@mailwoman/corpus 9.1.0 → 9.3.0

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 (1202) hide show
  1. package/README.md +24 -24
  2. package/data/PROVENANCE.md +20 -7
  3. package/data/reviewed-ve-postcode-tuples.json +74 -0
  4. package/lib/adapters/ban/adapter.ts +190 -0
  5. package/lib/adapters/ban/street-decompose.ts +66 -0
  6. package/lib/adapters/fcc-bdc/adapter.ts +174 -0
  7. package/lib/adapters/geonames/adapter.ts +199 -0
  8. package/lib/adapters/geonames-postal/adapter.ts +122 -0
  9. package/lib/adapters/gnaf/adapter.ts +149 -0
  10. package/lib/adapters/gnaf/assemble.ts +225 -0
  11. package/lib/adapters/index.ts +153 -0
  12. package/lib/adapters/openaddresses/adapter.ts +251 -0
  13. package/lib/adapters/overture/adapter.ts +162 -0
  14. package/lib/adapters/state-hi-schools/adapter.ts +170 -0
  15. package/lib/adapters/state-hi-schools/workbook.ts +35 -0
  16. package/lib/adapters/state-ia-contractors/adapter.ts +144 -0
  17. package/lib/adapters/state-ny-notaries/adapter.ts +141 -0
  18. package/lib/adapters/state-tx-notaries/adapter.ts +157 -0
  19. package/lib/adapters/synth-po-box/adapter.ts +204 -0
  20. package/lib/adapters/tiger/adapter.ts +252 -0
  21. package/lib/adapters/tiger/street-decompose.ts +83 -0
  22. package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +167 -0
  23. package/lib/adapters/usgov-imls-pls/adapter.ts +143 -0
  24. package/lib/adapters/usgov-irs-bmf/adapter.ts +151 -0
  25. package/lib/adapters/usgov-nad/adapter.ts +334 -0
  26. package/lib/adapters/usgov-nppes/adapter.ts +151 -0
  27. package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +193 -0
  28. package/lib/adapters/utils/index.ts +307 -0
  29. package/lib/adapters/wof-admin-jp/adapter.ts +214 -0
  30. package/lib/adapters/wof-admin-json/adapter.ts +231 -0
  31. package/lib/adapters/wof-json-rows.ts +129 -0
  32. package/lib/adapters/wof-postalcode-json/adapter.ts +176 -0
  33. package/lib/build.ts +378 -0
  34. package/lib/env.ts +50 -0
  35. package/lib/index.ts +13 -0
  36. package/lib/name-prone-us-suffixes.ts +12 -0
  37. package/lib/recipes/anchor-absorption.ts +101 -0
  38. package/lib/recipes/bare-country.ts +95 -0
  39. package/lib/recipes/boundary-stress.ts +100 -0
  40. package/lib/recipes/cn-organizational-units.ts +199 -0
  41. package/lib/recipes/country-balanced.ts +509 -0
  42. package/lib/recipes/cz-pcfirst-preposition.ts +111 -0
  43. package/lib/recipes/fr-admin-split.ts +242 -0
  44. package/lib/recipes/fr-bare-street.ts +170 -0
  45. package/lib/recipes/fr-fragment.ts +333 -0
  46. package/lib/recipes/fr-lieudit.ts +301 -0
  47. package/lib/recipes/fr-order.ts +245 -0
  48. package/lib/recipes/german.ts +359 -0
  49. package/lib/recipes/house-venue.ts +92 -0
  50. package/lib/recipes/index.ts +97 -0
  51. package/lib/recipes/intersection.ts +618 -0
  52. package/lib/recipes/locale.ts +599 -0
  53. package/lib/recipes/nl-postcode.ts +115 -0
  54. package/lib/recipes/no-fragment.ts +219 -0
  55. package/lib/recipes/no-street-led.ts +141 -0
  56. package/lib/recipes/no-street.ts +90 -0
  57. package/lib/recipes/po-box-cedex.ts +976 -0
  58. package/lib/recipes/po-box.ts +123 -0
  59. package/lib/recipes/reviewed-postcode-tail.ts +190 -0
  60. package/lib/recipes/scaffold.ts +469 -0
  61. package/lib/recipes/si-bare-village.ts +97 -0
  62. package/lib/recipes/street-affix.ts +804 -0
  63. package/lib/recipes/street-bare.ts +100 -0
  64. package/lib/recipes/street.ts +81 -0
  65. package/lib/recipes/sub-venue-sources.ts +877 -0
  66. package/lib/recipes/sub-venue.ts +997 -0
  67. package/lib/recipes/trailing-region.ts +183 -0
  68. package/lib/recipes/unit.ts +304 -0
  69. package/lib/runner.ts +312 -0
  70. package/lib/synthesizers/anchor-absorption.ts +288 -0
  71. package/lib/synthesizers/boundary-stress.ts +532 -0
  72. package/lib/synthesizers/german.ts +260 -0
  73. package/lib/synthesizers/house-venue.ts +308 -0
  74. package/lib/synthesizers/intersection.ts +233 -0
  75. package/lib/synthesizers/no-street.ts +327 -0
  76. package/lib/synthesizers/po-box.ts +323 -0
  77. package/lib/synthesizers/street.ts +269 -0
  78. package/lib/synthesizers/utils.ts +993 -0
  79. package/lib/test-kit/corpus-recipe.ts +86 -0
  80. package/lib/test-kit/index.ts +100 -0
  81. package/lib/tools/align-slice.ts +68 -0
  82. package/lib/tools/audit.ts +403 -0
  83. package/lib/tools/corpus-stats.ts +136 -0
  84. package/lib/tools/fetch/ban.ts +289 -0
  85. package/lib/tools/fetch/download.ts +262 -0
  86. package/lib/tools/fetch/geonames-dump.ts +257 -0
  87. package/lib/tools/fetch/geonames-postal.ts +180 -0
  88. package/lib/tools/fetch/hrsa.ts +59 -0
  89. package/lib/tools/fetch/imls-pls.ts +149 -0
  90. package/lib/tools/fetch/index.ts +147 -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 +683 -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/license.ts +50 -0
  125. package/lib/utils/parquet.ts +582 -0
  126. package/lib/utils/slice-stats.ts +95 -0
  127. package/lib/utils/split.ts +279 -0
  128. package/lib/utils/tokenize.ts +120 -0
  129. package/lib/utils/wof-json.ts +247 -0
  130. package/out/adapters/ban/adapter.d.ts +44 -0
  131. package/out/adapters/ban/adapter.d.ts.map +1 -0
  132. package/out/adapters/ban/adapter.js +149 -0
  133. package/out/adapters/ban/adapter.js.map +1 -0
  134. package/out/adapters/ban/street-decompose.d.ts.map +1 -0
  135. package/out/adapters/ban/street-decompose.js +51 -0
  136. package/out/adapters/ban/street-decompose.js.map +1 -0
  137. package/out/adapters/fcc-bdc/adapter.d.ts +68 -0
  138. package/out/adapters/fcc-bdc/adapter.d.ts.map +1 -0
  139. package/out/adapters/fcc-bdc/adapter.js +144 -0
  140. package/out/adapters/fcc-bdc/adapter.js.map +1 -0
  141. package/out/adapters/geonames/adapter.d.ts +46 -0
  142. package/out/adapters/geonames/adapter.d.ts.map +1 -0
  143. package/out/adapters/geonames/adapter.js +176 -0
  144. package/out/adapters/geonames/adapter.js.map +1 -0
  145. package/out/adapters/geonames-postal/adapter.d.ts +54 -0
  146. package/out/adapters/geonames-postal/adapter.d.ts.map +1 -0
  147. package/out/adapters/geonames-postal/adapter.js +107 -0
  148. package/out/adapters/geonames-postal/adapter.js.map +1 -0
  149. package/out/adapters/gnaf/adapter.d.ts +49 -0
  150. package/out/adapters/gnaf/adapter.d.ts.map +1 -0
  151. package/out/adapters/gnaf/adapter.js +124 -0
  152. package/out/adapters/gnaf/adapter.js.map +1 -0
  153. package/out/adapters/gnaf/assemble.d.ts +65 -0
  154. package/out/adapters/gnaf/assemble.d.ts.map +1 -0
  155. package/out/adapters/gnaf/assemble.js +154 -0
  156. package/out/adapters/gnaf/assemble.js.map +1 -0
  157. package/out/adapters/index.d.ts +51 -0
  158. package/out/adapters/index.d.ts.map +1 -0
  159. package/out/adapters/index.js +95 -0
  160. package/out/adapters/index.js.map +1 -0
  161. package/out/adapters/openaddresses/adapter.d.ts +72 -0
  162. package/out/adapters/openaddresses/adapter.d.ts.map +1 -0
  163. package/out/adapters/openaddresses/adapter.js +186 -0
  164. package/out/adapters/openaddresses/adapter.js.map +1 -0
  165. package/out/adapters/overture/adapter.d.ts +48 -0
  166. package/out/adapters/overture/adapter.d.ts.map +1 -0
  167. package/out/adapters/overture/adapter.js +125 -0
  168. package/out/adapters/overture/adapter.js.map +1 -0
  169. package/out/adapters/state-hi-schools/adapter.d.ts +46 -0
  170. package/out/adapters/state-hi-schools/adapter.d.ts.map +1 -0
  171. package/out/adapters/state-hi-schools/adapter.js +145 -0
  172. package/out/adapters/state-hi-schools/adapter.js.map +1 -0
  173. package/out/adapters/state-hi-schools/workbook.d.ts +29 -0
  174. package/out/adapters/state-hi-schools/workbook.d.ts.map +1 -0
  175. package/out/adapters/state-hi-schools/workbook.js +20 -0
  176. package/out/adapters/state-hi-schools/workbook.js.map +1 -0
  177. package/out/adapters/state-ia-contractors/adapter.d.ts +34 -0
  178. package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
  179. package/out/adapters/state-ia-contractors/adapter.js +111 -0
  180. package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
  181. package/out/adapters/state-ny-notaries/adapter.d.ts +32 -0
  182. package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
  183. package/out/adapters/state-ny-notaries/adapter.js +119 -0
  184. package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
  185. package/out/adapters/state-tx-notaries/adapter.d.ts +33 -0
  186. package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
  187. package/out/adapters/state-tx-notaries/adapter.js +125 -0
  188. package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
  189. package/out/adapters/synth-po-box/adapter.d.ts +67 -0
  190. package/out/adapters/synth-po-box/adapter.d.ts.map +1 -0
  191. package/out/adapters/synth-po-box/adapter.js +140 -0
  192. package/out/adapters/synth-po-box/adapter.js.map +1 -0
  193. package/out/adapters/tiger/adapter.d.ts +55 -0
  194. package/out/adapters/tiger/adapter.d.ts.map +1 -0
  195. package/out/adapters/tiger/adapter.js +201 -0
  196. package/out/adapters/tiger/adapter.js.map +1 -0
  197. package/out/adapters/tiger/street-decompose.d.ts.map +1 -0
  198. package/out/adapters/tiger/street-decompose.js +68 -0
  199. package/out/adapters/tiger/street-decompose.js.map +1 -0
  200. package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +56 -0
  201. package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -0
  202. package/out/adapters/usgov-hrsa-fqhc/adapter.js +132 -0
  203. package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -0
  204. package/out/adapters/usgov-imls-pls/adapter.d.ts +36 -0
  205. package/out/adapters/usgov-imls-pls/adapter.d.ts.map +1 -0
  206. package/out/adapters/usgov-imls-pls/adapter.js +114 -0
  207. package/out/adapters/usgov-imls-pls/adapter.js.map +1 -0
  208. package/out/adapters/usgov-irs-bmf/adapter.d.ts +37 -0
  209. package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -0
  210. package/out/adapters/usgov-irs-bmf/adapter.js +120 -0
  211. package/out/adapters/usgov-irs-bmf/adapter.js.map +1 -0
  212. package/out/adapters/usgov-nad/adapter.d.ts +48 -0
  213. package/out/adapters/usgov-nad/adapter.d.ts.map +1 -0
  214. package/out/adapters/usgov-nad/adapter.js +249 -0
  215. package/out/adapters/usgov-nad/adapter.js.map +1 -0
  216. package/out/adapters/usgov-nppes/adapter.d.ts +39 -0
  217. package/out/adapters/usgov-nppes/adapter.d.ts.map +1 -0
  218. package/out/adapters/usgov-nppes/adapter.js +118 -0
  219. package/out/adapters/usgov-nppes/adapter.js.map +1 -0
  220. package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts +46 -0
  221. package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -0
  222. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +154 -0
  223. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -0
  224. package/out/adapters/utils/index.d.ts +191 -0
  225. package/out/adapters/utils/index.d.ts.map +1 -0
  226. package/out/adapters/utils/index.js +206 -0
  227. package/out/adapters/utils/index.js.map +1 -0
  228. package/out/adapters/wof-admin-jp/adapter.d.ts +65 -0
  229. package/out/adapters/wof-admin-jp/adapter.d.ts.map +1 -0
  230. package/out/adapters/wof-admin-jp/adapter.js +161 -0
  231. package/out/adapters/wof-admin-jp/adapter.js.map +1 -0
  232. package/out/adapters/wof-admin-json/adapter.d.ts +79 -0
  233. package/out/adapters/wof-admin-json/adapter.d.ts.map +1 -0
  234. package/out/adapters/wof-admin-json/adapter.js +197 -0
  235. package/out/adapters/wof-admin-json/adapter.js.map +1 -0
  236. package/out/adapters/wof-json-rows.d.ts +62 -0
  237. package/out/adapters/wof-json-rows.d.ts.map +1 -0
  238. package/out/adapters/wof-json-rows.js +83 -0
  239. package/out/adapters/wof-json-rows.js.map +1 -0
  240. package/out/adapters/wof-postalcode-json/adapter.d.ts +65 -0
  241. package/out/adapters/wof-postalcode-json/adapter.d.ts.map +1 -0
  242. package/out/adapters/wof-postalcode-json/adapter.js +151 -0
  243. package/out/adapters/wof-postalcode-json/adapter.js.map +1 -0
  244. package/out/build.d.ts +132 -0
  245. package/out/build.d.ts.map +1 -0
  246. package/out/build.js +245 -0
  247. package/out/build.js.map +1 -0
  248. package/out/codex/us-fips-state.d.ts.map +1 -0
  249. package/out/codex/us-fips-state.js.map +1 -0
  250. package/out/env.d.ts +46 -0
  251. package/out/env.d.ts.map +1 -0
  252. package/out/env.js +46 -0
  253. package/out/env.js.map +1 -0
  254. package/out/index.d.ts +13 -0
  255. package/out/index.d.ts.map +1 -0
  256. package/out/index.js +13 -0
  257. package/out/index.js.map +1 -0
  258. package/out/name-prone-us-suffixes.d.ts +12 -0
  259. package/out/name-prone-us-suffixes.d.ts.map +1 -0
  260. package/out/name-prone-us-suffixes.js +12 -0
  261. package/out/name-prone-us-suffixes.js.map +1 -0
  262. package/out/recipes/anchor-absorption.d.ts +20 -0
  263. package/out/recipes/anchor-absorption.d.ts.map +1 -0
  264. package/out/recipes/anchor-absorption.js +81 -0
  265. package/out/recipes/anchor-absorption.js.map +1 -0
  266. package/out/recipes/bare-country.d.ts +25 -0
  267. package/out/recipes/bare-country.d.ts.map +1 -0
  268. package/out/recipes/bare-country.js +87 -0
  269. package/out/recipes/bare-country.js.map +1 -0
