@mailwoman/corpus 9.4.0 → 10.0.0

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 (981) hide show
  1. package/README.md +16 -0
  2. package/lib/adapters/geonames/adapter.ts +3 -3
  3. package/lib/adapters/geonames/postal/adapter.ts +122 -0
  4. package/lib/adapters/index.ts +39 -32
  5. package/lib/adapters/openaddresses/adapter.ts +4 -7
  6. package/lib/adapters/osm/adapter.ts +278 -0
  7. package/lib/adapters/overture/adapter.ts +22 -7
  8. package/lib/adapters/utils/index.ts +1 -1
  9. package/lib/adapters/wof/admin/json/adapter.ts +239 -0
  10. package/lib/adapters/wof/json-rows.ts +181 -0
  11. package/lib/adapters/wof/postalcode-json/adapter.ts +196 -0
  12. package/lib/au/adapters/gnaf/adapter.ts +152 -0
  13. package/lib/au/adapters/gnaf/assemble.ts +225 -0
  14. package/lib/de/recipes/locale.ts +360 -0
  15. package/lib/fr/adapters/ban/adapter.ts +159 -0
  16. package/lib/fr/recipes/admin-split.ts +243 -0
  17. package/lib/fr/recipes/bare-street.ts +171 -0
  18. package/lib/fr/recipes/fragment.ts +334 -0
  19. package/lib/fr/recipes/lieudit.ts +274 -0
  20. package/lib/fr/recipes/order.ts +246 -0
  21. package/lib/fr/tools/fetch/ban.ts +289 -0
  22. package/lib/index.ts +1 -1
  23. package/lib/international/recipes/locale.ts +598 -0
  24. package/lib/jp/tools/fetch/houjin.ts +141 -0
  25. package/lib/kr/adapters/juso/label-rows.ts +259 -0
  26. package/lib/kr/adapters/localdata/align.ts +299 -0
  27. package/lib/kr/adapters/localdata/key-index.ts +185 -0
  28. package/lib/kr/adapters/localdata/permit-rows.ts +186 -0
  29. package/lib/kr/tools/fetch/juso.ts +172 -0
  30. package/lib/kr/tools/fetch/localdata.ts +206 -0
  31. package/lib/recipes/bare/postcode/eval.ts +99 -0
  32. package/lib/recipes/bare/postcode/index.ts +327 -0
  33. package/lib/recipes/country-balanced.ts +1 -1
  34. package/lib/recipes/index.ts +28 -21
  35. package/lib/recipes/intersection.ts +1 -1
  36. package/lib/recipes/po/box/cedex/au-nz.ts +82 -0
  37. package/lib/recipes/po/box/cedex/ca.ts +58 -0
  38. package/lib/recipes/po/box/cedex/fr.ts +76 -0
  39. package/lib/recipes/po/box/cedex/phrases.ts +108 -0
  40. package/lib/recipes/po/box/cedex/recipe.ts +203 -0
  41. package/lib/recipes/po/box/cedex/sources.ts +189 -0
  42. package/lib/recipes/po/box/cedex/types.ts +35 -0
  43. package/lib/recipes/po/box/cedex/us.ts +69 -0
  44. package/lib/recipes/po/box/cedex/vocabulary.ts +106 -0
  45. package/lib/recipes/po/box/cedex.ts +9 -0
  46. package/lib/recipes/po/box/index.ts +128 -0
  47. package/lib/recipes/scaffold.ts +18 -41
  48. package/lib/recipes/street/affix.ts +807 -0
  49. package/lib/recipes/sub/venue/context.ts +149 -0
  50. package/lib/recipes/sub/venue/index.ts +997 -0
  51. package/lib/recipes/sub/venue/sources.ts +739 -0
  52. package/lib/recipes/trailing-region.ts +6 -1
  53. package/lib/recipes/unit.ts +1 -1
  54. package/lib/sg/recipes/register.ts +270 -0
  55. package/lib/sg/tools/fetch/acra.ts +179 -0
  56. package/lib/south-asia/recipes/register.ts +214 -0
  57. package/lib/synthesizers/anchor-absorption.ts +1 -1
  58. package/lib/synthesizers/locale.ts +261 -0
  59. package/lib/synthesizers/street.ts +1 -1
  60. package/lib/synthesizers/utils.ts +2 -2
  61. package/lib/tools/audit.ts +3 -2
  62. package/lib/tools/corpus-stats.ts +3 -3
  63. package/lib/tools/fetch/download/index.ts +10 -0
  64. package/lib/tools/fetch/download/manifest.ts +102 -0
  65. package/lib/tools/fetch/download/network.ts +226 -0
  66. package/lib/tools/fetch/download/retry.ts +173 -0
  67. package/lib/tools/fetch/geonames/dump.ts +257 -0
  68. package/lib/tools/fetch/geonames/postal.ts +180 -0
  69. package/lib/tools/fetch/index.ts +30 -30
  70. package/lib/tools/fetch/openaddresses.ts +2 -2
  71. package/lib/tools/fetch/ourairports.ts +2 -2
  72. package/lib/tools/fetch/ppd.ts +1 -3
  73. package/lib/tools/fetch/wikidata-subvenue.ts +2 -2
  74. package/lib/tools/golden/promote.ts +340 -0
  75. package/lib/tools/golden/relabel-street/directory.ts +340 -0
  76. package/lib/tools/golden/relabel-street/index.ts +9 -0
  77. package/lib/tools/golden/relabel-street/row.ts +361 -0
  78. package/lib/tools/index.ts +10 -10
  79. package/lib/tools/ingest-csv.ts +5 -7
  80. package/lib/tools/lint/slice/vocab.ts +376 -0
  81. package/lib/tools/overlay-manifest.ts +92 -25
  82. package/lib/tools/overture-subvenue.ts +1 -1
  83. package/lib/tools/postcode-triples.ts +138 -14
  84. package/lib/tools/sub/venue/harvest.ts +234 -0
  85. package/lib/tools/sub/venue/head-nouns.ts +245 -0
  86. package/lib/tools/sub/venue/lexicon.ts +429 -0
  87. package/lib/tools/sub/venue/surfaces.ts +95 -0
  88. package/lib/tools/sub/venue/table.ts +281 -0
  89. package/lib/tools/sub/venue/wikidata.ts +85 -0
  90. package/lib/tw/tools/fetch/gcis.ts +180 -0
  91. package/lib/types.ts +1 -1
  92. package/lib/us/adapters/fcc-bdc/adapter.ts +173 -0
  93. package/lib/us/adapters/state/hi-schools/adapter.ts +160 -0
  94. package/lib/us/adapters/state/ia-contractors/adapter.ts +136 -0
  95. package/lib/us/adapters/state/ny-notaries/adapter.ts +133 -0
  96. package/lib/us/adapters/state/tx-notaries/adapter.ts +149 -0
  97. package/lib/us/adapters/tiger/adapter.ts +250 -0
  98. package/lib/us/adapters/usgov/hrsa-fqhc/adapter.ts +156 -0
  99. package/lib/us/adapters/usgov/imls-pls/adapter.ts +134 -0
  100. package/lib/us/adapters/usgov/irs-bmf/adapter.ts +145 -0
  101. package/lib/us/adapters/usgov/nad/adapter.ts +324 -0
  102. package/lib/us/adapters/usgov/nppes/adapter.ts +143 -0
  103. package/lib/us/adapters/usgov/samhsa-treatment-locator/adapter.ts +182 -0
  104. package/lib/us/tools/fetch/hrsa.ts +59 -0
  105. package/lib/us/tools/fetch/imls-pls.ts +149 -0
  106. package/lib/us/tools/fetch/nad.ts +341 -0
  107. package/lib/us/tools/fetch/nppes.ts +165 -0
  108. package/lib/us/tools/fetch/state/hi-schools.ts +161 -0
  109. package/lib/us/tools/fetch/state/sources.ts +146 -0
  110. package/lib/us/tools/fetch/tiger-full.ts +308 -0
  111. package/lib/utils/align.ts +1 -1
  112. package/lib/utils/golden.ts +12 -8
  113. package/lib/utils/wof-json.ts +7 -13
  114. package/out/adapters/geonames/adapter.d.ts +1 -1
  115. package/out/adapters/geonames/adapter.js +3 -3
  116. package/out/adapters/geonames/adapter.js.map +1 -1
  117. package/out/adapters/geonames/postal/adapter.d.ts.map +1 -0
  118. package/out/adapters/geonames/postal/adapter.js +107 -0
  119. package/out/adapters/geonames/postal/adapter.js.map +1 -0
  120. package/out/adapters/index.d.ts +16 -16
  121. package/out/adapters/index.d.ts.map +1 -1
  122. package/out/adapters/index.js +34 -32
  123. package/out/adapters/index.js.map +1 -1
  124. package/out/adapters/openaddresses/adapter.d.ts.map +1 -1
  125. package/out/adapters/openaddresses/adapter.js +4 -6
  126. package/out/adapters/openaddresses/adapter.js.map +1 -1
  127. package/out/adapters/osm/adapter.d.ts +95 -0
  128. package/out/adapters/osm/adapter.d.ts.map +1 -0
  129. package/out/adapters/osm/adapter.js +211 -0
  130. package/out/adapters/osm/adapter.js.map +1 -0
  131. package/out/adapters/overture/adapter.d.ts +10 -0
  132. package/out/adapters/overture/adapter.d.ts.map +1 -1
  133. package/out/adapters/overture/adapter.js +20 -7
  134. package/out/adapters/overture/adapter.js.map +1 -1
  135. package/out/adapters/synth-po-box/adapter.js.map +1 -1
  136. package/out/adapters/utils/index.d.ts +1 -1
  137. package/out/adapters/utils/index.d.ts.map +1 -1
  138. package/out/adapters/utils/index.js.map +1 -1
  139. package/out/adapters/wof/admin/json/adapter.d.ts +79 -0
  140. package/out/adapters/wof/admin/json/adapter.d.ts.map +1 -0
  141. package/out/adapters/wof/admin/json/adapter.js +204 -0
  142. package/out/adapters/wof/admin/json/adapter.js.map +1 -0
  143. package/out/adapters/wof/json-rows.d.ts +73 -0
  144. package/out/adapters/wof/json-rows.d.ts.map +1 -0
  145. package/out/adapters/wof/json-rows.js +115 -0
  146. package/out/adapters/wof/json-rows.js.map +1 -0
  147. package/out/adapters/wof/postalcode-json/adapter.d.ts +65 -0
  148. package/out/adapters/wof/postalcode-json/adapter.d.ts.map +1 -0
  149. package/out/adapters/wof/postalcode-json/adapter.js +167 -0
  150. package/out/adapters/wof/postalcode-json/adapter.js.map +1 -0
  151. package/out/au/adapters/gnaf/adapter.d.ts.map +1 -0
  152. package/out/au/adapters/gnaf/adapter.js +127 -0
  153. package/out/au/adapters/gnaf/adapter.js.map +1 -0
  154. package/out/au/adapters/gnaf/assemble.d.ts +65 -0
  155. package/out/au/adapters/gnaf/assemble.d.ts.map +1 -0
  156. package/out/au/adapters/gnaf/assemble.js +154 -0
  157. package/out/au/adapters/gnaf/assemble.js.map +1 -0
  158. package/out/cn/recipes/organizational-units.d.ts +36 -0
  159. package/out/cn/recipes/organizational-units.d.ts.map +1 -0
  160. package/out/cn/recipes/organizational-units.js +159 -0
  161. package/out/cn/recipes/organizational-units.js.map +1 -0
  162. package/out/cz/recipes/pcfirst-preposition.d.ts +22 -0
  163. package/out/cz/recipes/pcfirst-preposition.d.ts.map +1 -0
  164. package/out/cz/recipes/pcfirst-preposition.js +101 -0
  165. package/out/cz/recipes/pcfirst-preposition.js.map +1 -0
  166. package/out/de/recipes/locale.d.ts +44 -0
  167. package/out/de/recipes/locale.d.ts.map +1 -0
  168. package/out/de/recipes/locale.js +289 -0
  169. package/out/de/recipes/locale.js.map +1 -0
  170. package/out/env.d.ts +1 -1
  171. package/out/fr/adapters/ban/adapter.d.ts.map +1 -0
  172. package/out/fr/adapters/ban/adapter.js +123 -0
  173. package/out/fr/adapters/ban/adapter.js.map +1 -0
  174. package/out/fr/adapters/ban/street-decompose.d.ts.map +1 -0
  175. package/out/fr/adapters/ban/street-decompose.js.map +1 -0
  176. package/out/fr/recipes/admin-split.d.ts +38 -0
  177. package/out/fr/recipes/admin-split.d.ts.map +1 -0
  178. package/out/fr/recipes/admin-split.js +192 -0
  179. package/out/fr/recipes/admin-split.js.map +1 -0
  180. package/out/fr/recipes/bare-street.d.ts +28 -0
  181. package/out/fr/recipes/bare-street.d.ts.map +1 -0
  182. package/out/fr/recipes/bare-street.js +144 -0
  183. package/out/fr/recipes/bare-street.js.map +1 -0
  184. package/out/fr/recipes/fragment.d.ts +77 -0
  185. package/out/fr/recipes/fragment.d.ts.map +1 -0
  186. package/out/fr/recipes/fragment.js +277 -0
  187. package/out/fr/recipes/fragment.js.map +1 -0
  188. package/out/fr/recipes/lieudit.d.ts +32 -0
  189. package/out/fr/recipes/lieudit.d.ts.map +1 -0
  190. package/out/fr/recipes/lieudit.js +211 -0
  191. package/out/fr/recipes/lieudit.js.map +1 -0
  192. package/out/fr/recipes/order.d.ts +38 -0
  193. package/out/fr/recipes/order.d.ts.map +1 -0
  194. package/out/fr/recipes/order.js +198 -0
  195. package/out/fr/recipes/order.js.map +1 -0
  196. package/out/fr/tools/fetch/ban.d.ts +31 -0
  197. package/out/fr/tools/fetch/ban.d.ts.map +1 -0
  198. package/out/fr/tools/fetch/ban.js +239 -0
  199. package/out/fr/tools/fetch/ban.js.map +1 -0
  200. package/out/index.d.ts +1 -1
  201. package/out/index.d.ts.map +1 -1
  202. package/out/index.js +1 -1
  203. package/out/index.js.map +1 -1
  204. package/out/international/recipes/locale.d.ts +136 -0
  205. package/out/international/recipes/locale.d.ts.map +1 -0
  206. package/out/international/recipes/locale.js +458 -0
  207. package/out/international/recipes/locale.js.map +1 -0
  208. package/out/jp/adapters/wof-admin/adapter.d.ts.map +1 -0
  209. package/out/jp/adapters/wof-admin/adapter.js.map +1 -0
  210. package/out/jp/tools/fetch/houjin.d.ts +24 -0
  211. package/out/jp/tools/fetch/houjin.d.ts.map +1 -0
  212. package/out/jp/tools/fetch/houjin.js +102 -0
  213. package/out/jp/tools/fetch/houjin.js.map +1 -0
  214. package/out/kr/adapters/juso/label-rows.d.ts +76 -0
  215. package/out/kr/adapters/juso/label-rows.d.ts.map +1 -0
  216. package/out/kr/adapters/juso/label-rows.js +194 -0
  217. package/out/kr/adapters/juso/label-rows.js.map +1 -0
  218. package/out/kr/adapters/localdata/align.d.ts +43 -0
  219. package/out/kr/adapters/localdata/align.d.ts.map +1 -0
  220. package/out/kr/adapters/localdata/align.js +223 -0
  221. package/out/kr/adapters/localdata/align.js.map +1 -0
  222. package/out/kr/adapters/localdata/key-index.d.ts +71 -0
  223. package/out/kr/adapters/localdata/key-index.d.ts.map +1 -0
  224. package/out/kr/adapters/localdata/key-index.js +133 -0
  225. package/out/kr/adapters/localdata/key-index.js.map +1 -0
  226. package/out/kr/adapters/localdata/permit-rows.d.ts +66 -0
  227. package/out/kr/adapters/localdata/permit-rows.d.ts.map +1 -0
  228. package/out/kr/adapters/localdata/permit-rows.js +131 -0
  229. package/out/kr/adapters/localdata/permit-rows.js.map +1 -0
  230. package/out/kr/tools/fetch/juso.d.ts +30 -0
  231. package/out/kr/tools/fetch/juso.d.ts.map +1 -0
  232. package/out/kr/tools/fetch/juso.js +120 -0
  233. package/out/kr/tools/fetch/juso.js.map +1 -0
  234. package/out/kr/tools/fetch/localdata.d.ts +30 -0
  235. package/out/kr/tools/fetch/localdata.d.ts.map +1 -0
  236. package/out/kr/tools/fetch/localdata.js +139 -0
  237. package/out/kr/tools/fetch/localdata.js.map +1 -0
  238. package/out/nl/recipes/postcode.d.ts +26 -0
  239. package/out/nl/recipes/postcode.d.ts.map +1 -0
  240. package/out/nl/recipes/postcode.js +103 -0
  241. package/out/nl/recipes/postcode.js.map +1 -0
  242. package/out/no/recipes/fragment.d.ts +43 -0
  243. package/out/no/recipes/fragment.d.ts.map +1 -0
  244. package/out/no/recipes/fragment.js +183 -0
  245. package/out/no/recipes/fragment.js.map +1 -0
  246. package/out/no/recipes/street/index.d.ts +18 -0
  247. package/out/no/recipes/street/index.d.ts.map +1 -0
  248. package/out/no/recipes/street/index.js +72 -0
  249. package/out/no/recipes/street/index.js.map +1 -0
  250. package/out/no/recipes/street/led.d.ts +24 -0
  251. package/out/no/recipes/street/led.d.ts.map +1 -0
  252. package/out/no/recipes/street/led.js +114 -0
  253. package/out/no/recipes/street/led.js.map +1 -0
  254. package/out/recipes/bare/country.d.ts +25 -0
  255. package/out/recipes/bare/country.d.ts.map +1 -0
