@mailwoman/corpus 9.2.0 → 9.4.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (1261) hide show
  1. package/README.md +22 -22
  2. package/data/PROVENANCE.md +7 -7
  3. package/lib/adapters/ban/adapter.ts +190 -0
  4. package/lib/adapters/ban/street-decompose.ts +66 -0
  5. package/lib/adapters/fcc-bdc/adapter.ts +174 -0
  6. package/lib/adapters/geonames/adapter.ts +199 -0
  7. package/lib/adapters/geonames-postal/adapter.ts +122 -0
  8. package/lib/adapters/gnaf/adapter.ts +149 -0
  9. package/lib/adapters/gnaf/assemble.ts +225 -0
  10. package/lib/adapters/index.ts +153 -0
  11. package/lib/adapters/openaddresses/adapter.ts +251 -0
  12. package/lib/adapters/overture/adapter.ts +162 -0
  13. package/lib/adapters/state-hi-schools/adapter.ts +170 -0
  14. package/lib/adapters/state-hi-schools/workbook.ts +35 -0
  15. package/lib/adapters/synth-po-box/adapter.ts +204 -0
  16. package/lib/adapters/tiger/adapter.ts +252 -0
  17. package/lib/adapters/tiger/street-decompose.ts +83 -0
  18. package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +167 -0
  19. package/lib/adapters/usgov-imls-pls/adapter.ts +143 -0
  20. package/lib/adapters/usgov-irs-bmf/adapter.ts +151 -0
  21. package/lib/adapters/usgov-nad/adapter.ts +334 -0
  22. package/lib/adapters/usgov-nppes/adapter.ts +151 -0
  23. package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +193 -0
  24. package/lib/adapters/utils/index.ts +307 -0
  25. package/lib/adapters/wof-admin-jp/adapter.ts +214 -0
  26. package/lib/adapters/wof-admin-json/adapter.ts +231 -0
  27. package/lib/adapters/wof-json-rows.ts +129 -0
  28. package/lib/adapters/wof-postalcode-json/adapter.ts +176 -0
  29. package/lib/build.ts +378 -0
  30. package/lib/env.ts +50 -0
  31. package/lib/index.ts +13 -0
  32. package/lib/recipes/anchor-absorption.ts +101 -0
  33. package/lib/recipes/bare-country.ts +95 -0
  34. package/lib/recipes/boundary-stress.ts +102 -0
  35. package/lib/recipes/cn-organizational-units.ts +199 -0
  36. package/lib/recipes/country-balanced.ts +510 -0
  37. package/lib/recipes/cz-pcfirst-preposition.ts +112 -0
  38. package/lib/recipes/fr-admin-split.ts +243 -0
  39. package/lib/recipes/fr-bare-street.ts +171 -0
  40. package/lib/recipes/fr-fragment.ts +334 -0
  41. package/lib/recipes/fr-lieudit.ts +301 -0
  42. package/lib/recipes/fr-order.ts +246 -0
  43. package/lib/recipes/german.ts +360 -0
  44. package/lib/recipes/house-venue.ts +93 -0
  45. package/lib/recipes/index.ts +97 -0
  46. package/lib/recipes/intersection.ts +619 -0
  47. package/lib/recipes/locale.ts +600 -0
  48. package/lib/recipes/nl-postcode.ts +117 -0
  49. package/lib/recipes/no-fragment.ts +213 -0
  50. package/lib/recipes/no-street-led.ts +135 -0
  51. package/lib/recipes/no-street.ts +91 -0
  52. package/lib/recipes/po-box-cedex.ts +976 -0
  53. package/lib/recipes/po-box.ts +124 -0
  54. package/lib/recipes/reviewed-postcode-tail.ts +190 -0
  55. package/lib/recipes/scaffold.ts +468 -0
  56. package/lib/recipes/si-bare-village.ts +99 -0
  57. package/lib/recipes/street-affix.ts +805 -0
  58. package/lib/recipes/street-bare.ts +102 -0
  59. package/lib/recipes/street.ts +83 -0
  60. package/lib/recipes/sub-venue-sources.ts +878 -0
  61. package/lib/recipes/sub-venue.ts +998 -0
  62. package/lib/recipes/trailing-region.ts +178 -0
  63. package/lib/recipes/unit.ts +304 -0
  64. package/lib/runner.ts +312 -0
  65. package/lib/synthesizers/anchor-absorption.ts +288 -0
  66. package/lib/synthesizers/boundary-stress.ts +532 -0
  67. package/lib/synthesizers/german.ts +260 -0
  68. package/lib/synthesizers/house-venue.ts +308 -0
  69. package/lib/synthesizers/intersection.ts +233 -0
  70. package/lib/synthesizers/no-street.ts +327 -0
  71. package/lib/synthesizers/po-box.ts +323 -0
  72. package/lib/synthesizers/street.ts +269 -0
  73. package/lib/synthesizers/utils.ts +993 -0
  74. package/lib/test-kit/corpus-recipe.ts +86 -0
  75. package/lib/test-kit/index.ts +100 -0
  76. package/lib/tools/align-slice.ts +68 -0
  77. package/lib/tools/audit.ts +403 -0
  78. package/lib/tools/corpus-stats.ts +136 -0
  79. package/lib/tools/fetch/acra-sg.ts +174 -0
  80. package/lib/tools/fetch/ban.ts +289 -0
  81. package/lib/tools/fetch/download.ts +477 -0
  82. package/lib/tools/fetch/gcis-tw.ts +175 -0
  83. package/lib/tools/fetch/geonames-dump.ts +257 -0
  84. package/lib/tools/fetch/geonames-postal.ts +180 -0
  85. package/lib/tools/fetch/houjin-jp.ts +135 -0
  86. package/lib/tools/fetch/hrsa.ts +59 -0
  87. package/lib/tools/fetch/imls-pls.ts +149 -0
  88. package/lib/tools/fetch/index.ts +174 -0
  89. package/lib/tools/fetch/juso-kr.ts +165 -0
  90. package/lib/tools/fetch/localdata-kr.ts +194 -0
  91. package/lib/tools/fetch/nad.ts +341 -0
  92. package/lib/tools/fetch/nppes.ts +165 -0
  93. package/lib/tools/fetch/openaddresses.ts +347 -0
  94. package/lib/tools/fetch/ourairports.ts +170 -0
  95. package/lib/tools/fetch/ppd.ts +121 -0
  96. package/lib/tools/fetch/state-hi-schools.ts +161 -0
  97. package/lib/tools/fetch/state-sources.ts +146 -0
  98. package/lib/tools/fetch/tiger-full.ts +308 -0
  99. package/lib/tools/fetch/wikidata-subvenue.ts +384 -0
  100. package/lib/tools/golden-expand.ts +574 -0
  101. package/lib/tools/golden-promote.ts +337 -0
  102. package/lib/tools/golden-relabel-street.ts +686 -0
  103. package/lib/tools/index.ts +28 -0
  104. package/lib/tools/ingest-csv.ts +378 -0
  105. package/lib/tools/jsonl-to-parquet.ts +207 -0
  106. package/lib/tools/lint-slice-vocab.ts +388 -0
  107. package/lib/tools/lint-slice.ts +496 -0
  108. package/lib/tools/overlay-manifest.ts +148 -0
  109. package/lib/tools/overture-subvenue.ts +209 -0
  110. package/lib/tools/postcode-triples.ts +363 -0
  111. package/lib/tools/slice-kryptonite.ts +137 -0
  112. package/lib/tools/slice-translit.ts +218 -0
  113. package/lib/tools/sub-venue/harvest.ts +234 -0
  114. package/lib/tools/sub-venue/head-nouns.ts +245 -0
  115. package/lib/tools/sub-venue/surfaces.ts +95 -0
  116. package/lib/tools/sub-venue/table.ts +281 -0
  117. package/lib/tools/sub-venue/wikidata.ts +85 -0
  118. package/lib/tools/sub-venue-lexicon.ts +429 -0
  119. package/lib/tools/sub-venue-promotions.ts +330 -0
  120. package/lib/types.ts +247 -0
  121. package/lib/utils/align.ts +330 -0
  122. package/lib/utils/golden.ts +189 -0
  123. package/lib/utils/index.ts +14 -0
  124. package/lib/utils/parquet.ts +582 -0
  125. package/lib/utils/slice-stats.ts +95 -0
  126. package/lib/utils/split.ts +279 -0
  127. package/lib/utils/tokenize.ts +120 -0
  128. package/lib/utils/wof-json.ts +247 -0
  129. package/out/adapters/ban/adapter.d.ts.map +1 -0
  130. package/out/adapters/ban/adapter.js +149 -0
  131. package/out/adapters/ban/adapter.js.map +1 -0
  132. package/out/adapters/ban/street-decompose.d.ts.map +1 -0
  133. package/out/adapters/ban/street-decompose.js +51 -0
  134. package/out/adapters/ban/street-decompose.js.map +1 -0
  135. package/out/adapters/fcc-bdc/adapter.d.ts.map +1 -0
  136. package/out/adapters/fcc-bdc/adapter.js +144 -0
  137. package/out/adapters/fcc-bdc/adapter.js.map +1 -0
  138. package/out/adapters/geonames/adapter.d.ts.map +1 -0
  139. package/out/adapters/geonames/adapter.js +176 -0
  140. package/out/adapters/geonames/adapter.js.map +1 -0
  141. package/out/adapters/geonames-postal/adapter.d.ts +54 -0
  142. package/out/adapters/geonames-postal/adapter.d.ts.map +1 -0
  143. package/out/adapters/geonames-postal/adapter.js +107 -0
  144. package/out/adapters/geonames-postal/adapter.js.map +1 -0
  145. package/out/adapters/gnaf/adapter.d.ts +49 -0
  146. package/out/adapters/gnaf/adapter.d.ts.map +1 -0
  147. package/out/adapters/gnaf/adapter.js +124 -0
  148. package/out/adapters/gnaf/adapter.js.map +1 -0
  149. package/out/adapters/gnaf/assemble.d.ts +65 -0
  150. package/out/adapters/gnaf/assemble.d.ts.map +1 -0
  151. package/out/adapters/gnaf/assemble.js +154 -0
  152. package/out/adapters/gnaf/assemble.js.map +1 -0
  153. package/out/adapters/index.d.ts +51 -0
  154. package/out/adapters/index.d.ts.map +1 -0
  155. package/out/adapters/index.js +95 -0
  156. package/out/adapters/index.js.map +1 -0
  157. package/out/adapters/openaddresses/adapter.d.ts.map +1 -0
  158. package/out/adapters/openaddresses/adapter.js +186 -0
  159. package/out/adapters/openaddresses/adapter.js.map +1 -0
  160. package/out/adapters/overture/adapter.d.ts +48 -0
  161. package/out/adapters/overture/adapter.d.ts.map +1 -0
  162. package/out/adapters/overture/adapter.js +125 -0
  163. package/out/adapters/overture/adapter.js.map +1 -0
  164. package/out/adapters/state-hi-schools/adapter.d.ts +46 -0
  165. package/out/adapters/state-hi-schools/adapter.d.ts.map +1 -0
  166. package/out/adapters/state-hi-schools/adapter.js +145 -0
  167. package/out/adapters/state-hi-schools/adapter.js.map +1 -0
  168. package/out/adapters/state-hi-schools/workbook.d.ts +29 -0
  169. package/out/adapters/state-hi-schools/workbook.d.ts.map +1 -0
  170. package/out/adapters/state-hi-schools/workbook.js +20 -0
  171. package/out/adapters/state-hi-schools/workbook.js.map +1 -0
  172. package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
  173. package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
  174. package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
  175. package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
  176. package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
  177. package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
  178. package/out/adapters/synth-po-box/adapter.d.ts.map +1 -0
  179. package/out/adapters/synth-po-box/adapter.js +140 -0
  180. package/out/adapters/synth-po-box/adapter.js.map +1 -0
  181. package/out/adapters/tiger/adapter.d.ts +55 -0
  182. package/out/adapters/tiger/adapter.d.ts.map +1 -0
  183. package/out/adapters/tiger/adapter.js +201 -0
  184. package/out/adapters/tiger/adapter.js.map +1 -0
  185. package/out/adapters/tiger/street-decompose.d.ts.map +1 -0
  186. package/out/adapters/tiger/street-decompose.js +68 -0
  187. package/out/adapters/tiger/street-decompose.js.map +1 -0
  188. package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +56 -0
  189. package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -0
  190. package/out/adapters/usgov-hrsa-fqhc/adapter.js +132 -0
  191. package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -0
  192. package/out/adapters/usgov-imls-pls/adapter.d.ts +36 -0
  193. package/out/adapters/usgov-imls-pls/adapter.d.ts.map +1 -0
  194. package/out/adapters/usgov-imls-pls/adapter.js +114 -0
  195. package/out/adapters/usgov-imls-pls/adapter.js.map +1 -0
  196. package/out/adapters/usgov-irs-bmf/adapter.d.ts +37 -0
  197. package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -0
  198. package/out/adapters/usgov-irs-bmf/adapter.js +120 -0
  199. package/out/adapters/usgov-irs-bmf/adapter.js.map +1 -0
  200. package/out/adapters/usgov-nad/adapter.d.ts +48 -0
  201. package/out/adapters/usgov-nad/adapter.d.ts.map +1 -0
  202. package/out/adapters/usgov-nad/adapter.js +249 -0
  203. package/out/adapters/usgov-nad/adapter.js.map +1 -0
  204. package/out/adapters/usgov-nppes/adapter.d.ts.map +1 -0
  205. package/out/adapters/usgov-nppes/adapter.js +118 -0
  206. package/out/adapters/usgov-nppes/adapter.js.map +1 -0
  207. package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -0
  208. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +154 -0
  209. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -0
  210. package/out/adapters/utils/index.d.ts +191 -0
  211. package/out/adapters/utils/index.d.ts.map +1 -0
  212. package/out/adapters/utils/index.js +206 -0
  213. package/out/adapters/utils/index.js.map +1 -0
  214. package/out/adapters/wof-admin-jp/adapter.d.ts.map +1 -0
  215. package/out/adapters/wof-admin-jp/adapter.js +161 -0
  216. package/out/adapters/wof-admin-jp/adapter.js.map +1 -0
  217. package/out/adapters/wof-admin-json/adapter.d.ts +79 -0
  218. package/out/adapters/wof-admin-json/adapter.d.ts.map +1 -0
  219. package/out/adapters/wof-admin-json/adapter.js +197 -0
  220. package/out/adapters/wof-admin-json/adapter.js.map +1 -0
  221. package/out/adapters/wof-json-rows.d.ts +62 -0
  222. package/out/adapters/wof-json-rows.d.ts.map +1 -0
  223. package/out/adapters/wof-json-rows.js +83 -0
  224. package/out/adapters/wof-json-rows.js.map +1 -0
  225. package/out/adapters/wof-postalcode-json/adapter.d.ts +65 -0
  226. package/out/adapters/wof-postalcode-json/adapter.d.ts.map +1 -0
  227. package/out/adapters/wof-postalcode-json/adapter.js +151 -0
  228. package/out/adapters/wof-postalcode-json/adapter.js.map +1 -0
  229. package/out/build.d.ts +132 -0
  230. package/out/build.d.ts.map +1 -0
  231. package/out/build.js +245 -0
  232. package/out/build.js.map +1 -0
  233. package/out/codex/us-fips-state.d.ts.map +1 -0
  234. package/out/codex/us-fips-state.js.map +1 -0
  235. package/out/env.d.ts +46 -0
  236. package/out/env.d.ts.map +1 -0
  237. package/out/env.js +46 -0
  238. package/out/env.js.map +1 -0
  239. package/out/index.d.ts +13 -0
  240. package/out/index.d.ts.map +1 -0
  241. package/out/index.js +13 -0
  242. package/out/index.js.map +1 -0
  243. package/out/recipes/anchor-absorption.d.ts +20 -0
  244. package/out/recipes/anchor-absorption.d.ts.map +1 -0
  245. package/out/recipes/anchor-absorption.js +82 -0
  246. package/out/recipes/anchor-absorption.js.map +1 -0
  247. package/out/recipes/bare-country.d.ts +25 -0
  248. package/out/recipes/bare-country.d.ts.map +1 -0
  249. package/out/recipes/bare-country.js +88 -0
  250. package/out/recipes/bare-country.js.map +1 -0
  251. package/out/recipes/boundary-stress.d.ts +20 -0
  252. package/out/recipes/boundary-stress.d.ts.map +1 -0
  253. package/out/recipes/boundary-stress.js +84 -0
  254. package/out/recipes/boundary-stress.js.map +1 -0
  255. package/out/recipes/cn-organizational-units.d.ts +36 -0
  256. package/out/recipes/cn-organizational-units.d.ts.map +1 -0
  257. package/out/recipes/cn-organizational-units.js +159 -0
  258. package/out/recipes/cn-organizational-units.js.map +1 -0
  259. package/out/recipes/country-balanced.d.ts +32 -0
  260. package/out/recipes/country-balanced.d.ts.map +1 -0
  261. package/out/recipes/country-balanced.js +394 -0
  262. package/out/recipes/country-balanced.js.map +1 -0
  263. package/out/recipes/cz-pcfirst-preposition.d.ts +22 -0
  264. package/out/recipes/cz-pcfirst-preposition.d.ts.map +1 -0
  265. package/out/recipes/cz-pcfirst-preposition.js +101 -0
  266. package/out/recipes/cz-pcfirst-preposition.js.map +1 -0
  267. package/out/recipes/fr-admin-split.d.ts +38 -0
  268. package/out/recipes/fr-admin-split.d.ts.map +1 -0
  269. package/out/recipes/fr-admin-split.js +192 -0
  270. package/out/recipes/fr-admin-split.js.map +1 -0
  271. package/out/recipes/fr-bare-street.d.ts +28 -0
