@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 +1,198 @@
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
+ var __importDefault = (this && this.__importDefault) || function (mod) {
12
+ return (mod && mod.__esModule) ? mod : { "default": mod };
13
+ };
14
+ Object.defineProperty(exports, "__esModule", { value: true });
15
+ exports.MistralOcrReader = void 0;
16
+ const FileReader_1 = require("./FileReader");
17
+ const path_1 = __importDefault(require("path"));
18
+ const promises_1 = __importDefault(require("fs/promises"));
19
+ /**
20
+ * PDF reader backed by the Mistral OCR HTTP API. Native fetch (no SDK, no Python),
21
+ * mirroring `GrobidClient`'s injected-`fetchFn` shape so it is unit-testable.
22
+ * Claims `.pdf` only.
23
+ *
24
+ * Flow (per kcd's pipeline): upload file (purpose=ocr) → signed URL → `POST /v1/ocr`
25
+ * → `pages[].markdown` → delete the upload. Each page becomes a chunk (like
26
+ * PdfReader's per-page chunks). OCR costs money, so results cache to a
27
+ * `<pdf>.mistral.json` sidecar reused when newer than the source — re-runs never
28
+ * re-spend. Missing key / HTTP error **degrades to the injected pdf2json fallback**.
29
+ */
30
+ class MistralOcrReader extends FileReader_1.FileReader {
31
+ constructor(opts, fallback, chunker, logger, fetchFn = globalThis.fetch) {
32
+ super([".pdf"], chunker, logger);
33
+ this.opts = opts;
34
+ this.fallback = fallback;
35
+ this.fetchFn = fetchFn;
36
+ }
37
+ getName() {
38
+ return "MistralOcrReader";
39
+ }
40
+ adapterId() {
41
+ return "pdf:mistral";
42
+ }
43
+ read(filePath) {
44
+ return __awaiter(this, void 0, void 0, function* () {
45
+ yield this.validateFile(filePath);
46
+ if (!this.opts.apiKey) {
47
+ this.logger.warn(`Mistral OCR engine selected but no API key (set readers.mistral.apiKey or $MISTRAL_API_KEY); falling back to pdf2json for ${filePath}`);
48
+ return this.fallback.read(filePath);
49
+ }
50
+ try {
51
+ const startTime = Date.now();
52
+ const { pages, cached } = yield this.ocr(filePath);
53
+ const usable = pages.filter((p) => p.markdown.trim());
54
+ if (usable.length === 0)
55
+ throw new Error("Mistral OCR returned no page text");
56
+ const chunks = [];
57
+ let offset = 0;
58
+ usable.forEach((p, i) => {
59
+ const content = p.markdown;
60
+ chunks.push({
61
+ content, index: i + 1, totalChunks: usable.length,
62
+ startOffset: offset, endOffset: offset + content.length,
63
+ provenance: { locator: `p.${p.index + 1}` }, // 1-based page number (ECS locator)
64
+ });
65
+ offset += content.length;
66
+ });
67
+ const stats = yield promises_1.default.stat(filePath);
68
+ return {
69
+ chunks,
70
+ metadata: {
71
+ type: "pdf",
72
+ fileName: filePath,
73
+ fileSize: stats.size,
74
+ pdfEngine: "mistral",
75
+ mistralModel: this.opts.model,
76
+ mistralCached: cached,
77
+ pageCount: usable.length,
78
+ processingTimeMs: Date.now() - startTime,
79
+ status: "success",
80
+ },
81
+ };
82
+ }
83
+ catch (error) {
84
+ this.logger.warn(`Mistral OCR engine failed for ${filePath} (${error.message}); falling back to pdf2json`);
85
+ return this.fallback.read(filePath);
86
+ }
87
+ });
88
+ }
89
+ /** OCR the PDF (or reuse the sidecar). Throws on any API failure. */
90
+ ocr(filePath) {
91
+ return __awaiter(this, void 0, void 0, function* () {
92
+ const sidecar = `${filePath}.mistral.json`;
93
+ if (yield this.sidecarIsFresh(sidecar, filePath)) {
94
+ this.logger.debug(`Reusing Mistral OCR sidecar: ${sidecar}`);
95
+ return { pages: JSON.parse(yield promises_1.default.readFile(sidecar, "utf-8")), cached: true };
96
+ }
97
+ const buf = yield promises_1.default.readFile(filePath);
98
+ const fileId = yield this.uploadFile(buf, path_1.default.basename(filePath));
99
+ try {
100
+ const url = yield this.signedUrl(fileId);
101
+ const pages = yield this.processOcr(url);
102
+ yield promises_1.default.writeFile(sidecar, JSON.stringify(pages), "utf-8");
103
+ return { pages, cached: false };
104
+ }
105
+ finally {
106
+ // Best-effort cleanup of the uploaded file (don't fail the read on this).
107
+ yield this.deleteFile(fileId).catch((e) => this.logger.debug(`Mistral file delete failed for ${fileId}: ${e}`));
108
+ }
109
+ });
110
+ }
111
+ uploadFile(buf, fileName) {
112
+ return __awaiter(this, void 0, void 0, function* () {
113
+ var _a;
114
+ const form = new FormData();
115
+ form.append("purpose", "ocr");
116
+ form.append("file", new Blob([buf]), fileName || "doc.pdf");
117
+ const res = yield this.fetchFn(`${this.opts.host}/v1/files`, {
118
+ method: "POST",
119
+ headers: { Authorization: `Bearer ${this.opts.apiKey}` },
120
+ body: form,
121
+ signal: this.timeout(),
122
+ });
123
+ if (!res.ok)
124
+ throw new Error(`Mistral files.upload ${res.status}`);
125
+ const id = (_a = (yield res.json())) === null || _a === void 0 ? void 0 : _a.id;
126
+ if (!id)
127
+ throw new Error("Mistral files.upload returned no id");
128
+ return id;
129
+ });
130
+ }
131
+ signedUrl(fileId) {
132
+ return __awaiter(this, void 0, void 0, function* () {
133
+ var _a;
134
