@mailwoman/corpus 9.4.0 → 10.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (981) hide show
  1. package/README.md +16 -0
  2. package/lib/adapters/geonames/adapter.ts +3 -3
  3. package/lib/adapters/geonames/postal/adapter.ts +122 -0
  4. package/lib/adapters/index.ts +39 -32
  5. package/lib/adapters/openaddresses/adapter.ts +4 -7
  6. package/lib/adapters/osm/adapter.ts +278 -0
  7. package/lib/adapters/overture/adapter.ts +22 -7
  8. package/lib/adapters/utils/index.ts +1 -1
  9. package/lib/adapters/wof/admin/json/adapter.ts +239 -0
  10. package/lib/adapters/wof/json-rows.ts +181 -0
  11. package/lib/adapters/wof/postalcode-json/adapter.ts +196 -0
  12. package/lib/au/adapters/gnaf/adapter.ts +152 -0
  13. package/lib/au/adapters/gnaf/assemble.ts +225 -0
  14. package/lib/de/recipes/locale.ts +360 -0
  15. package/lib/fr/adapters/ban/adapter.ts +159 -0
  16. package/lib/fr/recipes/admin-split.ts +243 -0
  17. package/lib/fr/recipes/bare-street.ts +171 -0
  18. package/lib/fr/recipes/fragment.ts +334 -0
  19. package/lib/fr/recipes/lieudit.ts +274 -0
  20. package/lib/fr/recipes/order.ts +246 -0
  21. package/lib/fr/tools/fetch/ban.ts +289 -0
  22. package/lib/index.ts +1 -1
  23. package/lib/international/recipes/locale.ts +598 -0
  24. package/lib/jp/tools/fetch/houjin.ts +141 -0
  25. package/lib/kr/adapters/juso/label-rows.ts +259 -0
  26. package/lib/kr/adapters/localdata/align.ts +299 -0
  27. package/lib/kr/adapters/localdata/key-index.ts +185 -0
  28. package/lib/kr/adapters/localdata/permit-rows.ts +186 -0
  29. package/lib/kr/tools/fetch/juso.ts +172 -0
  30. package/lib/kr/tools/fetch/localdata.ts +206 -0
  31. package/lib/recipes/bare/postcode/eval.ts +99 -0
  32. package/lib/recipes/bare/postcode/index.ts +327 -0
  33. package/lib/recipes/country-balanced.ts +1 -1
  34. package/lib/recipes/index.ts +28 -21
  35. package/lib/recipes/intersection.ts +1 -1
  36. package/lib/recipes/po/box/cedex/au-nz.ts +82 -0
  37. package/lib/recipes/po/box/cedex/ca.ts +58 -0
  38. package/lib/recipes/po/box/cedex/fr.ts +76 -0
  39. package/lib/recipes/po/box/cedex/phrases.ts +108 -0
  40. package/lib/recipes/po/box/cedex/recipe.ts +203 -0
  41. package/lib/recipes/po/box/cedex/sources.ts +189 -0
  42. package/lib/recipes/po/box/cedex/types.ts +35 -0
  43. package/lib/recipes/po/box/cedex/us.ts +69 -0
  44. package/lib/recipes/po/box/cedex/vocabulary.ts +106 -0
  45. package/lib/recipes/po/box/cedex.ts +9 -0
  46. package/lib/recipes/po/box/index.ts +128 -0
  47. package/lib/recipes/scaffold.ts +18 -41
  48. package/lib/recipes/street/affix.ts +807 -0
  49. package/lib/recipes/sub/venue/context.ts +149 -0
  50. package/lib/recipes/sub/venue/index.ts +997 -0
  51. package/lib/recipes/sub/venue/sources.ts +739 -0
  52. package/lib/recipes/trailing-region.ts +6 -1
  53. package/lib/recipes/unit.ts +1 -1
  54. package/lib/sg/recipes/register.ts +270 -0
  55. package/lib/sg/tools/fetch/acra.ts +179 -0
  56. package/lib/south-asia/recipes/register.ts +214 -0
  57. package/lib/synthesizers/anchor-absorption.ts +1 -1
  58. package/lib/synthesizers/locale.ts +261 -0
  59. package/lib/synthesizers/street.ts +1 -1
  60. package/lib/synthesizers/utils.ts +2 -2
  61. package/lib/tools/audit.ts +3 -2
  62. package/lib/tools/corpus-stats.ts +3 -3
  63. package/lib/tools/fetch/download/index.ts +10 -0
  64. package/lib/tools/fetch/download/manifest.ts +102 -0
  65. package/lib/tools/fetch/download/network.ts +226 -0
  66. package/lib/tools/fetch/download/retry.ts +173 -0
  67. package/lib/tools/fetch/geonames/dump.ts +257 -0
  68. package/lib/tools/fetch/geonames/postal.ts +180 -0
  69. package/lib/tools/fetch/index.ts +30 -30
  70. package/lib/tools/fetch/openaddresses.ts +2 -2
  71. package/lib/tools/fetch/ourairports.ts +2 -2
  72. package/lib/tools/fetch/ppd.ts +1 -3
  73. package/lib/tools/fetch/wikidata-subvenue.ts +2 -2
  74. package/lib/tools/golden/promote.ts +340 -0
  75. package/lib/tools/golden/relabel-street/directory.ts +340 -0
  76. package/lib/tools/golden/relabel-street/index.ts +9 -0
  77. package/lib/tools/golden/relabel-street/row.ts +361 -0
  78. package/lib/tools/index.ts +10 -10
  79. package/lib/tools/ingest-csv.ts +5 -7
  80. package/lib/tools/lint/slice/vocab.ts +376 -0
  81. package/lib/tools/overlay-manifest.ts +92 -25
  82. package/lib/tools/overture-subvenue.ts +1 -1
  83. package/lib/tools/postcode-triples.ts +138 -14
  84. package/lib/tools/sub/venue/harvest.ts +234 -0
  85. package/lib/tools/sub/venue/head-nouns.ts +245 -0
  86. package/lib/tools/sub/venue/lexicon.ts +429 -0
  87. package/lib/tools/sub/venue/surfaces.ts +95 -0
  88. package/lib/tools/sub/venue/table.ts +281 -0
  89. package/lib/tools/sub/venue/wikidata.ts +85 -0
  90. package/lib/tw/tools/fetch/gcis.ts +180 -0
  91. package/lib/types.ts +1 -1
  92. package/lib/us/adapters/fcc-bdc/adapter.ts +173 -0
  93. package/lib/us/adapters/state/hi-schools/adapter.ts +160 -0
  94. package/lib/us/adapters/state/ia-contractors/adapter.ts +136 -0
  95. package/lib/us/adapters/state/ny-notaries/adapter.ts +133 -0
  96. package/lib/us/adapters/state/tx-notaries/adapter.ts +149 -0
  97. package/lib/us/adapters/tiger/adapter.ts +250 -0
  98. package/lib/us/adapters/usgov/hrsa-fqhc/adapter.ts +156 -0
  99. package/lib/us/adapters/usgov/imls-pls/adapter.ts +134 -0
  100. package/lib/us/adapters/usgov/irs-bmf/adapter.ts +145 -0
  101. package/lib/us/adapters/usgov/nad/adapter.ts +324 -0
  102. package/lib/us/adapters/usgov/nppes/adapter.ts +143 -0
  103. package/lib/us/adapters/usgov/samhsa-treatment-locator/adapter.ts +182 -0
  104. package/lib/us/tools/fetch/hrsa.ts +59 -0
  105. package/lib/us/tools/fetch/imls-pls.ts +149 -0
  106. package/lib/us/tools/fetch/nad.ts +341 -0
  107. package/lib/us/tools/fetch/nppes.ts +165 -0
  108. package/lib/us/tools/fetch/state/hi-schools.ts +161 -0
  109. package/lib/us/tools/fetch/state/sources.ts +146 -0
  110. package/lib/us/tools/fetch/tiger-full.ts +308 -0
  111. package/lib/utils/align.ts +1 -1
  112. package/lib/utils/golden.ts +12 -8
  113. package/lib/utils/wof-json.ts +7 -13
  114. package/out/adapters/geonames/adapter.d.ts +1 -1
  115. package/out/adapters/geonames/adapter.js +3 -3
  116. package/out/adapters/geonames/adapter.js.map +1 -1
  117. package/out/adapters/geonames/postal/adapter.d.ts.map +1 -0
  118. package/out/adapters/geonames/postal/adapter.js +107 -0
  119. package/out/adapters/geonames/postal/adapter.js.map +1 -0
  120. package/out/adapters/index.d.ts +16 -16
  121. package/out/adapters/index.d.ts.map +1 -1
  122. package/out/adapters/index.js +34 -32
  123. package/out/adapters/index.js.map +1 -1
  124. package/out/adapters/openaddresses/adapter.d.ts.map +1 -1
  125. package/out/adapters/openaddresses/adapter.js +4 -6
  126. package/out/adapters/openaddresses/adapter.js.map +1 -1
  127. package/out/adapters/osm/adapter.d.ts +95 -0
  128. package/out/adapters/osm/adapter.d.ts.map +1 -0
  129. package/out/adapters/osm/adapter.js +211 -0
  130. package/out/adapters/osm/adapter.js.map +1 -0
  131. package/out/adapters/overture/adapter.d.ts +10 -0
  132. package/out/adapters/overture/adapter.d.ts.map +1 -1
  133. package/out/adapters/overture/adapter.js +20 -7
  134. package/out/adapters/overture/adapter.js.map +1 -1
  135. package/out/adapters/synth-po-box/adapter.js.map +1 -1
  136. package/out/adapters/utils/index.d.ts +1 -1
  137. package/out/adapters/utils/index.d.ts.map +1 -1
  138. package/out/adapters/utils/index.js.map +1 -1
  139. package/out/adapters/wof/admin/json/adapter.d.ts +79 -0
  140. package/out/adapters/wof/admin/json/adapter.d.ts.map +1 -0
  141. package/out/adapters/wof/admin/json/adapter.js +204 -0
  142. package/out/adapters/wof/admin/json/adapter.js.map +1 -0
  143. package/out/adapters/wof/json-rows.d.ts +73 -0
  144. package/out/adapters/wof/json-rows.d.ts.map +1 -0
  145. package/out/adapters/wof/json-rows.js +115 -0
  146. package/out/adapters/wof/json-rows.js.map +1 -0
  147. package/out/adapters/wof/postalcode-json/adapter.d.ts +65 -0
  148. package/out/adapters/wof/postalcode-json/adapter.d.ts.map +1 -0
  149. package/out/adapters/wof/postalcode-json/adapter.js +167 -0
  150. package/out/adapters/wof/postalcode-json/adapter.js.map +1 -0
  151. package/out/au/adapters/gnaf/adapter.d.ts.map +1 -0
  152. package/out/au/adapters/gnaf/adapter.js +127 -0
  153. package/out/au/adapters/gnaf/adapter.js.map +1 -0
  154. package/out/au/adapters/gnaf/assemble.d.ts +65 -0
  155. package/out/au/adapters/gnaf/assemble.d.ts.map +1 -0
  156. package/out/au/adapters/gnaf/assemble.js +154 -0
  157. package/out/au/adapters/gnaf/assemble.js.map +1 -0
  158. package/out/cn/recipes/organizational-units.d.ts +36 -0
  159. package/out/cn/recipes/organizational-units.d.ts.map +1 -0
  160. package/out/cn/recipes/organizational-units.js +159 -0
  161. package/out/cn/recipes/organizational-units.js.map +1 -0
  162. package/out/cz/recipes/pcfirst-preposition.d.ts +22 -0
  163. package/out/cz/recipes/pcfirst-preposition.d.ts.map +1 -0
  164. package/out/cz/recipes/pcfirst-preposition.js +101 -0
  165. package/out/cz/recipes/pcfirst-preposition.js.map +1 -0
  166. package/out/de/recipes/locale.d.ts +44 -0
  167. package/out/de/recipes/locale.d.ts.map +1 -0
  168. package/out/de/recipes/locale.js +289 -0
  169. package/out/de/recipes/locale.js.map +1 -0
  170. package/out/env.d.ts +1 -1
  171. package/out/fr/adapters/ban/adapter.d.ts.map +1 -0
  172. package/out/fr/adapters/ban/adapter.js +123 -0
  173. package/out/fr/adapters/ban/adapter.js.map +1 -0
  174. package/out/fr/adapters/ban/street-decompose.d.ts.map +1 -0
  175. package/out/fr/adapters/ban/street-decompose.js.map +1 -0
  176. package/out/fr/recipes/admin-split.d.ts +38 -0
  177. package/out/fr/recipes/admin-split.d.ts.map +1 -0
  178. package/out/fr/recipes/admin-split.js +192 -0
  179. package/out/fr/recipes/admin-split.js.map +1 -0
  180. package/out/fr/recipes/bare-street.d.ts +28 -0
  181. package/out/fr/recipes/bare-street.d.ts.map +1 -0
  182. package/out/fr/recipes/bare-street.js +144 -0
  183. package/out/fr/recipes/bare-street.js.map +1 -0
  184. package/out/fr/recipes/fragment.d.ts +77 -0
  185. package/out/fr/recipes/fragment.d.ts.map +1 -0
  186. package/out/fr/recipes/fragment.js +277 -0
  187. package/out/fr/recipes/fragment.js.map +1 -0
  188. package/out/fr/recipes/lieudit.d.ts +32 -0
  189. package/out/fr/recipes/lieudit.d.ts.map +1 -0
  190. package/out/fr/recipes/lieudit.js +211 -0
  191. package/out/fr/recipes/lieudit.js.map +1 -0
  192. package/out/fr/recipes/order.d.ts +38 -0
  193. package/out/fr/recipes/order.d.ts.map +1 -0
  194. package/out/fr/recipes/order.js +198 -0
  195. package/out/fr/recipes/order.js.map +1 -0
  196. package/out/fr/tools/fetch/ban.d.ts +31 -0
  197. package/out/fr/tools/fetch/ban.d.ts.map +1 -0
  198. package/out/fr/tools/fetch/ban.js +239 -0
  199. package/out/fr/tools/fetch/ban.js.map +1 -0
  200. package/out/index.d.ts +1 -1
  201. package/out/index.d.ts.map +1 -1
  202. package/out/index.js +1 -1
  203. package/out/index.js.map +1 -1
  204. package/out/international/recipes/locale.d.ts +136 -0
  205. package/out/international/recipes/locale.d.ts.map +1 -0
  206. package/out/international/recipes/locale.js +458 -0
  207. package/out/international/recipes/locale.js.map +1 -0
  208. package/out/jp/adapters/wof-admin/adapter.d.ts.map +1 -0
  209. package/out/jp/adapters/wof-admin/adapter.js.map +1 -0
  210. package/out/jp/tools/fetch/houjin.d.ts +24 -0
  211. package/out/jp/tools/fetch/houjin.d.ts.map +1 -0
  212. package/out/jp/tools/fetch/houjin.js +102 -0
  213. package/out/jp/tools/fetch/houjin.js.map +1 -0
  214. package/out/kr/adapters/juso/label-rows.d.ts +76 -0
  215. package/out/kr/adapters/juso/label-rows.d.ts.map +1 -0
  216. package/out/kr/adapters/juso/label-rows.js +194 -0
  217. package/out/kr/adapters/juso/label-rows.js.map +1 -0
  218. package/out/kr/adapters/localdata/align.d.ts +43 -0
  219. package/out/kr/adapters/localdata/align.d.ts.map +1 -0
  220. package/out/kr/adapters/localdata/align.js +223 -0
  221. package/out/kr/adapters/localdata/align.js.map +1 -0
  222. package/out/kr/adapters/localdata/key-index.d.ts +71 -0
  223. package/out/kr/adapters/localdata/key-index.d.ts.map +1 -0
  224. package/out/kr/adapters/localdata/key-index.js +133 -0
  225. package/out/kr/adapters/localdata/key-index.js.map +1 -0
