@mailwoman/corpus 9.2.0 → 9.3.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (1241) hide show
  1. package/README.md +22 -22
  2. package/data/PROVENANCE.md +7 -7
  3. package/lib/adapters/ban/adapter.ts +190 -0
  4. package/lib/adapters/ban/street-decompose.ts +66 -0
  5. package/lib/adapters/fcc-bdc/adapter.ts +174 -0
  6. package/lib/adapters/geonames/adapter.ts +199 -0
  7. package/lib/adapters/geonames-postal/adapter.ts +122 -0
  8. package/lib/adapters/gnaf/adapter.ts +149 -0
  9. package/lib/adapters/gnaf/assemble.ts +225 -0
  10. package/lib/adapters/index.ts +153 -0
  11. package/lib/adapters/openaddresses/adapter.ts +251 -0
  12. package/lib/adapters/overture/adapter.ts +162 -0
  13. package/lib/adapters/state-hi-schools/adapter.ts +170 -0
  14. package/lib/adapters/state-hi-schools/workbook.ts +35 -0
  15. package/lib/adapters/synth-po-box/adapter.ts +204 -0
  16. package/lib/adapters/tiger/adapter.ts +252 -0
  17. package/lib/adapters/tiger/street-decompose.ts +83 -0
  18. package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +167 -0
  19. package/lib/adapters/usgov-imls-pls/adapter.ts +143 -0
  20. package/lib/adapters/usgov-irs-bmf/adapter.ts +151 -0
  21. package/lib/adapters/usgov-nad/adapter.ts +334 -0
  22. package/lib/adapters/usgov-nppes/adapter.ts +151 -0
  23. package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +193 -0
  24. package/lib/adapters/utils/index.ts +307 -0
  25. package/lib/adapters/wof-admin-jp/adapter.ts +214 -0
  26. package/lib/adapters/wof-admin-json/adapter.ts +231 -0
  27. package/lib/adapters/wof-json-rows.ts +129 -0
  28. package/lib/adapters/wof-postalcode-json/adapter.ts +176 -0
  29. package/lib/build.ts +378 -0
  30. package/lib/env.ts +50 -0
  31. package/lib/index.ts +13 -0
  32. package/lib/name-prone-us-suffixes.ts +12 -0
  33. package/lib/recipes/anchor-absorption.ts +101 -0
  34. package/lib/recipes/bare-country.ts +95 -0
  35. package/lib/recipes/boundary-stress.ts +100 -0
  36. package/lib/recipes/cn-organizational-units.ts +199 -0
  37. package/lib/recipes/country-balanced.ts +509 -0
  38. package/lib/recipes/cz-pcfirst-preposition.ts +111 -0
  39. package/lib/recipes/fr-admin-split.ts +242 -0
  40. package/lib/recipes/fr-bare-street.ts +170 -0
  41. package/lib/recipes/fr-fragment.ts +333 -0
  42. package/lib/recipes/fr-lieudit.ts +301 -0
  43. package/lib/recipes/fr-order.ts +245 -0
  44. package/lib/recipes/german.ts +359 -0
  45. package/lib/recipes/house-venue.ts +92 -0
  46. package/lib/recipes/index.ts +97 -0
  47. package/lib/recipes/intersection.ts +618 -0
  48. package/lib/recipes/locale.ts +599 -0
  49. package/lib/recipes/nl-postcode.ts +115 -0
  50. package/lib/recipes/no-fragment.ts +219 -0
  51. package/lib/recipes/no-street-led.ts +141 -0
  52. package/lib/recipes/no-street.ts +90 -0
  53. package/lib/recipes/po-box-cedex.ts +976 -0
  54. package/lib/recipes/po-box.ts +123 -0
  55. package/lib/recipes/reviewed-postcode-tail.ts +190 -0
  56. package/lib/recipes/scaffold.ts +469 -0
  57. package/lib/recipes/si-bare-village.ts +97 -0
  58. package/lib/recipes/street-affix.ts +804 -0
  59. package/lib/recipes/street-bare.ts +100 -0
  60. package/lib/recipes/street.ts +81 -0
  61. package/lib/recipes/sub-venue-sources.ts +877 -0
  62. package/lib/recipes/sub-venue.ts +997 -0
  63. package/lib/recipes/trailing-region.ts +183 -0
  64. package/lib/recipes/unit.ts +304 -0
  65. package/lib/runner.ts +312 -0
  66. package/lib/synthesizers/anchor-absorption.ts +288 -0
  67. package/lib/synthesizers/boundary-stress.ts +532 -0
  68. package/lib/synthesizers/german.ts +260 -0
  69. package/lib/synthesizers/house-venue.ts +308 -0
  70. package/lib/synthesizers/intersection.ts +233 -0
  71. package/lib/synthesizers/no-street.ts +327 -0
  72. package/lib/synthesizers/po-box.ts +323 -0
  73. package/lib/synthesizers/street.ts +269 -0
  74. package/lib/synthesizers/utils.ts +993 -0
  75. package/lib/test-kit/corpus-recipe.ts +86 -0
  76. package/lib/test-kit/index.ts +100 -0
  77. package/lib/tools/align-slice.ts +68 -0
  78. package/lib/tools/audit.ts +403 -0
  79. package/lib/tools/corpus-stats.ts +136 -0
  80. package/lib/tools/fetch/ban.ts +289 -0
  81. package/lib/tools/fetch/download.ts +262 -0
  82. package/lib/tools/fetch/geonames-dump.ts +257 -0
  83. package/lib/tools/fetch/geonames-postal.ts +180 -0
  84. package/lib/tools/fetch/hrsa.ts +59 -0
  85. package/lib/tools/fetch/imls-pls.ts +149 -0
  86. package/lib/tools/fetch/index.ts +147 -0
  87. package/lib/tools/fetch/nad.ts +341 -0
  88. package/lib/tools/fetch/nppes.ts +165 -0
  89. package/lib/tools/fetch/openaddresses.ts +347 -0
  90. package/lib/tools/fetch/ourairports.ts +170 -0
  91. package/lib/tools/fetch/ppd.ts +121 -0
  92. package/lib/tools/fetch/state-hi-schools.ts +161 -0
  93. package/lib/tools/fetch/state-sources.ts +146 -0
  94. package/lib/tools/fetch/tiger-full.ts +308 -0
  95. package/lib/tools/fetch/wikidata-subvenue.ts +384 -0
  96. package/lib/tools/golden-expand.ts +574 -0
  97. package/lib/tools/golden-promote.ts +337 -0
  98. package/lib/tools/golden-relabel-street.ts +683 -0
  99. package/lib/tools/index.ts +28 -0
  100. package/lib/tools/ingest-csv.ts +378 -0
  101. package/lib/tools/jsonl-to-parquet.ts +207 -0
  102. package/lib/tools/lint-slice-vocab.ts +388 -0
  103. package/lib/tools/lint-slice.ts +496 -0
  104. package/lib/tools/overlay-manifest.ts +148 -0
  105. package/lib/tools/overture-subvenue.ts +209 -0
  106. package/lib/tools/postcode-triples.ts +363 -0
  107. package/lib/tools/slice-kryptonite.ts +137 -0
  108. package/lib/tools/slice-translit.ts +218 -0
  109. package/lib/tools/sub-venue/harvest.ts +234 -0
  110. package/lib/tools/sub-venue/head-nouns.ts +245 -0
  111. package/lib/tools/sub-venue/surfaces.ts +95 -0
  112. package/lib/tools/sub-venue/table.ts +281 -0
  113. package/lib/tools/sub-venue/wikidata.ts +85 -0
  114. package/lib/tools/sub-venue-lexicon.ts +429 -0
  115. package/lib/tools/sub-venue-promotions.ts +330 -0
  116. package/lib/types.ts +247 -0
  117. package/lib/utils/align.ts +330 -0
  118. package/lib/utils/golden.ts +189 -0
  119. package/lib/utils/index.ts +14 -0
  120. package/lib/utils/parquet.ts +582 -0
  121. package/lib/utils/slice-stats.ts +95 -0
  122. package/lib/utils/split.ts +279 -0
  123. package/lib/utils/tokenize.ts +120 -0
  124. package/lib/utils/wof-json.ts +247 -0
  125. package/out/adapters/ban/adapter.d.ts.map +1 -0
  126. package/out/adapters/ban/adapter.js +149 -0
  127. package/out/adapters/ban/adapter.js.map +1 -0
  128. package/out/adapters/ban/street-decompose.d.ts.map +1 -0
  129. package/out/adapters/ban/street-decompose.js +51 -0
  130. package/out/adapters/ban/street-decompose.js.map +1 -0
  131. package/out/adapters/fcc-bdc/adapter.d.ts.map +1 -0
  132. package/out/adapters/fcc-bdc/adapter.js +144 -0
  133. package/out/adapters/fcc-bdc/adapter.js.map +1 -0
  134. package/out/adapters/geonames/adapter.d.ts.map +1 -0
  135. package/out/adapters/geonames/adapter.js +176 -0
  136. package/out/adapters/geonames/adapter.js.map +1 -0
  137. package/out/adapters/geonames-postal/adapter.d.ts +54 -0
  138. package/out/adapters/geonames-postal/adapter.d.ts.map +1 -0
  139. package/out/adapters/geonames-postal/adapter.js +107 -0
  140. package/out/adapters/geonames-postal/adapter.js.map +1 -0
  141. package/out/adapters/gnaf/adapter.d.ts +49 -0
  142. package/out/adapters/gnaf/adapter.d.ts.map +1 -0
  143. package/out/adapters/gnaf/adapter.js +124 -0
  144. package/out/adapters/gnaf/adapter.js.map +1 -0
  145. package/out/adapters/gnaf/assemble.d.ts +65 -0
  146. package/out/adapters/gnaf/assemble.d.ts.map +1 -0
  147. package/out/adapters/gnaf/assemble.js +154 -0
  148. package/out/adapters/gnaf/assemble.js.map +1 -0
  149. package/out/adapters/index.d.ts +51 -0
  150. package/out/adapters/index.d.ts.map +1 -0
  151. package/out/adapters/index.js +95 -0
  152. package/out/adapters/index.js.map +1 -0
  153. package/out/adapters/openaddresses/adapter.d.ts.map +1 -0
  154. package/out/adapters/openaddresses/adapter.js +186 -0
  155. package/out/adapters/openaddresses/adapter.js.map +1 -0
  156. package/out/adapters/overture/adapter.d.ts +48 -0
  157. package/out/adapters/overture/adapter.d.ts.map +1 -0
  158. package/out/adapters/overture/adapter.js +125 -0
  159. package/out/adapters/overture/adapter.js.map +1 -0
  160. package/out/adapters/state-hi-schools/adapter.d.ts +46 -0
  161. package/out/adapters/state-hi-schools/adapter.d.ts.map +1 -0
  162. package/out/adapters/state-hi-schools/adapter.js +145 -0
  163. package/out/adapters/state-hi-schools/adapter.js.map +1 -0
  164. package/out/adapters/state-hi-schools/workbook.d.ts +29 -0
  165. package/out/adapters/state-hi-schools/workbook.d.ts.map +1 -0
  166. package/out/adapters/state-hi-schools/workbook.js +20 -0
  167. package/out/adapters/state-hi-schools/workbook.js.map +1 -0
  168. package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
  169. package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
  170. package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
  171. package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
  172. package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
  173. package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
  174. package/out/adapters/synth-po-box/adapter.d.ts.map +1 -0
  175. package/out/adapters/synth-po-box/adapter.js +140 -0
  176. package/out/adapters/synth-po-box/adapter.js.map +1 -0
  177. package/out/adapters/tiger/adapter.d.ts +55 -0
  178. package/out/adapters/tiger/adapter.d.ts.map +1 -0
  179. package/out/adapters/tiger/adapter.js +201 -0
  180. package/out/adapters/tiger/adapter.js.map +1 -0
  181. package/out/adapters/tiger/street-decompose.d.ts.map +1 -0
  182. package/out/adapters/tiger/street-decompose.js +68 -0
  183. package/out/adapters/tiger/street-decompose.js.map +1 -0
  184. package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +56 -0
  185. package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -0
  186. package/out/adapters/usgov-hrsa-fqhc/adapter.js +132 -0
  187. package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -0
  188. package/out/adapters/usgov-imls-pls/adapter.d.ts +36 -0
  189. package/out/adapters/usgov-imls-pls/adapter.d.ts.map +1 -0
  190. package/out/adapters/usgov-imls-pls/adapter.js +114 -0
  191. package/out/adapters/usgov-imls-pls/adapter.js.map +1 -0
  192. package/out/adapters/usgov-irs-bmf/adapter.d.ts +37 -0
  193. package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -0
  194. package/out/adapters/usgov-irs-bmf/adapter.js +120 -0
  195. package/out/adapters/usgov-irs-bmf/adapter.js.map +1 -0
  196. package/out/adapters/usgov-nad/adapter.d.ts +48 -0
  197. package/out/adapters/usgov-nad/adapter.d.ts.map +1 -0
  198. package/out/adapters/usgov-nad/adapter.js +249 -0
  199. package/out/adapters/usgov-nad/adapter.js.map +1 -0
  200. package/out/adapters/usgov-nppes/adapter.d.ts.map +1 -0
  201. package/out/adapters/usgov-nppes/adapter.js +118 -0
  202. package/out/adapters/usgov-nppes/adapter.js.map +1 -0
  203. package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -0
  204. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +154 -0
  205. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -0
  206. package/out/adapters/utils/index.d.ts +191 -0
  207. package/out/adapters/utils/index.d.ts.map +1 -0
  208. package/out/adapters/utils/index.js +206 -0
  209. package/out/adapters/utils/index.js.map +1 -0
  210. package/out/adapters/wof-admin-jp/adapter.d.ts.map +1 -0
  211. package/out/adapters/wof-admin-jp/adapter.js +161 -0
  212. package/out/adapters/wof-admin-jp/adapter.js.map +1 -0
  213. package/out/adapters/wof-admin-json/adapter.d.ts +79 -0
  214. package/out/adapters/wof-admin-json/adapter.d.ts.map +1 -0
  215. package/out/adapters/wof-admin-json/adapter.js +197 -0
  216. package/out/adapters/wof-admin-json/adapter.js.map +1 -0
  217. package/out/adapters/wof-json-rows.d.ts +62 -0
  218. package/out/adapters/wof-json-rows.d.ts.map +1 -0
  219. package/out/adapters/wof-json-rows.js +83 -0
  220. package/out/adapters/wof-json-rows.js.map +1 -0
  221. package/out/adapters/wof-postalcode-json/adapter.d.ts +65 -0
  222. package/out/adapters/wof-postalcode-json/adapter.d.ts.map +1 -0
  223. package/out/adapters/wof-postalcode-json/adapter.js +151 -0
  224. package/out/adapters/wof-postalcode-json/adapter.js.map +1 -0
  225. package/out/build.d.ts +132 -0
  226. package/out/build.d.ts.map +1 -0
  227. package/out/build.js +245 -0
  228. package/out/build.js.map +1 -0
  229. package/out/codex/us-fips-state.d.ts.map +1 -0
  230. package/out/codex/us-fips-state.js.map +1 -0
  231. package/out/env.d.ts +46 -0
  232. package/out/env.d.ts.map +1 -0
  233. package/out/env.js +46 -0
  234. package/out/env.js.map +1 -0
  235. package/out/index.d.ts +13 -0
  236. package/out/index.d.ts.map +1 -0
  237. package/out/index.js +13 -0
  238. package/out/index.js.map +1 -0
  239. package/out/name-prone-us-suffixes.d.ts +12 -0
  240. package/out/name-prone-us-suffixes.d.ts.map +1 -0
  241. package/out/name-prone-us-suffixes.js +12 -0
  242. package/out/name-prone-us-suffixes.js.map +1 -0
  243. package/out/recipes/anchor-absorption.d.ts +20 -0
  244. package/out/recipes/anchor-absorption.d.ts.map +1 -0
  245. package/out/recipes/anchor-absorption.js +81 -0
  246. package/out/recipes/anchor-absorption.js.map +1 -0
  247. package/out/recipes/bare-country.d.ts +25 -0
  248. package/out/recipes/bare-country.d.ts.map +1 -0
  249. package/out/recipes/bare-country.js +87 -0
  250. package/out/recipes/bare-country.js.map +1 -0
  251. package/out/recipes/boundary-stress.d.ts +20 -0
  252. package/out/recipes/boundary-stress.d.ts.map +1 -0
  253. package/out/recipes/boundary-stress.js +83 -0
  254. package/out/recipes/boundary-stress.js.map +1 -0
  255. package/out/recipes/cn-organizational-units.d.ts +36 -0
  256. package/out/recipes/cn-organizational-units.d.ts.map +1 -0
