@mailwoman/corpus 9.2.0 → 9.4.0

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 (1261) hide show
  1. package/README.md +22 -22
  2. package/data/PROVENANCE.md +7 -7
  3. package/lib/adapters/ban/adapter.ts +190 -0
  4. package/lib/adapters/ban/street-decompose.ts +66 -0
  5. package/lib/adapters/fcc-bdc/adapter.ts +174 -0
  6. package/lib/adapters/geonames/adapter.ts +199 -0
  7. package/lib/adapters/geonames-postal/adapter.ts +122 -0
  8. package/lib/adapters/gnaf/adapter.ts +149 -0
  9. package/lib/adapters/gnaf/assemble.ts +225 -0
  10. package/lib/adapters/index.ts +153 -0
  11. package/lib/adapters/openaddresses/adapter.ts +251 -0
  12. package/lib/adapters/overture/adapter.ts +162 -0
  13. package/lib/adapters/state-hi-schools/adapter.ts +170 -0
  14. package/lib/adapters/state-hi-schools/workbook.ts +35 -0
  15. package/lib/adapters/synth-po-box/adapter.ts +204 -0
  16. package/lib/adapters/tiger/adapter.ts +252 -0
  17. package/lib/adapters/tiger/street-decompose.ts +83 -0
  18. package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +167 -0
  19. package/lib/adapters/usgov-imls-pls/adapter.ts +143 -0
  20. package/lib/adapters/usgov-irs-bmf/adapter.ts +151 -0
  21. package/lib/adapters/usgov-nad/adapter.ts +334 -0
  22. package/lib/adapters/usgov-nppes/adapter.ts +151 -0
  23. package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +193 -0
  24. package/lib/adapters/utils/index.ts +307 -0
  25. package/lib/adapters/wof-admin-jp/adapter.ts +214 -0
  26. package/lib/adapters/wof-admin-json/adapter.ts +231 -0
  27. package/lib/adapters/wof-json-rows.ts +129 -0
  28. package/lib/adapters/wof-postalcode-json/adapter.ts +176 -0
  29. package/lib/build.ts +378 -0
  30. package/lib/env.ts +50 -0
  31. package/lib/index.ts +13 -0
  32. package/lib/recipes/anchor-absorption.ts +101 -0
  33. package/lib/recipes/bare-country.ts +95 -0
  34. package/lib/recipes/boundary-stress.ts +102 -0
  35. package/lib/recipes/cn-organizational-units.ts +199 -0
  36. package/lib/recipes/country-balanced.ts +510 -0
  37. package/lib/recipes/cz-pcfirst-preposition.ts +112 -0
  38. package/lib/recipes/fr-admin-split.ts +243 -0
  39. package/lib/recipes/fr-bare-street.ts +171 -0
  40. package/lib/recipes/fr-fragment.ts +334 -0
  41. package/lib/recipes/fr-lieudit.ts +301 -0
  42. package/lib/recipes/fr-order.ts +246 -0
  43. package/lib/recipes/german.ts +360 -0
  44. package/lib/recipes/house-venue.ts +93 -0
  45. package/lib/recipes/index.ts +97 -0
  46. package/lib/recipes/intersection.ts +619 -0
  47. package/lib/recipes/locale.ts +600 -0
  48. package/lib/recipes/nl-postcode.ts +117 -0
  49. package/lib/recipes/no-fragment.ts +213 -0
  50. package/lib/recipes/no-street-led.ts +135 -0
  51. package/lib/recipes/no-street.ts +91 -0
  52. package/lib/recipes/po-box-cedex.ts +976 -0
  53. package/lib/recipes/po-box.ts +124 -0
  54. package/lib/recipes/reviewed-postcode-tail.ts +190 -0
  55. package/lib/recipes/scaffold.ts +468 -0
  56. package/lib/recipes/si-bare-village.ts +99 -0
  57. package/lib/recipes/street-affix.ts +805 -0
  58. package/lib/recipes/street-bare.ts +102 -0
  59. package/lib/recipes/street.ts +83 -0
  60. package/lib/recipes/sub-venue-sources.ts +878 -0
  61. package/lib/recipes/sub-venue.ts +998 -0
  62. package/lib/recipes/trailing-region.ts +178 -0
  63. package/lib/recipes/unit.ts +304 -0
  64. package/lib/runner.ts +312 -0
  65. package/lib/synthesizers/anchor-absorption.ts +288 -0
  66. package/lib/synthesizers/boundary-stress.ts +532 -0
  67. package/lib/synthesizers/german.ts +260 -0
  68. package/lib/synthesizers/house-venue.ts +308 -0
  69. package/lib/synthesizers/intersection.ts +233 -0
  70. package/lib/synthesizers/no-street.ts +327 -0
  71. package/lib/synthesizers/po-box.ts +323 -0
  72. package/lib/synthesizers/street.ts +269 -0
  73. package/lib/synthesizers/utils.ts +993 -0
  74. package/lib/test-kit/corpus-recipe.ts +86 -0
  75. package/lib/test-kit/index.ts +100 -0
  76. package/lib/tools/align-slice.ts +68 -0
  77. package/lib/tools/audit.ts +403 -0
  78. package/lib/tools/corpus-stats.ts +136 -0
  79. package/lib/tools/fetch/acra-sg.ts +174 -0
  80. package/lib/tools/fetch/ban.ts +289 -0
  81. package/lib/tools/fetch/download.ts +477 -0
  82. package/lib/tools/fetch/gcis-tw.ts +175 -0
  83. package/lib/tools/fetch/geonames-dump.ts +257 -0
  84. package/lib/tools/fetch/geonames-postal.ts +180 -0
  85. package/lib/tools/fetch/houjin-jp.ts +135 -0
  86. package/lib/tools/fetch/hrsa.ts +59 -0
  87. package/lib/tools/fetch/imls-pls.ts +149 -0
  88. package/lib/tools/fetch/index.ts +174 -0
  89. package/lib/tools/fetch/juso-kr.ts +165 -0
  90. package/lib/tools/fetch/localdata-kr.ts +194 -0
  91. package/lib/tools/fetch/nad.ts +341 -0
  92. package/lib/tools/fetch/nppes.ts +165 -0
  93. package/lib/tools/fetch/openaddresses.ts +347 -0
  94. package/lib/tools/fetch/ourairports.ts +170 -0
  95. package/lib/tools/fetch/ppd.ts +121 -0
  96. package/lib/tools/fetch/state-hi-schools.ts +161 -0
  97. package/lib/tools/fetch/state-sources.ts +146 -0
  98. package/lib/tools/fetch/tiger-full.ts +308 -0
  99. package/lib/tools/fetch/wikidata-subvenue.ts +384 -0
  100. package/lib/tools/golden-expand.ts +574 -0
  101. package/lib/tools/golden-promote.ts +337 -0
  102. package/lib/tools/golden-relabel-street.ts +686 -0
  103. package/lib/tools/index.ts +28 -0
  104. package/lib/tools/ingest-csv.ts +378 -0
  105. package/lib/tools/jsonl-to-parquet.ts +207 -0
  106. package/lib/tools/lint-slice-vocab.ts +388 -0
  107. package/lib/tools/lint-slice.ts +496 -0
  108. package/lib/tools/overlay-manifest.ts +148 -0
  109. package/lib/tools/overture-subvenue.ts +209 -0
  110. package/lib/tools/postcode-triples.ts +363 -0
  111. package/lib/tools/slice-kryptonite.ts +137 -0
  112. package/lib/tools/slice-translit.ts +218 -0
  113. package/lib/tools/sub-venue/harvest.ts +234 -0
  114. package/lib/tools/sub-venue/head-nouns.ts +245 -0
  115. package/lib/tools/sub-venue/surfaces.ts +95 -0
  116. package/lib/tools/sub-venue/table.ts +281 -0
  117. package/lib/tools/sub-venue/wikidata.ts +85 -0
  118. package/lib/tools/sub-venue-lexicon.ts +429 -0
  119. package/lib/tools/sub-venue-promotions.ts +330 -0
  120. package/lib/types.ts +247 -0
  121. package/lib/utils/align.ts +330 -0
  122. package/lib/utils/golden.ts +189 -0
  123. package/lib/utils/index.ts +14 -0
  124. package/lib/utils/parquet.ts +582 -0
  125. package/lib/utils/slice-stats.ts +95 -0
  126. package/lib/utils/split.ts +279 -0
  127. package/lib/utils/tokenize.ts +120 -0
  128. package/lib/utils/wof-json.ts +247 -0
  129. package/out/adapters/ban/adapter.d.ts.map +1 -0
  130. package/out/adapters/ban/adapter.js +149 -0
  131. package/out/adapters/ban/adapter.js.map +1 -0
  132. package/out/adapters/ban/street-decompose.d.ts.map +1 -0
  133. package/out/adapters/ban/street-decompose.js +51 -0
  134. package/out/adapters/ban/street-decompose.js.map +1 -0
  135. package/out/adapters/fcc-bdc/adapter.d.ts.map +1 -0
  136. package/out/adapters/fcc-bdc/adapter.js +144 -0
  137. package/out/adapters/fcc-bdc/adapter.js.map +1 -0
  138. package/out/adapters/geonames/adapter.d.ts.map +1 -0
  139. package/out/adapters/geonames/adapter.js +176 -0
  140. package/out/adapters/geonames/adapter.js.map +1 -0
  141. package/out/adapters/geonames-postal/adapter.d.ts +54 -0
  142. package/out/adapters/geonames-postal/adapter.d.ts.map +1 -0
  143. package/out/adapters/geonames-postal/adapter.js +107 -0
  144. package/out/adapters/geonames-postal/adapter.js.map +1 -0
  145. package/out/adapters/gnaf/adapter.d.ts +49 -0
  146. package/out/adapters/gnaf/adapter.d.ts.map +1 -0
  147. package/out/adapters/gnaf/adapter.js +124 -0
  148. package/out/adapters/gnaf/adapter.js.map +1 -0
  149. package/out/adapters/gnaf/assemble.d.ts +65 -0
  150. package/out/adapters/gnaf/assemble.d.ts.map +1 -0
  151. package/out/adapters/gnaf/assemble.js +154 -0
  152. package/out/adapters/gnaf/assemble.js.map +1 -0
  153. package/out/adapters/index.d.ts +51 -0
  154. package/out/adapters/index.d.ts.map +1 -0
  155. package/out/adapters/index.js +95 -0
  156. package/out/adapters/index.js.map +1 -0
  157. package/out/adapters/openaddresses/adapter.d.ts.map +1 -0
  158. package/out/adapters/openaddresses/adapter.js +186 -0
  159. package/out/adapters/openaddresses/adapter.js.map +1 -0
  160. package/out/adapters/overture/adapter.d.ts +48 -0
  161. package/out/adapters/overture/adapter.d.ts.map +1 -0
  162. package/out/adapters/overture/adapter.js +125 -0
  163. package/out/adapters/overture/adapter.js.map +1 -0
  164. package/out/adapters/state-hi-schools/adapter.d.ts +46 -0
  165. package/out/adapters/state-hi-schools/adapter.d.ts.map +1 -0
  166. package/out/adapters/state-hi-schools/adapter.js +145 -0
  167. package/out/adapters/state-hi-schools/adapter.js.map +1 -0
  168. package/out/adapters/state-hi-schools/workbook.d.ts +29 -0
  169. package/out/adapters/state-hi-schools/workbook.d.ts.map +1 -0
  170. package/out/adapters/state-hi-schools/workbook.js +20 -0
  171. package/out/adapters/state-hi-schools/workbook.js.map +1 -0
  172. package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
  173. package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
  174. package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
  175. package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
  176. package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
  177. package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
  178. package/out/adapters/synth-po-box/adapter.d.ts.map +1 -0
  179. package/out/adapters/synth-po-box/adapter.js +140 -0
  180. package/out/adapters/synth-po-box/adapter.js.map +1 -0
  181. package/out/adapters/tiger/adapter.d.ts +55 -0
  182. package/out/adapters/tiger/adapter.d.ts.map +1 -0
  183. package/out/adapters/tiger/adapter.js +201 -0
  184. package/out/adapters/tiger/adapter.js.map +1 -0
  185. package/out/adapters/tiger/street-decompose.d.ts.map +1 -0
  186. package/out/adapters/tiger/street-decompose.js +68 -0
  187. package/out/adapters/tiger/street-decompose.js.map +1 -0
  188. package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +56 -0
  189. package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -0
  190. package/out/adapters/usgov-hrsa-fqhc/adapter.js +132 -0
  191. package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -0
  192. package/out/adapters/usgov-imls-pls/adapter.d.ts +36 -0
  193. package/out/adapters/usgov-imls-pls/adapter.d.ts.map +1 -0
  194. package/out/adapters/usgov-imls-pls/adapter.js +114 -0
  195. package/out/adapters/usgov-imls-pls/adapter.js.map +1 -0
  196. package/out/adapters/usgov-irs-bmf/adapter.d.ts +37 -0
  197. package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -0
  198. package/out/adapters/usgov-irs-bmf/adapter.js +120 -0
  199. package/out/adapters/usgov-irs-bmf/adapter.js.map +1 -0
  200. package/out/adapters/usgov-nad/adapter.d.ts +48 -0
  201. package/out/adapters/usgov-nad/adapter.d.ts.map +1 -0
  202. package/out/adapters/usgov-nad/adapter.js +249 -0
  203. package/out/adapters/usgov-nad/adapter.js.map +1 -0
  204. package/out/adapters/usgov-nppes/adapter.d.ts.map +1 -0
  205. package/out/adapters/usgov-nppes/adapter.js +118 -0
  206. package/out/adapters/usgov-nppes/adapter.js.map +1 -0
  207. package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -0
  208. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +154 -0
  209. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -0
  210. package/out/adapters/utils/index.d.ts +191 -0
  211. package/out/adapters/utils/index.d.ts.map +1 -0
  212. package/out/adapters/utils/index.js +206 -0
  213. package/out/adapters/utils/index.js.map +1 -0
  214. package/out/adapters/wof-admin-jp/adapter.d.ts.map +1 -0
  215. package/out/adapters/wof-admin-jp/adapter.js +161 -0
  216. package/out/adapters/wof-admin-jp/adapter.js.map +1 -0