  272. package/out/recipes/fr-bare-street.d.ts.map +1 -0
  273. package/out/recipes/fr-bare-street.js +144 -0
  274. package/out/recipes/fr-bare-street.js.map +1 -0
  275. package/out/recipes/fr-fragment.d.ts +77 -0
  276. package/out/recipes/fr-fragment.d.ts.map +1 -0
  277. package/out/recipes/fr-fragment.js +277 -0
  278. package/out/recipes/fr-fragment.js.map +1 -0
  279. package/out/recipes/fr-lieudit.d.ts +32 -0
  280. package/out/recipes/fr-lieudit.d.ts.map +1 -0
  281. package/out/recipes/fr-lieudit.js +227 -0
  282. package/out/recipes/fr-lieudit.js.map +1 -0
  283. package/out/recipes/fr-order.d.ts +38 -0
  284. package/out/recipes/fr-order.d.ts.map +1 -0
  285. package/out/recipes/fr-order.js +198 -0
  286. package/out/recipes/fr-order.js.map +1 -0
  287. package/out/recipes/german.d.ts +44 -0
  288. package/out/recipes/german.d.ts.map +1 -0
  289. package/out/recipes/german.js +289 -0
  290. package/out/recipes/german.js.map +1 -0
  291. package/out/recipes/house-venue.d.ts +18 -0
  292. package/out/recipes/house-venue.d.ts.map +1 -0
  293. package/out/recipes/house-venue.js +74 -0
  294. package/out/recipes/house-venue.js.map +1 -0
  295. package/out/recipes/index.d.ts +24 -0
  296. package/out/recipes/index.d.ts.map +1 -0
  297. package/out/recipes/index.js +91 -0
  298. package/out/recipes/index.js.map +1 -0
  299. package/out/recipes/intersection.d.ts +42 -0
  300. package/out/recipes/intersection.d.ts.map +1 -0
  301. package/out/recipes/intersection.js +453 -0
  302. package/out/recipes/intersection.js.map +1 -0
  303. package/out/recipes/locale.d.ts +136 -0
  304. package/out/recipes/locale.d.ts.map +1 -0
  305. package/out/recipes/locale.js +460 -0
  306. package/out/recipes/locale.js.map +1 -0
  307. package/out/recipes/nl-postcode.d.ts +26 -0
  308. package/out/recipes/nl-postcode.d.ts.map +1 -0
  309. package/out/recipes/nl-postcode.js +103 -0
  310. package/out/recipes/nl-postcode.js.map +1 -0
  311. package/out/recipes/no-fragment.d.ts +43 -0
  312. package/out/recipes/no-fragment.d.ts.map +1 -0
  313. package/out/recipes/no-fragment.js +183 -0
  314. package/out/recipes/no-fragment.js.map +1 -0
  315. package/out/recipes/no-street-led.d.ts +24 -0
  316. package/out/recipes/no-street-led.d.ts.map +1 -0
  317. package/out/recipes/no-street-led.js +114 -0
  318. package/out/recipes/no-street-led.js.map +1 -0
  319. package/out/recipes/no-street.d.ts +18 -0
  320. package/out/recipes/no-street.d.ts.map +1 -0
  321. package/out/recipes/no-street.js +72 -0
  322. package/out/recipes/no-street.js.map +1 -0
  323. package/out/recipes/po-box-cedex.d.ts +38 -0
  324. package/out/recipes/po-box-cedex.d.ts.map +1 -0
  325. package/out/recipes/po-box-cedex.js +768 -0
  326. package/out/recipes/po-box-cedex.js.map +1 -0
  327. package/out/recipes/po-box.d.ts +17 -0
  328. package/out/recipes/po-box.d.ts.map +1 -0
  329. package/out/recipes/po-box.js +101 -0
  330. package/out/recipes/po-box.js.map +1 -0
  331. package/out/recipes/reviewed-postcode-tail.d.ts +47 -0
  332. package/out/recipes/reviewed-postcode-tail.d.ts.map +1 -0
  333. package/out/recipes/reviewed-postcode-tail.js +125 -0
  334. package/out/recipes/reviewed-postcode-tail.js.map +1 -0
  335. package/out/recipes/scaffold.d.ts +323 -0
  336. package/out/recipes/scaffold.d.ts.map +1 -0
  337. package/out/recipes/scaffold.js +174 -0
  338. package/out/recipes/scaffold.js.map +1 -0
  339. package/out/recipes/si-bare-village.d.ts +32 -0
  340. package/out/recipes/si-bare-village.d.ts.map +1 -0
  341. package/out/recipes/si-bare-village.js +89 -0
  342. package/out/recipes/si-bare-village.js.map +1 -0
  343. package/out/recipes/street-affix.d.ts +89 -0
  344. package/out/recipes/street-affix.d.ts.map +1 -0
  345. package/out/recipes/street-affix.js +563 -0
  346. package/out/recipes/street-affix.js.map +1 -0
  347. package/out/recipes/street-bare.d.ts +25 -0
  348. package/out/recipes/street-bare.d.ts.map +1 -0
  349. package/out/recipes/street-bare.js +87 -0
  350. package/out/recipes/street-bare.js.map +1 -0
  351. package/out/recipes/street.d.ts +15 -0
  352. package/out/recipes/street.d.ts.map +1 -0
  353. package/out/recipes/street.js +70 -0
  354. package/out/recipes/street.js.map +1 -0
  355. package/out/recipes/sub-venue-sources.d.ts +229 -0
  356. package/out/recipes/sub-venue-sources.d.ts.map +1 -0
  357. package/out/recipes/sub-venue-sources.js +654 -0
  358. package/out/recipes/sub-venue-sources.js.map +1 -0
  359. package/out/recipes/sub-venue.d.ts +269 -0
  360. package/out/recipes/sub-venue.d.ts.map +1 -0
  361. package/out/recipes/sub-venue.js +726 -0
  362. package/out/recipes/sub-venue.js.map +1 -0
  363. package/out/recipes/trailing-region.d.ts +74 -0
  364. package/out/recipes/trailing-region.d.ts.map +1 -0
  365. package/out/recipes/trailing-region.js +158 -0
  366. package/out/recipes/trailing-region.js.map +1 -0
  367. package/out/recipes/unit.d.ts +29 -0
  368. package/out/recipes/unit.d.ts.map +1 -0
  369. package/out/recipes/unit.js +231 -0
  370. package/out/recipes/unit.js.map +1 -0
  371. package/out/runner.d.ts +130 -0
  372. package/out/runner.d.ts.map +1 -0
  373. package/out/runner.js +185 -0
  374. package/out/runner.js.map +1 -0
  375. package/out/synthesizers/anchor-absorption.d.ts +63 -0
  376. package/out/synthesizers/anchor-absorption.d.ts.map +1 -0
  377. package/out/synthesizers/anchor-absorption.js +221 -0
  378. package/out/synthesizers/anchor-absorption.js.map +1 -0
  379. package/out/synthesizers/boundary-stress.d.ts +78 -0
  380. package/out/synthesizers/boundary-stress.d.ts.map +1 -0
  381. package/out/synthesizers/boundary-stress.js +455 -0
  382. package/out/synthesizers/boundary-stress.js.map +1 -0
  383. package/out/synthesizers/german.d.ts +115 -0
  384. package/out/synthesizers/german.d.ts.map +1 -0
  385. package/out/synthesizers/german.js +149 -0
  386. package/out/synthesizers/german.js.map +1 -0
  387. package/out/synthesizers/house-venue.d.ts +56 -0
  388. package/out/synthesizers/house-venue.d.ts.map +1 -0
  389. package/out/synthesizers/house-venue.js +247 -0
  390. package/out/synthesizers/house-venue.js.map +1 -0
  391. package/out/synthesizers/intersection.d.ts +52 -0
  392. package/out/synthesizers/intersection.d.ts.map +1 -0
  393. package/out/synthesizers/intersection.js +175 -0
  394. package/out/synthesizers/intersection.js.map +1 -0
  395. package/out/synthesizers/no-street.d.ts +72 -0
  396. package/out/synthesizers/no-street.d.ts.map +1 -0
  397. package/out/synthesizers/no-street.js +262 -0
  398. package/out/synthesizers/no-street.js.map +1 -0
  399. package/out/synthesizers/po-box.d.ts +108 -0
  400. package/out/synthesizers/po-box.d.ts.map +1 -0
  401. package/out/synthesizers/po-box.js +250 -0
  402. package/out/synthesizers/po-box.js.map +1 -0
  403. package/out/synthesizers/street.d.ts +54 -0
  404. package/out/synthesizers/street.d.ts.map +1 -0
  405. package/out/synthesizers/street.js +218 -0
  406. package/out/synthesizers/street.js.map +1 -0
  407. package/out/synthesizers/utils.d.ts +241 -0
  408. package/out/synthesizers/utils.d.ts.map +1 -0
  409. package/out/synthesizers/utils.js +776 -0
  410. package/out/synthesizers/utils.js.map +1 -0
  411. package/out/test-kit/corpus-recipe.d.ts +59 -0
  412. package/out/test-kit/corpus-recipe.d.ts.map +1 -0
  413. package/out/test-kit/corpus-recipe.js +39 -0
  414. package/out/test-kit/corpus-recipe.js.map +1 -0
  415. package/out/test-kit/index.d.ts +48 -0
  416. package/out/test-kit/index.d.ts.map +1 -0
  417. package/out/test-kit/index.js +78 -0
  418. package/out/test-kit/index.js.map +1 -0
  419. package/out/tools/align-slice.d.ts +7 -0
  420. package/out/tools/align-slice.d.ts.map +1 -0
  421. package/out/tools/align-slice.js +55 -0
  422. package/out/tools/align-slice.js.map +1 -0
  423. package/out/tools/audit.d.ts +29 -0
  424. package/out/tools/audit.d.ts.map +1 -0
  425. package/out/tools/audit.js +282 -0
  426. package/out/tools/audit.js.map +1 -0
  427. package/out/tools/corpus-stats.d.ts +44 -0
  428. package/out/tools/corpus-stats.d.ts.map +1 -0
  429. package/out/tools/corpus-stats.js +102 -0
  430. package/out/tools/corpus-stats.js.map +1 -0
  431. package/out/tools/fetch/acra-sg.d.ts +23 -0
  432. package/out/tools/fetch/acra-sg.d.ts.map +1 -0
  433. package/out/tools/fetch/acra-sg.js +126 -0
  434. package/out/tools/fetch/acra-sg.js.map +1 -0
  435. package/out/tools/fetch/ban.d.ts +31 -0
  436. package/out/tools/fetch/ban.d.ts.map +1 -0
  437. package/out/tools/fetch/ban.js +239 -0
  438. package/out/tools/fetch/ban.js.map +1 -0
  439. package/out/tools/fetch/download.d.ts +182 -0
  440. package/out/tools/fetch/download.d.ts.map +1 -0
  441. package/out/tools/fetch/download.js +318 -0
  442. package/out/tools/fetch/download.js.map +1 -0
  443. package/out/tools/fetch/gcis-tw.d.ts +23 -0
  444. package/out/tools/fetch/gcis-tw.d.ts.map +1 -0
  445. package/out/tools/fetch/gcis-tw.js +135 -0
  446. package/out/tools/fetch/gcis-tw.js.map +1 -0
  447. package/out/tools/fetch/geonames-dump.d.ts +91 -0
  448. package/out/tools/fetch/geonames-dump.d.ts.map +1 -0
  449. package/out/tools/fetch/geonames-dump.js +171 -0
  450. package/out/tools/fetch/geonames-dump.js.map +1 -0
  451. package/out/tools/fetch/geonames-postal.d.ts +76 -0
  452. package/out/tools/fetch/geonames-postal.d.ts.map +1 -0
  453. package/out/tools/fetch/geonames-postal.js +126 -0
  454. package/out/tools/fetch/geonames-postal.js.map +1 -0
  455. package/out/tools/fetch/houjin-jp.d.ts +24 -0
  456. package/out/tools/fetch/houjin-jp.d.ts.map +1 -0
  457. package/out/tools/fetch/houjin-jp.js +102 -0
  458. package/out/tools/fetch/houjin-jp.js.map +1 -0
  459. package/out/tools/fetch/hrsa.d.ts +18 -0
  460. package/out/tools/fetch/hrsa.d.ts.map +1 -0
  461. package/out/tools/fetch/hrsa.js +46 -0
  462. package/out/tools/fetch/hrsa.js.map +1 -0
  463. package/out/tools/fetch/imls-pls.d.ts +25 -0
  464. package/out/tools/fetch/imls-pls.d.ts.map +1 -0
  465. package/out/tools/fetch/imls-pls.js +108 -0
  466. package/out/tools/fetch/imls-pls.js.map +1 -0
  467. package/out/tools/fetch/index.d.ts +171 -0
  468. package/out/tools/fetch/index.d.ts.map +1 -0
  469. package/out/tools/fetch/index.js +170 -0
  470. package/out/tools/fetch/index.js.map +1 -0
  471. package/out/tools/fetch/juso-kr.d.ts +30 -0
  472. package/out/tools/fetch/juso-kr.d.ts.map +1 -0
  473. package/out/tools/fetch/juso-kr.js +120 -0
  474. package/out/tools/fetch/juso-kr.js.map +1 -0
  475. package/out/tools/fetch/localdata-kr.d.ts +30 -0
  476. package/out/tools/fetch/localdata-kr.d.ts.map +1 -0
  477. package/out/tools/fetch/localdata-kr.js +139 -0
  478. package/out/tools/fetch/localdata-kr.js.map +1 -0
  479. package/out/tools/fetch/nad.d.ts +70 -0
  480. package/out/tools/fetch/nad.d.ts.map +1 -0
  481. package/out/tools/fetch/nad.js +234 -0
  482. package/out/tools/fetch/nad.js.map +1 -0
  483. package/out/tools/fetch/nppes.d.ts +26 -0
  484. package/out/tools/fetch/nppes.d.ts.map +1 -0
  485. package/out/tools/fetch/nppes.js +126 -0
  486. package/out/tools/fetch/nppes.js.map +1 -0
  487. package/out/tools/fetch/openaddresses.d.ts +9 -0
  488. package/out/tools/fetch/openaddresses.d.ts.map +1 -0
  489. package/out/tools/fetch/openaddresses.js +279 -0
  490. package/out/tools/fetch/openaddresses.js.map +1 -0
  491. package/out/tools/fetch/ourairports.d.ts +45 -0
  492. package/out/tools/fetch/ourairports.d.ts.map +1 -0
  493. package/out/tools/fetch/ourairports.js +128 -0
  494. package/out/tools/fetch/ourairports.js.map +1 -0
  495. package/out/tools/fetch/ppd.d.ts.map +1 -0
  496. package/out/tools/fetch/ppd.js +85 -0
  497. package/out/tools/fetch/ppd.js.map +1 -0
  498. package/out/tools/fetch/state-hi-schools.d.ts +26 -0
  499. package/out/tools/fetch/state-hi-schools.d.ts.map +1 -0
  500. package/out/tools/fetch/state-hi-schools.js +112 -0
  501. package/out/tools/fetch/state-hi-schools.js.map +1 -0
  502. package/out/tools/fetch/state-sources.d.ts +26 -0
  503. package/out/tools/fetch/state-sources.d.ts.map +1 -0
  504. package/out/tools/fetch/state-sources.js +111 -0
  505. package/out/tools/fetch/state-sources.js.map +1 -0
  506. package/out/tools/fetch/tiger-full.d.ts +22 -0
  507. package/out/tools/fetch/tiger-full.d.ts.map +1 -0
  508. package/out/tools/fetch/tiger-full.js +217 -0
  509. package/out/tools/fetch/tiger-full.js.map +1 -0
  510. package/out/tools/fetch/wikidata-subvenue.d.ts +171 -0
  511. package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -0
  512. package/out/tools/fetch/wikidata-subvenue.js +274 -0
  513. package/out/tools/fetch/wikidata-subvenue.js.map +1 -0
  514. package/out/tools/gb-title-case.d.ts.map +1 -0
  515. package/out/tools/gb-title-case.js.map +1 -0
  516. package/out/tools/golden-expand.d.ts +90 -0
  517. package/out/tools/golden-expand.d.ts.map +1 -0
  518. package/out/tools/golden-expand.js +406 -0
  519. package/out/tools/golden-expand.js.map +1 -0
  520. package/out/tools/golden-promote.d.ts.map +1 -0
  521. package/out/tools/golden-promote.js +240 -0
  522. package/out/tools/golden-promote.js.map +1 -0
  523. package/out/tools/golden-relabel-street.d.ts +196 -0
  524. package/out/tools/golden-relabel-street.d.ts.map +1 -0
  525. package/out/tools/golden-relabel-street.js +439 -0
  526. package/out/tools/golden-relabel-street.js.map +1 -0
  527. package/out/tools/index.d.ts +28 -0
  528. package/out/tools/index.d.ts.map +1 -0
  529. package/out/tools/index.js +28 -0
  530. package/out/tools/index.js.map +1 -0
  531. package/out/tools/ingest-csv.d.ts.map +1 -0
  532. package/out/tools/ingest-csv.js +265 -0
  533. package/out/tools/ingest-csv.js.map +1 -0
  534. package/out/tools/jsonl-to-parquet.d.ts +61 -0
  535. package/out/tools/jsonl-to-parquet.d.ts.map +1 -0
  536. package/out/tools/jsonl-to-parquet.js +150 -0
  537. package/out/tools/jsonl-to-parquet.js.map +1 -0
  538. package/out/tools/lint-slice-vocab.d.ts +90 -0
  539. package/out/tools/lint-slice-vocab.d.ts.map +1 -0
  540. package/out/tools/lint-slice-vocab.js +267 -0
  541. package/out/tools/lint-slice-vocab.js.map +1 -0
  542. package/out/tools/lint-slice.d.ts +93 -0
  543. package/out/tools/lint-slice.d.ts.map +1 -0
  544. package/out/tools/lint-slice.js +322 -0
  545. package/out/tools/lint-slice.js.map +1 -0
  546. package/out/tools/overlay-manifest.d.ts +39 -0
  547. package/out/tools/overlay-manifest.d.ts.map +1 -0
  548. package/out/tools/overlay-manifest.js +90 -0
  549. package/out/tools/overlay-manifest.js.map +1 -0
  550. package/out/tools/overture-subvenue.d.ts +112 -0
  551. package/out/tools/overture-subvenue.d.ts.map +1 -0
  552. package/out/tools/overture-subvenue.js +139 -0
  553. package/out/tools/overture-subvenue.js.map +1 -0
  554. package/out/tools/postcode-triples.d.ts +174 -0
