@mailwoman/corpus 9.2.0 → 9.4.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (1261) hide show
  1. package/README.md +22 -22
  2. package/data/PROVENANCE.md +7 -7
  3. package/lib/adapters/ban/adapter.ts +190 -0
  4. package/lib/adapters/ban/street-decompose.ts +66 -0
  5. package/lib/adapters/fcc-bdc/adapter.ts +174 -0
  6. package/lib/adapters/geonames/adapter.ts +199 -0
  7. package/lib/adapters/geonames-postal/adapter.ts +122 -0
  8. package/lib/adapters/gnaf/adapter.ts +149 -0
  9. package/lib/adapters/gnaf/assemble.ts +225 -0
  10. package/lib/adapters/index.ts +153 -0
  11. package/lib/adapters/openaddresses/adapter.ts +251 -0
  12. package/lib/adapters/overture/adapter.ts +162 -0
  13. package/lib/adapters/state-hi-schools/adapter.ts +170 -0
  14. package/lib/adapters/state-hi-schools/workbook.ts +35 -0
  15. package/lib/adapters/synth-po-box/adapter.ts +204 -0
  16. package/lib/adapters/tiger/adapter.ts +252 -0
  17. package/lib/adapters/tiger/street-decompose.ts +83 -0
  18. package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +167 -0
  19. package/lib/adapters/usgov-imls-pls/adapter.ts +143 -0
  20. package/lib/adapters/usgov-irs-bmf/adapter.ts +151 -0
  21. package/lib/adapters/usgov-nad/adapter.ts +334 -0
  22. package/lib/adapters/usgov-nppes/adapter.ts +151 -0
  23. package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +193 -0
  24. package/lib/adapters/utils/index.ts +307 -0
  25. package/lib/adapters/wof-admin-jp/adapter.ts +214 -0
  26. package/lib/adapters/wof-admin-json/adapter.ts +231 -0
  27. package/lib/adapters/wof-json-rows.ts +129 -0
  28. package/lib/adapters/wof-postalcode-json/adapter.ts +176 -0
  29. package/lib/build.ts +378 -0
  30. package/lib/env.ts +50 -0
  31. package/lib/index.ts +13 -0
  32. package/lib/recipes/anchor-absorption.ts +101 -0
  33. package/lib/recipes/bare-country.ts +95 -0
  34. package/lib/recipes/boundary-stress.ts +102 -0
  35. package/lib/recipes/cn-organizational-units.ts +199 -0
  36. package/lib/recipes/country-balanced.ts +510 -0
  37. package/lib/recipes/cz-pcfirst-preposition.ts +112 -0
  38. package/lib/recipes/fr-admin-split.ts +243 -0
  39. package/lib/recipes/fr-bare-street.ts +171 -0
  40. package/lib/recipes/fr-fragment.ts +334 -0
  41. package/lib/recipes/fr-lieudit.ts +301 -0
  42. package/lib/recipes/fr-order.ts +246 -0
  43. package/lib/recipes/german.ts +360 -0
  44. package/lib/recipes/house-venue.ts +93 -0
  45. package/lib/recipes/index.ts +97 -0
  46. package/lib/recipes/intersection.ts +619 -0
  47. package/lib/recipes/locale.ts +600 -0
  48. package/lib/recipes/nl-postcode.ts +117 -0
  49. package/lib/recipes/no-fragment.ts +213 -0
  50. package/lib/recipes/no-street-led.ts +135 -0
  51. package/lib/recipes/no-street.ts +91 -0
  52. package/lib/recipes/po-box-cedex.ts +976 -0
  53. package/lib/recipes/po-box.ts +124 -0
  54. package/lib/recipes/reviewed-postcode-tail.ts +190 -0
  55. package/lib/recipes/scaffold.ts +468 -0
  56. package/lib/recipes/si-bare-village.ts +99 -0
  57. package/lib/recipes/street-affix.ts +805 -0
  58. package/lib/recipes/street-bare.ts +102 -0
  59. package/lib/recipes/street.ts +83 -0
  60. package/lib/recipes/sub-venue-sources.ts +878 -0
  61. package/lib/recipes/sub-venue.ts +998 -0
  62. package/lib/recipes/trailing-region.ts +178 -0
  63. package/lib/recipes/unit.ts +304 -0
  64. package/lib/runner.ts +312 -0
  65. package/lib/synthesizers/anchor-absorption.ts +288 -0
  66. package/lib/synthesizers/boundary-stress.ts +532 -0
  67. package/lib/synthesizers/german.ts +260 -0
  68. package/lib/synthesizers/house-venue.ts +308 -0
  69. package/lib/synthesizers/intersection.ts +233 -0
  70. package/lib/synthesizers/no-street.ts +327 -0
  71. package/lib/synthesizers/po-box.ts +323 -0
  72. package/lib/synthesizers/street.ts +269 -0
  73. package/lib/synthesizers/utils.ts +993 -0
  74. package/lib/test-kit/corpus-recipe.ts +86 -0
  75. package/lib/test-kit/index.ts +100 -0
  76. package/lib/tools/align-slice.ts +68 -0
  77. package/lib/tools/audit.ts +403 -0
  78. package/lib/tools/corpus-stats.ts +136 -0
  79. package/lib/tools/fetch/acra-sg.ts +174 -0
  80. package/lib/tools/fetch/ban.ts +289 -0
  81. package/lib/tools/fetch/download.ts +477 -0
  82. package/lib/tools/fetch/gcis-tw.ts +175 -0
  83. package/lib/tools/fetch/geonames-dump.ts +257 -0
  84. package/lib/tools/fetch/geonames-postal.ts +180 -0
  85. package/lib/tools/fetch/houjin-jp.ts +135 -0
  86. package/lib/tools/fetch/hrsa.ts +59 -0
  87. package/lib/tools/fetch/imls-pls.ts +149 -0
  88. package/lib/tools/fetch/index.ts +174 -0
  89. package/lib/tools/fetch/juso-kr.ts +165 -0
  90. package/lib/tools/fetch/localdata-kr.ts +194 -0
  91. package/lib/tools/fetch/nad.ts +341 -0
  92. package/lib/tools/fetch/nppes.ts +165 -0
  93. package/lib/tools/fetch/openaddresses.ts +347 -0
  94. package/lib/tools/fetch/ourairports.ts +170 -0
  95. package/lib/tools/fetch/ppd.ts +121 -0
  96. package/lib/tools/fetch/state-hi-schools.ts +161 -0
  97. package/lib/tools/fetch/state-sources.ts +146 -0
  98. package/lib/tools/fetch/tiger-full.ts +308 -0
  99. package/lib/tools/fetch/wikidata-subvenue.ts +384 -0
  100. package/lib/tools/golden-expand.ts +574 -0
  101. package/lib/tools/golden-promote.ts +337 -0
  102. package/lib/tools/golden-relabel-street.ts +686 -0
  103. package/lib/tools/index.ts +28 -0
  104. package/lib/tools/ingest-csv.ts +378 -0
  105. package/lib/tools/jsonl-to-parquet.ts +207 -0
  106. package/lib/tools/lint-slice-vocab.ts +388 -0
  107. package/lib/tools/lint-slice.ts +496 -0
  108. package/lib/tools/overlay-manifest.ts +148 -0
  109. package/lib/tools/overture-subvenue.ts +209 -0
  110. package/lib/tools/postcode-triples.ts +363 -0
  111. package/lib/tools/slice-kryptonite.ts +137 -0
  112. package/lib/tools/slice-translit.ts +218 -0
  113. package/lib/tools/sub-venue/harvest.ts +234 -0
  114. package/lib/tools/sub-venue/head-nouns.ts +245 -0
  115. package/lib/tools/sub-venue/surfaces.ts +95 -0
  116. package/lib/tools/sub-venue/table.ts +281 -0
  117. package/lib/tools/sub-venue/wikidata.ts +85 -0
  118. package/lib/tools/sub-venue-lexicon.ts +429 -0
  119. package/lib/tools/sub-venue-promotions.ts +330 -0
  120. package/lib/types.ts +247 -0
  121. package/lib/utils/align.ts +330 -0
  122. package/lib/utils/golden.ts +189 -0
  123. package/lib/utils/index.ts +14 -0
  124. package/lib/utils/parquet.ts +582 -0
  125. package/lib/utils/slice-stats.ts +95 -0
  126. package/lib/utils/split.ts +279 -0
  127. package/lib/utils/tokenize.ts +120 -0
  128. package/lib/utils/wof-json.ts +247 -0
  129. package/out/adapters/ban/adapter.d.ts.map +1 -0
  130. package/out/adapters/ban/adapter.js +149 -0
  131. package/out/adapters/ban/adapter.js.map +1 -0
  132. package/out/adapters/ban/street-decompose.d.ts.map +1 -0
  133. package/out/adapters/ban/street-decompose.js +51 -0
  134. package/out/adapters/ban/street-decompose.js.map +1 -0
  135. package/out/adapters/fcc-bdc/adapter.d.ts.map +1 -0
  136. package/out/adapters/fcc-bdc/adapter.js +144 -0
  137. package/out/adapters/fcc-bdc/adapter.js.map +1 -0
  138. package/out/adapters/geonames/adapter.d.ts.map +1 -0
  139. package/out/adapters/geonames/adapter.js +176 -0
  140. package/out/adapters/geonames/adapter.js.map +1 -0
  141. package/out/adapters/geonames-postal/adapter.d.ts +54 -0
  142. package/out/adapters/geonames-postal/adapter.d.ts.map +1 -0
  143. package/out/adapters/geonames-postal/adapter.js +107 -0
  144. package/out/adapters/geonames-postal/adapter.js.map +1 -0
  145. package/out/adapters/gnaf/adapter.d.ts +49 -0
  146. package/out/adapters/gnaf/adapter.d.ts.map +1 -0
  147. package/out/adapters/gnaf/adapter.js +124 -0
  148. package/out/adapters/gnaf/adapter.js.map +1 -0
  149. package/out/adapters/gnaf/assemble.d.ts +65 -0
  150. package/out/adapters/gnaf/assemble.d.ts.map +1 -0
  151. package/out/adapters/gnaf/assemble.js +154 -0
  152. package/out/adapters/gnaf/assemble.js.map +1 -0
  153. package/out/adapters/index.d.ts +51 -0
  154. package/out/adapters/index.d.ts.map +1 -0
  155. package/out/adapters/index.js +95 -0
  156. package/out/adapters/index.js.map +1 -0
  157. package/out/adapters/openaddresses/adapter.d.ts.map +1 -0
  158. package/out/adapters/openaddresses/adapter.js +186 -0
  159. package/out/adapters/openaddresses/adapter.js.map +1 -0
  160. package/out/adapters/overture/adapter.d.ts +48 -0
  161. package/out/adapters/overture/adapter.d.ts.map +1 -0
  162. package/out/adapters/overture/adapter.js +125 -0
  163. package/out/adapters/overture/adapter.js.map +1 -0
  164. package/out/adapters/state-hi-schools/adapter.d.ts +46 -0
  165. package/out/adapters/state-hi-schools/adapter.d.ts.map +1 -0
  166. package/out/adapters/state-hi-schools/adapter.js +145 -0
  167. package/out/adapters/state-hi-schools/adapter.js.map +1 -0
  168. package/out/adapters/state-hi-schools/workbook.d.ts +29 -0
  169. package/out/adapters/state-hi-schools/workbook.d.ts.map +1 -0
  170. package/out/adapters/state-hi-schools/workbook.js +20 -0
  171. package/out/adapters/state-hi-schools/workbook.js.map +1 -0
  172. package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
  173. package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
  174. package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
  175. package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
  176. package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
  177. package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
  178. package/out/adapters/synth-po-box/adapter.d.ts.map +1 -0
  179. package/out/adapters/synth-po-box/adapter.js +140 -0
  180. package/out/adapters/synth-po-box/adapter.js.map +1 -0
  181. package/out/adapters/tiger/adapter.d.ts +55 -0
  182. package/out/adapters/tiger/adapter.d.ts.map +1 -0
  183. package/out/adapters/tiger/adapter.js +201 -0
  184. package/out/adapters/tiger/adapter.js.map +1 -0
  185. package/out/adapters/tiger/street-decompose.d.ts.map +1 -0
  186. package/out/adapters/tiger/street-decompose.js +68 -0
  187. package/out/adapters/tiger/street-decompose.js.map +1 -0
  188. package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +56 -0
  189. package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -0
  190. package/out/adapters/usgov-hrsa-fqhc/adapter.js +132 -0
  191. package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -0
  192. package/out/adapters/usgov-imls-pls/adapter.d.ts +36 -0
  193. package/out/adapters/usgov-imls-pls/adapter.d.ts.map +1 -0
  194. package/out/adapters/usgov-imls-pls/adapter.js +114 -0
  195. package/out/adapters/usgov-imls-pls/adapter.js.map +1 -0
  196. package/out/adapters/usgov-irs-bmf/adapter.d.ts +37 -0
  197. package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -0
  198. package/out/adapters/usgov-irs-bmf/adapter.js +120 -0
  199. package/out/adapters/usgov-irs-bmf/adapter.js.map +1 -0
  200. package/out/adapters/usgov-nad/adapter.d.ts +48 -0
  201. package/out/adapters/usgov-nad/adapter.d.ts.map +1 -0
  202. package/out/adapters/usgov-nad/adapter.js +249 -0
  203. package/out/adapters/usgov-nad/adapter.js.map +1 -0
  204. package/out/adapters/usgov-nppes/adapter.d.ts.map +1 -0
  205. package/out/adapters/usgov-nppes/adapter.js +118 -0
  206. package/out/adapters/usgov-nppes/adapter.js.map +1 -0
  207. package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -0
  208. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +154 -0
  209. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -0
  210. package/out/adapters/utils/index.d.ts +191 -0
  211. package/out/adapters/utils/index.d.ts.map +1 -0
  212. package/out/adapters/utils/index.js +206 -0
  213. package/out/adapters/utils/index.js.map +1 -0
  214. package/out/adapters/wof-admin-jp/adapter.d.ts.map +1 -0
  215. package/out/adapters/wof-admin-jp/adapter.js +161 -0
  216. package/out/adapters/wof-admin-jp/adapter.js.map +1 -0
  217. package/out/adapters/wof-admin-json/adapter.d.ts +79 -0
  218. package/out/adapters/wof-admin-json/adapter.d.ts.map +1 -0
  219. package/out/adapters/wof-admin-json/adapter.js +197 -0
  220. package/out/adapters/wof-admin-json/adapter.js.map +1 -0
  221. package/out/adapters/wof-json-rows.d.ts +62 -0
  222. package/out/adapters/wof-json-rows.d.ts.map +1 -0
  223. package/out/adapters/wof-json-rows.js +83 -0
  224. package/out/adapters/wof-json-rows.js.map +1 -0
  225. package/out/adapters/wof-postalcode-json/adapter.d.ts +65 -0
  226. package/out/adapters/wof-postalcode-json/adapter.d.ts.map +1 -0
  227. package/out/adapters/wof-postalcode-json/adapter.js +151 -0
  228. package/out/adapters/wof-postalcode-json/adapter.js.map +1 -0
  229. package/out/build.d.ts +132 -0
  230. package/out/build.d.ts.map +1 -0
  231. package/out/build.js +245 -0
  232. package/out/build.js.map +1 -0
  233. package/out/codex/us-fips-state.d.ts.map +1 -0
  234. package/out/codex/us-fips-state.js.map +1 -0
  235. package/out/env.d.ts +46 -0
  236. package/out/env.d.ts.map +1 -0
  237. package/out/env.js +46 -0
  238. package/out/env.js.map +1 -0
  239. package/out/index.d.ts +13 -0
  240. package/out/index.d.ts.map +1 -0
  241. package/out/index.js +13 -0
  242. package/out/index.js.map +1 -0
  243. package/out/recipes/anchor-absorption.d.ts +20 -0
  244. package/out/recipes/anchor-absorption.d.ts.map +1 -0
  245. package/out/recipes/anchor-absorption.js +82 -0
  246. package/out/recipes/anchor-absorption.js.map +1 -0
  247. package/out/recipes/bare-country.d.ts +25 -0
  248. package/out/recipes/bare-country.d.ts.map +1 -0
  249. package/out/recipes/bare-country.js +88 -0
  250. package/out/recipes/bare-country.js.map +1 -0
  251. package/out/recipes/boundary-stress.d.ts +20 -0
  252. package/out/recipes/boundary-stress.d.ts.map +1 -0
  253. package/out/recipes/boundary-stress.js +84 -0
  254. package/out/recipes/boundary-stress.js.map +1 -0
  255. package/out/recipes/cn-organizational-units.d.ts +36 -0
  256. package/out/recipes/cn-organizational-units.d.ts.map +1 -0
  257. package/out/recipes/cn-organizational-units.js +159 -0
  258. package/out/recipes/cn-organizational-units.js.map +1 -0
  259. package/out/recipes/country-balanced.d.ts +32 -0
  260. package/out/recipes/country-balanced.d.ts.map +1 -0
  261. package/out/recipes/country-balanced.js +394 -0
  262. package/out/recipes/country-balanced.js.map +1 -0
  263. package/out/recipes/cz-pcfirst-preposition.d.ts +22 -0
  264. package/out/recipes/cz-pcfirst-preposition.d.ts.map +1 -0
  265. package/out/recipes/cz-pcfirst-preposition.js +101 -0
  266. package/out/recipes/cz-pcfirst-preposition.js.map +1 -0
  267. package/out/recipes/fr-admin-split.d.ts +38 -0
  268. package/out/recipes/fr-admin-split.d.ts.map +1 -0
  269. package/out/recipes/fr-admin-split.js +192 -0
  270. package/out/recipes/fr-admin-split.js.map +1 -0
  271. package/out/recipes/fr-bare-street.d.ts +28 -0
  272. package/out/recipes/fr-bare-street.d.ts.map +1 -0
  273. package/out/recipes/fr-bare-street.js +144 -0
  274. package/out/recipes/fr-bare-street.js.map +1 -0
  275. package/out/recipes/fr-fragment.d.ts +77 -0
  276. package/out/recipes/fr-fragment.d.ts.map +1 -0
  277. package/out/recipes/fr-fragment.js +277 -0
  278. package/out/recipes/fr-fragment.js.map +1 -0
  279. package/out/recipes/fr-lieudit.d.ts +32 -0
  280. package/out/recipes/fr-lieudit.d.ts.map +1 -0
  281. package/out/recipes/fr-lieudit.js +227 -0
  282. package/out/recipes/fr-lieudit.js.map +1 -0
  283. package/out/recipes/fr-order.d.ts +38 -0
  284. package/out/recipes/fr-order.d.ts.map +1 -0
  285. package/out/recipes/fr-order.js +198 -0
  286. package/out/recipes/fr-order.js.map +1 -0
  287. package/out/recipes/german.d.ts +44 -0
  288. package/out/recipes/german.d.ts.map +1 -0
  289. package/out/recipes/german.js +289 -0
  290. package/out/recipes/german.js.map +1 -0
  291. package/out/recipes/house-venue.d.ts +18 -0
  292. package/out/recipes/house-venue.d.ts.map +1 -0
  293. package/out/recipes/house-venue.js +74 -0
  294. package/out/recipes/house-venue.js.map +1 -0
  295. package/out/recipes/index.d.ts +24 -0
  296. package/out/recipes/index.d.ts.map +1 -0
  297. package/out/recipes/index.js +91 -0
  298. package/out/recipes/index.js.map +1 -0
  299. package/out/recipes/intersection.d.ts +42 -0
