@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
@@ -1,49 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * Typed wrapper around `@dsnp/parquetjs`'s schema definition. Adds:
7
- *
8
- * - `ParquetSchema<T>`: a generic class narrowing the base schema's `schema` property to a
9
- * field-by-field typed dict.
10
- * - `ParquetSchemaDefinitionCache`: an LRU lookup so hot paths that compute the same schema
11
- * repeatedly pay the cost once. Implements `Disposable` so `using` works.
12
- * - `createBloomFilters<T>`: helper that takes a schema and a list of columns and returns the
13
- * `@dsnp/parquetjs`-shaped bloom-filter spec array.
14
- *
15
- * `Symbol.dispose` is sync (the original was async, but `Disposable`'s contract is sync — async
16
- * cleanup belongs on `AsyncDisposable`).
17
- */
18
- import { ParquetSchema as BaseParquetSchema } from "@dsnp/parquetjs";
19
- import type { createSBBFParams as BloomFilterCreation } from "@dsnp/parquetjs/dist/lib/bloomFilterIO/bloomFilterWriter.js";
20
- import type { FieldDefinition } from "@dsnp/parquetjs/dist/lib/declare.js";
21
- import { LRUCache } from "lru-cache";
22
- /**
23
- * A Parquet record-like object, i.e. a record with string keys and JSON-serializable values.
24
- */
25
- /**
26
- * Shape a row type must satisfy. Declare yours as a `type` alias — TypeScript gives an alias an implicit index
27
- * signature and an `interface` none, so an otherwise-identical interface does not satisfy this.
28
- */
29
- export type ParquetRecordLike = Record<string, unknown | undefined>;
30
- /**
31
- * Typed Parquet schema definition.
32
- */
33
- export type ParquetSchemaDefinition<T = ParquetRecordLike> = Record<Extract<keyof T, string>, FieldDefinition>;
34
- /**
35
- * Typed Parquet schema.
36
- */
37
- export declare class ParquetSchema<T> extends BaseParquetSchema {
38
- schema: ParquetSchemaDefinition<T>;
39
- }
40
- /**
41
- * Given a Parquet schema and a list of columns, create a list of Bloom filters for those columns.
42
- */
43
- export declare function createBloomFilters<T>(parquetSchemaDef: ParquetSchemaDefinition<T>, columns: Extract<keyof T, string>[]): BloomFilterCreation[];
44
- export declare class ParquetSchemaDefinitionCache extends LRUCache<ParquetSchemaDefinition<ParquetRecordLike>, ParquetSchema<ParquetRecordLike>> implements Disposable {
45
- constructor(max?: number);
46
- findOrCreateSchema<T extends ParquetRecordLike>(schemaDef: ParquetSchemaDefinition<T>): ParquetSchema<T>;
47
- [Symbol.dispose](): void;
48
- }
49
- //# sourceMappingURL=schema.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"schema.d.ts","sourceRoot":"","sources":["../../../src/parquet-wrapper/schema.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAEH,OAAO,EAAE,aAAa,IAAI,iBAAiB,EAAE,MAAM,iBAAiB,CAAA;AACpE,OAAO,KAAK,EAAE,gBAAgB,IAAI,mBAAmB,EAAE,MAAM,6DAA6D,CAAA;AAC1H,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,qCAAqC,CAAA;AAC1E,OAAO,EAAE,QAAQ,EAAE,MAAM,WAAW,CAAA;AAEpC;;GAEG;AACH;;;GAGG;AACH,MAAM,MAAM,iBAAiB,GAAG,MAAM,CAAC,MAAM,EAAE,OAAO,GAAG,SAAS,CAAC,CAAA;AAEnE;;GAEG;AACH,MAAM,MAAM,uBAAuB,CAAC,CAAC,GAAG,iBAAiB,IAAI,MAAM,CAAC,OAAO,CAAC,MAAM,CAAC,EAAE,MAAM,CAAC,EAAE,eAAe,CAAC,CAAA;AAE9G;;GAEG;AACH,qBAAa,aAAa,CAAC,CAAC,CAAE,SAAQ,iBAAiB;IAC9C,MAAM,EAAE,uBAAuB,CAAC,CAAC,CAAC,CAAA;CAC1C;AAED;;GAEG;AACH,wBAAgB,kBAAkB,CAAC,CAAC,EACnC,gBAAgB,EAAE,uBAAuB,CAAC,CAAC,CAAC,EAC5C,OAAO,EAAE,OAAO,CAAC,MAAM,CAAC,EAAE,MAAM,CAAC,EAAE,yBAanC;AAED,qBAAa,4BACZ,SAAQ,QAAQ,CAAC,uBAAuB,CAAC,iBAAiB,CAAC,EAAE,aAAa,CAAC,iBAAiB,CAAC,CAC7F,YAAW,UAAU;gBAET,GAAG,SAAO;IAIf,kBAAkB,CAAC,CAAC,SAAS,iBAAiB,EAAE,SAAS,EAAE,uBAAuB,CAAC,CAAC,CAAC,GAAG,aAAa,CAAC,CAAC,CAAC;IAYxG,CAAC,MAAM,CAAC,OAAO,CAAC;CAGvB"}
@@ -1,55 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * Typed wrapper around `@dsnp/parquetjs`'s schema definition. Adds:
7
- *
8
- * - `ParquetSchema<T>`: a generic class narrowing the base schema's `schema` property to a
9
- * field-by-field typed dict.
10
- * - `ParquetSchemaDefinitionCache`: an LRU lookup so hot paths that compute the same schema
11
- * repeatedly pay the cost once. Implements `Disposable` so `using` works.
12
- * - `createBloomFilters<T>`: helper that takes a schema and a list of columns and returns the
13
- * `@dsnp/parquetjs`-shaped bloom-filter spec array.
14
- *
15
- * `Symbol.dispose` is sync (the original was async, but `Disposable`'s contract is sync — async
16
- * cleanup belongs on `AsyncDisposable`).
17
- */
18
- import { ParquetSchema as BaseParquetSchema } from "@dsnp/parquetjs";
19
- import { LRUCache } from "lru-cache";
20
- /**
21
- * Typed Parquet schema.