  256. package/out/recipes/bare/country.js +88 -0
  257. package/out/recipes/bare/country.js.map +1 -0
  258. package/out/recipes/bare/postcode/eval.d.ts +29 -0
  259. package/out/recipes/bare/postcode/eval.d.ts.map +1 -0
  260. package/out/recipes/bare/postcode/eval.js +85 -0
  261. package/out/recipes/bare/postcode/eval.js.map +1 -0
  262. package/out/recipes/bare/postcode/index.d.ts +62 -0
  263. package/out/recipes/bare/postcode/index.d.ts.map +1 -0
  264. package/out/recipes/bare/postcode/index.js +267 -0
  265. package/out/recipes/bare/postcode/index.js.map +1 -0
  266. package/out/recipes/country-balanced.js.map +1 -1
  267. package/out/recipes/index.d.ts.map +1 -1
  268. package/out/recipes/index.js +28 -21
  269. package/out/recipes/index.js.map +1 -1
  270. package/out/recipes/intersection.js.map +1 -1
  271. package/out/recipes/po/box/cedex/au-nz.d.ts +7 -0
  272. package/out/recipes/po/box/cedex/au-nz.d.ts.map +1 -0
  273. package/out/recipes/po/box/cedex/au-nz.js +56 -0
  274. package/out/recipes/po/box/cedex/au-nz.js.map +1 -0
  275. package/out/recipes/po/box/cedex/ca.d.ts +7 -0
  276. package/out/recipes/po/box/cedex/ca.d.ts.map +1 -0
  277. package/out/recipes/po/box/cedex/ca.js +38 -0
  278. package/out/recipes/po/box/cedex/ca.js.map +1 -0
  279. package/out/recipes/po/box/cedex/fr.d.ts +7 -0
  280. package/out/recipes/po/box/cedex/fr.d.ts.map +1 -0
  281. package/out/recipes/po/box/cedex/fr.js +57 -0
  282. package/out/recipes/po/box/cedex/fr.js.map +1 -0
  283. package/out/recipes/po/box/cedex/phrases.d.ts +8 -0
  284. package/out/recipes/po/box/cedex/phrases.d.ts.map +1 -0
  285. package/out/recipes/po/box/cedex/phrases.js +76 -0
  286. package/out/recipes/po/box/cedex/phrases.js.map +1 -0
  287. package/out/recipes/po/box/cedex/recipe.d.ts +9 -0
  288. package/out/recipes/po/box/cedex/recipe.d.ts.map +1 -0
  289. package/out/recipes/po/box/cedex/recipe.js +153 -0
  290. package/out/recipes/po/box/cedex/recipe.js.map +1 -0
  291. package/out/recipes/po/box/cedex/sources.d.ts +86 -0
  292. package/out/recipes/po/box/cedex/sources.d.ts.map +1 -0
  293. package/out/recipes/po/box/cedex/sources.js +143 -0
  294. package/out/recipes/po/box/cedex/sources.js.map +1 -0
  295. package/out/recipes/po/box/cedex/types.d.ts +31 -0
  296. package/out/recipes/po/box/cedex/types.d.ts.map +1 -0
  297. package/out/recipes/po/box/cedex/types.js +5 -0
  298. package/out/recipes/po/box/cedex/types.js.map +1 -0
  299. package/out/recipes/po/box/cedex/us.d.ts +7 -0
  300. package/out/recipes/po/box/cedex/us.d.ts.map +1 -0
  301. package/out/recipes/po/box/cedex/us.js +51 -0
  302. package/out/recipes/po/box/cedex/us.js.map +1 -0
  303. package/out/recipes/po/box/cedex/vocabulary.d.ts +68 -0
  304. package/out/recipes/po/box/cedex/vocabulary.d.ts.map +1 -0
  305. package/out/recipes/po/box/cedex/vocabulary.js +90 -0
  306. package/out/recipes/po/box/cedex/vocabulary.js.map +1 -0
  307. package/out/recipes/po/box/cedex.d.ts +9 -0
  308. package/out/recipes/po/box/cedex.d.ts.map +1 -0
  309. package/out/recipes/po/box/cedex.js +9 -0
  310. package/out/recipes/po/box/cedex.js.map +1 -0
  311. package/out/recipes/po/box/index.d.ts +17 -0
  312. package/out/recipes/po/box/index.d.ts.map +1 -0
  313. package/out/recipes/po/box/index.js +105 -0
  314. package/out/recipes/po/box/index.js.map +1 -0
  315. package/out/recipes/scaffold.d.ts +20 -0
  316. package/out/recipes/scaffold.d.ts.map +1 -1
  317. package/out/recipes/scaffold.js +18 -37
  318. package/out/recipes/scaffold.js.map +1 -1
  319. package/out/recipes/street/affix.d.ts +89 -0
  320. package/out/recipes/street/affix.d.ts.map +1 -0
  321. package/out/recipes/street/affix.js +565 -0
  322. package/out/recipes/street/affix.js.map +1 -0
  323. package/out/recipes/street/bare.d.ts +25 -0
  324. package/out/recipes/street/bare.d.ts.map +1 -0
  325. package/out/recipes/street/bare.js +87 -0
  326. package/out/recipes/street/bare.js.map +1 -0
  327. package/out/recipes/sub/venue/context.d.ts +29 -0
  328. package/out/recipes/sub/venue/context.d.ts.map +1 -0
  329. package/out/recipes/sub/venue/context.js +106 -0
  330. package/out/recipes/sub/venue/context.js.map +1 -0
  331. package/out/recipes/sub/venue/index.d.ts +270 -0
  332. package/out/recipes/sub/venue/index.d.ts.map +1 -0
  333. package/out/recipes/sub/venue/index.js +728 -0
  334. package/out/recipes/sub/venue/index.js.map +1 -0
  335. package/out/recipes/sub/venue/sources.d.ts +209 -0
  336. package/out/recipes/sub/venue/sources.d.ts.map +1 -0
  337. package/out/recipes/sub/venue/sources.js +555 -0
  338. package/out/recipes/sub/venue/sources.js.map +1 -0
  339. package/out/recipes/trailing-region.d.ts.map +1 -1
  340. package/out/recipes/trailing-region.js +6 -1
  341. package/out/recipes/trailing-region.js.map +1 -1
  342. package/out/recipes/unit.js.map +1 -1
  343. package/out/sg/recipes/register.d.ts +69 -0
  344. package/out/sg/recipes/register.d.ts.map +1 -0
  345. package/out/sg/recipes/register.js +211 -0
  346. package/out/sg/recipes/register.js.map +1 -0
  347. package/out/sg/tools/fetch/acra.d.ts +23 -0
  348. package/out/sg/tools/fetch/acra.d.ts.map +1 -0
  349. package/out/sg/tools/fetch/acra.js +126 -0
  350. package/out/sg/tools/fetch/acra.js.map +1 -0
  351. package/out/si/recipes/bare-village.d.ts +32 -0
  352. package/out/si/recipes/bare-village.d.ts.map +1 -0
  353. package/out/si/recipes/bare-village.js +89 -0
  354. package/out/si/recipes/bare-village.js.map +1 -0
  355. package/out/south-asia/recipes/register.d.ts +51 -0
  356. package/out/south-asia/recipes/register.d.ts.map +1 -0
  357. package/out/south-asia/recipes/register.js +154 -0
  358. package/out/south-asia/recipes/register.js.map +1 -0
  359. package/out/synthesizers/anchor-absorption.d.ts +1 -1
  360. package/out/synthesizers/anchor-absorption.d.ts.map +1 -1
  361. package/out/synthesizers/anchor-absorption.js.map +1 -1
  362. package/out/synthesizers/boundary-stress.js.map +1 -1
  363. package/out/synthesizers/house-venue.js.map +1 -1
  364. package/out/synthesizers/intersection.js.map +1 -1
  365. package/out/synthesizers/locale.d.ts +116 -0
  366. package/out/synthesizers/locale.d.ts.map +1 -0
  367. package/out/synthesizers/locale.js +150 -0
  368. package/out/synthesizers/locale.js.map +1 -0
  369. package/out/synthesizers/no-street.d.ts.map +1 -1
  370. package/out/synthesizers/no-street.js.map +1 -1
  371. package/out/synthesizers/po-box.js.map +1 -1
  372. package/out/synthesizers/street.d.ts.map +1 -1
  373. package/out/synthesizers/street.js +1 -1
  374. package/out/synthesizers/street.js.map +1 -1
  375. package/out/synthesizers/utils.js +1 -1
  376. package/out/synthesizers/utils.js.map +1 -1
  377. package/out/test-kit/corpus-recipe.d.ts.map +1 -1
  378. package/out/test-kit/corpus-recipe.js.map +1 -1
  379. package/out/tools/audit.d.ts.map +1 -1
  380. package/out/tools/audit.js +3 -2
  381. package/out/tools/audit.js.map +1 -1
  382. package/out/tools/corpus-stats.js +3 -3
  383. package/out/tools/corpus-stats.js.map +1 -1
  384. package/out/tools/fetch/download/index.d.ts +10 -0
  385. package/out/tools/fetch/download/index.d.ts.map +1 -0
  386. package/out/tools/fetch/download/index.js +10 -0
  387. package/out/tools/fetch/download/index.js.map +1 -0
  388. package/out/tools/fetch/download/manifest.d.ts +47 -0
  389. package/out/tools/fetch/download/manifest.d.ts.map +1 -0
  390. package/out/tools/fetch/download/manifest.js +74 -0
  391. package/out/tools/fetch/download/manifest.js.map +1 -0
  392. package/out/tools/fetch/download/network.d.ts +105 -0
  393. package/out/tools/fetch/download/network.d.ts.map +1 -0
  394. package/out/tools/fetch/download/network.js +130 -0
  395. package/out/tools/fetch/download/network.js.map +1 -0
  396. package/out/tools/fetch/download/retry.d.ts +45 -0
  397. package/out/tools/fetch/download/retry.d.ts.map +1 -0
  398. package/out/tools/fetch/download/retry.js +136 -0
  399. package/out/tools/fetch/download/retry.js.map +1 -0
  400. package/out/tools/fetch/geonames/dump.d.ts +91 -0
  401. package/out/tools/fetch/geonames/dump.d.ts.map +1 -0
  402. package/out/tools/fetch/geonames/dump.js +171 -0
  403. package/out/tools/fetch/geonames/dump.js.map +1 -0
  404. package/out/tools/fetch/geonames/postal.d.ts +76 -0
  405. package/out/tools/fetch/geonames/postal.d.ts.map +1 -0
  406. package/out/tools/fetch/geonames/postal.js +126 -0
  407. package/out/tools/fetch/geonames/postal.js.map +1 -0
  408. package/out/tools/fetch/index.d.ts +30 -30
  409. package/out/tools/fetch/index.d.ts.map +1 -1
  410. package/out/tools/fetch/index.js +30 -30
  411. package/out/tools/fetch/index.js.map +1 -1
  412. package/out/tools/fetch/openaddresses.d.ts +1 -1
  413. package/out/tools/fetch/openaddresses.d.ts.map +1 -1
  414. package/out/tools/fetch/openaddresses.js +1 -1
  415. package/out/tools/fetch/openaddresses.js.map +1 -1
  416. package/out/tools/fetch/ourairports.d.ts +1 -1
  417. package/out/tools/fetch/ourairports.d.ts.map +1 -1
  418. package/out/tools/fetch/ourairports.js +1 -1
  419. package/out/tools/fetch/ourairports.js.map +1 -1
  420. package/out/tools/fetch/ppd.js +1 -3
  421. package/out/tools/fetch/ppd.js.map +1 -1
  422. package/out/tools/fetch/wikidata-subvenue.d.ts +1 -1
  423. package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -1
  424. package/out/tools/fetch/wikidata-subvenue.js +1 -1
  425. package/out/tools/fetch/wikidata-subvenue.js.map +1 -1
  426. package/out/tools/golden/expand.d.ts +90 -0
  427. package/out/tools/golden/expand.d.ts.map +1 -0
  428. package/out/tools/golden/expand.js +406 -0
  429. package/out/tools/golden/expand.js.map +1 -0
  430. package/out/tools/golden/promote.d.ts +72 -0
  431. package/out/tools/golden/promote.d.ts.map +1 -0
  432. package/out/tools/golden/promote.js +243 -0
  433. package/out/tools/golden/promote.js.map +1 -0
  434. package/out/tools/golden/relabel-street/directory.d.ts +83 -0
  435. package/out/tools/golden/relabel-street/directory.d.ts.map +1 -0
  436. package/out/tools/golden/relabel-street/directory.js +216 -0
  437. package/out/tools/golden/relabel-street/directory.js.map +1 -0
  438. package/out/tools/golden/relabel-street/index.d.ts +9 -0
  439. package/out/tools/golden/relabel-street/index.d.ts.map +1 -0
  440. package/out/tools/golden/relabel-street/index.js +9 -0
  441. package/out/tools/golden/relabel-street/index.js.map +1 -0
  442. package/out/tools/golden/relabel-street/row.d.ts +121 -0
  443. package/out/tools/golden/relabel-street/row.d.ts.map +1 -0
  444. package/out/tools/golden/relabel-street/row.js +232 -0
  445. package/out/tools/golden/relabel-street/row.js.map +1 -0
  446. package/out/tools/index.d.ts +10 -10
  447. package/out/tools/index.d.ts.map +1 -1
  448. package/out/tools/index.js +10 -10
  449. package/out/tools/index.js.map +1 -1
  450. package/out/tools/ingest-csv.d.ts.map +1 -1
  451. package/out/tools/ingest-csv.js +5 -7
  452. package/out/tools/ingest-csv.js.map +1 -1
  453. package/out/tools/lint/slice/index.d.ts +93 -0
  454. package/out/tools/lint/slice/index.d.ts.map +1 -0
  455. package/out/tools/lint/slice/index.js +322 -0
  456. package/out/tools/lint/slice/index.js.map +1 -0
  457. package/out/tools/lint/slice/vocab.d.ts +90 -0
  458. package/out/tools/lint/slice/vocab.d.ts.map +1 -0
  459. package/out/tools/lint/slice/vocab.js +254 -0
  460. package/out/tools/lint/slice/vocab.js.map +1 -0
  461. package/out/tools/overlay-manifest.d.ts +56 -6
  462. package/out/tools/overlay-manifest.d.ts.map +1 -1
  463. package/out/tools/overlay-manifest.js +56 -15
  464. package/out/tools/overlay-manifest.js.map +1 -1
  465. package/out/tools/overture-subvenue.d.ts +1 -1
  466. package/out/tools/postcode-triples.d.ts +36 -0
  467. package/out/tools/postcode-triples.d.ts.map +1 -1
  468. package/out/tools/postcode-triples.js +91 -12
  469. package/out/tools/postcode-triples.js.map +1 -1
  470. package/out/tools/slice/kryptonite.d.ts +32 -0
  471. package/out/tools/slice/kryptonite.d.ts.map +1 -0
  472. package/out/tools/slice/kryptonite.js +99 -0
  473. package/out/tools/slice/kryptonite.js.map +1 -0
  474. package/out/tools/slice/translit.d.ts +51 -0
  475. package/out/tools/slice/translit.d.ts.map +1 -0
  476. package/out/tools/slice/translit.js +166 -0
  477. package/out/tools/slice/translit.js.map +1 -0
  478. package/out/tools/sub/venue/harvest.d.ts +100 -0
  479. package/out/tools/sub/venue/harvest.d.ts.map +1 -0
  480. package/out/tools/sub/venue/harvest.js +168 -0
  481. package/out/tools/sub/venue/harvest.js.map +1 -0
  482. package/out/tools/sub/venue/head-nouns.d.ts +50 -0
  483. package/out/tools/sub/venue/head-nouns.d.ts.map +1 -0
  484. package/out/tools/sub/venue/head-nouns.js.map +1 -0
  485. package/out/tools/sub/venue/lexicon.d.ts +156 -0
  486. package/out/tools/sub/venue/lexicon.d.ts.map +1 -0
  487. package/out/tools/sub/venue/lexicon.js +283 -0
  488. package/out/tools/sub/venue/lexicon.js.map +1 -0
  489. package/out/tools/sub/venue/promotions.d.ts +94 -0
  490. package/out/tools/sub/venue/promotions.d.ts.map +1 -0
  491. package/out/tools/sub/venue/promotions.js +266 -0
  492. package/out/tools/sub/venue/promotions.js.map +1 -0
  493. package/out/tools/sub/venue/surfaces.d.ts +45 -0
  494. package/out/tools/sub/venue/surfaces.d.ts.map +1 -0
  495. package/out/tools/sub/venue/surfaces.js.map +1 -0
  496. package/out/tools/sub/venue/table.d.ts +229 -0
  497. package/out/tools/sub/venue/table.d.ts.map +1 -0
  498. package/out/tools/sub/venue/table.js.map +1 -0
  499. package/out/tools/sub/venue/wikidata.d.ts +26 -0
  500. package/out/tools/sub/venue/wikidata.d.ts.map +1 -0
  501. package/out/tools/sub/venue/wikidata.js +62 -0
  502. package/out/tools/sub/venue/wikidata.js.map +1 -0
  503. package/out/tw/tools/fetch/gcis.d.ts +23 -0
  504. package/out/tw/tools/fetch/gcis.d.ts.map +1 -0
  505. package/out/tw/tools/fetch/gcis.js +135 -0
  506. package/out/tw/tools/fetch/gcis.js.map +1 -0
  507. package/out/types.d.ts +1 -1