  257. package/out/recipes/cn-organizational-units.js +159 -0
  258. package/out/recipes/cn-organizational-units.js.map +1 -0
  259. package/out/recipes/country-balanced.d.ts +32 -0
  260. package/out/recipes/country-balanced.d.ts.map +1 -0
  261. package/out/recipes/country-balanced.js +393 -0
  262. package/out/recipes/country-balanced.js.map +1 -0
  263. package/out/recipes/cz-pcfirst-preposition.d.ts +22 -0
  264. package/out/recipes/cz-pcfirst-preposition.d.ts.map +1 -0
  265. package/out/recipes/cz-pcfirst-preposition.js +100 -0
  266. package/out/recipes/cz-pcfirst-preposition.js.map +1 -0
  267. package/out/recipes/fr-admin-split.d.ts +38 -0
  268. package/out/recipes/fr-admin-split.d.ts.map +1 -0
  269. package/out/recipes/fr-admin-split.js +192 -0
  270. package/out/recipes/fr-admin-split.js.map +1 -0
  271. package/out/recipes/fr-bare-street.d.ts +28 -0
  272. package/out/recipes/fr-bare-street.d.ts.map +1 -0
  273. package/out/recipes/fr-bare-street.js +143 -0
  274. package/out/recipes/fr-bare-street.js.map +1 -0
  275. package/out/recipes/fr-fragment.d.ts +77 -0
  276. package/out/recipes/fr-fragment.d.ts.map +1 -0
  277. package/out/recipes/fr-fragment.js +276 -0
  278. package/out/recipes/fr-fragment.js.map +1 -0
  279. package/out/recipes/fr-lieudit.d.ts +32 -0
  280. package/out/recipes/fr-lieudit.d.ts.map +1 -0
  281. package/out/recipes/fr-lieudit.js +227 -0
  282. package/out/recipes/fr-lieudit.js.map +1 -0
  283. package/out/recipes/fr-order.d.ts +38 -0
  284. package/out/recipes/fr-order.d.ts.map +1 -0
  285. package/out/recipes/fr-order.js +197 -0
  286. package/out/recipes/fr-order.js.map +1 -0
  287. package/out/recipes/german.d.ts +44 -0
  288. package/out/recipes/german.d.ts.map +1 -0
  289. package/out/recipes/german.js +288 -0
  290. package/out/recipes/german.js.map +1 -0
  291. package/out/recipes/house-venue.d.ts +18 -0
  292. package/out/recipes/house-venue.d.ts.map +1 -0
  293. package/out/recipes/house-venue.js +73 -0
  294. package/out/recipes/house-venue.js.map +1 -0
  295. package/out/recipes/index.d.ts +24 -0
  296. package/out/recipes/index.d.ts.map +1 -0
  297. package/out/recipes/index.js +91 -0
  298. package/out/recipes/index.js.map +1 -0
  299. package/out/recipes/intersection.d.ts +42 -0
  300. package/out/recipes/intersection.d.ts.map +1 -0
  301. package/out/recipes/intersection.js +452 -0
  302. package/out/recipes/intersection.js.map +1 -0
  303. package/out/recipes/locale.d.ts +136 -0
  304. package/out/recipes/locale.d.ts.map +1 -0
  305. package/out/recipes/locale.js +460 -0
  306. package/out/recipes/locale.js.map +1 -0
  307. package/out/recipes/nl-postcode.d.ts +26 -0
  308. package/out/recipes/nl-postcode.d.ts.map +1 -0
  309. package/out/recipes/nl-postcode.js +102 -0
  310. package/out/recipes/nl-postcode.js.map +1 -0
  311. package/out/recipes/no-fragment.d.ts +43 -0
  312. package/out/recipes/no-fragment.d.ts.map +1 -0
  313. package/out/recipes/no-fragment.js +182 -0
  314. package/out/recipes/no-fragment.js.map +1 -0
  315. package/out/recipes/no-street-led.d.ts +24 -0
  316. package/out/recipes/no-street-led.d.ts.map +1 -0
  317. package/out/recipes/no-street-led.js +113 -0
  318. package/out/recipes/no-street-led.js.map +1 -0
  319. package/out/recipes/no-street.d.ts +18 -0
  320. package/out/recipes/no-street.d.ts.map +1 -0
  321. package/out/recipes/no-street.js +71 -0
  322. package/out/recipes/no-street.js.map +1 -0
  323. package/out/recipes/po-box-cedex.d.ts +38 -0
  324. package/out/recipes/po-box-cedex.d.ts.map +1 -0
  325. package/out/recipes/po-box-cedex.js +767 -0
  326. package/out/recipes/po-box-cedex.js.map +1 -0
  327. package/out/recipes/po-box.d.ts +17 -0
  328. package/out/recipes/po-box.d.ts.map +1 -0
  329. package/out/recipes/po-box.js +100 -0
  330. package/out/recipes/po-box.js.map +1 -0
  331. package/out/recipes/reviewed-postcode-tail.d.ts +47 -0
  332. package/out/recipes/reviewed-postcode-tail.d.ts.map +1 -0
  333. package/out/recipes/reviewed-postcode-tail.js +125 -0
  334. package/out/recipes/reviewed-postcode-tail.js.map +1 -0
  335. package/out/recipes/scaffold.d.ts +324 -0
  336. package/out/recipes/scaffold.d.ts.map +1 -0
  337. package/out/recipes/scaffold.js +186 -0
  338. package/out/recipes/scaffold.js.map +1 -0
  339. package/out/recipes/si-bare-village.d.ts +32 -0
  340. package/out/recipes/si-bare-village.d.ts.map +1 -0
  341. package/out/recipes/si-bare-village.js +88 -0
  342. package/out/recipes/si-bare-village.js.map +1 -0
  343. package/out/recipes/street-affix.d.ts +89 -0
  344. package/out/recipes/street-affix.d.ts.map +1 -0
  345. package/out/recipes/street-affix.js +563 -0
  346. package/out/recipes/street-affix.js.map +1 -0
  347. package/out/recipes/street-bare.d.ts +25 -0
  348. package/out/recipes/street-bare.d.ts.map +1 -0
  349. package/out/recipes/street-bare.js +86 -0
  350. package/out/recipes/street-bare.js.map +1 -0
  351. package/out/recipes/street.d.ts +15 -0
  352. package/out/recipes/street.d.ts.map +1 -0
  353. package/out/recipes/street.js +69 -0
  354. package/out/recipes/street.js.map +1 -0
  355. package/out/recipes/sub-venue-sources.d.ts +229 -0
  356. package/out/recipes/sub-venue-sources.d.ts.map +1 -0
  357. package/out/recipes/sub-venue-sources.js +653 -0
  358. package/out/recipes/sub-venue-sources.js.map +1 -0
  359. package/out/recipes/sub-venue.d.ts +269 -0
  360. package/out/recipes/sub-venue.d.ts.map +1 -0
  361. package/out/recipes/sub-venue.js +725 -0
  362. package/out/recipes/sub-venue.js.map +1 -0
  363. package/out/recipes/trailing-region.d.ts +74 -0
  364. package/out/recipes/trailing-region.d.ts.map +1 -0
  365. package/out/recipes/trailing-region.js +157 -0
  366. package/out/recipes/trailing-region.js.map +1 -0
  367. package/out/recipes/unit.d.ts +29 -0
  368. package/out/recipes/unit.d.ts.map +1 -0
  369. package/out/recipes/unit.js +230 -0
  370. package/out/recipes/unit.js.map +1 -0
  371. package/out/runner.d.ts +130 -0
  372. package/out/runner.d.ts.map +1 -0
  373. package/out/runner.js +185 -0
  374. package/out/runner.js.map +1 -0
  375. package/out/synthesizers/anchor-absorption.d.ts +63 -0
  376. package/out/synthesizers/anchor-absorption.d.ts.map +1 -0
  377. package/out/synthesizers/anchor-absorption.js +221 -0
  378. package/out/synthesizers/anchor-absorption.js.map +1 -0
  379. package/out/synthesizers/boundary-stress.d.ts +78 -0
  380. package/out/synthesizers/boundary-stress.d.ts.map +1 -0
  381. package/out/synthesizers/boundary-stress.js +455 -0
  382. package/out/synthesizers/boundary-stress.js.map +1 -0
  383. package/out/synthesizers/german.d.ts +115 -0
  384. package/out/synthesizers/german.d.ts.map +1 -0
  385. package/out/synthesizers/german.js +149 -0
  386. package/out/synthesizers/german.js.map +1 -0
  387. package/out/synthesizers/house-venue.d.ts +56 -0
  388. package/out/synthesizers/house-venue.d.ts.map +1 -0
  389. package/out/synthesizers/house-venue.js +247 -0
  390. package/out/synthesizers/house-venue.js.map +1 -0
  391. package/out/synthesizers/intersection.d.ts +52 -0
  392. package/out/synthesizers/intersection.d.ts.map +1 -0
  393. package/out/synthesizers/intersection.js +175 -0
  394. package/out/synthesizers/intersection.js.map +1 -0
  395. package/out/synthesizers/no-street.d.ts +72 -0
  396. package/out/synthesizers/no-street.d.ts.map +1 -0
  397. package/out/synthesizers/no-street.js +262 -0
  398. package/out/synthesizers/no-street.js.map +1 -0
  399. package/out/synthesizers/po-box.d.ts +108 -0
  400. package/out/synthesizers/po-box.d.ts.map +1 -0
  401. package/out/synthesizers/po-box.js +250 -0
  402. package/out/synthesizers/po-box.js.map +1 -0
  403. package/out/synthesizers/street.d.ts +54 -0
  404. package/out/synthesizers/street.d.ts.map +1 -0
  405. package/out/synthesizers/street.js +218 -0
  406. package/out/synthesizers/street.js.map +1 -0
  407. package/out/synthesizers/utils.d.ts +241 -0
  408. package/out/synthesizers/utils.d.ts.map +1 -0
  409. package/out/synthesizers/utils.js +776 -0
  410. package/out/synthesizers/utils.js.map +1 -0
  411. package/out/test-kit/corpus-recipe.d.ts +59 -0
  412. package/out/test-kit/corpus-recipe.d.ts.map +1 -0
  413. package/out/test-kit/corpus-recipe.js +39 -0
  414. package/out/test-kit/corpus-recipe.js.map +1 -0
  415. package/out/test-kit/index.d.ts +48 -0
  416. package/out/test-kit/index.d.ts.map +1 -0
  417. package/out/test-kit/index.js +78 -0
  418. package/out/test-kit/index.js.map +1 -0
  419. package/out/tools/align-slice.d.ts +7 -0
  420. package/out/tools/align-slice.d.ts.map +1 -0
  421. package/out/tools/align-slice.js +55 -0
  422. package/out/tools/align-slice.js.map +1 -0
  423. package/out/tools/audit.d.ts +29 -0
  424. package/out/tools/audit.d.ts.map +1 -0
  425. package/out/tools/audit.js +282 -0
  426. package/out/tools/audit.js.map +1 -0
  427. package/out/tools/corpus-stats.d.ts +44 -0
  428. package/out/tools/corpus-stats.d.ts.map +1 -0
  429. package/out/tools/corpus-stats.js +102 -0
  430. package/out/tools/corpus-stats.js.map +1 -0
  431. package/out/tools/fetch/ban.d.ts +31 -0
  432. package/out/tools/fetch/ban.d.ts.map +1 -0
  433. package/out/tools/fetch/ban.js +239 -0
  434. package/out/tools/fetch/ban.js.map +1 -0
  435. package/out/tools/fetch/download.d.ts +117 -0
  436. package/out/tools/fetch/download.d.ts.map +1 -0
  437. package/out/tools/fetch/download.js +160 -0
  438. package/out/tools/fetch/download.js.map +1 -0
  439. package/out/tools/fetch/geonames-dump.d.ts +91 -0
  440. package/out/tools/fetch/geonames-dump.d.ts.map +1 -0
  441. package/out/tools/fetch/geonames-dump.js +171 -0
  442. package/out/tools/fetch/geonames-dump.js.map +1 -0
  443. package/out/tools/fetch/geonames-postal.d.ts +76 -0
  444. package/out/tools/fetch/geonames-postal.d.ts.map +1 -0
  445. package/out/tools/fetch/geonames-postal.js +126 -0
  446. package/out/tools/fetch/geonames-postal.js.map +1 -0
  447. package/out/tools/fetch/hrsa.d.ts +18 -0
  448. package/out/tools/fetch/hrsa.d.ts.map +1 -0
  449. package/out/tools/fetch/hrsa.js +46 -0
  450. package/out/tools/fetch/hrsa.js.map +1 -0
  451. package/out/tools/fetch/imls-pls.d.ts +25 -0
  452. package/out/tools/fetch/imls-pls.d.ts.map +1 -0
  453. package/out/tools/fetch/imls-pls.js +108 -0
  454. package/out/tools/fetch/imls-pls.js.map +1 -0
  455. package/out/tools/fetch/index.d.ts +144 -0
  456. package/out/tools/fetch/index.d.ts.map +1 -0
  457. package/out/tools/fetch/index.js +143 -0
  458. package/out/tools/fetch/index.js.map +1 -0
  459. package/out/tools/fetch/nad.d.ts +70 -0
  460. package/out/tools/fetch/nad.d.ts.map +1 -0
  461. package/out/tools/fetch/nad.js +234 -0
  462. package/out/tools/fetch/nad.js.map +1 -0
  463. package/out/tools/fetch/nppes.d.ts +26 -0
  464. package/out/tools/fetch/nppes.d.ts.map +1 -0
  465. package/out/tools/fetch/nppes.js +126 -0
  466. package/out/tools/fetch/nppes.js.map +1 -0
  467. package/out/tools/fetch/openaddresses.d.ts +9 -0
  468. package/out/tools/fetch/openaddresses.d.ts.map +1 -0
  469. package/out/tools/fetch/openaddresses.js +279 -0
  470. package/out/tools/fetch/openaddresses.js.map +1 -0
  471. package/out/tools/fetch/ourairports.d.ts +45 -0
  472. package/out/tools/fetch/ourairports.d.ts.map +1 -0
  473. package/out/tools/fetch/ourairports.js +128 -0
  474. package/out/tools/fetch/ourairports.js.map +1 -0
  475. package/out/tools/fetch/ppd.d.ts.map +1 -0
  476. package/out/tools/fetch/ppd.js +85 -0
  477. package/out/tools/fetch/ppd.js.map +1 -0
  478. package/out/tools/fetch/state-hi-schools.d.ts +26 -0
  479. package/out/tools/fetch/state-hi-schools.d.ts.map +1 -0
  480. package/out/tools/fetch/state-hi-schools.js +112 -0
  481. package/out/tools/fetch/state-hi-schools.js.map +1 -0
  482. package/out/tools/fetch/state-sources.d.ts +26 -0
  483. package/out/tools/fetch/state-sources.d.ts.map +1 -0
  484. package/out/tools/fetch/state-sources.js +111 -0
  485. package/out/tools/fetch/state-sources.js.map +1 -0
  486. package/out/tools/fetch/tiger-full.d.ts +22 -0
  487. package/out/tools/fetch/tiger-full.d.ts.map +1 -0
  488. package/out/tools/fetch/tiger-full.js +217 -0
  489. package/out/tools/fetch/tiger-full.js.map +1 -0
  490. package/out/tools/fetch/wikidata-subvenue.d.ts +171 -0
  491. package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -0
  492. package/out/tools/fetch/wikidata-subvenue.js +274 -0
  493. package/out/tools/fetch/wikidata-subvenue.js.map +1 -0
  494. package/out/tools/gb-title-case.d.ts.map +1 -0
  495. package/out/tools/gb-title-case.js.map +1 -0
  496. package/out/tools/golden-expand.d.ts +90 -0
  497. package/out/tools/golden-expand.d.ts.map +1 -0
  498. package/out/tools/golden-expand.js +406 -0
  499. package/out/tools/golden-expand.js.map +1 -0
  500. package/out/tools/golden-promote.d.ts.map +1 -0
  501. package/out/tools/golden-promote.js +240 -0
  502. package/out/tools/golden-promote.js.map +1 -0
  503. package/out/tools/golden-relabel-street.d.ts +196 -0
  504. package/out/tools/golden-relabel-street.d.ts.map +1 -0
  505. package/out/tools/golden-relabel-street.js +440 -0
  506. package/out/tools/golden-relabel-street.js.map +1 -0
  507. package/out/tools/index.d.ts +28 -0
  508. package/out/tools/index.d.ts.map +1 -0
  509. package/out/tools/index.js +28 -0
  510. package/out/tools/index.js.map +1 -0
  511. package/out/tools/ingest-csv.d.ts.map +1 -0
  512. package/out/tools/ingest-csv.js +265 -0
  513. package/out/tools/ingest-csv.js.map +1 -0
  514. package/out/tools/jsonl-to-parquet.d.ts +61 -0
  515. package/out/tools/jsonl-to-parquet.d.ts.map +1 -0
  516. package/out/tools/jsonl-to-parquet.js +150 -0
  517. package/out/tools/jsonl-to-parquet.js.map +1 -0
  518. package/out/tools/lint-slice-vocab.d.ts +90 -0
  519. package/out/tools/lint-slice-vocab.d.ts.map +1 -0
  520. package/out/tools/lint-slice-vocab.js +267 -0
  521. package/out/tools/lint-slice-vocab.js.map +1 -0
  522. package/out/tools/lint-slice.d.ts +93 -0