22
- */
23
- export class ParquetSchema extends BaseParquetSchema {
24
- }
25
- /**
26
- * Given a Parquet schema and a list of columns, create a list of Bloom filters for those columns.
27
- */
28
- export function createBloomFilters(parquetSchemaDef, columns) {
29
- const bloomFilters = [];
30
- for (const column of columns) {
31
- if (!parquetSchemaDef[column]) {
32
- throw new Error(`Bloom filter column ${column} not found in Parquet schema`);
33
- }
34
- bloomFilters.push({ column });
35
- }
36
- return bloomFilters;
37
- }
38
- export class ParquetSchemaDefinitionCache extends LRUCache {
39
- constructor(max = 1000) {
40
- super({ max });
41
- }
42
- findOrCreateSchema(schemaDef) {
43
- const key = schemaDef;
44
- let schema = this.get(key);
45
- if (!schema) {
46
- schema = new ParquetSchema(schemaDef);
47
- this.set(key, schema);
48
- }
49
- return schema;
50
- }
51
- [Symbol.dispose]() {
52
- this.clear();
53
- }
54
- }
55
- //# sourceMappingURL=schema.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"schema.js","sourceRoot":"","sources":["../../../src/parquet-wrapper/schema.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAEH,OAAO,EAAE,aAAa,IAAI,iBAAiB,EAAE,MAAM,iBAAiB,CAAA;AAGpE,OAAO,EAAE,QAAQ,EAAE,MAAM,WAAW,CAAA;AAgBpC;;GAEG;AACH,MAAM,OAAO,aAAiB,SAAQ,iBAAiB;CAEtD;AAED;;GAEG;AACH,MAAM,UAAU,kBAAkB,CACjC,gBAA4C,EAC5C,OAAmC;IAEnC,MAAM,YAAY,GAA0B,EAAE,CAAA;IAE9C,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;QAC9B,IAAI,CAAC,gBAAgB,CAAC,MAAM,CAAC,EAAE,CAAC;YAC/B,MAAM,IAAI,KAAK,CAAC,uBAAuB,MAAM,8BAA8B,CAAC,CAAA;QAC7E,CAAC;QAED,YAAY,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,CAAC,CAAA;IAC9B,CAAC;IAED,OAAO,YAAY,CAAA;AACpB,CAAC;AAED,MAAM,OAAO,4BACZ,SAAQ,QAAsF;IAG9F,YAAY,GAAG,GAAG,IAAI;QACrB,KAAK,CAAC,EAAE,GAAG,EAAE,CAAC,CAAA;IACf,CAAC;IAEM,kBAAkB,CAA8B,SAAqC;QAC3F,MAAM,GAAG,GAAG,SAAuD,CAAA;QACnE,IAAI,MAAM,GAAG,IAAI,CAAC,GAAG,CAAC,GAAG,CAAiC,CAAA;QAE1D,IAAI,CAAC,MAAM,EAAE,CAAC;YACb,MAAM,GAAG,IAAI,aAAa,CAAI,SAAS,CAAC,CAAA;YACxC,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,MAA0C,CAAC,CAAA;QAC1D,CAAC;QAED,OAAO,MAAM,CAAA;IACd,CAAC;IAEM,CAAC,MAAM,CAAC,OAAO,CAAC;QACtB,IAAI,CAAC,KAAK,EAAE,CAAA;IACb,CAAC;CACD"}
@@ -1,46 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * Typed Parquet writer. Two static constructors mirror the base class:
7
- *
8
- * - `openStream`: wrap an existing writable stream.
9
- * - `openFile`: open a path on disk, ensuring the parent directory exists first.
10
- *
11
- * Implements `AsyncDisposable` so `await using writer = await ParquetWriter.openFile(...)` flushes
12
- * and closes cleanly. `close()` internally serializes against any in-flight flush so back-to-back
13
- * dispose calls don't race.
14
- */
15
- import { ParquetWriter as BaseParquetWriter } from "@dsnp/parquetjs";
16
- import type { WriterOptions } from "@dsnp/parquetjs/dist/lib/declare.js";
17
- import { type WriteStreamMinimal } from "@dsnp/parquetjs/dist/lib/util.js";
18
- import { type ParquetRecordLike, ParquetSchema, type ParquetSchemaDefinition, ParquetSchemaDefinitionCache } from "./schema.ts";
19
- /**
20
- * A typed Parquet writer, wrapping the base Parquet writer.
21
- */
22
- export declare class ParquetWriter<T extends ParquetRecordLike> extends BaseParquetWriter implements AsyncDisposable {
23
- #private;
24
- schema: ParquetSchema<T>;
25
- protected static readonly SchemaDefinitionCache: ParquetSchemaDefinitionCache;
26
- static openStream<T extends ParquetRecordLike>(schemaLike: ParquetSchema<T> | ParquetSchemaDefinition<T>, outputStream: WriteStreamMinimal, opts?: WriterOptions): Promise<ParquetWriter<T>>;
27
- /**
28
- * Convenience method to create a new buffered parquet writer that writes to the specified file.
29
- */
30
- static openFile<T extends ParquetRecordLike>(schemaLike: ParquetSchema<T> | ParquetSchemaDefinition<T>, sourcePath: string | Buffer | URL, opts?: WriterOptions): Promise<ParquetWriter<T>>;
31
- /**
32
- * Set a metadata key-value pair on the writer.
33
- */
34
- setMetadata(key: string, value: string): void;
35
- /**
36
- * Append a row to the buffer. If the buffer is full, the data will be written to disk.
37
- */
38
- appendRow(row: T): Promise<void>;
39
- /**
40
- * Flush all buffered data to disk, close the file, and release resources.
