core/errors/CustomErrors.js +342 -0
  70. package/dist/core/errors/CustomErrors.js.map +1 -0
  71. package/dist/core/errors/index.js +18 -0
  72. package/dist/core/errors/index.js.map +1 -0
  73. package/dist/core/export/KnowledgeGraphExportService.js +56 -0
  74. package/dist/core/export/KnowledgeGraphExportService.js.map +1 -0
  75. package/dist/core/export/index.js +19 -0
  76. package/dist/core/export/index.js.map +1 -0
  77. package/dist/core/export/strategies/GraphitiExportStrategy.js +115 -0
  78. package/dist/core/export/strategies/GraphitiExportStrategy.js.map +1 -0
  79. package/dist/core/export/strategies/GraphvizDotExportStrategy.js +331 -0
  80. package/dist/core/export/strategies/GraphvizDotExportStrategy.js.map +1 -0
  81. package/dist/core/export/strategies/IExportStrategy.js +3 -0
  82. package/dist/core/export/strategies/IExportStrategy.js.map +1 -0
  83. package/dist/core/export/strategies/JsonExportStrategy.js +19 -0
  84. package/dist/core/export/strategies/JsonExportStrategy.js.map +1 -0
  85. package/dist/core/export/strategies/JsonlExportStrategy.js +69 -0
  86. package/dist/core/export/strategies/JsonlExportStrategy.js.map +1 -0
  87. package/dist/core/export/strategies/KblamExportStrategy.js +36 -0
  88. package/dist/core/export/strategies/KblamExportStrategy.js.map +1 -0
  89. package/dist/core/export/strategies/LoraExportStrategy.js +46 -0
  90. package/dist/core/export/strategies/LoraExportStrategy.js.map +1 -0
  91. package/dist/core/export/strategies/McpExportStrategy.js +67 -0
  92. package/dist/core/export/strategies/McpExportStrategy.js.map +1 -0
  93. package/dist/core/export/strategies/index.js +25 -0
  94. package/dist/core/export/strategies/index.js.map +1 -0
  95. package/dist/core/export/strategies/kbTriples.js +60 -0
  96. package/dist/core/export/strategies/kbTriples.js.map +1 -0
  97. package/dist/core/index.js +22 -0
  98. package/dist/core/index.js.map +1 -0
  99. package/dist/core/knowledge/KnowledgeGraphBuilder.js +627 -0
  100. package/dist/core/knowledge/KnowledgeGraphBuilder.js.map +1 -0
  101. package/dist/core/knowledge/MergeRecord.js +3 -0
  102. package/dist/core/knowledge/MergeRecord.js.map +1 -0
  103. package/dist/core/knowledge/canon/Canonicalizer.js +414 -0
  104. package/dist/core/knowledge/canon/Canonicalizer.js.map +1 -0
  105. package/dist/core/knowledge/canon/index.js +18 -0
  106. package/dist/core/knowledge/canon/index.js.map +1 -0
  107. package/dist/core/knowledge/contradiction/HeuristicContradictionChecker.js +92 -0
  108. package/dist/core/knowledge/contradiction/HeuristicContradictionChecker.js.map +1 -0
  109. package/dist/core/knowledge/contradiction/LlmContradictionChecker.js +52 -0
  110. package/dist/core/knowledge/contradiction/LlmContradictionChecker.js.map +1 -0
  111. package/dist/core/knowledge/contradiction/index.js +19 -0
  112. package/dist/core/knowledge/contradiction/index.js.map +1 -0
  113. package/dist/core/knowledge/grounding/KeywordGroundingChecker.js +33 -0
  114. package/dist/core/knowledge/grounding/KeywordGroundingChecker.js.map +1 -0
  115. package/dist/core/knowledge/grounding/MiniCheckGroundingChecker.js +82 -0
  116. package/dist/core/knowledge/grounding/MiniCheckGroundingChecker.js.map +1 -0
  117. package/dist/core/knowledge/grounding/index.js +20 -0
  118. package/dist/core/knowledge/grounding/index.js.map +1 -0
  119. package/dist/core/knowledge/grounding/verbalize.js +38 -0
  120. package/dist/core/knowledge/grounding/verbalize.js.map +1 -0
  121. package/dist/core/knowledge/images/imageMetaGraph.js +136 -0
  122. package/dist/core/knowledge/images/imageMetaGraph.js.map +1 -0
  123. package/dist/core/knowledge/index.js +20 -0
  124. package/dist/core/knowledge/index.js.map +1 -0
  125. package/dist/core/knowledge/merging/KnowledgeMerger.js +624 -0
  126. package/dist/core/knowledge/merging/KnowledgeMerger.js.map +1 -0
  127. package/dist/core/knowledge/references/ReferenceResolver.js +184 -0
  128. package/dist/core/knowledge/references/ReferenceResolver.js.map +1 -0
  129. package/dist/core/knowledge/references/citations/CitationEvidenceProcessor.js +401 -0
  130. package/dist/core/knowledge/references/citations/CitationEvidenceProcessor.js.map +1 -0
  131. package/dist/core/knowledge/references/citations/CitationResolver.js +95 -0
  132. package/dist/core/knowledge/references/citations/CitationResolver.js.map +1 -0
  133. package/dist/core/knowledge/references/citations/GrobidClient.js +143 -0
  134. package/dist/core/knowledge/references/citations/GrobidClient.js.map +1 -0
  135. package/dist/core/knowledge/references/citations/TitleIdResolver.js +101 -0
  136. package/dist/core/knowledge/references/citations/TitleIdResolver.js.map +1 -0
  137. package/dist/core/knowledge/references/web/FetchCacheService.js +114 -0
  138. package/dist/core/knowledge/references/web/FetchCacheService.js.map +1 -0
  139. package/dist/core/knowledge/references/web/GatedFetcher.js +228 -0
  140. package/dist/core/knowledge/references/web/GatedFetcher.js.map +1 -0
  141. package/dist/core/knowledge/references/web/WebReferenceProcessor.js +164 -0
  142. package/dist/core/knowledge/references/web/WebReferenceProcessor.js.map +1 -0
  143. package/dist/core/knowledge/search/KnowledgeGraphSearch.js +261 -0
  144. package/dist/core/knowledge/search/KnowledgeGraphSearch.js.map +1 -0
  145. package/dist/core/knowledge/vocabulary.js +162 -0
  146. package/dist/core/knowledge/vocabulary.js.map +1 -0
  147. package/dist/core/llm/EmbeddingService.js +113 -0
  148. package/dist/core/llm/EmbeddingService.js.map +1 -0
  149. package/dist/core/llm/OllamaService.js +146 -0
  150. package/dist/core/llm/OllamaService.js.map +1 -0
  151. package/dist/core/llm/OpenAICompatibleService.js +190 -0
  152. package/dist/core/llm/OpenAICompatibleService.js.map +1 -0
  153. package/dist/core/llm/OpenAIEmbeddingService.js +129 -0
  154. package/dist/core/llm/OpenAIEmbeddingService.js.map +1 -0
  155. package/dist/core/llm/embeddingUtils.js +25 -0
  156. package/dist/core/llm/embeddingUtils.js.map +1 -0
  157. package/dist/core/llm/index.js +23 -0
  158. package/dist/core/llm/index.js.map +1 -0
  159. package/dist/core/llm/prompts/PromptManager.js +388 -0
  160. package/dist/core/llm/prompts/PromptManager.js.map +1 -0
  161. package/dist/core/llm/prompts/PromptTemplateEngine.js +257 -0
  162. package/dist/core/llm/prompts/PromptTemplateEngine.js.map +1 -0
  163. package/dist/core/llm/prompts/templates/partials/examples/EXAMPLE_STYLE_GUIDE.md +84 -0
  164. package/dist/core/llm/prompts/templates/partials/examples/article.md +187 -0
  165. package/dist/core/llm/prompts/templates/partials/examples/code.md +229 -0
  166. package/dist/core/llm/prompts/templates/partials/examples/communication.md +205 -0
  167. package/dist/core/llm/prompts/templates/partials/examples/documentation.md +262 -0
  168. package/dist/core/llm/prompts/templates/partials/examples/financial.md +157 -0
  169. package/dist/core/llm/prompts/templates/partials/examples/legal.md +153 -0
  170. package/dist/core/llm/prompts/templates/partials/examples/logs.md +127 -0
  171. package/dist/core/llm/prompts/templates/partials/examples/medical.md +218 -0
  172. package/dist/core/llm/prompts/templates/partials/examples/notes.md +201 -0
  173. package/dist/core/llm/prompts/templates/partials/examples/research.md +208 -0
  174. package/dist/core/llm/prompts/templates/partials/examples/tabular.md +178 -0
  175. package/dist/core/llm/prompts/templates/partials/examples/transcript.md +204 -0
  176. package/dist/core/llm/prompts/templates/partials/retrieved-context.hbs +18 -0
  177. package/dist/core/llm/prompts/templates/v1/system.hbs +371 -0
  178. package/dist/core/llm/prompts/templates/v1/user.hbs +20 -0
  179. package/dist/core/llm/prompts/templates/v2/system.hbs +573 -0
  180. package/dist/core/llm/prompts/templates/v2/user.hbs +20 -0
  181. package/dist/core/llm/prompts/templates/v3/system.hbs +861 -0
  182. package/dist/core/llm/prompts/templates/v3/user.hbs +16 -0
  183. package/dist/core/llm/prompts/templates/v4/system.hbs +800 -0
  184. package/dist/core/llm/prompts/templates/v4/user.hbs +40 -0
  185. package/dist/core/llm/prompts/templates/v4.5/system.hbs +71 -0
  186. package/dist/core/llm/prompts/templates/v4.5/user.hbs +46 -0
  187. package/dist/core/llm/prompts/templates/v5/glossary/system.hbs +40 -0
  188. package/dist/core/llm/prompts/templates/v5/glossary/user.hbs +11 -0
  189. package/dist/core/llm/prompts/templates/v5/system.hbs +163 -0
  190. package/dist/core/llm/prompts/templates/v5/user.hbs +55 -0
  191. package/dist/core/pipeline/GroundingTransform.js +52 -0
  192. package/dist/core/pipeline/GroundingTransform.js.map +1 -0
  193. package/dist/core/pipeline/PipelineRunner.js +51 -0
  194. package/dist/core/pipeline/PipelineRunner.js.map +1 -0
  195. package/dist/core/pipeline/RelationFilterTransform.js +72 -0
  196. package/dist/core/pipeline/RelationFilterTransform.js.map +1 -0
  197. package/dist/core/pipeline/index.js +20 -0
  198. package/dist/core/pipeline/index.js.map +1 -0
