@zvec/zvec-grep 0.1.5 → 0.1.7

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 (358) hide show
  1. package/README.md +154 -236
  2. package/README_CN.md +142 -233
  3. package/dist/authorization/index.d.ts +7 -0
  4. package/dist/authorization/index.js +7 -0
  5. package/dist/authorization/index.js.map +1 -0
  6. package/dist/authorization/manager.d.ts +8 -0
  7. package/dist/authorization/manager.js +19 -0
  8. package/dist/authorization/manager.js.map +1 -0
  9. package/dist/authorization/operation.d.ts +7 -0
  10. package/dist/authorization/operation.js +50 -0
  11. package/dist/authorization/operation.js.map +1 -0
  12. package/dist/authorization/planner.d.ts +21 -0
  13. package/dist/authorization/planner.js +97 -0
  14. package/dist/authorization/planner.js.map +1 -0
  15. package/dist/authorization/prompt.d.ts +11 -0
  16. package/dist/authorization/prompt.js +62 -0
  17. package/dist/authorization/prompt.js.map +1 -0
  18. package/dist/authorization/store.d.ts +20 -0
  19. package/dist/authorization/store.js +251 -0
  20. package/dist/authorization/store.js.map +1 -0
  21. package/dist/authorization/target.d.ts +15 -0
  22. package/dist/authorization/target.js +49 -0
  23. package/dist/authorization/target.js.map +1 -0
  24. package/dist/authorization/types.d.ts +61 -0
  25. package/dist/authorization/types.js +2 -0
  26. package/dist/authorization/types.js.map +1 -0
  27. package/dist/cli/args.d.ts +1 -1
  28. package/dist/cli/args.js +338 -55
  29. package/dist/cli/args.js.map +1 -1
  30. package/dist/cli/auth.d.ts +21 -0
  31. package/dist/cli/auth.js +209 -0
  32. package/dist/cli/auth.js.map +1 -0
  33. package/dist/cli/commands.js +469 -625
  34. package/dist/cli/commands.js.map +1 -1
  35. package/dist/cli/errors.js +2 -2
  36. package/dist/cli/errors.js.map +1 -1
  37. package/dist/cli/format/context.d.ts +4 -0
  38. package/dist/cli/format/context.js +311 -44
  39. package/dist/cli/format/context.js.map +1 -1
  40. package/dist/cli/format/debug.js +12 -6
  41. package/dist/cli/format/debug.js.map +1 -1
  42. package/dist/cli/format/progress.d.ts +4 -0
  43. package/dist/cli/format/progress.js +219 -46
  44. package/dist/cli/format/progress.js.map +1 -1
  45. package/dist/cli/format/status.d.ts +79 -6
  46. package/dist/cli/format/status.js +341 -111
  47. package/dist/cli/format/status.js.map +1 -1
  48. package/dist/cli/help.js +395 -63
  49. package/dist/cli/help.js.map +1 -1
  50. package/dist/cli/index.d.ts +1 -1
  51. package/dist/cli/index.js +1 -1
  52. package/dist/cli/install.d.ts +4 -0
  53. package/dist/cli/install.js +963 -0
  54. package/dist/cli/install.js.map +1 -0
  55. package/dist/cli/managed-rg.d.ts +10 -0
  56. package/dist/cli/managed-rg.js +329 -0
  57. package/dist/cli/managed-rg.js.map +1 -0
  58. package/dist/cli/server-search.d.ts +3 -0
  59. package/dist/cli/server-search.js +12 -0
  60. package/dist/cli/server-search.js.map +1 -0
  61. package/dist/cli/types.d.ts +23 -6
  62. package/dist/cli/types.js.map +1 -1
  63. package/dist/client/daemon-client.d.ts +31 -0
  64. package/dist/client/daemon-client.js +203 -0
  65. package/dist/client/daemon-client.js.map +1 -0
  66. package/dist/client/mode-router.d.ts +9 -0
  67. package/dist/client/mode-router.js +28 -0
  68. package/dist/client/mode-router.js.map +1 -0
  69. package/dist/client/search-policy.d.ts +11 -0
  70. package/dist/client/search-policy.js +15 -0
  71. package/dist/client/search-policy.js.map +1 -0
  72. package/dist/daemon/backend.d.ts +77 -0
  73. package/dist/daemon/backend.js +1087 -0
  74. package/dist/daemon/backend.js.map +1 -0
  75. package/dist/daemon/change-set.d.ts +25 -0
  76. package/dist/daemon/change-set.js +101 -0
  77. package/dist/daemon/change-set.js.map +1 -0
  78. package/dist/daemon/config.d.ts +24 -0
  79. package/dist/daemon/config.js +88 -0
  80. package/dist/daemon/config.js.map +1 -0
  81. package/dist/daemon/errors.d.ts +5 -0
  82. package/dist/daemon/errors.js +11 -0
  83. package/dist/daemon/errors.js.map +1 -0
  84. package/dist/daemon/http-server.d.ts +30 -0
  85. package/dist/daemon/http-server.js +288 -0
  86. package/dist/daemon/http-server.js.map +1 -0
  87. package/dist/daemon/index-coordinator.d.ts +24 -0
  88. package/dist/daemon/index-coordinator.js +68 -0
  89. package/dist/daemon/index-coordinator.js.map +1 -0
  90. package/dist/daemon/job-scheduler.d.ts +70 -0
  91. package/dist/daemon/job-scheduler.js +366 -0
  92. package/dist/daemon/job-scheduler.js.map +1 -0
  93. package/dist/daemon/logger.d.ts +9 -0
  94. package/dist/daemon/logger.js +53 -0
  95. package/dist/daemon/logger.js.map +1 -0
  96. package/dist/daemon/model-pool.d.ts +45 -0
  97. package/dist/daemon/model-pool.js +187 -0
  98. package/dist/daemon/model-pool.js.map +1 -0
  99. package/dist/daemon/root-lease.d.ts +14 -0
  100. package/dist/daemon/root-lease.js +188 -0
  101. package/dist/daemon/root-lease.js.map +1 -0
  102. package/dist/daemon/root-runtime.d.ts +78 -0
  103. package/dist/daemon/root-runtime.js +333 -0
  104. package/dist/daemon/root-runtime.js.map +1 -0
  105. package/dist/daemon/runtime-manager.d.ts +46 -0
  106. package/dist/daemon/runtime-manager.js +246 -0
  107. package/dist/daemon/runtime-manager.js.map +1 -0
  108. package/dist/daemon/runtime.d.ts +12 -0
  109. package/dist/daemon/runtime.js +102 -0
  110. package/dist/daemon/runtime.js.map +1 -0
  111. package/dist/daemon/server-controller.d.ts +39 -0
  112. package/dist/daemon/server-controller.js +254 -0
  113. package/dist/daemon/server-controller.js.map +1 -0
  114. package/dist/daemon/watch-manager.d.ts +50 -0
  115. package/dist/daemon/watch-manager.js +293 -0
  116. package/dist/daemon/watch-manager.js.map +1 -0
  117. package/dist/daemon/workspace-read-session-cache.d.ts +31 -0
  118. package/dist/daemon/workspace-read-session-cache.js +115 -0
  119. package/dist/daemon/workspace-read-session-cache.js.map +1 -0
  120. package/dist/engine/code-formats.d.ts +3 -0
  121. package/dist/engine/code-formats.js +14 -0
  122. package/dist/engine/code-formats.js.map +1 -0
  123. package/dist/engine/config.d.ts +30 -8
  124. package/dist/engine/config.js +171 -45
  125. package/dist/engine/config.js.map +1 -1
  126. package/dist/engine/{errors/index.d.ts → errors.d.ts} +6 -1
  127. package/dist/engine/{errors/details.js → errors.js} +17 -4
  128. package/dist/engine/errors.js.map +1 -0
  129. package/dist/engine/extraction/code/adapter.d.ts +1 -1
  130. package/dist/engine/extraction/code/adapter.js +1 -1
  131. package/dist/engine/extraction/code/adapter.js.map +1 -1
  132. package/dist/engine/extraction/code/extractor.d.ts +5 -11
  133. package/dist/engine/extraction/code/extractor.js +116 -48
  134. package/dist/engine/extraction/code/extractor.js.map +1 -1
  135. package/dist/engine/extraction/code/families/c-family.js +1 -1
  136. package/dist/engine/extraction/code/families/c-family.js.map +1 -1
  137. package/dist/engine/extraction/code/families/js-ts.d.ts +1 -1
  138. package/dist/engine/extraction/code/families/metadata.d.ts +1 -1
  139. package/dist/engine/extraction/code/tree-sitter/grammar.js.map +1 -0
  140. package/dist/engine/extraction/code/tree-sitter/nodes.js.map +1 -0
  141. package/dist/engine/extraction/code/tree-sitter/parser.js.map +1 -0
  142. package/dist/engine/extraction/image/extractor.d.ts +5 -0
  143. package/dist/engine/extraction/image/extractor.js +35 -0
  144. package/dist/engine/extraction/image/extractor.js.map +1 -0
  145. package/dist/engine/extraction/index.d.ts +4 -44
  146. package/dist/engine/extraction/index.js +2 -280
  147. package/dist/engine/extraction/index.js.map +1 -1
  148. package/dist/engine/extraction/markdown/extractor.d.ts +5 -11
  149. package/dist/engine/extraction/markdown/extractor.js +38 -17
  150. package/dist/engine/extraction/markdown/extractor.js.map +1 -1
  151. package/dist/engine/extraction/runtime.d.ts +4 -0
  152. package/dist/engine/extraction/runtime.js +26 -0
  153. package/dist/engine/extraction/runtime.js.map +1 -0
  154. package/dist/engine/extraction/source.d.ts +18 -0
  155. package/dist/engine/extraction/source.js +22 -0
  156. package/dist/engine/extraction/source.js.map +1 -0
  157. package/dist/engine/extraction/text/extractor.d.ts +7 -0
  158. package/dist/engine/extraction/text/extractor.js +168 -0
  159. package/dist/engine/extraction/text/extractor.js.map +1 -0
  160. package/dist/engine/extraction/types.d.ts +4 -0
  161. package/dist/engine/{models → extraction}/types.js.map +1 -1
  162. package/dist/engine/extraction/vector-content.d.ts +5 -0
  163. package/dist/engine/extraction/vector-content.js +95 -0
  164. package/dist/engine/extraction/vector-content.js.map +1 -0
  165. package/dist/engine/file-size-policy.d.ts +6 -0
  166. package/dist/engine/file-size-policy.js +20 -0
  167. package/dist/engine/file-size-policy.js.map +1 -0
  168. package/dist/engine/file-type.d.ts +15 -0
  169. package/dist/engine/file-type.js +152 -0
  170. package/dist/engine/file-type.js.map +1 -0
  171. package/dist/engine/index-status.d.ts +9 -0
  172. package/dist/engine/index-status.js +38 -0
  173. package/dist/engine/index-status.js.map +1 -0
  174. package/dist/engine/manifest.d.ts +13 -0
  175. package/dist/engine/manifest.js +124 -0
  176. package/dist/engine/manifest.js.map +1 -0
  177. package/dist/engine/models/{providers/llama-cpp/embedding.d.ts → backends/llama-cpp.d.ts} +25 -20
