@mailwoman/corpus 9.4.0 → 10.1.0

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 (1724) hide show
  1. package/README.md +134 -32
  2. package/data/PROVENANCE.md +623 -17
  3. package/data/address-source-register.json +14249 -0
  4. package/data/builds/v0.7.0-de-holdout/inputs.json +22 -0
  5. package/data/builds/v0.8.0-registers/inputs.json +92 -0
  6. package/data/license-decisions.json +1603 -0
  7. package/data/licenses/PROVENANCE.md +65 -0
  8. package/data/licenses/cdla-permissive-2.0.md +43 -0
  9. package/data/licenses/geonames-publication.md +34 -0
  10. package/data/licenses/licence-ouverte-2.0.md +36 -0
  11. package/data/licenses/national-address-database.md +46 -0
  12. package/data/licenses/nlod-2.0.md +90 -0
  13. package/data/licenses/sirene-publication.md +38 -0
  14. package/data/licenses/whosonfirst-licenses.md +65 -0
  15. package/data/source-resolutions.json +804 -0
  16. package/data/sub-venue-lexicon.json +1 -1
  17. package/data/training-manifests/v0.7.0-de-holdout.effective.json +477 -0
  18. package/data/training-manifests/v0.7.0-de-holdout.json +78 -0
  19. package/lib/adapters/cordis/adapter.ts +785 -0
  20. package/lib/adapters/dedup-key.ts +40 -0
  21. package/lib/adapters/errors.ts +21 -0
  22. package/lib/adapters/geonames/adapter.ts +43 -53
  23. package/lib/adapters/geonames/postal/adapter.ts +116 -0
  24. package/lib/adapters/gleif/adapter.ts +828 -0
  25. package/lib/adapters/libpostal-dictionary.ts +39 -0
  26. package/lib/adapters/openaddresses/adapter.ts +54 -61
  27. package/lib/adapters/osm/adapter.ts +356 -0
  28. package/lib/adapters/overture/adapter.ts +65 -41
  29. package/lib/adapters/po-box/adapter.ts +202 -0
  30. package/lib/adapters/registry.ts +79 -0
  31. package/lib/adapters/sha256-stream.ts +49 -0
  32. package/lib/adapters/source-id.ts +49 -0
  33. package/lib/adapters/street-line.ts +135 -0
  34. package/lib/adapters/wof/admin/json/adapter.ts +254 -0
  35. package/lib/adapters/wof/json-rows.ts +211 -0
  36. package/lib/adapters/wof/postalcode-json/adapter.ts +194 -0
  37. package/lib/adapters.ts +230 -0
  38. package/lib/au/adapters/gnaf/adapter.ts +144 -0
  39. package/lib/au/adapters/gnaf/assemble.ts +205 -0
  40. package/lib/be/adapters/brussels/adapter.ts +566 -0
  41. package/lib/be/adapters/vlaanderen/adapter.ts +670 -0
  42. package/lib/be/adapters/wallonie/adapter.ts +537 -0
  43. package/lib/be/tools/fetch/brussels.ts +239 -0
  44. package/lib/be/tools/fetch/wallonie.ts +274 -0
  45. package/lib/build/adapters.ts +110 -0
  46. package/lib/build/align.ts +364 -0
  47. package/lib/build/checkpoint.ts +131 -0
  48. package/lib/build/eligibility.ts +96 -0
  49. package/lib/build/heap.ts +53 -0
  50. package/lib/build/inputs.ts +81 -0
  51. package/lib/build/rows.ts +21 -0
  52. package/lib/build/types.ts +232 -0
  53. package/lib/build.ts +127 -315
  54. package/lib/cn/recipes/organizational-units.ts +178 -0
  55. package/lib/cz/adapters/cuzk/adapter.ts +317 -0
  56. package/lib/cz/recipes/pcfirst-preposition.ts +125 -0
