@nitpicker/crawler 0.11.0 → 0.13.0

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 (387) hide show
  1. package/README.md +6 -4
  2. package/lib/archive/archive-accessor.d.ts +2 -2
  3. package/lib/archive/archive-accessor.js +2 -2
  4. package/lib/archive/archive-lock.d.ts +7 -0
  5. package/lib/archive/archive-lock.js +7 -0
  6. package/lib/archive/archive.d.ts +175 -13
  7. package/lib/archive/archive.js +198 -14
  8. package/lib/archive/cache/compute-archive-cache-key.d.ts +39 -0
  9. package/lib/archive/cache/compute-archive-cache-key.js +95 -0
  10. package/lib/archive/cache/extract-archive-to-cache.d.ts +43 -0
  11. package/lib/archive/cache/extract-archive-to-cache.js +309 -0
  12. package/lib/archive/cache/get-archive-cache-root.d.ts +20 -0
  13. package/lib/archive/cache/get-archive-cache-root.js +53 -0
  14. package/lib/archive/cache/is-archive-cache-disabled.d.ts +24 -0
  15. package/lib/archive/cache/is-archive-cache-disabled.js +34 -0
  16. package/lib/archive/cache/resolve-archive-cache-dir.d.ts +26 -0
  17. package/lib/archive/cache/resolve-archive-cache-dir.js +32 -0
  18. package/lib/archive/create-adjunct-tables.d.ts +43 -0
  19. package/lib/archive/create-adjunct-tables.js +213 -0
  20. package/lib/archive/create-entity-tables.d.ts +173 -0
  21. package/lib/archive/create-entity-tables.js +318 -0
  22. package/lib/archive/create-progress-reporter.d.ts +30 -0
  23. package/lib/archive/create-progress-reporter.js +38 -0
  24. package/lib/archive/create-ref-tables.d.ts +35 -0
  25. package/lib/archive/create-ref-tables.js +188 -0
  26. package/lib/archive/database.d.ts +130 -182
  27. package/lib/archive/database.js +524 -1777
  28. package/lib/archive/db-ops/_shared/clear-write-ref-caches.d.ts +27 -0
  29. package/lib/archive/db-ops/_shared/clear-write-ref-caches.js +34 -0
  30. package/lib/archive/db-ops/_shared/create-write-ref-caches.d.ts +17 -0
  31. package/lib/archive/db-ops/_shared/create-write-ref-caches.js +26 -0
  32. package/lib/archive/db-ops/_shared/decode-json-ref.d.ts +17 -0
  33. package/lib/archive/db-ops/_shared/decode-json-ref.js +31 -0
  34. package/lib/archive/db-ops/_shared/load-response-headers-by-set-ids.d.ts +20 -0
  35. package/lib/archive/db-ops/_shared/load-response-headers-by-set-ids.js +53 -0
  36. package/lib/archive/db-ops/_shared/resolve-content-item-id.d.ts +61 -0
  37. package/lib/archive/db-ops/_shared/resolve-content-item-id.js +111 -0
  38. package/lib/archive/db-ops/_shared/resolve-url-or-blob.d.ts +23 -0
  39. package/lib/archive/db-ops/_shared/resolve-url-or-blob.js +29 -0
  40. package/lib/archive/db-ops/_shared/retry-setting.d.ts +16 -0
  41. package/lib/archive/db-ops/_shared/retry-setting.js +18 -0
  42. package/lib/archive/db-ops/_shared/safe-parse-json.d.ts +11 -0
  43. package/lib/archive/db-ops/_shared/safe-parse-json.js +18 -0
  44. package/lib/archive/db-ops/_shared/types.d.ts +53 -0
  45. package/lib/archive/db-ops/_shared/types.js +1 -0
  46. package/lib/archive/db-ops/_shared/upsert-blob-ref.d.ts +25 -0
  47. package/lib/archive/db-ops/_shared/upsert-blob-ref.js +48 -0
  48. package/lib/archive/db-ops/_shared/upsert-content-type-ref.d.ts +30 -0
  49. package/lib/archive/db-ops/_shared/upsert-content-type-ref.js +45 -0
  50. package/lib/archive/db-ops/_shared/upsert-json-ref.d.ts +22 -0
  51. package/lib/archive/db-ops/_shared/upsert-json-ref.js +41 -0
  52. package/lib/archive/db-ops/_shared/upsert-response-headers.d.ts +35 -0
  53. package/lib/archive/db-ops/_shared/upsert-response-headers.js +49 -0
  54. package/lib/archive/db-ops/_shared/upsert-url-ref.d.ts +39 -0
  55. package/lib/archive/db-ops/_shared/upsert-url-ref.js +62 -0
  56. package/lib/archive/db-ops/analysis/replace-analysis-violations.d.ts +28 -0
  57. package/lib/archive/db-ops/analysis/replace-analysis-violations.js +152 -0
  58. package/lib/archive/db-ops/anchors/get-anchors-on-page.d.ts +10 -0
  59. package/lib/archive/db-ops/anchors/get-anchors-on-page.js +21 -0
  60. package/lib/archive/db-ops/config/get-base-url.d.ts +8 -0
  61. package/lib/archive/db-ops/config/get-base-url.js +14 -0
  62. package/lib/archive/db-ops/config/get-config.d.ts +10 -0