  178. package/dist/engine/models/{providers/llama-cpp/embedding.js → backends/llama-cpp.js} +127 -106
  179. package/dist/engine/models/backends/llama-cpp.js.map +1 -0
  180. package/dist/engine/models/backends/model2vec-runtime.d.ts +63 -0
  181. package/dist/engine/models/backends/model2vec-runtime.js +112 -0
  182. package/dist/engine/models/backends/model2vec-runtime.js.map +1 -0
  183. package/dist/engine/models/backends/model2vec-tokenizer.d.ts +2 -0
  184. package/dist/engine/models/backends/model2vec-tokenizer.js +42 -0
  185. package/dist/engine/models/backends/model2vec-tokenizer.js.map +1 -0
  186. package/dist/engine/models/backends/model2vec-worker-pool.d.ts +25 -0
  187. package/dist/engine/models/backends/model2vec-worker-pool.js +264 -0
  188. package/dist/engine/models/backends/model2vec-worker-pool.js.map +1 -0
  189. package/dist/engine/models/backends/model2vec-worker.d.ts +1 -0
  190. package/dist/engine/models/backends/model2vec-worker.js +41 -0
  191. package/dist/engine/models/backends/model2vec-worker.js.map +1 -0
  192. package/dist/engine/models/backends/model2vec.d.ts +40 -0
  193. package/dist/engine/models/backends/model2vec.js +311 -0
  194. package/dist/engine/models/backends/model2vec.js.map +1 -0
  195. package/dist/engine/models/backends/qwen.d.ts +44 -0
  196. package/dist/engine/models/{providers/qwen/embedding.js → backends/qwen.js} +155 -94
  197. package/dist/engine/models/backends/qwen.js.map +1 -0
  198. package/dist/engine/models/backends/transformers-js.d.ts +87 -0
  199. package/dist/engine/models/backends/transformers-js.js +316 -0
  200. package/dist/engine/models/backends/transformers-js.js.map +1 -0
  201. package/dist/engine/models/catalog.d.ts +207 -23
  202. package/dist/engine/models/catalog.js +191 -25
  203. package/dist/engine/models/catalog.js.map +1 -1
  204. package/dist/engine/models/download-progress.d.ts +15 -0
  205. package/dist/engine/models/download-progress.js +48 -0
  206. package/dist/engine/models/download-progress.js.map +1 -0
  207. package/dist/engine/models/embeddings.d.ts +59 -18
  208. package/dist/engine/models/embeddings.js +52 -28
  209. package/dist/engine/models/embeddings.js.map +1 -1
  210. package/dist/engine/models/factory.d.ts +2 -5
  211. package/dist/engine/models/factory.js +41 -56
  212. package/dist/engine/models/factory.js.map +1 -1
  213. package/dist/engine/models/index.d.ts +4 -6
  214. package/dist/engine/models/index.js +4 -4
  215. package/dist/engine/models/index.js.map +1 -1
  216. package/dist/engine/models/ranking.d.ts +7 -3
  217. package/dist/engine/models/resolution.d.ts +8 -0
  218. package/dist/engine/models/resolution.js +22 -0
  219. package/dist/engine/models/resolution.js.map +1 -0
  220. package/dist/engine/pipeline/indexing/index.d.ts +9 -7
  221. package/dist/engine/pipeline/indexing/index.js +409 -165
  222. package/dist/engine/pipeline/indexing/index.js.map +1 -1
  223. package/dist/engine/pipeline/indexing/input-budget.d.ts +2 -0
  224. package/dist/engine/pipeline/indexing/input-budget.js +51 -0
  225. package/dist/engine/pipeline/indexing/input-budget.js.map +1 -0
  226. package/dist/engine/pipeline/indexing/root-paths.js +6 -6
  227. package/dist/engine/pipeline/indexing/root-paths.js.map +1 -1
  228. package/dist/engine/pipeline/indexing/scanner/index.d.ts +9 -2
  229. package/dist/engine/pipeline/indexing/scanner/index.js +291 -35
  230. package/dist/engine/pipeline/indexing/scanner/index.js.map +1 -1
  231. package/dist/engine/pipeline/search/index.d.ts +6 -6
  232. package/dist/engine/pipeline/search/index.js +8 -10
  233. package/dist/engine/pipeline/search/index.js.map +1 -1
  234. package/dist/engine/service/index.d.ts +3 -2
  235. package/dist/engine/service/index.js +1 -1
  236. package/dist/engine/service/index.js.map +1 -1
  237. package/dist/engine/service/root.d.ts +10 -12
  238. package/dist/engine/service/root.js +29 -25
  239. package/dist/engine/service/root.js.map +1 -1
  240. package/dist/engine/service/structure-enrichment.d.ts +1 -1
  241. package/dist/engine/service/structure-enrichment.js +20 -22
  242. package/dist/engine/service/structure-enrichment.js.map +1 -1
  243. package/dist/engine/service/types.d.ts +40 -38
  244. package/dist/engine/service/workspace-index.d.ts +26 -0
  245. package/dist/engine/service/workspace-index.js +157 -0
  246. package/dist/engine/service/workspace-index.js.map +1 -0
  247. package/dist/engine/service/zvec-grep.d.ts +12 -1
  248. package/dist/engine/service/zvec-grep.js +698 -489
  249. package/dist/engine/service/zvec-grep.js.map +1 -1
  250. package/dist/engine/storage/index.d.ts +30 -20
  251. package/dist/engine/storage/index.js +2 -1
  252. package/dist/engine/storage/index.js.map +1 -1
  253. package/dist/engine/storage/layout.d.ts +10 -0
  254. package/dist/engine/storage/layout.js +29 -0
  255. package/dist/engine/storage/layout.js.map +1 -0
  256. package/dist/engine/storage/zvec.d.ts +4 -67
  257. package/dist/engine/storage/zvec.js +115 -85
  258. package/dist/engine/storage/zvec.js.map +1 -1
  259. package/dist/engine/types.d.ts +29 -23
  260. package/dist/engine/types.js +1 -1
  261. package/dist/engine/types.js.map +1 -1
  262. package/dist/engine/utils/daemon-lease.d.ts +17 -0
  263. package/dist/engine/utils/daemon-lease.js +175 -0
  264. package/dist/engine/utils/daemon-lease.js.map +1 -0
  265. package/dist/engine/utils/file-selection.js +38 -1
  266. package/dist/engine/utils/file-selection.js.map +1 -1
  267. package/dist/engine/utils/lock.js +1 -1
  268. package/dist/engine/utils/lock.js.map +1 -1
  269. package/dist/index-progress.d.ts +10 -0
  270. package/dist/index-progress.js +159 -0
  271. package/dist/index-progress.js.map +1 -0
  272. package/dist/index.d.ts +4 -4
  273. package/dist/index.js +1 -1
  274. package/dist/index.js.map +1 -1
  275. package/dist/mcp/http-transport.d.ts +27 -0
  276. package/dist/mcp/http-transport.js +182 -0
  277. package/dist/mcp/http-transport.js.map +1 -0
  278. package/dist/mcp/input-normalization.d.ts +38 -0
  279. package/dist/mcp/input-normalization.js +104 -0
  280. package/dist/mcp/input-normalization.js.map +1 -0
  281. package/dist/mcp/progress-heartbeat.d.ts +17 -0
  282. package/dist/mcp/progress-heartbeat.js +46 -0
  283. package/dist/mcp/progress-heartbeat.js.map +1 -0
  284. package/dist/mcp/request-metadata.d.ts +2 -0
  285. package/dist/mcp/request-metadata.js +11 -0
  286. package/dist/mcp/request-metadata.js.map +1 -0
  287. package/dist/mcp/request-state.d.ts +40 -0
  288. package/dist/mcp/request-state.js +210 -0
  289. package/dist/mcp/request-state.js.map +1 -0
  290. package/dist/mcp/result-format.d.ts +13 -0
  291. package/dist/mcp/result-format.js +75 -0
  292. package/dist/mcp/result-format.js.map +1 -0
  293. package/dist/mcp/schemas.d.ts +672 -0
  294. package/dist/mcp/schemas.js +506 -0
  295. package/dist/mcp/schemas.js.map +1 -0
  296. package/dist/mcp/stdio-bridge.d.ts +9 -0
  297. package/dist/mcp/stdio-bridge.js +131 -0
  298. package/dist/mcp/stdio-bridge.js.map +1 -0
  299. package/dist/mcp/tools.d.ts +153 -0
  300. package/dist/mcp/tools.js +482 -0
  301. package/dist/mcp/tools.js.map +1 -0
  302. package/dist/mcp/toolset.d.ts +5 -0
  303. package/dist/mcp/toolset.js +12 -0
  304. package/dist/mcp/toolset.js.map +1 -0
  305. package/dist/observability/trace-context.d.ts +11 -0
  306. package/dist/observability/trace-context.js +138 -0
  307. package/dist/observability/trace-context.js.map +1 -0
  308. package/dist/prompts/zvec-grep-guidance.d.ts +2 -0
  309. package/dist/prompts/zvec-grep-guidance.js +9 -0
  310. package/dist/prompts/zvec-grep-guidance.js.map +1 -0
  311. package/docs/01-agents.md +132 -0
  312. package/docs/02-cli.md +239 -0
  313. package/docs/03-mcp.md +185 -0
  314. package/docs/04-pipeline.md +226 -0
  315. package/docs/05-architecture.md +86 -0
  316. package/docs/06-server.md +215 -0
  317. package/docs/07-embedding.md +182 -0
  318. package/docs/08-roadmap.md +85 -0
  319. package/docs/README.md +53 -0
  320. package/package.json +20 -11
  321. package/dist/cli/mcp.d.ts +0 -2
  322. package/dist/cli/mcp.js +0 -354
  323. package/dist/cli/mcp.js.map +0 -1
  324. package/dist/engine/collection/index.d.ts +0 -55
  325. package/dist/engine/collection/index.js +0 -710
  326. package/dist/engine/collection/index.js.map +0 -1
  327. package/dist/engine/errors/details.d.ts +0 -6
  328. package/dist/engine/errors/details.js.map +0 -1
  329. package/dist/engine/errors/index.js +0 -16
  330. package/dist/engine/errors/index.js.map +0 -1
  331. package/dist/engine/extraction/tree-sitter/grammar.js.map +0 -1
  332. package/dist/engine/extraction/tree-sitter/nodes.js.map +0 -1
  333. package/dist/engine/extraction/tree-sitter/parser.js.map +0 -1
  334. package/dist/engine/files/file-type.d.ts +0 -5
  335. package/dist/engine/files/file-type.js +0 -119
  336. package/dist/engine/files/file-type.js.map +0 -1
  337. package/dist/engine/models/providers/index.d.ts +0 -2
  338. package/dist/engine/models/providers/index.js +0 -3
  339. package/dist/engine/models/providers/index.js.map +0 -1
  340. package/dist/engine/models/providers/llama-cpp/embedding.js.map +0 -1
  341. package/dist/engine/models/providers/llama-cpp/index.d.ts +0 -1
  342. package/dist/engine/models/providers/llama-cpp/index.js +0 -2
  343. package/dist/engine/models/providers/llama-cpp/index.js.map +0 -1
  344. package/dist/engine/models/providers/qwen/embedding.d.ts +0 -42