  57. package/lib/cz/tools/fetch/cuzk.ts +699 -0
  58. package/lib/de/recipes/locale.ts +370 -0
  59. package/lib/directory.ts +31 -0
  60. package/lib/dk/adapters/inspire/adapter.ts +345 -0
  61. package/lib/dk/tools/fetch/inspire.ts +321 -0
  62. package/lib/ee/adapters/ads/adapter.ts +246 -0
  63. package/lib/ee/tools/fetch/ads.ts +270 -0
  64. package/lib/env.ts +6 -2
  65. package/lib/es/adapters/bizkaia/adapter.ts +388 -0
  66. package/lib/es/adapters/catastro/adapter.ts +343 -0
  67. package/lib/es/adapters/gipuzkoa/adapter.ts +263 -0
  68. package/lib/es/adapters/navarra/adapter.ts +289 -0
  69. package/lib/es/cadastre.ts +194 -0
  70. package/lib/es/tools/fetch/bizkaia.ts +748 -0
  71. package/lib/es/tools/fetch/catastro.ts +754 -0
  72. package/lib/es/tools/fetch/gipuzkoa.ts +336 -0
  73. package/lib/es/tools/fetch/navarra.ts +488 -0
  74. package/lib/fi/adapters/ryhti/adapter.ts +323 -0
  75. package/lib/fi/tools/fetch/ryhti.ts +476 -0
  76. package/lib/fingerprints.ts +154 -0
  77. package/lib/fr/adapters/annuaire-education/adapter.ts +598 -0
  78. package/lib/fr/adapters/ban/adapter.ts +187 -0
  79. package/lib/fr/adapters/finess/adapter.ts +618 -0
  80. package/lib/fr/adapters/finess/postal-lines.ts +157 -0
  81. package/lib/fr/adapters/finess/voie-type.ts +200 -0
  82. package/lib/fr/insee-country.ts +62 -0
  83. package/lib/fr/recipes/admin-split.ts +221 -0
  84. package/lib/fr/recipes/bare-street.ts +158 -0
  85. package/lib/fr/recipes/fragment.ts +251 -0
  86. package/lib/fr/recipes/lieudit.ts +310 -0
  87. package/lib/fr/recipes/order.ts +219 -0
  88. package/lib/fr/street-decompose.ts +67 -0
  89. package/lib/fr/tools/fetch/annuaire-education.ts +306 -0
  90. package/lib/fr/tools/fetch/ban.ts +298 -0
  91. package/lib/fr/tools/fetch/finess.ts +352 -0
  92. package/lib/gauntlet-inputs.ts +92 -0
  93. package/lib/index.ts +10 -4
  94. package/lib/inspire/address.ts +457 -0
  95. package/lib/inspire/archive.ts +44 -0
  96. package/lib/inspire/errors.ts +71 -0
  97. package/lib/inspire/stream.ts +262 -0
  98. package/lib/international/recipes/locale.ts +556 -0
  99. package/lib/it/adapters/anac/adapter.ts +522 -0
  100. package/lib/it/tools/fetch/anac.ts +394 -0
  101. package/lib/jp/adapters/wof-admin/adapter.ts +224 -0
  102. package/lib/jp/tools/fetch/houjin.ts +139 -0
  103. package/lib/kr/adapters/juso/label-rows.ts +239 -0
  104. package/lib/kr/adapters/localdata/align.ts +288 -0
  105. package/lib/kr/adapters/localdata/key-index.ts +177 -0
  106. package/lib/kr/adapters/localdata/permit-rows.ts +193 -0
  107. package/lib/kr/tools/fetch/juso.ts +170 -0
  108. package/lib/kr/tools/fetch/localdata.ts +205 -0
  109. package/lib/lu/adapters/bd-adresses/adapter.ts +240 -0
  110. package/lib/lu/tools/fetch/bd-adresses.ts +351 -0
  111. package/lib/lv/adapters/varis/adapter.ts +499 -0
  112. package/lib/lv/tools/fetch/varis.ts +214 -0
  113. package/lib/nl/adapters/kadaster/adapter.ts +386 -0
  114. package/lib/nl/recipes/postcode.ts +139 -0
  115. package/lib/nl/tools/fetch/kadaster.ts +298 -0