  217. package/out/adapters/wof-admin-json/adapter.d.ts +79 -0
  218. package/out/adapters/wof-admin-json/adapter.d.ts.map +1 -0
  219. package/out/adapters/wof-admin-json/adapter.js +197 -0
  220. package/out/adapters/wof-admin-json/adapter.js.map +1 -0
  221. package/out/adapters/wof-json-rows.d.ts +62 -0
  222. package/out/adapters/wof-json-rows.d.ts.map +1 -0
  223. package/out/adapters/wof-json-rows.js +83 -0
  224. package/out/adapters/wof-json-rows.js.map +1 -0
  225. package/out/adapters/wof-postalcode-json/adapter.d.ts +65 -0
  226. package/out/adapters/wof-postalcode-json/adapter.d.ts.map +1 -0
  227. package/out/adapters/wof-postalcode-json/adapter.js +151 -0
  228. package/out/adapters/wof-postalcode-json/adapter.js.map +1 -0
  229. package/out/build.d.ts +132 -0
  230. package/out/build.d.ts.map +1 -0
  231. package/out/build.js +245 -0
  232. package/out/build.js.map +1 -0
  233. package/out/codex/us-fips-state.d.ts.map +1 -0
  234. package/out/codex/us-fips-state.js.map +1 -0
  235. package/out/env.d.ts +46 -0
  236. package/out/env.d.ts.map +1 -0
  237. package/out/env.js +46 -0
  238. package/out/env.js.map +1 -0
  239. package/out/index.d.ts +13 -0
  240. package/out/index.d.ts.map +1 -0
  241. package/out/index.js +13 -0
  242. package/out/index.js.map +1 -0
  243. package/out/recipes/anchor-absorption.d.ts +20 -0
  244. package/out/recipes/anchor-absorption.d.ts.map +1 -0
  245. package/out/recipes/anchor-absorption.js +82 -0
  246. package/out/recipes/anchor-absorption.js.map +1 -0
  247. package/out/recipes/bare-country.d.ts +25 -0
  248. package/out/recipes/bare-country.d.ts.map +1 -0
  249. package/out/recipes/bare-country.js +88 -0
  250. package/out/recipes/bare-country.js.map +1 -0
  251. package/out/recipes/boundary-stress.d.ts +20 -0
  252. package/out/recipes/boundary-stress.d.ts.map +1 -0
  253. package/out/recipes/boundary-stress.js +84 -0
  254. package/out/recipes/boundary-stress.js.map +1 -0
  255. package/out/recipes/cn-organizational-units.d.ts +36 -0
  256. package/out/recipes/cn-organizational-units.d.ts.map +1 -0
  257. package/out/recipes/cn-organizational-units.js +159 -0
  258. package/out/recipes/cn-organizational-units.js.map +1 -0
  259. package/out/recipes/country-balanced.d.ts +32 -0
  260. package/out/recipes/country-balanced.d.ts.map +1 -0
  261. package/out/recipes/country-balanced.js +394 -0
  262. package/out/recipes/country-balanced.js.map +1 -0
  263. package/out/recipes/cz-pcfirst-preposition.d.ts +22 -0
  264. package/out/recipes/cz-pcfirst-preposition.d.ts.map +1 -0
  265. package/out/recipes/cz-pcfirst-preposition.js +101 -0
  266. package/out/recipes/cz-pcfirst-preposition.js.map +1 -0
  267. package/out/recipes/fr-admin-split.d.ts +38 -0
  268. package/out/recipes/fr-admin-split.d.ts.map +1 -0
  269. package/out/recipes/fr-admin-split.js +192 -0
  270. package/out/recipes/fr-admin-split.js.map +1 -0
  271. package/out/recipes/fr-bare-street.d.ts +28 -0
  272. package/out/recipes/fr-bare-street.d.ts.map +1 -0
  273. package/out/recipes/fr-bare-street.js +144 -0
  274. package/out/recipes/fr-bare-street.js.map +1 -0
  275. package/out/recipes/fr-fragment.d.ts +77 -0
  276. package/out/recipes/fr-fragment.d.ts.map +1 -0
  277. package/out/recipes/fr-fragment.js +277 -0
  278. package/out/recipes/fr-fragment.js.map +1 -0
  279. package/out/recipes/fr-lieudit.d.ts +32 -0
  280. package/out/recipes/fr-lieudit.d.ts.map +1 -0
  281. package/out/recipes/fr-lieudit.js +227 -0
  282. package/out/recipes/fr-lieudit.js.map +1 -0
  283. package/out/recipes/fr-order.d.ts +38 -0
  284. package/out/recipes/fr-order.d.ts.map +1 -0
  285. package/out/recipes/fr-order.js +198 -0
  286. package/out/recipes/fr-order.js.map +1 -0
  287. package/out/recipes/german.d.ts +44 -0
  288. package/out/recipes/german.d.ts.map +1 -0
  289. package/out/recipes/german.js +289 -0
  290. package/out/recipes/german.js.map +1 -0
  291. package/out/recipes/house-venue.d.ts +18 -0
  292. package/out/recipes/house-venue.d.ts.map +1 -0
  293. package/out/recipes/house-venue.js +74 -0
  294. package/out/recipes/house-venue.js.map +1 -0
  295. package/out/recipes/index.d.ts +24 -0
  296. package/out/recipes/index.d.ts.map +1 -0
  297. package/out/recipes/index.js +91 -0
  298. package/out/recipes/index.js.map +1 -0
  299. package/out/recipes/intersection.d.ts +42 -0
  300. package/out/recipes/intersection.d.ts.map +1 -0
  301. package/out/recipes/intersection.js +453 -0
  302. package/out/recipes/intersection.js.map +1 -0
  303. package/out/recipes/locale.d.ts +136 -0
  304. package/out/recipes/locale.d.ts.map +1 -0
  305. package/out/recipes/locale.js +460 -0
  306. package/out/recipes/locale.js.map +1 -0
  307. package/out/recipes/nl-postcode.d.ts +26 -0
  308. package/out/recipes/nl-postcode.d.ts.map +1 -0
  309. package/out/recipes/nl-postcode.js +103 -0
  310. package/out/recipes/nl-postcode.js.map +1 -0
  311. package/out/recipes/no-fragment.d.ts +43 -0
  312. package/out/recipes/no-fragment.d.ts.map +1 -0
  313. package/out/recipes/no-fragment.js +183 -0
  314. package/out/recipes/no-fragment.js.map +1 -0
  315. package/out/recipes/no-street-led.d.ts +24 -0
  316. package/out/recipes/no-street-led.d.ts.map +1 -0
  317. package/out/recipes/no-street-led.js +114 -0
  318. package/out/recipes/no-street-led.js.map +1 -0
  319. package/out/recipes/no-street.d.ts +18 -0
  320. package/out/recipes/no-street.d.ts.map +1 -0
  321. package/out/recipes/no-street.js +72 -0
  322. package/out/recipes/no-street.js.map +1 -0
  323. package/out/recipes/po-box-cedex.d.ts +38 -0
  324. package/out/recipes/po-box-cedex.d.ts.map +1 -0
  325. package/out/recipes/po-box-cedex.js +768 -0
  326. package/out/recipes/po-box-cedex.js.map +1 -0
  327. package/out/recipes/po-box.d.ts +17 -0
  328. package/out/recipes/po-box.d.ts.map +1 -0
  329. package/out/recipes/po-box.js +101 -0
  330. package/out/recipes/po-box.js.map +1 -0
  331. package/out/recipes/reviewed-postcode-tail.d.ts +47 -0
  332. package/out/recipes/reviewed-postcode-tail.d.ts.map +1 -0
  333. package/out/recipes/reviewed-postcode-tail.js +125 -0
  334. package/out/recipes/reviewed-postcode-tail.js.map +1 -0
  335. package/out/recipes/scaffold.d.ts +323 -0
  336. package/out/recipes/scaffold.d.ts.map +1 -0
  337. package/out/recipes/scaffold.js +174 -0
  338. package/out/recipes/scaffold.js.map +1 -0
  339. package/out/recipes/si-bare-village.d.ts +32 -0
  340. package/out/recipes/si-bare-village.d.ts.map +1 -0
  341. package/out/recipes/si-bare-village.js +89 -0
  342. package/out/recipes/si-bare-village.js.map +1 -0
  343. package/out/recipes/street-affix.d.ts +89 -0
  344. package/out/recipes/street-affix.d.ts.map +1 -0
  345. package/out/recipes/street-affix.js +563 -0
  346. package/out/recipes/street-affix.js.map +1 -0
  347. package/out/recipes/street-bare.d.ts +25 -0
  348. package/out/recipes/street-bare.d.ts.map +1 -0
  349. package/out/recipes/street-bare.js +87 -0
  350. package/out/recipes/street-bare.js.map +1 -0
  351. package/out/recipes/street.d.ts +15 -0
  352. package/out/recipes/street.d.ts.map +1 -0
  353. package/out/recipes/street.js +70 -0
  354. package/out/recipes/street.js.map +1 -0
  355. package/out/recipes/sub-venue-sources.d.ts +229 -0
  356. package/out/recipes/sub-venue-sources.d.ts.map +1 -0
  357. package/out/recipes/sub-venue-sources.js +654 -0
  358. package/out/recipes/sub-venue-sources.js.map +1 -0
  359. package/out/recipes/sub-venue.d.ts +269 -0
  360. package/out/recipes/sub-venue.d.ts.map +1 -0
  361. package/out/recipes/sub-venue.js +726 -0
  362. package/out/recipes/sub-venue.js.map +1 -0
  363. package/out/recipes/trailing-region.d.ts +74 -0
  364. package/out/recipes/trailing-region.d.ts.map +1 -0
  365. package/out/recipes/trailing-region.js +158 -0
  366. package/out/recipes/trailing-region.js.map +1 -0
  367. package/out/recipes/unit.d.ts +29 -0
  368. package/out/recipes/unit.d.ts.map +1 -0
  369. package/out/recipes/unit.js +231 -0
  370. package/out/recipes/unit.js.map +1 -0
  371. package/out/runner.d.ts +130 -0
  372. package/out/runner.d.ts.map +1 -0
  373. package/out/runner.js +185 -0
  374. package/out/runner.js.map +1 -0
  375. package/out/synthesizers/anchor-absorption.d.ts +63 -0
  376. package/out/synthesizers/anchor-absorption.d.ts.map +1 -0
  377. package/out/synthesizers/anchor-absorption.js +221 -0
  378. package/out/synthesizers/anchor-absorption.js.map +1 -0
  379. package/out/synthesizers/boundary-stress.d.ts +78 -0
  380. package/out/synthesizers/boundary-stress.d.ts.map +1 -0
  381. package/out/synthesizers/boundary-stress.js +455 -0
  382. package/out/synthesizers/boundary-stress.js.map +1 -0
  383. package/out/synthesizers/german.d.ts +115 -0
  384. package/out/synthesizers/german.d.ts.map +1 -0
  385. package/out/synthesizers/german.js +149 -0
  386. package/out/synthesizers/german.js.map +1 -0
  387. package/out/synthesizers/house-venue.d.ts +56 -0
  388. package/out/synthesizers/house-venue.d.ts.map +1 -0
  389. package/out/synthesizers/house-venue.js +247 -0
  390. package/out/synthesizers/house-venue.js.map +1 -0
  391. package/out/synthesizers/intersection.d.ts +52 -0
  392. package/out/synthesizers/intersection.d.ts.map +1 -0
  393. package/out/synthesizers/intersection.js +175 -0
  394. package/out/synthesizers/intersection.js.map +1 -0
  395. package/out/synthesizers/no-street.d.ts +72 -0
  396. package/out/synthesizers/no-street.d.ts.map +1 -0
  397. package/out/synthesizers/no-street.js +262 -0
  398. package/out/synthesizers/no-street.js.map +1 -0
  399. package/out/synthesizers/po-box.d.ts +108 -0
  400. package/out/synthesizers/po-box.d.ts.map +1 -0
  401. package/out/synthesizers/po-box.js +250 -0
  402. package/out/synthesizers/po-box.js.map +1 -0
  403. package/out/synthesizers/street.d.ts +54 -0
  404. package/out/synthesizers/street.d.ts.map +1 -0
  405. package/out/synthesizers/street.js +218 -0
  406. package/out/synthesizers/street.js.map +1 -0
  407. package/out/synthesizers/utils.d.ts +241 -0
  408. package/out/synthesizers/utils.d.ts.map +1 -0
  409. package/out/synthesizers/utils.js +776 -0
  410. package/out/synthesizers/utils.js.map +1 -0
  411. package/out/test-kit/corpus-recipe.d.ts +59 -0
  412. package/out/test-kit/corpus-recipe.d.ts.map +1 -0
  413. package/out/test-kit/corpus-recipe.js +39 -0
  414. package/out/test-kit/corpus-recipe.js.map +1 -0
  415. package/out/test-kit/index.d.ts +48 -0
  416. package/out/test-kit/index.d.ts.map +1 -0
  417. package/out/test-kit/index.js +78 -0
  418. package/out/test-kit/index.js.map +1 -0
  419. package/out/tools/align-slice.d.ts +7 -0
  420. package/out/tools/align-slice.d.ts.map +1 -0
  421. package/out/tools/align-slice.js +55 -0
  422. package/out/tools/align-slice.js.map +1 -0
  423. package/out/tools/audit.d.ts +29 -0
  424. package/out/tools/audit.d.ts.map +1 -0
  425. package/out/tools/audit.js +282 -0
  426. package/out/tools/audit.js.map +1 -0
  427. package/out/tools/corpus-stats.d.ts +44 -0
  428. package/out/tools/corpus-stats.d.ts.map +1 -0
  429. package/out/tools/corpus-stats.js +102 -0
  430. package/out/tools/corpus-stats.js.map +1 -0
  431. package/out/tools/fetch/acra-sg.d.ts +23 -0
  432. package/out/tools/fetch/acra-sg.d.ts.map +1 -0
  433. package/out/tools/fetch/acra-sg.js +126 -0
  434. package/out/tools/fetch/acra-sg.js.map +1 -0
  435. package/out/tools/fetch/ban.d.ts +31 -0
  436. package/out/tools/fetch/ban.d.ts.map +1 -0
  437. package/out/tools/fetch/ban.js +239 -0
  438. package/out/tools/fetch/ban.js.map +1 -0
  439. package/out/tools/fetch/download.d.ts +182 -0
  440. package/out/tools/fetch/download.d.ts.map +1 -0
  441. package/out/tools/fetch/download.js +318 -0
  442. package/out/tools/fetch/download.js.map +1 -0
  443. package/out/tools/fetch/gcis-tw.d.ts +23 -0
  444. package/out/tools/fetch/gcis-tw.d.ts.map +1 -0
  445. package/out/tools/fetch/gcis-tw.js +135 -0