  345. package/dist/engine/models/providers/qwen/embedding.js.map +0 -1
  346. package/dist/engine/models/providers/qwen/index.d.ts +0 -1
  347. package/dist/engine/models/providers/qwen/index.js +0 -2
  348. package/dist/engine/models/providers/qwen/index.js.map +0 -1
  349. package/dist/engine/models/types.d.ts +0 -30
  350. package/skills/zvec-grep/SKILL.md +0 -151
  351. package/skills/zvec-grep/agents/openai.yaml +0 -4
  352. /package/dist/engine/extraction/{tree-sitter → code/tree-sitter}/grammar.d.ts +0 -0
  353. /package/dist/engine/extraction/{tree-sitter → code/tree-sitter}/grammar.js +0 -0
  354. /package/dist/engine/extraction/{tree-sitter → code/tree-sitter}/nodes.d.ts +0 -0
  355. /package/dist/engine/extraction/{tree-sitter → code/tree-sitter}/nodes.js +0 -0
  356. /package/dist/engine/extraction/{tree-sitter → code/tree-sitter}/parser.d.ts +0 -0
  357. /package/dist/engine/extraction/{tree-sitter → code/tree-sitter}/parser.js +0 -0
  358. /package/dist/engine/{models → extraction}/types.js +0 -0
@@ -1,281 +1,3 @@
1
- import { EngineError } from "../errors/index.js";
2
- import { makeEntityId } from "./ids.js";
3
- import { CodeExtractor } from "./code/extractor.js";
4
- import { MarkdownExtractor } from "./markdown/extractor.js";
5
- const DEFAULT_TEXT_CHUNK_CHARS = 3600;
6
- const DEFAULT_TEXT_CHUNK_OVERLAP_CHARS = 540;
7
- export class TextExtractor {
8
- maxChunkChars;
9
- chunkOverlapChars;
10
- constructor(options = {}) {
11
- const maxChunkChars = options.maxChunkChars ?? DEFAULT_TEXT_CHUNK_CHARS;
12
- const chunkOverlapChars = options.chunkOverlapChars ?? DEFAULT_TEXT_CHUNK_OVERLAP_CHARS;
13
- if (!Number.isInteger(maxChunkChars) || maxChunkChars <= 0) {
14
- throw new EngineError("Text extractor requires a positive integer chunk size", {
15
- code: "ZVEC_GREP.ENGINE.EXTRACTORS.TEXT_INVALID_CHUNK_SIZE",
16
- context: `maxChunkChars=${maxChunkChars}`,
17
- });
18
- }
19
- if (!Number.isInteger(chunkOverlapChars) ||
20
- chunkOverlapChars < 0 ||
21
- chunkOverlapChars >= maxChunkChars) {
22
- throw new EngineError("Text extractor requires overlap to be smaller than chunk size", {
23
- code: "ZVEC_GREP.ENGINE.EXTRACTORS.TEXT_INVALID_CHUNK_OVERLAP",
24
- context: `maxChunkChars=${maxChunkChars} chunkOverlapChars=${chunkOverlapChars}`,
25
- });
26
- }
27
- this.maxChunkChars = maxChunkChars;
28
- this.chunkOverlapChars = chunkOverlapChars;
29
- }
30
- supports(source) {
31
- return source.kind === "text";
32
- }
33
- async extract(source) {
34
- if (source.kind !== "text") {
35
- throw new EngineError("Text extractor received a non-text source", {
36
- code: "ZVEC_GREP.ENGINE.EXTRACTORS.TEXT_UNSUPPORTED_SOURCE",
37
- context: `fileId=${source.file.id} sourceKind=${source.kind}`,
38
- });
39
- }
40
- validateSourceFile(source);
41
- const chunks = chunkText(source.text, this.maxChunkChars, this.chunkOverlapChars);
42
- return chunks.map((chunk, index) => ({
43
- id: makeEntityId(source.file.id, index),
44
- fileId: source.file.id,
45
- range: chunk.range,
46
- content: {
47
- kind: "text",
48
- text: chunk.text,
49
- },
50
- }));
51
- }
52
- }
53
- export class ImageExtractor {
54
- supports(source) {
55
- return source.kind === "image";
56
- }
57
- async extract(source) {
58
- if (source.kind !== "image") {
59
- throw new EngineError("Image extractor received a non-image source", {
60
- code: "ZVEC_GREP.ENGINE.EXTRACTORS.IMAGE_UNSUPPORTED_SOURCE",
61
- context: `fileId=${source.file.id} sourceKind=${source.kind}`,
62
- });
63
- }
64
- validateSourceFile(source);
65
- if (source.data.byteLength === 0) {
66
- throw new EngineError("Image extractor requires non-empty image data", {
67
- code: "ZVEC_GREP.ENGINE.EXTRACTORS.IMAGE_EMPTY_DATA",
68
- context: `fileId=${source.file.id} format=${source.format}`,
69
- });
70
- }
71
- return [
72
- {
73
- id: makeEntityId(source.file.id, 0),
74
- fileId: source.file.id,
75
- range: {
76
- kind: "file",
77
- },
78
- content: {
79
- kind: "image",
80
- data: source.data,
81
- format: source.format,
82
- },
83
- },
84
- ];
85
- }
86
- }
87
- const DEFAULT_EXTRACTORS = [
88
- new CodeExtractor(),
89
- new MarkdownExtractor(),
90
- new TextExtractor(),
91
- new ImageExtractor(),
92
- ];
93
- export class ExtractorRegistry {
94
- extractors;
95
- constructor(extractors = DEFAULT_EXTRACTORS) {
96
- if (extractors.length === 0) {
97
- throw new EngineError("Extractor registry requires at least one extractor", {
98
- code: "ZVEC_GREP.ENGINE.EXTRACTORS.EMPTY_REGISTRY",
99
- });
100
- }
101
- this.extractors = extractors;
102
- }
103
- resolve(source) {
104
- for (const extractor of this.extractors) {
105
- if (extractor.supports(source)) {
106
- return extractor;
107
- }
108
- }
109
- throw new EngineError("No extractor supports source", {
110
- code: "ZVEC_GREP.ENGINE.EXTRACTORS.UNSUPPORTED_SOURCE",
111
- context: `fileId=${source.file.id} sourceKind=${source.kind}`,
112
- });
113
- }
114
- extract(source) {
115
- return this.extractFirst(source);
116
- }
117
- async extractFirst(source) {
118
- let matched = false;
119
- let lastResult = [];
120
- for (const extractor of this.extractors) {
121
- if (!extractor.supports(source)) {
122
- continue;
123
- }
124
- matched = true;
125
- lastResult = await extractor.extract(source);
126
- if (lastResult.length > 0) {
127
- return lastResult;
128
- }
129
- }
130
- if (matched) {
131
- return lastResult;
132
- }
133
- throw new EngineError("No extractor supports source", {
134
- code: "ZVEC_GREP.ENGINE.EXTRACTORS.UNSUPPORTED_SOURCE",
135
- context: `fileId=${source.file.id} sourceKind=${source.kind}`,
136
- });
137
- }
138
- }
139
- export function extractFragments(source) {
140
- return new ExtractorRegistry().extract(source);
141
- }
142
- function chunkText(text, maxChars, overlapChars) {
143
- if (text.trim().length === 0) {
144
- return [];
145
- }
146
- const lines = text.split("\n");
147
- const lineOffsets = computeLineOffsets(lines);
148
- const chunks = [];
149
- let startIndex = 0;
150
- while (startIndex < lines.length) {
151
- if (lines[startIndex].length + 1 > maxChars) {
152
- const line = lines[startIndex];
153
- const lineNumber = startIndex + 1;
154
- let offset = 0;
155
- while (offset < line.length) {
156
- const remaining = line.length - offset;
157
- const sliceLength = remaining <= maxChars
158
- ? remaining
159
- : findLineCut(line.slice(offset), maxChars);
160
- const slice = line.slice(offset, offset + sliceLength);
161
- if (slice.trim().length > 0) {
162
- chunks.push({
163
- text: slice,
164
- range: {
165
- kind: "text",
166
- startLine: lineNumber,
167
- endLine: lineNumber,
168
- startOffset: lineOffsets[startIndex] + offset,
169
- endOffset: lineOffsets[startIndex] + offset + slice.length,
170
- },
171
- });
172
- }
173
- offset += sliceLength;
174
- }
175
- startIndex++;
176
- continue;
177
- }
178
- let usedChars = 0;
179
- let endIndex = startIndex;
180
- while (endIndex < lines.length) {
181
- const lineLength = lines[endIndex].length + 1;
182
- if (usedChars + lineLength > maxChars && endIndex > startIndex) {
183
- break;
184
- }
185
- usedChars += lineLength;
186
- endIndex++;
187
- }
188
- const chunkLines = lines.slice(startIndex, endIndex);
189
- const chunk = chunkLines.join("\n");
190
- if (chunk.trim().length > 0) {
191
- const endLineIndex = endIndex - 1;
192
- chunks.push({
193
- text: chunk,
194
- range: {
195
- kind: "text",
196
- startLine: startIndex + 1,
197
- endLine: endIndex,
198
- startOffset: lineOffsets[startIndex],
199
- endOffset: lineOffsets[endLineIndex] + lines[endLineIndex].length,
200
- },
201
- });
202
- }
203
- if (endIndex >= lines.length) {
204
- break;
205
- }
206
- startIndex = computeNextStartLine(lines, startIndex, endIndex, overlapChars);
207
- }
208
- return chunks;
209
- }
210
- function computeLineOffsets(lines) {
211
- const offsets = [];
212
- let offset = 0;
213
- for (const line of lines) {
214
- offsets.push(offset);
215
- offset += line.length + 1;
216
- }
217
- return offsets;
218
- }
219
- function computeNextStartLine(lines, startIndex, endIndex, overlapChars) {
220
- if (overlapChars === 0) {
221
- return endIndex;
222
- }
223
- let overlapLines = 0;
224
- let overlapCount = 0;
225
- for (let index = endIndex - 1; index >= startIndex && overlapCount < overlapChars; index--) {
226
- overlapCount += lines[index].length + 1;
227
- overlapLines++;
228
- }
229
- const nextStart = endIndex - overlapLines;
230
- return nextStart > startIndex ? nextStart : endIndex;
231
- }
232
- function findLineCut(line, maxChars) {
233
- if (line.length <= maxChars) {
234
- return line.length;
235
- }
236
- const minPosition = Math.floor(maxChars * 0.7);
237
- let bestPosition = -1;
238
- let bestScore = 0;
239
- for (let index = minPosition; index < maxChars; index++) {
240
- const character = line[index];
241
- let score = 0;
242
- if (character === "." || character === "!" || character === "?") {
243
- score = 4;
244
- }
245
- else if (character === "," || character === ";" || character === ":") {
246
- score = 3;
247
- }
248
- else if (character === " " || character === "\t") {
249
- score = 2;
250
- }
251
- else if (character === "-" || character === "/" || character === "\\") {
252
- score = 1;
253
- }
254
- if (score > 0 && score >= bestScore) {
255
- bestScore = score;
256
- bestPosition = index + 1;
257
- }
258
- }
259
- return bestPosition > 0 ? bestPosition : maxChars;
260
- }
261
- function validateSourceFile(source) {
262