  63. package/lib/archive/db-ops/config/get-config.js +27 -0
  64. package/lib/archive/db-ops/config/get-name.d.ts +8 -0
  65. package/lib/archive/db-ops/config/get-name.js +14 -0
  66. package/lib/archive/db-ops/config/info-column-allowlist.d.ts +7 -0
  67. package/lib/archive/db-ops/config/info-column-allowlist.js +26 -0
  68. package/lib/archive/db-ops/config/info-json-columns.d.ts +5 -0
  69. package/lib/archive/db-ops/config/info-json-columns.js +10 -0
  70. package/lib/archive/db-ops/config/set-config.d.ts +12 -0
  71. package/lib/archive/db-ops/config/set-config.js +21 -0
  72. package/lib/archive/db-ops/config/update-config.d.ts +17 -0
  73. package/lib/archive/db-ops/config/update-config.js +36 -0
  74. package/lib/archive/db-ops/errors/insert-crawl-error.d.ts +15 -0
  75. package/lib/archive/db-ops/errors/insert-crawl-error.js +21 -0
  76. package/lib/archive/db-ops/errors/insert-page-error.d.ts +21 -0
  77. package/lib/archive/db-ops/errors/insert-page-error.js +28 -0
  78. package/lib/archive/db-ops/errors/list-dns-burned-host-candidates.d.ts +22 -0
  79. package/lib/archive/db-ops/errors/list-dns-burned-host-candidates.js +141 -0
  80. package/lib/archive/db-ops/html/get-html-of-page-by-id.d.ts +18 -0
  81. package/lib/archive/db-ops/html/get-html-of-page-by-id.js +29 -0
  82. package/lib/archive/db-ops/inventory/record-inventory-run.d.ts +21 -0
  83. package/lib/archive/db-ops/inventory/record-inventory-run.js +38 -0
  84. package/lib/archive/db-ops/lifecycle/checkpoint.d.ts +8 -0
  85. package/lib/archive/db-ops/lifecycle/checkpoint.js +9 -0
  86. package/lib/archive/db-ops/lifecycle/destroy.d.ts +6 -0
  87. package/lib/archive/db-ops/lifecycle/destroy.js +7 -0
  88. package/lib/archive/db-ops/lifecycle/init.d.ts +22 -0
  89. package/lib/archive/db-ops/lifecycle/init.js +42 -0
  90. package/lib/archive/db-ops/meta/get-jsonld-of-page.d.ts +13 -0
  91. package/lib/archive/db-ops/meta/get-jsonld-of-page.js +27 -0
  92. package/lib/archive/db-ops/meta/get-tags-of-page.d.ts +12 -0
  93. package/lib/archive/db-ops/meta/get-tags-of-page.js +28 -0
  94. package/lib/archive/db-ops/pages/order/set-url-order.d.ts +8 -0
  95. package/lib/archive/db-ops/pages/order/set-url-order.js +32 -0
  96. package/lib/archive/db-ops/pages/read/build-page-query.d.ts +18 -0
  97. package/lib/archive/db-ops/pages/read/build-page-query.js +40 -0
  98. package/lib/archive/db-ops/pages/read/get-crawling-state.d.ts +70 -0
  99. package/lib/archive/db-ops/pages/read/get-crawling-state.js +98 -0
  100. package/lib/archive/db-ops/pages/read/get-existing-page-urls.d.ts +15 -0
  101. package/lib/archive/db-ops/pages/read/get-existing-page-urls.js +30 -0
  102. package/lib/archive/db-ops/pages/read/get-page-count.d.ts +12 -0
  103. package/lib/archive/db-ops/pages/read/get-page-count.js +21 -0
  104. package/lib/archive/db-ops/pages/read/get-page-source-by-url.d.ts +24 -0
  105. package/lib/archive/db-ops/pages/read/get-page-source-by-url.js +28 -0
  106. package/lib/archive/db-ops/pages/read/get-pages-with-rels.d.ts +38 -0
  107. package/lib/archive/db-ops/pages/read/get-pages-with-rels.js +107 -0
  108. package/lib/archive/db-ops/pages/read/get-pages.d.ts +11 -0
  109. package/lib/archive/db-ops/pages/read/get-pages.js +51 -0
  110. package/lib/archive/db-ops/pages/read/get-scraped-html-page-count.d.ts +18 -0
  111. package/lib/archive/db-ops/pages/read/get-scraped-html-page-count.js +25 -0
  112. package/lib/archive/db-ops/pages/read/reconstruct-page-rows.d.ts +31 -0
  113. package/lib/archive/db-ops/pages/read/reconstruct-page-rows.js +32 -0
  114. package/lib/archive/db-ops/pages/reset/repromote-external-pages.d.ts +24 -0
  115. package/lib/archive/db-ops/pages/reset/repromote-external-pages.js +93 -0
  116. package/lib/archive/db-ops/pages/reset/reset-failed-pages.d.ts +47 -0
  117. package/lib/archive/db-ops/pages/reset/reset-failed-pages.js +124 -0
  118. package/lib/archive/db-ops/pages/write/insert-inventory-seeds.d.ts +37 -0
  119. package/lib/archive/db-ops/pages/write/insert-inventory-seeds.js +72 -0
  120. package/lib/archive/db-ops/pages/write/insert-jsonld.d.ts +17 -0
