@mailwoman/corpus 9.2.0 → 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 (1241) hide show
  1. package/README.md +22 -22
  2. package/data/PROVENANCE.md +7 -7
  3. package/lib/adapters/ban/adapter.ts +190 -0
  4. package/lib/adapters/ban/street-decompose.ts +66 -0
  5. package/lib/adapters/fcc-bdc/adapter.ts +174 -0
  6. package/lib/adapters/geonames/adapter.ts +199 -0
  7. package/lib/adapters/geonames-postal/adapter.ts +122 -0
  8. package/lib/adapters/gnaf/adapter.ts +149 -0
  9. package/lib/adapters/gnaf/assemble.ts +225 -0
  10. package/lib/adapters/index.ts +153 -0
  11. package/lib/adapters/openaddresses/adapter.ts +251 -0
  12. package/lib/adapters/overture/adapter.ts +162 -0
  13. package/lib/adapters/state-hi-schools/adapter.ts +170 -0
  14. package/lib/adapters/state-hi-schools/workbook.ts +35 -0
  15. package/lib/adapters/synth-po-box/adapter.ts +204 -0
  16. package/lib/adapters/tiger/adapter.ts +252 -0
  17. package/lib/adapters/tiger/street-decompose.ts +83 -0
  18. package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +167 -0
  19. package/lib/adapters/usgov-imls-pls/adapter.ts +143 -0
  20. package/lib/adapters/usgov-irs-bmf/adapter.ts +151 -0
  21. package/lib/adapters/usgov-nad/adapter.ts +334 -0
  22. package/lib/adapters/usgov-nppes/adapter.ts +151 -0
  23. package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +193 -0
  24. package/lib/adapters/utils/index.ts +307 -0
  25. package/lib/adapters/wof-admin-jp/adapter.ts +214 -0
  26. package/lib/adapters/wof-admin-json/adapter.ts +231 -0
  27. package/lib/adapters/wof-json-rows.ts +129 -0
  28. package/lib/adapters/wof-postalcode-json/adapter.ts +176 -0
  29. package/lib/build.ts +378 -0
  30. package/lib/env.ts +50 -0
  31. package/lib/index.ts +13 -0
  32. package/lib/name-prone-us-suffixes.ts +12 -0
  33. package/lib/recipes/anchor-absorption.ts +101 -0
  34. package/lib/recipes/bare-country.ts +95 -0
  35. package/lib/recipes/boundary-stress.ts +100 -0
  36. package/lib/recipes/cn-organizational-units.ts +199 -0
  37. package/lib/recipes/country-balanced.ts +509 -0
  38. package/lib/recipes/cz-pcfirst-preposition.ts +111 -0
  39. package/lib/recipes/fr-admin-split.ts +242 -0
  40. package/lib/recipes/fr-bare-street.ts +170 -0
  41. package/lib/recipes/fr-fragment.ts +333 -0
  42. package/lib/recipes/fr-lieudit.ts +301 -0
  43. package/lib/recipes/fr-order.ts +245 -0
  44. package/lib/recipes/german.ts +359 -0
  45. package/lib/recipes/house-venue.ts +92 -0
  46. package/lib/recipes/index.ts +97 -0
  47. package/lib/recipes/intersection.ts +618 -0
  48. package/lib/recipes/locale.ts +599 -0
  49. package/lib/recipes/nl-postcode.ts +115 -0
  50. package/lib/recipes/no-fragment.ts +219 -0
  51. package/lib/recipes/no-street-led.ts +141 -0
  52. package/lib/recipes/no-street.ts +90 -0
  53. package/lib/recipes/po-box-cedex.ts +976 -0
  54. package/lib/recipes/po-box.ts +123 -0
  55. package/lib/recipes/reviewed-postcode-tail.ts +190 -0
  56. package/lib/recipes/scaffold.ts +469 -0
  57. package/lib/recipes/si-bare-village.ts +97 -0
  58. package/lib/recipes/street-affix.ts +804 -0
  59. package/lib/recipes/street-bare.ts +100 -0
  60. package/lib/recipes/street.ts +81 -0
  61. package/lib/recipes/sub-venue-sources.ts +877 -0
  62. package/lib/recipes/sub-venue.ts +997 -0
  63. package/lib/recipes/trailing-region.ts +183 -0
  64. package/lib/recipes/unit.ts +304 -0
  65. package/lib/runner.ts +312 -0
  66. package/lib/synthesizers/anchor-absorption.ts +288 -0
  67. package/lib/synthesizers/boundary-stress.ts +532 -0
  68. package/lib/synthesizers/german.ts +260 -0
  69. package/lib/synthesizers/house-venue.ts +308 -0
  70. package/lib/synthesizers/intersection.ts +233 -0
  71. package/lib/synthesizers/no-street.ts +327 -0
  72. package/lib/synthesizers/po-box.ts +323 -0
  73. package/lib/synthesizers/street.ts +269 -0
  74. package/lib/synthesizers/utils.ts +993 -0
  75. package/lib/test-kit/corpus-recipe.ts +86 -0
  76. package/lib/test-kit/index.ts +100 -0
  77. package/lib/tools/align-slice.ts +68 -0
  78. package/lib/tools/audit.ts +403 -0
  79. package/lib/tools/corpus-stats.ts +136 -0
  80. package/lib/tools/fetch/ban.ts +289 -0
  81. package/lib/tools/fetch/download.ts +262 -0
  82. package/lib/tools/fetch/geonames-dump.ts +257 -0
  83. package/lib/tools/fetch/geonames-postal.ts +180 -0
  84. package/lib/tools/fetch/hrsa.ts +59 -0
  85. package/lib/tools/fetch/imls-pls.ts +149 -0
  86. package/lib/tools/fetch/index.ts +147 -0
  87. package/lib/tools/fetch/nad.ts +341 -0
  88. package/lib/tools/fetch/nppes.ts +165 -0
  89. package/lib/tools/fetch/openaddresses.ts +347 -0
  90. package/lib/tools/fetch/ourairports.ts +170 -0
  91. package/lib/tools/fetch/ppd.ts +121 -0
  92. package/lib/tools/fetch/state-hi-schools.ts +161 -0
  93. package/lib/tools/fetch/state-sources.ts +146 -0
  94. package/lib/tools/fetch/tiger-full.ts +308 -0
  95. package/lib/tools/fetch/wikidata-subvenue.ts +384 -0
  96. package/lib/tools/golden-expand.ts +574 -0
  97. package/lib/tools/golden-promote.ts +337 -0
  98. package/lib/tools/golden-relabel-street.ts +683 -0
  99. package/lib/tools/index.ts +28 -0
  100. package/lib/tools/ingest-csv.ts +378 -0
  101. package/lib/tools/jsonl-to-parquet.ts +207 -0
  102. package/lib/tools/lint-slice-vocab.ts +388 -0
  103. package/lib/tools/lint-slice.ts +496 -0
  104. package/lib/tools/overlay-manifest.ts +148 -0
  105. package/lib/tools/overture-subvenue.ts +209 -0
  106. package/lib/tools/postcode-triples.ts +363 -0
  107. package/lib/tools/slice-kryptonite.ts +137 -0
  108. package/lib/tools/slice-translit.ts +218 -0
  109. package/lib/tools/sub-venue/harvest.ts +234 -0
  110. package/lib/tools/sub-venue/head-nouns.ts +245 -0
  111. package/lib/tools/sub-venue/surfaces.ts +95 -0
  112. package/lib/tools/sub-venue/table.ts +281 -0
  113. package/lib/tools/sub-venue/wikidata.ts +85 -0
  114. package/lib/tools/sub-venue-lexicon.ts +429 -0
  115. package/lib/tools/sub-venue-promotions.ts +330 -0
  116. package/lib/types.ts +247 -0
  117. package/lib/utils/align.ts +330 -0
  118. package/lib/utils/golden.ts +189 -0
  119. package/lib/utils/index.ts +14 -0
  120. package/lib/utils/parquet.ts +582 -0
  121. package/lib/utils/slice-stats.ts +95 -0
  122. package/lib/utils/split.ts +279 -0
  123. package/lib/utils/tokenize.ts +120 -0
  124. package/lib/utils/wof-json.ts +247 -0
  125. package/out/adapters/ban/adapter.d.ts.map +1 -0
  126. package/out/adapters/ban/adapter.js +149 -0
  127. package/out/adapters/ban/adapter.js.map +1 -0
  128. package/out/adapters/ban/street-decompose.d.ts.map +1 -0
  129. package/out/adapters/ban/street-decompose.js +51 -0
  130. package/out/adapters/ban/street-decompose.js.map +1 -0
  131. package/out/adapters/fcc-bdc/adapter.d.ts.map +1 -0
  132. package/out/adapters/fcc-bdc/adapter.js +144 -0
  133. package/out/adapters/fcc-bdc/adapter.js.map +1 -0
  134. package/out/adapters/geonames/adapter.d.ts.map +1 -0
  135. package/out/adapters/geonames/adapter.js +176 -0
  136. package/out/adapters/geonames/adapter.js.map +1 -0
  137. package/out/adapters/geonames-postal/adapter.d.ts +54 -0
  138. package/out/adapters/geonames-postal/adapter.d.ts.map +1 -0
  139. package/out/adapters/geonames-postal/adapter.js +107 -0
  140. package/out/adapters/geonames-postal/adapter.js.map +1 -0
  141. package/out/adapters/gnaf/adapter.d.ts +49 -0
  142. package/out/adapters/gnaf/adapter.d.ts.map +1 -0
  143. package/out/adapters/gnaf/adapter.js +124 -0
  144. package/out/adapters/gnaf/adapter.js.map +1 -0
  145. package/out/adapters/gnaf/assemble.d.ts +65 -0
  146. package/out/adapters/gnaf/assemble.d.ts.map +1 -0
  147. package/out/adapters/gnaf/assemble.js +154 -0
  148. package/out/adapters/gnaf/assemble.js.map +1 -0
  149. package/out/adapters/index.d.ts +51 -0
  150. package/out/adapters/index.d.ts.map +1 -0
  151. package/out/adapters/index.js +95 -0
  152. package/out/adapters/index.js.map +1 -0
  153. package/out/adapters/openaddresses/adapter.d.ts.map +1 -0
  154. package/out/adapters/openaddresses/adapter.js +186 -0
  155. package/out/adapters/openaddresses/adapter.js.map +1 -0
  156. package/out/adapters/overture/adapter.d.ts +48 -0
  157. package/out/adapters/overture/adapter.d.ts.map +1 -0
  158. package/out/adapters/overture/adapter.js +125 -0
  159. package/out/adapters/overture/adapter.js.map +1 -0
  160. package/out/adapters/state-hi-schools/adapter.d.ts +46 -0
  161. package/out/adapters/state-hi-schools/adapter.d.ts.map +1 -0
  162. package/out/adapters/state-hi-schools/adapter.js +145 -0
  163. package/out/adapters/state-hi-schools/adapter.js.map +1 -0
  164. package/out/adapters/state-hi-schools/workbook.d.ts +29 -0
  165. package/out/adapters/state-hi-schools/workbook.d.ts.map +1 -0
  166. package/out/adapters/state-hi-schools/workbook.js +20 -0
  167. package/out/adapters/state-hi-schools/workbook.js.map +1 -0
  168. package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
  169. package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
  170. package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
  171. package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
  172. package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
  173. package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
  174. package/out/adapters/synth-po-box/adapter.d.ts.map +1 -0
  175. package/out/adapters/synth-po-box/adapter.js +140 -0
  176. package/out/adapters/synth-po-box/adapter.js.map +1 -0
  177. package/out/adapters/tiger/adapter.d.ts +55 -0
  178. package/out/adapters/tiger/adapter.d.ts.map +1 -0
  179. package/out/adapters/tiger/adapter.js +201 -0
  180. package/out/adapters/tiger/adapter.js.map +1 -0
  181. package/out/adapters/tiger/street-decompose.d.ts.map +1 -0
  182. package/out/adapters/tiger/street-decompose.js +68 -0
  183. package/out/adapters/tiger/street-decompose.js.map +1 -0
  184. package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +56 -0
  185. package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -0
  186. package/out/adapters/usgov-hrsa-fqhc/adapter.js +132 -0
  187. package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -0
  188. package/out/adapters/usgov-imls-pls/adapter.d.ts +36 -0
  189. package/out/adapters/usgov-imls-pls/adapter.d.ts.map +1 -0
  190. package/out/adapters/usgov-imls-pls/adapter.js +114 -0
  191. package/out/adapters/usgov-imls-pls/adapter.js.map +1 -0
  192. package/out/adapters/usgov-irs-bmf/adapter.d.ts +37 -0
  193. package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -0
  194. package/out/adapters/usgov-irs-bmf/adapter.js +120 -0
  195. package/out/adapters/usgov-irs-bmf/adapter.js.map +1 -0
  196. package/out/adapters/usgov-nad/adapter.d.ts +48 -0
  197. package/out/adapters/usgov-nad/adapter.d.ts.map +1 -0
  198. package/out/adapters/usgov-nad/adapter.js +249 -0
  199. package/out/adapters/usgov-nad/adapter.js.map +1 -0
  200. package/out/adapters/usgov-nppes/adapter.d.ts.map +1 -0
  201. package/out/adapters/usgov-nppes/adapter.js +118 -0
  202. package/out/adapters/usgov-nppes/adapter.js.map +1 -0
  203. package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -0
  204. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +154 -0
  205. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -0
  206. package/out/adapters/utils/index.d.ts +191 -0
  207. package/out/adapters/utils/index.d.ts.map +1 -0
  208. package/out/adapters/utils/index.js +206 -0
  209. package/out/adapters/utils/index.js.map +1 -0
  210. package/out/adapters/wof-admin-jp/adapter.d.ts.map +1 -0
  211. package/out/adapters/wof-admin-jp/adapter.js +161 -0
  212. package/out/adapters/wof-admin-jp/adapter.js.map +1 -0
  213. package/out/adapters/wof-admin-json/adapter.d.ts +79 -0
  214. package/out/adapters/wof-admin-json/adapter.d.ts.map +1 -0
  215. package/out/adapters/wof-admin-json/adapter.js +197 -0
  216. package/out/adapters/wof-admin-json/adapter.js.map +1 -0
  217. package/out/adapters/wof-json-rows.d.ts +62 -0
  218. package/out/adapters/wof-json-rows.d.ts.map +1 -0
  219. package/out/adapters/wof-json-rows.js +83 -0
  220. package/out/adapters/wof-json-rows.js.map +1 -0
  221. package/out/adapters/wof-postalcode-json/adapter.d.ts +65 -0
  222. package/out/adapters/wof-postalcode-json/adapter.d.ts.map +1 -0
  223. package/out/adapters/wof-postalcode-json/adapter.js +151 -0
  224. package/out/adapters/wof-postalcode-json/adapter.js.map +1 -0
  225. package/out/build.d.ts +132 -0
  226. package/out/build.d.ts.map +1 -0
  227. package/out/build.js +245 -0
  228. package/out/build.js.map +1 -0
  229. package/out/codex/us-fips-state.d.ts.map +1 -0
  230. package/out/codex/us-fips-state.js.map +1 -0
  231. package/out/env.d.ts +46 -0