  116. package/lib/no/adapters/matrikkelen/adapter.ts +187 -0
  117. package/lib/no/recipes/fragment.ts +189 -0
  118. package/lib/no/recipes/street/led.ts +154 -0
  119. package/lib/no/recipes/street.ts +109 -0
  120. package/lib/no/tools/fetch/matrikkelen.ts +519 -0
  121. package/lib/parquet/duckdb.ts +144 -0
  122. package/lib/parquet/readers.ts +86 -0
  123. package/lib/parquet/schema.ts +214 -0
  124. package/lib/parquet/shuffle.ts +59 -0
  125. package/lib/parquet/span-sql.ts +54 -0
  126. package/lib/parquet/streams.ts +113 -0
  127. package/lib/parquet/writers.ts +451 -0
  128. package/lib/pl/adapters/emuia/adapter.ts +202 -0
  129. package/lib/pl/tools/fetch/emuia.ts +360 -0
  130. package/lib/recipes/anchor-absorption.ts +30 -19
  131. package/lib/recipes/bare/country.ts +87 -0
  132. package/lib/recipes/bare/postcode/eval.ts +99 -0
  133. package/lib/recipes/bare/postcode.ts +346 -0
  134. package/lib/recipes/boundary-stress.ts +36 -19
  135. package/lib/recipes/country-balanced.ts +67 -87
  136. package/lib/recipes/house-venue.ts +31 -13
  137. package/lib/recipes/intersection.ts +83 -61
  138. package/lib/recipes/po/box/cedex/au-nz.ts +82 -0
  139. package/lib/recipes/po/box/cedex/ca.ts +59 -0
  140. package/lib/recipes/po/box/cedex/fr.ts +77 -0
  141. package/lib/recipes/po/box/cedex/phrases.ts +109 -0
  142. package/lib/recipes/po/box/cedex/recipe.ts +215 -0
  143. package/lib/recipes/po/box/cedex/sources.ts +189 -0
  144. package/lib/recipes/po/box/cedex/types.ts +35 -0
  145. package/lib/recipes/po/box/cedex/us.ts +74 -0
  146. package/lib/recipes/po/box/cedex/vocabulary.ts +106 -0
  147. package/lib/recipes/po/box/cedex.ts +9 -0
  148. package/lib/recipes/po/box.ts +149 -0
  149. package/lib/recipes/scaffold.ts +258 -182
  150. package/lib/recipes/sources.ts +399 -0
  151. package/lib/recipes/street/affix.ts +707 -0
  152. package/lib/recipes/street/bare.ts +115 -0
  153. package/lib/recipes/street.ts +32 -8
  154. package/lib/recipes/sub/venue/context.ts +156 -0
  155. package/lib/recipes/sub/venue/render.ts +170 -0
  156. package/lib/recipes/sub/venue/sources.ts +588 -0
  157. package/lib/recipes/sub/venue.ts +801 -0
  158. package/lib/recipes/trailing-region.ts +70 -81
  159. package/lib/recipes/unit/sources.ts +44 -0
  160. package/lib/recipes/unit.ts +102 -90
  161. package/lib/recipes.ts +106 -0
  162. package/lib/registers.ts +278 -0
  163. package/lib/ro/adapters/retea-scolara/adapter.ts +264 -0
  164. package/lib/ro/tools/fetch/retea-scolara.ts +187 -0
  165. package/lib/runner.ts +220 -84
  166. package/lib/sg/recipes/register.ts +264 -0
  167. package/lib/sg/tools/fetch/acra.ts +174 -0
  168. package/lib/si/recipes/bare-village.ts +116 -0
  169. package/lib/sk/adapters/inspire/adapter.ts +395 -0
  170. package/lib/sk/tools/fetch/inspire.ts +402 -0
  171. package/lib/source-register/effective-manifest.ts +659 -0
  172. package/lib/source-register/register.ts +539 -0
  173. package/lib/source-register/training-manifest.ts +218 -0
  174. package/lib/source-register/types.ts +590 -0