  508. package/out/types.d.ts.map +1 -1
  509. package/out/us/adapters/fcc-bdc/adapter.d.ts.map +1 -0
  510. package/out/us/adapters/fcc-bdc/adapter.js +142 -0
  511. package/out/us/adapters/fcc-bdc/adapter.js.map +1 -0
  512. package/out/us/adapters/state/hi-schools/adapter.d.ts.map +1 -0
  513. package/out/us/adapters/state/hi-schools/adapter.js +136 -0
  514. package/out/us/adapters/state/hi-schools/adapter.js.map +1 -0
  515. package/out/us/adapters/state/hi-schools/workbook.d.ts.map +1 -0
  516. package/out/us/adapters/state/hi-schools/workbook.js.map +1 -0
  517. package/out/us/adapters/state/ia-contractors/adapter.d.ts.map +1 -0
  518. package/out/us/adapters/state/ia-contractors/adapter.js +104 -0
  519. package/out/us/adapters/state/ia-contractors/adapter.js.map +1 -0
  520. package/out/us/adapters/state/ny-notaries/adapter.d.ts.map +1 -0
  521. package/out/us/adapters/state/ny-notaries/adapter.js +112 -0
  522. package/out/us/adapters/state/ny-notaries/adapter.js.map +1 -0
  523. package/out/us/adapters/state/tx-notaries/adapter.d.ts.map +1 -0
  524. package/out/us/adapters/state/tx-notaries/adapter.js +118 -0
  525. package/out/us/adapters/state/tx-notaries/adapter.js.map +1 -0
  526. package/out/us/adapters/tiger/adapter.d.ts +55 -0
  527. package/out/us/adapters/tiger/adapter.d.ts.map +1 -0
  528. package/out/us/adapters/tiger/adapter.js +197 -0
  529. package/out/us/adapters/tiger/adapter.js.map +1 -0
  530. package/out/us/adapters/tiger/street-decompose.d.ts.map +1 -0
  531. package/out/us/adapters/tiger/street-decompose.js.map +1 -0
  532. package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts.map +1 -0
  533. package/out/us/adapters/usgov/hrsa-fqhc/adapter.js +121 -0
  534. package/out/us/adapters/usgov/hrsa-fqhc/adapter.js.map +1 -0
  535. package/out/us/adapters/usgov/imls-pls/adapter.d.ts.map +1 -0
  536. package/out/us/adapters/usgov/imls-pls/adapter.js +106 -0
  537. package/out/us/adapters/usgov/imls-pls/adapter.js.map +1 -0
  538. package/out/us/adapters/usgov/irs-bmf/adapter.d.ts.map +1 -0
  539. package/out/us/adapters/usgov/irs-bmf/adapter.js +116 -0
  540. package/out/us/adapters/usgov/irs-bmf/adapter.js.map +1 -0
  541. package/out/us/adapters/usgov/nad/adapter.d.ts.map +1 -0
  542. package/out/us/adapters/usgov/nad/adapter.js +239 -0
  543. package/out/us/adapters/usgov/nad/adapter.js.map +1 -0
  544. package/out/us/adapters/usgov/nppes/adapter.d.ts.map +1 -0
  545. package/out/us/adapters/usgov/nppes/adapter.js +110 -0
  546. package/out/us/adapters/usgov/nppes/adapter.js.map +1 -0
  547. package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts.map +1 -0
  548. package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js +143 -0
  549. package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js.map +1 -0
  550. package/out/us/fips-state.d.ts +41 -0
  551. package/out/us/fips-state.d.ts.map +1 -0
  552. package/out/us/fips-state.js +100 -0
  553. package/out/us/fips-state.js.map +1 -0
  554. package/out/us/tools/fetch/hrsa.d.ts +18 -0
  555. package/out/us/tools/fetch/hrsa.d.ts.map +1 -0
  556. package/out/us/tools/fetch/hrsa.js +46 -0
  557. package/out/us/tools/fetch/hrsa.js.map +1 -0
  558. package/out/us/tools/fetch/imls-pls.d.ts +25 -0
  559. package/out/us/tools/fetch/imls-pls.d.ts.map +1 -0
  560. package/out/us/tools/fetch/imls-pls.js +108 -0
  561. package/out/us/tools/fetch/imls-pls.js.map +1 -0
  562. package/out/us/tools/fetch/nad.d.ts +70 -0
  563. package/out/us/tools/fetch/nad.d.ts.map +1 -0
  564. package/out/us/tools/fetch/nad.js +234 -0
  565. package/out/us/tools/fetch/nad.js.map +1 -0
  566. package/out/us/tools/fetch/nppes.d.ts +26 -0
  567. package/out/us/tools/fetch/nppes.d.ts.map +1 -0
  568. package/out/us/tools/fetch/nppes.js +126 -0
  569. package/out/us/tools/fetch/nppes.js.map +1 -0
  570. package/out/us/tools/fetch/state/hi-schools.d.ts +26 -0
  571. package/out/us/tools/fetch/state/hi-schools.d.ts.map +1 -0
  572. package/out/us/tools/fetch/state/hi-schools.js +112 -0
  573. package/out/us/tools/fetch/state/hi-schools.js.map +1 -0
  574. package/out/us/tools/fetch/state/sources.d.ts +26 -0
  575. package/out/us/tools/fetch/state/sources.d.ts.map +1 -0
  576. package/out/us/tools/fetch/state/sources.js +111 -0
  577. package/out/us/tools/fetch/state/sources.js.map +1 -0
  578. package/out/us/tools/fetch/tiger-full.d.ts +22 -0
  579. package/out/us/tools/fetch/tiger-full.d.ts.map +1 -0
  580. package/out/us/tools/fetch/tiger-full.js +217 -0
  581. package/out/us/tools/fetch/tiger-full.js.map +1 -0
  582. package/out/utils/align.d.ts +1 -1
  583. package/out/utils/align.d.ts.map +1 -1
  584. package/out/utils/align.js.map +1 -1
  585. package/out/utils/golden.d.ts +7 -3
  586. package/out/utils/golden.d.ts.map +1 -1
  587. package/out/utils/golden.js +12 -8
  588. package/out/utils/golden.js.map +1 -1
  589. package/out/utils/parquet.d.ts.map +1 -1
  590. package/out/utils/split.js.map +1 -1
  591. package/out/utils/wof-json.d.ts.map +1 -1
  592. package/out/utils/wof-json.js +7 -12
  593. package/out/utils/wof-json.js.map +1 -1
  594. package/out/ve/recipes/reviewed-postcode-tail.d.ts.map +1 -0
  595. package/out/ve/recipes/reviewed-postcode-tail.js.map +1 -0
  596. package/package.json +196 -46
  597. package/lib/adapters/ban/adapter.ts +0 -190
  598. package/lib/adapters/fcc-bdc/adapter.ts +0 -174
  599. package/lib/adapters/geonames-postal/adapter.ts +0 -122
  600. package/lib/adapters/gnaf/adapter.ts +0 -149
  601. package/lib/adapters/gnaf/assemble.ts +0 -225
  602. package/lib/adapters/state-hi-schools/adapter.ts +0 -170
  603. package/lib/adapters/state-ia-contractors/adapter.ts +0 -144
  604. package/lib/adapters/state-ny-notaries/adapter.ts +0 -141
  605. package/lib/adapters/state-tx-notaries/adapter.ts +0 -157
  606. package/lib/adapters/tiger/adapter.ts +0 -252
  607. package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +0 -167
  608. package/lib/adapters/usgov-imls-pls/adapter.ts +0 -143
  609. package/lib/adapters/usgov-irs-bmf/adapter.ts +0 -151
  610. package/lib/adapters/usgov-nad/adapter.ts +0 -334
  611. package/lib/adapters/usgov-nppes/adapter.ts +0 -151
  612. package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -193
  613. package/lib/adapters/wof-admin-json/adapter.ts +0 -231
  614. package/lib/adapters/wof-json-rows.ts +0 -129
  615. package/lib/adapters/wof-postalcode-json/adapter.ts +0 -176
  616. package/lib/recipes/fr-admin-split.ts +0 -243
  617. package/lib/recipes/fr-bare-street.ts +0 -171
  618. package/lib/recipes/fr-fragment.ts +0 -334
  619. package/lib/recipes/fr-lieudit.ts +0 -301
  620. package/lib/recipes/fr-order.ts +0 -246
  621. package/lib/recipes/german.ts +0 -360
  622. package/lib/recipes/locale.ts +0 -600
  623. package/lib/recipes/po-box-cedex.ts +0 -976
  624. package/lib/recipes/po-box.ts +0 -124
  625. package/lib/recipes/street-affix.ts +0 -805
  626. package/lib/recipes/sub-venue-sources.ts +0 -878
  627. package/lib/recipes/sub-venue.ts +0 -998
  628. package/lib/synthesizers/german.ts +0 -260
  629. package/lib/tools/fetch/acra-sg.ts +0 -174
  630. package/lib/tools/fetch/ban.ts +0 -289
  631. package/lib/tools/fetch/download.ts +0 -477
  632. package/lib/tools/fetch/gcis-tw.ts +0 -175
  633. package/lib/tools/fetch/geonames-dump.ts +0 -257
  634. package/lib/tools/fetch/geonames-postal.ts +0 -180
  635. package/lib/tools/fetch/houjin-jp.ts +0 -135
  636. package/lib/tools/fetch/hrsa.ts +0 -59
  637. package/lib/tools/fetch/imls-pls.ts +0 -149
  638. package/lib/tools/fetch/juso-kr.ts +0 -165
  639. package/lib/tools/fetch/localdata-kr.ts +0 -194
  640. package/lib/tools/fetch/nad.ts +0 -341
  641. package/lib/tools/fetch/nppes.ts +0 -165
  642. package/lib/tools/fetch/state-hi-schools.ts +0 -161
  643. package/lib/tools/fetch/state-sources.ts +0 -146
  644. package/lib/tools/fetch/tiger-full.ts +0 -308
  645. package/lib/tools/golden-promote.ts +0 -337
  646. package/lib/tools/golden-relabel-street.ts +0 -686
  647. package/lib/tools/lint-slice-vocab.ts +0 -388
  648. package/lib/tools/sub-venue/harvest.ts +0 -234
  649. package/lib/tools/sub-venue/head-nouns.ts +0 -245
  650. package/lib/tools/sub-venue/surfaces.ts +0 -95
  651. package/lib/tools/sub-venue/table.ts +0 -281
  652. package/lib/tools/sub-venue/wikidata.ts +0 -85
  653. package/lib/tools/sub-venue-lexicon.ts +0 -429
  654. package/out/adapters/ban/adapter.d.ts.map +0 -1
  655. package/out/adapters/ban/adapter.js +0 -149
  656. package/out/adapters/ban/adapter.js.map +0 -1
  657. package/out/adapters/ban/street-decompose.d.ts.map +0 -1
  658. package/out/adapters/ban/street-decompose.js.map +0 -1
  659. package/out/adapters/fcc-bdc/adapter.d.ts.map +0 -1
  660. package/out/adapters/fcc-bdc/adapter.js +0 -144
  661. package/out/adapters/fcc-bdc/adapter.js.map +0 -1
  662. package/out/adapters/geonames-postal/adapter.d.ts.map +0 -1
  663. package/out/adapters/geonames-postal/adapter.js +0 -107
  664. package/out/adapters/geonames-postal/adapter.js.map +0 -1
  665. package/out/adapters/gnaf/adapter.d.ts.map +0 -1
  666. package/out/adapters/gnaf/adapter.js +0 -124
  667. package/out/adapters/gnaf/adapter.js.map +0 -1
  668. package/out/adapters/gnaf/assemble.d.ts +0 -65
  669. package/out/adapters/gnaf/assemble.d.ts.map +0 -1
  670. package/out/adapters/gnaf/assemble.js +0 -154
  671. package/out/adapters/gnaf/assemble.js.map +0 -1
  672. package/out/adapters/state-hi-schools/adapter.d.ts.map +0 -1
  673. package/out/adapters/state-hi-schools/adapter.js +0 -145
  674. package/out/adapters/state-hi-schools/adapter.js.map +0 -1
  675. package/out/adapters/state-hi-schools/workbook.d.ts.map +0 -1
  676. package/out/adapters/state-hi-schools/workbook.js.map +0 -1
  677. package/out/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
  678. package/out/adapters/state-ia-contractors/adapter.js +0 -111
  679. package/out/adapters/state-ia-contractors/adapter.js.map +0 -1
  680. package/out/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
  681. package/out/adapters/state-ny-notaries/adapter.js +0 -119
  682. package/out/adapters/state-ny-notaries/adapter.js.map +0 -1
  683. package/out/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
  684. package/out/adapters/state-tx-notaries/adapter.js +0 -125
  685. package/out/adapters/state-tx-notaries/adapter.js.map +0 -1
  686. package/out/adapters/tiger/adapter.d.ts +0 -55
  687. package/out/adapters/tiger/adapter.d.ts.map +0 -1
  688. package/out/adapters/tiger/adapter.js +0 -201
  689. package/out/adapters/tiger/adapter.js.map +0 -1
  690. package/out/adapters/tiger/street-decompose.d.ts.map +0 -1
  691. package/out/adapters/tiger/street-decompose.js.map +0 -1
  692. package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
  693. package/out/adapters/usgov-hrsa-fqhc/adapter.js +0 -132
  694. package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
  695. package/out/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
  696. package/out/adapters/usgov-imls-pls/adapter.js +0 -114
  697. package/out/adapters/usgov-imls-pls/adapter.js.map +0 -1
  698. package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
  699. package/out/adapters/usgov-irs-bmf/adapter.js +0 -120
  700. package/out/adapters/usgov-irs-bmf/adapter.js.map +0 -1
  701. package/out/adapters/usgov-nad/adapter.d.ts.map +0 -1
  702. package/out/adapters/usgov-nad/adapter.js +0 -249
  703. package/out/adapters/usgov-nad/adapter.js.map +0 -1
  704. package/out/adapters/usgov-nppes/adapter.d.ts.map +0 -1
  705. package/out/adapters/usgov-nppes/adapter.js +0 -118
  706. package/out/adapters/usgov-nppes/adapter.js.map +0 -1
  707. package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
  708. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -154
  709. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
  710. package/out/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
  711. package/out/adapters/wof-admin-jp/adapter.js.map +0 -1
  712. package/out/adapters/wof-admin-json/adapter.d.ts +0 -79
  713. package/out/adapters/wof-admin-json/adapter.d.ts.map +0 -1
  714. package/out/adapters/wof-admin-json/adapter.js +0 -197
  715. package/out/adapters/wof-admin-json/adapter.js.map +0 -1
  716. package/out/adapters/wof-json-rows.d.ts +0 -62
  717. package/out/adapters/wof-json-rows.d.ts.map +0 -1
  718. package/out/adapters/wof-json-rows.js +0 -83
  719. package/out/adapters/wof-json-rows.js.map +0 -1
  720. package/out/adapters/wof-postalcode-json/adapter.d.ts +0 -65
  721. package/out/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
  722. package/out/adapters/wof-postalcode-json/adapter.js +0 -151
  723. package/out/adapters/wof-postalcode-json/adapter.js.map +0 -1
  724. package/out/codex/us-fips-state.d.ts +0 -41
  725. package/out/codex/us-fips-state.d.ts.map +0 -1
  726. package/out/codex/us-fips-state.js +0 -100
  727. package/out/codex/us-fips-state.js.map +0 -1
  728. package/out/recipes/bare-country.d.ts +0 -25
  729. package/out/recipes/bare-country.d.ts.map +0 -1
  730. package/out/recipes/bare-country.js +0 -88
  731. package/out/recipes/bare-country.js.map +0 -1
  732. package/out/recipes/cn-organizational-units.d.ts +0 -36
  733. package/out/recipes/cn-organizational-units.d.ts.map +0 -1
  734. package/out/recipes/cn-organizational-units.js +0 -159
  735. package/out/recipes/cn-organizational-units.js.map +0 -1
  736. package/out/recipes/cz-pcfirst-preposition.d.ts +0 -22
  737. package/out/recipes/cz-pcfirst-preposition.d.ts.map +0 -1
  738. package/out/recipes/cz-pcfirst-preposition.js +0 -101
  739. package/out/recipes/cz-pcfirst-preposition.js.map +0 -1
  740. package/out/recipes/fr-admin-split.d.ts +0 -38
  741. package/out/recipes/fr-admin-split.d.ts.map +0 -1
  742. package/out/recipes/fr-admin-split.js +0 -192
  743. package/out/recipes/fr-admin-split.js.map +0 -1
  744. package/out/recipes/fr-bare-street.d.ts +0 -28
  745. package/out/recipes/fr-bare-street.d.ts.map +0 -1
  746. package/out/recipes/fr-bare-street.js +0 -144
  747. package/out/recipes/fr-bare-street.js.map +0 -1