  270. package/out/recipes/boundary-stress.d.ts +20 -0
  271. package/out/recipes/boundary-stress.d.ts.map +1 -0
  272. package/out/recipes/boundary-stress.js +83 -0
  273. package/out/recipes/boundary-stress.js.map +1 -0
  274. package/out/recipes/cn-organizational-units.d.ts +36 -0
  275. package/out/recipes/cn-organizational-units.d.ts.map +1 -0
  276. package/out/recipes/cn-organizational-units.js +159 -0
  277. package/out/recipes/cn-organizational-units.js.map +1 -0
  278. package/out/recipes/country-balanced.d.ts +32 -0
  279. package/out/recipes/country-balanced.d.ts.map +1 -0
  280. package/out/recipes/country-balanced.js +393 -0
  281. package/out/recipes/country-balanced.js.map +1 -0
  282. package/out/recipes/cz-pcfirst-preposition.d.ts +22 -0
  283. package/out/recipes/cz-pcfirst-preposition.d.ts.map +1 -0
  284. package/out/recipes/cz-pcfirst-preposition.js +100 -0
  285. package/out/recipes/cz-pcfirst-preposition.js.map +1 -0
  286. package/out/recipes/fr-admin-split.d.ts +38 -0
  287. package/out/recipes/fr-admin-split.d.ts.map +1 -0
  288. package/out/recipes/fr-admin-split.js +192 -0
  289. package/out/recipes/fr-admin-split.js.map +1 -0
  290. package/out/recipes/fr-bare-street.d.ts +28 -0
  291. package/out/recipes/fr-bare-street.d.ts.map +1 -0
  292. package/out/recipes/fr-bare-street.js +143 -0
  293. package/out/recipes/fr-bare-street.js.map +1 -0
  294. package/out/recipes/fr-fragment.d.ts +77 -0
  295. package/out/recipes/fr-fragment.d.ts.map +1 -0
  296. package/out/recipes/fr-fragment.js +276 -0
  297. package/out/recipes/fr-fragment.js.map +1 -0
  298. package/out/recipes/fr-lieudit.d.ts +32 -0
  299. package/out/recipes/fr-lieudit.d.ts.map +1 -0
  300. package/out/recipes/fr-lieudit.js +227 -0
  301. package/out/recipes/fr-lieudit.js.map +1 -0
  302. package/out/recipes/fr-order.d.ts +38 -0
  303. package/out/recipes/fr-order.d.ts.map +1 -0
  304. package/out/recipes/fr-order.js +197 -0
  305. package/out/recipes/fr-order.js.map +1 -0
  306. package/out/recipes/german.d.ts +44 -0
  307. package/out/recipes/german.d.ts.map +1 -0
  308. package/out/recipes/german.js +288 -0
  309. package/out/recipes/german.js.map +1 -0
  310. package/out/recipes/house-venue.d.ts +18 -0
  311. package/out/recipes/house-venue.d.ts.map +1 -0
  312. package/out/recipes/house-venue.js +73 -0
  313. package/out/recipes/house-venue.js.map +1 -0
  314. package/out/recipes/index.d.ts +24 -0
  315. package/out/recipes/index.d.ts.map +1 -0
  316. package/out/recipes/index.js +91 -0
  317. package/out/recipes/index.js.map +1 -0
  318. package/out/recipes/intersection.d.ts +42 -0
  319. package/out/recipes/intersection.d.ts.map +1 -0
  320. package/out/recipes/intersection.js +452 -0
  321. package/out/recipes/intersection.js.map +1 -0
  322. package/out/recipes/locale.d.ts +136 -0
  323. package/out/recipes/locale.d.ts.map +1 -0
  324. package/out/recipes/locale.js +460 -0
  325. package/out/recipes/locale.js.map +1 -0
  326. package/out/recipes/nl-postcode.d.ts +26 -0
  327. package/out/recipes/nl-postcode.d.ts.map +1 -0
  328. package/out/recipes/nl-postcode.js +102 -0
  329. package/out/recipes/nl-postcode.js.map +1 -0
  330. package/out/recipes/no-fragment.d.ts +43 -0
  331. package/out/recipes/no-fragment.d.ts.map +1 -0
  332. package/out/recipes/no-fragment.js +182 -0
  333. package/out/recipes/no-fragment.js.map +1 -0
  334. package/out/recipes/no-street-led.d.ts +24 -0
  335. package/out/recipes/no-street-led.d.ts.map +1 -0
  336. package/out/recipes/no-street-led.js +113 -0
  337. package/out/recipes/no-street-led.js.map +1 -0
  338. package/out/recipes/no-street.d.ts +18 -0
  339. package/out/recipes/no-street.d.ts.map +1 -0
  340. package/out/recipes/no-street.js +71 -0
  341. package/out/recipes/no-street.js.map +1 -0
  342. package/out/recipes/po-box-cedex.d.ts +38 -0
  343. package/out/recipes/po-box-cedex.d.ts.map +1 -0
  344. package/out/recipes/po-box-cedex.js +767 -0
  345. package/out/recipes/po-box-cedex.js.map +1 -0
  346. package/out/recipes/po-box.d.ts +17 -0
  347. package/out/recipes/po-box.d.ts.map +1 -0
  348. package/out/recipes/po-box.js +100 -0
  349. package/out/recipes/po-box.js.map +1 -0
  350. package/out/recipes/reviewed-postcode-tail.d.ts +47 -0
  351. package/out/recipes/reviewed-postcode-tail.d.ts.map +1 -0
  352. package/out/recipes/reviewed-postcode-tail.js +125 -0
  353. package/out/recipes/reviewed-postcode-tail.js.map +1 -0
  354. package/out/recipes/scaffold.d.ts +324 -0
  355. package/out/recipes/scaffold.d.ts.map +1 -0
  356. package/out/recipes/scaffold.js +186 -0
  357. package/out/recipes/scaffold.js.map +1 -0
  358. package/out/recipes/si-bare-village.d.ts +32 -0
  359. package/out/recipes/si-bare-village.d.ts.map +1 -0
  360. package/out/recipes/si-bare-village.js +88 -0
  361. package/out/recipes/si-bare-village.js.map +1 -0
  362. package/out/recipes/street-affix.d.ts +89 -0
  363. package/out/recipes/street-affix.d.ts.map +1 -0
  364. package/out/recipes/street-affix.js +563 -0
  365. package/out/recipes/street-affix.js.map +1 -0
  366. package/out/recipes/street-bare.d.ts +25 -0
  367. package/out/recipes/street-bare.d.ts.map +1 -0
  368. package/out/recipes/street-bare.js +86 -0
  369. package/out/recipes/street-bare.js.map +1 -0
  370. package/out/recipes/street.d.ts +15 -0
  371. package/out/recipes/street.d.ts.map +1 -0
  372. package/out/recipes/street.js +69 -0
  373. package/out/recipes/street.js.map +1 -0
  374. package/out/recipes/sub-venue-sources.d.ts +229 -0
  375. package/out/recipes/sub-venue-sources.d.ts.map +1 -0
  376. package/out/recipes/sub-venue-sources.js +653 -0
  377. package/out/recipes/sub-venue-sources.js.map +1 -0
  378. package/out/recipes/sub-venue.d.ts +269 -0
  379. package/out/recipes/sub-venue.d.ts.map +1 -0
  380. package/out/recipes/sub-venue.js +725 -0
  381. package/out/recipes/sub-venue.js.map +1 -0
  382. package/out/recipes/trailing-region.d.ts +74 -0
  383. package/out/recipes/trailing-region.d.ts.map +1 -0
  384. package/out/recipes/trailing-region.js +157 -0
  385. package/out/recipes/trailing-region.js.map +1 -0
  386. package/out/recipes/unit.d.ts +29 -0
  387. package/out/recipes/unit.d.ts.map +1 -0
  388. package/out/recipes/unit.js +230 -0
  389. package/out/recipes/unit.js.map +1 -0
  390. package/out/runner.d.ts +130 -0
  391. package/out/runner.d.ts.map +1 -0
  392. package/out/runner.js +185 -0
  393. package/out/runner.js.map +1 -0
  394. package/out/synthesizers/anchor-absorption.d.ts +63 -0
  395. package/out/synthesizers/anchor-absorption.d.ts.map +1 -0
  396. package/out/synthesizers/anchor-absorption.js +221 -0
  397. package/out/synthesizers/anchor-absorption.js.map +1 -0
  398. package/out/synthesizers/boundary-stress.d.ts +78 -0
  399. package/out/synthesizers/boundary-stress.d.ts.map +1 -0
  400. package/out/synthesizers/boundary-stress.js +455 -0
  401. package/out/synthesizers/boundary-stress.js.map +1 -0
  402. package/out/synthesizers/german.d.ts +115 -0
  403. package/out/synthesizers/german.d.ts.map +1 -0
  404. package/out/synthesizers/german.js +149 -0
  405. package/out/synthesizers/german.js.map +1 -0
  406. package/out/synthesizers/house-venue.d.ts +56 -0
  407. package/out/synthesizers/house-venue.d.ts.map +1 -0
  408. package/out/synthesizers/house-venue.js +247 -0
  409. package/out/synthesizers/house-venue.js.map +1 -0
  410. package/out/synthesizers/intersection.d.ts +52 -0
  411. package/out/synthesizers/intersection.d.ts.map +1 -0
  412. package/out/synthesizers/intersection.js +175 -0
  413. package/out/synthesizers/intersection.js.map +1 -0
  414. package/out/synthesizers/no-street.d.ts +72 -0
  415. package/out/synthesizers/no-street.d.ts.map +1 -0
  416. package/out/synthesizers/no-street.js +262 -0
  417. package/out/synthesizers/no-street.js.map +1 -0
  418. package/out/synthesizers/po-box.d.ts +108 -0
  419. package/out/synthesizers/po-box.d.ts.map +1 -0
  420. package/out/synthesizers/po-box.js +250 -0
  421. package/out/synthesizers/po-box.js.map +1 -0
  422. package/out/synthesizers/street.d.ts +54 -0
  423. package/out/synthesizers/street.d.ts.map +1 -0
  424. package/out/synthesizers/street.js +218 -0
  425. package/out/synthesizers/street.js.map +1 -0
  426. package/out/synthesizers/utils.d.ts +241 -0
  427. package/out/synthesizers/utils.d.ts.map +1 -0
  428. package/out/synthesizers/utils.js +776 -0
  429. package/out/synthesizers/utils.js.map +1 -0
  430. package/out/test-kit/corpus-recipe.d.ts +59 -0
  431. package/out/test-kit/corpus-recipe.d.ts.map +1 -0
  432. package/out/test-kit/corpus-recipe.js +39 -0
  433. package/out/test-kit/corpus-recipe.js.map +1 -0
  434. package/out/test-kit/index.d.ts +48 -0
  435. package/out/test-kit/index.d.ts.map +1 -0
  436. package/out/test-kit/index.js +78 -0
  437. package/out/test-kit/index.js.map +1 -0
  438. package/out/tools/align-slice.d.ts +7 -0
  439. package/out/tools/align-slice.d.ts.map +1 -0
  440. package/out/tools/align-slice.js +55 -0
  441. package/out/tools/align-slice.js.map +1 -0
  442. package/out/tools/audit.d.ts +29 -0
  443. package/out/tools/audit.d.ts.map +1 -0
  444. package/out/tools/audit.js +282 -0
  445. package/out/tools/audit.js.map +1 -0
  446. package/out/tools/corpus-stats.d.ts +44 -0
  447. package/out/tools/corpus-stats.d.ts.map +1 -0
  448. package/out/tools/corpus-stats.js +102 -0
  449. package/out/tools/corpus-stats.js.map +1 -0
  450. package/out/tools/fetch/ban.d.ts +31 -0
  451. package/out/tools/fetch/ban.d.ts.map +1 -0
  452. package/out/tools/fetch/ban.js +239 -0
  453. package/out/tools/fetch/ban.js.map +1 -0
  454. package/out/tools/fetch/download.d.ts +117 -0
  455. package/out/tools/fetch/download.d.ts.map +1 -0
  456. package/out/tools/fetch/download.js +160 -0
  457. package/out/tools/fetch/download.js.map +1 -0
  458. package/out/tools/fetch/geonames-dump.d.ts +91 -0
  459. package/out/tools/fetch/geonames-dump.d.ts.map +1 -0
  460. package/out/tools/fetch/geonames-dump.js +171 -0
  461. package/out/tools/fetch/geonames-dump.js.map +1 -0
  462. package/out/tools/fetch/geonames-postal.d.ts +76 -0
  463. package/out/tools/fetch/geonames-postal.d.ts.map +1 -0
  464. package/out/tools/fetch/geonames-postal.js +126 -0
  465. package/out/tools/fetch/geonames-postal.js.map +1 -0
  466. package/out/tools/fetch/hrsa.d.ts +18 -0
  467. package/out/tools/fetch/hrsa.d.ts.map +1 -0
  468. package/out/tools/fetch/hrsa.js +46 -0
  469. package/out/tools/fetch/hrsa.js.map +1 -0
  470. package/out/tools/fetch/imls-pls.d.ts +25 -0
  471. package/out/tools/fetch/imls-pls.d.ts.map +1 -0
  472. package/out/tools/fetch/imls-pls.js +108 -0
  473. package/out/tools/fetch/imls-pls.js.map +1 -0
  474. package/out/tools/fetch/index.d.ts +144 -0
  475. package/out/tools/fetch/index.d.ts.map +1 -0
  476. package/out/tools/fetch/index.js +143 -0
  477. package/out/tools/fetch/index.js.map +1 -0
  478. package/out/tools/fetch/nad.d.ts +70 -0
  479. package/out/tools/fetch/nad.d.ts.map +1 -0
  480. package/out/tools/fetch/nad.js +234 -0
  481. package/out/tools/fetch/nad.js.map +1 -0
  482. package/out/tools/fetch/nppes.d.ts +26 -0
  483. package/out/tools/fetch/nppes.d.ts.map +1 -0
  484. package/out/tools/fetch/nppes.js +126 -0
  485. package/out/tools/fetch/nppes.js.map +1 -0
  486. package/out/tools/fetch/openaddresses.d.ts +9 -0
  487. package/out/tools/fetch/openaddresses.d.ts.map +1 -0
  488. package/out/tools/fetch/openaddresses.js +279 -0
  489. package/out/tools/fetch/openaddresses.js.map +1 -0
  490. package/out/tools/fetch/ourairports.d.ts +45 -0
  491. package/out/tools/fetch/ourairports.d.ts.map +1 -0
  492. package/out/tools/fetch/ourairports.js +128 -0
  493. package/out/tools/fetch/ourairports.js.map +1 -0
  494. package/out/tools/fetch/ppd.d.ts +14 -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 +440 -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 +47 -0
  611. package/out/utils/license.js.map +1 -0
  612. package/out/utils/parquet.d.ts +178 -0
  613. package/out/utils/parquet.d.ts.map +1 -0
  614. package/out/utils/parquet.js +371 -0
  615. package/out/utils/parquet.js.map +1 -0
  616. package/out/utils/slice-stats.d.ts +52 -0
  617. package/out/utils/slice-stats.d.ts.map +1 -0
  618. package/out/utils/slice-stats.js +58 -0
  619. package/out/utils/slice-stats.js.map +1 -0
  620. package/out/utils/split.d.ts +128 -0
  621. package/out/utils/split.d.ts.map +1 -0
  622. package/out/utils/split.js +204 -0
  623. package/out/utils/split.js.map +1 -0
  624. package/out/utils/tokenize.d.ts +64 -0
  625. package/out/utils/tokenize.d.ts.map +1 -0
  626. package/out/utils/tokenize.js +82 -0
  627. package/out/utils/tokenize.js.map +1 -0
  628. package/out/utils/wof-json.d.ts +113 -0
  629. package/out/utils/wof-json.d.ts.map +1 -0
  630. package/out/utils/wof-json.js +173 -0
  631. package/out/utils/wof-json.js.map +1 -0
  632. package/package.json +350 -65
  633. package/out/src/adapters/ban/adapter.d.ts +0 -44
  634. package/out/src/adapters/ban/adapter.d.ts.map +0 -1
  635. package/out/src/adapters/ban/adapter.js +0 -148
  636. package/out/src/adapters/ban/adapter.js.map +0 -1
  637. package/out/src/adapters/ban/street-decompose.d.ts.map +0 -1