  175. package/lib/source-register.ts +71 -0
  176. package/lib/south-asia/recipes/register.ts +233 -0
  177. package/lib/subvenue/harvest.ts +251 -0
  178. package/lib/subvenue/promotions.ts +293 -0
  179. package/lib/subvenue/surfaces.ts +94 -0
  180. package/lib/subvenue/table.ts +264 -0
  181. package/lib/surfaces/locale.ts +246 -0
  182. package/lib/synthesizers/anchor-absorption.ts +55 -91
  183. package/lib/synthesizers/boundary-stress.ts +49 -131
  184. package/lib/synthesizers/house-venue.ts +44 -102
  185. package/lib/synthesizers/intersection.ts +37 -26
  186. package/lib/synthesizers/no-street.ts +70 -119
  187. package/lib/synthesizers/po-box.ts +90 -105
  188. package/lib/synthesizers/street.ts +47 -35
  189. package/lib/synthesizers/utils.ts +65 -219
  190. package/lib/test-kit/corpus-recipe.ts +45 -28
  191. package/lib/test-kit.ts +116 -0
  192. package/lib/tools/align-canonical.ts +64 -0
  193. package/lib/tools/audit.ts +114 -118
  194. package/lib/tools/corpus-stats.ts +46 -32
  195. package/lib/tools/fetch/atom.ts +164 -0
  196. package/lib/tools/fetch/cordis.ts +318 -0
  197. package/lib/tools/fetch/download/manifest.ts +114 -0
  198. package/lib/tools/fetch/download/network.ts +250 -0
  199. package/lib/tools/fetch/download/retry.ts +174 -0
  200. package/lib/tools/fetch/download.ts +4 -471
  201. package/lib/tools/fetch/geonames/dump.ts +275 -0
  202. package/lib/tools/fetch/geonames/postal.ts +145 -0
  203. package/lib/tools/fetch/gleif.ts +360 -0
  204. package/lib/tools/fetch/header.ts +69 -0
  205. package/lib/tools/fetch/inspire-addresses.ts +495 -0
  206. package/lib/tools/fetch/openaddresses.ts +20 -109
  207. package/lib/tools/fetch/ourairports.ts +16 -49
  208. package/lib/tools/fetch/ppd.ts +10 -10
  209. package/lib/tools/fetch/vlaanderen-ad.ts +435 -0
  210. package/lib/tools/fetch/wfs-harvest.ts +943 -0
  211. package/lib/tools/fetch/wikidata-subvenue.ts +43 -143
  212. package/lib/tools/fetch/zip-archive.ts +100 -0
  213. package/lib/tools/fetch.ts +143 -0
  214. package/lib/tools/golden/expand.ts +605 -0
  215. package/lib/tools/golden/promote.ts +349 -0
  216. package/lib/tools/golden/relabel-street/directory.ts +367 -0
  217. package/lib/tools/golden/relabel-street/row.ts +283 -0
  218. package/lib/tools/golden/relabel-street.ts +9 -0
  219. package/lib/tools/ingest-csv.ts +45 -50
  220. package/lib/tools/jsonl-to-parquet.ts +59 -98
  221. package/lib/tools/lint/recipe-output/vocab.ts +366 -0
  222. package/lib/tools/lint/recipe-output.ts +482 -0
  223. package/lib/tools/migrate/overlay-parquet.ts +173 -0
  224. package/lib/tools/migrate/recipe-output.ts +153 -0
  225. package/lib/tools/migrate/source-names.ts +161 -0
  226. package/lib/tools/overlay/kryptonite.ts +144 -0
  227. package/lib/tools/overlay/manifest.ts +407 -0
  228. package/lib/tools/overlay/merge-source.ts +138 -0
  229. package/lib/tools/overlay/split-slice.ts +144 -0
  230. package/lib/tools/overlay/translit.ts +234 -0
  231. package/lib/tools/overture-subvenue.ts +18 -91
  232. package/lib/tools/postcode-triples.ts +362 -167