  232. package/out/env.d.ts.map +1 -0
  233. package/out/env.js +46 -0
  234. package/out/env.js.map +1 -0
  235. package/out/index.d.ts +13 -0
  236. package/out/index.d.ts.map +1 -0
  237. package/out/index.js +13 -0
  238. package/out/index.js.map +1 -0
  239. package/out/name-prone-us-suffixes.d.ts +12 -0
  240. package/out/name-prone-us-suffixes.d.ts.map +1 -0
  241. package/out/name-prone-us-suffixes.js +12 -0
  242. package/out/name-prone-us-suffixes.js.map +1 -0
  243. package/out/recipes/anchor-absorption.d.ts +20 -0
  244. package/out/recipes/anchor-absorption.d.ts.map +1 -0
  245. package/out/recipes/anchor-absorption.js +81 -0
  246. package/out/recipes/anchor-absorption.js.map +1 -0
  247. package/out/recipes/bare-country.d.ts +25 -0
  248. package/out/recipes/bare-country.d.ts.map +1 -0
  249. package/out/recipes/bare-country.js +87 -0
  250. package/out/recipes/bare-country.js.map +1 -0
  251. package/out/recipes/boundary-stress.d.ts +20 -0
  252. package/out/recipes/boundary-stress.d.ts.map +1 -0
  253. package/out/recipes/boundary-stress.js +83 -0
  254. package/out/recipes/boundary-stress.js.map +1 -0
  255. package/out/recipes/cn-organizational-units.d.ts +36 -0
  256. package/out/recipes/cn-organizational-units.d.ts.map +1 -0
  257. package/out/recipes/cn-organizational-units.js +159 -0
  258. package/out/recipes/cn-organizational-units.js.map +1 -0
  259. package/out/recipes/country-balanced.d.ts +32 -0
  260. package/out/recipes/country-balanced.d.ts.map +1 -0
  261. package/out/recipes/country-balanced.js +393 -0
  262. package/out/recipes/country-balanced.js.map +1 -0
  263. package/out/recipes/cz-pcfirst-preposition.d.ts +22 -0
  264. package/out/recipes/cz-pcfirst-preposition.d.ts.map +1 -0
  265. package/out/recipes/cz-pcfirst-preposition.js +100 -0
  266. package/out/recipes/cz-pcfirst-preposition.js.map +1 -0
  267. package/out/recipes/fr-admin-split.d.ts +38 -0
  268. package/out/recipes/fr-admin-split.d.ts.map +1 -0
  269. package/out/recipes/fr-admin-split.js +192 -0
  270. package/out/recipes/fr-admin-split.js.map +1 -0
  271. package/out/recipes/fr-bare-street.d.ts +28 -0
  272. package/out/recipes/fr-bare-street.d.ts.map +1 -0
  273. package/out/recipes/fr-bare-street.js +143 -0
  274. package/out/recipes/fr-bare-street.js.map +1 -0
  275. package/out/recipes/fr-fragment.d.ts +77 -0
  276. package/out/recipes/fr-fragment.d.ts.map +1 -0
  277. package/out/recipes/fr-fragment.js +276 -0
  278. package/out/recipes/fr-fragment.js.map +1 -0
  279. package/out/recipes/fr-lieudit.d.ts +32 -0
  280. package/out/recipes/fr-lieudit.d.ts.map +1 -0
  281. package/out/recipes/fr-lieudit.js +227 -0
  282. package/out/recipes/fr-lieudit.js.map +1 -0
  283. package/out/recipes/fr-order.d.ts +38 -0
  284. package/out/recipes/fr-order.d.ts.map +1 -0
  285. package/out/recipes/fr-order.js +197 -0
  286. package/out/recipes/fr-order.js.map +1 -0
  287. package/out/recipes/german.d.ts +44 -0
  288. package/out/recipes/german.d.ts.map +1 -0
  289. package/out/recipes/german.js +288 -0
  290. package/out/recipes/german.js.map +1 -0
  291. package/out/recipes/house-venue.d.ts +18 -0
  292. package/out/recipes/house-venue.d.ts.map +1 -0
  293. package/out/recipes/house-venue.js +73 -0
  294. package/out/recipes/house-venue.js.map +1 -0
  295. package/out/recipes/index.d.ts +24 -0
  296. package/out/recipes/index.d.ts.map +1 -0
  297. package/out/recipes/index.js +91 -0
  298. package/out/recipes/index.js.map +1 -0
  299. package/out/recipes/intersection.d.ts +42 -0
  300. package/out/recipes/intersection.d.ts.map +1 -0
  301. package/out/recipes/intersection.js +452 -0
  302. package/out/recipes/intersection.js.map +1 -0
  303. package/out/recipes/locale.d.ts +136 -0
  304. package/out/recipes/locale.d.ts.map +1 -0
  305. package/out/recipes/locale.js +460 -0
  306. package/out/recipes/locale.js.map +1 -0
  307. package/out/recipes/nl-postcode.d.ts +26 -0
  308. package/out/recipes/nl-postcode.d.ts.map +1 -0
  309. package/out/recipes/nl-postcode.js +102 -0
  310. package/out/recipes/nl-postcode.js.map +1 -0
  311. package/out/recipes/no-fragment.d.ts +43 -0
  312. package/out/recipes/no-fragment.d.ts.map +1 -0
  313. package/out/recipes/no-fragment.js +182 -0
  314. package/out/recipes/no-fragment.js.map +1 -0
  315. package/out/recipes/no-street-led.d.ts +24 -0
  316. package/out/recipes/no-street-led.d.ts.map +1 -0
  317. package/out/recipes/no-street-led.js +113 -0
  318. package/out/recipes/no-street-led.js.map +1 -0
  319. package/out/recipes/no-street.d.ts +18 -0
  320. package/out/recipes/no-street.d.ts.map +1 -0
  321. package/out/recipes/no-street.js +71 -0
  322. package/out/recipes/no-street.js.map +1 -0
  323. package/out/recipes/po-box-cedex.d.ts +38 -0
  324. package/out/recipes/po-box-cedex.d.ts.map +1 -0
  325. package/out/recipes/po-box-cedex.js +767 -0
  326. package/out/recipes/po-box-cedex.js.map +1 -0
  327. package/out/recipes/po-box.d.ts +17 -0
  328. package/out/recipes/po-box.d.ts.map +1 -0
  329. package/out/recipes/po-box.js +100 -0
  330. package/out/recipes/po-box.js.map +1 -0
  331. package/out/recipes/reviewed-postcode-tail.d.ts +47 -0
  332. package/out/recipes/reviewed-postcode-tail.d.ts.map +1 -0
  333. package/out/recipes/reviewed-postcode-tail.js +125 -0
  334. package/out/recipes/reviewed-postcode-tail.js.map +1 -0
  335. package/out/recipes/scaffold.d.ts +324 -0
  336. package/out/recipes/scaffold.d.ts.map +1 -0
  337. package/out/recipes/scaffold.js +186 -0
  338. package/out/recipes/scaffold.js.map +1 -0
  339. package/out/recipes/si-bare-village.d.ts +32 -0
  340. package/out/recipes/si-bare-village.d.ts.map +1 -0
  341. package/out/recipes/si-bare-village.js +88 -0
  342. package/out/recipes/si-bare-village.js.map +1 -0
  343. package/out/recipes/street-affix.d.ts +89 -0
  344. package/out/recipes/street-affix.d.ts.map +1 -0
  345. package/out/recipes/street-affix.js +563 -0
  346. package/out/recipes/street-affix.js.map +1 -0
  347. package/out/recipes/street-bare.d.ts +25 -0
  348. package/out/recipes/street-bare.d.ts.map +1 -0
  349. package/out/recipes/street-bare.js +86 -0
  350. package/out/recipes/street-bare.js.map +1 -0
  351. package/out/recipes/street.d.ts +15 -0
  352. package/out/recipes/street.d.ts.map +1 -0
  353. package/out/recipes/street.js +69 -0
  354. package/out/recipes/street.js.map +1 -0
  355. package/out/recipes/sub-venue-sources.d.ts +229 -0
  356. package/out/recipes/sub-venue-sources.d.ts.map +1 -0
  357. package/out/recipes/sub-venue-sources.js +653 -0
  358. package/out/recipes/sub-venue-sources.js.map +1 -0
  359. package/out/recipes/sub-venue.d.ts +269 -0
  360. package/out/recipes/sub-venue.d.ts.map +1 -0
  361. package/out/recipes/sub-venue.js +725 -0
  362. package/out/recipes/sub-venue.js.map +1 -0
  363. package/out/recipes/trailing-region.d.ts +74 -0
  364. package/out/recipes/trailing-region.d.ts.map +1 -0
  365. package/out/recipes/trailing-region.js +157 -0
  366. package/out/recipes/trailing-region.js.map +1 -0
  367. package/out/recipes/unit.d.ts +29 -0
  368. package/out/recipes/unit.d.ts.map +1 -0
  369. package/out/recipes/unit.js +230 -0
  370. package/out/recipes/unit.js.map +1 -0
  371. package/out/runner.d.ts +130 -0
  372. package/out/runner.d.ts.map +1 -0
  373. package/out/runner.js +185 -0
  374. package/out/runner.js.map +1 -0
  375. package/out/synthesizers/anchor-absorption.d.ts +63 -0
  376. package/out/synthesizers/anchor-absorption.d.ts.map +1 -0
  377. package/out/synthesizers/anchor-absorption.js +221 -0
  378. package/out/synthesizers/anchor-absorption.js.map +1 -0
  379. package/out/synthesizers/boundary-stress.d.ts +78 -0
  380. package/out/synthesizers/boundary-stress.d.ts.map +1 -0
  381. package/out/synthesizers/boundary-stress.js +455 -0
  382. package/out/synthesizers/boundary-stress.js.map +1 -0
  383. package/out/synthesizers/german.d.ts +115 -0
  384. package/out/synthesizers/german.d.ts.map +1 -0
  385. package/out/synthesizers/german.js +149 -0
  386. package/out/synthesizers/german.js.map +1 -0
  387. package/out/synthesizers/house-venue.d.ts +56 -0
  388. package/out/synthesizers/house-venue.d.ts.map +1 -0
  389. package/out/synthesizers/house-venue.js +247 -0
  390. package/out/synthesizers/house-venue.js.map +1 -0
  391. package/out/synthesizers/intersection.d.ts +52 -0
  392. package/out/synthesizers/intersection.d.ts.map +1 -0
  393. package/out/synthesizers/intersection.js +175 -0
  394. package/out/synthesizers/intersection.js.map +1 -0
  395. package/out/synthesizers/no-street.d.ts +72 -0
  396. package/out/synthesizers/no-street.d.ts.map +1 -0
  397. package/out/synthesizers/no-street.js +262 -0
  398. package/out/synthesizers/no-street.js.map +1 -0
  399. package/out/synthesizers/po-box.d.ts +108 -0
  400. package/out/synthesizers/po-box.d.ts.map +1 -0
  401. package/out/synthesizers/po-box.js +250 -0
  402. package/out/synthesizers/po-box.js.map +1 -0
  403. package/out/synthesizers/street.d.ts +54 -0
  404. package/out/synthesizers/street.d.ts.map +1 -0
  405. package/out/synthesizers/street.js +218 -0
  406. package/out/synthesizers/street.js.map +1 -0
  407. package/out/synthesizers/utils.d.ts +241 -0
  408. package/out/synthesizers/utils.d.ts.map +1 -0
  409. package/out/synthesizers/utils.js +776 -0
  410. package/out/synthesizers/utils.js.map +1 -0
  411. package/out/test-kit/corpus-recipe.d.ts +59 -0
  412. package/out/test-kit/corpus-recipe.d.ts.map +1 -0
  413. package/out/test-kit/corpus-recipe.js +39 -0
  414. package/out/test-kit/corpus-recipe.js.map +1 -0
  415. package/out/test-kit/index.d.ts +48 -0
  416. package/out/test-kit/index.d.ts.map +1 -0
  417. package/out/test-kit/index.js +78 -0
  418. package/out/test-kit/index.js.map +1 -0
  419. package/out/tools/align-slice.d.ts +7 -0
  420. package/out/tools/align-slice.d.ts.map +1 -0
  421. package/out/tools/align-slice.js +55 -0
  422. package/out/tools/align-slice.js.map +1 -0
  423. package/out/tools/audit.d.ts +29 -0
  424. package/out/tools/audit.d.ts.map +1 -0
  425. package/out/tools/audit.js +282 -0
  426. package/out/tools/audit.js.map +1 -0
  427. package/out/tools/corpus-stats.d.ts +44 -0
  428. package/out/tools/corpus-stats.d.ts.map +1 -0
  429. package/out/tools/corpus-stats.js +102 -0
  430. package/out/tools/corpus-stats.js.map +1 -0
  431. package/out/tools/fetch/ban.d.ts +31 -0
  432. package/out/tools/fetch/ban.d.ts.map +1 -0
  433. package/out/tools/fetch/ban.js +239 -0
  434. package/out/tools/fetch/ban.js.map +1 -0
  435. package/out/tools/fetch/download.d.ts +117 -0
  436. package/out/tools/fetch/download.d.ts.map +1 -0
  437. package/out/tools/fetch/download.js +160 -0
  438. package/out/tools/fetch/download.js.map +1 -0
  439. package/out/tools/fetch/geonames-dump.d.ts +91 -0
  440. package/out/tools/fetch/geonames-dump.d.ts.map +1 -0
  441. package/out/tools/fetch/geonames-dump.js +171 -0
  442. package/out/tools/fetch/geonames-dump.js.map +1 -0
  443. package/out/tools/fetch/geonames-postal.d.ts +76 -0
  444. package/out/tools/fetch/geonames-postal.d.ts.map +1 -0
  445. package/out/tools/fetch/geonames-postal.js +126 -0
  446. package/out/tools/fetch/geonames-postal.js.map +1 -0
  447. package/out/tools/fetch/hrsa.d.ts +18 -0
  448. package/out/tools/fetch/hrsa.d.ts.map +1 -0
  449. package/out/tools/fetch/hrsa.js +46 -0
  450. package/out/tools/fetch/hrsa.js.map +1 -0
  451. package/out/tools/fetch/imls-pls.d.ts +25 -0
  452. package/out/tools/fetch/imls-pls.d.ts.map +1 -0
  453. package/out/tools/fetch/imls-pls.js +108 -0
  454. package/out/tools/fetch/imls-pls.js.map +1 -0
  455. package/out/tools/fetch/index.d.ts +144 -0
  456. package/out/tools/fetch/index.d.ts.map +1 -0
  457. package/out/tools/fetch/index.js +143 -0
  458. package/out/tools/fetch/index.js.map +1 -0
  459. package/out/tools/fetch/nad.d.ts +70 -0
  460. package/out/tools/fetch/nad.d.ts.map +1 -0
  461. package/out/tools/fetch/nad.js +234 -0
  462. package/out/tools/fetch/nad.js.map +1 -0
  463. package/out/tools/fetch/nppes.d.ts +26 -0
  464. package/out/tools/fetch/nppes.d.ts.map +1 -0
  465. package/out/tools/fetch/nppes.js +126 -0
  466. package/out/tools/fetch/nppes.js.map +1 -0
  467. package/out/tools/fetch/openaddresses.d.ts +9 -0
  468. package/out/tools/fetch/openaddresses.d.ts.map +1 -0
  469. package/out/tools/fetch/openaddresses.js +279 -0
  470. package/out/tools/fetch/openaddresses.js.map +1 -0
  471. package/out/tools/fetch/ourairports.d.ts +45 -0
  472. package/out/tools/fetch/ourairports.d.ts.map +1 -0
  473. package/out/tools/fetch/ourairports.js +128 -0
  474. package/out/tools/fetch/ourairports.js.map +1 -0
  475. package/out/tools/fetch/ppd.d.ts.map +1 -0
  476. package/out/tools/fetch/ppd.js +85 -0