  300. package/out/recipes/intersection.d.ts.map +1 -0
  301. package/out/recipes/intersection.js +453 -0
  302. package/out/recipes/intersection.js.map +1 -0
  303. package/out/recipes/locale.d.ts +136 -0
  304. package/out/recipes/locale.d.ts.map +1 -0
  305. package/out/recipes/locale.js +460 -0
  306. package/out/recipes/locale.js.map +1 -0
  307. package/out/recipes/nl-postcode.d.ts +26 -0
  308. package/out/recipes/nl-postcode.d.ts.map +1 -0
  309. package/out/recipes/nl-postcode.js +103 -0
  310. package/out/recipes/nl-postcode.js.map +1 -0
  311. package/out/recipes/no-fragment.d.ts +43 -0
  312. package/out/recipes/no-fragment.d.ts.map +1 -0
  313. package/out/recipes/no-fragment.js +183 -0
  314. package/out/recipes/no-fragment.js.map +1 -0
  315. package/out/recipes/no-street-led.d.ts +24 -0
  316. package/out/recipes/no-street-led.d.ts.map +1 -0
  317. package/out/recipes/no-street-led.js +114 -0
  318. package/out/recipes/no-street-led.js.map +1 -0
  319. package/out/recipes/no-street.d.ts +18 -0
  320. package/out/recipes/no-street.d.ts.map +1 -0
  321. package/out/recipes/no-street.js +72 -0
  322. package/out/recipes/no-street.js.map +1 -0
  323. package/out/recipes/po-box-cedex.d.ts +38 -0
  324. package/out/recipes/po-box-cedex.d.ts.map +1 -0
  325. package/out/recipes/po-box-cedex.js +768 -0
  326. package/out/recipes/po-box-cedex.js.map +1 -0
  327. package/out/recipes/po-box.d.ts +17 -0
  328. package/out/recipes/po-box.d.ts.map +1 -0
  329. package/out/recipes/po-box.js +101 -0
  330. package/out/recipes/po-box.js.map +1 -0
  331. package/out/recipes/reviewed-postcode-tail.d.ts +47 -0
  332. package/out/recipes/reviewed-postcode-tail.d.ts.map +1 -0
  333. package/out/recipes/reviewed-postcode-tail.js +125 -0
  334. package/out/recipes/reviewed-postcode-tail.js.map +1 -0
  335. package/out/recipes/scaffold.d.ts +323 -0
  336. package/out/recipes/scaffold.d.ts.map +1 -0
  337. package/out/recipes/scaffold.js +174 -0
  338. package/out/recipes/scaffold.js.map +1 -0
  339. package/out/recipes/si-bare-village.d.ts +32 -0
  340. package/out/recipes/si-bare-village.d.ts.map +1 -0
  341. package/out/recipes/si-bare-village.js +89 -0
  342. package/out/recipes/si-bare-village.js.map +1 -0
  343. package/out/recipes/street-affix.d.ts +89 -0
  344. package/out/recipes/street-affix.d.ts.map +1 -0
  345. package/out/recipes/street-affix.js +563 -0
  346. package/out/recipes/street-affix.js.map +1 -0
  347. package/out/recipes/street-bare.d.ts +25 -0
  348. package/out/recipes/street-bare.d.ts.map +1 -0
  349. package/out/recipes/street-bare.js +87 -0
  350. package/out/recipes/street-bare.js.map +1 -0
  351. package/out/recipes/street.d.ts +15 -0
  352. package/out/recipes/street.d.ts.map +1 -0
  353. package/out/recipes/street.js +70 -0
  354. package/out/recipes/street.js.map +1 -0
  355. package/out/recipes/sub-venue-sources.d.ts +229 -0
  356. package/out/recipes/sub-venue-sources.d.ts.map +1 -0
  357. package/out/recipes/sub-venue-sources.js +654 -0
  358. package/out/recipes/sub-venue-sources.js.map +1 -0
  359. package/out/recipes/sub-venue.d.ts +269 -0
  360. package/out/recipes/sub-venue.d.ts.map +1 -0
  361. package/out/recipes/sub-venue.js +726 -0
  362. package/out/recipes/sub-venue.js.map +1 -0
  363. package/out/recipes/trailing-region.d.ts +74 -0
  364. package/out/recipes/trailing-region.d.ts.map +1 -0
  365. package/out/recipes/trailing-region.js +158 -0
  366. package/out/recipes/trailing-region.js.map +1 -0
  367. package/out/recipes/unit.d.ts +29 -0
  368. package/out/recipes/unit.d.ts.map +1 -0
  369. package/out/recipes/unit.js +231 -0
  370. package/out/recipes/unit.js.map +1 -0
  371. package/out/runner.d.ts +130 -0
  372. package/out/runner.d.ts.map +1 -0
  373. package/out/runner.js +185 -0
  374. package/out/runner.js.map +1 -0
  375. package/out/synthesizers/anchor-absorption.d.ts +63 -0
  376. package/out/synthesizers/anchor-absorption.d.ts.map +1 -0
  377. package/out/synthesizers/anchor-absorption.js +221 -0
  378. package/out/synthesizers/anchor-absorption.js.map +1 -0
  379. package/out/synthesizers/boundary-stress.d.ts +78 -0
  380. package/out/synthesizers/boundary-stress.d.ts.map +1 -0
  381. package/out/synthesizers/boundary-stress.js +455 -0
  382. package/out/synthesizers/boundary-stress.js.map +1 -0
  383. package/out/synthesizers/german.d.ts +115 -0
  384. package/out/synthesizers/german.d.ts.map +1 -0
  385. package/out/synthesizers/german.js +149 -0
  386. package/out/synthesizers/german.js.map +1 -0
  387. package/out/synthesizers/house-venue.d.ts +56 -0
  388. package/out/synthesizers/house-venue.d.ts.map +1 -0
  389. package/out/synthesizers/house-venue.js +247 -0
  390. package/out/synthesizers/house-venue.js.map +1 -0
  391. package/out/synthesizers/intersection.d.ts +52 -0
  392. package/out/synthesizers/intersection.d.ts.map +1 -0
  393. package/out/synthesizers/intersection.js +175 -0
  394. package/out/synthesizers/intersection.js.map +1 -0
  395. package/out/synthesizers/no-street.d.ts +72 -0
  396. package/out/synthesizers/no-street.d.ts.map +1 -0
  397. package/out/synthesizers/no-street.js +262 -0
  398. package/out/synthesizers/no-street.js.map +1 -0
  399. package/out/synthesizers/po-box.d.ts +108 -0
  400. package/out/synthesizers/po-box.d.ts.map +1 -0
  401. package/out/synthesizers/po-box.js +250 -0
  402. package/out/synthesizers/po-box.js.map +1 -0
  403. package/out/synthesizers/street.d.ts +54 -0
  404. package/out/synthesizers/street.d.ts.map +1 -0
  405. package/out/synthesizers/street.js +218 -0
  406. package/out/synthesizers/street.js.map +1 -0
  407. package/out/synthesizers/utils.d.ts +241 -0
  408. package/out/synthesizers/utils.d.ts.map +1 -0
  409. package/out/synthesizers/utils.js +776 -0
  410. package/out/synthesizers/utils.js.map +1 -0
  411. package/out/test-kit/corpus-recipe.d.ts +59 -0
  412. package/out/test-kit/corpus-recipe.d.ts.map +1 -0
  413. package/out/test-kit/corpus-recipe.js +39 -0
  414. package/out/test-kit/corpus-recipe.js.map +1 -0
  415. package/out/test-kit/index.d.ts +48 -0
  416. package/out/test-kit/index.d.ts.map +1 -0
  417. package/out/test-kit/index.js +78 -0
  418. package/out/test-kit/index.js.map +1 -0
  419. package/out/tools/align-slice.d.ts +7 -0
  420. package/out/tools/align-slice.d.ts.map +1 -0
  421. package/out/tools/align-slice.js +55 -0
  422. package/out/tools/align-slice.js.map +1 -0
  423. package/out/tools/audit.d.ts +29 -0
  424. package/out/tools/audit.d.ts.map +1 -0
  425. package/out/tools/audit.js +282 -0
  426. package/out/tools/audit.js.map +1 -0
  427. package/out/tools/corpus-stats.d.ts +44 -0
  428. package/out/tools/corpus-stats.d.ts.map +1 -0
  429. package/out/tools/corpus-stats.js +102 -0
  430. package/out/tools/corpus-stats.js.map +1 -0
  431. package/out/tools/fetch/acra-sg.d.ts +23 -0
  432. package/out/tools/fetch/acra-sg.d.ts.map +1 -0
  433. package/out/tools/fetch/acra-sg.js +126 -0
  434. package/out/tools/fetch/acra-sg.js.map +1 -0
  435. package/out/tools/fetch/ban.d.ts +31 -0
  436. package/out/tools/fetch/ban.d.ts.map +1 -0
  437. package/out/tools/fetch/ban.js +239 -0
  438. package/out/tools/fetch/ban.js.map +1 -0
  439. package/out/tools/fetch/download.d.ts +182 -0
  440. package/out/tools/fetch/download.d.ts.map +1 -0
  441. package/out/tools/fetch/download.js +318 -0
  442. package/out/tools/fetch/download.js.map +1 -0
  443. package/out/tools/fetch/gcis-tw.d.ts +23 -0
  444. package/out/tools/fetch/gcis-tw.d.ts.map +1 -0
  445. package/out/tools/fetch/gcis-tw.js +135 -0
  446. package/out/tools/fetch/gcis-tw.js.map +1 -0
  447. package/out/tools/fetch/geonames-dump.d.ts +91 -0
  448. package/out/tools/fetch/geonames-dump.d.ts.map +1 -0
  449. package/out/tools/fetch/geonames-dump.js +171 -0
  450. package/out/tools/fetch/geonames-dump.js.map +1 -0
  451. package/out/tools/fetch/geonames-postal.d.ts +76 -0
  452. package/out/tools/fetch/geonames-postal.d.ts.map +1 -0
  453. package/out/tools/fetch/geonames-postal.js +126 -0
  454. package/out/tools/fetch/geonames-postal.js.map +1 -0
  455. package/out/tools/fetch/houjin-jp.d.ts +24 -0
  456. package/out/tools/fetch/houjin-jp.d.ts.map +1 -0
  457. package/out/tools/fetch/houjin-jp.js +102 -0
  458. package/out/tools/fetch/houjin-jp.js.map +1 -0
  459. package/out/tools/fetch/hrsa.d.ts +18 -0
  460. package/out/tools/fetch/hrsa.d.ts.map +1 -0
  461. package/out/tools/fetch/hrsa.js +46 -0
  462. package/out/tools/fetch/hrsa.js.map +1 -0
  463. package/out/tools/fetch/imls-pls.d.ts +25 -0
  464. package/out/tools/fetch/imls-pls.d.ts.map +1 -0
  465. package/out/tools/fetch/imls-pls.js +108 -0
  466. package/out/tools/fetch/imls-pls.js.map +1 -0
  467. package/out/tools/fetch/index.d.ts +171 -0
  468. package/out/tools/fetch/index.d.ts.map +1 -0
  469. package/out/tools/fetch/index.js +170 -0
  470. package/out/tools/fetch/index.js.map +1 -0
  471. package/out/tools/fetch/juso-kr.d.ts +30 -0
  472. package/out/tools/fetch/juso-kr.d.ts.map +1 -0
  473. package/out/tools/fetch/juso-kr.js +120 -0
  474. package/out/tools/fetch/juso-kr.js.map +1 -0
  475. package/out/tools/fetch/localdata-kr.d.ts +30 -0
  476. package/out/tools/fetch/localdata-kr.d.ts.map +1 -0
  477. package/out/tools/fetch/localdata-kr.js +139 -0
  478. package/out/tools/fetch/localdata-kr.js.map +1 -0
  479. package/out/tools/fetch/nad.d.ts +70 -0
  480. package/out/tools/fetch/nad.d.ts.map +1 -0
  481. package/out/tools/fetch/nad.js +234 -0
  482. package/out/tools/fetch/nad.js.map +1 -0
  483. package/out/tools/fetch/nppes.d.ts +26 -0
  484. package/out/tools/fetch/nppes.d.ts.map +1 -0
  485. package/out/tools/fetch/nppes.js +126 -0
  486. package/out/tools/fetch/nppes.js.map +1 -0
  487. package/out/tools/fetch/openaddresses.d.ts +9 -0
  488. package/out/tools/fetch/openaddresses.d.ts.map +1 -0
  489. package/out/tools/fetch/openaddresses.js +279 -0
  490. package/out/tools/fetch/openaddresses.js.map +1 -0
  491. package/out/tools/fetch/ourairports.d.ts +45 -0
  492. package/out/tools/fetch/ourairports.d.ts.map +1 -0
  493. package/out/tools/fetch/ourairports.js +128 -0
  494. package/out/tools/fetch/ourairports.js.map +1 -0
  495. package/out/tools/fetch/ppd.d.ts.map +1 -0
  496. package/out/tools/fetch/ppd.js +85 -0
  497. package/out/tools/fetch/ppd.js.map +1 -0
  498. package/out/tools/fetch/state-hi-schools.d.ts +26 -0
  499. package/out/tools/fetch/state-hi-schools.d.ts.map +1 -0
  500. package/out/tools/fetch/state-hi-schools.js +112 -0
  501. package/out/tools/fetch/state-hi-schools.js.map +1 -0
  502. package/out/tools/fetch/state-sources.d.ts +26 -0
  503. package/out/tools/fetch/state-sources.d.ts.map +1 -0
  504. package/out/tools/fetch/state-sources.js +111 -0
  505. package/out/tools/fetch/state-sources.js.map +1 -0
  506. package/out/tools/fetch/tiger-full.d.ts +22 -0
  507. package/out/tools/fetch/tiger-full.d.ts.map +1 -0
  508. package/out/tools/fetch/tiger-full.js +217 -0
  509. package/out/tools/fetch/tiger-full.js.map +1 -0
  510. package/out/tools/fetch/wikidata-subvenue.d.ts +171 -0
  511. package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -0
  512. package/out/tools/fetch/wikidata-subvenue.js +274 -0
  513. package/out/tools/fetch/wikidata-subvenue.js.map +1 -0
  514. package/out/tools/gb-title-case.d.ts.map +1 -0
  515. package/out/tools/gb-title-case.js.map +1 -0
  516. package/out/tools/golden-expand.d.ts +90 -0
  517. package/out/tools/golden-expand.d.ts.map +1 -0
  518. package/out/tools/golden-expand.js +406 -0
  519. package/out/tools/golden-expand.js.map +1 -0
  520. package/out/tools/golden-promote.d.ts.map +1 -0
  521. package/out/tools/golden-promote.js +240 -0
  522. package/out/tools/golden-promote.js.map +1 -0
  523. package/out/tools/golden-relabel-street.d.ts +196 -0
  524. package/out/tools/golden-relabel-street.d.ts.map +1 -0
  525. package/out/tools/golden-relabel-street.js +439 -0
  526. package/out/tools/golden-relabel-street.js.map +1 -0
  527. package/out/tools/index.d.ts +28 -0
  528. package/out/tools/index.d.ts.map +1 -0
  529. package/out/tools/index.js +28 -0
  530. package/out/tools/index.js.map +1 -0
  531. package/out/tools/ingest-csv.d.ts.map +1 -0
  532. package/out/tools/ingest-csv.js +265 -0
  533. package/out/tools/ingest-csv.js.map +1 -0
  534. package/out/tools/jsonl-to-parquet.d.ts +61 -0
  535. package/out/tools/jsonl-to-parquet.d.ts.map +1 -0
  536. package/out/tools/jsonl-to-parquet.js +150 -0
  537. package/out/tools/jsonl-to-parquet.js.map +1 -0
  538. package/out/tools/lint-slice-vocab.d.ts +90 -0
  539. package/out/tools/lint-slice-vocab.d.ts.map +1 -0
  540. package/out/tools/lint-slice-vocab.js +267 -0
  541. package/out/tools/lint-slice-vocab.js.map +1 -0
  542. package/out/tools/lint-slice.d.ts +93 -0
  543. package/out/tools/lint-slice.d.ts.map +1 -0
  544. package/out/tools/lint-slice.js +322 -0
  545. package/out/tools/lint-slice.js.map +1 -0
  546. package/out/tools/overlay-manifest.d.ts +39 -0
  547. package/out/tools/overlay-manifest.d.ts.map +1 -0
  548. package/out/tools/overlay-manifest.js +90 -0
  549. package/out/tools/overlay-manifest.js.map +1 -0
  550. package/out/tools/overture-subvenue.d.ts +112 -0
  551. package/out/tools/overture-subvenue.d.ts.map +1 -0
  552. package/out/tools/overture-subvenue.js +139 -0
  553. package/out/tools/overture-subvenue.js.map +1 -0
  554. package/out/tools/postcode-triples.d.ts +174 -0
  555. package/out/tools/postcode-triples.d.ts.map +1 -0
  556. package/out/tools/postcode-triples.js +292 -0
  557. package/out/tools/postcode-triples.js.map +1 -0
  558. package/out/tools/slice-kryptonite.d.ts +32 -0
  559. package/out/tools/slice-kryptonite.d.ts.map +1 -0
  560. package/out/tools/slice-kryptonite.js +99 -0
  561. package/out/tools/slice-kryptonite.js.map +1 -0
  562. package/out/tools/slice-translit.d.ts +51 -0
  563. package/out/tools/slice-translit.d.ts.map +1 -0
  564. package/out/tools/slice-translit.js +166 -0
  565. package/out/tools/slice-translit.js.map +1 -0
  566. package/out/tools/sub-venue/harvest.d.ts +100 -0
  567. package/out/tools/sub-venue/harvest.d.ts.map +1 -0
  568. package/out/tools/sub-venue/harvest.js +168 -0
  569. package/out/tools/sub-venue/harvest.js.map +1 -0
  570. package/out/tools/sub-venue/head-nouns.d.ts +50 -0
  571. package/out/tools/sub-venue/head-nouns.d.ts.map +1 -0
  572. package/out/tools/sub-venue/head-nouns.js +213 -0
  573. package/out/tools/sub-venue/head-nouns.js.map +1 -0
  574. package/out/tools/sub-venue/surfaces.d.ts +45 -0
  575. package/out/tools/sub-venue/surfaces.d.ts.map +1 -0
  576. package/out/tools/sub-venue/surfaces.js +77 -0
  577. package/out/tools/sub-venue/surfaces.js.map +1 -0
  578. package/out/tools/sub-venue/table.d.ts +229 -0
  579. package/out/tools/sub-venue/table.d.ts.map +1 -0
  580. package/out/tools/sub-venue/table.js +108 -0
  581. package/out/tools/sub-venue/table.js.map +1 -0
  582. package/out/tools/sub-venue/wikidata.d.ts +26 -0
  583. package/out/tools/sub-venue/wikidata.d.ts.map +1 -0
  584. package/out/tools/sub-venue/wikidata.js +62 -0
  585. package/out/tools/sub-venue/wikidata.js.map +1 -0
  586. package/out/tools/sub-venue-lexicon.d.ts +156 -0
  587. package/out/tools/sub-venue-lexicon.d.ts.map +1 -0
  588. package/out/tools/sub-venue-lexicon.js +283 -0
  589. package/out/tools/sub-venue-lexicon.js.map +1 -0
  590. package/out/tools/sub-venue-promotions.d.ts +94 -0
  591. package/out/tools/sub-venue-promotions.d.ts.map +1 -0
  592. package/out/tools/sub-venue-promotions.js +266 -0
  593. package/out/tools/sub-venue-promotions.js.map +1 -0
  594. package/out/types.d.ts +221 -0
  595. package/out/types.d.ts.map +1 -0
  596. package/out/types.js.map +1 -0
  597. package/out/utils/align.d.ts +93 -0
  598. package/out/utils/align.d.ts.map +1 -0
  599. package/out/utils/align.js +234 -0
  600. package/out/utils/align.js.map +1 -0
  601. package/out/utils/golden.d.ts +85 -0
  602. package/out/utils/golden.d.ts.map +1 -0
  603. package/out/utils/golden.js +127 -0
  604. package/out/utils/golden.js.map +1 -0
  605. package/out/utils/index.d.ts +14 -0
  606. package/out/utils/index.d.ts.map +1 -0
  607. package/out/utils/index.js +14 -0
  608. package/out/utils/index.js.map +1 -0
  609. package/out/utils/license.d.ts.map +1 -0