  555. package/out/tools/postcode-triples.d.ts.map +1 -0
  556. package/out/tools/postcode-triples.js +292 -0
  557. package/out/tools/postcode-triples.js.map +1 -0
  558. package/out/tools/slice-kryptonite.d.ts +32 -0
  559. package/out/tools/slice-kryptonite.d.ts.map +1 -0
  560. package/out/tools/slice-kryptonite.js +99 -0
  561. package/out/tools/slice-kryptonite.js.map +1 -0
  562. package/out/tools/slice-translit.d.ts +51 -0
  563. package/out/tools/slice-translit.d.ts.map +1 -0
  564. package/out/tools/slice-translit.js +166 -0
  565. package/out/tools/slice-translit.js.map +1 -0
  566. package/out/tools/sub-venue/harvest.d.ts +100 -0
  567. package/out/tools/sub-venue/harvest.d.ts.map +1 -0
  568. package/out/tools/sub-venue/harvest.js +168 -0
  569. package/out/tools/sub-venue/harvest.js.map +1 -0
  570. package/out/tools/sub-venue/head-nouns.d.ts +50 -0
  571. package/out/tools/sub-venue/head-nouns.d.ts.map +1 -0
  572. package/out/tools/sub-venue/head-nouns.js +213 -0
  573. package/out/tools/sub-venue/head-nouns.js.map +1 -0
  574. package/out/tools/sub-venue/surfaces.d.ts +45 -0
  575. package/out/tools/sub-venue/surfaces.d.ts.map +1 -0
  576. package/out/tools/sub-venue/surfaces.js +77 -0
  577. package/out/tools/sub-venue/surfaces.js.map +1 -0
  578. package/out/tools/sub-venue/table.d.ts +229 -0
  579. package/out/tools/sub-venue/table.d.ts.map +1 -0
  580. package/out/tools/sub-venue/table.js +108 -0
  581. package/out/tools/sub-venue/table.js.map +1 -0
  582. package/out/tools/sub-venue/wikidata.d.ts +26 -0
  583. package/out/tools/sub-venue/wikidata.d.ts.map +1 -0
  584. package/out/tools/sub-venue/wikidata.js +62 -0
  585. package/out/tools/sub-venue/wikidata.js.map +1 -0
  586. package/out/tools/sub-venue-lexicon.d.ts +156 -0
  587. package/out/tools/sub-venue-lexicon.d.ts.map +1 -0
  588. package/out/tools/sub-venue-lexicon.js +283 -0
  589. package/out/tools/sub-venue-lexicon.js.map +1 -0
  590. package/out/tools/sub-venue-promotions.d.ts +94 -0
  591. package/out/tools/sub-venue-promotions.d.ts.map +1 -0
  592. package/out/tools/sub-venue-promotions.js +266 -0
  593. package/out/tools/sub-venue-promotions.js.map +1 -0
  594. package/out/types.d.ts +221 -0
  595. package/out/types.d.ts.map +1 -0
  596. package/out/types.js.map +1 -0
  597. package/out/utils/align.d.ts +93 -0
  598. package/out/utils/align.d.ts.map +1 -0
  599. package/out/utils/align.js +234 -0
  600. package/out/utils/align.js.map +1 -0
  601. package/out/utils/golden.d.ts +85 -0
  602. package/out/utils/golden.d.ts.map +1 -0
  603. package/out/utils/golden.js +127 -0
  604. package/out/utils/golden.js.map +1 -0
  605. package/out/utils/index.d.ts +14 -0
  606. package/out/utils/index.d.ts.map +1 -0
  607. package/out/utils/index.js +14 -0
  608. package/out/utils/index.js.map +1 -0
  609. package/out/utils/license.d.ts.map +1 -0
  610. package/out/utils/license.js.map +1 -0
  611. package/out/utils/parquet.d.ts +178 -0
  612. package/out/utils/parquet.d.ts.map +1 -0
  613. package/out/utils/parquet.js +371 -0
  614. package/out/utils/parquet.js.map +1 -0
  615. package/out/utils/slice-stats.d.ts +52 -0
  616. package/out/utils/slice-stats.d.ts.map +1 -0
  617. package/out/utils/slice-stats.js +58 -0
  618. package/out/utils/slice-stats.js.map +1 -0
  619. package/out/utils/split.d.ts +128 -0
  620. package/out/utils/split.d.ts.map +1 -0
  621. package/out/utils/split.js +204 -0
  622. package/out/utils/split.js.map +1 -0
  623. package/out/utils/tokenize.d.ts +64 -0
  624. package/out/utils/tokenize.d.ts.map +1 -0
  625. package/out/utils/tokenize.js +82 -0
  626. package/out/utils/tokenize.js.map +1 -0
  627. package/out/utils/wof-json.d.ts +113 -0
  628. package/out/utils/wof-json.d.ts.map +1 -0
  629. package/out/utils/wof-json.js +173 -0
  630. package/out/utils/wof-json.js.map +1 -0
  631. package/package.json +259 -194
  632. package/out/src/adapters/ban/adapter.d.ts.map +0 -1
  633. package/out/src/adapters/ban/adapter.js +0 -149
  634. package/out/src/adapters/ban/adapter.js.map +0 -1
  635. package/out/src/adapters/ban/street-decompose.d.ts.map +0 -1
  636. package/out/src/adapters/ban/street-decompose.js +0 -75
  637. package/out/src/adapters/ban/street-decompose.js.map +0 -1
  638. package/out/src/adapters/fcc-bdc/adapter.d.ts.map +0 -1
  639. package/out/src/adapters/fcc-bdc/adapter.js +0 -144
  640. package/out/src/adapters/fcc-bdc/adapter.js.map +0 -1
  641. package/out/src/adapters/geonames/adapter.d.ts.map +0 -1
  642. package/out/src/adapters/geonames/adapter.js +0 -176
  643. package/out/src/adapters/geonames/adapter.js.map +0 -1
  644. package/out/src/adapters/geonames-postal/adapter.d.ts +0 -41
  645. package/out/src/adapters/geonames-postal/adapter.d.ts.map +0 -1
  646. package/out/src/adapters/geonames-postal/adapter.js +0 -104
  647. package/out/src/adapters/geonames-postal/adapter.js.map +0 -1
  648. package/out/src/adapters/gnaf/adapter.d.ts +0 -49
  649. package/out/src/adapters/gnaf/adapter.d.ts.map +0 -1
  650. package/out/src/adapters/gnaf/adapter.js +0 -124
  651. package/out/src/adapters/gnaf/adapter.js.map +0 -1
  652. package/out/src/adapters/gnaf/assemble.d.ts +0 -65
  653. package/out/src/adapters/gnaf/assemble.d.ts.map +0 -1
  654. package/out/src/adapters/gnaf/assemble.js +0 -154
  655. package/out/src/adapters/gnaf/assemble.js.map +0 -1
  656. package/out/src/adapters/index.d.ts +0 -51
  657. package/out/src/adapters/index.d.ts.map +0 -1
  658. package/out/src/adapters/index.js +0 -95
  659. package/out/src/adapters/index.js.map +0 -1
  660. package/out/src/adapters/openaddresses/adapter.d.ts.map +0 -1
  661. package/out/src/adapters/openaddresses/adapter.js +0 -186
  662. package/out/src/adapters/openaddresses/adapter.js.map +0 -1
  663. package/out/src/adapters/overture/adapter.d.ts +0 -48
  664. package/out/src/adapters/overture/adapter.d.ts.map +0 -1
  665. package/out/src/adapters/overture/adapter.js +0 -125
  666. package/out/src/adapters/overture/adapter.js.map +0 -1
  667. package/out/src/adapters/state-hi-schools/adapter.d.ts +0 -47
  668. package/out/src/adapters/state-hi-schools/adapter.d.ts.map +0 -1
  669. package/out/src/adapters/state-hi-schools/adapter.js +0 -133
  670. package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
  671. package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
  672. package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
  673. package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
  674. package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
  675. package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
  676. package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
  677. package/out/src/adapters/synth-po-box/adapter.d.ts.map +0 -1
  678. package/out/src/adapters/synth-po-box/adapter.js +0 -140
  679. package/out/src/adapters/synth-po-box/adapter.js.map +0 -1
  680. package/out/src/adapters/tiger/adapter.d.ts +0 -55
  681. package/out/src/adapters/tiger/adapter.d.ts.map +0 -1
  682. package/out/src/adapters/tiger/adapter.js +0 -201
  683. package/out/src/adapters/tiger/adapter.js.map +0 -1
  684. package/out/src/adapters/tiger/street-decompose.d.ts.map +0 -1
  685. package/out/src/adapters/tiger/street-decompose.js +0 -90
  686. package/out/src/adapters/tiger/street-decompose.js.map +0 -1
  687. package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -47
  688. package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
  689. package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +0 -139
  690. package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
  691. package/out/src/adapters/usgov-imls-pls/adapter.d.ts +0 -36
  692. package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
  693. package/out/src/adapters/usgov-imls-pls/adapter.js +0 -114
  694. package/out/src/adapters/usgov-imls-pls/adapter.js.map +0 -1
  695. package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
  696. package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
  697. package/out/src/adapters/usgov-irs-bmf/adapter.js +0 -124
  698. package/out/src/adapters/usgov-irs-bmf/adapter.js.map +0 -1
  699. package/out/src/adapters/usgov-nad/adapter.d.ts +0 -48
  700. package/out/src/adapters/usgov-nad/adapter.d.ts.map +0 -1
  701. package/out/src/adapters/usgov-nad/adapter.js +0 -252
  702. package/out/src/adapters/usgov-nad/adapter.js.map +0 -1
  703. package/out/src/adapters/usgov-nppes/adapter.d.ts.map +0 -1
  704. package/out/src/adapters/usgov-nppes/adapter.js +0 -116
  705. package/out/src/adapters/usgov-nppes/adapter.js.map +0 -1
  706. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
  707. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -156
  708. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
  709. package/out/src/adapters/utils/index.d.ts +0 -150
  710. package/out/src/adapters/utils/index.d.ts.map +0 -1
  711. package/out/src/adapters/utils/index.js +0 -159
  712. package/out/src/adapters/utils/index.js.map +0 -1
  713. package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
  714. package/out/src/adapters/wof-admin-jp/adapter.js +0 -164
  715. package/out/src/adapters/wof-admin-jp/adapter.js.map +0 -1
  716. package/out/src/adapters/wof-admin-json/adapter.d.ts +0 -82
  717. package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
  718. package/out/src/adapters/wof-admin-json/adapter.js +0 -224
  719. package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
  720. package/out/src/adapters/wof-json-rows.d.ts +0 -32
  721. package/out/src/adapters/wof-json-rows.d.ts.map +0 -1
  722. package/out/src/adapters/wof-json-rows.js +0 -45
  723. package/out/src/adapters/wof-json-rows.js.map +0 -1
  724. package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -65
  725. package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
  726. package/out/src/adapters/wof-postalcode-json/adapter.js +0 -160
  727. package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
  728. package/out/src/build.d.ts +0 -132
  729. package/out/src/build.d.ts.map +0 -1
  730. package/out/src/build.js +0 -251
  731. package/out/src/build.js.map +0 -1
  732. package/out/src/codex/us-fips-state.d.ts.map +0 -1
  733. package/out/src/codex/us-fips-state.js.map +0 -1
  734. package/out/src/index.d.ts +0 -14
  735. package/out/src/index.d.ts.map +0 -1
  736. package/out/src/index.js +0 -14
  737. package/out/src/index.js.map +0 -1
  738. package/out/src/name-prone-us-suffixes.d.ts +0 -12
  739. package/out/src/name-prone-us-suffixes.d.ts.map +0 -1
  740. package/out/src/name-prone-us-suffixes.js +0 -12
  741. package/out/src/name-prone-us-suffixes.js.map +0 -1
  742. package/out/src/parquet-wrapper/index.d.ts +0 -9
  743. package/out/src/parquet-wrapper/index.d.ts.map +0 -1
  744. package/out/src/parquet-wrapper/index.js +0 -9
  745. package/out/src/parquet-wrapper/index.js.map +0 -1
  746. package/out/src/parquet-wrapper/reader.d.ts +0 -34
  747. package/out/src/parquet-wrapper/reader.d.ts.map +0 -1
  748. package/out/src/parquet-wrapper/reader.js +0 -69
  749. package/out/src/parquet-wrapper/reader.js.map +0 -1
  750. package/out/src/parquet-wrapper/schema.d.ts +0 -49
  751. package/out/src/parquet-wrapper/schema.d.ts.map +0 -1
  752. package/out/src/parquet-wrapper/schema.js +0 -55
  753. package/out/src/parquet-wrapper/schema.js.map +0 -1
  754. package/out/src/parquet-wrapper/writer.d.ts +0 -46
  755. package/out/src/parquet-wrapper/writer.d.ts.map +0 -1
  756. package/out/src/parquet-wrapper/writer.js +0 -76
  757. package/out/src/parquet-wrapper/writer.js.map +0 -1
  758. package/out/src/runner.d.ts +0 -126
  759. package/out/src/runner.d.ts.map +0 -1
  760. package/out/src/runner.js +0 -189
  761. package/out/src/runner.js.map +0 -1
  762. package/out/src/shard-recipes/anchor-absorption.d.ts +0 -20
  763. package/out/src/shard-recipes/anchor-absorption.d.ts.map +0 -1
  764. package/out/src/shard-recipes/anchor-absorption.js +0 -82
  765. package/out/src/shard-recipes/anchor-absorption.js.map +0 -1
  766. package/out/src/shard-recipes/bare-country.d.ts +0 -25
  767. package/out/src/shard-recipes/bare-country.d.ts.map +0 -1
  768. package/out/src/shard-recipes/bare-country.js +0 -87
  769. package/out/src/shard-recipes/bare-country.js.map +0 -1
  770. package/out/src/shard-recipes/boundary-stress.d.ts +0 -20
  771. package/out/src/shard-recipes/boundary-stress.d.ts.map +0 -1
  772. package/out/src/shard-recipes/boundary-stress.js +0 -83
  773. package/out/src/shard-recipes/boundary-stress.js.map +0 -1
  774. package/out/src/shard-recipes/country-balanced.d.ts +0 -32
  775. package/out/src/shard-recipes/country-balanced.d.ts.map +0 -1
  776. package/out/src/shard-recipes/country-balanced.js +0 -406
  777. package/out/src/shard-recipes/country-balanced.js.map +0 -1
  778. package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts +0 -22
  779. package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +0 -1
  780. package/out/src/shard-recipes/cz-pcfirst-preposition.js +0 -100
  781. package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +0 -1
  782. package/out/src/shard-recipes/fr-admin-split.d.ts +0 -38
  783. package/out/src/shard-recipes/fr-admin-split.d.ts.map +0 -1
  784. package/out/src/shard-recipes/fr-admin-split.js +0 -188
  785. package/out/src/shard-recipes/fr-admin-split.js.map +0 -1
  786. package/out/src/shard-recipes/fr-bare-street.d.ts +0 -28
  787. package/out/src/shard-recipes/fr-bare-street.d.ts.map +0 -1
  788. package/out/src/shard-recipes/fr-bare-street.js +0 -143
  789. package/out/src/shard-recipes/fr-bare-street.js.map +0 -1
  790. package/out/src/shard-recipes/fr-fragment.d.ts +0 -77
  791. package/out/src/shard-recipes/fr-fragment.d.ts.map +0 -1
  792. package/out/src/shard-recipes/fr-fragment.js +0 -276
  793. package/out/src/shard-recipes/fr-fragment.js.map +0 -1
  794. package/out/src/shard-recipes/fr-lieudit.d.ts +0 -32
  795. package/out/src/shard-recipes/fr-lieudit.d.ts.map +0 -1
  796. package/out/src/shard-recipes/fr-lieudit.js +0 -226
  797. package/out/src/shard-recipes/fr-lieudit.js.map +0 -1
  798. package/out/src/shard-recipes/fr-order.d.ts +0 -38
  799. package/out/src/shard-recipes/fr-order.d.ts.map +0 -1
  800. package/out/src/shard-recipes/fr-order.js +0 -208
  801. package/out/src/shard-recipes/fr-order.js.map +0 -1
  802. package/out/src/shard-recipes/german.d.ts +0 -23
  803. package/out/src/shard-recipes/german.d.ts.map +0 -1
  804. package/out/src/shard-recipes/german.js +0 -132
  805. package/out/src/shard-recipes/german.js.map +0 -1
  806. package/out/src/shard-recipes/house-venue.d.ts +0 -18
  807. package/out/src/shard-recipes/house-venue.d.ts.map +0 -1
  808. package/out/src/shard-recipes/house-venue.js +0 -74
  809. package/out/src/shard-recipes/house-venue.js.map +0 -1
  810. package/out/src/shard-recipes/index.d.ts +0 -24
