@mailwoman/corpus 10.0.0 → 10.2.0

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 (1382) hide show
  1. package/README.md +120 -34
  2. package/data/PROVENANCE.md +623 -17
  3. package/data/address-source-register.json +14249 -0
  4. package/data/builds/v0.7.0-de-holdout/inputs.json +22 -0
  5. package/data/builds/v0.8.0-registers/inputs.json +92 -0
  6. package/data/license-decisions.json +1603 -0
  7. package/data/licenses/PROVENANCE.md +65 -0
  8. package/data/licenses/cdla-permissive-2.0.md +43 -0
  9. package/data/licenses/geonames-publication.md +34 -0
  10. package/data/licenses/licence-ouverte-2.0.md +36 -0
  11. package/data/licenses/national-address-database.md +46 -0
  12. package/data/licenses/nlod-2.0.md +90 -0
  13. package/data/licenses/sirene-publication.md +38 -0
  14. package/data/licenses/whosonfirst-licenses.md +65 -0
  15. package/data/source-resolutions.json +804 -0
  16. package/data/sub-venue-lexicon.json +1 -1
  17. package/data/training-manifests/v0.7.0-de-holdout.effective.json +477 -0
  18. package/data/training-manifests/v0.7.0-de-holdout.json +78 -0
  19. package/lib/adapters/cordis/adapter.ts +791 -0
  20. package/lib/adapters/dedup-key.ts +40 -0
  21. package/lib/adapters/errors.ts +21 -0
  22. package/lib/adapters/geonames/adapter.ts +43 -53
  23. package/lib/adapters/geonames/postal/adapter.ts +31 -37
  24. package/lib/adapters/gleif/adapter.ts +829 -0
  25. package/lib/adapters/libpostal-dictionary.ts +37 -0
  26. package/lib/adapters/openaddresses/adapter.ts +52 -55
  27. package/lib/adapters/osm/adapter.ts +162 -83
  28. package/lib/adapters/overture/adapter.ts +52 -43
  29. package/lib/adapters/po-box/adapter.ts +207 -0
  30. package/lib/adapters/registry.ts +79 -0
  31. package/lib/adapters/sha256-stream.ts +49 -0
  32. package/lib/adapters/source-id.ts +49 -0
  33. package/lib/adapters/street-line.ts +136 -0
  34. package/lib/adapters/wof/admin/json/adapter.ts +50 -35
  35. package/lib/adapters/wof/json-rows.ts +57 -26
  36. package/lib/adapters/wof/postalcode-json/adapter.ts +63 -61
  37. package/lib/adapters.ts +230 -0
  38. package/lib/au/adapters/gnaf/adapter.ts +36 -44
  39. package/lib/au/adapters/gnaf/assemble.ts +31 -51
  40. package/lib/be/adapters/brussels/adapter.ts +566 -0
  41. package/lib/be/adapters/vlaanderen/adapter.ts +667 -0
  42. package/lib/be/adapters/wallonie/adapter.ts +537 -0
  43. package/lib/be/tools/fetch/brussels.ts +242 -0
  44. package/lib/be/tools/fetch/wallonie.ts +275 -0
  45. package/lib/build/adapters.ts +111 -0
  46. package/lib/build/align.ts +365 -0
  47. package/lib/build/checkpoint.ts +133 -0
  48. package/lib/build/eligibility.ts +96 -0
  49. package/lib/build/heap.ts +53 -0
  50. package/lib/build/inputs.ts +81 -0
  51. package/lib/build/rows.ts +21 -0
  52. package/lib/build/types.ts +234 -0
  53. package/lib/build.ts +127 -315
  54. package/lib/cn/recipes/organizational-units.ts +20 -41
  55. package/lib/cz/adapters/cuzk/adapter.ts +320 -0
  56. package/lib/cz/recipes/pcfirst-preposition.ts +40 -27
  57. package/lib/cz/tools/fetch/cuzk.ts +710 -0
  58. package/lib/de/recipes/locale.ts +69 -59
  59. package/lib/directory.ts +31 -0
  60. package/lib/dk/adapters/inspire/adapter.ts +345 -0
  61. package/lib/dk/tools/fetch/inspire.ts +323 -0
  62. package/lib/ee/adapters/ads/adapter.ts +240 -0
  63. package/lib/ee/tools/fetch/ads.ts +272 -0
  64. package/lib/env.ts +6 -2
  65. package/lib/es/adapters/bizkaia/adapter.ts +388 -0
  66. package/lib/es/adapters/catastro/adapter.ts +345 -0
  67. package/lib/es/adapters/gipuzkoa/adapter.ts +256 -0
  68. package/lib/es/adapters/navarra/adapter.ts +290 -0
  69. package/lib/es/cadastre.ts +194 -0
  70. package/lib/es/tools/fetch/bizkaia.ts +752 -0
  71. package/lib/es/tools/fetch/catastro.ts +765 -0
  72. package/lib/es/tools/fetch/gipuzkoa.ts +338 -0
  73. package/lib/es/tools/fetch/navarra.ts +496 -0
  74. package/lib/fi/adapters/ryhti/adapter.ts +319 -0
  75. package/lib/fi/tools/fetch/ryhti.ts +476 -0
  76. package/lib/fingerprints.ts +154 -0
  77. package/lib/fr/adapters/annuaire-education/adapter.ts +600 -0
  78. package/lib/fr/adapters/ban/adapter.ts +87 -59
  79. package/lib/fr/adapters/finess/adapter.ts +619 -0
  80. package/lib/fr/adapters/finess/postal-lines.ts +157 -0
  81. package/lib/fr/adapters/finess/voie-type.ts +201 -0
  82. package/lib/fr/insee-country.ts +62 -0
  83. package/lib/fr/recipes/admin-split.ts +38 -60
  84. package/lib/fr/recipes/bare-street.ts +37 -50
  85. package/lib/fr/recipes/fragment.ts +59 -142
  86. package/lib/fr/recipes/lieudit.ts +111 -73
  87. package/lib/fr/recipes/order.ts +32 -59
  88. package/lib/fr/{adapters/ban/street-decompose.ts → street-decompose.ts} +4 -3
  89. package/lib/fr/tools/fetch/annuaire-education.ts +309 -0
  90. package/lib/fr/tools/fetch/ban.ts +30 -20
  91. package/lib/fr/tools/fetch/finess.ts +353 -0
  92. package/lib/gauntlet-inputs.ts +92 -0
  93. package/lib/index.ts +9 -3
  94. package/lib/inspire/address.ts +465 -0
  95. package/lib/inspire/archive.ts +44 -0
  96. package/lib/inspire/errors.ts +72 -0
  97. package/lib/inspire/stream.ts +265 -0
  98. package/lib/international/recipes/locale.ts +146 -184
  99. package/lib/it/adapters/anac/adapter.ts +527 -0
  100. package/lib/it/tools/fetch/anac.ts +391 -0
  101. package/lib/jp/adapters/wof-admin/adapter.ts +29 -23
  102. package/lib/jp/tools/fetch/houjin.ts +19 -21
  103. package/lib/kr/adapters/juso/label-rows.ts +24 -44
  104. package/lib/kr/adapters/localdata/align.ts +20 -31
  105. package/lib/kr/adapters/localdata/key-index.ts +17 -25
  106. package/lib/kr/adapters/localdata/permit-rows.ts +34 -27
  107. package/lib/kr/tools/fetch/juso.ts +19 -21
  108. package/lib/kr/tools/fetch/localdata.ts +29 -30
  109. package/lib/lu/adapters/bd-adresses/adapter.ts +240 -0
  110. package/lib/lu/tools/fetch/bd-adresses.ts +353 -0
  111. package/lib/lv/adapters/varis/adapter.ts +500 -0
  112. package/lib/lv/tools/fetch/varis.ts +215 -0
  113. package/lib/nl/adapters/kadaster/adapter.ts +386 -0
  114. package/lib/nl/recipes/postcode.ts +46 -24
  115. package/lib/nl/tools/fetch/kadaster.ts +302 -0
  116. package/lib/no/adapters/matrikkelen/adapter.ts +188 -0
  117. package/lib/no/recipes/fragment.ts +34 -58
  118. package/lib/no/recipes/street/led.ts +44 -25
  119. package/lib/no/recipes/{street/index.ts → street.ts} +29 -11
  120. package/lib/no/tools/fetch/matrikkelen.ts +531 -0
  121. package/lib/parquet/duckdb.ts +147 -0
  122. package/lib/parquet/readers.ts +86 -0
  123. package/lib/parquet/schema.ts +214 -0
  124. package/lib/parquet/shuffle.ts +59 -0
  125. package/lib/parquet/span-sql.ts +54 -0
  126. package/lib/parquet/streams.ts +113 -0
  127. package/lib/parquet/writers.ts +452 -0
  128. package/lib/pl/adapters/emuia/adapter.ts +202 -0
  129. package/lib/pl/tools/fetch/emuia.ts +361 -0
  130. package/lib/recipes/anchor-absorption.ts +30 -19
  131. package/lib/recipes/bare/country.ts +24 -32
  132. package/lib/recipes/bare/postcode/eval.ts +1 -1
  133. package/lib/recipes/bare/postcode.ts +346 -0
  134. package/lib/recipes/boundary-stress.ts +37 -20
  135. package/lib/recipes/country-balanced.ts +66 -86
  136. package/lib/recipes/house-venue.ts +36 -14
  137. package/lib/recipes/intersection.ts +84 -62
  138. package/lib/recipes/po/box/cedex/au-nz.ts +3 -3
  139. package/lib/recipes/po/box/cedex/ca.ts +3 -2
  140. package/lib/recipes/po/box/cedex/fr.ts +4 -3
  141. package/lib/recipes/po/box/cedex/phrases.ts +7 -6
  142. package/lib/recipes/po/box/cedex/recipe.ts +31 -19
  143. package/lib/recipes/po/box/cedex/sources.ts +16 -4
  144. package/lib/recipes/po/box/cedex/us.ts +7 -2
  145. package/lib/recipes/po/{box/index.ts → box.ts} +39 -18
  146. package/lib/recipes/scaffold.ts +267 -158
  147. package/lib/recipes/sources.ts +412 -0
  148. package/lib/recipes/street/affix.ts +54 -154
  149. package/lib/recipes/street/bare.ts +30 -17
  150. package/lib/recipes/street.ts +35 -9
  151. package/lib/recipes/sub/venue/context.ts +32 -23
  152. package/lib/recipes/sub/venue/render.ts +170 -0
  153. package/lib/recipes/sub/venue/sources.ts +92 -248
  154. package/lib/recipes/sub/venue.ts +795 -0
  155. package/lib/recipes/trailing-region.ts +75 -87
  156. package/lib/recipes/unit/sources.ts +44 -0
  157. package/lib/recipes/unit.ts +101 -89
  158. package/lib/recipes/venue.ts +347 -0
  159. package/lib/{recipes/index.ts → recipes.ts} +15 -11
  160. package/lib/registers.ts +280 -0
  161. package/lib/ro/adapters/retea-scolara/adapter.ts +264 -0
  162. package/lib/ro/tools/fetch/retea-scolara.ts +187 -0
  163. package/lib/runner.ts +221 -84
  164. package/lib/sg/recipes/register.ts +47 -53
  165. package/lib/sg/tools/fetch/acra.ts +23 -28
  166. package/lib/si/recipes/bare-village.ts +34 -17
  167. package/lib/sk/adapters/inspire/adapter.ts +393 -0
  168. package/lib/sk/tools/fetch/inspire.ts +403 -0
  169. package/lib/source-register/effective-manifest.ts +659 -0
  170. package/lib/source-register/register.ts +539 -0
  171. package/lib/source-register/training-manifest.ts +218 -0
  172. package/lib/source-register/types.ts +589 -0
  173. package/lib/source-register.ts +71 -0
  174. package/lib/south-asia/recipes/register.ts +45 -26
  175. package/lib/subvenue/harvest.ts +251 -0
  176. package/lib/{tools/sub/venue → subvenue}/promotions.ts +33 -70
  177. package/lib/subvenue/surfaces.ts +94 -0
  178. package/lib/subvenue/table.ts +264 -0
  179. package/lib/surfaces/locale.ts +248 -0
  180. package/lib/synthesizers/anchor-absorption.ts +56 -91
  181. package/lib/synthesizers/boundary-stress.ts +67 -155
  182. package/lib/synthesizers/house-venue.ts +65 -127
  183. package/lib/synthesizers/no-street.ts +71 -119
  184. package/lib/synthesizers/po-box.ts +93 -105
  185. package/lib/synthesizers/tail.ts +55 -0
  186. package/lib/synthesizers/utils.ts +82 -219
  187. package/lib/test-kit/corpus-recipe.ts +45 -28
  188. package/lib/test-kit.ts +116 -0
  189. package/lib/tools/align-canonical.ts +64 -0
  190. package/lib/tools/audit.ts +117 -120
  191. package/lib/tools/corpus-stats.ts +45 -31
  192. package/lib/tools/fetch/atom.ts +164 -0
  193. package/lib/tools/fetch/cordis.ts +320 -0
  194. package/lib/tools/fetch/download/manifest.ts +36 -23
  195. package/lib/tools/fetch/download/network.ts +55 -31
  196. package/lib/tools/fetch/download/retry.ts +30 -29
  197. package/lib/tools/fetch/geonames/dump.ts +75 -55
  198. package/lib/tools/fetch/geonames/postal.ts +27 -62
  199. package/lib/tools/fetch/gleif.ts +362 -0
  200. package/lib/tools/fetch/header.ts +71 -0
  201. package/lib/tools/fetch/inspire-addresses.ts +500 -0
  202. package/lib/tools/fetch/openaddresses.ts +23 -112
  203. package/lib/tools/fetch/ourairports.ts +18 -51
  204. package/lib/tools/fetch/ppd.ts +10 -8
  205. package/lib/tools/fetch/vlaanderen-ad.ts +435 -0
  206. package/lib/tools/fetch/wfs-harvest.ts +954 -0
  207. package/lib/tools/fetch/wikidata-subvenue.ts +45 -145
  208. package/lib/tools/fetch/zip-archive.ts +100 -0
  209. package/lib/tools/fetch.ts +101 -0
  210. package/lib/tools/golden/expand.ts +75 -44
  211. package/lib/tools/golden/promote.ts +47 -34
  212. package/lib/tools/golden/relabel-street/directory.ts +67 -39
  213. package/lib/tools/golden/relabel-street/row.ts +32 -109
  214. package/lib/tools/ingest-csv.ts +48 -51
  215. package/lib/tools/jsonl-to-parquet.ts +59 -98
  216. package/lib/tools/lint/recipe-output/vocab.ts +371 -0
  217. package/lib/tools/lint/{slice/index.ts → recipe-output.ts} +130 -126
  218. package/lib/tools/migrate/overlay-parquet.ts +173 -0
  219. package/lib/tools/migrate/recipe-output.ts +153 -0
  220. package/lib/tools/migrate/source-names.ts +161 -0
  221. package/lib/tools/{slice → overlay}/kryptonite.ts +47 -39
  222. package/lib/tools/overlay/manifest.ts +409 -0
  223. package/lib/tools/overlay/merge-source.ts +139 -0
  224. package/lib/tools/overlay/split-slice.ts +144 -0
  225. package/lib/tools/overlay/translit.ts +236 -0
  226. package/lib/tools/overture-subvenue.ts +18 -91
  227. package/lib/tools/postcode-triples.ts +284 -212
  228. package/lib/tools/source-register/build.ts +822 -0
  229. package/lib/tools/sub/venue/head-nouns.ts +38 -75
  230. package/lib/tools/sub/venue/lexicon.ts +71 -110
  231. package/lib/tools/sub/venue/wikidata.ts +13 -10
  232. package/lib/tw/tools/fetch/gcis.ts +21 -20
  233. package/lib/types.ts +305 -101
  234. package/lib/us/adapters/fcc-bdc/adapter.ts +26 -41
  235. package/lib/us/adapters/state/hi-schools/adapter.ts +28 -17
  236. package/lib/us/adapters/state/hi-schools/workbook.ts +8 -3
  237. package/lib/us/adapters/state/ia-contractors/adapter.ts +27 -15
  238. package/lib/us/adapters/state/ny-notaries/adapter.ts +24 -25
  239. package/lib/us/adapters/state/tx-notaries/adapter.ts +21 -15
  240. package/lib/us/adapters/tiger/adapter.ts +19 -44
  241. package/lib/us/adapters/tiger/street-decompose.ts +7 -17
  242. package/lib/us/adapters/usgov/hrsa-fqhc/adapter.ts +49 -34
  243. package/lib/us/adapters/usgov/imls-pls/adapter.ts +25 -19
  244. package/lib/us/adapters/usgov/irs-bmf/adapter.ts +32 -23
  245. package/lib/us/adapters/usgov/nad/adapter.ts +61 -122
  246. package/lib/us/adapters/usgov/nppes/adapter.ts +72 -35
  247. package/lib/us/adapters/usgov/samhsa-treatment-locator/adapter.ts +47 -34
  248. package/lib/us/fips-state.ts +19 -10
  249. package/lib/{synthesizers → us/synthesizers}/intersection.ts +45 -35
  250. package/lib/{synthesizers → us/synthesizers}/street.ts +56 -43
  251. package/lib/us/tools/fetch/hrsa.ts +7 -8
  252. package/lib/us/tools/fetch/imls-pls.ts +18 -36
  253. package/lib/us/tools/fetch/nad.ts +51 -33
  254. package/lib/us/tools/fetch/nppes.ts +27 -39
  255. package/lib/us/tools/fetch/state/hi-schools.ts +24 -17
  256. package/lib/us/tools/fetch/state/sources.ts +12 -12
  257. package/lib/us/tools/fetch/tiger-full.ts +22 -74
  258. package/lib/utils/align.ts +52 -59
  259. package/lib/utils/{slice-stats.ts → cooccurrence-stats.ts} +22 -16
  260. package/lib/utils/golden.ts +36 -51
  261. package/lib/utils/license.ts +239 -27
  262. package/lib/utils/split.ts +209 -88
  263. package/lib/utils/tokenize.ts +25 -56
  264. package/lib/utils/wof-json.ts +130 -77
  265. package/lib/{utils/index.ts → utils.ts} +0 -1
  266. package/lib/ve/recipes/reviewed-postcode-tail.ts +40 -13
  267. package/out/adapters/cordis/adapter.d.ts +326 -0
  268. package/out/adapters/cordis/adapter.d.ts.map +1 -0
  269. package/out/adapters/cordis/adapter.js +622 -0
  270. package/out/adapters/cordis/adapter.js.map +1 -0
  271. package/out/adapters/dedup-key.d.ts +30 -0
  272. package/out/adapters/dedup-key.d.ts.map +1 -0
  273. package/out/adapters/dedup-key.js +35 -0
  274. package/out/adapters/dedup-key.js.map +1 -0
  275. package/out/adapters/errors.d.ts +17 -0
  276. package/out/adapters/errors.d.ts.map +1 -0
  277. package/out/adapters/errors.js +20 -0
  278. package/out/adapters/errors.js.map +1 -0
  279. package/out/adapters/geonames/adapter.d.ts +26 -28
  280. package/out/adapters/geonames/adapter.d.ts.map +1 -1
  281. package/out/adapters/geonames/adapter.js +40 -50
  282. package/out/adapters/geonames/adapter.js.map +1 -1
  283. package/out/adapters/geonames/postal/adapter.d.ts +14 -27
  284. package/out/adapters/geonames/postal/adapter.d.ts.map +1 -1
  285. package/out/adapters/geonames/postal/adapter.js +30 -35
  286. package/out/adapters/geonames/postal/adapter.js.map +1 -1