  226. package/out/kr/adapters/localdata/permit-rows.d.ts +66 -0
  227. package/out/kr/adapters/localdata/permit-rows.d.ts.map +1 -0
  228. package/out/kr/adapters/localdata/permit-rows.js +131 -0
  229. package/out/kr/adapters/localdata/permit-rows.js.map +1 -0
  230. package/out/kr/tools/fetch/juso.d.ts +30 -0
  231. package/out/kr/tools/fetch/juso.d.ts.map +1 -0
  232. package/out/kr/tools/fetch/juso.js +120 -0
  233. package/out/kr/tools/fetch/juso.js.map +1 -0
  234. package/out/kr/tools/fetch/localdata.d.ts +30 -0
  235. package/out/kr/tools/fetch/localdata.d.ts.map +1 -0
  236. package/out/kr/tools/fetch/localdata.js +139 -0
  237. package/out/kr/tools/fetch/localdata.js.map +1 -0
  238. package/out/nl/recipes/postcode.d.ts +26 -0
  239. package/out/nl/recipes/postcode.d.ts.map +1 -0
  240. package/out/nl/recipes/postcode.js +103 -0
  241. package/out/nl/recipes/postcode.js.map +1 -0
  242. package/out/no/recipes/fragment.d.ts +43 -0
  243. package/out/no/recipes/fragment.d.ts.map +1 -0
  244. package/out/no/recipes/fragment.js +183 -0
  245. package/out/no/recipes/fragment.js.map +1 -0
  246. package/out/no/recipes/street/index.d.ts +18 -0
  247. package/out/no/recipes/street/index.d.ts.map +1 -0
  248. package/out/no/recipes/street/index.js +72 -0
  249. package/out/no/recipes/street/index.js.map +1 -0
  250. package/out/no/recipes/street/led.d.ts +24 -0
  251. package/out/no/recipes/street/led.d.ts.map +1 -0
  252. package/out/no/recipes/street/led.js +114 -0
  253. package/out/no/recipes/street/led.js.map +1 -0
  254. package/out/recipes/bare/country.d.ts +25 -0
  255. package/out/recipes/bare/country.d.ts.map +1 -0
  256. package/out/recipes/bare/country.js +88 -0
  257. package/out/recipes/bare/country.js.map +1 -0
  258. package/out/recipes/bare/postcode/eval.d.ts +29 -0
  259. package/out/recipes/bare/postcode/eval.d.ts.map +1 -0
  260. package/out/recipes/bare/postcode/eval.js +85 -0
  261. package/out/recipes/bare/postcode/eval.js.map +1 -0
  262. package/out/recipes/bare/postcode/index.d.ts +62 -0
  263. package/out/recipes/bare/postcode/index.d.ts.map +1 -0
  264. package/out/recipes/bare/postcode/index.js +267 -0
  265. package/out/recipes/bare/postcode/index.js.map +1 -0
  266. package/out/recipes/country-balanced.js.map +1 -1
  267. package/out/recipes/index.d.ts.map +1 -1
  268. package/out/recipes/index.js +28 -21
  269. package/out/recipes/index.js.map +1 -1
  270. package/out/recipes/intersection.js.map +1 -1
  271. package/out/recipes/po/box/cedex/au-nz.d.ts +7 -0
  272. package/out/recipes/po/box/cedex/au-nz.d.ts.map +1 -0
  273. package/out/recipes/po/box/cedex/au-nz.js +56 -0
  274. package/out/recipes/po/box/cedex/au-nz.js.map +1 -0
  275. package/out/recipes/po/box/cedex/ca.d.ts +7 -0
  276. package/out/recipes/po/box/cedex/ca.d.ts.map +1 -0
  277. package/out/recipes/po/box/cedex/ca.js +38 -0
  278. package/out/recipes/po/box/cedex/ca.js.map +1 -0
  279. package/out/recipes/po/box/cedex/fr.d.ts +7 -0
  280. package/out/recipes/po/box/cedex/fr.d.ts.map +1 -0
  281. package/out/recipes/po/box/cedex/fr.js +57 -0
  282. package/out/recipes/po/box/cedex/fr.js.map +1 -0
  283. package/out/recipes/po/box/cedex/phrases.d.ts +8 -0
  284. package/out/recipes/po/box/cedex/phrases.d.ts.map +1 -0
  285. package/out/recipes/po/box/cedex/phrases.js +76 -0
  286. package/out/recipes/po/box/cedex/phrases.js.map +1 -0
  287. package/out/recipes/po/box/cedex/recipe.d.ts +9 -0
  288. package/out/recipes/po/box/cedex/recipe.d.ts.map +1 -0
  289. package/out/recipes/po/box/cedex/recipe.js +153 -0
  290. package/out/recipes/po/box/cedex/recipe.js.map +1 -0
  291. package/out/recipes/po/box/cedex/sources.d.ts +86 -0
  292. package/out/recipes/po/box/cedex/sources.d.ts.map +1 -0
  293. package/out/recipes/po/box/cedex/sources.js +143 -0
  294. package/out/recipes/po/box/cedex/sources.js.map +1 -0
  295. package/out/recipes/po/box/cedex/types.d.ts +31 -0
  296. package/out/recipes/po/box/cedex/types.d.ts.map +1 -0
  297. package/out/recipes/po/box/cedex/types.js +5 -0
  298. package/out/recipes/po/box/cedex/types.js.map +1 -0
  299. package/out/recipes/po/box/cedex/us.d.ts +7 -0
  300. package/out/recipes/po/box/cedex/us.d.ts.map +1 -0
  301. package/out/recipes/po/box/cedex/us.js +51 -0
  302. package/out/recipes/po/box/cedex/us.js.map +1 -0
  303. package/out/recipes/po/box/cedex/vocabulary.d.ts +68 -0
  304. package/out/recipes/po/box/cedex/vocabulary.d.ts.map +1 -0
  305. package/out/recipes/po/box/cedex/vocabulary.js +90 -0
  306. package/out/recipes/po/box/cedex/vocabulary.js.map +1 -0
  307. package/out/recipes/po/box/cedex.d.ts +9 -0
  308. package/out/recipes/po/box/cedex.d.ts.map +1 -0
  309. package/out/recipes/po/box/cedex.js +9 -0
  310. package/out/recipes/po/box/cedex.js.map +1 -0
  311. package/out/recipes/po/box/index.d.ts +17 -0
  312. package/out/recipes/po/box/index.d.ts.map +1 -0
  313. package/out/recipes/po/box/index.js +105 -0
  314. package/out/recipes/po/box/index.js.map +1 -0
  315. package/out/recipes/scaffold.d.ts +20 -0
  316. package/out/recipes/scaffold.d.ts.map +1 -1
  317. package/out/recipes/scaffold.js +18 -37
  318. package/out/recipes/scaffold.js.map +1 -1
  319. package/out/recipes/street/affix.d.ts +89 -0
  320. package/out/recipes/street/affix.d.ts.map +1 -0
  321. package/out/recipes/street/affix.js +565 -0
  322. package/out/recipes/street/affix.js.map +1 -0
  323. package/out/recipes/street/bare.d.ts +25 -0
  324. package/out/recipes/street/bare.d.ts.map +1 -0
  325. package/out/recipes/street/bare.js +87 -0
  326. package/out/recipes/street/bare.js.map +1 -0
  327. package/out/recipes/sub/venue/context.d.ts +29 -0
  328. package/out/recipes/sub/venue/context.d.ts.map +1 -0
  329. package/out/recipes/sub/venue/context.js +106 -0
  330. package/out/recipes/sub/venue/context.js.map +1 -0
  331. package/out/recipes/sub/venue/index.d.ts +270 -0
  332. package/out/recipes/sub/venue/index.d.ts.map +1 -0
  333. package/out/recipes/sub/venue/index.js +728 -0
  334. package/out/recipes/sub/venue/index.js.map +1 -0
  335. package/out/recipes/sub/venue/sources.d.ts +209 -0
  336. package/out/recipes/sub/venue/sources.d.ts.map +1 -0
  337. package/out/recipes/sub/venue/sources.js +555 -0
  338. package/out/recipes/sub/venue/sources.js.map +1 -0
  339. package/out/recipes/trailing-region.d.ts.map +1 -1
  340. package/out/recipes/trailing-region.js +6 -1
  341. package/out/recipes/trailing-region.js.map +1 -1
  342. package/out/recipes/unit.js.map +1 -1
  343. package/out/sg/recipes/register.d.ts +69 -0
  344. package/out/sg/recipes/register.d.ts.map +1 -0
  345. package/out/sg/recipes/register.js +211 -0
  346. package/out/sg/recipes/register.js.map +1 -0
  347. package/out/sg/tools/fetch/acra.d.ts +23 -0
  348. package/out/sg/tools/fetch/acra.d.ts.map +1 -0
  349. package/out/sg/tools/fetch/acra.js +126 -0
  350. package/out/sg/tools/fetch/acra.js.map +1 -0
  351. package/out/si/recipes/bare-village.d.ts +32 -0
  352. package/out/si/recipes/bare-village.d.ts.map +1 -0
  353. package/out/si/recipes/bare-village.js +89 -0
  354. package/out/si/recipes/bare-village.js.map +1 -0
  355. package/out/south-asia/recipes/register.d.ts +51 -0
  356. package/out/south-asia/recipes/register.d.ts.map +1 -0
  357. package/out/south-asia/recipes/register.js +154 -0
  358. package/out/south-asia/recipes/register.js.map +1 -0
  359. package/out/synthesizers/anchor-absorption.d.ts +1 -1
  360. package/out/synthesizers/anchor-absorption.d.ts.map +1 -1
  361. package/out/synthesizers/anchor-absorption.js.map +1 -1
  362. package/out/synthesizers/boundary-stress.js.map +1 -1
  363. package/out/synthesizers/house-venue.js.map +1 -1
  364. package/out/synthesizers/intersection.js.map +1 -1
  365. package/out/synthesizers/locale.d.ts +116 -0
  366. package/out/synthesizers/locale.d.ts.map +1 -0
  367. package/out/synthesizers/locale.js +150 -0
  368. package/out/synthesizers/locale.js.map +1 -0
  369. package/out/synthesizers/no-street.d.ts.map +1 -1
  370. package/out/synthesizers/no-street.js.map +1 -1
  371. package/out/synthesizers/po-box.js.map +1 -1
  372. package/out/synthesizers/street.d.ts.map +1 -1
  373. package/out/synthesizers/street.js +1 -1
  374. package/out/synthesizers/street.js.map +1 -1
  375. package/out/synthesizers/utils.js +1 -1
  376. package/out/synthesizers/utils.js.map +1 -1
  377. package/out/test-kit/corpus-recipe.d.ts.map +1 -1
  378. package/out/test-kit/corpus-recipe.js.map +1 -1
  379. package/out/tools/audit.d.ts.map +1 -1
  380. package/out/tools/audit.js +3 -2
  381. package/out/tools/audit.js.map +1 -1
  382. package/out/tools/corpus-stats.js +3 -3
  383. package/out/tools/corpus-stats.js.map +1 -1
  384. package/out/tools/fetch/download/index.d.ts +10 -0
  385. package/out/tools/fetch/download/index.d.ts.map +1 -0
  386. package/out/tools/fetch/download/index.js +10 -0
  387. package/out/tools/fetch/download/index.js.map +1 -0
  388. package/out/tools/fetch/download/manifest.d.ts +47 -0
  389. package/out/tools/fetch/download/manifest.d.ts.map +1 -0
  390. package/out/tools/fetch/download/manifest.js +74 -0
  391. package/out/tools/fetch/download/manifest.js.map +1 -0
  392. package/out/tools/fetch/download/network.d.ts +105 -0
  393. package/out/tools/fetch/download/network.d.ts.map +1 -0
  394. package/out/tools/fetch/download/network.js +130 -0
  395. package/out/tools/fetch/download/network.js.map +1 -0
  396. package/out/tools/fetch/download/retry.d.ts +45 -0
  397. package/out/tools/fetch/download/retry.d.ts.map +1 -0
  398. package/out/tools/fetch/download/retry.js +136 -0
  399. package/out/tools/fetch/download/retry.js.map +1 -0
  400. package/out/tools/fetch/geonames/dump.d.ts +91 -0
  401. package/out/tools/fetch/geonames/dump.d.ts.map +1 -0
  402. package/out/tools/fetch/geonames/dump.js +171 -0
  403. package/out/tools/fetch/geonames/dump.js.map +1 -0
  404. package/out/tools/fetch/geonames/postal.d.ts +76 -0
  405. package/out/tools/fetch/geonames/postal.d.ts.map +1 -0
  406. package/out/tools/fetch/geonames/postal.js +126 -0
  407. package/out/tools/fetch/geonames/postal.js.map +1 -0
  408. package/out/tools/fetch/index.d.ts +30 -30
  409. package/out/tools/fetch/index.d.ts.map +1 -1
  410. package/out/tools/fetch/index.js +30 -30
  411. package/out/tools/fetch/index.js.map +1 -1
  412. package/out/tools/fetch/openaddresses.d.ts +1 -1
  413. package/out/tools/fetch/openaddresses.d.ts.map +1 -1
  414. package/out/tools/fetch/openaddresses.js +1 -1
  415. package/out/tools/fetch/openaddresses.js.map +1 -1
  416. package/out/tools/fetch/ourairports.d.ts +1 -1
  417. package/out/tools/fetch/ourairports.d.ts.map +1 -1
  418. package/out/tools/fetch/ourairports.js +1 -1
  419. package/out/tools/fetch/ourairports.js.map +1 -1
  420. package/out/tools/fetch/ppd.js +1 -3
  421. package/out/tools/fetch/ppd.js.map +1 -1
  422. package/out/tools/fetch/wikidata-subvenue.d.ts +1 -1
  423. package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -1
  424. package/out/tools/fetch/wikidata-subvenue.js +1 -1
  425. package/out/tools/fetch/wikidata-subvenue.js.map +1 -1
  426. package/out/tools/golden/expand.d.ts +90 -0
  427. package/out/tools/golden/expand.d.ts.map +1 -0
  428. package/out/tools/golden/expand.js +406 -0
  429. package/out/tools/golden/expand.js.map +1 -0
  430. package/out/tools/golden/promote.d.ts +72 -0
  431. package/out/tools/golden/promote.d.ts.map +1 -0
  432. package/out/tools/golden/promote.js +243 -0
  433. package/out/tools/golden/promote.js.map +1 -0
  434. package/out/tools/golden/relabel-street/directory.d.ts +83 -0
  435. package/out/tools/golden/relabel-street/directory.d.ts.map +1 -0
  436. package/out/tools/golden/relabel-street/directory.js +216 -0
  437. package/out/tools/golden/relabel-street/directory.js.map +1 -0
  438. package/out/tools/golden/relabel-street/index.d.ts +9 -0
  439. package/out/tools/golden/relabel-street/index.d.ts.map +1 -0
  440. package/out/tools/golden/relabel-street/index.js +9 -0
  441. package/out/tools/golden/relabel-street/index.js.map +1 -0
  442. package/out/tools/golden/relabel-street/row.d.ts +121 -0
  443. package/out/tools/golden/relabel-street/row.d.ts.map +1 -0
  444. package/out/tools/golden/relabel-street/row.js +232 -0
  445. package/out/tools/golden/relabel-street/row.js.map +1 -0
  446. package/out/tools/index.d.ts +10 -10