  523. package/out/tools/lint-slice.d.ts.map +1 -0
  524. package/out/tools/lint-slice.js +322 -0
  525. package/out/tools/lint-slice.js.map +1 -0
  526. package/out/tools/overlay-manifest.d.ts +39 -0
  527. package/out/tools/overlay-manifest.d.ts.map +1 -0
  528. package/out/tools/overlay-manifest.js +90 -0
  529. package/out/tools/overlay-manifest.js.map +1 -0
  530. package/out/tools/overture-subvenue.d.ts +112 -0
  531. package/out/tools/overture-subvenue.d.ts.map +1 -0
  532. package/out/tools/overture-subvenue.js +139 -0
  533. package/out/tools/overture-subvenue.js.map +1 -0
  534. package/out/tools/postcode-triples.d.ts +174 -0
  535. package/out/tools/postcode-triples.d.ts.map +1 -0
  536. package/out/tools/postcode-triples.js +292 -0
  537. package/out/tools/postcode-triples.js.map +1 -0
  538. package/out/tools/slice-kryptonite.d.ts +32 -0
  539. package/out/tools/slice-kryptonite.d.ts.map +1 -0
  540. package/out/tools/slice-kryptonite.js +99 -0
  541. package/out/tools/slice-kryptonite.js.map +1 -0
  542. package/out/tools/slice-translit.d.ts +51 -0
  543. package/out/tools/slice-translit.d.ts.map +1 -0
  544. package/out/tools/slice-translit.js +166 -0
  545. package/out/tools/slice-translit.js.map +1 -0
  546. package/out/tools/sub-venue/harvest.d.ts +100 -0
  547. package/out/tools/sub-venue/harvest.d.ts.map +1 -0
  548. package/out/tools/sub-venue/harvest.js +168 -0
  549. package/out/tools/sub-venue/harvest.js.map +1 -0
  550. package/out/tools/sub-venue/head-nouns.d.ts +50 -0
  551. package/out/tools/sub-venue/head-nouns.d.ts.map +1 -0
  552. package/out/tools/sub-venue/head-nouns.js +213 -0
  553. package/out/tools/sub-venue/head-nouns.js.map +1 -0
  554. package/out/tools/sub-venue/surfaces.d.ts +45 -0
  555. package/out/tools/sub-venue/surfaces.d.ts.map +1 -0
  556. package/out/tools/sub-venue/surfaces.js +77 -0
  557. package/out/tools/sub-venue/surfaces.js.map +1 -0
  558. package/out/tools/sub-venue/table.d.ts +229 -0
  559. package/out/tools/sub-venue/table.d.ts.map +1 -0
  560. package/out/tools/sub-venue/table.js +108 -0
  561. package/out/tools/sub-venue/table.js.map +1 -0
  562. package/out/tools/sub-venue/wikidata.d.ts +26 -0
  563. package/out/tools/sub-venue/wikidata.d.ts.map +1 -0
  564. package/out/tools/sub-venue/wikidata.js +62 -0
  565. package/out/tools/sub-venue/wikidata.js.map +1 -0
  566. package/out/tools/sub-venue-lexicon.d.ts +156 -0
  567. package/out/tools/sub-venue-lexicon.d.ts.map +1 -0
  568. package/out/tools/sub-venue-lexicon.js +283 -0
  569. package/out/tools/sub-venue-lexicon.js.map +1 -0
  570. package/out/tools/sub-venue-promotions.d.ts +94 -0
  571. package/out/tools/sub-venue-promotions.d.ts.map +1 -0
  572. package/out/tools/sub-venue-promotions.js +266 -0
  573. package/out/tools/sub-venue-promotions.js.map +1 -0
  574. package/out/types.d.ts +221 -0
  575. package/out/types.d.ts.map +1 -0
  576. package/out/types.js.map +1 -0
  577. package/out/utils/align.d.ts +93 -0
  578. package/out/utils/align.d.ts.map +1 -0
  579. package/out/utils/align.js +234 -0
  580. package/out/utils/align.js.map +1 -0
  581. package/out/utils/golden.d.ts +85 -0
  582. package/out/utils/golden.d.ts.map +1 -0
  583. package/out/utils/golden.js +127 -0
  584. package/out/utils/golden.js.map +1 -0
  585. package/out/utils/index.d.ts +14 -0
  586. package/out/utils/index.d.ts.map +1 -0
  587. package/out/utils/index.js +14 -0
  588. package/out/utils/index.js.map +1 -0
  589. package/out/utils/license.d.ts.map +1 -0
  590. package/out/utils/license.js.map +1 -0
  591. package/out/utils/parquet.d.ts +178 -0
  592. package/out/utils/parquet.d.ts.map +1 -0
  593. package/out/utils/parquet.js +371 -0
  594. package/out/utils/parquet.js.map +1 -0
  595. package/out/utils/slice-stats.d.ts +52 -0
  596. package/out/utils/slice-stats.d.ts.map +1 -0
  597. package/out/utils/slice-stats.js +58 -0
  598. package/out/utils/slice-stats.js.map +1 -0
  599. package/out/utils/split.d.ts +128 -0
  600. package/out/utils/split.d.ts.map +1 -0
  601. package/out/utils/split.js +204 -0
  602. package/out/utils/split.js.map +1 -0
  603. package/out/utils/tokenize.d.ts +64 -0
  604. package/out/utils/tokenize.d.ts.map +1 -0
  605. package/out/utils/tokenize.js +82 -0
  606. package/out/utils/tokenize.js.map +1 -0
  607. package/out/utils/wof-json.d.ts +113 -0
  608. package/out/utils/wof-json.d.ts.map +1 -0
  609. package/out/utils/wof-json.js +173 -0
  610. package/out/utils/wof-json.js.map +1 -0
  611. package/package.json +259 -194
  612. package/out/src/adapters/ban/adapter.d.ts.map +0 -1
  613. package/out/src/adapters/ban/adapter.js +0 -149
  614. package/out/src/adapters/ban/adapter.js.map +0 -1
  615. package/out/src/adapters/ban/street-decompose.d.ts.map +0 -1
  616. package/out/src/adapters/ban/street-decompose.js +0 -75
  617. package/out/src/adapters/ban/street-decompose.js.map +0 -1
  618. package/out/src/adapters/fcc-bdc/adapter.d.ts.map +0 -1
  619. package/out/src/adapters/fcc-bdc/adapter.js +0 -144
  620. package/out/src/adapters/fcc-bdc/adapter.js.map +0 -1
  621. package/out/src/adapters/geonames/adapter.d.ts.map +0 -1
  622. package/out/src/adapters/geonames/adapter.js +0 -176
  623. package/out/src/adapters/geonames/adapter.js.map +0 -1
  624. package/out/src/adapters/geonames-postal/adapter.d.ts +0 -41
  625. package/out/src/adapters/geonames-postal/adapter.d.ts.map +0 -1
  626. package/out/src/adapters/geonames-postal/adapter.js +0 -104
  627. package/out/src/adapters/geonames-postal/adapter.js.map +0 -1
  628. package/out/src/adapters/gnaf/adapter.d.ts +0 -49
  629. package/out/src/adapters/gnaf/adapter.d.ts.map +0 -1
  630. package/out/src/adapters/gnaf/adapter.js +0 -124
  631. package/out/src/adapters/gnaf/adapter.js.map +0 -1
  632. package/out/src/adapters/gnaf/assemble.d.ts +0 -65
  633. package/out/src/adapters/gnaf/assemble.d.ts.map +0 -1
  634. package/out/src/adapters/gnaf/assemble.js +0 -154
  635. package/out/src/adapters/gnaf/assemble.js.map +0 -1
  636. package/out/src/adapters/index.d.ts +0 -51
  637. package/out/src/adapters/index.d.ts.map +0 -1
  638. package/out/src/adapters/index.js +0 -95
  639. package/out/src/adapters/index.js.map +0 -1
  640. package/out/src/adapters/openaddresses/adapter.d.ts.map +0 -1
  641. package/out/src/adapters/openaddresses/adapter.js +0 -186
  642. package/out/src/adapters/openaddresses/adapter.js.map +0 -1
  643. package/out/src/adapters/overture/adapter.d.ts +0 -48
  644. package/out/src/adapters/overture/adapter.d.ts.map +0 -1
  645. package/out/src/adapters/overture/adapter.js +0 -125
  646. package/out/src/adapters/overture/adapter.js.map +0 -1
  647. package/out/src/adapters/state-hi-schools/adapter.d.ts +0 -47
  648. package/out/src/adapters/state-hi-schools/adapter.d.ts.map +0 -1
  649. package/out/src/adapters/state-hi-schools/adapter.js +0 -133
  650. package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
  651. package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
  652. package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
  653. package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
  654. package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
  655. package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
  656. package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
  657. package/out/src/adapters/synth-po-box/adapter.d.ts.map +0 -1
  658. package/out/src/adapters/synth-po-box/adapter.js +0 -140
  659. package/out/src/adapters/synth-po-box/adapter.js.map +0 -1
  660. package/out/src/adapters/tiger/adapter.d.ts +0 -55
  661. package/out/src/adapters/tiger/adapter.d.ts.map +0 -1
  662. package/out/src/adapters/tiger/adapter.js +0 -201
  663. package/out/src/adapters/tiger/adapter.js.map +0 -1
  664. package/out/src/adapters/tiger/street-decompose.d.ts.map +0 -1
  665. package/out/src/adapters/tiger/street-decompose.js +0 -90
  666. package/out/src/adapters/tiger/street-decompose.js.map +0 -1
  667. package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -47
  668. package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
  669. package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +0 -139
  670. package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
  671. package/out/src/adapters/usgov-imls-pls/adapter.d.ts +0 -36
  672. package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
  673. package/out/src/adapters/usgov-imls-pls/adapter.js +0 -114
  674. package/out/src/adapters/usgov-imls-pls/adapter.js.map +0 -1
  675. package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
  676. package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
  677. package/out/src/adapters/usgov-irs-bmf/adapter.js +0 -124
  678. package/out/src/adapters/usgov-irs-bmf/adapter.js.map +0 -1
  679. package/out/src/adapters/usgov-nad/adapter.d.ts +0 -48
  680. package/out/src/adapters/usgov-nad/adapter.d.ts.map +0 -1
  681. package/out/src/adapters/usgov-nad/adapter.js +0 -252
  682. package/out/src/adapters/usgov-nad/adapter.js.map +0 -1
  683. package/out/src/adapters/usgov-nppes/adapter.d.ts.map +0 -1
  684. package/out/src/adapters/usgov-nppes/adapter.js +0 -116
  685. package/out/src/adapters/usgov-nppes/adapter.js.map +0 -1
  686. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
  687. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -156
  688. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
  689. package/out/src/adapters/utils/index.d.ts +0 -150
  690. package/out/src/adapters/utils/index.d.ts.map +0 -1
  691. package/out/src/adapters/utils/index.js +0 -159
  692. package/out/src/adapters/utils/index.js.map +0 -1
  693. package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
  694. package/out/src/adapters/wof-admin-jp/adapter.js +0 -164
  695. package/out/src/adapters/wof-admin-jp/adapter.js.map +0 -1
  696. package/out/src/adapters/wof-admin-json/adapter.d.ts +0 -82
  697. package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
  698. package/out/src/adapters/wof-admin-json/adapter.js +0 -224
  699. package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
  700. package/out/src/adapters/wof-json-rows.d.ts +0 -32
  701. package/out/src/adapters/wof-json-rows.d.ts.map +0 -1
  702. package/out/src/adapters/wof-json-rows.js +0 -45
  703. package/out/src/adapters/wof-json-rows.js.map +0 -1
  704. package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -65
  705. package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
  706. package/out/src/adapters/wof-postalcode-json/adapter.js +0 -160
  707. package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
  708. package/out/src/build.d.ts +0 -132
  709. package/out/src/build.d.ts.map +0 -1
  710. package/out/src/build.js +0 -251
  711. package/out/src/build.js.map +0 -1
  712. package/out/src/codex/us-fips-state.d.ts.map +0 -1
  713. package/out/src/codex/us-fips-state.js.map +0 -1
  714. package/out/src/index.d.ts +0 -14
  715. package/out/src/index.d.ts.map +0 -1
  716. package/out/src/index.js +0 -14
  717. package/out/src/index.js.map +0 -1
  718. package/out/src/name-prone-us-suffixes.d.ts +0 -12
  719. package/out/src/name-prone-us-suffixes.d.ts.map +0 -1
  720. package/out/src/name-prone-us-suffixes.js +0 -12
  721. package/out/src/name-prone-us-suffixes.js.map +0 -1
  722. package/out/src/parquet-wrapper/index.d.ts +0 -9
  723. package/out/src/parquet-wrapper/index.d.ts.map +0 -1
  724. package/out/src/parquet-wrapper/index.js +0 -9
  725. package/out/src/parquet-wrapper/index.js.map +0 -1
  726. package/out/src/parquet-wrapper/reader.d.ts +0 -34
  727. package/out/src/parquet-wrapper/reader.d.ts.map +0 -1
  728. package/out/src/parquet-wrapper/reader.js +0 -69
  729. package/out/src/parquet-wrapper/reader.js.map +0 -1
  730. package/out/src/parquet-wrapper/schema.d.ts +0 -49
  731. package/out/src/parquet-wrapper/schema.d.ts.map +0 -1
  732. package/out/src/parquet-wrapper/schema.js +0 -55
  733. package/out/src/parquet-wrapper/schema.js.map +0 -1
  734. package/out/src/parquet-wrapper/writer.d.ts +0 -46
  735. package/out/src/parquet-wrapper/writer.d.ts.map +0 -1
  736. package/out/src/parquet-wrapper/writer.js +0 -76
  737. package/out/src/parquet-wrapper/writer.js.map +0 -1
  738. package/out/src/runner.d.ts +0 -126
  739. package/out/src/runner.d.ts.map +0 -1
  740. package/out/src/runner.js +0 -189
  741. package/out/src/runner.js.map +0 -1
  742. package/out/src/shard-recipes/anchor-absorption.d.ts +0 -20
  743. package/out/src/shard-recipes/anchor-absorption.d.ts.map +0 -1
  744. package/out/src/shard-recipes/anchor-absorption.js +0 -82
  745. package/out/src/shard-recipes/anchor-absorption.js.map +0 -1
  746. package/out/src/shard-recipes/bare-country.d.ts +0 -25
  747. package/out/src/shard-recipes/bare-country.d.ts.map +0 -1
  748. package/out/src/shard-recipes/bare-country.js +0 -87
  749. package/out/src/shard-recipes/bare-country.js.map +0 -1
  750. package/out/src/shard-recipes/boundary-stress.d.ts +0 -20
  751. package/out/src/shard-recipes/boundary-stress.d.ts.map +0 -1
  752. package/out/src/shard-recipes/boundary-stress.js +0 -83
  753. package/out/src/shard-recipes/boundary-stress.js.map +0 -1
  754. package/out/src/shard-recipes/country-balanced.d.ts +0 -32
  755. package/out/src/shard-recipes/country-balanced.d.ts.map +0 -1
  756. package/out/src/shard-recipes/country-balanced.js +0 -406
  757. package/out/src/shard-recipes/country-balanced.js.map +0 -1
  758. package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts +0 -22
  759. package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +0 -1
  760. package/out/src/shard-recipes/cz-pcfirst-preposition.js +0 -100
  761. package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +0 -1
  762. package/out/src/shard-recipes/fr-admin-split.d.ts +0 -38
  763. package/out/src/shard-recipes/fr-admin-split.d.ts.map +0 -1
  764. package/out/src/shard-recipes/fr-admin-split.js +0 -188
  765. package/out/src/shard-recipes/fr-admin-split.js.map +0 -1
