@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
package/out/runner.js CHANGED
@@ -3,54 +3,74 @@
3
3
  * @license AGPL-3.0
4
4
  * @author Teffen Ellis, et al.
5
5
  *
6
- * Adapter runner — drives a `CorpusAdapter` to completion and writes intermediate JSONL + a
7
- * per-slice manifest.
8
- *
9
- * Output layout under `outputDir`:
10
- *
11
- * ```
12
- * <outputDir>/<adapter.id>/
13
- * canonical.jsonl # one row per line, in emission order
14
- * MANIFEST.json # adapter id, version, row count, sha256, license, started_at, ended_at
15
- * ```
16
- *
17
- * The runner is responsible for everything an adapter is **not** responsible for:
18
- *
19
- * - Stamping `corpus_version` on every row (adapters must NOT set it).
20
- * - Applying `canonicalDedupKey` and skipping duplicates.
21
- * - Streaming sha256 over JSONL bytes so the manifest checksum doesn't require a re-read.
22
- * - Honoring backpressure on the output write stream.
23
- * - Counting + emitting periodic progress to an optional callback.
24
- * - Honoring `signal` (delegates to adapter's iteration boundary).
25
- *
26
- * The runner does NOT perform alignment, tokenization, synthesis, or slicing into Parquet. Those
27
- * steps run later, consuming the JSONL slices this writes.
6
+ * Adapter runner — drives a `CorpusAdapter` to completion and writes `canonical.jsonl` plus a
7
+ * `MANIFEST.json` per adapter. It does not align, tokenize, synthesize, or write Parquet.
28
8
  */
9
+ import { isAlpha2CodeShape } from "@mailwoman/codex/country";
29
10
  import { openWriteStream } from "@mailwoman/core/fs/streams";
30
11
  import { writeLocalJSONFile, makeDirectories } from "@mailwoman/core/fs/writers";
31
- import { join } from "path-ts";
32
- import { canonicalDedupKey, streamingSha256 } from "#adapters/utils";
12
+ import { stringifyJSON } from "@mailwoman/core/json";
13
+ import { resolvePathBuilder } from "path-ts";
14
+ import { canonicalDedupKey } from "#adapters/dedup-key";
15
+ import { streamingSha256 } from "#adapters/sha256-stream";
16
+ import { FingerprintSet } from "#fingerprints";
33
17
  /**
34
- * Drive a single adapter to completion.
18
+ * Base-2 logarithm of the fingerprint table's slot count.
35
19
  *
36
- * Returns the manifest describing the run. Writes `canonical.jsonl` + `MANIFEST.json` under `outputDir/<adapter.id>/`.
37
- * Throws if the output directory cannot be created, if a row arrives with a missing required field, or if the abort
38
- * signal fires.
20
+ * 2^27 slots hold 93,952,409 keys before the load limit.
21
+ * The largest measured adapter has 57,570,829 distinct keys.
22
+ * The table occupies 2.0 GiB outside the V8 heap.
23
+ */
24
+ export const DEFAULT_DEDUP_SLOTS_LOG2 = 27;
25
+ /**
26
+ * How many distinct dedup keys a `Set`-backed run holds before it stops adding new ones.
27
+ *
28
+ * A V8 `Set` refuses a 16,777,216th entry outright, so this cap was a real bound rather than a preference.
29
+ * It applies only to a run that opts out of the fingerprint table
30
+ * through {@linkcode RunAdapterOptions.dedupMaxSize}.
31
+ */
32
+ export const DEFAULT_DEDUP_MAX_SIZE = 10_000_000;
33
+ /**
34
+ * Where a run held its dedup keys.
35
+ */
36
+ export const DedupStore = {
37
+ /**
38
+ * 128-bit fingerprints in a flat `Uint32Array`, bounded by the array the run sized.
39
+ */
40
+ FingerprintTable: "fingerprint-table",
41
+ /**
42
+ * A V8 `Set` of key strings, capped because V8 refuses a 16,777,216th entry.
43
+ */
44
+ CappedSet: "capped-set",
45
+ };
46
+ /**
47
+ * Drive a single adapter to completion, writing its jsonl and manifest under `outputDir/<adapter.id>/`.
39
48
  */
40
49
  export async function runAdapter(opts) {
41
- const { adapter, adapterOptions, outputDir, corpusVersion } = opts;
50
+ const { adapter, outputDir, corpusVersion } = opts;
51
+ // A caller that passes its own map reads the counts back from it.
52
+ // Otherwise the runner supplies one, so every manifest records the adapter's drop reasons.
53
+ const dropped = opts.adapterOptions.dropped ?? new Map();
54
+ const adapterOptions = { ...opts.adapterOptions, dropped };
42
55
  const progressEvery = opts.progressEvery ?? 1000;
43
- const adapterDir = join(outputDir, adapter.id);
56
+ const adapterDir = resolvePathBuilder(outputDir, adapter.id);
44
57
  await makeDirectories(adapterDir);
45
- const jsonlPath = join(adapterDir, "canonical.jsonl");
46
- const manifestPath = join(adapterDir, "MANIFEST.json");
58
+ const jsonlPath = adapterDir("canonical.jsonl");
59
+ const manifestPath = adapterDir("MANIFEST.json");
47
60
  const startedAt = new Date();
48
61
  const t0 = performance.now();
49
62
  const stream = openWriteStream(jsonlPath, { encoding: "utf8" });
50
63
  const hasher = streamingSha256();
51
- const seen = new Set();
52
- const DEDUP_MAX_SIZE = 10_000_000;
64
+ // The `Set` path serves callers that cannot accept a fingerprint collision dropping a legitimate row.
65
+ // A test also uses it to reach the capped behavior in three rows.
66
+ // Every other run takes the table.
67
+ // Its entry count is bounded by the array it sized rather than by V8's `Set` limit.
68
+ const capped = opts.dedupMaxSize !== undefined;
69
+ const seen = capped ? new Set() : null;
70
+ const fingerprints = capped ? null : new FingerprintSet(opts.dedupSlotsLog2 ?? DEFAULT_DEDUP_SLOTS_LOG2);
71
+ const dedupMaxSize = opts.dedupMaxSize ?? DEFAULT_DEDUP_MAX_SIZE;
53
72
  let dedupExhausted = false;
73
+ let dedupExhaustedAtYielded = null;
54
74
  let yielded = 0;
55
75
  let written = 0;
56
76
  let bytes = 0;
@@ -70,24 +90,54 @@ export async function runAdapter(opts) {
70
90
  }
71
91
  yielded++;
72
92
  assertEmittedRow(adapter, row);
73
- const stamped = { ...row, corpus_version: corpusVersion };
93
+ const stamped = {
94
+ ...row,
95
+ // The rename is the runner's, after `assertEmittedRow` has held the adapter to emitting its own id.
96
+ source: opts.sourceName ?? row.source,
97
+ corpus_version: corpusVersion,
98
+ addressRole: row.addressRole ?? adapter.addressRole,
99
+ // `register` is nullable and null is a statement rather than an absence,
100
+ // so only an undefined field takes the adapter's declaration.
101
+ register: row.register === undefined ? adapter.register : row.register,
102
+ surface: row.surface ?? adapter.surface,
103
+ };
74
104
  const key = canonicalDedupKey(stamped);
75
- if (!dedupExhausted) {
76
- if (seen.has(key)) {
105
+ if (fingerprints) {
106
+ // The table holds every key the run has seen, so a duplicate is refused wherever it arrives.
107
+ if (!fingerprints.add(key)) {
77
108
  if (yielded % progressEvery === 0) {
78
109
  emitProgress();
79
110
  }
80
111
  continue;
81
112
  }
82
- if (seen.size >= DEDUP_MAX_SIZE) {
83
- dedupExhausted = true;
84
- process.stderr.write(` runner: dedup set full at ${DEDUP_MAX_SIZE.toLocaleString()} — skipping dedup for remaining rows\n`);
113
+ }
114
+ else if (seen) {
115
+ // The membership test runs whether or not the set is full.
116
+ // The cap stops the set from growing.
117
+ // The set still rejects every duplicate of a key it holds.
118
+ // Without the membership test at the cap, duplicates of the first
119
+ // `dedupMaxSize` keys passed through.
120
+ // This ordering keeps those duplicates out.
121
+ if (seen.has(key)) {
122
+ if (yielded % progressEvery === 0) {
123
+ emitProgress();
124
+ }
125
+ continue;
85
126
  }
86
- else {
87
- seen.add(key);
127
+ if (!dedupExhausted) {
128
+ if (seen.size >= dedupMaxSize) {
129
+ dedupExhausted = true;
130
+ dedupExhaustedAtYielded = yielded;
131
+ process.stderr.write(` runner: dedup set full at ${dedupMaxSize.toLocaleString()} keys after ${yielded.toLocaleString()} ` +
132
+ `yielded rows — a later row duplicating a key already held is still dropped, and a duplicate of ` +
133
+ `a key first seen from here on is written\n`);
134
+ }
135
+ else {
136
+ seen.add(key);
137
+ }
88
138
  }
89
139
  }
90
- const line = `${JSON.stringify(stamped)}\n`;
140
+ const line = `${stringifyJSON(stamped)}\n`;
91
141
  hasher.update(line);
92
142
  bytes += Buffer.byteLength(line, "utf8");
93
143
  written++;
@@ -103,6 +153,9 @@ export async function runAdapter(opts) {
103
153
  stream.end();
104
154
  await once(stream, "close");
105
155
  }
156
+ // Every adapter honors `signal` by returning instead, so without this a truncated
157
+ // `canonical.jsonl` would be recorded as a finished run.
158
+ adapterOptions.signal?.throwIfAborted();
106
159
  const endedAt = new Date();
107
160
  const elapsed_ms = performance.now() - t0;
108
161
  emitProgress();
@@ -114,9 +167,13 @@ export async function runAdapter(opts) {
114
167
  yielded,
115
168
  written,
116
169
  deduped: yielded - written,
170
+ dropped: Object.fromEntries([...dropped].toSorted(([a], [b]) => a.localeCompare(b))),
171
+ dedup_exhausted_at_yielded: dedupExhaustedAtYielded,
172
+ dedup_store: fingerprints ? DedupStore.FingerprintTable : DedupStore.CappedSet,
173
+ dedup_keys: fingerprints?.size ?? seen?.size ?? 0,
117
174
  bytes,
118
175
  sha256: hasher.digest(),
119
- jsonl_path: jsonlPath,
176
+ jsonl_path: jsonlPath.toString(),
120
177
  started_at: startedAt.toISOString(),
121
178
  ended_at: endedAt.toISOString(),
122
179
  elapsed_ms,
@@ -125,10 +182,7 @@ export async function runAdapter(opts) {
125
182
  return manifest;
126
183
  }
127
184
  /**
128
- * Drive every adapter in a registry sequentially. Stops on the first failure (caller can filter the registry before
129
- * calling if partial-failure is desired).