  610. package/out/utils/license.js.map +1 -0
  611. package/out/utils/parquet.d.ts +178 -0
  612. package/out/utils/parquet.d.ts.map +1 -0
  613. package/out/utils/parquet.js +371 -0
  614. package/out/utils/parquet.js.map +1 -0
  615. package/out/utils/slice-stats.d.ts +52 -0
  616. package/out/utils/slice-stats.d.ts.map +1 -0
  617. package/out/utils/slice-stats.js +58 -0
  618. package/out/utils/slice-stats.js.map +1 -0
  619. package/out/utils/split.d.ts +128 -0
  620. package/out/utils/split.d.ts.map +1 -0
  621. package/out/utils/split.js +204 -0
  622. package/out/utils/split.js.map +1 -0
  623. package/out/utils/tokenize.d.ts +64 -0
  624. package/out/utils/tokenize.d.ts.map +1 -0
  625. package/out/utils/tokenize.js +82 -0
  626. package/out/utils/tokenize.js.map +1 -0
  627. package/out/utils/wof-json.d.ts +113 -0
  628. package/out/utils/wof-json.d.ts.map +1 -0
  629. package/out/utils/wof-json.js +173 -0
  630. package/out/utils/wof-json.js.map +1 -0
  631. package/package.json +259 -194
  632. package/out/src/adapters/ban/adapter.d.ts.map +0 -1
  633. package/out/src/adapters/ban/adapter.js +0 -149
  634. package/out/src/adapters/ban/adapter.js.map +0 -1
  635. package/out/src/adapters/ban/street-decompose.d.ts.map +0 -1
  636. package/out/src/adapters/ban/street-decompose.js +0 -75
  637. package/out/src/adapters/ban/street-decompose.js.map +0 -1
  638. package/out/src/adapters/fcc-bdc/adapter.d.ts.map +0 -1
  639. package/out/src/adapters/fcc-bdc/adapter.js +0 -144
  640. package/out/src/adapters/fcc-bdc/adapter.js.map +0 -1
  641. package/out/src/adapters/geonames/adapter.d.ts.map +0 -1
  642. package/out/src/adapters/geonames/adapter.js +0 -176
  643. package/out/src/adapters/geonames/adapter.js.map +0 -1
  644. package/out/src/adapters/geonames-postal/adapter.d.ts +0 -41
  645. package/out/src/adapters/geonames-postal/adapter.d.ts.map +0 -1
  646. package/out/src/adapters/geonames-postal/adapter.js +0 -104
  647. package/out/src/adapters/geonames-postal/adapter.js.map +0 -1
  648. package/out/src/adapters/gnaf/adapter.d.ts +0 -49
  649. package/out/src/adapters/gnaf/adapter.d.ts.map +0 -1
  650. package/out/src/adapters/gnaf/adapter.js +0 -124
  651. package/out/src/adapters/gnaf/adapter.js.map +0 -1
  652. package/out/src/adapters/gnaf/assemble.d.ts +0 -65
  653. package/out/src/adapters/gnaf/assemble.d.ts.map +0 -1
  654. package/out/src/adapters/gnaf/assemble.js +0 -154
  655. package/out/src/adapters/gnaf/assemble.js.map +0 -1
  656. package/out/src/adapters/index.d.ts +0 -51
  657. package/out/src/adapters/index.d.ts.map +0 -1
  658. package/out/src/adapters/index.js +0 -95
  659. package/out/src/adapters/index.js.map +0 -1
  660. package/out/src/adapters/openaddresses/adapter.d.ts.map +0 -1
  661. package/out/src/adapters/openaddresses/adapter.js +0 -186
  662. package/out/src/adapters/openaddresses/adapter.js.map +0 -1
  663. package/out/src/adapters/overture/adapter.d.ts +0 -48
  664. package/out/src/adapters/overture/adapter.d.ts.map +0 -1
  665. package/out/src/adapters/overture/adapter.js +0 -125
  666. package/out/src/adapters/overture/adapter.js.map +0 -1
  667. package/out/src/adapters/state-hi-schools/adapter.d.ts +0 -47
  668. package/out/src/adapters/state-hi-schools/adapter.d.ts.map +0 -1
  669. package/out/src/adapters/state-hi-schools/adapter.js +0 -133
  670. package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
  671. package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
  672. package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
  673. package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
  674. package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
  675. package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
  676. package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
  677. package/out/src/adapters/synth-po-box/adapter.d.ts.map +0 -1
  678. package/out/src/adapters/synth-po-box/adapter.js +0 -140
  679. package/out/src/adapters/synth-po-box/adapter.js.map +0 -1
  680. package/out/src/adapters/tiger/adapter.d.ts +0 -55
  681. package/out/src/adapters/tiger/adapter.d.ts.map +0 -1
  682. package/out/src/adapters/tiger/adapter.js +0 -201
  683. package/out/src/adapters/tiger/adapter.js.map +0 -1
  684. package/out/src/adapters/tiger/street-decompose.d.ts.map +0 -1
  685. package/out/src/adapters/tiger/street-decompose.js +0 -90
  686. package/out/src/adapters/tiger/street-decompose.js.map +0 -1
  687. package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -47
  688. package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
  689. package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +0 -139
  690. package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
  691. package/out/src/adapters/usgov-imls-pls/adapter.d.ts +0 -36
  692. package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
  693. package/out/src/adapters/usgov-imls-pls/adapter.js +0 -114
  694. package/out/src/adapters/usgov-imls-pls/adapter.js.map +0 -1
  695. package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
  696. package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
  697. package/out/src/adapters/usgov-irs-bmf/adapter.js +0 -124
  698. package/out/src/adapters/usgov-irs-bmf/adapter.js.map +0 -1
  699. package/out/src/adapters/usgov-nad/adapter.d.ts +0 -48
  700. package/out/src/adapters/usgov-nad/adapter.d.ts.map +0 -1
  701. package/out/src/adapters/usgov-nad/adapter.js +0 -252
  702. package/out/src/adapters/usgov-nad/adapter.js.map +0 -1
  703. package/out/src/adapters/usgov-nppes/adapter.d.ts.map +0 -1
  704. package/out/src/adapters/usgov-nppes/adapter.js +0 -116
  705. package/out/src/adapters/usgov-nppes/adapter.js.map +0 -1
  706. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
  707. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -156
  708. package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
  709. package/out/src/adapters/utils/index.d.ts +0 -150
  710. package/out/src/adapters/utils/index.d.ts.map +0 -1
  711. package/out/src/adapters/utils/index.js +0 -159
  712. package/out/src/adapters/utils/index.js.map +0 -1
  713. package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
  714. package/out/src/adapters/wof-admin-jp/adapter.js +0 -164
  715. package/out/src/adapters/wof-admin-jp/adapter.js.map +0 -1
  716. package/out/src/adapters/wof-admin-json/adapter.d.ts +0 -82
  717. package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
  718. package/out/src/adapters/wof-admin-json/adapter.js +0 -224
  719. package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
  720. package/out/src/adapters/wof-json-rows.d.ts +0 -32
  721. package/out/src/adapters/wof-json-rows.d.ts.map +0 -1
  722. package/out/src/adapters/wof-json-rows.js +0 -45
  723. package/out/src/adapters/wof-json-rows.js.map +0 -1
  724. package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -65
  725. package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
  726. package/out/src/adapters/wof-postalcode-json/adapter.js +0 -160
  727. package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
  728. package/out/src/build.d.ts +0 -132
  729. package/out/src/build.d.ts.map +0 -1
  730. package/out/src/build.js +0 -251
  731. package/out/src/build.js.map +0 -1
  732. package/out/src/codex/us-fips-state.d.ts.map +0 -1
  733. package/out/src/codex/us-fips-state.js.map +0 -1
  734. package/out/src/index.d.ts +0 -14
  735. package/out/src/index.d.ts.map +0 -1
  736. package/out/src/index.js +0 -14
  737. package/out/src/index.js.map +0 -1
  738. package/out/src/name-prone-us-suffixes.d.ts +0 -12
  739. package/out/src/name-prone-us-suffixes.d.ts.map +0 -1
  740. package/out/src/name-prone-us-suffixes.js +0 -12
  741. package/out/src/name-prone-us-suffixes.js.map +0 -1
  742. package/out/src/parquet-wrapper/index.d.ts +0 -9
  743. package/out/src/parquet-wrapper/index.d.ts.map +0 -1
  744. package/out/src/parquet-wrapper/index.js +0 -9
  745. package/out/src/parquet-wrapper/index.js.map +0 -1
  746. package/out/src/parquet-wrapper/reader.d.ts +0 -34
  747. package/out/src/parquet-wrapper/reader.d.ts.map +0 -1
  748. package/out/src/parquet-wrapper/reader.js +0 -69
  749. package/out/src/parquet-wrapper/reader.js.map +0 -1
  750. package/out/src/parquet-wrapper/schema.d.ts +0 -49
  751. package/out/src/parquet-wrapper/schema.d.ts.map +0 -1
  752. package/out/src/parquet-wrapper/schema.js +0 -55
  753. package/out/src/parquet-wrapper/schema.js.map +0 -1
  754. package/out/src/parquet-wrapper/writer.d.ts +0 -46
  755. package/out/src/parquet-wrapper/writer.d.ts.map +0 -1
  756. package/out/src/parquet-wrapper/writer.js +0 -76
  757. package/out/src/parquet-wrapper/writer.js.map +0 -1
  758. package/out/src/runner.d.ts +0 -126
  759. package/out/src/runner.d.ts.map +0 -1
  760. package/out/src/runner.js +0 -189
  761. package/out/src/runner.js.map +0 -1
  762. package/out/src/shard-recipes/anchor-absorption.d.ts +0 -20
  763. package/out/src/shard-recipes/anchor-absorption.d.ts.map +0 -1
  764. package/out/src/shard-recipes/anchor-absorption.js +0 -82
  765. package/out/src/shard-recipes/anchor-absorption.js.map +0 -1
  766. package/out/src/shard-recipes/bare-country.d.ts +0 -25
  767. package/out/src/shard-recipes/bare-country.d.ts.map +0 -1
  768. package/out/src/shard-recipes/bare-country.js +0 -87
  769. package/out/src/shard-recipes/bare-country.js.map +0 -1
  770. package/out/src/shard-recipes/boundary-stress.d.ts +0 -20
  771. package/out/src/shard-recipes/boundary-stress.d.ts.map +0 -1
  772. package/out/src/shard-recipes/boundary-stress.js +0 -83
  773. package/out/src/shard-recipes/boundary-stress.js.map +0 -1
  774. package/out/src/shard-recipes/country-balanced.d.ts +0 -32
  775. package/out/src/shard-recipes/country-balanced.d.ts.map +0 -1
  776. package/out/src/shard-recipes/country-balanced.js +0 -406
  777. package/out/src/shard-recipes/country-balanced.js.map +0 -1
  778. package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts +0 -22
  779. package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +0 -1
  780. package/out/src/shard-recipes/cz-pcfirst-preposition.js +0 -100
  781. package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +0 -1
  782. package/out/src/shard-recipes/fr-admin-split.d.ts +0 -38
  783. package/out/src/shard-recipes/fr-admin-split.d.ts.map +0 -1
  784. package/out/src/shard-recipes/fr-admin-split.js +0 -188
  785. package/out/src/shard-recipes/fr-admin-split.js.map +0 -1
  786. package/out/src/shard-recipes/fr-bare-street.d.ts +0 -28
  787. package/out/src/shard-recipes/fr-bare-street.d.ts.map +0 -1
  788. package/out/src/shard-recipes/fr-bare-street.js +0 -143
  789. package/out/src/shard-recipes/fr-bare-street.js.map +0 -1
  790. package/out/src/shard-recipes/fr-fragment.d.ts +0 -77
  791. package/out/src/shard-recipes/fr-fragment.d.ts.map +0 -1
  792. package/out/src/shard-recipes/fr-fragment.js +0 -276
  793. package/out/src/shard-recipes/fr-fragment.js.map +0 -1
  794. package/out/src/shard-recipes/fr-lieudit.d.ts +0 -32
  795. package/out/src/shard-recipes/fr-lieudit.d.ts.map +0 -1
  796. package/out/src/shard-recipes/fr-lieudit.js +0 -226
  797. package/out/src/shard-recipes/fr-lieudit.js.map +0 -1
  798. package/out/src/shard-recipes/fr-order.d.ts +0 -38
  799. package/out/src/shard-recipes/fr-order.d.ts.map +0 -1
  800. package/out/src/shard-recipes/fr-order.js +0 -208
  801. package/out/src/shard-recipes/fr-order.js.map +0 -1
  802. package/out/src/shard-recipes/german.d.ts +0 -23
  803. package/out/src/shard-recipes/german.d.ts.map +0 -1
  804. package/out/src/shard-recipes/german.js +0 -132
  805. package/out/src/shard-recipes/german.js.map +0 -1
  806. package/out/src/shard-recipes/house-venue.d.ts +0 -18
  807. package/out/src/shard-recipes/house-venue.d.ts.map +0 -1
  808. package/out/src/shard-recipes/house-venue.js +0 -74
  809. package/out/src/shard-recipes/house-venue.js.map +0 -1
  810. package/out/src/shard-recipes/index.d.ts +0 -24
  811. package/out/src/shard-recipes/index.d.ts.map +0 -1
  812. package/out/src/shard-recipes/index.js +0 -89
  813. package/out/src/shard-recipes/index.js.map +0 -1
  814. package/out/src/shard-recipes/intersection.d.ts +0 -42
  815. package/out/src/shard-recipes/intersection.d.ts.map +0 -1
  816. package/out/src/shard-recipes/intersection.js +0 -460
  817. package/out/src/shard-recipes/intersection.js.map +0 -1
  818. package/out/src/shard-recipes/locale.d.ts +0 -135
  819. package/out/src/shard-recipes/locale.d.ts.map +0 -1
  820. package/out/src/shard-recipes/locale.js +0 -459
  821. package/out/src/shard-recipes/locale.js.map +0 -1
  822. package/out/src/shard-recipes/nl-postcode.d.ts +0 -26
  823. package/out/src/shard-recipes/nl-postcode.d.ts.map +0 -1
  824. package/out/src/shard-recipes/nl-postcode.js +0 -102
  825. package/out/src/shard-recipes/nl-postcode.js.map +0 -1
  826. package/out/src/shard-recipes/no-fragment.d.ts +0 -43
  827. package/out/src/shard-recipes/no-fragment.d.ts.map +0 -1
  828. package/out/src/shard-recipes/no-fragment.js +0 -188
  829. package/out/src/shard-recipes/no-fragment.js.map +0 -1
  830. package/out/src/shard-recipes/no-street-led.d.ts +0 -24
  831. package/out/src/shard-recipes/no-street-led.d.ts.map +0 -1
  832. package/out/src/shard-recipes/no-street-led.js +0 -121
  833. package/out/src/shard-recipes/no-street-led.js.map +0 -1
  834. package/out/src/shard-recipes/no-street.d.ts +0 -18
  835. package/out/src/shard-recipes/no-street.d.ts.map +0 -1
  836. package/out/src/shard-recipes/no-street.js +0 -72
  837. package/out/src/shard-recipes/no-street.js.map +0 -1
  838. package/out/src/shard-recipes/po-box-cedex.d.ts +0 -38
  839. package/out/src/shard-recipes/po-box-cedex.d.ts.map +0 -1
  840. package/out/src/shard-recipes/po-box-cedex.js +0 -726
  841. package/out/src/shard-recipes/po-box-cedex.js.map +0 -1
  842. package/out/src/shard-recipes/po-box.d.ts +0 -17
  843. package/out/src/shard-recipes/po-box.d.ts.map +0 -1
  844. package/out/src/shard-recipes/po-box.js +0 -101
  845. package/out/src/shard-recipes/po-box.js.map +0 -1
  846. package/out/src/shard-recipes/reviewed-postcode-tail.d.ts +0 -47
  847. package/out/src/shard-recipes/reviewed-postcode-tail.d.ts.map +0 -1
  848. package/out/src/shard-recipes/reviewed-postcode-tail.js +0 -125
  849. package/out/src/shard-recipes/reviewed-postcode-tail.js.map +0 -1
  850. package/out/src/shard-recipes/scaffold.d.ts +0 -246
  851. package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
  852. package/out/src/shard-recipes/scaffold.js +0 -137
  853. package/out/src/shard-recipes/scaffold.js.map +0 -1
  854. package/out/src/shard-recipes/si-bare-village.d.ts +0 -32
  855. package/out/src/shard-recipes/si-bare-village.d.ts.map +0 -1
  856. package/out/src/shard-recipes/si-bare-village.js +0 -88
  857. package/out/src/shard-recipes/si-bare-village.js.map +0 -1
  858. package/out/src/shard-recipes/street-affix.d.ts +0 -89
  859. package/out/src/shard-recipes/street-affix.d.ts.map +0 -1
  860. package/out/src/shard-recipes/street-affix.js +0 -578
  861. package/out/src/shard-recipes/street-affix.js.map +0 -1
  862. package/out/src/shard-recipes/street-bare.d.ts +0 -25
  863. package/out/src/shard-recipes/street-bare.d.ts.map +0 -1
  864. package/out/src/shard-recipes/street-bare.js +0 -86
  865. package/out/src/shard-recipes/street-bare.js.map +0 -1
  866. package/out/src/shard-recipes/street.d.ts +0 -15
  867. package/out/src/shard-recipes/street.d.ts.map +0 -1
  868. package/out/src/shard-recipes/street.js +0 -69
  869. package/out/src/shard-recipes/street.js.map +0 -1
  870. package/out/src/shard-recipes/sub-venue-sources.d.ts +0 -228
  871. package/out/src/shard-recipes/sub-venue-sources.d.ts.map +0 -1
  872. package/out/src/shard-recipes/sub-venue-sources.js +0 -664
  873. package/out/src/shard-recipes/sub-venue-sources.js.map +0 -1
  874. package/out/src/shard-recipes/sub-venue.d.ts +0 -269
  875. package/out/src/shard-recipes/sub-venue.d.ts.map +0 -1
  876. package/out/src/shard-recipes/sub-venue.js +0 -710
  877. package/out/src/shard-recipes/sub-venue.js.map +0 -1
  878. package/out/src/shard-recipes/trailing-region.d.ts +0 -74
  879. package/out/src/shard-recipes/trailing-region.d.ts.map +0 -1