41
- */
42
- close(): Promise<void>;
43
- [Symbol.asyncDispose](): Promise<void>;
44
- dispose(): Promise<void>;
45
- }
46
- //# sourceMappingURL=writer.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"writer.d.ts","sourceRoot":"","sources":["../../../src/parquet-wrapper/writer.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;GAaG;AAKH,OAAO,EAAE,aAAa,IAAI,iBAAiB,EAAE,MAAM,iBAAiB,CAAA;AACpE,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,qCAAqC,CAAA;AACxE,OAAO,EAAU,KAAK,kBAAkB,EAAE,MAAM,kCAAkC,CAAA;AAGlF,OAAO,EACN,KAAK,iBAAiB,EACtB,aAAa,EACb,KAAK,uBAAuB,EAC5B,4BAA4B,EAC5B,MAAM,aAAa,CAAA;AAEpB;;GAEG;AACH,qBAAa,aAAa,CAAC,CAAC,SAAS,iBAAiB,CAAE,SAAQ,iBAAkB,YAAW,eAAe;;IACnG,MAAM,EAAE,aAAa,CAAC,CAAC,CAAC,CAAA;IAChC,SAAS,CAAC,MAAM,CAAC,QAAQ,CAAC,qBAAqB,+BAAqC;WAG9D,UAAU,CAAC,CAAC,SAAS,iBAAiB,EAC3D,UAAU,EAAE,aAAa,CAAC,CAAC,CAAC,GAAG,uBAAuB,CAAC,CAAC,CAAC,EACzD,YAAY,EAAE,kBAAkB,EAChC,IAAI,GAAE,aAAkB,GACtB,OAAO,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC;IAW5B;;OAEG;WACmB,QAAQ,CAAC,CAAC,SAAS,iBAAiB,EACzD,UAAU,EAAE,aAAa,CAAC,CAAC,CAAC,GAAG,uBAAuB,CAAC,CAAC,CAAC,EACzD,UAAU,EAAE,MAAM,GAAG,MAAM,GAAG,GAAG,EACjC,IAAI,CAAC,EAAE,aAAa,GAClB,OAAO,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC;IAW5B;;OAEG;IACa,WAAW,CAAC,GAAG,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,GAAG,IAAI;IAI7D;;OAEG;IACmB,SAAS,CAAC,GAAG,EAAE,CAAC,GAAG,OAAO,CAAC,IAAI,CAAC;IAItD;;OAEG;IACmB,KAAK,IAAI,OAAO,CAAC,IAAI,CAAC;IAc/B,CAAC,MAAM,CAAC,YAAY,CAAC;IAIrB,OAAO;CAGpB"}
@@ -1,76 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * Typed Parquet writer. Two static constructors mirror the base class:
7
- *
8
- * - `openStream`: wrap an existing writable stream.
9
- * - `openFile`: open a path on disk, ensuring the parent directory exists first.
10
- *
11
- * Implements `AsyncDisposable` so `await using writer = await ParquetWriter.openFile(...)` flushes
12
- * and closes cleanly. `close()` internally serializes against any in-flight flush so back-to-back
13
- * dispose calls don't race.
14
- */
15
- import * as fs from "node:fs/promises";
16
- import * as path from "node:path";
17
- import { ParquetWriter as BaseParquetWriter } from "@dsnp/parquetjs";
18
- import { osopen } from "@dsnp/parquetjs/dist/lib/util.js";
19
- import { ParquetEnvelopeWriter } from "@dsnp/parquetjs/dist/lib/writer.js";
20
- import { ParquetSchema, ParquetSchemaDefinitionCache, } from "./schema.js";
21
- /**
22
- * A typed Parquet writer, wrapping the base Parquet writer.
23
- */
24
- export class ParquetWriter extends BaseParquetWriter {
25
- static SchemaDefinitionCache = new ParquetSchemaDefinitionCache();
26
- #flushing = Promise.resolve();
27
- static async openStream(schemaLike, outputStream, opts = {}) {
28
- const schema = schemaLike instanceof ParquetSchema
29
- ? schemaLike
30
- : ParquetWriter.SchemaDefinitionCache.findOrCreateSchema(schemaLike);
31
- const envelopeWriter = await ParquetEnvelopeWriter.openStream(schema, outputStream, opts);
32
- return new ParquetWriter(schema, envelopeWriter, opts);
33
- }
34
- /**
35
- * Convenience method to create a new buffered parquet writer that writes to the specified file.
36
- */
37
- static async openFile(schemaLike, sourcePath, opts) {
38
- if (typeof sourcePath === "string") {
39
- await fs.mkdir(path.dirname(sourcePath), { recursive: true });
40
- }
41
- const outputStream = await osopen(sourcePath, opts);
42
- return ParquetWriter.openStream(schemaLike, outputStream, opts);
43
- }
44
- // @note This fixes invalid Markdown in the base class JSDoc.
45
- /**
46
- * Set a metadata key-value pair on the writer.
47
- */
48
- setMetadata(key, value) {
49
- return super.setMetadata(key, value);
50
- }
51
- /**
52
- * Append a row to the buffer. If the buffer is full, the data will be written to disk.
53
- */
54
- async appendRow(row) {
55
- return super.appendRow(row);
56
- }
57
- /**
58
- * Flush all buffered data to disk, close the file, and release resources.