130
- *
131
- * Returns the manifests in registry insertion order.
185
+ * Drive every adapter in a registry sequentially, stopping on the first failure.
132
186
  */
133
187
  export async function runAllAdapters(registry, common) {
134
188
  const out = [];
@@ -142,13 +196,9 @@ export async function runAllAdapters(registry, common) {
142
196
  }
143
197
  return out;
144
198
  }
145
- /**
146
- * Validate an emitted row. Cheap; runs once per row. Catches adapter bugs early so the JSONL doesn't end up
147
- * half-malformed.
148
- */
149
199
  function assertEmittedRow(adapter, row) {
150
200
  if (row.source !== adapter.id) {
151
- throw new Error(`adapter ${adapter.id}: row.source must equal adapter.id (got ${JSON.stringify(row.source)})`);
201
+ throw new Error(`adapter ${adapter.id}: row.source must equal adapter.id (got ${stringifyJSON(row.source)})`);
152
202
  }
153
203
  if (!row.source_id) {
154
204
  throw new Error(`adapter ${adapter.id}: row.source_id is empty`);
@@ -159,14 +209,38 @@ function assertEmittedRow(adapter, row) {
159
209
  if (!row.country) {
160
210
  throw new Error(`adapter ${adapter.id}: row.country is empty for source_id=${row.source_id}`);
161
211
  }
212
+ // `country_weights` and every country filter use this value.
213
+ // Validate its ISO 3166-1 alpha-2 shape.
214
+ // `ZZ` and `XK` are legitimate codes even though ISO membership does not list them.
215
+ if (!isAlpha2CodeShape(row.country)) {
216
+ throw new Error(`adapter ${adapter.id}: row.country ${stringifyJSON(row.country)} is not two upper-case letters ` +
217
+ `for source_id=${row.source_id}. ISO 3166-1 alpha-2 is the shape country_weights and every ` +
218
+ `country filter key on, so a code outside it trains on nothing and matches no filter.`);
219
+ }
162
220
  if (!row.license) {
163
221
  throw new Error(`adapter ${adapter.id}: row.license is empty for source_id=${row.source_id}`);
164
222
  }
165
223
  }
166
224
  /**
167
- * Promise-ify a single event emission. Used to await `drain` / `close` on the write stream. Exported for `build.ts`,
168
- * whose stage streams await `close` the same way; unlike a bare two-listener race, the loser listener is detached so a
169
- * long-lived stream does not accumulate one orphan handler per wait.
225
+ * Resolve once everything written to `stream` so far has reached the file.
226
+ *
227
+ * A zero-length write acts as a barrier.
228
+ * Its callback runs after earlier queued writes.
229
+ *
230
+ * A caller can then record a byte offset for the bytes in the file.
231
+ * `drain` fires only when the buffer was full.
232
+ *
233
+ * `bytesWritten` excludes queued data.
234
+ * Neither value answers when all earlier writes have reached the file.
235
+ */
236
+ export function flushStream(stream) {
237
+ return new Promise((resolve, reject) => {
238
+ stream.write("", (error) => (error ? reject(error) : resolve()));
239
+ });
240
+ }
241
+ /**
242
+ * Promise-ify a single `drain` or `close` emission, detaching the loser listener
243
+ * so a long-lived stream does not accumulate an orphan handler per wait.
170
244
  */
171
245
  export function once(emitter, event) {
172
246
  return new Promise((resolve, reject) => {
package/out/runner.js.map CHANGED
@@ -1 +1 @@
1
- {"version":3,"file":"runner.js","sourceRoot":"","sources":["../lib/runner.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;GA2BG;AAEH,OAAO,EAAE,eAAe,EAAoB,MAAM,4BAA4B,CAAA;AAC9E,OAAO,EAAE,kBAAkB,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAA;AAChF,OAAO,EAAE,IAAI,EAAwB,MAAM,SAAS,CAAA;AAEpD,OAAO,EAAE,iBAAiB,EAAE,eAAe,EAA8C,MAAM,iBAAiB,CAAA;AAyFhH;;;;;;GAMG;AACH,MAAM,CAAC,KAAK,UAAU,UAAU,CAAC,IAAuB;IACvD,MAAM,EAAE,OAAO,EAAE,cAAc,EAAE,SAAS,EAAE,aAAa,EAAE,GAAG,IAAI,CAAA;IAClE,MAAM,aAAa,GAAG,IAAI,CAAC,aAAa,IAAI,IAAI,CAAA;IAEhD,MAAM,UAAU,GAAG,IAAI,CAAC,SAAS,EAAE,OAAO,CAAC,EAAE,CAAC,CAAA;IAC9C,MAAM,eAAe,CAAC,UAAU,CAAC,CAAA;IAEjC,MAAM,SAAS,GAAG,IAAI,CAAC,UAAU,EAAE,iBAAiB,CAAC,CAAA;IACrD,MAAM,YAAY,GAAG,IAAI,CAAC,UAAU,EAAE,eAAe,CAAC,CAAA;IAEtD,MAAM,SAAS,GAAG,IAAI,IAAI,EAAE,CAAA;IAC5B,MAAM,EAAE,GAAG,WAAW,CAAC,GAAG,EAAE,CAAA;IAE5B,MAAM,MAAM,GAAG,eAAe,CAAC,SAAS,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,CAAC,CAAA;IAC/D,MAAM,MAAM,GAAoB,eAAe,EAAE,CAAA;IACjD,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAA;IAC9B,MAAM,cAAc,GAAG,UAAU,CAAA;IACjC,IAAI,cAAc,GAAG,KAAK,CAAA;IAE1B,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,KAAK,GAAG,CAAC,CAAA;IAEb,MAAM,YAAY,GAAG,GAAS,EAAE;QAC/B,IAAI,CAAC,UAAU,EAAE,CAAC;YACjB,SAAS,EAAE,OAAO,CAAC,EAAE;YACrB,OAAO;YACP,OAAO;YACP,KAAK;YACL,UAAU,EAAE,WAAW,CAAC,GAAG,EAAE,GAAG,EAAE;SAClC,CAAC,CAAA;IACH,CAAC,CAAA;IAED,IAAI,CAAC;QACJ,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,OAAO,CAAC,IAAI,CAAC,cAAc,CAAC,EAAE,CAAC;YACtD,IAAI,cAAc,CAAC,MAAM,EAAE,OAAO,EAAE,CAAC;gBACpC,MAAM,IAAI,YAAY,CAAC,+BAA+B,EAAE,YAAY,CAAC,CAAA;YACtE,CAAC;YAED,OAAO,EAAE,CAAA;YACT,gBAAgB,CAAC,OAAO,EAAE,GAAG,CAAC,CAAA;YAE9B,MAAM,OAAO,GAAiB,EAAE,GAAG,GAAG,EAAE,cAAc,EAAE,aAAa,EAAE,CAAA;YACvE,MAAM,GAAG,GAAG,iBAAiB,CAAC,OAAO,CAAC,CAAA;YAEtC,IAAI,CAAC,cAAc,EAAE,CAAC;gBACrB,IAAI,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,EAAE,CAAC;oBACnB,IAAI,OAAO,GAAG,aAAa,KAAK,CAAC,EAAE,CAAC;wBACnC,YAAY,EAAE,CAAA;oBACf,CAAC;oBAED,SAAQ;gBACT,CAAC;gBAED,IAAI,IAAI,CAAC,IAAI,IAAI,cAAc,EAAE,CAAC;oBACjC,cAAc,GAAG,IAAI,CAAA;oBAErB,OAAO,CAAC,MAAM,CAAC,KAAK,CACnB,+BAA+B,cAAc,CAAC,cAAc,EAAE,wCAAwC,CACtG,CAAA;gBACF,CAAC;qBAAM,CAAC;oBACP,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;gBACd,CAAC;YACF,CAAC;YAED,MAAM,IAAI,GAAG,GAAG,IAAI,CAAC,SAAS,CAAC,OAAO,CAAC,IAAI,CAAA;YAC3C,MAAM,CAAC,MAAM,CAAC,IAAI,CAAC,CAAA;YACnB,KAAK,IAAI,MAAM,CAAC,UAAU,CAAC,IAAI,EAAE,MAAM,CAAC,CAAA;YAExC,OAAO,EAAE,CAAA;YAET,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC;gBACzB,MAAM,IAAI,CAAC,MAAM,EAAE,OAAO,CAAC,CAAA;YAC5B,CAAC;YAED,IAAI,OAAO,GAAG,aAAa,KAAK,CAAC,EAAE,CAAC;gBACnC,YAAY,EAAE,CAAA;YACf,CAAC;QACF,CAAC;IACF,CAAC;YAAS,CAAC;QACV,MAAM,CAAC,GAAG,EAAE,CAAA;QACZ,MAAM,IAAI,CAAC,MAAM,EAAE,OAAO,CAAC,CAAA;IAC5B,CAAC;IAED,MAAM,OAAO,GAAG,IAAI,IAAI,EAAE,CAAA;IAC1B,MAAM,UAAU,GAAG,WAAW,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;IACzC,YAAY,EAAE,CAAA;IAEd,MAAM,QAAQ,GAAuB;QACpC,UAAU,EAAE,OAAO,CAAC,EAAE;QACtB,cAAc,EAAE,aAAa;QAC7B,eAAe,EAAE,OAAO,CAAC,cAAc;QACvC,WAAW,EAAE,OAAO,CAAC,WAAW;QAChC,OAAO;QACP,OAAO;QACP,OAAO,EAAE,OAAO,GAAG,OAAO;QAC1B,KAAK;QACL,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE;QACvB,UAAU,EAAE,SAAS;QACrB,UAAU,EAAE,SAAS,CAAC,WAAW,EAAE;QACnC,QAAQ,EAAE,OAAO,CAAC,WAAW,EAAE;QAC/B,UAAU;KACV,CAAA;IAED,MAAM,kBAAkB,CAAC,QAAQ,EAAE,YAAY,CAAC