  638. package/out/src/adapters/ban/street-decompose.js +0 -75
  639. package/out/src/adapters/ban/street-decompose.js.map +0 -1
  640. package/out/src/adapters/fcc-bdc/adapter.d.ts +0 -68
  641. package/out/src/adapters/fcc-bdc/adapter.d.ts.map +0 -1
  642. package/out/src/adapters/fcc-bdc/adapter.js +0 -144
  643. package/out/src/adapters/fcc-bdc/adapter.js.map +0 -1
  644. package/out/src/adapters/geonames/adapter.d.ts +0 -46
  645. package/out/src/adapters/geonames/adapter.d.ts.map +0 -1
  646. package/out/src/adapters/geonames/adapter.js +0 -176
  647. package/out/src/adapters/geonames/adapter.js.map +0 -1
  648. package/out/src/adapters/geonames-postal/adapter.d.ts +0 -41
  649. package/out/src/adapters/geonames-postal/adapter.d.ts.map +0 -1
  650. package/out/src/adapters/geonames-postal/adapter.js +0 -104
  651. package/out/src/adapters/geonames-postal/adapter.js.map +0 -1
  652. package/out/src/adapters/gnaf/adapter.d.ts +0 -49
  653. package/out/src/adapters/gnaf/adapter.d.ts.map +0 -1
  654. package/out/src/adapters/gnaf/adapter.js +0 -124
  655. package/out/src/adapters/gnaf/adapter.js.map +0 -1
  656. package/out/src/adapters/gnaf/assemble.d.ts +0 -65
  657. package/out/src/adapters/gnaf/assemble.d.ts.map +0 -1
  658. package/out/src/adapters/gnaf/assemble.js +0 -154
  659. package/out/src/adapters/gnaf/assemble.js.map +0 -1
  660. package/out/src/adapters/index.d.ts +0 -51
  661. package/out/src/adapters/index.d.ts.map +0 -1
  662. package/out/src/adapters/index.js +0 -95
  663. package/out/src/adapters/index.js.map +0 -1
  664. package/out/src/adapters/openaddresses/adapter.d.ts +0 -72
  665. package/out/src/adapters/openaddresses/adapter.d.ts.map +0 -1
  666. package/out/src/adapters/openaddresses/adapter.js +0 -186
  667. package/out/src/adapters/openaddresses/adapter.js.map +0 -1
  668. package/out/src/adapters/overture/adapter.d.ts +0 -48
  669. package/out/src/adapters/overture/adapter.d.ts.map +0 -1
  670. package/out/src/adapters/overture/adapter.js +0 -125
  671. package/out/src/adapters/overture/adapter.js.map +0 -1
  672. package/out/src/adapters/state-hi-schools/adapter.d.ts +0 -47
  673. package/out/src/adapters/state-hi-schools/adapter.d.ts.map +0 -1
  674. package/out/src/adapters/state-hi-schools/adapter.js +0 -132
  675. package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
  676. package/out/src/adapters/state-ia-contractors/adapter.d.ts +0 -34
  677. package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
  678. package/out/src/adapters/state-ia-contractors/adapter.js +0 -106
  679. package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
  680. package/out/src/adapters/state-ny-notaries/adapter.d.ts +0 -32
  681. package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
  682. package/out/src/adapters/state-ny-notaries/adapter.js +0 -125
  683. package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
  684. package/out/src/adapters/state-tx-notaries/adapter.d.ts +0 -33
  685. package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
  686. package/out/src/adapters/state-tx-notaries/adapter.js +0 -120
  687. package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
  688. package/out/src/adapters/synth-po-box/adapter.d.ts +0 -67
  689. package/out/src/adapters/synth-po-box/adapter.d.ts.map +0 -1
  690. package/out/src/adapters/synth-po-box/adapter.js +0 -140
  691. package/out/src/adapters/synth-po-box/adapter.js.map +0 -1
  692. package/out/src/adapters/tiger/adapter.d.ts +0 -55
  693. package/out/src/adapters/tiger/adapter.d.ts.map +0 -1
  694. package/out/src/adapters/tiger/adapter.js +0 -201
  695. package/out/src/adapters/tiger/adapter.js.map +0 -1
  696. package/out/src/adapters/tiger/street-decompose.d.ts.map +0 -1
  697. package/out/src/adapters/tiger/street-decompose.js +0 -90
  698. package/out/src/adapters/tiger/street-decompose.js.map +0 -1
  699. package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -47
  700. package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
  701. package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +0 -138
  702. package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
  703. package/out/src/adapters/usgov-imls-pls/adapter.d.ts +0 -36
  704. package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
  705. package/out/src/adapters/usgov-imls-pls/adapter.js +0 -110
  706. package/out/src/adapters/usgov-imls-pls/adapter.js.map +0 -1
  707. package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
  708. package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
  709. package/out/src/adapters/usgov-irs-bmf/adapter.js +0 -123
  710. package/out/src/adapters/usgov-irs-bmf/adapter.js.map +0 -1
  711. package/out/src/adapters/usgov-nad/adapter.d.ts +0 -48
  712. package/out/src/adapters/usgov-nad/adapter.d.ts.map +0 -1
  713. package/out/src/adapters/usgov-nad/adapter.js +0 -252
  714. package/out/src/adapters/usgov-nad/adapter.js.map +0 -1
  715. package/out/src/adapters/usgov-nppes/adapter.d.ts +0 -39
  716. package/out/src/adapters/usgov-nppes/adapter.d.ts.map +0 -1
  717. package/out/src/adapters/usgov-nppes/adapter.js +0 -116
  718. package/out/src/adapters/usgov-nppes/adapter.js.map +0 -1
  719. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts +0 -46
  720. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
  721. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -155
  722. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
  723. package/out/src/adapters/utils/index.d.ts +0 -144
  724. package/out/src/adapters/utils/index.d.ts.map +0 -1
  725. package/out/src/adapters/utils/index.js +0 -151
  726. package/out/src/adapters/utils/index.js.map +0 -1
  727. package/out/src/adapters/wof-admin-jp/adapter.d.ts +0 -65
  728. package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
  729. package/out/src/adapters/wof-admin-jp/adapter.js +0 -164
  730. package/out/src/adapters/wof-admin-jp/adapter.js.map +0 -1
  731. package/out/src/adapters/wof-admin-json/adapter.d.ts +0 -93
  732. package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
  733. package/out/src/adapters/wof-admin-json/adapter.js +0 -248
  734. package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
  735. package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -70
  736. package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
  737. package/out/src/adapters/wof-postalcode-json/adapter.js +0 -185
  738. package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
  739. package/out/src/build.d.ts +0 -131
  740. package/out/src/build.d.ts.map +0 -1
  741. package/out/src/build.js +0 -248
  742. package/out/src/build.js.map +0 -1
  743. package/out/src/codex/us-fips-state.d.ts.map +0 -1
  744. package/out/src/codex/us-fips-state.js.map +0 -1
  745. package/out/src/index.d.ts +0 -14
  746. package/out/src/index.d.ts.map +0 -1
  747. package/out/src/index.js +0 -14
  748. package/out/src/index.js.map +0 -1
  749. package/out/src/name-prone-us-suffixes.d.ts +0 -12
  750. package/out/src/name-prone-us-suffixes.d.ts.map +0 -1
  751. package/out/src/name-prone-us-suffixes.js +0 -12
  752. package/out/src/name-prone-us-suffixes.js.map +0 -1
  753. package/out/src/parquet-wrapper/index.d.ts +0 -9
  754. package/out/src/parquet-wrapper/index.d.ts.map +0 -1
  755. package/out/src/parquet-wrapper/index.js +0 -9
  756. package/out/src/parquet-wrapper/index.js.map +0 -1
  757. package/out/src/parquet-wrapper/reader.d.ts +0 -34
  758. package/out/src/parquet-wrapper/reader.d.ts.map +0 -1
  759. package/out/src/parquet-wrapper/reader.js +0 -64
  760. package/out/src/parquet-wrapper/reader.js.map +0 -1
  761. package/out/src/parquet-wrapper/schema.d.ts +0 -49
  762. package/out/src/parquet-wrapper/schema.d.ts.map +0 -1
  763. package/out/src/parquet-wrapper/schema.js +0 -55
  764. package/out/src/parquet-wrapper/schema.js.map +0 -1
  765. package/out/src/parquet-wrapper/writer.d.ts +0 -46
  766. package/out/src/parquet-wrapper/writer.d.ts.map +0 -1
  767. package/out/src/parquet-wrapper/writer.js +0 -76
  768. package/out/src/parquet-wrapper/writer.js.map +0 -1
  769. package/out/src/runner.d.ts +0 -126
  770. package/out/src/runner.d.ts.map +0 -1
  771. package/out/src/runner.js +0 -189
  772. package/out/src/runner.js.map +0 -1
  773. package/out/src/shard-recipes/anchor-absorption.d.ts +0 -20
  774. package/out/src/shard-recipes/anchor-absorption.d.ts.map +0 -1
  775. package/out/src/shard-recipes/anchor-absorption.js +0 -83
  776. package/out/src/shard-recipes/anchor-absorption.js.map +0 -1
  777. package/out/src/shard-recipes/boundary-stress.d.ts +0 -20
  778. package/out/src/shard-recipes/boundary-stress.d.ts.map +0 -1
  779. package/out/src/shard-recipes/boundary-stress.js +0 -83
  780. package/out/src/shard-recipes/boundary-stress.js.map +0 -1
  781. package/out/src/shard-recipes/country-balanced.d.ts +0 -32
  782. package/out/src/shard-recipes/country-balanced.d.ts.map +0 -1
  783. package/out/src/shard-recipes/country-balanced.js +0 -405
  784. package/out/src/shard-recipes/country-balanced.js.map +0 -1
  785. package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts +0 -22
  786. package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +0 -1
  787. package/out/src/shard-recipes/cz-pcfirst-preposition.js +0 -82
  788. package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +0 -1
  789. package/out/src/shard-recipes/fr-admin-split.d.ts +0 -38
  790. package/out/src/shard-recipes/fr-admin-split.d.ts.map +0 -1
  791. package/out/src/shard-recipes/fr-admin-split.js +0 -187
  792. package/out/src/shard-recipes/fr-admin-split.js.map +0 -1
  793. package/out/src/shard-recipes/fr-bare-street.d.ts +0 -28
  794. package/out/src/shard-recipes/fr-bare-street.d.ts.map +0 -1
  795. package/out/src/shard-recipes/fr-bare-street.js +0 -82
  796. package/out/src/shard-recipes/fr-bare-street.js.map +0 -1
  797. package/out/src/shard-recipes/fr-fragment.d.ts +0 -77
  798. package/out/src/shard-recipes/fr-fragment.d.ts.map +0 -1
  799. package/out/src/shard-recipes/fr-fragment.js +0 -276
  800. package/out/src/shard-recipes/fr-fragment.js.map +0 -1
  801. package/out/src/shard-recipes/fr-lieudit.d.ts +0 -32
  802. package/out/src/shard-recipes/fr-lieudit.d.ts.map +0 -1
  803. package/out/src/shard-recipes/fr-lieudit.js +0 -225
  804. package/out/src/shard-recipes/fr-lieudit.js.map +0 -1
  805. package/out/src/shard-recipes/fr-order.d.ts +0 -38
  806. package/out/src/shard-recipes/fr-order.d.ts.map +0 -1
  807. package/out/src/shard-recipes/fr-order.js +0 -207
  808. package/out/src/shard-recipes/fr-order.js.map +0 -1
  809. package/out/src/shard-recipes/german.d.ts +0 -23
  810. package/out/src/shard-recipes/german.d.ts.map +0 -1
  811. package/out/src/shard-recipes/german.js +0 -132
  812. package/out/src/shard-recipes/german.js.map +0 -1
  813. package/out/src/shard-recipes/house-venue.d.ts +0 -18
  814. package/out/src/shard-recipes/house-venue.d.ts.map +0 -1
  815. package/out/src/shard-recipes/house-venue.js +0 -74
  816. package/out/src/shard-recipes/house-venue.js.map +0 -1
  817. package/out/src/shard-recipes/index.d.ts +0 -24
  818. package/out/src/shard-recipes/index.d.ts.map +0 -1
  819. package/out/src/shard-recipes/index.js +0 -83
  820. package/out/src/shard-recipes/index.js.map +0 -1
  821. package/out/src/shard-recipes/intersection.d.ts +0 -42
  822. package/out/src/shard-recipes/intersection.d.ts.map +0 -1
  823. package/out/src/shard-recipes/intersection.js +0 -460
  824. package/out/src/shard-recipes/intersection.js.map +0 -1
  825. package/out/src/shard-recipes/locale.d.ts +0 -135
  826. package/out/src/shard-recipes/locale.d.ts.map +0 -1
  827. package/out/src/shard-recipes/locale.js +0 -458
  828. package/out/src/shard-recipes/locale.js.map +0 -1
  829. package/out/src/shard-recipes/nl-postcode.d.ts +0 -26
  830. package/out/src/shard-recipes/nl-postcode.d.ts.map +0 -1
  831. package/out/src/shard-recipes/nl-postcode.js +0 -102
  832. package/out/src/shard-recipes/nl-postcode.js.map +0 -1
  833. package/out/src/shard-recipes/no-fragment.d.ts +0 -43
  834. package/out/src/shard-recipes/no-fragment.d.ts.map +0 -1
  835. package/out/src/shard-recipes/no-fragment.js +0 -188
  836. package/out/src/shard-recipes/no-fragment.js.map +0 -1
  837. package/out/src/shard-recipes/no-street-led.d.ts +0 -24
  838. package/out/src/shard-recipes/no-street-led.d.ts.map +0 -1
  839. package/out/src/shard-recipes/no-street-led.js +0 -121
  840. package/out/src/shard-recipes/no-street-led.js.map +0 -1
  841. package/out/src/shard-recipes/no-street.d.ts +0 -18
  842. package/out/src/shard-recipes/no-street.d.ts.map +0 -1
  843. package/out/src/shard-recipes/no-street.js +0 -72
  844. package/out/src/shard-recipes/no-street.js.map +0 -1
  845. package/out/src/shard-recipes/po-box-cedex.d.ts +0 -38
  846. package/out/src/shard-recipes/po-box-cedex.d.ts.map +0 -1
  847. package/out/src/shard-recipes/po-box-cedex.js +0 -726
  848. package/out/src/shard-recipes/po-box-cedex.js.map +0 -1
  849. package/out/src/shard-recipes/po-box.d.ts +0 -17
  850. package/out/src/shard-recipes/po-box.d.ts.map +0 -1
  851. package/out/src/shard-recipes/po-box.js +0 -101
  852. package/out/src/shard-recipes/po-box.js.map +0 -1
  853. package/out/src/shard-recipes/scaffold.d.ts +0 -217