  121. package/lib/archive/db-ops/pages/write/insert-jsonld.js +49 -0
  122. package/lib/archive/db-ops/pages/write/insert-page.d.ts +36 -0
  123. package/lib/archive/db-ops/pages/write/insert-page.js +208 -0
  124. package/lib/archive/db-ops/pages/write/insert-tags.d.ts +16 -0
  125. package/lib/archive/db-ops/pages/write/insert-tags.js +34 -0
  126. package/lib/archive/db-ops/pages/write/link-redirect-sources.d.ts +36 -0
  127. package/lib/archive/db-ops/pages/write/link-redirect-sources.js +93 -0
  128. package/lib/archive/db-ops/pages/write/record-redirect.d.ts +35 -0
  129. package/lib/archive/db-ops/pages/write/record-redirect.js +100 -0
  130. package/lib/archive/db-ops/pages/write/set-skipped-page.d.ts +13 -0
  131. package/lib/archive/db-ops/pages/write/set-skipped-page.js +22 -0
  132. package/lib/archive/db-ops/pages/write/update-page.d.ts +29 -0
  133. package/lib/archive/db-ops/pages/write/update-page.js +334 -0
  134. package/lib/archive/db-ops/pages/write/write-page-html-blob.d.ts +19 -0
  135. package/lib/archive/db-ops/pages/write/write-page-html-blob.js +41 -0
  136. package/lib/archive/db-ops/referrers/get-redirects-for-pages.d.ts +9 -0
  137. package/lib/archive/db-ops/referrers/get-redirects-for-pages.js +15 -0
  138. package/lib/archive/db-ops/referrers/get-referrers-of-page.d.ts +17 -0
  139. package/lib/archive/db-ops/referrers/get-referrers-of-page.js +32 -0
  140. package/lib/archive/db-ops/referrers/get-referrers-of-resource.d.ts +8 -0
  141. package/lib/archive/db-ops/referrers/get-referrers-of-resource.js +15 -0
  142. package/lib/archive/db-ops/resources/build-resource-query.d.ts +25 -0
  143. package/lib/archive/db-ops/resources/build-resource-query.js +29 -0
  144. package/lib/archive/db-ops/resources/get-existing-resource-urls.d.ts +9 -0
  145. package/lib/archive/db-ops/resources/get-existing-resource-urls.js +24 -0
  146. package/lib/archive/db-ops/resources/get-resource-by-url.d.ts +13 -0
  147. package/lib/archive/db-ops/resources/get-resource-by-url.js +22 -0
  148. package/lib/archive/db-ops/resources/get-resource-url-list.d.ts +9 -0
  149. package/lib/archive/db-ops/resources/get-resource-url-list.js +13 -0
  150. package/lib/archive/db-ops/resources/get-resources.d.ts +8 -0
  151. package/lib/archive/db-ops/resources/get-resources.js +11 -0
  152. package/lib/archive/db-ops/resources/insert-inventory-resources.d.ts +24 -0
  153. package/lib/archive/db-ops/resources/insert-inventory-resources.js +64 -0
  154. package/lib/archive/db-ops/resources/insert-resource-referrers.d.ts +15 -0
  155. package/lib/archive/db-ops/resources/insert-resource-referrers.js +54 -0
  156. package/lib/archive/db-ops/resources/insert-resource.d.ts +34 -0
  157. package/lib/archive/db-ops/resources/insert-resource.js +73 -0
  158. package/lib/archive/db-ops/resources/reconstruct-resource-rows.d.ts +26 -0
  159. package/lib/archive/db-ops/resources/reconstruct-resource-rows.js +30 -0
  160. package/lib/archive/decode-html-blob.d.ts +18 -0
  161. package/lib/archive/decode-html-blob.js +31 -0
  162. package/lib/archive/derive-lineage-from-parent.d.ts +37 -0
  163. package/lib/archive/derive-lineage-from-parent.js +42 -0
  164. package/lib/archive/drop-legacy-tables.d.ts +45 -0
  165. package/lib/archive/drop-legacy-tables.js +56 -0
  166. package/lib/archive/filesystem/rename.js +1 -1
  167. package/lib/archive/get-failed-page-messages.d.ts +44 -0
  168. package/lib/archive/get-failed-page-messages.js +132 -0
  169. package/lib/archive/init-schema.d.ts +35 -39
  170. package/lib/archive/init-schema.js +111 -320
  171. package/lib/archive/is-inventory-source.d.ts +21 -0
  172. package/lib/archive/is-inventory-source.js +22 -0
  173. package/lib/archive/limited-page-ids.d.ts +2 -1
  174. package/lib/archive/limited-page-ids.js +5 -4
  175. package/lib/archive/meta/assert-compatible-version.d.ts +24 -3
  176. package/lib/archive/meta/assert-compatible-version.js +24 -3
  177. package/lib/archive/meta/types.d.ts +87 -1
  178. package/lib/archive/meta/types.js +34 -2
  179. package/lib/archive/migrate-entity-tables.d.ts +45 -0
  180. package/lib/archive/migrate-entity-tables.js +56 -0