  748. package/out/recipes/fr-fragment.d.ts +0 -77
  749. package/out/recipes/fr-fragment.d.ts.map +0 -1
  750. package/out/recipes/fr-fragment.js +0 -277
  751. package/out/recipes/fr-fragment.js.map +0 -1
  752. package/out/recipes/fr-lieudit.d.ts +0 -32
  753. package/out/recipes/fr-lieudit.d.ts.map +0 -1
  754. package/out/recipes/fr-lieudit.js +0 -227
  755. package/out/recipes/fr-lieudit.js.map +0 -1
  756. package/out/recipes/fr-order.d.ts +0 -38
  757. package/out/recipes/fr-order.d.ts.map +0 -1
  758. package/out/recipes/fr-order.js +0 -198
  759. package/out/recipes/fr-order.js.map +0 -1
  760. package/out/recipes/german.d.ts +0 -44
  761. package/out/recipes/german.d.ts.map +0 -1
  762. package/out/recipes/german.js +0 -289
  763. package/out/recipes/german.js.map +0 -1
  764. package/out/recipes/locale.d.ts +0 -136
  765. package/out/recipes/locale.d.ts.map +0 -1
  766. package/out/recipes/locale.js +0 -460
  767. package/out/recipes/locale.js.map +0 -1
  768. package/out/recipes/nl-postcode.d.ts +0 -26
  769. package/out/recipes/nl-postcode.d.ts.map +0 -1
  770. package/out/recipes/nl-postcode.js +0 -103
  771. package/out/recipes/nl-postcode.js.map +0 -1
  772. package/out/recipes/no-fragment.d.ts +0 -43
  773. package/out/recipes/no-fragment.d.ts.map +0 -1
  774. package/out/recipes/no-fragment.js +0 -183
  775. package/out/recipes/no-fragment.js.map +0 -1
  776. package/out/recipes/no-street-led.d.ts +0 -24
  777. package/out/recipes/no-street-led.d.ts.map +0 -1
  778. package/out/recipes/no-street-led.js +0 -114
  779. package/out/recipes/no-street-led.js.map +0 -1
  780. package/out/recipes/no-street.d.ts +0 -18
  781. package/out/recipes/no-street.d.ts.map +0 -1
  782. package/out/recipes/no-street.js +0 -72
  783. package/out/recipes/no-street.js.map +0 -1
  784. package/out/recipes/po-box-cedex.d.ts +0 -38
  785. package/out/recipes/po-box-cedex.d.ts.map +0 -1
  786. package/out/recipes/po-box-cedex.js +0 -768
  787. package/out/recipes/po-box-cedex.js.map +0 -1
  788. package/out/recipes/po-box.d.ts +0 -17
  789. package/out/recipes/po-box.d.ts.map +0 -1
  790. package/out/recipes/po-box.js +0 -101
  791. package/out/recipes/po-box.js.map +0 -1
  792. package/out/recipes/reviewed-postcode-tail.d.ts.map +0 -1
  793. package/out/recipes/reviewed-postcode-tail.js.map +0 -1
  794. package/out/recipes/si-bare-village.d.ts +0 -32
  795. package/out/recipes/si-bare-village.d.ts.map +0 -1
  796. package/out/recipes/si-bare-village.js +0 -89
  797. package/out/recipes/si-bare-village.js.map +0 -1
  798. package/out/recipes/street-affix.d.ts +0 -89
  799. package/out/recipes/street-affix.d.ts.map +0 -1
  800. package/out/recipes/street-affix.js +0 -563
  801. package/out/recipes/street-affix.js.map +0 -1
  802. package/out/recipes/street-bare.d.ts +0 -25
  803. package/out/recipes/street-bare.d.ts.map +0 -1
  804. package/out/recipes/street-bare.js +0 -87
  805. package/out/recipes/street-bare.js.map +0 -1
  806. package/out/recipes/sub-venue-sources.d.ts +0 -229
  807. package/out/recipes/sub-venue-sources.d.ts.map +0 -1
  808. package/out/recipes/sub-venue-sources.js +0 -654
  809. package/out/recipes/sub-venue-sources.js.map +0 -1
  810. package/out/recipes/sub-venue.d.ts +0 -269
  811. package/out/recipes/sub-venue.d.ts.map +0 -1
  812. package/out/recipes/sub-venue.js +0 -726
  813. package/out/recipes/sub-venue.js.map +0 -1
  814. package/out/synthesizers/german.d.ts +0 -115
  815. package/out/synthesizers/german.d.ts.map +0 -1
  816. package/out/synthesizers/german.js +0 -149
  817. package/out/synthesizers/german.js.map +0 -1
  818. package/out/tools/fetch/acra-sg.d.ts +0 -23
  819. package/out/tools/fetch/acra-sg.d.ts.map +0 -1
  820. package/out/tools/fetch/acra-sg.js +0 -126
  821. package/out/tools/fetch/acra-sg.js.map +0 -1
  822. package/out/tools/fetch/ban.d.ts +0 -31
  823. package/out/tools/fetch/ban.d.ts.map +0 -1
  824. package/out/tools/fetch/ban.js +0 -239
  825. package/out/tools/fetch/ban.js.map +0 -1
  826. package/out/tools/fetch/download.d.ts +0 -182
  827. package/out/tools/fetch/download.d.ts.map +0 -1
  828. package/out/tools/fetch/download.js +0 -318
  829. package/out/tools/fetch/download.js.map +0 -1
  830. package/out/tools/fetch/gcis-tw.d.ts +0 -23
  831. package/out/tools/fetch/gcis-tw.d.ts.map +0 -1
  832. package/out/tools/fetch/gcis-tw.js +0 -135
  833. package/out/tools/fetch/gcis-tw.js.map +0 -1
  834. package/out/tools/fetch/geonames-dump.d.ts +0 -91
  835. package/out/tools/fetch/geonames-dump.d.ts.map +0 -1
  836. package/out/tools/fetch/geonames-dump.js +0 -171
  837. package/out/tools/fetch/geonames-dump.js.map +0 -1
  838. package/out/tools/fetch/geonames-postal.d.ts +0 -76
  839. package/out/tools/fetch/geonames-postal.d.ts.map +0 -1
  840. package/out/tools/fetch/geonames-postal.js +0 -126
  841. package/out/tools/fetch/geonames-postal.js.map +0 -1
  842. package/out/tools/fetch/houjin-jp.d.ts +0 -24
  843. package/out/tools/fetch/houjin-jp.d.ts.map +0 -1
  844. package/out/tools/fetch/houjin-jp.js +0 -102
  845. package/out/tools/fetch/houjin-jp.js.map +0 -1
  846. package/out/tools/fetch/hrsa.d.ts +0 -18
  847. package/out/tools/fetch/hrsa.d.ts.map +0 -1
  848. package/out/tools/fetch/hrsa.js +0 -46
  849. package/out/tools/fetch/hrsa.js.map +0 -1
  850. package/out/tools/fetch/imls-pls.d.ts +0 -25
  851. package/out/tools/fetch/imls-pls.d.ts.map +0 -1
  852. package/out/tools/fetch/imls-pls.js +0 -108
  853. package/out/tools/fetch/imls-pls.js.map +0 -1
  854. package/out/tools/fetch/juso-kr.d.ts +0 -30
  855. package/out/tools/fetch/juso-kr.d.ts.map +0 -1
  856. package/out/tools/fetch/juso-kr.js +0 -120
  857. package/out/tools/fetch/juso-kr.js.map +0 -1
  858. package/out/tools/fetch/localdata-kr.d.ts +0 -30
  859. package/out/tools/fetch/localdata-kr.d.ts.map +0 -1
  860. package/out/tools/fetch/localdata-kr.js +0 -139
  861. package/out/tools/fetch/localdata-kr.js.map +0 -1
  862. package/out/tools/fetch/nad.d.ts +0 -70
  863. package/out/tools/fetch/nad.d.ts.map +0 -1
  864. package/out/tools/fetch/nad.js +0 -234
  865. package/out/tools/fetch/nad.js.map +0 -1
  866. package/out/tools/fetch/nppes.d.ts +0 -26
  867. package/out/tools/fetch/nppes.d.ts.map +0 -1
  868. package/out/tools/fetch/nppes.js +0 -126
  869. package/out/tools/fetch/nppes.js.map +0 -1
  870. package/out/tools/fetch/state-hi-schools.d.ts +0 -26
  871. package/out/tools/fetch/state-hi-schools.d.ts.map +0 -1
  872. package/out/tools/fetch/state-hi-schools.js +0 -112
  873. package/out/tools/fetch/state-hi-schools.js.map +0 -1
  874. package/out/tools/fetch/state-sources.d.ts +0 -26
  875. package/out/tools/fetch/state-sources.d.ts.map +0 -1
  876. package/out/tools/fetch/state-sources.js +0 -111
  877. package/out/tools/fetch/state-sources.js.map +0 -1
  878. package/out/tools/fetch/tiger-full.d.ts +0 -22
  879. package/out/tools/fetch/tiger-full.d.ts.map +0 -1
  880. package/out/tools/fetch/tiger-full.js +0 -217
  881. package/out/tools/fetch/tiger-full.js.map +0 -1
  882. package/out/tools/golden-expand.d.ts +0 -90
  883. package/out/tools/golden-expand.d.ts.map +0 -1
  884. package/out/tools/golden-expand.js +0 -406
  885. package/out/tools/golden-expand.js.map +0 -1
  886. package/out/tools/golden-promote.d.ts +0 -72
  887. package/out/tools/golden-promote.d.ts.map +0 -1
  888. package/out/tools/golden-promote.js +0 -240
  889. package/out/tools/golden-promote.js.map +0 -1
  890. package/out/tools/golden-relabel-street.d.ts +0 -196
  891. package/out/tools/golden-relabel-street.d.ts.map +0 -1
  892. package/out/tools/golden-relabel-street.js +0 -439
  893. package/out/tools/golden-relabel-street.js.map +0 -1
  894. package/out/tools/lint-slice-vocab.d.ts +0 -90
  895. package/out/tools/lint-slice-vocab.d.ts.map +0 -1
  896. package/out/tools/lint-slice-vocab.js +0 -267
  897. package/out/tools/lint-slice-vocab.js.map +0 -1
  898. package/out/tools/lint-slice.d.ts +0 -93
  899. package/out/tools/lint-slice.d.ts.map +0 -1
  900. package/out/tools/lint-slice.js +0 -322
  901. package/out/tools/lint-slice.js.map +0 -1
  902. package/out/tools/slice-kryptonite.d.ts +0 -32
  903. package/out/tools/slice-kryptonite.d.ts.map +0 -1
  904. package/out/tools/slice-kryptonite.js +0 -99
  905. package/out/tools/slice-kryptonite.js.map +0 -1
  906. package/out/tools/slice-translit.d.ts +0 -51
  907. package/out/tools/slice-translit.d.ts.map +0 -1
  908. package/out/tools/slice-translit.js +0 -166
  909. package/out/tools/slice-translit.js.map +0 -1
  910. package/out/tools/sub-venue/harvest.d.ts +0 -100
  911. package/out/tools/sub-venue/harvest.d.ts.map +0 -1
  912. package/out/tools/sub-venue/harvest.js +0 -168
  913. package/out/tools/sub-venue/harvest.js.map +0 -1
  914. package/out/tools/sub-venue/head-nouns.d.ts +0 -50
  915. package/out/tools/sub-venue/head-nouns.d.ts.map +0 -1
  916. package/out/tools/sub-venue/head-nouns.js.map +0 -1
  917. package/out/tools/sub-venue/surfaces.d.ts +0 -45
  918. package/out/tools/sub-venue/surfaces.d.ts.map +0 -1
  919. package/out/tools/sub-venue/surfaces.js.map +0 -1
  920. package/out/tools/sub-venue/table.d.ts +0 -229
  921. package/out/tools/sub-venue/table.d.ts.map +0 -1
  922. package/out/tools/sub-venue/table.js.map +0 -1
  923. package/out/tools/sub-venue/wikidata.d.ts +0 -26
  924. package/out/tools/sub-venue/wikidata.d.ts.map +0 -1
  925. package/out/tools/sub-venue/wikidata.js +0 -62
  926. package/out/tools/sub-venue/wikidata.js.map +0 -1
  927. package/out/tools/sub-venue-lexicon.d.ts +0 -156
  928. package/out/tools/sub-venue-lexicon.d.ts.map +0 -1
  929. package/out/tools/sub-venue-lexicon.js +0 -283
  930. package/out/tools/sub-venue-lexicon.js.map +0 -1
  931. package/out/tools/sub-venue-promotions.d.ts +0 -94
  932. package/out/tools/sub-venue-promotions.d.ts.map +0 -1
  933. package/out/tools/sub-venue-promotions.js +0 -266
  934. package/out/tools/sub-venue-promotions.js.map +0 -1
  935. /package/lib/{recipes/cn-organizational-units.ts → cn/recipes/organizational-units.ts} +0 -0
  936. /package/lib/{recipes/cz-pcfirst-preposition.ts → cz/recipes/pcfirst-preposition.ts} +0 -0
  937. /package/lib/{adapters → fr/adapters}/ban/street-decompose.ts +0 -0
  938. /package/lib/{adapters/wof-admin-jp → jp/adapters/wof-admin}/adapter.ts +0 -0
  939. /package/lib/{recipes/nl-postcode.ts → nl/recipes/postcode.ts} +0 -0
  940. /package/lib/{recipes/no-fragment.ts → no/recipes/fragment.ts} +0 -0
  941. /package/lib/{recipes/no-street.ts → no/recipes/street/index.ts} +0 -0
  942. /package/lib/{recipes/no-street-led.ts → no/recipes/street/led.ts} +0 -0
  943. /package/lib/recipes/{bare-country.ts → bare/country.ts} +0 -0
  944. /package/lib/recipes/{street-bare.ts → street/bare.ts} +0 -0
  945. /package/lib/{recipes/si-bare-village.ts → si/recipes/bare-village.ts} +0 -0
  946. /package/lib/tools/{golden-expand.ts → golden/expand.ts} +0 -0
  947. /package/lib/tools/{lint-slice.ts → lint/slice/index.ts} +0 -0
  948. /package/lib/tools/{slice-kryptonite.ts → slice/kryptonite.ts} +0 -0
  949. /package/lib/tools/{slice-translit.ts → slice/translit.ts} +0 -0
  950. /package/lib/tools/{sub-venue-promotions.ts → sub/venue/promotions.ts} +0 -0
  951. /package/lib/{adapters/state-hi-schools → us/adapters/state/hi-schools}/workbook.ts +0 -0
  952. /package/lib/{adapters → us/adapters}/tiger/street-decompose.ts +0 -0
  953. /package/lib/{codex/us-fips-state.ts → us/fips-state.ts} +0 -0
  954. /package/lib/{recipes → ve/recipes}/reviewed-postcode-tail.ts +0 -0
  955. /package/out/adapters/{geonames-postal → geonames/postal}/adapter.d.ts +0 -0
  956. /package/out/{adapters → au/adapters}/gnaf/adapter.d.ts +0 -0
  957. /package/out/{adapters → fr/adapters}/ban/adapter.d.ts +0 -0
  958. /package/out/{adapters → fr/adapters}/ban/street-decompose.d.ts +0 -0
  959. /package/out/{adapters → fr/adapters}/ban/street-decompose.js +0 -0
  960. /package/out/{adapters/wof-admin-jp → jp/adapters/wof-admin}/adapter.d.ts +0 -0
  961. /package/out/{adapters/wof-admin-jp → jp/adapters/wof-admin}/adapter.js +0 -0
  962. /package/out/tools/{sub-venue → sub/venue}/head-nouns.js +0 -0
  963. /package/out/tools/{sub-venue → sub/venue}/surfaces.js +0 -0
  964. /package/out/tools/{sub-venue → sub/venue}/table.js +0 -0
  965. /package/out/{adapters → us/adapters}/fcc-bdc/adapter.d.ts +0 -0
  966. /package/out/{adapters/state-hi-schools → us/adapters/state/hi-schools}/adapter.d.ts +0 -0
  967. /package/out/{adapters/state-hi-schools → us/adapters/state/hi-schools}/workbook.d.ts +0 -0
  968. /package/out/{adapters/state-hi-schools → us/adapters/state/hi-schools}/workbook.js +0 -0
  969. /package/out/{adapters/state-ia-contractors → us/adapters/state/ia-contractors}/adapter.d.ts +0 -0
  970. /package/out/{adapters/state-ny-notaries → us/adapters/state/ny-notaries}/adapter.d.ts +0 -0
  971. /package/out/{adapters/state-tx-notaries → us/adapters/state/tx-notaries}/adapter.d.ts +0 -0
  972. /package/out/{adapters → us/adapters}/tiger/street-decompose.d.ts +0 -0
  973. /package/out/{adapters → us/adapters}/tiger/street-decompose.js +0 -0
  974. /package/out/{adapters/usgov-hrsa-fqhc → us/adapters/usgov/hrsa-fqhc}/adapter.d.ts +0 -0
  975. /package/out/{adapters/usgov-imls-pls → us/adapters/usgov/imls-pls}/adapter.d.ts +0 -0
  976. /package/out/{adapters/usgov-irs-bmf → us/adapters/usgov/irs-bmf}/adapter.d.ts +0 -0
  977. /package/out/{adapters/usgov-nad → us/adapters/usgov/nad}/adapter.d.ts +0 -0
  978. /package/out/{adapters/usgov-nppes → us/adapters/usgov/nppes}/adapter.d.ts +0 -0
  979. /package/out/{adapters/usgov-samhsa-treatment-locator → us/adapters/usgov/samhsa-treatment-locator}/adapter.d.ts +0 -0
  980. /package/out/{recipes → ve/recipes}/reviewed-postcode-tail.d.ts +0 -0
  981. /package/out/{recipes → ve/recipes}/reviewed-postcode-tail.js +0 -0
@@ -0,0 +1,62 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ *
6
+ * @file The Wikidata leg of the sub-venue lexicon — turning the designator-label SPARQL payload into
7
+ * surfaces.
