@mailwoman/corpus 9.3.0 → 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 (991) 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/cz/recipes/pcfirst-preposition.ts +112 -0
  15. package/lib/de/recipes/locale.ts +360 -0
  16. package/lib/fr/adapters/ban/adapter.ts +159 -0
  17. package/lib/fr/recipes/admin-split.ts +243 -0
  18. package/lib/fr/recipes/bare-street.ts +171 -0
  19. package/lib/fr/recipes/fragment.ts +334 -0
  20. package/lib/fr/recipes/lieudit.ts +274 -0
  21. package/lib/fr/recipes/order.ts +246 -0
  22. package/lib/fr/tools/fetch/ban.ts +289 -0
  23. package/lib/index.ts +1 -1
  24. package/lib/international/recipes/locale.ts +598 -0
  25. package/lib/jp/tools/fetch/houjin.ts +141 -0
  26. package/lib/kr/adapters/juso/label-rows.ts +259 -0
  27. package/lib/kr/adapters/localdata/align.ts +299 -0
  28. package/lib/kr/adapters/localdata/key-index.ts +185 -0
  29. package/lib/kr/adapters/localdata/permit-rows.ts +186 -0
  30. package/lib/kr/tools/fetch/juso.ts +172 -0
  31. package/lib/kr/tools/fetch/localdata.ts +206 -0
  32. package/lib/nl/recipes/postcode.ts +117 -0
  33. package/lib/no/recipes/fragment.ts +213 -0
  34. package/lib/no/recipes/street/index.ts +91 -0
  35. package/lib/no/recipes/street/led.ts +135 -0
  36. package/lib/recipes/anchor-absorption.ts +2 -2
  37. package/lib/recipes/bare/country.ts +95 -0
  38. package/lib/recipes/bare/postcode/eval.ts +99 -0
  39. package/lib/recipes/bare/postcode/index.ts +327 -0
  40. package/lib/recipes/boundary-stress.ts +3 -1
  41. package/lib/recipes/country-balanced.ts +3 -2
  42. package/lib/recipes/house-venue.ts +2 -1
  43. package/lib/recipes/index.ts +28 -21
  44. package/lib/recipes/intersection.ts +3 -2
  45. package/lib/recipes/po/box/cedex/au-nz.ts +82 -0
  46. package/lib/recipes/po/box/cedex/ca.ts +58 -0
  47. package/lib/recipes/po/box/cedex/fr.ts +76 -0
  48. package/lib/recipes/po/box/cedex/phrases.ts +108 -0
  49. package/lib/recipes/po/box/cedex/recipe.ts +203 -0
  50. package/lib/recipes/po/box/cedex/sources.ts +189 -0
  51. package/lib/recipes/po/box/cedex/types.ts +35 -0
  52. package/lib/recipes/po/box/cedex/us.ts +69 -0
  53. package/lib/recipes/po/box/cedex/vocabulary.ts +106 -0
  54. package/lib/recipes/po/box/cedex.ts +9 -0
  55. package/lib/recipes/po/box/index.ts +128 -0
  56. package/lib/recipes/scaffold.ts +18 -42
  57. package/lib/recipes/street/affix.ts +807 -0
  58. package/lib/recipes/street/bare.ts +102 -0
  59. package/lib/recipes/street.ts +3 -1
  60. package/lib/recipes/sub/venue/context.ts +149 -0
  61. package/lib/recipes/sub/venue/index.ts +997 -0
  62. package/lib/recipes/sub/venue/sources.ts +739 -0
  63. package/lib/recipes/trailing-region.ts +9 -9
  64. package/lib/recipes/unit.ts +3 -3
  65. package/lib/sg/recipes/register.ts +270 -0
  66. package/lib/sg/tools/fetch/acra.ts +179 -0
  67. package/lib/si/recipes/bare-village.ts +99 -0
  68. package/lib/south-asia/recipes/register.ts +214 -0
  69. package/lib/synthesizers/anchor-absorption.ts +1 -1
  70. package/lib/synthesizers/locale.ts +261 -0
  71. package/lib/synthesizers/street.ts +1 -1
  72. package/lib/synthesizers/utils.ts +2 -2
  73. package/lib/tools/audit.ts +3 -2
  74. package/lib/tools/corpus-stats.ts +3 -3
  75. package/lib/tools/fetch/download/index.ts +10 -0
  76. package/lib/tools/fetch/download/manifest.ts +102 -0
  77. package/lib/tools/fetch/download/network.ts +226 -0
  78. package/lib/tools/fetch/download/retry.ts +173 -0
  79. package/lib/tools/fetch/geonames/dump.ts +257 -0
  80. package/lib/tools/fetch/geonames/postal.ts +180 -0
  81. package/lib/tools/fetch/index.ts +47 -20
  82. package/lib/tools/fetch/openaddresses.ts +2 -2
  83. package/lib/tools/fetch/ourairports.ts +2 -2
  84. package/lib/tools/fetch/ppd.ts +1 -3
  85. package/lib/tools/fetch/wikidata-subvenue.ts +2 -2
  86. package/lib/tools/golden/promote.ts +340 -0
  87. package/lib/tools/golden/relabel-street/directory.ts +340 -0
  88. package/lib/tools/golden/relabel-street/index.ts +9 -0
  89. package/lib/tools/golden/relabel-street/row.ts +361 -0
  90. package/lib/tools/index.ts +10 -10
  91. package/lib/tools/ingest-csv.ts +5 -7
  92. package/lib/tools/lint/slice/vocab.ts +376 -0
  93. package/lib/tools/overlay-manifest.ts +92 -25
  94. package/lib/tools/overture-subvenue.ts +1 -1
  95. package/lib/tools/postcode-triples.ts +138 -14
  96. package/lib/tools/sub/venue/harvest.ts +234 -0
  97. package/lib/tools/sub/venue/head-nouns.ts +245 -0
  98. package/lib/tools/sub/venue/lexicon.ts +429 -0
  99. package/lib/tools/sub/venue/surfaces.ts +95 -0
  100. package/lib/tools/sub/venue/table.ts +281 -0
  101. package/lib/tools/sub/venue/wikidata.ts +85 -0
  102. package/lib/tw/tools/fetch/gcis.ts +180 -0
  103. package/lib/types.ts +1 -1
  104. package/lib/us/adapters/fcc-bdc/adapter.ts +173 -0
  105. package/lib/us/adapters/state/hi-schools/adapter.ts +160 -0
  106. package/lib/us/adapters/state/ia-contractors/adapter.ts +136 -0
  107. package/lib/us/adapters/state/ny-notaries/adapter.ts +133 -0
  108. package/lib/us/adapters/state/tx-notaries/adapter.ts +149 -0
  109. package/lib/us/adapters/tiger/adapter.ts +250 -0
  110. package/lib/us/adapters/usgov/hrsa-fqhc/adapter.ts +156 -0
  111. package/lib/us/adapters/usgov/imls-pls/adapter.ts +134 -0
  112. package/lib/us/adapters/usgov/irs-bmf/adapter.ts +145 -0
  113. package/lib/us/adapters/usgov/nad/adapter.ts +324 -0
  114. package/lib/us/adapters/usgov/nppes/adapter.ts +143 -0
  115. package/lib/us/adapters/usgov/samhsa-treatment-locator/adapter.ts +182 -0
  116. package/lib/us/tools/fetch/hrsa.ts +59 -0
  117. package/lib/us/tools/fetch/imls-pls.ts +149 -0
  118. package/lib/us/tools/fetch/nad.ts +341 -0
  119. package/lib/us/tools/fetch/nppes.ts +165 -0
  120. package/lib/us/tools/fetch/state/hi-schools.ts +161 -0
  121. package/lib/us/tools/fetch/state/sources.ts +146 -0
  122. package/lib/us/tools/fetch/tiger-full.ts +308 -0
  123. package/lib/utils/align.ts +1 -1
  124. package/lib/utils/golden.ts +12 -8
  125. package/lib/utils/wof-json.ts +7 -13
  126. package/out/adapters/geonames/adapter.d.ts +1 -1
  127. package/out/adapters/geonames/adapter.js +3 -3
  128. package/out/adapters/geonames/adapter.js.map +1 -1
  129. package/out/adapters/geonames/postal/adapter.d.ts.map +1 -0
  130. package/out/adapters/geonames/postal/adapter.js +107 -0
  131. package/out/adapters/geonames/postal/adapter.js.map +1 -0
  132. package/out/adapters/index.d.ts +16 -16
  133. package/out/adapters/index.d.ts.map +1 -1
  134. package/out/adapters/index.js +34 -32
  135. package/out/adapters/index.js.map +1 -1
  136. package/out/adapters/openaddresses/adapter.d.ts.map +1 -1
  137. package/out/adapters/openaddresses/adapter.js +4 -6
  138. package/out/adapters/openaddresses/adapter.js.map +1 -1
  139. package/out/adapters/osm/adapter.d.ts +95 -0
  140. package/out/adapters/osm/adapter.d.ts.map +1 -0
  141. package/out/adapters/osm/adapter.js +211 -0
  142. package/out/adapters/osm/adapter.js.map +1 -0
  143. package/out/adapters/overture/adapter.d.ts +10 -0
  144. package/out/adapters/overture/adapter.d.ts.map +1 -1
  145. package/out/adapters/overture/adapter.js +20 -7
  146. package/out/adapters/overture/adapter.js.map +1 -1
  147. package/out/adapters/synth-po-box/adapter.js.map +1 -1
  148. package/out/adapters/utils/index.d.ts +1 -1
  149. package/out/adapters/utils/index.d.ts.map +1 -1
  150. package/out/adapters/utils/index.js.map +1 -1
  151. package/out/adapters/wof/admin/json/adapter.d.ts +79 -0
  152. package/out/adapters/wof/admin/json/adapter.d.ts.map +1 -0
  153. package/out/adapters/wof/admin/json/adapter.js +204 -0
  154. package/out/adapters/wof/admin/json/adapter.js.map +1 -0
  155. package/out/adapters/wof/json-rows.d.ts +73 -0
  156. package/out/adapters/wof/json-rows.d.ts.map +1 -0
  157. package/out/adapters/wof/json-rows.js +115 -0
  158. package/out/adapters/wof/json-rows.js.map +1 -0
  159. package/out/adapters/wof/postalcode-json/adapter.d.ts +65 -0
  160. package/out/adapters/wof/postalcode-json/adapter.d.ts.map +1 -0
  161. package/out/adapters/wof/postalcode-json/adapter.js +167 -0
  162. package/out/adapters/wof/postalcode-json/adapter.js.map +1 -0
  163. package/out/au/adapters/gnaf/adapter.d.ts.map +1 -0
  164. package/out/au/adapters/gnaf/adapter.js +127 -0
  165. package/out/au/adapters/gnaf/adapter.js.map +1 -0
  166. package/out/au/adapters/gnaf/assemble.d.ts +65 -0
  167. package/out/au/adapters/gnaf/assemble.d.ts.map +1 -0
  168. package/out/au/adapters/gnaf/assemble.js +154 -0
  169. package/out/au/adapters/gnaf/assemble.js.map +1 -0
  170. package/out/cn/recipes/organizational-units.d.ts +36 -0
  171. package/out/cn/recipes/organizational-units.d.ts.map +1 -0
  172. package/out/cn/recipes/organizational-units.js +159 -0
  173. package/out/cn/recipes/organizational-units.js.map +1 -0
  174. package/out/cz/recipes/pcfirst-preposition.d.ts +22 -0
  175. package/out/cz/recipes/pcfirst-preposition.d.ts.map +1 -0
  176. package/out/cz/recipes/pcfirst-preposition.js +101 -0
  177. package/out/cz/recipes/pcfirst-preposition.js.map +1 -0
  178. package/out/de/recipes/locale.d.ts +44 -0
  179. package/out/de/recipes/locale.d.ts.map +1 -0
  180. package/out/de/recipes/locale.js +289 -0
  181. package/out/de/recipes/locale.js.map +1 -0
  182. package/out/env.d.ts +1 -1
  183. package/out/fr/adapters/ban/adapter.d.ts.map +1 -0
  184. package/out/fr/adapters/ban/adapter.js +123 -0
  185. package/out/fr/adapters/ban/adapter.js.map +1 -0
  186. package/out/fr/adapters/ban/street-decompose.d.ts.map +1 -0
  187. package/out/fr/adapters/ban/street-decompose.js.map +1 -0
  188. package/out/fr/recipes/admin-split.d.ts +38 -0
  189. package/out/fr/recipes/admin-split.d.ts.map +1 -0
  190. package/out/fr/recipes/admin-split.js +192 -0
  191. package/out/fr/recipes/admin-split.js.map +1 -0
  192. package/out/fr/recipes/bare-street.d.ts +28 -0
  193. package/out/fr/recipes/bare-street.d.ts.map +1 -0
  194. package/out/fr/recipes/bare-street.js +144 -0
  195. package/out/fr/recipes/bare-street.js.map +1 -0
  196. package/out/fr/recipes/fragment.d.ts +77 -0
  197. package/out/fr/recipes/fragment.d.ts.map +1 -0
  198. package/out/fr/recipes/fragment.js +277 -0
  199. package/out/fr/recipes/fragment.js.map +1 -0
  200. package/out/fr/recipes/lieudit.d.ts +32 -0
  201. package/out/fr/recipes/lieudit.d.ts.map +1 -0
  202. package/out/fr/recipes/lieudit.js +211 -0
  203. package/out/fr/recipes/lieudit.js.map +1 -0
  204. package/out/fr/recipes/order.d.ts +38 -0
  205. package/out/fr/recipes/order.d.ts.map +1 -0
  206. package/out/fr/recipes/order.js +198 -0
  207. package/out/fr/recipes/order.js.map +1 -0
  208. package/out/fr/tools/fetch/ban.d.ts +31 -0
  209. package/out/fr/tools/fetch/ban.d.ts.map +1 -0
  210. package/out/fr/tools/fetch/ban.js +239 -0
  211. package/out/fr/tools/fetch/ban.js.map +1 -0
  212. package/out/index.d.ts +1 -1
  213. package/out/index.d.ts.map +1 -1
  214. package/out/index.js +1 -1
  215. package/out/index.js.map +1 -1
  216. package/out/international/recipes/locale.d.ts +136 -0
  217. package/out/international/recipes/locale.d.ts.map +1 -0
  218. package/out/international/recipes/locale.js +458 -0
  219. package/out/international/recipes/locale.js.map +1 -0