  880. package/out/src/shard-recipes/trailing-region.js +0 -157
  881. package/out/src/shard-recipes/trailing-region.js.map +0 -1
  882. package/out/src/shard-recipes/unit.d.ts +0 -29
  883. package/out/src/shard-recipes/unit.d.ts.map +0 -1
  884. package/out/src/shard-recipes/unit.js +0 -243
  885. package/out/src/shard-recipes/unit.js.map +0 -1
  886. package/out/src/synthesizers/anchor-absorption.d.ts +0 -63
  887. package/out/src/synthesizers/anchor-absorption.d.ts.map +0 -1
  888. package/out/src/synthesizers/anchor-absorption.js +0 -223
  889. package/out/src/synthesizers/anchor-absorption.js.map +0 -1
  890. package/out/src/synthesizers/boundary-stress.d.ts +0 -78
  891. package/out/src/synthesizers/boundary-stress.d.ts.map +0 -1
  892. package/out/src/synthesizers/boundary-stress.js +0 -455
  893. package/out/src/synthesizers/boundary-stress.js.map +0 -1
  894. package/out/src/synthesizers/german.d.ts +0 -107
  895. package/out/src/synthesizers/german.d.ts.map +0 -1
  896. package/out/src/synthesizers/german.js +0 -148
  897. package/out/src/synthesizers/german.js.map +0 -1
  898. package/out/src/synthesizers/house-venue.d.ts +0 -56
  899. package/out/src/synthesizers/house-venue.d.ts.map +0 -1
  900. package/out/src/synthesizers/house-venue.js +0 -267
  901. package/out/src/synthesizers/house-venue.js.map +0 -1
  902. package/out/src/synthesizers/intersection.d.ts +0 -52
  903. package/out/src/synthesizers/intersection.d.ts.map +0 -1
  904. package/out/src/synthesizers/intersection.js +0 -175
  905. package/out/src/synthesizers/intersection.js.map +0 -1
  906. package/out/src/synthesizers/no-street.d.ts +0 -72
  907. package/out/src/synthesizers/no-street.d.ts.map +0 -1
  908. package/out/src/synthesizers/no-street.js +0 -282
  909. package/out/src/synthesizers/no-street.js.map +0 -1
  910. package/out/src/synthesizers/po-box.d.ts +0 -104
  911. package/out/src/synthesizers/po-box.d.ts.map +0 -1
  912. package/out/src/synthesizers/po-box.js +0 -266
  913. package/out/src/synthesizers/po-box.js.map +0 -1
  914. package/out/src/synthesizers/street.d.ts +0 -54
  915. package/out/src/synthesizers/street.d.ts.map +0 -1
  916. package/out/src/synthesizers/street.js +0 -221
  917. package/out/src/synthesizers/street.js.map +0 -1
  918. package/out/src/synthesizers/utils.d.ts +0 -203
  919. package/out/src/synthesizers/utils.d.ts.map +0 -1
  920. package/out/src/synthesizers/utils.js +0 -708
  921. package/out/src/synthesizers/utils.js.map +0 -1
  922. package/out/src/tools/align-shard.d.ts +0 -8
  923. package/out/src/tools/align-shard.d.ts.map +0 -1
  924. package/out/src/tools/align-shard.js +0 -56
  925. package/out/src/tools/align-shard.js.map +0 -1
  926. package/out/src/tools/audit.d.ts +0 -28
  927. package/out/src/tools/audit.d.ts.map +0 -1
  928. package/out/src/tools/audit.js +0 -285
  929. package/out/src/tools/audit.js.map +0 -1
  930. package/out/src/tools/corpus-stats.d.ts +0 -44
  931. package/out/src/tools/corpus-stats.d.ts.map +0 -1
  932. package/out/src/tools/corpus-stats.js +0 -138
  933. package/out/src/tools/corpus-stats.js.map +0 -1
  934. package/out/src/tools/fetch/ban.d.ts +0 -31
  935. package/out/src/tools/fetch/ban.d.ts.map +0 -1
  936. package/out/src/tools/fetch/ban.js +0 -239
  937. package/out/src/tools/fetch/ban.js.map +0 -1
  938. package/out/src/tools/fetch/download.d.ts +0 -78
  939. package/out/src/tools/fetch/download.d.ts.map +0 -1
  940. package/out/src/tools/fetch/download.js +0 -116
  941. package/out/src/tools/fetch/download.js.map +0 -1
  942. package/out/src/tools/fetch/geonames-dump.d.ts +0 -87
  943. package/out/src/tools/fetch/geonames-dump.d.ts.map +0 -1
  944. package/out/src/tools/fetch/geonames-dump.js +0 -178
  945. package/out/src/tools/fetch/geonames-dump.js.map +0 -1
  946. package/out/src/tools/fetch/geonames-postal.d.ts +0 -76
  947. package/out/src/tools/fetch/geonames-postal.d.ts.map +0 -1
  948. package/out/src/tools/fetch/geonames-postal.js +0 -125
  949. package/out/src/tools/fetch/geonames-postal.js.map +0 -1
  950. package/out/src/tools/fetch/hrsa.d.ts +0 -18
  951. package/out/src/tools/fetch/hrsa.d.ts.map +0 -1
  952. package/out/src/tools/fetch/hrsa.js +0 -46
  953. package/out/src/tools/fetch/hrsa.js.map +0 -1
  954. package/out/src/tools/fetch/imls-pls.d.ts +0 -25
  955. package/out/src/tools/fetch/imls-pls.d.ts.map +0 -1
  956. package/out/src/tools/fetch/imls-pls.js +0 -108
  957. package/out/src/tools/fetch/imls-pls.js.map +0 -1
  958. package/out/src/tools/fetch/index.d.ts +0 -144
  959. package/out/src/tools/fetch/index.d.ts.map +0 -1
  960. package/out/src/tools/fetch/index.js +0 -143
  961. package/out/src/tools/fetch/index.js.map +0 -1
  962. package/out/src/tools/fetch/nad.d.ts +0 -70
  963. package/out/src/tools/fetch/nad.d.ts.map +0 -1
  964. package/out/src/tools/fetch/nad.js +0 -234
  965. package/out/src/tools/fetch/nad.js.map +0 -1
  966. package/out/src/tools/fetch/nppes.d.ts +0 -26
  967. package/out/src/tools/fetch/nppes.d.ts.map +0 -1
  968. package/out/src/tools/fetch/nppes.js +0 -126
  969. package/out/src/tools/fetch/nppes.js.map +0 -1
  970. package/out/src/tools/fetch/openaddresses.d.ts +0 -61
  971. package/out/src/tools/fetch/openaddresses.d.ts.map +0 -1
  972. package/out/src/tools/fetch/openaddresses.js +0 -317
  973. package/out/src/tools/fetch/openaddresses.js.map +0 -1
  974. package/out/src/tools/fetch/ourairports.d.ts +0 -45
  975. package/out/src/tools/fetch/ourairports.d.ts.map +0 -1
  976. package/out/src/tools/fetch/ourairports.js +0 -128
  977. package/out/src/tools/fetch/ourairports.js.map +0 -1
  978. package/out/src/tools/fetch/ppd.d.ts.map +0 -1
  979. package/out/src/tools/fetch/ppd.js +0 -100
  980. package/out/src/tools/fetch/ppd.js.map +0 -1
  981. package/out/src/tools/fetch/state-hi-schools.d.ts +0 -25
  982. package/out/src/tools/fetch/state-hi-schools.d.ts.map +0 -1
  983. package/out/src/tools/fetch/state-hi-schools.js +0 -162
  984. package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
  985. package/out/src/tools/fetch/state-sources.d.ts +0 -26
  986. package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
  987. package/out/src/tools/fetch/state-sources.js +0 -111
  988. package/out/src/tools/fetch/state-sources.js.map +0 -1
  989. package/out/src/tools/fetch/tiger-full.d.ts +0 -42
  990. package/out/src/tools/fetch/tiger-full.d.ts.map +0 -1
  991. package/out/src/tools/fetch/tiger-full.js +0 -248
  992. package/out/src/tools/fetch/tiger-full.js.map +0 -1
  993. package/out/src/tools/fetch/wikidata-subvenue.d.ts +0 -171
  994. package/out/src/tools/fetch/wikidata-subvenue.d.ts.map +0 -1
  995. package/out/src/tools/fetch/wikidata-subvenue.js +0 -275
  996. package/out/src/tools/fetch/wikidata-subvenue.js.map +0 -1
  997. package/out/src/tools/gb-title-case.d.ts.map +0 -1
  998. package/out/src/tools/gb-title-case.js.map +0 -1
  999. package/out/src/tools/golden-expand.d.ts +0 -90
  1000. package/out/src/tools/golden-expand.d.ts.map +0 -1
  1001. package/out/src/tools/golden-expand.js +0 -413
  1002. package/out/src/tools/golden-expand.js.map +0 -1
  1003. package/out/src/tools/golden-promote.d.ts.map +0 -1
  1004. package/out/src/tools/golden-promote.js +0 -244
  1005. package/out/src/tools/golden-promote.js.map +0 -1
  1006. package/out/src/tools/golden-relabel-street.d.ts +0 -196
  1007. package/out/src/tools/golden-relabel-street.d.ts.map +0 -1
  1008. package/out/src/tools/golden-relabel-street.js +0 -440
  1009. package/out/src/tools/golden-relabel-street.js.map +0 -1
  1010. package/out/src/tools/index.d.ts +0 -28
  1011. package/out/src/tools/index.d.ts.map +0 -1
  1012. package/out/src/tools/index.js +0 -28
  1013. package/out/src/tools/index.js.map +0 -1
  1014. package/out/src/tools/ingest-csv.d.ts.map +0 -1
  1015. package/out/src/tools/ingest-csv.js +0 -296
  1016. package/out/src/tools/ingest-csv.js.map +0 -1
  1017. package/out/src/tools/jsonl-to-parquet.d.ts +0 -61
  1018. package/out/src/tools/jsonl-to-parquet.d.ts.map +0 -1
  1019. package/out/src/tools/jsonl-to-parquet.js +0 -164
  1020. package/out/src/tools/jsonl-to-parquet.js.map +0 -1
  1021. package/out/src/tools/lint-shard-vocab.d.ts +0 -90
  1022. package/out/src/tools/lint-shard-vocab.d.ts.map +0 -1
  1023. package/out/src/tools/lint-shard-vocab.js +0 -281
  1024. package/out/src/tools/lint-shard-vocab.js.map +0 -1
  1025. package/out/src/tools/lint-shard.d.ts +0 -93
  1026. package/out/src/tools/lint-shard.d.ts.map +0 -1
  1027. package/out/src/tools/lint-shard.js +0 -354
  1028. package/out/src/tools/lint-shard.js.map +0 -1
  1029. package/out/src/tools/overlay-manifest.d.ts +0 -39
  1030. package/out/src/tools/overlay-manifest.d.ts.map +0 -1
  1031. package/out/src/tools/overlay-manifest.js +0 -98
  1032. package/out/src/tools/overlay-manifest.js.map +0 -1
  1033. package/out/src/tools/overture-subvenue.d.ts +0 -112
  1034. package/out/src/tools/overture-subvenue.d.ts.map +0 -1
  1035. package/out/src/tools/overture-subvenue.js +0 -144
  1036. package/out/src/tools/overture-subvenue.js.map +0 -1
  1037. package/out/src/tools/postcode-triples.d.ts +0 -175
  1038. package/out/src/tools/postcode-triples.d.ts.map +0 -1
  1039. package/out/src/tools/postcode-triples.js +0 -304
  1040. package/out/src/tools/postcode-triples.js.map +0 -1
  1041. package/out/src/tools/shard-kryptonite.d.ts +0 -32
  1042. package/out/src/tools/shard-kryptonite.d.ts.map +0 -1
  1043. package/out/src/tools/shard-kryptonite.js +0 -100
  1044. package/out/src/tools/shard-kryptonite.js.map +0 -1
  1045. package/out/src/tools/shard-translit.d.ts +0 -51
  1046. package/out/src/tools/shard-translit.d.ts.map +0 -1
  1047. package/out/src/tools/shard-translit.js +0 -175
  1048. package/out/src/tools/shard-translit.js.map +0 -1
  1049. package/out/src/tools/sub-venue/harvest.d.ts +0 -100
  1050. package/out/src/tools/sub-venue/harvest.d.ts.map +0 -1
  1051. package/out/src/tools/sub-venue/harvest.js +0 -168
  1052. package/out/src/tools/sub-venue/harvest.js.map +0 -1
  1053. package/out/src/tools/sub-venue/head-nouns.d.ts +0 -50
  1054. package/out/src/tools/sub-venue/head-nouns.d.ts.map +0 -1
  1055. package/out/src/tools/sub-venue/head-nouns.js +0 -210
  1056. package/out/src/tools/sub-venue/head-nouns.js.map +0 -1
  1057. package/out/src/tools/sub-venue/surfaces.d.ts +0 -45
  1058. package/out/src/tools/sub-venue/surfaces.d.ts.map +0 -1
  1059. package/out/src/tools/sub-venue/surfaces.js +0 -77
  1060. package/out/src/tools/sub-venue/surfaces.js.map +0 -1
  1061. package/out/src/tools/sub-venue/table.d.ts +0 -229
  1062. package/out/src/tools/sub-venue/table.d.ts.map +0 -1
  1063. package/out/src/tools/sub-venue/table.js +0 -108
  1064. package/out/src/tools/sub-venue/table.js.map +0 -1
  1065. package/out/src/tools/sub-venue/wikidata.d.ts +0 -26
  1066. package/out/src/tools/sub-venue/wikidata.d.ts.map +0 -1
  1067. package/out/src/tools/sub-venue/wikidata.js +0 -62
  1068. package/out/src/tools/sub-venue/wikidata.js.map +0 -1
  1069. package/out/src/tools/sub-venue-lexicon.d.ts +0 -156
  1070. package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
  1071. package/out/src/tools/sub-venue-lexicon.js +0 -282
  1072. package/out/src/tools/sub-venue-lexicon.js.map +0 -1
  1073. package/out/src/tools/sub-venue-promotions.d.ts +0 -94
  1074. package/out/src/tools/sub-venue-promotions.d.ts.map +0 -1
  1075. package/out/src/tools/sub-venue-promotions.js +0 -266
  1076. package/out/src/tools/sub-venue-promotions.js.map +0 -1
  1077. package/out/src/types.d.ts +0 -221
  1078. package/out/src/types.d.ts.map +0 -1
  1079. package/out/src/types.js.map +0 -1
  1080. package/out/src/utils/align.d.ts +0 -93
  1081. package/out/src/utils/align.d.ts.map +0 -1
  1082. package/out/src/utils/align.js +0 -234
  1083. package/out/src/utils/align.js.map +0 -1
  1084. package/out/src/utils/golden.d.ts +0 -69
  1085. package/out/src/utils/golden.d.ts.map +0 -1
  1086. package/out/src/utils/golden.js +0 -127
  1087. package/out/src/utils/golden.js.map +0 -1
  1088. package/out/src/utils/index.d.ts +0 -14
  1089. package/out/src/utils/index.d.ts.map +0 -1
  1090. package/out/src/utils/index.js +0 -14
  1091. package/out/src/utils/index.js.map +0 -1
  1092. package/out/src/utils/license.d.ts.map +0 -1
  1093. package/out/src/utils/license.js.map +0 -1
  1094. package/out/src/utils/parquet.d.ts +0 -162
  1095. package/out/src/utils/parquet.d.ts.map +0 -1
  1096. package/out/src/utils/parquet.js +0 -262
  1097. package/out/src/utils/parquet.js.map +0 -1
  1098. package/out/src/utils/split.d.ts +0 -127
  1099. package/out/src/utils/split.d.ts.map +0 -1
  1100. package/out/src/utils/split.js +0 -204
  1101. package/out/src/utils/split.js.map +0 -1
  1102. package/out/src/utils/tokenize.d.ts +0 -56
  1103. package/out/src/utils/tokenize.d.ts.map +0 -1
  1104. package/out/src/utils/tokenize.js +0 -48
  1105. package/out/src/utils/tokenize.js.map +0 -1
  1106. package/out/src/utils/wof-json.d.ts +0 -109
  1107. package/out/src/utils/wof-json.d.ts.map +0 -1
  1108. package/out/src/utils/wof-json.js +0 -173
  1109. package/out/src/utils/wof-json.js.map +0 -1
  1110. package/src/adapters/ban/adapter.ts +0 -191
  1111. package/src/adapters/ban/street-decompose.ts +0 -96
  1112. package/src/adapters/fcc-bdc/adapter.ts +0 -174
  1113. package/src/adapters/geonames/adapter.ts +0 -200
  1114. package/src/adapters/geonames-postal/adapter.ts +0 -119
  1115. package/src/adapters/gnaf/adapter.ts +0 -149
  1116. package/src/adapters/gnaf/assemble.ts +0 -226
  1117. package/src/adapters/index.ts +0 -149
  1118. package/src/adapters/openaddresses/adapter.ts +0 -251
  1119. package/src/adapters/overture/adapter.ts +0 -162
  1120. package/src/adapters/state-hi-schools/adapter.ts +0 -164
  1121. package/src/adapters/synth-po-box/adapter.ts +0 -204
  1122. package/src/adapters/tiger/adapter.ts +0 -253
  1123. package/src/adapters/tiger/street-decompose.ts +0 -111
  1124. package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -183
  1125. package/src/adapters/usgov-imls-pls/adapter.ts +0 -143
  1126. package/src/adapters/usgov-irs-bmf/adapter.ts +0 -163
  1127. package/src/adapters/usgov-nad/adapter.ts +0 -348
  1128. package/src/adapters/usgov-nppes/adapter.ts +0 -159
  1129. package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -204
  1130. package/src/adapters/utils/index.ts +0 -233
  1131. package/src/adapters/wof-admin-jp/adapter.ts +0 -216
  1132. package/src/adapters/wof-admin-json/adapter.ts +0 -256
  1133. package/src/adapters/wof-json-rows.ts +0 -79
  1134. package/src/adapters/wof-postalcode-json/adapter.ts +0 -183
  1135. package/src/build.ts +0 -386
  1136. package/src/index.ts +0 -14
  1137. package/src/name-prone-us-suffixes.ts +0 -12
  1138. package/src/parquet-wrapper/index.ts +0 -9
  1139. package/src/parquet-wrapper/reader.ts +0 -97
  1140. package/src/parquet-wrapper/schema.ts +0 -88
  1141. package/src/parquet-wrapper/writer.ts +0 -110
  1142. package/src/runner.ts +0 -317
  1143. package/src/shard-recipes/anchor-absorption.ts +0 -103
  1144. package/src/shard-recipes/bare-country.ts +0 -95
  1145. package/src/shard-recipes/boundary-stress.ts +0 -101
  1146. package/src/shard-recipes/country-balanced.ts +0 -524
  1147. package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -111
  1148. package/src/shard-recipes/fr-admin-split.ts +0 -239
  1149. package/src/shard-recipes/fr-bare-street.ts +0 -170
  1150. package/src/shard-recipes/fr-fragment.ts +0 -332
  1151. package/src/shard-recipes/fr-lieudit.ts +0 -302
  1152. package/src/shard-recipes/fr-order.ts +0 -258
  1153. package/src/shard-recipes/german.ts +0 -170
  1154. package/src/shard-recipes/house-venue.ts +0 -88
  1155. package/src/shard-recipes/index.ts +0 -95
  1156. package/src/shard-recipes/intersection.ts +0 -630
  1157. package/src/shard-recipes/locale.ts +0 -599
  1158. package/src/shard-recipes/nl-postcode.ts +0 -115
  1159. package/src/shard-recipes/no-fragment.ts +0 -219
  1160. package/src/shard-recipes/no-street-led.ts +0 -143
  1161. package/src/shard-recipes/no-street.ts +0 -86
  1162. package/src/shard-recipes/po-box-cedex.ts +0 -920
  1163. package/src/shard-recipes/po-box.ts +0 -119
  1164. package/src/shard-recipes/reviewed-postcode-tail.ts +0 -189