  199. package/dist/core/processor/FileProcessor.js +184 -0
  200. package/dist/core/processor/FileProcessor.js.map +1 -0
  201. package/dist/core/processor/ProcessedRegistry.js +38 -0
  202. package/dist/core/processor/ProcessedRegistry.js.map +1 -0
  203. package/dist/core/processor/ast/AstSeedService.js +0 -0
  204. package/dist/core/processor/ast/AstSeedService.js.map +1 -0
  205. package/dist/core/processor/ast/AstSymbolStore.js +110 -0
  206. package/dist/core/processor/ast/AstSymbolStore.js.map +1 -0
  207. package/dist/core/processor/ast/index.js +19 -0
  208. package/dist/core/processor/ast/index.js.map +1 -0
  209. package/dist/core/processor/chunking/TextChunker.js +98 -0
  210. package/dist/core/processor/chunking/TextChunker.js.map +1 -0
  211. package/dist/core/processor/chunking/index.js +18 -0
  212. package/dist/core/processor/chunking/index.js.map +1 -0
  213. package/dist/core/processor/classifier/CONTENT_CLASSES.js +294 -0
  214. package/dist/core/processor/classifier/CONTENT_CLASSES.js.map +1 -0
  215. package/dist/core/processor/classifier/CascadeContentClassifier.js +107 -0
  216. package/dist/core/processor/classifier/CascadeContentClassifier.js.map +1 -0
  217. package/dist/core/processor/classifier/HeuristicContentClassifier.js +113 -0
  218. package/dist/core/processor/classifier/HeuristicContentClassifier.js.map +1 -0
  219. package/dist/core/processor/classifier/IContentTypeClassifier.js +3 -0
  220. package/dist/core/processor/classifier/IContentTypeClassifier.js.map +1 -0
  221. package/dist/core/processor/classifier/LlmContentClassifier.js +107 -0
  222. package/dist/core/processor/classifier/LlmContentClassifier.js.map +1 -0
  223. package/dist/core/processor/classifier/NER_DOMAIN_EXAMPLES.js +498 -0
  224. package/dist/core/processor/classifier/NER_DOMAIN_EXAMPLES.js.map +1 -0
  225. package/dist/core/processor/classifier/index.js +21 -0
  226. package/dist/core/processor/classifier/index.js.map +1 -0
  227. package/dist/core/processor/classifier/mergeClassifications.js +32 -0
  228. package/dist/core/processor/classifier/mergeClassifications.js.map +1 -0
  229. package/dist/core/processor/index.js +20 -0
  230. package/dist/core/processor/index.js.map +1 -0
  231. package/dist/core/processor/readers/AudioReader.js +462 -0
  232. package/dist/core/processor/readers/AudioReader.js.map +1 -0
  233. package/dist/core/processor/readers/BinaryReader.js +90 -0
  234. package/dist/core/processor/readers/BinaryReader.js.map +1 -0
  235. package/dist/core/processor/readers/ChandraPdfReader.js +187 -0
  236. package/dist/core/processor/readers/ChandraPdfReader.js.map +1 -0
  237. package/dist/core/processor/readers/ChatExportReader.js +365 -0
  238. package/dist/core/processor/readers/ChatExportReader.js.map +1 -0
  239. package/dist/core/processor/readers/DoclingReader.js +445 -0
  240. package/dist/core/processor/readers/DoclingReader.js.map +1 -0
  241. package/dist/core/processor/readers/EmailReader.js +259 -0
  242. package/dist/core/processor/readers/EmailReader.js.map +1 -0
  243. package/dist/core/processor/readers/EpubReader.js +175 -0
  244. package/dist/core/processor/readers/EpubReader.js.map +1 -0
  245. package/dist/core/processor/readers/FileReader.js +90 -0
  246. package/dist/core/processor/readers/FileReader.js.map +1 -0
  247. package/dist/core/processor/readers/FileReaderFactory.js +49 -0
  248. package/dist/core/processor/readers/FileReaderFactory.js.map +1 -0
  249. package/dist/core/processor/readers/HtmlReader.js +371 -0
  250. package/dist/core/processor/readers/HtmlReader.js.map +1 -0
  251. package/dist/core/processor/readers/ImageReader.js +162 -0
  252. package/dist/core/processor/readers/ImageReader.js.map +1 -0
  253. package/dist/core/processor/readers/JsonFileReader.js +232 -0
  254. package/dist/core/processor/readers/JsonFileReader.js.map +1 -0
  255. package/dist/core/processor/readers/JupyterReader.js +178 -0
  256. package/dist/core/processor/readers/JupyterReader.js.map +1 -0
  257. package/dist/core/processor/readers/LatexReader.js +176 -0
  258. package/dist/core/processor/readers/LatexReader.js.map +1 -0
  259. package/dist/core/processor/readers/MarkdownReader.js +289 -0
  260. package/dist/core/processor/readers/MarkdownReader.js.map +1 -0
  261. package/dist/core/processor/readers/MarkerPdfReader.js +193 -0
  262. package/dist/core/processor/readers/MarkerPdfReader.js.map +1 -0
  263. package/dist/core/processor/readers/MistralOcrReader.js +198 -0
  264. package/dist/core/processor/readers/MistralOcrReader.js.map +1 -0
  265. package/dist/core/processor/readers/OfficeReader.js +174 -0
  266. package/dist/core/processor/readers/OfficeReader.js.map +1 -0
  267. package/dist/core/processor/readers/PdfReader.js +116 -0
  268. package/dist/core/processor/readers/PdfReader.js.map +1 -0
  269. package/dist/core/processor/readers/RtfReader.js +107 -0
  270. package/dist/core/processor/readers/RtfReader.js.map +1 -0
  271. package/dist/core/processor/readers/SubtitleReader.js +145 -0
  272. package/dist/core/processor/readers/SubtitleReader.js.map +1 -0
  273. package/dist/core/processor/readers/TesseractPdfReader.js +183 -0
  274. package/dist/core/processor/readers/TesseractPdfReader.js.map +1 -0
  275. package/dist/core/processor/readers/TextReader.js +129 -0
  276. package/dist/core/processor/readers/TextReader.js.map +1 -0
  277. package/dist/core/processor/readers/TranscriptReader.js +234 -0
  278. package/dist/core/processor/readers/TranscriptReader.js.map +1 -0
  279. package/dist/core/processor/readers/image/imageMetadata.js +155 -0
  280. package/dist/core/processor/readers/image/imageMetadata.js.map +1 -0
  281. package/dist/core/processor/readers/index.js +41 -0
  282. package/dist/core/processor/readers/index.js.map +1 -0
  283. package/dist/core/processor/readers/referenceExtraction.js +198 -0
  284. package/dist/core/processor/readers/referenceExtraction.js.map +1 -0
  285. package/dist/core/processor/readers/stripReferences.js +59 -0
  286. package/dist/core/processor/readers/stripReferences.js.map +1 -0
  287. package/dist/core/processor/readers/transcript/turnPacking.js +81 -0
  288. package/dist/core/processor/readers/transcript/turnPacking.js.map +1 -0
  289. package/dist/core/progress/NdjsonProgressEmitter.js +30 -0
  290. package/dist/core/progress/NdjsonProgressEmitter.js.map +1 -0
  291. package/dist/core/progress/NoopProgressEmitter.js +15 -0
  292. package/dist/core/progress/NoopProgressEmitter.js.map +1 -0
  293. package/dist/core/progress/index.js +19 -0
  294. package/dist/core/progress/index.js.map +1 -0
  295. package/dist/core/trace/TraceWriter.js +100 -0
  296. package/dist/core/trace/TraceWriter.js.map +1 -0
  297. package/dist/core/trace/events.js +13 -0
  298. package/dist/core/trace/events.js.map +1 -0
  299. package/dist/core/trace/index.js +20 -0
  300. package/dist/core/trace/index.js.map +1 -0
  301. package/dist/core/trace/lineage.js +97 -0
  302. package/dist/core/trace/lineage.js.map +1 -0
  303. package/dist/evaluation/BenchmarkRunner.js +171 -0
  304. package/dist/evaluation/BenchmarkRunner.js.map +1 -0
  305. package/dist/evaluation/classifier/ClassifierAccuracy.js +185 -0
  306. package/dist/evaluation/classifier/ClassifierAccuracy.js.map +1 -0
  307. package/dist/evaluation/classifier/labeledSamples.js +379 -0
  308. package/dist/evaluation/classifier/labeledSamples.js.map +1 -0
  309. package/dist/evaluation/compare/goldCompare.js +126 -0
  310. package/dist/evaluation/compare/goldCompare.js.map +1 -0
  311. package/dist/evaluation/crossre/compareScoring.js +30 -0
  312. package/dist/evaluation/crossre/compareScoring.js.map +1 -0
  313. package/dist/evaluation/datasets/CrossREDataset.js +170 -0
  314. package/dist/evaluation/datasets/CrossREDataset.js.map +1 -0
  315. package/dist/evaluation/datasets/IDataset.js +3 -0
  316. package/dist/evaluation/datasets/IDataset.js.map +1 -0
  317. package/dist/evaluation/datasets/RebelDataset.js +117 -0
  318. package/dist/evaluation/datasets/RebelDataset.js.map +1 -0
  319. package/dist/evaluation/datasets/RedocredDataset.js +218 -0
  320. package/dist/evaluation/datasets/RedocredDataset.js.map +1 -0
  321. package/dist/evaluation/datasets/SemEval2010Dataset.js +150 -0
  322. package/dist/evaluation/datasets/SemEval2010Dataset.js.map +1 -0
  323. package/dist/evaluation/index.js +33 -0
  324. package/dist/evaluation/index.js.map +1 -0
  325. package/dist/evaluation/matching/ExactMatcher.js +75 -0
  326. package/dist/evaluation/matching/ExactMatcher.js.map +1 -0
  327. package/dist/evaluation/matching/SemanticMatcher.js +143 -0
  328. package/dist/evaluation/matching/SemanticMatcher.js.map +1 -0
  329. package/dist/evaluation/metrics/TripleMetrics.js +64 -0
  330. package/dist/evaluation/metrics/TripleMetrics.js.map +1 -0
  331. package/dist/evaluation/mine/MineCheckpoint.js +114 -0
  332. package/dist/evaluation/mine/MineCheckpoint.js.map +1 -0
  333. package/dist/evaluation/mine/MineDataset.js +208 -0
  334. package/dist/evaluation/mine/MineDataset.js.map +1 -0