  220. package/out/jp/adapters/wof-admin/adapter.d.ts.map +1 -0
  221. package/out/jp/adapters/wof-admin/adapter.js.map +1 -0
  222. package/out/jp/tools/fetch/houjin.d.ts +24 -0
  223. package/out/jp/tools/fetch/houjin.d.ts.map +1 -0
  224. package/out/jp/tools/fetch/houjin.js +102 -0
  225. package/out/jp/tools/fetch/houjin.js.map +1 -0
  226. package/out/kr/adapters/juso/label-rows.d.ts +76 -0
  227. package/out/kr/adapters/juso/label-rows.d.ts.map +1 -0
  228. package/out/kr/adapters/juso/label-rows.js +194 -0
  229. package/out/kr/adapters/juso/label-rows.js.map +1 -0
  230. package/out/kr/adapters/localdata/align.d.ts +43 -0
  231. package/out/kr/adapters/localdata/align.d.ts.map +1 -0
  232. package/out/kr/adapters/localdata/align.js +223 -0
  233. package/out/kr/adapters/localdata/align.js.map +1 -0
  234. package/out/kr/adapters/localdata/key-index.d.ts +71 -0
  235. package/out/kr/adapters/localdata/key-index.d.ts.map +1 -0
  236. package/out/kr/adapters/localdata/key-index.js +133 -0
  237. package/out/kr/adapters/localdata/key-index.js.map +1 -0
  238. package/out/kr/adapters/localdata/permit-rows.d.ts +66 -0
  239. package/out/kr/adapters/localdata/permit-rows.d.ts.map +1 -0
  240. package/out/kr/adapters/localdata/permit-rows.js +131 -0
  241. package/out/kr/adapters/localdata/permit-rows.js.map +1 -0
  242. package/out/kr/tools/fetch/juso.d.ts +30 -0
  243. package/out/kr/tools/fetch/juso.d.ts.map +1 -0
  244. package/out/kr/tools/fetch/juso.js +120 -0
  245. package/out/kr/tools/fetch/juso.js.map +1 -0
  246. package/out/kr/tools/fetch/localdata.d.ts +30 -0
  247. package/out/kr/tools/fetch/localdata.d.ts.map +1 -0
  248. package/out/kr/tools/fetch/localdata.js +139 -0
  249. package/out/kr/tools/fetch/localdata.js.map +1 -0
  250. package/out/nl/recipes/postcode.d.ts +26 -0
  251. package/out/nl/recipes/postcode.d.ts.map +1 -0
  252. package/out/nl/recipes/postcode.js +103 -0
  253. package/out/nl/recipes/postcode.js.map +1 -0
  254. package/out/no/recipes/fragment.d.ts +43 -0
  255. package/out/no/recipes/fragment.d.ts.map +1 -0
  256. package/out/no/recipes/fragment.js +183 -0
  257. package/out/no/recipes/fragment.js.map +1 -0
  258. package/out/no/recipes/street/index.d.ts +18 -0
  259. package/out/no/recipes/street/index.d.ts.map +1 -0
  260. package/out/no/recipes/street/index.js +72 -0
  261. package/out/no/recipes/street/index.js.map +1 -0
  262. package/out/no/recipes/street/led.d.ts +24 -0
  263. package/out/no/recipes/street/led.d.ts.map +1 -0
  264. package/out/no/recipes/street/led.js +114 -0
  265. package/out/no/recipes/street/led.js.map +1 -0
  266. package/out/recipes/anchor-absorption.d.ts.map +1 -1
  267. package/out/recipes/anchor-absorption.js +2 -1
  268. package/out/recipes/anchor-absorption.js.map +1 -1
  269. package/out/recipes/bare/country.d.ts +25 -0
  270. package/out/recipes/bare/country.d.ts.map +1 -0
  271. package/out/recipes/bare/country.js +88 -0
  272. package/out/recipes/bare/country.js.map +1 -0
  273. package/out/recipes/bare/postcode/eval.d.ts +29 -0
  274. package/out/recipes/bare/postcode/eval.d.ts.map +1 -0
  275. package/out/recipes/bare/postcode/eval.js +85 -0
  276. package/out/recipes/bare/postcode/eval.js.map +1 -0
  277. package/out/recipes/bare/postcode/index.d.ts +62 -0
  278. package/out/recipes/bare/postcode/index.d.ts.map +1 -0
  279. package/out/recipes/bare/postcode/index.js +267 -0
  280. package/out/recipes/bare/postcode/index.js.map +1 -0
  281. package/out/recipes/boundary-stress.d.ts.map +1 -1
  282. package/out/recipes/boundary-stress.js +2 -1
  283. package/out/recipes/boundary-stress.js.map +1 -1
  284. package/out/recipes/country-balanced.d.ts.map +1 -1
  285. package/out/recipes/country-balanced.js +2 -1
  286. package/out/recipes/country-balanced.js.map +1 -1
  287. package/out/recipes/house-venue.d.ts.map +1 -1
  288. package/out/recipes/house-venue.js +2 -1
  289. package/out/recipes/house-venue.js.map +1 -1
  290. package/out/recipes/index.d.ts.map +1 -1
  291. package/out/recipes/index.js +28 -21
  292. package/out/recipes/index.js.map +1 -1
  293. package/out/recipes/intersection.d.ts.map +1 -1
  294. package/out/recipes/intersection.js +2 -1
  295. package/out/recipes/intersection.js.map +1 -1
  296. package/out/recipes/po/box/cedex/au-nz.d.ts +7 -0
  297. package/out/recipes/po/box/cedex/au-nz.d.ts.map +1 -0
  298. package/out/recipes/po/box/cedex/au-nz.js +56 -0
  299. package/out/recipes/po/box/cedex/au-nz.js.map +1 -0
  300. package/out/recipes/po/box/cedex/ca.d.ts +7 -0
  301. package/out/recipes/po/box/cedex/ca.d.ts.map +1 -0
  302. package/out/recipes/po/box/cedex/ca.js +38 -0
  303. package/out/recipes/po/box/cedex/ca.js.map +1 -0
  304. package/out/recipes/po/box/cedex/fr.d.ts +7 -0
  305. package/out/recipes/po/box/cedex/fr.d.ts.map +1 -0
  306. package/out/recipes/po/box/cedex/fr.js +57 -0
  307. package/out/recipes/po/box/cedex/fr.js.map +1 -0
  308. package/out/recipes/po/box/cedex/phrases.d.ts +8 -0
  309. package/out/recipes/po/box/cedex/phrases.d.ts.map +1 -0
  310. package/out/recipes/po/box/cedex/phrases.js +76 -0
  311. package/out/recipes/po/box/cedex/phrases.js.map +1 -0
  312. package/out/recipes/po/box/cedex/recipe.d.ts +9 -0
  313. package/out/recipes/po/box/cedex/recipe.d.ts.map +1 -0
  314. package/out/recipes/po/box/cedex/recipe.js +153 -0
  315. package/out/recipes/po/box/cedex/recipe.js.map +1 -0
  316. package/out/recipes/po/box/cedex/sources.d.ts +86 -0
  317. package/out/recipes/po/box/cedex/sources.d.ts.map +1 -0
  318. package/out/recipes/po/box/cedex/sources.js +143 -0
  319. package/out/recipes/po/box/cedex/sources.js.map +1 -0
  320. package/out/recipes/po/box/cedex/types.d.ts +31 -0
  321. package/out/recipes/po/box/cedex/types.d.ts.map +1 -0
  322. package/out/recipes/po/box/cedex/types.js +5 -0
  323. package/out/recipes/po/box/cedex/types.js.map +1 -0
  324. package/out/recipes/po/box/cedex/us.d.ts +7 -0
  325. package/out/recipes/po/box/cedex/us.d.ts.map +1 -0
  326. package/out/recipes/po/box/cedex/us.js +51 -0
  327. package/out/recipes/po/box/cedex/us.js.map +1 -0
  328. package/out/recipes/po/box/cedex/vocabulary.d.ts +68 -0
  329. package/out/recipes/po/box/cedex/vocabulary.d.ts.map +1 -0
  330. package/out/recipes/po/box/cedex/vocabulary.js +90 -0
  331. package/out/recipes/po/box/cedex/vocabulary.js.map +1 -0
  332. package/out/recipes/po/box/cedex.d.ts +9 -0
  333. package/out/recipes/po/box/cedex.d.ts.map +1 -0
  334. package/out/recipes/po/box/cedex.js +9 -0
  335. package/out/recipes/po/box/cedex.js.map +1 -0
  336. package/out/recipes/po/box/index.d.ts +17 -0
  337. package/out/recipes/po/box/index.d.ts.map +1 -0
  338. package/out/recipes/po/box/index.js +105 -0
  339. package/out/recipes/po/box/index.js.map +1 -0
  340. package/out/recipes/scaffold.d.ts +20 -1
  341. package/out/recipes/scaffold.d.ts.map +1 -1
  342. package/out/recipes/scaffold.js +18 -49
  343. package/out/recipes/scaffold.js.map +1 -1
  344. package/out/recipes/street/affix.d.ts +89 -0
  345. package/out/recipes/street/affix.d.ts.map +1 -0
  346. package/out/recipes/street/affix.js +565 -0
  347. package/out/recipes/street/affix.js.map +1 -0
  348. package/out/recipes/street/bare.d.ts +25 -0
  349. package/out/recipes/street/bare.d.ts.map +1 -0
  350. package/out/recipes/street/bare.js +87 -0
  351. package/out/recipes/street/bare.js.map +1 -0
  352. package/out/recipes/street.d.ts.map +1 -1
  353. package/out/recipes/street.js +2 -1
  354. package/out/recipes/street.js.map +1 -1
  355. package/out/recipes/sub/venue/context.d.ts +29 -0
  356. package/out/recipes/sub/venue/context.d.ts.map +1 -0
  357. package/out/recipes/sub/venue/context.js +106 -0
  358. package/out/recipes/sub/venue/context.js.map +1 -0
  359. package/out/recipes/sub/venue/index.d.ts +270 -0
  360. package/out/recipes/sub/venue/index.d.ts.map +1 -0
  361. package/out/recipes/sub/venue/index.js +728 -0
  362. package/out/recipes/sub/venue/index.js.map +1 -0
  363. package/out/recipes/sub/venue/sources.d.ts +209 -0
  364. package/out/recipes/sub/venue/sources.d.ts.map +1 -0
  365. package/out/recipes/sub/venue/sources.js +555 -0
  366. package/out/recipes/sub/venue/sources.js.map +1 -0
  367. package/out/recipes/trailing-region.d.ts.map +1 -1
  368. package/out/recipes/trailing-region.js +8 -2
  369. package/out/recipes/trailing-region.js.map +1 -1
  370. package/out/recipes/unit.d.ts.map +1 -1
  371. package/out/recipes/unit.js +2 -1
  372. package/out/recipes/unit.js.map +1 -1
  373. package/out/sg/recipes/register.d.ts +69 -0
  374. package/out/sg/recipes/register.d.ts.map +1 -0
  375. package/out/sg/recipes/register.js +211 -0
  376. package/out/sg/recipes/register.js.map +1 -0
  377. package/out/sg/tools/fetch/acra.d.ts +23 -0
  378. package/out/sg/tools/fetch/acra.d.ts.map +1 -0
  379. package/out/sg/tools/fetch/acra.js +126 -0
  380. package/out/sg/tools/fetch/acra.js.map +1 -0
  381. package/out/si/recipes/bare-village.d.ts +32 -0
  382. package/out/si/recipes/bare-village.d.ts.map +1 -0
  383. package/out/si/recipes/bare-village.js +89 -0
  384. package/out/si/recipes/bare-village.js.map +1 -0
  385. package/out/south-asia/recipes/register.d.ts +51 -0
  386. package/out/south-asia/recipes/register.d.ts.map +1 -0
  387. package/out/south-asia/recipes/register.js +154 -0
  388. package/out/south-asia/recipes/register.js.map +1 -0
  389. package/out/synthesizers/anchor-absorption.d.ts +1 -1
  390. package/out/synthesizers/anchor-absorption.d.ts.map +1 -1
  391. package/out/synthesizers/anchor-absorption.js.map +1 -1
  392. package/out/synthesizers/boundary-stress.js.map +1 -1
  393. package/out/synthesizers/house-venue.js.map +1 -1
  394. package/out/synthesizers/intersection.js.map +1 -1
  395. package/out/synthesizers/locale.d.ts +116 -0
  396. package/out/synthesizers/locale.d.ts.map +1 -0
  397. package/out/synthesizers/locale.js +150 -0
  398. package/out/synthesizers/locale.js.map +1 -0
  399. package/out/synthesizers/no-street.d.ts.map +1 -1
  400. package/out/synthesizers/no-street.js.map +1 -1
  401. package/out/synthesizers/po-box.js.map +1 -1
  402. package/out/synthesizers/street.d.ts.map +1 -1
  403. package/out/synthesizers/street.js +1 -1
  404. package/out/synthesizers/street.js.map +1 -1
  405. package/out/synthesizers/utils.js +1 -1
  406. package/out/synthesizers/utils.js.map +1 -1
  407. package/out/test-kit/corpus-recipe.d.ts.map +1 -1
  408. package/out/test-kit/corpus-recipe.js.map +1 -1
  409. package/out/tools/audit.d.ts.map +1 -1
  410. package/out/tools/audit.js +3 -2
  411. package/out/tools/audit.js.map +1 -1
  412. package/out/tools/corpus-stats.js +3 -3
  413. package/out/tools/corpus-stats.js.map +1 -1
  414. package/out/tools/fetch/download/index.d.ts +10 -0
  415. package/out/tools/fetch/download/index.d.ts.map +1 -0
  416. package/out/tools/fetch/download/index.js +10 -0
  417. package/out/tools/fetch/download/index.js.map +1 -0
  418. package/out/tools/fetch/download/manifest.d.ts +47 -0
  419. package/out/tools/fetch/download/manifest.d.ts.map +1 -0
  420. package/out/tools/fetch/download/manifest.js +74 -0
  421. package/out/tools/fetch/download/manifest.js.map +1 -0
  422. package/out/tools/fetch/download/network.d.ts +105 -0
  423. package/out/tools/fetch/download/network.d.ts.map +1 -0