59
- */
60
- async close() {
61
- await this.#flushing;
62
- if (this.closed)
63
- return;
64
- const { promise, resolve, reject } = Promise.withResolvers();
65
- super.close().then(resolve, reject);
66
- this.#flushing = promise;
67
- return this.#flushing;
68
- }
69
- async [Symbol.asyncDispose]() {
70
- return this.close();
71
- }
72
- async dispose() {
73
- return this[Symbol.asyncDispose]();
74
- }
75
- }
76
- //# sourceMappingURL=writer.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"writer.js","sourceRoot":"","sources":["../../../src/parquet-wrapper/writer.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;GAaG;AAEH,OAAO,KAAK,EAAE,MAAM,kBAAkB,CAAA;AACtC,OAAO,KAAK,IAAI,MAAM,WAAW,CAAA;AAEjC,OAAO,EAAE,aAAa,IAAI,iBAAiB,EAAE,MAAM,iBAAiB,CAAA;AAEpE,OAAO,EAAE,MAAM,EAA2B,MAAM,kCAAkC,CAAA;AAClF,OAAO,EAAE,qBAAqB,EAAE,MAAM,oCAAoC,CAAA;AAE1E,OAAO,EAEN,aAAa,EAEb,4BAA4B,GAC5B,MAAM,aAAa,CAAA;AAEpB;;GAEG;AACH,MAAM,OAAO,aAA2C,SAAQ,iBAAiB;IAEtE,MAAM,CAAU,qBAAqB,GAAG,IAAI,4BAA4B,EAAE,CAAA;IACpF,SAAS,GAAkB,OAAO,CAAC,OAAO,EAAE,CAAA;IAE5C,MAAM,CAAU,KAAK,CAAC,UAAU,CAC/B,UAAyD,EACzD,YAAgC,EAChC,OAAsB,EAAE;QAExB,MAAM,MAAM,GACX,UAAU,YAAY,aAAa;YAClC,CAAC,CAAC,UAAU;YACZ,CAAC,CAAC,aAAa,CAAC,qBAAqB,CAAC,kBAAkB,CAAC,UAAU,CAAC,CAAA;QAEtE,MAAM,cAAc,GAAG,MAAM,qBAAqB,CAAC,UAAU,CAAC,MAAM,EAAE,YAAY,EAAE,IAAI,CAAC,CAAA;QAEzF,OAAO,IAAI,aAAa,CAAI,MAAM,EAAE,cAAc,EAAE,IAAI,CAAC,CAAA;IAC1D,CAAC;IAED;;OAEG;IACH,MAAM,CAAU,KAAK,CAAC,QAAQ,CAC7B,UAAyD,EACzD,UAAiC,EACjC,IAAoB;QAEpB,IAAI,OAAO,UAAU,KAAK,QAAQ,EAAE,CAAC;YACpC,MAAM,EAAE,CAAC,KAAK,CAAC,IAAI,CAAC,OAAO,CAAC,UAAU,CAAC,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;QAC9D,CAAC;QAED,MAAM,YAAY,GAAG,MAAM,MAAM,CAAC,UAAU,EAAE,IAAI,CAAC,CAAA;QAEnD,OAAO,aAAa,CAAC,UAAU,CAAI,UAAU,EAAE,YAAY,EAAE,IAAI,CAAC,CAAA;IACnE,CAAC;IAED,6DAA6D;IAC7D;;OAEG;IACa,WAAW,CAAC,GAAW,EAAE,KAAa;QACrD,OAAO,KAAK,CAAC,WAAW,CAAC,GAAG,EAAE,KAAK,CAAC,CAAA;IACrC,CAAC;IAED;;OAEG;IACa,KAAK,CAAC,SAAS,CAAC,GAAM;QACrC,OAAO,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAA;IAC5B,CAAC;IAED;;OAEG;IACa,KAAK,CAAC,KAAK;QAC1B,MAAM,IAAI,CAAC,SAAS,CAAA;QAEpB,IAAI,IAAI,CAAC,MAAM;YAAE,OAAM;QAEvB,MAAM,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,EAAE,GAAG,OAAO,CAAC,aAAa,EAAQ,CAAA;QAElE,KAAK,CAAC,KAAK,EAAE,CAAC,IAAI,CAAC,OAAO,EAAE,MAAM,CAAC,CAAA;QAEnC,IAAI,CAAC,SAAS,GAAG,OAAO,CAAA;QAExB,OAAO,IAAI,CAAC,SAAS,CAAA;IACtB,CAAC;IAEM,KAAK,CAAC,CAAC,MAAM,CAAC,YAAY,CAAC;QACjC,OAAO,IAAI,CAAC,KAAK,EAAE,CAAA;IACpB,CAAC;IAEM,KAAK,CAAC,OAAO;QACnB,OAAO,IAAI,CAAC,MAAM,CAAC,YAAY,CAAC,EAAE,CAAA;IACnC,CAAC"}
@@ -1,126 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * Adapter runner — drives a `CorpusAdapter` to completion and writes intermediate JSONL + a
7
- * per-shard manifest.
8
- *
9
- * Output layout under `outputDir`:
10
- *
11
- * ```
12
- * <outputDir>/<adapter.id>/
13
- * canonical.jsonl # one row per line, in emission order
14
- * MANIFEST.json # adapter id, version, row count, sha256, license, started_at, ended_at
15
- * ```
16
- *
17
- * The runner is responsible for everything an adapter is **not** responsible for:
18
- *
19
- * - Stamping `corpus_version` on every row (adapters must NOT set it).
20
- * - Applying `canonicalDedupKey` and skipping duplicates.
21
- * - Streaming sha256 over JSONL bytes so the manifest checksum doesn't require a re-read.
22
- * - Honoring backpressure on the output write stream.
23
- * - Counting + emitting periodic progress to an optional callback.
24
- * - Honoring `signal` (delegates to adapter's iteration boundary).
25
- *
26
- * The runner does NOT perform alignment, tokenization, synthesis, or sharding into Parquet. Those
27
- * steps run later, consuming the JSONL shards this writes.
28
- */
29
- import { type AdapterRegistry } from "#adapters/utils";
30
- import type { AdapterOptions, CorpusAdapter } from "#types";
31
- /**
32
- * Snapshot of the runner's state, emitted on every progress tick.
33
- */
34
- export interface RunnerProgress {
35
- /**
36
- * Adapter being driven.
37
- */
38
- adapterID: string;
39
- /**
40
- * Total rows the adapter has yielded (before dedup).
41
- */
42
- yielded: number;
43
- /**
44
- * Rows actually written to JSONL (after dedup).
45
- */
46
- written: number;
47
- /**
48
- * Bytes written to JSONL so far.
49
- */
50
- bytes: number;
51
- /**
52
- * Wall-clock milliseconds since the run started.
53
- */
54
- elapsed_ms: number;
55
- }
56
- /**
57
- * Per-invocation options for `runAdapter`.
58
- */
59
- export interface RunAdapterOptions {
60
- /**
61
- * Adapter to drive.
62
- */
63
- adapter: CorpusAdapter;
64
- /**
65
- * Options handed to the adapter (input path, country filter, limit, signal).
66
- */
67
- adapterOptions: AdapterOptions;
68
- /**
69
- * Root output directory; the runner creates `<outputDir>/<adapter.id>/` under it.
70
- */
71
- outputDir: string;
72
- /**
73
- * Corpus version stamped onto every row. Locked together with the tokenizer version.