  447. package/out/tools/index.d.ts.map +1 -1
  448. package/out/tools/index.js +10 -10
  449. package/out/tools/index.js.map +1 -1
  450. package/out/tools/ingest-csv.d.ts.map +1 -1
  451. package/out/tools/ingest-csv.js +5 -7
  452. package/out/tools/ingest-csv.js.map +1 -1
  453. package/out/tools/lint/slice/index.d.ts +93 -0
  454. package/out/tools/lint/slice/index.d.ts.map +1 -0
  455. package/out/tools/lint/slice/index.js +322 -0
  456. package/out/tools/lint/slice/index.js.map +1 -0
  457. package/out/tools/lint/slice/vocab.d.ts +90 -0
  458. package/out/tools/lint/slice/vocab.d.ts.map +1 -0
  459. package/out/tools/lint/slice/vocab.js +254 -0
  460. package/out/tools/lint/slice/vocab.js.map +1 -0
  461. package/out/tools/overlay-manifest.d.ts +56 -6
  462. package/out/tools/overlay-manifest.d.ts.map +1 -1
  463. package/out/tools/overlay-manifest.js +56 -15
  464. package/out/tools/overlay-manifest.js.map +1 -1
  465. package/out/tools/overture-subvenue.d.ts +1 -1
  466. package/out/tools/postcode-triples.d.ts +36 -0
  467. package/out/tools/postcode-triples.d.ts.map +1 -1
  468. package/out/tools/postcode-triples.js +91 -12
  469. package/out/tools/postcode-triples.js.map +1 -1
  470. package/out/tools/slice/kryptonite.d.ts +32 -0
  471. package/out/tools/slice/kryptonite.d.ts.map +1 -0
  472. package/out/tools/slice/kryptonite.js +99 -0
  473. package/out/tools/slice/kryptonite.js.map +1 -0
  474. package/out/tools/slice/translit.d.ts +51 -0
  475. package/out/tools/slice/translit.d.ts.map +1 -0
  476. package/out/tools/slice/translit.js +166 -0
  477. package/out/tools/slice/translit.js.map +1 -0
  478. package/out/tools/sub/venue/harvest.d.ts +100 -0
  479. package/out/tools/sub/venue/harvest.d.ts.map +1 -0
  480. package/out/tools/sub/venue/harvest.js +168 -0
  481. package/out/tools/sub/venue/harvest.js.map +1 -0
  482. package/out/tools/sub/venue/head-nouns.d.ts +50 -0
  483. package/out/tools/sub/venue/head-nouns.d.ts.map +1 -0
  484. package/out/tools/sub/venue/head-nouns.js.map +1 -0
  485. package/out/tools/sub/venue/lexicon.d.ts +156 -0
  486. package/out/tools/sub/venue/lexicon.d.ts.map +1 -0
  487. package/out/tools/sub/venue/lexicon.js +283 -0
  488. package/out/tools/sub/venue/lexicon.js.map +1 -0
  489. package/out/tools/sub/venue/promotions.d.ts +94 -0
  490. package/out/tools/sub/venue/promotions.d.ts.map +1 -0
  491. package/out/tools/sub/venue/promotions.js +266 -0
  492. package/out/tools/sub/venue/promotions.js.map +1 -0
  493. package/out/tools/sub/venue/surfaces.d.ts +45 -0
  494. package/out/tools/sub/venue/surfaces.d.ts.map +1 -0
  495. package/out/tools/sub/venue/surfaces.js.map +1 -0
  496. package/out/tools/sub/venue/table.d.ts +229 -0
  497. package/out/tools/sub/venue/table.d.ts.map +1 -0
  498. package/out/tools/sub/venue/table.js.map +1 -0
  499. package/out/tools/sub/venue/wikidata.d.ts +26 -0
  500. package/out/tools/sub/venue/wikidata.d.ts.map +1 -0
  501. package/out/tools/sub/venue/wikidata.js +62 -0
  502. package/out/tools/sub/venue/wikidata.js.map +1 -0
  503. package/out/tw/tools/fetch/gcis.d.ts +23 -0
  504. package/out/tw/tools/fetch/gcis.d.ts.map +1 -0
  505. package/out/tw/tools/fetch/gcis.js +135 -0
  506. package/out/tw/tools/fetch/gcis.js.map +1 -0
  507. package/out/types.d.ts +1 -1
  508. package/out/types.d.ts.map +1 -1
  509. package/out/us/adapters/fcc-bdc/adapter.d.ts.map +1 -0
  510. package/out/us/adapters/fcc-bdc/adapter.js +142 -0
  511. package/out/us/adapters/fcc-bdc/adapter.js.map +1 -0
  512. package/out/us/adapters/state/hi-schools/adapter.d.ts.map +1 -0
  513. package/out/us/adapters/state/hi-schools/adapter.js +136 -0
  514. package/out/us/adapters/state/hi-schools/adapter.js.map +1 -0
  515. package/out/us/adapters/state/hi-schools/workbook.d.ts.map +1 -0
  516. package/out/us/adapters/state/hi-schools/workbook.js.map +1 -0
  517. package/out/us/adapters/state/ia-contractors/adapter.d.ts.map +1 -0
  518. package/out/us/adapters/state/ia-contractors/adapter.js +104 -0
  519. package/out/us/adapters/state/ia-contractors/adapter.js.map +1 -0
  520. package/out/us/adapters/state/ny-notaries/adapter.d.ts.map +1 -0
  521. package/out/us/adapters/state/ny-notaries/adapter.js +112 -0
  522. package/out/us/adapters/state/ny-notaries/adapter.js.map +1 -0
  523. package/out/us/adapters/state/tx-notaries/adapter.d.ts.map +1 -0
  524. package/out/us/adapters/state/tx-notaries/adapter.js +118 -0
  525. package/out/us/adapters/state/tx-notaries/adapter.js.map +1 -0
  526. package/out/us/adapters/tiger/adapter.d.ts +55 -0
  527. package/out/us/adapters/tiger/adapter.d.ts.map +1 -0
  528. package/out/us/adapters/tiger/adapter.js +197 -0
  529. package/out/us/adapters/tiger/adapter.js.map +1 -0
  530. package/out/us/adapters/tiger/street-decompose.d.ts.map +1 -0
  531. package/out/us/adapters/tiger/street-decompose.js.map +1 -0
  532. package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts.map +1 -0
  533. package/out/us/adapters/usgov/hrsa-fqhc/adapter.js +121 -0
  534. package/out/us/adapters/usgov/hrsa-fqhc/adapter.js.map +1 -0
  535. package/out/us/adapters/usgov/imls-pls/adapter.d.ts.map +1 -0
  536. package/out/us/adapters/usgov/imls-pls/adapter.js +106 -0
  537. package/out/us/adapters/usgov/imls-pls/adapter.js.map +1 -0
  538. package/out/us/adapters/usgov/irs-bmf/adapter.d.ts.map +1 -0
  539. package/out/us/adapters/usgov/irs-bmf/adapter.js +116 -0
  540. package/out/us/adapters/usgov/irs-bmf/adapter.js.map +1 -0
  541. package/out/us/adapters/usgov/nad/adapter.d.ts.map +1 -0
  542. package/out/us/adapters/usgov/nad/adapter.js +239 -0
  543. package/out/us/adapters/usgov/nad/adapter.js.map +1 -0
  544. package/out/us/adapters/usgov/nppes/adapter.d.ts.map +1 -0
  545. package/out/us/adapters/usgov/nppes/adapter.js +110 -0
  546. package/out/us/adapters/usgov/nppes/adapter.js.map +1 -0
  547. package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts.map +1 -0
  548. package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js +143 -0
  549. package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js.map +1 -0
  550. package/out/us/fips-state.d.ts +41 -0
  551. package/out/us/fips-state.d.ts.map +1 -0
  552. package/out/us/fips-state.js +100 -0
  553. package/out/us/fips-state.js.map +1 -0
  554. package/out/us/tools/fetch/hrsa.d.ts +18 -0
  555. package/out/us/tools/fetch/hrsa.d.ts.map +1 -0
  556. package/out/us/tools/fetch/hrsa.js +46 -0
  557. package/out/us/tools/fetch/hrsa.js.map +1 -0
  558. package/out/us/tools/fetch/imls-pls.d.ts +25 -0
  559. package/out/us/tools/fetch/imls-pls.d.ts.map +1 -0
  560. package/out/us/tools/fetch/imls-pls.js +108 -0
  561. package/out/us/tools/fetch/imls-pls.js.map +1 -0
  562. package/out/us/tools/fetch/nad.d.ts +70 -0
  563. package/out/us/tools/fetch/nad.d.ts.map +1 -0
  564. package/out/us/tools/fetch/nad.js +234 -0
  565. package/out/us/tools/fetch/nad.js.map +1 -0
  566. package/out/us/tools/fetch/nppes.d.ts +26 -0
  567. package/out/us/tools/fetch/nppes.d.ts.map +1 -0
  568. package/out/us/tools/fetch/nppes.js +126 -0
  569. package/out/us/tools/fetch/nppes.js.map +1 -0
  570. package/out/us/tools/fetch/state/hi-schools.d.ts +26 -0
  571. package/out/us/tools/fetch/state/hi-schools.d.ts.map +1 -0
  572. package/out/us/tools/fetch/state/hi-schools.js +112 -0
  573. package/out/us/tools/fetch/state/hi-schools.js.map +1 -0
  574. package/out/us/tools/fetch/state/sources.d.ts +26 -0
  575. package/out/us/tools/fetch/state/sources.d.ts.map +1 -0
  576. package/out/us/tools/fetch/state/sources.js +111 -0
  577. package/out/us/tools/fetch/state/sources.js.map +1 -0
  578. package/out/us/tools/fetch/tiger-full.d.ts +22 -0
  579. package/out/us/tools/fetch/tiger-full.d.ts.map +1 -0
  580. package/out/us/tools/fetch/tiger-full.js +217 -0
  581. package/out/us/tools/fetch/tiger-full.js.map +1 -0
  582. package/out/utils/align.d.ts +1 -1
  583. package/out/utils/align.d.ts.map +1 -1
  584. package/out/utils/align.js.map +1 -1
  585. package/out/utils/golden.d.ts +7 -3
  586. package/out/utils/golden.d.ts.map +1 -1
  587. package/out/utils/golden.js +12 -8
  588. package/out/utils/golden.js.map +1 -1
  589. package/out/utils/parquet.d.ts.map +1 -1
  590. package/out/utils/split.js.map +1 -1
  591. package/out/utils/wof-json.d.ts.map +1 -1
  592. package/out/utils/wof-json.js +7 -12
  593. package/out/utils/wof-json.js.map +1 -1
  594. package/out/ve/recipes/reviewed-postcode-tail.d.ts.map +1 -0
  595. package/out/ve/recipes/reviewed-postcode-tail.js.map +1 -0
  596. package/package.json +196 -46
  597. package/lib/adapters/ban/adapter.ts +0 -190
  598. package/lib/adapters/fcc-bdc/adapter.ts +0 -174
  599. package/lib/adapters/geonames-postal/adapter.ts +0 -122
  600. package/lib/adapters/gnaf/adapter.ts +0 -149
  601. package/lib/adapters/gnaf/assemble.ts +0 -225
  602. package/lib/adapters/state-hi-schools/adapter.ts +0 -170
  603. package/lib/adapters/state-ia-contractors/adapter.ts +0 -144
  604. package/lib/adapters/state-ny-notaries/adapter.ts +0 -141
  605. package/lib/adapters/state-tx-notaries/adapter.ts +0 -157
  606. package/lib/adapters/tiger/adapter.ts +0 -252
  607. package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +0 -167
  608. package/lib/adapters/usgov-imls-pls/adapter.ts +0 -143
  609. package/lib/adapters/usgov-irs-bmf/adapter.ts +0 -151
  610. package/lib/adapters/usgov-nad/adapter.ts +0 -334
  611. package/lib/adapters/usgov-nppes/adapter.ts +0 -151
  612. package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -193
  613. package/lib/adapters/wof-admin-json/adapter.ts +0 -231
  614. package/lib/adapters/wof-json-rows.ts +0 -129
  615. package/lib/adapters/wof-postalcode-json/adapter.ts +0 -176
  616. package/lib/recipes/fr-admin-split.ts +0 -243
  617. package/lib/recipes/fr-bare-street.ts +0 -171
  618. package/lib/recipes/fr-fragment.ts +0 -334
  619. package/lib/recipes/fr-lieudit.ts +0 -301
  620. package/lib/recipes/fr-order.ts +0 -246
  621. package/lib/recipes/german.ts +0 -360
  622. package/lib/recipes/locale.ts +0 -600
  623. package/lib/recipes/po-box-cedex.ts +0 -976
  624. package/lib/recipes/po-box.ts +0 -124
  625. package/lib/recipes/street-affix.ts +0 -805
  626. package/lib/recipes/sub-venue-sources.ts +0 -878
  627. package/lib/recipes/sub-venue.ts +0 -998
  628. package/lib/synthesizers/german.ts +0 -260
  629. package/lib/tools/fetch/acra-sg.ts +0 -174
  630. package/lib/tools/fetch/ban.ts +0 -289
  631. package/lib/tools/fetch/download.ts +0 -477
  632. package/lib/tools/fetch/gcis-tw.ts +0 -175
  633. package/lib/tools/fetch/geonames-dump.ts +0 -257
  634. package/lib/tools/fetch/geonames-postal.ts +0 -180
  635. package/lib/tools/fetch/houjin-jp.ts +0 -135
  636. package/lib/tools/fetch/hrsa.ts +0 -59
  637. package/lib/tools/fetch/imls-pls.ts +0 -149
  638. package/lib/tools/fetch/juso-kr.ts +0 -165
  639. package/lib/tools/fetch/localdata-kr.ts +0 -194
  640. package/lib/tools/fetch/nad.ts +0 -341
  641. package/lib/tools/fetch/nppes.ts +0 -165
  642. package/lib/tools/fetch/state-hi-schools.ts +0 -161
  643. package/lib/tools/fetch/state-sources.ts +0 -146
  644. package/lib/tools/fetch/tiger-full.ts +0 -308
  645. package/lib/tools/golden-promote.ts +0 -337
  646. package/lib/tools/golden-relabel-street.ts +0 -686
  647. package/lib/tools/lint-slice-vocab.ts +0 -388
  648. package/lib/tools/sub-venue/harvest.ts +0 -234
  649. package/lib/tools/sub-venue/head-nouns.ts +0 -245
  650. package/lib/tools/sub-venue/surfaces.ts +0 -95
  651. package/lib/tools/sub-venue/table.ts +0 -281
  652. package/lib/tools/sub-venue/wikidata.ts +0 -85
  653. package/lib/tools/sub-venue-lexicon.ts +0 -429
  654. package/out/adapters/ban/adapter.d.ts.map +0 -1
  655. package/out/adapters/ban/adapter.js +0 -149
  656. package/out/adapters/ban/adapter.js.map +0 -1
  657. package/out/adapters/ban/street-decompose.d.ts.map +0 -1
  658. package/out/adapters/ban/street-decompose.js.map +0 -1
  659. package/out/adapters/fcc-bdc/adapter.d.ts.map +0 -1
  660. package/out/adapters/fcc-bdc/adapter.js +0 -144
  661. package/out/adapters/fcc-bdc/adapter.js.map +0 -1
  662. package/out/adapters/geonames-postal/adapter.d.ts.map +0 -1
  663. package/out/adapters/geonames-postal/adapter.js +0 -107
  664. package/out/adapters/geonames-postal/adapter.js.map +0 -1
  665. package/out/adapters/gnaf/adapter.d.ts.map +0 -1