  854. package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
  855. package/out/src/shard-recipes/scaffold.js +0 -138
  856. package/out/src/shard-recipes/scaffold.js.map +0 -1
  857. package/out/src/shard-recipes/si-bare-village.d.ts +0 -32
  858. package/out/src/shard-recipes/si-bare-village.d.ts.map +0 -1
  859. package/out/src/shard-recipes/si-bare-village.js +0 -88
  860. package/out/src/shard-recipes/si-bare-village.js.map +0 -1
  861. package/out/src/shard-recipes/street-affix.d.ts +0 -89
  862. package/out/src/shard-recipes/street-affix.d.ts.map +0 -1
  863. package/out/src/shard-recipes/street-affix.js +0 -578
  864. package/out/src/shard-recipes/street-affix.js.map +0 -1
  865. package/out/src/shard-recipes/street-bare.d.ts +0 -25
  866. package/out/src/shard-recipes/street-bare.d.ts.map +0 -1
  867. package/out/src/shard-recipes/street-bare.js +0 -86
  868. package/out/src/shard-recipes/street-bare.js.map +0 -1
  869. package/out/src/shard-recipes/street.d.ts +0 -15
  870. package/out/src/shard-recipes/street.d.ts.map +0 -1
  871. package/out/src/shard-recipes/street.js +0 -69
  872. package/out/src/shard-recipes/street.js.map +0 -1
  873. package/out/src/shard-recipes/sub-venue-sources.d.ts +0 -228
  874. package/out/src/shard-recipes/sub-venue-sources.d.ts.map +0 -1
  875. package/out/src/shard-recipes/sub-venue-sources.js +0 -664
  876. package/out/src/shard-recipes/sub-venue-sources.js.map +0 -1
  877. package/out/src/shard-recipes/sub-venue.d.ts +0 -269
  878. package/out/src/shard-recipes/sub-venue.d.ts.map +0 -1
  879. package/out/src/shard-recipes/sub-venue.js +0 -709
  880. package/out/src/shard-recipes/sub-venue.js.map +0 -1
  881. package/out/src/shard-recipes/unit.d.ts +0 -29
  882. package/out/src/shard-recipes/unit.d.ts.map +0 -1
  883. package/out/src/shard-recipes/unit.js +0 -243
  884. package/out/src/shard-recipes/unit.js.map +0 -1
  885. package/out/src/synthesizers/anchor-absorption.d.ts +0 -63
  886. package/out/src/synthesizers/anchor-absorption.d.ts.map +0 -1
  887. package/out/src/synthesizers/anchor-absorption.js +0 -223
  888. package/out/src/synthesizers/anchor-absorption.js.map +0 -1
  889. package/out/src/synthesizers/boundary-stress.d.ts +0 -78
  890. package/out/src/synthesizers/boundary-stress.d.ts.map +0 -1
  891. package/out/src/synthesizers/boundary-stress.js +0 -455
  892. package/out/src/synthesizers/boundary-stress.js.map +0 -1
  893. package/out/src/synthesizers/german.d.ts +0 -107
  894. package/out/src/synthesizers/german.d.ts.map +0 -1
  895. package/out/src/synthesizers/german.js +0 -148
  896. package/out/src/synthesizers/german.js.map +0 -1
  897. package/out/src/synthesizers/house-venue.d.ts +0 -56
  898. package/out/src/synthesizers/house-venue.d.ts.map +0 -1
  899. package/out/src/synthesizers/house-venue.js +0 -253
  900. package/out/src/synthesizers/house-venue.js.map +0 -1
  901. package/out/src/synthesizers/intersection.d.ts +0 -52
  902. package/out/src/synthesizers/intersection.d.ts.map +0 -1
  903. package/out/src/synthesizers/intersection.js +0 -175
  904. package/out/src/synthesizers/intersection.js.map +0 -1
  905. package/out/src/synthesizers/no-street.d.ts +0 -72
  906. package/out/src/synthesizers/no-street.d.ts.map +0 -1
  907. package/out/src/synthesizers/no-street.js +0 -282
  908. package/out/src/synthesizers/no-street.js.map +0 -1
  909. package/out/src/synthesizers/po-box.d.ts +0 -104
  910. package/out/src/synthesizers/po-box.d.ts.map +0 -1
  911. package/out/src/synthesizers/po-box.js +0 -266
  912. package/out/src/synthesizers/po-box.js.map +0 -1
  913. package/out/src/synthesizers/street.d.ts +0 -54
  914. package/out/src/synthesizers/street.d.ts.map +0 -1
  915. package/out/src/synthesizers/street.js +0 -220
  916. package/out/src/synthesizers/street.js.map +0 -1
  917. package/out/src/synthesizers/utils.d.ts +0 -203
  918. package/out/src/synthesizers/utils.d.ts.map +0 -1
  919. package/out/src/synthesizers/utils.js +0 -707
  920. package/out/src/synthesizers/utils.js.map +0 -1
  921. package/out/src/tools/align-shard.d.ts +0 -8
  922. package/out/src/tools/align-shard.d.ts.map +0 -1
  923. package/out/src/tools/align-shard.js +0 -56
  924. package/out/src/tools/align-shard.js.map +0 -1
  925. package/out/src/tools/audit.d.ts +0 -28
  926. package/out/src/tools/audit.d.ts.map +0 -1
  927. package/out/src/tools/audit.js +0 -285
  928. package/out/src/tools/audit.js.map +0 -1
  929. package/out/src/tools/corpus-stats.d.ts +0 -44
  930. package/out/src/tools/corpus-stats.d.ts.map +0 -1
  931. package/out/src/tools/corpus-stats.js +0 -138
  932. package/out/src/tools/corpus-stats.js.map +0 -1
  933. package/out/src/tools/fetch/ban.d.ts +0 -31
  934. package/out/src/tools/fetch/ban.d.ts.map +0 -1
  935. package/out/src/tools/fetch/ban.js +0 -255
  936. package/out/src/tools/fetch/ban.js.map +0 -1
  937. package/out/src/tools/fetch/download.d.ts +0 -69
  938. package/out/src/tools/fetch/download.d.ts.map +0 -1
  939. package/out/src/tools/fetch/download.js +0 -100
  940. package/out/src/tools/fetch/download.js.map +0 -1
  941. package/out/src/tools/fetch/hrsa.d.ts +0 -18
  942. package/out/src/tools/fetch/hrsa.d.ts.map +0 -1
  943. package/out/src/tools/fetch/hrsa.js +0 -46
  944. package/out/src/tools/fetch/hrsa.js.map +0 -1
  945. package/out/src/tools/fetch/imls-pls.d.ts +0 -25
  946. package/out/src/tools/fetch/imls-pls.d.ts.map +0 -1
  947. package/out/src/tools/fetch/imls-pls.js +0 -108
  948. package/out/src/tools/fetch/imls-pls.js.map +0 -1
  949. package/out/src/tools/fetch/index.d.ts +0 -133
  950. package/out/src/tools/fetch/index.d.ts.map +0 -1
  951. package/out/src/tools/fetch/index.js +0 -132
  952. package/out/src/tools/fetch/index.js.map +0 -1
  953. package/out/src/tools/fetch/nad.d.ts +0 -70
  954. package/out/src/tools/fetch/nad.d.ts.map +0 -1
  955. package/out/src/tools/fetch/nad.js +0 -225
  956. package/out/src/tools/fetch/nad.js.map +0 -1
  957. package/out/src/tools/fetch/nppes.d.ts +0 -26
  958. package/out/src/tools/fetch/nppes.d.ts.map +0 -1
  959. package/out/src/tools/fetch/nppes.js +0 -124
  960. package/out/src/tools/fetch/nppes.js.map +0 -1
  961. package/out/src/tools/fetch/openaddresses.d.ts +0 -61
  962. package/out/src/tools/fetch/openaddresses.d.ts.map +0 -1
  963. package/out/src/tools/fetch/openaddresses.js +0 -316
  964. package/out/src/tools/fetch/openaddresses.js.map +0 -1
  965. package/out/src/tools/fetch/ourairports.d.ts +0 -45
  966. package/out/src/tools/fetch/ourairports.d.ts.map +0 -1
  967. package/out/src/tools/fetch/ourairports.js +0 -123
  968. package/out/src/tools/fetch/ourairports.js.map +0 -1
  969. package/out/src/tools/fetch/ppd.d.ts +0 -18
  970. package/out/src/tools/fetch/ppd.d.ts.map +0 -1
  971. package/out/src/tools/fetch/ppd.js +0 -100
  972. package/out/src/tools/fetch/ppd.js.map +0 -1
  973. package/out/src/tools/fetch/state-hi-schools.d.ts +0 -25
  974. package/out/src/tools/fetch/state-hi-schools.d.ts.map +0 -1
  975. package/out/src/tools/fetch/state-hi-schools.js +0 -178
  976. package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
  977. package/out/src/tools/fetch/state-sources.d.ts +0 -22
  978. package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
  979. package/out/src/tools/fetch/state-sources.js +0 -115
  980. package/out/src/tools/fetch/state-sources.js.map +0 -1
  981. package/out/src/tools/fetch/tiger-full.d.ts +0 -42
  982. package/out/src/tools/fetch/tiger-full.d.ts.map +0 -1
  983. package/out/src/tools/fetch/tiger-full.js +0 -254
  984. package/out/src/tools/fetch/tiger-full.js.map +0 -1
  985. package/out/src/tools/fetch/wikidata-subvenue.d.ts +0 -171
  986. package/out/src/tools/fetch/wikidata-subvenue.d.ts.map +0 -1
  987. package/out/src/tools/fetch/wikidata-subvenue.js +0 -275
  988. package/out/src/tools/fetch/wikidata-subvenue.js.map +0 -1
  989. package/out/src/tools/gb-title-case.d.ts.map +0 -1
  990. package/out/src/tools/gb-title-case.js.map +0 -1
  991. package/out/src/tools/golden-expand.d.ts +0 -90
  992. package/out/src/tools/golden-expand.d.ts.map +0 -1
  993. package/out/src/tools/golden-expand.js +0 -404
  994. package/out/src/tools/golden-expand.js.map +0 -1
  995. package/out/src/tools/golden-promote.d.ts.map +0 -1
  996. package/out/src/tools/golden-promote.js +0 -244
  997. package/out/src/tools/golden-promote.js.map +0 -1
  998. package/out/src/tools/golden-relabel-street.d.ts +0 -196
  999. package/out/src/tools/golden-relabel-street.d.ts.map +0 -1
  1000. package/out/src/tools/golden-relabel-street.js +0 -440
  1001. package/out/src/tools/golden-relabel-street.js.map +0 -1
  1002. package/out/src/tools/index.d.ts +0 -28
  1003. package/out/src/tools/index.d.ts.map +0 -1
  1004. package/out/src/tools/index.js +0 -28
  1005. package/out/src/tools/index.js.map +0 -1
  1006. package/out/src/tools/ingest-csv.d.ts.map +0 -1
  1007. package/out/src/tools/ingest-csv.js +0 -307
  1008. package/out/src/tools/ingest-csv.js.map +0 -1
  1009. package/out/src/tools/jsonl-to-parquet.d.ts +0 -61
  1010. package/out/src/tools/jsonl-to-parquet.d.ts.map +0 -1
  1011. package/out/src/tools/jsonl-to-parquet.js +0 -164
  1012. package/out/src/tools/jsonl-to-parquet.js.map +0 -1
  1013. package/out/src/tools/lint-shard-vocab.d.ts +0 -90
  1014. package/out/src/tools/lint-shard-vocab.d.ts.map +0 -1
  1015. package/out/src/tools/lint-shard-vocab.js +0 -281
  1016. package/out/src/tools/lint-shard-vocab.js.map +0 -1
  1017. package/out/src/tools/lint-shard.d.ts +0 -93
  1018. package/out/src/tools/lint-shard.d.ts.map +0 -1
  1019. package/out/src/tools/lint-shard.js +0 -354
  1020. package/out/src/tools/lint-shard.js.map +0 -1
  1021. package/out/src/tools/overlay-manifest.d.ts +0 -35
  1022. package/out/src/tools/overlay-manifest.d.ts.map +0 -1
  1023. package/out/src/tools/overlay-manifest.js +0 -88
  1024. package/out/src/tools/overlay-manifest.js.map +0 -1
  1025. package/out/src/tools/overture-subvenue.d.ts +0 -112
  1026. package/out/src/tools/overture-subvenue.d.ts.map +0 -1
  1027. package/out/src/tools/overture-subvenue.js +0 -144
  1028. package/out/src/tools/overture-subvenue.js.map +0 -1
  1029. package/out/src/tools/shard-kryptonite.d.ts +0 -32
  1030. package/out/src/tools/shard-kryptonite.d.ts.map +0 -1
  1031. package/out/src/tools/shard-kryptonite.js +0 -101
  1032. package/out/src/tools/shard-kryptonite.js.map +0 -1
  1033. package/out/src/tools/shard-translit.d.ts +0 -51
  1034. package/out/src/tools/shard-translit.d.ts.map +0 -1
  1035. package/out/src/tools/shard-translit.js +0 -197
  1036. package/out/src/tools/shard-translit.js.map +0 -1
  1037. package/out/src/tools/sub-venue-lexicon.d.ts +0 -507
  1038. package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
  1039. package/out/src/tools/sub-venue-lexicon.js +0 -817
  1040. package/out/src/tools/sub-venue-lexicon.js.map +0 -1
  1041. package/out/src/tools/sub-venue-promotions.d.ts +0 -94
  1042. package/out/src/tools/sub-venue-promotions.d.ts.map +0 -1
  1043. package/out/src/tools/sub-venue-promotions.js +0 -266
  1044. package/out/src/tools/sub-venue-promotions.js.map +0 -1
  1045. package/out/src/types.d.ts +0 -221
  1046. package/out/src/types.d.ts.map +0 -1
  1047. package/out/src/types.js.map +0 -1
  1048. package/out/src/utils/align.d.ts +0 -93
  1049. package/out/src/utils/align.d.ts.map +0 -1
  1050. package/out/src/utils/align.js +0 -234
  1051. package/out/src/utils/align.js.map +0 -1
  1052. package/out/src/utils/golden.d.ts +0 -69
  1053. package/out/src/utils/golden.d.ts.map +0 -1
  1054. package/out/src/utils/golden.js +0 -127
  1055. package/out/src/utils/golden.js.map +0 -1
  1056. package/out/src/utils/index.d.ts +0 -14
  1057. package/out/src/utils/index.d.ts.map +0 -1
  1058. package/out/src/utils/index.js +0 -14
  1059. package/out/src/utils/index.js.map +0 -1
  1060. package/out/src/utils/license.d.ts.map +0 -1
  1061. package/out/src/utils/license.js +0 -47
  1062. package/out/src/utils/license.js.map +0 -1
  1063. package/out/src/utils/parquet.d.ts +0 -143
  1064. package/out/src/utils/parquet.d.ts.map +0 -1
  1065. package/out/src/utils/parquet.js +0 -258
  1066. package/out/src/utils/parquet.js.map +0 -1
  1067. package/out/src/utils/split.d.ts +0 -127
  1068. package/out/src/utils/split.d.ts.map +0 -1
  1069. package/out/src/utils/split.js +0 -204
  1070. package/out/src/utils/split.js.map +0 -1
  1071. package/out/src/utils/tokenize.d.ts +0 -56
  1072. package/out/src/utils/tokenize.d.ts.map +0 -1
  1073. package/out/src/utils/tokenize.js +0 -48
  1074. package/out/src/utils/tokenize.js.map +0 -1
  1075. package/out/src/utils/wof-json.d.ts +0 -109
  1076. package/out/src/utils/wof-json.d.ts.map +0 -1
  1077. package/out/src/utils/wof-json.js +0 -173
  1078. package/out/src/utils/wof-json.js.map +0 -1
  1079. package/src/adapters/ban/adapter.ts +0 -189
  1080. package/src/adapters/ban/street-decompose.ts +0 -96
  1081. package/src/adapters/fcc-bdc/adapter.ts +0 -173
  1082. package/src/adapters/geonames/adapter.ts +0 -199
  1083. package/src/adapters/geonames-postal/adapter.ts +0 -118
  1084. package/src/adapters/gnaf/adapter.ts +0 -148
  1085. package/src/adapters/gnaf/assemble.ts +0 -226
  1086. package/src/adapters/index.ts +0 -149