  811. package/out/src/shard-recipes/index.d.ts.map +0 -1
  812. package/out/src/shard-recipes/index.js +0 -89
  813. package/out/src/shard-recipes/index.js.map +0 -1
  814. package/out/src/shard-recipes/intersection.d.ts +0 -42
  815. package/out/src/shard-recipes/intersection.d.ts.map +0 -1
  816. package/out/src/shard-recipes/intersection.js +0 -460
  817. package/out/src/shard-recipes/intersection.js.map +0 -1
  818. package/out/src/shard-recipes/locale.d.ts +0 -135
  819. package/out/src/shard-recipes/locale.d.ts.map +0 -1
  820. package/out/src/shard-recipes/locale.js +0 -459
  821. package/out/src/shard-recipes/locale.js.map +0 -1
  822. package/out/src/shard-recipes/nl-postcode.d.ts +0 -26
  823. package/out/src/shard-recipes/nl-postcode.d.ts.map +0 -1
  824. package/out/src/shard-recipes/nl-postcode.js +0 -102
  825. package/out/src/shard-recipes/nl-postcode.js.map +0 -1
  826. package/out/src/shard-recipes/no-fragment.d.ts +0 -43
  827. package/out/src/shard-recipes/no-fragment.d.ts.map +0 -1
  828. package/out/src/shard-recipes/no-fragment.js +0 -188
  829. package/out/src/shard-recipes/no-fragment.js.map +0 -1
  830. package/out/src/shard-recipes/no-street-led.d.ts +0 -24
  831. package/out/src/shard-recipes/no-street-led.d.ts.map +0 -1
  832. package/out/src/shard-recipes/no-street-led.js +0 -121
  833. package/out/src/shard-recipes/no-street-led.js.map +0 -1
  834. package/out/src/shard-recipes/no-street.d.ts +0 -18
  835. package/out/src/shard-recipes/no-street.d.ts.map +0 -1
  836. package/out/src/shard-recipes/no-street.js +0 -72
  837. package/out/src/shard-recipes/no-street.js.map +0 -1
  838. package/out/src/shard-recipes/po-box-cedex.d.ts +0 -38
  839. package/out/src/shard-recipes/po-box-cedex.d.ts.map +0 -1
  840. package/out/src/shard-recipes/po-box-cedex.js +0 -726
  841. package/out/src/shard-recipes/po-box-cedex.js.map +0 -1
  842. package/out/src/shard-recipes/po-box.d.ts +0 -17
  843. package/out/src/shard-recipes/po-box.d.ts.map +0 -1
  844. package/out/src/shard-recipes/po-box.js +0 -101
  845. package/out/src/shard-recipes/po-box.js.map +0 -1
  846. package/out/src/shard-recipes/reviewed-postcode-tail.d.ts +0 -47
  847. package/out/src/shard-recipes/reviewed-postcode-tail.d.ts.map +0 -1
  848. package/out/src/shard-recipes/reviewed-postcode-tail.js +0 -125
  849. package/out/src/shard-recipes/reviewed-postcode-tail.js.map +0 -1
  850. package/out/src/shard-recipes/scaffold.d.ts +0 -246
  851. package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
  852. package/out/src/shard-recipes/scaffold.js +0 -137
  853. package/out/src/shard-recipes/scaffold.js.map +0 -1
  854. package/out/src/shard-recipes/si-bare-village.d.ts +0 -32
  855. package/out/src/shard-recipes/si-bare-village.d.ts.map +0 -1
  856. package/out/src/shard-recipes/si-bare-village.js +0 -88
  857. package/out/src/shard-recipes/si-bare-village.js.map +0 -1
  858. package/out/src/shard-recipes/street-affix.d.ts +0 -89
  859. package/out/src/shard-recipes/street-affix.d.ts.map +0 -1
  860. package/out/src/shard-recipes/street-affix.js +0 -578
  861. package/out/src/shard-recipes/street-affix.js.map +0 -1
  862. package/out/src/shard-recipes/street-bare.d.ts +0 -25
  863. package/out/src/shard-recipes/street-bare.d.ts.map +0 -1
  864. package/out/src/shard-recipes/street-bare.js +0 -86
  865. package/out/src/shard-recipes/street-bare.js.map +0 -1
  866. package/out/src/shard-recipes/street.d.ts +0 -15
  867. package/out/src/shard-recipes/street.d.ts.map +0 -1
  868. package/out/src/shard-recipes/street.js +0 -69
  869. package/out/src/shard-recipes/street.js.map +0 -1
  870. package/out/src/shard-recipes/sub-venue-sources.d.ts +0 -228
  871. package/out/src/shard-recipes/sub-venue-sources.d.ts.map +0 -1
  872. package/out/src/shard-recipes/sub-venue-sources.js +0 -664
  873. package/out/src/shard-recipes/sub-venue-sources.js.map +0 -1
  874. package/out/src/shard-recipes/sub-venue.d.ts +0 -269
  875. package/out/src/shard-recipes/sub-venue.d.ts.map +0 -1
  876. package/out/src/shard-recipes/sub-venue.js +0 -710
  877. package/out/src/shard-recipes/sub-venue.js.map +0 -1
  878. package/out/src/shard-recipes/trailing-region.d.ts +0 -74
  879. package/out/src/shard-recipes/trailing-region.d.ts.map +0 -1
  880. package/out/src/shard-recipes/trailing-region.js +0 -157
  881. package/out/src/shard-recipes/trailing-region.js.map +0 -1
  882. package/out/src/shard-recipes/unit.d.ts +0 -29
  883. package/out/src/shard-recipes/unit.d.ts.map +0 -1
  884. package/out/src/shard-recipes/unit.js +0 -243
  885. package/out/src/shard-recipes/unit.js.map +0 -1
  886. package/out/src/synthesizers/anchor-absorption.d.ts +0 -63
  887. package/out/src/synthesizers/anchor-absorption.d.ts.map +0 -1
  888. package/out/src/synthesizers/anchor-absorption.js +0 -223
  889. package/out/src/synthesizers/anchor-absorption.js.map +0 -1
  890. package/out/src/synthesizers/boundary-stress.d.ts +0 -78
  891. package/out/src/synthesizers/boundary-stress.d.ts.map +0 -1
  892. package/out/src/synthesizers/boundary-stress.js +0 -455
  893. package/out/src/synthesizers/boundary-stress.js.map +0 -1
  894. package/out/src/synthesizers/german.d.ts +0 -107
  895. package/out/src/synthesizers/german.d.ts.map +0 -1
  896. package/out/src/synthesizers/german.js +0 -148
  897. package/out/src/synthesizers/german.js.map +0 -1
  898. package/out/src/synthesizers/house-venue.d.ts +0 -56
  899. package/out/src/synthesizers/house-venue.d.ts.map +0 -1
  900. package/out/src/synthesizers/house-venue.js +0 -267
  901. package/out/src/synthesizers/house-venue.js.map +0 -1
  902. package/out/src/synthesizers/intersection.d.ts +0 -52
  903. package/out/src/synthesizers/intersection.d.ts.map +0 -1
  904. package/out/src/synthesizers/intersection.js +0 -175
  905. package/out/src/synthesizers/intersection.js.map +0 -1
  906. package/out/src/synthesizers/no-street.d.ts +0 -72
  907. package/out/src/synthesizers/no-street.d.ts.map +0 -1
  908. package/out/src/synthesizers/no-street.js +0 -282
  909. package/out/src/synthesizers/no-street.js.map +0 -1
  910. package/out/src/synthesizers/po-box.d.ts +0 -104
  911. package/out/src/synthesizers/po-box.d.ts.map +0 -1
  912. package/out/src/synthesizers/po-box.js +0 -266
  913. package/out/src/synthesizers/po-box.js.map +0 -1
  914. package/out/src/synthesizers/street.d.ts +0 -54
  915. package/out/src/synthesizers/street.d.ts.map +0 -1
  916. package/out/src/synthesizers/street.js +0 -221
  917. package/out/src/synthesizers/street.js.map +0 -1
  918. package/out/src/synthesizers/utils.d.ts +0 -203
  919. package/out/src/synthesizers/utils.d.ts.map +0 -1
  920. package/out/src/synthesizers/utils.js +0 -708
  921. package/out/src/synthesizers/utils.js.map +0 -1
  922. package/out/src/tools/align-shard.d.ts +0 -8
  923. package/out/src/tools/align-shard.d.ts.map +0 -1
  924. package/out/src/tools/align-shard.js +0 -56
  925. package/out/src/tools/align-shard.js.map +0 -1
  926. package/out/src/tools/audit.d.ts +0 -28
  927. package/out/src/tools/audit.d.ts.map +0 -1
  928. package/out/src/tools/audit.js +0 -285
  929. package/out/src/tools/audit.js.map +0 -1
  930. package/out/src/tools/corpus-stats.d.ts +0 -44
  931. package/out/src/tools/corpus-stats.d.ts.map +0 -1
  932. package/out/src/tools/corpus-stats.js +0 -138
  933. package/out/src/tools/corpus-stats.js.map +0 -1
  934. package/out/src/tools/fetch/ban.d.ts +0 -31
  935. package/out/src/tools/fetch/ban.d.ts.map +0 -1
  936. package/out/src/tools/fetch/ban.js +0 -239
  937. package/out/src/tools/fetch/ban.js.map +0 -1
  938. package/out/src/tools/fetch/download.d.ts +0 -78
  939. package/out/src/tools/fetch/download.d.ts.map +0 -1
  940. package/out/src/tools/fetch/download.js +0 -116
  941. package/out/src/tools/fetch/download.js.map +0 -1
  942. package/out/src/tools/fetch/geonames-dump.d.ts +0 -87
  943. package/out/src/tools/fetch/geonames-dump.d.ts.map +0 -1
  944. package/out/src/tools/fetch/geonames-dump.js +0 -178
  945. package/out/src/tools/fetch/geonames-dump.js.map +0 -1
  946. package/out/src/tools/fetch/geonames-postal.d.ts +0 -76
  947. package/out/src/tools/fetch/geonames-postal.d.ts.map +0 -1
  948. package/out/src/tools/fetch/geonames-postal.js +0 -125
  949. package/out/src/tools/fetch/geonames-postal.js.map +0 -1
  950. package/out/src/tools/fetch/hrsa.d.ts +0 -18
  951. package/out/src/tools/fetch/hrsa.d.ts.map +0 -1
  952. package/out/src/tools/fetch/hrsa.js +0 -46
  953. package/out/src/tools/fetch/hrsa.js.map +0 -1
  954. package/out/src/tools/fetch/imls-pls.d.ts +0 -25
  955. package/out/src/tools/fetch/imls-pls.d.ts.map +0 -1
  956. package/out/src/tools/fetch/imls-pls.js +0 -108
  957. package/out/src/tools/fetch/imls-pls.js.map +0 -1
  958. package/out/src/tools/fetch/index.d.ts +0 -144
  959. package/out/src/tools/fetch/index.d.ts.map +0 -1
  960. package/out/src/tools/fetch/index.js +0 -143
  961. package/out/src/tools/fetch/index.js.map +0 -1
  962. package/out/src/tools/fetch/nad.d.ts +0 -70
  963. package/out/src/tools/fetch/nad.d.ts.map +0 -1
  964. package/out/src/tools/fetch/nad.js +0 -234
  965. package/out/src/tools/fetch/nad.js.map +0 -1
  966. package/out/src/tools/fetch/nppes.d.ts +0 -26
  967. package/out/src/tools/fetch/nppes.d.ts.map +0 -1
  968. package/out/src/tools/fetch/nppes.js +0 -126
  969. package/out/src/tools/fetch/nppes.js.map +0 -1
  970. package/out/src/tools/fetch/openaddresses.d.ts +0 -61
  971. package/out/src/tools/fetch/openaddresses.d.ts.map +0 -1
  972. package/out/src/tools/fetch/openaddresses.js +0 -317
  973. package/out/src/tools/fetch/openaddresses.js.map +0 -1
  974. package/out/src/tools/fetch/ourairports.d.ts +0 -45
  975. package/out/src/tools/fetch/ourairports.d.ts.map +0 -1
  976. package/out/src/tools/fetch/ourairports.js +0 -128
  977. package/out/src/tools/fetch/ourairports.js.map +0 -1
  978. package/out/src/tools/fetch/ppd.d.ts.map +0 -1
  979. package/out/src/tools/fetch/ppd.js +0 -100
  980. package/out/src/tools/fetch/ppd.js.map +0 -1
  981. package/out/src/tools/fetch/state-hi-schools.d.ts +0 -25
  982. package/out/src/tools/fetch/state-hi-schools.d.ts.map +0 -1
  983. package/out/src/tools/fetch/state-hi-schools.js +0 -162
  984. package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
  985. package/out/src/tools/fetch/state-sources.d.ts +0 -26
  986. package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
  987. package/out/src/tools/fetch/state-sources.js +0 -111
  988. package/out/src/tools/fetch/state-sources.js.map +0 -1
  989. package/out/src/tools/fetch/tiger-full.d.ts +0 -42
  990. package/out/src/tools/fetch/tiger-full.d.ts.map +0 -1
  991. package/out/src/tools/fetch/tiger-full.js +0 -248
  992. package/out/src/tools/fetch/tiger-full.js.map +0 -1
  993. package/out/src/tools/fetch/wikidata-subvenue.d.ts +0 -171
  994. package/out/src/tools/fetch/wikidata-subvenue.d.ts.map +0 -1
  995. package/out/src/tools/fetch/wikidata-subvenue.js +0 -275
  996. package/out/src/tools/fetch/wikidata-subvenue.js.map +0 -1
  997. package/out/src/tools/gb-title-case.d.ts.map +0 -1
  998. package/out/src/tools/gb-title-case.js.map +0 -1
  999. package/out/src/tools/golden-expand.d.ts +0 -90
  1000. package/out/src/tools/golden-expand.d.ts.map +0 -1
  1001. package/out/src/tools/golden-expand.js +0 -413
  1002. package/out/src/tools/golden-expand.js.map +0 -1
  1003. package/out/src/tools/golden-promote.d.ts.map +0 -1
  1004. package/out/src/tools/golden-promote.js +0 -244
  1005. package/out/src/tools/golden-promote.js.map +0 -1
  1006. package/out/src/tools/golden-relabel-street.d.ts +0 -196
  1007. package/out/src/tools/golden-relabel-street.d.ts.map +0 -1
  1008. package/out/src/tools/golden-relabel-street.js +0 -440
  1009. package/out/src/tools/golden-relabel-street.js.map +0 -1
  1010. package/out/src/tools/index.d.ts +0 -28
  1011. package/out/src/tools/index.d.ts.map +0 -1
  1012. package/out/src/tools/index.js +0 -28
  1013. package/out/src/tools/index.js.map +0 -1
  1014. package/out/src/tools/ingest-csv.d.ts.map +0 -1
  1015. package/out/src/tools/ingest-csv.js +0 -296
  1016. package/out/src/tools/ingest-csv.js.map +0 -1
  1017. package/out/src/tools/jsonl-to-parquet.d.ts +0 -61
  1018. package/out/src/tools/jsonl-to-parquet.d.ts.map +0 -1
  1019. package/out/src/tools/jsonl-to-parquet.js +0 -164
  1020. package/out/src/tools/jsonl-to-parquet.js.map +0 -1
  1021. package/out/src/tools/lint-shard-vocab.d.ts +0 -90
  1022. package/out/src/tools/lint-shard-vocab.d.ts.map +0 -1
  1023. package/out/src/tools/lint-shard-vocab.js +0 -281
  1024. package/out/src/tools/lint-shard-vocab.js.map +0 -1
  1025. package/out/src/tools/lint-shard.d.ts +0 -93
  1026. package/out/src/tools/lint-shard.d.ts.map +0 -1
  1027. package/out/src/tools/lint-shard.js +0 -354
  1028. package/out/src/tools/lint-shard.js.map +0 -1
  1029. package/out/src/tools/overlay-manifest.d.ts +0 -39
  1030. package/out/src/tools/overlay-manifest.d.ts.map +0 -1
  1031. package/out/src/tools/overlay-manifest.js +0 -98
  1032. package/out/src/tools/overlay-manifest.js.map +0 -1
  1033. package/out/src/tools/overture-subvenue.d.ts +0 -112
  1034. package/out/src/tools/overture-subvenue.d.ts.map +0 -1
  1035. package/out/src/tools/overture-subvenue.js +0 -144
  1036. package/out/src/tools/overture-subvenue.js.map +0 -1
  1037. package/out/src/tools/postcode-triples.d.ts +0 -175
  1038. package/out/src/tools/postcode-triples.d.ts.map +0 -1
  1039. package/out/src/tools/postcode-triples.js +0 -304
  1040. package/out/src/tools/postcode-triples.js.map +0 -1
  1041. package/out/src/tools/shard-kryptonite.d.ts +0 -32
  1042. package/out/src/tools/shard-kryptonite.d.ts.map +0 -1
  1043. package/out/src/tools/shard-kryptonite.js +0 -100
  1044. package/out/src/tools/shard-kryptonite.js.map +0 -1
  1045. package/out/src/tools/shard-translit.d.ts +0 -51
  1046. package/out/src/tools/shard-translit.d.ts.map +0 -1
  1047. package/out/src/tools/shard-translit.js +0 -175
  1048. package/out/src/tools/shard-translit.js.map +0 -1
  1049. package/out/src/tools/sub-venue/harvest.d.ts +0 -100
  1050. package/out/src/tools/sub-venue/harvest.d.ts.map +0 -1
  1051. package/out/src/tools/sub-venue/harvest.js +0 -168
  1052. package/out/src/tools/sub-venue/harvest.js.map +0 -1
  1053. package/out/src/tools/sub-venue/head-nouns.d.ts +0 -50
  1054. package/out/src/tools/sub-venue/head-nouns.d.ts.map +0 -1
  1055. package/out/src/tools/sub-venue/head-nouns.js +0 -210
  1056. package/out/src/tools/sub-venue/head-nouns.js.map +0 -1
  1057. package/out/src/tools/sub-venue/surfaces.d.ts +0 -45
  1058. package/out/src/tools/sub-venue/surfaces.d.ts.map +0 -1
  1059. package/out/src/tools/sub-venue/surfaces.js +0 -77
  1060. package/out/src/tools/sub-venue/surfaces.js.map +0 -1
  1061. package/out/src/tools/sub-venue/table.d.ts +0 -229