  666. package/out/adapters/gnaf/adapter.js +0 -124
  667. package/out/adapters/gnaf/adapter.js.map +0 -1
  668. package/out/adapters/gnaf/assemble.d.ts +0 -65
  669. package/out/adapters/gnaf/assemble.d.ts.map +0 -1
  670. package/out/adapters/gnaf/assemble.js +0 -154
  671. package/out/adapters/gnaf/assemble.js.map +0 -1
  672. package/out/adapters/state-hi-schools/adapter.d.ts.map +0 -1
  673. package/out/adapters/state-hi-schools/adapter.js +0 -145
  674. package/out/adapters/state-hi-schools/adapter.js.map +0 -1
  675. package/out/adapters/state-hi-schools/workbook.d.ts.map +0 -1
  676. package/out/adapters/state-hi-schools/workbook.js.map +0 -1
  677. package/out/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
  678. package/out/adapters/state-ia-contractors/adapter.js +0 -111
  679. package/out/adapters/state-ia-contractors/adapter.js.map +0 -1
  680. package/out/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
  681. package/out/adapters/state-ny-notaries/adapter.js +0 -119
  682. package/out/adapters/state-ny-notaries/adapter.js.map +0 -1
  683. package/out/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
  684. package/out/adapters/state-tx-notaries/adapter.js +0 -125
  685. package/out/adapters/state-tx-notaries/adapter.js.map +0 -1
  686. package/out/adapters/tiger/adapter.d.ts +0 -55
  687. package/out/adapters/tiger/adapter.d.ts.map +0 -1
  688. package/out/adapters/tiger/adapter.js +0 -201
  689. package/out/adapters/tiger/adapter.js.map +0 -1
  690. package/out/adapters/tiger/street-decompose.d.ts.map +0 -1
  691. package/out/adapters/tiger/street-decompose.js.map +0 -1
  692. package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
  693. package/out/adapters/usgov-hrsa-fqhc/adapter.js +0 -132
  694. package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
  695. package/out/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
  696. package/out/adapters/usgov-imls-pls/adapter.js +0 -114
  697. package/out/adapters/usgov-imls-pls/adapter.js.map +0 -1
  698. package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
  699. package/out/adapters/usgov-irs-bmf/adapter.js +0 -120
  700. package/out/adapters/usgov-irs-bmf/adapter.js.map +0 -1
  701. package/out/adapters/usgov-nad/adapter.d.ts.map +0 -1
  702. package/out/adapters/usgov-nad/adapter.js +0 -249
  703. package/out/adapters/usgov-nad/adapter.js.map +0 -1
  704. package/out/adapters/usgov-nppes/adapter.d.ts.map +0 -1
  705. package/out/adapters/usgov-nppes/adapter.js +0 -118
  706. package/out/adapters/usgov-nppes/adapter.js.map +0 -1
  707. package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
  708. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -154
  709. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
  710. package/out/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
  711. package/out/adapters/wof-admin-jp/adapter.js.map +0 -1
  712. package/out/adapters/wof-admin-json/adapter.d.ts +0 -79
  713. package/out/adapters/wof-admin-json/adapter.d.ts.map +0 -1
  714. package/out/adapters/wof-admin-json/adapter.js +0 -197
  715. package/out/adapters/wof-admin-json/adapter.js.map +0 -1
  716. package/out/adapters/wof-json-rows.d.ts +0 -62
  717. package/out/adapters/wof-json-rows.d.ts.map +0 -1
  718. package/out/adapters/wof-json-rows.js +0 -83
  719. package/out/adapters/wof-json-rows.js.map +0 -1
  720. package/out/adapters/wof-postalcode-json/adapter.d.ts +0 -65
  721. package/out/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
  722. package/out/adapters/wof-postalcode-json/adapter.js +0 -151
  723. package/out/adapters/wof-postalcode-json/adapter.js.map +0 -1
  724. package/out/codex/us-fips-state.d.ts +0 -41
  725. package/out/codex/us-fips-state.d.ts.map +0 -1
  726. package/out/codex/us-fips-state.js +0 -100
  727. package/out/codex/us-fips-state.js.map +0 -1
  728. package/out/recipes/bare-country.d.ts +0 -25
  729. package/out/recipes/bare-country.d.ts.map +0 -1
  730. package/out/recipes/bare-country.js +0 -88
  731. package/out/recipes/bare-country.js.map +0 -1
  732. package/out/recipes/cn-organizational-units.d.ts +0 -36
  733. package/out/recipes/cn-organizational-units.d.ts.map +0 -1
  734. package/out/recipes/cn-organizational-units.js +0 -159
  735. package/out/recipes/cn-organizational-units.js.map +0 -1
  736. package/out/recipes/cz-pcfirst-preposition.d.ts +0 -22
  737. package/out/recipes/cz-pcfirst-preposition.d.ts.map +0 -1
  738. package/out/recipes/cz-pcfirst-preposition.js +0 -101
  739. package/out/recipes/cz-pcfirst-preposition.js.map +0 -1
  740. package/out/recipes/fr-admin-split.d.ts +0 -38
  741. package/out/recipes/fr-admin-split.d.ts.map +0 -1
  742. package/out/recipes/fr-admin-split.js +0 -192
  743. package/out/recipes/fr-admin-split.js.map +0 -1
  744. package/out/recipes/fr-bare-street.d.ts +0 -28
  745. package/out/recipes/fr-bare-street.d.ts.map +0 -1
  746. package/out/recipes/fr-bare-street.js +0 -144
  747. package/out/recipes/fr-bare-street.js.map +0 -1
  748. package/out/recipes/fr-fragment.d.ts +0 -77
  749. package/out/recipes/fr-fragment.d.ts.map +0 -1
  750. package/out/recipes/fr-fragment.js +0 -277
  751. package/out/recipes/fr-fragment.js.map +0 -1
  752. package/out/recipes/fr-lieudit.d.ts +0 -32
  753. package/out/recipes/fr-lieudit.d.ts.map +0 -1
  754. package/out/recipes/fr-lieudit.js +0 -227
  755. package/out/recipes/fr-lieudit.js.map +0 -1
  756. package/out/recipes/fr-order.d.ts +0 -38
  757. package/out/recipes/fr-order.d.ts.map +0 -1
  758. package/out/recipes/fr-order.js +0 -198
  759. package/out/recipes/fr-order.js.map +0 -1
  760. package/out/recipes/german.d.ts +0 -44
  761. package/out/recipes/german.d.ts.map +0 -1
  762. package/out/recipes/german.js +0 -289
  763. package/out/recipes/german.js.map +0 -1
  764. package/out/recipes/locale.d.ts +0 -136
  765. package/out/recipes/locale.d.ts.map +0 -1
  766. package/out/recipes/locale.js +0 -460
  767. package/out/recipes/locale.js.map +0 -1
  768. package/out/recipes/nl-postcode.d.ts +0 -26
  769. package/out/recipes/nl-postcode.d.ts.map +0 -1
  770. package/out/recipes/nl-postcode.js +0 -103
  771. package/out/recipes/nl-postcode.js.map +0 -1
  772. package/out/recipes/no-fragment.d.ts +0 -43
  773. package/out/recipes/no-fragment.d.ts.map +0 -1
  774. package/out/recipes/no-fragment.js +0 -183
  775. package/out/recipes/no-fragment.js.map +0 -1
  776. package/out/recipes/no-street-led.d.ts +0 -24
  777. package/out/recipes/no-street-led.d.ts.map +0 -1
  778. package/out/recipes/no-street-led.js +0 -114
  779. package/out/recipes/no-street-led.js.map +0 -1
  780. package/out/recipes/no-street.d.ts +0 -18
  781. package/out/recipes/no-street.d.ts.map +0 -1
  782. package/out/recipes/no-street.js +0 -72
  783. package/out/recipes/no-street.js.map +0 -1
  784. package/out/recipes/po-box-cedex.d.ts +0 -38
  785. package/out/recipes/po-box-cedex.d.ts.map +0 -1
  786. package/out/recipes/po-box-cedex.js +0 -768
  787. package/out/recipes/po-box-cedex.js.map +0 -1
  788. package/out/recipes/po-box.d.ts +0 -17
  789. package/out/recipes/po-box.d.ts.map +0 -1
  790. package/out/recipes/po-box.js +0 -101
  791. package/out/recipes/po-box.js.map +0 -1
  792. package/out/recipes/reviewed-postcode-tail.d.ts.map +0 -1
  793. package/out/recipes/reviewed-postcode-tail.js.map +0 -1
  794. package/out/recipes/si-bare-village.d.ts +0 -32
  795. package/out/recipes/si-bare-village.d.ts.map +0 -1
  796. package/out/recipes/si-bare-village.js +0 -89
  797. package/out/recipes/si-bare-village.js.map +0 -1
  798. package/out/recipes/street-affix.d.ts +0 -89
  799. package/out/recipes/street-affix.d.ts.map +0 -1
  800. package/out/recipes/street-affix.js +0 -563
  801. package/out/recipes/street-affix.js.map +0 -1
  802. package/out/recipes/street-bare.d.ts +0 -25
  803. package/out/recipes/street-bare.d.ts.map +0 -1
  804. package/out/recipes/street-bare.js +0 -87
  805. package/out/recipes/street-bare.js.map +0 -1
  806. package/out/recipes/sub-venue-sources.d.ts +0 -229
  807. package/out/recipes/sub-venue-sources.d.ts.map +0 -1
  808. package/out/recipes/sub-venue-sources.js +0 -654
  809. package/out/recipes/sub-venue-sources.js.map +0 -1
  810. package/out/recipes/sub-venue.d.ts +0 -269
  811. package/out/recipes/sub-venue.d.ts.map +0 -1
  812. package/out/recipes/sub-venue.js +0 -726
  813. package/out/recipes/sub-venue.js.map +0 -1
  814. package/out/synthesizers/german.d.ts +0 -115
  815. package/out/synthesizers/german.d.ts.map +0 -1
  816. package/out/synthesizers/german.js +0 -149
  817. package/out/synthesizers/german.js.map +0 -1
  818. package/out/tools/fetch/acra-sg.d.ts +0 -23
  819. package/out/tools/fetch/acra-sg.d.ts.map +0 -1
  820. package/out/tools/fetch/acra-sg.js +0 -126
  821. package/out/tools/fetch/acra-sg.js.map +0 -1
  822. package/out/tools/fetch/ban.d.ts +0 -31
  823. package/out/tools/fetch/ban.d.ts.map +0 -1
  824. package/out/tools/fetch/ban.js +0 -239
  825. package/out/tools/fetch/ban.js.map +0 -1
  826. package/out/tools/fetch/download.d.ts +0 -182
  827. package/out/tools/fetch/download.d.ts.map +0 -1
  828. package/out/tools/fetch/download.js +0 -318
  829. package/out/tools/fetch/download.js.map +0 -1
  830. package/out/tools/fetch/gcis-tw.d.ts +0 -23
  831. package/out/tools/fetch/gcis-tw.d.ts.map +0 -1
  832. package/out/tools/fetch/gcis-tw.js +0 -135
  833. package/out/tools/fetch/gcis-tw.js.map +0 -1
  834. package/out/tools/fetch/geonames-dump.d.ts +0 -91
  835. package/out/tools/fetch/geonames-dump.d.ts.map +0 -1
  836. package/out/tools/fetch/geonames-dump.js +0 -171
  837. package/out/tools/fetch/geonames-dump.js.map +0 -1
  838. package/out/tools/fetch/geonames-postal.d.ts +0 -76
  839. package/out/tools/fetch/geonames-postal.d.ts.map +0 -1
  840. package/out/tools/fetch/geonames-postal.js +0 -126
  841. package/out/tools/fetch/geonames-postal.js.map +0 -1
  842. package/out/tools/fetch/houjin-jp.d.ts +0 -24
  843. package/out/tools/fetch/houjin-jp.d.ts.map +0 -1
  844. package/out/tools/fetch/houjin-jp.js +0 -102
  845. package/out/tools/fetch/houjin-jp.js.map +0 -1
  846. package/out/tools/fetch/hrsa.d.ts +0 -18
  847. package/out/tools/fetch/hrsa.d.ts.map +0 -1
  848. package/out/tools/fetch/hrsa.js +0 -46
  849. package/out/tools/fetch/hrsa.js.map +0 -1
  850. package/out/tools/fetch/imls-pls.d.ts +0 -25
  851. package/out/tools/fetch/imls-pls.d.ts.map +0 -1
  852. package/out/tools/fetch/imls-pls.js +0 -108
  853. package/out/tools/fetch/imls-pls.js.map +0 -1
  854. package/out/tools/fetch/juso-kr.d.ts +0 -30
  855. package/out/tools/fetch/juso-kr.d.ts.map +0 -1
  856. package/out/tools/fetch/juso-kr.js +0 -120
  857. package/out/tools/fetch/juso-kr.js.map +0 -1
  858. package/out/tools/fetch/localdata-kr.d.ts +0 -30
  859. package/out/tools/fetch/localdata-kr.d.ts.map +0 -1
  860. package/out/tools/fetch/localdata-kr.js +0 -139
  861. package/out/tools/fetch/localdata-kr.js.map +0 -1
  862. package/out/tools/fetch/nad.d.ts +0 -70
  863. package/out/tools/fetch/nad.d.ts.map +0 -1
  864. package/out/tools/fetch/nad.js +0 -234
  865. package/out/tools/fetch/nad.js.map +0 -1
  866. package/out/tools/fetch/nppes.d.ts +0 -26
  867. package/out/tools/fetch/nppes.d.ts.map +0 -1
  868. package/out/tools/fetch/nppes.js +0 -126
  869. package/out/tools/fetch/nppes.js.map +0 -1
  870. package/out/tools/fetch/state-hi-schools.d.ts +0 -26
  871. package/out/tools/fetch/state-hi-schools.d.ts.map +0 -1
  872. package/out/tools/fetch/state-hi-schools.js +0 -112
  873. package/out/tools/fetch/state-hi-schools.js.map +0 -1
  874. package/out/tools/fetch/state-sources.d.ts +0 -26
  875. package/out/tools/fetch/state-sources.d.ts.map +0 -1
  876. package/out/tools/fetch/state-sources.js +0 -111
  877. package/out/tools/fetch/state-sources.js.map +0 -1
  878. package/out/tools/fetch/tiger-full.d.ts +0 -22
  879. package/out/tools/fetch/tiger-full.d.ts.map +0 -1
  880. package/out/tools/fetch/tiger-full.js +0 -217
  881. package/out/tools/fetch/tiger-full.js.map +0 -1
  882. package/out/tools/golden-expand.d.ts +0 -90
  883. package/out/tools/golden-expand.d.ts.map +0 -1
  884. package/out/tools/golden-expand.js +0 -406
  885. package/out/tools/golden-expand.js.map +0 -1
  886. package/out/tools/golden-promote.d.ts +0 -72
  887. package/out/tools/golden-promote.d.ts.map +0 -1