  1165. package/src/shard-recipes/scaffold.ts +0 -360
  1166. package/src/shard-recipes/si-bare-village.ts +0 -97
  1167. package/src/shard-recipes/street-affix.ts +0 -826
  1168. package/src/shard-recipes/street-bare.ts +0 -101
  1169. package/src/shard-recipes/street.ts +0 -82
  1170. package/src/shard-recipes/sub-venue-sources.ts +0 -885
  1171. package/src/shard-recipes/sub-venue.ts +0 -984
  1172. package/src/shard-recipes/trailing-region.ts +0 -183
  1173. package/src/shard-recipes/unit.ts +0 -321
  1174. package/src/synthesizers/anchor-absorption.ts +0 -290
  1175. package/src/synthesizers/boundary-stress.ts +0 -531
  1176. package/src/synthesizers/german.ts +0 -251
  1177. package/src/synthesizers/house-venue.ts +0 -330
  1178. package/src/synthesizers/intersection.ts +0 -232
  1179. package/src/synthesizers/no-street.ts +0 -349
  1180. package/src/synthesizers/po-box.ts +0 -339
  1181. package/src/synthesizers/street.ts +0 -274
  1182. package/src/synthesizers/utils.ts +0 -903
  1183. package/src/tools/align-shard.ts +0 -70
  1184. package/src/tools/audit.ts +0 -399
  1185. package/src/tools/corpus-stats.ts +0 -184
  1186. package/src/tools/fetch/ban.ts +0 -290
  1187. package/src/tools/fetch/download.ts +0 -176
  1188. package/src/tools/fetch/geonames-dump.ts +0 -267
  1189. package/src/tools/fetch/geonames-postal.ts +0 -180
  1190. package/src/tools/fetch/hrsa.ts +0 -68
  1191. package/src/tools/fetch/imls-pls.ts +0 -158
  1192. package/src/tools/fetch/index.ts +0 -147
  1193. package/src/tools/fetch/nad.ts +0 -342
  1194. package/src/tools/fetch/nppes.ts +0 -174
  1195. package/src/tools/fetch/openaddresses.ts +0 -404
  1196. package/src/tools/fetch/ourairports.ts +0 -171
  1197. package/src/tools/fetch/ppd.ts +0 -137
  1198. package/src/tools/fetch/state-hi-schools.ts +0 -208
  1199. package/src/tools/fetch/state-sources.ts +0 -155
  1200. package/src/tools/fetch/tiger-full.ts +0 -354
  1201. package/src/tools/fetch/wikidata-subvenue.ts +0 -386
  1202. package/src/tools/golden-expand.ts +0 -584
  1203. package/src/tools/golden-promote.ts +0 -353
  1204. package/src/tools/golden-relabel-street.ts +0 -685
  1205. package/src/tools/index.ts +0 -28
  1206. package/src/tools/ingest-csv.ts +0 -422
  1207. package/src/tools/jsonl-to-parquet.ts +0 -221
  1208. package/src/tools/lint-shard-vocab.ts +0 -409
  1209. package/src/tools/lint-shard.ts +0 -543
  1210. package/src/tools/overlay-manifest.ts +0 -157
  1211. package/src/tools/overture-subvenue.ts +0 -215
  1212. package/src/tools/postcode-triples.ts +0 -375
  1213. package/src/tools/shard-kryptonite.ts +0 -139
  1214. package/src/tools/shard-translit.ts +0 -245
  1215. package/src/tools/sub-venue/harvest.ts +0 -235
  1216. package/src/tools/sub-venue/head-nouns.ts +0 -242
  1217. package/src/tools/sub-venue/surfaces.ts +0 -95
  1218. package/src/tools/sub-venue/table.ts +0 -281
  1219. package/src/tools/sub-venue/wikidata.ts +0 -85
  1220. package/src/tools/sub-venue-lexicon.ts +0 -431
  1221. package/src/tools/sub-venue-promotions.ts +0 -330
  1222. package/src/types.ts +0 -247
  1223. package/src/utils/align.ts +0 -331
  1224. package/src/utils/golden.ts +0 -176
  1225. package/src/utils/index.ts +0 -14
  1226. package/src/utils/parquet.ts +0 -391
  1227. package/src/utils/split.ts +0 -279
  1228. package/src/utils/tokenize.ts +0 -78
  1229. package/src/utils/wof-json.ts +0 -244
  1230. /package/{src → lib}/adapters/state-ia-contractors/adapter.ts +0 -0
  1231. /package/{src → lib}/adapters/state-ny-notaries/adapter.ts +0 -0
  1232. /package/{src → lib}/adapters/state-tx-notaries/adapter.ts +0 -0
  1233. /package/{src → lib}/codex/us-fips-state.ts +0 -0
  1234. /package/{src → lib}/tools/gb-title-case.ts +0 -0
  1235. /package/{src → lib}/utils/license.ts +0 -0
  1236. /package/out/{src/adapters → adapters}/ban/adapter.d.ts +0 -0
  1237. /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
  1238. /package/out/{src/adapters → adapters}/fcc-bdc/adapter.d.ts +0 -0
  1239. /package/out/{src/adapters → adapters}/geonames/adapter.d.ts +0 -0
  1240. /package/out/{src/adapters → adapters}/openaddresses/adapter.d.ts +0 -0
  1241. /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.d.ts +0 -0
  1242. /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.js +0 -0
  1243. /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.d.ts +0 -0
  1244. /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.js +0 -0
  1245. /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.d.ts +0 -0
  1246. /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.js +0 -0
  1247. /package/out/{src/adapters → adapters}/synth-po-box/adapter.d.ts +0 -0
  1248. /package/out/{src/adapters → adapters}/tiger/street-decompose.d.ts +0 -0
  1249. /package/out/{src/adapters → adapters}/usgov-nppes/adapter.d.ts +0 -0
  1250. /package/out/{src/adapters → adapters}/usgov-samhsa-treatment-locator/adapter.d.ts +0 -0
  1251. /package/out/{src/adapters → adapters}/wof-admin-jp/adapter.d.ts +0 -0
  1252. /package/out/{src/codex → codex}/us-fips-state.d.ts +0 -0
  1253. /package/out/{src/codex → codex}/us-fips-state.js +0 -0
  1254. /package/out/{src/tools → tools}/fetch/ppd.d.ts +0 -0
  1255. /package/out/{src/tools → tools}/gb-title-case.d.ts +0 -0
  1256. /package/out/{src/tools → tools}/gb-title-case.js +0 -0
  1257. /package/out/{src/tools → tools}/golden-promote.d.ts +0 -0
  1258. /package/out/{src/tools → tools}/ingest-csv.d.ts +0 -0
  1259. /package/out/{src/types.js → types.js} +0 -0
  1260. /package/out/{src/utils → utils}/license.d.ts +0 -0
  1261. /package/out/{src/utils → utils}/license.js +0 -0
@@ -1 +0,0 @@
1
- {"version":3,"file":"utils.js","sourceRoot":"","sources":["../../../src/synthesizers/utils.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;GA0BG;AAEH,OAAO,EACN,+BAA+B,EAC/B,iCAAiC,EACjC,SAAS,EACT,sBAAsB,EACtB,mBAAmB,GACnB,MAAM,qBAAqB,CAAA;AAC5B,OAAO,EAAE,SAAS,EAAE,MAAM,yBAAyB,CAAA;AAEnD,OAAO,EAAE,UAAU,EAAE,MAAM,uBAAuB,CAAA;AAGlD,OAAO,EAAE,QAAQ,EAAE,oBAAoB,EAAsB,MAAM,cAAc,CAAA;AAEjF,OAAO,EAAE,mBAAmB,EAAkB,MAAM,sBAAsB,CAAA;AAU1E;;GAEG;AACH,SAAS,gBAAgB,CACxB,MAAoB,EACpB,MAAc,EACd,MAAc,EACd,aAA4B;IAE5B,MAAM,MAAM,GAAG,MAAM,CAAC,KAAK,EAAE,cAAc,IAAI,MAAM,CAAC,SAAS,CAAA;IAE/D,OAAO;QACN,GAAG,MAAM;QACT,GAAG,EAAE,MAAM;QACX,UAAU,EAAE,aAAa;QACzB,SAAS,EAAE,GAAG,MAAM,CAAC,SAAS,IAAI,MAAM,EAAE;QAC1C,KAAK,EAAE,EAAE,MAAM,EAAE,cAAc,EAAE,MAAM,EAAE;KACzC,CAAA;AACF,CAAC;AAED,8EAA8E;AAC9E,gCAAgC;AAChC,8EAA8E;AAE9E;;GAEG;AACH,MAAM,CAAC,MAAM,SAAS,GAAiB,CAAC,GAAG,EAAE,EAAE;IAC9C,IAAI,GAAG,CAAC,GAAG,KAAK,GAAG,CAAC,GAAG,CAAC,WAAW,EAAE;QAAE,OAAO,IAAI,CAAA;IAClD,MAAM,KAAK,GAAG,GAAG,CAAC,GAAG,CAAC,WAAW,EAAE,CAAA;IACnC,MAAM,YAAY,GAAkB,EAAE,CAAA;IAEtC,KAAK,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,GAAG,CAAC,UAAU,CAAC,EAAE,CAAC;QACrD,IAAI,CAAC,EAAE,CAAC;YACP,YAAY,CAAC,CAAiB,CAAC,GAAG,CAAC,CAAC,WAAW,EAAE,CAAA;QAClD,CAAC;IACF,CAAC;IAED,OAAO,gBAAgB,CAAC,GAAG,EAAE,YAAY,EAAE,KAAK,EAAE,YAAY,CAAC,CAAA;AAChE,CAAC,CAAA;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,SAAS,GAAiB,CAAC,GAAG,EAAE,EAAE;IAC9C,IAAI,GAAG,CAAC,GAAG,KAAK,GAAG,CAAC,GAAG,CAAC,WAAW,EAAE;QAAE,OAAO,IAAI,CAAA;IAClD,MAAM,OAAO,GAAG,GAAG,CAAC,GAAG,CAAC,WAAW,EAAE,CAAA;IACrC,MAAM,cAAc,GAAkB,EAAE,CAAA;IAExC,KAAK,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,GAAG,CAAC,UAAU,CAAC,EAAE,CAAC;QACrD,IAAI,CAAC,EAAE,CAAC;YACP,cAAc,CAAC,CAAiB,CAAC,GAAG,CAAC,CAAC,WAAW,EAAE,CAAA;QACpD,CAAC;IACF,CAAC;IAED,OAAO,gBAAgB,CAAC,GAAG,EAAE,YAAY,EAAE,OAAO,EAAE,cAAc,CAAC,CAAA;AACpE,CAAC,CAAA;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,UAAU,GAAiB,CAAC,GAAG,EAAE,EAAE;IAC/C,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,QAAQ,CAAC,GAAG,CAAC;QAAE,OAAO,IAAI,CAAA;IACvC,MAAM,MAAM,GAAG,GAAG,CAAC,GAAG,CAAC,UAAU,CAAC,GAAG,EAAE,EAAE,CAAC,CAAC,UAAU,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;IAEzE,OAAO,gBAAgB,CAAC,GAAG,EAAE,aAAa,EAAE,MAAM,EAAE,EAAE,GAAG,GAAG,CAAC,UAAU,EAAE,CAAC,CAAA;AAC3E,CAAC,CAAA;AAED;;;;;GAKG;AACH,MAAM,CAAC,MAAM,WAAW,GAAiB,CAAC,GAAG,EAAE,EAAE;IAChD,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC;QAAE,OAAO,IAAI,CAAA;IACnC,MAAM,MAAM,GAAG,GAAG,CAAC,GAAG,CAAC,UAAU,CAAC,GAAG,EAAE,IAAI,CAAC,CAAA;IAC5C,MAAM,aAAa,GAAkB,EAAE,CAAA;IAEvC,KAAK,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,GAAG,CAAC,UAAU,CAAC,EAAE,CAAC;QACrD,IAAI,CAAC,EAAE,CAAC;YACP,aAAa,CAAC,CAAiB,CAAC,GAAG,CAAC,CAAC,UAAU,CAAC,GAAG,EAAE,IAAI,CAAC,CAAA;QAC3D,CAAC;IACF,CAAC;IAED,OAAO,gBAAgB,CAAC,GAAG,EAAE,cAAc,EAAE,MAAM,EAAE,aAAa,CAAC,CAAA;AACpE,CAAC,CAAA;AAED;;;GAGG;AACH,MAAM,CAAC,MAAM,WAAW,GAAiB,CAAC,GAAG,EAAE,EAAE;IAChD,MAAM,QAAQ,GAAG,YAAY,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;IAEtC,IAAI,QAAQ,KAAK,GAAG,CAAC,GAAG;QAAE,OAAO,IAAI,CAAA;IACrC,MAAM,aAAa,GAAkB,EAAE,CAAA;IAEvC,KAAK,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,GAAG,CAAC,UAAU,CAAC,EAAE,CAAC;QACrD,IAAI,CAAC,EAAE,CAAC;YACP,aAAa,CAAC,CAAiB,CAAC,GAAG,YAAY,CAAC,CAAC,CAAC,CAAA;QACnD,CAAC;IACF,CAAC;IAED,OAAO,gBAAgB,CAAC,GAAG,EAAE,cAAc,EAAE,QAAQ,EAAE,aAAa,CAAC,CAAA;AACtE,CAAC,CAAA;AAED,SAAS,YAAY,CAAC,CAAS;IAC9B,OAAO,CAAC,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,UAAU,CAAC,SAAS,EAAE,EAAE,CAAC,CAAA;AACpD,CAAC;AAED,8EAA8E;AAC9E,kGAAkG;AAClG,kGAAkG;AAClG,+DAA+D;AAE/D;;GAEG;AACH,MAAM,gBAAgB,GAA2B;IAChD,CAAC,EAAE,MAAM;IACT,CAAC,EAAE,MAAM;IACT,CAAC,EAAE,MAAM;IACT,CAAC,EAAE,QAAQ;IACX,CAAC,EAAE,MAAM;IACT,CAAC,EAAE,QAAQ;IACX,CAAC,EAAE,QAAQ;IACX,CAAC,EAAE,QAAQ;IACX,CAAC,EAAE,MAAM;IACT,CAAC,EAAE,QAAQ;IACX,CAAC,EAAE,OAAO;IACV,CAAC,EAAE,KAAK;IACR,CAAC,EAAE,KAAK;IACR,CAAC,EAAE,MAAM;IACT,CAAC,EAAE,MAAM;IACT,CAAC,EAAE,IAAI;IACP,CAAC,EAAE,IAAI;IACP,CAAC,EAAE,MAAM;IACT,CAAC,EAAE,QAAQ;IACX,CAAC,EAAE,MAAM;IACT,CAAC,EAAE,MAAM;IACT,CAAC,EAAE,MAAM;IACT,CAAC,EAAE,MAAM;IACT,CAAC,EAAE,MAAM;IACT,CAAC,EAAE,MAAM;IACT,CAAC,EAAE,KAAK;CACR,CAAA;AAED;;GAEG;AACH,MAAM,UAAU,GAAG,2BAA2B,CAAA;AAE9C;;GAEG;AACH,SAAS,UAAU,CAAC,CAAS;IAC5B,IAAI,CAAC,GAAG,IAAI,CAAA;IAEZ,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,CAAC,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QACnC,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAA;IAC3C,CAAC;IAED,OAAO,CAAC,KAAK,CAAC,CAAA;AACf,CAAC;AAED;;;;;;GAMG;AACH,MAAM,CAAC,MAAM,UAAU,GAAiB,CAAC,GAAG,EAAE,EAAE;IAC/C,MAAM,GAAG,GAAG,UAAU,CAAC,UAAU,CAAC,GAAG,GAAG,CAAC,SAAS,OAAO,CAAC,CAAC,CAAA;IAE3D,iGAAiG;IACjG,mGAAmG;IACnG,kGAAkG;IAClG,qGAAqG;IACrG,MAAM,MAAM,GAAG,CAAC,MAAc,EAAU,EAAE;QACzC,IAAI,CAAC,GAAG,CAAC,CAAA;QAET,KAAK,IAAI,CAAC,GAAG,GAAG,CAAC,GAAG,CAAC,OAAO,CAAC,MAAM,CAAC,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC,GAAG,GAAG,CAAC,GAAG,CAAC,OAAO,CAAC,MAAM,EAAE,CAAC,GAAG,MAAM,CAAC,MAAM,CAAC,EAAE,CAAC;YAC9F,CAAC,EAAE,CAAA;QACJ,CAAC;QAED,OAAO,CAAC,CAAA;IACT,CAAC,CAAA;IAED,MAAM,MAAM,GAAG,MAAM,CAAC,MAAM,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAA;IAE9D,MAAM,QAAQ,GAAI,MAAM,CAAC,OAAO,CAAC,GAAG,CAAC,UAAU,CAAmC,CAAC,MAAM,CACxF,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,IAAI,UAAU,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,MAAM,CAAC,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CACtG,CAAA;IAED,IAAI,CAAC,QAAQ,CAAC,MAAM;QAAE,OAAO,IAAI,CAAA;IACjC,MAAM,CAAC,GAAG,EAAE,KAAK,CAAC,GAAG,QAAQ,CAAC,IAAI,CAAC,KAAK,CAAC,GAAG,EAAE,GAAG,QAAQ,CAAC,MAAM,CAAC,CAAE,CAAA;IACnE,0GAA0G;IAC1G,MAAM,SAAS,GAAa,EAAE,CAAA;IAE9B,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC,EAAE;QACxC,IAAI,QAAQ,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,CAAE,CAAC,EAAE,CAAC;YAC9B,SAAS,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QAClB,CAAC;IAEF,IAAI,CAAC,SAAS,CAAC,MAAM;QAAE,OAAO,IAAI,CAAA;IAClC,MAAM,CAAC,GAAG,SAAS,CAAC,IAAI,CAAC,KAAK,CAAC,GAAG,EAAE,GAAG,SAAS,CAAC,MAAM,CAAC,CAAE,CAAA;IAC1D,MAAM,EAAE,GAAG,KAAK,CAAC,CAAC,CAAE,CAAA;IACpB,IAAI,KAAa,CAAA;IAEjB,IAAI,GAAG,EAAE,GAAG,GAAG,EAAE,CAAC;QACjB,MAAM,IAAI,GAAG,KAAK,CAAC,CAAC,GAAG,CAAC,CAAE,CAAA;QAE1B,IAAI,EAAE,KAAK,IAAI;YAAE,OAAO,IAAI,CAAA,CAAC,qCAAqC;QAClE,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,GAAG,IAAI,GAAG,EAAE,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,CAAA;IAC3D,CAAC;SAAM,CAAC;QACP,MAAM,KAAK,GAAG,EAAE,CAAC,WAAW,EAAE,CAAA;QAC9B,MAAM,GAAG,GAAG,gBAAgB,CAAC,KAAK,CAAC,CAAA;QAEnC,IAAI,CAAC,GAAG;YAAE,OAAO,IAAI,CAAA;QACrB,MAAM,GAAG,GAAG,GAAG,CAAC,IAAI,CAAC,KAAK,CAAC,GAAG,EAAE,GAAG,GAAG,CAAC,MAAM,CAAC,CAAE,CAAA;QAChD,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,GAAG,CAAC,EAAE,KAAK,KAAK,CAAC,CAAC,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,CAAA;IAC1F,CAAC;IAED,IAAI,KAAK,KAAK,KAAK;QAAE,OAAO,IAAI,CAAA;IAChC,MAAM,MAAM,GAAG,GAAG,CAAC,GAAG,CAAC,OAAO,CAAC,KAAK,EAAE,KAAK,CAAC,CAAA;IAE5C,+DAA+D;IAC/D,OAAO,gBAAgB,CAAC,GAAG,EAAE,aAAa,EAAE,MAAM,EAAE,EAAE,GAAG,GAAG,CAAC,UAAU,EAAE,CAAC,GAAG,CAAC,EAAE,KAAK,EAAE,CAAC,CAAA;AACzF,CAAC,CAAA;AAED,8EAA8E;AAC9E,4BAA4B;AAC5B,8EAA8E;AAE9E;;GAEG;AACH,MAAM,kBAAkB,GAA2B;IAClD,OAAO,EAAE,IAAI;IACb,MAAM,EAAE,IAAI;IACZ,OAAO,EAAE,IAAI;IACb,QAAQ,EAAE,IAAI;IACd,UAAU,EAAE,IAAI;IAChB,QAAQ,EAAE,IAAI;IACd,WAAW,EAAE,IAAI;IACjB,QAAQ,EAAE,IAAI;IACd,OAAO,EAAE,IAAI;IACb,OAAO,EAAE,IAAI;IACb,MAAM,EAAE,IAAI;IACZ,KAAK,EAAE,IAAI;IACX,QAAQ,EAAE,IAAI;IACd,OAAO,EAAE,IAAI;IACb,IAAI,EAAE,IAAI;IACV,MAAM,EAAE,IAAI;IACZ,QAAQ,EAAE,IAAI;IACd,SAAS,EAAE,IAAI;IACf,KAAK,EAAE,IAAI;IACX,QAAQ,EAAE,IAAI;IACd,aAAa,EAAE,IAAI;IACnB,QAAQ,EAAE,IAAI;IACd,SAAS,EAAE,IAAI;IACf,WAAW,EAAE,IAAI;IACjB,QAAQ,EAAE,IAAI;IACd,OAAO,EAAE,IAAI;IACb,QAAQ,EAAE,IAAI;IACd,MAAM,EAAE,IAAI;IACZ,eAAe,EAAE,IAAI;IACrB,YAAY,EAAE,IAAI;IAClB,YAAY,EAAE,IAAI;IAClB,UAAU,EAAE,IAAI;IAChB,gBAAgB,EAAE,IAAI;IACtB,cAAc,EAAE,IAAI;IACpB,IAAI,EAAE,IAAI;IACV,QAAQ,EAAE,IAAI;IACd,MAAM,EAAE,IAAI;IACZ,YAAY,EAAE,IAAI;IAClB,cAAc,EAAE,IAAI;IACpB,gBAAgB,EAAE,IAAI;IACtB,cAAc,EAAE,IAAI;IACpB,SAAS,EAAE,IAAI;IACf,KAAK,EAAE,IAAI;IACX,IAAI,EAAE,IAAI;IACV,OAAO,EAAE,IAAI;IACb,QAAQ,EAAE,IAAI;IACd,UAAU,EAAE,IAAI;IAChB,eAAe,EAAE,IAAI;IACrB,SAAS,EAAE,IAAI;IACf,OAAO,EAAE,IAAI;IACb,sBAAsB,EAAE,IAAI;CAC5B,CAAA;AAED,MAAM,kBAAkB,GAA2B,MAAM,CAAC,WAAW,CACpE,MAAM,CAAC,OAAO,CAAC,kBAAkB,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAC1D,CAAA;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,WAAW,GAAiB,CAAC,GAAG,EAAE,EAAE;IAChD,IAAI,GAAG,CAAC,OAAO,KAAK,IAAI;QAAE,OAAO,IAAI,CAAA;IACrC,MAAM,MAAM,GAAG,GAAG,CAAC,UAAU,CAAC,MAAM,CAAA;IAEpC,IAAI,CAAC,MAAM;QAAE,OAAO,IAAI,CAAA;IACxB,MAAM,IAAI,GAAG,kBAAkB,CAAC,MAAM,CAAC,CAAA;IAEvC,IAAI,CAAC,IAAI;QAAE,OAAO,IAAI,CAAA;IACtB,wFAAwF;IACxF,wCAAwC;IACxC,MAAM,EAAE,GAAG,IAAI,MAAM,CAAC,MAAM,MAAM,KAAK,EAAE,GAAG,CAAC,CAAA;IAE7C,IAAI,CAAC,EAAE,CAAC,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC;QAAE,OAAO,IAAI,CAAA;IAClC,MAAM,MAAM,GAAG,GAAG,CAAC,GAAG,CAAC,UAAU,CAAC,IAAI,MAAM,CAAC,MAAM,MAAM,KAAK,EAAE,GAAG,CAAC,EAAE,IAAI,CAAC,CAAA;IAC3E,MAAM,aAAa,GAAkB,EAAE,GAAG,GAAG,CAAC,UAAU,EAAE,MAAM,EAAE,IAAI,EAAE,CAAA;IAExE,OAAO,gBAAgB,CAAC,GAAG,EAAE,cAAc,EAAE,MAAM,EAAE,aAAa,CAAC,CAAA;AACpE,CAAC,CAAA;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,eAAe,GAAiB,CAAC,GAAG,EAAE,EAAE;IACpD,IAAI,GAAG,CAAC,OAAO,KAAK,IAAI;QAAE,OAAO,IAAI,CAAA;IACrC,MAAM,MAAM,GAAG,GAAG,CAAC,UAAU,CAAC,MAAM,CAAA;IAEpC,IAAI,CAAC,MAAM;QAAE,OAAO,IAAI,CAAA;IACxB,MAAM,IAAI,GAAG,kBAAkB,CAAC,MAAM,CAAC,CAAA;IAEvC,IAAI,CAAC,IAAI;QAAE,OAAO,IAAI,CAAA;IACtB,MAAM,EAAE,GAAG,IAAI,MAAM,CAAC,MAAM,MAAM,KAAK,EAAE,GAAG,CAAC,CAAA;IAE7C,IAAI,CAAC,EAAE,CAAC,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC;QAAE,OAAO,IAAI,CAAA;IAClC,MAAM,MAAM,GAAG,GAAG,CAAC,GAAG,CAAC,UAAU,CAAC,IAAI,MAAM,CAAC,MAAM,MAAM,KAAK,EAAE,GAAG,CAAC,EAAE,IAAI,CAAC,CAAA;IAC3E,MAAM,aAAa,GAAkB,EAAE,GAAG,GAAG,CAAC,UAAU,EAAE,MAAM,EAAE,IAAI,EAAE,CAAA;IAExE,OAAO,gBAAgB,CAAC,GAAG,EAAE,kBAAkB,EAAE,MAAM,EAAE,aAAa,CAAC,CAAA;AACxE,CAAC,CAAA;AAED,MAAM,wBAAwB,GAA2B;IACxD,KAAK,EAAE,GAAG;IACV,KAAK,EAAE,GAAG;IACV,IAAI,EAAE,GAAG;IACT,IAAI,EAAE,GAAG;IACT,SAAS,EAAE,IAAI;IACf,SAAS,EAAE,IAAI;IACf,SAAS,EAAE,IAAI;IACf,SAAS,EAAE,IAAI;CACf,CAAA;AAED,MAAM,wBAAwB,GAA2B,MAAM,CAAC,WAAW,CAC1E,MAAM,CAAC,OAAO,CAAC,wBAAwB,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAChE,CAAA;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,iBAAiB,GAAiB,CAAC,GAAG,EAAE,EAAE;IACtD,IAAI,GAAG,CAAC,OAAO,KAAK,IAAI;QAAE,OAAO,IAAI,CAAA;IACrC,MAAM,WAAW,GAAmB,CAAC,QAAQ,EAAE,eAAe,EAAE,eAAe,CAAC,CAAA;IAChF,IAAI,OAAO,GAAG,KAAK,CAAA;IACnB,IAAI,MAAM,GAAG,GAAG,CAAC,GAAG,CAAA;IACpB,MAAM,aAAa,GAAkB,EAAE,GAAG,GAAG,CAAC,UAAU,EAAE,CAAA;IAE1D,KAAK,MAAM,GAAG,IAAI,WAAW,EAAE,CAAC;QAC/B,MAAM,CAAC,GAAG,aAAa,CAAC,GAAG,CAAC,CAAA;QAE5B,IAAI,CAAC,CAAC;YAAE,SAAQ;QAChB,MAAM,QAAQ,GAAG,CAAC,CAAC,UAAU,CAAC,4BAA4B,