8
+ *
9
+ * Reads an already-parsed payload rather than issuing a query: the acquisition lives in
10
+ * `fetch/wikidata-subvenue.ts`, and keeping the conversion a pure function of parsed input is what
11
+ * lets the builder stay deterministic and testable with no network and no fixture on disk.
12
+ *
13
+ * Wikidata gives a CONCEPT NAME per language, not a designator as addressed. Q849706's Spanish label
14
+ * is `terminal aeroportuaria`; the addressed form is `Terminal`. So every surface produced here lands
15
+ * `curated: false`, and the head-noun derivation is what proposes the addressed form from it.
16
+ */
17
+ import { normalizeSurface } from "#tools/sub/venue/surfaces";
18
+ import { CONCEPT_QIDS } from "#tools/sub/venue/table";
19
+ /**
20
+ * Turn the Wikidata designator-label payload into surfaces.
21
+ *
22
+ * A row is dropped when its language tag is empty (an untagged literal, which Wikidata occasionally carries), when the
23
+ * QID maps to no designator in {@link CONCEPT_QIDS}, or when the normalized phrase is empty. Everything that survives
24
+ * lands `curated: false` — see the module docstring.
25
+ */
26
+ export function surfacesFromWikidata(payload, conceptQIDs = CONCEPT_QIDS) {
27
+ const byQID = new Map(Object.entries(conceptQIDs).map(([id, qid]) => [qid, id]));
28
+ const envelope = payload;
29
+ const seen = new Set();
30
+ const out = [];
31
+ for (const binding of envelope.results?.bindings ?? []) {
32
+ const qid = binding.item?.value?.split("/").pop();
33
+ const recordID = qid ? byQID.get(qid) : undefined;
34
+ const lang = binding.lang?.value;
35
+ const raw = binding.label?.value;
36
+ if (!recordID || !lang || !raw)
37
+ continue;
38
+ const phrase = normalizeSurface(raw);
39
+ if (!phrase)
40
+ continue;
41
+ const source = binding.kind?.value === "alt" ? "wikidata:alt" : "wikidata:label";
42
+ // A concept can carry the same string as both a label and an alias, and across dialect subtags
43
+ // (`zh`, `zh-cn`, `zh-hans` all say 航站楼). Key the dedupe on the tuple that identifies a row.
44
+ const key = `${phrase}\0${recordID}\0${lang}\0${source}`;
45
+ if (seen.has(key))
46
+ continue;
47
+ seen.add(key);
48
+ out.push({
49
+ phrase,
50
+ recordID,
51
+ recordKind: "designator",
52
+ lang,
53
+ region: "",
54
+ source,
55
+ curated: false,
56
+ observations: 0,
57
+ context: {},
58
+ });
59
+ }
60
+ return out;
61
+ }
62
+ //# sourceMappingURL=wikidata.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"wikidata.js","sourceRoot":"","sources":["../../../../lib/tools/sub/venue/wikidata.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;GAeG;AAEH,OAAO,EAAE,gBAAgB,EAAE,MAAM,2BAA2B,CAAA;AAC5D,OAAO,EAAE,YAAY,EAAwB,MAAM,wBAAwB,CAAA;AAgB3E;;;;;;GAMG;AACH,MAAM,UAAU,oBAAoB,CACnC,OAAgB,EAChB,WAAW,GAAqC,YAAY;IAE5D,MAAM,KAAK,GAAG,IAAI,GAAG,CAAC,MAAM,CAAC,OAAO,CAAC,WAAW,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,GAAG,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,CAAC,CAAC,CAAA;IAChF,MAAM,QAAQ,GAAG,OAAyB,CAAA;IAC1C,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAA;IAC9B,MAAM,GAAG,GAAsB,EAAE,CAAA;IAEjC,KAAK,MAAM,OAAO,IAAI,QAAQ,CAAC,OAAO,EAAE,QAAQ,IAAI,EAAE,EAAE,CAAC;QACxD,MAAM,GAAG,GAAG,OAAO,CAAC,IAAI,EAAE,KAAK,EAAE,KAAK,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,CAAA;QACjD,MAAM,QAAQ,GAAG,GAAG,CAAC,CAAC,CAAC,KAAK,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,SAAS,CAAA;QACjD,MAAM,IAAI,GAAG,OAAO,CAAC,IAAI,EAAE,KAAK,CAAA;QAChC,MAAM,GAAG,GAAG,OAAO,CAAC,KAAK,EAAE,KAAK,CAAA;QAEhC,IAAI,CAAC,QAAQ,IAAI,CAAC,IAAI,IAAI,CAAC,GAAG;YAAE,SAAQ;QAExC,MAAM,MAAM,GAAG,gBAAgB,CAAC,GAAG,CAAC,CAAA;QAEpC,IAAI,CAAC,MAAM;YAAE,SAAQ;QAErB,MAAM,MAAM,GAAG,OAAO,CAAC,IAAI,EAAE,KAAK,KAAK,KAAK,CAAC,CAAC,CAAC,cAAc,CAAC,CAAC,CAAC,gBAAgB,CAAA;QAChF,+FAA+F;QAC/F,6FAA6F;QAC7F,MAAM,GAAG,GAAG,GAAG,MAAM,KAAK,QAAQ,KAAK,IAAI,KAAK,MAAM,EAAE,CAAA;QAExD,IAAI,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC;YAAE,SAAQ;QAC3B,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;QAEb,GAAG,CAAC,IAAI,CAAC;YACR,MAAM;YACN,QAAQ;YACR,UAAU,EAAE,YAAY;YACxB,IAAI;YACJ,MAAM,EAAE,EAAE;YACV,MAAM;YACN,OAAO,EAAE,KAAK;YACd,YAAY,EAAE,CAAC;YACf,OAAO,EAAE,EAAE;SACX,CAAC,CAAA;IACH,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC"}
@@ -0,0 +1,23 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ *
6
+ * Fetch Taiwan's company and business registers (公司登記資料, 商業登記資料) from the Ministry of
7
+ * Economic Affairs' commerce open-data platform, data.gcis.nat.gov.tw. The platform publishes the
8
+ * full registers as CSV files split by region (the six special municipalities each on their own,
9
+ * the rest of the island in four bands) and by industry letter, 148 files in all, each row carrying
10
+ * the registered address (公司地址) and, for companies, the tax office's business address
11
+ * (營業地址) as free text. This is the NOISY source for Taiwanese addresses: a person typed these.
12
+ *
13
+ * License: 政府資料開放授權條款-第1版 (Open Government Data License, Taiwan, v1.0). The platform's
14
+ * own dialog states the condition that binds: attribution in the form it prescribes, or the grant is
15
+ * void from the start ("未盡顯名標示義務者,視為自始未取得開放資料之授權"). The manifest records the
16
+ * prescribed wording per file so the corpus build and the model card can carry it.
17
+ *
18
+ * Invoke via `mailwoman corpus fetch gcis-tw --out-root <path>`.
19
+ */
20
+ import type { BaseFetchOptions, FetchSummary } from "#tools/fetch/download/index";
21
+ export type FetchGCISTWOptions = BaseFetchOptions;
22
+ export declare function fetchGCISTW(options: FetchGCISTWOptions, report?: (line: string) => void): Promise<FetchSummary>;
23
+ //# sourceMappingURL=gcis.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"gcis.d.ts","sourceRoot":"","sources":["../../../../lib/tw/tools/fetch/gcis.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;GAkBG;AASH,OAAO,KAAK,EACX,gBAAgB,EAChB,YAAY,EAGZ,MAAM,6BAA6B,CAAA;AAgBpC,MAAM,MAAM,kBAAkB,GAAG,gBAAgB,CAAA;AA+CjD,wBAAsB,WAAW,CAAC,OAAO,EAAE,kBAAkB,EAAE,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAAG,OAAO,CAAC,YAAY,CAAC,CAoFrH"}
@@ -0,0 +1,135 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ *
6
+ * Fetch Taiwan's company and business registers (公司登記資料, 商業登記資料) from the Ministry of
7
+ * Economic Affairs' commerce open-data platform, data.gcis.nat.gov.tw. The platform publishes the
8
+ * full registers as CSV files split by region (the six special municipalities each on their own,
9
+ * the rest of the island in four bands) and by industry letter, 148 files in all, each row carrying
10
+ * the registered address (公司地址) and, for companies, the tax office's business address
11
+ * (營業地址) as free text. This is the NOISY source for Taiwanese addresses: a person typed these.
12
+ *
13
+ * License: 政府資料開放授權條款-第1版 (Open Government Data License, Taiwan, v1.0). The platform's
14
+ * own dialog states the condition that binds: attribution in the form it prescribes, or the grant is
15
+ * void from the start ("未盡顯名標示義務者,視為自始未取得開放資料之授權"). The manifest records the
16
+ * prescribed wording per file so the corpus build and the model card can carry it.
17
+ *
18
+ * Invoke via `mailwoman corpus fetch gcis-tw --out-root <path>`.
19
+ */
20
+ import { BYTES_PER_KIB } from "@mailwoman/core/fs/formatters";
21
+ import { pathExists } from "@mailwoman/core/fs/readers";
22
+ import { makeDirectories } from "@mailwoman/core/fs/writers";
23
+ import { sha256File } from "@mailwoman/core/hash";
24
+ import { sleep } from "@mailwoman/core/utils/sleep";
25
+ import { join } from "path-ts";
26
+ import { loadCollectionFiles, streamBodyToFile, withRetries, writeManifest } from "#tools/fetch/download/index";
27
+ const SLUG = "gcis-tw";
28
+ const PORTAL = "https://data.gcis.nat.gov.tw";
29
+ const CATALOG_URL = `${PORTAL}/od/datacategory`;
30
+ const LICENSE = "政府資料開放授權條款-第1版 (Open Government Data License, Taiwan, v1.0) — http://data.gov.tw/license";
31
+ const ATTRIBUTION = "提供機關/經濟部商業發展署 [<dataset title>] — the 顯名聲明 each file's dialog prescribes";
32
+ const PACE_MS = 300;
33
+ /**
34
+ * The bulk register files: `<region><register>資料-<industry letter><industry>`. The per-industry API datasets and the
35
+ * monthly new-registration lists share the catalog and are not these.
36
+ */
37
+ const BULK_TITLE = /(公司登記資料|商業登記資料)-[A-Z]/;
38
+ /**
39
+ * A file name a shell and a manifest can carry: the title with its punctuation folded to underscores.
40
+ */
41
+ function filenameFor(title) {
42
+ return `${title
43
+ .replaceAll(/[()()、,/\\\s]+/g, "_")
44
+ .replaceAll(/_+/g, "_")
45
+ .replaceAll(/^_|_$/g, "")}.csv`;
46
+ }
47
+ async function listBulkDatasets() {
48
+ const res = await fetch(CATALOG_URL, { headers: { accept: "text/html" } });
49
+ if (!res.ok)
50
+ throw new Error(`gcis-tw: the catalog answered HTTP ${res.status}`);
51
+ const html = await res.text();
52
+ const datasets = [];
53
+ for (const [, path, rawTitle] of html.matchAll(/<a[^>]*href="(\/od\/detail[^"]*)"[^>]*>([^<]+)<\/a>/g)) {
54
+ const title = rawTitle?.trim();
55
+ if (!path || !title || !BULK_TITLE.test(title))
56
+ continue;
57
+ datasets.push({ title, detailPath: path.replace(/;jsessionid=[^?]*/, "") });
58
+ }
59
+ return datasets;
60
+ }
61
+ /**
62
+ * The `/od/file?oid=…` link a dataset's detail page hands its download dialog.