  1087. package/src/adapters/openaddresses/adapter.ts +0 -250
  1088. package/src/adapters/overture/adapter.ts +0 -161
  1089. package/src/adapters/state-hi-schools/adapter.ts +0 -162
  1090. package/src/adapters/state-ia-contractors/adapter.ts +0 -138
  1091. package/src/adapters/state-ny-notaries/adapter.ts +0 -159
  1092. package/src/adapters/state-tx-notaries/adapter.ts +0 -151
  1093. package/src/adapters/synth-po-box/adapter.ts +0 -203
  1094. package/src/adapters/tiger/adapter.ts +0 -252
  1095. package/src/adapters/tiger/street-decompose.ts +0 -111
  1096. package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -181
  1097. package/src/adapters/usgov-imls-pls/adapter.ts +0 -138
  1098. package/src/adapters/usgov-irs-bmf/adapter.ts +0 -161
  1099. package/src/adapters/usgov-nad/adapter.ts +0 -347
  1100. package/src/adapters/usgov-nppes/adapter.ts +0 -157
  1101. package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -202
  1102. package/src/adapters/utils/index.ts +0 -220
  1103. package/src/adapters/wof-admin-jp/adapter.ts +0 -219
  1104. package/src/adapters/wof-admin-json/adapter.ts +0 -294
  1105. package/src/adapters/wof-postalcode-json/adapter.ts +0 -216
  1106. package/src/build.ts +0 -386
  1107. package/src/index.ts +0 -14
  1108. package/src/name-prone-us-suffixes.ts +0 -12
  1109. package/src/parquet-wrapper/index.ts +0 -9
  1110. package/src/parquet-wrapper/reader.ts +0 -88
  1111. package/src/parquet-wrapper/schema.ts +0 -88
  1112. package/src/parquet-wrapper/writer.ts +0 -110
  1113. package/src/runner.ts +0 -322
  1114. package/src/shard-recipes/anchor-absorption.ts +0 -103
  1115. package/src/shard-recipes/boundary-stress.ts +0 -104
  1116. package/src/shard-recipes/country-balanced.ts +0 -522
  1117. package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -92
  1118. package/src/shard-recipes/fr-admin-split.ts +0 -237
  1119. package/src/shard-recipes/fr-bare-street.ts +0 -95
  1120. package/src/shard-recipes/fr-fragment.ts +0 -332
  1121. package/src/shard-recipes/fr-lieudit.ts +0 -300
  1122. package/src/shard-recipes/fr-order.ts +0 -256
  1123. package/src/shard-recipes/german.ts +0 -169
  1124. package/src/shard-recipes/house-venue.ts +0 -88
  1125. package/src/shard-recipes/index.ts +0 -89
  1126. package/src/shard-recipes/intersection.ts +0 -629
  1127. package/src/shard-recipes/locale.ts +0 -601
  1128. package/src/shard-recipes/nl-postcode.ts +0 -115
  1129. package/src/shard-recipes/no-fragment.ts +0 -219
  1130. package/src/shard-recipes/no-street-led.ts +0 -143
  1131. package/src/shard-recipes/no-street.ts +0 -86
  1132. package/src/shard-recipes/po-box-cedex.ts +0 -919
  1133. package/src/shard-recipes/po-box.ts +0 -123
  1134. package/src/shard-recipes/scaffold.ts +0 -329
  1135. package/src/shard-recipes/si-bare-village.ts +0 -97
  1136. package/src/shard-recipes/street-affix.ts +0 -825
  1137. package/src/shard-recipes/street-bare.ts +0 -101
  1138. package/src/shard-recipes/street.ts +0 -82
  1139. package/src/shard-recipes/sub-venue-sources.ts +0 -895
  1140. package/src/shard-recipes/sub-venue.ts +0 -982
  1141. package/src/shard-recipes/unit.ts +0 -320
  1142. package/src/synthesizers/anchor-absorption.ts +0 -290
  1143. package/src/synthesizers/boundary-stress.ts +0 -531
  1144. package/src/synthesizers/german.ts +0 -250
  1145. package/src/synthesizers/house-venue.ts +0 -316
  1146. package/src/synthesizers/intersection.ts +0 -232
  1147. package/src/synthesizers/no-street.ts +0 -349
  1148. package/src/synthesizers/po-box.ts +0 -339
  1149. package/src/synthesizers/street.ts +0 -272
  1150. package/src/synthesizers/utils.ts +0 -901
  1151. package/src/tools/align-shard.ts +0 -69
  1152. package/src/tools/audit.ts +0 -399
  1153. package/src/tools/corpus-stats.ts +0 -184
  1154. package/src/tools/fetch/ban.ts +0 -310
  1155. package/src/tools/fetch/download.ts +0 -158
  1156. package/src/tools/fetch/hrsa.ts +0 -68
  1157. package/src/tools/fetch/imls-pls.ts +0 -158
  1158. package/src/tools/fetch/index.ts +0 -136
  1159. package/src/tools/fetch/nad.ts +0 -331
  1160. package/src/tools/fetch/nppes.ts +0 -172
  1161. package/src/tools/fetch/openaddresses.ts +0 -408
  1162. package/src/tools/fetch/ourairports.ts +0 -166
  1163. package/src/tools/fetch/ppd.ts +0 -137
  1164. package/src/tools/fetch/state-hi-schools.ts +0 -228
  1165. package/src/tools/fetch/state-sources.ts +0 -155
  1166. package/src/tools/fetch/tiger-full.ts +0 -361
  1167. package/src/tools/fetch/wikidata-subvenue.ts +0 -386
  1168. package/src/tools/golden-expand.ts +0 -573
  1169. package/src/tools/golden-promote.ts +0 -353
  1170. package/src/tools/golden-relabel-street.ts +0 -685
  1171. package/src/tools/index.ts +0 -28
  1172. package/src/tools/ingest-csv.ts +0 -435
  1173. package/src/tools/jsonl-to-parquet.ts +0 -221
  1174. package/src/tools/lint-shard-vocab.ts +0 -409
  1175. package/src/tools/lint-shard.ts +0 -543
  1176. package/src/tools/overlay-manifest.ts +0 -145
  1177. package/src/tools/overture-subvenue.ts +0 -215
  1178. package/src/tools/shard-kryptonite.ts +0 -138
  1179. package/src/tools/shard-translit.ts +0 -270
  1180. package/src/tools/sub-venue-lexicon.ts +0 -1250
  1181. package/src/tools/sub-venue-promotions.ts +0 -330
  1182. package/src/types.ts +0 -247
  1183. package/src/utils/align.ts +0 -330
  1184. package/src/utils/golden.ts +0 -176
  1185. package/src/utils/index.ts +0 -14
  1186. package/src/utils/license.ts +0 -50
  1187. package/src/utils/parquet.ts +0 -377
  1188. package/src/utils/split.ts +0 -278
  1189. package/src/utils/tokenize.ts +0 -78
  1190. package/src/utils/wof-json.ts +0 -244
  1191. /package/{src → lib}/codex/us-fips-state.ts +0 -0
  1192. /package/{src → lib}/tools/gb-title-case.ts +0 -0
  1193. /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
  1194. /package/out/{src/adapters → adapters}/tiger/street-decompose.d.ts +0 -0
  1195. /package/out/{src/codex → codex}/us-fips-state.d.ts +0 -0
  1196. /package/out/{src/codex → codex}/us-fips-state.js +0 -0
  1197. /package/out/{src/tools → tools}/gb-title-case.d.ts +0 -0
  1198. /package/out/{src/tools → tools}/gb-title-case.js +0 -0
  1199. /package/out/{src/tools → tools}/golden-promote.d.ts +0 -0
  1200. /package/out/{src/tools → tools}/ingest-csv.d.ts +0 -0
  1201. /package/out/{src/types.js → types.js} +0 -0
  1202. /package/out/{src/utils → utils}/license.d.ts +0 -0
@@ -1,405 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * `country-balanced` shard recipe — the BALANCED, MODEL-FIRST country-coverage shard (#464). The
7
- * shipped model is STARVED on `country` (P=R=F1=0 on the homograph eval), so this fills the void
8
- * the way the `unit` shard did, but built to AVOID over-firing "trailing token ⇒ country". Three
9
- * ingredients, ported faithfully from scripts/build-country-shard-balanced.mjs:
10
- *
11
- * 1. Breadth/recall — real OA skeletons (US/DE/FR/IT/NL) with a country token in a varied surface form
12
- * from `@mailwoman/codex/country` (canonical / endonym / ISO code), + ~30% country-ABSENT
13
- * negatives (teach O-emission, the precision floor).
14
- * 2. Homograph CONTRAST pairs — each true country-name homograph (Georgia, Jordan, Lebanon, Mexico,
15
- * Peru, Turkey) rendered BOTH ways: as `country` (foreign-city context) AND as the US
16
- * `region`/`locality` (US-ZIP context). Teaches that the label is CONTEXTUAL, not
17
- * positional.
18
- * 3. Code-as-region negatives — 2-letter codes that are both a US state abbrev and an ISO country code
19
- * (CA/GA/IN/MA/PA/AL) in US-ZIP context → must read as `region`, never `country`.
20
- *
21
- * `--golden` emits a held-out synthetic val over the VT (US) + Berlin (DE) holdouts. This is a
22
- * `generate`-mode recipe that still reads REAL tuples off disk — `--count` bounds the OUTPUT, not
23
- * the input. The passed `random` (the framework LCG) is consumed in the exact call order the
24
- * legacy script used.
25
- */
26
- import { COUNTRY_SURFACE_FORMS, CountryNames } from "@mailwoman/codex/country";
27
- import { dataRootPath } from "@mailwoman/core/utils";
28
- import { stableSourceID } from "@mailwoman/corpus/adapters/utils";
29
- import { alignRow } from "@mailwoman/corpus/utils";
30
- import { makeMulberry32, readZippedCSVRecords } from "./scaffold.js";
31
- // v2: the country TOKEN is decoupled from the skeleton's locale and drawn from a BROAD pool — every
32
- // ISO canonical name + every curated surface form (endonyms/abbrevs). Surface forms are over-weighted
33
- // so endonyms/abbrevs ("Deutschland","USA","NL") get strong signal.
34
- /* oxlint-disable sister-software/no-unnamed-threshold -- the bare decimals below are weighted-sampler
35
- cutoffs, not thresholds: `const r = random()` followed by a cascade of `r < 0.4` branches IS the
36
- output distribution, and reading the cascade top-to-bottom is how you see it. Naming each cutoff
37
- would hide the distribution behind a wall of identifiers. Genuine thresholds in these files are
38
- extracted as named constants above. */
39
- const COUNTRY_FORM_POOL = (() => {
40
- const surface = Object.values(COUNTRY_SURFACE_FORMS).flat(); // endonyms + abbrevs + canonical (curated)
41
- const names = [...CountryNames];
42
- // all ~249 ISO canonical English names (breadth)
43
- return { surface, names };
44
- })();
45
- /**
46
- * Negatives: rows with NO country token → teach golden precision.
47
- */
48
- const COUNTRY_ABSENT_PROB = 0.3;
49
- /**
50
- * Multi-locale OA sources. region = implied admin where the extract is single-region (US states, DE Saxony);
51
- * countrywide extracts (FR/IT/NL) read region from the CSV when present.
52
- */
53
- const SOURCES = [
54
- {
55
- zip: dataRootPath("oa-cache", "us__ia__statewide.zip"),
56
- csv: "us/ia/statewide.csv",
57
- iso2: "US",
58
- region: "IA",
59
- order: "us",
60
- },
61
- { zip: dataRootPath("oa-cache", "us__il__cook.zip"), csv: "us/il/cook.csv", iso2: "US", region: "IL", order: "us" },
62
- {
63
- zip: dataRootPath("oa-cache", "us__mt__statewide.zip"),
64
- csv: "us/mt/statewide.csv",
65
- iso2: "US",
66
- region: "MT",
67
- order: "us",
68
- },
69
- {
70
- zip: dataRootPath("oa-cache", "us__sd__statewide.zip"),
71
- csv: "us/sd/statewide.csv",
72
- iso2: "US",
73
- region: "SD",
74
- order: "us",
75
- },
76
- {
77
- zip: dataRootPath("oa-cache", "de__sn__statewide.zip"),
78
- csv: "de/sn/statewide.csv",
79
- iso2: "DE",
80
- region: "",
81
- order: "eu",
82
- },
83
- {
84
- zip: dataRootPath("oa-cache", "fr__countrywide.zip"),
85
- csv: "fr/countrywide.csv",
86
- iso2: "FR",
87
- region: "",
88
- order: "fr",
89
- },
90
- // ES uses the Spanish IGN schema, not the OA standard columns — skipped here (codex still recognizes
91
- // "España"/"Spain"). A dedicated IGN adapter is a follow-up.
92
- {
93
- zip: dataRootPath("oa-cache", "it__countrywide.zip"),
94
- csv: "it/countrywide.csv",
95
- iso2: "IT",
96
- region: "",
97
- order: "eu",
98
- },
99
- {
100
- zip: dataRootPath("oa-cache", "nl__countrywide.zip"),
101
- csv: "nl/countrywide.csv",
102
- iso2: "NL",
103
- region: "",
104
- order: "eu",
105
- },
106
- ];
107
- /**
108
- * Held-out for --golden: Vermont (US holdout) + Berlin (DE holdout) — geographic split, never trained.
109
- */
110
- const EVAL_SOURCES = [
111
- {
112
- zip: dataRootPath("oa-cache", "us__vt__statewide.zip"),
113
- csv: "us/vt/statewide.csv",
114
- iso2: "US",
115
- region: "VT",
116
- order: "us",
117
- },
118
- { zip: dataRootPath("oa-cache", "de__berlin.zip"), csv: "de/berlin.csv", iso2: "DE", region: "", order: "eu" },
119
- ];
120
- /**
121
- * The countrywide extracts (FR/IT/NL) are GB-scale, so this reads only as far as `limit` distinct tuples: the `break`
122
- * closes the reader, which releases the archive without inflating the rest of the member.
123
- */
124
- async function readTuples(source, limit) {
125
- const tuples = [];
126
- const seen = new Set();
127
- for await (const row of readZippedCSVRecords(source.zip, source.csv)) {
128
- if (tuples.length >= limit)
129
- break;
130
- const street = row.street ?? "", locality = row.city ?? "", house_number = row.number ?? "";
131
- if (!street || !locality || !house_number)
132
- continue;
133
- const key = `${house_number}|${street}|${locality}`.toLowerCase();
134
- if (seen.has(key))
135
- continue;
136
- seen.add(key);
137
- tuples.push({
138
- house_number,
139
- street,
140
- locality,
141
- region: row.region || source.region,
142
- postcode: row.postcode ?? "",
143
- iso2: source.iso2,
144
- order: source.order,
145
- });
146
- }
147
- return tuples;
148
- }
149
- /**
150
- * Pick a country token from the BROAD pool, or null (a country-absent negative). v2.
151
- */
152
- function pickCountry(random) {
153
- if (random() < COUNTRY_ABSENT_PROB)
154
- return null; // negative — teaches "trailing token != always country"
155
- // 60% curated surface forms (endonym/abbrev variety), 40% broad ISO canonical names (coverage).
156
- const pool = random() < 0.6 ? COUNTRY_FORM_POOL.surface : COUNTRY_FORM_POOL.names;
157
- return pool[Math.floor(random() * pool.length)];
158
- }
159
- /**
160
- * Render the address body in native-ish order. `country` null → a country-ABSENT negative row.