+ const res = yield this.fetchFn(`${this.opts.host}/v1/files/${fileId}/url?expiry=24`, {
135
+ method: "GET",
136
+ headers: { Authorization: `Bearer ${this.opts.apiKey}`, Accept: "application/json" },
137
+ signal: this.timeout(),
138
+ });
139
+ if (!res.ok)
140
+ throw new Error(`Mistral files.get_signed_url ${res.status}`);
141
+ const url = (_a = (yield res.json())) === null || _a === void 0 ? void 0 : _a.url;
142
+ if (!url)
143
+ throw new Error("Mistral signed-url response had no url");
144
+ return url;
145
+ });
146
+ }
147
+ processOcr(documentUrl) {
148
+ return __awaiter(this, void 0, void 0, function* () {
149
+ const res = yield this.fetchFn(`${this.opts.host}/v1/ocr`, {
150
+ method: "POST",
151
+ headers: { Authorization: `Bearer ${this.opts.apiKey}`, "Content-Type": "application/json" },
152
+ body: JSON.stringify({
153
+ model: this.opts.model,
154
+ document: { type: "document_url", document_url: documentUrl },
155
+ include_image_base64: false,
156
+ }),
157
+ signal: this.timeout(),
158
+ });
159
+ if (!res.ok)
160
+ throw new Error(`Mistral ocr.process ${res.status}`);
161
+ const json = yield res.json();
162
+ const pages = Array.isArray(json === null || json === void 0 ? void 0 : json.pages) ? json.pages : [];
163
+ return pages.map((p, i) => ({
164
+ index: typeof p.index === "number" ? p.index : i,
165
+ markdown: typeof p.markdown === "string" ? p.markdown : "",
166
+ }));
167
+ });
168
+ }
169
+ deleteFile(fileId) {
170
+ return __awaiter(this, void 0, void 0, function* () {
171
+ const res = yield this.fetchFn(`${this.opts.host}/v1/files/${fileId}`, {
172
+ method: "DELETE",
173
+ headers: { Authorization: `Bearer ${this.opts.apiKey}` },
174
+ signal: this.timeout(),
175
+ });
176
+ if (!res.ok)
177
+ throw new Error(`Mistral files.delete ${res.status}`);
178
+ });
179
+ }
180
+ timeout() {
181
+ return typeof AbortSignal.timeout === "function"
182
+ ? AbortSignal.timeout(this.opts.timeoutMs)
183
+ : undefined;
184
+ }
185
+ sidecarIsFresh(sidecar, filePath) {
186
+ return __awaiter(this, void 0, void 0, function* () {
187
+ try {
188
+ const [s, a] = yield Promise.all([promises_1.default.stat(sidecar), promises_1.default.stat(filePath)]);
189
+ return s.mtimeMs >= a.mtimeMs;
190
+ }
191
+ catch (_a) {
192
+ return false;
193
+ }
194
+ });
195
+ }
196
+ }
197
+ exports.MistralOcrReader = MistralOcrReader;
198
+ //# sourceMappingURL=MistralOcrReader.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"MistralOcrReader.js","sourceRoot":"","sources":["../../../../src/core/processor/readers/MistralOcrReader.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;AAAA,6CAAuE;AACvE,gDAAwB;AACxB,2DAA6B;AAoB7B;;;;;;;;;;GAUG;AACH,MAAa,gBAAiB,SAAQ,uBAAU;IAC9C,YACmB,IAAoB,EACpB,QAAoB,EACrC,OAAoB,EACpB,MAAc,EACG,UAAoB,UAAkB,CAAC,KAAK;QAE7D,KAAK,CAAC,CAAC,MAAM,CAAC,EAAE,OAAO,EAAE,MAAM,CAAC,CAAC;QANhB,SAAI,GAAJ,IAAI,CAAgB;QACpB,aAAQ,GAAR,QAAQ,CAAY;QAGpB,YAAO,GAAP,OAAO,CAAqC;IAG/D,CAAC;IAED,OAAO;QACL,OAAO,kBAAkB,CAAC;IAC5B,CAAC;IAED,SAAS;QACP,OAAO,aAAa,CAAC;IACvB,CAAC;IAEK,IAAI,CAAC,QAAgB;;YACzB,MAAM,IAAI,CAAC,YAAY,CAAC,QAAQ,CAAC,CAAC;YAElC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,CAAC;gBACtB,IAAI,CAAC,MAAM,CAAC,IAAI,CACd,6HAA6H,QAAQ,EAAE,CACxI,CAAC;gBACF,OAAO,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;YACtC,CAAC;YAED,IAAI,CAAC;gBACH,MAAM,SAAS,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC;gBAC7B,MAAM,EAAE,KAAK,EAAE,MAAM,EAAE,GAAG,MAAM,IAAI,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAC;gBACnD,MAAM,MAAM,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAC,CAAC;gBACtD,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC;oBAAE,MAAM,IAAI,KAAK,CAAC,mCAAmC,CAAC,CAAC;gBAE9E,MAAM,MAAM,GAAkB,EAAE,CAAC;gBACjC,IAAI,MAAM,GAAG,CAAC,CAAC;gBACf,MAAM,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE;oBACtB,MAAM,OAAO,GAAG,CAAC,CAAC,QAAQ,CAAC;oBAC3B,MAAM,CAAC,IAAI,CAAC;wBACV,OAAO,EAAE,KAAK,EAAE,CAAC,GAAG,CAAC,EAAE,WAAW,EAAE,MAAM,CAAC,MAAM;wBACjD,WAAW,EAAE,MAAM,EAAE,SAAS,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM;wBACvD,UAAU,EAAE,EAAE,OAAO,EAAE,KAAK,CAAC,CAAC,KAAK,GAAG,CAAC,EAAE,EAAE,EAAE,oCAAoC;qBAClF,CAAC,CAAC;oBACH,MAAM,IAAI,OAAO,CAAC,MAAM,CAAC;gBAC3B,CAAC,CAAC,CAAC;gBAEH,MAAM,KAAK,GAAG,MAAM,kBAAE,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;gBACtC,OAAO;oBACL,MAAM;oBACN,QAAQ,EAAE;wBACR,IAAI,EAAE,KAAK;wBACX,QAAQ,EAAE,QAAQ;wBAClB,QAAQ,EAAE,KAAK,CAAC,IAAI;wBACpB,SAAS,EAAE,SAAS;wBACpB,YAAY,EAAE,IAAI,CAAC,IAAI,CAAC,KAAK;wBAC7B,aAAa,EAAE,MAAM;wBACrB,SAAS,EAAE,MAAM,CAAC,MAAM;wBACxB,gBAAgB,EAAE,IAAI,CAAC,GAAG,EAAE,GAAG,SAAS;wBACxC,MAAM,EAAE,SAAS;qBAClB;iBACF,CAAC;YACJ,CAAC;YAAC,OAAO,KAAU,EAAE,CAAC;gBACpB,IAAI,CAAC,MAAM,CAAC,IAAI,CACd,iCAAiC,QAAQ,KAAK,KAAK,CAAC,OAAO,6BAA6B,CACzF,CAAC;gBACF,OAAO,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;YACtC,CAAC;QACH,CAAC;KAAA;IAED,qEAAqE;IACvD,GAAG,CAAC,QAAgB;;YAChC,MAAM,OAAO,GAAG,GAAG,QAAQ,eAAe,CAAC;YAC3C,IAAI,MAAM,IAAI,CAAC,cAAc,CAAC,OAAO,EAAE,QAAQ,CAAC,EAAE,CAAC;gBACjD,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,gCAAgC,OAAO,EAAE,CAAC,CAAC;gBAC7D,OAAO,EAAE,KAAK,EAAE,IAAI,CAAC,KAAK,CAAC,MAAM,kBAAE,CAAC,QAAQ,CAAC,OAAO,EAAE,OAAO,CAAC,CAAc,EAAE,MAAM,EAAE,IAAI,EAAE,CAAC;YAC/F,CAAC;YAED,MAAM,GAAG,GAAG,MAAM,kBAAE,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC;YACxC,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,UAAU,CAAC,GAAG,EAAE,cAAI,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC,CAAC;YACnE,IAAI,CAAC;gBACH,MAAM,GAAG,GAAG,MAAM,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,CAAC;gBACzC,MAAM,KAAK,GAAG,MAAM,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,CAAC;gBACzC,MAAM,kBAAE,CAAC,SAAS,CAAC,OAAO,EAAE,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,EAAE,OAAO,CAAC,CAAC;gBAC5D,OAAO,EAAE,KAAK,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC;YAClC,CAAC;oBAAS,CAAC;gBACT,0EAA0E;gBAC1E,MAAM,IAAI,CAAC,UAAU,CAAC,MAAM,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,EAAE,CACxC,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,kCAAkC,MAAM,KAAK,CAAC,EAAE,CAAC,CACpE,CAAC;YACJ,CAAC;QACH,CAAC;KAAA;IAEa,UAAU,CAAC,GAAW,EAAE,QAAgB;;;YACpD,MAAM,IAAI,GAAG,IAAI,QAAQ,EAAE,CAAC;YAC5B,IAAI,CAAC,MAAM,CAAC,SAAS,EAAE,KAAK,CAAC,CAAC;YAC9B,IAAI,CAAC,MAAM,CAAC,MAAM,EAAE,IAAI,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,QAAQ,IAAI,SAAS,CAAC,CAAC;YAC5D,MAAM,GAAG,GAAG,MAAM,IAAI,CAAC,OAAO,CAAC,GAAG,IAAI,CAAC,IAAI,CAAC,IAAI,WAAW,EAAE;gBAC3D,MAAM,EAAE,MAAM;gBACd,OAAO,EAAE,EAAE,aAAa,EAAE,UAAU,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,EAAE;gBACxD,IAAI,EAAE,IAAI;gBACV,MAAM,EAAE,IAAI,CAAC,OAAO,EAAE;aACvB,CAAC,CAAC;YACH,IAAI,CAAC,GAAG,CAAC,EAAE;gBAAE,MAAM,IAAI,KAAK,CAAC,wBAAwB,GAAG,CAAC,MAAM,EAAE,CAAC,CAAC;YACnE,MAAM,EAAE,GAAG,MAAA,CAAC,MAAM,GAAG,CAAC,IAAI,EAAE,CAAC,0CAAE,EAAE,CAAC;YAClC,IAAI,CAAC,EAAE;gBAAE,MAAM,IAAI,KAAK,CAAC,qCAAqC,CAAC,CAAC;YAChE,OAAO,EAAE,CAAC;QACZ,CAAC;KAAA;IAEa,SAAS,CAAC,MAAc;;;YACpC,MAAM,GAAG,GAAG,MAAM,IAAI,CAAC,OAAO,CAAC,GAAG,IAAI,CAAC,IAAI,CAAC,IAAI,aAAa,MAAM,gBAAgB,EAAE;gBACnF,MAAM,EAAE,KAAK;gBACb,OAAO,EAAE,EAAE,aAAa,EAAE,UAAU,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,kBAAkB,EAAE;gBACpF,MAAM,EAAE,IAAI,CAAC,OAAO,EAAE;aACvB,CAAC,CAAC;YACH,IAAI,CAAC,GAAG,CAAC,EAAE;gBAAE,MAAM,IAAI,KAAK,CAAC,gCAAgC,GAAG,CAAC,MAAM,EAAE,CAAC,CAAC;YAC3E,MAAM,GAAG,GAAG,MAAA,CAAC,MAAM,GAAG,CAAC,IAAI,EAAE,CAAC,0CAAE,GAAG,CAAC;YACpC,IAAI,CAAC,GAAG;gBAAE,MAAM,IAAI,KAAK,CAAC,wCAAwC,CAAC,CAAC;YACpE,OAAO,GAAG,CAAC;QACb,CAAC;KAAA;IAEa,UAAU,CAAC,WAAmB;;YAC1C,MAAM,GAAG,GAAG,MAAM,IAAI,CAAC,OAAO,CAAC,GAAG,IAAI,CAAC,IAAI,CAAC,IAAI,SAAS,EAAE;gBACzD,MAAM,EAAE,MAAM;gBACd,OAAO,EAAE,EAAE,aAAa,EAAE,UAAU,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,EAAE,cAAc,EAAE,kBAAkB,EAAE;gBAC5F,IAAI,EAAE,IAAI,CAAC,SAAS,CAAC;oBACnB,KAAK,EAAE,IAAI,CAAC,IAAI,CAAC,KAAK;oBACtB,QAAQ,EAAE,EAAE,IAAI,EAAE,cAAc,EAAE,YAAY,EAAE,WAAW,EAAE;oBAC7D,oBAAoB,EAAE,KAAK;iBAC5B,CAAC;gBACF,MAAM,EAAE,IAAI,CAAC,OAAO,EAAE;aACvB,CAAC,CAAC;YACH,IAAI,CAAC,GAAG,CAAC,EAAE;gBAAE,MAAM,IAAI,KAAK,CAAC,uBAAuB,GAAG,CAAC,MAAM,EAAE,CAAC,CAAC;YAClE,MAAM,IAAI,GAAQ,MAAM,GAAG,CAAC,IAAI,EAAE,CAAC;YACnC,MAAM,KAAK,GAAU,KAAK,CAAC,OAAO,CAAC,IAAI,aAAJ,IAAI,uBAAJ,IAAI,CAAE,KAAK,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC;YAClE,OAAO,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC;gBAC1B,KAAK,EAAE,OAAO,CAAC,CAAC,KAAK,KAAK,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;gBAChD,QAAQ,EAAE,OAAO,CAAC,CAAC,QAAQ,KAAK,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE;aAC3D,CAAC,CAAC,CAAC;QACN,CAAC;KAAA;IAEa,UAAU,CAAC,MAAc;;YACrC,MAAM,GAAG,GAAG,MAAM,IAAI,CAAC,OAAO,CAAC,GAAG,IAAI,CAAC,IAAI,CAAC,IAAI,aAAa,MAAM,EAAE,EAAE;gBACrE,MAAM,EAAE,QAAQ;gBAChB,OAAO,EAAE,EAAE,aAAa,EAAE,UAAU,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,EAAE;gBACxD,MAAM,EAAE,IAAI,CAAC,OAAO,EAAE;aACvB,CAAC,CAAC;YACH,IAAI,CAAC,GAAG,CAAC,EAAE;gBAAE,MAAM,IAAI,KAAK,CAAC,wBAAwB,GAAG,CAAC,MAAM,EAAE,CAAC,CAAC;QACrE,CAAC;KAAA;IAEO,OAAO;QACb,OAAO,OAAQ,WAAmB,CAAC,OAAO,KAAK,UAAU;YACvD,CAAC,CAAE,WAAmB,CAAC,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,CAAC;YACnD,CAAC,CAAC,SAAS,CAAC;IAChB,CAAC;IAEa,cAAc,CAAC,OAAe,EAAE,QAAgB;;YAC5D,IAAI,CAAC;gBACH,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,GAAG,MAAM,OAAO,CAAC,GAAG,CAAC,CAAC,kBAAE,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE,kBAAE,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC;gBACxE,OAAO,CAAC,CAAC,OAAO,IAAI,CAAC,CAAC,OAAO,CAAC;YAChC,CAAC;YAAC,WAAM,CAAC;gBACP,OAAO,KAAK,CAAC;YACf,CAAC;QACH,CAAC;KAAA;CACF;AApKD,4CAoKC"}
@@ -0,0 +1,174 @@
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
+ var __importDefault = (this && this.__importDefault) || function (mod) {
45
+ return (mod && mod.__esModule) ? mod : { "default": mod };
46
+ };
47
+ Object.defineProperty(exports, "__esModule", { value: true });
48
+ exports.OfficeReader = void 0;
49
+ const FileReader_1 = require("./FileReader");
50
+ const path_1 = __importDefault(require("path"));
51
+ const officeParser = __importStar(require("officeparser"));
52
+ const promises_1 = __importDefault(require("fs/promises"));
53
+ /**
54
+ * Reader for Microsoft Office documents using officeparser
55
+ *
56
+ * Supported formats: .docx, .pptx, .xlsx, .odt, .odp, .ods
57
+ *
58
+ * NOTE: This implementation only extracts text content.