  1062. package/out/src/tools/sub-venue/table.d.ts.map +0 -1
  1063. package/out/src/tools/sub-venue/table.js +0 -108
  1064. package/out/src/tools/sub-venue/table.js.map +0 -1
  1065. package/out/src/tools/sub-venue/wikidata.d.ts +0 -26
  1066. package/out/src/tools/sub-venue/wikidata.d.ts.map +0 -1
  1067. package/out/src/tools/sub-venue/wikidata.js +0 -62
  1068. package/out/src/tools/sub-venue/wikidata.js.map +0 -1
  1069. package/out/src/tools/sub-venue-lexicon.d.ts +0 -156
  1070. package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
  1071. package/out/src/tools/sub-venue-lexicon.js +0 -282
  1072. package/out/src/tools/sub-venue-lexicon.js.map +0 -1
  1073. package/out/src/tools/sub-venue-promotions.d.ts +0 -94
  1074. package/out/src/tools/sub-venue-promotions.d.ts.map +0 -1
  1075. package/out/src/tools/sub-venue-promotions.js +0 -266
  1076. package/out/src/tools/sub-venue-promotions.js.map +0 -1
  1077. package/out/src/types.d.ts +0 -221
  1078. package/out/src/types.d.ts.map +0 -1
  1079. package/out/src/types.js.map +0 -1
  1080. package/out/src/utils/align.d.ts +0 -93
  1081. package/out/src/utils/align.d.ts.map +0 -1
  1082. package/out/src/utils/align.js +0 -234
  1083. package/out/src/utils/align.js.map +0 -1
  1084. package/out/src/utils/golden.d.ts +0 -69
  1085. package/out/src/utils/golden.d.ts.map +0 -1
  1086. package/out/src/utils/golden.js +0 -127
  1087. package/out/src/utils/golden.js.map +0 -1
  1088. package/out/src/utils/index.d.ts +0 -14
  1089. package/out/src/utils/index.d.ts.map +0 -1
  1090. package/out/src/utils/index.js +0 -14
  1091. package/out/src/utils/index.js.map +0 -1
  1092. package/out/src/utils/license.d.ts.map +0 -1
  1093. package/out/src/utils/license.js.map +0 -1
  1094. package/out/src/utils/parquet.d.ts +0 -162
  1095. package/out/src/utils/parquet.d.ts.map +0 -1
  1096. package/out/src/utils/parquet.js +0 -262
  1097. package/out/src/utils/parquet.js.map +0 -1
  1098. package/out/src/utils/split.d.ts +0 -127
  1099. package/out/src/utils/split.d.ts.map +0 -1
  1100. package/out/src/utils/split.js +0 -204
  1101. package/out/src/utils/split.js.map +0 -1
  1102. package/out/src/utils/tokenize.d.ts +0 -56
  1103. package/out/src/utils/tokenize.d.ts.map +0 -1
  1104. package/out/src/utils/tokenize.js +0 -48
  1105. package/out/src/utils/tokenize.js.map +0 -1
  1106. package/out/src/utils/wof-json.d.ts +0 -109
  1107. package/out/src/utils/wof-json.d.ts.map +0 -1
  1108. package/out/src/utils/wof-json.js +0 -173
  1109. package/out/src/utils/wof-json.js.map +0 -1
  1110. package/src/adapters/ban/adapter.ts +0 -191
  1111. package/src/adapters/ban/street-decompose.ts +0 -96
  1112. package/src/adapters/fcc-bdc/adapter.ts +0 -174
  1113. package/src/adapters/geonames/adapter.ts +0 -200
  1114. package/src/adapters/geonames-postal/adapter.ts +0 -119
  1115. package/src/adapters/gnaf/adapter.ts +0 -149
  1116. package/src/adapters/gnaf/assemble.ts +0 -226
  1117. package/src/adapters/index.ts +0 -149
  1118. package/src/adapters/openaddresses/adapter.ts +0 -251
  1119. package/src/adapters/overture/adapter.ts +0 -162
  1120. package/src/adapters/state-hi-schools/adapter.ts +0 -164
  1121. package/src/adapters/synth-po-box/adapter.ts +0 -204
  1122. package/src/adapters/tiger/adapter.ts +0 -253
  1123. package/src/adapters/tiger/street-decompose.ts +0 -111
  1124. package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -183
  1125. package/src/adapters/usgov-imls-pls/adapter.ts +0 -143
  1126. package/src/adapters/usgov-irs-bmf/adapter.ts +0 -163
  1127. package/src/adapters/usgov-nad/adapter.ts +0 -348
  1128. package/src/adapters/usgov-nppes/adapter.ts +0 -159
  1129. package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -204
  1130. package/src/adapters/utils/index.ts +0 -233
  1131. package/src/adapters/wof-admin-jp/adapter.ts +0 -216
  1132. package/src/adapters/wof-admin-json/adapter.ts +0 -256
  1133. package/src/adapters/wof-json-rows.ts +0 -79
  1134. package/src/adapters/wof-postalcode-json/adapter.ts +0 -183
  1135. package/src/build.ts +0 -386
  1136. package/src/index.ts +0 -14
  1137. package/src/name-prone-us-suffixes.ts +0 -12
  1138. package/src/parquet-wrapper/index.ts +0 -9
  1139. package/src/parquet-wrapper/reader.ts +0 -97
  1140. package/src/parquet-wrapper/schema.ts +0 -88
  1141. package/src/parquet-wrapper/writer.ts +0 -110
  1142. package/src/runner.ts +0 -317
  1143. package/src/shard-recipes/anchor-absorption.ts +0 -103
  1144. package/src/shard-recipes/bare-country.ts +0 -95
  1145. package/src/shard-recipes/boundary-stress.ts +0 -101
  1146. package/src/shard-recipes/country-balanced.ts +0 -524
  1147. package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -111
  1148. package/src/shard-recipes/fr-admin-split.ts +0 -239
  1149. package/src/shard-recipes/fr-bare-street.ts +0 -170
  1150. package/src/shard-recipes/fr-fragment.ts +0 -332
  1151. package/src/shard-recipes/fr-lieudit.ts +0 -302
  1152. package/src/shard-recipes/fr-order.ts +0 -258
  1153. package/src/shard-recipes/german.ts +0 -170
  1154. package/src/shard-recipes/house-venue.ts +0 -88
  1155. package/src/shard-recipes/index.ts +0 -95
  1156. package/src/shard-recipes/intersection.ts +0 -630
  1157. package/src/shard-recipes/locale.ts +0 -599
  1158. package/src/shard-recipes/nl-postcode.ts +0 -115
  1159. package/src/shard-recipes/no-fragment.ts +0 -219
  1160. package/src/shard-recipes/no-street-led.ts +0 -143
  1161. package/src/shard-recipes/no-street.ts +0 -86
  1162. package/src/shard-recipes/po-box-cedex.ts +0 -920
  1163. package/src/shard-recipes/po-box.ts +0 -119
  1164. package/src/shard-recipes/reviewed-postcode-tail.ts +0 -189
  1165. package/src/shard-recipes/scaffold.ts +0 -360
  1166. package/src/shard-recipes/si-bare-village.ts +0 -97
  1167. package/src/shard-recipes/street-affix.ts +0 -826
  1168. package/src/shard-recipes/street-bare.ts +0 -101
  1169. package/src/shard-recipes/street.ts +0 -82
  1170. package/src/shard-recipes/sub-venue-sources.ts +0 -885
  1171. package/src/shard-recipes/sub-venue.ts +0 -984
  1172. package/src/shard-recipes/trailing-region.ts +0 -183
  1173. package/src/shard-recipes/unit.ts +0 -321
  1174. package/src/synthesizers/anchor-absorption.ts +0 -290
  1175. package/src/synthesizers/boundary-stress.ts +0 -531
  1176. package/src/synthesizers/german.ts +0 -251
  1177. package/src/synthesizers/house-venue.ts +0 -330
  1178. package/src/synthesizers/intersection.ts +0 -232
  1179. package/src/synthesizers/no-street.ts +0 -349
  1180. package/src/synthesizers/po-box.ts +0 -339
  1181. package/src/synthesizers/street.ts +0 -274
  1182. package/src/synthesizers/utils.ts +0 -903
  1183. package/src/tools/align-shard.ts +0 -70
  1184. package/src/tools/audit.ts +0 -399
  1185. package/src/tools/corpus-stats.ts +0 -184
  1186. package/src/tools/fetch/ban.ts +0 -290
  1187. package/src/tools/fetch/download.ts +0 -176
  1188. package/src/tools/fetch/geonames-dump.ts +0 -267
  1189. package/src/tools/fetch/geonames-postal.ts +0 -180
  1190. package/src/tools/fetch/hrsa.ts +0 -68
  1191. package/src/tools/fetch/imls-pls.ts +0 -158
  1192. package/src/tools/fetch/index.ts +0 -147
  1193. package/src/tools/fetch/nad.ts +0 -342
  1194. package/src/tools/fetch/nppes.ts +0 -174
  1195. package/src/tools/fetch/openaddresses.ts +0 -404
  1196. package/src/tools/fetch/ourairports.ts +0 -171
  1197. package/src/tools/fetch/ppd.ts +0 -137
  1198. package/src/tools/fetch/state-hi-schools.ts +0 -208
  1199. package/src/tools/fetch/state-sources.ts +0 -155
  1200. package/src/tools/fetch/tiger-full.ts +0 -354
  1201. package/src/tools/fetch/wikidata-subvenue.ts +0 -386
  1202. package/src/tools/golden-expand.ts +0 -584
  1203. package/src/tools/golden-promote.ts +0 -353
  1204. package/src/tools/golden-relabel-street.ts +0 -685
  1205. package/src/tools/index.ts +0 -28
  1206. package/src/tools/ingest-csv.ts +0 -422
  1207. package/src/tools/jsonl-to-parquet.ts +0 -221
  1208. package/src/tools/lint-shard-vocab.ts +0 -409
  1209. package/src/tools/lint-shard.ts +0 -543
  1210. package/src/tools/overlay-manifest.ts +0 -157
  1211. package/src/tools/overture-subvenue.ts +0 -215
  1212. package/src/tools/postcode-triples.ts +0 -375
  1213. package/src/tools/shard-kryptonite.ts +0 -139
  1214. package/src/tools/shard-translit.ts +0 -245
  1215. package/src/tools/sub-venue/harvest.ts +0 -235
  1216. package/src/tools/sub-venue/head-nouns.ts +0 -242
  1217. package/src/tools/sub-venue/surfaces.ts +0 -95
  1218. package/src/tools/sub-venue/table.ts +0 -281
  1219. package/src/tools/sub-venue/wikidata.ts +0 -85
  1220. package/src/tools/sub-venue-lexicon.ts +0 -431
  1221. package/src/tools/sub-venue-promotions.ts +0 -330
  1222. package/src/types.ts +0 -247
  1223. package/src/utils/align.ts +0 -331
  1224. package/src/utils/golden.ts +0 -176
  1225. package/src/utils/index.ts +0 -14
  1226. package/src/utils/parquet.ts +0 -391
  1227. package/src/utils/split.ts +0 -279
  1228. package/src/utils/tokenize.ts +0 -78
  1229. package/src/utils/wof-json.ts +0 -244
  1230. /package/{src → lib}/adapters/state-ia-contractors/adapter.ts +0 -0
  1231. /package/{src → lib}/adapters/state-ny-notaries/adapter.ts +0 -0
  1232. /package/{src → lib}/adapters/state-tx-notaries/adapter.ts +0 -0
  1233. /package/{src → lib}/codex/us-fips-state.ts +0 -0
  1234. /package/{src → lib}/tools/gb-title-case.ts +0 -0
  1235. /package/{src → lib}/utils/license.ts +0 -0
  1236. /package/out/{src/adapters → adapters}/ban/adapter.d.ts +0 -0
  1237. /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
  1238. /package/out/{src/adapters → adapters}/fcc-bdc/adapter.d.ts +0 -0
  1239. /package/out/{src/adapters → adapters}/geonames/adapter.d.ts +0 -0
  1240. /package/out/{src/adapters → adapters}/openaddresses/adapter.d.ts +0 -0
  1241. /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.d.ts +0 -0
  1242. /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.js +0 -0
  1243. /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.d.ts +0 -0
  1244. /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.js +0 -0
  1245. /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.d.ts +0 -0
  1246. /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.js +0 -0
  1247. /package/out/{src/adapters → adapters}/synth-po-box/adapter.d.ts +0 -0
  1248. /package/out/{src/adapters → adapters}/tiger/street-decompose.d.ts +0 -0
  1249. /package/out/{src/adapters → adapters}/usgov-nppes/adapter.d.ts +0 -0
  1250. /package/out/{src/adapters → adapters}/usgov-samhsa-treatment-locator/adapter.d.ts +0 -0
  1251. /package/out/{src/adapters → adapters}/wof-admin-jp/adapter.d.ts +0 -0
  1252. /package/out/{src/codex → codex}/us-fips-state.d.ts +0 -0
  1253. /package/out/{src/codex → codex}/us-fips-state.js +0 -0
  1254. /package/out/{src/tools → tools}/fetch/ppd.d.ts +0 -0
  1255. /package/out/{src/tools → tools}/gb-title-case.d.ts +0 -0
  1256. /package/out/{src/tools → tools}/gb-title-case.js +0 -0
  1257. /package/out/{src/tools → tools}/golden-promote.d.ts +0 -0
  1258. /package/out/{src/tools → tools}/ingest-csv.d.ts +0 -0
  1259. /package/out/{src/types.js → types.js} +0 -0
  1260. /package/out/{src/utils → utils}/license.d.ts +0 -0
  1261. /package/out/{src/utils → utils}/license.js +0 -0
@@ -0,0 +1,322 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ *
6
+ * Corpus linter. Compares a new slice against pre-computed corpus statistics and flags patterns
7
+ * that would cause the class of failure we hit with v0.6.2's "5th Avenue Theatre" adversarial
8
+ * venue templates.
9
+ *
10
+ * Per DeepSeek turn 9 design (2026-05-29). v1 checks:
11
+ *
12
+ * 1. **Token-label distribution outliers.** For each token in the new slice, compare the slice's
13
+ * majority label to the corpus's majority label. Flag when the corpus has a
14
+ * confidently-established majority (>66%) AND the slice's majority differs AND both have
15
+ * non-trivial counts (slice ≥ 50, corpus ≥ 200).
16
+ * 2. **Label-vacuum tokens.** Token labeled with a tag that has ZERO instances in the corpus for that
17
+ * token, despite the token being well-represented in the corpus. Stronger signal than #1 —
18
+ * we're introducing a novel association, not shifting a distribution.
19
+ * 3. **Bigram-label collisions.** Identical (token_bigram, label_bigram) appears in slice while the
20
+ * same token_bigram has a DIFFERENT majority label_bigram in the corpus. The "5th Avenue"
21
+ * with [B-venue, I-venue] vs corpus's [B-house_number, I-street] case.
22
+ * 4. **Common-form anti-pattern rules.** Applies `lint-rules.json` — token-regex → forbidden-labels
23
+ * mappings — flagging matches.
24
+ * 5. **Basic sanity.** Truncated rows (tokens.length !== labels.length), all-O rows >90% of slice.
25
+ *
26
+ * Output: markdown report on stdout, optional JSON sidecar via `outJSON`. The command exits 0 if
27
+ * no errors, 1 if any errors (warnings don't check). Per the design, the MANIFEST entry for a
28
+ * flagged slice should require `lint_acknowledged: true` before training consumes it.
29
+ *
30
+ * Usage: mailwoman dev lint corpus-slice\
31
+ * --slice <new-slice.parquet>\
32
+ * --stats <corpus-stats.json>\
33
+ * [--rules <rules.json>]\
34
+ * [--out-md /tmp/lint-report.md]\
35
+ * [--out-json /tmp/lint-report.json]
36
+ */
37
+ import { readLocalJSONFile } from "@mailwoman/core/fs/readers";
38
+ import { writeLocalFile, writeLocalJSONFile } from "@mailwoman/core/fs/writers";
39
+ import { resolvePackagePath } from "@mailwoman/core/module/resolvers";
40
+ import { accumulateCooccurrences, createCooccurrenceStats, SLICE_STATS_SEP as SEP, streamTokenLabelRows, } from "#utils/slice-stats";
41
+ /**
42
+ * Occurrences of a forbidden label before it is reported — one or two are noise, five is a pattern.
43
+ */
44
+ const FORBIDDEN_LABEL_REPORT_THRESHOLD = 5;
45
+ /**
46
+ * Examples printed per finding before the list is truncated.
47
+ */
48
+ const MAX_LISTED_EXAMPLES = 20;
49
+ /**
50
+ * Calibrated thresholds (DeepSeek turn 9). These can be tuned over time if new failure modes surface that the current
51
+ * numbers miss.
52
+ */
53
+ const CORPUS_CONFIDENCE_FLOOR = 0.66;
54
+ const SLICE_MIN_COUNT = 50;
55
+ const CORPUS_MIN_COUNT = 200;
56
+ const VACUUM_SLICE_MIN_COUNT = 20;
57
+ const VACUUM_CORPUS_MIN_COUNT = 100;
58
+ const BIGRAM_MIN_COUNT = 10;
59
+ const ALL_O_RATIO_CEILING = 0.9;
60
+ /**
61
+ * Default `lint-rules.json` path — the rules ship beside this module in the source tree. tsc does not emit
62
+ * readFileSync'd JSON into `out/`, so the compiled tree falls back to the source-tree copy (corpus/out/src/tools/ →
63
+ * corpus/src/tools/). In-repo the `node` exports condition loads this module from source anyway, so the sibling URL is
64
+ * the common path.