  233. package/lib/tools/source-register/build.ts +819 -0
  234. package/lib/tools/sub/venue/head-nouns.ts +208 -0
  235. package/lib/tools/sub/venue/lexicon.ts +394 -0
  236. package/lib/tools/sub/venue/wikidata.ts +88 -0
  237. package/lib/tools.ts +31 -0
  238. package/lib/tw/tools/fetch/gcis.ts +181 -0
  239. package/lib/types.ts +304 -101
  240. package/lib/us/adapters/fcc-bdc/adapter.ts +158 -0
  241. package/lib/us/adapters/state/hi-schools/adapter.ts +171 -0
  242. package/lib/us/adapters/state/hi-schools/workbook.ts +40 -0
  243. package/lib/us/adapters/state/ia-contractors/adapter.ts +148 -0
  244. package/lib/us/adapters/state/ny-notaries/adapter.ts +132 -0
  245. package/lib/us/adapters/state/tx-notaries/adapter.ts +155 -0
  246. package/lib/us/adapters/tiger/adapter.ts +225 -0
  247. package/lib/us/adapters/tiger/street-decompose.ts +73 -0
  248. package/lib/us/adapters/usgov/hrsa-fqhc/adapter.ts +171 -0
  249. package/lib/us/adapters/usgov/imls-pls/adapter.ts +140 -0
  250. package/lib/us/adapters/usgov/irs-bmf/adapter.ts +154 -0
  251. package/lib/us/adapters/usgov/nad/adapter.ts +263 -0
  252. package/lib/us/adapters/usgov/nppes/adapter.ts +180 -0
  253. package/lib/us/adapters/usgov/samhsa-treatment-locator/adapter.ts +195 -0
  254. package/lib/us/fips-state.ts +122 -0
  255. package/lib/us/tools/fetch/hrsa.ts +58 -0
  256. package/lib/us/tools/fetch/imls-pls.ts +131 -0
  257. package/lib/us/tools/fetch/nad.ts +359 -0
  258. package/lib/us/tools/fetch/nppes.ts +153 -0
  259. package/lib/us/tools/fetch/state/hi-schools.ts +167 -0
  260. package/lib/us/tools/fetch/state/sources.ts +146 -0
  261. package/lib/us/tools/fetch/tiger-full.ts +256 -0
  262. package/lib/utils/align.ts +43 -53
  263. package/lib/utils/cooccurrence-stats.ts +101 -0
  264. package/lib/utils/golden.ts +39 -50
  265. package/lib/utils/license.ts +238 -26
  266. package/lib/utils/split.ts +205 -88
  267. package/lib/utils/tokenize.ts +22 -34
  268. package/lib/utils/wof-json.ts +134 -87
  269. package/lib/utils.ts +13 -0
  270. package/lib/ve/recipes/reviewed-postcode-tail.ts +217 -0
  271. package/out/adapters/cordis/adapter.d.ts +324 -0
  272. package/out/adapters/cordis/adapter.d.ts.map +1 -0
  273. package/out/adapters/cordis/adapter.js +616 -0
  274. package/out/adapters/cordis/adapter.js.map +1 -0
  275. package/out/adapters/dedup-key.d.ts +30 -0
  276. package/out/adapters/dedup-key.d.ts.map +1 -0
  277. package/out/adapters/dedup-key.js +35 -0
  278. package/out/adapters/dedup-key.js.map +1 -0
  279. package/out/adapters/errors.d.ts +17 -0
  280. package/out/adapters/errors.d.ts.map +1 -0
  281. package/out/adapters/errors.js +20 -0
  282. package/out/adapters/errors.js.map +1 -0
  283. package/out/adapters/geonames/adapter.d.ts +26 -28
  284. package/out/adapters/geonames/adapter.d.ts.map +1 -1
  285. package/out/adapters/geonames/adapter.js +40 -50
  286. package/out/adapters/geonames/adapter.js.map +1 -1
  287. package/out/adapters/geonames/postal/adapter.d.ts +41 -0
  288. package/out/adapters/geonames/postal/adapter.d.ts.map +1 -0