  888. package/out/tools/golden-promote.js +0 -240
  889. package/out/tools/golden-promote.js.map +0 -1
  890. package/out/tools/golden-relabel-street.d.ts +0 -196
  891. package/out/tools/golden-relabel-street.d.ts.map +0 -1
  892. package/out/tools/golden-relabel-street.js +0 -439
  893. package/out/tools/golden-relabel-street.js.map +0 -1
  894. package/out/tools/lint-slice-vocab.d.ts +0 -90
  895. package/out/tools/lint-slice-vocab.d.ts.map +0 -1
  896. package/out/tools/lint-slice-vocab.js +0 -267
  897. package/out/tools/lint-slice-vocab.js.map +0 -1
  898. package/out/tools/lint-slice.d.ts +0 -93
  899. package/out/tools/lint-slice.d.ts.map +0 -1
  900. package/out/tools/lint-slice.js +0 -322
  901. package/out/tools/lint-slice.js.map +0 -1
  902. package/out/tools/slice-kryptonite.d.ts +0 -32
  903. package/out/tools/slice-kryptonite.d.ts.map +0 -1
  904. package/out/tools/slice-kryptonite.js +0 -99
  905. package/out/tools/slice-kryptonite.js.map +0 -1
  906. package/out/tools/slice-translit.d.ts +0 -51
  907. package/out/tools/slice-translit.d.ts.map +0 -1
  908. package/out/tools/slice-translit.js +0 -166
  909. package/out/tools/slice-translit.js.map +0 -1
  910. package/out/tools/sub-venue/harvest.d.ts +0 -100
  911. package/out/tools/sub-venue/harvest.d.ts.map +0 -1
  912. package/out/tools/sub-venue/harvest.js +0 -168
  913. package/out/tools/sub-venue/harvest.js.map +0 -1
  914. package/out/tools/sub-venue/head-nouns.d.ts +0 -50
  915. package/out/tools/sub-venue/head-nouns.d.ts.map +0 -1
  916. package/out/tools/sub-venue/head-nouns.js.map +0 -1
  917. package/out/tools/sub-venue/surfaces.d.ts +0 -45
  918. package/out/tools/sub-venue/surfaces.d.ts.map +0 -1
  919. package/out/tools/sub-venue/surfaces.js.map +0 -1
  920. package/out/tools/sub-venue/table.d.ts +0 -229
  921. package/out/tools/sub-venue/table.d.ts.map +0 -1
  922. package/out/tools/sub-venue/table.js.map +0 -1
  923. package/out/tools/sub-venue/wikidata.d.ts +0 -26
  924. package/out/tools/sub-venue/wikidata.d.ts.map +0 -1
  925. package/out/tools/sub-venue/wikidata.js +0 -62
  926. package/out/tools/sub-venue/wikidata.js.map +0 -1
  927. package/out/tools/sub-venue-lexicon.d.ts +0 -156
  928. package/out/tools/sub-venue-lexicon.d.ts.map +0 -1
  929. package/out/tools/sub-venue-lexicon.js +0 -283
  930. package/out/tools/sub-venue-lexicon.js.map +0 -1
  931. package/out/tools/sub-venue-promotions.d.ts +0 -94
  932. package/out/tools/sub-venue-promotions.d.ts.map +0 -1
  933. package/out/tools/sub-venue-promotions.js +0 -266
  934. package/out/tools/sub-venue-promotions.js.map +0 -1
  935. /package/lib/{recipes/cn-organizational-units.ts → cn/recipes/organizational-units.ts} +0 -0
  936. /package/lib/{recipes/cz-pcfirst-preposition.ts → cz/recipes/pcfirst-preposition.ts} +0 -0
  937. /package/lib/{adapters → fr/adapters}/ban/street-decompose.ts +0 -0
  938. /package/lib/{adapters/wof-admin-jp → jp/adapters/wof-admin}/adapter.ts +0 -0
  939. /package/lib/{recipes/nl-postcode.ts → nl/recipes/postcode.ts} +0 -0
  940. /package/lib/{recipes/no-fragment.ts → no/recipes/fragment.ts} +0 -0
  941. /package/lib/{recipes/no-street.ts → no/recipes/street/index.ts} +0 -0
  942. /package/lib/{recipes/no-street-led.ts → no/recipes/street/led.ts} +0 -0
  943. /package/lib/recipes/{bare-country.ts → bare/country.ts} +0 -0
  944. /package/lib/recipes/{street-bare.ts → street/bare.ts} +0 -0
  945. /package/lib/{recipes/si-bare-village.ts → si/recipes/bare-village.ts} +0 -0
  946. /package/lib/tools/{golden-expand.ts → golden/expand.ts} +0 -0
  947. /package/lib/tools/{lint-slice.ts → lint/slice/index.ts} +0 -0
  948. /package/lib/tools/{slice-kryptonite.ts → slice/kryptonite.ts} +0 -0
  949. /package/lib/tools/{slice-translit.ts → slice/translit.ts} +0 -0
  950. /package/lib/tools/{sub-venue-promotions.ts → sub/venue/promotions.ts} +0 -0
  951. /package/lib/{adapters/state-hi-schools → us/adapters/state/hi-schools}/workbook.ts +0 -0
  952. /package/lib/{adapters → us/adapters}/tiger/street-decompose.ts +0 -0
  953. /package/lib/{codex/us-fips-state.ts → us/fips-state.ts} +0 -0
  954. /package/lib/{recipes → ve/recipes}/reviewed-postcode-tail.ts +0 -0
  955. /package/out/adapters/{geonames-postal → geonames/postal}/adapter.d.ts +0 -0
  956. /package/out/{adapters → au/adapters}/gnaf/adapter.d.ts +0 -0
  957. /package/out/{adapters → fr/adapters}/ban/adapter.d.ts +0 -0
  958. /package/out/{adapters → fr/adapters}/ban/street-decompose.d.ts +0 -0
  959. /package/out/{adapters → fr/adapters}/ban/street-decompose.js +0 -0
  960. /package/out/{adapters/wof-admin-jp → jp/adapters/wof-admin}/adapter.d.ts +0 -0
  961. /package/out/{adapters/wof-admin-jp → jp/adapters/wof-admin}/adapter.js +0 -0
  962. /package/out/tools/{sub-venue → sub/venue}/head-nouns.js +0 -0
  963. /package/out/tools/{sub-venue → sub/venue}/surfaces.js +0 -0
  964. /package/out/tools/{sub-venue → sub/venue}/table.js +0 -0
  965. /package/out/{adapters → us/adapters}/fcc-bdc/adapter.d.ts +0 -0
  966. /package/out/{adapters/state-hi-schools → us/adapters/state/hi-schools}/adapter.d.ts +0 -0
  967. /package/out/{adapters/state-hi-schools → us/adapters/state/hi-schools}/workbook.d.ts +0 -0
  968. /package/out/{adapters/state-hi-schools → us/adapters/state/hi-schools}/workbook.js +0 -0
  969. /package/out/{adapters/state-ia-contractors → us/adapters/state/ia-contractors}/adapter.d.ts +0 -0
  970. /package/out/{adapters/state-ny-notaries → us/adapters/state/ny-notaries}/adapter.d.ts +0 -0
  971. /package/out/{adapters/state-tx-notaries → us/adapters/state/tx-notaries}/adapter.d.ts +0 -0
  972. /package/out/{adapters → us/adapters}/tiger/street-decompose.d.ts +0 -0
  973. /package/out/{adapters → us/adapters}/tiger/street-decompose.js +0 -0
  974. /package/out/{adapters/usgov-hrsa-fqhc → us/adapters/usgov/hrsa-fqhc}/adapter.d.ts +0 -0
  975. /package/out/{adapters/usgov-imls-pls → us/adapters/usgov/imls-pls}/adapter.d.ts +0 -0
  976. /package/out/{adapters/usgov-irs-bmf → us/adapters/usgov/irs-bmf}/adapter.d.ts +0 -0
  977. /package/out/{adapters/usgov-nad → us/adapters/usgov/nad}/adapter.d.ts +0 -0
  978. /package/out/{adapters/usgov-nppes → us/adapters/usgov/nppes}/adapter.d.ts +0 -0
  979. /package/out/{adapters/usgov-samhsa-treatment-locator → us/adapters/usgov/samhsa-treatment-locator}/adapter.d.ts +0 -0
  980. /package/out/{recipes → ve/recipes}/reviewed-postcode-tail.d.ts +0 -0
  981. /package/out/{recipes → ve/recipes}/reviewed-postcode-tail.js +0 -0
@@ -0,0 +1,198 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ *
6
+ * `fr-order` slice recipe — French reversed-order coverage (#560). Reads REAL OpenAddresses FR
7
+ * tuples (`fr/countrywide.csv` from the cached zip), then for each row picks — by
8
+ * `--reversed-fraction` (default 0.5) — whether to render in CANONICAL French order
9
+ * (number-street, postcode-city) or one of four REVERSED / postcode-first variants the
10
+ * v4.4.0→v0.5.0 regression exposed (the model misses house_number in every reversed one):
11
+ *
12
+ * - A: "47110 Sainte-Livrade-sur-Lot, 69 Allée du Bugatel" (postcode city, HN street)
13
+ * - B: "Sainte-Livrade-sur-Lot, 47110, 619 Impasse de la Rose" (city, postcode, HN street)
14
+ * - C: "Sainte-Livrade-sur-Lot 59 bis Rue des Ecuries 47110" (city HN street postcode — NO commas)
15
+ * - D: "47110, 6 rue de la république, Sainte-Livrade-sur-Lot" (postcode, HN street, city)
16
+ *
17
+ * Sub-modes ride alongside order: `bis`/`ter`/`quater` ordinal suffixes in house_number, and
18
+ * ALL-CAPS locality. `--golden` emits a held-out reversed-order eval slice with a different
19
+ * seed.
20
+ *
21
+ * The inline synthesis (the OA-CSV reader, the ordinal/all-caps tables, the canonical + reversed
22
+ * renderers) is ported faithfully from scripts/build-fr-order-slice.mjs. This is a
23
+ * `generate`-mode recipe that still reads REAL tuples off disk — `--count` bounds the OUTPUT, not
24
+ * the input. The passed `random` (the framework LCG) is consumed in the exact call order the
25
+ * legacy script used.
26
+ *
27
+ * NOT ported (diagnostic-only, no effect on emitted bytes): the post-run `runSpanCheck` self-check
28
+ * (it reads the finished file back with a separate PRNG and prints to stderr; the recipe's output
29
+ * stream is still open during `run`), and the dead `renderReversed` helper (the legacy `main`
30
+ * inlined the variant logic and never called it).
31
+ */
32
+ import { dataRootPath } from "@mailwoman/core/data-root";
33
+ import { isPresent } from "@mailwoman/core/objects";
34
+ import { mulberry32 as makeMulberry32 } from "@mailwoman/core/utils";
35
+ import { stableSourceID } from "#adapters/utils";
36
+ import { readOATuples } from "#recipes/scaffold";
37
+ import { pick } from "#synthesizers/utils";
38
+ import { alignRow } from "#utils";
39
+ const SOURCE = { zip: dataRootPath("oa-cache", "fr__countrywide.zip"), csv: "fr/countrywide.csv" };
40
+ /**
41
+ * Ordinal suffixes used in French house numbers (BAN corpus), to cover the "8 bis" sub-mode.
42
+ */
43
+ const ORDINAL_SUFFIXES = ["bis", "ter", "quater"];
44
+ /**
45
+ * Probability that a row gets an ordinal suffix injected (matches the golden's ~10-15% rate).
46
+ */
47
+ const ORDINAL_PROB = 0.12;
48
+ /**
49
+ * Probability that a locality renders ALL-CAPS (another sub-mode: "SAINTE-LIVRADE-SUR-LOT").
50
+ */
51
+ const ALLCAPS_PROB = 0.1;
52
+ /**
53
+ * Stream FR tuples out of the cached OA zip. The countrywide extract is GB-scale, so this reads only as far as `limit`
54
+ * distinct tuples — the `break` closes the reader and releases the archive. Only keeps rows with a house_number (the
55
+ * slice's core signal) and a postcode (required for reversed-order rendering to be meaningful; it is also part of this
56
+ * recipe's dedup key).
57
+ */
58
+ async function readTuples(limit) {
59
+ return readOATuples(SOURCE, {
60
+ limit,
61
+ requirePostcode: true,
62
+ dedupIncludesPostcode: true,
63
+ extra: (fields) => fields,
64
+ });
65
+ }
66
+ /**
67
+ * Optionally augment a house_number with a French ordinal suffix ("59 bis", "4 ter"). Appended with a space so it forms
68
+ * one multi-token house_number string that alignRow can still locate verbatim.
69
+ */
70
+ function maybeAddOrdinal(random, house_number) {
71
+ if (random() >= ORDINAL_PROB)
72
+ return house_number;
73
+ const suffix = pick(ORDINAL_SUFFIXES, random);
74
+ // Vary suffix case: "bis" (lower) vs "BIS" (upper) — a real-world split in the golden.
75
+ return `${house_number} ${random() < 0.5 ? suffix : suffix.toUpperCase()}`;
76
+ }
77
+ /**
78
+ * Render a tuple in CANONICAL French order: "9 Rue de la Promenade, 01200 Villes".
79
+ */
80
+ function renderCanonical(hn, street, postcode, locality) {
81
+ const raw = `${hn} ${street}, ${postcode} ${locality}`;
82
+ return { raw, components: { house_number: hn, street, postcode, locality } };
83
+ }
84
+ // Reversed layouts, a quarter each: A postcode+city then HN+street; B city, postcode, HN+street; C run-together;
85
+ // D postcode, HN+street, city.
86
+ const REVERSED_VARIANT_A_CUTOFF = 0.25;
87
+ const REVERSED_VARIANT_B_CUTOFF = 0.5;
88
+ const REVERSED_VARIANT_C_CUTOFF = 0.75;
89
+ /**
90
+ * Slice recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
91
+ * and `description` below for the surface form it generates.
92
+ */
93
+ export const frOrderRecipe = {
94
+ name: "fr-order",
95
+ description: "French reversed-order rows (#560): real OA FR tuples rendered canonical + 4 postcode-first variants",
96
+ mode: "generate",
97
+ options: [
98
+ { flag: "--reversed-fraction <p>", description: "Fraction rendered reversed-order. Default 0.5" },
99
+ { flag: "--golden", description: "Emit the held-out reversed-order eval slice" },
100
+ ],
101
+ async run(opts, write) {
102
+ if (opts.count == null)
103
+ throw new Error("fr-order recipe requires --count <N>");
104
+ const count = opts.count;
105
+ // Legacy build-fr-order-slice.mjs seeded mulberry32 with the raw seed: `const random = mulberry32(opts.seed)`.
106
+ // (The omitted diagnostic runSpanCheck used a separate mulberry32(opts.seed + 1) — not part of generation.)
107
+ const random = makeMulberry32(opts.seed);
108
+ const source = opts.sourceName ?? "synth-fr-order";
109
+ const reversedFraction = opts.reversedFraction ?? 0.5;
110
+ // Over-read from the CSV so the dedup + filter pass can fill `count` rows.