65
+ */
66
+ function defaultRulesPath() {
67
+ return resolvePackagePath("@mailwoman/corpus", "lib", "tools", "lint-rules.json");
68
+ }
69
+ async function statsFromSlice(rows) {
70
+ const co = createCooccurrenceStats();
71
+ const out = {
72
+ rowCount: 0,
73
+ tokens: co.tokens,
74
+ bigrams: co.bigrams,
75
+ truncatedRows: 0,
76
+ allORows: 0,
77
+ };
78
+ for await (const row of rows) {
79
+ out.rowCount++;
80
+ if (row.tokens.length !== row.labels.length) {
81
+ out.truncatedRows++;
82
+ continue;
83
+ }
84
+ if (row.labels.every((l) => l === "O")) {
85
+ out.allORows++;
86
+ }
87
+ accumulateCooccurrences(co, row.tokens, row.labels);
88
+ }
89
+ return out;
90
+ }
91
+ function majorityLabel(distribution) {
92
+ const entries = distribution instanceof Map ? [...distribution.entries()] : Object.entries(distribution);
93
+ let bestLabel = "";
94
+ let bestCount = 0;
95
+ let total = 0;
96
+ for (const [label, count] of entries) {
97
+ total += count;
98
+ if (count > bestCount) {
99
+ bestCount = count;
100
+ bestLabel = label;
101
+ }
102
+ }
103
+ return { label: bestLabel, count: bestCount, total, confidence: total === 0 ? 0 : bestCount / total };
104
+ }
105
+ function checkDistributionOutliers(slice, corpus) {
106
+ const flags = [];
107
+ for (const [token, sliceLabelMap] of slice.tokens) {
108
+ const corpusLabelMap = corpus.tokens[token];
109
+ if (!corpusLabelMap)
110
+ continue;
111
+ const sliceMaj = majorityLabel(sliceLabelMap);
112
+ const corpusMaj = majorityLabel(corpusLabelMap);
113
+ if (corpusMaj.confidence >= CORPUS_CONFIDENCE_FLOOR &&
114
+ sliceMaj.label !== corpusMaj.label &&
115
+ sliceMaj.count >= SLICE_MIN_COUNT &&
116
+ corpusMaj.total >= CORPUS_MIN_COUNT) {
117
+ flags.push({
118
+ check: "distribution-outlier",
119
+ severity: "error",
120
+ token,
121
+ sliceLabel: sliceMaj.label,
122
+ corpusLabel: corpusMaj.label,
123
+ sliceCount: sliceMaj.count,
124
+ corpusCount: corpusMaj.count,
125
+ detail: `Token "${token}": slice majority is ${sliceMaj.label} (${sliceMaj.count}/${sliceMaj.total}, ${(sliceMaj.confidence * 100).toFixed(0)}%), corpus majority is ${corpusMaj.label} (${corpusMaj.count}/${corpusMaj.total}, ${(corpusMaj.confidence * 100).toFixed(0)}%).`,
126
+ });
127
+ }
128
+ }
129
+ return flags;
130
+ }
131
+ function checkLabelVacuum(slice, corpus) {
132
+ const flags = [];
133
+ for (const [token, sliceLabelMap] of slice.tokens) {
134
+ const corpusLabelMap = corpus.tokens[token];
135
+ if (!corpusLabelMap)
136
+ continue;
137
+ const corpusTotal = Object.values(corpusLabelMap).reduce((a, b) => a + b, 0);
138
+ if (corpusTotal < VACUUM_CORPUS_MIN_COUNT)
139
+ continue;
140
+ for (const [label, sliceCount] of sliceLabelMap) {
141
+ if (sliceCount < VACUUM_SLICE_MIN_COUNT)
142
+ continue;
143
+ if (corpusLabelMap[label] === undefined || corpusLabelMap[label] === 0) {
144
+ flags.push({
145
+ check: "label-vacuum",
146
+ severity: "error",
147
+ token,
148
+ sliceLabel: label,
149
+ sliceCount,
150
+ corpusCount: corpusTotal,
151
+ detail: `Token "${token}": slice labels it ${label} ${sliceCount} times, but the corpus (${corpusTotal} instances of this token) has ZERO instances of this label.`,
152
+ });
153
+ }
154
+ }
155
+ }
156
+ return flags;
157
+ }
158
+ function checkBigramCollisions(slice, corpus) {
159
+ const flags = [];
160
+ for (const [bigram, sliceLabelMap] of slice.bigrams) {
161
+ const corpusLabelMap = corpus.bigrams[bigram];
162
+ if (!corpusLabelMap)
163
+ continue;
164
+ const sliceMaj = majorityLabel(sliceLabelMap);
165
+ const corpusMaj = majorityLabel(corpusLabelMap);
166
+ if (sliceMaj.label !== corpusMaj.label &&
167
+ sliceMaj.count >= BIGRAM_MIN_COUNT &&
168
+ corpusMaj.count >= BIGRAM_MIN_COUNT) {
169
+ const renderBigram = bigram.split(SEP).join(" ");
170
+ const renderSliceLabel = sliceMaj.label.split(SEP).join(" → ");
171
+ const renderCorpusLabel = corpusMaj.label.split(SEP).join(" → ");
172
+ flags.push({
173
+ check: "bigram-collision",
174
+ severity: "error",
175
+ bigram: renderBigram,
176
+ sliceLabel: renderSliceLabel,
177
+ corpusLabel: renderCorpusLabel,
178
+ sliceCount: sliceMaj.count,
179
+ corpusCount: corpusMaj.count,
180
+ detail: `Bigram "${renderBigram}": slice label-bigram is [${renderSliceLabel}] (${sliceMaj.count}×), corpus label-bigram is [${renderCorpusLabel}] (${corpusMaj.count}×). Same surface text, different structural reading.`,
181
+ });
182
+ }
183
+ }
184
+ return flags;
185
+ }
186
+ function checkRules(slice, rulesFile) {
187
+ const flags = [];
188
+ const compiled = rulesFile.rules.map((r) => ({
189
+ rule: r,
190
+ regex: new RegExp(r.pattern, r.pattern_case_sensitive ? "" : "i"),
191
+ }));
192
+ for (const [token, labelMap] of slice.tokens) {
193
+ for (const { rule, regex } of compiled) {
194
+ if (!regex.test(token))
195
+ continue;
196
+ for (const [label, count] of labelMap) {
197
+ if (rule.forbidden_labels.includes(label) && count >= FORBIDDEN_LABEL_REPORT_THRESHOLD) {
198
+ flags.push({
199
+ check: "anti-pattern-rule",
200
+ severity: rule.severity,
201
+ ruleID: rule.id,
202
+ token,
203
+ sliceLabel: label,
204
+ sliceCount: count,
205
+ detail: `Token "${token}" matched rule ${rule.id} and is labeled ${label} ${count} time(s). Rule message: ${rule.message}`,
206
+ });
207
+ }
208
+ }
209
+ }
210
+ }
211
+ return flags;
212
+ }
213
+ function checkSanity(slice) {
214
+ const flags = [];
215
+ if (slice.truncatedRows > 0) {
216
+ flags.push({
217
+ check: "truncated-rows",
218
+ severity: "error",
219
+ detail: `${slice.truncatedRows} row(s) have tokens.length !== labels.length. Pipeline alignment bug.`,
220
+ });
221
+ }
222
+ const allORatio = slice.allORows / Math.max(1, slice.rowCount);
223
+ if (allORatio >= ALL_O_RATIO_CEILING) {
224
+ flags.push({
225
+ check: "all-O-slice",
226
+ severity: "warn",
227
+ detail: `${slice.allORows}/${slice.rowCount} rows (${(allORatio * 100).toFixed(0)}%) are entirely O-labeled. Slice contributes no signal.`,
228
+ });
229
+ }
230
+ return flags;
231
+ }
232
+ function renderReport(opts, slice, flags) {
233
+ const errors = flags.filter((f) => f.severity === "error");
234
+ const warns = flags.filter((f) => f.severity === "warn");
235
+ const verdict = !errors.length ? "**PASS** ✓" : "**FLAGGED** ⚠";
236
+ const lines = [
237
+ `# Corpus Lint: ${verdict}`,
238
+ "",
239
+ `- **Slice:** \`${opts.slicePath}\``,
240
+ `- **Corpus stats:** \`${opts.statsPath}\``,
241
+ `- **Rules:** \`${opts.rulesPath}\``,
242
+ `- **Slice rows:** ${slice.rowCount}`,
243
+ `- **Unique tokens:** ${slice.tokens.size}`,
244
+ `- **Unique bigrams:** ${slice.bigrams.size}`,
245
+ "",
246
+ `**Errors:** ${errors.length} (checks the slice's inclusion unless MANIFEST sets \`lint_acknowledged: true\`)`,
247
+ `**Warnings:** ${warns.length} (advisory)`,
248
+ "",
249
+ ];
250
+ if (!flags.length) {
251
+ lines.push("No anomalies detected.");
252
+ return lines.join("\n");
253
+ }
254
+ const byCheck = new Map();
255
+ for (const f of flags) {
256
+ const arr = byCheck.get(f.check) ?? [];
257
+ arr.push(f);
258
+ byCheck.set(f.check, arr);
259
+ }
260
+ for (const [check, list] of byCheck) {
261
+ lines.push(`## ${check} (${list.length})`);
262
+ lines.push("");
263
+ // Sort by sliceCount desc — highest-volume issues first
264
+ list.sort((a, b) => (b.sliceCount ?? 0) - (a.sliceCount ?? 0));
265
+ for (const f of list.slice(0, 20)) {
266
+ lines.push(`- **[${f.severity.toUpperCase()}]** ${f.detail}`);
267
+ }
268
+ if (list.length > MAX_LISTED_EXAMPLES) {
269
+ lines.push(`- ... and ${list.length - 20} more`);
270
+ }
271
+ lines.push("");
272
+ }
273
+ return lines.join("\n");
274
+ }
275
+ /**
276
+ * Lint a slice against corpus stats + the anti-pattern rules; print the markdown report to stdout.
277
+ */
278
+ export async function lintCorpusSlice(options, report) {
279
+ const rulesPath = options.rulesPath ?? defaultRulesPath();
280
+ report?.(`Reading corpus stats from ${options.statsPath}...`);
281
+ const corpus = await readLocalJSONFile(options.statsPath);
282
+ report?.(` ${corpus.row_count} rows from ${corpus.slice_paths.length} slice(s); ${Object.keys(corpus.tokens).length} tokens, ${Object.keys(corpus.bigrams).length} bigrams`);
283
+ report?.(`Reading slice from ${options.slicePath}...`);
284
+ const slice = await statsFromSlice(streamTokenLabelRows(options.slicePath));
285
+ report?.(` ${slice.rowCount} rows`);
286
+ report?.(`Loading rules from ${rulesPath}...`);
287
+ const rulesFile = await readLocalJSONFile(rulesPath);
288
+ report?.(`Running checks...`);
289
+ const flags = [
290
+ ...checkDistributionOutliers(slice, corpus),
291
+ ...checkLabelVacuum(slice, corpus),
292
+ ...checkBigramCollisions(slice, corpus),
293
+ ...checkRules(slice, rulesFile),
294
+ ...checkSanity(slice),
295
+ ];
296
+ const rendered = renderReport({ slicePath: options.slicePath, statsPath: options.statsPath, rulesPath }, slice, flags);
297
+ console.log(rendered);
298
+ if (options.outMd) {
299
+ await writeLocalFile(rendered, options.outMd);
300
+ }
301
+ if (options.outJSON) {
302
+ await writeLocalJSONFile({
303
+ slice: options.slicePath,
304
+ stats: options.statsPath,
305
+ flags,
306
+ summary: {
307
+ errors: flags.filter((f) => f.severity === "error").length,
308
+ warnings: flags.filter((f) => f.severity === "warn").length,
309
+ },
310
+ }, options.outJSON);
311
+ }
312
+ const errorCount = flags.filter((f) => f.severity === "error").length;
313
+ const warningCount = flags.filter((f) => f.severity === "warn").length;
314
+ if (errorCount > 0) {
315
+ report?.(`LINT FAILED: ${errorCount} error(s).`);
316
+ }
317
+ else {
318
+ report?.("LINT PASSED.");
319
+ }
320
+ return { errors: errorCount, warnings: warningCount, findings: flags, report: rendered };
321
+ }
322
+ //# sourceMappingURL=lint-slice.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"lint-slice.js","sourceRoot":"","sources":["../../lib/tools/lint-slice.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAmCG;AAEH,OAAO,EAAE,iBAAiB,EAAE,MAAM,4BAA4B,CAAA;AAC9D,OAAO,EAAE,cAAc,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAA;AAC/E,OAAO,EAAE,kBAAkB,EAAE,MAAM,kCAAkC,CAAA;AAErE,OAAO,EACN,uBAAuB,EACvB,uBAAuB,EACvB,eAAe,IAAI,GAAG,EACtB,oBAAoB,GAEpB,MAAM,oBAAoB,CAAA;AAE3B;;GAEG;AACH,MAAM,gCAAgC,GAAG,CAAC,CAAA;AAE1C;;GAEG;AACH,MAAM,mBAAmB,GAAG,EAAE,CAAA;AAE9B;;;GAGG;AACH,MAAM,uBAAuB,GAAG,IAAI,CAAA;AACpC,MAAM,eAAe,GAAG,EAAE,CAAA;AAC1B,MAAM,gBAAgB,GAAG,GAAG,CAAA;AAC5B,MAAM,sBAAsB,GAAG,EAAE,CAAA;AACjC,MAAM,uBAAuB,GAAG,GAAG,CAAA;AACnC,MAAM,gBAAgB,GAAG,EAAE,CAAA;AAC3B,MAAM,mBAAmB,GAAG,GAAG,CAAA;AAE/B;;;;;GAKG;AACH,SAAS,gBAAgB;IACxB,OAAO,kBAAkB,CAAC,mBAAmB,EAAE,KAAK,EAAE,OAAO,EAAE,iBAAiB,CAAC,CAAA;AAClF,CAAC;AAwDD,KAAK,UAAU,cAAc,CAAC,IAA6B;IAC1D,MAAM,EAAE,GAAG,uBAAuB,EAAE,CAAA;IAEpC,MAAM,GAAG,GAAe;QACvB,QAAQ,EAAE,CAAC;QACX,MAAM,EAAE,EAAE,CAAC,MAAM;QACjB,OAAO,EAAE,EAAE,CAAC,OAAO;QACnB,aAAa,EAAE,CAAC;QAChB,QAAQ,EAAE,CAAC;KACX,CAAA;IAED,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;QAC9B,GAAG,CAAC,QAAQ,EAAE,CAAA;QAEd,IAAI,GAAG,CAAC,MAAM,CAAC,MAAM,KAAK,GAAG,CAAC,MAAM,CAAC,MAAM,EAAE,CAAC;YAC7C,GAAG,CAAC,aAAa,EAAE,CAAA;YAEnB,SAAQ;QACT,CAAC;QAED,IAAI,GAAG,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,GAAG,CAAC,EAAE,CAAC;YACxC,GAAG,CAAC,QAAQ,EAAE,CAAA;QACf,CAAC;QAED,uBAAuB,CAAC,EAAE,EAAE,GAAG,CAAC,MAAM,EAAE,GAAG,CAAC,MAAM,CAAC,CAAA;IACpD,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC;AAED,SAAS,aAAa,CAAC,YAA0D;IAMhF,MAAM,OAAO,GAAG,YAAY,YAAY,GAAG,CAAC,CAAC,CAAC,CAAC,GAAG,YAAY,CAAC,OAAO,EAAE,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,YAAY,CAAC,CAAA;IACxG,IAAI,SAAS,GAAG,EAAE,CAAA;IAClB,IAAI,SAAS,GAAG,CAAC,CAAA;IACjB,IAAI,KAAK,GAAG,CAAC,CAAA;IAEb,KAAK,MAAM,CAAC,KAAK,EAAE,KAAK,CAAC,IAAI,OAAO,EAAE,CAAC;QACtC,KAAK,IAAI,KAAK,CAAA;QAEd,IAAI,KAAK,GAAG,SAAS,EAAE,CAAC;YACvB,SAAS,GAAG,KAAK,CAAA;YACjB,SAAS,GAAG,KAAK,CAAA;QAClB,CAAC;IACF,CAAC;IAED,OAAO,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,UAAU,EAAE,KAAK,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,SAAS,GAAG,KAAK,EAAE,CAAA;AACtG,CAAC;AA+BD,SAAS,yBAAyB,CAAC,KAAiB,EAAE,MAAmB;IACxE,MAAM,KAAK,GAAoB,EAAE,CAAA;IAEjC,KAAK,MAAM,CAAC,KAAK,EAAE,aAAa,CAAC,IAAI,KAAK,CAAC,MAAM,EAAE,CAAC;QACnD,MAAM,cAAc,GAAG,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAA;QAE3C,IAAI,CAAC,cAAc;YAAE,SAAQ;QAC7B,MAAM,QAAQ,GAAG,aAAa,CAAC,aAAa,CAAC,CAAA;QAC7C,MAAM,SAAS,GAAG,aAAa,CAAC,cAAc,CAAC,CAAA;QAE/C,IACC,SAAS,CAAC,UAAU,IAAI,uBAAuB;YAC/C,QAAQ,CAAC,KAAK,KAAK,SAAS,CAAC,KAAK;YAClC,QAAQ,CAAC,KAAK,IAAI,eAAe;YACjC,SAAS,CAAC,KAAK,IAAI,gBAAgB,EAClC,CAAC;YACF,KAAK,CAAC,IAAI,CAAC;gBACV,KAAK,EAAE,sBAAsB;gBAC7B,QAAQ,EAAE,OAAO;gBACjB,KAAK;gBACL,UAAU,EAAE,QAAQ,CAAC,KAAK;gBAC1B,WAAW,EAAE,SAAS,CAAC,KAAK;gBAC5B,UAAU,EAAE,QAAQ,CAAC,KAAK;gBAC1B,WAAW,EAAE,SAAS,CAAC,KAAK;gBAC5B,MAAM,EAAE,UAAU,KAAK,wBAAwB,QAAQ,CAAC,KAAK,KAAK,QAAQ,CAAC,KAAK,IAAI,QAAQ,CAAC,KAAK,KAAK,CAAC,QAAQ,CAAC,UAAU,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,0BAA0B,SAAS,CAAC,KAAK,KAAK,SAAS,CAAC,KAAK,IAAI,SAAS,CAAC,KAAK,KAAK,CAAC,SAAS,CAAC,UAAU,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