74
- */
75
- corpusVersion: string;
76
- /**
77
- * Optional progress callback. Invoked every `progressEvery` rows yielded (default 1000) and once at the end of the
78
- * run. Errors thrown from this callback abort the run.
79
- */
80
- onProgress?: (snapshot: RunnerProgress) => void;
81
- /**
82
- * Yielded-row interval at which `onProgress` fires. Defaults to 1000. The terminal tick is always emitted regardless
83
- * of this value.
84
- */
85
- progressEvery?: number;
86
- }
87
- /**
88
- * Return value of `runAdapter`: the same shape as `MANIFEST.json` on disk.
89
- */
90
- export interface AdapterRunManifest {
91
- adapter_id: string;
92
- corpus_version: string;
93
- default_license: string;
94
- description: string;
95
- yielded: number;
96
- written: number;
97
- deduped: number;
98
- bytes: number;
99
- sha256: string;
100
- jsonl_path: string;
101
- started_at: string;
102
- ended_at: string;
103
- elapsed_ms: number;
104
- }
105
- /**
106
- * Drive a single adapter to completion.
107
- *
108
- * Returns the manifest describing the run. Writes `canonical.jsonl` + `MANIFEST.json` under `outputDir/<adapter.id>/`.
109
- * Throws if the output directory cannot be created, if a row arrives with a missing required field, or if the abort
110
- * signal fires.
111
- */
112
- export declare function runAdapter(opts: RunAdapterOptions): Promise<AdapterRunManifest>;
113
- /**
114
- * Drive every adapter in a registry sequentially. Stops on the first failure (caller can filter the registry before
115
- * calling if partial-failure is desired).
116
- *
117
- * Returns the manifests in registry insertion order.
118
- */
119
- export declare function runAllAdapters(registry: AdapterRegistry, common: Omit<RunAdapterOptions, "adapter"> & {
120
- adapterOptionsFor?: (a: CorpusAdapter) => AdapterOptions;
121
- }): Promise<AdapterRunManifest[]>;
122
- /**
123
- * Convenience: ensure the parent directory of `filePath` exists.
124
- */
125
- export declare function ensureParentDir(filePath: string): Promise<void>;
126
- //# sourceMappingURL=runner.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"runner.d.ts","sourceRoot":"","sources":["../../src/runner.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;GA2BG;AAMH,OAAO,EAAsC,KAAK,eAAe,EAAwB,MAAM,iBAAiB,CAAA;AAChH,OAAO,KAAK,EAAE,cAAc,EAAgB,aAAa,EAAE,MAAM,QAAQ,CAAA;AAEzE;;GAEG;AACH,MAAM,WAAW,cAAc;IAC9B;;OAEG;IACH,SAAS,EAAE,MAAM,CAAA;IAEjB;;OAEG;IACH,OAAO,EAAE,MAAM,CAAA;IAEf;;OAEG;IACH,OAAO,EAAE,MAAM,CAAA;IAEf;;OAEG;IACH,KAAK,EAAE,MAAM,CAAA;IAEb;;OAEG;IACH,UAAU,EAAE,MAAM,CAAA;CAClB;AAED;;GAEG;AACH,MAAM,WAAW,iBAAiB;IACjC;;OAEG;IACH,OAAO,EAAE,aAAa,CAAA;IAEtB;;OAEG;IACH,cAAc,EAAE,cAAc,CAAA;IAE9B;;OAEG;IACH,SAAS,EAAE,MAAM,CAAA;IAEjB;;OAEG;IACH,aAAa,EAAE,MAAM,CAAA;IAErB;;;OAGG;IACH,UAAU,CAAC,EAAE,CAAC,QAAQ,EAAE,cAAc,KAAK,IAAI,CAAA;IAE/C;;;OAGG;IACH,aAAa,CAAC,EAAE,MAAM,CAAA;CACtB;AAED;;GAEG;AACH,MAAM,WAAW,kBAAkB;IAClC,UAAU,EAAE,MAAM,CAAA;IAClB,cAAc,EAAE,MAAM,CAAA;IACtB,eAAe,EAAE,MAAM,CAAA;IACvB,WAAW,EAAE,MAAM,CAAA;IACnB,OAAO,EAAE,MAAM,CAAA;IACf,OAAO,EAAE,MAAM,CAAA;IACf,OAAO,EAAE,MAAM,CAAA;IACf,KAAK,EAAE,MAAM,CAAA;IACb,MAAM,EAAE,MAAM,CAAA;IACd,UAAU,EAAE,MAAM,CAAA;IAClB,UAAU,EAAE,MAAM,CAAA;IAClB,QAAQ,EAAE,MAAM,CAAA;IAChB,UAAU,EAAE,MAAM,CAAA;CAClB;AAED;;;;;;GAMG;AACH,wBAAsB,UAAU,CAAC,IAAI,EAAE,iBAAiB,GAAG,OAAO,CAAC,kBAAkB,CAAC,CA2GrF;AAED;;;;;GAKG;AACH,wBAAsB,cAAc,CACnC,QAAQ,EAAE,eAAe,EACzB,MAAM,EAAE,IAAI,CAAC,iBAAiB,EAAE,SAAS,CAAC,GAAG;IAAE,iBAAiB,CAAC,EAAE,CAAC,CAAC,EAAE,aAAa,KAAK,cAAc,CAAA;CAAE,GACvG,OAAO,CAAC,kBAAkB,EAAE,CAAC,CAgB/B;AAgDD;;GAEG;AACH,wBAAsB,eAAe,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC,CAErE"}
package/out/src/runner.js DELETED
@@ -1,189 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * Adapter runner — drives a `CorpusAdapter` to completion and writes intermediate JSONL + a
7
- * per-shard manifest.
8
- *
9
- * Output layout under `outputDir`:
10
- *
11
- * ```
12
- * <outputDir>/<adapter.id>/
13
- * canonical.jsonl # one row per line, in emission order
14
- * MANIFEST.json # adapter id, version, row count, sha256, license, started_at, ended_at
15
- * ```
16
- *
17
- * The runner is responsible for everything an adapter is **not** responsible for:
18
- *
19
- * - Stamping `corpus_version` on every row (adapters must NOT set it).