  424. package/out/tools/fetch/download/network.js +130 -0
  425. package/out/tools/fetch/download/network.js.map +1 -0
  426. package/out/tools/fetch/download/retry.d.ts +45 -0
  427. package/out/tools/fetch/download/retry.d.ts.map +1 -0
  428. package/out/tools/fetch/download/retry.js +136 -0
  429. package/out/tools/fetch/download/retry.js.map +1 -0
  430. package/out/tools/fetch/geonames/dump.d.ts +91 -0
  431. package/out/tools/fetch/geonames/dump.d.ts.map +1 -0
  432. package/out/tools/fetch/geonames/dump.js +171 -0
  433. package/out/tools/fetch/geonames/dump.js.map +1 -0
  434. package/out/tools/fetch/geonames/postal.d.ts +76 -0
  435. package/out/tools/fetch/geonames/postal.d.ts.map +1 -0
  436. package/out/tools/fetch/geonames/postal.js +126 -0
  437. package/out/tools/fetch/geonames/postal.js.map +1 -0
  438. package/out/tools/fetch/index.d.ts +47 -20
  439. package/out/tools/fetch/index.d.ts.map +1 -1
  440. package/out/tools/fetch/index.js +47 -20
  441. package/out/tools/fetch/index.js.map +1 -1
  442. package/out/tools/fetch/openaddresses.d.ts +1 -1
  443. package/out/tools/fetch/openaddresses.d.ts.map +1 -1
  444. package/out/tools/fetch/openaddresses.js +1 -1
  445. package/out/tools/fetch/openaddresses.js.map +1 -1
  446. package/out/tools/fetch/ourairports.d.ts +1 -1
  447. package/out/tools/fetch/ourairports.d.ts.map +1 -1
  448. package/out/tools/fetch/ourairports.js +1 -1
  449. package/out/tools/fetch/ourairports.js.map +1 -1
  450. package/out/tools/fetch/ppd.js +1 -3
  451. package/out/tools/fetch/ppd.js.map +1 -1
  452. package/out/tools/fetch/wikidata-subvenue.d.ts +1 -1
  453. package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -1
  454. package/out/tools/fetch/wikidata-subvenue.js +1 -1
  455. package/out/tools/fetch/wikidata-subvenue.js.map +1 -1
  456. package/out/tools/golden/expand.d.ts +90 -0
  457. package/out/tools/golden/expand.d.ts.map +1 -0
  458. package/out/tools/golden/expand.js +406 -0
  459. package/out/tools/golden/expand.js.map +1 -0
  460. package/out/tools/golden/promote.d.ts +72 -0
  461. package/out/tools/golden/promote.d.ts.map +1 -0
  462. package/out/tools/golden/promote.js +243 -0
  463. package/out/tools/golden/promote.js.map +1 -0
  464. package/out/tools/golden/relabel-street/directory.d.ts +83 -0
  465. package/out/tools/golden/relabel-street/directory.d.ts.map +1 -0
  466. package/out/tools/golden/relabel-street/directory.js +216 -0
  467. package/out/tools/golden/relabel-street/directory.js.map +1 -0
  468. package/out/tools/golden/relabel-street/index.d.ts +9 -0
  469. package/out/tools/golden/relabel-street/index.d.ts.map +1 -0
  470. package/out/tools/golden/relabel-street/index.js +9 -0
  471. package/out/tools/golden/relabel-street/index.js.map +1 -0
  472. package/out/tools/golden/relabel-street/row.d.ts +121 -0
  473. package/out/tools/golden/relabel-street/row.d.ts.map +1 -0
  474. package/out/tools/golden/relabel-street/row.js +232 -0
  475. package/out/tools/golden/relabel-street/row.js.map +1 -0
  476. package/out/tools/index.d.ts +10 -10
  477. package/out/tools/index.d.ts.map +1 -1
  478. package/out/tools/index.js +10 -10
  479. package/out/tools/index.js.map +1 -1
  480. package/out/tools/ingest-csv.d.ts.map +1 -1
  481. package/out/tools/ingest-csv.js +5 -7
  482. package/out/tools/ingest-csv.js.map +1 -1
  483. package/out/tools/lint/slice/index.d.ts +93 -0
  484. package/out/tools/lint/slice/index.d.ts.map +1 -0
  485. package/out/tools/lint/slice/index.js +322 -0
  486. package/out/tools/lint/slice/index.js.map +1 -0
  487. package/out/tools/lint/slice/vocab.d.ts +90 -0
  488. package/out/tools/lint/slice/vocab.d.ts.map +1 -0
  489. package/out/tools/lint/slice/vocab.js +254 -0
  490. package/out/tools/lint/slice/vocab.js.map +1 -0
  491. package/out/tools/overlay-manifest.d.ts +56 -6
  492. package/out/tools/overlay-manifest.d.ts.map +1 -1
  493. package/out/tools/overlay-manifest.js +56 -15
  494. package/out/tools/overlay-manifest.js.map +1 -1
  495. package/out/tools/overture-subvenue.d.ts +1 -1
  496. package/out/tools/postcode-triples.d.ts +36 -0
  497. package/out/tools/postcode-triples.d.ts.map +1 -1
  498. package/out/tools/postcode-triples.js +91 -12
  499. package/out/tools/postcode-triples.js.map +1 -1
  500. package/out/tools/slice/kryptonite.d.ts +32 -0
  501. package/out/tools/slice/kryptonite.d.ts.map +1 -0
  502. package/out/tools/slice/kryptonite.js +99 -0
  503. package/out/tools/slice/kryptonite.js.map +1 -0
  504. package/out/tools/slice/translit.d.ts +51 -0
  505. package/out/tools/slice/translit.d.ts.map +1 -0
  506. package/out/tools/slice/translit.js +166 -0
  507. package/out/tools/slice/translit.js.map +1 -0
  508. package/out/tools/sub/venue/harvest.d.ts +100 -0
  509. package/out/tools/sub/venue/harvest.d.ts.map +1 -0
  510. package/out/tools/sub/venue/harvest.js +168 -0
  511. package/out/tools/sub/venue/harvest.js.map +1 -0
  512. package/out/tools/sub/venue/head-nouns.d.ts +50 -0
  513. package/out/tools/sub/venue/head-nouns.d.ts.map +1 -0
  514. package/out/tools/sub/venue/head-nouns.js.map +1 -0
  515. package/out/tools/sub/venue/lexicon.d.ts +156 -0
  516. package/out/tools/sub/venue/lexicon.d.ts.map +1 -0
  517. package/out/tools/sub/venue/lexicon.js +283 -0
  518. package/out/tools/sub/venue/lexicon.js.map +1 -0
  519. package/out/tools/sub/venue/promotions.d.ts +94 -0
  520. package/out/tools/sub/venue/promotions.d.ts.map +1 -0
  521. package/out/tools/sub/venue/promotions.js +266 -0
  522. package/out/tools/sub/venue/promotions.js.map +1 -0
  523. package/out/tools/sub/venue/surfaces.d.ts +45 -0
  524. package/out/tools/sub/venue/surfaces.d.ts.map +1 -0
  525. package/out/tools/sub/venue/surfaces.js.map +1 -0
  526. package/out/tools/sub/venue/table.d.ts +229 -0
  527. package/out/tools/sub/venue/table.d.ts.map +1 -0
  528. package/out/tools/sub/venue/table.js.map +1 -0
  529. package/out/tools/sub/venue/wikidata.d.ts +26 -0
  530. package/out/tools/sub/venue/wikidata.d.ts.map +1 -0
  531. package/out/tools/sub/venue/wikidata.js +62 -0
  532. package/out/tools/sub/venue/wikidata.js.map +1 -0
  533. package/out/tw/tools/fetch/gcis.d.ts +23 -0
  534. package/out/tw/tools/fetch/gcis.d.ts.map +1 -0
  535. package/out/tw/tools/fetch/gcis.js +135 -0
  536. package/out/tw/tools/fetch/gcis.js.map +1 -0
  537. package/out/types.d.ts +1 -1
  538. package/out/types.d.ts.map +1 -1
  539. package/out/us/adapters/fcc-bdc/adapter.d.ts.map +1 -0
  540. package/out/us/adapters/fcc-bdc/adapter.js +142 -0
  541. package/out/us/adapters/fcc-bdc/adapter.js.map +1 -0
  542. package/out/us/adapters/state/hi-schools/adapter.d.ts.map +1 -0
  543. package/out/us/adapters/state/hi-schools/adapter.js +136 -0
  544. package/out/us/adapters/state/hi-schools/adapter.js.map +1 -0
  545. package/out/us/adapters/state/hi-schools/workbook.d.ts.map +1 -0
  546. package/out/us/adapters/state/hi-schools/workbook.js.map +1 -0
  547. package/out/us/adapters/state/ia-contractors/adapter.d.ts.map +1 -0
  548. package/out/us/adapters/state/ia-contractors/adapter.js +104 -0
  549. package/out/us/adapters/state/ia-contractors/adapter.js.map +1 -0
  550. package/out/us/adapters/state/ny-notaries/adapter.d.ts.map +1 -0
  551. package/out/us/adapters/state/ny-notaries/adapter.js +112 -0
  552. package/out/us/adapters/state/ny-notaries/adapter.js.map +1 -0
  553. package/out/us/adapters/state/tx-notaries/adapter.d.ts.map +1 -0
  554. package/out/us/adapters/state/tx-notaries/adapter.js +118 -0
  555. package/out/us/adapters/state/tx-notaries/adapter.js.map +1 -0
  556. package/out/us/adapters/tiger/adapter.d.ts +55 -0
  557. package/out/us/adapters/tiger/adapter.d.ts.map +1 -0
  558. package/out/us/adapters/tiger/adapter.js +197 -0
  559. package/out/us/adapters/tiger/adapter.js.map +1 -0
  560. package/out/us/adapters/tiger/street-decompose.d.ts.map +1 -0
  561. package/out/us/adapters/tiger/street-decompose.js.map +1 -0
  562. package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts.map +1 -0
  563. package/out/us/adapters/usgov/hrsa-fqhc/adapter.js +121 -0
  564. package/out/us/adapters/usgov/hrsa-fqhc/adapter.js.map +1 -0
  565. package/out/us/adapters/usgov/imls-pls/adapter.d.ts.map +1 -0
  566. package/out/us/adapters/usgov/imls-pls/adapter.js +106 -0
  567. package/out/us/adapters/usgov/imls-pls/adapter.js.map +1 -0
  568. package/out/us/adapters/usgov/irs-bmf/adapter.d.ts.map +1 -0
  569. package/out/us/adapters/usgov/irs-bmf/adapter.js +116 -0
  570. package/out/us/adapters/usgov/irs-bmf/adapter.js.map +1 -0
  571. package/out/us/adapters/usgov/nad/adapter.d.ts.map +1 -0
  572. package/out/us/adapters/usgov/nad/adapter.js +239 -0
  573. package/out/us/adapters/usgov/nad/adapter.js.map +1 -0
  574. package/out/us/adapters/usgov/nppes/adapter.d.ts.map +1 -0
  575. package/out/us/adapters/usgov/nppes/adapter.js +110 -0
  576. package/out/us/adapters/usgov/nppes/adapter.js.map +1 -0
  577. package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts.map +1 -0
  578. package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js +143 -0
  579. package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js.map +1 -0
  580. package/out/us/fips-state.d.ts +41 -0
  581. package/out/us/fips-state.d.ts.map +1 -0
  582. package/out/us/fips-state.js +100 -0
  583. package/out/us/fips-state.js.map +1 -0
  584. package/out/us/tools/fetch/hrsa.d.ts +18 -0
  585. package/out/us/tools/fetch/hrsa.d.ts.map +1 -0
  586. package/out/us/tools/fetch/hrsa.js +46 -0
  587. package/out/us/tools/fetch/hrsa.js.map +1 -0
  588. package/out/us/tools/fetch/imls-pls.d.ts +25 -0
  589. package/out/us/tools/fetch/imls-pls.d.ts.map +1 -0
  590. package/out/us/tools/fetch/imls-pls.js +108 -0
  591. package/out/us/tools/fetch/imls-pls.js.map +1 -0
  592. package/out/us/tools/fetch/nad.d.ts +70 -0
  593. package/out/us/tools/fetch/nad.d.ts.map +1 -0
  594. package/out/us/tools/fetch/nad.js +234 -0
  595. package/out/us/tools/fetch/nad.js.map +1 -0
  596. package/out/us/tools/fetch/nppes.d.ts +26 -0
  597. package/out/us/tools/fetch/nppes.d.ts.map +1 -0
  598. package/out/us/tools/fetch/nppes.js +126 -0
  599. package/out/us/tools/fetch/nppes.js.map +1 -0
  600. package/out/us/tools/fetch/state/hi-schools.d.ts +26 -0
  601. package/out/us/tools/fetch/state/hi-schools.d.ts.map +1 -0
  602. package/out/us/tools/fetch/state/hi-schools.js +112 -0
  603. package/out/us/tools/fetch/state/hi-schools.js.map +1 -0
  604. package/out/us/tools/fetch/state/sources.d.ts +26 -0
  605. package/out/us/tools/fetch/state/sources.d.ts.map +1 -0
  606. package/out/us/tools/fetch/state/sources.js +111 -0
  607. package/out/us/tools/fetch/state/sources.js.map +1 -0
  608. package/out/us/tools/fetch/tiger-full.d.ts +22 -0
  609. package/out/us/tools/fetch/tiger-full.d.ts.map +1 -0
  610. package/out/us/tools/fetch/tiger-full.js +217 -0
  611. package/out/us/tools/fetch/tiger-full.js.map +1 -0
  612. package/out/utils/align.d.ts +1 -1
  613. package/out/utils/align.d.ts.map +1 -1
  614. package/out/utils/align.js.map +1 -1
  615. package/out/utils/golden.d.ts +7 -3
  616. package/out/utils/golden.d.ts.map +1 -1
  617. package/out/utils/golden.js +12 -8
  618. package/out/utils/golden.js.map +1 -1
  619. package/out/utils/parquet.d.ts.map +1 -1
  620. package/out/utils/split.js.map +1 -1