161
- */
162
- function renderCountry(random, t, country) {
163
- const { house_number: hn, street, locality: loc, region: reg, postcode: pc, order } = t;
164
- const components = { house_number: hn, street, locality: loc };
165
- if (reg) {
166
- components.region = reg;
167
- }
168
- if (pc) {
169
- components.postcode = pc;
170
- }
171
- let body;
172
- if (order === "us") {
173
- const regPc = [reg, pc].filter(Boolean).join(" ");
174
- body = `${hn} ${street}, ${loc}${regPc ? ", " + regPc : ""}`;
175
- }
176
- else if (order === "fr") {
177
- // French is NUMBER-street, postcode-city: "84 Route de la Fontaine, 75008 Paris".
178
- body = `${hn} ${street}, ${[pc, loc].filter(Boolean).join(" ")}`;
179
- }
180
- else {
181
- // DE/IT/NL: street-number, postcode-city: "Pariser Platz 1, 10117 Berlin".
182
- const pcCity = [pc, loc].filter(Boolean).join(" ");
183
- body = `${street} ${hn}, ${pcCity}`;
184
- }
185
- if (!country) {
186
- // Negative: a normal address, NO country token/component. Teaches that a trailing region/city/
187
- // postcode is NOT a country (counters the v1 golden over-firing).
188
- return { fmt: "negative", raw: body, components };
189
- }
190
- const withC = { ...components, country };
191
- const r = random();
192
- if (r < 0.8)
193
- return { fmt: "full", raw: `${body}, ${country}`, components: withC };
194
- if (r < 0.92)
195
- return { fmt: "full-nl", raw: `${body}\n${country}`, components: withC };
196
- const bareBody = order === "us" || order === "fr" ? `${hn} ${street}, ${loc}` : `${street} ${hn}, ${loc}`;
197
- return {
198
- fmt: "bare",
199
- raw: `${bareBody}, ${country}`,
200
- components: { house_number: hn, street, locality: loc, country },
201
- };
202
- }
203
- const HOMOGRAPHS = [
204
- {
205
- surface: "Georgia",
206
- iso2: "GE",
207
- cities: ["Tbilisi", "Batumi", "Kutaisi", "Rustavi"],
208
- us: { role: "region", locality: "Atlanta", region: "Georgia", postcodes: ["30309", "31401", "30601", "31201"] },
209
- },
210
- {
211
- surface: "Jordan",
212
- iso2: "JO",
213
- cities: ["Amman", "Irbid", "Zarqa", "Aqaba"],
214
- us: { role: "locality", locality: "Jordan", region: "MN", postcodes: ["55352"] },
215
- },
216
- {
217
- surface: "Lebanon",
218
- iso2: "LB",
219
- cities: ["Beirut", "Tripoli", "Sidon", "Byblos"],
220
- us: { role: "locality", locality: "Lebanon", region: "TN", postcodes: ["37087", "03766", "17042", "45036"] },
221
- },
222
- {
223
- surface: "Mexico",
224
- iso2: "MX",
225
- cities: ["Guadalajara", "Monterrey", "Puebla", "Oaxaca"],
226
- us: { role: "locality", locality: "Mexico", region: "MO", postcodes: ["65265"] },
227
- },
228
- {
229
- surface: "Peru",
230
- iso2: "PE",
231
- cities: ["Cusco", "Arequipa", "Trujillo", "Iquitos"],
232
- us: { role: "locality", locality: "Peru", region: "IL", postcodes: ["61354", "46970"] },
233
- },
234
- {
235
- surface: "Turkey",
236
- iso2: "TR",
237
- cities: ["Ankara", "Izmir", "Bursa", "Antalya"],
238
- us: { role: "locality", locality: "Turkey", region: "TX", postcodes: ["79261", "28393"] },
239
- },
240
- ];
241
- const ABBREV_REGIONS = [
242
- { code: "CA", localities: ["Los Angeles", "Sacramento", "San Diego"], postcodes: ["90012", "95814", "92101"] }, // California / Canada
243
- { code: "GA", localities: ["Atlanta", "Savannah", "Macon"], postcodes: ["30309", "31401", "31201"] }, // Georgia(US) / Georgia
244
- { code: "IN", localities: ["Indianapolis", "Fort Wayne"], postcodes: ["46204", "46802"] }, // Indiana / India
245
- { code: "MA", localities: ["Boston", "Worcester"], postcodes: ["02108", "01608"] }, // Massachusetts / Morocco
246
- { code: "PA", localities: ["Philadelphia", "Pittsburgh"], postcodes: ["19103", "15222"] }, // Pennsylvania / Panama
247
- { code: "AL", localities: ["Birmingham", "Montgomery"], postcodes: ["35203", "36104"] }, // Alabama / Albania
248
- ];
249
- const STREET_POOL = [
250
- "Main Street",
251
- "Oak Avenue",
252
- "Park Road",
253
- "Elm Street",
254
- "Hill Road",
255
- "Market Street",
256
- "Church Street",
257
- "King Street",
258
- "2nd Avenue",
259
- "Maple Drive",
260
- ];
261
- const pick = (random, arr) => arr[Math.floor(random() * arr.length)];
262
- const houseNo = (random) => String(1 + Math.floor(random() * 998));
263
- /**
264
- * A homograph CONTRAST row: ~half render the surface as `country` (foreign city), half as the US `region`/`locality`
265
- * (US ZIP, NO country). Returns iso2 for provenance.
266
- */
267
- function renderHomograph(random) {
268
- const h = pick(random, HOMOGRAPHS);
269
- const hn = houseNo(random), street = pick(random, STREET_POOL);
270
- if (random() < 0.5) {
271
- const city = pick(random, h.cities);
272
- const withStreet = random() < 0.6;
273
- const raw = withStreet ? `${hn} ${street}, ${city}, ${h.surface}` : `${city}, ${h.surface}`;
274
- const components = withStreet
275
- ? { house_number: hn, street, locality: city, country: h.surface }
276
- : { locality: city, country: h.surface };
277
- return { fmt: "homograph-country", raw, components, iso2: h.iso2 };
278
- }
279
- const pc = pick(random, h.us.postcodes);
280
- if (h.us.role === "region") {
281
- // surface is the US STATE: "123 Oak Ave, Atlanta, Georgia 30309" → region, no country
282
- return {
283
- fmt: "homograph-us-region",
284
- raw: `${hn} ${street}, ${h.us.locality}, ${h.surface} ${pc}`,
285
- components: { house_number: hn, street, locality: h.us.locality, region: h.surface, postcode: pc },
286
- iso2: "US",
287
- };
288
- }
289
- // surface is the US CITY: "123 Oak Ave, Lebanon, TN 37087" → locality, no country
290
- return {
291
- fmt: "homograph-us-locality",
292
- raw: `${hn} ${street}, ${h.surface}, ${h.us.region} ${pc}`,
293
- components: { house_number: hn, street, locality: h.surface, region: h.us.region, postcode: pc },
294
- iso2: "US",
295
- };
296
- }
297
- /**
298
- * An abbrev-as-region negative: "123 Main St, Los Angeles, CA 90012" → region CA, NO country.
299
- */
300
- function renderAbbrevRegion(random) {
301
- const a = pick(random, ABBREV_REGIONS);
302
- const hn = houseNo(random), street = pick(random, STREET_POOL), locality = pick(random, a.localities), postcode = pick(random, a.postcodes);
303
- return {
304
- fmt: "abbrev-region",
305
- raw: `${hn} ${street}, ${locality}, ${a.code} ${postcode}`,
306
- components: { house_number: hn, street, locality, region: a.code, postcode },
307
- iso2: "US",
308
- };
309
- }
310
- /**
311
- * Share of rows that are homograph contrast pairs.
312
- */
313
- const HOMOGRAPH_FRAC = 0.22;
314
- /**
315
- * Share that are code-as-region negatives (cumulative with HOMOGRAPH_FRAC)
316
- */
317
- const ABBREV_FRAC = 0.08;
318
- /**
319
- * Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
320
- * and `description` below for the surface form it generates.
321
- */
322
- export const countryBalancedRecipe = {
323
- name: "country-balanced",
324
- description: "Balanced model-first country rows (#464): OA skeletons + ISO surface forms + homograph contrast pairs",
325
- mode: "generate",
326
- options: [{ flag: "--golden", description: "Emit the held-out VT+Berlin eval slice" }],
327
- async run(opts, write) {
328
- if (opts.count == null)
329
- throw new Error("country-balanced recipe requires --count <N>");
330
- const count = opts.count;
331
- // Legacy build-country-shard-balanced.mjs seeded mulberry32 with the raw seed: `const random = mulberry32(opts.seed)`.
332
- const random = makeMulberry32(opts.seed);
333
- const source = opts.sourceName ?? "synth-country";
334
- const sources = opts.golden ? EVAL_SOURCES : SOURCES;
335
- const perSource = Math.ceil((count * 3) / sources.length); // over-read; balance locales
336
- const pool = [];
337
- for (const s of sources) {
338
- const t = await readTuples(s, perSource);
339
- console.error(` ${s.csv} (${s.iso2}): ${t.length} tuples`);
340
- for (const x of t) {
341
- pool.push(x);
342
- }
343
- }
344
- if (!pool.length) {
345
- throw new Error(`No tuples — are the cached OA zips present in ${dataRootPath("oa-cache")}?`);
346
- }
347
- let emitted = 0;
348
- let skipped = 0;
349
- let guard = 0;
350
- const N = pool.length;
351
- while (emitted < count && guard++ < count * 8) {
352
- // Mix three row types: homograph contrast (the distinction), code-as-region negatives, and the
353
- // breadth/recall main path (random ISO form on an OA skeleton, ~30% country-absent).
354
- const roll = random();
355
- let rendered;
356
- let rowISO2;
357
- if (roll < HOMOGRAPH_FRAC) {
358
- const h = renderHomograph(random);
359
- rendered = h;
360
- rowISO2 = h.iso2;
361
- }
362
- else if (roll < HOMOGRAPH_FRAC + ABBREV_FRAC) {
363
- const a = renderAbbrevRegion(random);
364
- rendered = a;
365
- rowISO2 = a.iso2;
366
- }
367
- else {
368
- const t = pool[Math.floor(random() * N)];
369
- const country = pickCountry(random); // may be null → a country-absent negative row
370
- rendered = renderCountry(random, t, country);
371
- rowISO2 = t.iso2;
372
- if (country && !rendered.raw.includes(country)) {
373
- skipped++;
374
- continue;
375
- }
376
- }
377
- const { raw, components } = rendered;
378
- const localeTag = rowISO2 === "US" ? "en-US" : `${rowISO2.toLowerCase()}-${rowISO2}`;
379
- if (opts.golden) {
380
- write(JSON.stringify({ raw, components, country: rowISO2 }) + "\n");
381
- emitted++;
382
- continue;
383
- }
384
- const canonical = {
385
- raw,
386
- components,
387
- country: rowISO2,
388
- locale: localeTag,
389
- source,
390
- source_id: stableSourceID(source, components),
391
- corpus_version: "0.4.0",
392
- license: "OpenAddresses multi-locale skeletons + injected ISO-3166 country surface forms (codex)",
393
- };
394
- const aligned = alignRow(canonical);
395
- if (aligned.kind !== "labeled" || !aligned.row) {
396
- skipped++;
397
- continue;
398
- }
399
- write(JSON.stringify({ ...aligned.row, synth_method: "country", synth_base_id: null }) + "\n");
400
- emitted++;
401
- }
402
- return { emitted, skipped };
403
- },
404
- };
405