  335. package/dist/evaluation/mine/MineReporter.js +98 -0
  336. package/dist/evaluation/mine/MineReporter.js.map +1 -0
  337. package/dist/evaluation/mine/MineRunner.js +148 -0
  338. package/dist/evaluation/mine/MineRunner.js.map +1 -0
  339. package/dist/evaluation/mine/MineScorer.js +127 -0
  340. package/dist/evaluation/mine/MineScorer.js.map +1 -0
  341. package/dist/evaluation/mine/types.js +12 -0
  342. package/dist/evaluation/mine/types.js.map +1 -0
  343. package/dist/evaluation/reporters/ConsoleReporter.js +55 -0
  344. package/dist/evaluation/reporters/ConsoleReporter.js.map +1 -0
  345. package/dist/evaluation/reporters/JsonReporter.js +50 -0
  346. package/dist/evaluation/reporters/JsonReporter.js.map +1 -0
  347. package/dist/index.js +28 -0
  348. package/dist/index.js.map +1 -0
  349. package/dist/quality/CompositeScore.js +61 -0
  350. package/dist/quality/CompositeScore.js.map +1 -0
  351. package/dist/quality/ConsistencyMetrics.js +70 -0
  352. package/dist/quality/ConsistencyMetrics.js.map +1 -0
  353. package/dist/quality/FactualMetrics.js +76 -0
  354. package/dist/quality/FactualMetrics.js.map +1 -0
  355. package/dist/quality/GraphHealthMetrics.js +68 -0
  356. package/dist/quality/GraphHealthMetrics.js.map +1 -0
  357. package/dist/quality/SemanticMetrics.js +102 -0
  358. package/dist/quality/SemanticMetrics.js.map +1 -0
  359. package/dist/quality/StructuralMetrics.js +60 -0
  360. package/dist/quality/StructuralMetrics.js.map +1 -0
  361. package/dist/quality/index.js +23 -0
  362. package/dist/quality/index.js.map +1 -0
  363. package/dist/shared/index.js +20 -0
  364. package/dist/shared/index.js.map +1 -0
  365. package/dist/shared/logger/Logger.js +3 -0
  366. package/dist/shared/logger/Logger.js.map +1 -0
  367. package/dist/shared/logger/LoggerFactory.js +75 -0
  368. package/dist/shared/logger/LoggerFactory.js.map +1 -0
  369. package/dist/shared/logger/index.js +19 -0
  370. package/dist/shared/logger/index.js.map +1 -0
  371. package/dist/shared/shutdown.js +30 -0
  372. package/dist/shared/shutdown.js.map +1 -0
  373. package/dist/shared/utils/agglomerativeCluster.js +269 -0
  374. package/dist/shared/utils/agglomerativeCluster.js.map +1 -0
  375. package/dist/shared/utils/astSymbols.js +69 -0
  376. package/dist/shared/utils/astSymbols.js.map +1 -0
  377. package/dist/shared/utils/cosineSimilarity.js +18 -0
  378. package/dist/shared/utils/cosineSimilarity.js.map +1 -0
  379. package/dist/shared/utils/directoryTree.js +184 -0
  380. package/dist/shared/utils/directoryTree.js.map +1 -0
  381. package/dist/shared/utils/documentOutline.js +74 -0
  382. package/dist/shared/utils/documentOutline.js.map +1 -0
  383. package/dist/shared/utils/index.js +24 -0
  384. package/dist/shared/utils/index.js.map +1 -0
  385. package/dist/shared/utils/jaroWinklerSimilarity.js +60 -0
  386. package/dist/shared/utils/jaroWinklerSimilarity.js.map +1 -0
  387. package/dist/shared/utils/parseJsonLenient.js +27 -0
  388. package/dist/shared/utils/parseJsonLenient.js.map +1 -0
  389. package/dist/shared/utils/readConfig.js +42 -0
  390. package/dist/shared/utils/readConfig.js.map +1 -0
  391. package/dist/shared/utils/readRtf.js +216 -0
  392. package/dist/shared/utils/readRtf.js.map +1 -0
  393. package/dist/shared/utils/softmax.js +26 -0
  394. package/dist/shared/utils/softmax.js.map +1 -0
  395. package/dist/types/ContentClass.js +3 -0
  396. package/dist/types/ContentClass.js.map +1 -0
  397. package/dist/types/CorpusProfile.js +3 -0
  398. package/dist/types/CorpusProfile.js.map +1 -0
  399. package/dist/types/IContradictionChecker.js +3 -0
  400. package/dist/types/IContradictionChecker.js.map +1 -0
  401. package/dist/types/ICorpusAnalyzer.js +3 -0
  402. package/dist/types/ICorpusAnalyzer.js.map +1 -0
  403. package/dist/types/IDirectoryProcessor.js +3 -0
  404. package/dist/types/IDirectoryProcessor.js.map +1 -0
  405. package/dist/types/IEmbeddingProvider.js +3 -0
  406. package/dist/types/IEmbeddingProvider.js.map +1 -0
  407. package/dist/types/IEmbeddingService.js +6 -0
  408. package/dist/types/IEmbeddingService.js.map +1 -0
  409. package/dist/types/IFileProcessor.js +3 -0
  410. package/dist/types/IFileProcessor.js.map +1 -0
  411. package/dist/types/IGroundingChecker.js +3 -0
  412. package/dist/types/IGroundingChecker.js.map +1 -0
  413. package/dist/types/IKnowledgeGraphBuilder.js +3 -0
  414. package/dist/types/IKnowledgeGraphBuilder.js.map +1 -0
  415. package/dist/types/IKnowledgeGraphExporter.js +3 -0
  416. package/dist/types/IKnowledgeGraphExporter.js.map +1 -0
  417. package/dist/types/IKnowledgeGraphMerger.js +3 -0
  418. package/dist/types/IKnowledgeGraphMerger.js.map +1 -0
  419. package/dist/types/IKnowledgeGraphSearch.js +3 -0
  420. package/dist/types/IKnowledgeGraphSearch.js.map +1 -0
  421. package/dist/types/ILLMProvider.js +3 -0
  422. package/dist/types/ILLMProvider.js.map +1 -0
  423. package/dist/types/ILLMService.js +3 -0
  424. package/dist/types/ILLMService.js.map +1 -0
  425. package/dist/types/IObjectDetector.js +3 -0
  426. package/dist/types/IObjectDetector.js.map +1 -0
  427. package/dist/types/IProcessingService.js +3 -0
  428. package/dist/types/IProcessingService.js.map +1 -0
  429. package/dist/types/IProgressEmitter.js +3 -0
  430. package/dist/types/IProgressEmitter.js.map +1 -0
  431. package/dist/types/IPromptManager.js +3 -0
  432. package/dist/types/IPromptManager.js.map +1 -0
  433. package/dist/types/KnowledgeGraph.js +3 -0
  434. package/dist/types/KnowledgeGraph.js.map +1 -0
  435. package/dist/types/MCPKnowledgeGraph.js +3 -0
  436. package/dist/types/MCPKnowledgeGraph.js.map +1 -0
  437. package/dist/types/Observation.js +21 -0
  438. package/dist/types/Observation.js.map +1 -0
  439. package/dist/types/ProcessingOptions.js +3 -0
  440. package/dist/types/ProcessingOptions.js.map +1 -0
  441. package/dist/types/index.js +40 -0
  442. package/dist/types/index.js.map +1 -0
  443. package/package.json +122 -0
@@ -0,0 +1,184 @@
1
+ "use strict";
2
+ var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
3
+ if (k2 === undefined) k2 = k;
4
+ var desc = Object.getOwnPropertyDescriptor(m, k);
5
+ if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
6
+ desc = { enumerable: true, get: function() { return m[k]; } };
7
+ }
8
+ Object.defineProperty(o, k2, desc);
9
+ }) : (function(o, m, k, k2) {
10
+ if (k2 === undefined) k2 = k;
11
+ o[k2] = m[k];
12
+ }));
13
+ var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
14
+ Object.defineProperty(o, "default", { enumerable: true, value: v });
15
+ }) : function(o, v) {
16
+ o["default"] = v;
17
+ });
18
+ var __importStar = (this && this.__importStar) || (function () {
19
+ var ownKeys = function(o) {
20
+ ownKeys = Object.getOwnPropertyNames || function (o) {
21
+ var ar = [];
22
+ for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
23
+ return ar;
24
+ };
25
+ return ownKeys(o);
26
+ };
27
+ return function (mod) {
28
+ if (mod && mod.__esModule) return mod;
29
+ var result = {};
30
+ if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
31
+ __setModuleDefault(result, mod);
32
+ return result;
33
+ };
34
+ })();
35
+ var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
36
+ function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
37
+ return new (P || (P = Promise))(function (resolve, reject) {
38
+ function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
39
+ function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
40
+ function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
41
+ step((generator = generator.apply(thisArg, _arguments || [])).next());
42
+ });
43
+ };
44
+ Object.defineProperty(exports, "__esModule", { value: true });
45
+ exports.FileProcessor = void 0;
46
+ const path = __importStar(require("path"));
47
+ const mergeClassifications_1 = require("./classifier/mergeClassifications");
48
+ const vocabulary_1 = require("../knowledge/vocabulary");
49
+ const trace_1 = require("../trace");
50
+ /**
51
+ * Main file processor that coordinates reading and chunking
52
+ */
53
+ class FileProcessor {
54
+ constructor(readerFactory, classifier, attachImages, logger) {
55
+ this.readerFactory = readerFactory;
56
+ this.logger = logger;
57
+ this.attachImages = attachImages;
58
+ this.classifier = classifier;
59
+ }
60
+ /**
61
+ * Process a single file - read and optionally chunk it
62
+ */
63
+ processFile(filePath, cachedClasses) {
64
+ return __awaiter(this, void 0, void 0, function* () {
65
+ this.logger.info(`Processing file: ${filePath}`);
66
+ // Get appropriate reader
67
+ const reader = this.readerFactory.getReader(filePath);
68
+ if (!reader) {
69
+ this.logger.warn(`No reader available for file: ${filePath}`);
70
+ return {
71
+ chunks: [],
72
+ path: filePath,
73
+ metadata: {
74
+ error: "No reader available",
75
+ fileType: path.extname(filePath),
76
+ },
77
+ };
78
+ }
79
+ try {
80
+ // Read the file
81
+ const readResult = yield reader.read(filePath);
82
+ // Ingest trace: which reader matched + chunk boundaries/provenance (the spine).