  287. package/out/adapters/gleif/adapter.d.ts +293 -0
  288. package/out/adapters/gleif/adapter.d.ts.map +1 -0
  289. package/out/adapters/gleif/adapter.js +685 -0
  290. package/out/adapters/gleif/adapter.js.map +1 -0
  291. package/out/adapters/libpostal-dictionary.d.ts +20 -0
  292. package/out/adapters/libpostal-dictionary.d.ts.map +1 -0
  293. package/out/adapters/libpostal-dictionary.js +34 -0
  294. package/out/adapters/libpostal-dictionary.js.map +1 -0
  295. package/out/adapters/openaddresses/adapter.d.ts +29 -43
  296. package/out/adapters/openaddresses/adapter.d.ts.map +1 -1
  297. package/out/adapters/openaddresses/adapter.js +34 -46
  298. package/out/adapters/openaddresses/adapter.js.map +1 -1
  299. package/out/adapters/osm/adapter.d.ts +59 -52
  300. package/out/adapters/osm/adapter.d.ts.map +1 -1
  301. package/out/adapters/osm/adapter.js +119 -69
  302. package/out/adapters/osm/adapter.js.map +1 -1
  303. package/out/adapters/overture/adapter.d.ts +11 -37
  304. package/out/adapters/overture/adapter.d.ts.map +1 -1
  305. package/out/adapters/overture/adapter.js +45 -42
  306. package/out/adapters/overture/adapter.js.map +1 -1
  307. package/out/adapters/po-box/adapter.d.ts +66 -0
  308. package/out/adapters/po-box/adapter.d.ts.map +1 -0
  309. package/out/adapters/{synth-po-box → po-box}/adapter.js +48 -47
  310. package/out/adapters/po-box/adapter.js.map +1 -0
  311. package/out/adapters/registry.d.ts +55 -0
  312. package/out/adapters/registry.d.ts.map +1 -0
  313. package/out/adapters/registry.js +43 -0
  314. package/out/adapters/registry.js.map +1 -0
  315. package/out/adapters/sha256-stream.d.ts +26 -0
  316. package/out/adapters/sha256-stream.d.ts.map +1 -0
  317. package/out/adapters/sha256-stream.js +34 -0
  318. package/out/adapters/sha256-stream.js.map +1 -0
  319. package/out/adapters/source-id.d.ts +33 -0
  320. package/out/adapters/source-id.d.ts.map +1 -0
  321. package/out/adapters/source-id.js +42 -0
  322. package/out/adapters/source-id.js.map +1 -0
  323. package/out/adapters/street-line.d.ts +103 -0
  324. package/out/adapters/street-line.d.ts.map +1 -0
  325. package/out/adapters/street-line.js +118 -0
  326. package/out/adapters/street-line.js.map +1 -0
  327. package/out/adapters/wof/admin/json/adapter.d.ts +27 -18
  328. package/out/adapters/wof/admin/json/adapter.d.ts.map +1 -1
  329. package/out/adapters/wof/admin/json/adapter.js +48 -32
  330. package/out/adapters/wof/admin/json/adapter.js.map +1 -1
  331. package/out/adapters/wof/json-rows.d.ts +36 -19
  332. package/out/adapters/wof/json-rows.d.ts.map +1 -1
  333. package/out/adapters/wof/json-rows.js +35 -15
  334. package/out/adapters/wof/json-rows.js.map +1 -1
  335. package/out/adapters/wof/postalcode-json/adapter.d.ts +22 -38
  336. package/out/adapters/wof/postalcode-json/adapter.d.ts.map +1 -1
  337. package/out/adapters/wof/postalcode-json/adapter.js +60 -58
  338. package/out/adapters/wof/postalcode-json/adapter.js.map +1 -1
  339. package/out/adapters.d.ts +75 -0
  340. package/out/adapters.d.ts.map +1 -0
  341. package/out/adapters.js +167 -0
  342. package/out/adapters.js.map +1 -0
  343. package/out/au/adapters/gnaf/adapter.d.ts +15 -27
  344. package/out/au/adapters/gnaf/adapter.d.ts.map +1 -1
  345. package/out/au/adapters/gnaf/adapter.js +35 -43
  346. package/out/au/adapters/gnaf/adapter.js.map +1 -1
  347. package/out/au/adapters/gnaf/assemble.d.ts +15 -26
  348. package/out/au/adapters/gnaf/assemble.d.ts.map +1 -1
  349. package/out/au/adapters/gnaf/assemble.js +26 -46
  350. package/out/au/adapters/gnaf/assemble.js.map +1 -1
  351. package/out/be/adapters/brussels/adapter.d.ts +212 -0
  352. package/out/be/adapters/brussels/adapter.d.ts.map +1 -0
  353. package/out/be/adapters/brussels/adapter.js +435 -0
  354. package/out/be/adapters/brussels/adapter.js.map +1 -0
  355. package/out/be/adapters/vlaanderen/adapter.d.ts +230 -0
  356. package/out/be/adapters/vlaanderen/adapter.d.ts.map +1 -0
  357. package/out/be/adapters/vlaanderen/adapter.js +418 -0
  358. package/out/be/adapters/vlaanderen/adapter.js.map +1 -0
  359. package/out/be/adapters/wallonie/adapter.d.ts +196 -0
  360. package/out/be/adapters/wallonie/adapter.d.ts.map +1 -0
  361. package/out/be/adapters/wallonie/adapter.js +437 -0
  362. package/out/be/adapters/wallonie/adapter.js.map +1 -0
  363. package/out/be/tools/fetch/brussels.d.ts +122 -0
  364. package/out/be/tools/fetch/brussels.d.ts.map +1 -0
  365. package/out/be/tools/fetch/brussels.js +148 -0
  366. package/out/be/tools/fetch/brussels.js.map +1 -0
  367. package/out/be/tools/fetch/wallonie.d.ts +120 -0
  368. package/out/be/tools/fetch/wallonie.d.ts.map +1 -0
  369. package/out/be/tools/fetch/wallonie.js +167 -0
  370. package/out/be/tools/fetch/wallonie.js.map +1 -0
  371. package/out/build/adapters.d.ts +33 -0
  372. package/out/build/adapters.d.ts.map +1 -0
  373. package/out/build/adapters.js +69 -0
  374. package/out/build/adapters.js.map +1 -0
  375. package/out/build/align.d.ts +74 -0
  376. package/out/build/align.d.ts.map +1 -0
  377. package/out/build/align.js +226 -0
  378. package/out/build/align.js.map +1 -0
  379. package/out/build/checkpoint.d.ts +94 -0
  380. package/out/build/checkpoint.d.ts.map +1 -0
  381. package/out/build/checkpoint.js +61 -0
  382. package/out/build/checkpoint.js.map +1 -0
  383. package/out/build/eligibility.d.ts +47 -0
  384. package/out/build/eligibility.d.ts.map +1 -0
  385. package/out/build/eligibility.js +80 -0
  386. package/out/build/eligibility.js.map +1 -0
  387. package/out/build/heap.d.ts +28 -0
  388. package/out/build/heap.d.ts.map +1 -0
  389. package/out/build/heap.js +47 -0
  390. package/out/build/heap.js.map +1 -0
  391. package/out/build/inputs.d.ts +52 -0
  392. package/out/build/inputs.d.ts.map +1 -0
  393. package/out/build/inputs.js +49 -0
  394. package/out/build/inputs.js.map +1 -0
  395. package/out/build/rows.d.ts +16 -0
  396. package/out/build/rows.d.ts.map +1 -0
  397. package/out/build/rows.js +19 -0
  398. package/out/build/rows.js.map +1 -0
  399. package/out/build/types.d.ts +222 -0
  400. package/out/build/types.d.ts.map +1 -0
  401. package/out/build/types.js +34 -0
  402. package/out/build/types.js.map +1 -0
  403. package/out/build.d.ts +6 -121
  404. package/out/build.d.ts.map +1 -1
  405. package/out/build.js +112 -207
  406. package/out/build.js.map +1 -1
  407. package/out/cn/recipes/organizational-units.d.ts +5 -22
  408. package/out/cn/recipes/organizational-units.d.ts.map +1 -1
  409. package/out/cn/recipes/organizational-units.js +20 -41
  410. package/out/cn/recipes/organizational-units.js.map +1 -1
  411. package/out/cz/adapters/cuzk/adapter.d.ts +52 -0
  412. package/out/cz/adapters/cuzk/adapter.d.ts.map +1 -0
  413. package/out/cz/adapters/cuzk/adapter.js +269 -0
  414. package/out/cz/adapters/cuzk/adapter.js.map +1 -0
  415. package/out/cz/recipes/pcfirst-preposition.d.ts +7 -11
  416. package/out/cz/recipes/pcfirst-preposition.d.ts.map +1 -1
  417. package/out/cz/recipes/pcfirst-preposition.js +36 -27
  418. package/out/cz/recipes/pcfirst-preposition.js.map +1 -1
  419. package/out/cz/tools/fetch/cuzk.d.ts +281 -0
  420. package/out/cz/tools/fetch/cuzk.d.ts.map +1 -0
  421. package/out/cz/tools/fetch/cuzk.js +448 -0
  422. package/out/cz/tools/fetch/cuzk.js.map +1 -0
  423. package/out/de/recipes/locale.d.ts +24 -26
  424. package/out/de/recipes/locale.d.ts.map +1 -1
  425. package/out/de/recipes/locale.js +67 -57
  426. package/out/de/recipes/locale.js.map +1 -1
  427. package/out/directory.d.ts +20 -0
  428. package/out/directory.d.ts.map +1 -0
  429. package/out/directory.js +27 -0
  430. package/out/directory.js.map +1 -0
  431. package/out/dk/adapters/inspire/adapter.d.ts +153 -0
  432. package/out/dk/adapters/inspire/adapter.d.ts.map +1 -0
  433. package/out/dk/adapters/inspire/adapter.js +258 -0
  434. package/out/dk/adapters/inspire/adapter.js.map +1 -0
  435. package/out/dk/tools/fetch/inspire.d.ts +101 -0
  436. package/out/dk/tools/fetch/inspire.d.ts.map +1 -0
  437. package/out/dk/tools/fetch/inspire.js +232 -0
  438. package/out/dk/tools/fetch/inspire.js.map +1 -0
  439. package/out/ee/adapters/ads/adapter.d.ts +102 -0
  440. package/out/ee/adapters/ads/adapter.d.ts.map +1 -0
  441. package/out/ee/adapters/ads/adapter.js +185 -0
  442. package/out/ee/adapters/ads/adapter.js.map +1 -0
  443. package/out/ee/tools/fetch/ads.d.ts +123 -0
  444. package/out/ee/tools/fetch/ads.d.ts.map +1 -0
  445. package/out/ee/tools/fetch/ads.js +197 -0
  446. package/out/ee/tools/fetch/ads.js.map +1 -0
  447. package/out/env.d.ts +6 -2
  448. package/out/env.d.ts.map +1 -1
  449. package/out/env.js +6 -2
  450. package/out/env.js.map +1 -1
  451. package/out/es/adapters/bizkaia/adapter.d.ts +143 -0
  452. package/out/es/adapters/bizkaia/adapter.d.ts.map +1 -0
  453. package/out/es/adapters/bizkaia/adapter.js +332 -0
  454. package/out/es/adapters/bizkaia/adapter.js.map +1 -0
  455. package/out/es/adapters/catastro/adapter.d.ts +103 -0
  456. package/out/es/adapters/catastro/adapter.d.ts.map +1 -0
  457. package/out/es/adapters/catastro/adapter.js +290 -0
  458. package/out/es/adapters/catastro/adapter.js.map +1 -0
  459. package/out/es/adapters/gipuzkoa/adapter.d.ts +84 -0
  460. package/out/es/adapters/gipuzkoa/adapter.d.ts.map +1 -0
  461. package/out/es/adapters/gipuzkoa/adapter.js +218 -0
  462. package/out/es/adapters/gipuzkoa/adapter.js.map +1 -0
  463. package/out/es/adapters/navarra/adapter.d.ts +106 -0
  464. package/out/es/adapters/navarra/adapter.d.ts.map +1 -0
  465. package/out/es/adapters/navarra/adapter.js +242 -0
  466. package/out/es/adapters/navarra/adapter.js.map +1 -0
  467. package/out/es/cadastre.d.ts +110 -0
  468. package/out/es/cadastre.d.ts.map +1 -0
  469. package/out/es/cadastre.js +128 -0
  470. package/out/es/cadastre.js.map +1 -0
  471. package/out/es/tools/fetch/bizkaia.d.ts +281 -0
  472. package/out/es/tools/fetch/bizkaia.d.ts.map +1 -0
  473. package/out/es/tools/fetch/bizkaia.js +478 -0
  474. package/out/es/tools/fetch/bizkaia.js.map +1 -0
  475. package/out/es/tools/fetch/catastro.d.ts +280 -0
  476. package/out/es/tools/fetch/catastro.d.ts.map +1 -0
  477. package/out/es/tools/fetch/catastro.js +491 -0
  478. package/out/es/tools/fetch/catastro.js.map +1 -0
  479. package/out/es/tools/fetch/gipuzkoa.d.ts +164 -0
  480. package/out/es/tools/fetch/gipuzkoa.d.ts.map +1 -0
  481. package/out/es/tools/fetch/gipuzkoa.js +210 -0
  482. package/out/es/tools/fetch/gipuzkoa.js.map +1 -0
  483. package/out/es/tools/fetch/navarra.d.ts +194 -0
  484. package/out/es/tools/fetch/navarra.d.ts.map +1 -0
  485. package/out/es/tools/fetch/navarra.js +321 -0
  486. package/out/es/tools/fetch/navarra.js.map +1 -0
  487. package/out/fi/adapters/ryhti/adapter.d.ts +111 -0
  488. package/out/fi/adapters/ryhti/adapter.d.ts.map +1 -0
  489. package/out/fi/adapters/ryhti/adapter.js +240 -0
  490. package/out/fi/adapters/ryhti/adapter.js.map +1 -0
  491. package/out/fi/tools/fetch/ryhti.d.ts +206 -0
  492. package/out/fi/tools/fetch/ryhti.d.ts.map +1 -0
  493. package/out/fi/tools/fetch/ryhti.js +324 -0
  494. package/out/fi/tools/fetch/ryhti.js.map +1 -0
  495. package/out/fingerprints.d.ts +68 -0
  496. package/out/fingerprints.d.ts.map +1 -0
  497. package/out/fingerprints.js +130 -0
  498. package/out/fingerprints.js.map +1 -0
  499. package/out/fr/adapters/annuaire-education/adapter.d.ts +236 -0
  500. package/out/fr/adapters/annuaire-education/adapter.d.ts.map +1 -0
  501. package/out/fr/adapters/annuaire-education/adapter.js +477 -0
  502. package/out/fr/adapters/annuaire-education/adapter.js.map +1 -0
  503. package/out/fr/adapters/ban/adapter.d.ts +19 -25
  504. package/out/fr/adapters/ban/adapter.d.ts.map +1 -1
  505. package/out/fr/adapters/ban/adapter.js +65 -54
  506. package/out/fr/adapters/ban/adapter.js.map +1 -1
  507. package/out/fr/adapters/finess/adapter.d.ts +277 -0
  508. package/out/fr/adapters/finess/adapter.d.ts.map +1 -0
  509. package/out/fr/adapters/finess/adapter.js +520 -0
  510. package/out/fr/adapters/finess/adapter.js.map +1 -0
  511. package/out/fr/adapters/finess/postal-lines.d.ts +61 -0
  512. package/out/fr/adapters/finess/postal-lines.d.ts.map +1 -0
  513. package/out/fr/adapters/finess/postal-lines.js +114 -0
  514. package/out/fr/adapters/finess/postal-lines.js.map +1 -0
  515. package/out/fr/adapters/finess/voie-type.d.ts +77 -0
  516. package/out/fr/adapters/finess/voie-type.d.ts.map +1 -0
  517. package/out/fr/adapters/finess/voie-type.js +173 -0
  518. package/out/fr/adapters/finess/voie-type.js.map +1 -0
  519. package/out/fr/insee-country.d.ts +45 -0
  520. package/out/fr/insee-country.d.ts.map +1 -0
  521. package/out/fr/insee-country.js +60 -0
  522. package/out/fr/insee-country.js.map +1 -0
  523. package/out/fr/recipes/admin-split.d.ts +4 -27
  524. package/out/fr/recipes/admin-split.d.ts.map +1 -1
  525. package/out/fr/recipes/admin-split.js +36 -58
  526. package/out/fr/recipes/admin-split.js.map +1 -1
  527. package/out/fr/recipes/bare-street.d.ts +2 -17
  528. package/out/fr/recipes/bare-street.d.ts.map +1 -1
  529. package/out/fr/recipes/bare-street.js +35 -50
  530. package/out/fr/recipes/bare-street.js.map +1 -1
  531. package/out/fr/recipes/fragment.d.ts +6 -65
  532. package/out/fr/recipes/fragment.d.ts.map +1 -1
  533. package/out/fr/recipes/fragment.js +55 -135
  534. package/out/fr/recipes/fragment.js.map +1 -1
  535. package/out/fr/recipes/lieudit.d.ts +17 -19
  536. package/out/fr/recipes/lieudit.d.ts.map +1 -1
  537. package/out/fr/recipes/lieudit.js +89 -68
  538. package/out/fr/recipes/lieudit.js.map +1 -1
  539. package/out/fr/recipes/order.d.ts +4 -27
  540. package/out/fr/recipes/order.d.ts.map +1 -1
  541. package/out/fr/recipes/order.js +31 -58
  542. package/out/fr/recipes/order.js.map +1 -1
  543. package/out/fr/{adapters/ban/street-decompose.d.ts → street-decompose.d.ts} +3 -2
  544. package/out/fr/street-decompose.d.ts.map +1 -0
  545. package/out/fr/{adapters/ban/street-decompose.js → street-decompose.js} +4 -3
  546. package/out/fr/street-decompose.js.map +1 -0
  547. package/out/fr/tools/fetch/annuaire-education.d.ts +133 -0
  548. package/out/fr/tools/fetch/annuaire-education.d.ts.map +1 -0
  549. package/out/fr/tools/fetch/annuaire-education.js +198 -0
  550. package/out/fr/tools/fetch/annuaire-education.js.map +1 -0
  551. package/out/fr/tools/fetch/ban.d.ts +9 -7
  552. package/out/fr/tools/fetch/ban.d.ts.map +1 -1
  553. package/out/fr/tools/fetch/ban.js +29 -19
  554. package/out/fr/tools/fetch/ban.js.map +1 -1
  555. package/out/fr/tools/fetch/finess.d.ts +145 -0
  556. package/out/fr/tools/fetch/finess.d.ts.map +1 -0
  557. package/out/fr/tools/fetch/finess.js +229 -0
  558. package/out/fr/tools/fetch/finess.js.map +1 -0
  559. package/out/gauntlet-inputs.d.ts +42 -0
  560. package/out/gauntlet-inputs.d.ts.map +1 -0
  561. package/out/gauntlet-inputs.js +78 -0
  562. package/out/gauntlet-inputs.js.map +1 -0
  563. package/out/index.d.ts +9 -3
  564. package/out/index.d.ts.map +1 -1
  565. package/out/index.js +9 -3
  566. package/out/index.js.map +1 -1
  567. package/out/inspire/address.d.ts +261 -0
  568. package/out/inspire/address.d.ts.map +1 -0
  569. package/out/inspire/address.js +395 -0
  570. package/out/inspire/address.js.map +1 -0
  571. package/out/inspire/archive.d.ts +36 -0
  572. package/out/inspire/archive.d.ts.map +1 -0