59
+ * Images and rich metadata are not supported by the underlying officeparser library.
60
+ *
61
+ * npm install officeparser
62
+ */
63
+ class OfficeReader extends FileReader_1.FileReader {
64
+ constructor(chunker, logger) {
65
+ super([".docx", ".pptx", ".xlsx", ".odt", ".odp", ".ods"], chunker, logger);
66
+ }
67
+ getName() {
68
+ return "OfficeReader";
69
+ }
70
+ read(filePath) {
71
+ return __awaiter(this, void 0, void 0, function* () {
72
+ yield this.validateFile(filePath);
73
+ try {
74
+ this.logger.debug(`Reading Office file: ${filePath}`);
75
+ // Get file stats for basic metadata
76
+ const stats = yield promises_1.default.stat(filePath);
77
+ const ext = path_1.default.extname(filePath).toLowerCase();
78
+ // Configure officeparser
79
+ const config = {
80
+ newlineDelimiter: "\n",
81
+ ignoreNotes: false, // Include notes in parsed text
82
+ outputErrorToConsole: false,
83
+ };
84
+ // Extract text content using officeparser
85
+ const content = yield officeParser.parseOfficeAsync(filePath, config);
86
+ // Build metadata object
87
+ const metadata = {
88
+ type: this.getDocumentType(ext),
89
+ description: this.matchExtensionToDescription(ext),
90
+ fileName: path_1.default.basename(filePath),
91
+ filePath: filePath,
92
+ fileSize: stats.size,
93
+ createdAt: stats.birthtime.toISOString(),
94
+ modifiedAt: stats.mtime.toISOString(),
95
+ accessedAt: stats.atime.toISOString(),
96
+ extension: ext,
97
+ status: "success",
98
+ // Note: officeparser doesn't provide document metadata like author, title, etc.
99
+ // These would need to be extracted using format-specific libraries
100
+ extractedTextLength: content.length,
101
+ hasContent: content.trim().length > 0,
102
+ };
103
+ this.logger.debug(`Successfully extracted ${content.length} characters from ${filePath}`);
104
+ return {
105
+ chunks: [
106
+ {
107
+ content: content,
108
+ startOffset: 0,
109
+ endOffset: content.length,
110
+ index: 1,
111
+ totalChunks: 1,
112
+ },
113
+ ],
114
+ // images: undefined, // officeparser doesn't extract images
115
+ metadata: metadata,
116
+ };
117
+ }
118
+ catch (error) {
119
+ this.logger.error(`Failed to read Office file ${filePath}: ${error.message}`);
120
+ // Return error result instead of throwing
121
+ return {
122
+ chunks: [
123
+ {
124
+ content: "",
125
+ startOffset: 0,
126
+ endOffset: 0,
127
+ index: 1,
128
+ totalChunks: 1,
129
+ },
130
+ ],
131
+ metadata: {
132
+ type: this.getDocumentType(path_1.default.extname(filePath).toLowerCase()),
133
+ description: this.matchExtensionToDescription(path_1.default.extname(filePath)),
134
+ fileName: path_1.default.basename(filePath),
135
+ filePath: filePath,
136
+ status: "error",
137
+ error: error.message,
138
+ errorType: error.name,
139
+ },
140
+ };
141
+ }
142
+ });
143
+ }
144
+ getDocumentType(ext) {
145
+ const types = {
146
+ ".docx": "word_document",
147
+ ".doc": "word_document_legacy",
148
+ ".pptx": "powerpoint_presentation",
149
+ ".ppt": "powerpoint_presentation_legacy",
150
+ ".xlsx": "excel_spreadsheet",
151
+ ".xls": "excel_spreadsheet_legacy",
152
+ ".odt": "openoffice_text",
153
+ ".odp": "openoffice_presentation",
154
+ ".ods": "openoffice_spreadsheet",
155
+ };
156
+ return types[ext] || "unknown_office_document";
157
+ }
158
+ matchExtensionToDescription(ext) {
159
+ const descriptions = {
160
+ ".docx": "Microsoft Word Document",
161
+ ".doc": "Microsoft Word 2003 Document",
162
+ ".pptx": "Microsoft PowerPoint Presentation",
163
+ ".ppt": "Microsoft PowerPoint 2003 Presentation",
164
+ ".xlsx": "Microsoft Excel Spreadsheet",
165
+ ".xls": "Microsoft Excel 2003 Spreadsheet",
166
+ ".odt": "OpenDocument Text Document",
167
+ ".odp": "OpenDocument Presentation",
168
+ ".ods": "OpenDocument Spreadsheet",
169
+ };
170
+ return descriptions[ext] || "Unknown Office Document";
171
+ }
172
+ }
173
+ exports.OfficeReader = OfficeReader;
174