83
+ if (trace_1.trace.enabled) {
84
+ for (const chunk of readResult.chunks) {
85
+ trace_1.trace.emit(Object.assign({ stage: "ingest", type: "chunk", chunkId: `${filePath}#${chunk.index}`, file: filePath, chunkIndex: chunk.index, totalChunks: chunk.totalChunks, reader: reader.getName(), contentLength: chunk.content.length }, (chunk.provenance ? { provenance: chunk.provenance } : {})));
86
+ }
87
+ }
88
+ // Return results
89
+ return {
90
+ path: filePath,
91
+ content: this.reconstructContent(readResult.chunks),
92
+ chunks: readResult.chunks.map((chunk) => {
93
+ var _a, _b, _c;
94
+ return Object.assign({ content: chunk.content, index: chunk.index, totalChunks: chunk.totalChunks, startOffset: chunk.startOffset, endOffset: chunk.endOffset,
95
+ // Central ECS source-tagging: stamp `sourceAdapter` from the matched
96
+ // reader onto every chunk (a reader may pre-set a finer id / a locator).
97
+ provenance: Object.assign(Object.assign({}, chunk.provenance), { sourceAdapter: (_b = (_a = chunk.provenance) === null || _a === void 0 ? void 0 : _a.sourceAdapter) !== null && _b !== void 0 ? _b : reader.adapterId() }) }, (this.attachImages && {
98
+ images: (_c = chunk.images) === null || _c === void 0 ? void 0 : _c.map((image) => {
99
+ var _a;
100
+ return {
101
+ path: image.path,
102
+ caption: image.alt,
103
+ base64: (_a = image.buffer) === null || _a === void 0 ? void 0 : _a.toString("base64"),
104
+ };
105
+ }),
106
+ }));
107
+ }),
108
+ metadata: Object.assign(Object.assign({}, readResult.metadata), {
109
+ // Reuse the corpus pre-pass's cached classification when provided,
110
+ // otherwise classify now (the classifier is the expensive bit).
111
+ classes: cachedClasses !== null && cachedClasses !== void 0 ? cachedClasses : (yield this.classifyContent(filePath, readResult)), chunked: false }),
112
+ };
113
+ }
114
+ catch (error) {
115
+ this.logger.error(`Failed to process file ${filePath}: ${error}`);
116
+ throw new Error(`Failed to process file ${filePath}: ${error}`);
117
+ }
118
+ });
119
+ }
120
+ /**
121
+ * Reconstruct the full source text from chunks using their offsets, dropping
122
+ * any overlap added by the chunker. Falls back to plain concatenation when
123
+ * offsets are absent/unreliable. Used for outline generation and grounding.
124
+ */
125
+ reconstructContent(chunks) {
126
+ var _a, _b;
127
+ if (chunks.length === 0)
128
+ return "";
129
+ if (chunks.length === 1)
130
+ return chunks[0].content;
131
+ const sorted = [...chunks].sort((a, b) => { var _a, _b; return ((_a = a.startOffset) !== null && _a !== void 0 ? _a : 0) - ((_b = b.startOffset) !== null && _b !== void 0 ? _b : 0); });
132
+ let result = "";
133
+ let cursor = 0;
134
+ for (const c of sorted) {
135
+ const start = (_a = c.startOffset) !== null && _a !== void 0 ? _a : cursor;
136
+ const end = (_b = c.endOffset) !== null && _b !== void 0 ? _b : start + c.content.length;
137
+ if (start >= cursor) {
138
+ result += c.content;
139
+ }
140
+ else {
141
+ const overlap = cursor - start;
142
+ result += overlap < c.content.length ? c.content.slice(overlap) : "";
143
+ }
144
+ cursor = Math.max(cursor, end);
145
+ }
146
+ return result;
147
+ }
148
+ classifyContent(filePath, readResult) {
149
+ return __awaiter(this, void 0, void 0, function* () {
150
+ const classifier = this.classifier;
151
+ if (!classifier)
152
+ return undefined;
153
+ try {
154
+ // Classify every chunk, then prevalence-weight across the whole file so a
155
+ // pervasive domain outranks a single off-topic chunk (see mergeChunkClassifications).
156
+ const perChunk = yield Promise.all(readResult.chunks.map((chunk) => classifier.classify(chunk.content, filePath)));
157
+ const merged = (0, mergeClassifications_1.mergeChunkClassifications)(perChunk);
158
+ if (trace_1.trace.enabled) {
159
+ const active = (0, vocabulary_1.activeDomainClasses)(merged);
160
+ trace_1.trace.emit({
161
+ stage: "classify", type: "classification", file: filePath,
162
+ distribution: merged.map((r) => ({ class: r.class, confidence: r.confidence })),
163
+ gate: active.length === 0 ? "abstain" : active.length === 1 ? "single" : "multi",
164
+ activeClasses: active,
165
+ escalated: false,
166
+ });
167
+ }
168
+ return merged;
169
+ }
170
+ catch (error) {
171
+ this.logger.error("Unable to classify file content.", error);
172
+ return undefined;
173
+ }
174
+ });
175
+ }
176
+ /**
177
+ * Check if a file can be processed
178
+ */
179
+ canProcess(filePath) {
180
+ return this.readerFactory.canRead(filePath);
181
+ }
182
+ }
183
+ exports.FileProcessor = FileProcessor;
184