  766. package/out/src/shard-recipes/fr-bare-street.d.ts +0 -28
  767. package/out/src/shard-recipes/fr-bare-street.d.ts.map +0 -1
  768. package/out/src/shard-recipes/fr-bare-street.js +0 -143
  769. package/out/src/shard-recipes/fr-bare-street.js.map +0 -1
  770. package/out/src/shard-recipes/fr-fragment.d.ts +0 -77
  771. package/out/src/shard-recipes/fr-fragment.d.ts.map +0 -1
  772. package/out/src/shard-recipes/fr-fragment.js +0 -276
  773. package/out/src/shard-recipes/fr-fragment.js.map +0 -1
  774. package/out/src/shard-recipes/fr-lieudit.d.ts +0 -32
  775. package/out/src/shard-recipes/fr-lieudit.d.ts.map +0 -1
  776. package/out/src/shard-recipes/fr-lieudit.js +0 -226
  777. package/out/src/shard-recipes/fr-lieudit.js.map +0 -1
  778. package/out/src/shard-recipes/fr-order.d.ts +0 -38
  779. package/out/src/shard-recipes/fr-order.d.ts.map +0 -1
  780. package/out/src/shard-recipes/fr-order.js +0 -208
  781. package/out/src/shard-recipes/fr-order.js.map +0 -1
  782. package/out/src/shard-recipes/german.d.ts +0 -23
  783. package/out/src/shard-recipes/german.d.ts.map +0 -1
  784. package/out/src/shard-recipes/german.js +0 -132
  785. package/out/src/shard-recipes/german.js.map +0 -1
  786. package/out/src/shard-recipes/house-venue.d.ts +0 -18
  787. package/out/src/shard-recipes/house-venue.d.ts.map +0 -1
  788. package/out/src/shard-recipes/house-venue.js +0 -74
  789. package/out/src/shard-recipes/house-venue.js.map +0 -1
  790. package/out/src/shard-recipes/index.d.ts +0 -24
  791. package/out/src/shard-recipes/index.d.ts.map +0 -1
  792. package/out/src/shard-recipes/index.js +0 -89
  793. package/out/src/shard-recipes/index.js.map +0 -1
  794. package/out/src/shard-recipes/intersection.d.ts +0 -42
  795. package/out/src/shard-recipes/intersection.d.ts.map +0 -1
  796. package/out/src/shard-recipes/intersection.js +0 -460
  797. package/out/src/shard-recipes/intersection.js.map +0 -1
  798. package/out/src/shard-recipes/locale.d.ts +0 -135
  799. package/out/src/shard-recipes/locale.d.ts.map +0 -1
  800. package/out/src/shard-recipes/locale.js +0 -459
  801. package/out/src/shard-recipes/locale.js.map +0 -1
  802. package/out/src/shard-recipes/nl-postcode.d.ts +0 -26
  803. package/out/src/shard-recipes/nl-postcode.d.ts.map +0 -1
  804. package/out/src/shard-recipes/nl-postcode.js +0 -102
  805. package/out/src/shard-recipes/nl-postcode.js.map +0 -1
  806. package/out/src/shard-recipes/no-fragment.d.ts +0 -43
  807. package/out/src/shard-recipes/no-fragment.d.ts.map +0 -1
  808. package/out/src/shard-recipes/no-fragment.js +0 -188
  809. package/out/src/shard-recipes/no-fragment.js.map +0 -1
  810. package/out/src/shard-recipes/no-street-led.d.ts +0 -24
  811. package/out/src/shard-recipes/no-street-led.d.ts.map +0 -1
  812. package/out/src/shard-recipes/no-street-led.js +0 -121
  813. package/out/src/shard-recipes/no-street-led.js.map +0 -1
  814. package/out/src/shard-recipes/no-street.d.ts +0 -18
  815. package/out/src/shard-recipes/no-street.d.ts.map +0 -1
  816. package/out/src/shard-recipes/no-street.js +0 -72
  817. package/out/src/shard-recipes/no-street.js.map +0 -1
  818. package/out/src/shard-recipes/po-box-cedex.d.ts +0 -38
  819. package/out/src/shard-recipes/po-box-cedex.d.ts.map +0 -1
  820. package/out/src/shard-recipes/po-box-cedex.js +0 -726
  821. package/out/src/shard-recipes/po-box-cedex.js.map +0 -1
  822. package/out/src/shard-recipes/po-box.d.ts +0 -17
  823. package/out/src/shard-recipes/po-box.d.ts.map +0 -1
  824. package/out/src/shard-recipes/po-box.js +0 -101
  825. package/out/src/shard-recipes/po-box.js.map +0 -1
  826. package/out/src/shard-recipes/reviewed-postcode-tail.d.ts +0 -47
  827. package/out/src/shard-recipes/reviewed-postcode-tail.d.ts.map +0 -1
  828. package/out/src/shard-recipes/reviewed-postcode-tail.js +0 -125
  829. package/out/src/shard-recipes/reviewed-postcode-tail.js.map +0 -1
  830. package/out/src/shard-recipes/scaffold.d.ts +0 -246
  831. package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
  832. package/out/src/shard-recipes/scaffold.js +0 -137
  833. package/out/src/shard-recipes/scaffold.js.map +0 -1
  834. package/out/src/shard-recipes/si-bare-village.d.ts +0 -32
  835. package/out/src/shard-recipes/si-bare-village.d.ts.map +0 -1
  836. package/out/src/shard-recipes/si-bare-village.js +0 -88
  837. package/out/src/shard-recipes/si-bare-village.js.map +0 -1
  838. package/out/src/shard-recipes/street-affix.d.ts +0 -89
  839. package/out/src/shard-recipes/street-affix.d.ts.map +0 -1
  840. package/out/src/shard-recipes/street-affix.js +0 -578
  841. package/out/src/shard-recipes/street-affix.js.map +0 -1
  842. package/out/src/shard-recipes/street-bare.d.ts +0 -25
  843. package/out/src/shard-recipes/street-bare.d.ts.map +0 -1
  844. package/out/src/shard-recipes/street-bare.js +0 -86
  845. package/out/src/shard-recipes/street-bare.js.map +0 -1
  846. package/out/src/shard-recipes/street.d.ts +0 -15
  847. package/out/src/shard-recipes/street.d.ts.map +0 -1
  848. package/out/src/shard-recipes/street.js +0 -69
  849. package/out/src/shard-recipes/street.js.map +0 -1
  850. package/out/src/shard-recipes/sub-venue-sources.d.ts +0 -228
  851. package/out/src/shard-recipes/sub-venue-sources.d.ts.map +0 -1
  852. package/out/src/shard-recipes/sub-venue-sources.js +0 -664
  853. package/out/src/shard-recipes/sub-venue-sources.js.map +0 -1
  854. package/out/src/shard-recipes/sub-venue.d.ts +0 -269
  855. package/out/src/shard-recipes/sub-venue.d.ts.map +0 -1
  856. package/out/src/shard-recipes/sub-venue.js +0 -710
  857. package/out/src/shard-recipes/sub-venue.js.map +0 -1
  858. package/out/src/shard-recipes/trailing-region.d.ts +0 -74
  859. package/out/src/shard-recipes/trailing-region.d.ts.map +0 -1
  860. package/out/src/shard-recipes/trailing-region.js +0 -157
  861. package/out/src/shard-recipes/trailing-region.js.map +0 -1
  862. package/out/src/shard-recipes/unit.d.ts +0 -29
  863. package/out/src/shard-recipes/unit.d.ts.map +0 -1
  864. package/out/src/shard-recipes/unit.js +0 -243
  865. package/out/src/shard-recipes/unit.js.map +0 -1
  866. package/out/src/synthesizers/anchor-absorption.d.ts +0 -63
  867. package/out/src/synthesizers/anchor-absorption.d.ts.map +0 -1
  868. package/out/src/synthesizers/anchor-absorption.js +0 -223
  869. package/out/src/synthesizers/anchor-absorption.js.map +0 -1
  870. package/out/src/synthesizers/boundary-stress.d.ts +0 -78
  871. package/out/src/synthesizers/boundary-stress.d.ts.map +0 -1
  872. package/out/src/synthesizers/boundary-stress.js +0 -455
  873. package/out/src/synthesizers/boundary-stress.js.map +0 -1
  874. package/out/src/synthesizers/german.d.ts +0 -107
  875. package/out/src/synthesizers/german.d.ts.map +0 -1
  876. package/out/src/synthesizers/german.js +0 -148
  877. package/out/src/synthesizers/german.js.map +0 -1
  878. package/out/src/synthesizers/house-venue.d.ts +0 -56
  879. package/out/src/synthesizers/house-venue.d.ts.map +0 -1
  880. package/out/src/synthesizers/house-venue.js +0 -267
  881. package/out/src/synthesizers/house-venue.js.map +0 -1
  882. package/out/src/synthesizers/intersection.d.ts +0 -52
  883. package/out/src/synthesizers/intersection.d.ts.map +0 -1
  884. package/out/src/synthesizers/intersection.js +0 -175
  885. package/out/src/synthesizers/intersection.js.map +0 -1
  886. package/out/src/synthesizers/no-street.d.ts +0 -72
  887. package/out/src/synthesizers/no-street.d.ts.map +0 -1
  888. package/out/src/synthesizers/no-street.js +0 -282
  889. package/out/src/synthesizers/no-street.js.map +0 -1
  890. package/out/src/synthesizers/po-box.d.ts +0 -104
  891. package/out/src/synthesizers/po-box.d.ts.map +0 -1
  892. package/out/src/synthesizers/po-box.js +0 -266
  893. package/out/src/synthesizers/po-box.js.map +0 -1
  894. package/out/src/synthesizers/street.d.ts +0 -54
  895. package/out/src/synthesizers/street.d.ts.map +0 -1
  896. package/out/src/synthesizers/street.js +0 -221
  897. package/out/src/synthesizers/street.js.map +0 -1
  898. package/out/src/synthesizers/utils.d.ts +0 -203
  899. package/out/src/synthesizers/utils.d.ts.map +0 -1
  900. package/out/src/synthesizers/utils.js +0 -708
  901. package/out/src/synthesizers/utils.js.map +0 -1
  902. package/out/src/tools/align-shard.d.ts +0 -8
  903. package/out/src/tools/align-shard.d.ts.map +0 -1
  904. package/out/src/tools/align-shard.js +0 -56
  905. package/out/src/tools/align-shard.js.map +0 -1
  906. package/out/src/tools/audit.d.ts +0 -28
  907. package/out/src/tools/audit.d.ts.map +0 -1
  908. package/out/src/tools/audit.js +0 -285
  909. package/out/src/tools/audit.js.map +0 -1
  910. package/out/src/tools/corpus-stats.d.ts +0 -44
  911. package/out/src/tools/corpus-stats.d.ts.map +0 -1
  912. package/out/src/tools/corpus-stats.js +0 -138
  913. package/out/src/tools/corpus-stats.js.map +0 -1
  914. package/out/src/tools/fetch/ban.d.ts +0 -31
  915. package/out/src/tools/fetch/ban.d.ts.map +0 -1
  916. package/out/src/tools/fetch/ban.js +0 -239
  917. package/out/src/tools/fetch/ban.js.map +0 -1
  918. package/out/src/tools/fetch/download.d.ts +0 -78
  919. package/out/src/tools/fetch/download.d.ts.map +0 -1
  920. package/out/src/tools/fetch/download.js +0 -116
  921. package/out/src/tools/fetch/download.js.map +0 -1
  922. package/out/src/tools/fetch/geonames-dump.d.ts +0 -87
  923. package/out/src/tools/fetch/geonames-dump.d.ts.map +0 -1
  924. package/out/src/tools/fetch/geonames-dump.js +0 -178
  925. package/out/src/tools/fetch/geonames-dump.js.map +0 -1
  926. package/out/src/tools/fetch/geonames-postal.d.ts +0 -76
  927. package/out/src/tools/fetch/geonames-postal.d.ts.map +0 -1
  928. package/out/src/tools/fetch/geonames-postal.js +0 -125
  929. package/out/src/tools/fetch/geonames-postal.js.map +0 -1
  930. package/out/src/tools/fetch/hrsa.d.ts +0 -18
  931. package/out/src/tools/fetch/hrsa.d.ts.map +0 -1
  932. package/out/src/tools/fetch/hrsa.js +0 -46
  933. package/out/src/tools/fetch/hrsa.js.map +0 -1
  934. package/out/src/tools/fetch/imls-pls.d.ts +0 -25
  935. package/out/src/tools/fetch/imls-pls.d.ts.map +0 -1
  936. package/out/src/tools/fetch/imls-pls.js +0 -108
  937. package/out/src/tools/fetch/imls-pls.js.map +0 -1
  938. package/out/src/tools/fetch/index.d.ts +0 -144
  939. package/out/src/tools/fetch/index.d.ts.map +0 -1
  940. package/out/src/tools/fetch/index.js +0 -143
  941. package/out/src/tools/fetch/index.js.map +0 -1
  942. package/out/src/tools/fetch/nad.d.ts +0 -70
  943. package/out/src/tools/fetch/nad.d.ts.map +0 -1
  944. package/out/src/tools/fetch/nad.js +0 -234
  945. package/out/src/tools/fetch/nad.js.map +0 -1
  946. package/out/src/tools/fetch/nppes.d.ts +0 -26
  947. package/out/src/tools/fetch/nppes.d.ts.map +0 -1
  948. package/out/src/tools/fetch/nppes.js +0 -126
  949. package/out/src/tools/fetch/nppes.js.map +0 -1
  950. package/out/src/tools/fetch/openaddresses.d.ts +0 -61
  951. package/out/src/tools/fetch/openaddresses.d.ts.map +0 -1
  952. package/out/src/tools/fetch/openaddresses.js +0 -317
  953. package/out/src/tools/fetch/openaddresses.js.map +0 -1
  954. package/out/src/tools/fetch/ourairports.d.ts +0 -45
  955. package/out/src/tools/fetch/ourairports.d.ts.map +0 -1
  956. package/out/src/tools/fetch/ourairports.js +0 -128
  957. package/out/src/tools/fetch/ourairports.js.map +0 -1
  958. package/out/src/tools/fetch/ppd.d.ts.map +0 -1
  959. package/out/src/tools/fetch/ppd.js +0 -100
  960. package/out/src/tools/fetch/ppd.js.map +0 -1
  961. package/out/src/tools/fetch/state-hi-schools.d.ts +0 -25
  962. package/out/src/tools/fetch/state-hi-schools.d.ts.map +0 -1
  963. package/out/src/tools/fetch/state-hi-schools.js +0 -162
  964. package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
  965. package/out/src/tools/fetch/state-sources.d.ts +0 -26
  966. package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
  967. package/out/src/tools/fetch/state-sources.js +0 -111
  968. package/out/src/tools/fetch/state-sources.js.map +0 -1
  969. package/out/src/tools/fetch/tiger-full.d.ts +0 -42
  970. package/out/src/tools/fetch/tiger-full.d.ts.map +0 -1
  971. package/out/src/tools/fetch/tiger-full.js +0 -248
  972. package/out/src/tools/fetch/tiger-full.js.map +0 -1
  973. package/out/src/tools/fetch/wikidata-subvenue.d.ts +0 -171
  974. package/out/src/tools/fetch/wikidata-subvenue.d.ts.map +0 -1
  975. package/out/src/tools/fetch/wikidata-subvenue.js +0 -275
  976. package/out/src/tools/fetch/wikidata-subvenue.js.map +0 -1
  977. package/out/src/tools/gb-title-case.d.ts.map +0 -1
  978. package/out/src/tools/gb-title-case.js.map +0 -1
  979. package/out/src/tools/golden-expand.d.ts +0 -90
  980. package/out/src/tools/golden-expand.d.ts.map +0 -1
  981. package/out/src/tools/golden-expand.js +0 -413
  982. package/out/src/tools/golden-expand.js.map +0 -1
  983. package/out/src/tools/golden-promote.d.ts.map +0 -1
  984. package/out/src/tools/golden-promote.js +0 -244
  985. package/out/src/tools/golden-promote.js.map +0 -1
  986. package/out/src/tools/golden-relabel-street.d.ts +0 -196
  987. package/out/src/tools/golden-relabel-street.d.ts.map +0 -1
  988. package/out/src/tools/golden-relabel-street.js +0 -440
  989. package/out/src/tools/golden-relabel-street.js.map +0 -1
  990. package/out/src/tools/index.d.ts +0 -28
  991. package/out/src/tools/index.d.ts.map +0 -1
  992. package/out/src/tools/index.js +0 -28
  993. package/out/src/tools/index.js.map +0 -1
  994. package/out/src/tools/ingest-csv.d.ts.map +0 -1
  995. package/out/src/tools/ingest-csv.js +0 -296
  996. package/out/src/tools/ingest-csv.js.map +0 -1
  997. package/out/src/tools/jsonl-to-parquet.d.ts +0 -61
  998. package/out/src/tools/jsonl-to-parquet.d.ts.map +0 -1
  999. package/out/src/tools/jsonl-to-parquet.js +0 -164
  1000. package/out/src/tools/jsonl-to-parquet.js.map +0 -1
  1001. package/out/src/tools/lint-shard-vocab.d.ts +0 -90
  1002. package/out/src/tools/lint-shard-vocab.d.ts.map +0 -1