  446. package/out/tools/fetch/gcis-tw.js.map +1 -0
  447. package/out/tools/fetch/geonames-dump.d.ts +91 -0
  448. package/out/tools/fetch/geonames-dump.d.ts.map +1 -0
  449. package/out/tools/fetch/geonames-dump.js +171 -0
  450. package/out/tools/fetch/geonames-dump.js.map +1 -0
  451. package/out/tools/fetch/geonames-postal.d.ts +76 -0
  452. package/out/tools/fetch/geonames-postal.d.ts.map +1 -0
  453. package/out/tools/fetch/geonames-postal.js +126 -0
  454. package/out/tools/fetch/geonames-postal.js.map +1 -0
  455. package/out/tools/fetch/houjin-jp.d.ts +24 -0
  456. package/out/tools/fetch/houjin-jp.d.ts.map +1 -0
  457. package/out/tools/fetch/houjin-jp.js +102 -0
  458. package/out/tools/fetch/houjin-jp.js.map +1 -0
  459. package/out/tools/fetch/hrsa.d.ts +18 -0
  460. package/out/tools/fetch/hrsa.d.ts.map +1 -0
  461. package/out/tools/fetch/hrsa.js +46 -0
  462. package/out/tools/fetch/hrsa.js.map +1 -0
  463. package/out/tools/fetch/imls-pls.d.ts +25 -0
  464. package/out/tools/fetch/imls-pls.d.ts.map +1 -0
  465. package/out/tools/fetch/imls-pls.js +108 -0
  466. package/out/tools/fetch/imls-pls.js.map +1 -0
  467. package/out/tools/fetch/index.d.ts +171 -0
  468. package/out/tools/fetch/index.d.ts.map +1 -0
  469. package/out/tools/fetch/index.js +170 -0
  470. package/out/tools/fetch/index.js.map +1 -0
  471. package/out/tools/fetch/juso-kr.d.ts +30 -0
  472. package/out/tools/fetch/juso-kr.d.ts.map +1 -0
  473. package/out/tools/fetch/juso-kr.js +120 -0
  474. package/out/tools/fetch/juso-kr.js.map +1 -0
  475. package/out/tools/fetch/localdata-kr.d.ts +30 -0
  476. package/out/tools/fetch/localdata-kr.d.ts.map +1 -0
  477. package/out/tools/fetch/localdata-kr.js +139 -0
  478. package/out/tools/fetch/localdata-kr.js.map +1 -0
  479. package/out/tools/fetch/nad.d.ts +70 -0
  480. package/out/tools/fetch/nad.d.ts.map +1 -0
  481. package/out/tools/fetch/nad.js +234 -0
  482. package/out/tools/fetch/nad.js.map +1 -0
  483. package/out/tools/fetch/nppes.d.ts +26 -0
  484. package/out/tools/fetch/nppes.d.ts.map +1 -0
  485. package/out/tools/fetch/nppes.js +126 -0
  486. package/out/tools/fetch/nppes.js.map +1 -0
  487. package/out/tools/fetch/openaddresses.d.ts +9 -0
  488. package/out/tools/fetch/openaddresses.d.ts.map +1 -0
  489. package/out/tools/fetch/openaddresses.js +279 -0
  490. package/out/tools/fetch/openaddresses.js.map +1 -0
  491. package/out/tools/fetch/ourairports.d.ts +45 -0
  492. package/out/tools/fetch/ourairports.d.ts.map +1 -0
  493. package/out/tools/fetch/ourairports.js +128 -0
  494. package/out/tools/fetch/ourairports.js.map +1 -0
  495. package/out/tools/fetch/ppd.d.ts.map +1 -0
  496. package/out/tools/fetch/ppd.js +85 -0
  497. package/out/tools/fetch/ppd.js.map +1 -0
  498. package/out/tools/fetch/state-hi-schools.d.ts +26 -0
  499. package/out/tools/fetch/state-hi-schools.d.ts.map +1 -0
  500. package/out/tools/fetch/state-hi-schools.js +112 -0
  501. package/out/tools/fetch/state-hi-schools.js.map +1 -0
  502. package/out/tools/fetch/state-sources.d.ts +26 -0
  503. package/out/tools/fetch/state-sources.d.ts.map +1 -0
  504. package/out/tools/fetch/state-sources.js +111 -0
  505. package/out/tools/fetch/state-sources.js.map +1 -0
  506. package/out/tools/fetch/tiger-full.d.ts +22 -0
  507. package/out/tools/fetch/tiger-full.d.ts.map +1 -0
  508. package/out/tools/fetch/tiger-full.js +217 -0
  509. package/out/tools/fetch/tiger-full.js.map +1 -0
  510. package/out/tools/fetch/wikidata-subvenue.d.ts +171 -0
  511. package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -0
  512. package/out/tools/fetch/wikidata-subvenue.js +274 -0
  513. package/out/tools/fetch/wikidata-subvenue.js.map +1 -0
  514. package/out/tools/gb-title-case.d.ts.map +1 -0
  515. package/out/tools/gb-title-case.js.map +1 -0
  516. package/out/tools/golden-expand.d.ts +90 -0
  517. package/out/tools/golden-expand.d.ts.map +1 -0
  518. package/out/tools/golden-expand.js +406 -0
  519. package/out/tools/golden-expand.js.map +1 -0
  520. package/out/tools/golden-promote.d.ts.map +1 -0
  521. package/out/tools/golden-promote.js +240 -0
  522. package/out/tools/golden-promote.js.map +1 -0
  523. package/out/tools/golden-relabel-street.d.ts +196 -0
  524. package/out/tools/golden-relabel-street.d.ts.map +1 -0
  525. package/out/tools/golden-relabel-street.js +439 -0
  526. package/out/tools/golden-relabel-street.js.map +1 -0
  527. package/out/tools/index.d.ts +28 -0
  528. package/out/tools/index.d.ts.map +1 -0
  529. package/out/tools/index.js +28 -0
  530. package/out/tools/index.js.map +1 -0
  531. package/out/tools/ingest-csv.d.ts.map +1 -0
  532. package/out/tools/ingest-csv.js +265 -0
  533. package/out/tools/ingest-csv.js.map +1 -0
  534. package/out/tools/jsonl-to-parquet.d.ts +61 -0
  535. package/out/tools/jsonl-to-parquet.d.ts.map +1 -0
  536. package/out/tools/jsonl-to-parquet.js +150 -0
  537. package/out/tools/jsonl-to-parquet.js.map +1 -0
  538. package/out/tools/lint-slice-vocab.d.ts +90 -0
  539. package/out/tools/lint-slice-vocab.d.ts.map +1 -0
  540. package/out/tools/lint-slice-vocab.js +267 -0
  541. package/out/tools/lint-slice-vocab.js.map +1 -0
  542. package/out/tools/lint-slice.d.ts +93 -0
  543. package/out/tools/lint-slice.d.ts.map +1 -0
  544. package/out/tools/lint-slice.js +322 -0
  545. package/out/tools/lint-slice.js.map +1 -0
  546. package/out/tools/overlay-manifest.d.ts +39 -0
  547. package/out/tools/overlay-manifest.d.ts.map +1 -0
  548. package/out/tools/overlay-manifest.js +90 -0
  549. package/out/tools/overlay-manifest.js.map +1 -0
  550. package/out/tools/overture-subvenue.d.ts +112 -0
  551. package/out/tools/overture-subvenue.d.ts.map +1 -0
  552. package/out/tools/overture-subvenue.js +139 -0
  553. package/out/tools/overture-subvenue.js.map +1 -0
  554. package/out/tools/postcode-triples.d.ts +174 -0
  555. package/out/tools/postcode-triples.d.ts.map +1 -0
  556. package/out/tools/postcode-triples.js +292 -0
  557. package/out/tools/postcode-triples.js.map +1 -0
  558. package/out/tools/slice-kryptonite.d.ts +32 -0
  559. package/out/tools/slice-kryptonite.d.ts.map +1 -0
  560. package/out/tools/slice-kryptonite.js +99 -0
  561. package/out/tools/slice-kryptonite.js.map +1 -0
  562. package/out/tools/slice-translit.d.ts +51 -0
  563. package/out/tools/slice-translit.d.ts.map +1 -0
  564. package/out/tools/slice-translit.js +166 -0
  565. package/out/tools/slice-translit.js.map +1 -0
  566. package/out/tools/sub-venue/harvest.d.ts +100 -0
  567. package/out/tools/sub-venue/harvest.d.ts.map +1 -0
  568. package/out/tools/sub-venue/harvest.js +168 -0
  569. package/out/tools/sub-venue/harvest.js.map +1 -0
  570. package/out/tools/sub-venue/head-nouns.d.ts +50 -0
  571. package/out/tools/sub-venue/head-nouns.d.ts.map +1 -0
  572. package/out/tools/sub-venue/head-nouns.js +213 -0
  573. package/out/tools/sub-venue/head-nouns.js.map +1 -0
  574. package/out/tools/sub-venue/surfaces.d.ts +45 -0
  575. package/out/tools/sub-venue/surfaces.d.ts.map +1 -0
  576. package/out/tools/sub-venue/surfaces.js +77 -0
  577. package/out/tools/sub-venue/surfaces.js.map +1 -0
  578. package/out/tools/sub-venue/table.d.ts +229 -0
  579. package/out/tools/sub-venue/table.d.ts.map +1 -0
  580. package/out/tools/sub-venue/table.js +108 -0
  581. package/out/tools/sub-venue/table.js.map +1 -0
  582. package/out/tools/sub-venue/wikidata.d.ts +26 -0
  583. package/out/tools/sub-venue/wikidata.d.ts.map +1 -0
  584. package/out/tools/sub-venue/wikidata.js +62 -0
  585. package/out/tools/sub-venue/wikidata.js.map +1 -0
  586. package/out/tools/sub-venue-lexicon.d.ts +156 -0
  587. package/out/tools/sub-venue-lexicon.d.ts.map +1 -0
  588. package/out/tools/sub-venue-lexicon.js +283 -0
  589. package/out/tools/sub-venue-lexicon.js.map +1 -0
  590. package/out/tools/sub-venue-promotions.d.ts +94 -0
  591. package/out/tools/sub-venue-promotions.d.ts.map +1 -0
  592. package/out/tools/sub-venue-promotions.js +266 -0
  593. package/out/tools/sub-venue-promotions.js.map +1 -0
  594. package/out/types.d.ts +221 -0
  595. package/out/types.d.ts.map +1 -0
  596. package/out/types.js.map +1 -0
  597. package/out/utils/align.d.ts +93 -0
  598. package/out/utils/align.d.ts.map +1 -0
  599. package/out/utils/align.js +234 -0
  600. package/out/utils/align.js.map +1 -0
  601. package/out/utils/golden.d.ts +85 -0
  602. package/out/utils/golden.d.ts.map +1 -0
  603. package/out/utils/golden.js +127 -0
  604. package/out/utils/golden.js.map +1 -0
  605. package/out/utils/index.d.ts +14 -0
  606. package/out/utils/index.d.ts.map +1 -0
  607. package/out/utils/index.js +14 -0
  608. package/out/utils/index.js.map +1 -0
  609. package/out/utils/license.d.ts.map +1 -0
  610. package/out/utils/license.js.map +1 -0
  611. package/out/utils/parquet.d.ts +178 -0
  612. package/out/utils/parquet.d.ts.map +1 -0
  613. package/out/utils/parquet.js +371 -0
  614. package/out/utils/parquet.js.map +1 -0
  615. package/out/utils/slice-stats.d.ts +52 -0
  616. package/out/utils/slice-stats.d.ts.map +1 -0
  617. package/out/utils/slice-stats.js +58 -0
  618. package/out/utils/slice-stats.js.map +1 -0
  619. package/out/utils/split.d.ts +128 -0
  620. package/out/utils/split.d.ts.map +1 -0
  621. package/out/utils/split.js +204 -0
  622. package/out/utils/split.js.map +1 -0
  623. package/out/utils/tokenize.d.ts +64 -0
  624. package/out/utils/tokenize.d.ts.map +1 -0
  625. package/out/utils/tokenize.js +82 -0
  626. package/out/utils/tokenize.js.map +1 -0
  627. package/out/utils/wof-json.d.ts +113 -0
  628. package/out/utils/wof-json.d.ts.map +1 -0
  629. package/out/utils/wof-json.js +173 -0
  630. package/out/utils/wof-json.js.map +1 -0
  631. package/package.json +259 -194
  632. package/out/src/adapters/ban/adapter.d.ts.map +0 -1
  633. package/out/src/adapters/ban/adapter.js +0 -149
  634. package/out/src/adapters/ban/adapter.js.map +0 -1
  635. package/out/src/adapters/ban/street-decompose.d.ts.map +0 -1
  636. package/out/src/adapters/ban/street-decompose.js +0 -75
  637. package/out/src/adapters/ban/street-decompose.js.map +0 -1
  638. package/out/src/adapters/fcc-bdc/adapter.d.ts.map +0 -1
  639. package/out/src/adapters/fcc-bdc/adapter.js +0 -144
  640. package/out/src/adapters/fcc-bdc/adapter.js.map +0 -1
  641. package/out/src/adapters/geonames/adapter.d.ts.map +0 -1
  642. package/out/src/adapters/geonames/adapter.js +0 -176
  643. package/out/src/adapters/geonames/adapter.js.map +0 -1
  644. package/out/src/adapters/geonames-postal/adapter.d.ts +0 -41
  645. package/out/src/adapters/geonames-postal/adapter.d.ts.map +0 -1
  646. package/out/src/adapters/geonames-postal/adapter.js +0 -104
  647. package/out/src/adapters/geonames-postal/adapter.js.map +0 -1
  648. package/out/src/adapters/gnaf/adapter.d.ts +0 -49
  649. package/out/src/adapters/gnaf/adapter.d.ts.map +0 -1
  650. package/out/src/adapters/gnaf/adapter.js +0 -124
  651. package/out/src/adapters/gnaf/adapter.js.map +0 -1
  652. package/out/src/adapters/gnaf/assemble.d.ts +0 -65
  653. package/out/src/adapters/gnaf/assemble.d.ts.map +0 -1
  654. package/out/src/adapters/gnaf/assemble.js +0 -154
  655. package/out/src/adapters/gnaf/assemble.js.map +0 -1
  656. package/out/src/adapters/index.d.ts +0 -51
  657. package/out/src/adapters/index.d.ts.map +0 -1
  658. package/out/src/adapters/index.js +0 -95
  659. package/out/src/adapters/index.js.map +0 -1
  660. package/out/src/adapters/openaddresses/adapter.d.ts.map +0 -1
  661. package/out/src/adapters/openaddresses/adapter.js +0 -186
  662. package/out/src/adapters/openaddresses/adapter.js.map +0 -1
  663. package/out/src/adapters/overture/adapter.d.ts +0 -48
  664. package/out/src/adapters/overture/adapter.d.ts.map +0 -1
  665. package/out/src/adapters/overture/adapter.js +0 -125
  666. package/out/src/adapters/overture/adapter.js.map +0 -1
  667. package/out/src/adapters/state-hi-schools/adapter.d.ts +0 -47