,CAAA;IAEhD,OAAO,QAAQ,CAAA;AAChB,CAAC;AAED;;;;;GAKG;AACH,MAAM,CAAC,KAAK,UAAU,cAAc,CACnC,QAAyB,EACzB,MAAyG;IAEzG,MAAM,GAAG,GAAyB,EAAE,CAAA;IAEpC,KAAK,MAAM,OAAO,IAAI,QAAQ,CAAC,IAAI,EAAE,EAAE,CAAC;QACvC,MAAM,cAAc,GAAG,MAAM,CAAC,iBAAiB,EAAE,CAAC,OAAO,CAAC,IAAI,MAAM,CAAC,cAAc,CAAA;QAEnF,GAAG,CAAC,IAAI,CACP,MAAM,UAAU,CAAC;YAChB,GAAG,MAAM;YACT,OAAO;YACP,cAAc;SACd,CAAC,CACF,CAAA;IACF,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC;AAED;;;GAGG;AACH,SAAS,gBAAgB,CAAC,OAAsB,EAAE,GAAiB;IAClE,IAAI,GAAG,CAAC,MAAM,KAAK,OAAO,CAAC,EAAE,EAAE,CAAC;QAC/B,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,2CAA2C,IAAI,CAAC,SAAS,CAAC,GAAG,CAAC,MAAM,CAAC,GAAG,CAAC,CAAA;IAC/G,CAAC;IAED,IAAI,CAAC,GAAG,CAAC,SAAS,EAAE,CAAC;QACpB,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,0BAA0B,CAAC,CAAA;IACjE,CAAC;IAED,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC;QACd,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,oCAAoC,GAAG,CAAC,SAAS,EAAE,CAAC,CAAA;IAC1F,CAAC;IAED,IAAI,CAAC,GAAG,CAAC,OAAO,EAAE,CAAC;QAClB,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,wCAAwC,GAAG,CAAC,SAAS,EAAE,CAAC,CAAA;IAC9F,CAAC;IAED,IAAI,CAAC,GAAG,CAAC,OAAO,EAAE,CAAC;QAClB,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,wCAAwC,GAAG,CAAC,SAAS,EAAE,CAAC,CAAA;IAC9F,CAAC;AACF,CAAC;AAED;;;;GAIG;AACH,MAAM,UAAU,IAAI,CAAC,OAAoB,EAAE,KAAwB;IAClE,OAAO,IAAI,OAAO,CAAC,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE;QACtC,MAAM,OAAO,GAAG,GAAS,EAAE;YAC1B,OAAO,CAAC,GAAG,CAAC,OAAO,EAAE,OAAO,CAAC,CAAA;YAC7B,OAAO,EAAE,CAAA;QACV,CAAC,CAAA;QAED,MAAM,OAAO,GAAG,CAAC,GAAU,EAAQ,EAAE;YACpC,OAAO,CAAC,GAAG,CAAC,KAAK,EAAE,OAAO,CAAC,CAAA;YAC3B,MAAM,CAAC,GAAG,CAAC,CAAA;QACZ,CAAC,CAAA;QAED,OAAO,CAAC,IAAI,CAAC,KAAK,EAAE,OAAO,CAAC,CAAA;QAC5B,OAAO,CAAC,IAAI,CAAC,OAAO,EAAE,OAAO,CAAC,CAAA;IAC/B,CAAC,CAAC,CAAA;AACH,CAAC"}
1
+ {"version":3,"file":"runner.js","sourceRoot":"","sources":["../lib/runner.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAEH,OAAO,EAAE,iBAAiB,EAAE,MAAM,0BAA0B,CAAA;AAC5D,OAAO,EAAE,eAAe,EAAoB,MAAM,4BAA4B,CAAA;AAC9E,OAAO,EAAE,kBAAkB,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAA;AAChF,OAAO,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAA;AACpD,OAAO,EAAwB,kBAAkB,EAAE,MAAM,SAAS,CAAA;AAElE,OAAO,EAAE,iBAAiB,EAAE,MAAM,qBAAqB,CAAA;AAEvD,OAAO,EAAE,eAAe,EAAwB,MAAM,yBAAyB,CAAA;AAC/E,OAAO,EAAE,cAAc,EAAE,MAAM,eAAe,CAAA;AAqB9C;;;;;;GAMG;AACH,MAAM,CAAC,MAAM,wBAAwB,GAAG,EAAE,CAAA;AAE1C;;;;;;GAMG;AACH,MAAM,CAAC,MAAM,sBAAsB,GAAG,UAAU,CAAA;AAEhD;;GAEG;AACH,MAAM,CAAC,MAAM,UAAU,GAAG;IACzB;;OAEG;IACH,gBAAgB,EAAE,mBAAmB;IAErC;;OAEG;IACH,SAAS,EAAE,YAAY;CACd,CAAA;AAyHV;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,UAAU,CAAC,IAAuB;IACvD,MAAM,EAAE,OAAO,EAAE,SAAS,EAAE,aAAa,EAAE,GAAG,IAAI,CAAA;IAClD,kEAAkE;IAClE,2FAA2F;IAC3F,MAAM,OAAO,GAAG,IAAI,CAAC,cAAc,CAAC,OAAO,IAAI,IAAI,GAAG,EAAkB,CAAA;IACxE,MAAM,cAAc,GAAmB,EAAE,GAAG,IAAI,CAAC,cAAc,EAAE,OAAO,EAAE,CAAA;IAC1E,MAAM,aAAa,GAAG,IAAI,CAAC,aAAa,IAAI,IAAI,CAAA;IAEhD,MAAM,UAAU,GAAG,kBAAkB,CAAC,SAAS,EAAE,OAAO,CAAC,EAAE,CAAC,CAAA;IAC5D,MAAM,eAAe,CAAC,UAAU,CAAC,CAAA;IAEjC,MAAM,SAAS,GAAG,UAAU,CAAC,iBAAiB,CAAC,CAAA;IAC/C,MAAM,YAAY,GAAG,UAAU,CAAC,eAAe,CAAC,CAAA;IAEhD,MAAM,SAAS,GAAG,IAAI,IAAI,EAAE,CAAA;IAC5B,MAAM,EAAE,GAAG,WAAW,CAAC,GAAG,EAAE,CAAA;IAE5B,MAAM,MAAM,GAAG,eAAe,CAAC,SAAS,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,CAAC,CAAA;IAC/D,MAAM,MAAM,GAAoB,eAAe,EAAE,CAAA;IAEjD,sGAAsG;IACtG,kEAAkE;IAClE,mCAAmC;IACnC,oFAAoF;IACpF,MAAM,MAAM,GAAG,IAAI,CAAC,YAAY,KAAK,SAAS,CAAA;IAC9C,MAAM,IAAI,GAAG,MAAM,CAAC,CAAC,CAAC,IAAI,GAAG,EAAU,CAAC,CAAC,CAAC,IAAI,CAAA;IAC9C,MAAM,YAAY,GAAG,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,cAAc,CAAC,IAAI,CAAC,cAAc,IAAI,wBAAwB,CAAC,CAAA;IACxG,MAAM,YAAY,GAAG,IAAI,CAAC,YAAY,IAAI,sBAAsB,CAAA;IAChE,IAAI,cAAc,GAAG,KAAK,CAAA;IAC1B,IAAI,uBAAuB,GAAkB,IAAI,CAAA;IAEjD,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,KAAK,GAAG,CAAC,CAAA;IAEb,MAAM,YAAY,GAAG,GAAS,EAAE;QAC/B,IAAI,CAAC,UAAU,EAAE,CAAC;YACjB,SAAS,EAAE,OAAO,CAAC,EAAE;YACrB,OAAO;YACP,OAAO;YACP,KAAK;YACL,UAAU,EAAE,WAAW,CAAC,GAAG,EAAE,GAAG,EAAE;SAClC,CAAC,CAAA;IACH,CAAC,CAAA;IAED,IAAI,CAAC;QACJ,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,OAAO,CAAC,IAAI,CAAC,cAAc,CAAC,EAAE,CAAC;YACtD,IAAI,cAAc,CAAC,MAAM,EAAE,OAAO,EAAE,CAAC;gBACpC,MAAM,IAAI,YAAY,CAAC,+BAA+B,EAAE,YAAY,CAAC,CAAA;YACtE,CAAC;YAED,OAAO,EAAE,CAAA;YACT,gBAAgB,CAAC,OAAO,EAAE,GAAG,CAAC,CAAA;YAE9B,MAAM,OAAO,GAAiB;gBAC7B,GAAG,GAAG;gBACN,oGAAoG;gBACpG,MAAM,EAAE,IAAI,CAAC,UAAU,IAAI,GAAG,CAAC,MAAM;gBACrC,cAAc,EAAE,aAAa;gBAC7B,WAAW,EAAE,GAAG,CAAC,WAAW,IAAI,OAAO,CAAC,WAAW;gBACnD,yEAAyE;gBACzE,8DAA8D;gBAC9D,QAAQ,EAAE,GAAG,CAAC,QAAQ,KAAK,SAAS,CAAC,CAAC,CAAC,OAAO,CAAC,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,QAAQ;gBACtE,OAAO,EAAE,GAAG,CAAC,OAAO,IAAI,OAAO,CAAC,OAAO;aACvC,CAAA;YAED,MAAM,GAAG,GAAG,iBAAiB,CAAC,OAAO,CAAC,CAAA;YAEtC,IAAI,YAAY,EAAE,CAAC;gBAClB,6FAA6F;gBAC7F,IAAI,CAAC,YAAY,CAAC,GAAG,CAAC,GAAG,CAAC,EAAE,CAAC;oBAC5B,IAAI,OAAO,GAAG,aAAa,KAAK,CAAC,EAAE,CAAC;wBACnC,YAAY,EAAE,CAAA;oBACf,CAAC;oBAED,SAAQ;gBACT,CAAC;YACF,CAAC;iBAAM,IAAI,IAAI,EAAE,CAAC;gBACjB,2DAA2D;gBAC3D,sCAAsC;gBACtC,2DAA2D;gBAC3D,kEAAkE;gBAClE,sCAAsC;gBACtC,4CAA4C;gBAC5C,IAAI,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,EAAE,CAAC;oBACnB,IAAI,OAAO,GAAG,aAAa,KAAK,CAAC,EAAE,CAAC;wBACnC,YAAY,EAAE,CAAA;oBACf,CAAC;oBAED,SAAQ;gBACT,CAAC;gBAED,IAAI,CAAC,cAAc,EAAE,CAAC;oBACrB,IAAI,IAAI,CAAC,IAAI,IAAI,YAAY,EAAE,CAAC;wBAC/B,cAAc,GAAG,IAAI,CAAA;wBACrB,uBAAuB,GAAG,OAAO,CAAA;wBAEjC,OAAO,CAAC,MAAM,CAAC,KAAK,CACnB,+BAA+B,YAAY,CAAC,cAAc,EAAE,eAAe,OAAO,CAAC,cAAc,EAAE,GAAG;4BACrG,iGAAiG;4BACjG,4CAA4C,CAC7C,CAAA;oBACF,CAAC;yBAAM,CAAC;wBACP,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;oBACd,CAAC;gBACF,CAAC;YACF,CAAC;YAED,MAAM,IAAI,GAAG,GAAG,aAAa,CAAC,OAAO,CAAC,IAAI,CAAA;YAC1C,MAAM,CAAC,MAAM,CAAC,IAAI,CAAC,CAAA;YACnB,KAAK,IAAI,MAAM,CAAC,UAAU,CAAC,IAAI,EAAE,MAAM,CAAC,CAAA;YAExC,OAAO,EAAE,CAAA;YAET,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC;gBACzB,MAAM,IAAI,CAAC,MAAM,EAAE,OAAO,CAAC,CAAA;YAC5B,CAAC;YAED,IAAI,OAAO,GAAG,aAAa,KAAK,CAAC,EAAE,CAAC;gBACnC,YAAY,EAAE,CAAA;YACf,CAAC;QACF,CAAC;IACF,CAAC;YAAS,CAAC;QACV,MAAM,CAAC,GAAG,EAAE,CAAA;QACZ,MAAM,IAAI,CAAC,MAAM,EAAE,OAAO,CAAC,CAAA;IAC5B,CAAC;IAED,kFAAkF;IAClF,yDAAyD;IACzD,cAAc,CAAC,MAAM,EAAE,cAAc,EAAE,CAAA;IAEvC,MAAM,OAAO,GAAG,IAAI,IAAI,EAAE,CAAA;IAC1B,MAAM,UAAU,GAAG,WAAW,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;IACzC,YAAY,EAAE,CAAA;IAEd,MAAM,QAAQ,GAAuB;QACpC,UAAU,EAAE,OAAO,CAAC,EAAE;QACtB,cAAc,EAAE,aAAa;QAC7B,eAAe,EAAE,OAAO,CAAC,cAAc;QACvC,WAAW,EAAE,OAAO,CAAC,WAAW;QAChC,OAAO;QACP,OAAO;QACP,OAAO,EAAE,OAAO,GAAG,OAAO;QAC1B,OAAO,EAAE,MAAM,CAAC,WAAW,CAAC,CAAC,GAAG,OAAO,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC,CAAC;QACpF,0BAA0B,EAAE,uBAAuB;QACnD,WAAW,EAAE,YAAY,CAAC,CAAC,CAAC,UAAU,CAAC,gBAAgB,CAAC,CAAC,CAAC,UAAU,CAAC,SAAS;QAC9E,UAAU,EAAE,YAAY,EAAE,IAAI,IAAI,IAAI,EAAE,IAAI,IAAI,CAAC;QACjD,KAAK;QACL,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE;QACvB,UAAU,EAAE,SAAS,CAAC,QAAQ,EAAE;QAChC,UAAU,EAAE,SAAS,CAAC,WAAW,EAAE;QACnC,QAAQ,EAAE,OAAO,CAAC,WAAW,EAAE;QAC/B,UAAU;KACV,CAAA;IAED,MAAM,kBAAkB,CAAC,QAAQ,EAAE,YAAY,CAAC,CAAA;IAEhD,OAAO,QAAQ,CAAA;AAChB,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,cAAc,CACnC,QAAyB,EACzB,MAAyG;IAEzG,MAAM,GAAG,GAAyB,EAAE,CAAA;IAEpC,KAAK,MAAM,OAAO,IAAI,QAAQ,CAAC,IAAI,EAAE,EAAE,CAAC;QACvC,MAAM,cAAc,GAAG,MAAM,CAAC,iBAAiB,EAAE,CAAC,OAAO,CAAC,IAAI,MAAM,CAAC,cAAc,CAAA;QAEnF,GAAG,CAAC,IAAI,CACP,MAAM,UAAU,CAAC;YAChB,GAAG,MAAM;YACT,OAAO;YACP,cAAc;SACd,CAAC,CACF,CAAA;IACF,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC;AAED,SAAS,gBAAgB,CAAC,OAAsB,EAAE,GAAiB;IAClE,IAAI,GAAG,CAAC,MAAM,KAAK,OAAO,CAAC,EAAE,EAAE,CAAC;QAC/B,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,2CAA2C,aAAa,CAAC,GAAG,CAAC,MAAM,CAAC,GAAG,CAAC,CAAA;IAC9G,CAAC;IAED,IAAI,CAAC,GAAG,CAAC,SAAS,EAAE,CAAC;QACpB,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,0BAA0B,CAAC,CAAA;IACjE,CAAC;IAED,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC;QACd,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,oCAAoC,GAAG,CAAC,SAAS,EAAE,CAAC,CAAA;IAC1F,CAAC;IAED,IAAI,CAAC,GAAG,CAAC,OAAO,EAAE,CAAC;QAClB,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,wCAAwC,GAAG,CAAC,SAAS,EAAE,CAAC,CAAA;IAC9F,CAAC;IAED,6DAA6D;IAC7D,yCAAyC;IACzC,oFAAoF;IACpF,IAAI,CAAC,iBAAiB,CAAC,GAAG,CAAC,OAAO,CAAC,EAAE,CAAC;QACrC,MAAM,IAAI,KAAK,CACd,WAAW,OAAO,CAAC,EAAE,iBAAiB,aAAa,CAAC,GAAG,CAAC,OAAO,CAAC,iCAAiC;YAChG,iBAAiB,GAAG,CAAC,SAAS,8DAA8D;YAC5F,sFAAsF,CACvF,CAAA;IACF,CAAC;IAED,IAAI,CAAC,GAAG,CAAC,OAAO,EAAE,CAAC;QAClB,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,wCAAwC,GAAG,CAAC,SAAS,EAAE,CAAC,CAAA;IAC9F,CAAC;AACF,CAAC;AAED;;;;;;;;;;;GAWG;AACH,MAAM,UAAU,WAAW,CAAC,MAAmB;IAC9C,OAAO,IAAI,OAAO,CAAC,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE;QACtC,MAAM,CAAC,KAAK,CAAC,EAAE,EAAE,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,OAAO,EAAE,CAAC,CAAC,CAAA;IACjE,CAAC,CAAC,CAAA;AACH,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,IAAI,CAAC,OAAoB,EAAE,KAAwB;IAClE,OAAO,IAAI,OAAO,CAAC,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE;QACtC,MAAM,OAAO,GAAG,GAAS,EAAE;YAC1B,OAAO,CAAC,GAAG,CAAC,OAAO,EAAE,OAAO,CAAC,CAAA;YAC7B,OAAO,EAAE,CAAA;QACV,CAAC,CAAA;QAED,MAAM,OAAO,GAAG,CAAC,GAAU,EAAQ,EAAE;YACpC,OAAO,CAAC,GAAG,CAAC,KAAK,EAAE,OAAO,CAAC,CAAA;YAC3B,MAAM,CAAC,GAAG,CAAC,CAAA;QACZ,CAAC,CAAA;QAED,OAAO,CAAC,IAAI,CAAC,KAAK,EAAE,OAAO,CAAC,CAAA;QAC5B,OAAO,CAAC,IAAI,CAAC,OAAO,EAAE,OAAO,CAAC,CAAA;IAC/B,CAAC,CAAC,CAAA;AACH,CAAC"}
@@ -3,38 +3,18 @@
3
3
  * @license AGPL-3.0
4
4
  * @author Teffen Ellis, et al.
5
5
  *
6
- * `sg-register` slice recipe — the forms a person in Singapore types, rendered over the Overture-SG register rows
7
- * (#2204 §4). The base `overture` source carries the register's own shape, `990 OLD CHOA CHU KANG ROAD, 699814,
8
- * Singapore`, and the Latin model has no register for the three forms that dominate typed Singapore addresses:
9
- *
10
- * - the HDB block line, `Blk 123 Ang Mo Kio Ave 3 #05-67 Singapore 560123` — `Blk` in front of the block number (the
11
- * register's `number`), a floor-unit `#NN-NN` after the street, the country name as the locality;
12
- * - the bracketed postcode, `123 Ang Mo Kio Ave 3 S(560123)` — the form the postal service prints;
13
- * - the building-led line, `National Shooting Centre, 990 Old Choa Chu Kang Road, Singapore 699814` — the register's
14
- * `unit` field holds the BUILDING or ESTATE name on 91,818 of 142,210 rows, which the adapter refuses as a unit and
15
- * this recipe renders as a `venue` when it reads as a building rather than an estate.
16
- *
17
- * Every value in `components` is a verbatim substring of `raw`, aligned by {@link alignAndWrite}. The floor-unit is
18
- * SYNTHESIZED (the register carries one on a single row): floor 01–30, unit 01–399, zero-padded — the shape, not a
19
- * real occupancy. `Blk` and the `S(` `)` around a postcode are untagged, as the board's `sg-cs-blk-12-kallang-ave`
20
- * row expects (`house_number: "12"`). Streets arrive upper-case and are rendered title-cased; a third abbreviate the
21
- * generic (`Avenue` → `Ave`, `Road` → `Rd`, …) the way a typed line does.
22
- *
23
- * Run: mailwoman corpus slice sg-register --input <overture-sg.corpus.jsonl> --count N --seed S
6
+ * Renders Overture Singapore address rows in the forms that people type, such as HDB block lines and `S(560123)` postcodes.
24
7
  */
25
8
  import { type CorpusRecipe } from "#recipes/scaffold";
26
9
  /**
27
- * `OLD CHOA CHU KANG ROAD` → `Old Choa Chu Kang Road`; an already-mixed value is returned as it is. The register writes
28
- * every street and building name upper-case, the same convention as G-NAF, so the G-NAF title-caser serves both.
29
- */
30
- export declare function titleCaseSGName(name: string): string;
31
- /**
32
- * Abbreviate the street's generic, wherever it sits (`Ang Mo Kio Avenue 3` → `Ang Mo Kio Ave 3`).
10
+ * Abbreviates the first street generic that the street contains, such as
11
+ * `Ang Mo Kio Avenue 3` to `Ang Mo Kio Ave 3`.
33
12
  */
34
13
  export declare function abbreviateSGStreet(street: string): string;
35
14
  /**
36
- * Whether the register's `unit` value names a building rather than an estate — the building-led register's lead. A name
37
- * carrying a digit, a parenthesized abbreviation (`DIABETES & METABOLISM CENTRE (DMC)`) or one word only is not one.
15
+ * Reports whether the source `unit` value looks like a building name that can lead a line.
16
+ *
17
+ * The check rejects `NIL`, single words, values with a digit or parenthesis, plus estate names.
38
18
  */
39
19
  export declare function isBuildingName(unit: string): boolean;
40
20
  interface SGRow {
@@ -44,11 +24,11 @@ interface SGRow {
44
24
  postcode: string;
45
25
  }
46
26
  /**
47
- * The four typed forms this recipe renders.
27
+ * The four typed forms that this recipe renders.
48
28
  */
49
29
  export type SGRegister = "official" | "block" | "bracket_postcode" | "building_led";
50
30
  /**
51
- * One rendered register: the raw line plus the components it carries, every value a substring of the line.
31
+ * One rendered line with its components, each of which is a substring of `raw`.