- if (source.file.id.trim().length === 0) {
263
- throw new EngineError("Extractor source requires a non-empty file id", {
264
- code: "ZVEC_GREP.ENGINE.EXTRACTORS.EMPTY_FILE_ID",
265
- context: `sourceKind=${source.kind}`,
266
- });
267
- }
268
- if (source.file.absolutePath.trim().length === 0) {
269
- throw new EngineError("Extractor source requires a non-empty absolute file path", {
270
- code: "ZVEC_GREP.ENGINE.EXTRACTORS.EMPTY_ABSOLUTE_FILE_PATH",
271
- context: `fileId=${source.file.id} sourceKind=${source.kind}`,
272
- });
273
- }
274
- if (source.file.relativePath.trim().length === 0) {
275
- throw new EngineError("Extractor source requires a non-empty relative file path", {
276
- code: "ZVEC_GREP.ENGINE.EXTRACTORS.EMPTY_RELATIVE_FILE_PATH",
277
- context: `fileId=${source.file.id} sourceKind=${source.kind}`,
278
- });
279
- }
280
- }
1
+ export { extract } from "./runtime.js";
2
+ export { vectorContentForFragment } from "./vector-content.js";
281
3
  //# sourceMappingURL=index.js.map
@@ -1 +1 @@
1
- {"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/engine/extraction/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,WAAW,EAAE,MAAM,oBAAoB,CAAC;AAOjD,OAAO,EAAE,YAAY,EAAE,MAAM,UAAU,CAAC;AACxC,OAAO,EAAE,aAAa,EAAE,MAAM,qBAAqB,CAAC;AACpD,OAAO,EAAE,iBAAiB,EAAE,MAAM,yBAAyB,CAAC;AAgC5D,MAAM,wBAAwB,GAAG,IAAI,CAAC;AAEtC,MAAM,gCAAgC,GAAG,GAAG,CAAC;AAE7C,MAAM,OAAO,aAAa;IACP,aAAa,CAAS;IACtB,iBAAiB,CAAS;IAE3C,YAAY,UAAgC,EAAE;QAC5C,MAAM,aAAa,GAAG,OAAO,CAAC,aAAa,IAAI,wBAAwB,CAAC;QACxE,MAAM,iBAAiB,GACrB,OAAO,CAAC,iBAAiB,IAAI,gCAAgC,CAAC;QAEhE,IAAI,CAAC,MAAM,CAAC,SAAS,CAAC,aAAa,CAAC,IAAI,aAAa,IAAI,CAAC,EAAE,CAAC;YAC3D,MAAM,IAAI,WAAW,CACnB,uDAAuD,EACvD;gBACE,IAAI,EAAE,qDAAqD;gBAC3D,OAAO,EAAE,iBAAiB,aAAa,EAAE;aAC1C,CACF,CAAC;QACJ,CAAC;QAED,IACE,CAAC,MAAM,CAAC,SAAS,CAAC,iBAAiB,CAAC;YACpC,iBAAiB,GAAG,CAAC;YACrB,iBAAiB,IAAI,aAAa,EAClC,CAAC;YACD,MAAM,IAAI,WAAW,CACnB,+DAA+D,EAC/D;gBACE,IAAI,EAAE,wDAAwD;gBAC9D,OAAO,EAAE,iBAAiB,aAAa,sBAAsB,iBAAiB,EAAE;aACjF,CACF,CAAC;QACJ,CAAC;QAED,IAAI,CAAC,aAAa,GAAG,aAAa,CAAC;QACnC,IAAI,CAAC,iBAAiB,GAAG,iBAAiB,CAAC;IAC7C,CAAC;IAED,QAAQ,CAAC,MAAc;QACrB,OAAO,MAAM,CAAC,IAAI,KAAK,MAAM,CAAC;IAChC,CAAC;IAED,KAAK,CAAC,OAAO,CAAC,MAAc;QAC1B,IAAI,MAAM,CAAC,IAAI,KAAK,MAAM,EAAE,CAAC;YAC3B,MAAM,IAAI,WAAW,CAAC,2CAA2C,EAAE;gBACjE,IAAI,EAAE,qDAAqD;gBAC3D,OAAO,EAAE,UAAU,MAAM,CAAC,IAAI,CAAC,EAAE,eAAe,MAAM,CAAC,IAAI,EAAE;aAC9D,CAAC,CAAC;QACL,CAAC;QAED,kBAAkB,CAAC,MAAM,CAAC,CAAC;QAE3B,MAAM,MAAM,GAAG,SAAS,CACtB,MAAM,CAAC,IAAI,EACX,IAAI,CAAC,aAAa,EAClB,IAAI,CAAC,iBAAiB,CACvB,CAAC;QAEF,OAAO,MAAM,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,KAAK,EAAkB,EAAE,CAAC,CAAC;YACnD,EAAE,EAAE,YAAY,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,EAAE,KAAK,CAAC;YACvC,MAAM,EAAE,MAAM,CAAC,IAAI,CAAC,EAAE;YACtB,KAAK,EAAE,KAAK,CAAC,KAAK;YAClB,OAAO,EAAE;gBACP,IAAI,EAAE,MAAM;gBACZ,IAAI,EAAE,KAAK,CAAC,IAAI;aACjB;SACF,CAAC,CAAC,CAAC;IACN,CAAC;CACF;AAED,MAAM,OAAO,cAAc;IACzB,QAAQ,CAAC,MAAc;QACrB,OAAO,MAAM,CAAC,IAAI,KAAK,OAAO,CAAC;IACjC,CAAC;IAED,KAAK,CAAC,OAAO,CAAC,MAAc;QAC1B,IAAI,MAAM,CAAC,IAAI,KAAK,OAAO,EAAE,CAAC;YAC5B,MAAM,IAAI,WAAW,CAAC,6CAA6C,EAAE;gBACnE,IAAI,EAAE,sDAAsD;gBAC5D,OAAO,EAAE,UAAU,MAAM,CAAC,IAAI,CAAC,EAAE,eAAe,MAAM,CAAC,IAAI,EAAE;aAC9D,CAAC,CAAC;QACL,CAAC;QAED,kBAAkB,CAAC,MAAM,CAAC,CAAC;QAE3B,IAAI,MAAM,CAAC,IAAI,CAAC,UAAU,KAAK,CAAC,EAAE,CAAC;YACjC,MAAM,IAAI,WAAW,CAAC,+CAA+C,EAAE;gBACrE,IAAI,EAAE,8CAA8C;gBACpD,OAAO,EAAE,UAAU,MAAM,CAAC,IAAI,CAAC,EAAE,WAAW,MAAM,CAAC,MAAM,EAAE;aAC5D,CAAC,CAAC;QACL,CAAC;QAED,OAAO;YACL;gBACE,EAAE,EAAE,YAAY,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,EAAE,CAAC,CAAC;gBACnC,MAAM,EAAE,MAAM,CAAC,IAAI,CAAC,EAAE;gBACtB,KAAK,EAAE;oBACL,IAAI,EAAE,MAAM;iBACb;gBACD,OAAO,EAAE;oBACP,IAAI,EAAE,OAAO;oBACb,IAAI,EAAE,MAAM,CAAC,IAAI;oBACjB,MAAM,EAAE,MAAM,CAAC,MAAM;iBACtB;aACF;SACF,CAAC;IACJ,CAAC;CACF;AAED,MAAM,kBAAkB,GAAyB;IAC/C,IAAI,aAAa,EAAE;IACnB,IAAI,iBAAiB,EAAE;IACvB,IAAI,aAAa,EAAE;IACnB,IAAI,cAAc,EAAE;CACrB,CAAC;AAEF,MAAM,OAAO,iBAAiB;IACX,UAAU,CAAuB;IAElD,YAAY,aAAmC,kBAAkB;QAC/D,IAAI,UAAU,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YAC5B,MAAM,IAAI,WAAW,CACnB,oDAAoD,EACpD;gBACE,IAAI,EAAE,4CAA4C;aACnD,CACF,CAAC;QACJ,CAAC;QAED,IAAI,CAAC,UAAU,GAAG,UAAU,CAAC;IAC/B,CAAC;IAED,OAAO,CAAC,MAAc;QACpB,KAAK,MAAM,SAAS,IAAI,IAAI,CAAC,UAAU,EAAE,CAAC;YACxC,IAAI,SAAS,CAAC,QAAQ,CAAC,MAAM,CAAC,EAAE,CAAC;gBAC/B,OAAO,SAAS,CAAC;YACnB,CAAC;QACH,CAAC;QAED,MAAM,IAAI,WAAW,CAAC,8BAA8B,EAAE;YACpD,IAAI,EAAE,gDAAgD;YACtD,OAAO,EAAE,UAAU,MAAM,CAAC,IAAI,CAAC,EAAE,eAAe,MAAM,CAAC,IAAI,EAAE;SAC9D,CAAC,CAAC;IACL,CAAC;IAED,OAAO,CAAC,MAAc;QACpB,OAAO,IAAI,CAAC,YAAY,CAAC,MAAM,CAAC,CAAC;IACnC,CAAC;IAEO,KAAK,CAAC,YAAY,CAAC,MAAc;QACvC,IAAI,OAAO,GAAG,KAAK,CAAC;QACpB,IAAI,UAAU,GAAqB,EAAE,CAAC;QAEtC,KAAK,MAAM,SAAS,IAAI,IAAI,CAAC,UAAU,EAAE,CAAC;YACxC,IAAI,CAAC,SAAS,CAAC,QAAQ,CAAC,MAAM,CAAC,EAAE,CAAC;gBAChC,SAAS;YACX,CAAC;YAED,OAAO,GAAG,IAAI,CAAC;YACf,UAAU,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC;YAE7C,IAAI,UAAU,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBAC1B,OAAO,UAAU,CAAC;YACpB,CAAC;QACH,CAAC;QAED,IAAI,OAAO,EAAE,CAAC;YACZ,OAAO,UAAU,CAAC;QACpB,CAAC;QAED,MAAM,IAAI,WAAW,CAAC,8BAA8B,EAAE;YACpD,IAAI,EAAE,gDAAgD;YACtD,OAAO,EAAE,UAAU,MAAM,CAAC,IAAI,CAAC,EAAE,eAAe,MAAM,CAAC,IAAI,EAAE;SAC9D,CAAC,CAAC;IACL,CAAC;CACF;AAED,MAAM,UAAU,gBAAgB,CAAC,MAAc;IAC7C,OAAO,IAAI,iBAAiB,EAAE,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC;AACjD,CAAC;AAOD,SAAS,SAAS,CAChB,IAAY,EACZ,QAAgB,EAChB,YAAoB;IAEpB,IAAI,IAAI,CAAC,IAAI,EAAE,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAC7B,OAAO,EAAE,CAAC;IACZ,CAAC;IAED,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;IAC/B,MAAM,WAAW,GAAG,kBAAkB,CAAC,KAAK,CAAC,CAAC;IAC9C,MAAM,MAAM,GAAgB,EAAE,CAAC;IAE/B,IAAI,UAAU,GAAG,CAAC,CAAC;IAEnB,OAAO,UAAU,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC;QACjC,IAAI,KAAK,CAAC,UAAU,CAAC,CAAC,MAAM,GAAG,CAAC,GAAG,QAAQ,EAAE,CAAC;YAC5C,MAAM,IAAI,GAAG,KAAK,CAAC,UAAU,CAAC,CAAC;YAC/B,MAAM,UAAU,GAAG,UAAU,GAAG,CAAC,CAAC;YAClC,IAAI,MAAM,GAAG,CAAC,CAAC;YAEf,OAAO,MAAM,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC;gBAC5B,MAAM,SAAS,GAAG,IAAI,CAAC,MAAM,GAAG,MAAM,CAAC;gBACvC,MAAM,WAAW,GACf,SAAS,IAAI,QAAQ;oBACnB,CAAC,CAAC,SAAS;oBACX,CAAC,CAAC,WAAW,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,EAAE,QAAQ,CAAC,CAAC;gBAChD,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,MAAM,GAAG,WAAW,CAAC,CAAC;gBAEvD,IAAI,KAAK,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;oBAC5B,MAAM,CAAC,IAAI,CAAC;wBACV,IAAI,EAAE,KAAK;wBACX,KAAK,EAAE;4BACL,IAAI,EAAE,MAAM;4BACZ,SAAS,EAAE,UAAU;4BACrB,OAAO,EAAE,UAAU;4BACnB,WAAW,EAAE,WAAW,CAAC,UAAU,CAAC,GAAG,MAAM;4BAC7C,SAAS,EAAE,WAAW,CAAC,UAAU,CAAC,GAAG,MAAM,GAAG,KAAK,CAAC,MAAM;yBAC3D;qBACF,CAAC,CAAC;gBACL,CAAC;gBAED,MAAM,IAAI,WAAW,CAAC;YACxB,CAAC;YAED,UAAU,EAAE,CAAC;YACb,SAAS;QACX,CAAC;QAED,IAAI,SAAS,GAAG,CAAC,CAAC;QAClB,IAAI,QAAQ,GAAG,UAAU,CAAC;QAE1B,OAAO,QAAQ,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC;YAC/B,MAAM,UAAU,GAAG,KAAK,CAAC,QAAQ,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC;YAE9C,IAAI,SAAS,GAAG,UAAU,GAAG,QAAQ,IAAI,QAAQ,GAAG,UAAU,EAAE,CAAC;gBAC/D,MAAM;YACR,CAAC;YAED,SAAS,IAAI,UAAU,CAAC;YACxB,QAAQ,EAAE,CAAC;QACb,CAAC;QAED,MAAM,UAAU,GAAG,KAAK,CAAC,KAAK,CAAC,UAAU,EAAE,QAAQ,CAAC,CAAC;QACrD,MAAM,KAAK,GAAG,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QAEpC,IAAI,KAAK,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YAC5B,MAAM,YAAY,GAAG,QAAQ,GAAG,CAAC,CAAC;YAElC,MAAM,CAAC,IAAI,CAAC;gBACV,IAAI,EAAE,KAAK;gBACX,KAAK,EAAE;oBACL,IAAI,EAAE,MAAM;oBACZ,SAAS,EAAE,UAAU,GAAG,CAAC;oBACzB,OAAO,EAAE,QAAQ;oBACjB,WAAW,EAAE,WAAW,CAAC,UAAU,CAAC;oBACpC,SAAS,EAAE,WAAW,CAAC,YAAY,CAAC,GAAG,KAAK,CAAC,YAAY,CAAC,CAAC,MAAM;iBAClE;aACF,CAAC,CAAC;QACL,CAAC;QAED,IAAI,QAAQ,IAAI,KAAK,CAAC,MAAM,EAAE,CAAC;YAC7B,MAAM;QACR,CAAC;QAED,UAAU,GAAG,oBAAoB,CAC/B,KAAK,EACL,UAAU,EACV,QAAQ,EACR,YAAY,CACb,CAAC;IACJ,CAAC;IAED,OAAO,MAAM,CAAC;AAChB,CAAC;AAED,SAAS,kBAAkB,CAAC,KAAwB;IAClD,MAAM,OAAO,GAAa,EAAE,CAAC;IAC7B,IAAI,MAAM,GAAG,CAAC,CAAC;IAEf,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QACzB,OAAO,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;QACrB,MAAM,IAAI,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC;IAC5B,CAAC;IAED,OAAO,OAAO,CAAC;AACjB,CAAC;AAED,SAAS,oBAAoB,CAC3B,KAAwB,EACxB,UAAkB,EAClB,QAAgB,EAChB,YAAoB;IAEpB,IAAI,YAAY,KAAK,CAAC,EAAE,CAAC;QACvB,OAAO,QAAQ,CAAC;IAClB,CAAC;IAED,IAAI,YAAY,GAAG,CAAC,CAAC;IACrB,IAAI,YAAY,GAAG,CAAC,CAAC;IAErB,KACE,IAAI,KAAK,GAAG,QAAQ,GAAG,CAAC,EACxB,KAAK,IAAI,UAAU,IAAI,YAAY,GAAG,YAAY,EAClD,KAAK,EAAE,EACP,CAAC;QACD,YAAY,IAAI,KAAK,CAAC,KAAK,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC;QACxC,YAAY,EAAE,CAAC;IACjB,CAAC;IAED,MAAM,SAAS,GAAG,QAAQ,GAAG,YAAY,CAAC;IAE1C,OAAO,SAAS,GAAG,UAAU,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,QAAQ,CAAC;AACvD,CAAC;AAED,SAAS,WAAW,CAAC,IAAY,EAAE,QAAgB;IACjD,IAAI,IAAI,CAAC,MAAM,IAAI,QAAQ,EAAE,CAAC;QAC5B,OAAO,IAAI,CAAC,MAAM,CAAC;IACrB,CAAC;IAED,MAAM,WAAW,GAAG,IAAI,CAAC,KAAK,CAAC,QAAQ,GAAG,GAAG,CAAC,CAAC;IAC/C,IAAI,YAAY,GAAG,CAAC,CAAC,CAAC;IACtB,IAAI,SAAS,GAAG,CAAC,CAAC;IAElB,KAAK,IAAI,KAAK,GAAG,WAAW,EAAE,KAAK,GAAG,QAAQ,EAAE,KAAK,EAAE,EAAE,CAAC;QACxD,MAAM,SAAS,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC;QAC9B,IAAI,KAAK,GAAG,CAAC,CAAC;QAEd,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,GAAG,EAAE,CAAC;YAChE,KAAK,GAAG,CAAC,CAAC;QACZ,CAAC;aAAM,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,GAAG,EAAE,CAAC;YACvE,KAAK,GAAG,CAAC,CAAC;QACZ,CAAC;aAAM,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,IAAI,EAAE,CAAC;YACnD,KAAK,GAAG,CAAC,CAAC;QACZ,CAAC;aAAM,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,IAAI,EAAE,CAAC;YACxE,KAAK,GAAG,CAAC,CAAC;QACZ,CAAC;QAED,IAAI,KAAK,GAAG,CAAC,IAAI,KAAK,IAAI,SAAS,EAAE,CAAC;YACpC,SAAS,GAAG,KAAK,CAAC;YAClB,YAAY,GAAG,KAAK,GAAG,CAAC,CAAC;QAC3B,CAAC;IACH,CAAC;IAED,OAAO,YAAY,GAAG,CAAC,CAAC,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,QAAQ,CAAC;AACpD,CAAC;AAED,SAAS,kBAAkB,CAAC,MAAc;IACxC,IAAI,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC,IAAI,EAAE,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACvC,MAAM,IAAI,WAAW,CAAC,+CAA+C,EAAE;YACrE,IAAI,EAAE,2CAA2C;YACjD,OAAO,EAAE,cAAc,MAAM,CAAC,IAAI,EAAE;SACrC,CAAC,CAAC;IACL,CAAC;IAED,IAAI,MAAM,CAAC,IAAI,CAAC,YAAY,CAAC,IAAI,EAAE,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACjD,MAAM,IAAI,WAAW,CACnB,0DAA0D,EAC1D;YACE,IAAI,EAAE,sDAAsD;YAC5D,OAAO,EAAE,UAAU,MAAM,CAAC,IAAI,CAAC,EAAE,eAAe,MAAM,CAAC,IAAI,EAAE;SAC9D,CACF,CAAC;IACJ,CAAC;IAED,IAAI,MAAM,CAAC,IAAI,CAAC,YAAY,CAAC,IAAI,EAAE,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACjD,MAAM,IAAI,WAAW,CACnB,0DAA0D,EAC1D;YACE,IAAI,EAAE,sDAAsD;YAC5D,OAAO,EAAE,UAAU,MAAM,CAAC,IAAI,CAAC,EAAE,eAAe,MAAM,CAAC,IAAI,EAAE;SAC9D,CACF,CAAC;IACJ,CAAC;AACH,CAAC"}