63
+ */
64
+ async function fileURLFor(dataset) {
65
+ const res = await fetch(`${PORTAL}${dataset.detailPath}`, { headers: { accept: "text/html" } });
66
+ if (!res.ok)
67
+ return undefined;
68
+ const html = await res.text();
69
+ const path = /showDialog\('(\/od\/file\?oid=[^']+)'\)/.exec(html)?.[1];
70
+ return path ? `${PORTAL}${path}` : undefined;
71
+ }
72
+ export async function fetchGCISTW(options, report) {
73
+ const destDir = join(options.outRoot, SLUG);
74
+ await makeDirectories(destDir);
75
+ const manifestPath = join(destDir, "MANIFEST.json");
76
+ const datasets = await listBulkDatasets();
77
+ report?.(`=== ${SLUG}: ${datasets.length} bulk register files in the catalog`);
78
+ const previous = await loadCollectionFiles(manifestPath);
79
+ const files = new Map();
80
+ let fetched = 0;
81
+ let skipped = 0;
82
+ const failedCodes = [];
83
+ for (const dataset of datasets) {
84
+ const filename = filenameFor(dataset.title);
85
+ const dest = join(destDir, filename);
86
+ const before = previous.get(filename);
87
+ if (before && (await pathExists(dest))) {
88
+ files.set(filename, before);
89
+ skipped++;
90
+ continue;
91
+ }
92
+ await sleep(PACE_MS);
93
+ const url = await fileURLFor(dataset);
94
+ if (!url) {
95
+ report?.(` ✗ no file link on the detail page for ${dataset.title}`);
96
+ failedCodes.push(dataset.title);
97
+ continue;
98
+ }
99
+ report?.(`--- ${dataset.title}`);
100
+ let bytes;
101
+ try {
102
+ bytes = await withRetries(async () => {
103
+ const res = await fetch(url, { headers: { accept: "*/*" }, signal: AbortSignal.timeout(1_800_000) });
104
+ if (!res.ok)
105
+ throw new Error(`HTTP ${res.status} for ${dataset.title}`);
106
+ return streamBodyToFile(res, dest);
107
+ }, { report, label: dataset.title });
108
+ }
109
+ catch (error) {
110
+ report?.(` ✗ ${error.message}`);
111
+ failedCodes.push(dataset.title);
112
+ continue;
113
+ }
114
+ if (bytes < BYTES_PER_KIB) {
115
+ report?.(` ✗ ${bytes} bytes — an error page, not the register`);
116
+ failedCodes.push(dataset.title);
117
+ continue;
118
+ }
119
+ const sha = await sha256File(dest);
120
+ files.set(filename, { source_url: url, downloaded_at: new Date().toISOString(), filename, sha256: sha, bytes });
121
+ fetched++;
122
+ report?.(` ✓ ${(bytes / 1024 / 1024).toFixed(1)} MB sha256=${sha}`);
123
+ const manifest = {
124
+ source: SLUG,
125
+ source_url: CATALOG_URL,
126
+ license: LICENSE,
127
+ attribution: ATTRIBUTION,
128
+ downloaded_at: new Date().toISOString(),
129
+ files: [...files.values()],
130
+ };
131
+ await writeManifest(manifestPath, manifest);
132
+ }
133
+ return { fetched, skipped, failed: failedCodes.length, failedCodes };
134
+ }
135
+ //# sourceMappingURL=gcis.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"gcis.js","sourceRoot":"","sources":["../../../../lib/tw/tools/fetch/gcis.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;GAkBG;AAEH,OAAO,EAAE,aAAa,EAAE,MAAM,+BAA+B,CAAA;AAC7D,OAAO,EAAE,UAAU,EAAE,MAAM,4BAA4B,CAAA;AACvD,OAAO,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAA;AAC5D,OAAO,EAAE,UAAU,EAAE,MAAM,sBAAsB,CAAA;AACjD,OAAO,EAAE,KAAK,EAAE,MAAM,6BAA6B,CAAA;AACnD,OAAO,EAAE,IAAI,EAAE,MAAM,SAAS,CAAA;AAQ9B,OAAO,EAAE,mBAAmB,EAAE,gBAAgB,EAAE,WAAW,EAAE,aAAa,EAAE,MAAM,6BAA6B,CAAA;AAE/G,MAAM,IAAI,GAAG,SAAS,CAAA;AACtB,MAAM,MAAM,GAAG,8BAA8B,CAAA;AAC7C,MAAM,WAAW,GAAG,GAAG,MAAM,kBAAkB,CAAA;AAC/C,MAAM,OAAO,GAAG,0FAA0F,CAAA;AAC1G,MAAM,WAAW,GAAG,0EAA0E,CAAA;AAC9F,MAAM,OAAO,GAAG,GAAG,CAAA;AAEnB;;;GAGG;AACH,MAAM,UAAU,GAAG,uBAAuB,CAAA;AAS1C;;GAEG;AACH,SAAS,WAAW,CAAC,KAAa;IACjC,OAAO,GAAG,KAAK;SACb,UAAU,CAAC,iBAAiB,EAAE,GAAG,CAAC;SAClC,UAAU,CAAC,KAAK,EAAE,GAAG,CAAC;SACtB,UAAU,CAAC,QAAQ,EAAE,EAAE,CAAC,MAAM,CAAA;AACjC,CAAC;AAED,KAAK,UAAU,gBAAgB;IAC9B,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,WAAW,EAAE,EAAE,OAAO,EAAE,EAAE,MAAM,EAAE,WAAW,EAAE,EAAE,CAAC,CAAA;IAE1E,IAAI,CAAC,GAAG,CAAC,EAAE;QAAE,MAAM,IAAI,KAAK,CAAC,sCAAsC,GAAG,CAAC,MAAM,EAAE,CAAC,CAAA;IAChF,MAAM,IAAI,GAAG,MAAM,GAAG,CAAC,IAAI,EAAE,CAAA;IAC7B,MAAM,QAAQ,GAAc,EAAE,CAAA;IAE9B,KAAK,MAAM,CAAC,EAAE,IAAI,EAAE,QAAQ,CAAC,IAAI,IAAI,CAAC,QAAQ,CAAC,sDAAsD,CAAC,EAAE,CAAC;QACxG,MAAM,KAAK,GAAG,QAAQ,EAAE,IAAI,EAAE,CAAA;QAE9B,IAAI,CAAC,IAAI,IAAI,CAAC,KAAK,IAAI,CAAC,UAAU,CAAC,IAAI,CAAC,KAAK,CAAC;YAAE,SAAQ;QACxD,QAAQ,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,UAAU,EAAE,IAAI,CAAC,OAAO,CAAC,mBAAmB,EAAE,EAAE,CAAC,EAAE,CAAC,CAAA;IAC5E,CAAC;IAED,OAAO,QAAQ,CAAA;AAChB,CAAC;AAED;;GAEG;AACH,KAAK,UAAU,UAAU,CAAC,OAAgB;IACzC,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,GAAG,MAAM,GAAG,OAAO,CAAC,UAAU,EAAE,EAAE,EAAE,OAAO,EAAE,EAAE,MAAM,EAAE,WAAW,EAAE,EAAE,CAAC,CAAA;IAE/F,IAAI,CAAC,GAAG,CAAC,EAAE;QAAE,OAAO,SAAS,CAAA;IAC7B,MAAM,IAAI,GAAG,MAAM,GAAG,CAAC,IAAI,EAAE,CAAA;IAC7B,MAAM,IAAI,GAAG,yCAAyC,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;IAEtE,OAAO,IAAI,CAAC,CAAC,CAAC,GAAG,MAAM,GAAG,IAAI,EAAE,CAAC,CAAC,CAAC,SAAS,CAAA;AAC7C,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,WAAW,CAAC,OAA2B,EAAE,MAA+B;IAC7F,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,IAAI,CAAC,CAAA;IAC3C,MAAM,eAAe,CAAC,OAAO,CAAC,CAAA;IAC9B,MAAM,YAAY,GAAG,IAAI,CAAC,OAAO,EAAE,eAAe,CAAC,CAAA;IAEnD,MAAM,QAAQ,GAAG,MAAM,gBAAgB,EAAE,CAAA;IACzC,MAAM,EAAE,CAAC,OAAO,IAAI,KAAK,QAAQ,CAAC,MAAM,qCAAqC,CAAC,CAAA;IAE9E,MAAM,QAAQ,GAAG,MAAM,mBAAmB,CAAC,YAAY,CAAC,CAAA;IACxD,MAAM,KAAK,GAAG,IAAI,GAAG,EAA0B,CAAA;IAC/C,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,MAAM,WAAW,GAAa,EAAE,CAAA;IAEhC,KAAK,MAAM,OAAO,IAAI,QAAQ,EAAE,CAAC;QAChC,MAAM,QAAQ,GAAG,WAAW,CAAC,OAAO,CAAC,KAAK,CAAC,CAAA;QAC3C,MAAM,IAAI,GAAG,IAAI,CAAC,OAAO,EAAE,QAAQ,CAAC,CAAA;QACpC,MAAM,MAAM,GAAG,QAAQ,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAA;QAErC,IAAI,MAAM,IAAI,CAAC,MAAM,UAAU,CAAC,IAAI,CAAC,CAAC,EAAE,CAAC;YACxC,KAAK,CAAC,GAAG,CAAC,QAAQ,EAAE,MAAM,CAAC,CAAA;YAE3B,OAAO,EAAE,CAAA;YAET,SAAQ;QACT,CAAC;QAED,MAAM,KAAK,CAAC,OAAO,CAAC,CAAA;QACpB,MAAM,GAAG,GAAG,MAAM,UAAU,CAAC,OAAO,CAAC,CAAA;QAErC,IAAI,CAAC,GAAG,EAAE,CAAC;YACV,MAAM,EAAE,CAAC,2CAA2C,OAAO,CAAC,KAAK,EAAE,CAAC,CAAA;YACpE,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,KAAK,CAAC,CAAA;YAE/B,SAAQ;QACT,CAAC;QAED,MAAM,EAAE,CAAC,OAAO,OAAO,CAAC,KAAK,EAAE,CAAC,CAAA;QAChC,IAAI,KAAa,CAAA;QAEjB,IAAI,CAAC;YACJ,KAAK,GAAG,MAAM,WAAW,CACxB,KAAK,IAAI,EAAE;gBACV,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,GAAG,EAAE,EAAE,OAAO,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,EAAE,MAAM,EAAE,WAAW,CAAC,OAAO,CAAC,SAAS,CAAC,EAAE,CAAC,CAAA;gBAEpG,IAAI,CAAC,GAAG,CAAC,EAAE;oBAAE,MAAM,IAAI,KAAK,CAAC,QAAQ,GAAG,CAAC,MAAM,QAAQ,OAAO,CAAC,KAAK,EAAE,CAAC,CAAA;gBAEvE,OAAO,gBAAgB,CAAC,GAAG,EAAE,IAAI,CAAC,CAAA;YACnC,CAAC,EACD,EAAE,MAAM,EAAE,KAAK,EAAE,OAAO,CAAC,KAAK,EAAE,CAChC,CAAA;QACF,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,MAAM,EAAE,CAAC,OAAQ,KAAe,CAAC,OAAO,EAAE,CAAC,CAAA;YAC3C,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,KAAK,CAAC,CAAA;YAE/B,SAAQ;QACT,CAAC;QAED,IAAI,KAAK,GAAG,aAAa,EAAE,CAAC;YAC3B,MAAM,EAAE,CAAC,OAAO,KAAK,0CAA0C,CAAC,CAAA;YAChE,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,KAAK,CAAC,CAAA;YAE/B,SAAQ;QACT,CAAC;QAED,MAAM,GAAG,GAAG,MAAM,UAAU,CAAC,IAAI,CAAC,CAAA;QAClC,KAAK,CAAC,GAAG,CAAC,QAAQ,EAAE,EAAE,UAAU,EAAE,GAAG,EAAE,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,GAAG,EAAE,KAAK,EAAE,CAAC,CAAA;QAE/G,OAAO,EAAE,CAAA;QACT,MAAM,EAAE,CAAC,OAAO,CAAC,KAAK,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe,GAAG,EAAE,CAAC,CAAA;QAErE,MAAM,QAAQ,GAA6B;YAC1C,MAAM,EAAE,IAAI;YACZ,UAAU,EAAE,WAAW;YACvB,OAAO,EAAE,OAAO;YAChB,WAAW,EAAE,WAAW;YACxB,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;YACvC,KAAK,EAAE,CAAC,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC;SAC1B,CAAA;QAED,MAAM,aAAa,CAAC,YAAY,EAAE,QAAQ,CAAC,CAAA;IAC5C,CAAC;IAED,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,EAAE,WAAW,CAAC,MAAM,EAAE,WAAW,EAAE,CAAA;AACrE,CAAC"}
package/out/types.d.ts CHANGED
@@ -15,7 +15,7 @@
15
15
  * `CorpusAdapter` is the contract every data source implements; `AdapterOptions` is the
16
16
  * per-invocation knob set (input path, optional country filter, row cap, abort signal).
17
17
  */
18
- import type { BIOLabel, ComponentTag } from "@mailwoman/core/types";
18
+ import type { BIOLabel, ComponentTag } from "@mailwoman/codex/component";
19
19
  /**
20
20
  * Provenance + augmentation metadata that travels with every corpus row.