52
32
  */
53
33
  export interface SGRegisterRendering {
54
34
  raw: string;
@@ -56,13 +36,19 @@ export interface SGRegisterRendering {
56
36
  register: SGRegister;
57
37
  }
58
38
  /**
59
- * Render one register form for one register row. Pure: every random draw comes through `random`. A `register` names the
60
- * form to render instead of drawing one, for a board that wants a balanced spread; `building_led` still needs a
61
- * building-shaped `unit` and falls back to `official` without one.
39
+ * Renders one source row in a sampled or requested form.
40
+ *
41
+ * All randomness comes from `random`.
42
+ * A requested `building_led` form falls back to `official` when the row's `unit` is not a building name.
43
+ *
44
+ * A requested `block` form falls back to `bracket_postcode` when the row's number is not a block number.
45
+ * `Blk` and the `S(` and `)` around a postcode stay untagged.
62
46
  */
63
47
  export declare function renderSGRegister(row: SGRow, random: () => number, register?: SGRegister): SGRegisterRendering;
64
48
  /**
65
- * Slice recipe registered with the corpus builder — see the file header for the registers and why each is here.
49
+ * Renders each Overture Singapore corpus row from `--input` once in a sampled typed form.
50
+ *
51
+ * The recipe skips rows without a street, a block-style number, or a six-digit postcode.
66
52
  */
67
53
  export declare const sgRegisterRecipe: CorpusRecipe;
68
54
  export {};
@@ -1 +1 @@
1
- {"version":3,"file":"register.d.ts","sourceRoot":"","sources":["../../../lib/sg/recipes/register.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAKH,OAAO,EAAiB,KAAK,YAAY,EAA6B,MAAM,mBAAmB,CAAA;AAmD/F;;;GAGG;AACH,wBAAgB,eAAe,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAEpD;AAED;;GAEG;AACH,wBAAgB,kBAAkB,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,CAQzD;AAED;;;GAGG;AACH,wBAAgB,cAAc,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAMpD;AAED,UAAU,KAAK;IACd,MAAM,EAAE,MAAM,CAAA;IACd,MAAM,EAAE,MAAM,CAAA;IACd,IAAI,EAAE,MAAM,CAAA;IACZ,QAAQ,EAAE,MAAM,CAAA;CAChB;AAED;;GAEG;AACH,MAAM,MAAM,UAAU,GAAG,UAAU,GAAG,OAAO,GAAG,kBAAkB,GAAG,cAAc,CAAA;AAEnF;;GAEG;AACH,MAAM,WAAW,mBAAmB;IACnC,GAAG,EAAE,MAAM,CAAA;IACX,UAAU,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IAClC,QAAQ,EAAE,UAAU,CAAA;CACpB;AAED;;;;GAIG;AACH,wBAAgB,gBAAgB,CAAC,GAAG,EAAE,KAAK,EAAE,MAAM,EAAE,MAAM,MAAM,EAAE,QAAQ,CAAC,EAAE,UAAU,GAAG,mBAAmB,CA2C7G;AAED;;GAEG;AACH,eAAO,MAAM,gBAAgB,EAAE,YAmF9B,CAAA"}
1
+ {"version":3,"file":"register.d.ts","sourceRoot":"","sources":["../../../lib/sg/recipes/register.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAMH,OAAO,EAAiB,KAAK,YAAY,EAA8B,MAAM,mBAAmB,CAAA;AAqDhG;;;GAGG;AACH,wBAAgB,kBAAkB,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,CAQzD;AAED;;;;GAIG;AACH,wBAAgB,cAAc,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAMpD;AAED,UAAU,KAAK;IACd,MAAM,EAAE,MAAM,CAAA;IACd,MAAM,EAAE,MAAM,CAAA;IACd,IAAI,EAAE,MAAM,CAAA;IACZ,QAAQ,EAAE,MAAM,CAAA;CAChB;AAED;;GAEG;AACH,MAAM,MAAM,UAAU,GAAG,UAAU,GAAG,OAAO,GAAG,kBAAkB,GAAG,cAAc,CAAA;AAEnF;;GAEG;AACH,MAAM,WAAW,mBAAmB;IACnC,GAAG,EAAE,MAAM,CAAA;IACX,UAAU,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IAClC,QAAQ,EAAE,UAAU,CAAA;CACpB;AAED;;;;;;;;GAQG;AACH,wBAAgB,gBAAgB,CAAC,GAAG,EAAE,KAAK,EAAE,MAAM,EAAE,MAAM,MAAM,EAAE,QAAQ,CAAC,EAAE,UAAU,GAAG,mBAAmB,CA2C7G;AAED;;;;GAIG;AACH,eAAO,MAAM,gBAAgB,EAAE,YA2F9B,CAAA"}
@@ -3,31 +3,18 @@
3
3
  * @license AGPL-3.0
4
4
  * @author Teffen Ellis, et al.
5
5
  *
6
- * `sg-register` slice recipe — the forms a person in Singapore types, rendered over the Overture-SG register rows
7
- * (#2204 §4). The base `overture` source carries the register's own shape, `990 OLD CHOA CHU KANG ROAD, 699814,
8
- * Singapore`, and the Latin model has no register for the three forms that dominate typed Singapore addresses:
9
- *
10
- * - the HDB block line, `Blk 123 Ang Mo Kio Ave 3 #05-67 Singapore 560123` — `Blk` in front of the block number (the
11
- * register's `number`), a floor-unit `#NN-NN` after the street, the country name as the locality;
12
- * - the bracketed postcode, `123 Ang Mo Kio Ave 3 S(560123)` — the form the postal service prints;
13
- * - the building-led line, `National Shooting Centre, 990 Old Choa Chu Kang Road, Singapore 699814` — the register's
14
- * `unit` field holds the BUILDING or ESTATE name on 91,818 of 142,210 rows, which the adapter refuses as a unit and
15
- * this recipe renders as a `venue` when it reads as a building rather than an estate.
16
- *
17
- * Every value in `components` is a verbatim substring of `raw`, aligned by {@link alignAndWrite}. The floor-unit is
18
- * SYNTHESIZED (the register carries one on a single row): floor 01–30, unit 01–399, zero-padded — the shape, not a
19
- * real occupancy. `Blk` and the `S(` `)` around a postcode are untagged, as the board's `sg-cs-blk-12-kallang-ave`
20
- * row expects (`house_number: "12"`). Streets arrive upper-case and are rendered title-cased; a third abbreviate the
21
- * generic (`Avenue` → `Ave`, `Road` → `Rd`, …) the way a typed line does.
22
- *
23
- * Run: mailwoman corpus slice sg-register --input <overture-sg.corpus.jsonl> --count N --seed S
6
+ * Renders Overture Singapore address rows in the forms that people type, such as HDB block lines and `S(560123)` postcodes.
24
7
  */
8
+ import { stringifyJSON } from "@mailwoman/core/json";
25
9
  import { mulberry32 as makeMulberry32 } from "@mailwoman/core/utils";
26
- import { titlecase } from "#au/adapters/gnaf/assemble";
27
- import { alignAndWrite, readTuples, sliceSourceID } from "#recipes/scaffold";
28
- const SOURCE = "synth-sg-register";
10
+ import { titleCaseIfUpper } from "spliterator";
11
+ import { alignAndWrite, readTuples, recipeSourceID } from "#recipes/scaffold";
12
+ import { defaultRecipeSource } from "#recipes/sources";
13
+ import { SourceRegister } from "#registers";
14
+ import { SurfaceOrigin } from "#types";
15
+ const SOURCE = defaultRecipeSource("synth-sg-register");
29
16
  /**
30
- * The register's generics and the abbreviation a typed line uses for each.
17
+ * Street generics and their typed abbreviations.
31
18
  */
32
19
  const GENERIC_ABBREVIATIONS = [
33
20
  ["Avenue", "Ave"],
@@ -43,24 +30,23 @@ const GENERIC_ABBREVIATIONS = [
43
30
  ["Walk", "Wk"],
44
31
  ];
45
32
  /**
46
- * Estate and area names the register's `unit` field carries beside building names. A name ending in one of these is an
47
- * estate, which no one writes in front of an address line; a name without one reads as a building and is rendered as a
48
- * `venue`.
33
+ * Name endings that mark an estate or area in the source `unit` field.
34
+ *
35
+ * People do not write an estate name before an address line, so the recipe
36
+ * renders only building names as a `venue`.
49
37
  */
50
38
  const ESTATE_TAILS = ["ESTATE", "CONSERVATION AREA", "HILLS", "PARK", "GARDENS", "GARDEN", "HEIGHTS", "GROVE", "VILLE"];
51
- /**
52
- * Share of rows per register. The block line and the bracketed postcode are the two the Latin model has never seen; the
53
- * official line keeps the register's own shape in the mix so the block forms train beside it.
54
- */
39
+ // The official form receives the probability left after the block, bracketed-postcode and building-led forms.
55
40
  const P_BLOCK = 0.4;
56
41
  const P_BRACKET_POSTCODE = 0.25;
57
42
  const P_BUILDING_LED = 0.15;
58
43
  const P_ABBREVIATE = 0.35;
59
44
  const P_UPPER = 0.1;
45
+ // The source rarely includes a floor-unit, so the recipe synthesizes one within these bounds.
60
46
  const FLOOR_MAX = 30;
61
47
  const UNIT_MAX = 399;
62
48
  /**
63
- * The draw value that lands each register in the branch order below, for a caller that names the form.
49
+ * The draw value that selects each form in {@link renderSGRegister} when a caller requests that form.
64
50
  */
65
51
  const REGISTER_DRAW = {
66
52
  block: 0,
@@ -69,14 +55,8 @@ const REGISTER_DRAW = {
69
55
  official: 1,
70
56
  };
71
57
  /**
72
- * `OLD CHOA CHU KANG ROAD` → `Old Choa Chu Kang Road`; an already-mixed value is returned as it is. The register writes
73
- * every street and building name upper-case, the same convention as G-NAF, so the G-NAF title-caser serves both.
74
- */
75
- export function titleCaseSGName(name) {
76
- return name === name.toUpperCase() ? titlecase(name) : name;
77
- }
78
- /**
79
- * Abbreviate the street's generic, wherever it sits (`Ang Mo Kio Avenue 3` → `Ang Mo Kio Ave 3`).
58
+ * Abbreviates the first street generic that the street contains, such as
59
+ * `Ang Mo Kio Avenue 3` to `Ang Mo Kio Ave 3`.
80
60
  */
81
61
  export function abbreviateSGStreet(street) {
82
62
  for (const [full, short] of GENERIC_ABBREVIATIONS) {
@@ -87,8 +67,9 @@ export function abbreviateSGStreet(street) {
87
67
  return street;
88
68
  }
89
69
  /**
90
- * Whether the register's `unit` value names a building rather than an estate — the building-led register's lead. A name
91
- * carrying a digit, a parenthesized abbreviation (`DIABETES & METABOLISM CENTRE (DMC)`) or one word only is not one.