  477. package/out/tools/fetch/ppd.js.map +1 -0
  478. package/out/tools/fetch/state-hi-schools.d.ts +26 -0
  479. package/out/tools/fetch/state-hi-schools.d.ts.map +1 -0
  480. package/out/tools/fetch/state-hi-schools.js +112 -0
  481. package/out/tools/fetch/state-hi-schools.js.map +1 -0
  482. package/out/tools/fetch/state-sources.d.ts +26 -0
  483. package/out/tools/fetch/state-sources.d.ts.map +1 -0
  484. package/out/tools/fetch/state-sources.js +111 -0
  485. package/out/tools/fetch/state-sources.js.map +1 -0
  486. package/out/tools/fetch/tiger-full.d.ts +22 -0
  487. package/out/tools/fetch/tiger-full.d.ts.map +1 -0
  488. package/out/tools/fetch/tiger-full.js +217 -0
  489. package/out/tools/fetch/tiger-full.js.map +1 -0
  490. package/out/tools/fetch/wikidata-subvenue.d.ts +171 -0
  491. package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -0
  492. package/out/tools/fetch/wikidata-subvenue.js +274 -0
  493. package/out/tools/fetch/wikidata-subvenue.js.map +1 -0
  494. package/out/tools/gb-title-case.d.ts.map +1 -0
  495. package/out/tools/gb-title-case.js.map +1 -0
  496. package/out/tools/golden-expand.d.ts +90 -0
  497. package/out/tools/golden-expand.d.ts.map +1 -0
  498. package/out/tools/golden-expand.js +406 -0
  499. package/out/tools/golden-expand.js.map +1 -0
  500. package/out/tools/golden-promote.d.ts.map +1 -0
  501. package/out/tools/golden-promote.js +240 -0
  502. package/out/tools/golden-promote.js.map +1 -0
  503. package/out/tools/golden-relabel-street.d.ts +196 -0
  504. package/out/tools/golden-relabel-street.d.ts.map +1 -0
  505. package/out/tools/golden-relabel-street.js +440 -0
  506. package/out/tools/golden-relabel-street.js.map +1 -0
  507. package/out/tools/index.d.ts +28 -0
  508. package/out/tools/index.d.ts.map +1 -0
  509. package/out/tools/index.js +28 -0
  510. package/out/tools/index.js.map +1 -0
  511. package/out/tools/ingest-csv.d.ts.map +1 -0
  512. package/out/tools/ingest-csv.js +265 -0
  513. package/out/tools/ingest-csv.js.map +1 -0
  514. package/out/tools/jsonl-to-parquet.d.ts +61 -0
  515. package/out/tools/jsonl-to-parquet.d.ts.map +1 -0
  516. package/out/tools/jsonl-to-parquet.js +150 -0
  517. package/out/tools/jsonl-to-parquet.js.map +1 -0
  518. package/out/tools/lint-slice-vocab.d.ts +90 -0
  519. package/out/tools/lint-slice-vocab.d.ts.map +1 -0
  520. package/out/tools/lint-slice-vocab.js +267 -0
  521. package/out/tools/lint-slice-vocab.js.map +1 -0
  522. package/out/tools/lint-slice.d.ts +93 -0
  523. package/out/tools/lint-slice.d.ts.map +1 -0
  524. package/out/tools/lint-slice.js +322 -0
  525. package/out/tools/lint-slice.js.map +1 -0
  526. package/out/tools/overlay-manifest.d.ts +39 -0
  527. package/out/tools/overlay-manifest.d.ts.map +1 -0
  528. package/out/tools/overlay-manifest.js +90 -0
  529. package/out/tools/overlay-manifest.js.map +1 -0
  530. package/out/tools/overture-subvenue.d.ts +112 -0
  531. package/out/tools/overture-subvenue.d.ts.map +1 -0
  532. package/out/tools/overture-subvenue.js +139 -0
  533. package/out/tools/overture-subvenue.js.map +1 -0
  534. package/out/tools/postcode-triples.d.ts +174 -0
  535. package/out/tools/postcode-triples.d.ts.map +1 -0
  536. package/out/tools/postcode-triples.js +292 -0
  537. package/out/tools/postcode-triples.js.map +1 -0
  538. package/out/tools/slice-kryptonite.d.ts +32 -0
  539. package/out/tools/slice-kryptonite.d.ts.map +1 -0
  540. package/out/tools/slice-kryptonite.js +99 -0
  541. package/out/tools/slice-kryptonite.js.map +1 -0
  542. package/out/tools/slice-translit.d.ts +51 -0
  543. package/out/tools/slice-translit.d.ts.map +1 -0
  544. package/out/tools/slice-translit.js +166 -0
  545. package/out/tools/slice-translit.js.map +1 -0
  546. package/out/tools/sub-venue/harvest.d.ts +100 -0
  547. package/out/tools/sub-venue/harvest.d.ts.map +1 -0
  548. package/out/tools/sub-venue/harvest.js +168 -0
  549. package/out/tools/sub-venue/harvest.js.map +1 -0
  550. package/out/tools/sub-venue/head-nouns.d.ts +50 -0
  551. package/out/tools/sub-venue/head-nouns.d.ts.map +1 -0
  552. package/out/tools/sub-venue/head-nouns.js +213 -0
  553. package/out/tools/sub-venue/head-nouns.js.map +1 -0
  554. package/out/tools/sub-venue/surfaces.d.ts +45 -0
  555. package/out/tools/sub-venue/surfaces.d.ts.map +1 -0
  556. package/out/tools/sub-venue/surfaces.js +77 -0
  557. package/out/tools/sub-venue/surfaces.js.map +1 -0
  558. package/out/tools/sub-venue/table.d.ts +229 -0
  559. package/out/tools/sub-venue/table.d.ts.map +1 -0
  560. package/out/tools/sub-venue/table.js +108 -0
  561. package/out/tools/sub-venue/table.js.map +1 -0
  562. package/out/tools/sub-venue/wikidata.d.ts +26 -0
  563. package/out/tools/sub-venue/wikidata.d.ts.map +1 -0
  564. package/out/tools/sub-venue/wikidata.js +62 -0
  565. package/out/tools/sub-venue/wikidata.js.map +1 -0
  566. package/out/tools/sub-venue-lexicon.d.ts +156 -0
  567. package/out/tools/sub-venue-lexicon.d.ts.map +1 -0
  568. package/out/tools/sub-venue-lexicon.js +283 -0
  569. package/out/tools/sub-venue-lexicon.js.map +1 -0
  570. package/out/tools/sub-venue-promotions.d.ts +94 -0
  571. package/out/tools/sub-venue-promotions.d.ts.map +1 -0
  572. package/out/tools/sub-venue-promotions.js +266 -0
  573. package/out/tools/sub-venue-promotions.js.map +1 -0
  574. package/out/types.d.ts +221 -0
  575. package/out/types.d.ts.map +1 -0
  576. package/out/types.js.map +1 -0
  577. package/out/utils/align.d.ts +93 -0
  578. package/out/utils/align.d.ts.map +1 -0
  579. package/out/utils/align.js +234 -0
  580. package/out/utils/align.js.map +1 -0
  581. package/out/utils/golden.d.ts +85 -0
  582. package/out/utils/golden.d.ts.map +1 -0
  583. package/out/utils/golden.js +127 -0
  584. package/out/utils/golden.js.map +1 -0
  585. package/out/utils/index.d.ts +14 -0
  586. package/out/utils/index.d.ts.map +1 -0
  587. package/out/utils/index.js +14 -0
  588. package/out/utils/index.js.map +1 -0
  589. package/out/utils/license.d.ts.map +1 -0
  590. package/out/utils/license.js.map +1 -0
  591. package/out/utils/parquet.d.ts +178 -0
  592. package/out/utils/parquet.d.ts.map +1 -0
  593. package/out/utils/parquet.js +371 -0
  594. package/out/utils/parquet.js.map +1 -0
  595. package/out/utils/slice-stats.d.ts +52 -0
  596. package/out/utils/slice-stats.d.ts.map +1 -0
  597. package/out/utils/slice-stats.js +58 -0
  598. package/out/utils/slice-stats.js.map +1 -0
  599. package/out/utils/split.d.ts +128 -0
  600. package/out/utils/split.d.ts.map +1 -0
  601. package/out/utils/split.js +204 -0
  602. package/out/utils/split.js.map +1 -0
  603. package/out/utils/tokenize.d.ts +64 -0
  604. package/out/utils/tokenize.d.ts.map +1 -0
  605. package/out/utils/tokenize.js +82 -0
  606. package/out/utils/tokenize.js.map +1 -0
  607. package/out/utils/wof-json.d.ts +113 -0
  608. package/out/utils/wof-json.d.ts.map +1 -0
  609. package/out/utils/wof-json.js +173 -0
  610. package/out/utils/wof-json.js.map +1 -0
  611. package/package.json +259 -194
  612. package/out/src/adapters/ban/adapter.d.ts.map +0 -1
  613. package/out/src/adapters/ban/adapter.js +0 -149
  614. package/out/src/adapters/ban/adapter.js.map +0 -1
  615. package/out/src/adapters/ban/street-decompose.d.ts.map +0 -1
  616. package/out/src/adapters/ban/street-decompose.js +0 -75
  617. package/out/src/adapters/ban/street-decompose.js.map +0 -1
  618. package/out/src/adapters/fcc-bdc/adapter.d.ts.map +0 -1
  619. package/out/src/adapters/fcc-bdc/adapter.js +0 -144
  620. package/out/src/adapters/fcc-bdc/adapter.js.map +0 -1
  621. package/out/src/adapters/geonames/adapter.d.ts.map +0 -1
  622. package/out/src/adapters/geonames/adapter.js +0 -176
  623. package/out/src/adapters/geonames/adapter.js.map +0 -1
  624. package/out/src/adapters/geonames-postal/adapter.d.ts +0 -41
  625. package/out/src/adapters/geonames-postal/adapter.d.ts.map +0 -1
  626. package/out/src/adapters/geonames-postal/adapter.js +0 -104
  627. package/out/src/adapters/geonames-postal/adapter.js.map +0 -1
  628. package/out/src/adapters/gnaf/adapter.d.ts +0 -49
  629. package/out/src/adapters/gnaf/adapter.d.ts.map +0 -1
  630. package/out/src/adapters/gnaf/adapter.js +0 -124
  631. package/out/src/adapters/gnaf/adapter.js.map +0 -1
  632. package/out/src/adapters/gnaf/assemble.d.ts +0 -65
  633. package/out/src/adapters/gnaf/assemble.d.ts.map +0 -1
  634. package/out/src/adapters/gnaf/assemble.js +0 -154
  635. package/out/src/adapters/gnaf/assemble.js.map +0 -1
  636. package/out/src/adapters/index.d.ts +0 -51
  637. package/out/src/adapters/index.d.ts.map +0 -1
  638. package/out/src/adapters/index.js +0 -95
  639. package/out/src/adapters/index.js.map +0 -1
  640. package/out/src/adapters/openaddresses/adapter.d.ts.map +0 -1
  641. package/out/src/adapters/openaddresses/adapter.js +0 -186
  642. package/out/src/adapters/openaddresses/adapter.js.map +0 -1
  643. package/out/src/adapters/overture/adapter.d.ts +0 -48
  644. package/out/src/adapters/overture/adapter.d.ts.map +0 -1
  645. package/out/src/adapters/overture/adapter.js +0 -125
  646. package/out/src/adapters/overture/adapter.js.map +0 -1
  647. package/out/src/adapters/state-hi-schools/adapter.d.ts +0 -47
  648. package/out/src/adapters/state-hi-schools/adapter.d.ts.map +0 -1
  649. package/out/src/adapters/state-hi-schools/adapter.js +0 -133
  650. package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
  651. package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
  652. package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
  653. package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
  654. package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
  655. package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
  656. package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
  657. package/out/src/adapters/synth-po-box/adapter.d.ts.map +0 -1
  658. package/out/src/adapters/synth-po-box/adapter.js +0 -140
  659. package/out/src/adapters/synth-po-box/adapter.js.map +0 -1
  660. package/out/src/adapters/tiger/adapter.d.ts +0 -55
  661. package/out/src/adapters/tiger/adapter.d.ts.map +0 -1
  662. package/out/src/adapters/tiger/adapter.js +0 -201
  663. package/out/src/adapters/tiger/adapter.js.map +0 -1
  664. package/out/src/adapters/tiger/street-decompose.d.ts.map +0 -1
  665. package/out/src/adapters/tiger/street-decompose.js +0 -90
  666. package/out/src/adapters/tiger/street-decompose.js.map +0 -1
  667. package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -47
  668. package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
  669. package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +0 -139
  670. package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
  671. package/out/src/adapters/usgov-imls-pls/adapter.d.ts +0 -36
  672. package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
  673. package/out/src/adapters/usgov-imls-pls/adapter.js +0 -114
  674. package/out/src/adapters/usgov-imls-pls/adapter.js.map +0 -1
  675. package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
  676. package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
  677. package/out/src/adapters/usgov-irs-bmf/adapter.js +0 -124
  678. package/out/src/adapters/usgov-irs-bmf/adapter.js.map +0 -1
  679. package/out/src/adapters/usgov-nad/adapter.d.ts +0 -48
  680. package/out/src/adapters/usgov-nad/adapter.d.ts.map +0 -1
  681. package/out/src/adapters/usgov-nad/adapter.js +0 -252
  682. package/out/src/adapters/usgov-nad/adapter.js.map +0 -1
  683. package/out/src/adapters/usgov-nppes/adapter.d.ts.map +0 -1
  684. package/out/src/adapters/usgov-nppes/adapter.js +0 -116
  685. package/out/src/adapters/usgov-nppes/adapter.js.map +0 -1
  686. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
  687. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -156
  688. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
  689. package/out/src/adapters/utils/index.d.ts +0 -150
  690. package/out/src/adapters/utils/index.d.ts.map +0 -1
  691. package/out/src/adapters/utils/index.js +0 -159
  692. package/out/src/adapters/utils/index.js.map +0 -1
  693. package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
  694. package/out/src/adapters/wof-admin-jp/adapter.js +0 -164
  695. package/out/src/adapters/wof-admin-jp/adapter.js.map +0 -1
  696. package/out/src/adapters/wof-admin-json/adapter.d.ts +0 -82
  697. package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
  698. package/out/src/adapters/wof-admin-json/adapter.js +0 -224
  699. package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
  700. package/out/src/adapters/wof-json-rows.d.ts +0 -32
  701. package/out/src/adapters/wof-json-rows.d.ts.map +0 -1