1
+ {"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/engine/extraction/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,OAAO,EAAE,MAAM,cAAc,CAAC;AAGvC,OAAO,EAAE,wBAAwB,EAAE,MAAM,qBAAqB,CAAC"}
@@ -1,13 +1,7 @@
1
1
  import type { EntityFragment } from "../../types.js";
2
- import type { Extractor, Source } from "../index.js";
3
- export type MarkdownExtractorOptions = {
4
- maxChunkChars?: number;
5
- chunkOverlapChars?: number;
6
- };
7
- export declare class MarkdownExtractor implements Extractor {
8
- private readonly maxChunkChars;
9
- private readonly chunkOverlapChars;
10
- constructor(options?: MarkdownExtractorOptions);
11
- supports(source: Source): boolean;
12
- extract(source: Source): Promise<EntityFragment[]>;
2
+ import { type Source } from "../source.js";
3
+ import type { ChunkOptions } from "../types.js";
4
+ export declare class MarkdownExtractor {
5
+ extract(source: Source, options?: ChunkOptions): Promise<EntityFragment[]>;
6
+ private fallback;
13
7
  }
@@ -1,25 +1,21 @@
1
+ import { EngineError } from "../../errors.js";
1
2
  import { makeEntityId } from "../ids.js";
3
+ import { validateSourceFile } from "../source.js";
4
+ import { extractPlainTextFragments } from "../text/extractor.js";
5
+ import { chunkOptionsForMetadata, fitTextToChars } from "../vector-content.js";
2
6
  const DEFAULT_MARKDOWN_CHUNK_CHARS = 3600;
3
7
  const DEFAULT_MARKDOWN_CHUNK_OVERLAP_CHARS = 540;
4
8
  export class MarkdownExtractor {
5
- maxChunkChars;
6
- chunkOverlapChars;
7
- constructor(options = {}) {
8
- this.maxChunkChars = options.maxChunkChars ?? DEFAULT_MARKDOWN_CHUNK_CHARS;
9
- this.chunkOverlapChars =
10
- options.chunkOverlapChars ?? DEFAULT_MARKDOWN_CHUNK_OVERLAP_CHARS;
11
- }
12
- supports(source) {
13
- return source.kind === "text" && source.file.format === "markdown";
14
- }
15
- async extract(source) {
16
- if (!this.supports(source) || source.kind !== "text") {
9
+ async extract(source, options = {}) {
10
+ if (source.kind !== "text" || source.file.format !== "markdown") {
17
11
  return [];
18
12
  }
13
+ validateSourceFile(source);
14
+ const chunkOptions = resolveMarkdownChunkOptions(options);
19
15
  const lines = source.text.split("\n");
20
16
  const headings = scanHeadings(lines);
21
17
  if (headings.length === 0) {
22
- return [];
18
+ return this.fallback(source, chunkOptions);
23
19
  }
24
20
  const lineOffsets = computeLineOffsets(lines);
25
21
  const fenceLines = computeFenceLines(lines);
@@ -27,13 +23,14 @@ export class MarkdownExtractor {
27
23
  const fragments = [];
28
24
  for (const section of sections) {
29
25
  const metadata = markdownMetadata(section);
26
+ const contentChunkOptions = chunkOptionsForMetadata(chunkOptions, metadata);
30
27
  const windows = splitMarkdownSection({
31
28
  lines,
32
29
  lineOffsets,
33
30
  fenceLines,
34
31
  section,
35
- maxChars: this.maxChunkChars,
36
- overlapChars: this.chunkOverlapChars,
32
+ maxChars: contentChunkOptions.maxChunkChars,
33
+ overlapChars: contentChunkOptions.chunkOverlapChars,
37
34
  });
38
35
  if (windows.length > 1) {
39
36
  const id = makeEntityId(source.file.id, fragments.length);
@@ -44,7 +41,7 @@ export class MarkdownExtractor {
44
41
  range: linesToWindow(lines, lineOffsets, section.startIndex, section.endIndex).range,
45
42
  content: {
46
43
  kind: "text",
47
- text: markdownOutline(metadata),
44
+ text: fitTextToChars(markdownOutline(metadata), contentChunkOptions.maxChunkChars),
48
45
  },
49
46
  metadata,
50
47
  });
@@ -66,8 +63,32 @@ export class MarkdownExtractor {
66
63
  });
67
64
  }
68
65
  }
69
- return fragments;
66
+ return fragments.length > 0
67
+ ? fragments
68
+ : this.fallback(source, chunkOptions);
69
+ }
70
+ fallback(source, options) {
71
+ return extractPlainTextFragments(source, options.maxChunkChars, options.chunkOverlapChars);
72
+ }
73
+ }
74
+ function resolveMarkdownChunkOptions(options) {
75
+ const maxChunkChars = options.maxChunkChars ?? DEFAULT_MARKDOWN_CHUNK_CHARS;
76
+ const chunkOverlapChars = options.chunkOverlapChars ?? DEFAULT_MARKDOWN_CHUNK_OVERLAP_CHARS;
77
+ if (!Number.isInteger(maxChunkChars) || maxChunkChars <= 0) {
78
+ throw new EngineError("Markdown extractor requires a positive integer chunk size", {
79
+ code: "ZVEC_GREP.ENGINE.EXTRACTORS.MARKDOWN_INVALID_CHUNK_SIZE",
80
+ context: `maxChunkChars=${maxChunkChars}`,
81
+ });
82
+ }
83
+ if (!Number.isInteger(chunkOverlapChars) ||
84
+ chunkOverlapChars < 0 ||
85
+ chunkOverlapChars >= maxChunkChars) {
86
+ throw new EngineError("Markdown extractor requires overlap to be smaller than chunk size", {
87
+ code: "ZVEC_GREP.ENGINE.EXTRACTORS.MARKDOWN_INVALID_CHUNK_OVERLAP",
88
+ context: `maxChunkChars=${maxChunkChars} chunkOverlapChars=${chunkOverlapChars}`,
89
+ });
70
90
  }
91
+ return { maxChunkChars, chunkOverlapChars };
71
92
  }
72
93
  function markdownWindowToFragment(source, metadata, window, index, group) {
73
94
  return {
@@ -1 +1 @@
1
- {"version":3,"file":"extractor.js","sourceRoot":"","sources":["../../../../src/engine/extraction/markdown/extractor.ts"],"names":[],"mappings":"AAKA,OAAO,EAAE,YAAY,EAAE,MAAM,WAAW,CAAC;AAQzC,MAAM,4BAA4B,GAAG,IAAI,CAAC;AAC1C,MAAM,oCAAoC,GAAG,GAAG,CAAC;AAoBjD,MAAM,OAAO,iBAAiB;IACX,aAAa,CAAS;IACtB,iBAAiB,CAAS;IAE3C,YAAY,UAAoC,EAAE;QAChD,IAAI,CAAC,aAAa,GAAG,OAAO,CAAC,aAAa,IAAI,4BAA4B,CAAC;QAC3E,IAAI,CAAC,iBAAiB;YACpB,OAAO,CAAC,iBAAiB,IAAI,oCAAoC,CAAC;IACtE,CAAC;IAED,QAAQ,CAAC,MAAc;QACrB,OAAO,MAAM,CAAC,IAAI,KAAK,MAAM,IAAI,MAAM,CAAC,IAAI,CAAC,MAAM,KAAK,UAAU,CAAC;IACrE,CAAC;IAED,KAAK,CAAC,OAAO,CAAC,MAAc;QAC1B,IAAI,CAAC,IAAI,CAAC,QAAQ,CAAC,MAAM,CAAC,IAAI,MAAM,CAAC,IAAI,KAAK,MAAM,EAAE,CAAC;YACrD,OAAO,EAAE,CAAC;QACZ,CAAC;QAED,MAAM,KAAK,GAAG,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QACtC,MAAM,QAAQ,GAAG,YAAY,CAAC,KAAK,CAAC,CAAC;QACrC,IAAI,QAAQ,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YAC1B,OAAO,EAAE,CAAC;QACZ,CAAC;QAED,MAAM,WAAW,GAAG,kBAAkB,CAAC,KAAK,CAAC,CAAC;QAC9C,MAAM,UAAU,GAAG,iBAAiB,CAAC,KAAK,CAAC,CAAC;QAC5C,MAAM,QAAQ,GAAG,aAAa,CAAC,QAAQ,EAAE,KAAK,CAAC,CAAC;QAChD,MAAM,SAAS,GAAqB,EAAE,CAAC;QAEvC,KAAK,MAAM,OAAO,IAAI,QAAQ,EAAE,CAAC;YAC/B,MAAM,QAAQ,GAAG,gBAAgB,CAAC,OAAO,CAAC,CAAC;YAC3C,MAAM,OAAO,GAAG,oBAAoB,CAAC;gBACnC,KAAK;gBACL,WAAW;gBACX,UAAU;gBACV,OAAO;gBACP,QAAQ,EAAE,IAAI,CAAC,aAAa;gBAC5B,YAAY,EAAE,IAAI,CAAC,iBAAiB;aACrC,CAAC,CAAC;YAEH,IAAI,OAAO,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBACvB,MAAM,EAAE,GAAG,YAAY,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,EAAE,SAAS,CAAC,MAAM,CAAC,CAAC;gBAC1D,SAAS,CAAC,IAAI,CAAC;oBACb,EAAE;oBACF,KAAK,EAAE,EAAE;oBACT,MAAM,EAAE,MAAM,CAAC,IAAI,CAAC,EAAE;oBACtB,KAAK,EAAE,aAAa,CAClB,KAAK,EACL,WAAW,EACX,OAAO,CAAC,UAAU,EAClB,OAAO,CAAC,QAAQ,CACjB,CAAC,KAAK;oBACP,OAAO,EAAE;wBACP,IAAI,EAAE,MAAM;wBACZ,IAAI,EAAE,eAAe,CAAC,QAAQ,CAAC;qBAChC;oBACD,QAAQ;iBACT,CAAC,CAAC;gBAEH,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;oBAC7B,SAAS,CAAC,IAAI,CACZ,wBAAwB,CACtB,MAAM,EACN,QAAQ,EACR,MAAM,EACN,SAAS,CAAC,MAAM,EAChB,EAAE,CACH,CACF,CAAC;gBACJ,CAAC;gBAED,SAAS;YACX,CAAC;YAED,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;gBAC7B,SAAS,CAAC,IAAI,CAAC;oBACb,EAAE,EAAE,YAAY,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,EAAE,SAAS,CAAC,MAAM,CAAC;oBAClD,MAAM,EAAE,MAAM,CAAC,IAAI,CAAC,EAAE;oBACtB,KAAK,EAAE,MAAM,CAAC,KAAK;oBACnB,OAAO,EAAE;wBACP,IAAI,EAAE,MAAM;wBACZ,IAAI,EAAE,MAAM,CAAC,IAAI;qBAClB;oBACD,QAAQ;iBACT,CAAC,CAAC;YACL,CAAC;QACH,CAAC;QAED,OAAO,SAAS,CAAC;IACnB,CAAC;CACF;AAED,SAAS,wBAAwB,CAC/B,MAAkB,EAClB,QAAgC,EAChC,MAAsB,EACtB,KAAa,EACb,KAAa;IAEb,OAAO;QACL,EAAE,EAAE,YAAY,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,EAAE,KAAK,CAAC;QACvC,KAAK;QACL,MAAM,EAAE,MAAM,CAAC,IAAI,CAAC,EAAE;QACtB,KAAK,EAAE,MAAM,CAAC,KAAK;QACnB,OAAO,EAAE;YACP,IAAI,EAAE,MAAM;YACZ,IAAI,EAAE,MAAM,CAAC,IAAI;SAClB;QACD,QAAQ;KACT,CAAC;AACJ,CAAC;AAED,SAAS,eAAe,CAAC,QAAgC;IACvD,OAAO,QAAQ,CAAC,OAAO,IAAI,kBAAkB,CAAC;AAChD,CAAC;AAED,SAAS,YAAY,CAAC,KAAwB;IAC5C,MAAM,QAAQ,GAAc,EAAE,CAAC;IAC/B,IAAI,KAAK,GAAyB,IAAI,CAAC;IAEvC,KAAK,IAAI,KAAK,GAAG,CAAC,EAAE,KAAK,GAAG,KAAK,CAAC,MAAM,EAAE,KAAK,EAAE,EAAE,CAAC;QAClD,MAAM,IAAI,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC;QAC1B,MAAM,OAAO,GAAG,IAAI,CAAC,SAAS,EAAE,CAAC;QAEjC,IAAI,KAAK,EAAE,CAAC;YACV,IAAI,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,EAAE,CAAC;gBAC9B,KAAK,GAAG,IAAI,CAAC;YACf,CAAC;YACD,SAAS;QACX,CAAC;QAED,IAAI,