  668. package/out/src/adapters/state-hi-schools/adapter.d.ts.map +0 -1
  669. package/out/src/adapters/state-hi-schools/adapter.js +0 -133
  670. package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
  671. package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
  672. package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
  673. package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
  674. package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
  675. package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
  676. package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
  677. package/out/src/adapters/synth-po-box/adapter.d.ts.map +0 -1
  678. package/out/src/adapters/synth-po-box/adapter.js +0 -140
  679. package/out/src/adapters/synth-po-box/adapter.js.map +0 -1
  680. package/out/src/adapters/tiger/adapter.d.ts +0 -55
  681. package/out/src/adapters/tiger/adapter.d.ts.map +0 -1
  682. package/out/src/adapters/tiger/adapter.js +0 -201
  683. package/out/src/adapters/tiger/adapter.js.map +0 -1
  684. package/out/src/adapters/tiger/street-decompose.d.ts.map +0 -1
  685. package/out/src/adapters/tiger/street-decompose.js +0 -90
  686. package/out/src/adapters/tiger/street-decompose.js.map +0 -1
  687. package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -47
  688. package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
  689. package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +0 -139
  690. package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
  691. package/out/src/adapters/usgov-imls-pls/adapter.d.ts +0 -36
  692. package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
  693. package/out/src/adapters/usgov-imls-pls/adapter.js +0 -114
  694. package/out/src/adapters/usgov-imls-pls/adapter.js.map +0 -1
  695. package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
  696. package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
  697. package/out/src/adapters/usgov-irs-bmf/adapter.js +0 -124
  698. package/out/src/adapters/usgov-irs-bmf/adapter.js.map +0 -1
  699. package/out/src/adapters/usgov-nad/adapter.d.ts +0 -48
  700. package/out/src/adapters/usgov-nad/adapter.d.ts.map +0 -1
  701. package/out/src/adapters/usgov-nad/adapter.js +0 -252
  702. package/out/src/adapters/usgov-nad/adapter.js.map +0 -1
  703. package/out/src/adapters/usgov-nppes/adapter.d.ts.map +0 -1
  704. package/out/src/adapters/usgov-nppes/adapter.js +0 -116
  705. package/out/src/adapters/usgov-nppes/adapter.js.map +0 -1
  706. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
  707. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -156
  708. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
  709. package/out/src/adapters/utils/index.d.ts +0 -150
  710. package/out/src/adapters/utils/index.d.ts.map +0 -1
  711. package/out/src/adapters/utils/index.js +0 -159
  712. package/out/src/adapters/utils/index.js.map +0 -1
  713. package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
  714. package/out/src/adapters/wof-admin-jp/adapter.js +0 -164
  715. package/out/src/adapters/wof-admin-jp/adapter.js.map +0 -1
  716. package/out/src/adapters/wof-admin-json/adapter.d.ts +0 -82
  717. package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
  718. package/out/src/adapters/wof-admin-json/adapter.js +0 -224
  719. package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
  720. package/out/src/adapters/wof-json-rows.d.ts +0 -32
  721. package/out/src/adapters/wof-json-rows.d.ts.map +0 -1
  722. package/out/src/adapters/wof-json-rows.js +0 -45
  723. package/out/src/adapters/wof-json-rows.js.map +0 -1
  724. package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -65
  725. package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
  726. package/out/src/adapters/wof-postalcode-json/adapter.js +0 -160
  727. package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
  728. package/out/src/build.d.ts +0 -132
  729. package/out/src/build.d.ts.map +0 -1
  730. package/out/src/build.js +0 -251
  731. package/out/src/build.js.map +0 -1
  732. package/out/src/codex/us-fips-state.d.ts.map +0 -1
  733. package/out/src/codex/us-fips-state.js.map +0 -1
  734. package/out/src/index.d.ts +0 -14
  735. package/out/src/index.d.ts.map +0 -1
  736. package/out/src/index.js +0 -14
  737. package/out/src/index.js.map +0 -1
  738. package/out/src/name-prone-us-suffixes.d.ts +0 -12
  739. package/out/src/name-prone-us-suffixes.d.ts.map +0 -1
  740. package/out/src/name-prone-us-suffixes.js +0 -12
  741. package/out/src/name-prone-us-suffixes.js.map +0 -1
  742. package/out/src/parquet-wrapper/index.d.ts +0 -9
  743. package/out/src/parquet-wrapper/index.d.ts.map +0 -1
  744. package/out/src/parquet-wrapper/index.js +0 -9
  745. package/out/src/parquet-wrapper/index.js.map +0 -1
  746. package/out/src/parquet-wrapper/reader.d.ts +0 -34
  747. package/out/src/parquet-wrapper/reader.d.ts.map +0 -1
  748. package/out/src/parquet-wrapper/reader.js +0 -69
  749. package/out/src/parquet-wrapper/reader.js.map +0 -1
  750. package/out/src/parquet-wrapper/schema.d.ts +0 -49
  751. package/out/src/parquet-wrapper/schema.d.ts.map +0 -1
  752. package/out/src/parquet-wrapper/schema.js +0 -55
  753. package/out/src/parquet-wrapper/schema.js.map +0 -1
  754. package/out/src/parquet-wrapper/writer.d.ts +0 -46
  755. package/out/src/parquet-wrapper/writer.d.ts.map +0 -1
  756. package/out/src/parquet-wrapper/writer.js +0 -76
  757. package/out/src/parquet-wrapper/writer.js.map +0 -1
  758. package/out/src/runner.d.ts +0 -126
  759. package/out/src/runner.d.ts.map +0 -1
  760. package/out/src/runner.js +0 -189
  761. package/out/src/runner.js.map +0 -1
  762. package/out/src/shard-recipes/anchor-absorption.d.ts +0 -20
  763. package/out/src/shard-recipes/anchor-absorption.d.ts.map +0 -1
  764. package/out/src/shard-recipes/anchor-absorption.js +0 -82
  765. package/out/src/shard-recipes/anchor-absorption.js.map +0 -1
  766. package/out/src/shard-recipes/bare-country.d.ts +0 -25
  767. package/out/src/shard-recipes/bare-country.d.ts.map +0 -1
  768. package/out/src/shard-recipes/bare-country.js +0 -87
  769. package/out/src/shard-recipes/bare-country.js.map +0 -1
  770. package/out/src/shard-recipes/boundary-stress.d.ts +0 -20
  771. package/out/src/shard-recipes/boundary-stress.d.ts.map +0 -1
  772. package/out/src/shard-recipes/boundary-stress.js +0 -83
  773. package/out/src/shard-recipes/boundary-stress.js.map +0 -1
  774. package/out/src/shard-recipes/country-balanced.d.ts +0 -32
  775. package/out/src/shard-recipes/country-balanced.d.ts.map +0 -1
  776. package/out/src/shard-recipes/country-balanced.js +0 -406
  777. package/out/src/shard-recipes/country-balanced.js.map +0 -1
  778. package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts +0 -22
  779. package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +0 -1
  780. package/out/src/shard-recipes/cz-pcfirst-preposition.js +0 -100
  781. package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +0 -1
  782. package/out/src/shard-recipes/fr-admin-split.d.ts +0 -38
  783. package/out/src/shard-recipes/fr-admin-split.d.ts.map +0 -1
  784. package/out/src/shard-recipes/fr-admin-split.js +0 -188
  785. package/out/src/shard-recipes/fr-admin-split.js.map +0 -1
  786. package/out/src/shard-recipes/fr-bare-street.d.ts +0 -28
  787. package/out/src/shard-recipes/fr-bare-street.d.ts.map +0 -1
  788. package/out/src/shard-recipes/fr-bare-street.js +0 -143
  789. package/out/src/shard-recipes/fr-bare-street.js.map +0 -1
  790. package/out/src/shard-recipes/fr-fragment.d.ts +0 -77
  791. package/out/src/shard-recipes/fr-fragment.d.ts.map +0 -1
  792. package/out/src/shard-recipes/fr-fragment.js +0 -276
  793. package/out/src/shard-recipes/fr-fragment.js.map +0 -1
  794. package/out/src/shard-recipes/fr-lieudit.d.ts +0 -32
  795. package/out/src/shard-recipes/fr-lieudit.d.ts.map +0 -1
  796. package/out/src/shard-recipes/fr-lieudit.js +0 -226
  797. package/out/src/shard-recipes/fr-lieudit.js.map +0 -1
  798. package/out/src/shard-recipes/fr-order.d.ts +0 -38
  799. package/out/src/shard-recipes/fr-order.d.ts.map +0 -1
  800. package/out/src/shard-recipes/fr-order.js +0 -208
  801. package/out/src/shard-recipes/fr-order.js.map +0 -1
  802. package/out/src/shard-recipes/german.d.ts +0 -23
  803. package/out/src/shard-recipes/german.d.ts.map +0 -1
  804. package/out/src/shard-recipes/german.js +0 -132
  805. package/out/src/shard-recipes/german.js.map +0 -1
  806. package/out/src/shard-recipes/house-venue.d.ts +0 -18
  807. package/out/src/shard-recipes/house-venue.d.ts.map +0 -1
  808. package/out/src/shard-recipes/house-venue.js +0 -74
  809. package/out/src/shard-recipes/house-venue.js.map +0 -1
  810. package/out/src/shard-recipes/index.d.ts +0 -24
  811. package/out/src/shard-recipes/index.d.ts.map +0 -1
  812. package/out/src/shard-recipes/index.js +0 -89
  813. package/out/src/shard-recipes/index.js.map +0 -1
  814. package/out/src/shard-recipes/intersection.d.ts +0 -42
  815. package/out/src/shard-recipes/intersection.d.ts.map +0 -1
  816. package/out/src/shard-recipes/intersection.js +0 -460
  817. package/out/src/shard-recipes/intersection.js.map +0 -1
  818. package/out/src/shard-recipes/locale.d.ts +0 -135
  819. package/out/src/shard-recipes/locale.d.ts.map +0 -1
  820. package/out/src/shard-recipes/locale.js +0 -459
  821. package/out/src/shard-recipes/locale.js.map +0 -1
  822. package/out/src/shard-recipes/nl-postcode.d.ts +0 -26
  823. package/out/src/shard-recipes/nl-postcode.d.ts.map +0 -1
  824. package/out/src/shard-recipes/nl-postcode.js +0 -102
  825. package/out/src/shard-recipes/nl-postcode.js.map +0 -1
  826. package/out/src/shard-recipes/no-fragment.d.ts +0 -43
  827. package/out/src/shard-recipes/no-fragment.d.ts.map +0 -1
  828. package/out/src/shard-recipes/no-fragment.js +0 -188
  829. package/out/src/shard-recipes/no-fragment.js.map +0 -1
  830. package/out/src/shard-recipes/no-street-led.d.ts +0 -24
  831. package/out/src/shard-recipes/no-street-led.d.ts.map +0 -1
  832. package/out/src/shard-recipes/no-street-led.js +0 -121
  833. package/out/src/shard-recipes/no-street-led.js.map +0 -1
  834. package/out/src/shard-recipes/no-street.d.ts +0 -18
  835. package/out/src/shard-recipes/no-street.d.ts.map +0 -1
  836. package/out/src/shard-recipes/no-street.js +0 -72
  837. package/out/src/shard-recipes/no-street.js.map +0 -1
  838. package/out/src/shard-recipes/po-box-cedex.d.ts +0 -38
  839. package/out/src/shard-recipes/po-box-cedex.d.ts.map +0 -1
  840. package/out/src/shard-recipes/po-box-cedex.js +0 -726
  841. package/out/src/shard-recipes/po-box-cedex.js.map +0 -1
  842. package/out/src/shard-recipes/po-box.d.ts +0 -17
  843. package/out/src/shard-recipes/po-box.d.ts.map +0 -1
  844. package/out/src/shard-recipes/po-box.js +0 -101
  845. package/out/src/shard-recipes/po-box.js.map +0 -1
  846. package/out/src/shard-recipes/reviewed-postcode-tail.d.ts +0 -47
  847. package/out/src/shard-recipes/reviewed-postcode-tail.d.ts.map +0 -1
  848. package/out/src/shard-recipes/reviewed-postcode-tail.js +0 -125
  849. package/out/src/shard-recipes/reviewed-postcode-tail.js.map +0 -1
  850. package/out/src/shard-recipes/scaffold.d.ts +0 -246
  851. package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
  852. package/out/src/shard-recipes/scaffold.js +0 -137
  853. package/out/src/shard-recipes/scaffold.js.map +0 -1
  854. package/out/src/shard-recipes/si-bare-village.d.ts +0 -32
  855. package/out/src/shard-recipes/si-bare-village.d.ts.map +0 -1
  856. package/out/src/shard-recipes/si-bare-village.js +0 -88
  857. package/out/src/shard-recipes/si-bare-village.js.map +0 -1
  858. package/out/src/shard-recipes/street-affix.d.ts +0 -89
  859. package/out/src/shard-recipes/street-affix.d.ts.map +0 -1
  860. package/out/src/shard-recipes/street-affix.js +0 -578