  702. package/out/src/adapters/wof-json-rows.js +0 -45
  703. package/out/src/adapters/wof-json-rows.js.map +0 -1
  704. package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -65
  705. package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
  706. package/out/src/adapters/wof-postalcode-json/adapter.js +0 -160
  707. package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
  708. package/out/src/build.d.ts +0 -132
  709. package/out/src/build.d.ts.map +0 -1
  710. package/out/src/build.js +0 -251
  711. package/out/src/build.js.map +0 -1
  712. package/out/src/codex/us-fips-state.d.ts.map +0 -1
  713. package/out/src/codex/us-fips-state.js.map +0 -1
  714. package/out/src/index.d.ts +0 -14
  715. package/out/src/index.d.ts.map +0 -1
  716. package/out/src/index.js +0 -14
  717. package/out/src/index.js.map +0 -1
  718. package/out/src/name-prone-us-suffixes.d.ts +0 -12
  719. package/out/src/name-prone-us-suffixes.d.ts.map +0 -1
  720. package/out/src/name-prone-us-suffixes.js +0 -12
  721. package/out/src/name-prone-us-suffixes.js.map +0 -1
  722. package/out/src/parquet-wrapper/index.d.ts +0 -9
  723. package/out/src/parquet-wrapper/index.d.ts.map +0 -1
  724. package/out/src/parquet-wrapper/index.js +0 -9
  725. package/out/src/parquet-wrapper/index.js.map +0 -1
  726. package/out/src/parquet-wrapper/reader.d.ts +0 -34
  727. package/out/src/parquet-wrapper/reader.d.ts.map +0 -1
  728. package/out/src/parquet-wrapper/reader.js +0 -69
  729. package/out/src/parquet-wrapper/reader.js.map +0 -1
  730. package/out/src/parquet-wrapper/schema.d.ts +0 -49
  731. package/out/src/parquet-wrapper/schema.d.ts.map +0 -1
  732. package/out/src/parquet-wrapper/schema.js +0 -55
  733. package/out/src/parquet-wrapper/schema.js.map +0 -1
  734. package/out/src/parquet-wrapper/writer.d.ts +0 -46
  735. package/out/src/parquet-wrapper/writer.d.ts.map +0 -1
  736. package/out/src/parquet-wrapper/writer.js +0 -76
  737. package/out/src/parquet-wrapper/writer.js.map +0 -1
  738. package/out/src/runner.d.ts +0 -126
  739. package/out/src/runner.d.ts.map +0 -1
  740. package/out/src/runner.js +0 -189
  741. package/out/src/runner.js.map +0 -1
  742. package/out/src/shard-recipes/anchor-absorption.d.ts +0 -20
  743. package/out/src/shard-recipes/anchor-absorption.d.ts.map +0 -1
  744. package/out/src/shard-recipes/anchor-absorption.js +0 -82
  745. package/out/src/shard-recipes/anchor-absorption.js.map +0 -1
  746. package/out/src/shard-recipes/bare-country.d.ts +0 -25
  747. package/out/src/shard-recipes/bare-country.d.ts.map +0 -1
  748. package/out/src/shard-recipes/bare-country.js +0 -87
  749. package/out/src/shard-recipes/bare-country.js.map +0 -1
  750. package/out/src/shard-recipes/boundary-stress.d.ts +0 -20
  751. package/out/src/shard-recipes/boundary-stress.d.ts.map +0 -1
  752. package/out/src/shard-recipes/boundary-stress.js +0 -83
  753. package/out/src/shard-recipes/boundary-stress.js.map +0 -1
  754. package/out/src/shard-recipes/country-balanced.d.ts +0 -32
  755. package/out/src/shard-recipes/country-balanced.d.ts.map +0 -1
  756. package/out/src/shard-recipes/country-balanced.js +0 -406
  757. package/out/src/shard-recipes/country-balanced.js.map +0 -1
  758. package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts +0 -22
  759. package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +0 -1
  760. package/out/src/shard-recipes/cz-pcfirst-preposition.js +0 -100
  761. package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +0 -1
  762. package/out/src/shard-recipes/fr-admin-split.d.ts +0 -38
  763. package/out/src/shard-recipes/fr-admin-split.d.ts.map +0 -1
  764. package/out/src/shard-recipes/fr-admin-split.js +0 -188
  765. package/out/src/shard-recipes/fr-admin-split.js.map +0 -1
  766. package/out/src/shard-recipes/fr-bare-street.d.ts +0 -28
  767. package/out/src/shard-recipes/fr-bare-street.d.ts.map +0 -1
  768. package/out/src/shard-recipes/fr-bare-street.js +0 -143
  769. package/out/src/shard-recipes/fr-bare-street.js.map +0 -1
  770. package/out/src/shard-recipes/fr-fragment.d.ts +0 -77
  771. package/out/src/shard-recipes/fr-fragment.d.ts.map +0 -1
  772. package/out/src/shard-recipes/fr-fragment.js +0 -276
  773. package/out/src/shard-recipes/fr-fragment.js.map +0 -1
  774. package/out/src/shard-recipes/fr-lieudit.d.ts +0 -32
  775. package/out/src/shard-recipes/fr-lieudit.d.ts.map +0 -1
  776. package/out/src/shard-recipes/fr-lieudit.js +0 -226
  777. package/out/src/shard-recipes/fr-lieudit.js.map +0 -1
  778. package/out/src/shard-recipes/fr-order.d.ts +0 -38
  779. package/out/src/shard-recipes/fr-order.d.ts.map +0 -1
  780. package/out/src/shard-recipes/fr-order.js +0 -208
  781. package/out/src/shard-recipes/fr-order.js.map +0 -1
  782. package/out/src/shard-recipes/german.d.ts +0 -23
  783. package/out/src/shard-recipes/german.d.ts.map +0 -1
  784. package/out/src/shard-recipes/german.js +0 -132
  785. package/out/src/shard-recipes/german.js.map +0 -1
  786. package/out/src/shard-recipes/house-venue.d.ts +0 -18
  787. package/out/src/shard-recipes/house-venue.d.ts.map +0 -1
  788. package/out/src/shard-recipes/house-venue.js +0 -74
  789. package/out/src/shard-recipes/house-venue.js.map +0 -1
  790. package/out/src/shard-recipes/index.d.ts +0 -24
  791. package/out/src/shard-recipes/index.d.ts.map +0 -1
  792. package/out/src/shard-recipes/index.js +0 -89
  793. package/out/src/shard-recipes/index.js.map +0 -1
  794. package/out/src/shard-recipes/intersection.d.ts +0 -42
  795. package/out/src/shard-recipes/intersection.d.ts.map +0 -1
  796. package/out/src/shard-recipes/intersection.js +0 -460
  797. package/out/src/shard-recipes/intersection.js.map +0 -1
  798. package/out/src/shard-recipes/locale.d.ts +0 -135
  799. package/out/src/shard-recipes/locale.d.ts.map +0 -1
  800. package/out/src/shard-recipes/locale.js +0 -459
  801. package/out/src/shard-recipes/locale.js.map +0 -1
  802. package/out/src/shard-recipes/nl-postcode.d.ts +0 -26
  803. package/out/src/shard-recipes/nl-postcode.d.ts.map +0 -1
  804. package/out/src/shard-recipes/nl-postcode.js +0 -102
  805. package/out/src/shard-recipes/nl-postcode.js.map +0 -1
  806. package/out/src/shard-recipes/no-fragment.d.ts +0 -43
  807. package/out/src/shard-recipes/no-fragment.d.ts.map +0 -1
  808. package/out/src/shard-recipes/no-fragment.js +0 -188
  809. package/out/src/shard-recipes/no-fragment.js.map +0 -1
  810. package/out/src/shard-recipes/no-street-led.d.ts +0 -24
  811. package/out/src/shard-recipes/no-street-led.d.ts.map +0 -1
  812. package/out/src/shard-recipes/no-street-led.js +0 -121
  813. package/out/src/shard-recipes/no-street-led.js.map +0 -1
  814. package/out/src/shard-recipes/no-street.d.ts +0 -18
  815. package/out/src/shard-recipes/no-street.d.ts.map +0 -1
  816. package/out/src/shard-recipes/no-street.js +0 -72
  817. package/out/src/shard-recipes/no-street.js.map +0 -1
  818. package/out/src/shard-recipes/po-box-cedex.d.ts +0 -38
  819. package/out/src/shard-recipes/po-box-cedex.d.ts.map +0 -1
  820. package/out/src/shard-recipes/po-box-cedex.js +0 -726
  821. package/out/src/shard-recipes/po-box-cedex.js.map +0 -1
  822. package/out/src/shard-recipes/po-box.d.ts +0 -17
  823. package/out/src/shard-recipes/po-box.d.ts.map +0 -1
  824. package/out/src/shard-recipes/po-box.js +0 -101
  825. package/out/src/shard-recipes/po-box.js.map +0 -1
  826. package/out/src/shard-recipes/reviewed-postcode-tail.d.ts +0 -47
  827. package/out/src/shard-recipes/reviewed-postcode-tail.d.ts.map +0 -1
  828. package/out/src/shard-recipes/reviewed-postcode-tail.js +0 -125
  829. package/out/src/shard-recipes/reviewed-postcode-tail.js.map +0 -1
  830. package/out/src/shard-recipes/scaffold.d.ts +0 -246
  831. package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
  832. package/out/src/shard-recipes/scaffold.js +0 -137
  833. package/out/src/shard-recipes/scaffold.js.map +0 -1
  834. package/out/src/shard-recipes/si-bare-village.d.ts +0 -32
  835. package/out/src/shard-recipes/si-bare-village.d.ts.map +0 -1
  836. package/out/src/shard-recipes/si-bare-village.js +0 -88
  837. package/out/src/shard-recipes/si-bare-village.js.map +0 -1
  838. package/out/src/shard-recipes/street-affix.d.ts +0 -89
  839. package/out/src/shard-recipes/street-affix.d.ts.map +0 -1
  840. package/out/src/shard-recipes/street-affix.js +0 -578
  841. package/out/src/shard-recipes/street-affix.js.map +0 -1
  842. package/out/src/shard-recipes/street-bare.d.ts +0 -25
  843. package/out/src/shard-recipes/street-bare.d.ts.map +0 -1
  844. package/out/src/shard-recipes/street-bare.js +0 -86
  845. package/out/src/shard-recipes/street-bare.js.map +0 -1
  846. package/out/src/shard-recipes/street.d.ts +0 -15
  847. package/out/src/shard-recipes/street.d.ts.map +0 -1
  848. package/out/src/shard-recipes/street.js +0 -69
  849. package/out/src/shard-recipes/street.js.map +0 -1
  850. package/out/src/shard-recipes/sub-venue-sources.d.ts +0 -228
  851. package/out/src/shard-recipes/sub-venue-sources.d.ts.map +0 -1
  852. package/out/src/shard-recipes/sub-venue-sources.js +0 -664
  853. package/out/src/shard-recipes/sub-venue-sources.js.map +0 -1
  854. package/out/src/shard-recipes/sub-venue.d.ts +0 -269
  855. package/out/src/shard-recipes/sub-venue.d.ts.map +0 -1
  856. package/out/src/shard-recipes/sub-venue.js +0 -710
  857. package/out/src/shard-recipes/sub-venue.js.map +0 -1
  858. package/out/src/shard-recipes/trailing-region.d.ts +0 -74
  859. package/out/src/shard-recipes/trailing-region.d.ts.map +0 -1
  860. package/out/src/shard-recipes/trailing-region.js +0 -157
  861. package/out/src/shard-recipes/trailing-region.js.map +0 -1
  862. package/out/src/shard-recipes/unit.d.ts +0 -29
  863. package/out/src/shard-recipes/unit.d.ts.map +0 -1
  864. package/out/src/shard-recipes/unit.js +0 -243
  865. package/out/src/shard-recipes/unit.js.map +0 -1
  866. package/out/src/synthesizers/anchor-absorption.d.ts +0 -63
  867. package/out/src/synthesizers/anchor-absorption.d.ts.map +0 -1
  868. package/out/src/synthesizers/anchor-absorption.js +0 -223
  869. package/out/src/synthesizers/anchor-absorption.js.map +0 -1
  870. package/out/src/synthesizers/boundary-stress.d.ts +0 -78
  871. package/out/src/synthesizers/boundary-stress.d.ts.map +0 -1
  872. package/out/src/synthesizers/boundary-stress.js +0 -455
  873. package/out/src/synthesizers/boundary-stress.js.map +0 -1
  874. package/out/src/synthesizers/german.d.ts +0 -107
  875. package/out/src/synthesizers/german.d.ts.map +0 -1
  876. package/out/src/synthesizers/german.js +0 -148
  877. package/out/src/synthesizers/german.js.map +0 -1
  878. package/out/src/synthesizers/house-venue.d.ts +0 -56
  879. package/out/src/synthesizers/house-venue.d.ts.map +0 -1
  880. package/out/src/synthesizers/house-venue.js +0 -267
  881. package/out/src/synthesizers/house-venue.js.map +0 -1
  882. package/out/src/synthesizers/intersection.d.ts +0 -52
  883. package/out/src/synthesizers/intersection.d.ts.map +0 -1
  884. package/out/src/synthesizers/intersection.js +0 -175
  885. package/out/src/synthesizers/intersection.js.map +0 -1
  886. package/out/src/synthesizers/no-street.d.ts +0 -72
  887. package/out/src/synthesizers/no-street.d.ts.map +0 -1
  888. package/out/src/synthesizers/no-street.js +0 -282
  889. package/out/src/synthesizers/no-street.js.map +0 -1
  890. package/out/src/synthesizers/po-box.d.ts +0 -104
  891. package/out/src/synthesizers/po-box.d.ts.map +0 -1
  892. package/out/src/synthesizers/po-box.js +0 -266
  893. package/out/src/synthesizers/po-box.js.map +0 -1
  894. package/out/src/synthesizers/street.d.ts +0 -54
  895. package/out/src/synthesizers/street.d.ts.map +0 -1
  896. package/out/src/synthesizers/street.js +0 -221
  897. package/out/src/synthesizers/street.js.map +0 -1
  898. package/out/src/synthesizers/utils.d.ts +0 -203
  899. package/out/src/synthesizers/utils.d.ts.map +0 -1
  900. package/out/src/synthesizers/utils.js +0 -708
  901. package/out/src/synthesizers/utils.js.map +0 -1
  902. package/out/src/tools/align-shard.d.ts +0 -8
  903. package/out/src/tools/align-shard.d.ts.map +0 -1
  904. package/out/src/tools/align-shard.js +0 -56
  905. package/out/src/tools/align-shard.js.map +0 -1
  906. package/out/src/tools/audit.d.ts +0 -28
  907. package/out/src/tools/audit.d.ts.map +0 -1
  908. package/out/src/tools/audit.js +0 -285
  909. package/out/src/tools/audit.js.map +0 -1
  910. package/out/src/tools/corpus-stats.d.ts +0 -44
  911. package/out/src/tools/corpus-stats.d.ts.map +0 -1
  912. package/out/src/tools/corpus-stats.js +0 -138
  913. package/out/src/tools/corpus-stats.js.map +0 -1
  914. package/out/src/tools/fetch/ban.d.ts +0 -31
  915. package/out/src/tools/fetch/ban.d.ts.map +0 -1