  181. package/lib/archive/migrate-ref-tables.d.ts +25 -0
  182. package/lib/archive/migrate-ref-tables.js +38 -0
  183. package/lib/archive/page-meta-column-maps.d.ts +32 -0
  184. package/lib/archive/page-meta-column-maps.js +43 -0
  185. package/lib/archive/page.d.ts +6 -6
  186. package/lib/archive/page.js +5 -5
  187. package/lib/archive/peek-archive-lock.d.ts +2 -2
  188. package/lib/archive/peek-archive-lock.js +2 -2
  189. package/lib/archive/populate-entity-tables/collapse-anchor-rows.d.ts +41 -0
  190. package/lib/archive/populate-entity-tables/collapse-anchor-rows.js +87 -0
  191. package/lib/archive/populate-entity-tables/derive-dom-path.d.ts +35 -0
  192. package/lib/archive/populate-entity-tables/derive-dom-path.js +72 -0
  193. package/lib/archive/populate-entity-tables/is-blob-ref-value.d.ts +16 -0
  194. package/lib/archive/populate-entity-tables/is-blob-ref-value.js +19 -0
  195. package/lib/archive/populate-entity-tables/match-images-to-dom-paths.d.ts +66 -0
  196. package/lib/archive/populate-entity-tables/match-images-to-dom-paths.js +96 -0
  197. package/lib/archive/populate-entity-tables/populate-anchor-edges.d.ts +33 -0
  198. package/lib/archive/populate-entity-tables/populate-anchor-edges.js +153 -0
  199. package/lib/archive/populate-entity-tables/populate-content-items.d.ts +40 -0
  200. package/lib/archive/populate-entity-tables/populate-content-items.js +141 -0
  201. package/lib/archive/populate-entity-tables/populate-entities.d.ts +81 -0
  202. package/lib/archive/populate-entity-tables/populate-entities.js +111 -0
  203. package/lib/archive/populate-entity-tables/populate-image-items.d.ts +91 -0
  204. package/lib/archive/populate-entity-tables/populate-image-items.js +223 -0
  205. package/lib/archive/populate-entity-tables/populate-page-meta.d.ts +33 -0
  206. package/lib/archive/populate-entity-tables/populate-page-meta.js +267 -0
  207. package/lib/archive/populate-entity-tables/populate-resource-items.d.ts +22 -0
  208. package/lib/archive/populate-entity-tables/populate-resource-items.js +114 -0
  209. package/lib/archive/populate-entity-tables/populate-resource-ref-edges.d.ts +31 -0
  210. package/lib/archive/populate-entity-tables/populate-resource-ref-edges.js +33 -0
  211. package/lib/archive/populate-entity-tables/resolve-blob-refs.d.ts +31 -0
  212. package/lib/archive/populate-entity-tables/resolve-blob-refs.js +100 -0
  213. package/lib/archive/populate-entity-tables/resolve-content-type-refs.d.ts +22 -0
  214. package/lib/archive/populate-entity-tables/resolve-content-type-refs.js +27 -0
  215. package/lib/archive/populate-entity-tables/resolve-header-sets.d.ts +49 -0
  216. package/lib/archive/populate-entity-tables/resolve-header-sets.js +122 -0
  217. package/lib/archive/populate-entity-tables/resolve-json-refs.d.ts +25 -0
  218. package/lib/archive/populate-entity-tables/resolve-json-refs.js +67 -0
  219. package/lib/archive/populate-entity-tables/resolve-text-refs.d.ts +30 -0
  220. package/lib/archive/populate-entity-tables/resolve-text-refs.js +61 -0
  221. package/lib/archive/populate-entity-tables/resolve-url-or-blob-from-maps.d.ts +21 -0
  222. package/lib/archive/populate-entity-tables/resolve-url-or-blob-from-maps.js +27 -0
  223. package/lib/archive/populate-entity-tables/resolve-url-refs.d.ts +33 -0
  224. package/lib/archive/populate-entity-tables/resolve-url-refs.js +60 -0
  225. package/lib/archive/populate-entity-tables/test-utils/count-rows.d.ts +17 -0
  226. package/lib/archive/populate-entity-tables/test-utils/count-rows.js +20 -0
  227. package/lib/archive/populate-entity-tables/test-utils/seed-content-items.d.ts +25 -0
  228. package/lib/archive/populate-entity-tables/test-utils/seed-content-items.js +42 -0
  229. package/lib/archive/populate-entity-tables/test-utils/setup-entities-db.d.ts +23 -0
  230. package/lib/archive/populate-entity-tables/test-utils/setup-entities-db.js +178 -0
  231. package/lib/archive/populate-entity-tables/types.d.ts +157 -0
  232. package/lib/archive/populate-entity-tables/types.js +12 -0
  233. package/lib/archive/populate-entity-tables/upsert-text-refs.d.ts +38 -0
  234. package/lib/archive/populate-entity-tables/upsert-text-refs.js +78 -0