,KAAK;aAC9Q,CAAC,CAAA;QACH,CAAC;IACF,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC;AAED,SAAS,gBAAgB,CAAC,KAAiB,EAAE,MAAmB;IAC/D,MAAM,KAAK,GAAoB,EAAE,CAAA;IAEjC,KAAK,MAAM,CAAC,KAAK,EAAE,aAAa,CAAC,IAAI,KAAK,CAAC,MAAM,EAAE,CAAC;QACnD,MAAM,cAAc,GAAG,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAA;QAE3C,IAAI,CAAC,cAAc;YAAE,SAAQ;QAC7B,MAAM,WAAW,GAAG,MAAM,CAAC,MAAM,CAAC,cAAc,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC,CAAA;QAE5E,IAAI,WAAW,GAAG,uBAAuB;YAAE,SAAQ;QAEnD,KAAK,MAAM,CAAC,KAAK,EAAE,UAAU,CAAC,IAAI,aAAa,EAAE,CAAC;YACjD,IAAI,UAAU,GAAG,sBAAsB;gBAAE,SAAQ;YAEjD,IAAI,cAAc,CAAC,KAAK,CAAC,KAAK,SAAS,IAAI,cAAc,CAAC,KAAK,CAAC,KAAK,CAAC,EAAE,CAAC;gBACxE,KAAK,CAAC,IAAI,CAAC;oBACV,KAAK,EAAE,cAAc;oBACrB,QAAQ,EAAE,OAAO;oBACjB,KAAK;oBACL,UAAU,EAAE,KAAK;oBACjB,UAAU;oBACV,WAAW,EAAE,WAAW;oBACxB,MAAM,EAAE,UAAU,KAAK,sBAAsB,KAAK,IAAI,UAAU,2BAA2B,WAAW,6DAA6D;iBACnK,CAAC,CAAA;YACH,CAAC;QACF,CAAC;IACF,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC;AAED,SAAS,qBAAqB,CAAC,KAAiB,EAAE,MAAmB;IACpE,MAAM,KAAK,GAAoB,EAAE,CAAA;IAEjC,KAAK,MAAM,CAAC,MAAM,EAAE,aAAa,CAAC,IAAI,KAAK,CAAC,OAAO,EAAE,CAAC;QACrD,MAAM,cAAc,GAAG,MAAM,CAAC,OAAO,CAAC,MAAM,CAAC,CAAA;QAE7C,IAAI,CAAC,cAAc;YAAE,SAAQ;QAC7B,MAAM,QAAQ,GAAG,aAAa,CAAC,aAAa,CAAC,CAAA;QAC7C,MAAM,SAAS,GAAG,aAAa,CAAC,cAAc,CAAC,CAAA;QAE/C,IACC,QAAQ,CAAC,KAAK,KAAK,SAAS,CAAC,KAAK;YAClC,QAAQ,CAAC,KAAK,IAAI,gBAAgB;YAClC,SAAS,CAAC,KAAK,IAAI,gBAAgB,EAClC,CAAC;YACF,MAAM,YAAY,GAAG,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;YAChD,MAAM,gBAAgB,GAAG,QAAQ,CAAC,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;YAC9D,MAAM,iBAAiB,GAAG,SAAS,CAAC,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;YAEhE,KAAK,CAAC,IAAI,CAAC;gBACV,KAAK,EAAE,kBAAkB;gBACzB,QAAQ,EAAE,OAAO;gBACjB,MAAM,EAAE,YAAY;gBACpB,UAAU,EAAE,gBAAgB;gBAC5B,WAAW,EAAE,iBAAiB;gBAC9B,UAAU,EAAE,QAAQ,CAAC,KAAK;gBAC1B,WAAW,EAAE,SAAS,CAAC,KAAK;gBAC5B,MAAM,EAAE,WAAW,YAAY,6BAA6B,gBAAgB,MAAM,QAAQ,CAAC,KAAK,+BAA+B,iBAAiB,MAAM,SAAS,CAAC,KAAK,sDAAsD;aAC3N,CAAC,CAAA;QACH,CAAC;IACF,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC;AAED,SAAS,UAAU,CAAC,KAAiB,EAAE,SAAwB;IAC9D,MAAM,KAAK,GAAoB,EAAE,CAAA;IAEjC,MAAM,QAAQ,GAAG,SAAS,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC;QAC5C,IAAI,EAAE,CAAC;QACP,KAAK,EAAE,IAAI,MAAM,CAAC,CAAC,CAAC,OAAO,EAAE,CAAC,CAAC,sBAAsB,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC;KACjE,CAAC,CAAC,CAAA;IAEH,KAAK,MAAM,CAAC,KAAK,EAAE,QAAQ,CAAC,IAAI,KAAK,CAAC,MAAM,EAAE,CAAC;QAC9C,KAAK,MAAM,EAAE,IAAI,EAAE,KAAK,EAAE,IAAI,QAAQ,EAAE,CAAC;YACxC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC;gBAAE,SAAQ;YAEhC,KAAK,MAAM,CAAC,KAAK,EAAE,KAAK,CAAC,IAAI,QAAQ,EAAE,CAAC;gBACvC,IAAI,IAAI,CAAC,gBAAgB,CAAC,QAAQ,CAAC,KAAK,CAAC,IAAI,KAAK,IAAI,gCAAgC,EAAE,CAAC;oBACxF,KAAK,CAAC,IAAI,CAAC;wBACV,KAAK,EAAE,mBAAmB;wBAC1B,QAAQ,EAAE,IAAI,CAAC,QAAQ;wBACvB,MAAM,EAAE,IAAI,CAAC,EAAE;wBACf,KAAK;wBACL,UAAU,EAAE,KAAK;wBACjB,UAAU,EAAE,KAAK;wBACjB,MAAM,EAAE,UAAU,KAAK,kBAAkB,IAAI,CAAC,EAAE,mBAAmB,KAAK,IAAI,KAAK,2BAA2B,IAAI,CAAC,OAAO,EAAE;qBAC1H,CAAC,CAAA;gBACH,CAAC;YACF,CAAC;QACF,CAAC;IACF,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC;AAED,SAAS,WAAW,CAAC,KAAiB;IACrC,MAAM,KAAK,GAAoB,EAAE,CAAA;IAEjC,IAAI,KAAK,CAAC,aAAa,GAAG,CAAC,EAAE,CAAC;QAC7B,KAAK,CAAC,IAAI,CAAC;YACV,KAAK,EAAE,gBAAgB;YACvB,QAAQ,EAAE,OAAO;YACjB,MAAM,EAAE,GAAG,KAAK,CAAC,aAAa,uEAAuE;SACrG,CAAC,CAAA;IACH,CAAC;IAED,MAAM,SAAS,GAAG,KAAK,CAAC,QAAQ,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,KAAK,CAAC,QAAQ,CAAC,CAAA;IAE9D,IAAI,SAAS,IAAI,mBAAmB,EAAE,CAAC;QACtC,KAAK,CAAC,IAAI,CAAC;YACV,KAAK,EAAE,aAAa;YACpB,QAAQ,EAAE,MAAM;YAChB,MAAM,EAAE,GAAG,KAAK,CAAC,QAAQ,IAAI,KAAK,CAAC,QAAQ,UAAU,CAAC,SAAS,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,yDAAyD;SAC1I,CAAC,CAAA;IACH,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC;AAED,SAAS,YAAY,CACpB,IAAiE,EACjE,KAAiB,EACjB,KAAsB;IAEtB,MAAM,MAAM,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,OAAO,CAAC,CAAA;IAC1D,MAAM,KAAK,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,MAAM,CAAC,CAAA;IACxD,MAAM,OAAO,GAAG,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,eAAe,CAAA;IAE/D,MAAM,KAAK,GAAa;QACvB,kBAAkB,OAAO,EAAE;QAC3B,EAAE;QACF,kBAAkB,IAAI,CAAC,SAAS,IAAI;QACpC,yBAAyB,IAAI,CAAC,SAAS,IAAI;QAC3C,kBAAkB,IAAI,CAAC,SAAS,IAAI;QACpC,qBAAqB,KAAK,CAAC,QAAQ,EAAE;QACrC,wBAAwB,KAAK,CAAC,MAAM,CAAC,IAAI,EAAE;QAC3C,yBAAyB,KAAK,CAAC,OAAO,CAAC,IAAI,EAAE;QAC7C,EAAE;QACF,eAAe,MAAM,CAAC,MAAM,kFAAkF;QAC9G,iBAAiB,KAAK,CAAC,MAAM,aAAa;QAC1C,EAAE;KACF,CAAA;IAED,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,CAAC;QACnB,KAAK,CAAC,IAAI,CAAC,wBAAwB,CAAC,CAAA;QAEpC,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;IACxB,CAAC;IAED,MAAM,OAAO,GAAG,IAAI,GAAG,EAA2B,CAAA;IAElD,KAAK,MAAM,CAAC,IAAI,KAAK,EAAE,CAAC;QACvB,MAAM,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,KAAK,CAAC,IAAI,EAAE,CAAA;QACtC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QACX,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,KAAK,EAAE,GAAG,CAAC,CAAA;IAC1B,CAAC;IAED,KAAK,MAAM,CAAC,KAAK,EAAE,IAAI,CAAC,IAAI,OAAO,EAAE,CAAC;QACrC,KAAK,CAAC,IAAI,CAAC,MAAM,KAAK,KAAK,IAAI,CAAC,MAAM,GAAG,CAAC,CAAA;QAC1C,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAA;QACd,wDAAwD;QACxD,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,UAAU,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,UAAU,IAAI,CAAC,CAAC,CAAC,CAAA;QAE9D,KAAK,MAAM,CAAC,IAAI,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,EAAE,CAAC,EAAE,CAAC;YACnC,KAAK,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,QAAQ,CAAC,WAAW,EAAE,OAAO,CAAC,CAAC,MAAM,EAAE,CAAC,CAAA;QAC9D,CAAC;QAED,IAAI,IAAI,CAAC,MAAM,GAAG,mBAAmB,EAAE,CAAC;YACvC,KAAK,CAAC,IAAI,CAAC,aAAa,IAAI,CAAC,MAAM,GAAG,EAAE,OAAO,CAAC,CAAA;QACjD,CAAC;QAED,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAA;IACf,CAAC;IAED,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;AACxB,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,eAAe,CACpC,OAA+B,EAC/B,MAA+B;IAE/B,MAAM,SAAS,GAAG,OAAO,CAAC,SAAS,IAAI,gBAAgB,EAAE,CAAA;IACzD,MAAM,EAAE,CAAC,6BAA6B,OAAO,CAAC,SAAS,KAAK,CAAC,CAAA;IAC7D,MAAM,MAAM,GAAG,MAAM,iBAAiB,CAAc,OAAO,CAAC,SAAS,CAAC,CAAA;IAEtE,MAAM,EAAE,CACP,KAAK,MAAM,CAAC,SAAS,cAAc,MAAM,CAAC,WAAW,CAAC,MAAM,cAAc,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,MAAM,YAAY,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,MAAM,UAAU,CACnK,CAAA;IAED,MAAM,EAAE,CAAC,sBAAsB,OAAO,CAAC,SAAS,KAAK,CAAC,CAAA;IAEtD,MAAM,KAAK,GAAG,MAAM,cAAc,CAAC,oBAAoB,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC,CAAA;IAE3E,MAAM,EAAE,CAAC,KAAK,KAAK,CAAC,QAAQ,OAAO,CAAC,CAAA;IAEpC,MAAM,EAAE,CAAC,sBAAsB,SAAS,KAAK,CAAC,CAAA;IAC9C,MAAM,SAAS,GAAG,MAAM,iBAAiB,CAAgB,SAAS,CAAC,CAAA;IAEnE,MAAM,EAAE,CAAC,mBAAmB,CAAC,CAAA;IAE7B,MAAM,KAAK,GAAoB;QAC9B,GAAG,yBAAyB,CAAC,KAAK,EAAE,MAAM,CAAC;QAC3C,GAAG,gBAAgB,CAAC,KAAK,EAAE,MAAM,CAAC;QAClC,GAAG,qBAAqB,CAAC,KAAK,EAAE,MAAM,CAAC;QACvC,GAAG,UAAU,CAAC,KAAK,EAAE,SAAS,CAAC;QAC/B,GAAG,WAAW,CAAC,KAAK,CAAC;KACrB,CAAA;IAED,MAAM,QAAQ,GAAG,YAAY,CAAC,EAAE,SAAS,EAAE,OAAO,CAAC,SAAS,EAAE,SAAS,EAAE,OAAO,CAAC,SAAS,EAAE,SAAS,EAAE,EAAE,KAAK,EAAE,KAAK,CAAC,CAAA;IAEtH,OAAO,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAA;IAErB,IAAI,OAAO,CAAC,KAAK,EAAE,CAAC;QACnB,MAAM,cAAc,CAAC,QAAQ,EAAE,OAAO,CAAC,KAAK,CAAC,CAAA;IAC9C,CAAC;IAED,IAAI,OAAO,CAAC,OAAO,EAAE,CAAC;QACrB,MAAM,kBAAkB,CACvB;YACC,KAAK,EAAE,OAAO,CAAC,SAAS;YACxB,KAAK,EAAE,OAAO,CAAC,SAAS;YACxB,KAAK;YACL,OAAO,EAAE;gBACR,MAAM,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,OAAO,CAAC,CAAC,MAAM;gBAC1D,QAAQ,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,MAAM,CAAC,CAAC,MAAM;aAC3D;SACD,EACD,OAAO,CAAC,OAAO,CACf,CAAA;IACF,CAAC;IAED,MAAM,UAAU,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,OAAO,CAAC,CAAC,MAAM,CAAA;IACrE,MAAM,YAAY,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,MAAM,CAAC,CAAC,MAAM,CAAA;IAEtE,IAAI,UAAU,GAAG,CAAC,EAAE,CAAC;QACpB,MAAM,EAAE,CAAC,gBAAgB,UAAU,YAAY,CAAC,CAAA;IACjD,CAAC;SAAM,CAAC;QACP,MAAM,EAAE,CAAC,cAAc,CAAC,CAAA;IACzB,CAAC;IAED,OAAO,EAAE,MAAM,EAAE,UAAU,EAAE,QAAQ,EAAE,YAAY,EAAE,QAAQ,EAAE,KAAK,EAAE,MAAM,EAAE,QAAQ,EAAE,CAAA;AACzF,CAAC"}
@@ -0,0 +1,39 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ *
6
+ * Assemble a corpus OVERLAY MANIFEST — generalized from assemble-fr-admin-split-overlay-manifest.
7
+ * ADDS one slice parquet to a base corpus, keeping every base slice VERBATIM (pure overlay ADD),
8
+ * and re-roots base paths to /data (the Modal volume). Parameterized by --slice-parquet +
9
+ * --source so it works for any overlay slice (the fr-admin-split one is the original; #148's
10
+ * overture-multilocale is the second user).
11
+ *
12
+ * Ported faithfully from scripts/assemble-overlay-manifest.py. The new slice's source_id column is
13
+ * read through DuckDB (`@duckdb/node-api`) instead of PyArrow; everything else is pure JSON.
14
+ *
15
+ * Pipeline (the recipe rides the result): node scripts/build-overture-multilocale-canonical.mjs
16
+ * --cap 150000 --out /tmp/ovl/overture-ml.canonical.jsonl node scripts/align-canonical-slice.ts
17
+ * --input <canonical> --output <labeled> --corpus-version 0.5.0 mailwoman dev jsonl-to-parquet
18
+ * --input <labeled> --output <NEW>/train/<slice-parquet> node
19
+ * scripts/assemble-overlay-manifest.ts --base <BASE>/MANIFEST.json --new-dir <NEW>\
20
+ * --modal-root /data/corpus/versioned/<ver>/<dir> --version <ver>\
21
+ * --slice-parquet <slice-parquet> --source <source> --note "..."
22
+ *
23
+ * # then push the overlay to R2 + sync + `modal run -d ... --config <recipe>.yaml --resume none`.
24
+ */
25
+ export interface OverlayManifestOptions {
26
+ base: string;
27
+ newDir: string;
28
+ modalRoot: string;
29
+ version: string;
30
+ sliceParquet: string;
31
+ source: string;
32
+ note: string;
33
+ }
34
+ /**
35
+ * Resolve a base manifest's slice path to the mounted corpus tree used by Modal.
36
+ */
37
+ export declare function rerootBaseSlicePath(path: string, baseManifestPath: string): string;
38
+ export declare function assembleOverlayManifest(args: OverlayManifestOptions): Promise<void>;
39
+ //# sourceMappingURL=overlay-manifest.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"overlay-manifest.d.ts","sourceRoot":"","sources":["../../lib/tools/overlay-manifest.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAwDH,MAAM,WAAW,sBAAsB;IACtC,IAAI,EAAE,MAAM,CAAA;IACZ,MAAM,EAAE,MAAM,CAAA;IACd,SAAS,EAAE,MAAM,CAAA;IACjB,OAAO,EAAE,MAAM,CAAA;IACf,YAAY,EAAE,MAAM,CAAA;IACpB,MAAM,EAAE,MAAM,CAAA;IACd,IAAI,EAAE,MAAM,CAAA;CACZ;AAED;;GAEG;AACH,wBAAgB,mBAAmB,CAAC,IAAI,EAAE,MAAM,EAAE,gBAAgB,EAAE,MAAM,GAAG,MAAM,CAalF;AAED,wBAAsB,uBAAuB,CAAC,IAAI,EAAE,sBAAsB,GAAG,OAAO,CAAC,IAAI,CAAC,CAwCzF"}
@@ -0,0 +1,90 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ *
6
+ * Assemble a corpus OVERLAY MANIFEST — generalized from assemble-fr-admin-split-overlay-manifest.
7
+ * ADDS one slice parquet to a base corpus, keeping every base slice VERBATIM (pure overlay ADD),
8
+ * and re-roots base paths to /data (the Modal volume). Parameterized by --slice-parquet +
9
+ * --source so it works for any overlay slice (the fr-admin-split one is the original; #148's
10
+ * overture-multilocale is the second user).
11
+ *
12
+ * Ported faithfully from scripts/assemble-overlay-manifest.py. The new slice's source_id column is
13
+ * read through DuckDB (`@duckdb/node-api`) instead of PyArrow; everything else is pure JSON.
14
+ *
15
+ * Pipeline (the recipe rides the result): node scripts/build-overture-multilocale-canonical.mjs
16
+ * --cap 150000 --out /tmp/ovl/overture-ml.canonical.jsonl node scripts/align-canonical-slice.ts
17
+ * --input <canonical> --output <labeled> --corpus-version 0.5.0 mailwoman dev jsonl-to-parquet
18
+ * --input <labeled> --output <NEW>/train/<slice-parquet> node
19
+ * scripts/assemble-overlay-manifest.ts --base <BASE>/MANIFEST.json --new-dir <NEW>\
20
+ * --modal-root /data/corpus/versioned/<ver>/<dir> --version <ver>\
21
+ * --slice-parquet <slice-parquet> --source <source> --note "..."
22
+ *
23
+ * # then push the overlay to R2 + sync + `modal run -d ... --config <recipe>.yaml --resume none`.
24
+ */
25
+ import { readLocalBuffer, readLocalJSONFile, statPath } from "@mailwoman/core/fs/readers";
26
+ import { writeLocalJSONFile } from "@mailwoman/core/fs/writers";
27
+ import { sha256Hex } from "@mailwoman/core/hash";
28
+ import { basename, dirname, join } from "path-ts";
29
+ import { connectDuckDB, escapeSQLString } from "#utils/parquet";
30
+ async function descriptor(localPath, modalPath, split, source) {
31
+ const db = await connectDuckDB();
32
+ const result = await db.runAndReadAll(`SELECT source_id FROM read_parquet('${escapeSQLString(localPath)}')`);
33
+ const sids = result.getRowObjects().map((r) => r.source_id);
34
+ return {
35
+ split,
36
+ path: modalPath,
37
+ format: "parquet",
38
+ compression: "SNAPPY",
39
+ rows: sids.length,
40
+ bytes: (await statPath(localPath)).size,
41
+ sha256: sha256Hex(await readLocalBuffer(localPath)),
42
+ first_source_id: sids[0],
43
+ last_source_id: sids.at(-1),
44
+ source,
45
+ };
46
+ }
47
+ /**
48
+ * Resolve a base manifest's slice path to the mounted corpus tree used by Modal.