- //# sourceMappingURL=country-balanced.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"country-balanced.js","sourceRoot":"","sources":["../../../src/shard-recipes/country-balanced.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;GAwBG;AAEH,OAAO,EAAE,qBAAqB,EAAE,YAAY,EAAE,MAAM,0BAA0B,CAAA;AAE9E,OAAO,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAA;AACpD,OAAO,EAAE,cAAc,EAAE,MAAM,kCAAkC,CAAA;AAEjE,OAAO,EAAE,QAAQ,EAAE,MAAM,yBAAyB,CAAA;AAElD,OAAO,EAAE,cAAc,EAAE,oBAAoB,EAAoB,MAAM,eAAe,CAAA;AAEtF,oGAAoG;AACpG,sGAAsG;AACtG,oEAAoE;AACpE;;;;yCAIyC;AAEzC,MAAM,iBAAiB,GAAG,CAAC,GAAG,EAAE;IAC/B,MAAM,OAAO,GAAG,MAAM,CAAC,MAAM,CAAC,qBAAqB,CAAC,CAAC,IAAI,EAAE,CAAA,CAAC,2CAA2C;IACvG,MAAM,KAAK,GAAG,CAAC,GAAG,YAAY,CAAC,CAAA;IAE/B,iDAAiD;IACjD,OAAO,EAAE,OAAO,EAAE,KAAK,EAAE,CAAA;AAC1B,CAAC,CAAC,EAAE,CAAA;AAEJ;;GAEG;AACH,MAAM,mBAAmB,GAAG,GAAG,CAAA;AAa/B;;;GAGG;AACH,MAAM,OAAO,GAA6B;IACzC;QACC,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,uBAAuB,CAAC;QACtD,GAAG,EAAE,qBAAqB;QAC1B,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,IAAI;QACZ,KAAK,EAAE,IAAI;KACX;IACD,EAAE,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,kBAAkB,CAAC,EAAE,GAAG,EAAE,gBAAgB,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,KAAK,EAAE,IAAI,EAAE;IACnH;QACC,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,uBAAuB,CAAC;QACtD,GAAG,EAAE,qBAAqB;QAC1B,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,IAAI;QACZ,KAAK,EAAE,IAAI;KACX;IACD;QACC,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,uBAAuB,CAAC;QACtD,GAAG,EAAE,qBAAqB;QAC1B,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,IAAI;QACZ,KAAK,EAAE,IAAI;KACX;IACD;QACC,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,uBAAuB,CAAC;QACtD,GAAG,EAAE,qBAAqB;QAC1B,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,EAAE;QACV,KAAK,EAAE,IAAI;KACX;IACD;QACC,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,qBAAqB,CAAC;QACpD,GAAG,EAAE,oBAAoB;QACzB,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,EAAE;QACV,KAAK,EAAE,IAAI;KACX;IACD,qGAAqG;IACrG,6DAA6D;IAC7D;QACC,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,qBAAqB,CAAC;QACpD,GAAG,EAAE,oBAAoB;QACzB,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,EAAE;QACV,KAAK,EAAE,IAAI;KACX;IACD;QACC,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,qBAAqB,CAAC;QACpD,GAAG,EAAE,oBAAoB;QACzB,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,EAAE;QACV,KAAK,EAAE,IAAI;KACX;CACD,CAAA;AAED;;GAEG;AACH,MAAM,YAAY,GAA6B;IAC9C;QACC,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,uBAAuB,CAAC;QACtD,GAAG,EAAE,qBAAqB;QAC1B,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,IAAI;QACZ,KAAK,EAAE,IAAI;KACX;IACD,EAAE,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,gBAAgB,CAAC,EAAE,GAAG,EAAE,eAAe,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE;CAC9G,CAAA;AAeD;;;GAGG;AACH,KAAK,UAAU,UAAU,CAAC,MAAqB,EAAE,KAAa;IAC7D,MAAM,MAAM,GAAmB,EAAE,CAAA;IACjC,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAA;IAE9B,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,oBAAoB,CAAC,MAAM,CAAC,GAAG,EAAE,MAAM,CAAC,GAAG,CAAC,EAAE,CAAC;QACtE,IAAI,MAAM,CAAC,MAAM,IAAI,KAAK;YAAE,MAAK;QAEjC,MAAM,MAAM,GAAG,GAAG,CAAC,MAAM,IAAI,EAAE,EAC9B,QAAQ,GAAG,GAAG,CAAC,IAAI,IAAI,EAAE,EACzB,YAAY,GAAG,GAAG,CAAC,MAAM,IAAI,EAAE,CAAA;QAEhC,IAAI,CAAC,MAAM,IAAI,CAAC,QAAQ,IAAI,CAAC,YAAY;YAAE,SAAQ;QACnD,MAAM,GAAG,GAAG,GAAG,YAAY,IAAI,MAAM,IAAI,QAAQ,EAAE,CAAC,WAAW,EAAE,CAAA;QAEjE,IAAI,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC;YAAE,SAAQ;QAC3B,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;QAEb,MAAM,CAAC,IAAI,CAAC;YACX,YAAY;YACZ,MAAM;YACN,QAAQ;YACR,MAAM,EAAE,GAAG,CAAC,MAAM,IAAI,MAAM,CAAC,MAAM;YACnC,QAAQ,EAAE,GAAG,CAAC,QAAQ,IAAI,EAAE;YAC5B,IAAI,EAAE,MAAM,CAAC,IAAI;YACjB,KAAK,EAAE,MAAM,CAAC,KAAK;SACnB,CAAC,CAAA;IACH,CAAC;IAED,OAAO,MAAM,CAAA;AACd,CAAC;AAED;;GAEG;AACH,SAAS,WAAW,CAAC,MAAoB;IACxC,IAAI,MAAM,EAAE,GAAG,mBAAmB;QAAE,OAAO,IAAI,CAAA,CAAC,wDAAwD;IACxG,gGAAgG;IAChG,MAAM,IAAI,GAAG,MAAM,EAAE,GAAG,GAAG,CAAC,CAAC,CAAC,iBAAiB,CAAC,OAAO,CAAC,CAAC,CAAC,iBAAiB,CAAC,KAAK,CAAA;IAEjF,OAAO,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,IAAI,CAAC,MAAM,CAAC,CAAE,CAAA;AACjD,CAAC;AAED;;GAEG;AACH,SAAS,aAAa,CACrB,MAAoB,EACpB,CAAe,EACf,OAAsB;IAEtB,MAAM,EAAE,YAAY,EAAE,EAAE,EAAE,MAAM,EAAE,QAAQ,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE,QAAQ,EAAE,EAAE,EAAE,KAAK,EAAE,GAAG,CAAC,CAAA;IACvF,MAAM,UAAU,GAA0C,EAAE,YAAY,EAAE,EAAE,EAAE,MAAM,EAAE,QAAQ,EAAE,GAAG,EAAE,CAAA;IAErG,IAAI,GAAG,EAAE,CAAC;QACT,UAAU,CAAC,MAAM,GAAG,GAAG,CAAA;IACxB,CAAC;IAED,IAAI,EAAE,EAAE,CAAC;QACR,UAAU,CAAC,QAAQ,GAAG,EAAE,CAAA;IACzB,CAAC;IAED,IAAI,IAAY,CAAA;IAEhB,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;QACpB,MAAM,KAAK,GAAG,CAAC,GAAG,EAAE,EAAE,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;QACjD,IAAI,GAAG,GAAG,EAAE,IAAI,MAAM,KAAK,GAAG,GAAG,KAAK,CAAC,CAAC,CAAC,IAAI,GAAG,KAAK,CAAC,CAAC,CAAC,EAAE,EAAE,CAAA;IAC7D,CAAC;SAAM,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;QAC3B,kFAAkF;QAClF,IAAI,GAAG,GAAG,EAAE,IAAI,MAAM,KAAK,CAAC,EAAE,EAAE,GAAG,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,CAAA;IACjE,CAAC;SAAM,CAAC;QACP,2EAA2E;QAC3E,MAAM,MAAM,GAAG,CAAC,EAAE,EAAE,GAAG,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;QAClD,IAAI,GAAG,GAAG,MAAM,IAAI,EAAE,KAAK,MAAM,EAAE,CAAA;IACpC,CAAC;IAED,IAAI,CAAC,OAAO,EAAE,CAAC;QACd,+FAA+F;QAC/F,kEAAkE;QAClE,OAAO,EAAE,GAAG,EAAE,UAAU,EAAE,GAAG,EAAE,IAAI,EAAE,UAAU,EAAE,CAAA;IAClD,CAAC;IAED,MAAM,KAAK,GAA0C,EAAE,GAAG,UAAU,EAAE,OAAO,EAAE,CAAA;IAC/E,MAAM,CAAC,GAAG,MAAM,EAAE,CAAA;IAElB,IAAI,CAAC,GAAG,GAAG;QAAE,OAAO,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE,GAAG,IAAI,KAAK,OAAO,EAAE,EAAE,UAAU,EAAE,KAAK,EAAE,CAAA;IAElF,IAAI,CAAC,GAAG,IAAI;QAAE,OAAO,EAAE,GAAG,EAAE,SAAS,EAAE,GAAG,EAAE,GAAG,IAAI,KAAK,OAAO,EAAE,EAAE,UAAU,EAAE,KAAK,EAAE,CAAA;IACtF,MAAM,QAAQ,GAAG,KAAK,KAAK,IAAI,IAAI,KAAK,KAAK,IAAI,CAAC,CAAC,CAAC,GAAG,EAAE,IAAI,MAAM,KAAK,GAAG,EAAE,CAAC,CAAC,CAAC,GAAG,MAAM,IAAI,EAAE,KAAK,GAAG,EAAE,CAAA;IAEzG,OAAO;QACN,GAAG,EAAE,MAAM;QACX,GAAG,EAAE,GAAG,QAAQ,KAAK,OAAO,EAAE;QAC9B,UAAU,EAAE,EAAE,YAAY,EAAE,EAAE,EAAE,MAAM,EAAE,QAAQ,EAAE,GAAG,EAAE,OAAO,EAAE;KAChE,CAAA;AACF,CAAC;AAaD,MAAM,UAAU,GAAyB;IACxC;QACC,OAAO,EAAE,SAAS;QAClB,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,CAAC,SAAS,EAAE,QAAQ,EAAE,SAAS,EAAE,SAAS,CAAC;QACnD,EAAE,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,QAAQ,EAAE,SAAS,EAAE,MAAM,EAAE,SAAS,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC,EAAE;KAC/G;IACD;QACC,OAAO,EAAE,QAAQ;QACjB,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC;QAC5C,EAAE,EAAE,EAAE,IAAI,EAAE,UAAU,EAAE,QAAQ,EAAE,QAAQ,EAAE,MAAM,EAAE,IAAI,EAAE,SAAS,EAAE,CAAC,OAAO,CAAC,EAAE;KAChF;IACD;QACC,OAAO,EAAE,SAAS;QAClB,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,CAAC,QAAQ,EAAE,SAAS,EAAE,OAAO,EAAE,QAAQ,CAAC;QAChD,EAAE,EAAE,EAAE,IAAI,EAAE,UAAU,EAAE,QAAQ,EAAE,SAAS,EAAE,MAAM,EAAE,IAAI,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC,EAAE;KAC5G;IACD;QACC,OAAO,EAAE,QAAQ;QACjB,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,CAAC,aAAa,EAAE,WAAW,EAAE,QAAQ,EAAE,QAAQ,CAAC;QACxD,EAAE,EAAE,EAAE,IAAI,EAAE,UAAU,EAAE,QAAQ,EAAE,QAAQ,EAAE,MAAM,EAAE,IAAI,EAAE,SAAS,EAAE,CAAC,OAAO,CAAC,EAAE;KAChF;IACD;QACC,OAAO,EAAE,MAAM;QACf,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,CAAC,OAAO,EAAE,UAAU,EAAE,UAAU,EAAE,SAAS,CAAC;QACpD,EAAE,EAAE,EAAE,IAAI,EAAE,UAAU,EAAE,QAAQ,EAAE,MAAM,EAAE,MAAM,EAAE,IAAI,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,CAAC,EAAE;KACvF;IACD;QACC,OAAO,EAAE,QAAQ;QACjB,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,CAAC,QAAQ,EAAE,OAAO,EAAE,OAAO,EAAE,SAAS,CAAC;QAC/C,EAAE,EAAE,EAAE,IAAI,EAAE,UAAU,EAAE,QAAQ,EAAE,QAAQ,EAAE,MAAM,EAAE,IAAI,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,CAAC,EAAE;KACzF;CACD,CAAA;AASD,MAAM,cAAc,GAA4B;IAC/C,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE,CAAC,aAAa,EAAE,YAAY,EAAE,WAAW,CAAC,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC,EAAE,EAAE,sBAAsB;IACtI,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE,CAAC,SAAS,EAAE,UAAU,EAAE,OAAO,CAAC,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC,EAAE,EAAE,wBAAwB;IAC9H,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE,CAAC,cAAc,EAAE,YAAY,CAAC,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,CAAC,EAAE,EAAE,kBAAkB;IAC7G,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE,CAAC,QAAQ,EAAE,WAAW,CAAC,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,CAAC,EAAE,EAAE,0BAA0B;IAC9G,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE,CAAC,cAAc,EAAE,YAAY,CAAC,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,CAAC,EAAE,EAAE,wBAAwB;IACnH,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE,CAAC,YAAY,EAAE,YAAY,CAAC,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,CAAC,EAAE,EAAE,oBAAoB;CAC7G,CAAA;AAED,MAAM,WAAW,GAAsB;IACtC,aAAa;IACb,YAAY;IACZ,WAAW;IACX,YAAY;IACZ,WAAW;IACX,eAAe;IACf,eAAe;IACf,aAAa;IACb,YAAY;IACZ,aAAa;CACb,CAAA;AAED,MAAM,IAAI,GAAG,CAAI,MAAoB,EAAE,GAAiB,EAAK,EAAE,CAAC,GAAG,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,GAAG,CAAC,MAAM,CAAC,CAAE,CAAA;AACvG,MAAM,OAAO,GAAG,CAAC,MAAoB,EAAU,EAAE,CAAC,MAAM,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,GAAG,CAAC,CAAC,CAAA;AAExF;;;GAGG;AACH,SAAS,eAAe,CAAC,MAAoB;IAM5C,MAAM,CAAC,GAAG,IAAI,CAAC,MAAM,EAAE,UAAU,CAAC,CAAA;IAElC,MAAM,EAAE,GAAG,OAAO,CAAC,MAAM,CAAC,EACzB,MAAM,GAAG,IAAI,CAAC,MAAM,EAAE,WAAW,CAAC,CAAA;IAEnC,IAAI,MAAM,EAAE,GAAG,GAAG,EAAE,CAAC;QACpB,MAAM,IAAI,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC,CAAC,MAAM,CAAC,CAAA;QACnC,MAAM,UAAU,GAAG,MAAM,EAAE,GAAG,GAAG,CAAA;QACjC,MAAM,GAAG,GAAG,UAAU,CAAC,CAAC,CAAC,GAAG,EAAE,IAAI,MAAM,KAAK,IAAI,KAAK,CAAC,CAAC,OAAO,EAAE,CAAC,CAAC,CAAC,GAAG,IAAI,KAAK,CAAC,CAAC,OAAO,EAAE,CAAA;QAE3F,MAAM,UAAU,GAA0C,UAAU;YACnE,CAAC,CAAC,EAAE,YAAY,EAAE,EAAE,EAAE,MAAM,EAAE,QAAQ,EAAE,IAAI,EAAE,OAAO,EAAE,CAAC,CAAC,OAAO,EAAE;YAClE,CAAC,CAAC,EAAE,QAAQ,EAAE,IAAI,EAAE,OAAO,EAAE,CAAC,CAAC,OAAO,EAAE,CAAA;QAEzC,OAAO,EAAE,GAAG,EAAE,mBAAmB,EAAE,GAAG,EAAE,UAAU,EAAE,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;IACnE,CAAC;IAED,MAAM,EAAE,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC,CAAC,EAAE,CAAC,SAAS,CAAC,CAAA;IAEvC,IAAI,CAAC,CAAC,EAAE,CAAC,IAAI,KAAK,QAAQ,EAAE,CAAC;QAC5B,sFAAsF;QACtF,OAAO;YACN,GAAG,EAAE,qBAAqB;YAC1B,GAAG,EAAE,GAAG,EAAE,IAAI,MAAM,KAAK,CAAC,CAAC,EAAE,CAAC,QAAQ,KAAK,CAAC,CAAC,OAAO,IAAI,EAAE,EAAE;YAC5D,UAAU,EAAE,EAAE,YAAY,EAAE,EAAE,EAAE,MAAM,EAAE,QAAQ,EAAE,CAAC,CAAC,EAAE,CAAC,QAAQ,EAAE,MAAM,EAAE,CAAC,CAAC,OAAO,EAAE,QAAQ,EAAE,EAAE,EAAE;YAClG,IAAI,EAAE,IAAI;SACV,CAAA;IACF,CAAC;IAED,kFAAkF;IAClF,OAAO;QACN,GAAG,EAAE,uBAAuB;QAC5B,GAAG,EAAE,GAAG,EAAE,IAAI,MAAM,KAAK,CAAC,CAAC,OAAO,KAAK,CAAC,CAAC,EAAE,CAAC,MAAM,IAAI,EAAE,EAAE;QAC1D,UAAU,EAAE,EAAE,YAAY,EAAE,EAAE,EAAE,MAAM,EAAE,QAAQ,EAAE,CAAC,CAAC,OAAO,EAAE,MAAM,EAAE,CAAC,CAAC,EAAE,CAAC,MAAM,EAAE,QAAQ,EAAE,EAAE,EAAE;QAChG,IAAI,EAAE,IAAI;KACV,CAAA;AACF,CAAC;AAED;;GAEG;AACH,SAAS,kBAAkB,CAAC,MAAoB;IAM/C,MAAM,CAAC,GAAG,IAAI,CAAC,MAAM,EAAE,cAAc,CAAC,CAAA;IAEtC,MAAM,EAAE,GAAG,OAAO,CAAC,MAAM,CAAC,EACzB,MAAM,GAAG,IAAI,CAAC,MAAM,EAAE,WAAW,CAAC,EAClC,QAAQ,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC,CAAC,UAAU,CAAC,EACrC,QAAQ,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC,CAAC,SAAS,CAAC,CAAA;IAErC,OAAO;QACN,GAAG,EAAE,eAAe;QACpB,GAAG,EAAE,GAAG,EAAE,IAAI,MAAM,KAAK,QAAQ,KAAK,CAAC,CAAC,IAAI,IAAI,QAAQ,EAAE;QAC1D,UAAU,EAAE,EAAE,YAAY,EAAE,EAAE,EAAE,MAAM,EAAE,QAAQ,EAAE,MAAM,EAAE,CAAC,CAAC,IAAI,EAAE,QAAQ,EAAE;QAC5E,IAAI,EAAE,IAAI;KACV,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,cAAc,GAAG,IAAI,CAAA;AAC3B;;GAEG;AACH,MAAM,WAAW,GAAG,IAAI,CAAA;AAExB;;;GAGG;AACH,MAAM,CAAC,MAAM,qBAAqB,GAAgB;IACjD,IAAI,EAAE,kBAAkB;IACxB,WAAW,EAAE,uGAAuG;IACpH,IAAI,EAAE,UAAU;IAChB,OAAO,EAAE,CAAC,EAAE,IAAI,EAAE,UAAU,EAAE,WAAW,EAAE,wCAAwC,EAAE,CAAC;IACtF,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,IAAI,IAAI,CAAC,KAAK,IAAI,IAAI;YAAE,MAAM,IAAI,KAAK,CAAC,8CAA8C,CAAC,CAAA;QACvF,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAA;QACxB,uHAAuH;QACvH,MAAM,MAAM,GAAG,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACxC,MAAM,MAAM,GAAG,IAAI,CAAC,UAAU,IAAI,eAAe,CAAA;QACjD,MAAM,OAAO,GAAG,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,OAAO,CAAA;QACpD,MAAM,SAAS,GAAG,IAAI,CAAC,IAAI,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,GAAG,OAAO,CAAC,MAAM,CAAC,CAAA,CAAC,6BAA6B;QAEvF,MAAM,IAAI,GAAmB,EAAE,CAAA;QAE/B,KAAK,MAAM,CAAC,IAAI,OAAO,EAAE,CAAC;YACzB,MAAM,CAAC,GAAG,MAAM,UAAU,CAAC,CAAC,EAAE,SAAS,CAAC,CAAA;YAExC,OAAO,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,GAAG,KAAK,CAAC,CAAC,IAAI,MAAM,CAAC,CAAC,MAAM,SAAS,CAAC,CAAA;YAE3D,KAAK,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC;gBACnB,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;YACb,CAAC;QACF,CAAC;QAED,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,CAAC;YAClB,MAAM,IAAI,KAAK,CAAC,iDAAiD,YAAY,CAAC