70
+ * Reports whether the source `unit` value looks like a building name that can lead a line.
71
+ *
72
+ * The check rejects `NIL`, single words, values with a digit or parenthesis, plus estate names.
92
73
  */
93
74
  export function isBuildingName(unit) {
94
75
  const value = unit.trim().toUpperCase();
@@ -97,16 +78,20 @@ export function isBuildingName(unit) {
97
78
  return !ESTATE_TAILS.some((tail) => value.endsWith(tail));
98
79
  }
99
80
  /**
100
- * Render one register form for one register row. Pure: every random draw comes through `random`. A `register` names the
101
- * form to render instead of drawing one, for a board that wants a balanced spread; `building_led` still needs a
102
- * building-shaped `unit` and falls back to `official` without one.
81
+ * Renders one source row in a sampled or requested form.
82
+ *
83
+ * All randomness comes from `random`.
84
+ * A requested `building_led` form falls back to `official` when the row's `unit` is not a building name.
85
+ *
86
+ * A requested `block` form falls back to `bracket_postcode` when the row's number is not a block number.
87
+ * `Blk` and the `S(` and `)` around a postcode stay untagged.
103
88
  */
104
89
  export function renderSGRegister(row, random, register) {
105
- const street0 = titleCaseSGName(row.street);
90
+ const street0 = titleCaseIfUpper(row.street);
106
91
  const street = random() < P_ABBREVIATE ? abbreviateSGStreet(street0) : street0;
107
92
  const drawn = random();
108
- const building = isBuildingName(row.unit) ? titleCaseSGName(row.unit) : null;
109
- const draw = register === undefined ? drawn : REGISTER_DRAW[register];
93
+ const building = isBuildingName(row.unit) ? titleCaseIfUpper(row.unit) : null;
94
+ const draw = register ? REGISTER_DRAW[register] : drawn;
110
95
  let raw;
111
96
  let rendered;
112
97
  const components = { house_number: row.number, street, postcode: row.postcode };
@@ -143,7 +128,9 @@ export function renderSGRegister(row, random, register) {
143
128
  return { raw, components, register: rendered };
144
129
  }
145
130
  /**
146
- * Slice recipe registered with the corpus builder — see the file header for the registers and why each is here.
131
+ * Renders each Overture Singapore corpus row from `--input` once in a sampled typed form.
132
+ *
133
+ * The recipe skips rows without a street, a block-style number, or a six-digit postcode.
147
134
  */
148
135
  export const sgRegisterRecipe = {
149
136
  name: "sg-register",
@@ -179,7 +166,7 @@ export const sgRegisterRecipe = {
179
166
  const rendering = renderSGRegister({ street, number, unit, postcode }, random);
180
167
  if (opts.golden) {
181
168
  const golden = { raw: rendering.raw, components: rendering.components, country: "SG", locale: "en-SG" };
182
- write(JSON.stringify(golden) + "\n");
169
+ write(stringifyJSON(golden));
183
170
  emitted++;
184
171
  registers[rendering.register] = (registers[rendering.register] ?? 0) + 1;
185
172
  continue;
@@ -190,10 +177,18 @@ export const sgRegisterRecipe = {
190
177
  country: "SG",
191
178
  locale: "en-SG",
192
179
  source,
193
- source_id: sliceSourceID(source, { raw: rendering.raw }),
180
+ source_id: recipeSourceID(source, { raw: rendering.raw }),
194
181
  corpus_version: "0.1.0",
195
182
  license: "CDLA-Permissive-2.0 — Overture Maps addresses over the Singapore Open Data Licence 1.0 (OneMap / Singapore Land Authority)",
196
- }, `sg-register:${rendering.register}`);
183
+ }, `sg-register:${rendering.register}`,
184
+ // The values come from Overture and the recipe chose only their arrangement,
185
+ // so the Overture record behind each row is what `baseSourceID` names
186
+ // when the tuples file includes its id.
187
+ {
188
+ register: SourceRegister.Overture,
189
+ surface: SurfaceOrigin.Composed,
190
+ baseSourceID: tuple.sourceID ?? null,
191
+ });
197
192
  if (ok) {
198
193
  emitted++;
199
194
  registers[rendering.register] = (registers[rendering.register] ?? 0) + 1;
@@ -1 +1 @@
1
- {"version":3,"file":"register.js","sourceRoot":"","sources":["../../../lib/sg/recipes/register.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAEH,OAAO,EAAE,UAAU,IAAI,cAAc,EAAE,MAAM,uBAAuB,CAAA;AAEpE,OAAO,EAAE,SAAS,EAAE,MAAM,4BAA4B,CAAA;AACtD,OAAO,EAAE,aAAa,EAAqB,UAAU,EAAE,aAAa,EAAE,MAAM,mBAAmB,CAAA;AAE/F,MAAM,MAAM,GAAG,mBAAmB,CAAA;AAElC;;GAEG;AACH,MAAM,qBAAqB,GAA0D;IACpF,CAAC,QAAQ,EAAE,KAAK,CAAC;IACjB,CAAC,MAAM,EAAE,IAAI,CAAC;IACd,CAAC,QAAQ,EAAE,IAAI,CAAC;IAChB,CAAC,OAAO,EAAE,IAAI,CAAC;IACf,CAAC,UAAU,EAAE,MAAM,CAAC;IACpB,CAAC,MAAM,EAAE,IAAI,CAAC;IACd,CAAC,WAAW,EAAE,MAAM,CAAC;IACrB,CAAC,SAAS,EAAE,KAAK,CAAC;IAClB,CAAC,OAAO,EAAE,IAAI,CAAC;IACf,CAAC,OAAO,EAAE,IAAI,CAAC;IACf,CAAC,MAAM,EAAE,IAAI,CAAC;CACd,CAAA;AAED;;;;GAIG;AACH,MAAM,YAAY,GAAG,CAAC,QAAQ,EAAE,mBAAmB,EAAE,OAAO,EAAE,MAAM,EAAE,SAAS,EAAE,QAAQ,EAAE,SAAS,EAAE,OAAO,EAAE,OAAO,CAAC,CAAA;AAEvH;;;GAGG;AACH,MAAM,OAAO,GAAG,GAAG,CAAA;AACnB,MAAM,kBAAkB,GAAG,IAAI,CAAA;AAC/B,MAAM,cAAc,GAAG,IAAI,CAAA;AAC3B,MAAM,YAAY,GAAG,IAAI,CAAA;AACzB,MAAM,OAAO,GAAG,GAAG,CAAA;AAEnB,MAAM,SAAS,GAAG,EAAE,CAAA;AACpB,MAAM,QAAQ,GAAG,GAAG,CAAA;AAEpB;;GAEG;AACH,MAAM,aAAa,GAA+B;IACjD,KAAK,EAAE,CAAC;IACR,gBAAgB,EAAE,OAAO;IACzB,YAAY,EAAE,OAAO,GAAG,kBAAkB;IAC1C,QAAQ,EAAE,CAAC;CACX,CAAA;AAED;;;GAGG;AACH,MAAM,UAAU,eAAe,CAAC,IAAY;IAC3C,OAAO,IAAI,KAAK,IAAI,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAA;AAC5D,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,kBAAkB,CAAC,MAAc;IAChD,KAAK,MAAM,CAAC,IAAI,EAAE,KAAK,CAAC,IAAI,qBAAqB,EAAE,CAAC;QACnD,MAAM,OAAO,GAAG,IAAI,MAAM,CAAC,MAAM,IAAI,KAAK,EAAE,GAAG,CAAC,CAAA;QAEhD,IAAI,OAAO,CAAC,IAAI,CAAC,MAAM,CAAC;YAAE,OAAO,MAAM,CAAC,OAAO,CAAC,OAAO,EAAE,KAAK,CAAC,CAAA;IAChE,CAAC;IAED,OAAO,MAAM,CAAA;AACd,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,cAAc,CAAC,IAAY;IAC1C,MAAM,KAAK,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAA;IAEvC,IAAI,CAAC,KAAK,IAAI,KAAK,KAAK,KAAK,IAAI,SAAS,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC;QAAE,OAAO,KAAK,CAAA;IAE1F,OAAO,CAAC,YAAY,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAA;AAC1D,CAAC;AAuBD;;;;GAIG;AACH,MAAM,UAAU,gBAAgB,CAAC,GAAU,EAAE,MAAoB,EAAE,QAAqB;IACvF,MAAM,OAAO,GAAG,eAAe,CAAC,GAAG,CAAC,MAAM,CAAC,CAAA;IAC3C,MAAM,MAAM,GAAG,MAAM,EAAE,GAAG,YAAY,CAAC,CAAC,CAAC,kBAAkB,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,OAAO,CAAA;IAC9E,MAAM,KAAK,GAAG,MAAM,EAAE,CAAA;IACtB,MAAM,QAAQ,GAAG,cAAc,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,eAAe,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAA;IAC5E,MAAM,IAAI,GAAG,QAAQ,KAAK,SAAS,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,aAAa,CAAC,QAAQ,CAAC,CAAA;IAErE,IAAI,GAAW,CAAA;IACf,IAAI,QAAoB,CAAA;IACxB,MAAM,UAAU,GAA2B,EAAE,YAAY,EAAE,GAAG,CAAC,MAAM,EAAE,MAAM,EAAE,QAAQ,EAAE,GAAG,CAAC,QAAQ,EAAE,CAAA;IAEvG,IAAI,IAAI,GAAG,OAAO,IAAI