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,wBAAwB,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAA;QAEpG,IAAI,QAAQ,KAAK,CAAC,EAAE,CAAC;YACpB,aAAa,CAAC,GAAG,CAAC,GAAG,QAAQ,CAAA;YAC7B,MAAM,GAAG,MAAM,CAAC,UAAU,CAAC,IAAI,MAAM,CAAC,MAAM,WAAW,CAAC,CAAC,CAAC,KAAK,EAAE,GAAG,CAAC,EAAE,QAAQ,CAAC,CAAA;YAChF,OAAO,GAAG,IAAI,CAAA;QACf,CAAC;IACF,CAAC;IAED,IAAI,CAAC,OAAO;QAAE,OAAO,IAAI,CAAA;IAEzB,OAAO,gBAAgB,CAAC,GAAG,EAAE,oBAAoB,EAAE,MAAM,EAAE,aAAa,CAAC,CAAA;AAC1E,CAAC,CAAA;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,qBAAqB,GAAiB,CAAC,GAAG,EAAE,EAAE;IAC1D,IAAI,GAAG,CAAC,OAAO,KAAK,IAAI;QAAE,OAAO,IAAI,CAAA;IACrC,MAAM,WAAW,GAAmB,CAAC,QAAQ,EAAE,eAAe,EAAE,eAAe,CAAC,CAAA;IAChF,IAAI,OAAO,GAAG,KAAK,CAAA;IACnB,IAAI,MAAM,GAAG,GAAG,CAAC,GAAG,CAAA;IACpB,MAAM,aAAa,GAAkB,EAAE,GAAG,GAAG,CAAC,UAAU,EAAE,CAAA;IAE1D,KAAK,MAAM,GAAG,IAAI,WAAW,EAAE,CAAC;QAC/B,MAAM,CAAC,GAAG,aAAa,CAAC,GAAG,CAAC,CAAA;QAE5B,IAAI,CAAC,CAAC;YAAE,SAAQ;QAEhB,MAAM,QAAQ,GAAG,CAAC,CAAC,UAAU,CAC5B,sEAAsE,EACtE,CAAC,CAAC,EAAE,EAAE,CAAC,wBAAwB,CAAC,CAAC,CAAC,IAAI,CAAC,CACvC,CAAA;QAED,IAAI,QAAQ,KAAK,CAAC,EAAE,CAAC;YACpB,aAAa,CAAC,GAAG,CAAC,GAAG,QAAQ,CAAA;YAC7B,MAAM,GAAG,MAAM,CAAC,UAAU,CAAC,IAAI,MAAM,CAAC,MAAM,WAAW,CAAC,CAAC,CAAC,KAAK,EAAE,GAAG,CAAC,EAAE,QAAQ,CAAC,CAAA;YAChF,OAAO,GAAG,IAAI,CAAA;QACf,CAAC;IACF,CAAC;IAED,IAAI,CAAC,OAAO;QAAE,OAAO,IAAI,CAAA;IAEzB,OAAO,gBAAgB,CAAC,GAAG,EAAE,wBAAwB,EAAE,MAAM,EAAE,aAAa,CAAC,CAAA;AAC9E,CAAC,CAAA;AAED;;;;;;;;GAQG;AACH,MAAM,CAAC,MAAM,sBAAsB,GAAiB,CAAC,GAAG,EAAE,EAAE;IAC3D,IAAI,GAAG,CAAC,OAAO,KAAK,IAAI;QAAE,OAAO,IAAI,CAAA;IACrC,MAAM,MAAM,GAAG,GAAG,CAAC,UAAU,CAAC,MAAM,CAAA;IAEpC,IAAI,CAAC,MAAM;QAAE,OAAO,IAAI,CAAA;IACxB,MAAM,KAAK,GAAG,mBAAmB,CAAC,MAAM,CAAC,CAAA;IAEzC,IAAI,CAAC,KAAK;QAAE,OAAO,IAAI,CAAA;IAEvB,MAAM,SAAS,GAAG,+BAA+B,CAAC,KAAK,CAAC,SAAS,CAAC,CAAA;IAClE,MAAM,MAAM,GAAG,SAAS,CAAC,SAAS,EAAE,KAAK,CAAC,OAAO,CAAC,CAAA;IAElD,IAAI,MAAM,KAAK,KAAK,CAAC,OAAO;QAAE,OAAO,IAAI,CAAA;IAEzC,MAAM,SAAS,GAAG,GAAG,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,MAAM,CAAC,WAAW,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,GAAG,MAAM,EAAE,CAAA;IAElF,IAAI,SAAS,KAAK,MAAM;QAAE,OAAO,IAAI,CAAA;IAErC,MAAM,aAAa,GAAkB,EAAE,GAAG,GAAG,CAAC,UAAU,EAAE,MAAM,EAAE,SAAS,EAAE,CAAA;IAC7E,MAAM,MAAM,GAAG,GAAG,CAAC,GAAG,CAAC,UAAU,CAAC,IAAI,MAAM,CAAC,MAAM,WAAW,CAAC,MAAM,CAAC,KAAK,EAAE,GAAG,CAAC,EAAE,SAAS,CAAC,CAAA;IAE7F,IAAI,MAAM,KAAK,GAAG,CAAC,GAAG;QAAE,OAAO,IAAI,CAAA;IAEnC,OAAO,gBAAgB,CAAC,GAAG,EAAE,6BAA6B,EAAE,MAAM,EAAE,aAAa,CAAC,CAAA;AACnF,CAAC,CAAA;AAED;;;;;;;GAOG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAAiB,CAAC,GAAG,EAAE,EAAE;IACvD,IAAI,GAAG,CAAC,OAAO,KAAK,IAAI;QAAE,OAAO,IAAI,CAAA;IACrC,MAAM,MAAM,GAAG,GAAG,CAAC,UAAU,CAAC,MAAM,CAAA;IAEpC,IAAI,CAAC,MAAM;QAAE,OAAO,IAAI,CAAA;IACxB,MAAM,KAAK,GAAG,mBAAmB,CAAC,MAAM,CAAC,CAAA;IAEzC,IAAI,CAAC,KAAK;QAAE,OAAO,IAAI,CAAA;IAEvB,MAAM,MAAM,GAAG,SAAS,CAAC,KAAK,CAAC,SAAS,EAAE,KAAK,CAAC,OAAO,CAAC,CAAA;IAExD,IAAI,MAAM,KAAK,KAAK,CAAC,OAAO;QAAE,OAAO,IAAI,CAAA;IAEzC,MAAM,SAAS,GAAG,GAAG,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,MAAM,CAAC,WAAW,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,GAAG,MAAM,EAAE,CAAA;IAElF,IAAI,SAAS,KAAK,MAAM;QAAE,OAAO,IAAI,CAAA;IAErC,MAAM,aAAa,GAAkB,EAAE,GAAG,GAAG,CAAC,UAAU,EAAE,MAAM,EAAE,SAAS,EAAE,CAAA;IAC7E,MAAM,MAAM,GAAG,GAAG,CAAC,GAAG,CAAC,UAAU,CAAC,IAAI,MAAM,CAAC,MAAM,WAAW,CAAC,MAAM,CAAC,KAAK,EAAE,GAAG,CAAC,EAAE,SAAS,CAAC,CAAA;IAE7F,IAAI,MAAM,KAAK,GAAG,CAAC,GAAG;QAAE,OAAO,IAAI,CAAA;IAEnC,OAAO,gBAAgB,CAAC,GAAG,EAAE,yBAAyB,EAAE,MAAM,EAAE,aAAa,CAAC,CAAA;AAC/E,CAAC,CAAA;AAED;;;;;;;;GAQG;AACH,MAAM,CAAC,MAAM,wBAAwB,GAAiB,CAAC,GAAG,EAAE,EAAE;IAC7D,IAAI,GAAG,CAAC,OAAO,KAAK,IAAI;QAAE,OAAO,IAAI,CAAA;IACrC,MAAM,IAAI,GAAG,GAAG,CAAC,UAAU,CAAC,IAAI,CAAA;IAEhC,IAAI,CAAC,IAAI;QAAE,OAAO,IAAI,CAAA;IACtB,MAAM,KAAK,GAAG,sBAAsB,CAAC,IAAI,CAAC,CAAA;IAE1C,IAAI,CAAC,KAAK;QAAE,OAAO,IAAI,CAAA;IAEvB,MAAM,SAAS,GAAG,iCAAiC,CAAC,KAAK,CAAC,SAAS,CAAC,CAAA;IACpE,MAAM,MAAM,GAAG,SAAS,CAAC,SAAS,EAAE,KAAK,CAAC,OAAO,CAAC,CAAA;IAElD,IAAI,MAAM,KAAK,KAAK,CAAC,OAAO;QAAE,OAAO,IAAI,CAAA;IAEzC,MAAM,OAAO,GAAG,GAAG,MAAM,GAAG,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,OAAO,CAAC,MAAM,CAAC,EAAE,CAAA;IAE9D,IAAI,OAAO,KAAK,IAAI;QAAE,OAAO,IAAI,CAAA;IAEjC,MAAM,aAAa,GAAkB,EAAE,GAAG,GAAG,CAAC,UAAU,EAAE,IAAI,EAAE,OAAO,EAAE,CAAA;IACzE,MAAM,MAAM,GAAG,GAAG,CAAC,GAAG,CAAC,UAAU,CAAC,IAAI,MAAM,CAAC,MAAM,WAAW,CAAC,IAAI,CAAC,KAAK,EAAE,GAAG,CAAC,EAAE,OAAO,CAAC,CAAA;IAEzF,IAAI,MAAM,KAAK,GAAG,CAAC,GAAG;QAAE,OAAO,IAAI,CAAA;IAEnC,OAAO,gBAAgB,CAAC,GAAG,EAAE,+BAA+B,EAAE,MAAM,EAAE,aAAa,CAAC,CAAA;AACrF,CAAC,CAAA;AAED;;;;;GAKG;AACH,MAAM,CAAC,MAAM,oBAAoB,GAAiB,CAAC,GAAG,EAAE,EAAE;IACzD,IAAI,GAAG,CAAC,OAAO,KAAK,IAAI;QAAE,OAAO,IAAI,CAAA;IACrC,MAAM,IAAI,GAAG,GAAG,CAAC,UAAU,CAAC,IAAI,CAAA;IAEhC,IAAI,CAAC,IAAI;QAAE,OAAO,IAAI,CAAA;IACtB,MAAM,KAAK,GAAG,sBAAsB,CAAC,IAAI,CAAC,CAAA;IAE1C,IAAI,CAAC,KAAK;QAAE,OAAO,IAAI,CAAA;IAEvB,MAAM,MAAM,GAAG,SAAS,CAAC,KAAK,CAAC,SAAS,EAAE,KAAK,CAAC,OAAO,CAAC,CAAA;IAExD,IAAI,MAAM,KAAK,KAAK,CAAC,OAAO;QAAE,OAAO,IAAI,CAAA;IAEzC,MAAM,OAAO,GAAG,GAAG,MAAM,GAAG,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,OAAO,CAAC,MAAM,CAAC,EAAE,CAAA;IAE9D,IAAI,OAAO,KAAK,IAAI;QAAE,OAAO,IAAI,CAAA;IAEjC,MAAM,aAAa,GAAkB,EAAE,GAAG,GAAG,CAAC,UAAU,EAAE,IAAI,EAAE,OAAO,EAAE,CAAA;IACzE,MAAM,MAAM,GAAG,GAAG,CAAC,GAAG,CAAC,UAAU,CAAC,IAAI,MAAM,CAAC,MAAM,WAAW,CAAC,IAAI,CAAC,KAAK,EAAE,GAAG,CAAC,EAAE,OAAO,CAAC,CAAA;IAEzF,IAAI,MAAM,KAAK,GAAG,CAAC,GAAG;QAAE,OAAO,IAAI,CAAA;IAEnC,OAAO,gBAAgB,CAAC,GAAG,EAAE,2BAA2B,EAAE,MAAM,EAAE,aAAa,CAAC,CAAA;AACjF,CAAC,CAAA;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,gBAAgB,GAAiB,CAAC,GAAG,EAAE,EAAE;IACrD,IAAI,GAAG,CAAC,OAAO,KAAK,IAAI;QAAE,OAAO,IAAI,CAAA;IACrC,MAAM,QAAQ,GAAG,GAAG,CAAC,UAAU,CAAC,QAAQ,CAAA;IAExC,IAAI,CAAC,QAAQ,IAAI,CAAC,eAAe,CAAC,IAAI,CAAC,QAAQ,CAAC;QAAE,OAAO,IAAI,CAAA;IAC7D,MAAM,MAAM,GAAG,QAAQ,CAAC,OAAO,CAAC,GAAG,EAAE,EAAE,CAAC,CAAA;IACxC,MAAM,MAAM,GAAG,GAAG,CAAC,GAAG,CAAC,OAAO,CAAC,QAAQ,EAAE,MAAM,CAAC,CAAA;IAEhD,IAAI,MAAM,KAAK,GAAG,CAAC,GAAG;QAAE,OAAO,IAAI,CAAA;IAEnC,OAAO,gBAAgB,CAAC,GAAG,EAAE,qBAAqB,EAAE,MAAM,EAAE,EAAE,GAAG,GAAG,CAAC,UAAU,EAAE,QAAQ,EAAE,MAAM,EAAE,CAAC,CAAA;AACrG,CAAC,CAAA;AAED,8EAA8E;AAC9E,4BAA4B;AAC5B,8EAA8E;AAE9E;;GAEG;AACH,MAAM,CAAC,MAAM,aAAa,GAAiB,CAAC,GAAG,EAAE,EAAE;IAClD,IAAI,GAAG,CAAC,OAAO,KAAK,IAAI;QAAE,OAAO,IAAI,CAAA;IACrC,MAAM,QAAQ,GAAG,GAAG,CAAC,UAAU,CAAC,sBAAsB,CAAA;IAEtD,IAAI,CAAC,QAAQ;QAAE,OAAO,IAAI,CAAA;IAC1B,MAAM,aAAa,GAAkB,EAAE,GAAG,GAAG,CAAC,UAAU,EAAE,CAAA;IAC1D,OAAO,aAAa,CAAC,sBAAsB,CAAA;IAC3C,+DAA+D;IAC/D,MAAM,EAAE,GAAG,IAAI,MAAM,CAAC,OAAO,WAAW,CAAC,QAAQ,CAAC,MAAM,EAAE,GAAG,CAAC,CAAA;IAE9D,IAAI,CAAC,EAAE,CAAC,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC;QAAE,OAAO,IAAI,CAAA;IAClC,MAAM,MAAM,GAAG,GAAG,CAAC,GAAG,CAAC,OAAO,CAAC,EAAE,EAAE,GAAG,CAAC,CAAC,UAAU,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;IAEtE,OAAO,gBAAgB,CAAC,GAAG,EAAE,gBAAgB,EAAE,MAAM,EAAE,aAAa,CAAC,CAAA;AACtE,CAAC,CAAA;AAED,8EAA8E;AAC9E,8BAA8B;AAC9B,8EAA8E;AAE9E;;GAEG;AACH,MAAM,CAAC,MAAM,aAAa,GAAiC;IAC1D,YAAY,EAAE,SAAS;IACvB,YAAY,EAAE,SAAS;IACvB,aAAa,EAAE,UAAU;IACzB,cAAc,EAAE,WAAW;IAC3B,cAAc,EAAE,WAAW;IAC3B,cAAc,EAAE,WAAW;IAC3B,kBAAkB,EAAE,eAAe;IACnC,oBAAoB,EAAE,iBAAiB;IACvC,wBAAwB,EAAE,qBAAqB;IAC/C,6BAA6B,EAAE,sBAAsB;IACrD,yBAAyB,EAAE,kBAAkB;IAC7C,+BAA+B,EAAE,wBAAwB;IACzD,2BAA2B,EAAE,oBAAoB;IACjD,qBAAqB,EAAE,gBAAgB;IACvC,gBAAgB,EAAE,aAAa;IAC/B,aAAa,EAAE,UAAU;CACzB,CAAA;AAED;;GAEG;AACH,MAAM,UAAU,8BAA8B,CAAC,OAAe;IAC7D,6FAA6F;IAC7F,kGAAkG;IAClG,gGAAgG;IAChG,iGAAiG;IACjG,4FAA4F;IAC5F,MAAM,SAAS,GAAG,CAAC,SAAS,EAAE,SAAS,EAAE,UAAU,EAAE,WAAW,CAAC,CAAA;IAEjE,QAAQ,OAAO,EAAE,CAAC;QACjB,KAAK,IAAI;YACR,OAAO;gBACN,GAAG,SAAS;gBACZ,WAAW;gBACX,eAAe;gBACf,iBAAiB;gBACjB,qBAAqB;gBACrB,sBAAsB;gBACtB,kBAAkB;gBAClB,wBAAwB;gBACxB,oBAAoB;gBACpB,gBAAgB;aAChB,CAAA;QACF,KAAK,IAAI;YACR,OAAO,CAAC,GAAG,SAAS,EAAE,WAAW,EAAE,aAAa,CAAC,CAAA;QAClD;YACC,OAAO,SAAS,CAAA;IAClB,CAAC;AACF,CAAC;AAED;;;GAGG;AACH,MAAM,SAAS,CAAC,CAAC,aAAa,CAC7B,GAAiB,EACjB,gBAAyC,8BAA8B,CAAC,GAAG,CAAC,OAAO,CAAC;IAEpF,KAAK,MAAM,GAAG,IAAI,aAAa,EAAE,CAAC;QACjC,MAAM,GAAG,GAAG,GAAG,CAAC,GAAG,CAAC,CAAA;QAEpB,IAAI,GAAG,EAAE,CAAC;YACT,MAAM,GAAG,CAAA;QACV,CAAC;IACF,CAAC;AACF,CAAC;AAED,SAAS,WAAW,CAAC,CAAS;IAC7B,OAAO,CAAC,CAAC,UAAU,CAAC,qBAAqB,EAAE,MAAM,CAAC,CAAA;AACnD,CAAC;AAoED;;;;;;;;;;;;;;;;;;;;;;;;GAwBG;AACH,MAAM,UAAU,qBAAqB,CACpC,KAAa,EACb,OAAqB,EACrB,OAAkC;IAElC,MAAM,SAAS,GAAG,OAAO,CAAC,SAAS,IAAI,IAAI,CAAA;IAC3C,MAAM,SAAS,GAAG,OAAO,CAAC,SAAS,IAAI,mBAAmB,EAAE,CAAA;IAE5D,MAAM,YAAY,GAAG,KAAK,CAAC,IAAI,EAAE,CAAA;IAEjC,IAAI,CAAC,YAAY,EAAE,CAAC;QACnB,OAAO,EAAE,IAAI,EAAE,aAAa,EAAE,GAAG,EAAE,EAAE,GAAG,EAAE,OAAO,EAAE,MAAM,EAAE,aAAa,EAAE,EAAE,CAAA;IAC7E,CAAC;IAED,6FAA6F;IAC7F,+EAA+E;IAC/E,IAAI,YAAY,CAAC,SAAS,CAAC,KAAK,CAAC,KAAK,YAAY,EAAE,CAAC;QACpD,OAAO,EAAE,IAAI,EAAE,aAAa,EAAE,GAAG,EAAE,EAAE,GAAG,EAAE,OAAO,EAAE,MAAM,EAAE,eAAe,EAAE,EAAE,CAAA;IAC/E,CAAC;IAED,MAAM,cAAc,GAAG,QAAQ,CAAC,OAAO,EAAE,EAAE,SAAS,EAAE,CAAC,CAAA;IAEvD,IAAI,cAAc,CAAC,IAAI,KAAK,SAAS,EAAE,CAAC;QACvC,kFAAkF;QAClF,kFAAkF;QAClF,+BAA+B;QAC/B,OAAO;YACN,IAAI,EAAE,aAAa;YACnB,GAAG,EAAE,EAAE,GAAG,EAAE,OAAO,EAAE,MAAM,EAAE,mBAAmB,cAAc,CAAC,GAAG,CAAC,MAAM,EAAE,EAAE;SAC7E,CAAA;IACF,CAAC;IAED,MAAM,WAAW,GAAG,SAAS,CAAC,QAAQ,CAAC,YAAY,CAAC,CAAA;IAEpD,IAAI,CAAC,WAAW,CAAC,MAAM,EAAE,CAAC;QACzB,OAAO,EAAE,IAAI,EAAE,aAAa,EAAE,GAAG,EAAE,EAAE,GAAG,EAAE,OAAO,EAAE,MAAM,EAAE,iBAAiB,EAAE,EAAE,CAAA;IACjF,CAAC;IAED,MAAM,WAAW,GAAe,WAAW,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAA;IAE5F,MAAM,MAAM,GAAa,CAAC,GAAG,WAAW,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,EAAE,GAAG,cAAc,CAAC,GAAG,CAAC,MAAM,CAAC,CAAA;IAC1F,MAAM,MAAM,GAAe,CAAC,GAAG,WAAW,EAAE,GAAG,cAAc,CAAC,GAAG,CAAC,MAAM,CAAC,CAAA;IAEzE,MAAM,WAAW,GAAG,GAAG,YAAY,GAAG,SAAS,GAAG,OAAO,CAAC,GAAG,EAAE,CAAA;IAE/D,MAAM,kBAAkB,GAAG;QAC1B,KAAK,EAAE,YAAY;QACnB,GAAG,OAAO,CAAC,UAAU;KACrB,CAAA;IAED,8FAA8F;IAC9F,gGAAgG;IAChG,4FAA4F;IAC5F,2FAA2F;IAC3F,MAAM,EAAE,WAAW,EAAE,UAAU,EAAE,SAAS,EAAE,QAAQ,EAAE,SAAS,EAAE,QAAQ,EAAE,GAAG,cAAc,CAAC,GAAG,CAAA;IAEhG,IAAI,UAAU,KAAK,SAAS,IAAI,QAAQ,KAAK,SAAS,IAAI,QAAQ,KAAK,SAAS,EAAE,CAAC;QAClF,MAAM,IAAI,KAAK,CACd,iFAAiF;YAChF,WAAW,OAAO,CAAC,MAAM,eAAe,OAAO,CAAC,SAAS,kCAAkC,CAC5F,CAAA;IACF,CAAC;IAED,MAAM,MAAM,GAAG,YAAY,CAAC,MAAM,GAAG,SAAS,CAAC,MAAM,CAAA;IAErD,MAAM,KAAK,GAAoB;QAC9B,EAAE,GAAG,EAAE,OAAO,EAAE,KAAK,EAAE,CAAC,EAAE,GAAG,EAAE,YAAY,CAAC,MAAM,EAAE;QACpD,GAAG,QAAQ,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,EAAE,GAAG,EAAE,KAAK,EAAE,UAAU,CAAC,CAAC,CAAE,GAAG,MAAM,EAAE,GAAG,EAAE,QAAQ,CAAC,CAAC,CAAE,GAAG,MAAM,EAAE,CAAC,CAAC;KAClG,CAAA;IAED,MAAM,YAAY,GAAG,OAAO,CAAC,KAAK,EAAE,cAAc,IAAI,OAAO,CAAC,SAAS,CAAA;IACvE,MAAM,MAAM,GAAG,WAAW,OAAO,CAAC,OAAO,EAAE,CAAA;IAE3C,MAAM,QAAQ,GAAe;QAC5B,GAAG,EAAE,WAAW;QAChB,UAAU,EAAE,kBAAkB;QAC9B,OAAO,EAAE,OAAO,CAAC,OAAO;QACxB,MAAM,EAAE,OAAO,CAAC,MAAM;QACtB,MAAM,EAAE,OAAO,CAAC,MAAM;QACtB,SAAS,EAAE,GAAG,OAAO,CAAC,SAAS,IAAI,MAAM,EAAE;QAC3C,cAAc,EAAE,OAAO,CAAC,cAAc;QACtC,OAAO,EAAE,OAAO,CAAC,OAAO;QACxB,KAAK,EAAE,EAAE,MAAM,EAAE,cAAc,EAAE,YAAY,EAAE;QAC/C,MAAM;QACN,MAAM;QACN,WAAW,EAAE,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,KAAK,CAAC;QACtC,SAAS,EAAE,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC;QAClC,SAAS,EAAE,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC;KAClC,CAAA;IAED,oBAAoB,CAAC,KAAK,EAAE,QAAQ,CAAC,CAAA;IAErC,OAAO,EAAE,IAAI,EAAE,SAAS,EAAE,GAAG,EAAE,QAAQ,EAAE,CAAA;AAC1C,CAAC"}
@@ -1,8 +0,0 @@
1
- #!/usr/bin/env node
2
- export interface AlignShardOptions {
3
- input: string;
4
- output: string;
5
- corpusVersion: string;
6
- }
7
- export declare function alignCanonicalShard(args: AlignShardOptions): Promise<void>;
8
- //# sourceMappingURL=align-shard.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"align-shard.d.ts","sourceRoot":"","sources":["../../../src/tools/align-shard.ts"],"names":[],"mappings":";AAgCA,MAAM,WAAW,iBAAiB;IACjC,KAAK,EAAE,MAAM,CAAA;IACb,MAAM,EAAE,MAAM,CAAA;IACd,aAAa,EAAE,MAAM,CAAA;CACrB;AAED,wBAAsB,mBAAmB,CAAC,IAAI,EAAE,iBAAiB,GAAG,OAAO,CAAC,IAAI,CAAC,CA+BhF"}
@@ -1,56 +0,0 @@
1
- #!/usr/bin/env node
2
- import { createWriteStream } from "node:fs";
3
- import { JSONSpliterator } from "spliterator";
4
- /**
5
- * Re-emit a CANONICAL jsonl ({raw, components, country, source, ...}) as a LABELED jsonl in the CURRENT align format,
6
- * by running every row through `alignRow` (corpus/src/align.ts).
7
- *
8
- * ## Why this exists
9
- *
10
- * Most synthetic shards are GENERATED on demand by a `build-*-shard` recipe (parametrized by --count), so re-emitting
11
- * them in a new label format is just a re-run. A few shards are FIXED corpora with a hand/DeepSeek-authored canonical
12
- * source that is never regenerated — notably `deepseek-kryptonite` (the adversarial hard-case set) and the
13
- * `deepseek-translit-*` variants. Their committed parquets carry whatever label format was current when they were first
14
- * built.
15
- *
16
- * When the corpus label format changes (the v0.5.0 char-offset triple, #519), those fixed shards must be RE-ALIGNED,
17
- * not regenerated — feed the canonical source back through the same `alignRow` the from-source build uses, so the spans
18
- * land in the new format with zero drift. That is exactly what this does: canonical jsonl in → labeled jsonl out, one
19
- * `alignRow` per row, quarantine on miss.
20
- *
21
- * It is the uniform counterpart to corpus/src/tools/shard-kryptonite.ts (which couples to a base manifest and writes
22
- * parquet directly). Output goes to jsonl so it joins the SAME jsonl-to-parquet path every other overlay shard uses.
23
- *
24
- * Usage: node scripts/align-canonical-shard.ts\
25
- * --input /path/canonical-kryptonite.jsonl\
26
- * --output /tmp/kryptonite-labeled.jsonl\
27
- * --corpus-version 0.5.0
28
- */
29
- import { alignRow } from "#utils";
30
- export async function alignCanonicalShard(args) {
31
- // Read phase only — the write path stays on createWriteStream.
32
- const outStream = createWriteStream(args.output, { encoding: "utf8" });
33
- let labeled = 0;
34
- let quarantined = 0;
35
- const quarantineReasons = {};
36
- for await (const canonical of JSONSpliterator.fromAsync(args.input)) {
37
- // Stamp the target corpus version so the emitted row's provenance matches the run it joins.
38
- canonical.corpus_version = args.corpusVersion;
39
- const result = alignRow(canonical);
40
- if (result.kind === "labeled") {
41
- outStream.write(JSON.stringify(result.row) + "\n");
42
- labeled++;
43
- }
44
- else {
45
- quarantined++;
46
- const r = result.row.reason ?? "unknown";
47
- quarantineReasons[r] = (quarantineReasons[r] ?? 0) + 1;
48
- }
49
- }
50
- await new Promise((res) => {
51
- outStream.end(res);
52
- });
53
- console.error(`align-canonical-shard: ${labeled} labeled, ${quarantined} quarantined → ${args.output}\n` +
54
- ` quarantine reasons: ${JSON.stringify(quarantineReasons)}`);
55
- }
56
- //# sourceMappingURL=align-shard.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"align-shard.js","sourceRoot":"","sources":["../../../src/tools/align-shard.ts"],"names":[],"mappings":";AACA,OAAO,EAAE,iBAAiB,EAAE,MAAM,SAAS,CAAA;AAE3C,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C;;;;;;;;;;;;;;;;;;;;;;;;GAwBG;AACH,OAAO,EAAE,QAAQ,EAAE,MAAM,QAAQ,CAAA;AAQjC,MAAM,CAAC,KAAK,UAAU,mBAAmB,CAAC,IAAuB;IAChE,+DAA+D;IAC/D,MAAM,SAAS,GAAG,iBAAiB,CAAC,IAAI,CAAC,MAAM,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,CAAC,CAAA;IACtE,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,WAAW,GAAG,CAAC,CAAA;IACnB,MAAM,iBAAiB,GAA2B,EAAE,CAAA;IAEpD,IAAI,KAAK,EAAE,MAAM,SAAS,IAAI,eAAe,CAAC,SAAS,CAAiC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;QACrG,4FAA4F;QAC5F,SAAS,CAAC,cAAc,GAAG,IAAI,CAAC,aAAa,CAAA;QAC7C,MAAM,MAAM,GAAG,QAAQ,CAAC,SAAS,CAAC,CAAA;QAElC,IAAI,MAAM,CAAC,IAAI,KAAK,SAAS,EAAE,CAAC;YAC/B,SAAS,CAAC,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,GAAG,CAAC,GAAG,IAAI,CAAC,CAAA;YAElD,OAAO,EAAE,CAAA;QACV,CAAC;aAAM,CAAC;YACP,WAAW,EAAE,CAAA;YACb,MAAM,CAAC,GAAG,MAAM,CAAC,GAAG,CAAC,MAAM,IAAI,SAAS,CAAA;YACxC,iBAAiB,CAAC,CAAC,CAAC,GAAG,CAAC,iBAAiB,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAA;QACvD,CAAC;IACF,CAAC;IAED,MAAM,IAAI,OAAO,CAAO,CAAC,GAAG,EAAE,EAAE;QAC/B,SAAS,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;IACnB,CAAC,CAAC,CAAA;IAEF,OAAO,CAAC,KAAK,CACZ,0BAA0B,OAAO,aAAa,WAAW,kBAAkB,IAAI,CAAC,MAAM,IAAI;QACzF,yBAAyB,IAAI,CAAC,SAAS,CAAC,iBAAiB,CAAC,EAAE,CAC7D,CAAA;AACF,CAAC"}
@@ -1,28 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * `mailwoman corpus audit` — per-source shard-count vs source_weight diagnostic.