  916. package/out/src/tools/fetch/ban.js +0 -239
  917. package/out/src/tools/fetch/ban.js.map +0 -1
  918. package/out/src/tools/fetch/download.d.ts +0 -78
  919. package/out/src/tools/fetch/download.d.ts.map +0 -1
  920. package/out/src/tools/fetch/download.js +0 -116
  921. package/out/src/tools/fetch/download.js.map +0 -1
  922. package/out/src/tools/fetch/geonames-dump.d.ts +0 -87
  923. package/out/src/tools/fetch/geonames-dump.d.ts.map +0 -1
  924. package/out/src/tools/fetch/geonames-dump.js +0 -178
  925. package/out/src/tools/fetch/geonames-dump.js.map +0 -1
  926. package/out/src/tools/fetch/geonames-postal.d.ts +0 -76
  927. package/out/src/tools/fetch/geonames-postal.d.ts.map +0 -1
  928. package/out/src/tools/fetch/geonames-postal.js +0 -125
  929. package/out/src/tools/fetch/geonames-postal.js.map +0 -1
  930. package/out/src/tools/fetch/hrsa.d.ts +0 -18
  931. package/out/src/tools/fetch/hrsa.d.ts.map +0 -1
  932. package/out/src/tools/fetch/hrsa.js +0 -46
  933. package/out/src/tools/fetch/hrsa.js.map +0 -1
  934. package/out/src/tools/fetch/imls-pls.d.ts +0 -25
  935. package/out/src/tools/fetch/imls-pls.d.ts.map +0 -1
  936. package/out/src/tools/fetch/imls-pls.js +0 -108
  937. package/out/src/tools/fetch/imls-pls.js.map +0 -1
  938. package/out/src/tools/fetch/index.d.ts +0 -144
  939. package/out/src/tools/fetch/index.d.ts.map +0 -1
  940. package/out/src/tools/fetch/index.js +0 -143
  941. package/out/src/tools/fetch/index.js.map +0 -1
  942. package/out/src/tools/fetch/nad.d.ts +0 -70
  943. package/out/src/tools/fetch/nad.d.ts.map +0 -1
  944. package/out/src/tools/fetch/nad.js +0 -234
  945. package/out/src/tools/fetch/nad.js.map +0 -1
  946. package/out/src/tools/fetch/nppes.d.ts +0 -26
  947. package/out/src/tools/fetch/nppes.d.ts.map +0 -1
  948. package/out/src/tools/fetch/nppes.js +0 -126
  949. package/out/src/tools/fetch/nppes.js.map +0 -1
  950. package/out/src/tools/fetch/openaddresses.d.ts +0 -61
  951. package/out/src/tools/fetch/openaddresses.d.ts.map +0 -1
  952. package/out/src/tools/fetch/openaddresses.js +0 -317
  953. package/out/src/tools/fetch/openaddresses.js.map +0 -1
  954. package/out/src/tools/fetch/ourairports.d.ts +0 -45
  955. package/out/src/tools/fetch/ourairports.d.ts.map +0 -1
  956. package/out/src/tools/fetch/ourairports.js +0 -128
  957. package/out/src/tools/fetch/ourairports.js.map +0 -1
  958. package/out/src/tools/fetch/ppd.d.ts.map +0 -1
  959. package/out/src/tools/fetch/ppd.js +0 -100
  960. package/out/src/tools/fetch/ppd.js.map +0 -1
  961. package/out/src/tools/fetch/state-hi-schools.d.ts +0 -25
  962. package/out/src/tools/fetch/state-hi-schools.d.ts.map +0 -1
  963. package/out/src/tools/fetch/state-hi-schools.js +0 -162
  964. package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
  965. package/out/src/tools/fetch/state-sources.d.ts +0 -26
  966. package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
  967. package/out/src/tools/fetch/state-sources.js +0 -111
  968. package/out/src/tools/fetch/state-sources.js.map +0 -1
  969. package/out/src/tools/fetch/tiger-full.d.ts +0 -42
  970. package/out/src/tools/fetch/tiger-full.d.ts.map +0 -1
  971. package/out/src/tools/fetch/tiger-full.js +0 -248
  972. package/out/src/tools/fetch/tiger-full.js.map +0 -1
  973. package/out/src/tools/fetch/wikidata-subvenue.d.ts +0 -171
  974. package/out/src/tools/fetch/wikidata-subvenue.d.ts.map +0 -1
  975. package/out/src/tools/fetch/wikidata-subvenue.js +0 -275
  976. package/out/src/tools/fetch/wikidata-subvenue.js.map +0 -1
  977. package/out/src/tools/gb-title-case.d.ts.map +0 -1
  978. package/out/src/tools/gb-title-case.js.map +0 -1
  979. package/out/src/tools/golden-expand.d.ts +0 -90
  980. package/out/src/tools/golden-expand.d.ts.map +0 -1
  981. package/out/src/tools/golden-expand.js +0 -413
  982. package/out/src/tools/golden-expand.js.map +0 -1
  983. package/out/src/tools/golden-promote.d.ts.map +0 -1
  984. package/out/src/tools/golden-promote.js +0 -244
  985. package/out/src/tools/golden-promote.js.map +0 -1
  986. package/out/src/tools/golden-relabel-street.d.ts +0 -196
  987. package/out/src/tools/golden-relabel-street.d.ts.map +0 -1
  988. package/out/src/tools/golden-relabel-street.js +0 -440
  989. package/out/src/tools/golden-relabel-street.js.map +0 -1
  990. package/out/src/tools/index.d.ts +0 -28
  991. package/out/src/tools/index.d.ts.map +0 -1
  992. package/out/src/tools/index.js +0 -28
  993. package/out/src/tools/index.js.map +0 -1
  994. package/out/src/tools/ingest-csv.d.ts.map +0 -1
  995. package/out/src/tools/ingest-csv.js +0 -296
  996. package/out/src/tools/ingest-csv.js.map +0 -1
  997. package/out/src/tools/jsonl-to-parquet.d.ts +0 -61
  998. package/out/src/tools/jsonl-to-parquet.d.ts.map +0 -1
  999. package/out/src/tools/jsonl-to-parquet.js +0 -164
  1000. package/out/src/tools/jsonl-to-parquet.js.map +0 -1
  1001. package/out/src/tools/lint-shard-vocab.d.ts +0 -90
  1002. package/out/src/tools/lint-shard-vocab.d.ts.map +0 -1
  1003. package/out/src/tools/lint-shard-vocab.js +0 -281
  1004. package/out/src/tools/lint-shard-vocab.js.map +0 -1
  1005. package/out/src/tools/lint-shard.d.ts +0 -93
  1006. package/out/src/tools/lint-shard.d.ts.map +0 -1
  1007. package/out/src/tools/lint-shard.js +0 -354
  1008. package/out/src/tools/lint-shard.js.map +0 -1
  1009. package/out/src/tools/overlay-manifest.d.ts +0 -39
  1010. package/out/src/tools/overlay-manifest.d.ts.map +0 -1
  1011. package/out/src/tools/overlay-manifest.js +0 -98
  1012. package/out/src/tools/overlay-manifest.js.map +0 -1
  1013. package/out/src/tools/overture-subvenue.d.ts +0 -112
  1014. package/out/src/tools/overture-subvenue.d.ts.map +0 -1
  1015. package/out/src/tools/overture-subvenue.js +0 -144
  1016. package/out/src/tools/overture-subvenue.js.map +0 -1
  1017. package/out/src/tools/postcode-triples.d.ts +0 -175
  1018. package/out/src/tools/postcode-triples.d.ts.map +0 -1
  1019. package/out/src/tools/postcode-triples.js +0 -304
  1020. package/out/src/tools/postcode-triples.js.map +0 -1
  1021. package/out/src/tools/shard-kryptonite.d.ts +0 -32
  1022. package/out/src/tools/shard-kryptonite.d.ts.map +0 -1
  1023. package/out/src/tools/shard-kryptonite.js +0 -100
  1024. package/out/src/tools/shard-kryptonite.js.map +0 -1
  1025. package/out/src/tools/shard-translit.d.ts +0 -51
  1026. package/out/src/tools/shard-translit.d.ts.map +0 -1
  1027. package/out/src/tools/shard-translit.js +0 -175
  1028. package/out/src/tools/shard-translit.js.map +0 -1
  1029. package/out/src/tools/sub-venue/harvest.d.ts +0 -100
  1030. package/out/src/tools/sub-venue/harvest.d.ts.map +0 -1
  1031. package/out/src/tools/sub-venue/harvest.js +0 -168
  1032. package/out/src/tools/sub-venue/harvest.js.map +0 -1
  1033. package/out/src/tools/sub-venue/head-nouns.d.ts +0 -50
  1034. package/out/src/tools/sub-venue/head-nouns.d.ts.map +0 -1
  1035. package/out/src/tools/sub-venue/head-nouns.js +0 -210
  1036. package/out/src/tools/sub-venue/head-nouns.js.map +0 -1
  1037. package/out/src/tools/sub-venue/surfaces.d.ts +0 -45
  1038. package/out/src/tools/sub-venue/surfaces.d.ts.map +0 -1
  1039. package/out/src/tools/sub-venue/surfaces.js +0 -77
  1040. package/out/src/tools/sub-venue/surfaces.js.map +0 -1
  1041. package/out/src/tools/sub-venue/table.d.ts +0 -229
  1042. package/out/src/tools/sub-venue/table.d.ts.map +0 -1
  1043. package/out/src/tools/sub-venue/table.js +0 -108
  1044. package/out/src/tools/sub-venue/table.js.map +0 -1
  1045. package/out/src/tools/sub-venue/wikidata.d.ts +0 -26
  1046. package/out/src/tools/sub-venue/wikidata.d.ts.map +0 -1
  1047. package/out/src/tools/sub-venue/wikidata.js +0 -62
  1048. package/out/src/tools/sub-venue/wikidata.js.map +0 -1
  1049. package/out/src/tools/sub-venue-lexicon.d.ts +0 -156
  1050. package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
  1051. package/out/src/tools/sub-venue-lexicon.js +0 -282
  1052. package/out/src/tools/sub-venue-lexicon.js.map +0 -1
  1053. package/out/src/tools/sub-venue-promotions.d.ts +0 -94
  1054. package/out/src/tools/sub-venue-promotions.d.ts.map +0 -1
  1055. package/out/src/tools/sub-venue-promotions.js +0 -266
  1056. package/out/src/tools/sub-venue-promotions.js.map +0 -1
  1057. package/out/src/types.d.ts +0 -221
  1058. package/out/src/types.d.ts.map +0 -1
  1059. package/out/src/types.js.map +0 -1
  1060. package/out/src/utils/align.d.ts +0 -93
  1061. package/out/src/utils/align.d.ts.map +0 -1
  1062. package/out/src/utils/align.js +0 -234
  1063. package/out/src/utils/align.js.map +0 -1
  1064. package/out/src/utils/golden.d.ts +0 -69
  1065. package/out/src/utils/golden.d.ts.map +0 -1
  1066. package/out/src/utils/golden.js +0 -127
  1067. package/out/src/utils/golden.js.map +0 -1
  1068. package/out/src/utils/index.d.ts +0 -14
  1069. package/out/src/utils/index.d.ts.map +0 -1
  1070. package/out/src/utils/index.js +0 -14
  1071. package/out/src/utils/index.js.map +0 -1
  1072. package/out/src/utils/license.d.ts.map +0 -1
  1073. package/out/src/utils/license.js.map +0 -1
  1074. package/out/src/utils/parquet.d.ts +0 -162
  1075. package/out/src/utils/parquet.d.ts.map +0 -1
  1076. package/out/src/utils/parquet.js +0 -262
  1077. package/out/src/utils/parquet.js.map +0 -1
  1078. package/out/src/utils/split.d.ts +0 -127
  1079. package/out/src/utils/split.d.ts.map +0 -1
  1080. package/out/src/utils/split.js +0 -204
  1081. package/out/src/utils/split.js.map +0 -1
  1082. package/out/src/utils/tokenize.d.ts +0 -56
  1083. package/out/src/utils/tokenize.d.ts.map +0 -1
  1084. package/out/src/utils/tokenize.js +0 -48
  1085. package/out/src/utils/tokenize.js.map +0 -1
  1086. package/out/src/utils/wof-json.d.ts +0 -109
  1087. package/out/src/utils/wof-json.d.ts.map +0 -1
  1088. package/out/src/utils/wof-json.js +0 -173
  1089. package/out/src/utils/wof-json.js.map +0 -1
  1090. package/src/adapters/ban/adapter.ts +0 -191
  1091. package/src/adapters/ban/street-decompose.ts +0 -96
  1092. package/src/adapters/fcc-bdc/adapter.ts +0 -174
  1093. package/src/adapters/geonames/adapter.ts +0 -200
  1094. package/src/adapters/geonames-postal/adapter.ts +0 -119
  1095. package/src/adapters/gnaf/adapter.ts +0 -149
  1096. package/src/adapters/gnaf/assemble.ts +0 -226
  1097. package/src/adapters/index.ts +0 -149
  1098. package/src/adapters/openaddresses/adapter.ts +0 -251
  1099. package/src/adapters/overture/adapter.ts +0 -162
  1100. package/src/adapters/state-hi-schools/adapter.ts +0 -164
  1101. package/src/adapters/synth-po-box/adapter.ts +0 -204
  1102. package/src/adapters/tiger/adapter.ts +0 -253
  1103. package/src/adapters/tiger/street-decompose.ts +0 -111
  1104. package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -183
  1105. package/src/adapters/usgov-imls-pls/adapter.ts +0 -143
  1106. package/src/adapters/usgov-irs-bmf/adapter.ts +0 -163
  1107. package/src/adapters/usgov-nad/adapter.ts +0 -348
  1108. package/src/adapters/usgov-nppes/adapter.ts +0 -159
  1109. package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -204
  1110. package/src/adapters/utils/index.ts +0 -233
  1111. package/src/adapters/wof-admin-jp/adapter.ts +0 -216
  1112. package/src/adapters/wof-admin-json/adapter.ts +0 -256
  1113. package/src/adapters/wof-json-rows.ts +0 -79
  1114. package/src/adapters/wof-postalcode-json/adapter.ts +0 -183
  1115. package/src/build.ts +0 -386
  1116. package/src/index.ts +0 -14
  1117. package/src/name-prone-us-suffixes.ts +0 -12
  1118. package/src/parquet-wrapper/index.ts +0 -9
  1119. package/src/parquet-wrapper/reader.ts +0 -97
  1120. package/src/parquet-wrapper/schema.ts +0 -88
  1121. package/src/parquet-wrapper/writer.ts +0 -110
  1122. package/src/runner.ts +0 -317
  1123. package/src/shard-recipes/anchor-absorption.ts +0 -103
  1124. package/src/shard-recipes/bare-country.ts +0 -95
  1125. package/src/shard-recipes/boundary-stress.ts +0 -101
  1126. package/src/shard-recipes/country-balanced.ts +0 -524
  1127. package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -111
  1128. package/src/shard-recipes/fr-admin-split.ts +0 -239
  1129. package/src/shard-recipes/fr-bare-street.ts +0 -170
  1130. package/src/shard-recipes/fr-fragment.ts +0 -332
  1131. package/src/shard-recipes/fr-lieudit.ts +0 -302
  1132. package/src/shard-recipes/fr-order.ts +0 -258
  1133. package/src/shard-recipes/german.ts +0 -170
  1134. package/src/shard-recipes/house-venue.ts +0 -88
  1135. package/src/shard-recipes/index.ts +0 -95
  1136. package/src/shard-recipes/intersection.ts +0 -630
  1137. package/src/shard-recipes/locale.ts +0 -599
  1138. package/src/shard-recipes/nl-postcode.ts +0 -115
  1139. package/src/shard-recipes/no-fragment.ts +0 -219