,cAAc,CAAC,IAAI,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC;QACvD,MAAM,KAAK,GAAG,MAAM,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,SAAS,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAA;QAC3E,MAAM,MAAM,GAAG,MAAM,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,QAAQ,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAA;QAC3E,MAAM,IAAI,GAAG,IAAI,KAAK,IAAI,MAAM,EAAE,CAAA;QAElC,GAAG,GAAG,OAAO,GAAG,CAAC,MAAM,IAAI,MAAM,IAAI,IAAI,cAAc,GAAG,CAAC,QAAQ,EAAE,CAAA;QACrE,UAAU,CAAC,IAAI,GAAG,IAAI,CAAA;QACtB,UAAU,CAAC,QAAQ,GAAG,WAAW,CAAA;QACjC,QAAQ,GAAG,OAAO,CAAA;IACnB,CAAC;SAAM,IAAI,IAAI,GAAG,OAAO,GAAG,kBAAkB,EAAE,CAAC;QAChD,GAAG,GAAG,GAAG,GAAG,CAAC,MAAM,IAAI,MAAM,MAAM,GAAG,CAAC,QAAQ,GAAG,CAAA;QAClD,QAAQ,GAAG,kBAAkB,CAAA;IAC9B,CAAC;SAAM,IAAI,IAAI,GAAG,OAAO,GAAG,kBAAkB,GAAG,cAAc,IAAI,QAAQ,EAAE,CAAC;QAC7E,GAAG,GAAG,GAAG,QAAQ,KAAK,GAAG,CAAC,MAAM,IAAI,MAAM,eAAe,GAAG,CAAC,QAAQ,EAAE,CAAA;QACvE,UAAU,CAAC,KAAK,GAAG,QAAQ,CAAA;QAC3B,UAAU,CAAC,QAAQ,GAAG,WAAW,CAAA;QACjC,QAAQ,GAAG,cAAc,CAAA;IAC1B,CAAC;SAAM,CAAC;QACP,GAAG,GAAG,GAAG,GAAG,CAAC,MAAM,IAAI,MAAM,cAAc,GAAG,CAAC,QAAQ,EAAE,CAAA;QACzD,UAAU,CAAC,QAAQ,GAAG,WAAW,CAAA;QACjC,QAAQ,GAAG,UAAU,CAAA;IACtB,CAAC;IAED,IAAI,MAAM,EAAE,GAAG,OAAO,EAAE,CAAC;QACxB,GAAG,GAAG,GAAG,CAAC,WAAW,EAAE,CAAA;QAEvB,KAAK,MAAM,GAAG,IAAI,MAAM,CAAC,IAAI,CAAC,UAAU,CAAC,EAAE,CAAC;YAC3C,UAAU,CAAC,GAAG,CAAC,GAAG,UAAU,CAAC,GAAG,CAAE,CAAC,WAAW,EAAE,CAAA;QACjD,CAAC;IACF,CAAC;IAED,OAAO,EAAE,GAAG,EAAE,UAAU,EAAE,QAAQ,EAAE,QAAQ,EAAE,CAAA;AAC/C,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,gBAAgB,GAAiB;IAC7C,IAAI,EAAE,aAAa;IACnB,WAAW,EACV,2IAA2I;IAC5I,IAAI,EAAE,QAAQ;IACd,OAAO,EAAE;QACR,EAAE,IAAI,EAAE,SAAS,EAAE,WAAW,EAAE,8CAA8C,EAAE;QAChF,EAAE,IAAI,EAAE,SAAS,EAAE,WAAW,EAAE,6EAA6E,EAAE;KAC/G;IACD,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,IAAI,CAAC,IAAI,CAAC,KAAK,EAAE,CAAC;YACjB,MAAM,IAAI,KAAK,CAAC,6DAA6D,CAAC,CAAA;QAC/E,CAAC;QAED,MAAM,MAAM,GAAG,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACxC,MAAM,MAAM,GAAG,IAAI,CAAC,UAAU,IAAI,MAAM,CAAA;QACxC,MAAM,SAAS,GAA2B,EAAE,CAAA;QAC5C,IAAI,IAAI,GAAG,CAAC,CAAA;QACZ,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,WAAW,GAAG,CAAC,CAAA;QAEnB,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,UAAU,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;YAClD,IAAI,EAAE,CAAA;YAEN,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;gBAAE,MAAK;YAE5D,MAAM,MAAM,GAAG,OAAO,KAAK,CAAC,QAAQ,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;YAChF,MAAM,MAAM,GAAG,OAAO,KAAK,CAAC,QAAQ,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;YAChF,MAAM,QAAQ,GAAG,OAAO,KAAK,CAAC,UAAU,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;YACtF,MAAM,IAAI,GAAG,OAAO,KAAK,CAAC,MAAM,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;YAE1E,IAAI,CAAC,MAAM,IAAI,CAAC,cAAc,CAAC,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,UAAU,CAAC,IAAI,CAAC,QAAQ,CAAC,EAAE,CAAC;gBAC3E,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,MAAM,SAAS,GAAG,gBAAgB,CAAC,EAAE,MAAM,EAAE,MAAM,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,MAAM,CAAC,CAAA;YAE9E,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC;gBACjB,MAAM,MAAM,GAAG,EAAE,GAAG,EAAE,SAAS,CAAC,GAAG,EAAE,UAAU,EAAE,SAAS,CAAC,UAAU,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,EAAE,OAAO,EAAE,CAAA;gBAEvG,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,GAAG,IAAI,CAAC,CAAA;gBAEpC,OAAO,EAAE,CAAA;gBACT,SAAS,CAAC,SAAS,CAAC,QAAQ,CAAC,GAAG,CAAC,SAAS,CAAC,SAAS,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAA;gBAExE,SAAQ;YACT,CAAC;YAED,MAAM,EAAE,GAAG,aAAa,CACvB,KAAK,EACL;gBACC,GAAG,EAAE,SAAS,CAAC,GAAG;gBAClB,UAAU,EAAE,SAAS,CAAC,UAAU;gBAChC,OAAO,EAAE,IAAI;gBACb,MAAM,EAAE,OAAO;gBACf,MAAM;gBACN,SAAS,EAAE,aAAa,CAAC,MAAM,EAAE,EAAE,GAAG,EAAE,SAAS,CAAC,GAAG,EAAE,CAAC;gBACxD,cAAc,EAAE,OAAO;gBACvB,OAAO,EACN,4HAA4H;aAC7H,EACD,eAAe,SAAS,CAAC,QAAQ,EAAE,CACnC,CAAA;YAED,IAAI,EAAE,EAAE,CAAC;gBACR,OAAO,EAAE,CAAA;gBACT,SAAS,CAAC,SAAS,CAAC,QAAQ,CAAC,GAAG,CAAC,SAAS,CAAC,SAAS,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAA;YACzE,CAAC;iBAAM,CAAC;gBACP,WAAW,EAAE,CAAA;YACd,CAAC;QACF,CAAC;QAED,OAAO,CAAC,KAAK,CACZ,kBAAkB,OAAO,aAAa,MAAM,CAAC,OAAO,CAAC,SAAS,CAAC;aAC7D,GAAG,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC;aAC5B,IAAI,CAAC,IAAI,CAAC,MAAM,OAAO,aAAa,WAAW,mBAAmB,IAAI,OAAO,CAC/E,CAAA;QAED,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;IAClC,CAAC;CACD,CAAA"}
1
+ {"version":3,"file":"register.js","sourceRoot":"","sources":["../../../lib/sg/recipes/register.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH,OAAO,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAA;AACpD,OAAO,EAAE,UAAU,IAAI,cAAc,EAAE,MAAM,uBAAuB,CAAA;AACpE,OAAO,EAAE,gBAAgB,EAAE,MAAM,aAAa,CAAA;AAE9C,OAAO,EAAE,aAAa,EAAqB,UAAU,EAAE,cAAc,EAAE,MAAM,mBAAmB,CAAA;AAChG,OAAO,EAAE,mBAAmB,EAAE,MAAM,kBAAkB,CAAA;AACtD,OAAO,EAAE,cAAc,EAAE,MAAM,YAAY,CAAA;AAC3C,OAAO,EAAE,aAAa,EAAE,MAAM,QAAQ,CAAA;AAEtC,MAAM,MAAM,GAAG,mBAAmB,CAAC,mBAAmB,CAAC,CAAA;AAEvD;;GAEG;AACH,MAAM,qBAAqB,GAA0D;IACpF,CAAC,QAAQ,EAAE,KAAK,CAAC;IACjB,CAAC,MAAM,EAAE,IAAI,CAAC;IACd,CAAC,QAAQ,EAAE,IAAI,CAAC;IAChB,CAAC,OAAO,EAAE,IAAI,CAAC;IACf,CAAC,UAAU,EAAE,MAAM,CAAC;IACpB,CAAC,MAAM,EAAE,IAAI,CAAC;IACd,CAAC,WAAW,EAAE,MAAM,CAAC;IACrB,CAAC,SAAS,EAAE,KAAK,CAAC;IAClB,CAAC,OAAO,EAAE,IAAI,CAAC;IACf,CAAC,OAAO,EAAE,IAAI,CAAC;IACf,CAAC,MAAM,EAAE,IAAI,CAAC;CACd,CAAA;AAED;;;;;GAKG;AACH,MAAM,YAAY,GAAG,CAAC,QAAQ,EAAE,mBAAmB,EAAE,OAAO,EAAE,MAAM,EAAE,SAAS,EAAE,QAAQ,EAAE,SAAS,EAAE,OAAO,EAAE,OAAO,CAAC,CAAA;AAEvH,8GAA8G;AAC9G,MAAM,OAAO,GAAG,GAAG,CAAA;AACnB,MAAM,kBAAkB,GAAG,IAAI,CAAA;AAC/B,MAAM,cAAc,GAAG,IAAI,CAAA;AAC3B,MAAM,YAAY,GAAG,IAAI,CAAA;AACzB,MAAM,OAAO,GAAG,GAAG,CAAA;AAEnB,8FAA8F;AAC9F,MAAM,SAAS,GAAG,EAAE,CAAA;AACpB,MAAM,QAAQ,GAAG,GAAG,CAAA;AAEpB;;GAEG;AACH,MAAM,aAAa,GAA+B;IACjD,KAAK,EAAE,CAAC;IACR,gBAAgB,EAAE,OAAO;IACzB,YAAY,EAAE,OAAO,GAAG,kBAAkB;IAC1C,QAAQ,EAAE,CAAC;CACX,CAAA;AAED;;;GAGG;AACH,MAAM,UAAU,kBAAkB,CAAC,MAAc;IAChD,KAAK,MAAM,CAAC,IAAI,EAAE,KAAK,CAAC,IAAI,qBAAqB,EAAE,CAAC;QACnD,MAAM,OAAO,GAAG,IAAI,MAAM,CAAC,MAAM,IAAI,KAAK,EAAE,GAAG,CAAC,CAAA;QAEhD,IAAI,OAAO,CAAC,IAAI,CAAC,MAAM,CAAC;YAAE,OAAO,MAAM,CAAC,OAAO,CAAC,OAAO,EAAE,KAAK,CAAC,CAAA;IAChE,CAAC;IAED,OAAO,MAAM,CAAA;AACd,CAAC;AAED;;;;GAIG;AACH,MAAM,UAAU,cAAc,CAAC,IAAY;IAC1C,MAAM,KAAK,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAA;IAEvC,IAAI,CAAC,KAAK,IAAI,KAAK,KAAK,KAAK,IAAI,SAAS,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC;QAAE,OAAO,KAAK,CAAA;IAE1F,OAAO,CAAC,YAAY,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAA;AAC1D,CAAC;AAuBD;;;;;;;;GAQG;AACH,MAAM,UAAU,gBAAgB,CAAC,GAAU,EAAE,MAAoB,EAAE,QAAqB;IACvF,MAAM,OAAO,GAAG,gBAAgB,CAAC,GAAG,CAAC,MAAM,CAAC,CAAA;IAC5C,MAAM,MAAM,GAAG,MAAM,EAAE,GAAG,YAAY,CAAC,CAAC,CAAC,kBAAkB,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,OAAO,CAAA;IAC9E,MAAM,KAAK,GAAG,MAAM,EAAE,CAAA;IACtB,MAAM