+ //# sourceMappingURL=OfficeReader.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"OfficeReader.js","sourceRoot":"","sources":["../../../../src/core/processor/readers/OfficeReader.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAAA,6CAA0D;AAC1D,gDAAwB;AACxB,2DAA6C;AAC7C,2DAA6B;AAI7B;;;;;;;;;GASG;AACH,MAAa,YAAa,SAAQ,uBAAU;IAC1C,YAAY,OAAoB,EAAE,MAAc;QAC9C,KAAK,CAAC,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,CAAC,EAAE,OAAO,EAAE,MAAM,CAAC,CAAC;IAC9E,CAAC;IAED,OAAO;QACL,OAAO,cAAc,CAAC;IACxB,CAAC;IAEK,IAAI,CAAC,QAAgB;;YACzB,MAAM,IAAI,CAAC,YAAY,CAAC,QAAQ,CAAC,CAAC;YAElC,IAAI,CAAC;gBACH,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,wBAAwB,QAAQ,EAAE,CAAC,CAAC;gBAEtD,oCAAoC;gBACpC,MAAM,KAAK,GAAG,MAAM,kBAAE,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;gBACtC,MAAM,GAAG,GAAG,cAAI,CAAC,OAAO,CAAC,QAAQ,CAAC,CAAC,WAAW,EAAE,CAAC;gBAEjD,yBAAyB;gBACzB,MAAM,MAAM,GAAG;oBACb,gBAAgB,EAAE,IAAI;oBACtB,WAAW,EAAE,KAAK,EAAE,+BAA+B;oBACnD,oBAAoB,EAAE,KAAK;iBAC5B,CAAC;gBAEF,0CAA0C;gBAC1C,MAAM,OAAO,GAAG,MAAM,YAAY,CAAC,gBAAgB,CAAC,QAAQ,EAAE,MAAM,CAAC,CAAC;gBAEtE,wBAAwB;gBACxB,MAAM,QAAQ,GAAG;oBACf,IAAI,EAAE,IAAI,CAAC,eAAe,CAAC,GAAG,CAAC;oBAC/B,WAAW,EAAE,IAAI,CAAC,2BAA2B,CAAC,GAAG,CAAC;oBAClD,QAAQ,EAAE,cAAI,CAAC,QAAQ,CAAC,QAAQ,CAAC;oBACjC,QAAQ,EAAE,QAAQ;oBAClB,QAAQ,EAAE,KAAK,CAAC,IAAI;oBACpB,SAAS,EAAE,KAAK,CAAC,SAAS,CAAC,WAAW,EAAE;oBACxC,UAAU,EAAE,KAAK,CAAC,KAAK,CAAC,WAAW,EAAE;oBACrC,UAAU,EAAE,KAAK,CAAC,KAAK,CAAC,WAAW,EAAE;oBACrC,SAAS,EAAE,GAAG;oBACd,MAAM,EAAE,SAAS;oBACjB,gFAAgF;oBAChF,mEAAmE;oBACnE,mBAAmB,EAAE,OAAO,CAAC,MAAM;oBACnC,UAAU,EAAE,OAAO,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC;iBACtC,CAAC;gBAEF,IAAI,CAAC,MAAM,CAAC,KAAK,CACf,0BAA0B,OAAO,CAAC,MAAM,oBAAoB,QAAQ,EAAE,CACvE,CAAC;gBAEF,OAAO;oBACL,MAAM,EAAE;wBACN;4BACE,OAAO,EAAE,OAAO;4BAChB,WAAW,EAAE,CAAC;4BACd,SAAS,EAAE,OAAO,CAAC,MAAM;4BACzB,KAAK,EAAE,CAAC;4BACR,WAAW,EAAE,CAAC;yBACf;qBACF;oBACD,4DAA4D;oBAC5D,QAAQ,EAAE,QAAQ;iBACnB,CAAC;YACJ,CAAC;YAAC,OAAO,KAAU,EAAE,CAAC;gBACpB,IAAI,CAAC,MAAM,CAAC,KAAK,CACf,8BAA8B,QAAQ,KAAK,KAAK,CAAC,OAAO,EAAE,CAC3D,CAAC;gBAEF,0CAA0C;gBAC1C,OAAO;oBACL,MAAM,EAAE;wBACN;4BACE,OAAO,EAAE,EAAE;4BACX,WAAW,EAAE,CAAC;4BACd,SAAS,EAAE,CAAC;4BACZ,KAAK,EAAE,CAAC;4BACR,WAAW,EAAE,CAAC;yBACf;qBACF;oBACD,QAAQ,EAAE;wBACR,IAAI,EAAE,IAAI,CAAC,eAAe,CAAC,cAAI,CAAC,OAAO,CAAC,QAAQ,CAAC,CAAC,WAAW,EAAE,CAAC;wBAChE,WAAW,EAAE,IAAI,CAAC,2BAA2B,CAAC,cAAI,CAAC,OAAO,CAAC,QAAQ,CAAC,CAAC;wBACrE,QAAQ,EAAE,cAAI,CAAC,QAAQ,CAAC,QAAQ,CAAC;wBACjC,QAAQ,EAAE,QAAQ;wBAClB,MAAM,EAAE,OAAO;wBACf,KAAK,EAAE,KAAK,CAAC,OAAO;wBACpB,SAAS,EAAE,KAAK,CAAC,IAAI;qBACtB;iBACF,CAAC;YACJ,CAAC;QACH,CAAC;KAAA;IAEO,eAAe,CAAC,GAAW;QACjC,MAAM,KAAK,GAA8B;YACvC,OAAO,EAAE,eAAe;YACxB,MAAM,EAAE,sBAAsB;YAC9B,OAAO,EAAE,yBAAyB;YAClC,MAAM,EAAE,gCAAgC;YACxC,OAAO,EAAE,mBAAmB;YAC5B,MAAM,EAAE,0BAA0B;YAClC,MAAM,EAAE,iBAAiB;YACzB,MAAM,EAAE,yBAAyB;YACjC,MAAM,EAAE,wBAAwB;SACjC,CAAC;QACF,OAAO,KAAK,CAAC,GAAG,CAAC,IAAI,yBAAyB,CAAC;IACjD,CAAC;IAEO,2BAA2B,CAAC,GAAW;QAC7C,MAAM,YAAY,GAA8B;YAC9C,OAAO,EAAE,yBAAyB;YAClC,MAAM,EAAE,8BAA8B;YACtC,OAAO,EAAE,mCAAmC;YAC5C,MAAM,EAAE,wCAAwC;YAChD,OAAO,EAAE,6BAA6B;YACtC,MAAM,EAAE,kCAAkC;YAC1C,MAAM,EAAE,4BAA4B;YACpC,MAAM,EAAE,2BAA2B;YACnC,MAAM,EAAE,0BAA0B;SACnC,CAAC;QACF,OAAO,YAAY,CAAC,GAAG,CAAC,IAAI,yBAAyB,CAAC;IACxD,CAAC;CACF;AA1HD,oCA0HC"}
@@ -0,0 +1,116 @@
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
+ var __importDefault = (this && this.__importDefault) || function (mod) {
12
+ return (mod && mod.__esModule) ? mod : { "default": mod };
13
+ };
14
+ Object.defineProperty(exports, "__esModule", { value: true });
15
+ exports.PdfReader = void 0;
16
+ exports.extractArxivId = extractArxivId;
17
+ const FileReader_1 = require("./FileReader");
18
+ const stripReferences_1 = require("./stripReferences");
19
+ const referenceExtraction_1 = require("./referenceExtraction");
20
+ const pdf2json_1 = __importDefault(require("pdf2json"));
21
+ /**
22
+ * Extract an arXiv identifier from page text (the sidebar/footer stamp on
23
+ * arXiv-hosted PDFs). Pure — exported for tests.