7
- *
8
- * Reads a corpus dir's MANIFEST.json (or scans shards directly), counts shards per source,
9
- * optionally loads a training config to pair the counts with the configured source_weights, and
10
- * reports the estimated sampled-row distribution at training time.
11
- *
12
- * Would have caught v0.3.0's "NAD = 411/674 train shards × 2.0 weight = ~75% of sampled mix"
13
- * finding before the v0.3.0 retrospective surfaced it.
14
- *
15
- * Emits warnings to stderr and the audit table to stdout; never throws on an empty corpus.
16
- */
17
- export interface AuditOpts {
18
- corpusDir: string;
19
- configPath?: string;
20
- /**
21
- * Sample at most N shards per split when counting sources. Default 100 for speed; bump to read the full set on a slow
22
- * run. The first row of each shard determines its source — corpus-v0.2.0+ shards are 100% source-segregated, so a
23
- * one-row read is authoritative.
24
- */
25
- sampleShardCount?: number;
26
- }
27
- export declare function audit(opts: AuditOpts): void;
28
- //# sourceMappingURL=audit.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"audit.d.ts","sourceRoot":"","sources":["../../../src/tools/audit.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;GAeG;AAmBH,MAAM,WAAW,SAAS;IACzB,SAAS,EAAE,MAAM,CAAA;IACjB,UAAU,CAAC,EAAE,MAAM,CAAA;IACnB;;;;OAIG;IACH,gBAAgB,CAAC,EAAE,MAAM,CAAA;CACzB;AA0VD,wBAAgB,KAAK,CAAC,IAAI,EAAE,SAAS,GAAG,IAAI,CAS3C"}
@@ -1,285 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * `mailwoman corpus audit` — per-source shard-count vs source_weight diagnostic.
7
- *
8
- * Reads a corpus dir's MANIFEST.json (or scans shards directly), counts shards per source,
9
- * optionally loads a training config to pair the counts with the configured source_weights, and
10
- * reports the estimated sampled-row distribution at training time.
11
- *
12
- * Would have caught v0.3.0's "NAD = 411/674 train shards × 2.0 weight = ~75% of sampled mix"
13
- * finding before the v0.3.0 retrospective surfaced it.
14
- *
15
- * Emits warnings to stderr and the audit table to stdout; never throws on an empty corpus.
16
- */
17
- import { existsSync, readFileSync, readdirSync } from "node:fs";
18
- import { basename, join } from "node:path";
19
- import { parseJSONStrict } from "@mailwoman/core/objects";
20
- import { TextSpliterator } from "spliterator";
21
- /**
22
- * Share of a shard one source may hold before the mix is flagged as dominated by it.
23
- */
24
- const DOMINANT_SOURCE_SHARE = 0.4;
25
- /**
26
- * How far the leading source may outweigh the runner-up before the mix is flagged. Catches the case where no single
27
- * source clears {@link DOMINANT_SOURCE_SHARE} but the distribution is still lopsided.
28
- */
29
- const MAX_TOP_TO_RUNNER_UP_RATIO = 1.5;
30
- /**
31
- * Try parsing a training YAML's source_weights as a minimal regex-based extract. We don't pull in a YAML lib for this
32
- * script — the syntax is so small that a regex over the source_weights block is sufficient + keeps the script
33
- * dep-free.
34
- */
35
- function parseConfig(configPath) {
36
- if (!existsSync(configPath))
37
- return null;
38
- const weights = {};
39
- let inBlock = false;
40
- let blockIndent = -1;
41
- for (const raw of TextSpliterator.from(readFileSync(configPath))) {
42
- const sourceWeightsMatch = raw.match(/^([\t ]*)source_weights:\s*$/);
43
- if (sourceWeightsMatch) {
44
- inBlock = true;
45
- blockIndent = sourceWeightsMatch[1].length;
46
- continue;
47
- }
48
- if (!inBlock)
49
- continue;
50
- // Skip blank lines and comments.
51
- if (/^[\t ]*(#|$)/.test(raw))
52
- continue;
53
- // Lines indented MORE than `source_weights:` are entries; lines with ≤ indent end the block.
54
- const indent = raw.match(/^[\t ]*/)[0].length;
55
- if (indent <= blockIndent) {
56
- inBlock = false;
57
- continue;
58
- }
59
- const m = raw.match(/^[\t ]+([\w-]+):\s*([\d.]+)/);
60
- if (m) {
61
- weights[m[1]] = Number.parseFloat(m[2]);
62
- }
63
- }
64
- return { sourceWeights: weights };
65
- }
66
- /**
67
- * Scan a corpus directory's shards (typically under <corpus_dir>/train, /val, /test) and count shards per source per
68
- * split.
69
- */
70
- function scanShards(corpusDir, sampleCount) {
71
- const stats = { bySplit: {}, totalShards: 0, totalFiles: 0 };
72
- for (const split of ["train", "val", "test"]) {
73
- const splitDir = join(corpusDir, split);
74
- if (!existsSync(splitDir))
75
- continue;
76
- const files = readdirSync(splitDir)
77
- .filter((f) => f.endsWith(".parquet"))
78
- .toSorted();
79
- stats.totalFiles += files.length;
80
- const sampleEvery = Math.max(1, Math.floor(files.length / sampleCount));
81
- const sampled = files.filter((_, i) => i % sampleEvery === 0).slice(0, sampleCount);
82
- const splitMap = {};
83
- // We can't read parquet without a dep, so we infer source from filenames where possible.
84
- // The corpus build typically writes deterministically by source — fall back to "<unknown>"
85
- // when filename gives no hint. For accurate per-source counts on real corpora, the
86
- // MANIFEST.json route below is preferred.
87
- for (const f of sampled) {
88
- const inferred = inferSourceFromFilename(f);
89
- splitMap[inferred] = (splitMap[inferred] ?? 0) + 1;
90
- }
91
- // Scale to estimated full-shard counts.
92
- const scale = files.length / Math.max(sampled.length, 1);
93
- for (const k of Object.keys(splitMap)) {
94
- splitMap[k] = Math.round(splitMap[k] * scale);
95
- }
96
- stats.bySplit[split] = splitMap;
97
- stats.totalShards += files.length;
98
- }
99
- return stats;
100
- }
101
- function inferSourceFromFilename(filename) {
102
- // Many corpus builds write part-<source>-<n>.parquet or part-<n>.parquet. The latter (current
103
- // build at corpus-v0.3.0) gives no source signal in the filename — see manifestScan() for the
104
- // authoritative path. Return "<unknown>" so the caller flags this case.
105
- const m = basename(filename).match(/part-([\w-]+)-\d+\.parquet$/);
106
- if (m && m[1] !== undefined)
107
- return m[1];
108
- return "<unknown>";
109
- }
110
- /**
111
- * Known source name prefixes. Corpus-v0.3.0 uses these as `source_id` prefixes; matching against the longest prefix
112
- * that fits a given `first_source_id` recovers the canonical source name.
113
- *
114
- * Order matters: longer prefixes must be tried first so `usgov-nad-...` matches `usgov-nad` rather than `usgov`. Sorted
115
- * descending by length at use site.
116
- */
117
- const KNOWN_SOURCE_PREFIXES = [
118
- "wof-admin",
119
- "wof-postalcode",
120
- "ban",
121
- "tiger",
122
- "usgov-nad",
123
- "usgov-nppes",
124
- "usgov-hrsa-fqhc",
125
- "usgov-imls-pls",
126
- "state-ia-contractors",
127
- "state-tx-notaries",
128
- "state-ny-notaries",
129
- "openaddresses",
130
- // Synthetic adversarial sources (corpus-v0.4.0+, Thread B).
131
- "deepseek-kryptonite",
132
- "deepseek-translit-cyrl",
133
- "deepseek-translit-jpan",
134
- "deepseek-translit-hans",
135
- "deepseek-translit-hang",
136
- "deepseek-translit-armn",
137
- ];
138
- /**
139
- * Extract the source-name prefix from a `first_source_id` value.
140
- */
141
- function sourceFromID(sourceID, knownPrefixes) {
142
- // Sort longest-first so usgov-nad beats usgov, wof-admin beats wof.
143
- const sorted = [...knownPrefixes].toSorted((a, b) => b.length - a.length);
144
- for (const prefix of sorted) {
145
- if (sourceID.startsWith(prefix + "-") || sourceID === prefix)
146
- return prefix;
147
- }
148
- return "<unknown>";
149
- }
150
- /**
151
- * Prefer reading MANIFEST.json when present — uses each shard's `first_source_id` + prefix matching to recover the
152
- * source name. Falls back to scanShards when MANIFEST is absent.
153
- *
154
- * NOTE: corpus-v0.3.0 shards can mix sources (see `last_source_id` differing from `first_source_id`). The first-row
155
- * source is an approximation; reading the parquet's full source column would be authoritative but requires a parquet
156
- * dep. For audit purposes the first-row approximation is accurate within ~5% for the corpus-v0.3.0 shape (most shards
157
- * are >95% one source).
158
- */
159
- function manifestScan(corpusDir, knownPrefixes) {
160
- const manifestPath = join(corpusDir, "MANIFEST.json");
161
- if (!existsSync(manifestPath))
162
- return null;
163
- const manifest = parseJSONStrict(readFileSync(manifestPath, "utf8"));
164
- if (!Array.isArray(manifest.shards))
165
- return null;
166
- const bySplit = {};
167
- for (const shard of manifest.shards) {
168
- const split = shard.split;
169
- const src = shard.source ?? sourceFromID(shard.first_source_id ?? "", knownPrefixes);
170
- bySplit[split] ??= {};
171
- bySplit[split][src] = (bySplit[split][src] ?? 0) + 1;
172
- }
173
- const total = Object.values(bySplit).reduce((sum, m) => sum + Object.values(m).reduce((a, b) => a + b, 0), 0);
174
- return { bySplit, totalShards: total, totalFiles: total };
175
- }
176
- function buildAuditRows(stats, weights) {
177
- const totalShards = Object.values(stats).reduce((a, b) => a + b, 0);
178
- const allSources = new Set([...Object.keys(stats), ...Object.keys(weights)]);
179
- const rows = [];
180
- // Compute effective sample weight: shard_count × source_weight. Sources with no weight get the
181
- // "—" marker (loader skips them).
182
- const sampleWeights = [];
183
- for (const src of allSources) {
184
- const shards = stats[src] ?? 0;
185
- const weight = weights[src];
186
- const effective = weight !== undefined ? shards * weight : 0;
187
- sampleWeights.push([src, effective]);
188
- }
189
- const totalSampleWeight = sampleWeights.reduce((a, [, w]) => a + w, 0);
190
- for (const src of allSources) {
191
- const shards = stats[src] ?? 0;
192
- const weight = weights[src] ?? "—";
193
- const effective = typeof weight === "number" ? (shards * weight) / Math.max(totalSampleWeight, 1) : "—";
194
- rows.push({
195
- source: src,
196
- shards,
197
- shardPct: totalShards > 0 ? shards / totalShards : 0,
198
- weight,
199
- effectiveSamplePct: typeof effective === "number" ? effective : "—",
200
- });
201
- }
202
- // Flag the dominator: empirically calibrated against the v0.3.0 → v0.4.0 retrospective.
203
- // v0.3.0 had usgov-nad at 52% effective sample (1.9× ban); the resulting label-space dilution
204
- // was responsible for the coarse-F1 regression. So flag a source as "concentration warning"
205
- // when it's above 40% effective sample OR more than 1.5× the next-highest.
206
- const numeric = rows.filter((r) => typeof r.effectiveSamplePct === "number");
207
- numeric.sort((a, b) => b.effectiveSamplePct - a.effectiveSamplePct);
208
- if (numeric.length) {
209
- const top = numeric[0];
210
- const next = numeric[1]?.effectiveSamplePct ?? 0;
211
- if (top.effectiveSamplePct > DOMINANT_SOURCE_SHARE ||
212
- (next > 0 && top.effectiveSamplePct / next > MAX_TOP_TO_RUNNER_UP_RATIO)) {
213
- top.overweightFactor = next > 0 ? top.effectiveSamplePct / next : Infinity;
214
- }
215
- }
216
- rows.sort((a, b) => b.shards - a.shards);
217
- return rows;
218
- }
219
- function formatPct(v) {
220
- if (v === "—")
221
- return "—";
222
- return `${(v * 100).toFixed(1)}%`;
223
- }
224
- function printReport(corpusDir, configPath, stats, rows) {
225
- console.log(`\nCorpus audit — ${corpusDir}`);
226
- if (configPath) {
227
- console.log(`Config: ${configPath}`);
228
- }
229
- console.log(`Total shards: ${stats.totalShards}${stats.totalFiles !== stats.totalShards ? ` (${stats.totalFiles} files on disk)` : ""}`);
230
- console.log("");
231
- const trainStats = stats.bySplit["train"];
232
- if (trainStats) {
233
- const total = Object.values(trainStats).reduce((a, b) => a + b, 0);
234
- console.log(`Train split: ${total} shards`);
235
- console.log("");
236
- const headers = ["source", "shards", "shard %", "weight", "eff. sample %"];
237
- const widths = [22, 8, 10, 8, 14];
238
- const fmtRow = (cells) => cells.map((c, i) => c.padEnd(widths[i])).join(" ");
239
- console.log(fmtRow(headers));
240
- console.log(fmtRow(widths.map((w) => "─".repeat(w))));
241
- for (const row of rows) {
242
- console.log(fmtRow([
243
- row.source,
244
- String(row.shards),
245
- formatPct(row.shardPct),
246
- typeof row.weight === "number" ? row.weight.toFixed(2) : "—",
247
- formatPct(row.effectiveSamplePct),
248
- ]));
249
- }
250
- console.log("");
251
- const dominator = rows.find((r) => r.overweightFactor !== undefined);
252
- if (dominator) {
253
- const factor = dominator.overweightFactor;
254
- const factorStr = factor === Infinity ? "∞" : factor?.toFixed(1);
255
- console.error(`⚠ Concentration: ${dominator.source} would sample ${formatPct(dominator.effectiveSamplePct)} ` +
256
- `of training rows (${factorStr}× the next-highest). ` +
257
- `Past lesson: v0.3.0's NAD at ~52% caused the 21-label coarse regression. ` +
258
- `Consider lowering this source's weight or boosting others.`);
259
- }
260
- else {
261
- console.log("✓ No single-source concentration (top source < 40% effective sample AND < 1.5× next).");
262
- }
263
- const missingWeights = rows.filter((r) => r.weight === "—" && r.shards > 0);
264
- if (missingWeights.length && configPath) {
265
- console.error(`⚠ Sources present in corpus but absent from config.source_weights ` +
266
- `(loader will skip them): ${missingWeights.map((r) => r.source).join(", ")}`);
267
- }
268
- const orphanWeights = rows.filter((r) => typeof r.weight === "number" && r.shards === 0);
269
- if (orphanWeights.length) {
270
- console.error(`⚠ Sources weighted in config but no shards found in corpus ` +
271
- `(no-op weights): ${orphanWeights.map((r) => r.source).join(", ")}`);
272
- }
273
- }
274
- }
275
- export function audit(opts) {
276
- const config = opts.configPath ? parseConfig(opts.configPath) : null;
277
- // Compose the known-prefix list from both the hardcoded set and any extra names in the config
278
- // (forward-compat for future adapters added before this file is updated).