  235. package/lib/archive/populate-ref-tables/classify-content-type.d.ts +16 -0
  236. package/lib/archive/populate-ref-tables/classify-content-type.js +52 -0
  237. package/lib/archive/populate-ref-tables/compute-content-hash.d.ts +22 -0
  238. package/lib/archive/populate-ref-tables/compute-content-hash.js +26 -0
  239. package/lib/archive/populate-ref-tables/compute-header-flags.d.ts +16 -0
  240. package/lib/archive/populate-ref-tables/compute-header-flags.js +70 -0
  241. package/lib/archive/populate-ref-tables/content-type-rules.d.ts +38 -0
  242. package/lib/archive/populate-ref-tables/content-type-rules.js +133 -0
  243. package/lib/archive/populate-ref-tables/create-header-table-caches.d.ts +25 -0
  244. package/lib/archive/populate-ref-tables/create-header-table-caches.js +49 -0
  245. package/lib/archive/populate-ref-tables/data-uri-url-refs-limit.d.ts +15 -0
  246. package/lib/archive/populate-ref-tables/data-uri-url-refs-limit.js +15 -0
  247. package/lib/archive/populate-ref-tables/decode-data-uri.d.ts +21 -0
  248. package/lib/archive/populate-ref-tables/decode-data-uri.js +126 -0
  249. package/lib/archive/populate-ref-tables/decompose-header-set.d.ts +29 -0
  250. package/lib/archive/populate-ref-tables/decompose-header-set.js +157 -0
  251. package/lib/archive/populate-ref-tables/decompose-url.d.ts +25 -0
  252. package/lib/archive/populate-ref-tables/decompose-url.js +70 -0
  253. package/lib/archive/populate-ref-tables/header-stability.d.ts +19 -0
  254. package/lib/archive/populate-ref-tables/header-stability.js +22 -0
  255. package/lib/archive/populate-ref-tables/header-value-cache-key.d.ts +17 -0
  256. package/lib/archive/populate-ref-tables/header-value-cache-key.js +19 -0
  257. package/lib/archive/populate-ref-tables/normalize-mime.d.ts +24 -0
  258. package/lib/archive/populate-ref-tables/normalize-mime.js +36 -0
  259. package/lib/archive/populate-ref-tables/populate-blob-refs.d.ts +38 -0
  260. package/lib/archive/populate-ref-tables/populate-blob-refs.js +134 -0
  261. package/lib/archive/populate-ref-tables/populate-content-type-refs.d.ts +27 -0
  262. package/lib/archive/populate-ref-tables/populate-content-type-refs.js +70 -0
  263. package/lib/archive/populate-ref-tables/populate-header-tables.d.ts +35 -0
  264. package/lib/archive/populate-ref-tables/populate-header-tables.js +80 -0
  265. package/lib/archive/populate-ref-tables/populate-json-refs.d.ts +29 -0
  266. package/lib/archive/populate-ref-tables/populate-json-refs.js +101 -0
  267. package/lib/archive/populate-ref-tables/populate-refs.d.ts +51 -0
  268. package/lib/archive/populate-ref-tables/populate-refs.js +62 -0
  269. package/lib/archive/populate-ref-tables/populate-text-refs.d.ts +32 -0
  270. package/lib/archive/populate-ref-tables/populate-text-refs.js +133 -0
  271. package/lib/archive/populate-ref-tables/populate-url-refs.d.ts +28 -0
  272. package/lib/archive/populate-ref-tables/populate-url-refs.js +148 -0
  273. package/lib/archive/populate-ref-tables/test-utils/count-rows.d.ts +15 -0
  274. package/lib/archive/populate-ref-tables/test-utils/count-rows.js +17 -0
  275. package/lib/archive/populate-ref-tables/types.d.ts +197 -0
  276. package/lib/archive/populate-ref-tables/types.js +7 -0
  277. package/lib/archive/populate-ref-tables/upsert-one-header-set.d.ts +34 -0
  278. package/lib/archive/populate-ref-tables/upsert-one-header-set.js +208 -0
  279. package/lib/archive/populate-ref-tables/volatile-header-names.d.ts +20 -0
  280. package/lib/archive/populate-ref-tables/volatile-header-names.js +33 -0
  281. package/lib/archive/redirect-table.d.ts +4 -2
  282. package/lib/archive/redirect-table.js +15 -10
  283. package/lib/archive/resolve-redirect-chain.d.ts +3 -3
  284. package/lib/archive/resolve-redirect-chain.js +2 -2
  285. package/lib/archive/resource.d.ts +1 -1
  286. package/lib/archive/retarget-legacy-fk-tables.d.ts +47 -0
  287. package/lib/archive/retarget-legacy-fk-tables.js +107 -0
  288. package/lib/archive/test-utils/fk-parent-tables.d.ts +15 -0
  289. package/lib/archive/test-utils/fk-parent-tables.js +19 -0