,UAAU,CAAC,GAAG,CAAC,CAAA;QAC9F,CAAC;QAED,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,KAAK,GAAG,CAAC,CAAA;QACb,MAAM,CAAC,GAAG,IAAI,CAAC,MAAM,CAAA;QAErB,OAAO,OAAO,GAAG,KAAK,IAAI,KAAK,EAAE,GAAG,KAAK,GAAG,CAAC,EAAE,CAAC;YAC/C,+FAA+F;YAC/F,qFAAqF;YACrF,MAAM,IAAI,GAAG,MAAM,EAAE,CAAA;YACrB,IAAI,QAAyF,CAAA;YAC7F,IAAI,OAAe,CAAA;YAEnB,IAAI,IAAI,GAAG,cAAc,EAAE,CAAC;gBAC3B,MAAM,CAAC,GAAG,eAAe,CAAC,MAAM,CAAC,CAAA;gBACjC,QAAQ,GAAG,CAAC,CAAA;gBACZ,OAAO,GAAG,CAAC,CAAC,IAAI,CAAA;YACjB,CAAC;iBAAM,IAAI,IAAI,GAAG,cAAc,GAAG,WAAW,EAAE,CAAC;gBAChD,MAAM,CAAC,GAAG,kBAAkB,CAAC,MAAM,CAAC,CAAA;gBACpC,QAAQ,GAAG,CAAC,CAAA;gBACZ,OAAO,GAAG,CAAC,CAAC,IAAI,CAAA;YACjB,CAAC;iBAAM,CAAC;gBACP,MAAM,CAAC,GAAG,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,CAAE,CAAA;gBACzC,MAAM,OAAO,GAAG,WAAW,CAAC,MAAM,CAAC,CAAA,CAAC,8CAA8C;gBAClF,QAAQ,GAAG,aAAa,CAAC,MAAM,EAAE,CAAC,EAAE,OAAO,CAAC,CAAA;gBAC5C,OAAO,GAAG,CAAC,CAAC,IAAI,CAAA;gBAEhB,IAAI,OAAO,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,QAAQ,CAAC,OAAO,CAAC,EAAE,CAAC;oBAChD,OAAO,EAAE,CAAA;oBAET,SAAQ;gBACT,CAAC;YACF,CAAC;YAED,MAAM,EAAE,GAAG,EAAE,UAAU,EAAE,GAAG,QAAQ,CAAA;YACpC,MAAM,SAAS,GAAG,OAAO,KAAK,IAAI,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,GAAG,OAAO,CAAC,WAAW,EAAE,IAAI,OAAO,EAAE,CAAA;YAEpF,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC;gBACjB,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,GAAG,EAAE,UAAU,EAAE,OAAO,EAAE,OAAO,EAAE,CAAC,GAAG,IAAI,CAAC,CAAA;gBAEnE,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,MAAM,SAAS,GAAiB;gBAC/B,GAAG;gBACH,UAAU;gBACV,OAAO,EAAE,OAAO;gBAChB,MAAM,EAAE,SAAS;gBACjB,MAAM;gBACN,SAAS,EAAE,cAAc,CAAC,MAAM,EAAE,UAAU,CAAC;gBAC7C,cAAc,EAAE,OAAO;gBACvB,OAAO,EAAE,wFAAwF;aACjG,CAAA;YAED,MAAM,OAAO,GAAG,QAAQ,CAAC,SAAS,CAAC,CAAA;YAEnC,IAAI,OAAO,CAAC,IAAI,KAAK,SAAS,IAAI,CAAC,OAAO,CAAC,GAAG,EAAE,CAAC;gBAChD,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,GAAG,OAAO,CAAC,GAAG,EAAE,YAAY,EAAE,SAAS,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,GAAG,IAAI,CAAC,CAAA;YAE9F,OAAO,EAAE,CAAA;QACV,CAAC;QAED,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;IAC5B,CAAC;CACD,CAAA"}
@@ -1,22 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * `cz-pcfirst-preposition` — the Czech pc-first prepositional-locality shard, fourth orthography
7
- * of the #901 leading-name-boundary family. The #897 close-out read all 8 residual CZ rows as one
8
- * class: a LEADING postcode mis-assigned as house_number while the multi-word "nad/pod/u X"
9
- * locality shatters ("51244 Rokytnice nad Jizerou, Dolní Rokytnice 111" → street
10
- * 'RokytnicenadJizerou' + house_number '51244'). That leading-5-digit confusion is the
11
- * anchor-pollution class whose decode-time OVERRIDE was correctly killed in #723 — this shard is
12
- * the model-first fix as DATA: real prepositional localities in the order that breaks, so the
13
- * model learns that a leading postcode before a multi-word name is a postcode. pc-first leads the
14
- * cycle (the lesson); canonical and city-first keep the polarity balanced (the v1.9.9 lesson).
15
- */
16
- import { type ShardRecipe } from "./scaffold.ts";
17
- /**
18
- * Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
19
- * and `description` below for the surface form it generates.
20
- */
21
- export declare const czPcFirstPrepositionRecipe: ShardRecipe;
22
- //# sourceMappingURL=cz-pcfirst-preposition.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"cz-pcfirst-preposition.d.ts","sourceRoot":"","sources":["../../../src/shard-recipes/cz-pcfirst-preposition.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;GAcG;AAEH,OAAO,EAA6C,KAAK,WAAW,EAAiB,MAAM,eAAe,CAAA;AAE1G;;;GAGG;AACH,eAAO,MAAM,0BAA0B,EAAE,WAqExC,CAAA"}
@@ -1,82 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * `cz-pcfirst-preposition` — the Czech pc-first prepositional-locality shard, fourth orthography
7
- * of the #901 leading-name-boundary family. The #897 close-out read all 8 residual CZ rows as one
8
- * class: a LEADING postcode mis-assigned as house_number while the multi-word "nad/pod/u X"
9
- * locality shatters ("51244 Rokytnice nad Jizerou, Dolní Rokytnice 111" → street
10
- * 'RokytnicenadJizerou' + house_number '51244'). That leading-5-digit confusion is the
11
- * anchor-pollution class whose decode-time OVERRIDE was correctly killed in #723 — this shard is
12
- * the model-first fix as DATA: real prepositional localities in the order that breaks, so the
13
- * model learns that a leading postcode before a multi-word name is a postcode. pc-first leads the
14
- * cycle (the lesson); canonical and city-first keep the polarity balanced (the v1.9.9 lesson).
15
- */
16
- import { alignAndWrite, makeMulberry32, readTuples, shardSourceID } from "./scaffold.js";
17
- /**
18
- * Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
19
- * and `description` below for the surface form it generates.
20
- */
21
- export const czPcFirstPrepositionRecipe = {
22
- name: "cz-pcfirst-preposition",
23
- description: "CZ pc-first + prepositional locality (#901 family): '«pc» «city nad X», «st» «n»' — the #723 class as data",
24
- mode: "tuples",
25
- async run(opts, write) {
26
- makeMulberry32(opts.seed);
27
- let read = 0;
28
- let emitted = 0;
29
- let skipped = 0;
30
- for await (const t of readTuples(opts.input)) {
31
- read++;
32
- const street = String(t.street ?? "").trim();
33
- const city = String(t.locality ?? "").trim();
34
- const number = String(t.number ?? "").trim();
35
- const postcode = String(t.postcode ?? "").trim();
36
- if (!street || !city || !number || !postcode) {
37
- skipped++;
38
- continue;
39
- }
40
- const order = read % 3;
41
- let raw;
42
- const components = {
43
- street,
44
- house_number: number,
45
- postcode,
46
- locality: city,
47
- };
48
- if (order === 0) {
49
- raw = `${postcode} ${city}, ${street} ${number}`;
50
- }
51
- else if (order === 1) {
52
- raw = `${street} ${number}, ${postcode} ${city}`;
53
- }
54
- else {
55
- raw = `${city}, ${postcode}, ${street} ${number}`;
56
- }
57
- const source_id = shardSourceID("synth-cz-pcfirst-preposition", {
58
- ...components,
59
- o: String(order),
60
- v: String(read),
61
- });
62
- const canonical = {
63
- raw,
64
- components,
65
- country: "CZ",
66
- locale: "cs-CZ",
67
- source: "synth-cz-pcfirst-preposition",
68
- source_id,
69
- corpus_version: "0.10.0",
70
- license: "Synthetic — cz-pcfirst-preposition; (street, number, postcode, city) from OpenAddresses CZ (per-source attribution in the model card)",
71
- };
72
- if (alignAndWrite(write, canonical, "cz-pcfirst-preposition")) {
73
- emitted++;
74
- }
75
- else {
76
- skipped++;
77
- }
78
- }
79
- return { read, emitted, skipped };
80
- },
81
- };
82
- //# sourceMappingURL=cz-pcfirst-preposition.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"cz-pcfirst-preposition.js","sourceRoot":"","sources":["../../../src/shard-recipes/cz-pcfirst-preposition.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;GAcG;AAEH,OAAO,EAAE,aAAa,EAAE,cAAc,EAAE,UAAU,EAAoB,aAAa,EAAE,MAAM,eAAe,CAAA;AAE1G;;;GAGG;AACH,MAAM,CAAC,MAAM,0BAA0B,GAAgB;IACtD,IAAI,EAAE,wBAAwB;IAC9B,WAAW,EACV,4GAA4G;IAC7G,IAAI,EAAE,QAAQ;IACd,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACzB,IAAI,IAAI,GAAG,CAAC,CAAA;QACZ,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QAEf,IAAI,KAAK,EAAE,MAAM,CAAC,IAAI,UAAU,CAAC,IAAI,CAAC,KAAM,CAAC,EAAE,CAAC;YAC/C,IAAI,EAAE,CAAA;YACN,MAAM,MAAM,GAAG,MAAM,CAAC,CAAC,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAC5C,MAAM,IAAI,GAAG,MAAM,CAAC,CAAC,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAC5C,MAAM,MAAM,GAAG,MAAM,CAAC,CAAC,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAC5C,MAAM,QAAQ,GAAG,MAAM,CAAC,CAAC,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAEhD,IAAI,CAAC,MAAM,IAAI,CAAC,IAAI,IAAI,CAAC,MAAM,IAAI,CAAC,QAAQ,EAAE,CAAC;gBAC9C,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,MAAM,KAAK,GAAG,IAAI,GAAG,CAAC,CAAA;YACtB,IAAI,GAAW,CAAA;YAEf,MAAM,UAAU,GAA2B;gBAC1C,MAAM;gBACN,YAAY,EAAE,MAAM;gBACpB,QAAQ;gBACR,QAAQ,EAAE,IAAI;aACd,CAAA;YAED,IAAI,KAAK,KAAK,CAAC,EAAE,CAAC;gBACjB,GAAG,GAAG,GAAG,QAAQ,IAAI,IAAI,KAAK,MAAM,IAAI,MAAM,EAAE,CAAA;YACjD,CAAC;iBAAM,IAAI,KAAK,KAAK,CAAC,EAAE,CAAC;gBACxB,GAAG,GAAG,GAAG,MAAM,IAAI,MAAM,KAAK,QAAQ,IAAI,IAAI,EAAE,CAAA;YACjD,CAAC;iBAAM,CAAC;gBACP,GAAG,GAAG,GAAG,IAAI,KAAK,QAAQ,KAAK,MAAM,IAAI,MAAM,EAAE,CAAA;YAClD,CAAC;YAED,MAAM,SAAS,GAAG,aAAa,CAAC,8BAA8B,EAAE;gBAC/D,GAAG,UAAU;gBACb,CAAC,EAAE,MAAM,CAAC,KAAK,CAAC;gBAChB,CAAC,EAAE,MAAM,CAAC,IAAI,CAAC;aACf,CAAC,CAAA;YAEF,MAAM,SAAS,GAAG;gBACjB,GAAG;gBACH,UAAU;gBACV,OAAO,EAAE,IAAI;gBACb,MAAM,EAAE,OAAO;gBACf,MAAM,EAAE,8BAA8B;gBACtC,SAAS;gBACT,cAAc,EAAE,QAAQ;gBACxB,OAAO,EACN,uIAAuI;aACxI,CAAA;YAED,IAAI,aAAa,CAAC,KAAK,EAAE,SAAS,EAAE,wBAAwB,CAAC,EAAE,CAAC;gBAC/D,OAAO,EAAE,CAAA;YACV,CAAC;iBAAM,CAAC;gBACP,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;QAED,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;IAClC,CAAC;CACD,CAAA"}
@@ -1,38 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * `fr-admin-split` shard recipe — the FR admin-split coverage shard (night 2026-06-19,
7
- * surpass-v1.5.0). Teaches the model to SPLIT the département out of the locality on
8
- * bare/space/comma-delimited French place rows — the admin-deciding failure class the pre-GPU
9
- * self-validation proved moves the resolved coordinate (collision communes −61%; see
10
- * docs/articles/evals/experiments/2026-06-19-fr-admin-split-prevalidation.md). Ported from
11
- * scripts/build-fr-admin-split-shard.mjs.
12
- *
13
- * Failure shapes (the model currently mis-handles all of these):
14
- *
15
- * - `Thauron, Creuse` → région dropped to null (the comma+full-name miss)
16
- * - `Montredon, Lozère` → région = "ère" (the diacritic subword split, #727)
17
- * - (AU analog) `CANBERRA ACT` → the space-delimited admin fuse
18
- *
19
- * The département is the essential admin unit for FR postal geography and maps to the `region`
20
- * component tag in our schema. We derive it DETERMINISTICALLY from the real postcode via codex
21
- * `departementForCodePostal` (first two digits = département) — salvage-first, no re-derived
22
- * table.
23
- *
24
- * Data (`--communes`, opts.communes): REAL BAN (Base Adresse Nationale) commune+postcode+coord
25
- * tuples, one per line, TAB-separated `commune <TAB> postcode <TAB> lon <TAB> lat`. Build the
26
- * input TSV once from the BAN staging CSV (see the legacy script header). Anchor-ON by
27
- * construction: rows carry a REAL postcode token in `raw` + a `postcode` component, so the
28
- * training loader paints the anchor feature onto that span automatically. The trailing-postcode
29
- * anchor REINFORCES the FR split (FR postcode is trailing, unlike German PLZ-leading — the v0.9.2
30
- * scar is positional, not universal).
31
- */
32
- import { type ShardRecipe } from "./scaffold.ts";
33
- /**
34
- * Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
35
- * and `description` below for the surface form it generates.
36
- */
37
- export declare const frAdminSplitRecipe: ShardRecipe;
38
- //# sourceMappingURL=fr-admin-split.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"fr-admin-split.d.ts","sourceRoot":"","sources":["../../../src/shard-recipes/fr-admin-split.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8BG;AASH,OAAO,EAAkB,KAAK,WAAW,EAAE,MAAM,eAAe,CAAA;AAwGhE;;;GAGG;AACH,eAAO,MAAM,kBAAkB,EAAE,WAyFhC,CAAA"}