  1140. package/src/shard-recipes/no-street-led.ts +0 -143
  1141. package/src/shard-recipes/no-street.ts +0 -86
  1142. package/src/shard-recipes/po-box-cedex.ts +0 -920
  1143. package/src/shard-recipes/po-box.ts +0 -119
  1144. package/src/shard-recipes/reviewed-postcode-tail.ts +0 -189
  1145. package/src/shard-recipes/scaffold.ts +0 -360
  1146. package/src/shard-recipes/si-bare-village.ts +0 -97
  1147. package/src/shard-recipes/street-affix.ts +0 -826
  1148. package/src/shard-recipes/street-bare.ts +0 -101
  1149. package/src/shard-recipes/street.ts +0 -82
  1150. package/src/shard-recipes/sub-venue-sources.ts +0 -885
  1151. package/src/shard-recipes/sub-venue.ts +0 -984
  1152. package/src/shard-recipes/trailing-region.ts +0 -183
  1153. package/src/shard-recipes/unit.ts +0 -321
  1154. package/src/synthesizers/anchor-absorption.ts +0 -290
  1155. package/src/synthesizers/boundary-stress.ts +0 -531
  1156. package/src/synthesizers/german.ts +0 -251
  1157. package/src/synthesizers/house-venue.ts +0 -330
  1158. package/src/synthesizers/intersection.ts +0 -232
  1159. package/src/synthesizers/no-street.ts +0 -349
  1160. package/src/synthesizers/po-box.ts +0 -339
  1161. package/src/synthesizers/street.ts +0 -274
  1162. package/src/synthesizers/utils.ts +0 -903
  1163. package/src/tools/align-shard.ts +0 -70
  1164. package/src/tools/audit.ts +0 -399
  1165. package/src/tools/corpus-stats.ts +0 -184
  1166. package/src/tools/fetch/ban.ts +0 -290
  1167. package/src/tools/fetch/download.ts +0 -176
  1168. package/src/tools/fetch/geonames-dump.ts +0 -267
  1169. package/src/tools/fetch/geonames-postal.ts +0 -180
  1170. package/src/tools/fetch/hrsa.ts +0 -68
  1171. package/src/tools/fetch/imls-pls.ts +0 -158
  1172. package/src/tools/fetch/index.ts +0 -147
  1173. package/src/tools/fetch/nad.ts +0 -342
  1174. package/src/tools/fetch/nppes.ts +0 -174
  1175. package/src/tools/fetch/openaddresses.ts +0 -404
  1176. package/src/tools/fetch/ourairports.ts +0 -171
  1177. package/src/tools/fetch/ppd.ts +0 -137
  1178. package/src/tools/fetch/state-hi-schools.ts +0 -208
  1179. package/src/tools/fetch/state-sources.ts +0 -155
  1180. package/src/tools/fetch/tiger-full.ts +0 -354
  1181. package/src/tools/fetch/wikidata-subvenue.ts +0 -386
  1182. package/src/tools/golden-expand.ts +0 -584
  1183. package/src/tools/golden-promote.ts +0 -353
  1184. package/src/tools/golden-relabel-street.ts +0 -685
  1185. package/src/tools/index.ts +0 -28
  1186. package/src/tools/ingest-csv.ts +0 -422
  1187. package/src/tools/jsonl-to-parquet.ts +0 -221
  1188. package/src/tools/lint-shard-vocab.ts +0 -409
  1189. package/src/tools/lint-shard.ts +0 -543
  1190. package/src/tools/overlay-manifest.ts +0 -157
  1191. package/src/tools/overture-subvenue.ts +0 -215
  1192. package/src/tools/postcode-triples.ts +0 -375
  1193. package/src/tools/shard-kryptonite.ts +0 -139
  1194. package/src/tools/shard-translit.ts +0 -245
  1195. package/src/tools/sub-venue/harvest.ts +0 -235
  1196. package/src/tools/sub-venue/head-nouns.ts +0 -242
  1197. package/src/tools/sub-venue/surfaces.ts +0 -95
  1198. package/src/tools/sub-venue/table.ts +0 -281
  1199. package/src/tools/sub-venue/wikidata.ts +0 -85
  1200. package/src/tools/sub-venue-lexicon.ts +0 -431
  1201. package/src/tools/sub-venue-promotions.ts +0 -330
  1202. package/src/types.ts +0 -247
  1203. package/src/utils/align.ts +0 -331
  1204. package/src/utils/golden.ts +0 -176
  1205. package/src/utils/index.ts +0 -14
  1206. package/src/utils/parquet.ts +0 -391
  1207. package/src/utils/split.ts +0 -279
  1208. package/src/utils/tokenize.ts +0 -78
  1209. package/src/utils/wof-json.ts +0 -244
  1210. /package/{src → lib}/adapters/state-ia-contractors/adapter.ts +0 -0
  1211. /package/{src → lib}/adapters/state-ny-notaries/adapter.ts +0 -0
  1212. /package/{src → lib}/adapters/state-tx-notaries/adapter.ts +0 -0
  1213. /package/{src → lib}/codex/us-fips-state.ts +0 -0
  1214. /package/{src → lib}/tools/gb-title-case.ts +0 -0
  1215. /package/{src → lib}/utils/license.ts +0 -0
  1216. /package/out/{src/adapters → adapters}/ban/adapter.d.ts +0 -0
  1217. /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
  1218. /package/out/{src/adapters → adapters}/fcc-bdc/adapter.d.ts +0 -0
  1219. /package/out/{src/adapters → adapters}/geonames/adapter.d.ts +0 -0
  1220. /package/out/{src/adapters → adapters}/openaddresses/adapter.d.ts +0 -0
  1221. /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.d.ts +0 -0
  1222. /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.js +0 -0
  1223. /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.d.ts +0 -0
  1224. /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.js +0 -0
  1225. /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.d.ts +0 -0
  1226. /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.js +0 -0
  1227. /package/out/{src/adapters → adapters}/synth-po-box/adapter.d.ts +0 -0
  1228. /package/out/{src/adapters → adapters}/tiger/street-decompose.d.ts +0 -0
  1229. /package/out/{src/adapters → adapters}/usgov-nppes/adapter.d.ts +0 -0
  1230. /package/out/{src/adapters → adapters}/usgov-samhsa-treatment-locator/adapter.d.ts +0 -0
  1231. /package/out/{src/adapters → adapters}/wof-admin-jp/adapter.d.ts +0 -0
  1232. /package/out/{src/codex → codex}/us-fips-state.d.ts +0 -0
  1233. /package/out/{src/codex → codex}/us-fips-state.js +0 -0
  1234. /package/out/{src/tools → tools}/fetch/ppd.d.ts +0 -0
  1235. /package/out/{src/tools → tools}/gb-title-case.d.ts +0 -0
  1236. /package/out/{src/tools → tools}/gb-title-case.js +0 -0
  1237. /package/out/{src/tools → tools}/golden-promote.d.ts +0 -0
  1238. /package/out/{src/tools → tools}/ingest-csv.d.ts +0 -0
  1239. /package/out/{src/types.js → types.js} +0 -0
  1240. /package/out/{src/utils → utils}/license.d.ts +0 -0
  1241. /package/out/{src/utils → utils}/license.js +0 -0
@@ -0,0 +1,159 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ * @file `cn-organizational-units` recipe (#2034) — real CN address strings whose settlement is an ORGANIZATIONAL
6
+ * ladder (`赵光三分场二十九队`: the Zhaoguang farm, No. 3 sub-farm, No. 29 production team), labeled by rule and aligned
7
+ * character by character for the CJK sibling model.
8
+ *
9
+ * THE LABELS ARE A READING OF THE SUFFIX, NOT A GUESS. Every generic that ends an ordinal unit (`分场`, `大队`, `队`,
10
+ * `连`, `团`, `组`, `场部`) is in `@mailwoman/core/locale/zh-cn-units`' one table, and the same table reads the span back
11
+ * after decode. The whole ordinal chain is ONE `locality_unit` span; the named head it belongs to (`赵光`, `孟定农场`) is
12
+ * `dependent_locality`; a province, city or county written in front of it takes `region`, `locality`, `subregion`; a
13
+ * Latin admin tail (`, Heilongjiang, China`) takes `region` and `country`. A row with no chain is skipped, not labeled:
14
+ * `红卫大队` is a village name whose generic carries no ordinal, and `苗辽林场` is a named forest farm.
15
+ *
16
+ * WHERE THE ROWS COME FROM. `--input` is a JSONL of `{ raw, country }` rows — the shape of `data/coarse-placer/*.jsonl`,
17
+ * whose 50,000 CN rows hold 328 with unit vocabulary. That file is a local artifact and carries no per-row source; the
18
+ * `<name>, <admin1>, <country>` shape is the corpus's GeoNames adapter's, so the rows are stamped with GeoNames'
19
+ * licence and the inference is stated in the `license` field rather than hidden behind it.
20
+ *
21
+ * FOR THE CJK MODEL ONLY. The tokenizer is {@link cjkAwareTokenizer}: one token per Han character, because the
22
+ * whitespace tokenizer reads `三分场八队` as one word and could never give it two labels. The Latin model never trains
23
+ * on this recipe's rows; its label set has no `locality_unit`.
24
+ */
25
+ import { splitCNUnitChain } from "@mailwoman/core/locale/zh-cn-units";
26
+ import { readTuples, sliceSourceID } from "#recipes/scaffold";
27
+ import { alignRow } from "#utils/align";
28
+ import { cjkAwareTokenizer } from "#utils/tokenize";
29
+ /**
30
+ * The leading run of Han characters (plus the digits an ordinal may be written with): the Chinese half of a row.
31
+ */
32
+ const LEADING_HAN = /^[\p{Script=Han}〇\d]+/u;
33
+ /**
34
+ * Admin prefixes a CJK address writes in front of the settlement, coarsest first. Each is matched at the START of what
35
+ * remains, so `云南省临沧市孟定农场三分场二队` peels `云南省` (province), `临沧市` (city), and hands `孟定农场三分场二队` to the unit reader.
36
+ */
37
+ const ADMIN_PREFIXES = [
38
+ [/^(.+?(?:省|自治区))/u, "region"],
39
+ [/^(.+?市)/u, "locality"],
40
+ [/^(.+?(?:自治县|县|旗))/u, "subregion"],
41
+ ];
42
+ /**
43
+ * The components a row's string supports, every value a verbatim substring of `raw`, or `null` when the string carries
44
+ * no organizational chain and so teaches nothing this recipe exists for.
45
+ */
46
+ export function labelCNOrganizationalRow(raw) {
47
+ const han = LEADING_HAN.exec(raw)?.[0];
48
+ if (!han)
49
+ return null;
50
+ const components = {};
51
+ let rest = han;
52
+ for (const [pattern, tag] of ADMIN_PREFIXES) {
53
+ const match = pattern.exec(rest);
54
+ // A prefix must leave something behind it, or the whole run was the admin name and there is no settlement.
55
+ if (match && match[1].length < rest.length) {
56
+ components[tag] = match[1];
57
+ rest = rest.slice(match[1].length);
58
+ }
59
+ }
60
+ const split = splitCNUnitChain(rest);
61
+ if (!split)
62
+ return null;
63
+ if (split.head) {
64
+ components.dependent_locality = split.head;
65
+ }
66
+ components.locality_unit = split.chain;
67
+ const tail = raw.slice(han.length).trim();
68
+ if (tail) {
69
+ // `, Heilongjiang, China` or `Hunan China` or `Inner Mongolia`: comma segments when there are commas, else the last
70
+ // word is the country when it says so and the rest is the admin1 name.
71
+ const segments = tail.includes(",")
72
+ ? tail
73
+ .split(",")
74
+ .map((segment) => segment.trim())
75
+ .filter((segment) => segment.length > 0)
76
+ : tailWithoutCommas(tail);
77
+ for (const segment of segments) {
78
+ if (/^china$/iu.test(segment)) {
79
+ components.country = segment;
80
+ }
81
+ else if (!components.region && !/^\d+$/u.test(segment)) {
82
+ components.region = segment;
83
+ }
84
+ }
85
+ }
86
+ return components;
87
+ }
88
+ /**
89
+ * A space-separated tail: `Hunan China` → [`Hunan`, `China`]; `Inner Mongolia` → [`Inner Mongolia`]; `Xinjiang Uyghur`
90
+ * → [`Xinjiang Uyghur`].
91
+ */
92
+ function tailWithoutCommas(tail) {
93
+ const words = tail.split(/\s+/u).filter((word) => word.length > 0);
94
+ const last = words.at(-1);
95
+ if (last && /^china$/iu.test(last) && words.length > 1) {
96
+ return [words.slice(0, -1).join(" "), last];
97
+ }
98
+ return [words.join(" ")];
99
+ }
100
+ const SOURCE = "coarse-placer-cn-units";
101
+ /**
102
+ * Slice recipe registered with the corpus builder — see the file header for the rows it labels and why every label is a
103
+ * reading of a generic rather than a guess.
104
+ */
105
+ export const cnOrganizationalUnitsRecipe = {
106
+ name: "cn-organizational-units",
107
+ description: "CN rows whose settlement is an organizational ladder (分场/队/连/组), labeled by the suffix grammar as one locality_unit span, per-character BIO",
108
+ mode: "tuples",
109
+ options: [],
110
+ async run(opts, write) {
111
+ if (!opts.input) {
112
+ throw new Error("cn-organizational-units: --input <rows.jsonl> is required ({ raw, country } rows)");
113
+ }
114
+ const tokenizer = cjkAwareTokenizer();
115
+ let emitted = 0;
116
+ let skipped = 0;
117
+ let quarantined = 0;
118
+ for await (const tuple of readTuples(opts.input)) {
119
+ const raw = typeof tuple["raw"] === "string" ? tuple["raw"].trim() : "";
120
+ const country = typeof tuple["country"] === "string" ? tuple["country"].toUpperCase() : "CN";
121
+ if (!raw || country !== "CN") {
122
+ skipped++;
123
+ continue;
124
+ }
125
+ const components = labelCNOrganizationalRow(raw);
126
+ if (!components) {
127
+ skipped++;
128
+ continue;
129
+ }
130
+ if (opts.golden) {
131
+ write(JSON.stringify({ raw, components, country: "CN", locale: "zh-CN" }) + "\n");
132
+ emitted++;
133
+ continue;
134
+ }
135
+ const canonical = {
136
+ raw,
137
+ components,
138
+ country: "CN",
139
+ locale: "zh-CN",
140
+ source: opts.sourceName ?? SOURCE,
141
+ source_id: sliceSourceID(opts.sourceName ?? SOURCE, { raw }),
142
+ corpus_version: "0.4.0",
143
+ license: "CC-BY-4.0 — GeoNames populated places, INFERRED from the `<name>, <admin1>, <country>` row shape; data/coarse-placer carries no per-row source",
144
+ };
145
+ // Verbatim only: every value above was sliced out of `raw`, so an edit-distance match would mean this file
146
+ // has a bug, not that the source spells something differently.