  290. package/lib/archive/test-utils/seed-content-item.d.ts +35 -0
  291. package/lib/archive/test-utils/seed-content-item.js +42 -0
  292. package/lib/archive/test-utils/setup-legacy-fk-db.d.ts +33 -0
  293. package/lib/archive/test-utils/setup-legacy-fk-db.js +270 -0
  294. package/lib/archive/types.d.ts +151 -15
  295. package/lib/archive/verify-migration/capture-rejection.d.ts +24 -0
  296. package/lib/archive/verify-migration/capture-rejection.js +31 -0
  297. package/lib/archive/verify-migration/check-anchor-edges-count.d.ts +34 -0
  298. package/lib/archive/verify-migration/check-anchor-edges-count.js +72 -0
  299. package/lib/archive/verify-migration/check-anchor-edges-sum.d.ts +13 -0
  300. package/lib/archive/verify-migration/check-anchor-edges-sum.js +27 -0
  301. package/lib/archive/verify-migration/check-content-items-count.d.ts +16 -0
  302. package/lib/archive/verify-migration/check-content-items-count.js +30 -0
  303. package/lib/archive/verify-migration/check-content-type-preservation.d.ts +22 -0
  304. package/lib/archive/verify-migration/check-content-type-preservation.js +40 -0
  305. package/lib/archive/verify-migration/check-foreign-key-integrity.d.ts +31 -0
  306. package/lib/archive/verify-migration/check-foreign-key-integrity.js +47 -0
  307. package/lib/archive/verify-migration/check-image-items-count.d.ts +12 -0
  308. package/lib/archive/verify-migration/check-image-items-count.js +26 -0
  309. package/lib/archive/verify-migration/check-page-meta-count.d.ts +15 -0
  310. package/lib/archive/verify-migration/check-page-meta-count.js +31 -0
  311. package/lib/archive/verify-migration/check-reader-parity.d.ts +23 -0
  312. package/lib/archive/verify-migration/check-reader-parity.js +211 -0
  313. package/lib/archive/verify-migration/check-resource-items-count.d.ts +17 -0
  314. package/lib/archive/verify-migration/check-resource-items-count.js +33 -0
  315. package/lib/archive/verify-migration/check-url-round-trip.d.ts +43 -0
  316. package/lib/archive/verify-migration/check-url-round-trip.js +112 -0
  317. package/lib/archive/verify-migration/types.d.ts +70 -0
  318. package/lib/archive/verify-migration/types.js +63 -0
  319. package/lib/archive/verify-migration/verify-migration.d.ts +41 -0
  320. package/lib/archive/verify-migration/verify-migration.js +120 -0
  321. package/lib/classify-error-kind.d.ts +19 -0
  322. package/lib/classify-error-kind.js +122 -0
  323. package/lib/crawler/build-js-redirect-edge.d.ts +68 -0
  324. package/lib/crawler/build-js-redirect-edge.js +57 -0
  325. package/lib/crawler/build-redirect-event.d.ts +24 -0
  326. package/lib/crawler/build-redirect-event.js +28 -0
  327. package/lib/crawler/capture-image-dom-paths.d.ts +33 -0
  328. package/lib/crawler/capture-image-dom-paths.js +39 -0
  329. package/lib/crawler/clear-dns-burned-host-cache.d.ts +6 -0
  330. package/lib/crawler/clear-dns-burned-host-cache.js +11 -0
  331. package/lib/crawler/collect-image-dom-paths.d.ts +23 -0
  332. package/lib/crawler/collect-image-dom-paths.js +64 -0
  333. package/lib/crawler/crawler.d.ts +22 -1
  334. package/lib/crawler/crawler.js +679 -117
  335. package/lib/crawler/derive-js-redirect-target.d.ts +68 -0
  336. package/lib/crawler/derive-js-redirect-target.js +129 -0
  337. package/lib/crawler/derive-resource-source.d.ts +25 -15
  338. package/lib/crawler/derive-resource-source.js +28 -17
  339. package/lib/crawler/dns-burned-host-cache.d.ts +26 -0
  340. package/lib/crawler/dns-burned-host-cache.js +25 -0
  341. package/lib/crawler/dns-burned-host-short-circuit-counter.d.ts +13 -0
  342. package/lib/crawler/dns-burned-host-short-circuit-counter.js +11 -0
  343. package/lib/crawler/fetch-destination.d.ts +12 -4
  344. package/lib/crawler/fetch-destination.js +94 -16
  345. package/lib/crawler/inject-scope-auth.d.ts +1 -1
  346. package/lib/crawler/inject-scope-auth.js +1 -1
  347. package/lib/crawler/is-js-redirect-error-shape.d.ts +40 -0
  348. package/lib/crawler/is-js-redirect-error-shape.js +53 -0
  349. package/lib/crawler/is-puppeteer-fallback-candidate.d.ts +16 -0
  350. package/lib/crawler/is-puppeteer-fallback-candidate.js +63 -0
  351. package/lib/crawler/link-list.d.ts +21 -1