  861. package/out/src/shard-recipes/street-affix.js.map +0 -1
  862. package/out/src/shard-recipes/street-bare.d.ts +0 -25
  863. package/out/src/shard-recipes/street-bare.d.ts.map +0 -1
  864. package/out/src/shard-recipes/street-bare.js +0 -86
  865. package/out/src/shard-recipes/street-bare.js.map +0 -1
  866. package/out/src/shard-recipes/street.d.ts +0 -15
  867. package/out/src/shard-recipes/street.d.ts.map +0 -1
  868. package/out/src/shard-recipes/street.js +0 -69
  869. package/out/src/shard-recipes/street.js.map +0 -1
  870. package/out/src/shard-recipes/sub-venue-sources.d.ts +0 -228
  871. package/out/src/shard-recipes/sub-venue-sources.d.ts.map +0 -1
  872. package/out/src/shard-recipes/sub-venue-sources.js +0 -664
  873. package/out/src/shard-recipes/sub-venue-sources.js.map +0 -1
  874. package/out/src/shard-recipes/sub-venue.d.ts +0 -269
  875. package/out/src/shard-recipes/sub-venue.d.ts.map +0 -1
  876. package/out/src/shard-recipes/sub-venue.js +0 -710
  877. package/out/src/shard-recipes/sub-venue.js.map +0 -1
  878. package/out/src/shard-recipes/trailing-region.d.ts +0 -74
  879. package/out/src/shard-recipes/trailing-region.d.ts.map +0 -1
  880. package/out/src/shard-recipes/trailing-region.js +0 -157
  881. package/out/src/shard-recipes/trailing-region.js.map +0 -1
  882. package/out/src/shard-recipes/unit.d.ts +0 -29
  883. package/out/src/shard-recipes/unit.d.ts.map +0 -1
  884. package/out/src/shard-recipes/unit.js +0 -243
  885. package/out/src/shard-recipes/unit.js.map +0 -1
  886. package/out/src/synthesizers/anchor-absorption.d.ts +0 -63
  887. package/out/src/synthesizers/anchor-absorption.d.ts.map +0 -1
  888. package/out/src/synthesizers/anchor-absorption.js +0 -223
  889. package/out/src/synthesizers/anchor-absorption.js.map +0 -1
  890. package/out/src/synthesizers/boundary-stress.d.ts +0 -78
  891. package/out/src/synthesizers/boundary-stress.d.ts.map +0 -1
  892. package/out/src/synthesizers/boundary-stress.js +0 -455
  893. package/out/src/synthesizers/boundary-stress.js.map +0 -1
  894. package/out/src/synthesizers/german.d.ts +0 -107
  895. package/out/src/synthesizers/german.d.ts.map +0 -1
  896. package/out/src/synthesizers/german.js +0 -148
  897. package/out/src/synthesizers/german.js.map +0 -1
  898. package/out/src/synthesizers/house-venue.d.ts +0 -56
  899. package/out/src/synthesizers/house-venue.d.ts.map +0 -1
  900. package/out/src/synthesizers/house-venue.js +0 -267
  901. package/out/src/synthesizers/house-venue.js.map +0 -1
  902. package/out/src/synthesizers/intersection.d.ts +0 -52
  903. package/out/src/synthesizers/intersection.d.ts.map +0 -1
  904. package/out/src/synthesizers/intersection.js +0 -175
  905. package/out/src/synthesizers/intersection.js.map +0 -1
  906. package/out/src/synthesizers/no-street.d.ts +0 -72
  907. package/out/src/synthesizers/no-street.d.ts.map +0 -1
  908. package/out/src/synthesizers/no-street.js +0 -282
  909. package/out/src/synthesizers/no-street.js.map +0 -1
  910. package/out/src/synthesizers/po-box.d.ts +0 -104
  911. package/out/src/synthesizers/po-box.d.ts.map +0 -1
  912. package/out/src/synthesizers/po-box.js +0 -266
  913. package/out/src/synthesizers/po-box.js.map +0 -1
  914. package/out/src/synthesizers/street.d.ts +0 -54
  915. package/out/src/synthesizers/street.d.ts.map +0 -1
  916. package/out/src/synthesizers/street.js +0 -221
  917. package/out/src/synthesizers/street.js.map +0 -1
  918. package/out/src/synthesizers/utils.d.ts +0 -203
  919. package/out/src/synthesizers/utils.d.ts.map +0 -1
  920. package/out/src/synthesizers/utils.js +0 -708
  921. package/out/src/synthesizers/utils.js.map +0 -1
  922. package/out/src/tools/align-shard.d.ts +0 -8
  923. package/out/src/tools/align-shard.d.ts.map +0 -1
  924. package/out/src/tools/align-shard.js +0 -56
  925. package/out/src/tools/align-shard.js.map +0 -1
  926. package/out/src/tools/audit.d.ts +0 -28
  927. package/out/src/tools/audit.d.ts.map +0 -1
  928. package/out/src/tools/audit.js +0 -285
  929. package/out/src/tools/audit.js.map +0 -1
  930. package/out/src/tools/corpus-stats.d.ts +0 -44
  931. package/out/src/tools/corpus-stats.d.ts.map +0 -1
  932. package/out/src/tools/corpus-stats.js +0 -138
  933. package/out/src/tools/corpus-stats.js.map +0 -1
  934. package/out/src/tools/fetch/ban.d.ts +0 -31
  935. package/out/src/tools/fetch/ban.d.ts.map +0 -1
  936. package/out/src/tools/fetch/ban.js +0 -239
  937. package/out/src/tools/fetch/ban.js.map +0 -1
  938. package/out/src/tools/fetch/download.d.ts +0 -78
  939. package/out/src/tools/fetch/download.d.ts.map +0 -1
  940. package/out/src/tools/fetch/download.js +0 -116
  941. package/out/src/tools/fetch/download.js.map +0 -1
  942. package/out/src/tools/fetch/geonames-dump.d.ts +0 -87
  943. package/out/src/tools/fetch/geonames-dump.d.ts.map +0 -1
  944. package/out/src/tools/fetch/geonames-dump.js +0 -178
  945. package/out/src/tools/fetch/geonames-dump.js.map +0 -1
  946. package/out/src/tools/fetch/geonames-postal.d.ts +0 -76
  947. package/out/src/tools/fetch/geonames-postal.d.ts.map +0 -1
  948. package/out/src/tools/fetch/geonames-postal.js +0 -125
  949. package/out/src/tools/fetch/geonames-postal.js.map +0 -1
  950. package/out/src/tools/fetch/hrsa.d.ts +0 -18
  951. package/out/src/tools/fetch/hrsa.d.ts.map +0 -1
  952. package/out/src/tools/fetch/hrsa.js +0 -46
  953. package/out/src/tools/fetch/hrsa.js.map +0 -1
  954. package/out/src/tools/fetch/imls-pls.d.ts +0 -25
  955. package/out/src/tools/fetch/imls-pls.d.ts.map +0 -1
  956. package/out/src/tools/fetch/imls-pls.js +0 -108
  957. package/out/src/tools/fetch/imls-pls.js.map +0 -1
  958. package/out/src/tools/fetch/index.d.ts +0 -144
  959. package/out/src/tools/fetch/index.d.ts.map +0 -1
  960. package/out/src/tools/fetch/index.js +0 -143
  961. package/out/src/tools/fetch/index.js.map +0 -1
  962. package/out/src/tools/fetch/nad.d.ts +0 -70
  963. package/out/src/tools/fetch/nad.d.ts.map +0 -1
  964. package/out/src/tools/fetch/nad.js +0 -234
  965. package/out/src/tools/fetch/nad.js.map +0 -1
  966. package/out/src/tools/fetch/nppes.d.ts +0 -26
  967. package/out/src/tools/fetch/nppes.d.ts.map +0 -1
  968. package/out/src/tools/fetch/nppes.js +0 -126
  969. package/out/src/tools/fetch/nppes.js.map +0 -1
  970. package/out/src/tools/fetch/openaddresses.d.ts +0 -61
  971. package/out/src/tools/fetch/openaddresses.d.ts.map +0 -1
  972. package/out/src/tools/fetch/openaddresses.js +0 -317
  973. package/out/src/tools/fetch/openaddresses.js.map +0 -1
  974. package/out/src/tools/fetch/ourairports.d.ts +0 -45
  975. package/out/src/tools/fetch/ourairports.d.ts.map +0 -1
  976. package/out/src/tools/fetch/ourairports.js +0 -128
  977. package/out/src/tools/fetch/ourairports.js.map +0 -1
  978. package/out/src/tools/fetch/ppd.d.ts.map +0 -1
  979. package/out/src/tools/fetch/ppd.js +0 -100
  980. package/out/src/tools/fetch/ppd.js.map +0 -1
  981. package/out/src/tools/fetch/state-hi-schools.d.ts +0 -25
  982. package/out/src/tools/fetch/state-hi-schools.d.ts.map +0 -1
  983. package/out/src/tools/fetch/state-hi-schools.js +0 -162
  984. package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
  985. package/out/src/tools/fetch/state-sources.d.ts +0 -26
  986. package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
  987. package/out/src/tools/fetch/state-sources.js +0 -111
  988. package/out/src/tools/fetch/state-sources.js.map +0 -1
  989. package/out/src/tools/fetch/tiger-full.d.ts +0 -42
  990. package/out/src/tools/fetch/tiger-full.d.ts.map +0 -1
  991. package/out/src/tools/fetch/tiger-full.js +0 -248
  992. package/out/src/tools/fetch/tiger-full.js.map +0 -1
  993. package/out/src/tools/fetch/wikidata-subvenue.d.ts +0 -171
  994. package/out/src/tools/fetch/wikidata-subvenue.d.ts.map +0 -1
  995. package/out/src/tools/fetch/wikidata-subvenue.js +0 -275
  996. package/out/src/tools/fetch/wikidata-subvenue.js.map +0 -1
  997. package/out/src/tools/gb-title-case.d.ts.map +0 -1
  998. package/out/src/tools/gb-title-case.js.map +0 -1
  999. package/out/src/tools/golden-expand.d.ts +0 -90
  1000. package/out/src/tools/golden-expand.d.ts.map +0 -1
  1001. package/out/src/tools/golden-expand.js +0 -413
  1002. package/out/src/tools/golden-expand.js.map +0 -1
  1003. package/out/src/tools/golden-promote.d.ts.map +0 -1
  1004. package/out/src/tools/golden-promote.js +0 -244
  1005. package/out/src/tools/golden-promote.js.map +0 -1
  1006. package/out/src/tools/golden-relabel-street.d.ts +0 -196
  1007. package/out/src/tools/golden-relabel-street.d.ts.map +0 -1
  1008. package/out/src/tools/golden-relabel-street.js +0 -440
  1009. package/out/src/tools/golden-relabel-street.js.map +0 -1
  1010. package/out/src/tools/index.d.ts +0 -28
  1011. package/out/src/tools/index.d.ts.map +0 -1
  1012. package/out/src/tools/index.js +0 -28
  1013. package/out/src/tools/index.js.map +0 -1
  1014. package/out/src/tools/ingest-csv.d.ts.map +0 -1
  1015. package/out/src/tools/ingest-csv.js +0 -296
  1016. package/out/src/tools/ingest-csv.js.map +0 -1
  1017. package/out/src/tools/jsonl-to-parquet.d.ts +0 -61
  1018. package/out/src/tools/jsonl-to-parquet.d.ts.map +0 -1
  1019. package/out/src/tools/jsonl-to-parquet.js +0 -164
  1020. package/out/src/tools/jsonl-to-parquet.js.map +0 -1
  1021. package/out/src/tools/lint-shard-vocab.d.ts +0 -90
  1022. package/out/src/tools/lint-shard-vocab.d.ts.map +0 -1
  1023. package/out/src/tools/lint-shard-vocab.js +0 -281
  1024. package/out/src/tools/lint-shard-vocab.js.map +0 -1
  1025. package/out/src/tools/lint-shard.d.ts +0 -93
  1026. package/out/src/tools/lint-shard.d.ts.map +0 -1
  1027. package/out/src/tools/lint-shard.js +0 -354
  1028. package/out/src/tools/lint-shard.js.map +0 -1
  1029. package/out/src/tools/overlay-manifest.d.ts +0 -39
  1030. package/out/src/tools/overlay-manifest.d.ts.map +0 -1
  1031. package/out/src/tools/overlay-manifest.js +0 -98
  1032. package/out/src/tools/overlay-manifest.js.map +0 -1
  1033. package/out/src/tools/overture-subvenue.d.ts +0 -112
  1034. package/out/src/tools/overture-subvenue.d.ts.map +0 -1
  1035. package/out/src/tools/overture-subvenue.js +0 -144
  1036. package/out/src/tools/overture-subvenue.js.map +0 -1
  1037. package/out/src/tools/postcode-triples.d.ts +0 -175
  1038. package/out/src/tools/postcode-triples.d.ts.map +0 -1
  1039. package/out/src/tools/postcode-triples.js +0 -304
  1040. package/out/src/tools/postcode-triples.js.map +0 -1
  1041. package/out/src/tools/shard-kryptonite.d.ts +0 -32
  1042. package/out/src/tools/shard-kryptonite.d.ts.map +0 -1
  1043. package/out/src/tools/shard-kryptonite.js +0 -100
  1044. package/out/src/tools/shard-kryptonite.js.map +0 -1
  1045. package/out/src/tools/shard-translit.d.ts +0 -51
  1046. package/out/src/tools/shard-translit.d.ts.map +0 -1
  1047. package/out/src/tools/shard-translit.js +0 -175
  1048. package/out/src/tools/shard-translit.js.map +0 -1
  1049. package/out/src/tools/sub-venue/harvest.d.ts +0 -100
  1050. package/out/src/tools/sub-venue/harvest.d.ts.map +0 -1
  1051. package/out/src/tools/sub-venue/harvest.js +0 -168
  1052. package/out/src/tools/sub-venue/harvest.js.map +0 -1
  1053. package/out/src/tools/sub-venue/head-nouns.d.ts +0 -50
  1054. package/out/src/tools/sub-venue/head-nouns.d.ts.map +0 -1
  1055. package/out/src/tools/sub-venue/head-nouns.js +0 -210
  1056. package/out/src/tools/sub-venue/head-nouns.js.map +0 -1
  1057. package/out/src/tools/sub-venue/surfaces.d.ts +0 -45
  1058. package/out/src/tools/sub-venue/surfaces.d.ts.map +0 -1
  1059. package/out/src/tools/sub-venue/surfaces.js +0 -77
  1060. package/out/src/tools/sub-venue/surfaces.js.map +0 -1
  1061. package/out/src/tools/sub-venue/table.d.ts +0 -229
  1062. package/out/src/tools/sub-venue/table.d.ts.map +0 -1
  1063. package/out/src/tools/sub-venue/table.js +0 -108
  1064. package/out/src/tools/sub-venue/table.js.map +0 -1