49
+ */
50
+ export function rerootBaseSlicePath(path, baseManifestPath) {
51
+ const versionedIndex = path.indexOf("/corpus/versioned/");
52
+ if (versionedIndex !== -1)
53
+ return "/data" + path.slice(versionedIndex);
54
+ if (/^\/data\/(?:train|val|test)\//u.test(path)) {
55
+ const localBaseDir = dirname(baseManifestPath);
56
+ const baseModalRoot = `/data/corpus/versioned/${basename(dirname(localBaseDir))}/${basename(localBaseDir)}`;
57
+ return baseModalRoot + path.slice("/data".length);
58
+ }
59
+ return path;
60
+ }
61
+ export async function assembleOverlayManifest(args) {
62
+ const base = await readLocalJSONFile(args.base);
63
+ if (base.slices.some((s) => s.source === args.source)) {
64
+ console.log(`WARN: base already contains source '${args.source}' — is this the right base?`);
65
+ }
66
+ const kept = base.slices.map((s) => ({ ...s, path: rerootBaseSlicePath(s.path, args.base) }));
67
+ const newTrain = await descriptor(join(args.newDir, "train", args.sliceParquet), `${args.modalRoot}/train/${args.sliceParquet}`, "train", args.source);
68
+ const manifest = {
69
+ corpus_version: args.version,
70
+ overlay_base: base.corpus_version ?? null,
71
+ note: args.note || `${base.corpus_version} slices (all kept verbatim) + the ${args.source} slice. Pure overlay add.`,
72
+ schema: base.schema,
73
+ rows_per_slice: base.rows_per_slice,
74
+ row_group_size: base.row_group_size,
75
+ slices: [...kept, newTrain],
76
+ counts: {
77
+ train: base.counts.train + newTrain.rows,
78
+ val: base.counts.val,
79
+ test: base.counts.test,
80
+ },
81
+ total_rows: base.total_rows + newTrain.rows,
82
+ };
83
+ const out = join(args.newDir, "MANIFEST.json");
84
+ await writeLocalJSONFile(manifest, out);
85
+ console.log(`wrote ${out}`);
86
+ console.log(` slices: ${manifest.slices.length} (${kept.length} base kept, +1 ${args.source})`);
87
+ console.log(` counts: ${JSON.stringify(manifest.counts)} total: ${manifest.total_rows}`);
88
+ console.log(` ${args.source} train: ${newTrain.rows} rows (${newTrain.bytes} bytes)`);
89
+ }
90
+ //# sourceMappingURL=overlay-manifest.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"overlay-manifest.js","sourceRoot":"","sources":["../../lib/tools/overlay-manifest.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAEH,OAAO,EAAE,eAAe,EAAE,iBAAiB,EAAE,QAAQ,EAAE,MAAM,4BAA4B,CAAA;AACzF,OAAO,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAA;AAC/D,OAAO,EAAE,SAAS,EAAE,MAAM,sBAAsB,CAAA;AAChD,OAAO,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,SAAS,CAAA;AAEjD,OAAO,EAAE,aAAa,EAAE,eAAe,EAAE,MAAM,gBAAgB,CAAA;AAyB/D,KAAK,UAAU,UAAU,CACxB,SAAiB,EACjB,SAAiB,EACjB,KAAa,EACb,MAAc;IAEd,MAAM,EAAE,GAAG,MAAM,aAAa,EAAE,CAAA;IAChC,MAAM,MAAM,GAAG,MAAM,EAAE,CAAC,aAAa,CAAC,uCAAuC,eAAe,CAAC,SAAS,CAAC,IAAI,CAAC,CAAA;IAC5G,MAAM,IAAI,GAAG,MAAM,CAAC,aAAa,EAAE,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,SAAmB,CAAC,CAAA;IAErE,OAAO;QACN,KAAK;QACL,IAAI,EAAE,SAAS;QACf,MAAM,EAAE,SAAS;QACjB,WAAW,EAAE,QAAQ;QACrB,IAAI,EAAE,IAAI,CAAC,MAAM;QACjB,KAAK,EAAE,CAAC,MAAM,QAAQ,CAAC,SAAS,CAAC,CAAC,CAAC,IAAI;QACvC,MAAM,EAAE,SAAS,CAAC,MAAM,eAAe,CAAC,SAAS,CAAC,CAAC;QACnD,eAAe,EAAE,IAAI,CAAC,CAAC,CAAE;QACzB,cAAc,EAAE,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC,CAAE;QAC5B,MAAM;KACN,CAAA;AACF,CAAC;AAYD;;GAEG;AACH,MAAM,UAAU,mBAAmB,CAAC,IAAY,EAAE,gBAAwB;IACzE,MAAM,cAAc,GAAG,IAAI,CAAC,OAAO,CAAC,oBAAoB,CAAC,CAAA;IAEzD,IAAI,cAAc,KAAK,CAAC,CAAC;QAAE,OAAO,OAAO,GAAG,IAAI,CAAC,KAAK,CAAC,cAAc,CAAC,CAAA;IAEtE,IAAI,gCAAgC,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;QACjD,MAAM,YAAY,GAAG,OAAO,CAAC,gBAAgB,CAAC,CAAA;QAC9C,MAAM,aAAa,GAAG,0BAA0B,QAAQ,CAAC,OAAO,CAAC,YAAY,CAAC,CAAC,IAAI,QAAQ,CAAC,YAAY,CAAC,EAAE,CAAA;QAE3G,OAAO,aAAa,GAAG,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,MAAM,CAAC,CAAA;IAClD,CAAC;IAED,OAAO,IAAI,CAAA;AACZ,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,uBAAuB,CAAC,IAA4B;IACzE,MAAM,IAAI,GAAG,MAAM,iBAAiB,CAAe,IAAI,CAAC,IAAI,CAAC,CAAA;IAE7D,IAAI,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,KAAK,IAAI,CAAC,MAAM,CAAC,EAAE,CAAC;QACvD,OAAO,CAAC,GAAG,CAAC,uCAAuC,IAAI,CAAC,MAAM,6BAA6B,CAAC,CAAA;IAC7F,CAAC;IAED,MAAM,IAAI,GAAG,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,EAAE,GAAG,CAAC,EAAE,IAAI,EAAE,mBAAmB,CAAC,CAAC,CAAC,IAAI,EAAE,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAA;IAE7F,MAAM,QAAQ,GAAG,MAAM,UAAU,CAChC,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,OAAO,EAAE,IAAI,CAAC,YAAY,CAAC,EAC7C,GAAG,IAAI,CAAC,SAAS,UAAU,IAAI,CAAC,YAAY,EAAE,EAC9C,OAAO,EACP,IAAI,CAAC,MAAM,CACX,CAAA;IAED,MAAM,QAAQ,GAAG;QAChB,cAAc,EAAE,IAAI,CAAC,OAAO;QAC5B,YAAY,EAAE,IAAI,CAAC,cAAc,IAAI,IAAI;QACzC,IAAI,EACH,IAAI,CAAC,IAAI,IAAI,GAAG,IAAI,CAAC,cAAc,qCAAqC,IAAI,CAAC,MAAM,2BAA2B;QAC/G,MAAM,EAAE,IAAI,CAAC,MAAM;QACnB,cAAc,EAAE,IAAI,CAAC,cAAc;QACnC,cAAc,EAAE,IAAI,CAAC,cAAc;QACnC,MAAM,EAAE,CAAC,GAAG,IAAI,EAAE,QAAQ,CAAC;QAC3B,MAAM,EAAE;YACP,KAAK,EAAE,IAAI,CAAC,MAAM,CAAC,KAAK,GAAG,QAAQ,CAAC,IAAI;YACxC,GAAG,EAAE,IAAI,CAAC,MAAM,CAAC,GAAG;YACpB,IAAI,EAAE,IAAI,CAAC,MAAM,CAAC,IAAI;SACtB;QACD,UAAU,EAAE,IAAI,CAAC,UAAU,GAAG,QAAQ,CAAC,IAAI;KAC3C,CAAA;IAED,MAAM,GAAG,GAAG,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,eAAe,CAAC,CAAA;IAC9C,MAAM,kBAAkB,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAA;IAEvC,OAAO,CAAC,GAAG,CAAC,SAAS,GAAG,EAAE,CAAC,CAAA;IAC3B,OAAO,CAAC,GAAG,CAAC,aAAa,QAAQ,CAAC,MAAM,CAAC,MAAM,KAAK,IAAI,CAAC,MAAM,kBAAkB,IAAI,CAAC,MAAM,GAAG,CAAC,CAAA;IAChG,OAAO,CAAC,GAAG,CAAC,aAAa,IAAI,CAAC,SAAS,CAAC,QAAQ,CAAC,MAAM,CAAC,YAAY,QAAQ,CAAC,UAAU,EAAE,CAAC,CAAA;IAC1F,OAAO,CAAC,GAAG,CAAC,KAAK,IAAI,CAAC,MAAM,WAAW,QAAQ,CAAC,IAAI,UAAU,QAAQ,CAAC,KAAK,SAAS,CAAC,CAAA;AACvF,CAAC"}
@@ -0,0 +1,112 @@
1
+ /**
2
+ * @copyright Sister Software
3
+ * @license AGPL-3.0
4
+ * @author Teffen Ellis, et al.
5
+ *
6
+ * Overture Places source for the sub-venue lexicon (#35 wave 2) — read the sub-venue-bearing
7
+ * category slices of `poi.db` (spatial layer #1, `$MAILWOMAN_DATA_ROOT/poi/poi.db`) and yield
8
+ * {@link SubVenueHarvestRow}s the lexicon builder consumes exactly like an OSM extract.
9
+ *
10
+ * ── WHY OVERTURE AT ALL, when the OSM extractor already exists ────────────────────────────────────
11
+ * Wave 1 measured `concourse` at 21 real Overture rows against 4 in the whole Great Britain OSM
12
+ * extract, 3 of which are a street called CONCOURSE WAY. Overture's `airport_terminal` category is
13
+ * curated venue-interior naming; OSM's `aeroway=terminal` is a building footprint that usually
14
+ * carries the AIRPORT's name. The two sources fail differently, so both are read.
15
+ *
16
+ * ── THE CATEGORY SET IS MEASURED, NOT GUESSED ────────────────────────────────────────────────────
17
+ * A full scan of all 13,681,698 rows (2026-08-05, poi.db vintage 2026-05-20.0) counted, per
18
+ * category, how many named rows carry a designator token. The ranking is NOT what a category name
19
+ * predicts — `gas_station` leads the whole table with 12,996 hits, every one of them the token
20
+ * `station` inside "Holiday Station" / "Chevron Station Seward", and `shoe_store` contributes 708
21
+ * hits of `wing` because Red Wing sells boots. {@link OVERTURE_SUBVENUE_CATEGORIES} is the four
22
+ * categories whose hits survived reading the distribution; the rejects are listed below it so nobody
23
+ * re-proposes them.
24
+ *
25
+ * ── poi.db IS FOUR COUNTRIES ─────────────────────────────────────────────────────────────────────
26
+ * Measured the same day: US 11,521,612 / CA 794,418 / FR 721,352 / MX 644,316, and nothing else. The
27
+ * shipped layer is not a world gazetteer, so Overture can attest en-US, en-CA, fr-FR and es-MX
28
+ * surfaces and NOTHING ELSE. Every non-Latin designator the corpus task asks for — `ターミナル`,
29
+ * `Halle`, `Flügel` — has to come from the OSM leg. Do not read a zero count here as evidence of
30
+ * absence in the world; it is evidence of absence in four countries.
31
+ *
32
+ * ── The row shape fits; the PROVENANCE STAMP did not ─────────────────────────────────────────────
33
+ * Wave 1's `OSMSubVenueRow` was written to accept a non-OSM row, and it does: an Overture row is
34
+ * `{ designatorID, name }` with no `ref` and no `localizedNames`. What did NOT fit is
35
+ * `extractAttestedPhrases`, which hardcoded `osm:name` as the surface's `source`. Feeding Overture
36
+ * rows through it unchanged would have labelled every Overture surface as OSM-attested — a
37
+ * provenance lie, and under ODbL a consequential one. Hence the `source`/`region` options on that
38
+ * function and the source-neutral {@link SubVenueHarvestRow} name.
39
+ */
40
+ import type { SubVenueHarvestRow } from "#tools/sub-venue-lexicon";
41
+ /**
42
+ * Overture Places category → the designator its rows attest.
43
+ *
44
+ * Each entry carries the 2026-08-05 full-scan measurement in a comment: `rows` is the category's total, `hits` is how
45
+ * many of its named rows contain any designator token, and the token list is the top of that distribution.
46
+ *
47
+ * REJECTED, with the number that rejected them — do not re-add without a fresh census:
48
+ *
49
+ * - `gas_station` (12,996 hits) — all `station` inside a brand name (Holiday Station, Chevron Station Seward).
50
+ * - `fire_station` (10,377) — same, plus 330 `hall` from fire halls, which are venues rather than sub-venues.
51
+ * - `town_hall` (5,528) — `City Hall` is a whole building, the `venue` tier, not interior structure.
52
+ * - `building_supply_store` (4,030) — `building` inside "Allied Building Products".
53
+ * - `jehovahs_witness_place_of_worship` (2,334) — every hit is "Kingdom Hall of Jehovah's Witnesses".
54
+ * - `shoe_store` (909, of which 708 `wing`) — Red Wing. This one is a CONFOUND BOARD entry, not a source.
55
+ * - `college_university` (3,697) — 2,082 `campus`, but the row names the whole institution; `campus_building` is the
56
+ * interior slice and is kept instead.
57
+ * - `airport` (6,000 rows, 4,302 hits) — 4,071 of them are the token `airport` in the aerodrome's own name. Venue tier,
58
+ * already covered by OurAirports, and it drowns the interior signal.
59
+ * - `transport_interchange` (1 row), `rail_facility_or_service` (81 rows, 2 hits) — too small to matter.
60
+ * - `public_transit_facility_or_service` (2,274 rows, 185 hits) — 161 are `station` naming the station itself.
61
+ */
62
+ export declare const OVERTURE_SUBVENUE_CATEGORIES: Readonly<Record<string, string>>;
63
+ /**
64
+ * The layer's `source_vintage` — the Overture release the rows came from (`2026-05-20.0`), for the lexicon's
65
+ * `sources[]`.
66
+ *
67
+ * Read off the database rather than passed in, because a vintage a caller types is a vintage that goes stale silently.
68
+ * The layer-contract tables are part of every layer database by construction — see `docs/engineering/reference/
69
+ * layer-contract.mdx` — so there is no version of poi.db where this is absent.
70
+ */
71
+ export declare function readOvertureLayerVintage(databasePath: string): Promise<string>;
72
+ export interface ReadOvertureSubVenuesOptions {
73
+ /**
74
+ * Path to `poi.db`. Typically `dataRootPath("poi", "poi.db")`.
75
+ */
76
+ databasePath: string;
77
+ /**
78
+ * Category → designator map. Defaults to {@link OVERTURE_SUBVENUE_CATEGORIES}.
79
+ */
80
+ categories?: Readonly<Record<string, string>>;
81
+ /**
82
+ * Restrict to these ISO 3166-1 alpha-2 countries. Omit for all four the layer carries.
83
+ */
84
+ countries?: readonly string[];
85
+ }
86
+ /**
87
+ * One Overture row plus the country it came from — {@link SubVenueHarvestRow} widened by the field the layer has and an
88
+ * OSM extract does not (a Geofabrik extract's country is a property of the invocation, so OSM rows carry `country:
89
+ * ""`).
90
+ */
91
+ export interface OvertureSubVenueRow extends SubVenueHarvestRow {
92
+ /**
93
+ * ISO 3166-1 alpha-2, straight off the Overture partition.
94
+ */
95
+ country: string;
96
+ /**
97
+ * The Overture category the row was read from, so a surface's provenance survives past the designator.
98
+ */
99
+ category: string;
100
+ }
101
+ /**
102
+ * Read the sub-venue-bearing category slices of `poi.db`.
103
+ *
104
+ * Cold path, already async, no interface constraint — so Kysely, per the repo's inline-SQL rule.
105
+ *
106
+ * `category_id` is the SECOND component of poi.db's clustered `(h3_cell, category_id, …)` primary key, which reads like
107
+ * a full 13.7M-row scan and is not one: SQLite skip-scans the leading `h3_cell` and the whole four-category read
108
+ * returned 9,219 rows in **1.4 s** on the shipped layer (2026-08-05). A JS-side scan of every row to survey the same
109
+ * question took 52 s, which is the number to remember if you are tempted to filter in JS instead.
110
+ */
111
+ export declare function readOvertureSubVenues(options: ReadOvertureSubVenuesOptions): Promise<OvertureSubVenueRow[]>;
112
+ //# sourceMappingURL=overture-subvenue.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"overture-subvenue.d.ts","sourceRoot":"","sources":["../../lib/tools/overture-subvenue.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAsCG;AAIH,OAAO,KAAK,EAAE,kBAAkB,EAAE,MAAM,0BAA0B,CAAA;AAElE;;;;;;;;;;;;;;;;;;;;GAoBG;AACH,eAAO,MAAM,4BAA4B,EAAE,QAAQ,CAAC,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAczE,CAAA;AA0BD;;;;;;;GAOG;AACH,wBAAsB,wBAAwB,CAAC,YAAY,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,CAAC,CAUpF;AAED,MAAM,WAAW,4BAA4B;IAC5C;;OAEG;IACH,YAAY,EAAE,MAAM,CAAA;IACpB;;OAEG;IACH,UAAU,CAAC,EAAE,QAAQ,CAAC,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC,CAAA;IAC7C;;OAEG;IACH,SAAS,CAAC,EAAE,SAAS,MAAM,EAAE,CAAA;CAC7B;AAED;;;;GAIG;AACH,MAAM,WAAW,mBAAoB,SAAQ,kBAAkB;IAC9D;;OAEG;IACH,OAAO,EAAE,MAAM,CAAA;IACf;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAA;CAChB;AAED;;;;;;;;;GASG;AACH,wBAAsB,qBAAqB,CAAC,OAAO,EAAE,4BAA4B,GAAG,OAAO,CAAC,mBAAmB,EAAE,CAAC,CA0CjH"}