279
- const prefixes = [...new Set([...KNOWN_SOURCE_PREFIXES, ...Object.keys(config?.sourceWeights ?? {})])];
280
- const stats = manifestScan(opts.corpusDir, prefixes) ?? scanShards(opts.corpusDir, opts.sampleShardCount ?? 100);
281
- const trainStats = stats.bySplit["train"] ?? {};
282
- const rows = buildAuditRows(trainStats, config?.sourceWeights ?? {});
283
- printReport(opts.corpusDir, opts.configPath, stats, rows);
284
- }
285
- //# sourceMappingURL=audit.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"audit.js","sourceRoot":"","sources":["../../../src/tools/audit.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;GAeG;AAEH,OAAO,EAAE,UAAU,EAAE,YAAY,EAAE,WAAW,EAAE,MAAM,SAAS,CAAA;AAC/D,OAAO,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAE1C,OAAO,EAAE,eAAe,EAAE,MAAM,yBAAyB,CAAA;AACzD,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C;;GAEG;AACH,MAAM,qBAAqB,GAAG,GAAG,CAAA;AAEjC;;;GAGG;AACH,MAAM,0BAA0B,GAAG,GAAG,CAAA;AAgCtC;;;;GAIG;AACH,SAAS,WAAW,CAAC,UAAkB;IACtC,IAAI,CAAC,UAAU,CAAC,UAAU,CAAC;QAAE,OAAO,IAAI,CAAA;IACxC,MAAM,OAAO,GAA2B,EAAE,CAAA;IAC1C,IAAI,OAAO,GAAG,KAAK,CAAA;IACnB,IAAI,WAAW,GAAG,CAAC,CAAC,CAAA;IAEpB,KAAK,MAAM,GAAG,IAAI,eAAe,CAAC,IAAI,CAAC,YAAY,CAAC,UAAU,CAAC,CAAC,EAAE,CAAC;QAClE,MAAM,kBAAkB,GAAG,GAAG,CAAC,KAAK,CAAC,8BAA8B,CAAC,CAAA;QAEpE,IAAI,kBAAkB,EAAE,CAAC;YACxB,OAAO,GAAG,IAAI,CAAA;YACd,WAAW,GAAG,kBAAkB,CAAC,CAAC,CAAE,CAAC,MAAM,CAAA;YAE3C,SAAQ;QACT,CAAC;QAED,IAAI,CAAC,OAAO;YAAE,SAAQ;QAEtB,iCAAiC;QACjC,IAAI,cAAc,CAAC,IAAI,CAAC,GAAG,CAAC;YAAE,SAAQ;QACtC,6FAA6F;QAC7F,MAAM,MAAM,GAAG,GAAG,CAAC,KAAK,CAAC,SAAS,CAAE,CAAC,CAAC,CAAC,CAAC,MAAM,CAAA;QAE9C,IAAI,MAAM,IAAI,WAAW,EAAE,CAAC;YAC3B,OAAO,GAAG,KAAK,CAAA;YAEf,SAAQ;QACT,CAAC;QAED,MAAM,CAAC,GAAG,GAAG,CAAC,KAAK,CAAC,6BAA6B,CAAC,CAAA;QAElD,IAAI,CAAC,EAAE,CAAC;YACP,OAAO,CAAC,CAAC,CAAC,CAAC,CAAE,CAAC,GAAG,MAAM,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,CAAE,CAAC,CAAA;QAC1C,CAAC;IACF,CAAC;IAED,OAAO,EAAE,aAAa,EAAE,OAAO,EAAE,CAAA;AAClC,CAAC;AAED;;;GAGG;AACH,SAAS,UAAU,CAAC,SAAiB,EAAE,WAAmB;IACzD,MAAM,KAAK,GAAe,EAAE,OAAO,EAAE,EAAE,EAAE,WAAW,EAAE,CAAC,EAAE,UAAU,EAAE,CAAC,EAAE,CAAA;IAExE,KAAK,MAAM,KAAK,IAAI,CAAC,OAAO,EAAE,KAAK,EAAE,MAAM,CAAC,EAAE,CAAC;QAC9C,MAAM,QAAQ,GAAG,IAAI,CAAC,SAAS,EAAE,KAAK,CAAC,CAAA;QAEvC,IAAI,CAAC,UAAU,CAAC,QAAQ,CAAC;YAAE,SAAQ;QAEnC,MAAM,KAAK,GAAG,WAAW,CAAC,QAAQ,CAAC;aACjC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,CAAC,UAAU,CAAC,CAAC;aACrC,QAAQ,EAAE,CAAA;QAEZ,KAAK,CAAC,UAAU,IAAI,KAAK,CAAC,MAAM,CAAA;QAChC,MAAM,WAAW,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,MAAM,GAAG,WAAW,CAAC,CAAC,CAAA;QACvE,MAAM,OAAO,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,WAAW,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,EAAE,WAAW,CAAC,CAAA;QACnF,MAAM,QAAQ,GAA2B,EAAE,CAAA;QAE3C,yFAAyF;QACzF,2FAA2F;QAC3F,mFAAmF;QACnF,0CAA0C;QAC1C,KAAK,MAAM,CAAC,IAAI,OAAO,EAAE,CAAC;YACzB,MAAM,QAAQ,GAAG,uBAAuB,CAAC,CAAC,CAAC,CAAA;YAC3C,QAAQ,CAAC,QAAQ,CAAC,GAAG,CAAC,QAAQ,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAA;QACnD,CAAC;QAED,wCAAwC;QACxC,MAAM,KAAK,GAAG,KAAK,CAAC,MAAM,GAAG,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,MAAM,EAAE,CAAC,CAAC,CAAA;QAExD,KAAK,MAAM,CAAC,IAAI,MAAM,CAAC,IAAI,CAAC,QAAQ,CAAC,EAAE,CAAC;YACvC,QAAQ,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC,CAAE,GAAG,KAAK,CAAC,CAAA;QAC/C,CAAC;QAED,KAAK,CAAC,OAAO,CAAC,KAAK,CAAC,GAAG,QAAQ,CAAA;QAC/B,KAAK,CAAC,WAAW,IAAI,KAAK,CAAC,MAAM,CAAA;IAClC,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC;AAED,SAAS,uBAAuB,CAAC,QAAgB;IAChD,8FAA8F;IAC9F,8FAA8F;IAC9F,wEAAwE;IACxE,MAAM,CAAC,GAAG,QAAQ,CAAC,QAAQ,CAAC,CAAC,KAAK,CAAC,6BAA6B,CAAC,CAAA;IAEjE,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,KAAK,SAAS;QAAE,OAAO,CAAC,CAAC,CAAC,CAAC,CAAA;IAExC,OAAO,WAAW,CAAA;AACnB,CAAC;AAED;;;;;;GAMG;AACH,MAAM,qBAAqB,GAA0B;IACpD,WAAW;IACX,gBAAgB;IAChB,KAAK;IACL,OAAO;IACP,WAAW;IACX,aAAa;IACb,iBAAiB;IACjB,gBAAgB;IAChB,sBAAsB;IACtB,mBAAmB;IACnB,mBAAmB;IACnB,eAAe;IACf,4DAA4D;IAC5D,qBAAqB;IACrB,wBAAwB;IACxB,wBAAwB;IACxB,wBAAwB;IACxB,wBAAwB;IACxB,wBAAwB;CACxB,CAAA;AAED;;GAEG;AACH,SAAS,YAAY,CAAC,QAAgB,EAAE,aAAgC;IACvE,oEAAoE;IACpE,MAAM,MAAM,GAAG,CAAC,GAAG,aAAa,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,MAAM,CAAC,CAAA;IAEzE,KAAK,MAAM,MAAM,IAAI,MAAM,EAAE,CAAC;QAC7B,IAAI,QAAQ,CAAC,UAAU,CAAC,MAAM,GAAG,GAAG,CAAC,IAAI,QAAQ,KAAK,MAAM;YAAE,OAAO,MAAM,CAAA;IAC5E,CAAC;IAED,OAAO,WAAW,CAAA;AACnB,CAAC;AAED;;;;;;;;GAQG;AACH,SAAS,YAAY,CAAC,SAAiB,EAAE,aAAgC;IACxE,MAAM,YAAY,GAAG,IAAI,CAAC,SAAS,EAAE,eAAe,CAAC,CAAA;IAErD,IAAI,CAAC,UAAU,CAAC,YAAY,CAAC;QAAE,OAAO,IAAI,CAAA;IAE1C,MAAM,QAAQ,GAAG,eAAe,CAE7B,YAAY,CAAC,YAAY,EAAE,MAAM,CAAC,CAAC,CAAA;IAEtC,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAC;QAAE,OAAO,IAAI,CAAA;IAChD,MAAM,OAAO,GAA2C,EAAE,CAAA;IAE1D,KAAK,MAAM,KAAK,IAAI,QAAQ,CAAC,MAAM,EAAE,CAAC;QACrC,MAAM,KAAK,GAAG,KAAK,CAAC,KAAK,CAAA;QACzB,MAAM,GAAG,GAAG,KAAK,CAAC,MAAM,IAAI,YAAY,CAAC,KAAK,CAAC,eAAe,IAAI,EAAE,EAAE,aAAa,CAAC,CAAA;QACpF,OAAO,CAAC,KAAK,CAAC,KAAK,EAAE,CAAA;QACrB,OAAO,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,GAAG,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAA;IACrD,CAAC;IAED,MAAM,KAAK,GAAG,MAAM,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,CAAC,EAAE,EAAE,CAAC,GAAG,GAAG,MAAM,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,CAAA;IAE7G,OAAO,EAAE,OAAO,EAAE,WAAW,EAAE,KAAK,EAAE,UAAU,EAAE,KAAK,EAAE,CAAA;AAC1D,CAAC;AAWD,SAAS,cAAc,CAAC,KAA6B,EAAE,OAA+B;IACrF,MAAM,WAAW,GAAG,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC,CAAA;IACnE,MAAM,UAAU,GAAG,IAAI,GAAG,CAAC,CAAC,GAAG,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,GAAG,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,CAAC,CAAA;IAC5E,MAAM,IAAI,GAAe,EAAE,CAAA;IAC3B,+FAA+F;IAC/F,kCAAkC;IAClC,MAAM,aAAa,GAA4B,EAAE,CAAA;IAEjD,KAAK,MAAM,GAAG,IAAI,UAAU,EAAE,CAAC;QAC9B,MAAM,MAAM,GAAG,KAAK,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;QAC9B,MAAM,MAAM,GAAG,OAAO,CAAC,GAAG,CAAC,CAAA;QAC3B,MAAM,SAAS,GAAG,MAAM,KAAK,SAAS,CAAC,CAAC,CAAC,MAAM,GAAG,MAAM,CAAC,CAAC,CAAC,CAAC,CAAA;QAC5D,aAAa,CAAC,IAAI,CAAC,CAAC,GAAG,EAAE,SAAS,CAAC,CAAC,CAAA;IACrC,CAAC;IAED,MAAM,iBAAiB,GAAG,aAAa,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC,CAAA;IAEtE,KAAK,MAAM,GAAG,IAAI,UAAU,EAAE,CAAC;QAC9B,MAAM,MAAM,GAAG,KAAK,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;QAC9B,MAAM,MAAM,GAAG,OAAO,CAAC,GAAG,CAAC,IAAI,GAAG,CAAA;QAClC,MAAM,SAAS,GAAG,OAAO,MAAM,KAAK,QAAQ,CAAC,CAAC,CAAC,CAAC,MAAM,GAAG,MAAM,CAAC,GAAG,IAAI,CAAC,GAAG,CAAC,iBAAiB,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,GAAG,CAAA;QAEvG,IAAI,CAAC,IAAI,CAAC;YACT,MAAM,EAAE,GAAG;YACX,MAAM;YACN,QAAQ,EAAE,WAAW,GAAG,CAAC,CAAC,CAAC,CAAC,MAAM,GAAG,WAAW,CAAC,CAAC,CAAC,CAAC;YACpD,MAAM;YACN,kBAAkB,EAAE,OAAO,SAAS,KAAK,QAAQ,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,GAAG;SACnE,CAAC,CAAA;IACH,CAAC;IAED,wFAAwF;IACxF,8FAA8F;IAC9F,4FAA4F;IAC5F,2EAA2E;IAC3E,MAAM,OAAO,GAAG,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,OAAO,CAAC,CAAC,kBAAkB,KAAK,QAAQ,CAE1E,CAAA;IAED,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,kBAAkB,GAAG,CAAC,CAAC,kBAAkB,CAAC,CAAA;IAEnE,IAAI,OAAO,CAAC,MAAM,EAAE,CAAC;QACpB,MAAM,GAAG,GAAG,OAAO,CAAC,CAAC,CAAE,CAAA;QACvB,MAAM,IAAI,GAAG,OAAO,CAAC,CAAC,CAAC,EAAE,kBAAkB,IAAI,CAAC,CAAA;QAEhD,IACC,GAAG,CAAC,kBAAkB,GAAG,qBAAqB;YAC9C,CAAC,IAAI,GAAG,CAAC,IAAI,GAAG,CAAC,kBAAkB,GAAG,IAAI,GAAG,0BAA0B,CAAC,EACvE,CAAC;YACF,GAAG,CAAC,gBAAgB,GAAG,IAAI,GAAG,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,kBAAkB,GAAG,IAAI,CAAC,CAAC,CAAC,QAAQ,CAAA;QAC3E,CAAC;IACF,CAAC;IAED,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,MAAM,CAAC,CAAA;IAExC,OAAO,IAAI,CAAA;AACZ,CAAC;AAED,SAAS,SAAS,CAAC,CAAe;IACjC,IAAI,CAAC,KAAK,GAAG;QAAE,OAAO,GAAG,CAAA;IAEzB,OAAO,GAAG,CAAC,CAAC,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,GAAG,CAAA;AAClC,CAAC;AAED,SAAS,WAAW,CAAC,SAAiB,EAAE,UAA8B,EAAE,KAAiB,EAAE,IAAgB;IAC1G,OAAO,CAAC,GAAG,CAAC,oBAAoB,SAAS,EAAE,CAAC,CAAA;IAE5C,IAAI,UAAU,EAAE,CAAC;QAChB,OAAO,CAAC,GAAG,CAAC,kBAAkB,UAAU,EAAE,CAAC,CAAA;IAC5C,CAAC;IAED,OAAO,CAAC,GAAG,CACV,kBAAkB,KAAK,CAAC,WAAW,GAAG,KAAK,CAAC,UAAU,KAAK,KAAK,CAAC,WAAW,CAAC,CAAC,CAAC,KAAK,KAAK,CAAC,UAAU,iBAAiB,CAAC,CAAC,CAAC,EAAE,EAAE,CAC5H,CAAA;IACD,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,CAAA;IAEf,MAAM,UAAU,GAAG,KAAK,CAAC,OAAO,CAAC,OAAO,CAAC,CAAA;IAEzC,IAAI,UAAU,EAAE,CAAC;QAChB,MAAM,KAAK,GAAG,MAAM,CAAC,MAAM,CAAC,UAAU,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC,CAAA;QAElE,OAAO,CAAC,GAAG,CAAC,gBAAgB,KAAK,SAAS,CAAC,CAAA;QAC3C,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,CAAA;QAEf,MAAM,OAAO,GAAG,CAAC,QAAQ,EAAE,QAAQ,EAAE,SAAS,EAAE,QAAQ,EAAE,eAAe,CAAC,CAAA;QAC1E,MAAM,MAAM,GAAG,CAAC,EAAE,EAAE,CAAC,EAAE,EAAE,EAAE,CAAC,EAAE,EAAE,CAAC,CAAA;QACjC,MAAM,MAAM,GAAG,CAAC,KAAe,EAAE,EAAE,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,CAAE,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QAExF,OAAO,CAAC,GAAG,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,CAAA;QAC5B,OAAO,CAAC,GAAG,CAAC,MAAM,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAA;QAErD,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;YACxB,OAAO,CAAC,GAAG,CACV,MAAM,CAAC;gBACN,GAAG,CAAC,MAAM;gBACV,MAAM,CAAC,GAAG,CAAC,MAAM,CAAC;gBAClB,SAAS,CAAC,GAAG,CAAC,QAAQ,CAAC;gBACvB,OAAO,GAAG,CAAC,MAAM,KAAK,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,GAAG;gBAC5D,SAAS,CAAC,GAAG,CAAC,kBAAkB,CAAC;aACjC,CAAC,CACF,CAAA;QACF,CAAC;QAED,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,CAAA;QAEf,MAAM,SAAS,GAAG,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,gBAAgB,KAAK,SAAS,CAAC,CAAA;QAEpE,IAAI,SAAS,EAAE,CAAC;YACf,MAAM,MAAM,GAAG,SAAS,CAAC,gBAAgB,CAAA;YACzC,MAAM,SAAS,GAAG,MAAM,KAAK,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC,CAAC,CAAA;YAEhE,OAAO,CAAC,KAAK,CACZ,oBAAoB,SAAS,CAAC,MAAM,iBAAiB,SAAS,CAAC,SAAS,CAAC,kBAAkB,CAAC,GAAG;gBAC9F,qBAAqB,SAAS,uBAAuB;gBACrD,2EAA2E;gBAC3E,4DAA4D,CAC7D,CAAA;QACF,CAAC;aAAM,CAAC;YACP,OAAO,CAAC,GAAG,CAAC,uFAAuF,CAAC,CAAA;QACrG,CAAC;QAED,MAAM,cAAc,GAAG,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,KAAK,GAAG,IAAI,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,CAAA;QAE3E,IAAI,cAAc,CAAC,MAAM,IAAI,UAAU,EAAE,CAAC;YACzC,OAAO,CAAC,KAAK,CACZ,oEAAoE;gBACnE,4BAA4B,cAAc,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAC7E,CAAA;QACF,CAAC;QAED,MAAM,aAAa,GAAG,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,OAAO,CAAC,CAAC,MAAM,KAAK,QAAQ,IAAI,CAAC,CAAC,MAAM,KAAK,CAAC,CAAC,CAAA;QAExF,IAAI,aAAa,CAAC,MAAM,EAAE,CAAC;YAC1B,OAAO,CAAC,KAAK,CACZ,6DAA6D;gBAC5D,oBAAoB,aAAa,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CACpE,CAAA;QACF,CAAC;IACF,CAAC;AACF,CAAC;AAED,MAAM,UAAU,KAAK,CAAC,IAAe;IACpC,MAAM,MAAM,GAAG,IAAI,CAAC,UAAU,CAAC,CAAC,CAAC,WAAW,CAAC,IAAI,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,IAAI,CAAA;IACpE,8FAA8F;IAC9F,0EAA0E;IAC1E,MAAM,QAAQ,GAAG,CAAC,GAAG,IAAI,GAAG,CAAC,CAAC,GAAG,qBAAqB,EAAE,GAAG,MAAM,CAAC,IAAI,CAAC,MAAM,EAAE,aAAa,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC,CAAA;IACtG,MAAM,KAAK,GAAG,YAAY,CAAC,IAAI,CAAC,SAAS,EAAE,QAAQ,CAAC,IAAI,UAAU,CAAC,IAAI,CAAC,SAAS,EAAE,IAAI,CAAC,gBAAgB,IAAI,GAAG,CAAC,CAAA;IAChH,MAAM,UAAU,GAAG,KAAK,CAAC,OAAO,CAAC,OAAO,CAAC,IAAI,EAAE,CAAA;IAC/C,MAAM,IAAI,GAAG,cAAc,CAAC,UAAU,EAAE,MAAM,EAAE,aAAa,IAAI,EAAE,CAAC,CAAA;IACpE,WAAW,CAAC,IAAI,CAAC,SAAS,EAAE,IAAI,CAAC,UAAU,EAAE,KAAK,EAAE,IAAI,CAAC,CAAA;AAC1D,CAAC"}
@@ -1,44 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * Pre-compute corpus-wide token + bigram label distributions for the corpus linter.
7
- *
8
- * Reads one or more Parquet shards, builds per-(token, label) and per-(bigram, label-bigram)
9
- * histograms, and serializes them as JSON. The output file is consumed by `lint-corpus-shard.ts`
10
- * as the baseline against which a new shard is compared.
11
- *
12
- * Stats are cheap to compute (~5–30s per 100K rows) but expensive enough that we cache them between
13
- * linter invocations. Re-run this script whenever the corpus changes substantially (a new
14
- * mainline shard added, a source-pool re-weighted, etc.).
15
- *
16
- * Output schema:
17
- *
18
- * ```ts
19
- * interface CorpusStats {
20
- * row_count: number
21
- * shard_paths: string[]
22
- * tokens: { [token: string]: { [label: string]: number } }
23
- * bigrams: { [token_bigram: string]: { [label_bigram: string]: number } }
24
- * // token_bigram = "tok1tok2" (US sep), label_bigram = "lab1lab2"
25
- * // For memory: only keep bigrams with count >= MIN_BIGRAM_COUNT (2).
26
- * }
27
- * ```
28
- *
29
- * Usage: node scripts/build-corpus-stats.ts\
30
- * --shards <glob-pattern-or-dir>\
31
- * --output <stats.json>
32
- *
33
- * For a quick local-corpus baseline (limited but useful for linter testing): node
34
- * scripts/build-corpus-stats.ts\
35
- * --shards $MAILWOMAN_DATA_ROOT/corpus/versioned/v0.4.0/corpus-v0.4.0/train/\
36
- * --output /tmp/corpus-stats-local.json
37
- */
38
- export interface CorpusStatsOptions {
39
- shardsArg: string;
40
- outputPath: string;
41
- limitPerShard?: number;
42
- }
43
- export declare function buildCorpusStats(args: CorpusStatsOptions): Promise<void>;
44
- //# sourceMappingURL=corpus-stats.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"corpus-stats.d.ts","sourceRoot":"","sources":["../../../src/tools/corpus-stats.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAoCG;AAUH,MAAM,WAAW,kBAAkB;IAClC,SAAS,EAAE,MAAM,CAAA;IACjB,UAAU,EAAE,MAAM,CAAA;IAClB,aAAa,CAAC,EAAE,MAAM,CAAA;CACtB;AAuCD,wBAAsB,gBAAgB,CAAC,IAAI,EAAE,kBAAkB,GAAG,OAAO,CAAC,IAAI,CAAC,CA8F9E"}
@@ -1,138 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * Pre-compute corpus-wide token + bigram label distributions for the corpus linter.
7
- *
8
- * Reads one or more Parquet shards, builds per-(token, label) and per-(bigram, label-bigram)
9
- * histograms, and serializes them as JSON. The output file is consumed by `lint-corpus-shard.ts`
10
- * as the baseline against which a new shard is compared.
11
- *
12
- * Stats are cheap to compute (~5–30s per 100K rows) but expensive enough that we cache them between
13
- * linter invocations. Re-run this script whenever the corpus changes substantially (a new
14
- * mainline shard added, a source-pool re-weighted, etc.).
15
- *
16
- * Output schema:
17
- *
18
- * ```ts
19
- * interface CorpusStats {
20
- * row_count: number
21
- * shard_paths: string[]
22
- * tokens: { [token: string]: { [label: string]: number } }
23
- * bigrams: { [token_bigram: string]: { [label_bigram: string]: number } }
24
- * // token_bigram = "tok1tok2" (US sep), label_bigram = "lab1lab2"
25
- * // For memory: only keep bigrams with count >= MIN_BIGRAM_COUNT (2).
26
- * }
27
- * ```
28
- *
29
- * Usage: node scripts/build-corpus-stats.ts\
30
- * --shards <glob-pattern-or-dir>\
31
- * --output <stats.json>
32
- *
33
- * For a quick local-corpus baseline (limited but useful for linter testing): node
34
- * scripts/build-corpus-stats.ts\
35
- * --shards $MAILWOMAN_DATA_ROOT/corpus/versioned/v0.4.0/corpus-v0.4.0/train/\
36
- * --output /tmp/corpus-stats-local.json
37
- */
38
- import { readdirSync, statSync, writeFileSync } from "node:fs";
39
- import { join } from "node:path";
40
- import { ParquetReader } from "../parquet-wrapper/index.js";
41
- const SEP = "";
42
- const MIN_BIGRAM_COUNT = 2;
43
- function discoverShards(shardsArg) {
44
- const stat = statSync(shardsArg);
45
- if (stat.isDirectory()) {
46
- return readdirSync(shardsArg)
47
- .filter((f) => f.endsWith(".parquet"))
48
- .map((f) => join(shardsArg, f));
49
- }
50
- if (stat.isFile() && shardsArg.endsWith(".parquet"))
51
- return [shardsArg];
52
- // Otherwise treat as a literal path list (one per line if it's stdin-friendly).
53
- return [shardsArg];
54
- }
55
- /**
56
- * Stream a shard's `tokens`/`labels` columns.
57
- *
58
- * `limit` stops the iteration rather than filtering afterwards, so a capped run reads only the row groups it needs.
59
- */
60
- async function* streamShardRows(shardPath, limit) {
61
- await using reader = await ParquetReader.openFile(shardPath);
62
- let emitted = 0;
63
- for await (const row of reader.project("tokens", "labels")) {
64
- if (limit !== undefined && emitted >= limit)
65
- break;
66
- yield row;
67
- emitted++;
68
- }
69
- }
70
- export async function buildCorpusStats(args) {
71
- const shardPaths = discoverShards(args.shardsArg);
72
- console.error(`Discovered ${shardPaths.length} parquet shard(s)`);
73
- const tokenStats = new Map();
74
- const bigramStats = new Map();
75
- let totalRows = 0;
76
- for (const path of shardPaths) {
77
- console.error(`Reading ${path}...`);
78
- const before = totalRows;
79
- for await (const { tokens, labels } of streamShardRows(path, args.limitPerShard)) {
80
- totalRows++;
81
- if (tokens.length !== labels.length)
82
- continue;
83
- // skip malformed
84
- for (let i = 0; i < tokens.length; i++) {
85
- const tk = tokens[i];
86
- const lb = labels[i];
87
- let labelMap = tokenStats.get(tk);
88
- if (!labelMap) {
89
- labelMap = new Map();
90
- tokenStats.set(tk, labelMap);
91
- }
92
- labelMap.set(lb, (labelMap.get(lb) ?? 0) + 1);
93
- if (i + 1 < tokens.length) {
94
- const bigramKey = tk + SEP + tokens[i + 1];
95
- const bigramLabel = lb + SEP + labels[i + 1];
96
- let bMap = bigramStats.get(bigramKey);
97
- if (!bMap) {
98
- bMap = new Map();
99
- bigramStats.set(bigramKey, bMap);
100
- }
101
- bMap.set(bigramLabel, (bMap.get(bigramLabel) ?? 0) + 1);
102
- }
103
- }
104
- }
105
- console.error(` ${totalRows - before} rows; running totals: ${tokenStats.size} unique tokens, ${bigramStats.size} unique bigrams`);
106
- }
107
- // Prune bigrams below MIN_BIGRAM_COUNT to keep the output file size sane. Token stats
108
- // stay complete — they're cheap and we need accuracy at the long tail for label-vacuum
109
- // detection.
110
- let prunedBigrams = 0;
111
- for (const [k, labelMap] of bigramStats) {
112
- let total = 0;
113
- for (const v of labelMap.values()) {
114
- total += v;
115
- }
116
- if (total < MIN_BIGRAM_COUNT) {
117
- bigramStats.delete(k);
118
- prunedBigrams++;
119
- }
120
- }
121
- console.error(`Pruned ${prunedBigrams} singleton bigrams; ${bigramStats.size} remain`);
122
- const out = {
123
- row_count: totalRows,
124
- shard_paths: shardPaths,
125
- tokens: {},
126
- bigrams: {},
127
- };
128
- for (const [tk, labelMap] of tokenStats) {
129
- out.tokens[tk] = Object.fromEntries(labelMap);
130
- }
131
- for (const [k, labelMap] of bigramStats) {
132
- out.bigrams[k] = Object.fromEntries(labelMap);
133
- }
134
- writeFileSync(args.outputPath, JSON.stringify(out));
135
- const sizeMB = (Buffer.byteLength(JSON.stringify(out)) / 1024 / 1024).toFixed(1);
136
- console.error(`Wrote ${args.outputPath} (${sizeMB} MB) — ${totalRows} rows, ${tokenStats.size} tokens, ${bigramStats.size} bigrams`);
137
- }
138
- //# sourceMappingURL=corpus-stats.js.map