147
+ const aligned = alignRow(canonical, { tokenizer, maxEditDistance: 0 });
148
+ if (aligned.kind !== "labeled" || !aligned.row) {
149
+ quarantined++;
150
+ continue;
151
+ }
152
+ write(JSON.stringify({ ...aligned.row, synth_method: "cn-organizational-units", synth_base_id: null }) + "\n");
153
+ emitted++;
154
+ }
155
+ console.error(` cn-organizational-units: ${emitted} labeled, ${skipped} without a chain, ${quarantined} quarantined`);
156
+ return { emitted, skipped, quarantined };
157
+ },
158
+ };
159
+ //# sourceMappingURL=cn-organizational-units.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"cn-organizational-units.js","sourceRoot":"","sources":["../../lib/recipes/cn-organizational-units.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAEH,OAAO,EAAE,gBAAgB,EAAE,MAAM,oCAAoC,CAAA;AAErE,OAAO,EAAqB,UAAU,EAAE,aAAa,EAAE,MAAM,mBAAmB,CAAA;AAChF,OAAO,EAAE,QAAQ,EAAE,MAAM,cAAc,CAAA;AACvC,OAAO,EAAE,iBAAiB,EAAE,MAAM,iBAAiB,CAAA;AAEnD;;GAEG;AACH,MAAM,WAAW,GAAG,wBAAwB,CAAA;AAE5C;;;GAGG;AACH,MAAM,cAAc,GAAwF;IAC3G,CAAC,kBAAkB,EAAE,QAAQ,CAAC;IAC9B,CAAC,UAAU,EAAE,UAAU,CAAC;IACxB,CAAC,oBAAoB,EAAE,WAAW,CAAC;CACnC,CAAA;AAED;;;GAGG;AACH,MAAM,UAAU,wBAAwB,CAAC,GAAW;IACnD,MAAM,GAAG,GAAG,WAAW,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;IAEtC,IAAI,CAAC,GAAG;QAAE,OAAO,IAAI,CAAA;IAErB,MAAM,UAAU,GAA2B,EAAE,CAAA;IAC7C,IAAI,IAAI,GAAG,GAAG,CAAA;IAEd,KAAK,MAAM,CAAC,OAAO,EAAE,GAAG,CAAC,IAAI,cAAc,EAAE,CAAC;QAC7C,MAAM,KAAK,GAAG,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QAEhC,2GAA2G;QAC3G,IAAI,KAAK,IAAI,KAAK,CAAC,CAAC,CAAE,CAAC,MAAM,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC;YAC7C,UAAU,CAAC,GAAG,CAAC,GAAG,KAAK,CAAC,CAAC,CAAE,CAAA;YAC3B,IAAI,GAAG,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,CAAE,CAAC,MAAM,CAAC,CAAA;QACpC,CAAC;IACF,CAAC;IAED,MAAM,KAAK,GAAG,gBAAgB,CAAC,IAAI,CAAC,CAAA;IAEpC,IAAI,CAAC,KAAK;QAAE,OAAO,IAAI,CAAA;IAEvB,IAAI,KAAK,CAAC,IAAI,EAAE,CAAC;QAChB,UAAU,CAAC,kBAAkB,GAAG,KAAK,CAAC,IAAI,CAAA;IAC3C,CAAC;IAED,UAAU,CAAC,aAAa,GAAG,KAAK,CAAC,KAAK,CAAA;IAEtC,MAAM,IAAI,GAAG,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,CAAA;IAEzC,IAAI,IAAI,EAAE,CAAC;QACV,oHAAoH;QACpH,uEAAuE;QACvE,MAAM,QAAQ,GAAG,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC;YAClC,CAAC,CAAC,IAAI;iBACH,KAAK,CAAC,GAAG,CAAC;iBACV,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC;iBAChC,MAAM,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,CAAC,MAAM,GAAG,CAAC,CAAC;YAC1C,CAAC,CAAC,iBAAiB,CAAC,IAAI,CAAC,CAAA;QAE1B,KAAK,MAAM,OAAO,IAAI,QAAQ,EAAE,CAAC;YAChC,IAAI,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE,CAAC;gBAC/B,UAAU,CAAC,OAAO,GAAG,OAAO,CAAA;YAC7B,CAAC;iBAAM,IAAI,CAAC,UAAU,CAAC,MAAM,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE,CAAC;gBAC1D,UAAU,CAAC,MAAM,GAAG,OAAO,CAAA;YAC5B,CAAC;QACF,CAAC;IACF,CAAC;IAED,OAAO,UAAU,CAAA;AAClB,CAAC;AAED;;;GAGG;AACH,SAAS,iBAAiB,CAAC,IAAY;IACtC,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,MAAM,GAAG,CAAC,CAAC,CAAA;IAClE,MAAM,IAAI,GAAG,KAAK,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,CAAA;IAEzB,IAAI,IAAI,IAAI,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACxD,OAAO,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,IAAI,CAAC,CAAA;IAC5C,CAAC;IAED,OAAO,CAAC,KAAK,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAA;AACzB,CAAC;AAED,MAAM,MAAM,GAAG,wBAAwB,CAAA;AAEvC;;;GAGG;AACH,MAAM,CAAC,MAAM,2BAA2B,GAAiB;IACxD,IAAI,EAAE,yBAAyB;IAC/B,WAAW,EACV,6IAA6I;IAC9I,IAAI,EAAE,QAAQ;IACd,OAAO,EAAE,EAAE;IACX,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,IAAI,CAAC,IAAI,CAAC,KAAK,EAAE,CAAC;YACjB,MAAM,IAAI,KAAK,CAAC,mFAAmF,CAAC,CAAA;QACrG,CAAC;QAED,MAAM,SAAS,GAAG,iBAAiB,EAAE,CAAA;QACrC,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,WAAW,GAAG,CAAC,CAAA;QAEnB,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,UAAU,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;YAClD,MAAM,GAAG,GAAG,OAAO,KAAK,CAAC,KAAK,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;YACvE,MAAM,OAAO,GAAG,OAAO,KAAK,CAAC,SAAS,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,SAAS,CAAC,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,IAAI,CAAA;YAE5F,IAAI,CAAC,GAAG,IAAI,OAAO,KAAK,IAAI,EAAE,CAAC;gBAC9B,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,MAAM,UAAU,GAAG,wBAAwB,CAAC,GAAG,CAAC,CAAA;YAEhD,IAAI,CAAC,UAAU,EAAE,CAAC;gBACjB,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC;gBACjB,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,GAAG,EAAE,UAAU,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,EAAE,OAAO,EAAE,CAAC,GAAG,IAAI,CAAC,CAAA;gBAEjF,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,MAAM,SAAS,GAAG;gBACjB,GAAG;gBACH,UAAU;gBACV,OAAO,EAAE,IAAI;gBACb,MAAM,EAAE,OAAO;gBACf,MAAM,EAAE,IAAI,CAAC,UAAU,IAAI,MAAM;gBACjC,SAAS,EAAE,aAAa,CAAC,IAAI,CAAC,UAAU,IAAI,MAAM,EAAE,EAAE,GAAG,EAAE,CAAC;gBAC5D,cAAc,EAAE,OAAO;gBACvB,OAAO,EACN,gJAAgJ;aACjJ,CAAA;YAED,2GAA2G;YAC3G,+DAA+D;YAC/D,MAAM,OAAO,GAAG,QAAQ,CAAC,SAA2C,EAAE,EAAE,SAAS,EAAE,eAAe,EAAE,CAAC,EAAE,CAAC,CAAA;YAExG,IAAI,OAAO,CAAC,IAAI,KAAK,SAAS,IAAI,CAAC,OAAO,CAAC,GAAG,EAAE,CAAC;gBAChD,WAAW,EAAE,CAAA;gBAEb,SAAQ;YACT,CAAC;YAED,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,GAAG,OAAO,CAAC,GAAG,EAAE,YAAY,EAAE,yBAAyB,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,GAAG,IAAI,CAAC,CAAA;YAE9G,OAAO,EAAE,CAAA;QACV,CAAC;QAED,OAAO,CAAC,KAAK,CACZ,8BAA8B,OAAO,aAAa,OAAO,qBAAqB,WAAW,cAAc,CACvG,CAAA;QAED,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,WAAW,EAAE,CAAA;IACzC,CAAC;CACD,CAAA"}
@@ -0,0 +1,32 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ *
6
+ * `country-balanced` slice recipe — the BALANCED, MODEL-FIRST country-coverage slice (#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` slice did, but built to AVOID over-firing "trailing token ⇒ country". Three
9
+ * ingredients, ported faithfully from scripts/build-country-slice-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 { type CorpusRecipe } from "#recipes/scaffold";
27
+ /**
28
+ * Slice recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
29
+ * and `description` below for the surface form it generates.
30
+ */
31
+ export declare const countryBalancedRecipe: CorpusRecipe;
32
+ //# sourceMappingURL=country-balanced.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"country-balanced.d.ts","sourceRoot":"","sources":["../../lib/recipes/country-balanced.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;GAwBG;AASH,OAAO,EAAgC,KAAK,YAAY,EAAE,MAAM,mBAAmB,CAAA;AAmXnF;;;GAGG;AACH,eAAO,MAAM,qBAAqB,EAAE,YAoGnC,CAAA"}
@@ -0,0 +1,393 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ *
6
+ * `country-balanced` slice recipe — the BALANCED, MODEL-FIRST country-coverage slice (#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` slice did, but built to AVOID over-firing "trailing token ⇒ country". Three
9
+ * ingredients, ported faithfully from scripts/build-country-slice-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/data-root";
28
+ import { isPresent } from "@mailwoman/core/objects";
29
+ import { stableSourceID } from "#adapters/utils";
30
+ import { makeMulberry32, readOATuples } from "#recipes/scaffold";
31
+ import { pick } from "#synthesizers/utils";
32
+ import { alignRow } from "#utils";
33
+ // v2: the country TOKEN is decoupled from the skeleton's locale and drawn from a BROAD pool — every
34
+ // ISO canonical name + every curated surface form (endonyms/abbrevs). Surface forms are over-weighted
35
+ // so endonyms/abbrevs ("Deutschland","USA","NL") get strong signal.
36
+ const COUNTRY_FORM_POOL = (() => {
37
+ const surface = Object.values(COUNTRY_SURFACE_FORMS).flat(); // endonyms + abbrevs + canonical (curated)
38
+ const names = [...CountryNames];
39
+ // all ~249 ISO canonical English names (breadth)
40
+ return { surface, names };
41
+ })();
42
+ /**
43
+ * Negatives: rows with NO country token → teach golden precision.
44
+ */
45
+ const COUNTRY_ABSENT_PROB = 0.3;
46
+ /**
47
+ * Multi-locale OA sources. region = implied admin where the extract is single-region (US states, DE Saxony);
48
+ * countrywide extracts (FR/IT/NL) read region from the CSV when present.
49
+ */
50
+ const SOURCES = [
51
+ {
52
+ zip: dataRootPath("oa-cache", "us__ia__statewide.zip"),
53
+ csv: "us/ia/statewide.csv",
54
+ iso2: "US",
55
+ region: "IA",
56
+ order: "us",
57
+ },
58
+ { zip: dataRootPath("oa-cache", "us__il__cook.zip"), csv: "us/il/cook.csv", iso2: "US", region: "IL", order: "us" },
59
+ {
60
+ zip: dataRootPath("oa-cache", "us__mt__statewide.zip"),
61
+ csv: "us/mt/statewide.csv",
62
+ iso2: "US",
63
+ region: "MT",
64
+ order: "us",
65
+ },
66
+ {
67
+ zip: dataRootPath("oa-cache", "us__sd__statewide.zip"),
68
+ csv: "us/sd/statewide.csv",
69
+ iso2: "US",
70
+ region: "SD",
71
+ order: "us",
72
+ },
73
+ {
74
+ zip: dataRootPath("oa-cache", "de__sn__statewide.zip"),
75
+ csv: "de/sn/statewide.csv",
76
+ iso2: "DE",
77
+ region: "",
78
+ order: "eu",
79
+ },
80
+ {
81
+ zip: dataRootPath("oa-cache", "fr__countrywide.zip"),
82
+ csv: "fr/countrywide.csv",
83
+ iso2: "FR",
84
+ region: "",
85
+ order: "fr",
86
+ },
87
+ // ES uses the Spanish IGN schema, not the OA standard columns — skipped here (codex still recognizes
88
+ // "España"/"Spain"). A dedicated IGN adapter is a follow-up.
89
+ {
90
+ zip: dataRootPath("oa-cache", "it__countrywide.zip"),
91
+ csv: "it/countrywide.csv",
92
+ iso2: "IT",
93
+ region: "",
94
+ order: "eu",
95
+ },
96
+ {
97
+ zip: dataRootPath("oa-cache", "nl__countrywide.zip"),
98
+ csv: "nl/countrywide.csv",
99
+ iso2: "NL",
100
+ region: "",
101
+ order: "eu",
102
+ },
103
+ ];
104
+ /**
105
+ * Held-out for --golden: Vermont (US holdout) + Berlin (DE holdout) — geographic split, never trained.
106
+ */
107
+ const EVAL_SOURCES = [
108
+ {
109
+ zip: dataRootPath("oa-cache", "us__vt__statewide.zip"),
110
+ csv: "us/vt/statewide.csv",
111
+ iso2: "US",
112
+ region: "VT",
113
+ order: "us",
114
+ },
115
+ { zip: dataRootPath("oa-cache", "de__berlin.zip"), csv: "de/berlin.csv", iso2: "DE", region: "", order: "eu" },
116
+ ];
117
+ /**
118
+ * The countrywide extracts (FR/IT/NL) are GB-scale, so this reads only as far as `limit` distinct tuples: the `break`
119
+ * closes the reader, which releases the archive without inflating the rest of the member.
120
+ */
121
+ async function readTuples(source, limit) {
122
+ return readOATuples(source, {
123
+ limit,
124
+ extra: (fields, row) => ({
125
+ ...fields,
126
+ region: row.region || source.region,
127
+ iso2: source.iso2,
128
+ order: source.order,
129
+ }),
130
+ });
131
+ }
132
+ // After the absent draw: 60% curated surface forms (endonym/abbrev variety), 40% broad ISO canonical names.
133
+ const SURFACE_FORM_SHARE = 0.6;
134
+ /**
135
+ * Pick a country token from the BROAD pool, or null (a country-absent negative). v2.
136
+ */
137
+ function pickCountry(random) {
138
+ if (random() < COUNTRY_ABSENT_PROB)
139
+ return null; // negative — teaches "trailing token != always country"
140
+ const pool = random() < SURFACE_FORM_SHARE ? COUNTRY_FORM_POOL.surface : COUNTRY_FORM_POOL.names;
141
+ return pick(pool, random);
142
+ }
143
+ // Country-bearing rows: 80% full, 12% full-nl, 8% bare.
144
+ const FULL_CUTOFF = 0.8;
145
+ const FULL_NEWLINE_CUTOFF = 0.92;
146
+ /**
147
+ * Render the address body in native-ish order. `country` null → a country-ABSENT negative row.
148
+ */
149
+ function renderCountry(random, t, country) {
150
+ const { house_number: hn, street, locality: loc, region: reg, postcode: pc, order } = t;
151
+ const components = { house_number: hn, street, locality: loc };
152
+ if (reg) {
153
+ components.region = reg;
154
+ }
155
+ if (pc) {
156
+ components.postcode = pc;
157
+ }
158
+ let body;
159
+ if (order === "us") {
160
+ const regPc = [reg, pc].filter(isPresent).join(" ");
161
+ body = `${hn} ${street}, ${loc}${regPc ? ", " + regPc : ""}`;
162
+ }
163
+ else if (order === "fr") {
164
+ // French is NUMBER-street, postcode-city: "84 Route de la Fontaine, 75008 Paris".
165
+ body = `${hn} ${street}, ${[pc, loc].filter(isPresent).join(" ")}`;
166
+ }
167
+ else {
168
+ // DE/IT/NL: street-number, postcode-city: "Pariser Platz 1, 10117 Berlin".
169
+ const pcCity = [pc, loc].filter(isPresent).join(" ");
170
+ body = `${street} ${hn}, ${pcCity}`;
171
+ }
172
+ if (!country) {
173
+ // Negative: a normal address, NO country token/component. Teaches that a trailing region/city/
174
+ // postcode is NOT a country (counters the v1 golden over-firing).