  1065. package/out/src/tools/sub-venue/wikidata.d.ts +0 -26
  1066. package/out/src/tools/sub-venue/wikidata.d.ts.map +0 -1
  1067. package/out/src/tools/sub-venue/wikidata.js +0 -62
  1068. package/out/src/tools/sub-venue/wikidata.js.map +0 -1
  1069. package/out/src/tools/sub-venue-lexicon.d.ts +0 -156
  1070. package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
  1071. package/out/src/tools/sub-venue-lexicon.js +0 -282
  1072. package/out/src/tools/sub-venue-lexicon.js.map +0 -1
  1073. package/out/src/tools/sub-venue-promotions.d.ts +0 -94
  1074. package/out/src/tools/sub-venue-promotions.d.ts.map +0 -1
  1075. package/out/src/tools/sub-venue-promotions.js +0 -266
  1076. package/out/src/tools/sub-venue-promotions.js.map +0 -1
  1077. package/out/src/types.d.ts +0 -221
  1078. package/out/src/types.d.ts.map +0 -1
  1079. package/out/src/types.js.map +0 -1
  1080. package/out/src/utils/align.d.ts +0 -93
  1081. package/out/src/utils/align.d.ts.map +0 -1
  1082. package/out/src/utils/align.js +0 -234
  1083. package/out/src/utils/align.js.map +0 -1
  1084. package/out/src/utils/golden.d.ts +0 -69
  1085. package/out/src/utils/golden.d.ts.map +0 -1
  1086. package/out/src/utils/golden.js +0 -127
  1087. package/out/src/utils/golden.js.map +0 -1
  1088. package/out/src/utils/index.d.ts +0 -14
  1089. package/out/src/utils/index.d.ts.map +0 -1
  1090. package/out/src/utils/index.js +0 -14
  1091. package/out/src/utils/index.js.map +0 -1
  1092. package/out/src/utils/license.d.ts.map +0 -1
  1093. package/out/src/utils/license.js.map +0 -1
  1094. package/out/src/utils/parquet.d.ts +0 -162
  1095. package/out/src/utils/parquet.d.ts.map +0 -1
  1096. package/out/src/utils/parquet.js +0 -262
  1097. package/out/src/utils/parquet.js.map +0 -1
  1098. package/out/src/utils/split.d.ts +0 -127
  1099. package/out/src/utils/split.d.ts.map +0 -1
  1100. package/out/src/utils/split.js +0 -204
  1101. package/out/src/utils/split.js.map +0 -1
  1102. package/out/src/utils/tokenize.d.ts +0 -56
  1103. package/out/src/utils/tokenize.d.ts.map +0 -1
  1104. package/out/src/utils/tokenize.js +0 -48
  1105. package/out/src/utils/tokenize.js.map +0 -1
  1106. package/out/src/utils/wof-json.d.ts +0 -109
  1107. package/out/src/utils/wof-json.d.ts.map +0 -1
  1108. package/out/src/utils/wof-json.js +0 -173
  1109. package/out/src/utils/wof-json.js.map +0 -1
  1110. package/src/adapters/ban/adapter.ts +0 -191
  1111. package/src/adapters/ban/street-decompose.ts +0 -96
  1112. package/src/adapters/fcc-bdc/adapter.ts +0 -174
  1113. package/src/adapters/geonames/adapter.ts +0 -200
  1114. package/src/adapters/geonames-postal/adapter.ts +0 -119
  1115. package/src/adapters/gnaf/adapter.ts +0 -149
  1116. package/src/adapters/gnaf/assemble.ts +0 -226
  1117. package/src/adapters/index.ts +0 -149
  1118. package/src/adapters/openaddresses/adapter.ts +0 -251
  1119. package/src/adapters/overture/adapter.ts +0 -162
  1120. package/src/adapters/state-hi-schools/adapter.ts +0 -164
  1121. package/src/adapters/synth-po-box/adapter.ts +0 -204
  1122. package/src/adapters/tiger/adapter.ts +0 -253
  1123. package/src/adapters/tiger/street-decompose.ts +0 -111
  1124. package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -183
  1125. package/src/adapters/usgov-imls-pls/adapter.ts +0 -143
  1126. package/src/adapters/usgov-irs-bmf/adapter.ts +0 -163
  1127. package/src/adapters/usgov-nad/adapter.ts +0 -348
  1128. package/src/adapters/usgov-nppes/adapter.ts +0 -159
  1129. package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -204
  1130. package/src/adapters/utils/index.ts +0 -233
  1131. package/src/adapters/wof-admin-jp/adapter.ts +0 -216
  1132. package/src/adapters/wof-admin-json/adapter.ts +0 -256
  1133. package/src/adapters/wof-json-rows.ts +0 -79
  1134. package/src/adapters/wof-postalcode-json/adapter.ts +0 -183
  1135. package/src/build.ts +0 -386
  1136. package/src/index.ts +0 -14
  1137. package/src/name-prone-us-suffixes.ts +0 -12
  1138. package/src/parquet-wrapper/index.ts +0 -9
  1139. package/src/parquet-wrapper/reader.ts +0 -97
  1140. package/src/parquet-wrapper/schema.ts +0 -88
  1141. package/src/parquet-wrapper/writer.ts +0 -110
  1142. package/src/runner.ts +0 -317
  1143. package/src/shard-recipes/anchor-absorption.ts +0 -103
  1144. package/src/shard-recipes/bare-country.ts +0 -95
  1145. package/src/shard-recipes/boundary-stress.ts +0 -101
  1146. package/src/shard-recipes/country-balanced.ts +0 -524
  1147. package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -111
  1148. package/src/shard-recipes/fr-admin-split.ts +0 -239
  1149. package/src/shard-recipes/fr-bare-street.ts +0 -170
  1150. package/src/shard-recipes/fr-fragment.ts +0 -332
  1151. package/src/shard-recipes/fr-lieudit.ts +0 -302
  1152. package/src/shard-recipes/fr-order.ts +0 -258
  1153. package/src/shard-recipes/german.ts +0 -170
  1154. package/src/shard-recipes/house-venue.ts +0 -88
  1155. package/src/shard-recipes/index.ts +0 -95
  1156. package/src/shard-recipes/intersection.ts +0 -630
  1157. package/src/shard-recipes/locale.ts +0 -599
  1158. package/src/shard-recipes/nl-postcode.ts +0 -115
  1159. package/src/shard-recipes/no-fragment.ts +0 -219
  1160. package/src/shard-recipes/no-street-led.ts +0 -143
  1161. package/src/shard-recipes/no-street.ts +0 -86
  1162. package/src/shard-recipes/po-box-cedex.ts +0 -920
  1163. package/src/shard-recipes/po-box.ts +0 -119
  1164. package/src/shard-recipes/reviewed-postcode-tail.ts +0 -189
  1165. package/src/shard-recipes/scaffold.ts +0 -360
  1166. package/src/shard-recipes/si-bare-village.ts +0 -97
  1167. package/src/shard-recipes/street-affix.ts +0 -826
  1168. package/src/shard-recipes/street-bare.ts +0 -101
  1169. package/src/shard-recipes/street.ts +0 -82
  1170. package/src/shard-recipes/sub-venue-sources.ts +0 -885
  1171. package/src/shard-recipes/sub-venue.ts +0 -984
  1172. package/src/shard-recipes/trailing-region.ts +0 -183
  1173. package/src/shard-recipes/unit.ts +0 -321
  1174. package/src/synthesizers/anchor-absorption.ts +0 -290
  1175. package/src/synthesizers/boundary-stress.ts +0 -531
  1176. package/src/synthesizers/german.ts +0 -251
  1177. package/src/synthesizers/house-venue.ts +0 -330
  1178. package/src/synthesizers/intersection.ts +0 -232
  1179. package/src/synthesizers/no-street.ts +0 -349
  1180. package/src/synthesizers/po-box.ts +0 -339
  1181. package/src/synthesizers/street.ts +0 -274
  1182. package/src/synthesizers/utils.ts +0 -903
  1183. package/src/tools/align-shard.ts +0 -70
  1184. package/src/tools/audit.ts +0 -399
  1185. package/src/tools/corpus-stats.ts +0 -184
  1186. package/src/tools/fetch/ban.ts +0 -290
  1187. package/src/tools/fetch/download.ts +0 -176
  1188. package/src/tools/fetch/geonames-dump.ts +0 -267
  1189. package/src/tools/fetch/geonames-postal.ts +0 -180
  1190. package/src/tools/fetch/hrsa.ts +0 -68
  1191. package/src/tools/fetch/imls-pls.ts +0 -158
  1192. package/src/tools/fetch/index.ts +0 -147
  1193. package/src/tools/fetch/nad.ts +0 -342
  1194. package/src/tools/fetch/nppes.ts +0 -174
  1195. package/src/tools/fetch/openaddresses.ts +0 -404
  1196. package/src/tools/fetch/ourairports.ts +0 -171
  1197. package/src/tools/fetch/ppd.ts +0 -137
  1198. package/src/tools/fetch/state-hi-schools.ts +0 -208
  1199. package/src/tools/fetch/state-sources.ts +0 -155
  1200. package/src/tools/fetch/tiger-full.ts +0 -354
  1201. package/src/tools/fetch/wikidata-subvenue.ts +0 -386
  1202. package/src/tools/golden-expand.ts +0 -584
  1203. package/src/tools/golden-promote.ts +0 -353
  1204. package/src/tools/golden-relabel-street.ts +0 -685
  1205. package/src/tools/index.ts +0 -28
  1206. package/src/tools/ingest-csv.ts +0 -422
  1207. package/src/tools/jsonl-to-parquet.ts +0 -221
  1208. package/src/tools/lint-shard-vocab.ts +0 -409
  1209. package/src/tools/lint-shard.ts +0 -543
  1210. package/src/tools/overlay-manifest.ts +0 -157
  1211. package/src/tools/overture-subvenue.ts +0 -215
  1212. package/src/tools/postcode-triples.ts +0 -375
  1213. package/src/tools/shard-kryptonite.ts +0 -139
  1214. package/src/tools/shard-translit.ts +0 -245
  1215. package/src/tools/sub-venue/harvest.ts +0 -235
  1216. package/src/tools/sub-venue/head-nouns.ts +0 -242
  1217. package/src/tools/sub-venue/surfaces.ts +0 -95
  1218. package/src/tools/sub-venue/table.ts +0 -281
  1219. package/src/tools/sub-venue/wikidata.ts +0 -85
  1220. package/src/tools/sub-venue-lexicon.ts +0 -431
  1221. package/src/tools/sub-venue-promotions.ts +0 -330
  1222. package/src/types.ts +0 -247
  1223. package/src/utils/align.ts +0 -331
  1224. package/src/utils/golden.ts +0 -176
  1225. package/src/utils/index.ts +0 -14
  1226. package/src/utils/parquet.ts +0 -391
  1227. package/src/utils/split.ts +0 -279
  1228. package/src/utils/tokenize.ts +0 -78
  1229. package/src/utils/wof-json.ts +0 -244
  1230. /package/{src → lib}/adapters/state-ia-contractors/adapter.ts +0 -0
  1231. /package/{src → lib}/adapters/state-ny-notaries/adapter.ts +0 -0
  1232. /package/{src → lib}/adapters/state-tx-notaries/adapter.ts +0 -0
  1233. /package/{src → lib}/codex/us-fips-state.ts +0 -0
  1234. /package/{src → lib}/tools/gb-title-case.ts +0 -0
  1235. /package/{src → lib}/utils/license.ts +0 -0
  1236. /package/out/{src/adapters → adapters}/ban/adapter.d.ts +0 -0
  1237. /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
  1238. /package/out/{src/adapters → adapters}/fcc-bdc/adapter.d.ts +0 -0
  1239. /package/out/{src/adapters → adapters}/geonames/adapter.d.ts +0 -0
  1240. /package/out/{src/adapters → adapters}/openaddresses/adapter.d.ts +0 -0
  1241. /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.d.ts +0 -0
  1242. /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.js +0 -0
  1243. /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.d.ts +0 -0
  1244. /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.js +0 -0
  1245. /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.d.ts +0 -0
  1246. /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.js +0 -0
  1247. /package/out/{src/adapters → adapters}/synth-po-box/adapter.d.ts +0 -0
  1248. /package/out/{src/adapters → adapters}/tiger/street-decompose.d.ts +0 -0
  1249. /package/out/{src/adapters → adapters}/usgov-nppes/adapter.d.ts +0 -0
  1250. /package/out/{src/adapters → adapters}/usgov-samhsa-treatment-locator/adapter.d.ts +0 -0
  1251. /package/out/{src/adapters → adapters}/wof-admin-jp/adapter.d.ts +0 -0
  1252. /package/out/{src/codex → codex}/us-fips-state.d.ts +0 -0
  1253. /package/out/{src/codex → codex}/us-fips-state.js +0 -0
  1254. /package/out/{src/tools → tools}/fetch/ppd.d.ts +0 -0
  1255. /package/out/{src/tools → tools}/gb-title-case.d.ts +0 -0
  1256. /package/out/{src/tools → tools}/gb-title-case.js +0 -0
  1257. /package/out/{src/tools → tools}/golden-promote.d.ts +0 -0
  1258. /package/out/{src/tools → tools}/ingest-csv.d.ts +0 -0
  1259. /package/out/{src/types.js → types.js} +0 -0
  1260. /package/out/{src/utils → utils}/license.d.ts +0 -0
  1261. /package/out/{src/utils → utils}/license.js +0 -0
@@ -0,0 +1,330 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ *
6
+ * The sub-venue curation ledger (#35 wave 2) — every decision taken about whether a designator
7
+ * surface may be used for parsing IN A GIVEN LOCALE, with the census that backs it.
8
+ *
9
+ * This file is HAND-AUTHORED. `sub-venue-lexicon.ts` is a pure function of its sources; nothing in it
10
+ * can decide that Spanish `terminal` is safe and British `hall` is not, because that judgement is
11
+ * about the confounds a token has in a language, and a confound is a fact about the world rather than
12
+ * about the data. What the builder does is APPLY these decisions — {@link SUBVENUE_PROMOTIONS} is the
13
+ * only thing that ever sets `curated: true` on a machine-derived surface.