  573. package/out/inspire/archive.js +42 -0
  574. package/out/inspire/archive.js.map +1 -0
  575. package/out/inspire/errors.d.ts +56 -0
  576. package/out/inspire/errors.d.ts.map +1 -0
  577. package/out/inspire/errors.js +65 -0
  578. package/out/inspire/errors.js.map +1 -0
  579. package/out/inspire/stream.d.ts +140 -0
  580. package/out/inspire/stream.d.ts.map +1 -0
  581. package/out/inspire/stream.js +123 -0
  582. package/out/inspire/stream.js.map +1 -0
  583. package/out/international/recipes/locale.d.ts +40 -86
  584. package/out/international/recipes/locale.d.ts.map +1 -1
  585. package/out/international/recipes/locale.js +122 -157
  586. package/out/international/recipes/locale.js.map +1 -1
  587. package/out/it/adapters/anac/adapter.d.ts +269 -0
  588. package/out/it/adapters/anac/adapter.d.ts.map +1 -0
  589. package/out/it/adapters/anac/adapter.js +434 -0
  590. package/out/it/adapters/anac/adapter.js.map +1 -0
  591. package/out/it/tools/fetch/anac.d.ts +171 -0
  592. package/out/it/tools/fetch/anac.d.ts.map +1 -0
  593. package/out/it/tools/fetch/anac.js +269 -0
  594. package/out/it/tools/fetch/anac.js.map +1 -0
  595. package/out/jp/adapters/wof-admin/adapter.d.ts +14 -11
  596. package/out/jp/adapters/wof-admin/adapter.d.ts.map +1 -1
  597. package/out/jp/adapters/wof-admin/adapter.js +27 -16
  598. package/out/jp/adapters/wof-admin/adapter.js.map +1 -1
  599. package/out/jp/tools/fetch/houjin.d.ts +7 -4
  600. package/out/jp/tools/fetch/houjin.d.ts.map +1 -1
  601. package/out/jp/tools/fetch/houjin.js +17 -13
  602. package/out/jp/tools/fetch/houjin.js.map +1 -1
  603. package/out/kr/adapters/juso/label-rows.d.ts +17 -31
  604. package/out/kr/adapters/juso/label-rows.d.ts.map +1 -1
  605. package/out/kr/adapters/juso/label-rows.js +19 -41
  606. package/out/kr/adapters/juso/label-rows.js.map +1 -1
  607. package/out/kr/adapters/localdata/align.d.ts +4 -16
  608. package/out/kr/adapters/localdata/align.d.ts.map +1 -1
  609. package/out/kr/adapters/localdata/align.js +19 -30
  610. package/out/kr/adapters/localdata/align.js.map +1 -1
  611. package/out/kr/adapters/localdata/key-index.d.ts +13 -22
  612. package/out/kr/adapters/localdata/key-index.d.ts.map +1 -1
  613. package/out/kr/adapters/localdata/key-index.js +15 -21
  614. package/out/kr/adapters/localdata/key-index.js.map +1 -1
  615. package/out/kr/adapters/localdata/permit-rows.d.ts +21 -14
  616. package/out/kr/adapters/localdata/permit-rows.d.ts.map +1 -1
  617. package/out/kr/adapters/localdata/permit-rows.js +31 -26
  618. package/out/kr/adapters/localdata/permit-rows.js.map +1 -1
  619. package/out/kr/tools/fetch/juso.d.ts +11 -8
  620. package/out/kr/tools/fetch/juso.d.ts.map +1 -1
  621. package/out/kr/tools/fetch/juso.js +15 -14
  622. package/out/kr/tools/fetch/juso.js.map +1 -1
  623. package/out/kr/tools/fetch/localdata.d.ts +16 -9
  624. package/out/kr/tools/fetch/localdata.d.ts.map +1 -1
  625. package/out/kr/tools/fetch/localdata.js +24 -16
  626. package/out/kr/tools/fetch/localdata.js.map +1 -1
  627. package/out/lu/adapters/bd-adresses/adapter.d.ts +109 -0
  628. package/out/lu/adapters/bd-adresses/adapter.d.ts.map +1 -0
  629. package/out/lu/adapters/bd-adresses/adapter.js +196 -0
  630. package/out/lu/adapters/bd-adresses/adapter.js.map +1 -0
  631. package/out/lu/tools/fetch/bd-adresses.d.ts +165 -0
  632. package/out/lu/tools/fetch/bd-adresses.d.ts.map +1 -0
  633. package/out/lu/tools/fetch/bd-adresses.js +223 -0
  634. package/out/lu/tools/fetch/bd-adresses.js.map +1 -0
  635. package/out/lv/adapters/varis/adapter.d.ts +284 -0
  636. package/out/lv/adapters/varis/adapter.d.ts.map +1 -0
  637. package/out/lv/adapters/varis/adapter.js +405 -0
  638. package/out/lv/adapters/varis/adapter.js.map +1 -0
  639. package/out/lv/tools/fetch/varis.d.ts +81 -0
  640. package/out/lv/tools/fetch/varis.d.ts.map +1 -0
  641. package/out/lv/tools/fetch/varis.js +133 -0
  642. package/out/lv/tools/fetch/varis.js.map +1 -0
  643. package/out/nl/adapters/kadaster/adapter.d.ts +125 -0
  644. package/out/nl/adapters/kadaster/adapter.d.ts.map +1 -0
  645. package/out/nl/adapters/kadaster/adapter.js +309 -0
  646. package/out/nl/adapters/kadaster/adapter.js.map +1 -0
  647. package/out/nl/recipes/postcode.d.ts +12 -14
  648. package/out/nl/recipes/postcode.d.ts.map +1 -1
  649. package/out/nl/recipes/postcode.js +42 -24
  650. package/out/nl/recipes/postcode.js.map +1 -1
  651. package/out/nl/tools/fetch/kadaster.d.ts +159 -0
  652. package/out/nl/tools/fetch/kadaster.d.ts.map +1 -0
  653. package/out/nl/tools/fetch/kadaster.js +182 -0
  654. package/out/nl/tools/fetch/kadaster.js.map +1 -0
  655. package/out/no/adapters/matrikkelen/adapter.d.ts +44 -0
  656. package/out/no/adapters/matrikkelen/adapter.d.ts.map +1 -0
  657. package/out/no/adapters/matrikkelen/adapter.js +143 -0
  658. package/out/no/adapters/matrikkelen/adapter.js.map +1 -0
  659. package/out/no/recipes/fragment.d.ts +1 -33
  660. package/out/no/recipes/fragment.d.ts.map +1 -1
  661. package/out/no/recipes/fragment.js +23 -57
  662. package/out/no/recipes/fragment.js.map +1 -1
  663. package/out/no/recipes/street/led.d.ts +9 -12
  664. package/out/no/recipes/street/led.d.ts.map +1 -1
  665. package/out/no/recipes/street/led.js +34 -24
  666. package/out/no/recipes/street/led.js.map +1 -1
  667. package/out/no/recipes/street.d.ts +19 -0
  668. package/out/no/recipes/street.d.ts.map +1 -0
  669. package/out/no/recipes/{street/index.js → street.js} +28 -12
  670. package/out/no/recipes/street.js.map +1 -0
  671. package/out/no/tools/fetch/matrikkelen.d.ts +263 -0
  672. package/out/no/tools/fetch/matrikkelen.d.ts.map +1 -0
  673. package/out/no/tools/fetch/matrikkelen.js +353 -0
  674. package/out/no/tools/fetch/matrikkelen.js.map +1 -0
  675. package/out/parquet/duckdb.d.ts +103 -0
  676. package/out/parquet/duckdb.d.ts.map +1 -0
  677. package/out/parquet/duckdb.js +93 -0
  678. package/out/parquet/duckdb.js.map +1 -0
  679. package/out/parquet/readers.d.ts +44 -0
  680. package/out/parquet/readers.d.ts.map +1 -0
  681. package/out/parquet/readers.js +69 -0
  682. package/out/parquet/readers.js.map +1 -0
  683. package/out/parquet/schema.d.ts +95 -0
  684. package/out/parquet/schema.d.ts.map +1 -0
  685. package/out/parquet/schema.js +157 -0
  686. package/out/parquet/schema.js.map +1 -0
  687. package/out/parquet/shuffle.d.ts +25 -0
  688. package/out/parquet/shuffle.d.ts.map +1 -0
  689. package/out/parquet/shuffle.js +44 -0
  690. package/out/parquet/shuffle.js.map +1 -0
  691. package/out/parquet/span-sql.d.ts +49 -0
  692. package/out/parquet/span-sql.d.ts.map +1 -0
  693. package/out/parquet/span-sql.js +53 -0
  694. package/out/parquet/span-sql.js.map +1 -0
  695. package/out/parquet/streams.d.ts +47 -0
  696. package/out/parquet/streams.d.ts.map +1 -0
  697. package/out/parquet/streams.js +78 -0
  698. package/out/parquet/streams.js.map +1 -0
  699. package/out/parquet/writers.d.ts +124 -0
  700. package/out/parquet/writers.d.ts.map +1 -0
  701. package/out/parquet/writers.js +252 -0
  702. package/out/parquet/writers.js.map +1 -0
  703. package/out/pl/adapters/emuia/adapter.d.ts +81 -0
  704. package/out/pl/adapters/emuia/adapter.d.ts.map +1 -0
  705. package/out/pl/adapters/emuia/adapter.js +178 -0
  706. package/out/pl/adapters/emuia/adapter.js.map +1 -0
  707. package/out/pl/tools/fetch/emuia.d.ts +166 -0
  708. package/out/pl/tools/fetch/emuia.d.ts.map +1 -0
  709. package/out/pl/tools/fetch/emuia.js +261 -0
  710. package/out/pl/tools/fetch/emuia.js.map +1 -0
  711. package/out/recipes/anchor-absorption.d.ts +9 -9
  712. package/out/recipes/anchor-absorption.d.ts.map +1 -1
  713. package/out/recipes/anchor-absorption.js +29 -19
  714. package/out/recipes/anchor-absorption.js.map +1 -1
  715. package/out/recipes/bare/country.d.ts +2 -20
  716. package/out/recipes/bare/country.d.ts.map +1 -1
  717. package/out/recipes/bare/country.js +20 -31
  718. package/out/recipes/bare/country.js.map +1 -1
  719. package/out/recipes/bare/postcode/eval.d.ts +1 -1
  720. package/out/recipes/bare/postcode/eval.js +1 -1
  721. package/out/recipes/bare/postcode.d.ts +41 -0
  722. package/out/recipes/bare/postcode.d.ts.map +1 -0
  723. package/out/recipes/bare/{postcode/index.js → postcode.js} +92 -80
  724. package/out/recipes/bare/postcode.js.map +1 -0
  725. package/out/recipes/boundary-stress.d.ts +8 -8
  726. package/out/recipes/boundary-stress.d.ts.map +1 -1
  727. package/out/recipes/boundary-stress.js +37 -20
  728. package/out/recipes/boundary-stress.js.map +1 -1
  729. package/out/recipes/country-balanced.d.ts +3 -21
  730. package/out/recipes/country-balanced.d.ts.map +1 -1
  731. package/out/recipes/country-balanced.js +58 -76
  732. package/out/recipes/country-balanced.js.map +1 -1
  733. package/out/recipes/house-venue.d.ts +8 -6
  734. package/out/recipes/house-venue.d.ts.map +1 -1
  735. package/out/recipes/house-venue.js +33 -14
  736. package/out/recipes/house-venue.js.map +1 -1
  737. package/out/recipes/intersection.d.ts +20 -20
  738. package/out/recipes/intersection.d.ts.map +1 -1
  739. package/out/recipes/intersection.js +67 -55
  740. package/out/recipes/intersection.js.map +1 -1
  741. package/out/recipes/po/box/cedex/au-nz.d.ts.map +1 -1
  742. package/out/recipes/po/box/cedex/au-nz.js +3 -3
  743. package/out/recipes/po/box/cedex/au-nz.js.map +1 -1
  744. package/out/recipes/po/box/cedex/ca.d.ts.map +1 -1
  745. package/out/recipes/po/box/cedex/ca.js +2 -2
  746. package/out/recipes/po/box/cedex/ca.js.map +1 -1
  747. package/out/recipes/po/box/cedex/fr.d.ts.map +1 -1
  748. package/out/recipes/po/box/cedex/fr.js +3 -3
  749. package/out/recipes/po/box/cedex/fr.js.map +1 -1
  750. package/out/recipes/po/box/cedex/phrases.d.ts.map +1 -1
  751. package/out/recipes/po/box/cedex/phrases.js +7 -6
  752. package/out/recipes/po/box/cedex/phrases.js.map +1 -1
  753. package/out/recipes/po/box/cedex/recipe.d.ts +1 -1
  754. package/out/recipes/po/box/cedex/recipe.d.ts.map +1 -1
  755. package/out/recipes/po/box/cedex/recipe.js +27 -16
  756. package/out/recipes/po/box/cedex/recipe.js.map +1 -1
  757. package/out/recipes/po/box/cedex/sources.d.ts +20 -14
  758. package/out/recipes/po/box/cedex/sources.d.ts.map +1 -1
  759. package/out/recipes/po/box/cedex/sources.js +2 -2
  760. package/out/recipes/po/box/cedex/sources.js.map +1 -1
  761. package/out/recipes/po/box/cedex/us.d.ts.map +1 -1
  762. package/out/recipes/po/box/cedex/us.js +5 -2
  763. package/out/recipes/po/box/cedex/us.js.map +1 -1
  764. package/out/recipes/po/box.d.ts +18 -0
  765. package/out/recipes/po/box.d.ts.map +1 -0
  766. package/out/recipes/po/{box/index.js → box.js} +37 -19
  767. package/out/recipes/po/box.js.map +1 -0
  768. package/out/recipes/scaffold.d.ts +223 -141
  769. package/out/recipes/scaffold.d.ts.map +1 -1
  770. package/out/recipes/scaffold.js +75 -65
  771. package/out/recipes/scaffold.js.map +1 -1
  772. package/out/recipes/sources.d.ts +178 -0
  773. package/out/recipes/sources.d.ts.map +1 -0
  774. package/out/recipes/sources.js +361 -0
  775. package/out/recipes/sources.js.map +1 -0
  776. package/out/recipes/street/affix.d.ts +20 -50
  777. package/out/recipes/street/affix.d.ts.map +1 -1
  778. package/out/recipes/street/affix.js +45 -133
  779. package/out/recipes/street/affix.js.map +1 -1
  780. package/out/recipes/street/bare.d.ts +9 -7
  781. package/out/recipes/street/bare.d.ts.map +1 -1
  782. package/out/recipes/street/bare.js +27 -16
  783. package/out/recipes/street/bare.js.map +1 -1
  784. package/out/recipes/street.d.ts +6 -4
  785. package/out/recipes/street.d.ts.map +1 -1
  786. package/out/recipes/street.js +32 -9
  787. package/out/recipes/street.js.map +1 -1
  788. package/out/recipes/sub/venue/context.d.ts +12 -9
  789. package/out/recipes/sub/venue/context.d.ts.map +1 -1
  790. package/out/recipes/sub/venue/context.js +23 -17
  791. package/out/recipes/sub/venue/context.js.map +1 -1
  792. package/out/recipes/sub/venue/render.d.ts +58 -0
  793. package/out/recipes/sub/venue/render.d.ts.map +1 -0
  794. package/out/recipes/sub/venue/render.js +118 -0
  795. package/out/recipes/sub/venue/render.js.map +1 -0
  796. package/out/recipes/sub/venue/sources.d.ts +53 -93
  797. package/out/recipes/sub/venue/sources.d.ts.map +1 -1
  798. package/out/recipes/sub/venue/sources.js +57 -197
  799. package/out/recipes/sub/venue/sources.js.map +1 -1
  800. package/out/recipes/sub/venue.d.ts +173 -0
  801. package/out/recipes/sub/venue.d.ts.map +1 -0
  802. package/out/recipes/sub/venue.js +558 -0
  803. package/out/recipes/sub/venue.js.map +1 -0
  804. package/out/recipes/trailing-region.d.ts +9 -61
  805. package/out/recipes/trailing-region.d.ts.map +1 -1
  806. package/out/recipes/trailing-region.js +61 -86
  807. package/out/recipes/trailing-region.js.map +1 -1
  808. package/out/recipes/unit/sources.d.ts +28 -0
  809. package/out/recipes/unit/sources.d.ts.map +1 -0
  810. package/out/recipes/unit/sources.js +30 -0
  811. package/out/recipes/unit/sources.js.map +1 -0
  812. package/out/recipes/unit.d.ts +30 -17
  813. package/out/recipes/unit.d.ts.map +1 -1
  814. package/out/recipes/unit.js +90 -79
  815. package/out/recipes/unit.js.map +1 -1
  816. package/out/recipes/venue.d.ts +119 -0
  817. package/out/recipes/venue.d.ts.map +1 -0
  818. package/out/recipes/venue.js +245 -0
  819. package/out/recipes/venue.js.map +1 -0
  820. package/out/recipes.d.ts +26 -0
  821. package/out/recipes.d.ts.map +1 -0
  822. package/out/{recipes/index.js → recipes.js} +16 -12
  823. package/out/recipes.js.map +1 -0
  824. package/out/registers.d.ts +279 -0
  825. package/out/registers.d.ts.map +1 -0
  826. package/out/registers.js +275 -0
  827. package/out/registers.js.map +1 -0
  828. package/out/ro/adapters/retea-scolara/adapter.d.ts +114 -0
  829. package/out/ro/adapters/retea-scolara/adapter.d.ts.map +1 -0
  830. package/out/ro/adapters/retea-scolara/adapter.js +209 -0
  831. package/out/ro/adapters/retea-scolara/adapter.js.map +1 -0
  832. package/out/ro/tools/fetch/retea-scolara.d.ts +69 -0
  833. package/out/ro/tools/fetch/retea-scolara.d.ts.map +1 -0
  834. package/out/ro/tools/fetch/retea-scolara.js +117 -0
  835. package/out/ro/tools/fetch/retea-scolara.js.map +1 -0
  836. package/out/runner.d.ts +121 -60
  837. package/out/runner.d.ts.map +1 -1
  838. package/out/runner.js +130 -56
  839. package/out/runner.js.map +1 -1
  840. package/out/sg/recipes/register.d.ts +18 -32
  841. package/out/sg/recipes/register.d.ts.map +1 -1
  842. package/out/sg/recipes/register.js +45 -50
  843. package/out/sg/recipes/register.js.map +1 -1
  844. package/out/sg/tools/fetch/acra.d.ts +11 -14
  845. package/out/sg/tools/fetch/acra.d.ts.map +1 -1
  846. package/out/sg/tools/fetch/acra.js +18 -21
  847. package/out/sg/tools/fetch/acra.js.map +1 -1
  848. package/out/si/recipes/bare-village.d.ts +12 -13
  849. package/out/si/recipes/bare-village.d.ts.map +1 -1
  850. package/out/si/recipes/bare-village.js +31 -17
  851. package/out/si/recipes/bare-village.js.map +1 -1
  852. package/out/sk/adapters/inspire/adapter.d.ts +119 -0
  853. package/out/sk/adapters/inspire/adapter.d.ts.map +1 -0
  854. package/out/sk/adapters/inspire/adapter.js +318 -0
  855. package/out/sk/adapters/inspire/adapter.js.map +1 -0
  856. package/out/sk/tools/fetch/inspire.d.ts +196 -0
  857. package/out/sk/tools/fetch/inspire.d.ts.map +1 -0