  621. package/out/utils/wof-json.d.ts.map +1 -1
  622. package/out/utils/wof-json.js +7 -12
  623. package/out/utils/wof-json.js.map +1 -1
  624. package/out/ve/recipes/reviewed-postcode-tail.d.ts.map +1 -0
  625. package/out/ve/recipes/reviewed-postcode-tail.js.map +1 -0
  626. package/package.json +196 -46
  627. package/lib/adapters/ban/adapter.ts +0 -190
  628. package/lib/adapters/fcc-bdc/adapter.ts +0 -174
  629. package/lib/adapters/geonames-postal/adapter.ts +0 -122
  630. package/lib/adapters/gnaf/adapter.ts +0 -149
  631. package/lib/adapters/gnaf/assemble.ts +0 -225
  632. package/lib/adapters/state-hi-schools/adapter.ts +0 -170
  633. package/lib/adapters/state-ia-contractors/adapter.ts +0 -144
  634. package/lib/adapters/state-ny-notaries/adapter.ts +0 -141
  635. package/lib/adapters/state-tx-notaries/adapter.ts +0 -157
  636. package/lib/adapters/tiger/adapter.ts +0 -252
  637. package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +0 -167
  638. package/lib/adapters/usgov-imls-pls/adapter.ts +0 -143
  639. package/lib/adapters/usgov-irs-bmf/adapter.ts +0 -151
  640. package/lib/adapters/usgov-nad/adapter.ts +0 -334
  641. package/lib/adapters/usgov-nppes/adapter.ts +0 -151
  642. package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -193
  643. package/lib/adapters/wof-admin-json/adapter.ts +0 -231
  644. package/lib/adapters/wof-json-rows.ts +0 -129
  645. package/lib/adapters/wof-postalcode-json/adapter.ts +0 -176
  646. package/lib/name-prone-us-suffixes.ts +0 -12
  647. package/lib/recipes/bare-country.ts +0 -95
  648. package/lib/recipes/cz-pcfirst-preposition.ts +0 -111
  649. package/lib/recipes/fr-admin-split.ts +0 -242
  650. package/lib/recipes/fr-bare-street.ts +0 -170
  651. package/lib/recipes/fr-fragment.ts +0 -333
  652. package/lib/recipes/fr-lieudit.ts +0 -301
  653. package/lib/recipes/fr-order.ts +0 -245
  654. package/lib/recipes/german.ts +0 -359
  655. package/lib/recipes/locale.ts +0 -599
  656. package/lib/recipes/nl-postcode.ts +0 -115
  657. package/lib/recipes/no-fragment.ts +0 -219
  658. package/lib/recipes/no-street-led.ts +0 -141
  659. package/lib/recipes/no-street.ts +0 -90
  660. package/lib/recipes/po-box-cedex.ts +0 -976
  661. package/lib/recipes/po-box.ts +0 -123
  662. package/lib/recipes/si-bare-village.ts +0 -97
  663. package/lib/recipes/street-affix.ts +0 -804
  664. package/lib/recipes/street-bare.ts +0 -100
  665. package/lib/recipes/sub-venue-sources.ts +0 -877
  666. package/lib/recipes/sub-venue.ts +0 -997
  667. package/lib/synthesizers/german.ts +0 -260
  668. package/lib/tools/fetch/ban.ts +0 -289
  669. package/lib/tools/fetch/download.ts +0 -262
  670. package/lib/tools/fetch/geonames-dump.ts +0 -257
  671. package/lib/tools/fetch/geonames-postal.ts +0 -180
  672. package/lib/tools/fetch/hrsa.ts +0 -59
  673. package/lib/tools/fetch/imls-pls.ts +0 -149
  674. package/lib/tools/fetch/nad.ts +0 -341
  675. package/lib/tools/fetch/nppes.ts +0 -165
  676. package/lib/tools/fetch/state-hi-schools.ts +0 -161
  677. package/lib/tools/fetch/state-sources.ts +0 -146
  678. package/lib/tools/fetch/tiger-full.ts +0 -308
  679. package/lib/tools/golden-promote.ts +0 -337
  680. package/lib/tools/golden-relabel-street.ts +0 -683
  681. package/lib/tools/lint-slice-vocab.ts +0 -388
  682. package/lib/tools/sub-venue/harvest.ts +0 -234
  683. package/lib/tools/sub-venue/head-nouns.ts +0 -245
  684. package/lib/tools/sub-venue/surfaces.ts +0 -95
  685. package/lib/tools/sub-venue/table.ts +0 -281
  686. package/lib/tools/sub-venue/wikidata.ts +0 -85
  687. package/lib/tools/sub-venue-lexicon.ts +0 -429
  688. package/out/adapters/ban/adapter.d.ts.map +0 -1
  689. package/out/adapters/ban/adapter.js +0 -149
  690. package/out/adapters/ban/adapter.js.map +0 -1
  691. package/out/adapters/ban/street-decompose.d.ts.map +0 -1
  692. package/out/adapters/ban/street-decompose.js.map +0 -1
  693. package/out/adapters/fcc-bdc/adapter.d.ts.map +0 -1
  694. package/out/adapters/fcc-bdc/adapter.js +0 -144
  695. package/out/adapters/fcc-bdc/adapter.js.map +0 -1
  696. package/out/adapters/geonames-postal/adapter.d.ts.map +0 -1
  697. package/out/adapters/geonames-postal/adapter.js +0 -107
  698. package/out/adapters/geonames-postal/adapter.js.map +0 -1
  699. package/out/adapters/gnaf/adapter.d.ts.map +0 -1
  700. package/out/adapters/gnaf/adapter.js +0 -124
  701. package/out/adapters/gnaf/adapter.js.map +0 -1
  702. package/out/adapters/gnaf/assemble.d.ts +0 -65
  703. package/out/adapters/gnaf/assemble.d.ts.map +0 -1
  704. package/out/adapters/gnaf/assemble.js +0 -154
  705. package/out/adapters/gnaf/assemble.js.map +0 -1
  706. package/out/adapters/state-hi-schools/adapter.d.ts.map +0 -1
  707. package/out/adapters/state-hi-schools/adapter.js +0 -145
  708. package/out/adapters/state-hi-schools/adapter.js.map +0 -1
  709. package/out/adapters/state-hi-schools/workbook.d.ts.map +0 -1
  710. package/out/adapters/state-hi-schools/workbook.js.map +0 -1
  711. package/out/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
  712. package/out/adapters/state-ia-contractors/adapter.js +0 -111
  713. package/out/adapters/state-ia-contractors/adapter.js.map +0 -1
  714. package/out/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
  715. package/out/adapters/state-ny-notaries/adapter.js +0 -119
  716. package/out/adapters/state-ny-notaries/adapter.js.map +0 -1
  717. package/out/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
  718. package/out/adapters/state-tx-notaries/adapter.js +0 -125
  719. package/out/adapters/state-tx-notaries/adapter.js.map +0 -1
  720. package/out/adapters/tiger/adapter.d.ts +0 -55
  721. package/out/adapters/tiger/adapter.d.ts.map +0 -1
  722. package/out/adapters/tiger/adapter.js +0 -201
  723. package/out/adapters/tiger/adapter.js.map +0 -1
  724. package/out/adapters/tiger/street-decompose.d.ts.map +0 -1
  725. package/out/adapters/tiger/street-decompose.js.map +0 -1
  726. package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
  727. package/out/adapters/usgov-hrsa-fqhc/adapter.js +0 -132
  728. package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
  729. package/out/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
  730. package/out/adapters/usgov-imls-pls/adapter.js +0 -114
  731. package/out/adapters/usgov-imls-pls/adapter.js.map +0 -1
  732. package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
  733. package/out/adapters/usgov-irs-bmf/adapter.js +0 -120
  734. package/out/adapters/usgov-irs-bmf/adapter.js.map +0 -1
  735. package/out/adapters/usgov-nad/adapter.d.ts.map +0 -1
  736. package/out/adapters/usgov-nad/adapter.js +0 -249
  737. package/out/adapters/usgov-nad/adapter.js.map +0 -1
  738. package/out/adapters/usgov-nppes/adapter.d.ts.map +0 -1
  739. package/out/adapters/usgov-nppes/adapter.js +0 -118
  740. package/out/adapters/usgov-nppes/adapter.js.map +0 -1
  741. package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
  742. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -154
  743. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
  744. package/out/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
  745. package/out/adapters/wof-admin-jp/adapter.js.map +0 -1
  746. package/out/adapters/wof-admin-json/adapter.d.ts +0 -79
  747. package/out/adapters/wof-admin-json/adapter.d.ts.map +0 -1
  748. package/out/adapters/wof-admin-json/adapter.js +0 -197
  749. package/out/adapters/wof-admin-json/adapter.js.map +0 -1
  750. package/out/adapters/wof-json-rows.d.ts +0 -62
  751. package/out/adapters/wof-json-rows.d.ts.map +0 -1
  752. package/out/adapters/wof-json-rows.js +0 -83
  753. package/out/adapters/wof-json-rows.js.map +0 -1
  754. package/out/adapters/wof-postalcode-json/adapter.d.ts +0 -65
  755. package/out/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
  756. package/out/adapters/wof-postalcode-json/adapter.js +0 -151
  757. package/out/adapters/wof-postalcode-json/adapter.js.map +0 -1
  758. package/out/codex/us-fips-state.d.ts +0 -41
  759. package/out/codex/us-fips-state.d.ts.map +0 -1
  760. package/out/codex/us-fips-state.js +0 -100
  761. package/out/codex/us-fips-state.js.map +0 -1
  762. package/out/name-prone-us-suffixes.d.ts +0 -12
  763. package/out/name-prone-us-suffixes.d.ts.map +0 -1
  764. package/out/name-prone-us-suffixes.js +0 -12
  765. package/out/name-prone-us-suffixes.js.map +0 -1
  766. package/out/recipes/bare-country.d.ts +0 -25
  767. package/out/recipes/bare-country.d.ts.map +0 -1
  768. package/out/recipes/bare-country.js +0 -87
  769. package/out/recipes/bare-country.js.map +0 -1
  770. package/out/recipes/cn-organizational-units.d.ts +0 -36
  771. package/out/recipes/cn-organizational-units.d.ts.map +0 -1
  772. package/out/recipes/cn-organizational-units.js +0 -159
  773. package/out/recipes/cn-organizational-units.js.map +0 -1
  774. package/out/recipes/cz-pcfirst-preposition.d.ts +0 -22
  775. package/out/recipes/cz-pcfirst-preposition.d.ts.map +0 -1
  776. package/out/recipes/cz-pcfirst-preposition.js +0 -100
  777. package/out/recipes/cz-pcfirst-preposition.js.map +0 -1
  778. package/out/recipes/fr-admin-split.d.ts +0 -38
  779. package/out/recipes/fr-admin-split.d.ts.map +0 -1
  780. package/out/recipes/fr-admin-split.js +0 -192
  781. package/out/recipes/fr-admin-split.js.map +0 -1
  782. package/out/recipes/fr-bare-street.d.ts +0 -28
  783. package/out/recipes/fr-bare-street.d.ts.map +0 -1
  784. package/out/recipes/fr-bare-street.js +0 -143
  785. package/out/recipes/fr-bare-street.js.map +0 -1
  786. package/out/recipes/fr-fragment.d.ts +0 -77
  787. package/out/recipes/fr-fragment.d.ts.map +0 -1
  788. package/out/recipes/fr-fragment.js +0 -276
  789. package/out/recipes/fr-fragment.js.map +0 -1
  790. package/out/recipes/fr-lieudit.d.ts +0 -32
  791. package/out/recipes/fr-lieudit.d.ts.map +0 -1
  792. package/out/recipes/fr-lieudit.js +0 -227
  793. package/out/recipes/fr-lieudit.js.map +0 -1
  794. package/out/recipes/fr-order.d.ts +0 -38
  795. package/out/recipes/fr-order.d.ts.map +0 -1
  796. package/out/recipes/fr-order.js +0 -197
  797. package/out/recipes/fr-order.js.map +0 -1
  798. package/out/recipes/german.d.ts +0 -44
  799. package/out/recipes/german.d.ts.map +0 -1
  800. package/out/recipes/german.js +0 -288
  801. package/out/recipes/german.js.map +0 -1
  802. package/out/recipes/locale.d.ts +0 -136
  803. package/out/recipes/locale.d.ts.map +0 -1
  804. package/out/recipes/locale.js +0 -460
  805. package/out/recipes/locale.js.map +0 -1
  806. package/out/recipes/nl-postcode.d.ts +0 -26
  807. package/out/recipes/nl-postcode.d.ts.map +0 -1
  808. package/out/recipes/nl-postcode.js +0 -102
  809. package/out/recipes/nl-postcode.js.map +0 -1
  810. package/out/recipes/no-fragment.d.ts +0 -43
  811. package/out/recipes/no-fragment.d.ts.map +0 -1
  812. package/out/recipes/no-fragment.js +0 -182
  813. package/out/recipes/no-fragment.js.map +0 -1
  814. package/out/recipes/no-street-led.d.ts +0 -24
  815. package/out/recipes/no-street-led.d.ts.map +0 -1
  816. package/out/recipes/no-street-led.js +0 -113
  817. package/out/recipes/no-street-led.js.map +0 -1
  818. package/out/recipes/no-street.d.ts +0 -18
  819. package/out/recipes/no-street.d.ts.map +0 -1