111
+ const poolLimit = Math.max(count * 8, 40_000);
112
+ const pool = await readTuples(poolLimit);
113
+ console.error(` ${SOURCE.csv}: ${pool.length} unique tuples (capped read)`);
114
+ if (!pool.length) {
115
+ throw new Error(`No FR tuples found — is ${SOURCE.zip} present?`);
116
+ }
117
+ let emitted = 0;
118
+ let skipped = 0;
119
+ let guard = 0;
120
+ const N = pool.length;
121
+ while (emitted < count && guard++ < count * 10) {
122
+ const base = pool[Math.floor(random() * N)];
123
+ const { street, postcode } = base;
124
+ const locality = random() < ALLCAPS_PROB ? base.locality.toUpperCase() : base.locality;
125
+ const house_number = maybeAddOrdinal(random, base.house_number);
126
+ // Pick canonical vs reversed by --reversed-fraction.
127
+ const isReversed = random() < reversedFraction;
128
+ let rendered;
129
+ if (isReversed) {
130
+ const variantRoll = random();
131
+ let raw;
132
+ if (variantRoll < REVERSED_VARIANT_A_CUTOFF) {
133
+ // Variant A: postcode+city as a unit, then HN+street
134
+ raw = `${postcode} ${locality}, ${house_number} ${street}`;
135
+ }
136
+ else if (variantRoll < REVERSED_VARIANT_B_CUTOFF) {
137
+ // Variant B: city, then postcode, then HN+street (comma-separated, postcode isolated)
138
+ raw = `${locality}, ${postcode}, ${house_number} ${street}`;
139
+ }
140
+ else if (variantRoll < REVERSED_VARIANT_C_CUTOFF) {
141
+ // Variant C: no commas — locality HN street postcode (the "run-together" format)
142
+ raw = `${locality} ${house_number} ${street} ${postcode}`;
143
+ }
144
+ else {
145
+ // Variant D: postcode, HN+street, city (reversed top-to-bottom)
146
+ raw = `${postcode}, ${house_number} ${street}, ${locality}`;
147
+ }
148
+ rendered = { raw, components: { house_number, street, postcode, locality } };
149
+ }
150
+ else {
151
+ rendered = renderCanonical(house_number, street, postcode, locality);
152
+ }
153
+ const { raw, components } = rendered;
154
+ // Safety check: every component must appear verbatim in raw (alignment precondition).
155
+ const componentValues = Object.values(components).filter(isPresent);
156
+ if (!componentValues.every((v) => raw.includes(v))) {
157
+ skipped++;
158
+ continue;
159
+ }
160
+ // --golden: emit per-locale-f1 eval rows ({raw, components, country:"FR"}).
161
+ if (opts.golden) {
162
+ write(JSON.stringify({ raw, components, country: "FR" }) + "\n");
163
+ emitted++;
164
+ continue;
165
+ }
166
+ const sourceID = stableSourceID(source, {
167
+ street: components.street,
168
+ house_number: components.house_number,
169
+ locality: components.locality,
170
+ postcode: components.postcode,
171
+ });
172
+ const canonical = {
173
+ raw,
174
+ components,
175
+ country: "FR",
176
+ locale: "fr-FR",
177
+ source,
178
+ source_id: sourceID,
179
+ corpus_version: "0.5.0",
180
+ license: "OpenAddresses FR countrywide tuples, rendered canonical + reversed-order — see ingest SOURCE",
181
+ };
182
+ const aligned = alignRow(canonical);
183
+ if (aligned.kind !== "labeled" || !aligned.row) {
184
+ skipped++;
185
+ continue;
186
+ }
187
+ write(JSON.stringify({
188
+ ...aligned.row,
189
+ synth_method: "fr-order",
190
+ synth_order: isReversed ? "reversed" : "canonical",
191
+ synth_base_id: null,
192
+ }) + "\n");
193
+ emitted++;
194
+ }
195
+ return { emitted, skipped };
196
+ },
197
+ };
198
+ //# sourceMappingURL=order.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"order.js","sourceRoot":"","sources":["../../../lib/fr/recipes/order.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8BG;AAGH,OAAO,EAAE,YAAY,EAAE,MAAM,2BAA2B,CAAA;AACxD,OAAO,EAAE,SAAS,EAAE,MAAM,yBAAyB,CAAA;AACnD,OAAO,EAAE,UAAU,IAAI,cAAc,EAAE,MAAM,uBAAuB,CAAA;AAEpE,OAAO,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAA;AAChD,OAAO,EAAE,YAAY,EAAqB,MAAM,mBAAmB,CAAA;AACnE,OAAO,EAAE,IAAI,EAAE,MAAM,qBAAqB,CAAA;AAE1C,OAAO,EAAE,QAAQ,EAAE,MAAM,QAAQ,CAAA;AAEjC,MAAM,MAAM,GAAG,EAAE,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,qBAAqB,CAAC,EAAE,GAAG,EAAE,oBAAoB,EAAE,CAAA;AAElG;;GAEG;AACH,MAAM,gBAAgB,GAAsB,CAAC,KAAK,EAAE,KAAK,EAAE,QAAQ,CAAC,CAAA;AACpE;;GAEG;AACH,MAAM,YAAY,GAAG,IAAI,CAAA;AACzB;;GAEG;AACH,MAAM,YAAY,GAAG,GAAG,CAAA;AAYxB;;;;;GAKG;AACH,KAAK,UAAU,UAAU,CAAC,KAAa;IACtC,OAAO,YAAY,CAAC,MAAM,EAAE;QAC3B,KAAK;QACL,eAAe,EAAE,IAAI;QACrB,qBAAqB,EAAE,IAAI;QAC3B,KAAK,EAAE,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM;KACzB,CAAC,CAAA;AACH,CAAC;AAED;;;GAGG;AACH,SAAS,eAAe,CAAC,MAAoB,EAAE,YAAoB;IAClE,IAAI,MAAM,EAAE,IAAI,YAAY;QAAE,OAAO,YAAY,CAAA;IACjD,MAAM,MAAM,GAAG,IAAI,CAAC,gBAAgB,EAAE,MAAM,CAAC,CAAA;IAE7C,uFAAuF;IACvF,OAAO,GAAG,YAAY,IAAI,MAAM,EAAE,GAAG,GAAG,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,WAAW,EAAE,EAAE,CAAA;AAC3E,CAAC;AAED;;GAEG;AACH,SAAS,eAAe,CACvB,EAAU,EACV,MAAc,EACd,QAAgB,EAChB,QAAgB;IAEhB,MAAM,GAAG,GAAG,GAAG,EAAE,IAAI,MAAM,KAAK,QAAQ,IAAI,QAAQ,EAAE,CAAA;IAEtD,OAAO,EAAE,GAAG,EAAE,UAAU,EAAE,EAAE,YAAY,EAAE,EAAE,EAAE,MAAM,EAAE,QAAQ,EAAE,QAAQ,EAAE,EAAE,CAAA;AAC7E,CAAC;AAED,iHAAiH;AACjH,+BAA+B;AAC/B,MAAM,yBAAyB,GAAG,IAAI,CAAA;AACtC,MAAM,yBAAyB,GAAG,GAAG,CAAA;AACrC,MAAM,yBAAyB,GAAG,IAAI,CAAA;AAEtC;;;GAGG;AACH,MAAM,CAAC,MAAM,aAAa,GAAiB;IAC1C,IAAI,EAAE,UAAU;IAChB,WAAW,EAAE,qGAAqG;IAClH,IAAI,EAAE,UAAU;IAChB,OAAO,EAAE;QACR,EAAE,IAAI,EAAE,yBAAyB,EAAE,WAAW,EAAE,+CAA+C,EAAE;QACjG,EAAE,IAAI,EAAE,UAAU,EAAE,WAAW,EAAE,6CAA6C,EAAE;KAChF;IACD,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,IAAI,IAAI,CAAC,KAAK,IAAI,IAAI;YAAE,MAAM,IAAI,KAAK,CAAC,sCAAsC,CAAC,CAAA;QAC/E,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAA;QACxB,+GAA+G;QAC/G,4GAA4G;QAC5G,MAAM,MAAM,GAAG,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACxC,MAAM,MAAM,GAAG,IAAI,CAAC,UAAU,IAAI,gBAAgB,CAAA;QAClD,MAAM,gBAAgB,GAAG,IAAI,CAAC,gBAAgB,IAAI,GAAG,CAAA;QAErD,2EAA2E;QAC3E,MAAM,SAAS,GAAG,IAAI,CAAC,GAAG,CAAC,KAAK,GAAG,CAAC,EAAE,MAAM,CAAC,CAAA;QAC7C,MAAM,IAAI,GAAG,MAAM,UAAU,CAAC,SAAS,CAAC,CAAA;QAExC,OAAO,CAAC,KAAK,CAAC,KAAK,MAAM,CAAC,GAAG,KAAK,IAAI,CAAC,MAAM,8BAA8B,CAAC,CAAA;QAE5E,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,CAAC;YAClB,MAAM,IAAI,KAAK,CAAC,2BAA2B,MAAM,CAAC,GAAG,WAAW,CAAC,CAAA;QAClE,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,EAAE,EAAE,CAAC;YAChD,MAAM,IAAI,GAAG,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,CAAE,CAAA;YAC5C,MAAM,EAAE,MAAM,EAAE,QAAQ,EAAE,GAAG,IAAI,CAAA;YACjC,MAAM,QAAQ,GAAG,MAAM,EAAE,GAAG,YAAY,CAAC,CAAC,CAAC,IAAI,CAAC,QAAQ,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,QAAQ,CAAA;YACtF,MAAM,YAAY,GAAG,eAAe,CAAC,MAAM,EAAE,IAAI,CAAC,YAAY,CAAC,CAAA;YAE/D,qDAAqD;YACrD,MAAM,UAAU,GAAG,MAAM,EAAE,GAAG,gBAAgB,CAAA;YAE9C,IAAI,QAA4E,CAAA;YAEhF,IAAI,UAAU,EAAE,CAAC;gBAChB,MAAM,WAAW,GAAG,MAAM,EAAE,CAAA;gBAC5B,IAAI,GAAW,CAAA;gBAEf,IAAI,WAAW,GAAG,yBAAyB,EAAE,CAAC;oBAC7C,qDAAqD;oBACrD,GAAG,GAAG,GAAG,QAAQ,IAAI,QAAQ,KAAK,YAAY,IAAI,MAAM,EAAE,CAAA;gBAC3D,CAAC;qBAAM,IAAI,WAAW,GAAG,yBAAyB,EAAE,CAAC;oBACpD,sFAAsF;oBACtF,GAAG,GAAG,GAAG,QAAQ,KAAK,QAAQ,KAAK,YAAY,IAAI,MAAM,EAAE,CAAA;gBAC5D,CAAC;qBAAM,IAAI,WAAW,GAAG,yBAAyB,EAAE,CAAC;oBACpD,iFAAiF;oBACjF,GAAG,GAAG,GAAG,QAAQ,IAAI,YAAY,IAAI,MAAM,IAAI,QAAQ,EAAE,CAAA;gBAC1D,CAAC;qBAAM,CAAC;oBACP,gEAAgE;oBAChE,GAAG,GAAG,GAAG,QAAQ,KAAK,YAAY,IAAI,MAAM,KAAK,QAAQ,EAAE,CAAA;gBAC5D,CAAC;gBAED,QAAQ,GAAG,EAAE,GAAG,EAAE,UAAU,EAAE,EAAE,YAAY,EAAE,MAAM,EAAE,QAAQ,EAAE,QAAQ,EAAE,EAAE,CAAA;YAC7E,CAAC;iBAAM,CAAC;gBACP,QAAQ,GAAG,eAAe,CAAC,YAAY,EAAE,MAAM,EAAE,QAAQ,EAAE,QAAQ,CAAC,CAAA;YACrE,CAAC;YAED,MAAM,EAAE,GAAG,EAAE,UAAU,EAAE,GAAG,QAAQ,CAAA;YAEpC,sFAAsF;YACtF,MAAM,eAAe,GAAG,MAAM,CAAC,MAAM,CAAC,UAAU,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAA;YAEnE,IAAI,CAAC,eAAe,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;gBACpD,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,4EAA4E;YAC5E,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC;gBACjB,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,GAAG,EAAE,UAAU,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,GAAG,IAAI,CAAC,CAAA;gBAEhE,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,MAAM,QAAQ,GAAG,cAAc,CAAC,MAAM,EAAE;gBACvC,MAAM,EAAE,UAAU,CAAC,MAAM;gBACzB,YAAY,EAAE,UAAU,CAAC,YAAY;gBACrC,QAAQ,EAAE,UAAU,CAAC,QAAQ;gBAC7B,QAAQ,EAAE,UAAU,CAAC,QAAQ;aAC7B,CAAC,CAAA;YAEF,MAAM,SAAS,GAAiB;gBAC/B,GAAG;gBACH,UAAU;gBACV,OAAO,EAAE,IAAI;gBACb,MAAM,EAAE,OAAO;gBACf,MAAM;gBACN,SAAS,EAAE,QAAQ;gBACnB,cAAc,EAAE,OAAO;gBACvB,OAAO,EAAE,8FAA8F;aACvG,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,CACJ,IAAI,CAAC,SAAS,CAAC;gBACd,GAAG,OAAO,CAAC,GAAG;gBACd,YAAY,EAAE,UAAU;gBACxB,WAAW,EAAE,UAAU,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,WAAW;gBAClD,aAAa,EAAE,IAAI;aACnB,CAAC,GAAG,IAAI,CACT,CAAA;YAED,OAAO,EAAE,CAAA;QACV,CAAC;QAED,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;IAC5B,CAAC;CACD,CAAA"}
@@ -0,0 +1,31 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ *
6
+ * Fetch the full French BAN (Base Adresse Nationale) — all metropolitan départements (01-95, 2A,
7
+ * 2B) plus 5 overseas DOM/TOM (971-976 excl. 975).
8
+ *
9
+ * Source: https://adresse.data.gouv.fr/data/ban/adresses/latest/csv/
10
+ * Licence: Licence Ouverte 2.0 (attribution required — Tier B).
11
+ *
12
+ * Files already present with matching sha256 are skipped (re-runnable). Downloads `.csv.gz`,
13
+ * decompresses to `.csv`, deletes the `.gz` artifact. One shared `MANIFEST.json` at
14
+ * `<outRoot>/ban/MANIFEST.json` covers all codes.
15
+ *
16
+ * Invoke via `mailwoman corpus fetch ban --out-root <path>`. Built-in `fetch` with gzip/brotli
17
+ * decompression replaces curl; native `node:zlib` gunzip replaces the `gunzip` subprocess; no
18
+ * Python.