20
- * - Applying `canonicalDedupKey` and skipping duplicates.
21
- * - Streaming sha256 over JSONL bytes so the manifest checksum doesn't require a re-read.
22
- * - Honoring backpressure on the output write stream.
23
- * - Counting + emitting periodic progress to an optional callback.
24
- * - Honoring `signal` (delegates to adapter's iteration boundary).
25
- *
26
- * The runner does NOT perform alignment, tokenization, synthesis, or sharding into Parquet. Those
27
- * steps run later, consuming the JSONL shards this writes.
28
- */
29
- import { createWriteStream } from "node:fs";
30
- import { mkdir, writeFile } from "node:fs/promises";
31
- import { dirname, join } from "node:path";
32
- import { canonicalDedupKey, streamingSha256 } from "#adapters/utils";
33
- /**
34
- * Drive a single adapter to completion.
35
- *
36
- * Returns the manifest describing the run. Writes `canonical.jsonl` + `MANIFEST.json` under `outputDir/<adapter.id>/`.
37
- * Throws if the output directory cannot be created, if a row arrives with a missing required field, or if the abort
38
- * signal fires.
39
- */
40
- export async function runAdapter(opts) {
41
- const { adapter, adapterOptions, outputDir, corpusVersion } = opts;
42
- const progressEvery = opts.progressEvery ?? 1000;
43
- const adapterDir = join(outputDir, adapter.id);
44
- await mkdir(adapterDir, { recursive: true });
45
- const jsonlPath = join(adapterDir, "canonical.jsonl");
46
- const manifestPath = join(adapterDir, "MANIFEST.json");
47
- const startedAt = new Date();
48
- const t0 = performance.now();
49
- const stream = createWriteStream(jsonlPath, { encoding: "utf8" });
50
- const hasher = streamingSha256();
51
- const seen = new Set();
52
- const DEDUP_MAX_SIZE = 10_000_000;
53
- let dedupExhausted = false;
54
- let yielded = 0;
55
- let written = 0;
56
- let bytes = 0;
57
- const emitProgress = () => {
58
- opts.onProgress?.({
59
- adapterID: adapter.id,
60
- yielded,
61
- written,
62
- bytes,
63
- elapsed_ms: performance.now() - t0,
64
- });
65
- };
66
- try {
67
- for await (const row of adapter.rows(adapterOptions)) {
68
- if (adapterOptions.signal?.aborted) {
69
- throw new DOMException("Adapter run aborted by signal", "AbortError");
70
- }
71
- yielded++;
72
- assertEmittedRow(adapter, row);
73
- const stamped = { ...row, corpus_version: corpusVersion };
74
- const key = canonicalDedupKey(stamped);
75
- if (!dedupExhausted) {
76
- if (seen.has(key)) {
77
- if (yielded % progressEvery === 0) {
78
- emitProgress();
79
- }
80
- continue;
81
- }
82
- if (seen.size >= DEDUP_MAX_SIZE) {
83
- dedupExhausted = true;
84
- process.stderr.write(` runner: dedup set full at ${DEDUP_MAX_SIZE.toLocaleString()} — skipping dedup for remaining rows\n`);
85
- }
86
- else {
87
- seen.add(key);
88
- }
89
- }
90
- const line = `${JSON.stringify(stamped)}\n`;
91
- hasher.update(line);
92
- bytes += Buffer.byteLength(line, "utf8");
93
- written++;
94
- if (!stream.write(line)) {
95
- await once(stream, "drain");
96
- }
97
- if (yielded % progressEvery === 0) {
98
- emitProgress();
99
- }
100
- }
101
- }
102
- finally {
103
- stream.end();
104
- await once(stream, "close");
105
- }
106
- const endedAt = new Date();
107
- const elapsed_ms = performance.now() - t0;
108
- emitProgress();
109
- const manifest = {
110
- adapter_id: adapter.id,
111
- corpus_version: corpusVersion,
112
- default_license: adapter.defaultLicense,
113
- description: adapter.description,
114
- yielded,
115
- written,
116
- deduped: yielded - written,
117
- bytes,
118
- sha256: hasher.digest(),
119
- jsonl_path: jsonlPath,
120
- started_at: startedAt.toISOString(),
121
- ended_at: endedAt.toISOString(),
122
- elapsed_ms,
123
- };
124
- await writeFile(manifestPath, `${JSON.stringify(manifest, null, 2)}\n`, "utf8");
125
- return manifest;
126
- }
127
- /**
128
- * Drive every adapter in a registry sequentially. Stops on the first failure (caller can filter the registry before
129
- * calling if partial-failure is desired).
130
- *
131
- * Returns the manifests in registry insertion order.
132
- */
133
- export async function runAllAdapters(registry, common) {
134
- const out = [];
135
- for (const adapter of registry.list()) {
136
- const adapterOptions = common.adapterOptionsFor?.(adapter) ?? common.adapterOptions;
137
- out.push(await runAdapter({
138
- ...common,
139
- adapter,
140
- adapterOptions,
141
- }));
142
- }
143
- return out;
144
- }
145
- /**
146
- * Validate an emitted row. Cheap; runs once per row. Catches adapter bugs early so the JSONL doesn't end up
147
- * half-malformed.
148
- */
149
- function assertEmittedRow(adapter, row) {
150
- if (row.source !== adapter.id) {
151
- throw new Error(`adapter ${adapter.id}: row.source must equal adapter.id (got ${JSON.stringify(row.source)})`);
152
- }
153
- if (!row.source_id) {
154
- throw new Error(`adapter ${adapter.id}: row.source_id is empty`);
155
- }
156
- if (!row.raw) {
157
- throw new Error(`adapter ${adapter.id}: row.raw is empty for source_id=${row.source_id}`);
158
- }
159
- if (!row.country) {
160
- throw new Error(`adapter ${adapter.id}: row.country is empty for source_id=${row.source_id}`);
161
- }
162
- if (!row.license) {
163
- throw new Error(`adapter ${adapter.id}: row.license is empty for source_id=${row.source_id}`);
164
- }
165
- }
166
- /**
167
- * Promise-ify a single event emission. Used to await `drain` / `close` on the write stream.