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,EAAE,CAAC;YAC9B,KAAK,GAAG,KAAK,CAAC;YACd,SAAS;QACX,CAAC;QAED,IAAI,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,EAAE,CAAC;YAC9B,KAAK,GAAG,KAAK,CAAC;YACd,SAAS;QACX,CAAC;QAED,MAAM,GAAG,GAAG,IAAI,CAAC,KAAK,CAAC,4BAA4B,CAAC,CAAC;QACrD,IAAI,GAAG,EAAE,CAAC;YACR,QAAQ,CAAC,IAAI,CAAC;gBACZ,KAAK,EAAE,GAAG,CAAC,CAAC,CAAC,CAAC,MAAM;gBACpB,IAAI,EAAE,GAAG,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE;gBACnB,SAAS,EAAE,KAAK;aACjB,CAAC,CAAC;YACH,SAAS;QACX,CAAC;QAED,MAAM,IAAI,GAAG,KAAK,CAAC,KAAK,GAAG,CAAC,CAAC,EAAE,IAAI,EAAE,CAAC;QACtC,IAAI,IAAI,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,IAAI,IAAI,IAAI,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;YAChE,QAAQ,CAAC,IAAI,CAAC;gBACZ,KAAK,EAAE,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;gBACnC,IAAI,EAAE,IAAI,CAAC,IAAI,EAAE;gBACjB,SAAS,EAAE,KAAK;aACjB,CAAC,CAAC;YACH,KAAK,EAAE,CAAC;QACV,CAAC;IACH,CAAC;IAED,OAAO,QAAQ,CAAC;AAClB,CAAC;AAED,SAAS,aAAa,CACpB,QAA4B,EAC5B,KAAwB;IAExB,MAAM,KAAK,GAAc,EAAE,CAAC;IAC5B,MAAM,QAAQ,GAAc,EAAE,CAAC;IAC/B,MAAM,YAAY,GAAG,QAAQ,CAAC,CAAC,CAAC,CAAC;IAEjC,IACE,YAAY,CAAC,SAAS,GAAG,CAAC;QAC1B,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,YAAY,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,EACnE,CAAC;QACD,QAAQ,CAAC,IAAI,CAAC;YACZ,OAAO,EAAE,IAAI;YACb,UAAU,EAAE,CAAC;YACb,QAAQ,EAAE,YAAY,CAAC,SAAS,GAAG,CAAC;YACpC,UAAU,EAAE,EAAE;SACf,CAAC,CAAC;IACL,CAAC;IAED,KAAK,IAAI,KAAK,GAAG,CAAC,EAAE,KAAK,GAAG,QAAQ,CAAC,MAAM,EAAE,KAAK,EAAE,EAAE,CAAC;QACrD,MAAM,OAAO,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAC;QAEhC,OAAO,KAAK,CAAC,MAAM,GAAG,CAAC,IAAI,KAAK,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,KAAK,IAAI,OAAO,CAAC,KAAK,EAAE,CAAC;YAC1E,KAAK,CAAC,GAAG,EAAE,CAAC;QACd,CAAC;QAED,QAAQ,CAAC,IAAI,CAAC;YACZ,OAAO;YACP,UAAU,EAAE,OAAO,CAAC,SAAS;YAC7B,QAAQ,EACN,KAAK,GAAG,CAAC,GAAG,QAAQ,CAAC,MAAM;gBACzB,CAAC,CAAC,QAAQ,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC,SAAS,GAAG,CAAC;gBACnC,CAAC,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC;YACtB,UAAU,EAAE,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,IAAI,CAAC;SAC3C,CAAC,CAAC;QACH,KAAK,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;IACtB,CAAC;IAED,OAAO,QAAQ,CAAC;AAClB,CAAC;AAED,SAAS,oBAAoB,CAAC,KAO7B;IACC,MAAM,OAAO,GAAqB,EAAE,CAAC;IACrC,IAAI,UAAU,GAAG,KAAK,CAAC,OAAO,CAAC,UAAU,CAAC;IAE1C,OAAO,UAAU,IAAI,KAAK,CAAC,OAAO,CAAC,QAAQ,EAAE,CAAC;QAC5C,IAAI,KAAK,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC,MAAM,GAAG,CAAC,GAAG,KAAK,CAAC,QAAQ,EAAE,CAAC;YACxD,OAAO,CAAC,IAAI,CACV,GAAG,aAAa,CACd,KAAK,CAAC,KAAK,CAAC,UAAU,CAAC,EACvB,UAAU,EACV,KAAK,CAAC,WAAW,CAAC,UAAU,CAAC,EAC7B,KAAK,CAAC,QAAQ,CACf,CACF,CAAC;YACF,UAAU,EAAE,CAAC;YACb,SAAS;QACX,CAAC;QAED,IAAI,QAAQ,GAAG,UAAU,CAAC;QAC1B,IAAI,SAAS,GAAG,CAAC,CAAC;QAElB,OAAO,QAAQ,IAAI,KAAK,CAAC,OAAO,CAAC,QAAQ,EAAE,CAAC;YAC1C,MAAM,UAAU,GAAG,KAAK,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC;YACpD,IAAI,SAAS,GAAG,UAAU,GAAG,KAAK,CAAC,QAAQ,IAAI,QAAQ,GAAG,UAAU,EAAE,CAAC;gBACrE,MAAM;YACR,CAAC;YACD,SAAS,IAAI,UAAU,CAAC;YACxB,QAAQ,EAAE,CAAC;QACb,CAAC;QAED,IAAI,QAAQ,IAAI,KAAK,CAAC,OAAO,CAAC,QAAQ,IAAI,QAAQ,GAAG,UAAU,GAAG,CAAC,EAAE,CAAC;YACpE,QAAQ,GAAG,mBAAmB,CAC5B,KAAK,CAAC,KAAK,EACX,KAAK,CAAC,UAAU,EAChB,UAAU,EACV,QAAQ,CACT,CAAC;QACJ,CAAC;QAED,OAAO,CAAC,IAAI,CACV,aAAa,CAAC,KAAK,CAAC,KAAK,EAAE,KAAK,CAAC,WAAW,EAAE,UAAU,EAAE,QAAQ,GAAG,CAAC,CAAC,CACxE,CAAC;QAEF,IAAI,QAAQ,GAAG,KAAK,CAAC,OAAO,CAAC,QAAQ,EAAE,CAAC;YACtC,MAAM;QACR,CAAC;QAED,MAAM,YAAY,GAAG,2BAA2B,CAC9C,KAAK,CAAC,KAAK,EACX,UAAU,EACV,QAAQ,EACR,KAAK,CAAC,YAAY,CACnB,CAAC;QACF,MAAM,SAAS,GAAG,QAAQ,GAAG,YAAY,CAAC;QAC1C,UAAU,GAAG,SAAS,GAAG,UAAU,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,QAAQ,CAAC;IAC7D,CAAC;IAED,OAAO,OAAO,CAAC,MAAM,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;AACnE,CAAC;AAED,SAAS,mBAAmB,CAC1B,KAAwB,EACxB,UAA8B,EAC9B,UAAkB,EAClB,QAAgB;IAEhB,MAAM,QAAQ,GACZ,UAAU,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,IAAI,CAAC,KAAK,CAAC,CAAC,QAAQ,GAAG,UAAU,CAAC,GAAG,GAAG,CAAC,CAAC,CAAC;IACtE,IAAI,SAAS,GAAG,QAAQ,CAAC;IACzB,IAAI,SAAS,GAAG,kBAAkB,CAAC,KAAK,EAAE,UAAU,EAAE,QAAQ,CAAC,CAAC;IAEhE,KAAK,IAAI,KAAK,GAAG,QAAQ,EAAE,KAAK,IAAI,QAAQ,EAAE,KAAK,EAAE,EAAE,CAAC;QACtD,MAAM,KAAK,GAAG,kBAAkB,CAAC,KAAK,EAAE,UAAU,EAAE,KAAK,CAAC,CAAC;QAC3D,IAAI,KAAK,GAAG,SAAS,EAAE,CAAC;YACtB,SAAS,GAAG,KAAK,CAAC;YAClB,SAAS,GAAG,KAAK,CAAC;QACpB,CAAC;IACH,CAAC;IAED,OAAO,SAAS,CAAC;AACnB,CAAC;AAED,SAAS,kBAAkB,CACzB,KAAwB,EACxB,UAA8B,EAC9B,UAAkB;IAElB,IAAI,UAAU,IAAI,CAAC,IAAI,UAAU,IAAI,KAAK,CAAC,MAAM,IAAI,UAAU,CAAC,UAAU,CAAC,EAAE,CAAC;QAC5E,OAAO,CAAC,CAAC;IACX,CAAC;IAED,MAAM,OAAO,GAAG,KAAK,CAAC,UAAU,CAAC,CAAC,IAAI,EAAE,CAAC;IACzC,MAAM,QAAQ,GAAG,KAAK,CAAC,UAAU,GAAG,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;IAE9C,IAAI,YAAY,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE,CAAC;QAC/B,OAAO,GAAG,CAAC;IACb,CAAC;IAED,IAAI,QAAQ,KAAK,EAAE,IAAI,OAAO,KAAK,EAAE,EAAE,CAAC;QACtC,OAAO,EAAE,CAAC;IACZ,CAAC;IAED,IAAI,QAAQ,KAAK,EAAE,EAAE,CAAC;QACpB,OAAO,EAAE,CAAC;IACZ,CAAC;IAED,IAAI,mBAAmB,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE,CAAC;QACtC,OAAO,EAAE,CAAC;IACZ,CAAC;IAED,IAAI,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE,CAAC;QAC1B,OAAO,EAAE,CAAC;IACZ,CAAC;IAED,OAAO,EAAE,CAAC;AACZ,CAAC;AAED,SAAS,aAAa,CACpB,IAAY,EACZ,SAAiB,EACjB,UAAkB,EAClB,QAAgB;IAEhB,MAAM,OAAO,GAAqB,EAAE,CAAC;IACrC,IAAI,MAAM,GAAG,CAAC,CAAC;IAEf,OAAO,MAAM,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC;QAC5B,MAAM,SAAS,GAAG,IAAI,CAAC,MAAM,GAAG,MAAM,CAAC;QACvC,MAAM,WAAW,GACf,SAAS,IAAI,QAAQ;YACnB,CAAC,CAAC,SAAS;YACX,CAAC,CAAC,WAAW,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,EAAE,QAAQ,CAAC,CAAC;QAChD,MAAM,IAAI,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,MAAM,GAAG,WAAW,CAAC,CAAC;QAEtD,OAAO,CAAC,IAAI,CAAC;YACX,IAAI;YACJ,KAAK,EAAE;gBACL,IAAI,EAAE,MAAM;gBACZ,SAAS,EAAE,SAAS,GAAG,CAAC;gBACxB,OAAO,EAAE,SAAS,GAAG,CAAC;gBACtB,WAAW,EAAE,UAAU,GAAG,MAAM;gBAChC,SAAS,EAAE,UAAU,GAAG,MAAM,GAAG,IAAI,CAAC,MAAM;aAC7C;SACF,CAAC,CAAC;QACH,MAAM,IAAI,WAAW,CAAC;IACxB,CAAC;IAED,OAAO,OAAO,CAAC;AACjB,CAAC;AAED,SAAS,aAAa,CACpB,KAAwB,EACxB,WAA8B,EAC9B,UAAkB,EAClB,QAAgB;IAEhB,OAAO;QACL,IAAI,EAAE,KAAK,CAAC,KAAK,CAAC,UAAU,EAAE,QAAQ,GAAG,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC;QACtD,KAAK,EAAE;YACL,IAAI,EAAE,MAAM;YACZ,SAAS,EAAE,UAAU,GAAG,CAAC;YACzB,OAAO,EAAE,QAAQ,GAAG,CAAC;YACrB,WAAW,EAAE,WAAW,CAAC,UAAU,CAAC;YACpC,SAAS,EAAE,WAAW,CAAC,QAAQ,CAAC,GAAG,KAAK,CAAC,QAAQ,CAAC,CAAC,MAAM;SAC1D;KACF,CAAC;AACJ,CAAC;AAED,SAAS,kBAAkB,CAAC,KAAwB;IAClD,MAAM,OAAO,GAAa,EAAE,CAAC;IAC7B,IAAI,MAAM,GAAG,CAAC,CAAC;IAEf,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QACzB,OAAO,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;QACrB,MAAM,IAAI,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC;IAC5B,CAAC;IAED,OAAO,OAAO,CAAC;AACjB,CAAC;AAED,SAAS,iBAAiB,CAAC,KAAwB;IACjD,MAAM,OAAO,GAAG,IAAI,KAAK,CAAU,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;IAC7D,IAAI,KAAK,GAAyB,IAAI,CAAC;IAEvC,KAAK,IAAI,KAAK,GAAG,CAAC,EAAE,KAAK,GAAG,KAAK,CAAC,MAAM,EAAE,KAAK,EAAE,EAAE,CAAC;QAClD,MAAM,OAAO,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,SAAS,EAAE,CAAC;QAEzC,IAAI,KAAK,EAAE,CAAC;YACV,OAAO,CAAC,KAAK,CAAC,GAAG,IAAI,CAAC;YACtB,IAAI,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,EAAE,CAAC;gBAC9B,KAAK,GAAG,IAAI,CAAC;YACf,CAAC;YACD,SAAS;QACX,CAAC;QAED,IAAI,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,EAAE,CAAC;YAC9B,KAAK,GAAG,KAAK,CAAC;QAChB,CAAC;aAAM,IAAI,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,EAAE,CAAC;YACrC,KAAK,GAAG,KAAK,CAAC;QAChB,CAAC;IACH,CAAC;IAED,OAAO,OAAO,CAAC;AACjB,CAAC;AAED,SAAS,2BAA2B,CAClC,KAAwB,EACxB,UAAkB,EAClB,QAAgB,EAChB,YAAoB;IAEpB,IAAI,YAAY,IAAI,CAAC,EAAE,CAAC;QACtB,OAAO,CAAC,CAAC;IACX,CAAC;IAED,IAAI,KAAK,GAAG,CAAC,CAAC;IACd,IAAI,KAAK,GAAG,CAAC,CAAC;IAEd,KAAK,IAAI,KAAK,GAAG,QAAQ,GAAG,CAAC,EAAE,KAAK,GAAG,UAAU,EAAE,KAAK,EAAE,EAAE,CAAC;QAC3D,KAAK,IAAI,KAAK,CAAC,KAAK,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC;QACjC,IAAI,KAAK,GAAG,YAAY,EAAE,CAAC;YACzB,MAAM;QACR,CAAC;QACD,KAAK,EAAE,CAAC;IACV,CAAC;IAED,OAAO,IAAI,CAAC,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,KAAK,CAAC,CAAC,QAAQ,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC;AAClE,CAAC;AAED,SAAS,WAAW,CAAC,IAAY,EAAE,QAAgB;IACjD,MAAM,WAAW,GAAG,IAAI,CAAC,KAAK,CAAC,QAAQ,GAAG,GAAG,CAAC,CAAC;IAC/C,IAAI,YAAY,GAAG,CAAC,CAAC,CAAC;IACtB,IAAI,SAAS,GAAG,CAAC,CAAC;IAElB,KAAK,IAAI,KAAK,GAAG,WAAW,EAAE,KAAK,GAAG,QAAQ,EAAE,KAAK,EAAE,EAAE,CAAC;QACxD,MAAM,SAAS,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC;QAC9B,IAAI,KAAK,GAAG,CAAC,CAAC;QAEd,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,GAAG,EAAE,CAAC;YAChE,KAAK,GAAG,CAAC,CAAC;QACZ,CAAC;aAAM,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,GAAG,EAAE,CAAC;YACvE,KAAK,GAAG,CAAC,CAAC;QACZ,CAAC;aAAM,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,IAAI,EAAE,CAAC;YACnD,KAAK,GAAG,CAAC,CAAC;QACZ,CAAC;aAAM,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,IAAI,EAAE,CAAC;YACxE,KAAK,GAAG,CAAC,CAAC;QACZ,CAAC;QAED,IAAI,KAAK,IAAI,SAAS,IAAI,KAAK,GAAG,CAAC,EAAE,CAAC;YACpC,SAAS,GAAG,KAAK,CAAC;YAClB,YAAY,GAAG,KAAK,GAAG,CAAC,CAAC;QAC3B,CAAC;IACH,CAAC;IAED,OAAO,YAAY,GAAG,CAAC,CAAC,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,QAAQ,CAAC;AACpD,CAAC;AAED,SAAS,gBAAgB,CAAC,OAAgB;IACxC,OAAO;QACL,IAAI,EAAE,UAAU;QAChB,OAAO,EAAE,OAAO,CAAC,OAAO,EAAE,IAAI,IAAI,IAAI;QACtC,KAAK,EAAE,OAAO,CAAC,OAAO,EAAE,KAAK,IAAI,IAAI;QACrC,KAAK,EAAE,OAAO,CAAC,UAAU,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI;KAC5E,CAAC;AACJ,CAAC"}
1