,QAAQ,GAAG,cAAc,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,gBAAgB,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAA;IAC7E,MAAM,IAAI,GAAG,QAAQ,CAAC,CAAC,CAAC,aAAa,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,KAAK,CAAA;IAEvD,IAAI,GAAW,CAAA;IACf,IAAI,QAAoB,CAAA;IACxB,MAAM,UAAU,GAA2B,EAAE,YAAY,EAAE,GAAG,CAAC,MAAM,EAAE,MAAM,EAAE,QAAQ,EAAE,GAAG,CAAC,QAAQ,EAAE,CAAA;IAEvG,IAAI,IAAI,GAAG,OAAO,IAAI,cAAc,CAAC,IAAI,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC;QACvD,MAAM,KAAK,GAAG,MAAM,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,SAAS,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAA;QAC3E,MAAM,MAAM,GAAG,MAAM,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,QAAQ,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAA;QAC3E,MAAM,IAAI,GAAG,IAAI,KAAK,IAAI,MAAM,EAAE,CAAA;QAElC,GAAG,GAAG,OAAO,GAAG,CAAC,MAAM,IAAI,MAAM,IAAI,IAAI,cAAc,GAAG,CAAC,QAAQ,EAAE,CAAA;QACrE,UAAU,CAAC,IAAI,GAAG,IAAI,CAAA;QACtB,UAAU,CAAC,QAAQ,GAAG,WAAW,CAAA;QACjC,QAAQ,GAAG,OAAO,CAAA;IACnB,CAAC;SAAM,IAAI,IAAI,GAAG,OAAO,GAAG,kBAAkB,EAAE,CAAC;QAChD,GAAG,GAAG,GAAG,GAAG,CAAC,MAAM,IAAI,MAAM,MAAM,GAAG,CAAC,QAAQ,GAAG,CAAA;QAClD,QAAQ,GAAG,kBAAkB,CAAA;IAC9B,CAAC;SAAM,IAAI,IAAI,GAAG,OAAO,GAAG,kBAAkB,GAAG,cAAc,IAAI,QAAQ,EAAE,CAAC;QAC7E,GAAG,GAAG,GAAG,QAAQ,KAAK,GAAG,CAAC,MAAM,IAAI,MAAM,eAAe,GAAG,CAAC,QAAQ,EAAE,CAAA;QACvE,UAAU,CAAC,KAAK,GAAG,QAAQ,CAAA;QAC3B,UAAU,CAAC,QAAQ,GAAG,WAAW,CAAA;QACjC,QAAQ,GAAG,cAAc,CAAA;IAC1B,CAAC;SAAM,CAAC;QACP,GAAG,GAAG,GAAG,GAAG,CAAC,MAAM,IAAI,MAAM,cAAc,GAAG,CAAC,QAAQ,EAAE,CAAA;QACzD,UAAU,CAAC,QAAQ,GAAG,WAAW,CAAA;QACjC,QAAQ,GAAG,UAAU,CAAA;IACtB,CAAC;IAED,IAAI,MAAM,EAAE,GAAG,OAAO,EAAE,CAAC;QACxB,GAAG,GAAG,GAAG,CAAC,WAAW,EAAE,CAAA;QAEvB,KAAK,MAAM,GAAG,IAAI,MAAM,CAAC,IAAI,CAAC,UAAU,CAAC,EAAE,CAAC;YAC3C,UAAU,CAAC,GAAG,CAAC,GAAG,UAAU,CAAC,GAAG,CAAE,CAAC,WAAW,EAAE,CAAA;QACjD,CAAC;IACF,CAAC;IAED,OAAO,EAAE,GAAG,EAAE,UAAU,EAAE,QAAQ,EAAE,QAAQ,EAAE,CAAA;AAC/C,CAAC;AAED;;;;GAIG;AACH,MAAM,CAAC,MAAM,gBAAgB,GAAiB;IAC7C,IAAI,EAAE,aAAa;IACnB,WAAW,EACV,2IAA2I;IAC5I,IAAI,EAAE,QAAQ;IACd,OAAO,EAAE;QACR,EAAE,IAAI,EAAE,SAAS,EAAE,WAAW,EAAE,8CAA8C,EAAE;QAChF,EAAE,IAAI,EAAE,SAAS,EAAE,WAAW,EAAE,6EAA6E,EAAE;KAC/G;IACD,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,IAAI,CAAC,IAAI,CAAC,KAAK,EAAE,CAAC;YACjB,MAAM,IAAI,KAAK,CAAC,6DAA6D,CAAC,CAAA;QAC/E,CAAC;QAED,MAAM,MAAM,GAAG,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACxC,MAAM,MAAM,GAAG,IAAI,CAAC,UAAU,IAAI,MAAM,CAAA;QACxC,MAAM,SAAS,GAA2B,EAAE,CAAA;QAC5C,IAAI,IAAI,GAAG,CAAC,CAAA;QACZ,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,WAAW,GAAG,CAAC,CAAA;QAEnB,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,UAAU,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;YAClD,IAAI,EAAE,CAAA;YAEN,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;gBAAE,MAAK;YAE5D,MAAM,MAAM,GAAG,OAAO,KAAK,CAAC,QAAQ,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;YAChF,MAAM,MAAM,GAAG,OAAO,KAAK,CAAC,QAAQ,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;YAChF,MAAM,QAAQ,GAAG,OAAO,KAAK,CAAC,UAAU,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;YACtF,MAAM,IAAI,GAAG,OAAO,KAAK,CAAC,MAAM,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;YAE1E,IAAI,CAAC,MAAM,IAAI,CAAC,cAAc,CAAC,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,UAAU,CAAC,IAAI,CAAC,QAAQ,CAAC,EAAE,CAAC;gBAC3E,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,MAAM,SAAS,GAAG,gBAAgB,CAAC,EAAE,MAAM,EAAE,MAAM,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,MAAM,CAAC,CAAA;YAE9E,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC;gBACjB,MAAM,MAAM,GAAG,EAAE,GAAG,EAAE,SAAS,CAAC,GAAG,EAAE,UAAU,EAAE,SAAS,CAAC,UAAU,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,EAAE,OAAO,EAAE,CAAA;gBAEvG,KAAK,CAAC,aAAa,CAAC,MAAM,CAAC,CAAC,CAAA;gBAE5B,OAAO,EAAE,CAAA;gBACT,SAAS,CAAC,SAAS,CAAC,QAAQ,CAAC,GAAG,CAAC,SAAS,CAAC,SAAS,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAA;gBAExE,SAAQ;YACT,CAAC;YAED,MAAM,EAAE,GAAG,aAAa,CACvB,KAAK,EACL;gBACC,GAAG,EAAE,SAAS,CAAC,GAAG;gBAClB,UAAU,EAAE,SAAS,CAAC,UAAU;gBAChC,OAAO,EAAE,IAAI;gBACb,MAAM,EAAE,OAAO;gBACf,MAAM;gBACN,SAAS,EAAE,cAAc,CAAC,MAAM,EAAE,EAAE,GAAG,EAAE,SAAS,CAAC,GAAG,EAAE,CAAC;gBACzD,cAAc,EAAE,OAAO;gBACvB,OAAO,EACN,4HAA4H;aAC7H,EACD,eAAe,SAAS,CAAC,QAAQ,EAAE;YACnC,6EAA6E;YAC7E,sEAAsE;YACtE,wCAAwC;YACxC;gBACC,QAAQ,EAAE,cAAc,CAAC,QAAQ;gBACjC,OAAO,EAAE,aAAa,CAAC,QAAQ;gBAC/B,YAAY,EAAE,KAAK,CAAC,QAAQ,IAAI,IAAI;aACpC,CACD,CAAA;YAED,IAAI,EAAE,EAAE,CAAC;gBACR,OAAO,EAAE,CAAA;gBACT,SAAS,CAAC,SAAS,CAAC,QAAQ,CAAC,GAAG,CAAC,SAAS,CAAC,SAAS,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAA;YACzE,CAAC;iBAAM,CAAC;gBACP,WAAW,EAAE,CAAA;YACd,CAAC;QACF,CAAC;QAED,OAAO,CAAC,KAAK,CACZ,kBAAkB,OAAO,aAAa,MAAM,CAAC,OAAO,CAAC,SAAS,CAAC;aAC7D,GAAG,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC;aAC5B,IAAI,CAAC,IAAI,CAAC,MAAM,OAAO,aAAa,WAAW,mBAAmB,IAAI,OAAO,CAC/E,CAAA;QAED,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;IAClC,CAAC;CACD,CAAA"}
@@ -3,21 +3,18 @@
3
3
  * @license AGPL-3.0
4
4
  * @author Teffen Ellis, et al.
5
5
  *
6
- * Fetch Singapore's ACRA corporate-entity register from data.gov.sg: 27 monthly CSVs (one per first
7
- * letter of the entity name plus "others"), 53 columns, the registered address FIELDED — `Block`,
8
- * `Street Name`, `Level No`, `Unit No`, `Building Name`, `Postal Code` — which is the NPPES shape,
9
- * so the corpus adapter renders the string and the spans fall out by construction. A Singapore
10
- * postcode names one building, so the postcode column is also the join to the OneMap/Overture rows.
11
- *
12
- * License: Singapore Open Data Licence version 1.0 (attribution; commercial use, modification and
13
- * adaptation permitted; no share-alike). The prescribed attribution sentence goes in the manifest.
14
- *
15
- * data.gov.sg serves a dataset in two calls: `initiate-download` prepares a signed URL and
16
- * `poll-download` answers it once the export is ready.
17
- *
18
- * Invoke via `mailwoman corpus fetch acra-sg --out-root <path>`.
6
+ * Fetches Singapore ACRA corporate-entity CSVs from data.gov.sg.
7
+ * The publisher includes fielded addresses in these files.
8
+ */
9
+ import type { BaseFetchOptions, FetchSummary } from "#tools/fetch/download";
10
+ /**
11
+ * Options for {@link fetchACRASG}.
19
12
  */
20
- import type { BaseFetchOptions, FetchSummary } from "#tools/fetch/download/index";
21
13
  export type FetchACRASGOptions = BaseFetchOptions;
14
+ /**
15
+ * Downloads every dataset in the ACRA collection and writes a collection manifest after each file.
16
+ *
17
+ * The function skips a file that the previous manifest lists and that still exists on disk.
18
+ */
22
19
  export declare function fetchACRASG(options: FetchACRASGOptions, report?: (line: string) => void): Promise<FetchSummary>;
23
20
  //# sourceMappingURL=acra.d.ts.map