  858. package/out/sk/tools/fetch/inspire.js +281 -0
  859. package/out/sk/tools/fetch/inspire.js.map +1 -0
  860. package/out/source-register/effective-manifest.d.ts +355 -0
  861. package/out/source-register/effective-manifest.d.ts.map +1 -0
  862. package/out/source-register/effective-manifest.js +355 -0
  863. package/out/source-register/effective-manifest.js.map +1 -0
  864. package/out/source-register/register.d.ts +79 -0
  865. package/out/source-register/register.d.ts.map +1 -0
  866. package/out/source-register/register.js +400 -0
  867. package/out/source-register/register.js.map +1 -0
  868. package/out/source-register/training-manifest.d.ts +111 -0
  869. package/out/source-register/training-manifest.d.ts.map +1 -0
  870. package/out/source-register/training-manifest.js +120 -0
  871. package/out/source-register/training-manifest.js.map +1 -0
  872. package/out/source-register/types.d.ts +538 -0
  873. package/out/source-register/types.d.ts.map +1 -0
  874. package/out/source-register/types.js +263 -0
  875. package/out/source-register/types.js.map +1 -0
  876. package/out/source-register.d.ts +19 -0
  877. package/out/source-register.d.ts.map +1 -0
  878. package/out/source-register.js +16 -0
  879. package/out/source-register.js.map +1 -0
  880. package/out/south-asia/recipes/register.d.ts +20 -17
  881. package/out/south-asia/recipes/register.d.ts.map +1 -1
  882. package/out/south-asia/recipes/register.js +44 -24
  883. package/out/south-asia/recipes/register.js.map +1 -1
  884. package/out/subvenue/harvest.d.ts +117 -0
  885. package/out/subvenue/harvest.d.ts.map +1 -0
  886. package/out/subvenue/harvest.js +172 -0
  887. package/out/subvenue/harvest.js.map +1 -0
  888. package/out/subvenue/promotions.d.ts +65 -0
  889. package/out/subvenue/promotions.d.ts.map +1 -0
  890. package/out/{tools/sub/venue → subvenue}/promotions.js +15 -55
  891. package/out/subvenue/promotions.js.map +1 -0
  892. package/out/subvenue/surfaces.d.ts +39 -0
  893. package/out/subvenue/surfaces.d.ts.map +1 -0
  894. package/out/subvenue/surfaces.js +75 -0
  895. package/out/subvenue/surfaces.js.map +1 -0
  896. package/out/subvenue/table.d.ts +212 -0
  897. package/out/subvenue/table.d.ts.map +1 -0
  898. package/out/subvenue/table.js +94 -0
  899. package/out/subvenue/table.js.map +1 -0
  900. package/out/surfaces/locale.d.ts +113 -0
  901. package/out/surfaces/locale.d.ts.map +1 -0
  902. package/out/surfaces/locale.js +138 -0
  903. package/out/surfaces/locale.js.map +1 -0
  904. package/out/synthesizers/anchor-absorption.d.ts +22 -30
  905. package/out/synthesizers/anchor-absorption.d.ts.map +1 -1
  906. package/out/synthesizers/anchor-absorption.js +30 -85
  907. package/out/synthesizers/anchor-absorption.js.map +1 -1
  908. package/out/synthesizers/boundary-stress.d.ts +18 -49
  909. package/out/synthesizers/boundary-stress.d.ts.map +1 -1
  910. package/out/synthesizers/boundary-stress.js +45 -142
  911. package/out/synthesizers/boundary-stress.js.map +1 -1
  912. package/out/synthesizers/house-venue.d.ts +23 -25
  913. package/out/synthesizers/house-venue.d.ts.map +1 -1
  914. package/out/synthesizers/house-venue.js +47 -118
  915. package/out/synthesizers/house-venue.js.map +1 -1
  916. package/out/synthesizers/no-street.d.ts +7 -37
  917. package/out/synthesizers/no-street.d.ts.map +1 -1
  918. package/out/synthesizers/no-street.js +55 -111
  919. package/out/synthesizers/no-street.js.map +1 -1
  920. package/out/synthesizers/po-box.d.ts +48 -45
  921. package/out/synthesizers/po-box.d.ts.map +1 -1
  922. package/out/synthesizers/po-box.js +57 -97
  923. package/out/synthesizers/po-box.js.map +1 -1
  924. package/out/synthesizers/tail.d.ts +36 -0
  925. package/out/synthesizers/tail.d.ts.map +1 -0
  926. package/out/synthesizers/tail.js +32 -0
  927. package/out/synthesizers/tail.js.map +1 -0
  928. package/out/synthesizers/utils.d.ts +33 -129
  929. package/out/synthesizers/utils.d.ts.map +1 -1
  930. package/out/synthesizers/utils.js +71 -167
  931. package/out/synthesizers/utils.js.map +1 -1
  932. package/out/test-kit/corpus-recipe.d.ts +29 -23
  933. package/out/test-kit/corpus-recipe.d.ts.map +1 -1
  934. package/out/test-kit/corpus-recipe.js +28 -13
  935. package/out/test-kit/corpus-recipe.js.map +1 -1
  936. package/out/test-kit.d.ts +63 -0
  937. package/out/test-kit.d.ts.map +1 -0
  938. package/out/test-kit.js +88 -0
  939. package/out/test-kit.js.map +1 -0
  940. package/out/tools/align-canonical.d.ts +7 -0
  941. package/out/tools/align-canonical.d.ts.map +1 -0
  942. package/out/tools/align-canonical.js +52 -0
  943. package/out/tools/align-canonical.js.map +1 -0
  944. package/out/tools/audit.d.ts +19 -11
  945. package/out/tools/audit.d.ts.map +1 -1
  946. package/out/tools/audit.js +89 -97
  947. package/out/tools/audit.js.map +1 -1
  948. package/out/tools/corpus-stats.d.ts +24 -15
  949. package/out/tools/corpus-stats.d.ts.map +1 -1
  950. package/out/tools/corpus-stats.js +34 -30
  951. package/out/tools/corpus-stats.js.map +1 -1
  952. package/out/tools/fetch/atom.d.ts +115 -0
  953. package/out/tools/fetch/atom.d.ts.map +1 -0
  954. package/out/tools/fetch/atom.js +83 -0
  955. package/out/tools/fetch/atom.js.map +1 -0
  956. package/out/tools/fetch/cordis.d.ts +124 -0
  957. package/out/tools/fetch/cordis.d.ts.map +1 -0
  958. package/out/tools/fetch/cordis.js +210 -0
  959. package/out/tools/fetch/cordis.js.map +1 -0
  960. package/out/tools/fetch/download/manifest.d.ts +27 -18
  961. package/out/tools/fetch/download/manifest.d.ts.map +1 -1
  962. package/out/tools/fetch/download/manifest.js +22 -14
  963. package/out/tools/fetch/download/manifest.js.map +1 -1
  964. package/out/tools/fetch/download/network.d.ts +48 -27
  965. package/out/tools/fetch/download/network.d.ts.map +1 -1
  966. package/out/tools/fetch/download/network.js +26 -16
  967. package/out/tools/fetch/download/network.js.map +1 -1
  968. package/out/tools/fetch/download/retry.d.ts +16 -15
  969. package/out/tools/fetch/download/retry.d.ts.map +1 -1
  970. package/out/tools/fetch/download/retry.js +28 -28
  971. package/out/tools/fetch/download/retry.js.map +1 -1
  972. package/out/tools/fetch/{download/index.d.ts → download.d.ts} +1 -1
  973. package/out/tools/fetch/download.d.ts.map +1 -0
  974. package/out/tools/fetch/{download/index.js → download.js} +1 -1
  975. package/out/tools/fetch/download.js.map +1 -0
  976. package/out/tools/fetch/geonames/dump.d.ts +51 -32
  977. package/out/tools/fetch/geonames/dump.d.ts.map +1 -1
  978. package/out/tools/fetch/geonames/dump.js +54 -43
  979. package/out/tools/fetch/geonames/dump.js.map +1 -1
  980. package/out/tools/fetch/geonames/postal.d.ts +14 -49
  981. package/out/tools/fetch/geonames/postal.d.ts.map +1 -1
  982. package/out/tools/fetch/geonames/postal.js +17 -56
  983. package/out/tools/fetch/geonames/postal.js.map +1 -1
  984. package/out/tools/fetch/gleif.d.ts +138 -0
  985. package/out/tools/fetch/gleif.d.ts.map +1 -0
  986. package/out/tools/fetch/gleif.js +222 -0
  987. package/out/tools/fetch/gleif.js.map +1 -0
  988. package/out/tools/fetch/header.d.ts +43 -0
  989. package/out/tools/fetch/header.d.ts.map +1 -0
  990. package/out/tools/fetch/header.js +61 -0
  991. package/out/tools/fetch/header.js.map +1 -0
  992. package/out/tools/fetch/inspire-addresses.d.ts +254 -0
  993. package/out/tools/fetch/inspire-addresses.d.ts.map +1 -0
  994. package/out/tools/fetch/inspire-addresses.js +277 -0
  995. package/out/tools/fetch/inspire-addresses.js.map +1 -0
  996. package/out/tools/fetch/openaddresses.d.ts +1 -4
  997. package/out/tools/fetch/openaddresses.d.ts.map +1 -1
  998. package/out/tools/fetch/openaddresses.js +20 -99
  999. package/out/tools/fetch/openaddresses.js.map +1 -1
  1000. package/out/tools/fetch/ourairports.d.ts +6 -33
  1001. package/out/tools/fetch/ourairports.d.ts.map +1 -1
  1002. package/out/tools/fetch/ourairports.js +14 -47
  1003. package/out/tools/fetch/ourairports.js.map +1 -1
  1004. package/out/tools/fetch/ppd.d.ts +4 -3
  1005. package/out/tools/fetch/ppd.d.ts.map +1 -1
  1006. package/out/tools/fetch/ppd.js +10 -7
  1007. package/out/tools/fetch/ppd.js.map +1 -1
  1008. package/out/tools/fetch/vlaanderen-ad.d.ts +131 -0
  1009. package/out/tools/fetch/vlaanderen-ad.d.ts.map +1 -0
  1010. package/out/tools/fetch/vlaanderen-ad.js +293 -0
  1011. package/out/tools/fetch/vlaanderen-ad.js.map +1 -0
  1012. package/out/tools/fetch/wfs-harvest.d.ts +420 -0
  1013. package/out/tools/fetch/wfs-harvest.d.ts.map +1 -0
  1014. package/out/tools/fetch/wfs-harvest.js +525 -0
  1015. package/out/tools/fetch/wfs-harvest.js.map +1 -0
  1016. package/out/tools/fetch/wikidata-subvenue.d.ts +32 -100
  1017. package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -1
  1018. package/out/tools/fetch/wikidata-subvenue.js +27 -122
  1019. package/out/tools/fetch/wikidata-subvenue.js.map +1 -1
  1020. package/out/tools/fetch/zip-archive.d.ts +54 -0
  1021. package/out/tools/fetch/zip-archive.d.ts.map +1 -0
  1022. package/out/tools/fetch/zip-archive.js +58 -0
  1023. package/out/tools/fetch/zip-archive.js.map +1 -0
  1024. package/out/tools/fetch.d.ts +99 -0
  1025. package/out/tools/fetch.d.ts.map +1 -0
  1026. package/out/tools/fetch.js +95 -0
  1027. package/out/tools/fetch.js.map +1 -0
  1028. package/out/tools/golden/expand.d.ts +28 -13
  1029. package/out/tools/golden/expand.d.ts.map +1 -1
  1030. package/out/tools/golden/expand.js +51 -37
  1031. package/out/tools/golden/expand.js.map +1 -1
  1032. package/out/tools/golden/promote.d.ts +13 -8
  1033. package/out/tools/golden/promote.d.ts.map +1 -1
  1034. package/out/tools/golden/promote.js +38 -30
  1035. package/out/tools/golden/promote.js.map +1 -1
  1036. package/out/tools/golden/relabel-street/directory.d.ts +25 -10
  1037. package/out/tools/golden/relabel-street/directory.d.ts.map +1 -1
  1038. package/out/tools/golden/relabel-street/directory.js +44 -32
  1039. package/out/tools/golden/relabel-street/directory.js.map +1 -1
  1040. package/out/tools/golden/relabel-street/row.d.ts +18 -69
  1041. package/out/tools/golden/relabel-street/row.d.ts.map +1 -1
  1042. package/out/tools/golden/relabel-street/row.js +19 -77
  1043. package/out/tools/golden/relabel-street/row.js.map +1 -1
  1044. package/out/tools/golden/{relabel-street/index.d.ts → relabel-street.d.ts} +1 -1
  1045. package/out/tools/golden/relabel-street.d.ts.map +1 -0
  1046. package/out/tools/golden/{relabel-street/index.js → relabel-street.js} +1 -1
  1047. package/out/tools/golden/relabel-street.js.map +1 -0
  1048. package/out/tools/ingest-csv.d.ts +19 -15
  1049. package/out/tools/ingest-csv.d.ts.map +1 -1
  1050. package/out/tools/ingest-csv.js +42 -46
  1051. package/out/tools/ingest-csv.js.map +1 -1
  1052. package/out/tools/jsonl-to-parquet.d.ts +15 -28
  1053. package/out/tools/jsonl-to-parquet.d.ts.map +1 -1
  1054. package/out/tools/jsonl-to-parquet.js +49 -91
  1055. package/out/tools/jsonl-to-parquet.js.map +1 -1
  1056. package/out/tools/lint/recipe-output/vocab.d.ts +82 -0
  1057. package/out/tools/lint/recipe-output/vocab.d.ts.map +1 -0
  1058. package/out/tools/lint/{slice → recipe-output}/vocab.js +54 -69
  1059. package/out/tools/lint/recipe-output/vocab.js.map +1 -0
  1060. package/out/tools/lint/recipe-output.d.ts +73 -0
  1061. package/out/tools/lint/recipe-output.d.ts.map +1 -0
  1062. package/out/tools/lint/{slice/index.js → recipe-output.js} +93 -96
  1063. package/out/tools/lint/recipe-output.js.map +1 -0
  1064. package/out/tools/migrate/overlay-parquet.d.ts +30 -0
  1065. package/out/tools/migrate/overlay-parquet.d.ts.map +1 -0
  1066. package/out/tools/migrate/overlay-parquet.js +141 -0
  1067. package/out/tools/migrate/overlay-parquet.js.map +1 -0
  1068. package/out/tools/migrate/recipe-output.d.ts +35 -0
  1069. package/out/tools/migrate/recipe-output.d.ts.map +1 -0
  1070. package/out/tools/migrate/recipe-output.js +124 -0
  1071. package/out/tools/migrate/recipe-output.js.map +1 -0
  1072. package/out/tools/migrate/source-names.d.ts +52 -0
  1073. package/out/tools/migrate/source-names.d.ts.map +1 -0
  1074. package/out/tools/migrate/source-names.js +105 -0
  1075. package/out/tools/migrate/source-names.js.map +1 -0
  1076. package/out/tools/overlay/kryptonite.d.ts +33 -0
  1077. package/out/tools/overlay/kryptonite.d.ts.map +1 -0
  1078. package/out/tools/{slice → overlay}/kryptonite.js +39 -29
  1079. package/out/tools/overlay/kryptonite.js.map +1 -0
  1080. package/out/tools/overlay/manifest.d.ts +143 -0
  1081. package/out/tools/overlay/manifest.d.ts.map +1 -0
  1082. package/out/tools/overlay/manifest.js +261 -0
  1083. package/out/tools/overlay/manifest.js.map +1 -0
  1084. package/out/tools/overlay/merge-source.d.ts +74 -0
  1085. package/out/tools/overlay/merge-source.d.ts.map +1 -0
  1086. package/out/tools/overlay/merge-source.js +63 -0
  1087. package/out/tools/overlay/merge-source.js.map +1 -0
  1088. package/out/tools/overlay/split-slice.d.ts +66 -0
  1089. package/out/tools/overlay/split-slice.d.ts.map +1 -0
  1090. package/out/tools/overlay/split-slice.js +78 -0
  1091. package/out/tools/overlay/split-slice.js.map +1 -0
  1092. package/out/tools/overlay/translit.d.ts +55 -0
  1093. package/out/tools/overlay/translit.d.ts.map +1 -0
  1094. package/out/tools/{slice → overlay}/translit.js +61 -49
  1095. package/out/tools/overlay/translit.js.map +1 -0
  1096. package/out/tools/overture-subvenue.d.ts +17 -76
  1097. package/out/tools/overture-subvenue.d.ts.map +1 -1
  1098. package/out/tools/overture-subvenue.js +7 -74
  1099. package/out/tools/overture-subvenue.js.map +1 -1
  1100. package/out/tools/postcode-triples.d.ts +78 -127
  1101. package/out/tools/postcode-triples.d.ts.map +1 -1
  1102. package/out/tools/postcode-triples.js +200 -193
  1103. package/out/tools/postcode-triples.js.map +1 -1
  1104. package/out/tools/source-register/build.d.ts +147 -0
  1105. package/out/tools/source-register/build.d.ts.map +1 -0
  1106. package/out/tools/source-register/build.js +517 -0
  1107. package/out/tools/source-register/build.js.map +1 -0
  1108. package/out/tools/sub/venue/head-nouns.d.ts +9 -38
  1109. package/out/tools/sub/venue/head-nouns.d.ts.map +1 -1
  1110. package/out/tools/sub/venue/head-nouns.js +37 -74
  1111. package/out/tools/sub/venue/head-nouns.js.map +1 -1
  1112. package/out/tools/sub/venue/lexicon.d.ts +53 -84
  1113. package/out/tools/sub/venue/lexicon.d.ts.map +1 -1
  1114. package/out/tools/sub/venue/lexicon.js +42 -90
  1115. package/out/tools/sub/venue/lexicon.js.map +1 -1
  1116. package/out/tools/sub/venue/wikidata.d.ts +8 -6
  1117. package/out/tools/sub/venue/wikidata.d.ts.map +1 -1
  1118. package/out/tools/sub/venue/wikidata.js +12 -9
  1119. package/out/tools/sub/venue/wikidata.js.map +1 -1
  1120. package/out/tw/tools/fetch/gcis.d.ts +9 -3
  1121. package/out/tw/tools/fetch/gcis.d.ts.map +1 -1
  1122. package/out/tw/tools/fetch/gcis.js +19 -13
  1123. package/out/tw/tools/fetch/gcis.js.map +1 -1
  1124. package/out/types.d.ts +271 -101
  1125. package/out/types.d.ts.map +1 -1
  1126. package/out/types.js +133 -9
  1127. package/out/types.js.map +1 -1
  1128. package/out/us/adapters/fcc-bdc/adapter.d.ts +18 -36
  1129. package/out/us/adapters/fcc-bdc/adapter.d.ts.map +1 -1
  1130. package/out/us/adapters/fcc-bdc/adapter.js +25 -38
  1131. package/out/us/adapters/fcc-bdc/adapter.js.map +1 -1
  1132. package/out/us/adapters/state/hi-schools/adapter.d.ts +12 -11