+ //# sourceMappingURL=FileProcessor.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"FileProcessor.js","sourceRoot":"","sources":["../../../src/core/processor/FileProcessor.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAAA,2CAA6B;AAW7B,4EAA8E;AAC9E,wDAA8D;AAC9D,oCAAiC;AAEjC;;GAEG;AACH,MAAa,aAAa;IAMxB,YACE,aAAgC,EAChC,UAA0C,EAC1C,YAAqB,EACrB,MAAc;QAEd,IAAI,CAAC,aAAa,GAAG,aAAa,CAAC;QACnC,IAAI,CAAC,MAAM,GAAG,MAAM,CAAC;QACrB,IAAI,CAAC,YAAY,GAAG,YAAY,CAAC;QACjC,IAAI,CAAC,UAAU,GAAG,UAAU,CAAC;IAC/B,CAAC;IAED;;OAEG;IACG,WAAW,CACf,QAAgB,EAChB,aAAsC;;YAEtC,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,oBAAoB,QAAQ,EAAE,CAAC,CAAC;YAEjD,yBAAyB;YACzB,MAAM,MAAM,GAAG,IAAI,CAAC,aAAa,CAAC,SAAS,CAAC,QAAQ,CAAC,CAAC;YACtD,IAAI,CAAC,MAAM,EAAE,CAAC;gBACZ,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,iCAAiC,QAAQ,EAAE,CAAC,CAAC;gBAC9D,OAAO;oBACL,MAAM,EAAE,EAAE;oBACV,IAAI,EAAE,QAAQ;oBACd,QAAQ,EAAE;wBACR,KAAK,EAAE,qBAAqB;wBAC5B,QAAQ,EAAE,IAAI,CAAC,OAAO,CAAC,QAAQ,CAAC;qBACjC;iBACF,CAAC;YACJ,CAAC;YAED,IAAI,CAAC;gBACH,gBAAgB;gBAChB,MAAM,UAAU,GAAG,MAAM,MAAM,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;gBAE/C,gFAAgF;gBAChF,IAAI,aAAK,CAAC,OAAO,EAAE,CAAC;oBAClB,KAAK,MAAM,KAAK,IAAI,UAAU,CAAC,MAAM,EAAE,CAAC;wBACtC,aAAK,CAAC,IAAI,iBACR,KAAK,EAAE,QAAQ,EAAE,IAAI,EAAE,OAAO,EAC9B,OAAO,EAAE,GAAG,QAAQ,IAAI,KAAK,CAAC,KAAK,EAAE,EAAE,IAAI,EAAE,QAAQ,EACrD,UAAU,EAAE,KAAK,CAAC,KAAK,EAAE,WAAW,EAAE,KAAK,CAAC,WAAW,EACvD,MAAM,EAAE,MAAM,CAAC,OAAO,EAAE,EAAE,aAAa,EAAE,KAAK,CAAC,OAAO,CAAC,MAAM,IAC1D,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC,CAAC,EAAE,UAAU,EAAE,KAAK,CAAC,UAAqC,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,EACxF,CAAC;oBACL,CAAC;gBACH,CAAC;gBAED,iBAAiB;gBACjB,OAAO;oBACL,IAAI,EAAE,QAAQ;oBACd,OAAO,EAAE,IAAI,CAAC,kBAAkB,CAAC,UAAU,CAAC,MAAM,CAAC;oBACnD,MAAM,EAAE,UAAU,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE;;wBACtC,OAAO,gBACL,OAAO,EAAE,KAAK,CAAC,OAAO,EACtB,KAAK,EAAE,KAAK,CAAC,KAAK,EAClB,WAAW,EAAE,KAAK,CAAC,WAAW,EAC9B,WAAW,EAAE,KAAK,CAAC,WAAW,EAC9B,SAAS,EAAE,KAAK,CAAC,SAAS;4BAC1B,qEAAqE;4BACrE,yEAAyE;4BACzE,UAAU,kCACL,KAAK,CAAC,UAAU,KACnB,aAAa,EAAE,MAAA,MAAA,KAAK,CAAC,UAAU,0CAAE,aAAa,mCAAI,MAAM,CAAC,SAAS,EAAE,OAEnE,CAAC,IAAI,CAAC,YAAY,IAAI;4BACvB,MAAM,EAAE,MAAA,KAAK,CAAC,MAAM,0CAAE,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE;;gCAClC,OAAO;oCACL,IAAI,EAAE,KAAK,CAAC,IAAI;oCAChB,OAAO,EAAE,KAAK,CAAC,GAAG;oCAClB,MAAM,EAAE,MAAA,KAAK,CAAC,MAAM,0CAAE,QAAQ,CAAC,QAAQ,CAAC;iCACvB,CAAC;4BACtB,CAAC,CAAC;yBACH,CAAC,CACe,CAAC;oBACtB,CAAC,CAAC;oBACF,QAAQ,kCACH,UAAU,CAAC,QAAQ;wBACtB,mEAAmE;wBACnE,gEAAgE;wBAChE,OAAO,EAAE,aAAa,aAAb,aAAa,cAAb,aAAa,GAAI,CAAC,MAAM,IAAI,CAAC,eAAe,CAAC,QAAQ,EAAE,UAAU,CAAC,CAAC,EAC5E,OAAO,EAAE,KAAK,GACf;iBACF,CAAC;YACJ,CAAC;YAAC,OAAO,KAAK,EAAE,CAAC;gBACf,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,0BAA0B,QAAQ,KAAK,KAAK,EAAE,CAAC,CAAC;gBAClE,MAAM,IAAI,KAAK,CAAC,0BAA0B,QAAQ,KAAK,KAAK,EAAE,CAAC,CAAC;YAClE,CAAC;QACH,CAAC;KAAA;IAED;;;;OAIG;IACK,kBAAkB,CACxB,MAAuE;;QAEvE,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC;YAAE,OAAO,EAAE,CAAC;QACnC,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC;YAAE,OAAO,MAAM,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC;QAElD,MAAM,MAAM,GAAG,CAAC,GAAG,MAAM,CAAC,CAAC,IAAI,CAC7B,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,eAAC,OAAA,CAAC,MAAA,CAAC,CAAC,WAAW,mCAAI,CAAC,CAAC,GAAG,CAAC,MAAA,CAAC,CAAC,WAAW,mCAAI,CAAC,CAAC,CAAA,EAAA,CACtD,CAAC;QACF,IAAI,MAAM,GAAG,EAAE,CAAC;QAChB,IAAI,MAAM,GAAG,CAAC,CAAC;QACf,KAAK,MAAM,CAAC,IAAI,MAAM,EAAE,CAAC;YACvB,MAAM,KAAK,GAAG,MAAA,CAAC,CAAC,WAAW,mCAAI,MAAM,CAAC;YACtC,MAAM,GAAG,GAAG,MAAA,CAAC,CAAC,SAAS,mCAAI,KAAK,GAAG,CAAC,CAAC,OAAO,CAAC,MAAM,CAAC;YACpD,IAAI,KAAK,IAAI,MAAM,EAAE,CAAC;gBACpB,MAAM,IAAI,CAAC,CAAC,OAAO,CAAC;YACtB,CAAC;iBAAM,CAAC;gBACN,MAAM,OAAO,GAAG,MAAM,GAAG,KAAK,CAAC;gBAC/B,MAAM,IAAI,OAAO,GAAG,CAAC,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;YACvE,CAAC;YACD,MAAM,GAAG,IAAI,CAAC,GAAG,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC;QACjC,CAAC;QACD,OAAO,MAAM,CAAC;IAChB,CAAC;IAEa,eAAe,CAAC,QAAgB,EAAE,UAA0B;;YACxE,MAAM,UAAU,GAAG,IAAI,CAAC,UAAU,CAAC;YACnC,IAAI,CAAC,UAAU;gBAAE,OAAO,SAAS,CAAC;YAClC,IAAI,CAAC;gBACH,0EAA0E;gBAC1E,sFAAsF;gBACtF,MAAM,QAAQ,GAAG,MAAM,OAAO,CAAC,GAAG,CAChC,UAAU,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAC9B,UAAU,CAAC,QAAQ,CAAC,KAAK,CAAC,OAAO,EAAE,QAAQ,CAAC,CAC7C,CACF,CAAC;gBACF,MAAM,MAAM,GAAG,IAAA,gDAAyB,EAAC,QAAQ,CAAC,CAAC;gBACnD,IAAI,aAAK,CAAC,OAAO,EAAE,CAAC;oBAClB,MAAM,MAAM,GAAG,IAAA,gCAAmB,EAAC,MAAM,CAAC,CAAC;oBAC3C,aAAK,CAAC,IAAI,CAAC;wBACT,KAAK,EAAE,UAAU,EAAE,IAAI,EAAE,gBAAgB,EAAE,IAAI,EAAE,QAAQ;wBACzD,YAAY,EAAE,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC,KAAK,EAAE,UAAU,EAAE,CAAC,CAAC,UAAU,EAAE,CAAC,CAAC;wBAC/E,IAAI,EAAE,MAAM,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,MAAM,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,OAAO;wBAChF,aAAa,EAAE,MAAM;wBACrB,SAAS,EAAE,KAAK;qBACjB,CAAC,CAAC;gBACL,CAAC;gBACD,OAAO,MAAM,CAAC;YAChB,CAAC;YAAC,OAAO,KAAK,EAAE,CAAC;gBACf,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,kCAAkC,EAAE,KAAK,CAAC,CAAC;gBAC7D,OAAO,SAAS,CAAC;YACnB,CAAC;QACH,CAAC;KAAA;IAED;;OAEG;IACH,UAAU,CAAC,QAAgB;QACzB,OAAO,IAAI,CAAC,aAAa,CAAC,OAAO,CAAC,QAAQ,CAAC,CAAC;IAC9C,CAAC;CACF;AArKD,sCAqKC"}
@@ -0,0 +1,38 @@
1
+ "use strict";
2
+ Object.defineProperty(exports, "__esModule", { value: true });
3
+ exports.ProcessedRegistry = void 0;
4
+ /**
5
+ * In-run processed-file registry — the "don't re-read already-processed files" gate.
6
+ *
7
+ * One shared instance per run, consulted by the file worklist (and, later, the
8
+ * Phase-1 network fetcher) so a file is read/extracted **at most once** no matter
9
+ * how it's reached: overlapping globs, reference-following (an INDEX doc linking to
10
+ * everything), or fetch. Primary identity is the canonical corpus-relative path id
11
+ * (`toRelPathId`); an optional content-hash secondary catches the same content under
12
+ * a different path (symlink/copy).
13
+ *
14
+ * Distinct from the resume checkpoint (`CheckpointService`): that dedups per-CHUNK
15
+ * LLM extraction ACROSS runs; this dedups whole-file READS WITHIN a run. They compose.