21
21
  *
@@ -1 +1 @@
1
- {"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../lib/types.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAEH,OAAO,KAAK,EAAE,QAAQ,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAA;AAEnE;;;;;GAKG;AACH,MAAM,WAAW,gBAAgB;IAChC;;OAEG;IACH,MAAM,EAAE,MAAM,CAAA;IAEd;;;;OAIG;IACH,SAAS,EAAE,MAAM,CAAA;IAEjB;;;OAGG;IACH,cAAc,EAAE,MAAM,CAAA;IAEtB;;;OAGG;IACH,OAAO,EAAE,MAAM,CAAA;CACf;AAED;;;GAGG;AACH,MAAM,WAAW,WAAW;IAC3B;;;OAGG;IACH,MAAM,EAAE,MAAM,CAAA;IAEd;;;OAGG;IACH,cAAc,EAAE,MAAM,CAAA;CACtB;AAED;;;;;;;;;GASG;AACH,MAAM,WAAW,YAAa,SAAQ,gBAAgB;IACrD;;OAEG;IACH,GAAG,EAAE,MAAM,CAAA;IAEX;;;OAGG;IACH,UAAU,EAAE,OAAO,CAAC,MAAM,CAAC,YAAY,EAAE,MAAM,CAAC,CAAC,CAAA;IAEjD;;OAEG;IACH,OAAO,EAAE,MAAM,CAAA;IAEf;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,CAAA;IAEf;;OAEG;IACH,KAAK,CAAC,EAAE,WAAW,CAAA;CACnB;AAED;;;;;;;;GAQG;AACH,MAAM,WAAW,UAAW,SAAQ,YAAY;IAC/C;;OAEG;IACH,MAAM,EAAE,SAAS,MAAM,EAAE,CAAA;IAEzB;;OAEG;IACH,MAAM,EAAE,SAAS,QAAQ,EAAE,CAAA;IAE3B;;;;;;;;OAQG;IACH,WAAW,CAAC,EAAE,SAAS,MAAM,EAAE,CAAA;IAE/B;;OAEG;IACH,SAAS,CAAC,EAAE,SAAS,MAAM,EAAE,CAAA;IAE7B;;OAEG;IACH,SAAS,CAAC,EAAE,SAAS,YAAY,EAAE,CAAA;CACnC;AAED;;;;;;GAMG;AACH,MAAM,WAAW,cAAc;IAC9B,GAAG,EAAE,YAAY,CAAA;IACjB,MAAM,EAAE,MAAM,CAAA;CACd;AAED;;;;;;;;;;;;;GAaG;AACH,MAAM,WAAW,cAAc;IAC9B;;OAEG;IACH,SAAS,EAAE,MAAM,CAAA;IAEjB;;OAEG;IACH,SAAS,CAAC,EAAE,MAAM,CAAA;IAElB;;OAEG;IACH,OAAO,CAAC,EAAE,MAAM,CAAA;IAEhB;;OAEG;IACH,KAAK,CAAC,EAAE,MAAM,CAAA;IAEd;;OAEG;IACH,MAAM,CAAC,EAAE,WAAW,CAAA;CACpB;AAED;;;;;;;;;GASG;AACH,MAAM,WAAW,aAAa;IAC7B;;OAEG;IACH,QAAQ,CAAC,EAAE,EAAE,MAAM,CAAA;IAEnB;;OAEG;IACH,QAAQ,CAAC,cAAc,EAAE,MAAM,CAAA;IAE/B;;OAEG;IACH,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAA;IAE5B;;;;;;;;;;;;;;;OAeG;IACH,IAAI,CAAC,IAAI,EAAE,cAAc,GAAG,aAAa,CAAC,YAAY,CAAC,CAAA;CACvD"}
1
+ {"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../lib/types.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAEH,OAAO,KAAK,EAAE,QAAQ,EAAE,YAAY,EAAE,MAAM,4BAA4B,CAAA;AAExE;;;;;GAKG;AACH,MAAM,WAAW,gBAAgB;IAChC;;OAEG;IACH,MAAM,EAAE,MAAM,CAAA;IAEd;;;;OAIG;IACH,SAAS,EAAE,MAAM,CAAA;IAEjB;;;OAGG;IACH,cAAc,EAAE,MAAM,CAAA;IAEtB;;;OAGG;IACH,OAAO,EAAE,MAAM,CAAA;CACf;AAED;;;GAGG;AACH,MAAM,WAAW,WAAW;IAC3B;;;OAGG;IACH,MAAM,EAAE,MAAM,CAAA;IAEd;;;OAGG;IACH,cAAc,EAAE,MAAM,CAAA;CACtB;AAED;;;;;;;;;GASG;AACH,MAAM,WAAW,YAAa,SAAQ,gBAAgB;IACrD;;OAEG;IACH,GAAG,EAAE,MAAM,CAAA;IAEX;;;OAGG;IACH,UAAU,EAAE,OAAO,CAAC,MAAM,CAAC,YAAY,EAAE,MAAM,CAAC,CAAC,CAAA;IAEjD;;OAEG;IACH,OAAO,EAAE,MAAM,CAAA;IAEf;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,CAAA;IAEf;;OAEG;IACH,KAAK,CAAC,EAAE,WAAW,CAAA;CACnB;AAED;;;;;;;;GAQG;AACH,MAAM,WAAW,UAAW,SAAQ,YAAY;IAC/C;;OAEG;IACH,MAAM,EAAE,SAAS,MAAM,EAAE,CAAA;IAEzB;;OAEG;IACH,MAAM,EAAE,SAAS,QAAQ,EAAE,CAAA;IAE3B;;;;;;;;OAQG;IACH,WAAW,CAAC,EAAE,SAAS,MAAM,EAAE,CAAA;IAE/B;;OAEG;IACH,SAAS,CAAC,EAAE,SAAS,MAAM,EAAE,CAAA;IAE7B;;OAEG;IACH,SAAS,CAAC,EAAE,SAAS,YAAY,EAAE,CAAA;CACnC;AAED;;;;;;GAMG;AACH,MAAM,WAAW,cAAc;IAC9B,GAAG,EAAE,YAAY,CAAA;IACjB,MAAM,EAAE,MAAM,CAAA;CACd;AAED;;;;;;;;;;;;;GAaG;AACH,MAAM,WAAW,cAAc;IAC9B;;OAEG;IACH,SAAS,EAAE,MAAM,CAAA;IAEjB;;OAEG;IACH,SAAS,CAAC,EAAE,MAAM,CAAA;IAElB;;OAEG;IACH,OAAO,CAAC,EAAE,MAAM,CAAA;IAEhB;;OAEG;IACH,KAAK,CAAC,EAAE,MAAM,CAAA;IAEd;;OAEG;IACH,MAAM,CAAC,EAAE,WAAW,CAAA;CACpB;AAED;;;;;;;;;GASG;AACH,MAAM,WAAW,aAAa;IAC7B;;OAEG;IACH,QAAQ,CAAC,EAAE,EAAE,MAAM,CAAA;IAEnB;;OAEG;IACH,QAAQ,CAAC,cAAc,EAAE,MAAM,CAAA;IAE/B;;OAEG;IACH,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAA;IAE5B;;;;;;;;;;;;;;;OAeG;IACH,IAAI,CAAC,IAAI,EAAE,cAAc,GAAG,aAAa,CAAC,YAAY,CAAC,CAAA;CACvD"}
@@ -0,0 +1 @@
1
+ {"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../lib/us/adapters/fcc-bdc/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAkCG;AAOH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,QAAQ,CAAA;AAGzE;;;GAGG;AACH,eAAO,MAAM,kBAAkB,YAAY,CAAA;AAC3C;;;GAGG;AACH,eAAO,MAAM,uBAAuB,kBAAkB,CAAA;AActD;;;;;;;;;;;GAWG;AACH,wBAAgB,aAAa,CAAC,GAAG,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,GAAG,IAAI,GAAG,MAAM,CAWxE;AAED;;GAEG;AACH,wBAAgB,mBAAmB,IAAI,aAAa,CAwEnD;AAED;;GAEG;AACH,eAAO,MAAM,aAAa,eAAwB,CAAA"}
@@ -0,0 +1,142 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ *
6
+ * `fcc-bdc`: FCC Broadband Data Collection (BDC) — Fabric-derived location consumer.
7
+ *
8
+ * The first member of Phase 1.6's "adversarial sources" class. BDC ships the public-domain US
9
+ * broadband-serviceable-location (BSL) fabric: ~120M addresses keyed by stable `location_id`,
10
+ * carrying `address_primary` + `city` + `state` + `zip` + `zip_suffix`. Compared to the clean
11
+ * gazetteer rows from WOF / TIGER / BAN, BDC carries the chaos of address data that has passed
12
+ * through several layers of human entry + automated geocoding + revision: abbreviation drift,
13
+ * inconsistent unit designators, "RR" / "HC" / "PSC" rural-route shapes, embedded apartment /
14
+ * suite numbers that did not survive the address parser cleanly. This is the highest-signal,
15
+ * hardest-to-normalize address corpus in the federal public-domain catalog.
16
+ *
17
+ * Following the `tiger` / `wof-admin` pattern, this adapter consumes a SQLite database the operator
18
+ * pre-builds via the isp-nexus BDC ETL (`/srv/isp-nexus/sync/fcc/bdc/`) or any equivalent
19
+ * host-side pipeline. The mailwoman side does not download or parse the raw CSV/ZIP distribution
20
+ * directly — that keeps the adapter narrow and the BDC ingest pluggable.
21
+ *
22
+ * The SQLite schema is documented in README.md and modeled after `NTIARecord`
23
+ * (`isp-nexus/fcc/bdc/data-collection.ts`): one row per `location_id`. The adapter splits
24
+ * `address_primary` into `house_number` (leading numeric prefix, if any) + `street` (everything
25
+ * after), and combines `zip` + `zip_suffix` into the canonical USPS `postcode` slot.
26
+ *
27
+ * One CanonicalRow per fabric record. Unlike `tiger` (multiple postcode variants per segment) or
28
+ * `wof-admin` (multiple hierarchy variants per place), BDC records already represent fully
29
+ * specified addresses; no fan-out is warranted. Adversarial composition (Phase 1.6 §2.1) is the
30
+ * mechanism for deriving multiple training rows per BDC record.
31
+ *
32
+ * License: stamped `"Public Domain"` per the BDC fabric's US federal-government distribution terms.
33
+ * The CostQuest Fabric source data has its own license; consumers who substitute that path should
34
+ * re-stamp accordingly.
35
+ */
36
+ import { formatAddressRow } from "@mailwoman/codex/address-format";
37
+ import { DatabaseClient } from "@mailwoman/sqlite/client";
38
+ import { splitStreetLine } from "#adapters/utils";
39
+ import { lookupStateAbbreviation } from "#us/fips-state";
40
+ /**
41
+ * Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
42
+ * it came from.
43
+ */
44
+ export const FCC_BDC_ADAPTER_ID = "fcc-bdc";
45
+ /**
46
+ * License carried by this source (Public Domain), attached to each row so downstream consumers inherit the terms rather
47
+ * than having to look them up.
48
+ */
49
+ export const FCC_BDC_DEFAULT_LICENSE = "Public Domain";
50
+ /**
51
+ * Combine `zip` + optional `zip_suffix` into the canonical USPS postcode surface form.
52
+ *
53
+ * NTIARecord doc is ambiguous about whether `zip_suffix` is the 4-digit extension alone or the full ZIP+4 string. This
54
+ * handles both:
55
+ *
56
+ * - Bare 4-digit extension (`zip="94103"`, `zip_suffix="1234"`) → `"94103-1234"`
57
+ * - Already-joined form (`zip_suffix="94103-1234"`) → returned as-is
58
+ * - No suffix → bare `zip`
59
+ *
60
+ * Empty / whitespace-only suffix is treated as missing.
61
+ */
62
+ export function buildPostcode(zip, suffix) {
63
+ const z = zip.trim();
64
+ if (!z)
65
+ return "";
66
+ const s = suffix?.trim() ?? "";
67
+ if (!s)
68
+ return z;
69
+ if (s.includes("-"))
70
+ return s;
71
+ return `${z}-${s}`;
72
+ }
73
+ /**
74
+ * Build a BDC adapter. Pure factory so multiple instances can be created in tests.
75
+ */
76
+ export function createFccBdcAdapter() {
77
+ return {
78
+ id: FCC_BDC_ADAPTER_ID,
79
+ defaultLicense: FCC_BDC_DEFAULT_LICENSE,
80
+ description: "FCC Broadband Data Collection — Fabric-derived BSL addresses (public-domain); SQLite DB the operator builds via the isp-nexus BDC ETL.",
81
+ async *rows(opts) {
82
+ if (opts.country && opts.country !== "US") {
83
+ throw new Error(`fcc-bdc adapter: only US supported, got country=${opts.country}`);
84
+ }
85
+ const db = new DatabaseClient(opts.inputPath, { readOnly: true });
86
+ let emitted = 0;
87
+ try {
88
+ const stmt = db.prepare(`SELECT location_id, address_primary, city, state, zip, zip_suffix
89
+ FROM bdc_locations
90
+ ORDER BY location_id`);
91
+ for (const row of stmt.iterate()) {
92
+ if (opts.signal?.aborted)
93
+ return;
94
+ if (opts.limit !== undefined && emitted >= opts.limit)
95
+ return;
96
+ const split = splitStreetLine(row.address_primary ?? "");
97
+ if (!split)
98
+ continue;
99
+ const state = lookupStateAbbreviation(row.state);
100
+ if (!state)
101
+ continue;
102
+ const locality = row.city?.trim();
103
+ if (!locality)
104
+ continue;
105
+ const postcode = buildPostcode(row.zip ?? "", row.zip_suffix ?? null);
106
+ if (!postcode)
107
+ continue;
108
+ const components = {
109
+ ...(split.house_number ? { house_number: split.house_number } : {}),
110
+ street: split.street,
111
+ locality,
112
+ region: state.abbreviation,
113
+ postcode,
114
+ };
115
+ const rendered = formatAddressRow(components, "US", { singleLine: true });
116
+ if (!rendered)
117
+ continue;
118
+ const { raw, components: aligned } = rendered;
119
+ yield {
120
+ raw,
121
+ components: aligned,
122
+ country: "US",
123
+ locale: "en-US",
124
+ source: FCC_BDC_ADAPTER_ID,
125
+ source_id: `${FCC_BDC_ADAPTER_ID}-${row.location_id}`,
126
+ corpus_version: "",
127
+ license: FCC_BDC_DEFAULT_LICENSE,
128
+ };
129
+ emitted++;
130
+ }
131
+ }
132
+ finally {
133
+ await db.destroy();
134
+ }
135
+ },
136
+ };
137
+ }
138
+ /**
139
+ * The configured adapter instance registered with the corpus builder.
140
+ */
141
+ export const fccBdcAdapter = createFccBdcAdapter();
142
+ //# sourceMappingURL=adapter.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../lib/us/adapters/fcc-bdc/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAkCG;AAGH,OAAO,EAAE,gBAAgB,EAAE,MAAM,iCAAiC,CAAA;AAClE,OAAO,EAAE,cAAc,EAAE,MAAM,0BAA0B,CAAA;AAEzD,OAAO,EAAE,eAAe,EAAE,MAAM,iBAAiB,CAAA;AAEjD,OAAO,EAAE,uBAAuB,EAAE,MAAM,gBAAgB,CAAA;AAExD;;;GAGG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAAG,SAAS,CAAA;AAC3C;;;GAGG;AACH,MAAM,CAAC,MAAM,uBAAuB,GAAG,eAAe,CAAA;AActD;;;;;;;;;;;GAWG;AACH,MAAM,UAAU,aAAa,CAAC,GAAW,EAAE,MAAqB;IAC/D,MAAM,CAAC,GAAG,GAAG,CAAC,IAAI,EAAE,CAAA;IAEpB,IAAI,CAAC,CAAC;QAAE,OAAO,EAAE,CAAA;IACjB,MAAM,CAAC,GAAG,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;IAE9B,IAAI,CAAC,CAAC;QAAE,OAAO,CAAC,CAAA;IAEhB,IAAI,CAAC,CAAC,QAAQ,CAAC,GAAG,CAAC;QAAE,OAAO,CAAC,CAAA;IAE7B,OAAO,GAAG,CAAC,IAAI,CAAC,EAAE,CAAA;AACnB,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,mBAAmB;IAClC,OAAO;QACN,EAAE,EAAE,kBAAkB;QACtB,cAAc,EAAE,uBAAuB;QACvC,WAAW,EACV,wIAAwI;QAEzI,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,IAAI,IAAI,CAAC,OAAO,IAAI,IAAI,CAAC,OAAO,KAAK,IAAI,EAAE,CAAC;gBAC3C,MAAM,IAAI,KAAK,CAAC,mDAAmD,IAAI,CAAC,OAAO,EAAE,CAAC,CAAA;YACnF,CAAC;YAED,MAAM,EAAE,GAAG,IAAI,cAAc,CAAc,IAAI,CAAC,SAAS,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAA;YAC9E,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,CAAC;gBACJ,MAAM,IAAI,GAAG,EAAE,CAAC,OAAO,CACtB;;2BAEsB,CACtB,CAAA;gBAED,KAAK,MAAM,GAAG,IAAI,IAAI,CAAC,OAAO,EAAsC,EAAE,CAAC;oBACtE,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;wBAAE,OAAM;oBAEhC,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;wBAAE,OAAM;oBAE7D,MAAM,KAAK,GAAG,eAAe,CAAC,GAAG,CAAC,eAAe,IAAI,EAAE,CAAC,CAAA;oBAExD,IAAI,CAAC,KAAK;wBAAE,SAAQ;oBACpB,MAAM,KAAK,GAAG,uBAAuB,CAAC,GAAG,CAAC,KAAK,CAAC,CAAA;oBAEhD,IAAI,CAAC,KAAK;wBAAE,SAAQ;oBACpB,MAAM,QAAQ,GAAG,GAAG,CAAC,IAAI,EAAE,IAAI,EAAE,CAAA;oBAEjC,IAAI,CAAC,QAAQ;wBAAE,SAAQ;oBACvB,MAAM,QAAQ,GAAG,aAAa,CAAC,GAAG,CAAC,GAAG,IAAI,EAAE,EAAE,GAAG,CAAC,UAAU,IAAI,IAAI,CAAC,CAAA;oBAErE,IAAI,CAAC,QAAQ;wBAAE,SAAQ;oBAEvB,MAAM,UAAU,GAA+B;wBAC9C,GAAG,CAAC,KAAK,CAAC,YAAY,CAAC,CAAC,CAAC,EAAE,YAAY,EAAE,KAAK,CAAC,YAAY,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;wBACnE,MAAM,EAAE,KAAK,CAAC,MAAM;wBACpB,QAAQ;wBACR,MAAM,EAAE,KAAK,CAAC,YAAY;wBAC1B,QAAQ;qBACR,CAAA;oBAED,MAAM,QAAQ,GAAG,gBAAgB,CAAC,UAAU,EAAE,IAAI,EAAE,EAAE,UAAU,EAAE,IAAI,EAAE,CAAC,CAAA;oBAEzE,IAAI,CAAC,QAAQ;wBAAE,SAAQ;oBAEvB,MAAM,EAAE,GAAG,EAAE,UAAU,EAAE,OAAO,EAAE,GAAG,QAAQ,CAAA;oBAE7C,MAAM;wBACL,GAAG;wBACH,UAAU,EAAE,OAAO;wBACnB,OAAO,EAAE,IAAI;wBACb,MAAM,EAAE,OAAO;wBACf,MAAM,EAAE,kBAAkB;wBAC1B,SAAS,EAAE,GAAG,kBAAkB,IAAI,GAAG,CAAC,WAAW,EAAE;wBACrD,cAAc,EAAE,EAAE;wBAClB,OAAO,EAAE,uBAAuB;qBAChC,CAAA;oBAED,OAAO,EAAE,CAAA;gBACV,CAAC;YACF,CAAC;oBAAS,CAAC;gBACV,MAAM,EAAE,CAAC,OAAO,EAAE,CAAA;YACnB,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,aAAa,GAAG,mBAAmB,EAAE,CAAA"}
@@ -0,0 +1 @@
1
+ {"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../../lib/us/adapters/state/hi-schools/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AAMH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,QAAQ,CAAA;AAIzE;;;GAGG;AACH,eAAO,MAAM,2BAA2B,qBAAqB,CAAA;AAC7D;;;GAGG;AACH,eAAO,MAAM,gCAAgC,kBAAkB,CAAA;AAkC/D,wBAAgB,2BAA2B,IAAI,aAAa,CAyE3D;AAED;;GAEG;AACH,eAAO,MAAM,qBAAqB,eAAgC,CAAA"}
@@ -0,0 +1,136 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ *
6
+ * `state-hi-schools`: Hawaii DOE public + charter school workbook consumer.