  1133. package/out/us/adapters/state/hi-schools/adapter.d.ts.map +1 -1
  1134. package/out/us/adapters/state/hi-schools/adapter.js +26 -16
  1135. package/out/us/adapters/state/hi-schools/adapter.js.map +1 -1
  1136. package/out/us/adapters/state/hi-schools/workbook.d.ts +8 -3
  1137. package/out/us/adapters/state/hi-schools/workbook.d.ts.map +1 -1
  1138. package/out/us/adapters/state/hi-schools/workbook.js +3 -1
  1139. package/out/us/adapters/state/hi-schools/workbook.js.map +1 -1
  1140. package/out/us/adapters/state/ia-contractors/adapter.d.ts +13 -6
  1141. package/out/us/adapters/state/ia-contractors/adapter.d.ts.map +1 -1
  1142. package/out/us/adapters/state/ia-contractors/adapter.js +27 -14
  1143. package/out/us/adapters/state/ia-contractors/adapter.js.map +1 -1
  1144. package/out/us/adapters/state/ny-notaries/adapter.d.ts +7 -6
  1145. package/out/us/adapters/state/ny-notaries/adapter.d.ts.map +1 -1
  1146. package/out/us/adapters/state/ny-notaries/adapter.js +24 -22
  1147. package/out/us/adapters/state/ny-notaries/adapter.js.map +1 -1
  1148. package/out/us/adapters/state/tx-notaries/adapter.d.ts +8 -7
  1149. package/out/us/adapters/state/tx-notaries/adapter.d.ts.map +1 -1
  1150. package/out/us/adapters/state/tx-notaries/adapter.js +21 -14
  1151. package/out/us/adapters/state/tx-notaries/adapter.js.map +1 -1
  1152. package/out/us/adapters/tiger/adapter.d.ts +10 -34
  1153. package/out/us/adapters/tiger/adapter.d.ts.map +1 -1
  1154. package/out/us/adapters/tiger/adapter.js +18 -42
  1155. package/out/us/adapters/tiger/adapter.js.map +1 -1
  1156. package/out/us/adapters/tiger/street-decompose.d.ts +6 -13
  1157. package/out/us/adapters/tiger/street-decompose.d.ts.map +1 -1
  1158. package/out/us/adapters/tiger/street-decompose.js +7 -17
  1159. package/out/us/adapters/tiger/street-decompose.js.map +1 -1
  1160. package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts +26 -20
  1161. package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts.map +1 -1
  1162. package/out/us/adapters/usgov/hrsa-fqhc/adapter.js +41 -29
  1163. package/out/us/adapters/usgov/hrsa-fqhc/adapter.js.map +1 -1
  1164. package/out/us/adapters/usgov/imls-pls/adapter.d.ts +8 -7
  1165. package/out/us/adapters/usgov/imls-pls/adapter.d.ts.map +1 -1
  1166. package/out/us/adapters/usgov/imls-pls/adapter.js +25 -18
  1167. package/out/us/adapters/usgov/imls-pls/adapter.js.map +1 -1
  1168. package/out/us/adapters/usgov/irs-bmf/adapter.d.ts +11 -10
  1169. package/out/us/adapters/usgov/irs-bmf/adapter.d.ts.map +1 -1
  1170. package/out/us/adapters/usgov/irs-bmf/adapter.js +32 -22
  1171. package/out/us/adapters/usgov/irs-bmf/adapter.js.map +1 -1
  1172. package/out/us/adapters/usgov/nad/adapter.d.ts +11 -31
  1173. package/out/us/adapters/usgov/nad/adapter.d.ts.map +1 -1
  1174. package/out/us/adapters/usgov/nad/adapter.js +57 -111
  1175. package/out/us/adapters/usgov/nad/adapter.js.map +1 -1
  1176. package/out/us/adapters/usgov/nppes/adapter.d.ts +12 -22
  1177. package/out/us/adapters/usgov/nppes/adapter.d.ts.map +1 -1
  1178. package/out/us/adapters/usgov/nppes/adapter.js +62 -32
  1179. package/out/us/adapters/usgov/nppes/adapter.js.map +1 -1
  1180. package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts +16 -15
  1181. package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts.map +1 -1
  1182. package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js +38 -28
  1183. package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js.map +1 -1
  1184. package/out/us/fips-state.d.ts +19 -10
  1185. package/out/us/fips-state.d.ts.map +1 -1
  1186. package/out/us/fips-state.js +17 -8
  1187. package/out/us/fips-state.js.map +1 -1
  1188. package/out/{synthesizers → us/synthesizers}/intersection.d.ts +10 -8
  1189. package/out/us/synthesizers/intersection.d.ts.map +1 -0
  1190. package/out/{synthesizers → us/synthesizers}/intersection.js +46 -35
  1191. package/out/us/synthesizers/intersection.js.map +1 -0
  1192. package/out/{synthesizers → us/synthesizers}/street.d.ts +19 -12
  1193. package/out/us/synthesizers/street.d.ts.map +1 -0
  1194. package/out/{synthesizers → us/synthesizers}/street.js +45 -38
  1195. package/out/us/synthesizers/street.js.map +1 -0
  1196. package/out/us/tools/fetch/hrsa.d.ts +3 -3
  1197. package/out/us/tools/fetch/hrsa.d.ts.map +1 -1
  1198. package/out/us/tools/fetch/hrsa.js +6 -7
  1199. package/out/us/tools/fetch/hrsa.js.map +1 -1
  1200. package/out/us/tools/fetch/imls-pls.d.ts +5 -16
  1201. package/out/us/tools/fetch/imls-pls.d.ts.map +1 -1
  1202. package/out/us/tools/fetch/imls-pls.js +17 -34
  1203. package/out/us/tools/fetch/imls-pls.js.map +1 -1
  1204. package/out/us/tools/fetch/nad.d.ts +22 -10
  1205. package/out/us/tools/fetch/nad.d.ts.map +1 -1
  1206. package/out/us/tools/fetch/nad.js +30 -25
  1207. package/out/us/tools/fetch/nad.js.map +1 -1
  1208. package/out/us/tools/fetch/nppes.d.ts +6 -16
  1209. package/out/us/tools/fetch/nppes.d.ts.map +1 -1
  1210. package/out/us/tools/fetch/nppes.js +24 -36
  1211. package/out/us/tools/fetch/nppes.js.map +1 -1
  1212. package/out/us/tools/fetch/state/hi-schools.d.ts +9 -5
  1213. package/out/us/tools/fetch/state/hi-schools.d.ts.map +1 -1
  1214. package/out/us/tools/fetch/state/hi-schools.js +16 -14
  1215. package/out/us/tools/fetch/state/hi-schools.js.map +1 -1
  1216. package/out/us/tools/fetch/state/sources.d.ts +8 -7
  1217. package/out/us/tools/fetch/state/sources.d.ts.map +1 -1
  1218. package/out/us/tools/fetch/state/sources.js +8 -9
  1219. package/out/us/tools/fetch/state/sources.js.map +1 -1
  1220. package/out/us/tools/fetch/tiger-full.d.ts +1 -14
  1221. package/out/us/tools/fetch/tiger-full.d.ts.map +1 -1
  1222. package/out/us/tools/fetch/tiger-full.js +16 -55
  1223. package/out/us/tools/fetch/tiger-full.js.map +1 -1
  1224. package/out/utils/align.d.ts +26 -19
  1225. package/out/utils/align.d.ts.map +1 -1
  1226. package/out/utils/align.js +32 -47
  1227. package/out/utils/align.js.map +1 -1
  1228. package/out/utils/cooccurrence-stats.d.ts +58 -0
  1229. package/out/utils/cooccurrence-stats.d.ts.map +1 -0
  1230. package/out/utils/cooccurrence-stats.js +62 -0
  1231. package/out/utils/cooccurrence-stats.js.map +1 -0
  1232. package/out/utils/golden.d.ts +21 -31
  1233. package/out/utils/golden.d.ts.map +1 -1
  1234. package/out/utils/golden.js +30 -46
  1235. package/out/utils/golden.js.map +1 -1
  1236. package/out/utils/license.d.ts +159 -22
  1237. package/out/utils/license.d.ts.map +1 -1
  1238. package/out/utils/license.js +156 -26
  1239. package/out/utils/license.js.map +1 -1
  1240. package/out/utils/split.d.ts +66 -70
  1241. package/out/utils/split.d.ts.map +1 -1
  1242. package/out/utils/split.js +162 -69
  1243. package/out/utils/split.js.map +1 -1
  1244. package/out/utils/tokenize.d.ts +15 -44
  1245. package/out/utils/tokenize.d.ts.map +1 -1
  1246. package/out/utils/tokenize.js +18 -31
  1247. package/out/utils/tokenize.js.map +1 -1
  1248. package/out/utils/wof-json.d.ts +88 -62
  1249. package/out/utils/wof-json.d.ts.map +1 -1
  1250. package/out/utils/wof-json.js +77 -56
  1251. package/out/utils/wof-json.js.map +1 -1
  1252. package/out/{utils/index.js → utils.d.ts} +1 -2
  1253. package/out/utils.d.ts.map +1 -0
  1254. package/out/{utils/index.d.ts → utils.js} +1 -2
  1255. package/out/utils.js.map +1 -0
  1256. package/out/ve/recipes/reviewed-postcode-tail.d.ts +25 -7
  1257. package/out/ve/recipes/reviewed-postcode-tail.d.ts.map +1 -1
  1258. package/out/ve/recipes/reviewed-postcode-tail.js +33 -12
  1259. package/out/ve/recipes/reviewed-postcode-tail.js.map +1 -1
  1260. package/package.json +45 -488
  1261. package/lib/adapters/index.ts +0 -160
  1262. package/lib/adapters/synth-po-box/adapter.ts +0 -204
  1263. package/lib/adapters/utils/index.ts +0 -307
  1264. package/lib/recipes/bare/postcode/index.ts +0 -327
  1265. package/lib/recipes/sub/venue/index.ts +0 -997
  1266. package/lib/synthesizers/locale.ts +0 -261
  1267. package/lib/test-kit/index.ts +0 -100
  1268. package/lib/tools/align-slice.ts +0 -68
  1269. package/lib/tools/fetch/index.ts +0 -174
  1270. package/lib/tools/gb-title-case.ts +0 -69
  1271. package/lib/tools/index.ts +0 -28
  1272. package/lib/tools/lint/slice/vocab.ts +0 -376
  1273. package/lib/tools/overlay-manifest.ts +0 -215
  1274. package/lib/tools/slice/translit.ts +0 -218
  1275. package/lib/tools/sub/venue/harvest.ts +0 -234
  1276. package/lib/tools/sub/venue/surfaces.ts +0 -95
  1277. package/lib/tools/sub/venue/table.ts +0 -281
  1278. package/lib/utils/parquet.ts +0 -582
  1279. package/out/adapters/index.d.ts +0 -51
  1280. package/out/adapters/index.d.ts.map +0 -1
  1281. package/out/adapters/index.js +0 -97
  1282. package/out/adapters/index.js.map +0 -1
  1283. package/out/adapters/synth-po-box/adapter.d.ts +0 -67
  1284. package/out/adapters/synth-po-box/adapter.d.ts.map +0 -1
  1285. package/out/adapters/synth-po-box/adapter.js.map +0 -1
  1286. package/out/adapters/utils/index.d.ts +0 -191
  1287. package/out/adapters/utils/index.d.ts.map +0 -1
  1288. package/out/adapters/utils/index.js +0 -206
  1289. package/out/adapters/utils/index.js.map +0 -1
  1290. package/out/fr/adapters/ban/street-decompose.d.ts.map +0 -1
  1291. package/out/fr/adapters/ban/street-decompose.js.map +0 -1
  1292. package/out/no/recipes/street/index.d.ts +0 -18
  1293. package/out/no/recipes/street/index.d.ts.map +0 -1
  1294. package/out/no/recipes/street/index.js.map +0 -1
  1295. package/out/recipes/bare/postcode/index.d.ts +0 -62
  1296. package/out/recipes/bare/postcode/index.d.ts.map +0 -1
  1297. package/out/recipes/bare/postcode/index.js.map +0 -1
  1298. package/out/recipes/index.d.ts +0 -24
  1299. package/out/recipes/index.d.ts.map +0 -1
  1300. package/out/recipes/index.js.map +0 -1
  1301. package/out/recipes/po/box/index.d.ts +0 -17
  1302. package/out/recipes/po/box/index.d.ts.map +0 -1
  1303. package/out/recipes/po/box/index.js.map +0 -1
  1304. package/out/recipes/sub/venue/index.d.ts +0 -270
  1305. package/out/recipes/sub/venue/index.d.ts.map +0 -1
  1306. package/out/recipes/sub/venue/index.js +0 -728
  1307. package/out/recipes/sub/venue/index.js.map +0 -1
  1308. package/out/synthesizers/intersection.d.ts.map +0 -1
  1309. package/out/synthesizers/intersection.js.map +0 -1
  1310. package/out/synthesizers/locale.d.ts +0 -116
  1311. package/out/synthesizers/locale.d.ts.map +0 -1
  1312. package/out/synthesizers/locale.js +0 -150
  1313. package/out/synthesizers/locale.js.map +0 -1
  1314. package/out/synthesizers/street.d.ts.map +0 -1
  1315. package/out/synthesizers/street.js.map +0 -1
  1316. package/out/test-kit/index.d.ts +0 -48
  1317. package/out/test-kit/index.d.ts.map +0 -1
  1318. package/out/test-kit/index.js +0 -78
  1319. package/out/test-kit/index.js.map +0 -1
  1320. package/out/tools/align-slice.d.ts +0 -7
  1321. package/out/tools/align-slice.d.ts.map +0 -1
  1322. package/out/tools/align-slice.js +0 -55
  1323. package/out/tools/align-slice.js.map +0 -1
  1324. package/out/tools/fetch/download/index.d.ts.map +0 -1
  1325. package/out/tools/fetch/download/index.js.map +0 -1
  1326. package/out/tools/fetch/index.d.ts +0 -171
  1327. package/out/tools/fetch/index.d.ts.map +0 -1
  1328. package/out/tools/fetch/index.js +0 -170
  1329. package/out/tools/fetch/index.js.map +0 -1
  1330. package/out/tools/gb-title-case.d.ts +0 -2
  1331. package/out/tools/gb-title-case.d.ts.map +0 -1
  1332. package/out/tools/gb-title-case.js +0 -65
  1333. package/out/tools/gb-title-case.js.map +0 -1
  1334. package/out/tools/golden/relabel-street/index.d.ts.map +0 -1
  1335. package/out/tools/golden/relabel-street/index.js.map +0 -1
  1336. package/out/tools/index.d.ts +0 -28
  1337. package/out/tools/index.d.ts.map +0 -1
  1338. package/out/tools/index.js +0 -28
  1339. package/out/tools/index.js.map +0 -1
  1340. package/out/tools/lint/slice/index.d.ts +0 -93
  1341. package/out/tools/lint/slice/index.d.ts.map +0 -1
  1342. package/out/tools/lint/slice/index.js.map +0 -1
  1343. package/out/tools/lint/slice/vocab.d.ts +0 -90
  1344. package/out/tools/lint/slice/vocab.d.ts.map +0 -1
  1345. package/out/tools/lint/slice/vocab.js.map +0 -1
  1346. package/out/tools/overlay-manifest.d.ts +0 -89
  1347. package/out/tools/overlay-manifest.d.ts.map +0 -1
  1348. package/out/tools/overlay-manifest.js +0 -131
  1349. package/out/tools/overlay-manifest.js.map +0 -1
  1350. package/out/tools/slice/kryptonite.d.ts +0 -32
  1351. package/out/tools/slice/kryptonite.d.ts.map +0 -1
  1352. package/out/tools/slice/kryptonite.js.map +0 -1
  1353. package/out/tools/slice/translit.d.ts +0 -51
  1354. package/out/tools/slice/translit.d.ts.map +0 -1
  1355. package/out/tools/slice/translit.js.map +0 -1
  1356. package/out/tools/sub/venue/harvest.d.ts +0 -100
  1357. package/out/tools/sub/venue/harvest.d.ts.map +0 -1
  1358. package/out/tools/sub/venue/harvest.js +0 -168
  1359. package/out/tools/sub/venue/harvest.js.map +0 -1
  1360. package/out/tools/sub/venue/promotions.d.ts +0 -94
  1361. package/out/tools/sub/venue/promotions.d.ts.map +0 -1
  1362. package/out/tools/sub/venue/promotions.js.map +0 -1
  1363. package/out/tools/sub/venue/surfaces.d.ts +0 -45
  1364. package/out/tools/sub/venue/surfaces.d.ts.map +0 -1
  1365. package/out/tools/sub/venue/surfaces.js +0 -77
  1366. package/out/tools/sub/venue/surfaces.js.map +0 -1
  1367. package/out/tools/sub/venue/table.d.ts +0 -229
  1368. package/out/tools/sub/venue/table.d.ts.map +0 -1
  1369. package/out/tools/sub/venue/table.js +0 -108
  1370. package/out/tools/sub/venue/table.js.map +0 -1
  1371. package/out/utils/index.d.ts.map +0 -1
  1372. package/out/utils/index.js.map +0 -1
  1373. package/out/utils/parquet.d.ts +0 -178
  1374. package/out/utils/parquet.d.ts.map +0 -1
  1375. package/out/utils/parquet.js +0 -371
  1376. package/out/utils/parquet.js.map +0 -1
  1377. package/out/utils/slice-stats.d.ts +0 -52
  1378. package/out/utils/slice-stats.d.ts.map +0 -1
  1379. package/out/utils/slice-stats.js +0 -58
  1380. package/out/utils/slice-stats.js.map +0 -1
  1381. /package/lib/tools/fetch/{download/index.ts → download.ts} +0 -0
  1382. /package/lib/tools/golden/{relabel-street/index.ts → relabel-street.ts} +0 -0
@@ -0,0 +1,69 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ * @file The adapter phase: drive each configured adapter to its own `canonical.jsonl`, or reuse the run a
6
+ * previous build finished.
7
+ */
8
+ import { readLocalJSONFile } from "@mailwoman/core/fs/readers";
9
+ import { pathExists, statPath } from "@mailwoman/core/fs/readers/stat";
10
+ import { $public } from "#env";
11
+ import { runAdapter } from "#runner";
12
+ /**
13
+ * Reuse a finished adapter run, or return `null` when this build has to drive the adapter.
14
+ *
15
+ * @throws When the cached manifest and the file on disk disagree on the byte count.
16
+ * The writer flushes the canonical file before writing the manifest.
17
+ * Manifest presence establishes that the writer reached the end of its run.
18
+ * The manifest describes the file as of that moment.
19
+ * A truncated copy, an interrupted move or a partial transfer leaves the
20
+ * manifest intact beside a shorter file.
21
+ * The recorded byte count distinguishes those cases.
22
+ * A resumed build that reuses a short file can produce a corpus whose row count later readers accept.