  820. package/out/recipes/no-street.js +0 -71
  821. package/out/recipes/no-street.js.map +0 -1
  822. package/out/recipes/po-box-cedex.d.ts +0 -38
  823. package/out/recipes/po-box-cedex.d.ts.map +0 -1
  824. package/out/recipes/po-box-cedex.js +0 -767
  825. package/out/recipes/po-box-cedex.js.map +0 -1
  826. package/out/recipes/po-box.d.ts +0 -17
  827. package/out/recipes/po-box.d.ts.map +0 -1
  828. package/out/recipes/po-box.js +0 -100
  829. package/out/recipes/po-box.js.map +0 -1
  830. package/out/recipes/reviewed-postcode-tail.d.ts.map +0 -1
  831. package/out/recipes/reviewed-postcode-tail.js.map +0 -1
  832. package/out/recipes/si-bare-village.d.ts +0 -32
  833. package/out/recipes/si-bare-village.d.ts.map +0 -1
  834. package/out/recipes/si-bare-village.js +0 -88
  835. package/out/recipes/si-bare-village.js.map +0 -1
  836. package/out/recipes/street-affix.d.ts +0 -89
  837. package/out/recipes/street-affix.d.ts.map +0 -1
  838. package/out/recipes/street-affix.js +0 -563
  839. package/out/recipes/street-affix.js.map +0 -1
  840. package/out/recipes/street-bare.d.ts +0 -25
  841. package/out/recipes/street-bare.d.ts.map +0 -1
  842. package/out/recipes/street-bare.js +0 -86
  843. package/out/recipes/street-bare.js.map +0 -1
  844. package/out/recipes/sub-venue-sources.d.ts +0 -229
  845. package/out/recipes/sub-venue-sources.d.ts.map +0 -1
  846. package/out/recipes/sub-venue-sources.js +0 -653
  847. package/out/recipes/sub-venue-sources.js.map +0 -1
  848. package/out/recipes/sub-venue.d.ts +0 -269
  849. package/out/recipes/sub-venue.d.ts.map +0 -1
  850. package/out/recipes/sub-venue.js +0 -725
  851. package/out/recipes/sub-venue.js.map +0 -1
  852. package/out/synthesizers/german.d.ts +0 -115
  853. package/out/synthesizers/german.d.ts.map +0 -1
  854. package/out/synthesizers/german.js +0 -149
  855. package/out/synthesizers/german.js.map +0 -1
  856. package/out/tools/fetch/ban.d.ts +0 -31
  857. package/out/tools/fetch/ban.d.ts.map +0 -1
  858. package/out/tools/fetch/ban.js +0 -239
  859. package/out/tools/fetch/ban.js.map +0 -1
  860. package/out/tools/fetch/download.d.ts +0 -117
  861. package/out/tools/fetch/download.d.ts.map +0 -1
  862. package/out/tools/fetch/download.js +0 -160
  863. package/out/tools/fetch/download.js.map +0 -1
  864. package/out/tools/fetch/geonames-dump.d.ts +0 -91
  865. package/out/tools/fetch/geonames-dump.d.ts.map +0 -1
  866. package/out/tools/fetch/geonames-dump.js +0 -171
  867. package/out/tools/fetch/geonames-dump.js.map +0 -1
  868. package/out/tools/fetch/geonames-postal.d.ts +0 -76
  869. package/out/tools/fetch/geonames-postal.d.ts.map +0 -1
  870. package/out/tools/fetch/geonames-postal.js +0 -126
  871. package/out/tools/fetch/geonames-postal.js.map +0 -1
  872. package/out/tools/fetch/hrsa.d.ts +0 -18
  873. package/out/tools/fetch/hrsa.d.ts.map +0 -1
  874. package/out/tools/fetch/hrsa.js +0 -46
  875. package/out/tools/fetch/hrsa.js.map +0 -1
  876. package/out/tools/fetch/imls-pls.d.ts +0 -25
  877. package/out/tools/fetch/imls-pls.d.ts.map +0 -1
  878. package/out/tools/fetch/imls-pls.js +0 -108
  879. package/out/tools/fetch/imls-pls.js.map +0 -1
  880. package/out/tools/fetch/nad.d.ts +0 -70
  881. package/out/tools/fetch/nad.d.ts.map +0 -1
  882. package/out/tools/fetch/nad.js +0 -234
  883. package/out/tools/fetch/nad.js.map +0 -1
  884. package/out/tools/fetch/nppes.d.ts +0 -26
  885. package/out/tools/fetch/nppes.d.ts.map +0 -1
  886. package/out/tools/fetch/nppes.js +0 -126
  887. package/out/tools/fetch/nppes.js.map +0 -1
  888. package/out/tools/fetch/state-hi-schools.d.ts +0 -26
  889. package/out/tools/fetch/state-hi-schools.d.ts.map +0 -1
  890. package/out/tools/fetch/state-hi-schools.js +0 -112
  891. package/out/tools/fetch/state-hi-schools.js.map +0 -1
  892. package/out/tools/fetch/state-sources.d.ts +0 -26
  893. package/out/tools/fetch/state-sources.d.ts.map +0 -1
  894. package/out/tools/fetch/state-sources.js +0 -111
  895. package/out/tools/fetch/state-sources.js.map +0 -1
  896. package/out/tools/fetch/tiger-full.d.ts +0 -22
  897. package/out/tools/fetch/tiger-full.d.ts.map +0 -1
  898. package/out/tools/fetch/tiger-full.js +0 -217
  899. package/out/tools/fetch/tiger-full.js.map +0 -1
  900. package/out/tools/golden-expand.d.ts +0 -90
  901. package/out/tools/golden-expand.d.ts.map +0 -1
  902. package/out/tools/golden-expand.js +0 -406
  903. package/out/tools/golden-expand.js.map +0 -1
  904. package/out/tools/golden-promote.d.ts +0 -72
  905. package/out/tools/golden-promote.d.ts.map +0 -1
  906. package/out/tools/golden-promote.js +0 -240
  907. package/out/tools/golden-promote.js.map +0 -1
  908. package/out/tools/golden-relabel-street.d.ts +0 -196
  909. package/out/tools/golden-relabel-street.d.ts.map +0 -1
  910. package/out/tools/golden-relabel-street.js +0 -440
  911. package/out/tools/golden-relabel-street.js.map +0 -1
  912. package/out/tools/lint-slice-vocab.d.ts +0 -90
  913. package/out/tools/lint-slice-vocab.d.ts.map +0 -1
  914. package/out/tools/lint-slice-vocab.js +0 -267
  915. package/out/tools/lint-slice-vocab.js.map +0 -1
  916. package/out/tools/lint-slice.d.ts +0 -93
  917. package/out/tools/lint-slice.d.ts.map +0 -1
  918. package/out/tools/lint-slice.js +0 -322
  919. package/out/tools/lint-slice.js.map +0 -1
  920. package/out/tools/slice-kryptonite.d.ts +0 -32
  921. package/out/tools/slice-kryptonite.d.ts.map +0 -1
  922. package/out/tools/slice-kryptonite.js +0 -99
  923. package/out/tools/slice-kryptonite.js.map +0 -1
  924. package/out/tools/slice-translit.d.ts +0 -51
  925. package/out/tools/slice-translit.d.ts.map +0 -1
  926. package/out/tools/slice-translit.js +0 -166
  927. package/out/tools/slice-translit.js.map +0 -1
  928. package/out/tools/sub-venue/harvest.d.ts +0 -100
  929. package/out/tools/sub-venue/harvest.d.ts.map +0 -1
  930. package/out/tools/sub-venue/harvest.js +0 -168
  931. package/out/tools/sub-venue/harvest.js.map +0 -1
  932. package/out/tools/sub-venue/head-nouns.d.ts +0 -50
  933. package/out/tools/sub-venue/head-nouns.d.ts.map +0 -1
  934. package/out/tools/sub-venue/head-nouns.js.map +0 -1
  935. package/out/tools/sub-venue/surfaces.d.ts +0 -45
  936. package/out/tools/sub-venue/surfaces.d.ts.map +0 -1
  937. package/out/tools/sub-venue/surfaces.js.map +0 -1
  938. package/out/tools/sub-venue/table.d.ts +0 -229
  939. package/out/tools/sub-venue/table.d.ts.map +0 -1
  940. package/out/tools/sub-venue/table.js.map +0 -1
  941. package/out/tools/sub-venue/wikidata.d.ts +0 -26
  942. package/out/tools/sub-venue/wikidata.d.ts.map +0 -1
  943. package/out/tools/sub-venue/wikidata.js +0 -62
  944. package/out/tools/sub-venue/wikidata.js.map +0 -1
  945. package/out/tools/sub-venue-lexicon.d.ts +0 -156
  946. package/out/tools/sub-venue-lexicon.d.ts.map +0 -1
  947. package/out/tools/sub-venue-lexicon.js +0 -283
  948. package/out/tools/sub-venue-lexicon.js.map +0 -1
  949. package/out/tools/sub-venue-promotions.d.ts +0 -94
  950. package/out/tools/sub-venue-promotions.d.ts.map +0 -1
  951. package/out/tools/sub-venue-promotions.js +0 -266
  952. package/out/tools/sub-venue-promotions.js.map +0 -1
  953. /package/lib/{recipes/cn-organizational-units.ts → cn/recipes/organizational-units.ts} +0 -0
  954. /package/lib/{adapters → fr/adapters}/ban/street-decompose.ts +0 -0
  955. /package/lib/{adapters/wof-admin-jp → jp/adapters/wof-admin}/adapter.ts +0 -0
  956. /package/lib/tools/{golden-expand.ts → golden/expand.ts} +0 -0
  957. /package/lib/tools/{lint-slice.ts → lint/slice/index.ts} +0 -0
  958. /package/lib/tools/{slice-kryptonite.ts → slice/kryptonite.ts} +0 -0
  959. /package/lib/tools/{slice-translit.ts → slice/translit.ts} +0 -0
  960. /package/lib/tools/{sub-venue-promotions.ts → sub/venue/promotions.ts} +0 -0
  961. /package/lib/{adapters/state-hi-schools → us/adapters/state/hi-schools}/workbook.ts +0 -0
  962. /package/lib/{adapters → us/adapters}/tiger/street-decompose.ts +0 -0
  963. /package/lib/{codex/us-fips-state.ts → us/fips-state.ts} +0 -0
  964. /package/lib/{recipes → ve/recipes}/reviewed-postcode-tail.ts +0 -0
  965. /package/out/adapters/{geonames-postal → geonames/postal}/adapter.d.ts +0 -0
  966. /package/out/{adapters → au/adapters}/gnaf/adapter.d.ts +0 -0
  967. /package/out/{adapters → fr/adapters}/ban/adapter.d.ts +0 -0
  968. /package/out/{adapters → fr/adapters}/ban/street-decompose.d.ts +0 -0
  969. /package/out/{adapters → fr/adapters}/ban/street-decompose.js +0 -0
  970. /package/out/{adapters/wof-admin-jp → jp/adapters/wof-admin}/adapter.d.ts +0 -0
  971. /package/out/{adapters/wof-admin-jp → jp/adapters/wof-admin}/adapter.js +0 -0
  972. /package/out/tools/{sub-venue → sub/venue}/head-nouns.js +0 -0
  973. /package/out/tools/{sub-venue → sub/venue}/surfaces.js +0 -0
  974. /package/out/tools/{sub-venue → sub/venue}/table.js +0 -0
  975. /package/out/{adapters → us/adapters}/fcc-bdc/adapter.d.ts +0 -0
  976. /package/out/{adapters/state-hi-schools → us/adapters/state/hi-schools}/adapter.d.ts +0 -0
  977. /package/out/{adapters/state-hi-schools → us/adapters/state/hi-schools}/workbook.d.ts +0 -0
  978. /package/out/{adapters/state-hi-schools → us/adapters/state/hi-schools}/workbook.js +0 -0
  979. /package/out/{adapters/state-ia-contractors → us/adapters/state/ia-contractors}/adapter.d.ts +0 -0
  980. /package/out/{adapters/state-ny-notaries → us/adapters/state/ny-notaries}/adapter.d.ts +0 -0
  981. /package/out/{adapters/state-tx-notaries → us/adapters/state/tx-notaries}/adapter.d.ts +0 -0
  982. /package/out/{adapters → us/adapters}/tiger/street-decompose.d.ts +0 -0
  983. /package/out/{adapters → us/adapters}/tiger/street-decompose.js +0 -0
  984. /package/out/{adapters/usgov-hrsa-fqhc → us/adapters/usgov/hrsa-fqhc}/adapter.d.ts +0 -0
  985. /package/out/{adapters/usgov-imls-pls → us/adapters/usgov/imls-pls}/adapter.d.ts +0 -0
  986. /package/out/{adapters/usgov-irs-bmf → us/adapters/usgov/irs-bmf}/adapter.d.ts +0 -0
  987. /package/out/{adapters/usgov-nad → us/adapters/usgov/nad}/adapter.d.ts +0 -0
  988. /package/out/{adapters/usgov-nppes → us/adapters/usgov/nppes}/adapter.d.ts +0 -0
  989. /package/out/{adapters/usgov-samhsa-treatment-locator → us/adapters/usgov/samhsa-treatment-locator}/adapter.d.ts +0 -0
  990. /package/out/{recipes → ve/recipes}/reviewed-postcode-tail.d.ts +0 -0
  991. /package/out/{recipes → ve/recipes}/reviewed-postcode-tail.js +0 -0
@@ -1,111 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * Re-fetch the state-level open-data sources (NY/TX/DE/OR notaries, IA contractors, WA health
7
- * providers, HI lobbyists). Reproducible recovery if `$MAILWOMAN_DATA_ROOT` is lost.
8
- *
9
- * HI public schools is fetched separately by `mailwoman corpus fetch state-hi-schools` — its
10
- * upstream is an XLSX workbook that requires an openpyxl-driven sheet-concatenation pre-step
11
- * before the adapter can consume it.
12
- *
13
- * Each source lands in its own subdirectory of `<outRoot>/<slug>/` along with a `MANIFEST.json`
14
- * recording origin URL + download timestamp + sha256 so downstream adapters can verify provenance.
15
- *
16
- * Invoke via `mailwoman corpus fetch state-sources --out-root <path>`. Uses Node's built-in fetch
17
- * (gzip/brotli) and streaming sha256 instead of curl + sha256sum.