7
+ *
8
+ * The Hawaii State Department of Education publishes a directory of all HIDOE schools and public
9
+ * charter schools (PCS) as an XLSX workbook (`SchoolList.xlsx`) with two sheets: `HIDOE` (~258
10
+ * rows) and `PCS` (~38 rows). Total ~296 rows statewide. Each row carries a school name,
11
+ * single-line street address, city, ZIP, a numeric `code`, and HI-specific administrative columns
12
+ * (complex, complex_area, district, island, charter).
13
+ *
14
+ * The adapter consumes the original XLSX retained by the fetcher and reads both worksheets directly.
15
+ * Legacy flat CSV artifacts remain accepted so existing source caches do not need conversion.
16
+ *
17
+ * Address parsing notes: Hawaii's residential numbering is hyphenated on Oahu (`47-470 Hui Aeko
18
+ * Place`), Kauai (`2-4035 Kaumualii Hwy`), and elsewhere. The shared HOUSE_NUMBER_PREFIX regex
19
+ * covers this via its optional `(?:-\d+)?` group.
20
+ *
21
+ * The `island` and `district` columns are HIDOE administrative labels (Honolulu, Central, Leeward,
22
+ * Windward, Hilo, Hawaii, Maui, Kauai) — they are NOT US counties and intentionally are not
23
+ * surfaced as `subregion`.
24
+ *
25
+ * Output: one row per school with `venue` (school name), `(house_number?, street, locality,
26
+ * region=HI, postcode)`, and a stable `source_id` derived from the school `code`.
27
+ *
28
+ * License: stamped `"Public Domain"` per Hawaii state government open-data terms.
29
+ */
30
+ import { formatAddressRow } from "@mailwoman/codex/address-format";
31
+ import { CSVSpliterator, XLSXSpliterator } from "spliterator";
32
+ import { splitStreetLine, stableSourceID } from "#adapters/utils";
33
+ import { schoolCellText, STATE_HI_SCHOOL_SHEETS } from "#us/adapters/state/hi-schools/workbook";
34
+ import { lookupStateAbbreviation } from "#us/fips-state";
35
+ /**
36
+ * Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
37
+ * it came from.
38
+ */
39
+ export const STATE_HI_SCHOOLS_ADAPTER_ID = "state-hi-schools";
40
+ /**
41
+ * License carried by this source (Public Domain), attached to each row so downstream consumers inherit the terms rather
42
+ * than having to look them up.
43
+ */
44
+ export const STATE_HI_SCHOOLS_DEFAULT_LICENSE = "Public Domain";
45
+ const HI_STATE_ABBR = "HI";
46
+ function normalizeZip(raw) {
47
+ const trimmed = schoolCellText(raw);
48
+ if (!trimmed)
49
+ return "";
50
+ // XLSX → CSV conversion may emit numeric ZIPs without leading zeros. HI ZIPs all begin
51
+ // with 96, so a 4-digit value indicates a leading-zero stripped during numeric coercion
52
+ // (defensive — has not been observed in the published file as of 2026-05).
53
+ if (/^\d{4}$/.test(trimmed))
54
+ return `0${trimmed}`;
55
+ return trimmed;
56
+ }
57
+ async function* readSchoolRows(inputPath) {
58
+ if (inputPath.toLowerCase().endsWith(".xlsx")) {
59
+ for (const sheet of STATE_HI_SCHOOL_SHEETS) {
60
+ yield* XLSXSpliterator.fromAsync(inputPath, {
61
+ sheet,
62
+ normalizeKeys: false,
63
+ });
64
+ }
65
+ return;
66
+ }
67
+ yield* CSVSpliterator.fromAsync(inputPath, {
68
+ normalizeKeys: false,
69
+ });
70
+ }
71
+ export function createStateHiSchoolsAdapter() {
72
+ return {
73
+ id: STATE_HI_SCHOOLS_ADAPTER_ID,
74
+ defaultLicense: STATE_HI_SCHOOLS_DEFAULT_LICENSE,
75
+ description: "Hawaii DOE School Directory — ~300 K-12 public + charter schools with venue+address (public-domain).",
76
+ async *rows(opts) {
77
+ if (opts.country && opts.country !== "US") {
78
+ throw new Error(`state-hi-schools adapter: only US supported, got country=${opts.country}`);
79
+ }
80
+ const state = lookupStateAbbreviation(HI_STATE_ABBR);
81
+ if (!state) {
82
+ throw new Error(`state-hi-schools adapter: HI not found in state codex (corpus bug)`);
83
+ }
84
+ let emitted = 0;
85
+ for await (const record of readSchoolRows(opts.inputPath)) {
86
+ if (opts.signal?.aborted)
87
+ break;
88
+ if (opts.limit !== undefined && emitted >= opts.limit)
89
+ break;
90
+ const name = schoolCellText(record.name);
91
+ const address = schoolCellText(record.address);
92
+ const city = schoolCellText(record.city);
93
+ const zip = normalizeZip(record.zip);
94
+ if (!name || !address || !city || !zip)
95
+ continue;
96
+ const split = splitStreetLine(address);
97
+ if (!split)
98
+ continue;
99
+ const components = {
100
+ venue: name,
101
+ ...(split.house_number ? { house_number: split.house_number } : {}),
102
+ street: split.street,
103
+ locality: city,
104
+ region: state.abbreviation,
105
+ postcode: zip,
106
+ };
107
+ const rendered = formatAddressRow(components, "US", { singleLine: true });
108
+ if (!rendered)
109
+ continue;
110
+ const { raw, components: aligned } = rendered;
111
+ if (Object.keys(aligned).length <= 2)
112
+ continue;
113
+ const code = schoolCellText(record.code);
114
+ const sourceID = code
115
+ ? `${STATE_HI_SCHOOLS_ADAPTER_ID}-${code}`
116
+ : stableSourceID(STATE_HI_SCHOOLS_ADAPTER_ID, aligned);
117
+ yield {
118
+ raw,
119
+ components: aligned,
120
+ country: "US",
121
+ locale: "en-US",
122
+ source: STATE_HI_SCHOOLS_ADAPTER_ID,
123
+ source_id: sourceID,
124
+ corpus_version: "",
125
+ license: STATE_HI_SCHOOLS_DEFAULT_LICENSE,
126
+ };
127
+ emitted++;
128
+ }
129
+ },
130
+ };
131
+ }
132
+ /**
133
+ * The configured adapter instance registered with the corpus builder.
134
+ */
135
+ export const stateHiSchoolsAdapter = createStateHiSchoolsAdapter();
136
+ //# sourceMappingURL=adapter.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../../lib/us/adapters/state/hi-schools/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AAEH,OAAO,EAAE,gBAAgB,EAAE,MAAM,iCAAiC,CAAA;AAClE,OAAO,EAAE,cAAc,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7D,OAAO,EAAE,eAAe,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAA;AAEjE,OAAO,EAAoB,cAAc,EAAE,sBAAsB,EAAE,MAAM,wCAAwC,CAAA;AACjH,OAAO,EAAE,uBAAuB,EAAE,MAAM,gBAAgB,CAAA;AAExD;;;GAGG;AACH,MAAM,CAAC,MAAM,2BAA2B,GAAG,kBAAkB,CAAA;AAC7D;;;GAGG;AACH,MAAM,CAAC,MAAM,gCAAgC,GAAG,eAAe,CAAA;AAE/D,MAAM,aAAa,GAAG,IAAI,CAAA;AAE1B,SAAS,YAAY,CAAC,GAAuB;IAC5C,MAAM,OAAO,GAAG,cAAc,CAAC,GAAG,CAAC,CAAA;IAEnC,IAAI,CAAC,OAAO;QAAE,OAAO,EAAE,CAAA;IAEvB,uFAAuF;IACvF,wFAAwF;IACxF,2EAA2E;IAC3E,IAAI,SAAS,CAAC,IAAI,CAAC,OAAO,CAAC;QAAE,OAAO,IAAI,OAAO,EAAE,CAAA;IAEjD,OAAO,OAAO,CAAA;AACf,CAAC;AAED,KAAK,SAAS,CAAC,CAAC,cAAc,CAAC,SAAiB;IAC/C,IAAI,SAAS,CAAC,WAAW,EAAE,CAAC,QAAQ,CAAC,OAAO,CAAC,EAAE,CAAC;QAC/C,KAAK,MAAM,KAAK,IAAI,sBAAsB,EAAE,CAAC;YAC5C,KAAK,CAAC,CAAC,eAAe,CAAC,SAAS,CAAc,SAAS,EAAE;gBACxD,KAAK;gBACL,aAAa,EAAE,KAAK;aACpB,CAAC,CAAA;QACH,CAAC;QAED,OAAM;IACP,CAAC;IAED,KAAK,CAAC,CAAC,cAAc,CAAC,SAAS,CAAc,SAAS,EAAE;QACvD,aAAa,EAAE,KAAK;KACpB,CAAC,CAAA;AACH,CAAC;AAED,MAAM,UAAU,2BAA2B;IAC1C,OAAO;QACN,EAAE,EAAE,2BAA2B;QAC/B,cAAc,EAAE,gCAAgC;QAChD,WAAW,EAAE,sGAAsG;QAEnH,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,IAAI,IAAI,CAAC,OAAO,IAAI,IAAI,CAAC,OAAO,KAAK,IAAI,EAAE,CAAC;gBAC3C,MAAM,IAAI,KAAK,CAAC,4DAA4D,IAAI,CAAC,OAAO,EAAE,CAAC,CAAA;YAC5F,CAAC;YAED,MAAM,KAAK,GAAG,uBAAuB,CAAC,aAAa,CAAC,CAAA;YAEpD,IAAI,CAAC,KAAK,EAAE,CAAC;gBACZ,MAAM,IAAI,KAAK,CAAC,oEAAoE,CAAC,CAAA;YACtF,CAAC;YAED,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,KAAK,EAAE,MAAM,MAAM,IAAI,cAAc,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,CAAC;gBAC3D,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;oBAAE,MAAK;gBAE/B,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;oBAAE,MAAK;gBAE5D,MAAM,IAAI,GAAG,cAAc,CAAC,MAAM,CAAC,IAAI,CAAC,CAAA;gBACxC,MAAM,OAAO,GAAG,cAAc,CAAC,MAAM,CAAC,OAAO,CAAC,CAAA;gBAC9C,MAAM,IAAI,GAAG,cAAc,CAAC,MAAM,CAAC,IAAI,CAAC,CAAA;gBACxC,MAAM,GAAG,GAAG,YAAY,CAAC,MAAM,CAAC,GAAG,CAAC,CAAA;gBAEpC,IAAI,CAAC,IAAI,IAAI,CAAC,OAAO,IAAI,CAAC,IAAI,IAAI,CAAC,GAAG;oBAAE,SAAQ;gBAEhD,MAAM,KAAK,GAAG,eAAe,CAAC,OAAO,CAAC,CAAA;gBAEtC,IAAI,CAAC,KAAK;oBAAE,SAAQ;gBAEpB,MAAM,UAAU,GAA+B;oBAC9C,KAAK,EAAE,IAAI;oBACX,GAAG,CAAC,KAAK,CAAC,YAAY,CAAC,CAAC,CAAC,EAAE,YAAY,EAAE,KAAK,CAAC,YAAY,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;oBACnE,MAAM,EAAE,KAAK,CAAC,MAAM;oBACpB,QAAQ,EAAE,IAAI;oBACd,MAAM,EAAE,KAAK,CAAC,YAAY;oBAC1B,QAAQ,EAAE,GAAG;iBACb,CAAA;gBAED,MAAM,QAAQ,GAAG,gBAAgB,CAAC,UAAU,EAAE,IAAI,EAAE,EAAE,UAAU,EAAE,IAAI,EAAE,CAAC,CAAA;gBAEzE,IAAI,CAAC,QAAQ;oBAAE,SAAQ;gBAEvB,MAAM,EAAE,GAAG,EAAE,UAAU,EAAE,OAAO,EAAE,GAAG,QAAQ,CAAA;gBAE7C,IAAI,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM,IAAI,CAAC;oBAAE,SAAQ;gBAE9C,MAAM,IAAI,GAAG,cAAc,CAAC,MAAM,CAAC,IAAI,CAAC,CAAA;gBAExC,MAAM,QAAQ,GAAG,IAAI;oBACpB,CAAC,CAAC,GAAG,2BAA2B,IAAI,IAAI,EAAE;oBAC1C,CAAC,CAAC,cAAc,CAAC,2BAA2B,EAAE,OAAO,CAAC,CAAA;gBAEvD,MAAM;oBACL,GAAG;oBACH,UAAU,EAAE,OAAO;oBACnB,OAAO,EAAE,IAAI;oBACb,MAAM,EAAE,OAAO;oBACf,MAAM,EAAE,2BAA2B;oBACnC,SAAS,EAAE,QAAQ;oBACnB,cAAc,EAAE,EAAE;oBAClB,OAAO,EAAE,gCAAgC;iBACzC,CAAA;gBAED,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,qBAAqB,GAAG,2BAA2B,EAAE,CAAA"}
@@ -0,0 +1 @@
1
+ {"version":3,"file":"workbook.d.ts","sourceRoot":"","sources":["../../../../../lib/us/adapters/state/hi-schools/workbook.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,aAAa,CAAA;AAEhD;;GAEG;AACH,eAAO,MAAM,sBAAsB,YAAI,OAAO,EAAE,KAAK,CAAU,CAAA;AAE/D;;GAEG;AACH,eAAO,MAAM,gCAAgC,YAAI,MAAM,EAAE,MAAM,EAAE,SAAS,EAAE,MAAM,EAAE,KAAK,CAAU,CAAA;AAEnG;;GAEG;AACH,MAAM,WAAW,WAAW;IAC3B,IAAI,EAAE,aAAa,GAAG,SAAS,CAAA;IAC/B,IAAI,EAAE,aAAa,GAAG,SAAS,CAAA;IAC/B,OAAO,EAAE,aAAa,GAAG,SAAS,CAAA;IAClC,IAAI,EAAE,aAAa,GAAG,SAAS,CAAA;IAC/B,GAAG,EAAE,aAAa,GAAG,SAAS,CAAA;CAC9B;AAED;;GAEG;AACH,wBAAgB,cAAc,CAAC,KAAK,EAAE,aAAa,GAAG,SAAS,GAAG,MAAM,CAEvE"}
@@ -0,0 +1 @@
1
+ {"version":3,"file":"workbook.js","sourceRoot":"","sources":["../../../../../lib/us/adapters/state/hi-schools/workbook.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAIH;;GAEG;AACH,MAAM,CAAC,MAAM,sBAAsB,GAAG,CAAC,OAAO,EAAE,KAAK,CAAU,CAAA;AAE/D;;GAEG;AACH,MAAM,CAAC,MAAM,gCAAgC,GAAG,CAAC,MAAM,EAAE,MAAM,EAAE,SAAS,EAAE,MAAM,EAAE,KAAK,CAAU,CAAA;AAanG;;GAEG;AACH,MAAM,UAAU,cAAc,CAAC,KAAgC;IAC9D,OAAO,KAAK,KAAK,IAAI,IAAI,KAAK,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,IAAI,EAAE,CAAA;AACzE,CAAC"}
@@ -0,0 +1 @@
1
+ {"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../../lib/us/adapters/state/ia-contractors/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAOH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,QAAQ,CAAA;AAGzE;;;GAGG;AACH,eAAO,MAAM,+BAA+B,yBAAyB,CAAA;AACrE;;;GAGG;AACH,eAAO,MAAM,oCAAoC,kBAAkB,CAAA;AAcnE,wBAAgB,+BAA+B,IAAI,aAAa,CAiF/D;AAED;;GAEG;AACH,eAAO,MAAM,yBAAyB,eAAoC,CAAA"}