23
+ */
24
+ async function reusableRun(adapterID, adapterDir) {
25
+ if ($public.MAILWOMAN_RESUME !== "1")
26
+ return null;
27
+ const cachedManifest = adapterDir("MANIFEST.json");
28
+ const canonicalPath = adapterDir("canonical.jsonl");
29
+ if (!(await pathExists(cachedManifest)) || !(await pathExists(canonicalPath)))
30
+ return null;
31
+ const cached = await readLocalJSONFile(cachedManifest);
32
+ const onDisk = (await statPath(canonicalPath)).size;
33
+ if (onDisk !== cached.bytes) {
34
+ throw new Error(`resume refused for ${adapterID}: ${canonicalPath} is ${onDisk.toLocaleString()} bytes and its ` +
35
+ `manifest records ${cached.bytes.toLocaleString()}. Delete ${cachedManifest} to ` +
36
+ `re-run the adapter, or restore the file this manifest describes.`);
37
+ }
38
+ return cached;
39
+ }
40
+ /**
41
+ * Drive every configured adapter, reusing whatever a previous build already finished.
42
+ */
43
+ export async function runAdapterPhase(opts) {
44
+ const runs = [];
45
+ const skipped = [];
46
+ for (const adapter of opts.adapters) {
47
+ const adapterOptions = opts.adapterInputs[adapter.id];
48
+ if (!adapterOptions) {
49
+ skipped.push(adapter.id);
50
+ opts.onProgress?.("adapter-run", `skipped ${adapter.id} (no input configured)`);
51
+ continue;
52
+ }
53
+ const cached = await reusableRun(adapter.id, opts.intermediateDir(adapter.id));
54
+ if (cached) {
55
+ opts.onProgress?.("adapter-run", `resumed ${adapter.id} (reused ${cached.yielded} canonical rows)`);
56
+ runs.push(cached);
57
+ continue;
58
+ }
59
+ opts.onProgress?.("adapter-run", `running ${adapter.id}`);
60
+ runs.push(await runAdapter({
61
+ adapter,
62
+ adapterOptions,
63
+ outputDir: opts.intermediateDir,
64
+ corpusVersion: opts.corpusVersion,
65
+ }));
66
+ }
67
+ return { runs, skipped };
68
+ }
69
+ //# sourceMappingURL=adapters.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"adapters.js","sourceRoot":"","sources":["../../lib/build/adapters.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH,OAAO,EAAE,iBAAiB,EAAE,MAAM,4BAA4B,CAAA;AAC9D,OAAO,EAAE,UAAU,EAAE,QAAQ,EAAE,MAAM,iCAAiC,CAAA;AAItE,OAAO,EAAE,OAAO,EAAE,MAAM,MAAM,CAAA;AAC9B,OAAO,EAAE,UAAU,EAA2B,MAAM,SAAS,CAAA;AAuB7D;;;;;;;;;;;GAWG;AACH,KAAK,UAAU,WAAW,CAAC,SAAiB,EAAE,UAAuB;IACpE,IAAI,OAAO,CAAC,gBAAgB,KAAK,GAAG;QAAE,OAAO,IAAI,CAAA;IAEjD,MAAM,cAAc,GAAG,UAAU,CAAC,eAAe,CAAC,CAAA;IAClD,MAAM,aAAa,GAAG,UAAU,CAAC,iBAAiB,CAAC,CAAA;IAEnD,IAAI,CAAC,CAAC,MAAM,UAAU,CAAC,cAAc,CAAC,CAAC,IAAI,CAAC,CAAC,MAAM,UAAU,CAAC,aAAa,CAAC,CAAC;QAAE,OAAO,IAAI,CAAA;IAE1F,MAAM,MAAM,GAAG,MAAM,iBAAiB,CAAqB,cAAc,CAAC,CAAA;IAC1E,MAAM,MAAM,GAAG,CAAC,MAAM,QAAQ,CAAC,aAAa,CAAC,CAAC,CAAC,IAAI,CAAA;IAEnD,IAAI,MAAM,KAAK,MAAM,CAAC,KAAK,EAAE,CAAC;QAC7B,MAAM,IAAI,KAAK,CACd,sBAAsB,SAAS,KAAK,aAAa,OAAO,MAAM,CAAC,cAAc,EAAE,iBAAiB;YAC/F,oBAAoB,MAAM,CAAC,KAAK,CAAC,cAAc,EAAE,YAAY,cAAc,MAAM;YACjF,kEAAkE,CACnE,CAAA;IACF,CAAC;IAED,OAAO,MAAM,CAAA;AACd,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,eAAe,CAAC,IAAyB;IAC9D,MAAM,IAAI,GAAyB,EAAE,CAAA;IACrC,MAAM,OAAO,GAAa,EAAE,CAAA;IAE5B,KAAK,MAAM,OAAO,IAAI,IAAI,CAAC,QAAQ,EAAE,CAAC;QACrC,MAAM,cAAc,GAAG,IAAI,CAAC,aAAa,CAAC,OAAO,CAAC,EAAE,CAAC,CAAA;QAErD,IAAI,CAAC,cAAc,EAAE,CAAC;YACrB,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE,CAAC,CAAA;YACxB,IAAI,CAAC,UAAU,EAAE,CAAC,aAAa,EAAE,WAAW,OAAO,CAAC,EAAE,wBAAwB,CAAC,CAAA;YAE/E,SAAQ;QACT,CAAC;QAED,MAAM,MAAM,GAAG,MAAM,WAAW,CAAC,OAAO,CAAC,EAAE,EAAE,IAAI,CAAC,eAAe,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC,CAAA;QAE9E,IAAI,MAAM,EAAE,CAAC;YACZ,IAAI,CAAC,UAAU,EAAE,CAAC,aAAa,EAAE,WAAW,OAAO,CAAC,EAAE,YAAY,MAAM,CAAC,OAAO,kBAAkB,CAAC,CAAA;YACnG,IAAI,CAAC,IAAI,CAAC,MAAM,CAAC,CAAA;YAEjB,SAAQ;QACT,CAAC;QAED,IAAI,CAAC,UAAU,EAAE,CAAC,aAAa,EAAE,WAAW,OAAO,CAAC,EAAE,EAAE,CAAC,CAAA;QAEzD,IAAI,CAAC,IAAI,CACR,MAAM,UAAU,CAAC;YAChB,OAAO;YACP,cAAc;YACd,SAAS,EAAE,IAAI,CAAC,eAAe;YAC/B,aAAa,EAAE,IAAI,CAAC,aAAa;SACjC,CAAC,CACF,CAAA;IACF,CAAC;IAED,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,CAAA;AACzB,CAAC"}
@@ -0,0 +1,74 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ * @file The align phase reads each adapter's canonical rows and applies license and register refusals.
6
+ * It expands synthesis and aligns each row. It then routes the result to a split or quarantine.
7
+ *
8
+ * The phase appends to four files. It writes a checkpoint at each adapter boundary, allowing an interrupted
9
+ * build to resume at the next adapter without aligning earlier adapters again.
10
+ */
11
+ import type { PathBuilder } from "path-ts";
12
+ import type { BuildProfile, BuildStage } from "#build/types";
13
+ import { type AdapterRunManifest } from "#runner";
14
+ import { type LicensePolicy, type LicenseRefusalKind, type LicenseVerdictCache } from "#utils/license";
15
+ import { type CountryHoldout, type SplitName } from "#utils/split";
16
+ export interface AlignPhaseOptions {
17
+ /**
18
+ * The adapter runs to align, in the order their rows enter the output files.
19
+ */
20
+ adapterRuns: readonly AdapterRunManifest[];
21
+ corpusVersion: string;
22
+ synthesize: boolean;
23
+ profile: BuildProfile;
24
+ licensePolicy: LicensePolicy;
25
+ excludeLicenses: readonly RegExp[];
26
+ holdouts: Record<string, CountryHoldout>;
27
+ /**
28
+ * Each register source's ingest-eligibility reasons, or `null` under the exploratory profile.
29
+ */
30
+ eligibility: ReadonlyMap<string, readonly string[]> | null;
31
+ labeledPaths: Record<SplitName, PathBuilder>;
32
+ quarantinePath: PathBuilder;
33
+ checkpointPath: PathBuilder;
34
+ onProgress?: (stage: BuildStage, message: string) => void;
35
+ }
36
+ /**
37
+ * The counts produced by the align phase.
38
+ *
39
+ * The build uses them in its manifest and frozen source record.
40
+ */
41
+ export interface AlignPhaseResult {
42
+ aligned: number;
43
+ quarantined: number;
44
+ counts: Record<SplitName, number>;
45
+ licenseCounts: Map<string, number>;
46
+ refusedByKind: Map<LicenseRefusalKind, number>;
47
+ /**
48
+ * Rows the license policy refused, counted per `source`.
49
+ *
50
+ * A source here contributed zero rows to the corpus whatever its adapter reported writing.
51
+ * That is the distinction between a source present in corpus provenance
52
+ * and one present in model provenance.
53
+ */
54
+ refusedBySource: Map<string, number>;
55
+ excludedByLicense: number;
56
+ admittedUnresolved: number;
57
+ excludedByEligibility: number;
58
+ rowsBySource: Map<string, {
59
+ rows: number;
60
+ license: string;
61
+ }>;
62
+ ineligibleSources: Map<string, readonly string[]>;
63
+ /**
64
+ * The license cache used by this phase.
65
+ *
66
+ * Its `refusedValues()` method returns every value it refused.
67
+ */
68
+ licenses: LicenseVerdictCache;
69
+ }
70
+ /**
71
+ * Align every adapter run's rows into the four output files, writing a checkpoint at each adapter boundary.
72
+ */
73
+ export declare function runAlignPhase(opts: AlignPhaseOptions): Promise<AlignPhaseResult>;
74
+ //# sourceMappingURL=align.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"align.d.ts","sourceRoot":"","sources":["../../lib/build/align.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAMH,OAAO,KAAK,EAAE,WAAW,EAAE,MAAM,SAAS,CAAA;AAY1C,OAAO,KAAK,EAAE,YAAY,EAAE,UAAU,EAAE,MAAM,cAAc,CAAA;AAE5D,OAAO,EAAqB,KAAK,kBAAkB,EAAE,MAAM,SAAS,CAAA;AAIpE,OAAO,EAEN,KAAK,aAAa,EAClB,KAAK,kBAAkB,EACvB,KAAK,mBAAmB,EACxB,MAAM,gBAAgB,CAAA;AACvB,OAAO,EAAe,KAAK,cAAc,EAAE,KAAK,SAAS,EAAE,MAAM,cAAc,CAAA;AAE/E,MAAM,WAAW,iBAAiB;IACjC;;OAEG;IACH,WAAW,EAAE,SAAS,kBAAkB,EAAE,CAAA;IAE1C,aAAa,EAAE,MAAM,CAAA;IACrB,UAAU,EAAE,OAAO,CAAA;IACnB,OAAO,EAAE,YAAY,CAAA;IACrB,aAAa,EAAE,aAAa,CAAA;IAC5B,eAAe,EAAE,SAAS,MAAM,EAAE,CAAA;IAClC,QAAQ,EAAE,MAAM,CAAC,MAAM,EAAE,cAAc,CAAC,CAAA;IAExC;;OAEG;IACH,WAAW,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,GAAG,IAAI,CAAA;IAE1D,YAAY,EAAE,MAAM,CAAC,SAAS,EAAE,WAAW,CAAC,CAAA;IAC5C,cAAc,EAAE,WAAW,CAAA;IAC3B,cAAc,EAAE,WAAW,CAAA;IAE3B,UAAU,CAAC,EAAE,CAAC,KAAK,EAAE,UAAU,EAAE,OAAO,EAAE,MAAM,KAAK,IAAI,CAAA;CACzD;AAED;;;;GAIG;AACH,MAAM,WAAW,gBAAgB;IAChC,OAAO,EAAE,MAAM,CAAA;IACf,WAAW,EAAE,MAAM,CAAA;IACnB,MAAM,EAAE,MAAM,CAAC,SAAS,EAAE,MAAM,CAAC,CAAA;IACjC,aAAa,EAAE,GAAG,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IAClC,aAAa,EAAE,GAAG,CAAC,kBAAkB,EAAE,MAAM,CAAC,CAAA;IAC9C;;;;;;OAMG;IACH,eAAe,EAAE,GAAG,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IACpC,iBAAiB,EAAE,MAAM,CAAA;IACzB,kBAAkB,EAAE,MAAM,CAAA;IAC1B,qBAAqB,EAAE,MAAM,CAAA;IAC7B,YAAY,EAAE,GAAG,CAAC,MAAM,EAAE;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAA;KAAE,CAAC,CAAA;IAC5D,iBAAiB,EAAE,GAAG,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAA;IAEjD;;;;OAIG;IACH,QAAQ,EAAE,mBAAmB,CAAA;CAC7B;AA2DD;;GAEG;AACH,wBAAsB,aAAa,CAAC,IAAI,EAAE,iBAAiB,GAAG,OAAO,CAAC,gBAAgB,CAAC,CA6MtF"}
@@ -0,0 +1,226 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ * @file The align phase reads each adapter's canonical rows and applies license and register refusals.
6
+ * It expands synthesis and aligns each row. It then routes the result to a split or quarantine.
7
+ *
8
+ * The phase appends to four files. It writes a checkpoint at each adapter boundary, allowing an interrupted
9
+ * build to resume at the next adapter without aligning earlier adapters again.
10
+ */
11
+ import { openWriteStream } from "@mailwoman/core/fs/streams";
12
+ import { truncateFile } from "@mailwoman/core/fs/writers";
13
+ import { sha256Hex } from "@mailwoman/core/hash";
14
+ import { stringifyJSON } from "@mailwoman/core/json";
15
+ import { ALIGN_OUTPUTS, readAlignCheckpoint, writeAlignCheckpoint, } from "#build/checkpoint";
16
+ import { createIneligibilityReader } from "#build/eligibility";
17
+ import { streamJSONL } from "#build/rows";
18
+ import { $public } from "#env";
19
+ import { flushStream, once } from "#runner";
20
+ import { defaultAugmentationsForCountry, synthesizeRow } from "#synthesizers/utils";
21
+ import { alignRow } from "#utils/align";
22
+ import { createLicenseVerdictCache, } from "#utils/license";
23
+ import { splitForRow } from "#utils/split";
24
+ /**
25
+ * Return each output to the length the checkpoint recorded.
26
+ *
27
+ * Whatever the interrupted adapter wrote past the boundary is discarded, because the checkpoint's
28
+ * accumulators do not count those rows and the split manifests are computed from the accumulators.
29
+ */
30
+ async function restoreOutputs(checkpoint, paths) {
31
+ for (const name of ALIGN_OUTPUTS) {
32
+ await truncateFile(paths[name], checkpoint.offsets[name]);
33
+ }
34
+ }
35
+ /**
36
+ * Restore the accumulators a checkpoint recorded into this run's containers.
37
+ */
38
+ function restoreTally(checkpoint, result) {
39
+ for (const name of ["train", "val", "test"]) {
40
+ result.counts[name] = checkpoint.counts[name];
41
+ }
42
+ for (const [license, count] of Object.entries(checkpoint.license_counts)) {
43
+ result.licenseCounts.set(license, count);
44
+ }
45
+ for (const [kind, count] of Object.entries(checkpoint.refused_by_kind)) {
46
+ result.refusedByKind.set(kind, count);
47
+ }
48
+ for (const [source, count] of Object.entries(checkpoint.refused_by_source)) {
49
+ result.refusedBySource.set(source, count);
50
+ }
51
+ for (const [source, contributed] of Object.entries(checkpoint.rows_by_source)) {
52
+ result.rowsBySource.set(source, contributed);
53
+ }
54
+ return {
55
+ aligned: checkpoint.aligned,
56
+ quarantined: checkpoint.quarantined,
57
+ excludedByLicense: checkpoint.excluded_by_license,
58
+ admittedUnresolved: checkpoint.admitted_unresolved_license_rows,
59
+ excludedByEligibility: checkpoint.excluded_by_eligibility,
60
+ };
61
+ }
62
+ /**
63
+ * Align every adapter run's rows into the four output files, writing a checkpoint at each adapter boundary.
64
+ */
65
+ export async function runAlignPhase(opts) {
66
+ const ineligibility = createIneligibilityReader(opts.eligibility);
67
+ const licenses = createLicenseVerdictCache(opts.licensePolicy, opts.excludeLicenses);
68
+ const result = {
69
+ aligned: 0,
70
+ quarantined: 0,
71
+ counts: { train: 0, val: 0, test: 0 },
72
+ licenseCounts: new Map(),
73
+ refusedByKind: new Map(),
74
+ excludedByLicense: 0,
75
+ admittedUnresolved: 0,
76
+ excludedByEligibility: 0,
77
+ refusedBySource: new Map(),
78
+ rowsBySource: new Map(),
79
+ ineligibleSources: ineligibility.refused,
80
+ licenses,
81
+ };
82
+ const settings = {
83
+ corpus_version: opts.corpusVersion,
84
+ synthesize: opts.synthesize,
85
+ license_policy: opts.licensePolicy,
86
+ exclude_licenses: opts.excludeLicenses.map((pattern) => pattern.source).toSorted(),
87
+ profile: opts.profile,
88
+ holdout_digest: sha256Hex(stringifyJSON(opts.holdouts)),
89
+ };
90
+ const paths = { ...opts.labeledPaths, quarantine: opts.quarantinePath };
91
+ const checkpoint = $public.MAILWOMAN_RESUME === "1"
92
+ ? await readAlignCheckpoint(opts.checkpointPath, {
93
+ settings,
94
+ adapterOrder: opts.adapterRuns.map((run) => run.adapter_id),
95
+ })
96
+ : null;
97
+ let tally = {
98
+ aligned: 0,
99
+ quarantined: 0,
100
+ excludedByLicense: 0,
101
+ admittedUnresolved: 0,
102
+ excludedByEligibility: 0,
103
+ };
104
+ if (checkpoint) {
105
+ await restoreOutputs(checkpoint, paths);
106
+ tally = restoreTally(checkpoint, result);
107
+ opts.onProgress?.("align", `resumed align after ${checkpoint.completed_adapters.join(", ")} ` +
108
+ `(${tally.aligned.toLocaleString()} aligned rows)`);
109
+ }
110
+ // `a` rather than the default `w` on a resume, because the files hold the rows the checkpoint counted.
111
+ const flags = checkpoint ? "a" : "w";
112
+ const streams = {
113
+ train: openWriteStream(paths.train, { encoding: "utf8", flags }),
114
+ val: openWriteStream(paths.val, { encoding: "utf8", flags }),
115
+ test: openWriteStream(paths.test, { encoding: "utf8", flags }),
116
+ quarantine: openWriteStream(paths.quarantine, { encoding: "utf8", flags }),
117
+ };
118
+ const offsets = checkpoint
119
+ ? { ...checkpoint.offsets }
120
+ : { train: 0, val: 0, test: 0, quarantine: 0 };
121
+ const writeLine = (name, line) => {
122
+ offsets[name] += Buffer.byteLength(line, "utf8");
123
+ streams[name].write(line);
124
+ };
125
+ const quarantine = (row, reason) => {
126
+ writeLine("quarantine", `${stringifyJSON({ row, reason })}\n`);
127
+ };
128
+ const completed = checkpoint ? [...checkpoint.completed_adapters] : [];
129
+ for (const adapterRun of opts.adapterRuns) {
130
+ if (completed.includes(adapterRun.adapter_id))
131
+ continue;
132
+ opts.onProgress?.("align", `aligning ${adapterRun.adapter_id}`);
133
+ for await (const row of streamJSONL(adapterRun.jsonl_path)) {
134
+ result.licenseCounts.set(row.license, (result.licenseCounts.get(row.license) ?? 0) + 1);
135
+ // The license count is incremented before the drop, so the manifest's license set
136
+ // reflects what the corpus contained and `excluded_by_license` what was removed.