16
+ */
17
+ class ProcessedRegistry {
18
+ constructor() {
19
+ this.ids = new Set();
20
+ this.hashes = new Set();
21
+ }
22
+ /** Already processed this run — by path id, or (if given) by identical content. */
23
+ has(relPathId, contentHash) {
24
+ return this.ids.has(relPathId) || (contentHash !== undefined && this.hashes.has(contentHash));
25
+ }
26
+ /** Record a file as processed. Idempotent. */
27
+ mark(relPathId, contentHash) {
28
+ this.ids.add(relPathId);
29
+ if (contentHash !== undefined)
30
+ this.hashes.add(contentHash);
31
+ }
32
+ /** Count of distinct files processed (by path id). */
33
+ get size() {
34
+ return this.ids.size;
35
+ }
36
+ }
37
+ exports.ProcessedRegistry = ProcessedRegistry;
38
+ //# sourceMappingURL=ProcessedRegistry.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"ProcessedRegistry.js","sourceRoot":"","sources":["../../../src/core/processor/ProcessedRegistry.ts"],"names":[],"mappings":";;;AAAA;;;;;;;;;;;;GAYG;AACH,MAAa,iBAAiB;IAA9B;QACmB,QAAG,GAAG,IAAI,GAAG,EAAU,CAAC;QACxB,WAAM,GAAG,IAAI,GAAG,EAAU,CAAC;IAiB9C,CAAC;IAfC,mFAAmF;IACnF,GAAG,CAAC,SAAiB,EAAE,WAAoB;QACzC,OAAO,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,SAAS,CAAC,IAAI,CAAC,WAAW,KAAK,SAAS,IAAI,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,WAAW,CAAC,CAAC,CAAC;IAChG,CAAC;IAED,8CAA8C;IAC9C,IAAI,CAAC,SAAiB,EAAE,WAAoB;QAC1C,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,SAAS,CAAC,CAAC;QACxB,IAAI,WAAW,KAAK,SAAS;YAAE,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,WAAW,CAAC,CAAC;IAC9D,CAAC;IAED,sDAAsD;IACtD,IAAI,IAAI;QACN,OAAO,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC;IACvB,CAAC;CACF;AAnBD,8CAmBC"}
@@ -0,0 +1 @@
1
+ {"version":3,"file":"AstSeedService.js","sourceRoot":"","sources":["../../../../src/core/processor/ast/AstSeedService.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAAA,2CAA6B;AAC7B,iEAAgE;AAIhE,iEAO0C;AAE1C;;;;;;;;;GASG;AACH,MAAa,cAAc;IAGzB,YACmB,KAAqB,EACrB,MAAc,EACd,YAAoB,EAAE;QAFtB,UAAK,GAAL,KAAK,CAAgB;QACrB,WAAM,GAAN,MAAM,CAAQ;QACd,cAAS,GAAT,SAAS,CAAa;QALxB,cAAS,GAAG,IAAI,iBAAe,EAAE,CAAC;IAMhD,CAAC;IAEJ,8DAA8D;IACxD,SAAS;;YACb,MAAM,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC;QAC1B,CAAC;KAAA;IAED,8DAA8D;IACxD,SAAS;;YACb,MAAM,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC;QAC1B,CAAC;KAAA;IAED,sFAAsF;IAChF,SAAS,CAAC,aAA4B;;YAC1C,MAAM,OAAO,GAAG,aAAa,CAAC,OAAO,CAAC;YACtC,IAAI,CAAC,OAAO;gBAAE,OAAO,IAAI,CAAC;YAC1B,MAAM,GAAG,GAAG,IAAI,CAAC,OAAO,CAAC,aAAa,CAAC,IAAI,CAAC,CAAC,OAAO,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC;YAChE,IAAI,CAAC,GAAG;gBAAE,OAAO,IAAI,CAAC;YAEtB,MAAM,IAAI,GAAG,IAAA,wBAAW,EAAC,OAAO,CAAC,CAAC;YAClC,IAAI,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;YACjC,IAAI,CAAC,KAAK,EAAE,CAAC;gBACX,KAAK,GAAG,MAAM,IAAI,CAAC,SAAS,CAAC,kBAAkB,CAAC,OAAO,EAAE,GAAG,CAAC,CAAC;gBAC9D,IAAI,CAAC,KAAK;oBAAE,OAAO,IAAI,CAAC,CAAC,kEAAkE;gBAC3F,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK,CAAC,CAAC;YAC9B,CAAC;YACD,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,MAAM;gBAAE,OAAO,IAAI,CAAC;YAEvC,OAAO,IAAI,CAAC,OAAO,CAAC,KAAK,EAAE,aAAa,CAAC,IAAI,CAAC,CAAC;QACjD,CAAC;KAAA;IAEO,OAAO,CAAC,KAAkB,EAAE,QAAgB;;QAClD,MAAM,SAAS,GAAG,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE,CAAC;QAC3C,MAAM,QAAQ,GAAa,EAAE,CAAC;QAC9B,MAAM,eAAe,GAAG,IAAI,GAAG,EAAkB,CAAC;QAElD,MAAM,GAAG,GAAG,CAAC,IAAY,EAAe,EAAE,CAAC,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,SAAS,EAAE,CAAC,CAAC;QAEnF,KAAK,MAAM,GAAG,IAAI,KAAK,CAAC,OAAO,EAAE,CAAC;YAChC,IAAI,CAAC,IAAA,6BAAgB,EAAC,GAAG,CAAC;gBAAE,SAAS;YACrC,2EAA2E;YAC3E,eAAe,CAAC,GAAG,CAAC,GAAG,CAAC,aAAa,EAAE,GAAG,CAAC,IAAI,CAAC,CAAC;YACjD,QAAQ,CAAC,IAAI,CAAC;gBACZ,IAAI,EAAE,GAAG,CAAC,IAAI;gBACd,UAAU,EAAE,uCAA0B,CAAC,GAAG,CAAC,IAAI,CAAC;gBAChD,KAAK,EAAE,CAAC,QAAQ,CAAC;gBACjB,YAAY,EAAE;oBACZ,GAAG,CAAC,GAAG,GAAG,CAAC,IAAI,IAAI,GAAG,CAAC,aAAa,GAAG,MAAA,GAAG,CAAC,SAAS,mCAAI,EAAE,GAAG,GAAG,CAAC,QAAQ,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC;iBAClG;aACF,CAAC,CAAC;QACL,CAAC;QACD,IAAI,QAAQ,CAAC,MAAM,KAAK,CAAC;YAAE,OAAO,IAAI,CAAC;QAEvC,2EAA2E;QAC3E,MAAM,UAAU,GAAG,IAAI,CAAC,OAAO,CAAC,QAAQ,CAAC,CAAC;QAC1C,IAAI,WAAW,GAAG,KAAK,CAAC;QACxB,MAAM,YAAY,GAAG,GAAW,EAAE;YAChC,IAAI,CAAC,WAAW,EAAE,CAAC;gBACjB,QAAQ,CAAC,IAAI,CAAC;oBACZ,IAAI,EAAE,UAAU;oBAChB,UAAU,EAAE,QAAQ;oBACpB,KAAK,EAAE,CAAC,QAAQ,CAAC;oBACjB,YAAY,EAAE,CAAC,GAAG,CAAC,UAAU,UAAU,EAAE,CAAC,CAAC;iBAC5C,CAAC,CAAC;gBACH,WAAW,GAAG,IAAI,CAAC;YACrB,CAAC;YACD,OAAO,UAAU,CAAC;QACpB,CAAC,CAAC;QACF,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAC;QAC/B,MAAM,SAAS,GAAG,CAAC,IAAY,EAAQ,EAAE;YACvC,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC;gBACpB,QAAQ,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE,YAAY,EAAE,KAAK,EAAE,CAAC,QAAQ,CAAC,EAAE,YAAY,EAAE,EAAE,EAAE,CAAC,CAAC;gBAC7F,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;YACjB,CAAC;QACH,CAAC,CAAC;QACF,MAAM,OAAO,GAAG,CAAC,GAAW,EAAU,EAAE,WACtC,OAAA,GAAG,KAAK,0BAAa,CAAC,CAAC,CAAC,YAAY,EAAE,CAAC,CAAC,CAAC,MAAA,eAAe,CAAC,GAAG,CAAC,GAAG,CAAC,mCAAI,GAAG,CAAA,EAAA,CAAC;QAE3E,MAAM,SAAS,GAAe,EAAE,CAAC;QACjC,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAC;QAC/B,MAAM,OAAO,GAAG,CAAC,IAAY,EAAE,EAAU,EAAE,SAAiB,EAAE,EAAE;YAC9D,IAAI,CAAC,IAAI,IAAI,CAAC,EAAE,IAAI,IAAI,KAAK,EAAE;gBAAE,OAAO;YACxC,MAAM,GAAG,GAAG,GAAG,IAAI,IAAI,EAAE,IAAI,SAAS,EAAE,CAAC;YACzC,IAAI,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC;gBAAE,OAAO;YAC1B,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC;YACd,SAAS,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,EAAE,EAAE,YAAY,EAAE,CAAC,SAAS,CAAC,EAAE,CAAC,CAAC;QAC1D,CAAC,CAAC;QAEF,KAAK,MAAM,GAAG,IAAI,KAAK,CAAC,UAAU,EAAE,CAAC;YACnC,MAAM,SAAS,GAAG,wCAA2B,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;YACxD,IAAI,GAAG,CAAC,IAAI,KAAK,SAAS,EAAE,CAAC;gBAC3B,SAAS,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;gBAClB,OAAO,CAAC,YAAY,EAAE,EAAE,GAAG,CAAC,EAAE,EAAE,SAAS,CAAC,CAAC;YAC7C,CAAC;iBAAM,CAAC;gBACN,OAAO,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,EAAE,SAAS,CAAC,CAAC;YACzD,CAAC;QACH,CAAC;QAED,OAAO,EAAE,QAAQ,EAAE,SAAS,EAAE,CAAC;IACjC,CAAC;IAED,8FAA8F;IACtF,OAAO,CAAC,QAAgB;QAC9B,IAAI,CAAC,IAAI,CAAC,SAAS;YAAE,OAAO,QAAQ,CAAC;QACrC,MAAM,GAAG,GAAG,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,SAAS,EAAE,QAAQ,CAAC,CAAC;QACpD,IAAI,CAAC,GAAG,IAAI,GAAG,CAAC,UAAU,CAAC,IAAI,CAAC,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC;YAAE,OAAO,QAAQ,CAAC;QAC1E,OAAO,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;IACvC,CAAC;CACF;AAnHD,wCAmHC"}
@@ -0,0 +1,110 @@
1
+ "use strict";
2
+ var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
3
+ if (k2 === undefined) k2 = k;
4
+ var desc = Object.getOwnPropertyDescriptor(m, k);
5
+ if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
6
+ desc = { enumerable: true, get: function() { return m[k]; } };
7
+ }
8
+ Object.defineProperty(o, k2, desc);
9
+ }) : (function(o, m, k, k2) {
10
+ if (k2 === undefined) k2 = k;
11
+ o[k2] = m[k];
12
+ }));
13
+ var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
14
+ Object.defineProperty(o, "default", { enumerable: true, value: v });
15
+ }) : function(o, v) {
16
+ o["default"] = v;
17
+ });
18
+ var __importStar = (this && this.__importStar) || (function () {
19
+ var ownKeys = function(o) {
20
+ ownKeys = Object.getOwnPropertyNames || function (o) {
21
+ var ar = [];
22
+ for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
23
+ return ar;
24
+ };
25
+ return ownKeys(o);
26
+ };
27
+ return function (mod) {
28
+ if (mod && mod.__esModule) return mod;
29
+ var result = {};
30
+ if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
31
+ __setModuleDefault(result, mod);
32
+ return result;
33
+ };
34
+ })();
35
+ var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
36
+ function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
37
+ return new (P || (P = Promise))(function (resolve, reject) {
38
+ function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
39
+ function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
40
+ function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
41
+ step((generator = generator.apply(thisArg, _arguments || [])).next());
42
+ });
43
+ };
44
+ Object.defineProperty(exports, "__esModule", { value: true });
45
+ exports.AstSymbolStore = void 0;
46
+ const fs = __importStar(require("fs"));
47
+ const path = __importStar(require("path"));
48
+ const outlion_1 = require("@wanshi-kg/outlion");
49
+ /**
50
+ * Content-hash → SymbolTable cache sidecar (`<output>.ast-cache.json`) for the AST
51
+ * seed pass (Phase 8). A hit lets `AstSeedService` skip re-parsing unchanged file
52
+ * content entirely — the "re-running on an unchanged file is a no-op" gate. Modeled
53
+ * on {@link CorpusProfileStore}: a missing or garbled sidecar is non-fatal (the pass
54
+ * just re-extracts), and entries written under an older `SYMBOL_SCHEMA_VERSION` are
55
+ * dropped on load (treated as a miss) so a dependency bump can't feed stale shapes.