19
+ */
20
+ import type { BaseFetchOptions, FetchSummary } from "#tools/fetch/download/index";
21
+ export interface BanManifestEntry {
22
+ dept_code: string;
23
+ filename: string;
24
+ source_url: string;
25
+ downloaded_at: string;
26
+ sha256: string;
27
+ bytes: number;
28
+ }
29
+ export type FetchBanOptions = BaseFetchOptions;
30
+ export declare function fetchBan(options: FetchBanOptions, report?: (line: string) => void): Promise<FetchSummary>;
31
+ //# sourceMappingURL=ban.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"ban.d.ts","sourceRoot":"","sources":["../../../../lib/fr/tools/fetch/ban.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;GAkBG;AAUH,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAAE,MAAM,6BAA6B,CAAA;AAsHjF,MAAM,WAAW,gBAAgB;IAChC,SAAS,EAAE,MAAM,CAAA;IACjB,QAAQ,EAAE,MAAM,CAAA;IAChB,UAAU,EAAE,MAAM,CAAA;IAClB,aAAa,EAAE,MAAM,CAAA;IACrB,MAAM,EAAE,MAAM,CAAA;IACd,KAAK,EAAE,MAAM,CAAA;CACb;AAED,MAAM,MAAM,eAAe,GAAG,gBAAgB,CAAA;AAE9C,wBAAsB,QAAQ,CAAC,OAAO,EAAE,eAAe,EAAE,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAAG,OAAO,CAAC,YAAY,CAAC,CAmI/G"}
@@ -0,0 +1,239 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ *
6
+ * Fetch the full French BAN (Base Adresse Nationale) — all metropolitan départements (01-95, 2A,
7
+ * 2B) plus 5 overseas DOM/TOM (971-976 excl. 975).
8
+ *
9
+ * Source: https://adresse.data.gouv.fr/data/ban/adresses/latest/csv/
10
+ * Licence: Licence Ouverte 2.0 (attribution required — Tier B).
11
+ *
12
+ * Files already present with matching sha256 are skipped (re-runnable). Downloads `.csv.gz`,
13
+ * decompresses to `.csv`, deletes the `.gz` artifact. One shared `MANIFEST.json` at
14
+ * `<outRoot>/ban/MANIFEST.json` covers all codes.
15
+ *
16
+ * Invoke via `mailwoman corpus fetch ban --out-root <path>`. Built-in `fetch` with gzip/brotli
17
+ * decompression replaces curl; native `node:zlib` gunzip replaces the `gunzip` subprocess; no
18
+ * Python.
19
+ */
20
+ import { gunzip } from "@mailwoman/core/fs/compression";
21
+ import { BYTES_PER_KIB, ByteFormatter } from "@mailwoman/core/fs/formatters";
22
+ import { isFile, readLocalBuffer, tryStat } from "@mailwoman/core/fs/readers";
23
+ import { makeDirectories, removePath, writeLocalFile } from "@mailwoman/core/fs/writers";
24
+ import { sha256File } from "@mailwoman/core/hash";
25
+ import { sleep } from "@mailwoman/core/utils/sleep";
26
+ import { join } from "path-ts";
27
+ import { downloadToFile, loadManifestEntries, writeManifest } from "#tools/fetch/download/index";
28
+ /**
29
+ * Bytes per KiB — the divisor for human-readable sizes, and the floor below which a "download" is an error page rather
30
+ * than data.
31
+ */
32
+ const BASE_URL = "https://adresse.data.gouv.fr/data/ban/adresses/latest/csv";
33
+ /**
34
+ * All département codes — metropolitan 01-95 (with 2A/2B for Corsica instead of 20) plus overseas DOM/TOM. Codes do not
35
+ * change.
36
+ */
37
+ const DEPT_CODES = [
38
+ "01",
39
+ "02",
40
+ "03",
41
+ "04",
42
+ "05",
43
+ "06",
44
+ "07",
45
+ "08",
46
+ "09",
47
+ "10",
48
+ "11",
49
+ "12",
50
+ "13",
51
+ "14",
52
+ "15",
53
+ "16",
54
+ "17",
55
+ "18",
56
+ "19",
57
+ "21",
58
+ "22",
59
+ "23",
60
+ "24",
61
+ "25",
62
+ "26",
63
+ "27",
64
+ "28",
65
+ "29",
66
+ "2A",
67
+ "2B",
68
+ "30",
69
+ "31",
70
+ "32",
71
+ "33",
72
+ "34",
73
+ "35",
74
+ "36",
75
+ "37",
76
+ "38",
77
+ "39",
78
+ "40",
79
+ "41",
80
+ "42",
81
+ "43",
82
+ "44",
83
+ "45",
84
+ "46",
85
+ "47",
86
+ "48",
87
+ "49",
88
+ "50",
89
+ "51",
90
+ "52",
91
+ "53",
92
+ "54",
93
+ "55",
94
+ "56",
95
+ "57",
96
+ "58",
97
+ "59",
98
+ "60",
99
+ "61",
100
+ "62",
101
+ "63",
102
+ "64",
103
+ "65",
104
+ "66",
105
+ "67",
106
+ "68",
107
+ "69",
108
+ "70",
109
+ "71",
110
+ "72",
111
+ "73",
112
+ "74",
113
+ "75",
114
+ "76",
115
+ "77",
116
+ "78",
117
+ "79",
118
+ "80",
119
+ "81",
120
+ "82",
121
+ "83",
122
+ "84",
123
+ "85",
124
+ "86",
125
+ "87",
126
+ "88",
127
+ "89",
128
+ "90",
129
+ "91",
130
+ "92",
131
+ "93",
132
+ "94",
133
+ "95",
134
+ "971",
135
+ "972",
136
+ "973",
137
+ "974",
138
+ "976",
139
+ ];
140
+ export async function fetchBan(options, report) {
141
+ const banDir = join(options.outRoot, "ban");
142
+ const manifestPath = join(banDir, "MANIFEST.json");
143
+ await makeDirectories(banDir);
144
+ // Load existing entries (code -> entry): skip detection + preservation of untouched codes.
145
+ const entries = await loadManifestEntries(manifestPath, (entry) => entry.dept_code);
146
+ let fetched = 0;
147
+ let skipped = 0;
148
+ let failed = 0;
149
+ const failedCodes = [];
150
+ for (const code of DEPT_CODES) {
151
+ const filename = `adresses-${code}.csv`;
152
+ const gzFile = join(banDir, `${filename}.gz`);
153
+ const csvFile = join(banDir, filename);
154
+ const url = `${BASE_URL}/adresses-${code}.csv.gz`;
155
+ report?.(`=== dept ${code}`);
156
+ // If the CSV already exists, compare its sha256 against the manifest.
157
+ if (await isFile(csvFile)) {
158
+ const existingSha = await sha256File(csvFile);
159
+ const recordedSha = entries.get(code)?.sha256;
160
+ if (recordedSha && existingSha === recordedSha) {
161
+ report?.(` → already present + sha matches — skipping`);
162
+ skipped++;
163
+ continue;
164
+ }
165
+ report?.(` → present but sha mismatch or no manifest entry — re-fetching`);
166
+ await removePath(csvFile);
167
+ }
168
+ // Download the gzipped CSV.
169
+ try {
170
+ await downloadToFile({
171
+ url,
172
+ dest: gzFile,
173
+ timeoutMs: 600_000,
174
+ headers: { "Accept-Encoding": "gzip, br" },
175
+ report,
176
+ });
177
+ }
178
+ catch (error) {
179
+ report?.(` ✗ download failed: ${url} (${error.message})`);
180
+ failed++;
181
+ failedCodes.push(code);
182
+ continue;
183
+ }
184
+ // Guard against truncated 404/error pages.
185
+ const gzSize = (await tryStat(gzFile))?.size ?? 0;
186
+ if (gzSize < BYTES_PER_KIB) {
187
+ report?.(` ✗ response too small (${gzSize} bytes) — probable 404 / error page`);
188
+ await removePath(gzFile);
189
+ failed++;
190
+ failedCodes.push(code);
191
+ continue;
192
+ }
193
+ // Decompress in-place; delete the .gz.
194
+ try {
195
+ await writeLocalFile(await gunzip(await readLocalBuffer(gzFile)), csvFile);
196
+ }
197
+ catch (error) {
198
+ report?.(` ✗ decompress failed: ${error.message}`);
199
+ await removePath(gzFile);
200
+ failed++;
201
+ failedCodes.push(code);
202
+ continue;
203
+ }
204
+ await removePath(gzFile);
205
+ if (!(await isFile(csvFile))) {
206
+ report?.(` ✗ decompressed file not found at ${csvFile}`);
207
+ failed++;
208
+ failedCodes.push(code);
209
+ continue;
210
+ }
211
+ const bytes = (await tryStat(csvFile))?.size ?? 0;
212
+ const sha = await sha256File(csvFile);
213
+ entries.set(code, {
214
+ dept_code: code,
215
+ filename,
216
+ source_url: url,
217
+ downloaded_at: new Date().toISOString(),
218
+ sha256: sha,
219
+ bytes,
220
+ });
221
+ report?.(` ✓ ${ByteFormatter.formatIEC(bytes)} sha256=${sha}`);
222
+ fetched++;
223
+ // Be a polite citizen — short pause between requests.
224
+ await sleep(200);
225
+ }
226
+ // Write the consolidated MANIFEST.json (entries sorted by dept_code, codepoint order).
227
+ const sorted = [...entries.values()].toSorted((a, b) => a.dept_code < b.dept_code ? -1 : a.dept_code > b.dept_code ? 1 : 0);
228
+ await writeManifest(manifestPath, sorted);
229
+ report?.(`Wrote ${manifestPath} with ${sorted.length} entries.`);
230
+ report?.(`=== summary ===`);
231
+ report?.(`fetched: ${fetched}`);
232
+ report?.(`skipped: ${skipped} (already present + sha matched)`);
233
+ report?.(`failed: ${failed}`);
234
+ if (failedCodes.length) {
235
+ report?.(`failed codes: ${failedCodes.join(" ")}`);
236
+ }
237
+ return { fetched, skipped, failed, failedCodes };
238
+ }
239
+ //# sourceMappingURL=ban.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"ban.js","sourceRoot":"","sources":["../../../../lib/fr/tools/fetch/ban.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;GAkBG;AAEH,OAAO,EAAE,MAAM,EAAE,MAAM,gCAAgC,CAAA;AACvD,OAAO,EAAE,aAAa,EAAE,aAAa,EAAE,MAAM,+BAA+B,CAAA;AAC5E,OAAO,EAAE,MAAM,EAAE,eAAe,EAAE,OAAO,EAAE,MAAM,4BAA4B,CAAA;AAC7E,OAAO,EAAE,eAAe,EAAE,UAAU,EAAE,cAAc,EAAE,MAAM,4BAA4B,CAAA;AACxF,OAAO,EAAE,UAAU,EAAE,MAAM,sBAAsB,CAAA;AACjD,OAAO,EAAE,KAAK,EAAE,MAAM,6BAA6B,CAAA;AACnD,OAAO,EAAE,IAAI,EAAE,MAAM,SAAS,CAAA;AAG9B,OAAO,EAAE,cAAc,EAAE,mBAAmB,EAAE,aAAa,EAAE,MAAM,6BAA6B,CAAA;AAEhG;;;GAGG;AAEH,MAAM,QAAQ,GAAG,2DAA2D,CAAA;AAE5E;;;GAGG;AACH,MAAM,UAAU,GAAG;IAClB,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,KAAK;IACL,KAAK;IACL,KAAK;IACL,KAAK;IACL,KAAK;CACL,CAAA;AAaD,MAAM,CAAC,KAAK,UAAU,QAAQ,CAAC,OAAwB,EAAE,MAA+B;IACvF,MAAM,MAAM,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,KAAK,CAAC,CAAA;IAC3C,MAAM,YAAY,GAAG,IAAI,CAAC,MAAM,EAAE,eAAe,CAAC,CAAA;IAClD,MAAM,eAAe,CAAC,MAAM,CAAC,CAAA;IAE7B,2FAA2F;IAC3F,MAAM,OAAO,GAAG,MAAM,mBAAmB,CAAmB,YAAY,EAAE,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,SAAS,CAAC,CAAA;IAErG,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,MAAM,GAAG,CAAC,CAAA;IACd,MAAM,WAAW,GAAa,EAAE,CAAA;IAEhC,KAAK,MAAM,IAAI,IAAI,UAAU,EAAE,CAAC;QAC/B,MAAM,QAAQ,GAAG,YAAY,IAAI,MAAM,CAAA;QACvC,MAAM,MAAM,GAAG,IAAI,CAAC,MAAM,EAAE,GAAG,QAAQ,KAAK,CAAC,CAAA;QAC7C,MAAM,OAAO,GAAG,IAAI,CAAC,MAAM,EAAE,QAAQ,CAAC,CAAA;QACtC,MAAM,GAAG,GAAG,GAAG,QAAQ,aAAa,IAAI,SAAS,CAAA;QAEjD,MAAM,EAAE,CAAC,YAAY,IAAI,EAAE,CAAC,CAAA;QAE5B,sEAAsE;QACtE,IAAI,MAAM,MAAM,CAAC,OAAO,CAAC,EAAE,CAAC;YAC3B,MAAM,WAAW,GAAG,MAAM,UAAU,CAAC,OAAO,CAAC,CAAA;YAC7C,MAAM,WAAW,GAAG,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,MAAM,CAAA;YAE7C,IAAI,WAAW,IAAI,WAAW,KAAK,WAAW,EAAE,CAAC;gBAChD,MAAM,EAAE,CAAC,8CAA8C,CAAC,CAAA;gBAExD,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,MAAM,EAAE,CAAC,iEAAiE,CAAC,CAAA;YAC3E,MAAM,UAAU,CAAC,OAAO,CAAC,CAAA;QAC1B,CAAC;QAED,4BAA4B;QAC5B,IAAI,CAAC;YACJ,MAAM,cAAc,CAAC;gBACpB,GAAG;gBACH,IAAI,EAAE,MAAM;gBACZ,SAAS,EAAE,OAAO;gBAClB,OAAO,EAAE,EAAE,iBAAiB,EAAE,UAAU,EAAE;gBAC1C,MAAM;aACN,CAAC,CAAA;QACH,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,MAAM,EAAE,CAAC,wBAAwB,GAAG,KAAM,KAAe,CAAC,OAAO,GAAG,CAAC,CAAA;YAErE,MAAM,EAAE,CAAA;YACR,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;YAEtB,SAAQ;QACT,CAAC;QAED,2CAA2C;QAC3C,MAAM,MAAM,GAAG,CAAC,MAAM,OAAO,CAAC,MAAM,CAAC,CAAC,EAAE,IAAI,IAAI,CAAC,CAAA;QAEjD,IAAI,MAAM,GAAG,aAAa,EAAE,CAAC;YAC5B,MAAM,EAAE,CAAC,2BAA2B,MAAM,qCAAqC,CAAC,CAAA;YAChF,MAAM,UAAU,CAAC,MAAM,CAAC,CAAA;YAExB,MAAM,EAAE,CAAA;YACR,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;YAEtB,SAAQ;QACT,CAAC;QAED,uCAAuC;QACvC,IAAI,CAAC;YACJ,MAAM,cAAc,CAAC,MAAM,MAAM,CAAC,MAAM,eAAe,CAAC,MAAM,CAAC,CAAC,EAAE,OAAO,CAAC,CAAA;QAC3E,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,MAAM,EAAE,CAAC,0BAA2B,KAAe,CAAC,OAAO,EAAE,CAAC,CAAA;YAC9D,MAAM,UAAU,CAAC,MAAM,CAAC,CAAA;YAExB,MAAM,EAAE,CAAA;YACR,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;YAEtB,SAAQ;QACT,CAAC;QAED,MAAM,UAAU,CAAC,MAAM,CAAC,CAAA;QAExB,IAAI,CAAC,CAAC,MAAM,MAAM,CAAC,OAAO,CAAC,CAAC,EAAE,CAAC;YAC9B,MAAM,EAAE,CAAC,sCAAsC,OAAO,EAAE,CAAC,CAAA;YAEzD,MAAM,EAAE,CAAA;YACR,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;YAEtB,SAAQ;QACT,CAAC;QAED,MAAM,KAAK,GAAG,CAAC,MAAM,OAAO,CAAC,OAAO,CAAC,CAAC,EAAE,IAAI,IAAI,CAAC,CAAA;QACjD,MAAM,GAAG,GAAG,MAAM,UAAU,CAAC,OAAO,CAAC,CAAA;QAErC,OAAO,CAAC,GAAG,CAAC,IAAI,EAAE;YACjB,SAAS,EAAE,IAAI;YACf,QAAQ;YACR,UAAU,EAAE,GAAG;YACf,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;YACvC,MAAM,EAAE,GAAG;YACX,KAAK;SACL,CAAC,CAAA;QAEF,MAAM,EAAE,CAAC,OAAO,aAAa,CAAC,SAAS,CAAC,KAAK,CAAC,YAAY,GAAG,EAAE,CAAC,CAAA;QAEhE,OAAO,EAAE,CAAA;QAET,sDAAsD;QACtD,MAAM,KAAK,CAAC,GAAG,CAAC,CAAA;IACjB,CAAC;IAED,uFAAuF;IACvF,MAAM,MAAM,GAAG,CAAC,GAAG,OAAO,CAAC,MAAM,EAAE,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CACtD,CAAC,CAAC,SAAS,GAAG,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,SAAS,GAAG,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAClE,CAAA;IAED,MAAM,aAAa,CAAC,YAAY,EAAE,MAAM,CAAC,CAAA;IACzC,MAAM,EAAE,CAAC,SAAS,YAAY,SAAS,MAAM,CAAC,MAAM,WAAW,CAAC,CAAA;IAEhE,MAAM,EAAE,CAAC,iBAAiB,CAAC,CAAA;IAC3B,MAAM,EAAE,CAAC,aAAa,OAAO,EAAE,CAAC,CAAA;IAChC,MAAM,EAAE,CAAC,aAAa,OAAO,kCAAkC,CAAC,CAAA;IAChE,MAAM,EAAE,CAAC,aAAa,MAAM,EAAE,CAAC,CAAA;IAE/B,IAAI,WAAW,CAAC,MAAM,EAAE,CAAC;QACxB,MAAM,EAAE,CAAC,iBAAiB,WAAW,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,CAAA;IACnD,CAAC;IAED,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,EAAE,WAAW,EAAE,CAAA;AACjD,CAAC"}
package/out/index.d.ts CHANGED
@@ -4,7 +4,7 @@
4
4
  * @author Teffen Ellis, et al.