137
+ const verdict = licenses.read(row.license);
138
+ if (verdict.refusal) {
139
+ tally.excludedByLicense++;
140
+ result.refusedByKind.set(verdict.refusal, (result.refusedByKind.get(verdict.refusal) ?? 0) + 1);
141
+ // Counted per source as well as per refusal kind, because an adapter's own
142
+ // `written` count records what it emitted rather than what entered the corpus.
143
+ // A source refused here contributed no row, and model provenance generated from model provenance
144
+ // generated from `adapters[].written` only would credit it with rows it did not supply.
145
+ result.refusedBySource.set(row.source, (result.refusedBySource.get(row.source) ?? 0) + 1);
146
+ continue;
147
+ }
148
+ // An admitted row whose license resolves to no expression entered with
149
+ // unknown obligations rather than with none.
150
+ // The manifest states the count so a consumer can tell the two apart.
151
+ if (!verdict.resolved) {
152
+ tally.admittedUnresolved++;
153
+ }
154
+ // Eligibility runs before augmentation: a synthetic row inherits its ancestor's `source`,
155
+ // so refusing the ancestor here refuses everything fanned from it.
156
+ const ineligible = ineligibility.read(row);
157
+ if (ineligible) {
158
+ tally.excludedByEligibility++;
159
+ quarantine(row, `source-ineligible:${ineligible.join("; ")}`);
160
+ continue;
161
+ }
162
+ // Counted after both refusals, so the frozen manifest records what a source
163
+ // contributed rather than what it offered.
164
+ const contributed = result.rowsBySource.get(row.source);
165
+ result.rowsBySource.set(row.source, { rows: (contributed?.rows ?? 0) + 1, license: row.license });
166
+ const fanned = [row];
167
+ if (opts.synthesize) {
168
+ for (const aug of synthesizeRow(row, defaultAugmentationsForCountry(row.country))) {
169
+ fanned.push(aug);
170
+ }
171
+ }
172
+ for (const r of fanned) {
173
+ let aligned;
174
+ try {
175
+ aligned = alignRow(r);
176
+ }
177
+ catch (error) {
178
+ // No single row may crash a multi-hour build.
179
+ // An unknown throw is quarantined as `align-threw`, and a rise in
180
+ // that reason's count is a finding.
181
+ quarantine(r, `align-threw:${error.message.slice(0, 160)}`);
182
+ tally.quarantined++;
183
+ continue;
184
+ }
185
+ if (aligned.kind === "labeled") {
186
+ const split = splitForRow(aligned.row, opts.holdouts);
187
+ writeLine(split, `${stringifyJSON(aligned.row)}\n`);
188
+ result.counts[split]++;
189
+ tally.aligned++;
190
+ }
191
+ else {
192
+ quarantine(r, aligned.row.reason);
193
+ tally.quarantined++;
194
+ }
195
+ }
196
+ }
197
+ // The checkpoint is written at the adapter boundary, after the bytes it counts have reached disk.
198
+ // Mid-adapter recovery is unavailable.
199
+ // The largest adapter takes about twenty minutes to align.
200
+ // A row offset inside one adapter's file would still require replaying that adapter's synthesis.
201
+ await Promise.all(ALIGN_OUTPUTS.map((name) => flushStream(streams[name])));
202
+ completed.push(adapterRun.adapter_id);
203
+ await writeAlignCheckpoint(opts.checkpointPath, {
204
+ settings,
205
+ completed_adapters: [...completed],
206
+ offsets: { ...offsets },
207
+ counts: { ...result.counts },
208
+ aligned: tally.aligned,
209
+ quarantined: tally.quarantined,
210
+ license_counts: Object.fromEntries(result.licenseCounts),
211
+ refused_by_kind: Object.fromEntries(result.refusedByKind),
212
+ refused_by_source: Object.fromEntries(result.refusedBySource),
213
+ excluded_by_license: tally.excludedByLicense,
214
+ admitted_unresolved_license_rows: tally.admittedUnresolved,
215
+ excluded_by_eligibility: tally.excludedByEligibility,
216
+ rows_by_source: Object.fromEntries(result.rowsBySource),
217
+ written_at: new Date().toISOString(),
218
+ });
219
+ }
220
+ for (const stream of Object.values(streams)) {
221
+ stream.end();
222
+ }
223
+ await Promise.all(Object.values(streams).map((stream) => once(stream, "close")));
224
+ return { ...result, ...tally };
225
+ }
226
+ //# sourceMappingURL=align.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"align.js","sourceRoot":"","sources":["../../lib/build/align.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAEH,OAAO,EAAE,eAAe,EAAoB,MAAM,4BAA4B,CAAA;AAC9E,OAAO,EAAE,YAAY,EAAE,MAAM,4BAA4B,CAAA;AACzD,OAAO,EAAE,SAAS,EAAE,MAAM,sBAAsB,CAAA;AAChD,OAAO,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAA;AAGpD,OAAO,EACN,aAAa,EACb,mBAAmB,EACnB,oBAAoB,GAIpB,MAAM,mBAAmB,CAAA;AAC1B,OAAO,EAAE,yBAAyB,EAAE,MAAM,oBAAoB,CAAA;AAC9D,OAAO,EAAE,WAAW,EAAE,MAAM,aAAa,CAAA;AAEzC,OAAO,EAAE,OAAO,EAAE,MAAM,MAAM,CAAA;AAC9B,OAAO,EAAE,WAAW,EAAE,IAAI,EAA2B,MAAM,SAAS,CAAA;AACpE,OAAO,EAAE,8BAA8B,EAAE,aAAa,EAAE,MAAM,qBAAqB,CAAA;AAEnF,OAAO,EAAE,QAAQ,EAAE,MAAM,cAAc,CAAA;AACvC,OAAO,EACN,yBAAyB,GAIzB,MAAM,gBAAgB,CAAA;AACvB,OAAO,EAAE,WAAW,EAAuC,MAAM,cAAc,CAAA;AAwE/E;;;;;GAKG;AACH,KAAK,UAAU,cAAc,CAAC,UAA2B,EAAE,KAA2C;IACrG,KAAK,MAAM,IAAI,IAAI,aAAa,EAAE,CAAC;QAClC,MAAM,YAAY,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,UAAU,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAA;IAC1D,CAAC;AACF,CAAC;AAED;;GAEG;AACH,SAAS,YAAY,CAAC,UAA2B,EAAE,MAAwB;IAC1E,KAAK,MAAM,IAAI,IAAI,CAAC,OAAO,EAAE,KAAK,EAAE,MAAM,CAAU,EAAE,CAAC;QACtD,MAAM,CAAC,MAAM,CAAC,IAAI,CAAC,GAAG,UAAU,CAAC,MAAM,CAAC,IAAI,CAAC,CAAA;IAC9C,CAAC;IAED,KAAK,MAAM,CAAC,OAAO,EAAE,KAAK,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,UAAU,CAAC,cAAc,CAAC,EAAE,CAAC;QAC1E,MAAM,CAAC,aAAa,CAAC,GAAG,CAAC,OAAO,EAAE,KAAK,CAAC,CAAA;IACzC,CAAC;IAED,KAAK,MAAM,CAAC,IAAI,EAAE,KAAK,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,UAAU,CAAC,eAAe,CAAC,EAAE,CAAC;QACxE,MAAM,CAAC,aAAa,CAAC,GAAG,CAAC,IAA0B,EAAE,KAAK,CAAC,CAAA;IAC5D,CAAC;IAED,KAAK,MAAM,CAAC,MAAM,EAAE,KAAK,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,UAAU,CAAC,iBAAiB,CAAC,EAAE,CAAC;QAC5E,MAAM,CAAC,eAAe,CAAC,GAAG,CAAC,MAAM,EAAE,KAAK,CAAC,CAAA;IAC1C,CAAC;IAED,KAAK,MAAM,CAAC,MAAM,EAAE,WAAW,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,UAAU,CAAC,cAAc,CAAC,EAAE,CAAC;QAC/E,MAAM,CAAC,YAAY,CAAC,GAAG,CAAC,MAAM,EAAE,WAAW,CAAC,CAAA;IAC7C,CAAC;IAED,OAAO;QACN,OAAO,EAAE,UAAU,CAAC,OAAO;QAC3B,WAAW,EAAE,UAAU,CAAC,WAAW;QACnC,iBAAiB,EAAE,UAAU,CAAC,mBAAmB;QACjD,kBAAkB,EAAE,UAAU,CAAC,gCAAgC;QAC/D,qBAAqB,EAAE,UAAU,CAAC,uBAAuB;KACzD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,aAAa,CAAC,IAAuB;IAC1D,MAAM,aAAa,GAAG,yBAAyB,CAAC,IAAI,CAAC,WAAW,CAAC,CAAA;IACjE,MAAM,QAAQ,GAAG,yBAAyB,CAAC,IAAI,CAAC,aAAa,EAAE,IAAI,CAAC,eAAe,CAAC,CAAA;IAEpF,MAAM,MAAM,GAAqB;QAChC,OAAO,EAAE,CAAC;QACV,WAAW,EAAE,CAAC;QACd,MAAM,EAAE,EAAE,KAAK,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,IAAI,EAAE,CAAC,EAAE;QACrC,aAAa,EAAE,IAAI,GAAG,EAAE;QACxB,aAAa,EAAE,IAAI,GAAG,EAAE;QACxB,iBAAiB,EAAE,CAAC;QACpB,kBAAkB,EAAE,CAAC;QACrB,qBAAqB,EAAE,CAAC;QACxB,eAAe,EAAE,IAAI,GAAG,EAAE;QAC1B,YAAY,EAAE,IAAI,GAAG,EAAE;QACvB,iBAAiB,EAAE,aAAa,CAAC,OAAO;QACxC,QAAQ;KACR,CAAA;IAED,MAAM,QAAQ,GAAkB;QAC/B,cAAc,EAAE,IAAI,CAAC,aAAa;QAClC,UAAU,EAAE,IAAI,CAAC,UAAU;QAC3B,cAAc,EAAE,IAAI,CAAC,aAAa;QAClC,gBAAgB,EAAE,IAAI,CAAC,eAAe,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC,QAAQ,EAAE;QAClF,OAAO,EAAE,IAAI,CAAC,OAAO;QACrB,cAAc,EAAE,SAAS,CAAC,aAAa,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;KACvD,CAAA;IAED,MAAM,KAAK,GAAyC,EAAE,GAAG,IAAI,CAAC,YAAY,EAAE,UAAU,EAAE,IAAI,CAAC,cAAc,EAAE,CAAA;IAE7G,MAAM,UAAU,GACf,OAAO,CAAC,gBAAgB,KAAK,GAAG;QAC/B,CAAC,CAAC,MAAM,mBAAmB,CAAC,IAAI,CAAC,cAAc,EAAE;YAC/C,QAAQ;YACR,YAAY,EAAE,IAAI,CAAC,WAAW,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,GAAG,CAAC,UAAU,CAAC;SAC3D,CAAC;QACH,CAAC,CAAC,IAAI,CAAA;IAER,IAAI,KAAK,GAAe;QACvB,OAAO,EAAE,CAAC;QACV,WAAW,EAAE,CAAC;QACd,iBAAiB,EAAE,CAAC;QACpB,kBAAkB,EAAE,CAAC;QACrB,qBAAqB,EAAE,CAAC;KACxB,CAAA;IAED,IAAI,UAAU,EAAE,CAAC;QAChB,MAAM,cAAc,CAAC,UAAU,EAAE,KAAK,CAAC,CAAA;QACvC,KAAK,GAAG,YAAY,CAAC,UAAU,EAAE,MAAM,CAAC,CAAA;QAExC,IAAI,CAAC,UAAU,EAAE,CAChB,OAAO,EACP,uBAAuB,UAAU,CAAC,kBAAkB,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG;YACjE,IAAI,KAAK,CAAC,OAAO,CAAC,cAAc,EAAE,gBAAgB,CACnD,CAAA;IACF,CAAC;IAED,uGAAuG;IACvG,MAAM,KAAK,GAAG,UAAU,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,GAAG,CAAA;IAEpC,MAAM,OAAO,GAAyC;QACrD,KAAK,EAAE,eAAe,CAAC,KAAK,CAAC,KAAK,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC;QAChE,GAAG,EAAE,eAAe,CAAC,KAAK,CAAC,GAAG,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC;QAC5D,IAAI,EAAE,eAAe,CAAC,KAAK,CAAC,IAAI,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC;QAC9D,UAAU,EAAE,eAAe,CAAC,KAAK,CAAC,UAAU,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC;KAC1E,CAAA;IAED,MAAM,OAAO,GAAoC,UAAU;QAC1D,CAAC,CAAC,EAAE,GAAG,UAAU,CAAC,OAAO,EAAE;QAC3B,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,IAAI,EAAE,CAAC,EAAE,UAAU,EAAE,CAAC,EAAE,CAAA;IAE/C,MAAM,SAAS,GAAG,CAAC,IAAqB,EAAE,IAAY,EAAQ,EAAE;QAC/D,OAAO,CAAC,IAAI,CAAC,IAAI,MAAM,CAAC,UAAU,CAAC,IAAI,EAAE,MAAM,CAAC,CAAA;QAChD,OAAO,CAAC,IAAI,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,CAAA;IAC1B,CAAC,CAAA;IAED,MAAM,UAAU,GAAG,CAAC,GAAiB,EAAE,MAAc,EAAQ,EAAE;QAC9D,SAAS,CAAC,YAAY,EAAE,GAAG,aAAa,CAAC,EAAE,GAAG,EAAE,MAAM,EAAE,CAAC,IAAI,CAAC,CAAA;IAC/D,CAAC,CAAA;IAED,MAAM,SAAS,GAAG,UAAU,CAAC,CAAC,CAAC,CAAC,GAAG,UAAU,CAAC,kBAAkB,CAAC,CAAC,CAAC,CAAC,EAAE,CAAA;IAEtE,KAAK,MAAM,UAAU,IAAI,IAAI,CAAC,WAAW,EAAE,CAAC;QAC3C,IAAI,SAAS,CAAC,QAAQ,CAAC,UAAU,CAAC,UAAU,CAAC;YAAE,SAAQ;QAEvD,IAAI,CAAC,UAAU,EAAE,CAAC,OAAO,EAAE,YAAY,UAAU,CAAC,UAAU,EAAE,CAAC,CAAA;QAE/D,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,WAAW,CAAe,UAAU,CAAC,UAAU,CAAC,EAAE,CAAC;YAC1E,MAAM,CAAC,aAAa,CAAC,GAAG,CAAC,GAAG,CAAC,OAAO,EAAE,CAAC,MAAM,CAAC,aAAa,CAAC,GAAG,CAAC,GAAG,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAA;YAEvF,kFAAkF;YAClF,iFAAiF;YACjF,MAAM,OAAO,GAAG,QAAQ,CAAC,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,CAAA;YAE1C,IAAI,OAAO,CAAC,OAAO,EAAE,CAAC;gBACrB,KAAK,CAAC,iBAAiB,EAAE,CAAA;gBACzB,MAAM,CAAC,aAAa,CAAC,GAAG,CAAC,OAAO,CAAC,OAAO,EAAE,CAAC,MAAM,CAAC,aAAa,CAAC,GAAG,CAAC,OAAO,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAA;gBAE/F,2EAA2E;gBAC3E,+EAA+E;gBAC/E,iGAAiG;gBACjG,wFAAwF;gBACxF,MAAM,CAAC,eAAe,CAAC,GAAG,CAAC,GAAG,CAAC,MAAM,EAAE,CAAC,MAAM,CAAC,eAAe,CAAC,GAAG,CAAC,GAAG,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAA;gBAEzF,SAAQ;YACT,CAAC;YAED,uEAAuE;YACvE,6CAA6C;YAC7C,sEAAsE;YACtE,IAAI,CAAC,OAAO,CAAC,QAAQ,EAAE,CAAC;gBACvB,KAAK,CAAC,kBAAkB,EAAE,CAAA;YAC3B,CAAC;YAED,0FAA0F;YAC1F,mEAAmE;YACnE,MAAM,UAAU,GAAG,aAAa,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;YAE1C,IAAI,UAAU,EAAE,CAAC;gBAChB,KAAK,CAAC,qBAAqB,EAAE,CAAA;gBAE7B,UAAU,CAAC,GAAG,EAAE,qBAAqB,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAA;gBAE7D,SAAQ;YACT,CAAC;YAED,4EAA4E;YAC5E,2CAA2C;YAC3C,MAAM,WAAW,GAAG,MAAM,CAAC,YAAY,CAAC,GAAG,CAAC,GAAG,CAAC,MAAM,CAAC,CAAA;YAEvD,MAAM,CAAC,YAAY,CAAC,GAAG,CAAC,GAAG,CAAC,MAAM,EAAE,EAAE,IAAI,EAAE,CAAC,WAAW,EAAE,IAAI,IAAI,CAAC,CAAC,GAAG,CAAC,EAAE,OAAO,EAAE,GAAG,CAAC,OAAO,EAAE,CAAC,CAAA;YAEjG,MAAM,MAAM,GAAmB,CAAC,GAAG,CAAC,CAAA;YAEpC,IAAI,IAAI,CAAC,UAAU,EAAE,CAAC;gBACrB,KAAK,MAAM,GAAG,IAAI,aAAa,CAAC,GAAG,EAAE,8BAA8B,CAAC,GAAG,CAAC,OAAO,CAAC,CAAC,EAAE,CAAC;oBACnF,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;gBACjB,CAAC;YACF,CAAC;YAED,KAAK,MAAM,CAAC,IAAI,MAAM,EAAE,CAAC;gBACxB,IAAI,OAAoC,CAAA;gBAExC,IAAI,CAAC;oBACJ,OAAO,GAAG,QAAQ,CAAC,CAAC,CAAC,CAAA;gBACtB,CAAC;gBAAC,OAAO,KAAK,EAAE,CAAC;oBAChB,8CAA8C;oBAC9C,kEAAkE;oBAClE,oCAAoC;oBACpC,UAAU,CAAC,CAAC,EAAE,eAAgB,KAAe,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,EAAE,CAAC,CAAA;oBAEtE,KAAK,CAAC,WAAW,EAAE,CAAA;oBAEnB,SAAQ;gBACT,CAAC;gBAED,IAAI,OAAO,CAAC,IAAI,KAAK,SAAS,EAAE,CAAC;oBAChC,MAAM,KAAK,GAAG,WAAW,CAAC,OAAO,CAAC,GAAG,EAAE,IAAI,CAAC,QAAQ,CAAC,CAAA;oBAErD,SAAS,CAAC,KAAK,EAAE,GAAG,aAAa,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;oBAEnD,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE,CAAA;oBAEtB,KAAK,CAAC,OAAO,EAAE,CAAA;gBAChB,CAAC;qBAAM,CAAC;oBACP,UAAU,CAAC,CAAC,EAAE,OAAO,CAAC,GAAG,CAAC,MAAM,CAAC,CAAA;oBAEjC,KAAK,CAAC,WAAW,EAAE,CAAA;gBACpB,CAAC;YACF,CAAC;QACF,CAAC;QAED,kGAAkG;QAClG,uCAAuC;QACvC,2DAA2D;QAC3D,iGAAiG;QACjG,MAAM,OAAO,CAAC,GAAG,CAAC,aAAa,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,WAAW,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,CAAA;QAE1E,SAAS,CAAC,IAAI,CAAC,UAAU,CAAC,UAAU,CAAC,CAAA;QAErC,MAAM,oBAAoB,CAAC,IAAI,CAAC,cAAc,EAAE;YAC/C,QAAQ;YACR,kBAAkB,EAAE,CAAC,GAAG,SAAS,CAAC;YAClC,OAAO,EAAE,EAAE,GAAG,OAAO,EAAE;YACvB,MAAM,EAAE,EAAE,GAAG,MAAM,CAAC,MAAM,EAAE;YAC5B,OAAO,EAAE,KAAK,CAAC,OAAO;YACtB,WAAW,EAAE,KAAK,CAAC,WAAW;YAC9B,cAAc,EAAE,MAAM,CAAC,WAAW,CAAC,MAAM,CAAC,aAAa,CAAC;YACxD,eAAe,EAAE,MAAM,CAAC,WAAW,CAAC,MAAM,CAAC,aAAa,CAAC;YACzD,iBAAiB,EAAE,MAAM,CAAC,WAAW,CAAC,MAAM,CAAC,eAAe,CAAC;YAC7D,mBAAmB,EAAE,KAAK,CAAC,iBAAiB;YAC5C,gCAAgC,EAAE,KAAK,CAAC,kBAAkB;YAC1D,uBAAuB,EAAE,KAAK,CAAC,qBAAqB;YACpD,cAAc,EAAE,MAAM,CAAC,WAAW,CAAC,MAAM,CAAC,YAAY,CAAC;YACvD,UAAU,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;SACpC,CAAC,CAAA;IACH,CAAC;IAED,KAAK,MAAM,MAAM,IAAI,MAAM,CAAC,MAAM,CAAC,OAAO,CAAC,EAAE,CAAC;QAC7C,MAAM,CAAC,GAAG,EAAE,CAAA;IACb,CAAC;IAED,MAAM,OAAO,CAAC,GAAG,CAAC,MAAM,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,IAAI,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC,CAAC,CAAA;IAEhF,OAAO,EAAE,GAAG,MAAM,EAAE,GAAG,KAAK,EAAE,CAAA;AAC/B,CAAC"}
@@ -0,0 +1,94 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ * @file The align phase's resume point. It records aligned adapters and each output's length at that moment.