175
+ return { fmt: "negative", raw: body, components };
176
+ }
177
+ const withC = { ...components, country };
178
+ const r = random();
179
+ if (r < FULL_CUTOFF)
180
+ return { fmt: "full", raw: `${body}, ${country}`, components: withC };
181
+ if (r < FULL_NEWLINE_CUTOFF)
182
+ return { fmt: "full-nl", raw: `${body}\n${country}`, components: withC };
183
+ const bareBody = order === "us" || order === "fr" ? `${hn} ${street}, ${loc}` : `${street} ${hn}, ${loc}`;
184
+ return {
185
+ fmt: "bare",
186
+ raw: `${bareBody}, ${country}`,
187
+ components: { house_number: hn, street, locality: loc, country },
188
+ };
189
+ }
190
+ const HOMOGRAPHS = [
191
+ {
192
+ surface: "Georgia",
193
+ iso2: "GE",
194
+ cities: ["Tbilisi", "Batumi", "Kutaisi", "Rustavi"],
195
+ us: { role: "region", locality: "Atlanta", region: "Georgia", postcodes: ["30309", "31401", "30601", "31201"] },
196
+ },
197
+ {
198
+ surface: "Jordan",
199
+ iso2: "JO",
200
+ cities: ["Amman", "Irbid", "Zarqa", "Aqaba"],
201
+ us: { role: "locality", locality: "Jordan", region: "MN", postcodes: ["55352"] },
202
+ },
203
+ {
204
+ surface: "Lebanon",
205
+ iso2: "LB",
206
+ cities: ["Beirut", "Tripoli", "Sidon", "Byblos"],
207
+ us: { role: "locality", locality: "Lebanon", region: "TN", postcodes: ["37087", "03766", "17042", "45036"] },
208
+ },
209
+ {
210
+ surface: "Mexico",
211
+ iso2: "MX",
212
+ cities: ["Guadalajara", "Monterrey", "Puebla", "Oaxaca"],
213
+ us: { role: "locality", locality: "Mexico", region: "MO", postcodes: ["65265"] },
214
+ },
215
+ {
216
+ surface: "Peru",
217
+ iso2: "PE",
218
+ cities: ["Cusco", "Arequipa", "Trujillo", "Iquitos"],
219
+ us: { role: "locality", locality: "Peru", region: "IL", postcodes: ["61354", "46970"] },
220
+ },
221
+ {
222
+ surface: "Turkey",
223
+ iso2: "TR",
224
+ cities: ["Ankara", "Izmir", "Bursa", "Antalya"],
225
+ us: { role: "locality", locality: "Turkey", region: "TX", postcodes: ["79261", "28393"] },
226
+ },
227
+ ];
228
+ const ABBREV_REGIONS = [
229
+ { code: "CA", localities: ["Los Angeles", "Sacramento", "San Diego"], postcodes: ["90012", "95814", "92101"] }, // California / Canada
230
+ { code: "GA", localities: ["Atlanta", "Savannah", "Macon"], postcodes: ["30309", "31401", "31201"] }, // Georgia(US) / Georgia
231
+ { code: "IN", localities: ["Indianapolis", "Fort Wayne"], postcodes: ["46204", "46802"] }, // Indiana / India
232
+ { code: "MA", localities: ["Boston", "Worcester"], postcodes: ["02108", "01608"] }, // Massachusetts / Morocco
233
+ { code: "PA", localities: ["Philadelphia", "Pittsburgh"], postcodes: ["19103", "15222"] }, // Pennsylvania / Panama
234
+ { code: "AL", localities: ["Birmingham", "Montgomery"], postcodes: ["35203", "36104"] }, // Alabama / Albania
235
+ ];
236
+ const STREET_POOL = [
237
+ "Main Street",
238
+ "Oak Avenue",
239
+ "Park Road",
240
+ "Elm Street",
241
+ "Hill Road",
242
+ "Market Street",
243
+ "Church Street",
244
+ "King Street",
245
+ "2nd Avenue",
246
+ "Maple Drive",
247
+ ];
248
+ const houseNo = (random) => String(1 + Math.floor(random() * 998));
249
+ // Country-surface homograph rows: 60% carry a street line, 40% are a bare `city, surface`.
250
+ const HOMOGRAPH_WITH_STREET_SHARE = 0.6;
251
+ /**
252
+ * A homograph CONTRAST row: ~half render the surface as `country` (foreign city), half as the US `region`/`locality`
253
+ * (US ZIP, NO country). Returns iso2 for provenance.
254
+ */
255
+ function renderHomograph(random) {
256
+ const h = pick(HOMOGRAPHS, random);
257
+ const hn = houseNo(random), street = pick(STREET_POOL, random);
258
+ if (random() < 0.5) {
259
+ const city = pick(h.cities, random);
260
+ const withStreet = random() < HOMOGRAPH_WITH_STREET_SHARE;
261
+ const raw = withStreet ? `${hn} ${street}, ${city}, ${h.surface}` : `${city}, ${h.surface}`;
262
+ const components = withStreet
263
+ ? { house_number: hn, street, locality: city, country: h.surface }
264
+ : { locality: city, country: h.surface };
265
+ return { fmt: "homograph-country", raw, components, iso2: h.iso2 };
266
+ }
267
+ const pc = pick(h.us.postcodes, random);
268
+ if (h.us.role === "region") {
269
+ // surface is the US STATE: "123 Oak Ave, Atlanta, Georgia 30309" → region, no country
270
+ return {
271
+ fmt: "homograph-us-region",
272
+ raw: `${hn} ${street}, ${h.us.locality}, ${h.surface} ${pc}`,
273
+ components: { house_number: hn, street, locality: h.us.locality, region: h.surface, postcode: pc },
274
+ iso2: "US",
275
+ };
276
+ }
277
+ // surface is the US CITY: "123 Oak Ave, Lebanon, TN 37087" → locality, no country
278
+ return {
279
+ fmt: "homograph-us-locality",
280
+ raw: `${hn} ${street}, ${h.surface}, ${h.us.region} ${pc}`,
281
+ components: { house_number: hn, street, locality: h.surface, region: h.us.region, postcode: pc },
282
+ iso2: "US",
283
+ };
284
+ }
285
+ /**
286
+ * An abbrev-as-region negative: "123 Main St, Los Angeles, CA 90012" → region CA, NO country.
287
+ */
288
+ function renderAbbrevRegion(random) {
289
+ const a = pick(ABBREV_REGIONS, random);
290
+ const hn = houseNo(random), street = pick(STREET_POOL, random), locality = pick(a.localities, random), postcode = pick(a.postcodes, random);
291
+ return {
292
+ fmt: "abbrev-region",
293
+ raw: `${hn} ${street}, ${locality}, ${a.code} ${postcode}`,
294
+ components: { house_number: hn, street, locality, region: a.code, postcode },
295
+ iso2: "US",
296
+ };
297
+ }
298
+ /**
299
+ * Share of rows that are homograph contrast pairs.
300
+ */
301
+ const HOMOGRAPH_FRAC = 0.22;
302
+ /**
303
+ * Share that are code-as-region negatives (cumulative with HOMOGRAPH_FRAC)
304
+ */
305
+ const ABBREV_FRAC = 0.08;
306
+ /**
307
+ * Slice recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
308
+ * and `description` below for the surface form it generates.
309
+ */
310
+ export const countryBalancedRecipe = {
311
+ name: "country-balanced",
312
+ description: "Balanced model-first country rows (#464): OA skeletons + ISO surface forms + homograph contrast pairs",
313
+ mode: "generate",
314
+ options: [{ flag: "--golden", description: "Emit the held-out VT+Berlin eval slice" }],
315
+ async run(opts, write) {
316
+ if (opts.count == null)
317
+ throw new Error("country-balanced recipe requires --count <N>");
318
+ const count = opts.count;
319
+ // Legacy build-country-slice-balanced.mjs seeded mulberry32 with the raw seed: `const random = mulberry32(opts.seed)`.
320
+ const random = makeMulberry32(opts.seed);
321
+ const source = opts.sourceName ?? "synth-country";
322
+ const sources = opts.golden ? EVAL_SOURCES : SOURCES;
323
+ const perSource = Math.ceil((count * 3) / sources.length); // over-read; balance locales
324
+ const pool = [];
325
+ for (const s of sources) {
326
+ const t = await readTuples(s, perSource);
327
+ console.error(` ${s.csv} (${s.iso2}): ${t.length} tuples`);
328
+ for (const x of t) {
329
+ pool.push(x);
330
+ }
331
+ }
332
+ if (!pool.length) {
333
+ throw new Error(`No tuples — are the cached OA zips present in ${dataRootPath("oa-cache")}?`);
334
+ }
335
+ let emitted = 0;
336
+ let skipped = 0;
337
+ let guard = 0;
338
+ const N = pool.length;
339
+ while (emitted < count && guard++ < count * 8) {
340
+ // Mix three row types: homograph contrast (the distinction), code-as-region negatives, and the
341
+ // breadth/recall main path (random ISO form on an OA skeleton, ~30% country-absent).
342
+ const roll = random();
343
+ let rendered;
344
+ let rowISO2;
345
+ if (roll < HOMOGRAPH_FRAC) {
346
+ const h = renderHomograph(random);
347
+ rendered = h;
348
+ rowISO2 = h.iso2;
349
+ }
350
+ else if (roll < HOMOGRAPH_FRAC + ABBREV_FRAC) {
351
+ const a = renderAbbrevRegion(random);
352
+ rendered = a;
353
+ rowISO2 = a.iso2;
354
+ }
355
+ else {
356
+ const t = pool[Math.floor(random() * N)];
357
+ const country = pickCountry(random); // may be null → a country-absent negative row
358
+ rendered = renderCountry(random, t, country);
359
+ rowISO2 = t.iso2;
360
+ if (country && !rendered.raw.includes(country)) {
361
+ skipped++;
362
+ continue;
363
+ }
364
+ }
365
+ const { raw, components } = rendered;
366
+ const localeTag = rowISO2 === "US" ? "en-US" : `${rowISO2.toLowerCase()}-${rowISO2}`;
367
+ if (opts.golden) {
368
+ write(JSON.stringify({ raw, components, country: rowISO2 }) + "\n");
369
+ emitted++;
370
+ continue;
371
+ }
372
+ const canonical = {
373
+ raw,
374
+ components,
375
+ country: rowISO2,
376
+ locale: localeTag,
377
+ source,
378
+ source_id: stableSourceID(source, components),
379
+ corpus_version: "0.4.0",
380
+ license: "OpenAddresses multi-locale skeletons + injected ISO-3166 country surface forms (codex)",
381
+ };
382
+ const aligned = alignRow(canonical);
383
+ if (aligned.kind !== "labeled" || !aligned.row) {
384
+ skipped++;
385
+ continue;
386
+ }
387
+ write(JSON.stringify({ ...aligned.row, synth_method: "country", synth_base_id: null }) + "\n");
388
+ emitted++;
389
+ }
390
+ return { emitted, skipped };
391
+ },
392
+ };
393
+ //# sourceMappingURL=country-balanced.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"country-balanced.js","sourceRoot":"","sources":["../../lib/recipes/country-balanced.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;GAwBG;AAEH,OAAO,EAAE,qBAAqB,EAAE,YAAY,EAAE,MAAM,0BAA0B,CAAA;AAC9E,OAAO,EAAE,YAAY,EAAE,MAAM,2BAA2B,CAAA;AACxD,OAAO,EAAE,SAAS,EAAE,MAAM,yBAAyB,CAAA;AAInD,OAAO,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAA;AAChD,OAAO,EAAE,cAAc,EAAE,YAAY,EAAqB,MAAM,mBAAmB,CAAA;AACnF,OAAO,EAAE,IAAI,EAAE,MAAM,qBAAqB,CAAA;AAE1C,OAAO,EAAE,QAAQ,EAAE,MAAM,QAAQ,CAAA;AAEjC,oGAAoG;AACpG,sGAAsG;AACtG,oEAAoE;AAEpE,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,OAAO,YAAY,CAAC,MAAM,EAAE;QAC3B,KAAK;QACL,KAAK,EAAE,CAAC,MAAM,EAAE,GAAG,EAAE,EAAE,CAAC,CAAC;YACxB,GAAG,MAAM;YACT,MAAM,EAAE,GAAG,CAAC,MAAM,IAAI,MAAM,CAAC,MAAM;YACnC,IAAI,EAAE,MAAM,CAAC,IAAI;YACjB,KAAK,EAAE,MAAM,CAAC,KAAK;SACnB,CAAC;KACF,CAAC,CAAA;AACH,CAAC;AAED,4GAA4G;AAC5G,MAAM,kBAAkB,GAAG,GAAG,CAAA;AAE9B;;GAEG;AACH,SAAS,WAAW,CAAC,MAAoB;IACxC,IAAI,MAAM,EAAE,GAAG,mBAAmB;QAAE,OAAO,IAAI,CAAA,CAAC,wDAAwD;IACxG,MAAM,IAAI,GAAG,MAAM,EAAE,GAAG,kBAAkB,CAAC,CAAC,CAAC,iBAAiB,CAAC,OAAO,CAAC,CAAC,CAAC,iBAAiB,CAAC,KAAK,CAAA;IAEhG,OAAO,IAAI,CAAC,IAAI,EAAE,MAAM,CAAC,CAAA;AAC1B,CAAC;AAED,wDAAwD;AACxD,MAAM,WAAW,GAAG,GAAG,CAAA;AACvB,MAAM,mBAAmB,GAAG,IAAI,CAAA;AAEhC;;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,SAAS,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;QACnD,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,SAAS,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,CAAA;IACnE,CAAC;SAAM,CAAC;QACP,2EAA2E;QAC3E,MAAM,MAAM,GAAG,CAAC,EAAE,EAAE,GAAG,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;QACpD,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,WAAW;QAAE,OAAO,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE,GAAG,IAAI,KAAK,OAAO,EAAE,EAAE,UAAU,EAAE,KAAK,EAAE,CAAA;IAE1F,IAAI,CAAC,GAAG,mBAAmB;QAAE,OAAO,EAAE,GAAG,EAAE,SAAS,EAAE,GAAG,EAAE,GAAG,IAAI,KAAK,OAAO,EAAE,EAAE,UAAU,EAAE,KAAK,EAAE,CAAA;IACrG,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,OAAO,GAAG,CAAC,MAAoB,EAAU,EAAE,CAAC,MAAM,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,GAAG,CAAC,CAAC,CAAA;AAExF,2FAA2F;AAC3F,MAAM,2BAA2B,GAAG,GAAG,CAAA;AAEvC;;;GAGG;AACH,SAAS,eAAe,CAAC,MAAoB;IAM5C,MAAM,CAAC,GAAG,IAAI,CAAC,UAAU,EAAE,MAAM,CAAC,CAAA;IAElC,MAAM,EAAE,GAAG,OAAO,CAAC,MAAM,CAAC,EACzB,MAAM,GAAG,IAAI,CAAC,WAAW,EAAE,MAAM,CAAC,CAAA;IAEnC,IAAI,MAAM,EAAE,GAAG,GAAG,EAAE,CAAC;QACpB,MAAM,IAAI,GAAG,IAAI,CAAC,CAAC,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;QACnC,MAAM,UAAU,GAAG,MAAM,EAAE,GAAG,2BAA2B,CAAA;QACzD,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,CAAC,CAAC,EAAE,CAAC,SAAS,EAAE,MAAM,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,cAAc,EAAE,MAAM,CAAC,CAAA;IAEtC,MAAM,EAAE,GAAG,OAAO,CAAC,MAAM,CAAC,EACzB,MAAM,GAAG,IAAI,CAAC,WAAW,EAAE,MAAM,CAAC,EAClC,QAAQ,GAAG,IAAI,CAAC,CAAC,CAAC,UAAU,EAAE,MAAM,CAAC,EACrC,QAAQ,GAAG,IAAI,CAAC,CAAC,CAAC,SAAS,EAAE,MAAM,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,GAAiB;IAClD,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"}
@@ -0,0 +1,22 @@
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 slice, 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 slice 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 CorpusRecipe } from "#recipes/scaffold";
17
+ /**
18
+ * Slice 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: CorpusRecipe;
22
+ //# sourceMappingURL=cz-pcfirst-preposition.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"cz-pcfirst-preposition.d.ts","sourceRoot":"","sources":["../../lib/recipes/cz-pcfirst-preposition.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;GAcG;AAEH,OAAO,EAA6C,KAAK,YAAY,EAAiB,MAAM,mBAAmB,CAAA;AAS/G;;;GAGG;AACH,eAAO,MAAM,0BAA0B,EAAE,YAiFxC,CAAA"}