  352. package/lib/crawler/link-list.js +23 -3
  353. package/lib/crawler/normalize-content-type.d.ts +1 -1
  354. package/lib/crawler/normalize-content-type.js +1 -1
  355. package/lib/crawler/plan-sub-resource-emits.d.ts +63 -0
  356. package/lib/crawler/plan-sub-resource-emits.js +44 -0
  357. package/lib/crawler/preload-short-circuit-error.d.ts +22 -0
  358. package/lib/crawler/preload-short-circuit-error.js +25 -0
  359. package/lib/crawler/should-burn-host.d.ts +78 -0
  360. package/lib/crawler/should-burn-host.js +61 -0
  361. package/lib/crawler/should-get-fallback-on-head-failure.d.ts +38 -0
  362. package/lib/crawler/should-get-fallback-on-head-failure.js +46 -0
  363. package/lib/crawler/types.d.ts +108 -1
  364. package/lib/crawler-orchestrator.d.ts +22 -3
  365. package/lib/crawler-orchestrator.js +312 -73
  366. package/lib/crawler.d.ts +15 -2
  367. package/lib/crawler.js +24 -1
  368. package/lib/permanent-error-kinds.d.ts +43 -0
  369. package/lib/permanent-error-kinds.js +48 -0
  370. package/lib/types.d.ts +84 -0
  371. package/lib/utils/compute-file-sha256.d.ts +24 -0
  372. package/lib/utils/compute-file-sha256.js +56 -0
  373. package/lib/utils/error/emit-error-with-retry.d.ts +40 -0
  374. package/lib/utils/error/emit-error-with-retry.js +44 -0
  375. package/lib/utils/error/emit-error.d.ts +39 -0
  376. package/lib/utils/error/emit-error.js +41 -0
  377. package/package.json +12 -12
  378. package/lib/archive/migrate-crawl-errors.d.ts +0 -20
  379. package/lib/archive/migrate-crawl-errors.js +0 -38
  380. package/lib/archive/migrate-html-blob-tables.d.ts +0 -24
  381. package/lib/archive/migrate-html-blob-tables.js +0 -53
  382. package/lib/archive/migrate-page-errors.d.ts +0 -16
  383. package/lib/archive/migrate-page-errors.js +0 -35
  384. package/lib/archive/migrate-pages-resources-source.d.ts +0 -16
  385. package/lib/archive/migrate-pages-resources-source.js +0 -46
  386. package/lib/utils/error/error-emitter.d.ts +0 -18
  387. package/lib/utils/error/error-emitter.js +0 -29
@@ -1,35 +0,0 @@
1
- /**
2
- * Adds the `page_errors` table to archives created before partial-failure
3
- * recording landed.
4
- *
5
- * `page_errors` captures secondary scrape failures (e.g. a viewport switch
6
- * that detaches the frame and surfaces `retryExhausted`) so they show up in
7
- * the archive instead of being lost to stdout logs. Older `.nitpicker` files
8
- * predate this table; this migration creates it idempotently.
9
- *
10
- * Idempotent: when the table already exists, the function exits without
11
- * touching the schema or writing to stderr. When it has to run, a single
12
- * notice is written so the user knows the file was upgraded.
13
- * @param instance - The Knex query builder instance connected to the database.
14
- */
15
- export async function migratePageErrors(instance) {
16
- const hasTable = await instance.schema.hasTable('page_errors');
17
- if (hasTable) {
18
- return;
19
- }
20
- const hasPages = await instance.schema.hasTable('pages');
21
- if (!hasPages) {
22
- // Empty archive; the regular initSchema path will create both tables.
23
- return;
24
- }
25
- await instance.schema.createTable('page_errors', (t) => {
26
- t.increments('id');
27
- t.integer('pageId').notNullable().unsigned().references('pages.id');
28
- t.string('phase').notNullable();
29
- t.text('message').notNullable();
30
- t.integer('createdAt').notNullable();
31
- t.index('pageId');
32
- });
33
- // eslint-disable-next-line no-console
34
- console.error('[migrate] page_errors table created');
35
- }
@@ -1,16 +0,0 @@
1
- import type { Knex } from 'knex';
2
- /**
3
- * Add `pages.source` and `resources.source` columns (provenance taxonomy:
4
- * `crawled` / `inventory-seed` / `inventory-discovered`) and their indexes
5
- * to archives that pre-date the `crawl --inventory` feature.
6
- *
7
- * Idempotent: a no-op when both columns already exist. SQLite's
8
- * `ALTER TABLE ADD COLUMN` with a NOT NULL DEFAULT applies the default to
9
- * every existing row at column-add time, so no explicit `UPDATE` is needed
10
- * to backfill — pre-existing rows become `'crawled'` automatically.