14
+ *
15
+ * ── Why every decision is per-LOCALE ─────────────────────────────────────────────────────────────
16
+ * Wave 1 measured `hall` at 3,274 hits in the Great Britain extract and stopped there, which reads as
17
+ * a verdict on the word. It is not. Re-censused per region 2026-08-05, the same token is a British
18
+ * disaster and a German designator, and no single global flag can express that. The rule this file
19
+ * enforces: a promotion names a designator, a phrase, AND a locale, and it is earned by a count taken
20
+ * in that locale's own data.
21
+ *
22
+ * ── What "real" and "confound" mean in the numbers below ─────────────────────────────────────────
23
+ * Each census counts the surface's occurrences in one region's extract and splits them two ways:
24
+ *
25
+ * - **real** — the phrase sits in a name that is genuinely venue-interior structure, judged by the
26
+ * rule designator of the feature carrying it (`terminal`, `gate`, `campus`) and by the name taking a
27
+ * `<designator> <identifier>` or `<modifier> <designator>` shape.
28
+ * - **confound** — everything else, and the `confoundNote` says WHAT it is. A count with no note is
29
+ * not a census; "3,274 hits" told nobody that 3,205 of them were bus stops named after a village
30
+ * hall.
31
+ *
32
+ * The instrument is `context` on {@link SubVenueSurface} plus the name-shape split; both are
33
+ * reproducible from the committed extracts, and `PROVENANCE.md` records the commands.
34
+ *
35
+ * ── A rejection is a deliverable ─────────────────────────────────────────────────────────────────
36
+ * Rejections stay in this table forever. They are what stops the next contributor re-proposing
37
+ * `hall` for en-GB from the same Wikidata concept that proposed it the first time.
38
+ */
39
+
40
+ /**
41
+ * One curation decision.
42
+ */
43
+ export interface SubVenuePromotion {
44
+ /**
45
+ * The {@link SubVenueDesignator.id} the phrase is a surface of.
46
+ */
47
+ designatorID: string
48
+ /**
49
+ * The exact normalized surface being decided on — `halle`, not `hall`, when the German form is at issue.
50
+ */
51
+ phrase: string
52
+ /**
53
+ * BCP-47-ish `<lang>-<REGION>`. The region half is matched against a surface's `region` and the language half against
54
+ * its `lang`, so `de-DE` reaches both a German Wikidata label (region-free) and a German extract's untagged name.
55
+ */
56
+ locale: string
57
+ decision: "promote" | "reject"
58
+ /**
59
+ * Set when the board's verdict is valid ONLY under a syntactic shape — the machine-readable half of a shape-separable
60
+ * confound. `identifier-required` means the phrase is promoted solely in `<phrase> <identifier>` position (Halle 8);
61
+ * bare occurrences stay unpromoted. A consumer that reads promotions MUST honour this field: the de-DE `halle` board
62
+ * (2026-08-05 five-whys review) is the founding case — its 168-hit confound includes the CITY Halle (Saale), and the
63
+ * 32/32-real enumeration that justified promotion was an enumeration of the identifier-bearing shape, not of the
64
+ * phrase. Absent = the promotion holds in any shape.
65
+ */
66
+ shape?: "identifier-required"
67
+ /**
68
+ * Occurrences judged genuine venue-interior structure in that locale's census.
69
+ */
70
+ real: number
71
+ /**
72
+ * Occurrences judged confound.
73
+ */
74
+ confound: number
75
+ /**
76
+ * What the confound half IS. Required prose — a bare number is not a board.
77
+ */
78
+ confoundNote: string
79
+ /**
80
+ * Which extract or dataset the census was taken over, and when.
81
+ */
82
+ census: string
83
+ }
84
+
85
+ /**
86
+ * The ledger. Sorted by designator, then locale, then phrase in the emitted artifact; source order here is grouped by
87
+ * designator for reading.
88
+ *
89
+ * ── A rejection of a SHIPPED designator is ADVISORY ──────────────────────────────────────────────
90
+ * `neural/venue-structure.ts` ships `wing`, `terminal`, `concourse` and six more as a FLAT English vocabulary with no
91
+ * locale gate. Nothing in this table can un-ship them: the `wing` / en-US rejection below tells a slice author which
92
+ * locale to exclude from a generated line, and does not stop the span proposer from firing on "Red Wing". Giving the
93
+ * shipped vocabulary a per-locale gate is the largest thing the slice will want that does not exist yet.
94
+ */
95
+ export const SUBVENUE_PROMOTIONS: readonly SubVenuePromotion[] = [
96
+ // ── wing ────────────────────────────────────────────────────────────────────────────────────────
97
+ // The designator the corpus task's board rests on (`West Wing` is the one modifier case that
98
+ // already parses), and the cleanest per-locale split in the whole exercise.
99
+ {
100
+ designatorID: "wing",
101
+ phrase: "wing",
102
+ locale: "en-GB",
103
+ decision: "promote",
104
+ real: 23,
105
+ confound: 6,
106
+ confoundNote:
107
+ "Wing Close, Wing Road and Wing Tollgate House — the Buckinghamshire village of Wing — plus Cambian Wing " +
108
+ "College. All six are the <wing> <word> shape; every real hit is a hospital wing (Bexley Wing, Sorby Wing, " +
109
+ "Maternity Wing, West Wing, Bedford Hospital North Wing). CAVEAT, and it limits how far this generalizes: " +
110
+ "24 of the 29 hits sit on a public_transport=platform, because British bus stops are named after the " +
111
+ "hospital wing they serve. The extractor maps no building wings at all — `aile` in France is 0 hits, `ala` " +
112
+ "in Spain 0, `flügel` in Germany 0 — so this evidence is a property of British stop naming, not of a source " +
113
+ "that has wings in it.",
114
+ census: "great-britain.jsonl 2026-08-05, 29 name hits across name + name:<lang>",
115
+ },
116
+ {
117
+ designatorID: "wing",
118
+ phrase: "wing",
119
+ locale: "en-US",
120
+ decision: "reject",
121
+ real: 4,
122
+ confound: 3354,
123
+ confoundNote:
124
+ "Red Wing, the boot brand, is 676 shoe_store rows; chicken wings are another 759 " +
125
+ "(chicken_wings_restaurant 394, chicken_restaurant 365) plus 166 general restaurants. The four real hits are " +
126
+ "campus_building rows. This is the same word as en-GB's clean 23 and it is unusable here.",
127
+ census: "poi.db 2026-05-20.0, full 13,681,698-row scan 2026-08-05",
128
+ },
129
+ {
130
+ designatorID: "wing",
131
+ phrase: "wing",
132
+ locale: "fr-FR",
133
+ decision: "reject",
134
+ real: 0,
135
+ confound: 26,
136
+ confoundNote:
137
+ "Wing Chun and Wing Tsun martial-arts clubs, 15 of 26. Nothing in the French slice of the layer is a " +
138
+ "building wing.",
139
+ census: "poi.db 2026-05-20.0, full scan 2026-08-05 (FR partition, 721,352 rows)",
140
+ },
141
+
142
+ // ── hall ────────────────────────────────────────────────────────────────────────────────────────
143
+ // Wave 1 flagged `hall` as per-locale poison on a GB number alone. Two locales measured; both
144
+ // reject, and for DIFFERENT reasons, which is the part worth keeping.
145
+ {
146
+ designatorID: "hall",
147
+ phrase: "hall",
148
+ locale: "en-GB",
149
+ decision: "reject",
150
+ real: 0,
151
+ confound: 3273,
152
+ confoundNote:
153
+ "3,204 of 3,273 hits sit on a public_transport=platform: a British bus stop named after the village hall it " +
154
+ "stands outside. The distribution is Village Hall, Town Hall, British Legion Hall, and then Hall Lane / Hall " +
155
+ "Road / SPEKE HALL ROAD — streets. The 52 that take a <hall> <identifier> shape are bus-stop position codes " +
156
+ "(Village Hall (o/s), Town Hall (3)), and all 16 <modifier> <hall> hits are streets (East Hall Lane, North " +
157
+ "Hall Road).",
158
+ census: "great-britain.jsonl 2026-08-05, 3,273 name hits",
159
+ },
160
+ {
161
+ designatorID: "hall",
162
+ phrase: "hall",
163
+ locale: "en-US",
164
+ decision: "reject",
165
+ real: 2095,
166
+ confound: 27_081,
167
+ confoundNote:
168
+ "City Hall (5,066 town_hall rows), Kingdom Hall of Jehovah's Witnesses (2,312), event halls (2,622) and " +
169
+ "dormitory halls (1,989). Every one names a whole VENUE, not interior structure, so promoting the surface " +
170
+ "would tag them `unit`. The 2,095 real hits are US campus buildings (UAA Cuddy Hall) and they are outnumbered " +
171
+ "13 to 1.",
172
+ census: "poi.db 2026-05-20.0, full 13,681,698-row scan 2026-08-05",
173
+ },
174
+ {
175
+ designatorID: "hall",
176
+ phrase: "halle",
177
+ locale: "de-DE",
178
+ decision: "promote",
179
+ shape: "identifier-required",
180
+ real: 32,
181
+ confound: 168,
182
+ confoundNote:
183
+ "The confound is 97 hits of the CITY Halle — Halle (Saale), population 240,000, plus Halle (Westf) — and 68 " +
184
+ "village and event halls (PHOENIX Halle, Urexweiler Halle), which are whole venues. That is a worse " +
185
+ "confound than wave 1 assumed when it called `Halle 2` the German counter-example to en-GB: the word is " +
186
+ "also a locality. It is promoted anyway because the confound is SEPARABLE BY SHAPE, and that was checked " +
187
+ "rather than assumed — dumping all 32 <halle> <identifier> hits returns numbered factory, trade-fair and " +
188
+ "airport halls (VW Halle 42, Audi GVZ Halle G, Messe West Halle 8, Flughafen Halle 7, Speyer Halle 101) and " +
189
+ "not one instance of the city. Never modifier-eligible and never proposed bare.",
190
+ census: "germany.jsonl 2026-08-05 (403,863 rows), 200 hits; all 32 shape hits enumerated",
191
+ },
192
+ {
193
+ designatorID: "hall",
194
+ phrase: "hall",
195
+ locale: "fr-FR",
196
+ decision: "promote",
197
+ real: 35,
198
+ confound: 5,
199
+ confoundNote:
200
+ "Five: an English `Town Hall` and `Multipurpose hall` on French name:en tags, plus `Manning Hall`. French " +
201
+ "uses `hall` as the airport designator directly — 19 hits are Charles de Gaulle (Terminal 2E - Hall K/L/M, " +
202
+ "Terminal 1 - Hall A/B, Hall D) and 16 more are building halls (Hall des Sources, Hall du Marché, Hôpital " +
203
+ "Hall Sud). The word that is poison in en-GB is the ordinary designator one country away.",
204
+ census: "france.jsonl 2026-08-05 (251,260 rows), 40 hits; all 19 shape hits enumerated",
205
+ },
206
+
207
+ // ── gate ────────────────────────────────────────────────────────────────────────────────────────
208
+ // The English surface ships and is deliberately NOT modifier-eligible. These decide its localized
209
+ // forms, and the two land on opposite sides for a reason worth keeping.
210
+ {
211
+ designatorID: "gate",
212
+ phrase: "flugsteig",
213
+ locale: "de-DE",
214
+ decision: "promote",
215
+ real: 19,
216
+ confound: 0,
217
+ confoundNote:
218
+ "None, at full-country scale. 18 of 19 hits are <flugsteig> <identifier> (Flugsteig 10, Flugsteig 9/9A, " +
219
+ "Terminal 1 Flugsteig B) and the last is bare; context is 12 terminal features and 7 gates. The word is a " +
220
+ "pure aviation term with no street, locality or business collision in German. Frankfurt's own name:en " +
221
+ "renders Flugsteig J as `Pier J`, which is a second attestation of the same feature under a second " +
222
+ "designator. A 11-of-11 read on the Hessen extract was the hypothesis; this is the count that earned it.",
223
+ census: "germany.jsonl 2026-08-05 (403,863 rows), 19 hits across name + name:<lang>",
224
+ },
225
+ {
226
+ designatorID: "gate",
227
+ phrase: "porte",
228
+ locale: "fr-FR",
229
+ decision: "reject",
230
+ real: 19,
231
+ confound: 927,
232
+ confoundNote:
233
+ "946 hits, of which 894 are Paris city gates and the Métro stations named after them — Porte d'Orléans, " +
234
+ "Porte Dauphine, Porte de Champerret, Porte de Saint-Cloud. Unlike `halle`, the confound REACHES the " +
235
+ "designator+identifier shape: 17 of the 36 hits in that bucket are Porte Saint-Martin, Porte Saint-Denis, " +
236
+ "Porte Notre-Dame. Shape cannot separate it, which is the same test that killed `pier` for en-US. The 19 " +
237
+ "real hits are ferry and cruise gates (Porte 4 : Ferrys, Berliet Porte C).",
238
+ census: "france.jsonl 2026-08-05 (251,260 rows), 946 hits; all 36 shape hits enumerated",
239
+ },
240
+
241
+ // ── pier ────────────────────────────────────────────────────────────────────────────────────────
242
+ // New in wave 2, and the second clean per-locale split: promotable in en-GB, killed in en-US by a
243
+ // furniture chain whose name is exactly the designator+identifier shape.