168
- */
169
- function once(emitter, event) {
170
- return new Promise((resolve, reject) => {
171
- const onEvent = () => {
172
- emitter.off("error", onError);
173
- resolve();
174
- };
175
- const onError = (err) => {
176
- emitter.off(event, onEvent);
177
- reject(err);
178
- };
179
- emitter.once(event, onEvent);
180
- emitter.once("error", onError);
181
- });
182
- }
183
- /**
184
- * Convenience: ensure the parent directory of `filePath` exists.
185
- */
186
- export async function ensureParentDir(filePath) {
187
- await mkdir(dirname(filePath), { recursive: true });
188
- }
189
- //# sourceMappingURL=runner.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"runner.js","sourceRoot":"","sources":["../../src/runner.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;GA2BG;AAEH,OAAO,EAAE,iBAAiB,EAAoB,MAAM,SAAS,CAAA;AAC7D,OAAO,EAAE,KAAK,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAA;AACnD,OAAO,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAEzC,OAAO,EAAE,iBAAiB,EAAE,eAAe,EAA8C,MAAM,iBAAiB,CAAA;AAyFhH;;;;;;GAMG;AACH,MAAM,CAAC,KAAK,UAAU,UAAU,CAAC,IAAuB;IACvD,MAAM,EAAE,OAAO,EAAE,cAAc,EAAE,SAAS,EAAE,aAAa,EAAE,GAAG,IAAI,CAAA;IAClE,MAAM,aAAa,GAAG,IAAI,CAAC,aAAa,IAAI,IAAI,CAAA;IAEhD,MAAM,UAAU,GAAG,IAAI,CAAC,SAAS,EAAE,OAAO,CAAC,EAAE,CAAC,CAAA;IAC9C,MAAM,KAAK,CAAC,UAAU,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;IAE5C,MAAM,SAAS,GAAG,IAAI,CAAC,UAAU,EAAE,iBAAiB,CAAC,CAAA;IACrD,MAAM,YAAY,GAAG,IAAI,CAAC,UAAU,EAAE,eAAe,CAAC,CAAA;IAEtD,MAAM,SAAS,GAAG,IAAI,IAAI,EAAE,CAAA;IAC5B,MAAM,EAAE,GAAG,WAAW,CAAC,GAAG,EAAE,CAAA;IAE5B,MAAM,MAAM,GAAG,iBAAiB,CAAC,SAAS,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,CAAC,CAAA;IACjE,MAAM,MAAM,GAAoB,eAAe,EAAE,CAAA;IACjD,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAA;IAC9B,MAAM,cAAc,GAAG,UAAU,CAAA;IACjC,IAAI,cAAc,GAAG,KAAK,CAAA;IAE1B,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,KAAK,GAAG,CAAC,CAAA;IAEb,MAAM,YAAY,GAAG,GAAS,EAAE;QAC/B,IAAI,CAAC,UAAU,EAAE,CAAC;YACjB,SAAS,EAAE,OAAO,CAAC,EAAE;YACrB,OAAO;YACP,OAAO;YACP,KAAK;YACL,UAAU,EAAE,WAAW,CAAC,GAAG,EAAE,GAAG,EAAE;SAClC,CAAC,CAAA;IACH,CAAC,CAAA;IAED,IAAI,CAAC;QACJ,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,OAAO,CAAC,IAAI,CAAC,cAAc,CAAC,EAAE,CAAC;YACtD,IAAI,cAAc,CAAC,MAAM,EAAE,OAAO,EAAE,CAAC;gBACpC,MAAM,IAAI,YAAY,CAAC,+BAA+B,EAAE,YAAY,CAAC,CAAA;YACtE,CAAC;YAED,OAAO,EAAE,CAAA;YACT,gBAAgB,CAAC,OAAO,EAAE,GAAG,CAAC,CAAA;YAE9B,MAAM,OAAO,GAAiB,EAAE,GAAG,GAAG,EAAE,cAAc,EAAE,aAAa,EAAE,CAAA;YACvE,MAAM,GAAG,GAAG,iBAAiB,CAAC,OAAO,CAAC,CAAA;YAEtC,IAAI,CAAC,cAAc,EAAE,CAAC;gBACrB,IAAI,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,EAAE,CAAC;oBACnB,IAAI,OAAO,GAAG,aAAa,KAAK,CAAC,EAAE,CAAC;wBACnC,YAAY,EAAE,CAAA;oBACf,CAAC;oBAED,SAAQ;gBACT,CAAC;gBAED,IAAI,IAAI,CAAC,IAAI,IAAI,cAAc,EAAE,CAAC;oBACjC,cAAc,GAAG,IAAI,CAAA;oBAErB,OAAO,CAAC,MAAM,CAAC,KAAK,CACnB,+BAA+B,cAAc,CAAC,cAAc,EAAE,wCAAwC,CACtG,CAAA;gBACF,CAAC;qBAAM,CAAC;oBACP,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;gBACd,CAAC;YACF,CAAC;YAED,MAAM,IAAI,GAAG,GAAG,IAAI,CAAC,SAAS,CAAC,OAAO,CAAC,IAAI,CAAA;YAC3C,MAAM,CAAC,MAAM,CAAC,IAAI,CAAC,CAAA;YACnB,KAAK,IAAI,MAAM,CAAC,UAAU,CAAC,IAAI,EAAE,MAAM,CAAC,CAAA;YAExC,OAAO,EAAE,CAAA;YAET,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC;gBACzB,MAAM,IAAI,CAAC,MAAM,EAAE,OAAO,CAAC,CAAA;YAC5B,CAAC;YAED,IAAI,OAAO,GAAG,aAAa,KAAK,CAAC,EAAE,CAAC;gBACnC,YAAY,EAAE,CAAA;YACf,CAAC;QACF,CAAC;IACF,CAAC;YAAS,CAAC;QACV,MAAM,CAAC,GAAG,EAAE,CAAA;QACZ,MAAM,IAAI,CAAC,MAAM,EAAE,OAAO,CAAC,CAAA;IAC5B,CAAC;IAED,MAAM,OAAO,GAAG,IAAI,IAAI,EAAE,CAAA;IAC1B,MAAM,UAAU,GAAG,WAAW,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;IACzC,YAAY,EAAE,CAAA;IAEd,MAAM,QAAQ,GAAuB;QACpC,UAAU,EAAE,OAAO,CAAC,EAAE;QACtB,cAAc,EAAE,aAAa;QAC7B,eAAe,EAAE,OAAO,CAAC,cAAc;QACvC,WAAW,EAAE,OAAO,CAAC,WAAW;QAChC,OAAO;QACP,OAAO;QACP,OAAO,EAAE,OAAO,GAAG,OAAO;QAC1B,KAAK;QACL,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE;QACvB,UAAU,EAAE,SAAS;QACrB,UAAU,EAAE,SAAS,CAAC,WAAW,EAAE;QACnC,QAAQ,EAAE,OAAO,CAAC,WAAW,EAAE;QAC/B,UAAU;KACV,CAAA;IAED,MAAM,SAAS,CAAC,YAAY,EAAE,GAAG,IAAI,CAAC,SAAS,CAAC,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,MAAM,CAAC,CAAA;IAE/E,OAAO,QAAQ,CAAA;AAChB,CAAC;AAED;;;;;GAKG;AACH,MAAM,CAAC,KAAK,UAAU,cAAc,CACnC,QAAyB,EACzB,MAAyG;IAEzG,MAAM,GAAG,GAAyB,EAAE,CAAA;IAEpC,KAAK,MAAM,OAAO,IAAI,QAAQ,CAAC,IAAI,EAAE,EAAE,CAAC;QACvC,MAAM,cAAc,GAAG,MAAM,CAAC,iBAAiB,EAAE,CAAC,OAAO,CAAC,IAAI,MAAM,CAAC,cAAc,CAAA;QAEnF,GAAG,CAAC,IAAI,CACP,MAAM,UAAU,CAAC;YAChB,GAAG,MAAM;YACT,OAAO;YACP,cAAc;SACd,CAAC,CACF,CAAA;IACF,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC;AAED;;;GAGG;AACH,SAAS,gBAAgB,CAAC,OAAsB,EAAE,GAAiB;IAClE,IAAI,GAAG,CAAC,MAAM,KAAK,OAAO,CAAC,EAAE,EAAE,CAAC;QAC/B,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,2CAA2C,IAAI,CAAC,SAAS,CAAC,GAAG,CAAC,MAAM,CAAC,GAAG,CAAC,CAAA;IAC/G,CAAC;IAED,IAAI,CAAC,GAAG,CAAC,SAAS,EAAE,CAAC;QACpB,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,0BAA0B,CAAC,CAAA;IACjE,CAAC;IAED,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC;QACd,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,oCAAoC,GAAG,CAAC,SAAS,EAAE,CAAC,CAAA;IAC1F,CAAC;IAED,IAAI,CAAC,GAAG,CAAC,OAAO,EAAE,CAAC;QAClB,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,wCAAwC,GAAG,CAAC,SAAS,EAAE,CAAC,CAAA;IAC9F,CAAC;IAED,IAAI,CAAC,GAAG,CAAC,OAAO,EAAE,CAAC;QAClB,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,wCAAwC,GAAG,CAAC,SAAS,EAAE,CAAC,CAAA;IAC9F,CAAC;AACF,CAAC;AAED;;GAEG;AACH,SAAS,IAAI,CAAC,OAAoB,EAAE,KAAwB;IAC3D,OAAO,IAAI,OAAO,CAAC,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE;QACtC,MAAM,OAAO,GAAG,GAAS,EAAE;YAC1B,OAAO,CAAC,GAAG,CAAC,OAAO,EAAE,OAAO,CAAC,CAAA;YAC7B,OAAO,EAAE,CAAA;QACV,CAAC,CAAA;QAED,MAAM,OAAO,GAAG,CAAC,GAAU,EAAQ,EAAE;YACpC,OAAO,CAAC,GAAG,CAAC,KAAK,EAAE,OAAO,CAAC,CAAA;YAC3B,MAAM,CAAC,GAAG,CAAC,CAAA;QACZ,CAAC,CAAA;QAED,OAAO,CAAC,IAAI,CAAC,KAAK,EAAE,OAAO,CAAC,CAAA;QAC5B,OAAO,CAAC,IAAI,CAAC,OAAO,EAAE,OAAO,CAAC,CAAA;IAC/B,CAAC,CAAC,CAAA;AACH,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,eAAe,CAAC,QAAgB;IACrD,MAAM,KAAK,CAAC,OAAO,CAAC,QAAQ,CAAC,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;AACpD,CAAC"}
@@ -1,20 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * `anchor-absorption` shard recipe (#220/#723, Probe A1) — self-generates `--count` rows from
7
- * {@link synthesizeAnchorAbsorptionRow}'s 6-slice mix (CASE-H / CASE-P-us-rural / CASE-P-de /
8
- * anchor-fp / locale-ambig / standard), aligns each to BIO, and emits a labeled JSONL. The
9
- * LEADING 5-digit on CASE-H/anchor-fp/locale-ambig is sampled from the REAL US ZIPs in the
10
- * postcode-anchor lookup, so the shaped-painted anchor fires on it exactly as inference does —
11
- * teaching the model to OVERRIDE a present anchor from context. Ported from
12
- * scripts/build-anchor-absorption-shard.mjs.
13
- */
14
- import { type ShardRecipe } from "./scaffold.ts";
15
- /**
16
- * Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
17
- * and `description` below for the surface form it generates.
18
- */
19
- export declare const anchorAbsorptionRecipe: ShardRecipe;
20
- //# sourceMappingURL=anchor-absorption.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"anchor-absorption.d.ts","sourceRoot":"","sources":["../../../src/shard-recipes/anchor-absorption.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;GAYG;AAUH,OAAO,EAA0B,KAAK,WAAW,EAAE,MAAM,eAAe,CAAA;AAwBxE;;;GAGG;AACH,eAAO,MAAM,sBAAsB,EAAE,WAoDpC,CAAA"}