24
+ */
25
+ function extractArxivId(text) {
26
+ const m = text.match(/arXiv:\s*(\d{4}\.\d{4,5}(?:v\d+)?)/i);
27
+ return m ? m[1] : undefined;
28
+ }
29
+ /**
30
+ * Reader for PDF files
31
+ */
32
+ class PdfReader extends FileReader_1.FileReader {
33
+ constructor(chunker, logger, stripReferences = false, extractCites = false) {
34
+ super([".pdf"], chunker, logger);
35
+ this.stripReferences = stripReferences;
36
+ this.extractCites = extractCites;
37
+ }
38
+ getName() {
39
+ return "PdfReader";
40
+ }
41
+ adapterId() {
42
+ return "pdf:pdf2json";
43
+ }
44
+ read(filePath) {
45
+ return __awaiter(this, void 0, void 0, function* () {
46
+ yield this.validateFile(filePath);
47
+ try {
48
+ this.logger.debug(`Reading PDF file: ${filePath}`);
49
+ let { pages: content, title } = yield this.readPdfPages(filePath);
50
+ // Document identity is captured here, at ingest time — never extracted
51
+ // from body text, which is full of OTHER papers' arXiv IDs (citations).
52
+ const arxivId = extractArxivId(content.slice(0, 2).join("\n"));
53
+ // Detect the trailing bibliography once if either consumer needs it.
54
+ const split = this.stripReferences || this.extractCites
55
+ ? (0, stripReferences_1.splitPagesAtReferences)(content)
56
+ : undefined;
57
+ // Phase 0 citation extraction (network-free), gated by config. Drop the
58
+ // paper's OWN arXiv id (the host identity, not a citation).
59
+ let references;
60
+ if (this.extractCites) {
61
+ const cites = (0, referenceExtraction_1.extractCitations)(split === null || split === void 0 ? void 0 : split.references, content.join("\n")).filter((c) => !arxivId || c.arxivId !== arxivId);
62
+ if (cites.length)
63
+ references = { citations: cites };
64
+ }
65
+ if (this.stripReferences && (split === null || split === void 0 ? void 0 : split.references)) {
66
+ this.logger.info(`Quarantined trailing references section of ${filePath} ` +
67
+ `(${split.references.length} chars, ${content.length - split.pages.length} page(s) dropped)`);
68
+ content = split.pages;
69
+ }
70
+ const chunks = content.map((page, index) => {
71
+ const startOffset = content.slice(0, index).reduce((acc, curr) => acc + curr.length, 0);
72
+ return {
73
+ content: page,
74
+ startOffset: startOffset,
75
+ endOffset: startOffset + page.length,
76
+ index: index + 1,
77
+ totalChunks: content.length,
78
+ provenance: { locator: `p.${index + 1}` }, // 1-based page number (ECS locator)
79
+ };
80
+ });
81
+ return {
82
+ chunks: chunks,
83
+ metadata: Object.assign(Object.assign(Object.assign({ type: "pdf", fileName: filePath }, (arxivId ? { arxivId } : {})), (title ? { title } : {})), (references ? { references } : {})),
84
+ };
85
+ }
86
+ catch (error) {
87
+ this.logger.error(`Failed to read PDF file ${filePath}: ${error}`);
88
+ throw new Error(`Failed to read PDF file: ${error}`);
89
+ }
90
+ });
91
+ }
92
+ readPdfPages(filePath) {
93
+ return new Promise((resolve, reject) => {
94
+ const pdfParser = new pdf2json_1.default();
95
+ pdfParser.on("pdfParser_dataError", (errData) => reject(errData.parserError));
96
+ pdfParser.on("pdfParser_dataReady", (pdfData) => {
97
+ var _a;
98
+ const pages = pdfData.Pages.map((page) => page.Texts.map((t) => t.R.map((r) => decodeURIComponent(r.T)).join("")).join("\n"));
99
+ const rawTitle = (_a = pdfData.Meta) === null || _a === void 0 ? void 0 : _a.Title;
100
+ let title;
101
+ if (typeof rawTitle === "string" && rawTitle.trim()) {
102
+ try {
103
+ title = decodeURIComponent(rawTitle).trim();
104
+ }
105
+ catch (_b) {
106
+ title = rawTitle.trim();
107
+ }
108
+ }
109
+ resolve({ pages, title });
110
+ });
111
+ pdfParser.loadPDF(filePath);
112
+ });
113
+ }
114
+ }
115
+ exports.PdfReader = PdfReader;
116
+ //# sourceMappingURL=PdfReader.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"PdfReader.js","sourceRoot":"","sources":["../../../../src/core/processor/readers/PdfReader.