18
- */
19
- import { BYTES_PER_KIB } from "@mailwoman/core/fs/formatters";
20
- import { makeDirectories } from "@mailwoman/core/fs/writers";
21
- import { sha256File } from "@mailwoman/core/hash";
22
- import { join } from "path-ts";
23
- import { downloadToFile, writeManifest } from "#tools/fetch/download";
24
- const SOURCES = [
25
- {
26
- slug: "state-ny-notaries",
27
- filename: "NY_Commissioned_Notaries.csv",
28
- url: "https://data.ny.gov/api/views/rwbv-mz6z/rows.csv?accessType=DOWNLOAD",
29
- },
30
- {
31
- slug: "state-tx-notaries",
32
- filename: "TX_Notary_Public_Commissions.csv",
33
- url: "https://data.texas.gov/api/views/gmd3-bnrd/rows.csv?accessType=DOWNLOAD",
34
- },
35
- {
36
- slug: "state-de-notaries",
37
- filename: "DE_Notaries_Commissioned.csv",
38
- url: "https://data.delaware.gov/api/views/q8dr-mj6p/rows.csv?accessType=DOWNLOAD",
39
- },
40
- {
41
- slug: "state-or-notaries",
42
- filename: "OR_Active_Notaries.csv",
43
- url: "https://data.oregon.gov/api/views/j2pk-zk6z/rows.csv?accessType=DOWNLOAD",
44
- },
45
- {
46
- slug: "state-ia-contractors",
47
- filename: "IA_Active_Construction_Contractor_Registrations.csv",
48
- url: "https://data.iowa.gov/api/views/dpf3-iz94/rows.csv?accessType=DOWNLOAD",
49
- },
50
- {
51
- slug: "state-wa-health-providers",
52
- filename: "WA_Health_Care_Provider_Credential_Data.csv",
53
- url: "https://data.wa.gov/api/views/qxh8-f4bd/rows.csv?accessType=DOWNLOAD",
54
- },
55
- {
56
- slug: "state-hi-lobbyists",
57
- filename: "HI_Lobbyist_Registration_Statements.csv",
58
- url: "https://data.hawaii.gov/api/views/cm7c-skav/rows.csv?accessType=DOWNLOAD",
59
- },
60
- ];
61
- export async function fetchStateSources(options, report) {
62
- await makeDirectories(options.outRoot);
63
- let fetched = 0;
64
- let failed = 0;
65
- const failedCodes = [];
66
- for (const { slug, filename, url } of SOURCES) {
67
- const destDir = join(options.outRoot, slug);
68
- await makeDirectories(destDir);
69
- const dest = join(destDir, filename);
70
- report?.(`=== ${slug} / ${filename}`);
71
- let bytes;
72
- try {
73
- ;
74
- ({ bytes } = await downloadToFile({
75
- url,
76
- dest,
77
- timeoutMs: 600_000,
78
- headers: { "Accept-Encoding": "gzip, br" },
79
- report,
80
- }));
81
- }
82
- catch (error) {
83
- report?.(` ✗ download failed for ${url}: ${error.message}`);
84
- failed++;
85
- failedCodes.push(slug);
86
- continue;
87
- }
88
- if (bytes < BYTES_PER_KIB) {
89
- report?.(` ✗ response too small (${bytes} bytes) — probable 404 / error page`);
90
- failed++;
91
- failedCodes.push(slug);
92
- continue;
93
- }
94
- const sha = await sha256File(dest);
95
- const manifest = {
96
- source_url: url,
97
- downloaded_at: new Date().toISOString(),
98
- filename,
99
- sha256: sha,
100
- bytes,
101
- };
102
- await writeManifest(join(destDir, "MANIFEST.json"), manifest);
103
- report?.(` ✓ ${(bytes / 1024 / 1024).toFixed(1)} MB sha256=${sha}`);
104
- fetched++;
105
- }
106
- report?.(`=== summary ===`);
107
- report?.(`fetched: ${fetched}`);
108
- report?.(`failed: ${failed}`);
109
- return { fetched, skipped: 0, failed, failedCodes };
110
- }
111
- //# sourceMappingURL=state-sources.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"state-sources.js","sourceRoot":"","sources":["../../../lib/tools/fetch/state-sources.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;GAiBG;AAEH,OAAO,EAAE,aAAa,EAAE,MAAM,+BAA+B,CAAA;AAC7D,OAAO,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAA;AAC5D,OAAO,EAAE,UAAU,EAAE,MAAM,sBAAsB,CAAA;AACjD,OAAO,EAAE,IAAI,EAAE,MAAM,SAAS,CAAA;AAG9B,OAAO,EAAE,cAAc,EAAE,aAAa,EAAE,MAAM,uBAAuB,CAAA;AAerE,MAAM,OAAO,GAAsB;IAClC;QACC,IAAI,EAAE,mBAAmB;QACzB,QAAQ,EAAE,8BAA8B;QACxC,GAAG,EAAE,sEAAsE;KAC3E;IACD;QACC,IAAI,EAAE,mBAAmB;QACzB,QAAQ,EAAE,kCAAkC;QAC5C,GAAG,EAAE,yEAAyE;KAC9E;IACD;QACC,IAAI,EAAE,mBAAmB;QACzB,QAAQ,EAAE,8BAA8B;QACxC,GAAG,EAAE,4EAA4E;KACjF;IACD;QACC,IAAI,EAAE,mBAAmB;QACzB,QAAQ,EAAE,wBAAwB;QAClC,GAAG,EAAE,0EAA0E;KAC/E;IACD;QACC,IAAI,EAAE,sBAAsB;QAC5B,QAAQ,EAAE,qDAAqD;QAC/D,GAAG,EAAE,wEAAwE;KAC7E;IACD;QACC,IAAI,EAAE,2BAA2B;QACjC,QAAQ,EAAE,6CAA6C;QACvD,GAAG,EAAE,sEAAsE;KAC3E;IACD;QACC,IAAI,EAAE,oBAAoB;QAC1B,QAAQ,EAAE,yCAAyC;QACnD,GAAG,EAAE,0EAA0E;KAC/E;CACD,CAAA;AAED,MAAM,CAAC,KAAK,UAAU,iBAAiB,CACtC,OAAiC,EACjC,MAA+B;IAE/B,MAAM,eAAe,CAAC,OAAO,CAAC,OAAO,CAAC,CAAA;IAEtC,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,MAAM,GAAG,CAAC,CAAA;IACd,MAAM,WAAW,GAAa,EAAE,CAAA;IAEhC,KAAK,MAAM,EAAE,IAAI,EAAE,QAAQ,EAAE,GAAG,EAAE,IAAI,OAAO,EAAE,CAAC;QAC/C,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,IAAI,CAAC,CAAA;QAC3C,MAAM,eAAe,CAAC,OAAO,CAAC,CAAA;QAC9B,MAAM,IAAI,GAAG,IAAI,CAAC,OAAO,EAAE,QAAQ,CAAC,CAAA;QAEpC,MAAM,EAAE,CAAC,OAAO,IAAI,MAAM,QAAQ,EAAE,CAAC,CAAA;QAErC,IAAI,KAAa,CAAA;QAEjB,IAAI,CAAC;YACJ,CAAC;YAAA,CAAC,EAAE,KAAK,EAAE,GAAG,MAAM,cAAc,CAAC;gBAClC,GAAG;gBACH,IAAI;gBACJ,SAAS,EAAE,OAAO;gBAClB,OAAO,EAAE,EAAE,iBAAiB,EAAE,UAAU,EAAE;gBAC1C,MAAM;aACN,CAAC,CAAC,CAAA;QACJ,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,MAAM,EAAE,CAAC,2BAA2B,GAAG,KAAM,KAAe,CAAC,OAAO,EAAE,CAAC,CAAA;YAEvE,MAAM,EAAE,CAAA;YACR,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;YAEtB,SAAQ;QACT,CAAC;QAED,IAAI,KAAK,GAAG,aAAa,EAAE,CAAC;YAC3B,MAAM,EAAE,CAAC,2BAA2B,KAAK,qCAAqC,CAAC,CAAA;YAE/E,MAAM,EAAE,CAAA;YACR,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;YAEtB,SAAQ;QACT,CAAC;QAED,MAAM,GAAG,GAAG,MAAM,UAAU,CAAC,IAAI,CAAC,CAAA;QAElC,MAAM,QAAQ,GAAmB;YAChC,UAAU,EAAE,GAAG;YACf,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;YACvC,QAAQ;YACR,MAAM,EAAE,GAAG;YACX,KAAK;SACL,CAAA;QAED,MAAM,aAAa,CAAC,IAAI,CAAC,OAAO,EAAE,eAAe,CAAC,EAAE,QAAQ,CAAC,CAAA;QAE7D,MAAM,EAAE,CAAC,OAAO,CAAC,KAAK,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe,GAAG,EAAE,CAAC,CAAA;QAErE,OAAO,EAAE,CAAA;IACV,CAAC;IAED,MAAM,EAAE,CAAC,iBAAiB,CAAC,CAAA;IAC3B,MAAM,EAAE,CAAC,YAAY,OAAO,EAAE,CAAC,CAAA;IAC/B,MAAM,EAAE,CAAC,YAAY,MAAM,EAAE,CAAC,CAAA;IAE9B,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,WAAW,EAAE,CAAA;AACpD,CAAC"}
@@ -1,22 +0,0 @@
1
- import type { BaseFetchOptions, FetchSummary } from "#tools/fetch/download";
2
- export interface FetchTigerFullOptions extends BaseFetchOptions {
3
- /**
4
- * Space-separated list of 2-digit state FIPS codes to skip entirely. Default `"50"` — Vermont, already fetched in
5
- * v0.1.1.
6
- */
7
- skipStateFips?: string;
8
- /**
9
- * Seconds to sleep between downloads. Default `0.2`.
10
- */
11
- rateSleep?: number;
12
- /**
13
- * Max concurrent download workers per state. Default `4`.
14
- */
15
- maxParallel?: number;
16
- /**
17
- * Print planned downloads without fetching. Default `false`.
18
- */
19
- dryRun?: boolean;
20
- }
21
- export declare function fetchTigerFull(options: FetchTigerFullOptions, report?: (line: string) => void): Promise<FetchSummary>;
22
- //# sourceMappingURL=tiger-full.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"tiger-full.d.ts","sourceRoot":"","sources":["../../../lib/tools/fetch/tiger-full.ts"],"names":[],"mappings":"AA+BA,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAA;AAmB3E,MAAM,WAAW,qBAAsB,SAAQ,gBAAgB;IAC9D;;;OAGG;IACH,aAAa,CAAC,EAAE,MAAM,CAAA;IACtB;;OAEG;IACH,SAAS,CAAC,EAAE,MAAM,CAAA;IAClB;;OAEG;IACH,WAAW,CAAC,EAAE,MAAM,CAAA;IACpB;;OAEG;IACH,MAAM,CAAC,EAAE,OAAO,CAAA;CAChB;AA+DD,wBAAsB,cAAc,CACnC,OAAO,EAAE,qBAAqB,EAC9B,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,YAAY,CAAC,CA6KvB"}
@@ -1,217 +0,0 @@
1
- import { APIClient, pluckResponseData } from "@mailwoman/core/api";
2
- /**
3
- * @copyright Sister Software
4
- * @license AGPL-3.0
5
- * @author Teffen Ellis, et al.
6
- *
7
- * Fetch the full TIGER 2024 ADDRFEAT dataset — all US counties.
8
- *
9
- * TIGER ADDRFEAT 2024 source:
10
- *
11
- * - https://www2.census.gov/geo/tiger/TIGER2024/ADDRFEAT/
12
- * - Files: `tl_2024_<statefips><countyfips>_addrfeat.zip`
13
- *
14
- * Each state's ZIPs land in `<outRoot>/tiger/addrfeat/state-<statefips>/` with a per-state
15
- * `MANIFEST.json` recording filename, sha256, and bytes for every county ZIP so re-runs can skip
16
- * already-verified files. (Extraction + ogr2ogr ingestion happen later, in the `tiger` adapter;
17
- * this module is download + provenance only.)
18
- *
19
- * Invoke via `mailwoman corpus fetch tiger-full --out-root <path>`. Native `fetch` streams each
20
- * county ZIP to disk (no curl subprocess).
21
- */
22
- /* oxlint-disable sister-software/prefer-region-over-marks -- these markers label steps inside one
23
- procedure, not sections of declarations. A region there folds nothing a reader wants folded. */
24
- import { BYTES_PER_KIB, ByteFormatter } from "@mailwoman/core/fs/formatters";
25
- import { statPath, pathExists } from "@mailwoman/core/fs/readers";
26
- import { makeDirectories, removePathIfPresent } from "@mailwoman/core/fs/writers";
27
- import { sha256File } from "@mailwoman/core/hash";
28
- import { isoSeconds } from "@mailwoman/core/utils";
29
- import { sleep } from "@mailwoman/core/utils/sleep";
30
- import { basename, join } from "path-ts";
31
- import { readManifest, streamDownload, writeManifest } from "#tools/fetch/download";
32
- /**
33
- * Bytes per KiB — the divisor for human-readable sizes, and the floor below which a "download" is an error page rather
34
- * than data.
35
- */
36
- /**
37
- * Lowest 2xx status; anything below is informational.
38
- */
39
- const HTTP_OK = 200;
40
- /**
41
- * Lowest 3xx status; at or above it the response is a redirect or an error, not a body.
42
- */
43
- const HTTP_REDIRECT = 300;
44
- const TIGER_BASE_URL = "https://www2.census.gov/geo/tiger/TIGER2024/ADDRFEAT";
45
- /**
46
- * Read a per-state MANIFEST.json into a filename → entry map.
47
- */
48
- async function readCountyManifest(manifestPath) {
49
- const map = new Map();
50
- const parsed = await readManifest(manifestPath);
51
- for (const c of parsed?.counties ?? []) {
52
- if (c.filename) {
53
- map.set(c.filename, { filename: c.filename, sha256: c.sha256, bytes: c.bytes });
54
- }
55
- }
56
- return map;
57
- }
58
- /**
59
- * Check whether a file already matches a recorded sha256 and byte count.
60
- */
61
- async function fileMatchesSha(path, expectedSha, expectedBytes) {
62
- if (!(await pathExists(path)))
63
- return false;
64
- if ((await statPath(path)).size !== expectedBytes)
65
- return false;
66
- return (await sha256File(path)) === expectedSha;
67
- }
68
- /**
69
- * Download one county ZIP (size sanity check + sha256).