  1003. package/out/src/tools/lint-shard-vocab.js +0 -281
  1004. package/out/src/tools/lint-shard-vocab.js.map +0 -1
  1005. package/out/src/tools/lint-shard.d.ts +0 -93
  1006. package/out/src/tools/lint-shard.d.ts.map +0 -1
  1007. package/out/src/tools/lint-shard.js +0 -354
  1008. package/out/src/tools/lint-shard.js.map +0 -1
  1009. package/out/src/tools/overlay-manifest.d.ts +0 -39
  1010. package/out/src/tools/overlay-manifest.d.ts.map +0 -1
  1011. package/out/src/tools/overlay-manifest.js +0 -98
  1012. package/out/src/tools/overlay-manifest.js.map +0 -1
  1013. package/out/src/tools/overture-subvenue.d.ts +0 -112
  1014. package/out/src/tools/overture-subvenue.d.ts.map +0 -1
  1015. package/out/src/tools/overture-subvenue.js +0 -144
  1016. package/out/src/tools/overture-subvenue.js.map +0 -1
  1017. package/out/src/tools/postcode-triples.d.ts +0 -175
  1018. package/out/src/tools/postcode-triples.d.ts.map +0 -1
  1019. package/out/src/tools/postcode-triples.js +0 -304
  1020. package/out/src/tools/postcode-triples.js.map +0 -1
  1021. package/out/src/tools/shard-kryptonite.d.ts +0 -32
  1022. package/out/src/tools/shard-kryptonite.d.ts.map +0 -1
  1023. package/out/src/tools/shard-kryptonite.js +0 -100
  1024. package/out/src/tools/shard-kryptonite.js.map +0 -1
  1025. package/out/src/tools/shard-translit.d.ts +0 -51
  1026. package/out/src/tools/shard-translit.d.ts.map +0 -1
  1027. package/out/src/tools/shard-translit.js +0 -175
  1028. package/out/src/tools/shard-translit.js.map +0 -1
  1029. package/out/src/tools/sub-venue/harvest.d.ts +0 -100
  1030. package/out/src/tools/sub-venue/harvest.d.ts.map +0 -1
  1031. package/out/src/tools/sub-venue/harvest.js +0 -168
  1032. package/out/src/tools/sub-venue/harvest.js.map +0 -1
  1033. package/out/src/tools/sub-venue/head-nouns.d.ts +0 -50
  1034. package/out/src/tools/sub-venue/head-nouns.d.ts.map +0 -1
  1035. package/out/src/tools/sub-venue/head-nouns.js +0 -210
  1036. package/out/src/tools/sub-venue/head-nouns.js.map +0 -1
  1037. package/out/src/tools/sub-venue/surfaces.d.ts +0 -45
  1038. package/out/src/tools/sub-venue/surfaces.d.ts.map +0 -1
  1039. package/out/src/tools/sub-venue/surfaces.js +0 -77
  1040. package/out/src/tools/sub-venue/surfaces.js.map +0 -1
  1041. package/out/src/tools/sub-venue/table.d.ts +0 -229
  1042. package/out/src/tools/sub-venue/table.d.ts.map +0 -1
  1043. package/out/src/tools/sub-venue/table.js +0 -108
  1044. package/out/src/tools/sub-venue/table.js.map +0 -1
  1045. package/out/src/tools/sub-venue/wikidata.d.ts +0 -26
  1046. package/out/src/tools/sub-venue/wikidata.d.ts.map +0 -1
  1047. package/out/src/tools/sub-venue/wikidata.js +0 -62
  1048. package/out/src/tools/sub-venue/wikidata.js.map +0 -1
  1049. package/out/src/tools/sub-venue-lexicon.d.ts +0 -156
  1050. package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
  1051. package/out/src/tools/sub-venue-lexicon.js +0 -282
  1052. package/out/src/tools/sub-venue-lexicon.js.map +0 -1
  1053. package/out/src/tools/sub-venue-promotions.d.ts +0 -94
  1054. package/out/src/tools/sub-venue-promotions.d.ts.map +0 -1
  1055. package/out/src/tools/sub-venue-promotions.js +0 -266
  1056. package/out/src/tools/sub-venue-promotions.js.map +0 -1
  1057. package/out/src/types.d.ts +0 -221
  1058. package/out/src/types.d.ts.map +0 -1
  1059. package/out/src/types.js.map +0 -1
  1060. package/out/src/utils/align.d.ts +0 -93
  1061. package/out/src/utils/align.d.ts.map +0 -1
  1062. package/out/src/utils/align.js +0 -234
  1063. package/out/src/utils/align.js.map +0 -1
  1064. package/out/src/utils/golden.d.ts +0 -69
  1065. package/out/src/utils/golden.d.ts.map +0 -1
  1066. package/out/src/utils/golden.js +0 -127
  1067. package/out/src/utils/golden.js.map +0 -1
  1068. package/out/src/utils/index.d.ts +0 -14
  1069. package/out/src/utils/index.d.ts.map +0 -1
  1070. package/out/src/utils/index.js +0 -14
  1071. package/out/src/utils/index.js.map +0 -1
  1072. package/out/src/utils/license.d.ts.map +0 -1
  1073. package/out/src/utils/license.js.map +0 -1
  1074. package/out/src/utils/parquet.d.ts +0 -162
  1075. package/out/src/utils/parquet.d.ts.map +0 -1
  1076. package/out/src/utils/parquet.js +0 -262
  1077. package/out/src/utils/parquet.js.map +0 -1
  1078. package/out/src/utils/split.d.ts +0 -127
  1079. package/out/src/utils/split.d.ts.map +0 -1
  1080. package/out/src/utils/split.js +0 -204
  1081. package/out/src/utils/split.js.map +0 -1
  1082. package/out/src/utils/tokenize.d.ts +0 -56
  1083. package/out/src/utils/tokenize.d.ts.map +0 -1
  1084. package/out/src/utils/tokenize.js +0 -48
  1085. package/out/src/utils/tokenize.js.map +0 -1
  1086. package/out/src/utils/wof-json.d.ts +0 -109
  1087. package/out/src/utils/wof-json.d.ts.map +0 -1
  1088. package/out/src/utils/wof-json.js +0 -173
  1089. package/out/src/utils/wof-json.js.map +0 -1
  1090. package/src/adapters/ban/adapter.ts +0 -191
  1091. package/src/adapters/ban/street-decompose.ts +0 -96
  1092. package/src/adapters/fcc-bdc/adapter.ts +0 -174
  1093. package/src/adapters/geonames/adapter.ts +0 -200
  1094. package/src/adapters/geonames-postal/adapter.ts +0 -119
  1095. package/src/adapters/gnaf/adapter.ts +0 -149
  1096. package/src/adapters/gnaf/assemble.ts +0 -226
  1097. package/src/adapters/index.ts +0 -149
  1098. package/src/adapters/openaddresses/adapter.ts +0 -251
  1099. package/src/adapters/overture/adapter.ts +0 -162
  1100. package/src/adapters/state-hi-schools/adapter.ts +0 -164
  1101. package/src/adapters/synth-po-box/adapter.ts +0 -204
  1102. package/src/adapters/tiger/adapter.ts +0 -253
  1103. package/src/adapters/tiger/street-decompose.ts +0 -111
  1104. package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -183
  1105. package/src/adapters/usgov-imls-pls/adapter.ts +0 -143
  1106. package/src/adapters/usgov-irs-bmf/adapter.ts +0 -163
  1107. package/src/adapters/usgov-nad/adapter.ts +0 -348
  1108. package/src/adapters/usgov-nppes/adapter.ts +0 -159
  1109. package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -204
  1110. package/src/adapters/utils/index.ts +0 -233
  1111. package/src/adapters/wof-admin-jp/adapter.ts +0 -216
  1112. package/src/adapters/wof-admin-json/adapter.ts +0 -256
  1113. package/src/adapters/wof-json-rows.ts +0 -79
  1114. package/src/adapters/wof-postalcode-json/adapter.ts +0 -183
  1115. package/src/build.ts +0 -386
  1116. package/src/index.ts +0 -14
  1117. package/src/name-prone-us-suffixes.ts +0 -12
  1118. package/src/parquet-wrapper/index.ts +0 -9
  1119. package/src/parquet-wrapper/reader.ts +0 -97
  1120. package/src/parquet-wrapper/schema.ts +0 -88
  1121. package/src/parquet-wrapper/writer.ts +0 -110
  1122. package/src/runner.ts +0 -317
  1123. package/src/shard-recipes/anchor-absorption.ts +0 -103
  1124. package/src/shard-recipes/bare-country.ts +0 -95
  1125. package/src/shard-recipes/boundary-stress.ts +0 -101
  1126. package/src/shard-recipes/country-balanced.ts +0 -524
  1127. package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -111
  1128. package/src/shard-recipes/fr-admin-split.ts +0 -239
  1129. package/src/shard-recipes/fr-bare-street.ts +0 -170
  1130. package/src/shard-recipes/fr-fragment.ts +0 -332
  1131. package/src/shard-recipes/fr-lieudit.ts +0 -302
  1132. package/src/shard-recipes/fr-order.ts +0 -258
  1133. package/src/shard-recipes/german.ts +0 -170
  1134. package/src/shard-recipes/house-venue.ts +0 -88
  1135. package/src/shard-recipes/index.ts +0 -95
  1136. package/src/shard-recipes/intersection.ts +0 -630
  1137. package/src/shard-recipes/locale.ts +0 -599
  1138. package/src/shard-recipes/nl-postcode.ts +0 -115
  1139. package/src/shard-recipes/no-fragment.ts +0 -219
  1140. package/src/shard-recipes/no-street-led.ts +0 -143
  1141. package/src/shard-recipes/no-street.ts +0 -86
  1142. package/src/shard-recipes/po-box-cedex.ts +0 -920
  1143. package/src/shard-recipes/po-box.ts +0 -119
  1144. package/src/shard-recipes/reviewed-postcode-tail.ts +0 -189
  1145. package/src/shard-recipes/scaffold.ts +0 -360
  1146. package/src/shard-recipes/si-bare-village.ts +0 -97
  1147. package/src/shard-recipes/street-affix.ts +0 -826
  1148. package/src/shard-recipes/street-bare.ts +0 -101
  1149. package/src/shard-recipes/street.ts +0 -82
  1150. package/src/shard-recipes/sub-venue-sources.ts +0 -885
  1151. package/src/shard-recipes/sub-venue.ts +0 -984
  1152. package/src/shard-recipes/trailing-region.ts +0 -183
  1153. package/src/shard-recipes/unit.ts +0 -321
  1154. package/src/synthesizers/anchor-absorption.ts +0 -290
  1155. package/src/synthesizers/boundary-stress.ts +0 -531
  1156. package/src/synthesizers/german.ts +0 -251
  1157. package/src/synthesizers/house-venue.ts +0 -330
  1158. package/src/synthesizers/intersection.ts +0 -232
  1159. package/src/synthesizers/no-street.ts +0 -349
  1160. package/src/synthesizers/po-box.ts +0 -339
  1161. package/src/synthesizers/street.ts +0 -274
  1162. package/src/synthesizers/utils.ts +0 -903
  1163. package/src/tools/align-shard.ts +0 -70
  1164. package/src/tools/audit.ts +0 -399
  1165. package/src/tools/corpus-stats.ts +0 -184
  1166. package/src/tools/fetch/ban.ts +0 -290
  1167. package/src/tools/fetch/download.ts +0 -176
  1168. package/src/tools/fetch/geonames-dump.ts +0 -267
  1169. package/src/tools/fetch/geonames-postal.ts +0 -180
  1170. package/src/tools/fetch/hrsa.ts +0 -68
  1171. package/src/tools/fetch/imls-pls.ts +0 -158
  1172. package/src/tools/fetch/index.ts +0 -147
  1173. package/src/tools/fetch/nad.ts +0 -342
  1174. package/src/tools/fetch/nppes.ts +0 -174
  1175. package/src/tools/fetch/openaddresses.ts +0 -404
  1176. package/src/tools/fetch/ourairports.ts +0 -171
  1177. package/src/tools/fetch/ppd.ts +0 -137
  1178. package/src/tools/fetch/state-hi-schools.ts +0 -208
  1179. package/src/tools/fetch/state-sources.ts +0 -155
  1180. package/src/tools/fetch/tiger-full.ts +0 -354
  1181. package/src/tools/fetch/wikidata-subvenue.ts +0 -386
  1182. package/src/tools/golden-expand.ts +0 -584
  1183. package/src/tools/golden-promote.ts +0 -353
  1184. package/src/tools/golden-relabel-street.ts +0 -685
  1185. package/src/tools/index.ts +0 -28
  1186. package/src/tools/ingest-csv.ts +0 -422
  1187. package/src/tools/jsonl-to-parquet.ts +0 -221
  1188. package/src/tools/lint-shard-vocab.ts +0 -409
  1189. package/src/tools/lint-shard.ts +0 -543
  1190. package/src/tools/overlay-manifest.ts +0 -157
  1191. package/src/tools/overture-subvenue.ts +0 -215
  1192. package/src/tools/postcode-triples.ts +0 -375
  1193. package/src/tools/shard-kryptonite.ts +0 -139
  1194. package/src/tools/shard-translit.ts +0 -245
  1195. package/src/tools/sub-venue/harvest.ts +0 -235
  1196. package/src/tools/sub-venue/head-nouns.ts +0 -242
  1197. package/src/tools/sub-venue/surfaces.ts +0 -95
  1198. package/src/tools/sub-venue/table.ts +0 -281
  1199. package/src/tools/sub-venue/wikidata.ts +0 -85
  1200. package/src/tools/sub-venue-lexicon.ts +0 -431
  1201. package/src/tools/sub-venue-promotions.ts +0 -330
  1202. package/src/types.ts +0 -247
  1203. package/src/utils/align.ts +0 -331
  1204. package/src/utils/golden.ts +0 -176
  1205. package/src/utils/index.ts +0 -14
  1206. package/src/utils/parquet.ts +0 -391
  1207. package/src/utils/split.ts +0 -279
  1208. package/src/utils/tokenize.ts +0 -78
  1209. package/src/utils/wof-json.ts +0 -244
  1210. /package/{src → lib}/adapters/state-ia-contractors/adapter.ts +0 -0
  1211. /package/{src → lib}/adapters/state-ny-notaries/adapter.ts +0 -0
  1212. /package/{src → lib}/adapters/state-tx-notaries/adapter.ts +0 -0
  1213. /package/{src → lib}/codex/us-fips-state.ts +0 -0
  1214. /package/{src → lib}/tools/gb-title-case.ts +0 -0
  1215. /package/{src → lib}/utils/license.ts +0 -0
  1216. /package/out/{src/adapters → adapters}/ban/adapter.d.ts +0 -0
  1217. /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
  1218. /package/out/{src/adapters → adapters}/fcc-bdc/adapter.d.ts +0 -0
  1219. /package/out/{src/adapters → adapters}/geonames/adapter.d.ts +0 -0
  1220. /package/out/{src/adapters → adapters}/openaddresses/adapter.d.ts +0 -0
  1221. /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.d.ts +0 -0
  1222. /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.js +0 -0
  1223. /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.d.ts +0 -0
  1224. /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.js +0 -0
  1225. /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.d.ts +0 -0
  1226. /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.js +0 -0
  1227. /package/out/{src/adapters → adapters}/synth-po-box/adapter.d.ts +0 -0
  1228. /package/out/{src/adapters → adapters}/tiger/street-decompose.d.ts +0 -0
  1229. /package/out/{src/adapters → adapters}/usgov-nppes/adapter.d.ts +0 -0
  1230. /package/out/{src/adapters → adapters}/usgov-samhsa-treatment-locator/adapter.d.ts +0 -0
  1231. /package/out/{src/adapters → adapters}/wof-admin-jp/adapter.d.ts +0 -0
  1232. /package/out/{src/codex → codex}/us-fips-state.d.ts +0 -0
  1233. /package/out/{src/codex → codex}/us-fips-state.js +0 -0
  1234. /package/out/{src/tools → tools}/fetch/ppd.d.ts +0 -0
  1235. /package/out/{src/tools → tools}/gb-title-case.d.ts +0 -0
  1236. /package/out/{src/tools → tools}/gb-title-case.js +0 -0
  1237. /package/out/{src/tools → tools}/golden-promote.d.ts +0 -0
  1238. /package/out/{src/tools → tools}/ingest-csv.d.ts +0 -0
  1239. /package/out/{src/types.js → types.js} +0 -0
  1240. /package/out/{src/utils → utils}/license.d.ts +0 -0
  1241. /package/out/{src/utils → utils}/license.js +0 -0
@@ -1,32 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * Build a parquet shard from the DeepSeek-generated kryptonite JSONL and emit the corpus-v0.4.0
7
- * MANIFEST. corpus-v0.4.0 is a pure adapter-addition revision: it points at every shard from
8
- * v0.3.0 plus the new kryptonite shard(s). No v0.3.0 bytes are touched or re-shuffled.