5
5
  */
6
6
  export * from "#adapters/utils/index";
7
- export * from "#adapters/gnaf/assemble";
7
+ export * from "#au/adapters/gnaf/assemble";
8
8
  export * from "#adapters/index";
9
9
  export * from "#build";
10
10
  export * from "#runner";
@@ -1 +1 @@
1
- {"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../lib/index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,cAAc,uBAAuB,CAAA;AACrC,cAAc,yBAAyB,CAAA;AACvC,cAAc,iBAAiB,CAAA;AAC/B,cAAc,QAAQ,CAAA;AACtB,cAAc,SAAS,CAAA;AACvB,cAAc,gBAAgB,CAAA;AAC9B,cAAc,QAAQ,CAAA"}
1
+ {"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../lib/index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,cAAc,uBAAuB,CAAA;AACrC,cAAc,4BAA4B,CAAA;AAC1C,cAAc,iBAAiB,CAAA;AAC/B,cAAc,QAAQ,CAAA;AACtB,cAAc,SAAS,CAAA;AACvB,cAAc,gBAAgB,CAAA;AAC9B,cAAc,QAAQ,CAAA"}
package/out/index.js CHANGED
@@ -4,7 +4,7 @@
4
4
  * @author Teffen Ellis, et al.
5
5
  */
6
6
  export * from "#adapters/utils/index";
7
- export * from "#adapters/gnaf/assemble";
7
+ export * from "#au/adapters/gnaf/assemble";
8
8
  export * from "#adapters/index";
9
9
  export * from "#build";
10
10
  export * from "#runner";
package/out/index.js.map CHANGED
@@ -1 +1 @@
1
- {"version":3,"file":"index.js","sourceRoot":"","sources":["../lib/index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,cAAc,uBAAuB,CAAA;AACrC,cAAc,yBAAyB,CAAA;AACvC,cAAc,iBAAiB,CAAA;AAC/B,cAAc,QAAQ,CAAA;AACtB,cAAc,SAAS,CAAA;AACvB,cAAc,gBAAgB,CAAA;AAC9B,cAAc,QAAQ,CAAA"}
1
+ {"version":3,"file":"index.js","sourceRoot":"","sources":["../lib/index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,cAAc,uBAAuB,CAAA;AACrC,cAAc,4BAA4B,CAAA;AAC1C,cAAc,iBAAiB,CAAA;AAC/B,cAAc,QAAQ,CAAA;AACtB,cAAc,SAAS,CAAA;AACvB,cAAc,gBAAgB,CAAA;AAC9B,cAAc,QAAQ,CAAA"}
@@ -0,0 +1,136 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ *
6
+ * `locale` slice recipe — the multi-locale generalization of the `german` recipe. Reads REAL
7
+ * OpenAddresses tuples for a `--country` (DE/FR/NL/IT/ES), renders each via
8
+ * {@link synthesizeLocaleRow} in BOTH orders (`--intl-fraction`, default 0.4 international / the
9
+ * rest country-native), aligns to BIO, and emits a labeled JSONL. Generate-mode: it STREAMS each
10
+ * source CSV (a streamed zip member for cached zips, plain `createReadStream` for extracted CSVs) and
11
+ * reservoir-samples to {@link RESERVOIR_CAP} (so FR/ES countrywide work in bounded memory), then
12
+ * draws `--count` rows from the pool with the passed `random`. Ported from
13
+ * scripts/build-locale-slice.mjs.
14
+ *
15
+ * The reservoir uses its OWN seeded PRNG ({@link makeMulberry32}, per part), independent of the
16
+ * emit `random`, so the input sample is reproducible WITHOUT perturbing the synth/order draws.
17
+ *
18
+ * SURFACE DIVERSITY (#241): two per-country shape draws ride the emit loop, sized by the
19
+ * 2026-07-02 format-diversity audit against the `openaddresses-{es,nl,it}-sample.jsonl` observed
20
+ * forms. ES: the OpenCage template comma-joins the house number (`CALLE MAYOR, 12`) but all 3,000
21
+ * eval rows space-join (`CALLE MAYOR 12`) — {@link ES_SPACE_JOIN_FRACTION} of native rows collapse
22
+ * the comma. NL: OA (and the eval, 3,000/3,000) glue the postcode (`1187LM`) while the national
23
+ * convention spaces it (`1187 LM`) — {@link NL_GLUED_POSTCODE_FRACTION} of rows keep the glued
24
+ * source shape, the rest the spaced conventional one. These draws are consumed ONLY for their
25
+ * country, so DE/FR emit streams are unchanged for a given seed.
26
+ */
27
+ import type { PathBuilderLike } from "path-ts";
28
+ import type { CorpusRecipe } from "#recipes/scaffold";
29
+ import { type LocaleBaseTuple, type SynthesizedLocaleRow } from "#synthesizers/locale";
30
+ /**
31
+ * One per-country OA source part: either a cached `zip` + `csv` member (streamed out of the archive) or an extracted
32
+ * plain `path` (streamed via `createReadStream`). Both carry the standard OA header
33
+ * (LON,LAT,NUMBER,STREET,UNIT,CITY,DISTRICT,REGION,POSTCODE,ID,HASH). An optional `region` fallback covers countries
34
+ * whose REGION column is empty (DE — the Bundesland is implied by the per-state file).
35
+ */
36
+ export interface LocalePart {
37
+ zip?: PathBuilderLike;
38
+ csv?: string;
39
+ path?: PathBuilderLike;
40
+ region?: string;
41
+ /**
42
+ * NZ — the OA DISTRICT column holds the city (`Auckland`) and CITY holds the suburb (`Birkenhead`). When set, map
43
+ * DISTRICT→locality and CITY→dependent_locality (falling back to CITY→locality when DISTRICT is empty, ~18% of NZ
44
+ * rows). Without this, the default CITY→locality mapping wrongly trains the suburb as the locality.
45
+ */
46
+ districtAsLocality?: boolean;
47
+ /**
48
+ * ES pedanía part only — the header is the RAW (un-conformed) CNIG export schema (`numero`, `tipo_vial`,
49
+ * `nombre_via`, `poblacion`, `municipio`, `comunidad_autonoma`, `cod_postal`), NOT the standard OA
50
+ * NUMBER/STREET/CITY/DISTRICT/REGION/POSTCODE header every other part uses. Verified 2026-07-22 by exact- coordinate
51
+ * cross-check: the OA-conformed `extracted/es/countrywide.csv` collapses CITY to `municipio` and drops `poblacion`
52
+ * (Spain's below-municipio núcleo/pedanía name) entirely, so the pedanía signal survives ONLY in this raw export.
53
+ * `street` is reconstructed as `tipo_vial + " " + nombre_via` (verified byte-identical to the conformed STREET column
54
+ * for the same row). CITY-analog = `poblacion`, DISTRICT-analog = `municipio`.
55
+ */
56
+ cnigRaw?: boolean;
57
+ }
58
+ export interface LocaleCountrySource {
59
+ source: string;
60
+ parts: LocalePart[];
61
+ /**
62
+ * The `corpus_version` stamped on emitted rows. DE/FR keep the historical `0.4.0` (regenerating those slices must
63
+ * stay lineage-identical); ES/IT/NL are the #241 staging lineage (`v0.9.9-es-it-nl`).
64
+ */
65
+ corpusVersion: string;
66
+ /**
67
+ * An ALTERNATE part list, read instead of {@link parts} when the `--district-as-locality` override is explicitly
68
+ * `true` for this invocation (see `run()`). ES-only for now — the standard `parts` entry can't supply real
69
+ * dependent-locality signal (its OA-conformed CSV drops `poblacion`; see {@link LocalePart.cnigRaw}), so the pedanía
70
+ * build reads a wholly different raw source instead of flipping the standard CITY/DISTRICT columns. `undefined` for
71
+ * every other country — the override then just forces `districtAsLocality` on the normal `parts`, as GB/NZ already do
72
+ * per-part.
73
+ */
74
+ pedaniaParts?: LocalePart[];
75
+ }
76
+ /**
77
+ * OA CITY-noise normalization (#241) — the documented cleaning step, derived from the 2026-07-02 FULL-STREAM audit of
78
+ * the ES (15.6M rows), IT (13.9M), and NL (9.1M) sources (not a hand-list). Returns the cleaned city, or `null` to drop
79
+ * the tuple.
80
+ *
81
+ * Cleaned classes:
82
+ *
83
+ * 1. DROP pseudo-localities — the ES cadastral aggregates (`Comunidad de 09076, 09150 y 09578`, `Ledanía de …`; 0.06% of
84
+ * ES rows): any CITY containing a comma or a ≥4-digit run is a land-register aggregate, not a renderable city.
85
+ * Structural, locale-safe — NL's genuine `2e Valthermond` (one digit) survives; IT/NL have zero hits.
86
+ * 2. STRIP a trailing parenthesized 1–3-letter admin code — the NL BAG province disambiguator (`Bergen (NH)`, `Rijswijk
87
+ * (GLD)` → `Bergen`, `Rijswijk`; 0.13% of NL rows). The analogue of the German Kreis/region-suffix class (#241 names
88
+ * `Rabenau Sachs` / `Weißwasser /O.L.`): an admin-region gloss glued onto the locality value that dirties locality
89
+ * labels.
90
+ *
91
+ * Audit-verified NON-noise, deliberately NOT cleaned (a naive suffix rule would mangle real names):
92
+ *
93
+ * - ES/IT city-ends-with-province (`Alhama de Almería`, `GENZANO DI ROMA`; ~0.8% each): genuine toponyms whose linking
94
+ * `de`/`di` makes them full names, unlike the German glued-abbreviation class.
95
+ * - ES bilingual slash names (`Laudio/Llodio`; 2.16%): official co-names — the eval expects them verbatim.
96
+ * - IT ALL-CAPS city casing (98.79% of the source, and the eval's observed form): casing is the #829 case-augmentation
97
+ * change, not this slice's.
98
+ */
99
+ export declare function cleanCityNoise(city: string): string | null;
100
+ /**
101
+ * Stream real tuples out of an OA source part and reservoir-sample to {@link RESERVOIR_CAP}. Reads the CSV row-by-row —
102
+ * `readZipEntry | CSVSpliterator` for zip parts, `createReadStream | CSVSpliterator` for extracted parts (both bounded
103
+ * memory) — and keeps a uniform random sample (Algorithm R) seeded by `rng`, separate from the emit loop's PRNG. NO
104
+ * global dedup (a 25M-key Set would OOM; OA rows are near-unique). The city passes through {@link cleanCityNoise}; the
105
+ * region falls back to `part.region` when the row's REGION cell is empty (DE).
106
+ *
107
+ * Exported for {@link locale.test.ts} — the CSV read path (quote handling, CRLF, region fallback) has no other test.
108
+ */
109
+ export declare function readTuples(part: LocalePart, rng: () => number): Promise<LocaleBaseTuple[]>;
110
+ /**
111
+ * Country-append fraction (the fr-admin-split #728 pattern, generalized to the locale recipe): mutates `synth` in
112
+ * place, `countryFraction` of the time appending an explicit country surface form ("United Kingdom") to `raw` + a
113
+ * `country` component — the model relearns to emit country WHEN the token is present without over-firing it on the
114
+ * (still-majority) country-less rows. `countryFraction <= 0` (the default) short-circuits the `random()` draw away
115
+ * entirely — no `synth` mutation and no RNG consumption — so every existing locale's emit stream stays byte-identical
116
+ * to before this option existed. Exported for {@link locale.test.ts}.
117
+ */
118
+ export declare function applyCountryAppend(synth: SynthesizedLocaleRow, country: string, countryFraction: number, random: () => number): void;
119
+ /**
120
+ * Merge the `--district-as-locality` CLI override onto one part. `undefined` (flag absent) returns `part` unchanged
121
+ * (same object — no allocation, no behavior change); `true`/`false` returns a shallow copy with `districtAsLocality`
122
+ * forced to that value for this invocation only. Exported for {@link locale.test.ts}.
123
+ */
124
+ export declare function applyDistrictAsLocalityOverride(part: LocalePart, override: boolean | undefined): LocalePart;
125
+ /**
126
+ * Pick which part list a `--country` run reads: {@link LocaleCountrySource.pedaniaParts} when the override is explicitly
127
+ * `true` AND the country registers one (ES only, so far), else the default `parts` — unchanged for every other
128
+ * country/override combination. Exported for {@link locale.test.ts}.
129
+ */
130
+ export declare function resolveLocaleParts(countrySource: LocaleCountrySource, override: boolean | undefined): LocalePart[];
131
+ /**
132
+ * Slice recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
133
+ * and `description` below for the surface form it generates.
134
+ */
135
+ export declare const localeRecipe: CorpusRecipe;
136
+ //# sourceMappingURL=locale.d.ts.map