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;AAWA,wCAGC;AAZD,6CAA0D;AAC1D,uDAA2D;AAC3D,+DAAwE;AACxE,wDAAiC;AAEjC;;;GAGG;AACH,SAAgB,cAAc,CAAC,IAAY;IACzC,MAAM,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,qCAAqC,CAAC,CAAC;IAC5D,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;AAC9B,CAAC;AAED;;GAEG;AACH,MAAa,SAAU,SAAQ,uBAAU;IACvC,YACE,OAAoB,EACpB,MAAc,EACG,kBAA2B,KAAK,EAChC,eAAwB,KAAK;QAE9C,KAAK,CAAC,CAAC,MAAM,CAAC,EAAE,OAAO,EAAE,MAAM,CAAC,CAAC;QAHhB,oBAAe,GAAf,eAAe,CAAiB;QAChC,iBAAY,GAAZ,YAAY,CAAiB;IAGhD,CAAC;IAED,OAAO;QACL,OAAO,WAAW,CAAC;IACrB,CAAC;IAED,SAAS;QACP,OAAO,cAAc,CAAC;IACxB,CAAC;IAEK,IAAI,CAAC,QAAgB;;YACzB,MAAM,IAAI,CAAC,YAAY,CAAC,QAAQ,CAAC,CAAC;YAElC,IAAI,CAAC;gBACH,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,qBAAqB,QAAQ,EAAE,CAAC,CAAC;gBAEnD,IAAI,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,GAAG,MAAM,IAAI,CAAC,YAAY,CAAC,QAAQ,CAAC,CAAC;gBAElE,uEAAuE;gBACvE,wEAAwE;gBACxE,MAAM,OAAO,GAAG,cAAc,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC;gBAE/D,qEAAqE;gBACrE,MAAM,KAAK,GACT,IAAI,CAAC,eAAe,IAAI,IAAI,CAAC,YAAY;oBACvC,CAAC,CAAC,IAAA,wCAAsB,EAAC,OAAO,CAAC;oBACjC,CAAC,CAAC,SAAS,CAAC;gBAEhB,wEAAwE;gBACxE,4DAA4D;gBAC5D,IAAI,UAAqC,CAAC;gBAC1C,IAAI,IAAI,CAAC,YAAY,EAAE,CAAC;oBACtB,MAAM,KAAK,GAAG,IAAA,sCAAgB,EAAC,KAAK,aAAL,KAAK,uBAAL,KAAK,CAAE,UAAU,EAAE,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,MAAM,CAC1E,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,OAAO,IAAI,CAAC,CAAC,OAAO,KAAK,OAAO,CACzC,CAAC;oBACF,IAAI,KAAK,CAAC,MAAM;wBAAE,UAAU,GAAG,EAAE,SAAS,EAAE,KAAK,EAAE,CAAC;gBACtD,CAAC;gBAED,IAAI,IAAI,CAAC,eAAe,KAAI,KAAK,aAAL,KAAK,uBAAL,KAAK,CAAE,UAAU,CAAA,EAAE,CAAC;oBAC9C,IAAI,CAAC,MAAM,CAAC,IAAI,CACd,8CAA8C,QAAQ,GAAG;wBACvD,IAAI,KAAK,CAAC,UAAU,CAAC,MAAM,WAAW,OAAO,CAAC,MAAM,GAAG,KAAK,CAAC,KAAK,CAAC,MAAM,mBAAmB,CAC/F,CAAC;oBACF,OAAO,GAAG,KAAK,CAAC,KAAK,CAAC;gBACxB,CAAC;gBAED,MAAM,MAAM,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE;oBACzC,MAAM,WAAW,GAAG,OAAO,CAAC,KAAK,CAAC,CAAC,EAAE,KAAK,CAAC,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,IAAI,EAAE,EAAE,CAAC,GAAG,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC;oBACxF,OAAO;wBACL,OAAO,EAAE,IAAI;wBACb,WAAW,EAAE,WAAW;wBACxB,SAAS,EAAE,WAAW,GAAG,IAAI,CAAC,MAAM;wBACpC,KAAK,EAAE,KAAK,GAAG,CAAC;wBAChB,WAAW,EAAE,OAAO,CAAC,MAAM;wBAC3B,UAAU,EAAE,EAAE,OAAO,EAAE,KAAK,KAAK,GAAG,CAAC,EAAE,EAAE,EAAE,oCAAoC;qBAChF,CAAC;gBACJ,CAAC,CAAC,CAAC;gBAEH,OAAO;oBACL,MAAM,EAAE,MAAM;oBACd,QAAQ,8CACN,IAAI,EAAE,KAAK,EACX,QAAQ,EAAE,QAAQ,IACf,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,OAAO,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,GAC5B,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,GACxB,CAAC,UAAU,CAAC,CAAC,CAAC,EAAE,UAAU,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,CACtC;iBACF,CAAC;YACJ,CAAC;YAAC,OAAO,KAAK,EAAE,CAAC;gBACf,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,2BAA2B,QAAQ,KAAK,KAAK,EAAE,CAAC,CAAC;gBACnE,MAAM,IAAI,KAAK,CAAC,4BAA4B,KAAK,EAAE,CAAC,CAAC;YACvD,CAAC;QACH,CAAC;KAAA;IAEO,YAAY,CAAC,QAAgB;QACnC,OAAO,IAAI,OAAO,CAAC,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE;YACrC,MAAM,SAAS,GAAG,IAAI,kBAAS,EAAE,CAAC;YAElC,SAAS,CAAC,EAAE,CAAC,qBAAqB,EAAE,CAAC,OAAO,EAAE,EAAE,CAC9C,MAAM,CAAC,OAAO,CAAC,WAAW,CAAC,CAC5B,CAAC;YAEF,SAAS,CAAC,EAAE,CAAC,qBAAqB,EAAE,CAAC,OAAO,EAAE,EAAE;;gBAC9C,MAAM,KAAK,GAAG,OAAO,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CACvC,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CACnB,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,kBAAkB,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,CACjD,CAAC,IAAI,CAAC,IAAI,CAAC,CACb,CAAC;gBACF,MAAM,QAAQ,GAAG,MAAC,OAAe,CAAC,IAAI,0CAAE,KAAK,CAAC;gBAC9C,IAAI,KAAyB,CAAC;gBAC9B,IAAI,OAAO,QAAQ,KAAK,QAAQ,IAAI,QAAQ,CAAC,IAAI,EAAE,EAAE,CAAC;oBACpD,IAAI,CAAC;wBACH,KAAK,GAAG,kBAAkB,CAAC,QAAQ,CAAC,CAAC,IAAI,EAAE,CAAC;oBAC9C,CAAC;oBAAC,WAAM,CAAC;wBACP,KAAK,GAAG,QAAQ,CAAC,IAAI,EAAE,CAAC;oBAC1B,CAAC;gBACH,CAAC;gBACD,OAAO,CAAC,EAAE,KAAK,EAAE,KAAK,EAAE,CAAC,CAAC;YAC5B,CAAC,CAAC,CAAC;YAEH,SAAS,CAAC,OAAO,CAAC,QAAQ,CAAC,CAAC;QAC9B,CAAC,CAAC,CAAC;IACL,CAAC;CACF;AA/GD,8BA+GC"}
@@ -0,0 +1,107 @@
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
+ var __importDefault = (this && this.__importDefault) || function (mod) {
12
+ return (mod && mod.__esModule) ? mod : { "default": mod };
13
+ };
14
+ Object.defineProperty(exports, "__esModule", { value: true });
15
+ exports.RtfReader = void 0;
16
+ const FileReader_1 = require("./FileReader");
17
+ const path_1 = __importDefault(require("path"));
18
+ const promises_1 = __importDefault(require("fs/promises"));
19
+ const shared_1 = require("../../../shared");
20
+ /**
21
+ * Reader for Rich Text Format (RTF) documents
22
+ *
23
+ * Uses the rtf-parser npm package to extract text content from RTF files.
24
+ * RTF documents can contain rich formatting, images, and other elements,
25
+ * but this reader focuses on extracting plain text content for indexing.