9
- *
10
- * See docs/engineering/reference/CORPUS_V0_4_0_GENERATION.md for the why; that doc also pins the
11
- * DeepSeek model version + prompt versions used to produce the JSONL.
12
- *
13
- * Invoke via `mailwoman corpus shard kryptonite \
14
- * --jsonl /data/corpus/versioned/v0.4.0/kryptonite/canonical-kryptonite.jsonl \
15
- * --base-manifest /data/corpus/versioned/v0.3.0/corpus-v0.3.0/MANIFEST.json \
16
- * --out-dir /data/corpus/versioned/v0.4.0`
17
- */
18
- export interface ShardKryptoniteOptions {
19
- jsonl: string;
20
- baseManifest: string;
21
- outDir: string;
22
- /**
23
- * Default `"0.4.0"`.
24
- */
25
- corpusVersion?: string;
26
- /**
27
- * Default `"deepseek-kryptonite"`.
28
- */
29
- source?: string;
30
- }
31
- export declare function buildKryptoniteShard(options: ShardKryptoniteOptions, report?: (line: string) => void): Promise<void>;
32
- //# sourceMappingURL=shard-kryptonite.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"shard-kryptonite.d.ts","sourceRoot":"","sources":["../../../src/tools/shard-kryptonite.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAaH,MAAM,WAAW,sBAAsB;IACtC,KAAK,EAAE,MAAM,CAAA;IACb,YAAY,EAAE,MAAM,CAAA;IACpB,MAAM,EAAE,MAAM,CAAA;IACd;;OAEG;IACH,aAAa,CAAC,EAAE,MAAM,CAAA;IACtB;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,CAAA;CACf;AAiCD,wBAAsB,oBAAoB,CACzC,OAAO,EAAE,sBAAsB,EAC/B,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,IAAI,CAAC,CA6Df"}
@@ -1,100 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * Build a parquet shard from the DeepSeek-generated kryptonite JSONL and emit the corpus-v0.4.0
7
- * MANIFEST. corpus-v0.4.0 is a pure adapter-addition revision: it points at every shard from
8
- * v0.3.0 plus the new kryptonite shard(s). No v0.3.0 bytes are touched or re-shuffled.
9
- *
10
- * See docs/engineering/reference/CORPUS_V0_4_0_GENERATION.md for the why; that doc also pins the
11
- * DeepSeek model version + prompt versions used to produce the JSONL.
12
- *
13
- * Invoke via `mailwoman corpus shard kryptonite \
14
- * --jsonl /data/corpus/versioned/v0.4.0/kryptonite/canonical-kryptonite.jsonl \
15
- * --base-manifest /data/corpus/versioned/v0.3.0/corpus-v0.3.0/MANIFEST.json \
16
- * --out-dir /data/corpus/versioned/v0.4.0`
17
- */
18
- import { existsSync, readFileSync, writeFileSync } from "node:fs";
19
- import { mkdir } from "node:fs/promises";
20
- import { join } from "node:path";
21
- import { parseJSONStrict } from "@mailwoman/core/objects";
22
- import { JSONSpliterator } from "spliterator";
23
- import { alignRow, PARQUET_COLUMNS, ROW_GROUP_SIZE, SHARD_COMPRESSION, writeShards } from "#utils";
24
- async function* canonicalRows(jsonl, corpusVersion) {
25
- for await (const raw of JSONSpliterator.fromAsync(jsonl)) {
26
- // Strip sidecar underscore-prefixed fields the generator left behind for debugging.
27
- const components = raw["components"];
28
- yield {
29
- raw: raw["raw"],
30
- components,
31
- country: raw["country"] ?? "US",
32
- locale: raw["locale"] ?? undefined,
33
- source: raw["source"] ?? "deepseek-kryptonite",
34
- source_id: raw["source_id"],
35
- corpus_version: corpusVersion,
36
- license: raw["license"] ?? "Synthetic (DeepSeek-v4-flash, AGPL-compatible)",
37
- synth: raw["synth"],
38
- };
39
- }
40
- }
41
- async function* labeledRows(jsonl, corpusVersion, quarantineLog) {
42
- for await (const row of canonicalRows(jsonl, corpusVersion)) {
43
- const result = alignRow(row);
44
- if (result.kind === "labeled") {
45
- yield result.row;
46
- }
47
- else {
48
- quarantineLog.push(`${row.source_id}\t${result.row.reason}`);
49
- }
50
- }
51
- }
52
- export async function buildKryptoniteShard(options, report) {
53
- const corpusVersion = options.corpusVersion ?? "0.4.0";
54
- const source = options.source ?? "deepseek-kryptonite";
55
- if (!existsSync(options.jsonl))
56
- throw new Error(`jsonl not found: ${options.jsonl}`);
57
- if (!existsSync(options.baseManifest))
58
- throw new Error(`base-manifest not found: ${options.baseManifest}`);
59
- await mkdir(options.outDir, { recursive: true });
60
- const quarantine = [];
61
- const newManifest = await writeShards({ train: labeledRows(options.jsonl, corpusVersion, quarantine) }, { outputDir: options.outDir, corpusVersion });
62
- report?.(`wrote ${newManifest.total_rows} rows into ${newManifest.shards.length} shard(s); ` +
63
- `quarantined ${quarantine.length}`);
64
- if (quarantine.length) {
65
- const qPath = join(options.outDir, `corpus-v${corpusVersion}`, "quarantine-kryptonite.tsv");
66
- writeFileSync(qPath, quarantine.join("\n") + "\n", "utf8");
67
- report?.(`quarantine log → ${qPath}`);
68
- }
69
- // Stamp the new shard's source field for audit.ts (which prefers shard.source over
70
- // first_source_id-prefix inference). Without this, deepseek-kryptonite IDs would have
71
- // to match a prefix in KNOWN_SOURCE_PREFIXES — we add it there too as a belt-and-braces.
72
- for (const sh of newManifest.shards) {
73
- sh.source = source;
74
- }
75
- // Compose the final corpus-v0.4.0 manifest: every shard from base + the new shard(s).
76
- const base = parseJSONStrict(readFileSync(options.baseManifest, "utf8"));
77
- const combined = {
78
- corpus_version: corpusVersion,
79
- schema: PARQUET_COLUMNS,
80
- rows_per_shard: base.rows_per_shard,
81
- row_group_size: base.row_group_size ?? ROW_GROUP_SIZE,
82
- shards: [...base.shards, ...newManifest.shards],
83
- counts: {
84
- train: base.counts.train + (newManifest.counts.train ?? 0),
85
- val: base.counts.val,
86
- test: base.counts.test,
87
- },
88
- total_rows: base.total_rows + newManifest.total_rows,
89
- };
90
- // Stamp source on the legacy v0.3.0 shards too, so audit's shard.source path is the
91
- // authoritative one. v0.3.0 shards mix sources; we use the first_source_id-prefix
92
- // inference for them (audit.ts will re-derive on its own when shard.source is absent).
93
- const combinedPath = join(options.outDir, `corpus-v${corpusVersion}`, "MANIFEST.json");
94
- writeFileSync(combinedPath, JSON.stringify(combined, null, 2) + "\n", "utf8");
95
- report?.(`wrote combined manifest → ${combinedPath}`);
96
- report?.(` total_rows=${combined.total_rows} (base=${base.total_rows}, added=${newManifest.total_rows})`);
97
- report?.(` shards=${combined.shards.length} (base=${base.shards.length}, added=${newManifest.shards.length})`);
98
- report?.(` compression=${SHARD_COMPRESSION}`);
99
- }
100
- //# sourceMappingURL=shard-kryptonite.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"shard-kryptonite.js","sourceRoot":"","sources":["../../../src/tools/shard-kryptonite.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAEH,OAAO,EAAE,UAAU,EAAE,YAAY,EAAE,aAAa,EAAE,MAAM,SAAS,CAAA;AACjE,OAAO,EAAE,KAAK,EAAE,MAAM,kBAAkB,CAAA;AACxC,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAEhC,OAAO,EAAE,eAAe,EAAE,MAAM,yBAAyB,CAAA;AACzD,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAG7C,OAAO,EAAE,QAAQ,EAAE,eAAe,EAAE,cAAc,EAAE,iBAAiB,EAAE,WAAW,EAAE,MAAM,QAAQ,CAAA;AAiBlG,KAAK,SAAS,CAAC,CAAC,aAAa,CAAC,KAAa,EAAE,aAAqB;IACjE,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,eAAe,CAAC,SAAS,CAA0B,KAAK,CAAC,EAAE,CAAC;QACnF,oFAAoF;QACpF,MAAM,UAAU,GAAG,GAAG,CAAC,YAAY,CAA2B,CAAA;QAE9D,MAAM;YACL,GAAG,EAAE,GAAG,CAAC,KAAK,CAAW;YACzB,UAAU;YACV,OAAO,EAAG,GAAG,CAAC,SAAS,CAAY,IAAI,IAAI;YAC3C,MAAM,EAAG,GAAG,CAAC,QAAQ,CAAY,IAAI,SAAS;YAC9C,MAAM,EAAG,GAAG,CAAC,QAAQ,CAAY,IAAI,qBAAqB;YAC1D,SAAS,EAAE,GAAG,CAAC,WAAW,CAAW;YACrC,cAAc,EAAE,aAAa;YAC7B,OAAO,EAAG,GAAG,CAAC,SAAS,CAAY,IAAI,gDAAgD;YACvF,KAAK,EAAE,GAAG,CAAC,OAAO,CAA0B;SAC5C,CAAA;IACF,CAAC;AACF,CAAC;AAED,KAAK,SAAS,CAAC,CAAC,WAAW,CAAC,KAAa,EAAE,aAAqB,EAAE,aAAuB;IACxF,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,aAAa,CAAC,KAAK,EAAE,aAAa,CAAC,EAAE,CAAC;QAC7D,MAAM,MAAM,GAAG,QAAQ,CAAC,GAAG,CAAC,CAAA;QAE5B,IAAI,MAAM,CAAC,IAAI,KAAK,SAAS,EAAE,CAAC;YAC/B,MAAM,MAAM,CAAC,GAAG,CAAA;QACjB,CAAC;aAAM,CAAC;YACP,aAAa,CAAC,IAAI,CAAC,GAAG,GAAG,CAAC,SAAS,KAAK,MAAM,CAAC,GAAG,CAAC,MAAM,EAAE,CAAC,CAAA;QAC7D,CAAC;IACF,CAAC;AACF,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,oBAAoB,CACzC,OAA+B,EAC/B,MAA+B;IAE/B,MAAM,aAAa,GAAG,OAAO,CAAC,aAAa,IAAI,OAAO,CAAA;IACtD,MAAM,MAAM,GAAG,OAAO,CAAC,MAAM,IAAI,qBAAqB,CAAA;IAEtD,IAAI,CAAC,UAAU,CAAC,OAAO,CAAC,KAAK,CAAC;QAAE,MAAM,IAAI,KAAK,CAAC,oBAAoB,OAAO,CAAC,KAAK,EAAE,CAAC,CAAA;IAEpF,IAAI,CAAC,UAAU,CAAC,OAAO,CAAC,YAAY,CAAC;QAAE,MAAM,IAAI,KAAK,CAAC,4BAA4B,OAAO,CAAC,YAAY,EAAE,CAAC,CAAA;IAE1G,MAAM,KAAK,CAAC,OAAO,CAAC,MAAM,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;IAEhD,MAAM,UAAU,GAAa,EAAE,CAAA;IAE/B,MAAM,WAAW,GAAG,MAAM,WAAW,CACpC,EAAE,KAAK,EAAE,WAAW,CAAC,OAAO,CAAC,KAAK,EAAE,aAAa,EAAE,UAAU,CAAC,EAAE,EAChE,EAAE,SAAS,EAAE,OAAO,CAAC,MAAM,EAAE,aAAa,EAAE,CAC5C,CAAA;IAED,MAAM,EAAE,CACP,SAAS,WAAW,CAAC,UAAU,cAAc,WAAW,CAAC,MAAM,CAAC,MAAM,aAAa;QAClF,eAAe,UAAU,CAAC,MAAM,EAAE,CACnC,CAAA;IAED,IAAI,UAAU,CAAC,MAAM,EAAE,CAAC;QACvB,MAAM,KAAK,GAAG,IAAI,CAAC,OAAO,CAAC,MAAM,EAAE,WAAW,aAAa,EAAE,EAAE,2BAA2B,CAAC,CAAA;QAC3F,aAAa,CAAC,KAAK,EAAE,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,IAAI,EAAE,MAAM,CAAC,CAAA;QAC1D,MAAM,EAAE,CAAC,oBAAoB,KAAK,EAAE,CAAC,CAAA;IACtC,CAAC;IAED,mFAAmF;IACnF,sFAAsF;IACtF,yFAAyF;IACzF,KAAK,MAAM,EAAE,IAAI,WAAW,CAAC,MAAM,EAAE,CAAC;QACrC,EAAE,CAAC,MAAM,GAAG,MAAM,CAAA;IACnB,CAAC;IAED,sFAAsF;IACtF,MAAM,IAAI,GAAG,eAAe,CAAgB,YAAY,CAAC,OAAO,CAAC,YAAY,EAAE,MAAM,CAAC,CAAC,CAAA;IAEvF,MAAM,QAAQ,GAAkB;QAC/B,cAAc,EAAE,aAAa;QAC7B,MAAM,EAAE,eAAe;QACvB,cAAc,EAAE,IAAI,CAAC,cAAc;QACnC,cAAc,EAAE,IAAI,CAAC,cAAc,IAAI,cAAc;QACrD,MAAM,EAAE,CAAC,GAAG,IAAI,CAAC,MAAM,EAAE,GAAG,WAAW,CAAC,MAAM,CAAC;QAC/C,MAAM,EAAE;YACP,KAAK,EAAE,IAAI,CAAC,MAAM,CAAC,KAAK,GAAG,CAAC,WAAW,CAAC,MAAM,CAAC,KAAK,IAAI,CAAC,CAAC;YAC1D,GAAG,EAAE,IAAI,CAAC,MAAM,CAAC,GAAG;YACpB,IAAI,EAAE,IAAI,CAAC,MAAM,CAAC,IAAI;SACtB;QACD,UAAU,EAAE,IAAI,CAAC,UAAU,GAAG,WAAW,CAAC,UAAU;KACpD,CAAA;IAED,oFAAoF;IACpF,kFAAkF;IAClF,uFAAuF;IACvF,MAAM,YAAY,GAAG,IAAI,CAAC,OAAO,CAAC,MAAM,EAAE,WAAW,aAAa,EAAE,EAAE,eAAe,CAAC,CAAA;IACtF,aAAa,CAAC,YAAY,EAAE,IAAI,CAAC,SAAS,CAAC,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC,GAAG,IAAI,EAAE,MAAM,CAAC,CAAA;IAC7E,MAAM,EAAE,CAAC,6BAA6B,YAAY,EAAE,CAAC,CAAA;IACrD,MAAM,EAAE,CAAC,gBAAgB,QAAQ,CAAC,UAAU,UAAU,IAAI,CAAC,UAAU,WAAW,WAAW,CAAC,UAAU,GAAG,CAAC,CAAA;IAC1G,MAAM,EAAE,CAAC,YAAY,QAAQ,CAAC,MAAM,CAAC,MAAM,UAAU,IAAI,CAAC,MAAM,CAAC,MAAM,WAAW,WAAW,CAAC,MAAM,CAAC,MAAM,GAAG,CAAC,CAAA;IAC/G,MAAM,EAAE,CAAC,iBAAiB,iBAAiB,EAAE,CAAC,CAAA;AAC/C,CAAC"}
@@ -1,51 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * Build per-script parquet shards from the DeepSeek-generated transliteration JSONL and emit the
7
- * corpus-v0.4.0 MANIFEST that combines them with the existing kryptonite + v0.3.0 shards.