+ {"version":3,"file":"extractor.js","sourceRoot":"","sources":["../../../../src/engine/extraction/markdown/extractor.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,WAAW,EAAE,MAAM,iBAAiB,CAAC;AAM9C,OAAO,EAAE,YAAY,EAAE,MAAM,WAAW,CAAC;AACzC,OAAO,EAAE,kBAAkB,EAAgC,MAAM,cAAc,CAAC;AAChF,OAAO,EAAE,yBAAyB,EAAE,MAAM,sBAAsB,CAAC;AAEjE,OAAO,EAAE,uBAAuB,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAC;AAE/E,MAAM,4BAA4B,GAAG,IAAI,CAAC;AAC1C,MAAM,oCAAoC,GAAG,GAAG,CAAC;AAoBjD,MAAM,OAAO,iBAAiB;IAC5B,KAAK,CAAC,OAAO,CACX,MAAc,EACd,UAAwB,EAAE;QAE1B,IAAI,MAAM,CAAC,IAAI,KAAK,MAAM,IAAI,MAAM,CAAC,IAAI,CAAC,MAAM,KAAK,UAAU,EAAE,CAAC;YAChE,OAAO,EAAE,CAAC;QACZ,CAAC;QAED,kBAAkB,CAAC,MAAM,CAAC,CAAC;QAC3B,MAAM,YAAY,GAAG,2BAA2B,CAAC,OAAO,CAAC,CAAC;QAE1D,MAAM,KAAK,GAAG,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QACtC,MAAM,QAAQ,GAAG,YAAY,CAAC,KAAK,CAAC,CAAC;QACrC,IAAI,QAAQ,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YAC1B,OAAO,IAAI,CAAC,QAAQ,CAAC,MAAM,EAAE,YAAY,CAAC,CAAC;QAC7C,CAAC;QAED,MAAM,WAAW,GAAG,kBAAkB,CAAC,KAAK,CAAC,CAAC;QAC9C,MAAM,UAAU,GAAG,iBAAiB,CAAC,KAAK,CAAC,CAAC;QAC5C,MAAM,QAAQ,GAAG,aAAa,CAAC,QAAQ,EAAE,KAAK,CAAC,CAAC;QAChD,MAAM,SAAS,GAAqB,EAAE,CAAC;QAEvC,KAAK,MAAM,OAAO,IAAI,QAAQ,EAAE,CAAC;YAC/B,MAAM,QAAQ,GAAG,gBAAgB,CAAC,OAAO,CAAC,CAAC;YAC3C,MAAM,mBAAmB,GAAG,uBAAuB,CACjD,YAAY,EACZ,QAAQ,CACT,CAAC;YACF,MAAM,OAAO,GAAG,oBAAoB,CAAC;gBACnC,KAAK;gBACL,WAAW;gBACX,UAAU;gBACV,OAAO;gBACP,QAAQ,EAAE,mBAAmB,CAAC,aAAa;gBAC3C,YAAY,EAAE,mBAAmB,CAAC,iBAAiB;aACpD,CAAC,CAAC;YAEH,IAAI,OAAO,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBACvB,MAAM,EAAE,GAAG,YAAY,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,EAAE,SAAS,CAAC,MAAM,CAAC,CAAC;gBAC1D,SAAS,CAAC,IAAI,CAAC;oBACb,EAAE;oBACF,KAAK,EAAE,EAAE;oBACT,MAAM,EAAE,MAAM,CAAC,IAAI,CAAC,EAAE;oBACtB,KAAK,EAAE,aAAa,CAClB,KAAK,EACL,WAAW,EACX,OAAO,CAAC,UAAU,EAClB,OAAO,CAAC,QAAQ,CACjB,CAAC,KAAK;oBACP,OAAO,EAAE;wBACP,IAAI,EAAE,MAAM;wBACZ,IAAI,EAAE,cAAc,CAClB,eAAe,CAAC,QAAQ,CAAC,EACzB,mBAAmB,CAAC,aAAa,CAClC;qBACF;oBACD,QAAQ;iBACT,CAAC,CAAC;gBAEH,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;oBAC7B,SAAS,CAAC,IAAI,CACZ,wBAAwB,CACtB,MAAM,EACN,QAAQ,EACR,MAAM,EACN,SAAS,CAAC,MAAM,EAChB,EAAE,CACH,CACF,CAAC;gBACJ,CAAC;gBAED,SAAS;YACX,CAAC;YAED,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;gBAC7B,SAAS,CAAC,IAAI,CAAC;oBACb,EAAE,EAAE,YAAY,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,EAAE,SAAS,CAAC,MAAM,CAAC;oBAClD,MAAM,EAAE,MAAM,CAAC,IAAI,CAAC,EAAE;oBACtB,KAAK,EAAE,MAAM,CAAC,KAAK;oBACnB,OAAO,EAAE;wBACP,IAAI,EAAE,MAAM;wBACZ,IAAI,EAAE,MAAM,CAAC,IAAI;qBAClB;oBACD,QAAQ;iBACT,CAAC,CAAC;YACL,CAAC;QACH,CAAC;QAED,OAAO,SAAS,CAAC,MAAM,GAAG,CAAC;YACzB,CAAC,CAAC,SAAS;YACX,CAAC,CAAC,IAAI,CAAC,QAAQ,CAAC,MAAM,EAAE,YAAY,CAAC,CAAC;IAC1C,CAAC;IAEO,QAAQ,CACd,MAAkB,EAClB,OAA+B;QAE/B,OAAO,yBAAyB,CAC9B,MAAM,EACN,OAAO,CAAC,aAAa,EACrB,OAAO,CAAC,iBAAiB,CAC1B,CAAC;IACJ,CAAC;CACF;AAED,SAAS,2BAA2B,CAClC,OAAqB;IAErB,MAAM,aAAa,GAAG,OAAO,CAAC,aAAa,IAAI,4BAA4B,CAAC;IAC5E,MAAM,iBAAiB,GACrB,OAAO,CAAC,iBAAiB,IAAI,oCAAoC,CAAC;IAEpE,IAAI,CAAC,MAAM,CAAC,SAAS,CAAC,aAAa,CAAC,IAAI,aAAa,IAAI,CAAC,EAAE,CAAC;QAC3D,MAAM,IAAI,WAAW,CACnB,2DAA2D,EAC3D;YACE,IAAI,EAAE,yDAAyD;YAC/D,OAAO,EAAE,iBAAiB,aAAa,EAAE;SAC1C,CACF,CAAC;IACJ,CAAC;IAED,IACE,CAAC,MAAM,CAAC,SAAS,CAAC,iBAAiB,CAAC;QACpC,iBAAiB,GAAG,CAAC;QACrB,iBAAiB,IAAI,aAAa,EAClC,CAAC;QACD,MAAM,IAAI,WAAW,CACnB,mEAAmE,EACnE;YACE,IAAI,EAAE,4DAA4D;YAClE,OAAO,EAAE,iBAAiB,aAAa,sBAAsB,iBAAiB,EAAE;SACjF,CACF,CAAC;IACJ,CAAC;IAED,OAAO,EAAE,aAAa,EAAE,iBAAiB,EAAE,CAAC;AAC9C,CAAC;AAED,SAAS,wBAAwB,CAC/B,MAAkB,EAClB,QAAgC,EAChC,MAAsB,EACtB,KAAa,EACb,KAAa;IAEb,OAAO;QACL,EAAE,EAAE,YAAY,CAAC,MAAM,CAAC,IAAI,CAAC,EAAE,EAAE,KAAK,CAAC;QACvC,KAAK;QACL,MAAM,EAAE,MAAM,CAAC,IAAI,CAAC,EAAE;QACtB,KAAK,EAAE,MAAM,CAAC,KAAK;QACnB,OAAO,EAAE;YACP,IAAI,EAAE,MAAM;YACZ,IAAI,EAAE,MAAM,CAAC,IAAI;SAClB;QACD,QAAQ;KACT,CAAC;AACJ,CAAC;AAED,SAAS,eAAe,CAAC,QAAgC;IACvD,OAAO,QAAQ,CAAC,OAAO,IAAI,kBAAkB,CAAC;AAChD,CAAC;AAED,SAAS,YAAY,CAAC,KAAwB;IAC5C,MAAM,QAAQ,GAAc,EAAE,CAAC;IAC/B,IAAI,KAAK,GAAyB,IAAI,CAAC;IAEvC,KAAK,IAAI,KAAK,GAAG,CAAC,EAAE,KAAK,GAAG,KAAK,CAAC,MAAM,EAAE,KAAK,EAAE,EAAE,CAAC;QAClD,MAAM,IAAI,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC;QAC1B,MAAM,OAAO,GAAG,IAAI,CAAC,SAAS,EAAE,CAAC;QAEjC,IAAI,KAAK,EAAE,CAAC;YACV,IAAI,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,EAAE,CAAC;gBAC9B,KAAK,GAAG,IAAI,CAAC;YACf,CAAC;YACD,SAAS;QACX,CAAC;QAED,IAAI,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,EAAE,CAAC;YAC9B,KAAK,GAAG,KAAK,CAAC;YACd,SAAS;QACX,CAAC;QAED,IAAI,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,EAAE,CAAC;YAC9B,KAAK,GAAG,KAAK,CAAC;YACd,SAAS;QACX,CAAC;QAED,MAAM,GAAG,GAAG,IAAI,CAAC,KAAK,CAAC,4BAA4B,CAAC,CAAC;QACrD,IAAI,GAAG,EAAE,CAAC;YACR,QAAQ,CAAC,IAAI,CAAC;gBACZ,KAAK,EAAE,GAAG,CAAC,CAAC,CAAC,CAAC,MAAM;gBACpB,IAAI,EAAE,GAAG,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE;gBACnB,SAAS,EAAE,KAAK;aACjB,CAAC,CAAC;YACH,SAAS;QACX,CAAC;QAED,MAAM,IAAI,GAAG,KAAK,CAAC,KAAK,GAAG,CAAC,CAAC,EAAE,IAAI,EAAE,CAAC;QACtC,IAAI,IAAI,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,IAAI,IAAI,IAAI,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;YAChE,QAAQ,CAAC,IAAI,CAAC;gBACZ,KAAK,EAAE,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;gBACnC,IAAI,EAAE,IAAI,CAAC,IAAI,EAAE;gBACjB,SAAS,EAAE,KAAK;aACjB,CAAC,CAAC;YACH,KAAK,EAAE,CAAC;QACV,CAAC;IACH,CAAC;IAED,OAAO,QAAQ,CAAC;AAClB,CAAC;AAED,SAAS,aAAa,CACpB,QAA4B,EAC5B,KAAwB;IAExB,MAAM,KAAK,GAAc,EAAE,CAAC;IAC5B,MAAM,QAAQ,GAAc,EAAE,CAAC;IAC/B,MAAM,YAAY,GAAG,QAAQ,CAAC,CAAC,CAAC,CAAC;IAEjC,IACE,YAAY,CAAC,SAAS,GAAG,CAAC;QAC1B,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,YAAY,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,EACnE,CAAC;QACD,QAAQ,CAAC,IAAI,CAAC;YACZ,OAAO,EAAE,IAAI;YACb,UAAU,EAAE,CAAC;YACb,QAAQ,EAAE,YAAY,CAAC,SAAS,GAAG,CAAC;YACpC,UAAU,EAAE,EAAE;SACf,CAAC,CAAC;IACL,CAAC;IAED,KAAK,IAAI,KAAK,GAAG,CAAC,EAAE,KAAK,GAAG,QAAQ,CAAC,MAAM,EAAE,KAAK,EAAE,EAAE,CAAC;QACrD,MAAM,OAAO,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAC;QAEhC,OAAO,KAAK,CAAC,MAAM,GAAG,CAAC,IAAI,KAAK,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,KAAK,IAAI,OAAO,CAAC,KAAK,EAAE,CAAC;YAC1E,KAAK,CAAC,GAAG,EAAE,CAAC;QACd,CAAC;QAED,QAAQ,CAAC,IAAI,CAAC;YACZ,OAAO;YACP,UAAU,EAAE,OAAO,CAAC,SAAS;YAC7B,QAAQ,EACN,KAAK,GAAG,CAAC,GAAG,QAAQ,CAAC,MAAM;gBACzB,CAAC,CAAC,QAAQ,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC,SAAS,GAAG,CAAC;gBACnC,CAAC,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC;YACtB,UAAU,EAAE,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,IAAI,CAAC;SAC3C,CAAC,CAAC;QACH,KAAK,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;IACtB,CAAC;IAED,OAAO,QAAQ,CAAC;AAClB,CAAC;AAED,SAAS,oBAAoB,CAAC,KAO7B;IACC,MAAM,OAAO,GAAqB,EAAE,CAAC;IACrC,IAAI,UAAU,GAAG,KAAK,CAAC,OAAO,CAAC,UAAU,CAAC;IAE1C,OAAO,UAAU,IAAI,KAAK,CAAC,OAAO,CAAC,QAAQ,EAAE,CAAC;QAC5C,IAAI,KAAK,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC,MAAM,GAAG,CAAC,GAAG,KAAK,CAAC,QAAQ,EAAE,CAAC;YACxD,OAAO,CAAC,IAAI,CACV,GAAG,aAAa,CACd,KAAK,CAAC,KAAK,CAAC,UAAU,CAAC,EACvB,UAAU,EACV,KAAK,CAAC,WAAW,CAAC,UAAU,CAAC,EAC7B,KAAK,CAAC,QAAQ,CACf,CACF,CAAC;YACF,UAAU,EAAE,CAAC;YACb,SAAS;QACX,CAAC;QAED,IAAI,QAAQ,GAAG,UAAU,CAAC;QAC1B,IAAI,SAAS,GAAG,CAAC,CAAC;QAElB,OAAO,QAAQ,IAAI,KAAK,CAAC,OAAO,CAAC,QAAQ,EAAE,CAAC;YAC1C,MAAM,UAAU,GAAG,KAAK,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC;YACpD,IAAI,SAAS,GAAG,UAAU,GAAG,KAAK,CAAC,QAAQ,IAAI,QAAQ,GAAG,UAAU,EAAE,CAAC;gBACrE,MAAM;YACR,CAAC;YACD,SAAS,IAAI,UAAU,CAAC;YACxB,QAAQ,EAAE,CAAC;QACb,CAAC;QAED,IAAI,QAAQ,IAAI,KAAK,CAAC,OAAO,CAAC,QAAQ,IAAI,QAAQ,GAAG,UAAU,GAAG,CAAC,EAAE,CAAC;YACpE,QAAQ,GAAG,mBAAmB,CAC5B,KAAK,CAAC,KAAK,EACX,KAAK,CAAC,UAAU,EAChB,UAAU,EACV,QAAQ,CACT,CAAC;QACJ,CAAC;QAED,OAAO,CAAC,IAAI,CACV,aAAa,CAAC,KAAK,CAAC,KAAK,EAAE,KAAK,CAAC,WAAW,EAAE,UAAU,EAAE,QAAQ,GAAG,CAAC,CAAC,CACxE,CAAC;QAEF,IAAI,QAAQ,GAAG,KAAK,CAAC,OAAO,CAAC,QAAQ,EAAE,CAAC;YACtC,MAAM;QACR,CAAC;QAED,MAAM,YAAY,GAAG,2BAA2B,CAC9C,KAAK,CAAC,KAAK,EACX,UAAU,EACV,QAAQ,EACR,KAAK,CAAC,YAAY,CACnB,CAAC;QACF,MAAM,SAAS,GAAG,QAAQ,GAAG,YAAY,CAAC;QAC1C,UAAU,GAAG,SAAS,GAAG,UAAU,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,QAAQ,CAAC;IAC7D,CAAC;IAED,OAAO,OAAO,CAAC,MAAM,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;AACnE,CAAC;AAED,SAAS,mBAAmB,CAC1B,KAAwB,EACxB,UAA8B,EAC9B,UAAkB,EAClB,QAAgB;IAEhB,MAAM,QAAQ,GACZ,UAAU,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,IAAI,CAAC,KAAK,CAAC,CAAC,QAAQ,GAAG,UAAU,CAAC,GAAG,GAAG,CAAC,CAAC,CAAC;IACtE,IAAI,SAAS,GAAG,QAAQ,CAAC;IACzB,IAAI,SAAS,GAAG,kBAAkB,CAAC,KAAK,EAAE,UAAU,EAAE,QAAQ,CAAC,CAAC;IAEhE,KAAK,IAAI,KAAK,GAAG,QAAQ,EAAE,KAAK,IAAI,QAAQ,EAAE,KAAK,EAAE,EAAE,CAAC;QACtD,MAAM,KAAK,GAAG,kBAAkB,CAAC,KAAK,EAAE,UAAU,EAAE,KAAK,CAAC,CAAC;QAC3D,IAAI,KAAK,GAAG,SAAS,EAAE,CAAC;YACtB,SAAS,GAAG,KAAK,CAAC;YAClB,SAAS,GAAG,KAAK,CAAC;QACpB,CAAC;IACH,CAAC;IAED,OAAO,SAAS,CAAC;AACnB,CAAC;AAED,SAAS,kBAAkB,CACzB,KAAwB,EACxB,UAA8B,EAC9B,UAAkB;IAElB,IAAI,UAAU,IAAI,CAAC,IAAI,UAAU,IAAI,KAAK,CAAC,MAAM,IAAI,UAAU,CAAC,UAAU,CAAC,EAAE,CAAC;QAC5E,OAAO,CAAC,CAAC;IACX,CAAC;IAED,MAAM,OAAO,GAAG,KAAK,CAAC,UAAU,CAAC,CAAC,IAAI,EAAE,CAAC;IACzC,MAAM,QAAQ,GAAG,KAAK,CAAC,UAAU,GAAG,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;IAE9C,IAAI,YAAY,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE,CAAC;QAC/B,OAAO,GAAG,CAAC;IACb,CAAC;IAED,IAAI,QAAQ,KAAK,EAAE,IAAI,OAAO,KAAK,EAAE,EAAE,CAAC;QACtC,OAAO,EAAE,CAAC;IACZ,CAAC;IAED,IAAI,QAAQ,KAAK,EAAE,EAAE,CAAC;QACpB,OAAO,EAAE,CAAC;IACZ,CAAC;IAED,IAAI,mBAAmB,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE,CAAC;QACtC,OAAO,EAAE,CAAC;IACZ,CAAC;IAED,IAAI,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE,CAAC;QAC1B,OAAO,EAAE,CAAC;IACZ,CAAC;IAED,OAAO,EAAE,CAAC;AACZ,CAAC;AAED,SAAS,aAAa,CACpB,IAAY,EACZ,SAAiB,EACjB,UAAkB,EAClB,QAAgB;IAEhB,MAAM,OAAO,GAAqB,EAAE,CAAC;IACrC,IAAI,MAAM,GAAG,CAAC,CAAC;IAEf,OAAO,MAAM,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC;QAC5B,MAAM,SAAS,GAAG,IAAI,CAAC,MAAM,GAAG,MAAM,CAAC;QACvC,MAAM,WAAW,GACf,SAAS,IAAI,QAAQ;YACnB,CAAC,CAAC,SAAS;YACX,CAAC,CAAC,WAAW,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,EAAE,QAAQ,CAAC,CAAC;QAChD,MAAM,IAAI,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,MAAM,GAAG,WAAW,CAAC,CAAC;QAEtD,OAAO,CAAC,IAAI,CAAC;YACX,IAAI;YACJ,KAAK,EAAE;gBACL,IAAI,EAAE,MAAM;gBACZ,SAAS,EAAE,SAAS,GAAG,CAAC;gBACxB,OAAO,EAAE,SAAS,GAAG,CAAC;gBACtB,WAAW,EAAE,UAAU,GAAG,MAAM;gBAChC,SAAS,EAAE,UAAU,GAAG,MAAM,GAAG,IAAI,CAAC,MAAM;aAC7C;SACF,CAAC,CAAC;QACH,MAAM,IAAI,WAAW,CAAC;IACxB,CAAC;IAED,OAAO,OAAO,CAAC;AACjB,CAAC;AAED,SAAS,aAAa,CACpB,KAAwB,EACxB,WAA8B,EAC9B,UAAkB,EAClB,QAAgB;IAEhB,OAAO;QACL,IAAI,EAAE,KAAK,CAAC,KAAK,CAAC,UAAU,EAAE,QAAQ,GAAG,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC;QACtD,KAAK,EAAE;YACL,IAAI,EAAE,MAAM;YACZ,SAAS,EAAE,UAAU,GAAG,CAAC;YACzB,OAAO,EAAE,QAAQ,GAAG,CAAC;YACrB,WAAW,EAAE,WAAW,CAAC,UAAU,CAAC;YACpC,SAAS,EAAE,WAAW,CAAC,QAAQ,CAAC,GAAG,KAAK,CAAC,QAAQ,CAAC,CAAC,MAAM;SAC1D;KACF,CAAC;AACJ,CAAC;AAED,SAAS,kBAAkB,CAAC,KAAwB;IAClD,MAAM,OAAO,GAAa,EAAE,CAAC;IAC7B,IAAI,MAAM,GAAG,CAAC,CAAC;IAEf,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QACzB,OAAO,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;QACrB,MAAM,IAAI,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC;IAC5B,CAAC;IAED,OAAO,OAAO,CAAC;AACjB,CAAC;AAED,SAAS,iBAAiB,CAAC,KAAwB;IACjD,MAAM,OAAO,GAAG,IAAI,KAAK,CAAU,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;IAC7D,IAAI,KAAK,GAAyB,IAAI,CAAC;IAEvC,KAAK,IAAI,KAAK,GAAG,CAAC,EAAE,KAAK,GAAG,KAAK,CAAC,MAAM,EAAE,KAAK,EAAE,EAAE,CAAC;QAClD,MAAM,OAAO,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,SAAS,EAAE,CAAC;QAEzC,IAAI,KAAK,EAAE,CAAC;YACV,OAAO,CAAC,KAAK,CAAC,GAAG,IAAI,CAAC;YACtB,IAAI,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,EAAE,CAAC;gBAC9B,KAAK,GAAG,IAAI,CAAC;YACf,CAAC;YACD,SAAS;QACX,CAAC;QAED,IAAI,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,EAAE,CAAC;YAC9B,KAAK,GAAG,KAAK,CAAC;QAChB,CAAC;aAAM,IAAI,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,EAAE,CAAC;YACrC,KAAK,GAAG,KAAK,CAAC;QAChB,CAAC;IACH,CAAC;IAED,OAAO,OAAO,CAAC;AACjB,CAAC;AAED,SAAS,2BAA2B,CAClC,KAAwB,EACxB,UAAkB,EAClB,QAAgB,EAChB,YAAoB;IAEpB,IAAI,YAAY,IAAI,CAAC,EAAE,CAAC;QACtB,OAAO,CAAC,CAAC;IACX,CAAC;IAED,IAAI,KAAK,GAAG,CAAC,CAAC;IACd,IAAI,KAAK,GAAG,CAAC,CAAC;IAEd,KAAK,IAAI,KAAK,GAAG,QAAQ,GAAG,CAAC,EAAE,KAAK,GAAG,UAAU,EAAE,KAAK,EAAE,EAAE,CAAC;QAC3D,KAAK,IAAI,KAAK,CAAC,KAAK,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC;QACjC,IAAI,KAAK,GAAG,YAAY,EAAE,CAAC;YACzB,MAAM;QACR,CAAC;QACD,KAAK,EAAE,CAAC;IACV,CAAC;IAED,OAAO,IAAI,CAAC,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,KAAK,CAAC,CAAC,QAAQ,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC;AAClE,CAAC;AAED,SAAS,WAAW,CAAC,IAAY,EAAE,QAAgB;IACjD,MAAM,WAAW,GAAG,IAAI,CAAC,KAAK,CAAC,QAAQ,GAAG,GAAG,CAAC,CAAC;IAC/C,IAAI,YAAY,GAAG,CAAC,CAAC,CAAC;IACtB,IAAI,SAAS,GAAG,CAAC,CAAC;IAElB,KAAK,IAAI,KAAK,GAAG,WAAW,EAAE,KAAK,GAAG,QAAQ,EAAE,KAAK,EAAE,EAAE,CAAC;QACxD,MAAM,SAAS,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC;QAC9B,IAAI,KAAK,GAAG,CAAC,CAAC;QAEd,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,GAAG,EAAE,CAAC;YAChE,KAAK,GAAG,CAAC,CAAC;QACZ,CAAC;aAAM,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,GAAG,EAAE,CAAC;YACvE,KAAK,GAAG,CAAC,CAAC;QACZ,CAAC;aAAM,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,IAAI,EAAE,CAAC;YACnD,KAAK,GAAG,CAAC,CAAC;QACZ,CAAC;aAAM,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,GAAG,IAAI,SAAS,KAAK,IAAI,EAAE,CAAC;YACxE,KAAK,GAAG,CAAC,CAAC;QACZ,CAAC;QAED,IAAI,KAAK,IAAI,SAAS,IAAI,KAAK,GAAG,CAAC,EAAE,CAAC;YACpC,SAAS,GAAG,KAAK,CAAC;YAClB,YAAY,GAAG,KAAK,GAAG,CAAC,CAAC;QAC3B,CAAC;IACH,CAAC;IAED,OAAO,YAAY,GAAG,CAAC,CAAC,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,QAAQ,CAAC;AACpD,CAAC;AAED,SAAS,gBAAgB,CAAC,OAAgB;IACxC,OAAO;QACL,IAAI,EAAE,UAAU;QAChB,OAAO,EAAE,OAAO,CAAC,OAAO,EAAE,IAAI,IAAI,IAAI;QACtC,KAAK,EAAE,OAAO,CAAC,OAAO,EAAE,KAAK,IAAI,IAAI;QACrC,KAAK,EAAE,OAAO,CAAC,UAAU,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI;KAC5E,CAAC;AACJ,CAAC"}
@@ -0,0 +1,4 @@
1
+ import type { EntityFragment } from "../types.js";
2
+ import type { Source } from "./source.js";
3
+ import type { ChunkOptions } from "./types.js";
4
+ export declare function extract(source: Source, options?: ChunkOptions): Promise<EntityFragment[]>;
@@ -0,0 +1,26 @@
1
+ import { CodeExtractor } from "./code/extractor.js";
2
+ import { ImageExtractor } from "./image/extractor.js";
3
+ import { MarkdownExtractor } from "./markdown/extractor.js";
4
+ import { TextExtractor } from "./text/extractor.js";
5
+ const extractors = {
6
+ code: new CodeExtractor(),
7
+ image: new ImageExtractor(),
8
+ markdown: new MarkdownExtractor(),
9
+ text: new TextExtractor(),
10
+ };
11
+ export function extract(source, options = {}) {
12
+ return extractors[routeSource(source)].extract(source, options);
13
+ }
14
+ function routeSource(source) {
15
+ if (source.kind === "image") {
16
+ return "image";
17
+ }
18
+ if (source.file.kind === "code") {
19
+ return "code";
20
+ }
21
+ if (source.file.format === "markdown") {
22
+ return "markdown";
23
+ }
24
+ return "text";
25
+ }
26
+ //# sourceMappingURL=runtime.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"runtime.js","sourceRoot":"","sources":["../../../src/engine/extraction/runtime.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,aAAa,EAAE,MAAM,qBAAqB,CAAC;AACpD,OAAO,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAC;AACtD,OAAO,EAAE,iBAAiB,EAAE,MAAM,yBAAyB,CAAC;AAE5D,OAAO,EAAE,aAAa,EAAE,MAAM,qBAAqB,CAAC;AASpD,MAAM,UAAU,GAAG;IACjB,IAAI,EAAE,IAAI,aAAa,EAAE;IACzB,KAAK,EAAE,IAAI,cAAc,EAAE;IAC3B,QAAQ,EAAE,IAAI,iBAAiB,EAAE;IACjC,IAAI,EAAE,IAAI,aAAa,EAAE;CACwB,CAAC;AAEpD,MAAM,UAAU,OAAO,CACrB,MAAc,EACd,UAAwB,EAAE;IAE1B,OAAO,UAAU,CAAC,WAAW,CAAC,MAAM,CAAC,CAAC,CAAC,OAAO,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;AAClE,CAAC;AAED,SAAS,WAAW,CAAC,MAAc;IACjC,IAAI,MAAM,CAAC,IAAI,KAAK,OAAO,EAAE,CAAC;QAC5B,OAAO,OAAO,CAAC;IACjB,CAAC;IAED,IAAI,MAAM,CAAC,IAAI,CAAC,IAAI,KAAK,MAAM,EAAE,CAAC;QAChC,OAAO,MAAM,CAAC;IAChB,CAAC;IAED,IAAI,MAAM,CAAC,IAAI,CAAC,MAAM,KAAK,UAAU,EAAE,CAAC;QACtC,OAAO,UAAU,CAAC;IACpB,CAAC;IAED,OAAO,MAAM,CAAC;AAChB,CAAC"}
@@ -0,0 +1,18 @@
1
+ import type { FileInfo, ImageFormat } from "../types.js";
2
+ export type SourceKind = "text" | "image";
3
+ type SourceBase = {
4
+ kind: SourceKind;
5
+ file: FileInfo;
6
+ };
7
+ export type TextSource = SourceBase & {
8
+ kind: "text";
9
+ text: string;
10
+ };
11
+ export type ImageSource = SourceBase & {
12
+ kind: "image";
13
+ data: Uint8Array;
14
+ format: ImageFormat;
15
+ };
16
+ export type Source = TextSource | ImageSource;
17
+ export declare function validateSourceFile(source: Source): void;
18
+ export {};
@@ -0,0 +1,22 @@
1
+ import { EngineError } from "../errors.js";
2
+ export function validateSourceFile(source) {
3
+ if (source.file.id.trim().length === 0) {
4
+ throw new EngineError("Extractor source requires a non-empty file id", {
5
+ code: "ZVEC_GREP.ENGINE.EXTRACTORS.EMPTY_FILE_ID",
6
+ context: `sourceKind=${source.kind}`,
7
+ });
8
+ }
9
+ if (source.file.absolutePath.trim().length === 0) {
10
+ throw new EngineError("Extractor source requires a non-empty absolute file path", {
11
+ code: "ZVEC_GREP.ENGINE.EXTRACTORS.EMPTY_ABSOLUTE_FILE_PATH",
12
+ context: `fileId=${source.file.id} sourceKind=${source.kind}`,
13
+ });
14
+ }
15
+ if (source.file.relativePath.trim().length === 0) {
16
+ throw new EngineError("Extractor source requires a non-empty relative file path", {
17
+ code: "ZVEC_GREP.ENGINE.EXTRACTORS.EMPTY_RELATIVE_FILE_PATH",
18
+ context: `fileId=${source.file.id} sourceKind=${source.kind}`,
19
+ });
20
+ }
21
+ }
22
+ //# sourceMappingURL=source.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"source.js","sourceRoot":"","sources":["../../../src/engine/extraction/source.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,WAAW,EAAE,MAAM,cAAc,CAAC;AAuB3C,MAAM,UAAU,kBAAkB,CAAC,MAAc;IAC/C,IAAI,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC,IAAI,EAAE,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACvC,MAAM,IAAI,WAAW,CAAC,+CAA+C,EAAE;YACrE,IAAI,EAAE,2CAA2C;YACjD,OAAO,EAAE,cAAc,MAAM,CAAC,IAAI,EAAE;SACrC,CAAC,CAAC;IACL,CAAC;IAED,IAAI,MAAM,CAAC,IAAI,CAAC,YAAY,CAAC,IAAI,EAAE,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACjD,MAAM,IAAI,WAAW,CACnB,0DAA0D,EAC1D;YACE,IAAI,EAAE,sDAAsD;YAC5D,OAAO,EAAE,UAAU,MAAM,CAAC,IAAI,CAAC,EAAE,eAAe,MAAM,CAAC,IAAI,EAAE;SAC9D,CACF,CAAC;IACJ,CAAC;IAED,IAAI,MAAM,CAAC,IAAI,CAAC,YAAY,CAAC,IAAI,EAAE,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACjD,MAAM,IAAI,WAAW,CACnB,0DAA0D,EAC1D;YACE,IAAI,EAAE,sDAAsD;YAC5D,OAAO,EAAE,UAAU,MAAM,CAAC,IAAI,CAAC,EAAE,eAAe,MAAM,CAAC,IAAI,EAAE;SAC9D,CACF,CAAC;IACJ,CAAC;AACH,CAAC"}
@@ -0,0 +1,7 @@
1
+ import type { EntityFragment } from "../../types.js";
2
+ import { type Source, type TextSource } from "../source.js";
3
+ import type { ChunkOptions } from "../types.js";
4
+ export declare class TextExtractor {
5
+ extract(source: Source, options?: ChunkOptions): Promise<EntityFragment[]>;
6
+ }
7
+ export declare function extractPlainTextFragments(source: TextSource, maxChunkChars: number, chunkOverlapChars: number): EntityFragment[];