26
+ *
27
+ * Supported formats: .rtf
28
+ *
29
+ * npm install rtf-parser
30
+ */
31
+ class RtfReader extends FileReader_1.FileReader {
32
+ constructor(chunker, logger) {
33
+ super([".rtf"], chunker, logger);
34
+ }
35
+ getName() {
36
+ return "RtfReader";
37
+ }
38
+ read(filePath) {
39
+ return __awaiter(this, void 0, void 0, function* () {
40
+ yield this.validateFile(filePath);
41
+ try {
42
+ this.logger.debug(`Reading RTF file: ${filePath}`);
43
+ // Get file stats for basic metadata
44
+ const stats = yield promises_1.default.stat(filePath);
45
+ // Parse RTF content using rtf-parser
46
+ const { text, info } = yield (0, shared_1.readRtf)(filePath);
47
+ // Chunk the extracted text
48
+ const chunks = yield this.chunker.chunk(text);
49
+ // Convert to ChunkResult format
50
+ const chunkResults = chunks.map(chunk => ({
51
+ content: chunk.content,
52
+ startOffset: chunk.startOffset,
53
+ endOffset: chunk.endOffset,
54
+ index: chunk.index,
55
+ totalChunks: chunk.totalChunks,
56
+ }));
57
+ // Build metadata object
58
+ const metadata = {
59
+ type: "rtf_document",
60
+ description: "Rich Text Format Document",
61
+ fileName: path_1.default.basename(filePath),
62
+ filePath: filePath,
63
+ fileSize: stats.size,
64
+ createdAt: stats.birthtime.toISOString(),
65
+ modifiedAt: stats.mtime.toISOString(),
66
+ accessedAt: stats.atime.toISOString(),
67
+ extension: ".rtf",
68
+ status: "success",
69
+ extractedTextLength: text.length,
70
+ hasContent: text.trim().length > 0,
71
+ documentInfo: info,
72
+ };
73
+ this.logger.debug(`Successfully extracted ${text.length} characters from RTF file ${filePath}`);
74
+ return {
75
+ chunks: chunkResults,
76
+ metadata: metadata,
77
+ };
78
+ }
79
+ catch (error) {
80
+ this.logger.error(`Failed to read RTF file ${filePath}: ${error.message}`);
81
+ // Return error result instead of throwing
82
+ return {
83
+ chunks: [
84
+ {
85
+ content: "",
86
+ startOffset: 0,
87
+ endOffset: 0,
88
+ index: 1,
89
+ totalChunks: 1,
90
+ },
91
+ ],
92
+ metadata: {
93
+ type: "rtf_document",
94
+ description: "Rich Text Format Document",
95
+ fileName: path_1.default.basename(filePath),
96
+ filePath: filePath,
97
+ status: "error",
98
+ error: error.message,
99
+ errorType: error.name,
100
+ },
101
+ };
102
+ }
103
+ });
104
+ }
105
+ }
106
+ exports.RtfReader = RtfReader;
107
+ //# sourceMappingURL=RtfReader.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"RtfReader.js","sourceRoot":"","sources":["../../../../src/core/processor/readers/RtfReader.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;AAAA,6CAA0D;AAC1D,gDAAwB;AACxB,2DAA6B;AAG7B,4CAA0C;AAE1C;;;;;;;;;;GAUG;AACH,MAAa,SAAU,SAAQ,uBAAU;IACvC,YAAY,OAAoB,EAAE,MAAc;QAC9C,KAAK,CAAC,CAAC,MAAM,CAAC,EAAE,OAAO,EAAE,MAAM,CAAC,CAAC;IACnC,CAAC;IAED,OAAO;QACL,OAAO,WAAW,CAAC;IACrB,CAAC;IAEK,IAAI,CAAC,QAAgB;;YACzB,MAAM,IAAI,CAAC,YAAY,CAAC,QAAQ,CAAC,CAAC;YAElC,IAAI,CAAC;gBACH,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,qBAAqB,QAAQ,EAAE,CAAC,CAAC;gBAEnD,oCAAoC;gBACpC,MAAM,KAAK,GAAG,MAAM,kBAAE,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;gBAEtC,qCAAqC;gBACrC,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,GAAG,MAAM,IAAA,gBAAO,EAAC,QAAQ,CAAC,CAAC;gBAE/C,2BAA2B;gBAC3B,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,OAAO,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;gBAE9C,gCAAgC;gBAChC,MAAM,YAAY,GAAG,MAAM,CAAC,GAAG,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC;oBACxC,OAAO,EAAE,KAAK,CAAC,OAAO;oBACtB,WAAW,EAAE,KAAK,CAAC,WAAW;oBAC9B,SAAS,EAAE,KAAK,CAAC,SAAS;oBAC1B,KAAK,EAAE,KAAK,CAAC,KAAK;oBAClB,WAAW,EAAE,KAAK,CAAC,WAAW;iBAC/B,CAAC,CAAC,CAAC;gBAEJ,wBAAwB;gBACxB,MAAM,QAAQ,GAAG;oBACf,IAAI,EAAE,cAAc;oBACpB,WAAW,EAAE,2BAA2B;oBACxC,QAAQ,EAAE,cAAI,CAAC,QAAQ,CAAC,QAAQ,CAAC;oBACjC,QAAQ,EAAE,QAAQ;oBAClB,QAAQ,EAAE,KAAK,CAAC,IAAI;oBACpB,SAAS,EAAE,KAAK,CAAC,SAAS,CAAC,WAAW,EAAE;oBACxC,UAAU,EAAE,KAAK,CAAC,KAAK,CAAC,WAAW,EAAE;oBACrC,UAAU,EAAE,KAAK,CAAC,KAAK,CAAC,WAAW,EAAE;oBACrC,SAAS,EAAE,MAAM;oBACjB,MAAM,EAAE,SAAS;oBACjB,mBAAmB,EAAE,IAAI,CAAC,MAAM;oBAChC,UAAU,EAAE,IAAI,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC;oBAClC,YAAY,EAAE,IAAI;iBACnB,CAAC;gBAEF,IAAI,CAAC,MAAM,CAAC,KAAK,CACf,0BAA0B,IAAI,CAAC,MAAM,6BAA6B,QAAQ,EAAE,CAC7E,CAAC;gBAEF,OAAO;oBACL,MAAM,EAAE,YAAY;oBACpB,QAAQ,EAAE,QAAQ;iBACnB,CAAC;YACJ,CAAC;YAAC,OAAO,KAAU,EAAE,CAAC;gBACpB,IAAI,CAAC,MAAM,CAAC,KAAK,CACf,2BAA2B,QAAQ,KAAK,KAAK,CAAC,OAAO,EAAE,CACxD,CAAC;gBAEF,0CAA0C;gBAC1C,OAAO;oBACL,MAAM,EAAE;wBACN;4BACE,OAAO,EAAE,EAAE;4BACX,WAAW,EAAE,CAAC;4BACd,SAAS,EAAE,CAAC;4BACZ,KAAK,EAAE,CAAC;4BACR,WAAW,EAAE,CAAC;yBACf;qBACF;oBACD,QAAQ,EAAE;wBACR,IAAI,EAAE,cAAc;wBACpB,WAAW,EAAE,2BAA2B;wBACxC,QAAQ,EAAE,cAAI,CAAC,QAAQ,CAAC,QAAQ,CAAC;wBACjC,QAAQ,EAAE,QAAQ;wBAClB,MAAM,EAAE,OAAO;wBACf,KAAK,EAAE,KAAK,CAAC,OAAO;wBACpB,SAAS,EAAE,KAAK,CAAC,IAAI;qBACtB;iBACF,CAAC;YACJ,CAAC;QACH,CAAC;KAAA;CACF;AAtFD,8BAsFC"}