8
- *
9
- * Sibling to `shard-kryptonite.ts`. The two modules share the same composition pattern: take a
10
- * base MANIFEST, append new shards, write a combined MANIFEST. Differences specific to
11
- * transliteration:
12
- *
13
- * - One JSONL contains rows from N target scripts (source = `deepseek-translit-<slug>`). We bucket by
14
- * `source` and write one shard per script so `audit.ts` can attribute each shard to its
15
- * synthetic source without relying on filename-prefix inference.
16
- * - Each shard is written to `train/part-translit-<slug>.parquet` (distinct from kryptonite's
17
- * `part-0000.parquet`, which v0.4.0's first builder already produced).
18
- * - Inherits the path-canonicalization fix flagged in Thread B's postmortem: v0.3.0 shard paths are
19
- * rewritten from `$MAILWOMAN_DATA_ROOT/...` to `/data/...` in the combined MANIFEST so
20
- * all paths share one container-friendly form.
21
- *
22
- * See docs/engineering/reference/CORPUS_V0_4_0_GENERATION.md for prompts, model, and the
23
- * reproducibility contract.
24
- *
25
- * Invoke via `mailwoman corpus shard translit \
26
- * --jsonl /data/corpus/versioned/v0.4.0/transliteration/canonical-transliteration.jsonl \
27
- * --base-manifest /data/corpus/versioned/v0.4.0/corpus-v0.4.0/MANIFEST.json \
28
- * --out-dir /data/corpus/versioned/v0.4.0`
29
- */
30
- export interface ShardTranslitOptions {
31
- jsonl: string;
32
- baseManifest: string;
33
- outDir: string;
34
- /**
35
- * Default `"0.4.0"`.
36
- */
37
- corpusVersion?: string;
38
- /**
39
- * Default `"/data/"`.
40
- */
41
- canonicalPathPrefix?: string;
42
- /**
43
- * Prefix the base manifest's shard paths currently carry, to be rewritten to
44
- * {@link ShardTranslitOptions.canonicalPathPrefix}. Defaults to `mailwomanDataRoot()` with a trailing slash — the
45
- * root that WROTE those paths. Pass it explicitly when translating a manifest generated under a different
46
- * `$MAILWOMAN_DATA_ROOT` than the one you are running with.
47
- */
48
- legacyPathPrefix?: string;
49
- }
50
- export declare function buildTranslitShard(options: ShardTranslitOptions, report?: (line: string) => void): Promise<void>;
51
- //# sourceMappingURL=shard-translit.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"shard-translit.d.ts","sourceRoot":"","sources":["../../../src/tools/shard-translit.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AAwBH,MAAM,WAAW,oBAAoB;IACpC,KAAK,EAAE,MAAM,CAAA;IACb,YAAY,EAAE,MAAM,CAAA;IACpB,MAAM,EAAE,MAAM,CAAA;IACd;;OAEG;IACH,aAAa,CAAC,EAAE,MAAM,CAAA;IACtB;;OAEG;IACH,mBAAmB,CAAC,EAAE,MAAM,CAAA;IAC5B;;;;;OAKG;IACH,gBAAgB,CAAC,EAAE,MAAM,CAAA;CACzB;AA0ED,wBAAsB,kBAAkB,CACvC,OAAO,EAAE,oBAAoB,EAC7B,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,IAAI,CAAC,CAgGf"}
@@ -1,175 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * Build per-script parquet shards from the DeepSeek-generated transliteration JSONL and emit the
7
- * corpus-v0.4.0 MANIFEST that combines them with the existing kryptonite + v0.3.0 shards.
8
- *
9
- * Sibling to `shard-kryptonite.ts`. The two modules share the same composition pattern: take a
10
- * base MANIFEST, append new shards, write a combined MANIFEST. Differences specific to
11
- * transliteration:
12
- *
13
- * - One JSONL contains rows from N target scripts (source = `deepseek-translit-<slug>`). We bucket by
14
- * `source` and write one shard per script so `audit.ts` can attribute each shard to its
15
- * synthetic source without relying on filename-prefix inference.
16
- * - Each shard is written to `train/part-translit-<slug>.parquet` (distinct from kryptonite's
17
- * `part-0000.parquet`, which v0.4.0's first builder already produced).
18
- * - Inherits the path-canonicalization fix flagged in Thread B's postmortem: v0.3.0 shard paths are
19
- * rewritten from `$MAILWOMAN_DATA_ROOT/...` to `/data/...` in the combined MANIFEST so
20
- * all paths share one container-friendly form.
21
- *
22
- * See docs/engineering/reference/CORPUS_V0_4_0_GENERATION.md for prompts, model, and the
23
- * reproducibility contract.
24
- *
25
- * Invoke via `mailwoman corpus shard translit \
26
- * --jsonl /data/corpus/versioned/v0.4.0/transliteration/canonical-transliteration.jsonl \
27
- * --base-manifest /data/corpus/versioned/v0.4.0/corpus-v0.4.0/MANIFEST.json \
28
- * --out-dir /data/corpus/versioned/v0.4.0`
29
- */
30
- import { existsSync, readFileSync, writeFileSync } from "node:fs";
31
- import { mkdir, stat } from "node:fs/promises";
32
- import { join } from "node:path";
33
- import { parseJSONStrict } from "@mailwoman/core/objects";
34
- import { mailwomanDataRoot, sha256File } from "@mailwoman/core/utils";
35
- import { JSONSpliterator } from "spliterator";
36
- import { alignRow, appendShape, LABELED_ROW_SCHEMA, PARQUET_COLUMNS, ROW_GROUP_SIZE, rowToParquet, SHARD_COMPRESSION, } from "#utils";
37
- import { ParquetWriter } from "../parquet-wrapper/index.js";
38
- function toCanonicalRow(raw, corpusVersion) {
39
- return {
40
- raw: raw["raw"],
41
- components: raw["components"],
42
- country: raw["country"] ?? "US",
43
- locale: raw["locale"] ?? undefined,
44
- source: raw["source"],
45
- source_id: raw["source_id"],
46
- corpus_version: corpusVersion,
47
- license: raw["license"] ?? "Synthetic (DeepSeek-v4-flash, AGPL-compatible)",
48
- synth: raw["synth"],
49
- };
50
- }
51
- /**
52
- * Write one shard for a single source slug. Returns the populated ShardDescriptor + a list of quarantine reasons for
53
- * rows that failed alignment.
54
- */
55
- async function writeOneShard(rows, outPath, source, corpusVersion) {
56
- const writer = await ParquetWriter.openFile(LABELED_ROW_SCHEMA, outPath, {
57
- rowGroupSize: ROW_GROUP_SIZE,
58
- });
59
- writer.setMetadata("mailwoman.corpus_version", corpusVersion);
60
- writer.setMetadata("mailwoman.split", "train");
61
- writer.setMetadata("mailwoman.shard_source", source);
62
- let firstSourceID = "";
63
- let lastSourceID = "";
64
- for (const row of rows) {
65
- const pq = rowToParquet(row);
66
- await writer.appendRow(appendShape(pq));
67
- if (firstSourceID === "") {
68
- firstSourceID = row.source_id;
69
- }
70
- lastSourceID = row.source_id;
71
- }
72
- await writer.close();
73
- const fileStat = await stat(outPath);
74
- const sha256 = await sha256File(outPath);
75
- return {
76
- split: "train",
77
- path: outPath,
78
- format: "parquet",
79
- compression: SHARD_COMPRESSION,
80
- rows: rows.length,
81
- bytes: fileStat.size,
82
- sha256,
83
- first_source_id: firstSourceID,
84
- last_source_id: lastSourceID,
85
- // Stamp source so audit.ts attributes the shard without falling back to filename-prefix inference.
86
- source,
87
- };
88
- }
89
- function canonicalizeShardPath(path, legacyPrefix, canonicalPrefix) {
90
- if (path.startsWith(legacyPrefix))
91
- return canonicalPrefix + path.slice(legacyPrefix.length);
92
- return path;
93
- }
94
- export async function buildTranslitShard(options, report) {
95
- const corpusVersion = options.corpusVersion ?? "0.4.0";
96
- // This is a portable manifest namespace, not a host filesystem default.
97
- const canonicalPathPrefix = options.canonicalPathPrefix ?? "/data/";
98
- const legacyPathPrefix = options.legacyPathPrefix ?? `${mailwomanDataRoot()}/`;
99
- if (!existsSync(options.jsonl))
100
- throw new Error(`jsonl not found: ${options.jsonl}`);
101
- if (!existsSync(options.baseManifest))
102
- throw new Error(`base-manifest not found: ${options.baseManifest}`);
103
- const corpusDir = join(options.outDir, `corpus-v${corpusVersion}`);
104
- const trainDir = join(corpusDir, "train");
105
- await mkdir(trainDir, { recursive: true });
106
- // Bucket canonical rows by source. Quarantined rows are logged.
107
- const buckets = new Map();
108
- const quarantine = [];
109
- let totalIn = 0;
110
- for await (const raw of JSONSpliterator.fromAsync(options.jsonl)) {
111
- totalIn++;
112
- const canon = toCanonicalRow(raw, corpusVersion);
113
- const result = alignRow(canon);
114
- if (result.kind !== "labeled") {
115
- quarantine.push(`${canon.source_id}\t${result.row.reason}`);
116
- continue;
117
- }
118
- const bucket = buckets.get(canon.source);
119
- if (bucket) {
120
- bucket.push(result.row);
121
- }
122
- else {
123
- buckets.set(canon.source, [result.row]);
124
- }
125
- }
126
- report?.(`read ${totalIn} rows; ${quarantine.length} quarantined; ${buckets.size} script buckets`);
127
- const newShards = [];
128
- const sortedKeys = [...buckets.keys()].toSorted();
129
- for (const source of sortedKeys) {
130
- const rows = buckets.get(source);
131
- const slug = source.startsWith("deepseek-translit-") ? source.slice("deepseek-translit-".length) : source;
132
- const outPath = join(trainDir, `part-translit-${slug}.parquet`);
133
- const descriptor = await writeOneShard(rows, outPath, source, corpusVersion);
134
- newShards.push(descriptor);
135
- report?.(` ${source}: ${descriptor.rows} rows → ${outPath} (${descriptor.bytes} bytes)`);
136
- }
137
- if (quarantine.length) {
138
- const qPath = join(corpusDir, "quarantine-transliteration.tsv");
139
- writeFileSync(qPath, quarantine.join("\n") + "\n", "utf8");
140
- report?.(`quarantine log → ${qPath} (${quarantine.length} rows)`);
141
- }
142
- // Compose final MANIFEST: rewrite base.shards paths from /mnt/playpen/... → /data/... and append
143
- // the new translit shards. Kryptonite shard already lives in the base manifest (it was written
144
- // there by Thread B).
145
- const base = parseJSONStrict(readFileSync(options.baseManifest, "utf8"));
146
- const rewrittenBase = base.shards.map((sh) => ({
147
- ...sh,
148
- path: canonicalizeShardPath(sh.path, legacyPathPrefix, canonicalPathPrefix),
149
- }));
150
- const newTrainRows = newShards.reduce((sum, sh) => sum + sh.rows, 0);
151
- const combined = {
152
- corpus_version: corpusVersion,
153
- schema: PARQUET_COLUMNS,
154
- rows_per_shard: base.rows_per_shard,
155
- row_group_size: base.row_group_size ?? ROW_GROUP_SIZE,
156
- shards: [...rewrittenBase, ...newShards],
157
- counts: {
158
- train: base.counts.train + newTrainRows,
159
- val: base.counts.val,
160
- test: base.counts.test,
161
- },
162
- total_rows: base.total_rows + newTrainRows,
163
- };
164
- const combinedPath = join(corpusDir, "MANIFEST.json");
165
- writeFileSync(combinedPath, JSON.stringify(combined, null, 2) + "\n", "utf8");
166
- report?.(`wrote combined manifest → ${combinedPath}`);
167
- report?.(` total_rows=${combined.total_rows} (base=${base.total_rows}, added=${newTrainRows})`);
168
- report?.(` shards=${combined.shards.length} (base=${base.shards.length}, added=${newShards.length})`);
169
- report?.(` compression=${SHARD_COMPRESSION}`);
170
- const pathFix = rewrittenBase.filter((s, i) => s.path !== base.shards[i].path).length;
171
- if (pathFix > 0) {
172
- report?.(` path-canonicalized base shards: ${pathFix} (legacy '${legacyPathPrefix}' → '${canonicalPathPrefix}')`);
173
- }
174
- }
175