6
+ * It also records every accumulator used to compute the manifest.
7
+ *
8
+ * The adapter phase recovers from its per-adapter `MANIFEST.json`. Align, split and parquet ran 6 h 35 min
9
+ * of the 8 h 27 min `v0.7.0-de-holdout` build with no recovery point, because the four labeled streams are
10
+ * truncated at open and every accumulator is a local. This file is what a resumed align phase reads
11
+ * instead of starting over.
12
+ *
13
+ * The phase is replayable only when the same rows produce the same output, so the checkpoint records the
14
+ * settings that change alignment and refuses a resume under different ones. `align-determinism` in
15
+ * `build.test.ts` compares four output digests across two builds over one intermediate directory.
16
+ */
17
+ import type { PathBuilderLike } from "path-ts";
18
+ /**
19
+ * The four append-only outputs of the align phase, by the name in each file.
20
+ */
21
+ export declare const ALIGN_OUTPUTS: readonly ["train", "val", "test", "quarantine"];
22
+ export type AlignOutputName = (typeof ALIGN_OUTPUTS)[number];
23
+ /**
24
+ * The settings that change what the align phase writes for a given input row.
25
+ *
26
+ * A resume under different settings would mix two policies inside one output file,
27
+ * so the checkpoint records these and a mismatch refuses the resume rather than continuing.
28
+ */
29
+ export interface AlignSettings {
30
+ corpus_version: string;
31
+ synthesize: boolean;
32
+ license_policy: string;
33
+ exclude_licenses: readonly string[];
34
+ profile: string;
35
+ holdout_digest: string;
36
+ }
37
+ /**
38
+ * The align phase's state at an adapter boundary.
39
+ */
40
+ export interface AlignCheckpoint {
41
+ settings: AlignSettings;
42
+ /**
43
+ * Adapter ids whose rows are already in the four outputs, in the order they were aligned.
44
+ *
45
+ * A resume requires this to be a prefix of the current run's adapter order.
46
+ * Alignment appends, so a different order would place a later adapter's rows
47
+ * before an earlier one's and change every split file's contents.
48
+ */
49
+ completed_adapters: string[];
50
+ /**
51
+ * Byte length of each output at the checkpoint, after its writes were flushed.
52
+ *
53
+ * A resumed build shortens each file to this length.
54
+ * The shortening discards whatever the interrupted adapter wrote past the boundary.
55
+ */
56
+ offsets: Record<AlignOutputName, number>;
57
+ counts: Record<"train" | "val" | "test", number>;
58
+ aligned: number;
59
+ quarantined: number;
60
+ license_counts: Record<string, number>;
61
+ refused_by_kind: Record<string, number>;
62
+ /**
63
+ * Rows the license policy refused, counted per `source`, so a resumed build keeps the tally
64
+ * rather than restarting it at zero and understating the refusal in its manifest.
65
+ */
66
+ refused_by_source: Record<string, number>;
67
+ excluded_by_license: number;
68
+ admitted_unresolved_license_rows: number;
69
+ excluded_by_eligibility: number;
70
+ rows_by_source: Record<string, {
71
+ rows: number;
72
+ license: string;
73
+ }>;
74
+ written_at: string;
75
+ }
76
+ /**
77
+ * Read the align checkpoint, or return `null` when the build has not reached one.
78
+ *
79
+ * @throws When the checkpoint describes different settings, or an adapter order
80
+ * the current run does not begin with.
81
+ * Both cases would append this run's rows to a file written under different rules.
82
+ * The resulting corpus could report a row count that later readers accept.
83
+ */
84
+ export declare function readAlignCheckpoint(path: PathBuilderLike, expected: {
85
+ settings: AlignSettings;
86
+ adapterOrder: readonly string[];
87
+ }): Promise<AlignCheckpoint | null>;
88
+ /**
89
+ * Write the align checkpoint.
90
+ *
91
+ * The caller flushes the four outputs before calling this, so every byte the offsets count is on disk.
92
+ */
93
+ export declare function writeAlignCheckpoint(path: PathBuilderLike, checkpoint: AlignCheckpoint): Promise<void>;
94
+ //# sourceMappingURL=checkpoint.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"checkpoint.d.ts","sourceRoot":"","sources":["../../lib/build/checkpoint.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;GAeG;AAOH,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,SAAS,CAAA;AAE9C;;GAEG;AACH,eAAO,MAAM,aAAa,YAAI,OAAO,EAAE,KAAK,EAAE,MAAM,EAAE,YAAY,CAAU,CAAA;AAE5E,MAAM,MAAM,eAAe,GAAG,CAAC,OAAO,aAAa,CAAC,CAAC,MAAM,CAAC,CAAA;AAE5D;;;;;GAKG;AACH,MAAM,WAAW,aAAa;IAC7B,cAAc,EAAE,MAAM,CAAA;IACtB,UAAU,EAAE,OAAO,CAAA;IACnB,cAAc,EAAE,MAAM,CAAA;IACtB,gBAAgB,EAAE,SAAS,MAAM,EAAE,CAAA;IACnC,OAAO,EAAE,MAAM,CAAA;IACf,cAAc,EAAE,MAAM,CAAA;CACtB;AAED;;GAEG;AACH,MAAM,WAAW,eAAe;IAC/B,QAAQ,EAAE,aAAa,CAAA;IAEvB;;;;;;OAMG;IACH,kBAAkB,EAAE,MAAM,EAAE,CAAA;IAE5B;;;;;OAKG;IACH,OAAO,EAAE,MAAM,CAAC,eAAe,EAAE,MAAM,CAAC,CAAA;IAExC,MAAM,EAAE,MAAM,CAAC,OAAO,GAAG,KAAK,GAAG,MAAM,EAAE,MAAM,CAAC,CAAA;IAChD,OAAO,EAAE,MAAM,CAAA;IACf,WAAW,EAAE,MAAM,CAAA;IACnB,cAAc,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IACtC,eAAe,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IACvC;;;OAGG;IACH,iBAAiB,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IACzC,mBAAmB,EAAE,MAAM,CAAA;IAC3B,gCAAgC,EAAE,MAAM,CAAA;IACxC,uBAAuB,EAAE,MAAM,CAAA;IAC/B,cAAc,EAAE,MAAM,CAAC,MAAM,EAAE;QAAE,IAAI,EAAE,MAAM,CAAC;QAAC,OAAO,EAAE,MAAM,CAAA;KAAE,CAAC,CAAA;IACjE,UAAU,EAAE,MAAM,CAAA;CAClB;AAED;;;;;;;GAOG;AACH,wBAAsB,mBAAmB,CACxC,IAAI,EAAE,eAAe,EACrB,QAAQ,EAAE;IAAE,QAAQ,EAAE,aAAa,CAAC;IAAC,YAAY,EAAE,SAAS,MAAM,EAAE,CAAA;CAAE,GACpE,OAAO,CAAC,eAAe,GAAG,IAAI,CAAC,CA0BjC;AAED;;;;GAIG;AACH,wBAAgB,oBAAoB,CAAC,IAAI,EAAE,eAAe,EAAE,UAAU,EAAE,eAAe,GAAG,OAAO,CAAC,IAAI,CAAC,CAEtG"}
@@ -0,0 +1,61 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ * @file The align phase's resume point. It records aligned adapters and each output's length at that moment.
6
+ * It also records every accumulator used to compute the manifest.
7
+ *
8
+ * The adapter phase recovers from its per-adapter `MANIFEST.json`. Align, split and parquet ran 6 h 35 min
9
+ * of the 8 h 27 min `v0.7.0-de-holdout` build with no recovery point, because the four labeled streams are
10
+ * truncated at open and every accumulator is a local. This file is what a resumed align phase reads
11
+ * instead of starting over.
12
+ *
13
+ * The phase is replayable only when the same rows produce the same output, so the checkpoint records the
14
+ * settings that change alignment and refuses a resume under different ones. `align-determinism` in
15
+ * `build.test.ts` compares four output digests across two builds over one intermediate directory.
16
+ */
17
+ import { readLocalJSONFile } from "@mailwoman/core/fs/readers";
18
+ import { pathExists } from "@mailwoman/core/fs/readers/stat";
19
+ import { writeLocalJSONFile } from "@mailwoman/core/fs/writers";
20
+ import { isIdentical } from "@mailwoman/core/identical";
21
+ import { stringifyJSON } from "@mailwoman/core/json";
22
+ /**
23
+ * The four append-only outputs of the align phase, by the name in each file.
24
+ */
25
+ export const ALIGN_OUTPUTS = ["train", "val", "test", "quarantine"];
26
+ /**
27
+ * Read the align checkpoint, or return `null` when the build has not reached one.
28
+ *
29
+ * @throws When the checkpoint describes different settings, or an adapter order
30
+ * the current run does not begin with.
31
+ * Both cases would append this run's rows to a file written under different rules.
32
+ * The resulting corpus could report a row count that later readers accept.
33
+ */
34
+ export async function readAlignCheckpoint(path, expected) {
35
+ if (!(await pathExists(path)))
36
+ return null;
37
+ const checkpoint = await readLocalJSONFile(path);
38
+ const found = stringifyJSON(checkpoint.settings);
39
+ const wanted = stringifyJSON(expected.settings);
40
+ if (found !== wanted) {
41
+ throw new Error(`resume refused: ${path.toString()} was written under ${found} and this build runs under ${wanted}. ` +
42
+ `Delete the intermediate directory's labeled and quarantine files together with this checkpoint to ` +
43
+ `align from the start.`);
44
+ }
45
+ const prefix = expected.adapterOrder.slice(0, checkpoint.completed_adapters.length);
46
+ if (!isIdentical(prefix, checkpoint.completed_adapters)) {
47
+ throw new Error(`resume refused: ${path.toString()} recorded ${stringifyJSON(checkpoint.completed_adapters)} as aligned ` +
48
+ `and this build's adapter order begins ${stringifyJSON(prefix)}. Alignment appends, so the rows would ` +
49
+ `land in a different order than the recorded offsets describe.`);
50
+ }
51
+ return checkpoint;
52
+ }
53
+ /**
54
+ * Write the align checkpoint.
55
+ *
56
+ * The caller flushes the four outputs before calling this, so every byte the offsets count is on disk.
57
+ */
58
+ export function writeAlignCheckpoint(path, checkpoint) {
59
+ return writeLocalJSONFile(checkpoint, path).then(() => undefined);
60
+ }
61
+ //# sourceMappingURL=checkpoint.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"checkpoint.js","sourceRoot":"","sources":["../../lib/build/checkpoint.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;GAeG;AAEH,OAAO,EAAE,iBAAiB,EAAE,MAAM,4BAA4B,CAAA;AAC9D,OAAO,EAAE,UAAU,EAAE,MAAM,iCAAiC,CAAA;AAC5D,OAAO,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAA;AAC/D,OAAO,EAAE,WAAW,EAAE,MAAM,2BAA2B,CAAA;AACvD,OAAO,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAA;AAGpD;;GAEG;AACH,MAAM,CAAC,MAAM,aAAa,GAAG,CAAC,OAAO,EAAE,KAAK,EAAE,MAAM,EAAE,YAAY,CAAU,CAAA;AA2D5E;;;;;;;GAOG;AACH,MAAM,CAAC,KAAK,UAAU,mBAAmB,CACxC,IAAqB,EACrB,QAAsE;IAEtE,IAAI,CAAC,CAAC,MAAM,UAAU,CAAC,IAAI,CAAC,CAAC;QAAE,OAAO,IAAI,CAAA;IAE1C,MAAM,UAAU,GAAG,MAAM,iBAAiB,CAAkB,IAAI,CAAC,CAAA;IACjE,MAAM,KAAK,GAAG,aAAa,CAAC,UAAU,CAAC,QAAQ,CAAC,CAAA;IAChD,MAAM,MAAM,GAAG,aAAa,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAA;IAE/C,IAAI,KAAK,KAAK,MAAM,EAAE,CAAC;QACtB,MAAM,IAAI,KAAK,CACd,mBAAmB,IAAI,CAAC,QAAQ,EAAE,sBAAsB,KAAK,8BAA8B,MAAM,IAAI;YACpG,oGAAoG;YACpG,uBAAuB,CACxB,CAAA;IACF,CAAC;IAED,MAAM,MAAM,GAAG,QAAQ,CAAC,YAAY,CAAC,KAAK,CAAC,CAAC,EAAE,UAAU,CAAC,kBAAkB,CAAC,MAAM,CAAC,CAAA;IAEnF,IAAI,CAAC,WAAW,CAAC,MAAM,EAAE,UAAU,CAAC,kBAAkB,CAAC,EAAE,CAAC;QACzD,MAAM,IAAI,KAAK,CACd,mBAAmB,IAAI,CAAC,QAAQ,EAAE,aAAa,aAAa,CAAC,UAAU,CAAC,kBAAkB,CAAC,cAAc;YACxG,yCAAyC,aAAa,CAAC,MAAM,CAAC,yCAAyC;YACvG,+DAA+D,CAChE,CAAA;IACF,CAAC;IAED,OAAO,UAAU,CAAA;AAClB,CAAC;AAED;;;;GAIG;AACH,MAAM,UAAU,oBAAoB,CAAC,IAAqB,EAAE,UAA2B;IACtF,OAAO,kBAAkB,CAAC,UAAU,EAAE,IAAI,CAAC,CAAC,IAAI,CAAC,GAAG,EAAE,CAAC,SAAS,CAAC,CAAA;AAClE,CAAC"}
@@ -0,0 +1,47 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ * @file What the address-source register records about a row's source, read once per build.
6
+ */
7
+ import { type LicenseDecision } from "#source-register";
8
+ import type { CanonicalRow } from "#types";
9
+ /**
10
+ * The key a row is looked up under: the adapter that emitted it and the jurisdiction it describes.
11
+ *
12
+ * The register scopes a source to one publisher in one jurisdiction,
13
+ * so an adapter id by itself cannot address a record.
14
+ * One adapter serves several: `ban` emits eleven jurisdictions from one schema
15
+ * and each is its own source under its own license decision.
16
+ */
17
+ export declare function sourceEligibilityKey(adapterID: string, iso2: string): string;
18
+ /**
19
+ * Every register source's ingest-eligibility reasons, keyed by the adapter
20
+ * and jurisdiction of the rows that recorded it.
21
+ *
22
+ * A source declaring no `adapterID` is absent from the map, because no adapter emits it
23
+ * and no row can arrive under it.
24
+ * An empty array is the only value a caller may read as permission.
25
+ * An absent key is refused rather than admitted.
26
+ */
27
+ export declare function readSourceEligibility(): Promise<ReadonlyMap<string, readonly string[]>>;
28
+ /**
29
+ * The register's license decisions keyed by the label in a row.
30
+ *
31
+ * An unmatched adapter label records a `null` decision rather than inventing one.
32
+ */
33
+ export declare function readRegisterDecisions(): Promise<ReadonlyMap<string, LicenseDecision>>;
34
+ /**
35
+ * Reads why a row's source may be refused from a release-eligible corpus.
36
+ * Records each refused source.
37
+ *
38
+ * `refused` accumulates as rows arrive.
39
+ * The build manifest reports the collected values.
40
+ *
41
+ * A build whose `eligibility` is `null` runs under the exploratory profile and every row reads eligible.
42
+ */
43
+ export declare function createIneligibilityReader(eligibility: ReadonlyMap<string, readonly string[]> | null): {
44
+ refused: Map<string, readonly string[]>;
45
+ read: (row: CanonicalRow) => readonly string[] | null;
46
+ };
47
+ //# sourceMappingURL=eligibility.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"eligibility.d.ts","sourceRoot":"","sources":["../../lib/build/eligibility.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAIH,OAAO,EAAwD,KAAK,eAAe,EAAE,MAAM,kBAAkB,CAAA;AAC7G,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,QAAQ,CAAA;AAE1C;;;;;;;GAOG;AACH,wBAAgB,oBAAoB,CAAC,SAAS,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,GAAG,MAAM,CAE5E;AAED;;;;;;;;GAQG;AACH,wBAAsB,qBAAqB,IAAI,OAAO,CAAC,WAAW,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAC,CAW7F;AAED;;;;GAIG;AACH,wBAAsB,qBAAqB,IAAI,OAAO,CAAC,WAAW,CAAC,MAAM,EAAE,eAAe,CAAC,CAAC,CAI3F;AAED;;;;;;;;GAQG;AACH,wBAAgB,yBAAyB,CAAC,WAAW,EAAE,WAAW,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,GAAG,IAAI,GAAG;IACtG,OAAO,EAAE,GAAG,CAAC,MAAM,EAAE,SAAS,MAAM,EAAE,CAAC,CAAA;IACvC,IAAI,EAAE,CAAC,GAAG,EAAE,YAAY,KAAK,SAAS,MAAM,EAAE,GAAG,IAAI,CAAA;CACrD,CA0BA"}