70
- */
71
- async function downloadCounty(url, dest) {
72
- const filename = basename(dest);
73
- const status = await streamDownload(url, dest, { timeoutMs: 600_000, retries: 3, retryDelayMs: 5000 });
74
- if (status < HTTP_OK || status >= HTTP_REDIRECT) {
75
- return { ok: false, filename, reason: `HTTP ${status}` };
76
- }
77
- const bytes = (await statPath(dest)).size;
78
- if (bytes < BYTES_PER_KIB) {
79
- await removePathIfPresent(dest);
80
- return { ok: false, filename, reason: `too small (${bytes} bytes)` };
81
- }
82
- const sha256 = await sha256File(dest);
83
- return { ok: true, filename, sha256, bytes };
84
- }
85
- export async function fetchTigerFull(options, report) {
86
- const skipStateFips = (options.skipStateFips ?? "50").split(/\s+/).filter((value) => value.length > 0);
87
- const rateSleepMs = Math.round((options.rateSleep ?? 0.2) * 1000);
88
- const maxParallel = options.maxParallel ?? 4;
89
- const dryRun = options.dryRun ?? false;
90
- const addrfeatDir = join(options.outRoot, "tiger", "addrfeat");
91
- await makeDirectories(addrfeatDir);
92
- // MARK: Step 1 — discover the county file list
93
- report?.(`=== Fetching TIGER 2024 ADDRFEAT directory listing...`);
94
- // `responseType: "text"` — an Apache directory index, scraped below. The per-county ARCHIVE downloads
95
- // stay on raw `fetch` (they stream to disk; see `downloadOne`).
96
- const listingRes = await new APIClient({
97
- displayName: "tiger-listing",
98
- retry: true,
99
- axios: { headers: { "Accept-Encoding": "gzip, br" } },
100
- })
101
- .fetch({ url: `${TIGER_BASE_URL}/`, responseType: "text", timeout: 60_000 })
102
- .then(pluckResponseData);
103
- const html = listingRes;
104
- const allZips = [...new Set(html.match(/tl_2024_[0-9]{5}_addrfeat\.zip/g))].toSorted();
105
- const totalCounties = allZips.length;
106
- report?.(` Found ${totalCounties} county ZIPs in the TIGER 2024 ADDRFEAT index.`);
107
- // Build a map: state_fips -> list of filenames.
108
- // tl_2024_SSCCC_addrfeat.zip — SS = 2-digit state FIPS (chars 8-9), CCC = county FIPS.
109
- const stateFiles = new Map();
110
- for (const fname of allZips) {
111
- const stateFips = fname.slice(8, 10);
112
- const list = stateFiles.get(stateFips) ?? [];
113
- list.push(fname);
114
- stateFiles.set(stateFips, list);
115
- }
116
- report?.(` Spans ${stateFiles.size} state/territory FIPS codes.`);
117
- // MARK: Step 2 — download the county ZIPs
118
- let totalFetched = 0;
119
- let totalSkipped = 0;
120
- let totalSkippedState = 0;
121
- let totalFailed = 0;
122
- let totalBytesFetched = 0;
123
- const failedCodes = [];
124
- // Process states in sorted FIPS order for predictable output.
125
- const sortedStates = [...stateFiles.keys()].toSorted();
126
- for (const stateFips of sortedStates) {
127
- const countyFiles = stateFiles.get(stateFips) ?? [];
128
- // --- Skip entire state if requested ------------------------------------------
129
- if (skipStateFips.includes(stateFips)) {
130
- report?.(`--- State ${stateFips} — SKIPPED (in --skip-state-fips, ${countyFiles.length} counties)`);
131
- totalSkippedState += countyFiles.length;
132
- continue;
133
- }
134
- const stateDir = join(addrfeatDir, `state-${stateFips}`);
135
- await makeDirectories(stateDir);
136
- const manifestPath = join(stateDir, "MANIFEST.json");
137
- // Load existing manifest for O(1) verified-skip lookup.
138
- const manifest = await readCountyManifest(manifestPath);
139
- report?.(`--- State ${stateFips} — ${countyFiles.length} counties`);
140
- // Build a list of URLs+dests that need fetching.
141
- const pending = [];
142
- for (const fname of countyFiles) {
143
- const dest = join(stateDir, fname);
144
- const url = `${TIGER_BASE_URL}/${fname}`;
145
- const known = manifest.get(fname);
146
- // Skip if already verified via MANIFEST.
147
- if (known && (await fileMatchesSha(dest, known.sha256, known.bytes))) {
148
- report?.(` skip (verified) ${fname}`);
149
- totalSkipped++;
150
- continue;
151
- }
152
- if (dryRun) {
153
- report?.(` would fetch: ${url}`);
154
- totalFetched++;
155
- continue;
156
- }
157
- pending.push({ url, dest });
158
- }
159
- if (dryRun)
160
- continue;
161
- if (!pending.length)
162
- continue;
163
- // --- Download pending files with bounded parallelism + rate-limit spacing ---
164
- const results = Array.from({ length: pending.length });
165
- let cursor = 0;
166
- const workers = Array.from({ length: Math.min(maxParallel, pending.length) }, async () => {
167
- while (true) {
168
- const i = cursor++;
169
- if (i >= pending.length)
170
- return;
171
- const item = pending[i];
172
- // Rate-limit: polite spacing before each fetch.
173
- await sleep(rateSleepMs);
174
- results[i] = await downloadCounty(item.url, item.dest);
175
- }
176
- });
177
- await Promise.all(workers);
178
- // Collect results from this state.
179
- for (const result of results) {
180
- if (result.ok) {
181
- report?.(` ok ${result.filename} ${ByteFormatter.formatIEC(result.bytes)} sha256=${result.sha256.slice(0, 12)}...`);
182
- manifest.set(result.filename, { filename: result.filename, sha256: result.sha256, bytes: result.bytes });
183
- totalFetched++;
184
- totalBytesFetched += result.bytes;
185
- }
186
- else {
187
- report?.(` FAIL ${result.filename} -- ${result.reason}`);
188
- totalFailed++;
189
- failedCodes.push(result.filename);
190
- }
191
- }
192
- // Rewrite per-state MANIFEST.json with all known-good counties (sorted for determinism).
193
- const counties = [...manifest.values()].toSorted((a, b) => a.filename.localeCompare(b.filename));
194
- const manifestDoc = {
195
- state_fips: stateFips,
196
- updated_at: isoSeconds(),
197
- tiger_base_url: TIGER_BASE_URL,
198
- counties,
199
- };
200
- await writeManifest(manifestPath, manifestDoc);
201
- }
202
- // MARK: Summary
203
- report?.(`=== Summary ===`);
204
- report?.(` Total counties in index : ${totalCounties}`);
205
- report?.(` State(s) fully skipped : ${totalSkippedState} (--skip-state-fips "${skipStateFips.join(" ")}")`);
206
- report?.(` Counties already present : ${totalSkipped}`);
207
- report?.(` Counties fetched this run : ${totalFetched}`);
208
- report?.(` Counties failed : ${totalFailed}`);
209
- if (totalBytesFetched > 0) {
210
- report?.(` Bytes fetched this run : ${ByteFormatter.formatIEC(totalBytesFetched)} (${totalBytesFetched})`);
211
- }
212
- if (totalFailed > 0) {
213
- report?.(`WARNING: ${totalFailed} download(s) failed. Re-run to retry.`);
214
- }
215
- return { fetched: totalFetched, skipped: totalSkipped + totalSkippedState, failed: totalFailed, failedCodes };
216
- }
217
- //# sourceMappingURL=tiger-full.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"tiger-full.js","sourceRoot":"","sources":["../../../lib/tools/fetch/tiger-full.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,SAAS,EAAE,iBAAiB,EAAE,MAAM,qBAAqB,CAAA;AAClE;;;;;;;;;;;;;;;;;;;GAmBG;AACH;kGACkG;AAClG,OAAO,EAAE,aAAa,EAAE,aAAa,EAAE,MAAM,+BAA+B,CAAA;AAC5E,OAAO,EAAE,QAAQ,EAAE,UAAU,EAAE,MAAM,4BAA4B,CAAA;AACjE,OAAO,EAAE,eAAe,EAAE,mBAAmB,EAAE,MAAM,4BAA4B,CAAA;AACjF,OAAO,EAAE,UAAU,EAAE,MAAM,sBAAsB,CAAA;AACjD,OAAO,EAAE,UAAU,EAAE,MAAM,uBAAuB,CAAA;AAClD,OAAO,EAAE,KAAK,EAAE,MAAM,6BAA6B,CAAA;AACnD,OAAO,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,SAAS,CAAA;AAGxC,OAAO,EAAE,YAAY,EAAE,cAAc,EAAE,aAAa,EAAE,MAAM,uBAAuB,CAAA;AAEnF;;;GAGG;AACH;;GAEG;AACH,MAAM,OAAO,GAAG,GAAG,CAAA;AAEnB;;GAEG;AACH,MAAM,aAAa,GAAG,GAAG,CAAA;AAEzB,MAAM,cAAc,GAAG,sDAAsD,CAAA;AA4B7E;;GAEG;AACH,KAAK,UAAU,kBAAkB,CAAC,YAAoB;IACrD,MAAM,GAAG,GAAG,IAAI,GAAG,EAAuB,CAAA;IAC1C,MAAM,MAAM,GAAG,MAAM,YAAY,CAA+B,YAAY,CAAC,CAAA;IAE7E,KAAK,MAAM,CAAC,IAAI,MAAM,EAAE,QAAQ,IAAI,EAAE,EAAE,CAAC;QACxC,IAAI,CAAC,CAAC,QAAQ,EAAE,CAAC;YAChB,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,QAAQ,EAAE,EAAE,QAAQ,EAAE,CAAC,CAAC,QAAQ,EAAE,MAAM,EAAE,CAAC,CAAC,MAAM,EAAE,KAAK,EAAE,CAAC,CAAC,KAAK,EAAE,CAAC,CAAA;QAChF,CAAC;IACF,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC;AAED;;GAEG;AACH,KAAK,UAAU,cAAc,CAAC,IAAY,EAAE,WAAmB,EAAE,aAAqB;IACrF,IAAI,CAAC,CAAC,MAAM,UAAU,CAAC,IAAI,CAAC,CAAC;QAAE,OAAO,KAAK,CAAA;IAE3C,IAAI,CAAC,MAAM,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,KAAK,aAAa;QAAE,OAAO,KAAK,CAAA;IAE/D,OAAO,CAAC,MAAM,UAAU,CAAC,IAAI,CAAC,CAAC,KAAK,WAAW,CAAA;AAChD,CAAC;AAMD;;GAEG;AACH,KAAK,UAAU,cAAc,CAAC,GAAW,EAAE,IAAY;IACtD,MAAM,QAAQ,GAAG,QAAQ,CAAC,IAAI,CAAC,CAAA;IAC/B,MAAM,MAAM,GAAG,MAAM,cAAc,CAAC,GAAG,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,YAAY,EAAE,IAAI,EAAE,CAAC,CAAA;IAEtG,IAAI,MAAM,GAAG,OAAO,IAAI,MAAM,IAAI,aAAa,EAAE,CAAC;QACjD,OAAO,EAAE,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,MAAM,EAAE,QAAQ,MAAM,EAAE,EAAE,CAAA;IACzD,CAAC;IAED,MAAM,KAAK,GAAG,CAAC,MAAM,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,CAAA;IAEzC,IAAI,KAAK,GAAG,aAAa,EAAE,CAAC;QAC3B,MAAM,mBAAmB,CAAC,IAAI,CAAC,CAAA;QAE/B,OAAO,EAAE,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,MAAM,EAAE,cAAc,KAAK,SAAS,EAAE,CAAA;IACrE,CAAC;IAED,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,IAAI,CAAC,CAAA;IAErC,OAAO,EAAE,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,MAAM,EAAE,KAAK,EAAE,CAAA;AAC7C,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,cAAc,CACnC,OAA8B,EAC9B,MAA+B;IAE/B,MAAM,aAAa,GAAG,CAAC,OAAO,CAAC,aAAa,IAAI,IAAI,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,CAAC,CAAA;IACtG,MAAM,WAAW,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,OAAO,CAAC,SAAS,IAAI,GAAG,CAAC,GAAG