11
- *
12
- * Runs only on writer-side {@link Database.connect}; read-only viewer
13
- * attaches skip this so the user's tmpDir is never rewritten.
14
- * @param instance - The Knex query builder instance connected to the database.
15
- */
16
- export declare function migratePagesResourcesSource(instance: Knex): Promise<void>;
@@ -1,46 +0,0 @@
1
- /**
2
- * Add `pages.source` and `resources.source` columns (provenance taxonomy:
3
- * `crawled` / `inventory-seed` / `inventory-discovered`) and their indexes
4
- * to archives that pre-date the `crawl --inventory` feature.
5
- *
6
- * Idempotent: a no-op when both columns already exist. SQLite's
7
- * `ALTER TABLE ADD COLUMN` with a NOT NULL DEFAULT applies the default to
8
- * every existing row at column-add time, so no explicit `UPDATE` is needed
9
- * to backfill — pre-existing rows become `'crawled'` automatically.
10
- *
11
- * Runs only on writer-side {@link Database.connect}; read-only viewer
12
- * attaches skip this so the user's tmpDir is never rewritten.
13
- * @param instance - The Knex query builder instance connected to the database.
14
- */
15
- export async function migratePagesResourcesSource(instance) {
16
- const hasPages = await instance.schema.hasTable('pages');
17
- const hasResources = await instance.schema.hasTable('resources');
18
- if (!hasPages && !hasResources) {
19
- return;
20
- }
21
- const hasPagesSource = hasPages && (await instance.schema.hasColumn('pages', 'source'));
22
- const hasResourcesSource = hasResources && (await instance.schema.hasColumn('resources', 'source'));
23
- if (hasPagesSource && hasResourcesSource) {
24
- return;
25
- }
26
- const changes = [];
27
- if (hasPages && !hasPagesSource) {
28
- await instance.schema.table('pages', (t) => {
29
- t.string('source').notNullable().defaultTo('crawled');
30
- t.index('source');
31
- });
32
- changes.push('pages.source added');
33
- }
34
- if (hasResources && !hasResourcesSource) {
35
- await instance.schema.table('resources', (t) => {
36
- t.string('source').notNullable().defaultTo('crawled');
37
- t.index('source');
38
- });
39
- changes.push('resources.source added');
40
- }
41
- if (changes.length === 0) {
42
- return;
43
- }
44
- // eslint-disable-next-line no-console
45
- console.error(`[migrate] ${changes.join(', ')}`);
46
- }
@@ -1,18 +0,0 @@
1
- import type { TypedAwaitEventEmitter as EventEmitter } from '@d-zero/shared/typed-await-event-emitter';
2
- /**
3
- * Event payload type for error events emitted by classes using the {@link ErrorEmitter} decorator.
4
- * @template E - The specific error type, defaults to `Error`.
5
- */
6
- export type ErrorEvent<E extends Error = Error> = {
7
- /** The error instance that was caught. */
8
- error: E;
9
- };
10
- /**
11
- * A class method decorator factory that wraps the decorated method with error handling.
12
- * When the method throws an `Error`, it emits an `'error'` event on the class instance
13
- * (which must extend {@link EventEmitter}) with the caught error, then re-throws the error.
14
- * @template C - The class type, which must be an EventEmitter capable of emitting error events.
15
- * @template E - The error event type, defaults to {@link ErrorEvent}.
16
- * @returns A decorator function that wraps the target method with error-emitting behavior.
17
- */
18
- export declare function ErrorEmitter<C extends EventEmitter<E>, E extends ErrorEvent = ErrorEvent>(): (method: Function, context: ClassMethodDecoratorContext) => (this: C, ...args: unknown[]) => Promise<any>;
@@ -1,29 +0,0 @@
1
- import { log } from '../debug.js';
2
- const errorLog = log.extend('ErrorEmitter');
3
- /**
4
- * A class method decorator factory that wraps the decorated method with error handling.
5
- * When the method throws an `Error`, it emits an `'error'` event on the class instance
6
- * (which must extend {@link EventEmitter}) with the caught error, then re-throws the error.
7
- * @template C - The class type, which must be an EventEmitter capable of emitting error events.
8
- * @template E - The error event type, defaults to {@link ErrorEvent}.
9
- * @returns A decorator function that wraps the target method with error-emitting behavior.
10
- */
11
- export function ErrorEmitter() {
12
- // eslint-disable-next-line @typescript-eslint/no-unsafe-function-type
13
- return (method, context) => {
14
- return async function (...args) {
15
- const constructorName = String(this.constructor?.name || this.constructor || this);
16
- const methodName = `${constructorName}.${String(context.name)}`;
17
- try {
18
- return await method.apply(this, args);
19
- }
20
- catch (error) {
21
- if (error instanceof Error) {
22
- errorLog('%s: %O', methodName, error);
23
- void this.emit('error', error);
24
- }
25
- throw error;
26
- }
27
- };
28
- };
29
- }