- //# sourceMappingURL=shard-translit.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"shard-translit.js","sourceRoot":"","sources":["../../../src/tools/shard-translit.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AAEH,OAAO,EAAE,UAAU,EAAE,YAAY,EAAE,aAAa,EAAE,MAAM,SAAS,CAAA;AACjE,OAAO,EAAE,KAAK,EAAE,IAAI,EAAE,MAAM,kBAAkB,CAAA;AAC9C,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAEhC,OAAO,EAAE,eAAe,EAAE,MAAM,yBAAyB,CAAA;AACzD,OAAO,EAAE,iBAAiB,EAAE,UAAU,EAAE,MAAM,uBAAuB,CAAA;AACrE,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAG7C,OAAO,EACN,QAAQ,EACR,WAAW,EACX,kBAAkB,EAClB,eAAe,EACf,cAAc,EACd,YAAY,EACZ,iBAAiB,GACjB,MAAM,QAAQ,CAAA;AAGf,OAAO,EAAE,aAAa,EAAE,MAAM,6BAA6B,CAAA;AAuB3D,SAAS,cAAc,CAAC,GAA4B,EAAE,aAAqB;IAC1E,OAAO;QACN,GAAG,EAAE,GAAG,CAAC,KAAK,CAAW;QACzB,UAAU,EAAE,GAAG,CAAC,YAAY,CAA2B;QACvD,OAAO,EAAG,GAAG,CAAC,SAAS,CAAY,IAAI,IAAI;QAC3C,MAAM,EAAG,GAAG,CAAC,QAAQ,CAAY,IAAI,SAAS;QAC9C,MAAM,EAAE,GAAG,CAAC,QAAQ,CAAW;QAC/B,SAAS,EAAE,GAAG,CAAC,WAAW,CAAW;QACrC,cAAc,EAAE,aAAa;QAC7B,OAAO,EAAG,GAAG,CAAC,SAAS,CAAY,IAAI,gDAAgD;QACvF,KAAK,EAAE,GAAG,CAAC,OAAO,CAA0B;KAC5C,CAAA;AACF,CAAC;AAED;;;GAGG;AACH,KAAK,UAAU,aAAa,CAC3B,IAA2B,EAC3B,OAAe,EACf,MAAc,EACd,aAAqB;IAErB,MAAM,MAAM,GAAG,MAAM,aAAa,CAAC,QAAQ,CAAa,kBAAkB,EAAE,OAAO,EAAE;QACpF,YAAY,EAAE,cAAc;KAC5B,CAAC,CAAA;IAEF,MAAM,CAAC,WAAW,CAAC,0BAA0B,EAAE,aAAa,CAAC,CAAA;IAC7D,MAAM,CAAC,WAAW,CAAC,iBAAiB,EAAE,OAAO,CAAC,CAAA;IAC9C,MAAM,CAAC,WAAW,CAAC,wBAAwB,EAAE,MAAM,CAAC,CAAA;IAEpD,IAAI,aAAa,GAAG,EAAE,CAAA;IACtB,IAAI,YAAY,GAAG,EAAE,CAAA;IAErB,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;QACxB,MAAM,EAAE,GAAG,YAAY,CAAC,GAAG,CAAC,CAAA;QAC5B,MAAM,MAAM,CAAC,SAAS,CAAC,WAAW,CAAC,EAAE,CAAC,CAAC,CAAA;QAEvC,IAAI,aAAa,KAAK,EAAE,EAAE,CAAC;YAC1B,aAAa,GAAG,GAAG,CAAC,SAAS,CAAA;QAC9B,CAAC;QAED,YAAY,GAAG,GAAG,CAAC,SAAS,CAAA;IAC7B,CAAC;IAED,MAAM,MAAM,CAAC,KAAK,EAAE,CAAA;IAEpB,MAAM,QAAQ,GAAG,MAAM,IAAI,CAAC,OAAO,CAAC,CAAA;IACpC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,OAAO,CAAC,CAAA;IAExC,OAAO;QACN,KAAK,EAAE,OAAO;QACd,IAAI,EAAE,OAAO;QACb,MAAM,EAAE,SAAS;QACjB,WAAW,EAAE,iBAAiB;QAC9B,IAAI,EAAE,IAAI,CAAC,MAAM;QACjB,KAAK,EAAE,QAAQ,CAAC,IAAI;QACpB,MAAM;QACN,eAAe,EAAE,aAAa;QAC9B,cAAc,EAAE,YAAY;QAC5B,mGAAmG;QACnG,MAAM;KACN,CAAA;AACF,CAAC;AAED,SAAS,qBAAqB,CAAC,IAAY,EAAE,YAAoB,EAAE,eAAuB;IACzF,IAAI,IAAI,CAAC,UAAU,CAAC,YAAY,CAAC;QAAE,OAAO,eAAe,GAAG,IAAI,CAAC,KAAK,CAAC,YAAY,CAAC,MAAM,CAAC,CAAA;IAE3F,OAAO,IAAI,CAAA;AACZ,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,kBAAkB,CACvC,OAA6B,EAC7B,MAA+B;IAE/B,MAAM,aAAa,GAAG,OAAO,CAAC,aAAa,IAAI,OAAO,CAAA;IACtD,wEAAwE;IACxE,MAAM,mBAAmB,GAAG,OAAO,CAAC,mBAAmB,IAAI,QAAQ,CAAA;IACnE,MAAM,gBAAgB,GAAG,OAAO,CAAC,gBAAgB,IAAI,GAAG,iBAAiB,EAAE,GAAG,CAAA;IAE9E,IAAI,CAAC,UAAU,CAAC,OAAO,CAAC,KAAK,CAAC;QAAE,MAAM,IAAI,KAAK,CAAC,oBAAoB,OAAO,CAAC,KAAK,EAAE,CAAC,CAAA;IAEpF,IAAI,CAAC,UAAU,CAAC,OAAO,CAAC,YAAY,CAAC;QAAE,MAAM,IAAI,KAAK,CAAC,4BAA4B,OAAO,CAAC,YAAY,EAAE,CAAC,CAAA;IAE1G,MAAM,SAAS,GAAG,IAAI,CAAC,OAAO,CAAC,MAAM,EAAE,WAAW,aAAa,EAAE,CAAC,CAAA;IAClE,MAAM,QAAQ,GAAG,IAAI,CAAC,SAAS,EAAE,OAAO,CAAC,CAAA;IACzC,MAAM,KAAK,CAAC,QAAQ,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;IAE1C,gEAAgE;IAChE,MAAM,OAAO,GAAG,IAAI,GAAG,EAAwB,CAAA;IAC/C,MAAM,UAAU,GAAa,EAAE,CAAA;IAC/B,IAAI,OAAO,GAAG,CAAC,CAAA;IAEf,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,eAAe,CAAC,SAAS,CAA0B,OAAO,CAAC,KAAK,CAAC,EAAE,CAAC;QAC3F,OAAO,EAAE,CAAA;QACT,MAAM,KAAK,GAAG,cAAc,CAAC,GAAG,EAAE,aAAa,CAAC,CAAA;QAChD,MAAM,MAAM,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAA;QAE9B,IAAI,MAAM,CAAC,IAAI,KAAK,SAAS,EAAE,CAAC;YAC/B,UAAU,CAAC,IAAI,CAAC,GAAG,KAAK,CAAC,SAAS,KAAK,MAAM,CAAC,GAAG,CAAC,MAAM,EAAE,CAAC,CAAA;YAE3D,SAAQ;QACT,CAAC;QAED,MAAM,MAAM,GAAG,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,MAAM,CAAC,CAAA;QAExC,IAAI,MAAM,EAAE,CAAC;YACZ,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,CAAA;QACxB,CAAC;aAAM,CAAC;YACP,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,MAAM,EAAE,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAA;QACxC,CAAC;IACF,CAAC;IAED,MAAM,EAAE,CAAC,QAAQ,OAAO,UAAU,UAAU,CAAC,MAAM,iBAAiB,OAAO,CAAC,IAAI,iBAAiB,CAAC,CAAA;IAElG,MAAM,SAAS,GAAsB,EAAE,CAAA;IACvC,MAAM,UAAU,GAAG,CAAC,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,QAAQ,EAAE,CAAA;IAEjD,KAAK,MAAM,MAAM,IAAI,UAAU,EAAE,CAAC;QACjC,MAAM,IAAI,GAAG,OAAO,CAAC,GAAG,CAAC,MAAM,CAAE,CAAA;QACjC,MAAM,IAAI,GAAG,MAAM,CAAC,UAAU,CAAC,oBAAoB,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,oBAAoB,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAA;QACzG,MAAM,OAAO,GAAG,IAAI,CAAC,QAAQ,EAAE,iBAAiB,IAAI,UAAU,CAAC,CAAA;QAC/D,MAAM,UAAU,GAAG,MAAM,aAAa,CAAC,IAAI,EAAE,OAAO,EAAE,MAAM,EAAE,aAAa,CAAC,CAAA;QAC5E,SAAS,CAAC,IAAI,CAAC,UAAU,CAAC,CAAA;QAC1B,MAAM,EAAE,CAAC,KAAK,MAAM,KAAK,UAAU,CAAC,IAAI,WAAW,OAAO,KAAK,UAAU,CAAC,KAAK,SAAS,CAAC,CAAA;IAC1F,CAAC;IAED,IAAI,UAAU,CAAC,MAAM,EAAE,CAAC;QACvB,MAAM,KAAK,GAAG,IAAI,CAAC,SAAS,EAAE,gCAAgC,CAAC,CAAA;QAC/D,aAAa,CAAC,KAAK,EAAE,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,IAAI,EAAE,MAAM,CAAC,CAAA;QAC1D,MAAM,EAAE,CAAC,oBAAoB,KAAK,KAAK,UAAU,CAAC,MAAM,QAAQ,CAAC,CAAA;IAClE,CAAC;IAED,iGAAiG;IACjG,+FAA+F;IAC/F,sBAAsB;IACtB,MAAM,IAAI,GAAG,eAAe,CAAgB,YAAY,CAAC,OAAO,CAAC,YAAY,EAAE,MAAM,CAAC,CAAC,CAAA;IAEvF,MAAM,aAAa,GAAG,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,EAAE,EAAE,EAAE,CAAC,CAAC;QAC9C,GAAG,EAAE;QACL,IAAI,EAAE,qBAAqB,CAAC,EAAE,CAAC,IAAI,EAAE,gBAAgB,EAAE,mBAAmB,CAAC;KAC3E,CAAC,CAAC,CAAA;IAEH,MAAM,YAAY,GAAG,SAAS,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,EAAE,EAAE,EAAE,CAAC,GAAG,GAAG,EAAE,CAAC,IAAI,EAAE,CAAC,CAAC,CAAA;IAEpE,MAAM,QAAQ,GAAkB;QAC/B,cAAc,EAAE,aAAa;QAC7B,MAAM,EAAE,eAAe;QACvB,cAAc,EAAE,IAAI,CAAC,cAAc;QACnC,cAAc,EAAE,IAAI,CAAC,cAAc,IAAI,cAAc;QACrD,MAAM,EAAE,CAAC,GAAG,aAAa,EAAE,GAAG,SAAS,CAAC;QACxC,MAAM,EAAE;YACP,KAAK,EAAE,IAAI,CAAC,MAAM,CAAC,KAAK,GAAG,YAAY;YACvC,GAAG,EAAE,IAAI,CAAC,MAAM,CAAC,GAAG;YACpB,IAAI,EAAE,IAAI,CAAC,MAAM,CAAC,IAAI;SACtB;QACD,UAAU,EAAE,IAAI,CAAC,UAAU,GAAG,YAAY;KAC1C,CAAA;IAED,MAAM,YAAY,GAAG,IAAI,CAAC,SAAS,EAAE,eAAe,CAAC,CAAA;IACrD,aAAa,CAAC,YAAY,EAAE,IAAI,CAAC,SAAS,CAAC,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC,GAAG,IAAI,EAAE,MAAM,CAAC,CAAA;IAC7E,MAAM,EAAE,CAAC,6BAA6B,YAAY,EAAE,CAAC,CAAA;IACrD,MAAM,EAAE,CAAC,gBAAgB,QAAQ,CAAC,UAAU,UAAU,IAAI,CAAC,UAAU,WAAW,YAAY,GAAG,CAAC,CAAA;IAChG,MAAM,EAAE,CAAC,YAAY,QAAQ,CAAC,MAAM,CAAC,MAAM,UAAU,IAAI,CAAC,MAAM,CAAC,MAAM,WAAW,SAAS,CAAC,MAAM,GAAG,CAAC,CAAA;IACtG,MAAM,EAAE,CAAC,iBAAiB,iBAAiB,EAAE,CAAC,CAAA;IAC9C,MAAM,OAAO,GAAG,aAAa,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,KAAK,IAAI,CAAC,MAAM,CAAC,CAAC,CAAE,CAAC,IAAI,CAAC,CAAC,MAAM,CAAA;IAEtF,IAAI,OAAO,GAAG,CAAC,EAAE,CAAC;QACjB,MAAM,EAAE,CAAC,qCAAqC,OAAO,aAAa,gBAAgB,QAAQ,mBAAmB,IAAI,CAAC,CAAA;IACnH,CAAC;AACF,CAAC"}
@@ -1,100 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * @file The harvest side of the sub-venue lexicon: what one row of a harvestable source looks like,
7
- * how a file of them is read back, and what a pass over them extracts — attested surfaces plus the
8
- * measured shape of each designator's identifier half.
9
- *
10
- * {@link SubVenueHarvestRow} is SOURCE-NEUTRAL, and verified so: an Overture Places row from the
11
- * `airport_terminal` category is `{ designatorID, name }` and fits unchanged. It is declared here
12
- * rather than imported so the builder does not take a dependency on `@mailwoman/osm` (which
13
- * `@mailwoman/corpus` does not depend on) just to name a shape it reads from a file.
14
- *
15
- * Two measurements shape {@link extractAttestedPhrases}, and both are the reason it is safe to run
16
- * over raw OSM at all:
17
- *
18
- * **A feature's `name` is usually the VENUE's name, not a sub-venue phrase.** On the Berlin extract
19
- * (2,060 matched features) a `railway=platform` is named `Stendaler Straße` and an `amenity=university`
20
- * is named `Hertie School`; across 250,116 named Great Britain features only 6,003 (2.40%) contain a
21
- * designator token at all. So names are not harvested wholesale — a name contributes only when it
22
- * CONTAINS a phrase already in the surface index, which is what makes `Terminal E (Untere Ebene)`
23
- * evidence and `Otto Lilienthal Flughafen Berlin Tegel` not.
24
- *
25
- * **A matched phrase belongs to the record the PHRASE names, not the record the ROW carries.**
26
- * Attributing every hit to `row.designatorID` — the rule that matched the FEATURE — produced `west →
27
- * platform`, `hall → platform` and `biggin → platform` on the GB extract, because a bus stop tagged
28
- * `public_transport=platform` is named "Village Hall" or "West Kensington"; 108 of 133 OSM-derived
29
- * surfaces named a different record than the one they pointed at. Attribution therefore runs through
30
- * the index, and the row's own designator is kept as `context` — exactly the axis a confound board
31
- * needs, since a `hall` seen on a platform is a confound and a `hall` seen on a terminal is evidence.
32
- */
33
- import { type SurfaceIndex } from "./surfaces.ts";
34
- import type { IdentifierShape, SubVenueSurface } from "./table.ts";
35
- /**
36
- * One row of a harvestable source, as read back off JSONL or out of a layer database.
37
- *
38
- * SOURCE-NEUTRAL by design, and verified so in wave 2: an Overture Places row from the `airport_terminal` category is
39
- * `{ designatorID, name }` and fits unchanged. What did NOT fit was the harvest function's hardcoded `osm:name` source
40
- * stamp — see `overture-subvenue.ts`'s docstring. Declared locally so the builder does not import `@mailwoman/osm`
41
- * (which `@mailwoman/corpus` does not depend on) just to name a shape it reads from a file.
42
- */
43
- export interface SubVenueHarvestRow {
44
- /**
45
- * The designator the SOURCE's rule assigned to the FEATURE. Not necessarily the record a matched phrase names — see
46
- * this file's header on phrase attribution. Carried into {@link SubVenueSurface.context}.
47
- */
48
- designatorID: string;
49
- /**
50
- * `venue` (station, airport, campus) or `sub_venue`, when the source's rule assigns one. The harvest itself does not
51
- * read it; the sub-venue shard recipe fills its venue slot from it.
52
- */
53
- tier?: string;
54
- name?: string | null;
55
- ref?: string | null;
56
- localizedNames?: Record<string, string>;
57
- }
58
- /**
59
- * Classify an OSM `ref` into an {@link IdentifierShape} class.
60
- *
61
- * The classes are the ones Berlin's gates actually produced, plus the two aviation forms the corpus task names
62
- * (`Terminal 2F` is digit-letter, `Concourse B` is letter). `range` covers both separators OSM uses for a gate serving
63
- * more than one stand: `16-18` and `0/1`.
64
- */
65
- export declare function classifyIdentifier(ref: string): string;
66
- /**
67
- * Options for one harvest pass — which source stamp its surfaces carry and which region they were attested in.
68
- *
69
- * Both default to the OSM/unknown-region values wave 1 hardcoded, so an existing caller is unchanged.
70
- */
71
- export interface HarvestOptions {
72
- /**
73
- * Source family: `osm` yields `osm:name` / `osm:name:<lang>`, `overture` yields `overture:name`.
74
- */
75
- source?: string;
76
- /**
77
- * ISO 3166-1 alpha-2 of the extract or partition. `""` when unknown.
78
- */
79
- region?: string;
80
- }
81
- /**
82
- * Harvest attested phrases and identifier shapes out of a source's rows.
83
- *
84
- * `index` gates the name harvest — a name contributes only when it CONTAINS a phrase already in the table. That filter
85
- * is the whole reason this function is safe to run over raw OSM: see this file's header for the Berlin measurement that
86
- * motivated it. The index also decides ATTRIBUTION: a hit is a surface of the record the PHRASE names, and the row's
87
- * own designator is recorded as `context`.
88
- *
89
- * Returns surfaces with real `observations` counts, so the lexicon can rank `terminal` above a phrase attested once.
90
- */
91
- export declare function extractAttestedPhrases(rows: Iterable<SubVenueHarvestRow>, index: SurfaceIndex, options?: HarvestOptions): {
92
- surfaces: SubVenueSurface[];
93
- identifierShapes: IdentifierShape[];
94
- };
95
- /**
96
- * Read a JSONL file of {@link SubVenueHarvestRow}s. Blank lines and unparseable rows are skipped rather than fatal — an
97
- * extract is a build output, and one malformed line should not cost the whole lexicon.
98
- */
99
- export declare function readSubVenueJSONL(path: string): SubVenueHarvestRow[];
100
- //# sourceMappingURL=harvest.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"harvest.d.ts","sourceRoot":"","sources":["../../../../src/tools/sub-venue/harvest.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA+BG;AAOH,OAAO,EAAwB,KAAK,YAAY,EAAE,MAAM,eAAe,CAAA;AACvE,OAAO,KAAK,EAAE,eAAe,EAAE,eAAe,EAAE,MAAM,YAAY,CAAA;AAElE;;;;;;;GAOG;AACH,MAAM,WAAW,kBAAkB;IAClC;;;OAGG;IACH,YAAY,EAAE,MAAM,CAAA;IACpB;;;OAGG;IACH,IAAI,CAAC,EAAE,MAAM,CAAA;IACb,IAAI,CAAC,EAAE,MAAM,GAAG,IAAI,CAAA;IACpB,GAAG,CAAC,EAAE,MAAM,GAAG,IAAI,CAAA;IACnB,cAAc,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;CACvC;AAED;;;;;;GAMG;AACH,wBAAgB,kBAAkB,CAAC,GAAG,EAAE,MAAM,GAAG,MAAM,CActD;AAYD;;;;GAIG;AACH,MAAM,WAAW,cAAc;IAC9B;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,CAAA;IACf;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,CAAA;CACf;AAED;;;;;;;;;GASG;AACH,wBAAgB,sBAAsB,CACrC,IAAI,EAAE,QAAQ,CAAC,kBAAkB,CAAC,EAClC,KAAK,EAAE,YAAY,EACnB,OAAO,GAAE,cAAmB,GAC1B;IAAE,QAAQ,EAAE,eAAe,EAAE,CAAC;IAAC,gBAAgB,EAAE,eAAe,EAAE,CAAA;CAAE,CAiFtE;AAED;;;GAGG;AACH,wBAAgB,iBAAiB,CAAC,IAAI,EAAE,MAAM,GAAG,kBAAkB,EAAE,CAmBpE"}