,IAAI,CAAC,CAAA;IACjE,MAAM,WAAW,GAAG,OAAO,CAAC,WAAW,IAAI,CAAC,CAAA;IAC5C,MAAM,MAAM,GAAG,OAAO,CAAC,MAAM,IAAI,KAAK,CAAA;IAEtC,MAAM,WAAW,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,OAAO,EAAE,UAAU,CAAC,CAAA;IAC9D,MAAM,eAAe,CAAC,WAAW,CAAC,CAAA;IAElC,+CAA+C;IAE/C,MAAM,EAAE,CAAC,uDAAuD,CAAC,CAAA;IAEjE,sGAAsG;IACtG,gEAAgE;IAChE,MAAM,UAAU,GAAG,MAAM,IAAI,SAAS,CAAC;QACtC,WAAW,EAAE,eAAe;QAC5B,KAAK,EAAE,IAAI;QACX,KAAK,EAAE,EAAE,OAAO,EAAE,EAAE,iBAAiB,EAAE,UAAU,EAAE,EAAE;KACrD,CAAC;SACA,KAAK,CAAS,EAAE,GAAG,EAAE,GAAG,cAAc,GAAG,EAAE,YAAY,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC;SACnF,IAAI,CAAC,iBAAiB,CAAC,CAAA;IAEzB,MAAM,IAAI,GAAG,UAAU,CAAA;IACvB,MAAM,OAAO,GAAG,CAAC,GAAG,IAAI,GAAG,CAAC,IAAI,CAAC,KAAK,CAAC,iCAAiC,CAAC,CAAC,CAAC,CAAC,QAAQ,EAAE,CAAA;IACtF,MAAM,aAAa,GAAG,OAAO,CAAC,MAAM,CAAA;IACpC,MAAM,EAAE,CAAC,WAAW,aAAa,gDAAgD,CAAC,CAAA;IAElF,gDAAgD;IAChD,uFAAuF;IACvF,MAAM,UAAU,GAAG,IAAI,GAAG,EAAoB,CAAA;IAE9C,KAAK,MAAM,KAAK,IAAI,OAAO,EAAE,CAAC;QAC7B,MAAM,SAAS,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,EAAE,CAAC,CAAA;QACpC,MAAM,IAAI,GAAG,UAAU,CAAC,GAAG,CAAC,SAAS,CAAC,IAAI,EAAE,CAAA;QAC5C,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;QAChB,UAAU,CAAC,GAAG,CAAC,SAAS,EAAE,IAAI,CAAC,CAAA;IAChC,CAAC;IAED,MAAM,EAAE,CAAC,WAAW,UAAU,CAAC,IAAI,8BAA8B,CAAC,CAAA;IAElE,0CAA0C;IAE1C,IAAI,YAAY,GAAG,CAAC,CAAA;IACpB,IAAI,YAAY,GAAG,CAAC,CAAA;IACpB,IAAI,iBAAiB,GAAG,CAAC,CAAA;IACzB,IAAI,WAAW,GAAG,CAAC,CAAA;IACnB,IAAI,iBAAiB,GAAG,CAAC,CAAA;IACzB,MAAM,WAAW,GAAa,EAAE,CAAA;IAEhC,8DAA8D;IAC9D,MAAM,YAAY,GAAG,CAAC,GAAG,UAAU,CAAC,IAAI,EAAE,CAAC,CAAC,QAAQ,EAAE,CAAA;IAEtD,KAAK,MAAM,SAAS,IAAI,YAAY,EAAE,CAAC;QACtC,MAAM,WAAW,GAAG,UAAU,CAAC,GAAG,CAAC,SAAS,CAAC,IAAI,EAAE,CAAA;QAEnD,gFAAgF;QAChF,IAAI,aAAa,CAAC,QAAQ,CAAC,SAAS,CAAC,EAAE,CAAC;YACvC,MAAM,EAAE,CAAC,aAAa,SAAS,qCAAqC,WAAW,CAAC,MAAM,YAAY,CAAC,CAAA;YACnG,iBAAiB,IAAI,WAAW,CAAC,MAAM,CAAA;YAEvC,SAAQ;QACT,CAAC;QAED,MAAM,QAAQ,GAAG,IAAI,CAAC,WAAW,EAAE,SAAS,SAAS,EAAE,CAAC,CAAA;QACxD,MAAM,eAAe,CAAC,QAAQ,CAAC,CAAA;QAC/B,MAAM,YAAY,GAAG,IAAI,CAAC,QAAQ,EAAE,eAAe,CAAC,CAAA;QAEpD,wDAAwD;QACxD,MAAM,QAAQ,GAAG,MAAM,kBAAkB,CAAC,YAAY,CAAC,CAAA;QAEvD,MAAM,EAAE,CAAC,aAAa,SAAS,MAAM,WAAW,CAAC,MAAM,WAAW,CAAC,CAAA;QAEnE,iDAAiD;QACjD,MAAM,OAAO,GAAyC,EAAE,CAAA;QAExD,KAAK,MAAM,KAAK,IAAI,WAAW,EAAE,CAAC;YACjC,MAAM,IAAI,GAAG,IAAI,CAAC,QAAQ,EAAE,KAAK,CAAC,CAAA;YAClC,MAAM,GAAG,GAAG,GAAG,cAAc,IAAI,KAAK,EAAE,CAAA;YACxC,MAAM,KAAK,GAAG,QAAQ,CAAC,GAAG,CAAC,KAAK,CAAC,CAAA;YAEjC,yCAAyC;YACzC,IAAI,KAAK,IAAI,CAAC,MAAM,cAAc,CAAC,IAAI,EAAE,KAAK,CAAC,MAAM,EAAE,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC;gBACtE,MAAM,EAAE,CAAC,qBAAqB,KAAK,EAAE,CAAC,CAAA;gBAEtC,YAAY,EAAE,CAAA;gBAEd,SAAQ;YACT,CAAC;YAED,IAAI,MAAM,EAAE,CAAC;gBACZ,MAAM,EAAE,CAAC,kBAAkB,GAAG,EAAE,CAAC,CAAA;gBAEjC,YAAY,EAAE,CAAA;gBAEd,SAAQ;YACT,CAAC;YAED,OAAO,CAAC,IAAI,CAAC,EAAE,GAAG,EAAE,IAAI,EAAE,CAAC,CAAA;QAC5B,CAAC;QAED,IAAI,MAAM;YAAE,SAAQ;QAEpB,IAAI,CAAC,OAAO,CAAC,MAAM;YAAE,SAAQ;QAE7B,+EAA+E;QAC/E,MAAM,OAAO,GAAmB,KAAK,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,OAAO,CAAC,MAAM,EAAE,CAAC,CAAA;QACtE,IAAI,MAAM,GAAG,CAAC,CAAA;QAEd,MAAM,OAAO,GAAG,KAAK,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,IAAI,CAAC,GAAG,CAAC,WAAW,EAAE,OAAO,CAAC,MAAM,CAAC,EAAE,EAAE,KAAK,IAAI,EAAE;YACxF,OAAO,IAAI,EAAE,CAAC;gBACb,MAAM,CAAC,GAAG,MAAM,EAAE,CAAA;gBAElB,IAAI,CAAC,IAAI,OAAO,CAAC,MAAM;oBAAE,OAAM;gBAC/B,MAAM,IAAI,GAAG,OAAO,CAAC,CAAC,CAAE,CAAA;gBACxB,gDAAgD;gBAChD,MAAM,KAAK,CAAC,WAAW,CAAC,CAAA;gBACxB,OAAO,CAAC,CAAC,CAAC,GAAG,MAAM,cAAc,CAAC,IAAI,CAAC,GAAG,EAAE,IAAI,CAAC,IAAI,CAAC,CAAA;YACvD,CAAC;QACF,CAAC,CAAC,CAAA;QAEF,MAAM,OAAO,CAAC,GAAG,CAAC,OAAO,CAAC,CAAA;QAE1B,mCAAmC;QACnC,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;YAC9B,IAAI,MAAM,CAAC,EAAE,EAAE,CAAC;gBACf,MAAM,EAAE,CACP,QAAQ,MAAM,CAAC,QAAQ,KAAK,aAAa,CAAC,SAAS,CAAC,MAAM,CAAC,KAAK,CAAC,YAAY,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,EAAE,CAAC,KAAK,CAC5G,CAAA;gBAED,QAAQ,CAAC,GAAG,CAAC,MAAM,CAAC,QAAQ,EAAE,EAAE,QAAQ,EAAE,MAAM,CAAC,QAAQ,EAAE,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,KAAK,EAAE,MAAM,CAAC,KAAK,EAAE,CAAC,CAAA;gBAExG,YAAY,EAAE,CAAA;gBACd,iBAAiB,IAAI,MAAM,CAAC,KAAK,CAAA;YAClC,CAAC;iBAAM,CAAC;gBACP,MAAM,EAAE,CAAC,UAAU,MAAM,CAAC,QAAQ,OAAO,MAAM,CAAC,MAAM,EAAE,CAAC,CAAA;gBAEzD,WAAW,EAAE,CAAA;gBACb,WAAW,CAAC,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAA;YAClC,CAAC;QACF,CAAC;QAED,yFAAyF;QACzF,MAAM,QAAQ,GAAG,CAAC,GAAG,QAAQ,CAAC,MAAM,EAAE,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,CAAC,aAAa,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAA;QAEhG,MAAM,WAAW,GAAG;YACnB,UAAU,EAAE,SAAS;YACrB,UAAU,EAAE,UAAU,EAAE;YACxB,cAAc,EAAE,cAAc;YAC9B,QAAQ;SACR,CAAA;QAED,MAAM,aAAa,CAAC,YAAY,EAAE,WAAW,CAAC,CAAA;IAC/C,CAAC;IAED,gBAAgB;IAEhB,MAAM,EAAE,CAAC,iBAAiB,CAAC,CAAA;IAC3B,MAAM,EAAE,CAAC,iCAAiC,aAAa,EAAE,CAAC,CAAA;IAC1D,MAAM,EAAE,CAAC,iCAAiC,iBAAiB,wBAAwB,aAAa,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;IAC/G,MAAM,EAAE,CAAC,iCAAiC,YAAY,EAAE,CAAC,CAAA;IACzD,MAAM,EAAE,CAAC,iCAAiC,YAAY,EAAE,CAAC,CAAA;IACzD,MAAM,EAAE,CAAC,iCAAiC,WAAW,EAAE,CAAC,CAAA;IAExD,IAAI,iBAAiB,GAAG,CAAC,EAAE,CAAC;QAC3B,MAAM,EAAE,CAAC,iCAAiC,aAAa,CAAC,SAAS,CAAC,iBAAiB,CAAC,KAAK,iBAAiB,GAAG,CAAC,CAAA;IAC/G,CAAC;IAED,IAAI,WAAW,GAAG,CAAC,EAAE,CAAC;QACrB,MAAM,EAAE,CAAC,YAAY,WAAW,uCAAuC,CAAC,CAAA;IACzE,CAAC;IAED,OAAO,EAAE,OAAO,EAAE,YAAY,EAAE,OAAO,EAAE,YAAY,GAAG,iBAAiB,EAAE,MAAM,EAAE,WAAW,EAAE,WAAW,EAAE,CAAA;AAC9G,CAAC"}
@@ -1,90 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * Generate golden-set candidate entries by LLM-driven surface-form synthesis from a verified-label
7
- * seed pulled out of the corpus's labeled test split.
8
- *
9
- * ## Why this approach
10
- *
11
- * The Phase 2 golden set has 74 entries; session-notes.md called for ≥500/locale. Manual curation
12
- * doesn't scale. Pure-LLM generation (invent raw + labels from scratch) is too noisy — labels
13
- * would be unverified.
14
- *
15
- * This module takes the middle path:
16
- *
17
- * 1. **Seeds come from corpus-v0.2.0 test slice** — already through the alignment pipeline, so labels
18
- * are pipeline-verified.
19
- * 2. **LLM only varies the surface form** — case, abbreviations, reordering, dropped components. The
20
- * component VALUES (locality string, postcode digits, etc.) are preserved verbatim.
21
- * 3. **Programmatic validator drops hallucinations** — every component value must appear as a
22
- * substring (case-insensitive, whitespace-normalized) of the variant's raw. Failures dropped
23
- * silently; cost is wasted tokens, never bad-labeled golden entries.
24
- *
25
- * ## Usage
26
- *
27
- * ```sh
28
- * DEEPSEEK_API_KEY=sk-... \
29
- * mailwoman corpus golden expand \
30
- * --count 1000 \
31
- * --variants 5 \
32
- * --output data/eval/golden/candidates/expand-$(date +%Y%m%d-%H%M%S).jsonl
33
- * ```
34
- *
35
- * ## Env
36
- *
37
- * - `DEEPSEEK_API_KEY` — required for provider `deepseek`
38
- * - `ANTHROPIC_API_KEY` — required for provider `anthropic`
39
- *
40
- * ## What this module does NOT do
41
- *
42
- * - Does not commit anything or modify the versioned golden dir. Candidates land in
43
- * `data/eval/golden/candidates/` for operator review (skim, prune, then run
44
- * `mailwoman corpus golden promote`).
45
- * - Does not score the LLM's quality — that's an eyeball job after pilot lands.
46
- * - Does not retry hallucinated candidates. Cost of wasted tokens is trivial (~$0.0006/each).
47
- */
48
- export interface ExpandGoldenOptions {
49
- /**
50
- * Corpus test slice path(s), comma-separated. Default: the v0.2.0 test slice under the data root.
51
- */
52
- corpus?: string;
53
- /**
54
- * Total seeds to process. Default `100` (pilot).
55
- */
56
- count?: number;
57
- /**
58
- * Variants requested per seed. Default `5`.
59
- */
60
- variants?: number;
61
- /**
62
- * JSONL output path. Default `data/eval/golden/candidates/expand-<ts>.jsonl`.
63
- */
64
- output?: string;
65
- /**
66
- * LLM provider. Default `deepseek`.
67
- */
68
- provider?: "deepseek" | "anthropic";
69
- /**
70
- * Model id. Default depends on provider.
71
- */
72
- model?: string;
73
- /**
74
- * Parallel LLM calls. Default `4`.
75
- */
76
- concurrency?: number;
77
- /**
78
- * Comma-separated source allow-list.
79
- */
80
- includeSources?: string;
81
- }
82
- export interface ExpandGoldenSummary {
83
- seedsProcessed: number;
84
- kept: number;
85
- dropped: number;
86
- errored: number;
87
- outputPath: string;
88
- }
89
- export declare function expandGolden(options?: ExpandGoldenOptions, report?: (line: string) => void): Promise<ExpandGoldenSummary>;
90
- //# sourceMappingURL=golden-expand.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"golden-expand.d.ts","sourceRoot":"","sources":["../../lib/tools/golden-expand.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8CG;AAuDH,MAAM,WAAW,mBAAmB;IACnC;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,CAAA;IACf;;OAEG;IACH,KAAK,CAAC,EAAE,MAAM,CAAA;IACd;;OAEG;IACH,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,CAAA;IACf;;OAEG;IACH,QAAQ,CAAC,EAAE,UAAU,GAAG,WAAW,CAAA;IACnC;;OAEG;IACH,KAAK,CAAC,EAAE,MAAM,CAAA;IACd;;OAEG;IACH,WAAW,CAAC,EAAE,MAAM,CAAA;IACpB;;OAEG;IACH,cAAc,CAAC,EAAE,MAAM,CAAA;CACvB;AAED,MAAM,WAAW,mBAAmB;IACnC,cAAc,EAAE,MAAM,CAAA;IACtB,IAAI,EAAE,MAAM,CAAA;IACZ,OAAO,EAAE,MAAM,CAAA;IACf,OAAO,EAAE,MAAM,CAAA;IACf,UAAU,EAAE,MAAM,CAAA;CAClB;AA0UD,wBAAsB,YAAY,CACjC,OAAO,GAAE,mBAAwB,EACjC,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,mBAAmB,CAAC,CAkG9B"}