244
+ {
245
+ designatorID: "pier",
246
+ phrase: "pier",
247
+ locale: "en-GB",
248
+ decision: "promote",
249
+ real: 120,
250
+ confound: 44,
251
+ confoundNote:
252
+ "Pier Road, Pier Street, Pier Avenue, Pier Terrace — 44 street names, all of them the <pier> <street-type> " +
253
+ "shape, which the designator+identifier rule cannot reach. The real side is 98 named piers (Eastbourne Pier, " +
254
+ "Cadogan Pier), 10 in <pier> <identifier> shape (Pier 1, Pier 2, `Terminal 3, Pier 6`), 10 bare and 2 with a " +
255
+ "modifier. Promoted as a SURFACE only; not modifier-eligible, on the same reasoning that excludes `gate`.",
256
+ census: "great-britain.jsonl 2026-08-05, 164 name hits",
257
+ },
258
+ {
259
+ designatorID: "pier",
260
+ phrase: "pier",
261
+ locale: "en-US",
262
+ decision: "reject",
263
+ real: 278,
264
+ confound: 2330,
265
+ confoundNote:
266
+ "Pier 1 Imports and its franchises are 341 home_decor_store plus 217 furniture_store rows, and they carry the " +
267
+ "<pier> <identifier> shape EXACTLY — so unlike en-GB the confound is not separable by shape. Another 159 are " +
268
+ "seafood restaurants and 144 are parks.",
269
+ census: "poi.db 2026-05-20.0, full 13,681,698-row scan 2026-08-05",
270
+ },
271
+
272
+ // ── terminal ────────────────────────────────────────────────────────────────────────────────────
273
+ // The English surface already ships. These promote the LOCALIZED forms, which is what a non-English
274
+ // slice line needs and what wave 1 had none of.
275
+ {
276
+ designatorID: "terminal",
277
+ phrase: "terminal",
278
+ locale: "es-ES",
279
+ decision: "promote",
280
+ real: 190,
281
+ confound: 0,
282
+ confoundNote:
283
+ "None. Spanish borrows the English word unchanged and uses it in every shape the task targets: Terminal A, " +
284
+ "Terminal T1, Terminal 4S, plus named terminals (Terminal Marítima de Santander). No Spanish street type " +
285
+ "collides with it. The Wikidata label `terminal aeroportuaria` is the encyclopaedic form and stays uncurated; " +
286
+ "this promotes the derived head noun.",
287
+ census: "spain.jsonl 2026-08-05, 190 hits across name + name:<lang>",
288
+ },
289
+ {
290
+ designatorID: "terminal",
291
+ phrase: "terminal",
292
+ locale: "ca-ES",
293
+ decision: "promote",
294
+ real: 15,
295
+ confound: 0,
296
+ confoundNote:
297
+ "None. Catalan is the same borrowing (Terminal 1, Terminal Sortides, Terminal Arribades) and needs its own " +
298
+ "entry because a surface's language subtag is `ca`, which an es-ES decision does not reach.",
299
+ census: "spain.jsonl 2026-08-05, 15 name:ca hits",
300
+ },
301
+ {
302
+ designatorID: "terminal",
303
+ phrase: "terminal",
304
+ locale: "fr-FR",
305
+ decision: "promote",
306
+ real: 169,
307
+ confound: 0,
308
+ confoundNote:
309
+ "None. 99 hits are <terminal> <identifier> (Aéroport CDG Terminal 2F, Terminal 2G, Lyon Saint-Exupéry " +
310
+ "Terminal 1), 51 are named terminals (Terminal de Grande-Bretagne, Terminal Croisières) and 13 trail a " +
311
+ "venue name. French borrows the word unchanged and no French street type collides with it.",
312
+ census: "france.jsonl 2026-08-05 (251,260 rows), 169 hits across name + name:<lang>",
313
+ },
314
+ {
315
+ designatorID: "terminal",
316
+ phrase: "ターミナル",
317
+ locale: "ja-JP",
318
+ decision: "promote",
319
+ real: 1213,
320
+ confound: 2,
321
+ confoundNote:
322
+ "Two hits are `ターミナル前` — a bus stop named 'in front of the terminal', which is arguably still real. " +
323
+ "Japanese has no street-name class containing the word. 246 hits take the Japanese target shape " +
324
+ "<identifier><designator> (第2ターミナル, 羽田空港第1ターミナル); 957 are compounds naming a terminal " +
325
+ "(バスターミナル, フェリーターミナル, 成田空港第一ターミナル); 10 are <designator> <identifier>. This is the " +
326
+ "surface the corpus task named as missing, and it exists only because the head-noun derivation produced it " +
327
+ "from five compound Wikidata labels first.",
328
+ census: "japan.jsonl 2026-08-05, 1,215 hits across name + name:<lang>",
329
+ },
330
+ ]
package/lib/types.ts ADDED
@@ -0,0 +1,247 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ *
6
+ * Canonical row schemas for the corpus pipeline (per #6 / Phase 1 plan).
7
+ *
8
+ * The corpus pipeline produces two row shapes:
9
+ *
10
+ * 1. `CanonicalRow`: an adapter's raw output. Carries a free-form `raw` string, a per-component
11
+ * ground-truth dict, provenance, and an optional augmentation marker. Adapters emit these.
12
+ * 2. `LabeledRow`: alignment's output. Adds a SentencePiece token list and a parallel BIO label list,
13
+ * suitable for direct ingestion by the neural training loop.
14
+ *
15
+ * `CorpusAdapter` is the contract every data source implements; `AdapterOptions` is the
16
+ * per-invocation knob set (input path, optional country filter, row cap, abort signal).
17
+ */
18
+
19
+ import type { BIOLabel, ComponentTag } from "@mailwoman/core/types"
20
+
21
+ /**
22
+ * Provenance + augmentation metadata that travels with every corpus row.
23
+ *
24
+ * `synth` is `undefined` for natural (un-augmented) rows; present only when a row was produced by the synthesis
25
+ * pipeline (see `synthesize.ts`).
26
+ */
27
+ export interface SourceProvenance {
28
+ /**
29
+ * Adapter id that emitted this row, e.g. `"wof-admin"`, `"ban"`, `"openaddresses"`.
30
+ */
31
+ source: string
32
+
33
+ /**
34
+ * Stable id within the adapter's source. For SQLite-backed adapters this is the row's primary key; for CSV/GeoJSON, a
35
+ * hash of the canonical components. Must be stable across reruns so that dedup and holdout manifests are
36
+ * reproducible.
37
+ */
38
+ source_id: string
39
+
40
+ /**
41
+ * Corpus version string. Stamped by the runner, not the adapter. Locked together with the tokenizer version:
42
+ * `corpus-v0.1.0` ships with `tokenizer-v0.1.0`.
43
+ */
44
+ corpus_version: string
45
+
46
+ /**
47
+ * Short license label or SPDX id for _this_ row. Defaults to the adapter's `defaultLicense`, but per-row sources
48
+ * (OpenAddresses) override.
49
+ */
50
+ license: string
51
+ }
52
+
53
+ /**
54
+ * Marker placed on rows produced by `synthesize.ts`. Allows downstream code to weight, stratify, or exclude
55
+ * augmentations.
56
+ */
57
+ export interface SynthMarker {
58
+ /**
59
+ * Pipeline id describing what augmentation produced this row. Free-form but stable — e.g. `"case-perturb"`,
60
+ * `"accent-strip"`, `"abbrev-swap"`, `"compose:case-perturb+typo"`.
61
+ */
62
+ method: string
63
+
64
+ /**
65
+ * `source_id` of the un-augmented row this was derived from. Allows tracing every synthetic row back to its natural
66
+ * ancestor.
67
+ */
68
+ base_source_id: string
69
+ }
70
+
71
+ /**
72
+ * One address row, before tokenization + BIO labeling.
73
+ *
74
+ * `raw` is what a parser would see in the wild — possibly multi-line, with arbitrary whitespace. `components` is the
75
+ * ground-truth tagging: every `ComponentTag` present in the source data, mapped to its surface form _as it appears in
76
+ * `raw`_. Alignment uses this to assign BIO labels.
77
+ *
78
+ * Country is ISO 3166-1 alpha-2 (`"US"`, `"FR"`). Locale is BCP-47 (`"en-US"`, `"fr-FR"`) and is optional; adapters
79
+ * that can't be sure leave it empty and let the runner default by country.
80
+ */
81
+ export interface CanonicalRow extends SourceProvenance {
82
+ /**
83
+ * Address string as it might appear in source data.
84
+ */
85
+ raw: string
86
+
87
+ /**
88
+ * Component-by-tag ground truth. Surface forms must occur in `raw` (within the alignment edit distance threshold) or
89
+ * the row will land in the quarantine pile.
90
+ */
91
+ components: Partial<Record<ComponentTag, string>>
92
+
93
+ /**
94
+ * ISO 3166-1 alpha-2 country code.
95
+ */
96
+ country: string
97
+
98
+ /**
99
+ * Optional BCP-47 locale. Defaulted by country if absent.
100
+ */
101
+ locale?: string
102
+
103
+ /**
104
+ * Present only on synthetic rows.
105
+ */
106
+ synth?: SynthMarker
107
+ }
108
+
109
+ /**
110
+ * Output of `align.ts`. Carries everything `CanonicalRow` does, plus parallel `tokens` and `labels` arrays of identical
111
+ * length (`labels[i]` is the BIO tag for `tokens[i]`) and — as of the v0.5.0 char-offset migration (#519) — parallel
112
+ * char-span arrays addressing `raw` directly.
113
+ *
114
+ * The span triple is the v0.5.0 source of truth; `tokens`/`labels` remain emitted during the transition (and stay
115
+ * derivable afterwards: whitespace split + span lookup). The reverse derivation — today's token labels — is the lossy
116
+ * direction (punctuation-mute).
117
+ */
118
+ export interface LabeledRow extends CanonicalRow {
119
+ /**
120
+ * SentencePiece subword tokens for `raw`.
121
+ */
122
+ tokens: readonly string[]
123
+
124
+ /**
125
+ * BIO labels, one per token. Same length as `tokens`.
126
+ */
127
+ labels: readonly BIOLabel[]
128
+
129
+ /**
130
+ * Char-offset label spans over `raw` (parallel arrays, per the #519 ruling): `span_starts[i]` is the inclusive start
131
+ * offset (UTF-16 code units) of span `i`, `span_ends[i]` its exclusive end, `span_tags[i]` its component tag.
132
+ * Invariants — enforced loudly by `alignRow`, documented for every other producer: sorted ascending by start,
133
+ * non-overlapping. `raw` must be NFC-normalized or the offsets are ambiguous (also enforced by `alignRow`).
134
+ *
135
+ * Optional during the v0.4.x → v0.5.0 transition only: alignment always emits the triple; frozen historical corpora
136
+ * and not-yet-migrated synthesis paths may lack it. Required once v0.5.0 lands and the token path is deleted.
137
+ */
138
+ span_starts?: readonly number[]
139
+
140
+ /**
141
+ * Exclusive end offsets, parallel to `span_starts`.
142
+ */
143
+ span_ends?: readonly number[]
144
+
145
+ /**
146
+ * Component tags, parallel to `span_starts`.
147
+ */
148
+ span_tags?: readonly ComponentTag[]
149
+ }
150
+
151
+ /**
152
+ * A row that alignment refused to label. Lands in `/data/corpus/quarantine/` for human review.
153
+ *
154
+ * The `reason` is human-readable; common values are `"component-not-found:<tag>"`, `"edit-distance-exceeded:<tag>"`,
155
+ * `"raw-empty"`. Re-running alignment after a fix should re-emit the quarantined rows; the runner keys them by
156
+ * `source_id`.
157
+ */
158
+ export interface QuarantinedRow {
159
+ row: CanonicalRow
160
+ reason: string
161
+ }
162
+
163
+ /**
164
+ * Per-invocation knobs handed to an adapter by the runner.
165
+ *
166
+ * `inputPath` is interpreted by the adapter — it might be a single file path, a directory of slices, or even an HTTPS
167
+ * URL. Each adapter documents its own expected shape in its README.
168
+ *
169
+ * `country` filters to a single ISO 3166-1 alpha-2 country _at the adapter level_. Adapters that hold multi-country
170
+ * data (OSM PBF, OpenAddresses) MUST honor this; single-country adapters (BAN) may ignore it but should reject
171
+ * mismatches.
172
+ *
173
+ * `limit` is a soft cap on rows emitted; useful for fixture-driven tests and smoke runs.
174
+ *
175
+ * `signal` allows the runner to cancel a long-running scan cleanly.
176
+ */
177
+ export interface AdapterOptions {
178
+ /**
179
+ * Path to the adapter's input data (file, directory, or URL — adapter-specific).
180
+ */
181
+ inputPath: string
182
+
183
+ /**
184
+ * Optional output directory, available to adapters that maintain side state (rare).
185
+ */
186
+ outputDir?: string
187
+
188
+ /**
189
+ * ISO 3166-1 alpha-2 country filter.
190
+ */
191
+ country?: string
192
+
193
+ /**
194
+ * Soft row cap. Adapters should stop iterating once this is reached.
195
+ */
196
+ limit?: number
197
+
198
+ /**
199
+ * Cancellation hook. Adapters should respect this on every iteration boundary.
200
+ */
201
+ signal?: AbortSignal
202
+ }
203
+
204
+ /**
205
+ * The contract every data source implements.
206
+ *
207
+ * Adapters are async generators: they yield `CanonicalRow`s one at a time, the runner consumes them (writing JSONL +
208
+ * maintaining checksums + driving alignment). Streaming is mandatory — many sources are tens of millions of rows and
209
+ * cannot be buffered.
210
+ *
211
+ * `defaultLicense` is stamped onto every emitted row's `license` field unless the adapter sets `license` explicitly
212
+ * (e.g. OpenAddresses, which carries per-source licenses).
213
+ */
214
+ export interface CorpusAdapter {
215
+ /**
216
+ * Stable, machine-friendly id used in paths and CLI args. E.g. `"wof-admin"`.
217
+ */
218
+ readonly id: string
219
+
220
+ /**
221
+ * Default SPDX-ish license label for rows from this adapter. Per-row overrides allowed.
222
+ */
223
+ readonly defaultLicense: string
224
+
225
+ /**
226
+ * One-sentence description shown by `npx mailwoman corpus list`.
227
+ */
228
+ readonly description: string
229
+
230
+ /**
231
+ * Async iterable of canonical rows.
232
+ *
233
+ * Implementations MUST:
234
+ *
235
+ * - Honor `opts.country` (filter or reject mismatches).
236
+ * - Honor `opts.limit` (stop after N rows).
237
+ * - Respect `opts.signal` on every iteration.
238
+ * - Set `source` to `this.id` on every emitted row.
239
+ * - Set `license` to `this.defaultLicense` unless overriding per-row.
240
+ *
241
+ * Implementations MUST NOT:
242
+ *
243
+ * - Set `corpus_version` (the runner stamps it).
244
+ * - Mutate previously-yielded rows.
245
+ */
246
+ rows(opts: AdapterOptions): AsyncIterable<CanonicalRow>
247
+ }