56
+ */
57
+ class AstSymbolStore {
58
+ constructor(path, logger) {
59
+ this.path = path;
60
+ this.logger = logger;
61
+ this.cache = new Map();
62
+ this.loaded = false;
63
+ this.dirty = false;
64
+ }
65
+ load() {
66
+ return __awaiter(this, void 0, void 0, function* () {
67
+ if (this.loaded)
68
+ return;
69
+ this.loaded = true;
70
+ if (!fs.existsSync(this.path))
71
+ return;
72
+ try {
73
+ const parsed = JSON.parse(yield fs.promises.readFile(this.path, "utf-8"));
74
+ const entries = parsed && typeof parsed === "object" ? parsed.entries : undefined;
75
+ if (entries && typeof entries === "object") {
76
+ for (const [hash, table] of Object.entries(entries)) {
77
+ const t = table;
78
+ if (t && t.schemaVersion === outlion_1.SYMBOL_SCHEMA_VERSION)
79
+ this.cache.set(hash, t);
80
+ }
81
+ }
82
+ this.logger.info(`Loaded ${this.cache.size} cached AST symbol table(s) from ${this.path}`);
83
+ }
84
+ catch (error) {
85
+ this.logger.warn(`Could not read AST cache at ${this.path} (ignored): ${error}`);
86
+ }
87
+ });
88
+ }
89
+ get(hash) {
90
+ return this.cache.get(hash);
91
+ }
92
+ set(hash, table) {
93
+ this.cache.set(hash, table);
94
+ this.dirty = true;
95
+ }
96
+ save() {
97
+ return __awaiter(this, void 0, void 0, function* () {
98
+ if (!this.dirty)
99
+ return;
100
+ const dir = path.dirname(this.path);
101
+ if (dir && !fs.existsSync(dir))
102
+ yield fs.promises.mkdir(dir, { recursive: true });
103
+ const entries = Object.fromEntries(this.cache);
104
+ yield fs.promises.writeFile(this.path, JSON.stringify({ version: outlion_1.SYMBOL_SCHEMA_VERSION, entries }));
105
+ this.dirty = false;
106
+ });
107
+ }
108
+ }
109
+ exports.AstSymbolStore = AstSymbolStore;
110
+ //# sourceMappingURL=AstSymbolStore.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"AstSymbolStore.js","sourceRoot":"","sources":["../../../../src/core/processor/ast/AstSymbolStore.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAAA,uCAAyB;AACzB,2CAA6B;AAC7B,gDAA2D;AAI3D;;;;;;;GAOG;AACH,MAAa,cAAc;IAKzB,YAA6B,IAAY,EAAmB,MAAc;QAA7C,SAAI,GAAJ,IAAI,CAAQ;QAAmB,WAAM,GAAN,MAAM,CAAQ;QAJlE,UAAK,GAAG,IAAI,GAAG,EAAuB,CAAC;QACvC,WAAM,GAAG,KAAK,CAAC;QACf,UAAK,GAAG,KAAK,CAAC;IAEuD,CAAC;IAExE,IAAI;;YACR,IAAI,IAAI,CAAC,MAAM;gBAAE,OAAO;YACxB,IAAI,CAAC,MAAM,GAAG,IAAI,CAAC;YACnB,IAAI,CAAC,EAAE,CAAC,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC;gBAAE,OAAO;YACtC,IAAI,CAAC;gBACH,MAAM,MAAM,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,QAAQ,CAAC,IAAI,CAAC,IAAI,EAAE,OAAO,CAAC,CAAC,CAAC;gBAC1E,MAAM,OAAO,GAAG,MAAM,IAAI,OAAO,MAAM,KAAK,QAAQ,CAAC,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,CAAC,SAAS,CAAC;gBAClF,IAAI,OAAO,IAAI,OAAO,OAAO,KAAK,QAAQ,EAAE,CAAC;oBAC3C,KAAK,MAAM,CAAC,IAAI,EAAE,KAAK,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,OAAO,CAAC,EAAE,CAAC;wBACpD,MAAM,CAAC,GAAG,KAAoB,CAAC;wBAC/B,IAAI,CAAC,IAAI,CAAC,CAAC,aAAa,KAAK,+BAAqB;4BAAE,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC;oBAC9E,CAAC;gBACH,CAAC;gBACD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,UAAU,IAAI,CAAC,KAAK,CAAC,IAAI,oCAAoC,IAAI,CAAC,IAAI,EAAE,CAAC,CAAC;YAC7F,CAAC;YAAC,OAAO,KAAK,EAAE,CAAC;gBACf,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,+BAA+B,IAAI,CAAC,IAAI,eAAe,KAAK,EAAE,CAAC,CAAC;YACnF,CAAC;QACH,CAAC;KAAA;IAED,GAAG,CAAC,IAAY;QACd,OAAO,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;IAC9B,CAAC;IAED,GAAG,CAAC,IAAY,EAAE,KAAkB;QAClC,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK,CAAC,CAAC;QAC5B,IAAI,CAAC,KAAK,GAAG,IAAI,CAAC;IACpB,CAAC;IAEK,IAAI;;YACR,IAAI,CAAC,IAAI,CAAC,KAAK;gBAAE,OAAO;YACxB,MAAM,GAAG,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;YACpC,IAAI,GAAG,IAAI,CAAC,EAAE,CAAC,UAAU,CAAC,GAAG,CAAC;gBAAE,MAAM,EAAE,CAAC,QAAQ,CAAC,KAAK,CAAC,GAAG,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;YAClF,MAAM,OAAO,GAAG,MAAM,CAAC,WAAW,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;YAC/C,MAAM,EAAE,CAAC,QAAQ,CAAC,SAAS,CAAC,IAAI,CAAC,IAAI,EAAE,IAAI,CAAC,SAAS,CAAC,EAAE,OAAO,EAAE,+BAAqB,EAAE,OAAO,EAAE,CAAC,CAAC,CAAC;YACpG,IAAI,CAAC,KAAK,GAAG,KAAK,CAAC;QACrB,CAAC;KAAA;CACF;AA3CD,wCA2CC"}
@@ -0,0 +1,19 @@
1
+ "use strict";
2
+ var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
3
+ if (k2 === undefined) k2 = k;
4
+ var desc = Object.getOwnPropertyDescriptor(m, k);
5
+ if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
6
+ desc = { enumerable: true, get: function() { return m[k]; } };
7
+ }
8
+ Object.defineProperty(o, k2, desc);
9
+ }) : (function(o, m, k, k2) {
10
+ if (k2 === undefined) k2 = k;
11
+ o[k2] = m[k];
12
+ }));
13
+ var __exportStar = (this && this.__exportStar) || function(m, exports) {
14
+ for (var p in m) if (p !== "default" && !Object.prototype.hasOwnProperty.call(exports, p)) __createBinding(exports, m, p);
15
+ };
16
+ Object.defineProperty(exports, "__esModule", { value: true });
17
+ __exportStar(require("./AstSeedService"), exports);
18
+ __exportStar(require("./AstSymbolStore"), exports);
19
+ //# sourceMappingURL=index.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"index.js","sourceRoot":"","sources":["../../../../src/core/processor/ast/index.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;AAAA,mDAAiC;AACjC,mDAAiC"}
@@ -0,0 +1,98 @@
1
+ "use strict";
2
+ var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
3
+ function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
4
+ return new (P || (P = Promise))(function (resolve, reject) {
5
+ function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
6
+ function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
7
+ function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
8
+ step((generator = generator.apply(thisArg, _arguments || [])).next());
9
+ });
10
+ };
11
+ Object.defineProperty(exports, "__esModule", { value: true });
12
+ exports.TextChunker = void 0;
13
+ const textsplitters_1 = require("@langchain/textsplitters");
14
+ /**
15
+ * Smart text chunking service using LangChain's RecursiveCharacterTextSplitter
16
+ * Tries to split on natural boundaries (paragraphs, sentences, etc.)
17
+ */
18
+ class TextChunker {
19
+ constructor(options, logger) {
20
+ this.options = options;
21
+ this.logger = logger;
22
+ this.defaultSeparators = [
23
+ "\n\n", // Paragraph breaks
24
+ "\n", // Line breaks
25
+ ". ", // Sentence endings
26
+ "? ", // Question endings
27
+ "! ", // Exclamation endings
28
+ "; ", // Semicolons
29
+ ", ", // Commas
30
+ " ", // Spaces
31
+ "", // Character level as last resort
32
+ ];
33
+ }
34
+ /**
35
+ * Chunk text into smaller pieces with overlap
36
+ */
37
+ chunk(text) {
38
+ return __awaiter(this, void 0, void 0, function* () {
39
+ if (!this.options.enabled || text.length <= this.options.maxChunkSize) {
40
+ return [{
41
+ content: text,
42
+ index: 1,
43
+ totalChunks: 1,
44
+ startOffset: 0,
45
+ endOffset: text.length,
46
+ }];
47
+ }
48
+ this.logger.debug(`Chunking text of length ${text.length} with max size ${this.options.maxChunkSize}`);
49
+ const splitter = new textsplitters_1.RecursiveCharacterTextSplitter({
50
+ chunkSize: this.options.maxChunkSize,
51
+ chunkOverlap: this.options.overlapSize,
52
+ separators: this.defaultSeparators,
53
+ });
54
+ const chunks = yield splitter.splitText(text);
55
+ this.logger.info(`Split text into ${chunks.length} chunks`);
56
+ return chunks.map((chunk, index) => ({
57
+ content: chunk,
58
+ index: index + 1,
59
+ totalChunks: chunks.length,
60
+ startOffset: this.calculateStartPosition(chunks, index, this.options.overlapSize),
61
+ endOffset: this.calculateEndPosition(chunks, index, this.options.overlapSize)
62
+ }));
63
+ });
64
+ }
65
+ /**
66
+ * Calculate approximate start position of chunk in original text
67
+ */
68
+ calculateStartPosition(chunks, index, overlapSize) {
69
+ if (index === 0)
70
+ return 0;
71
+ let position = 0;
72
+ for (let i = 0; i < index; i++) {
73
+ position += chunks[i].length;
74
+ if (i < index - 1) {
75
+ position -= overlapSize;
76
+ }
77
+ }
78
+ return position;
79
+ }
80
+ /**
81
+ * Calculate approximate end position of chunk in original text
82
+ */
83
+ calculateEndPosition(chunks, index, overlapSize) {
84
+ return this.calculateStartPosition(chunks, index, overlapSize) + chunks[index].length;
85
+ }
86
+ /**
87
+ * Create a custom splitter with specific separators
88
+ */
89
+ createCustomSplitter(separators, chunkSize, overlapSize) {
90
+ return new textsplitters_1.RecursiveCharacterTextSplitter({
91
+ chunkSize,
92
+ chunkOverlap: overlapSize,
93
+ separators
94
+ });
95
+ }
96
+ }
97
+ exports.TextChunker = TextChunker;
98
+ //# sourceMappingURL=TextChunker.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"TextChunker.js","sourceRoot":"","sources":["../../../../src/core/processor/chunking/TextChunker.ts"],"names":[],"mappings":";;;;;;;;;;;;AAAA,4DAA0E;AAI1E;;;GAGG;AACH,MAAa,WAAW;IAatB,YAAoB,OAAwB,EAAU,MAAc;QAAhD,YAAO,GAAP,OAAO,CAAiB;QAAU,WAAM,GAAN,MAAM,CAAQ;QAZnD,sBAAiB,GAAG;YACnC,MAAM,EAAG,mBAAmB;YAC5B,IAAI,EAAK,cAAc;YACvB,IAAI,EAAK,mBAAmB;YAC5B,IAAI,EAAK,mBAAmB;YAC5B,IAAI,EAAK,sBAAsB;YAC/B,IAAI,EAAK,aAAa;YACtB,IAAI,EAAK,SAAS;YAClB,GAAG,EAAM,SAAS;YAClB,EAAE,EAAO,iCAAiC;SAC3C,CAAC;IAEsE,CAAC;IAEzE;;OAEG;IACG,KAAK,CACT,IAAY;;YAEZ,IAAI,CAAC,IAAI,CAAC,OAAO,CAAC,OAAO,IAAI,IAAI,CAAC,MAAM,IAAI,IAAI,CAAC,OAAO,CAAC,YAAY,EAAE,CAAC;gBACtE,OAAO,CAAC;wBACN,OAAO,EAAE,IAAI;wBACb,KAAK,EAAE,CAAC;wBACR,WAAW,EAAE,CAAC;wBACd,WAAW,EAAE,CAAC;wBACd,SAAS,EAAE,IAAI,CAAC,MAAM;qBACvB,CAAC,CAAC;YACL,CAAC;YAED,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,2BAA2B,IAAI,CAAC,MAAM,kBAAkB,IAAI,CAAC,OAAO,CAAC,YAAY,EAAE,CAAC,CAAC;YAEvG,MAAM,QAAQ,GAAG,IAAI,8CAA8B,CAAC;gBAClD,SAAS,EAAE,IAAI,CAAC,OAAO,CAAC,YAAY;gBACpC,YAAY,EAAE,IAAI,CAAC,OAAO,CAAC,WAAW;gBACtC,UAAU,EAAE,IAAI,CAAC,iBAAiB;aACnC,CAAC,CAAC;YAEH,MAAM,MAAM,GAAG,MAAM,QAAQ,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC;YAE9C,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,mBAAmB,MAAM,CAAC,MAAM,SAAS,CAAC,CAAC;YAE5D,OAAO,MAAM,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,KAAK,EAAE,EAAE,CAAC,CAAC;gBACnC,OAAO,EAAE,KAAK;gBACd,KAAK,EAAE,KAAK,GAAG,CAAC;gBAChB,WAAW,EAAE,MAAM,CAAC,MAAM;gBAC1B,WAAW,EAAE,IAAI,CAAC,sBAAsB,CAAC,MAAM,EAAE,KAAK,EAAE,IAAI,CAAC,OAAO,CAAC,WAAW,CAAC;gBACjF,SAAS,EAAE,IAAI,CAAC,oBAAoB,CAAC,MAAM,EAAE,KAAK,EAAE,IAAI,CAAC,OAAO,CAAC,WAAW,CAAC;aAC9E,CAAC,CAAC,CAAC;QACN,CAAC;KAAA;IAED;;OAEG;IACK,sBAAsB,CAC5B,MAAgB,EAChB,KAAa,EACb,WAAmB;QAEnB,IAAI,KAAK,KAAK,CAAC;YAAE,OAAO,CAAC,CAAC;QAE1B,IAAI,QAAQ,GAAG,CAAC,CAAC;QACjB,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,KAAK,EAAE,CAAC,EAAE,EAAE,CAAC;YAC/B,QAAQ,IAAI,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC;YAC7B,IAAI,CAAC,GAAG,KAAK,GAAG,CAAC,EAAE,CAAC;gBAClB,QAAQ,IAAI,WAAW,CAAC;YAC1B,CAAC;QACH,CAAC;QACD,OAAO,QAAQ,CAAC;IAClB,CAAC;IAED;;OAEG;IACK,oBAAoB,CAC1B,MAAgB,EAChB,KAAa,EACb,WAAmB;QAEnB,OAAO,IAAI,CAAC,sBAAsB,CAAC,MAAM,EAAE,KAAK,EAAE,WAAW,CAAC,GAAG,MAAM,CAAC,KAAK,CAAC,CAAC,MAAM,CAAC;IACxF,CAAC;IAED;;OAEG;IACH,oBAAoB,CAClB,UAAoB,EACpB,SAAiB,EACjB,WAAmB;QAEnB,OAAO,IAAI,8CAA8B,CAAC;YACxC,SAAS;YACT,YAAY,EAAE,WAAW;YACzB,UAAU;SACX,CAAC,CAAC;IACL,CAAC;CACF;AAjGD,kCAiGC"}
@@ -0,0 +1,18 @@
1
+ "use strict";
2
+ var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
3
+ if (k2 === undefined) k2 = k;
4
+ var desc = Object.getOwnPropertyDescriptor(m, k);
5
+ if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
6
+ desc = { enumerable: true, get: function() { return m[k]; } };
7
+ }
8
+ Object.defineProperty(o, k2, desc);
9
+ }) : (function(o, m, k, k2) {
10
+ if (k2 === undefined) k2 = k;
11
+ o[k2] = m[k];
12
+ }));
13
+ var __exportStar = (this && this.__exportStar) || function(m, exports) {
14
+ for (var p in m) if (p !== "default" && !Object.prototype.hasOwnProperty.call(exports, p)) __createBinding(exports, m, p);
15
+ };
16
+ Object.defineProperty(exports, "__esModule", { value: true });
17
+ __exportStar(require("./TextChunker"), exports);
18
+ //# sourceMappingURL=index.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"index.js","sourceRoot":"","sources":["../../../../src/core/processor/chunking/index.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;AAAA,gDAA8B"}