  289. package/out/adapters/geonames/postal/adapter.js +102 -0
  290. package/out/adapters/geonames/postal/adapter.js.map +1 -0
  291. package/out/adapters/gleif/adapter.d.ts +293 -0
  292. package/out/adapters/gleif/adapter.d.ts.map +1 -0
  293. package/out/adapters/gleif/adapter.js +684 -0
  294. package/out/adapters/gleif/adapter.js.map +1 -0
  295. package/out/adapters/libpostal-dictionary.d.ts +22 -0
  296. package/out/adapters/libpostal-dictionary.d.ts.map +1 -0
  297. package/out/adapters/libpostal-dictionary.js +36 -0
  298. package/out/adapters/libpostal-dictionary.js.map +1 -0
  299. package/out/adapters/openaddresses/adapter.d.ts +28 -43
  300. package/out/adapters/openaddresses/adapter.d.ts.map +1 -1
  301. package/out/adapters/openaddresses/adapter.js +37 -51
  302. package/out/adapters/openaddresses/adapter.js.map +1 -1
  303. package/out/adapters/osm/adapter.d.ts +101 -0
  304. package/out/adapters/osm/adapter.d.ts.map +1 -0
  305. package/out/adapters/osm/adapter.js +260 -0
  306. package/out/adapters/osm/adapter.js.map +1 -0
  307. package/out/adapters/overture/adapter.d.ts +14 -30
  308. package/out/adapters/overture/adapter.d.ts.map +1 -1
  309. package/out/adapters/overture/adapter.js +57 -41
  310. package/out/adapters/overture/adapter.js.map +1 -1
  311. package/out/adapters/po-box/adapter.d.ts +63 -0
  312. package/out/adapters/po-box/adapter.d.ts.map +1 -0
  313. package/out/adapters/po-box/adapter.js +139 -0
  314. package/out/adapters/po-box/adapter.js.map +1 -0
  315. package/out/adapters/registry.d.ts +55 -0
  316. package/out/adapters/registry.d.ts.map +1 -0
  317. package/out/adapters/registry.js +43 -0
  318. package/out/adapters/registry.js.map +1 -0
  319. package/out/adapters/sha256-stream.d.ts +26 -0
  320. package/out/adapters/sha256-stream.d.ts.map +1 -0
  321. package/out/adapters/sha256-stream.js +34 -0
  322. package/out/adapters/sha256-stream.js.map +1 -0
  323. package/out/adapters/source-id.d.ts +33 -0
  324. package/out/adapters/source-id.d.ts.map +1 -0
  325. package/out/adapters/source-id.js +42 -0
  326. package/out/adapters/source-id.js.map +1 -0
  327. package/out/adapters/street-line.d.ts +102 -0
  328. package/out/adapters/street-line.d.ts.map +1 -0
  329. package/out/adapters/street-line.js +117 -0
  330. package/out/adapters/street-line.js.map +1 -0
  331. package/out/adapters/wof/admin/json/adapter.d.ts +88 -0
  332. package/out/adapters/wof/admin/json/adapter.d.ts.map +1 -0
  333. package/out/adapters/wof/admin/json/adapter.js +220 -0
  334. package/out/adapters/wof/admin/json/adapter.js.map +1 -0
  335. package/out/adapters/wof/json-rows.d.ts +89 -0
  336. package/out/adapters/wof/json-rows.d.ts.map +1 -0
  337. package/out/adapters/wof/json-rows.js +135 -0
  338. package/out/adapters/wof/json-rows.js.map +1 -0
  339. package/out/adapters/wof/postalcode-json/adapter.d.ts +49 -0
  340. package/out/adapters/wof/postalcode-json/adapter.d.ts.map +1 -0
  341. package/out/adapters/wof/postalcode-json/adapter.js +165 -0
  342. package/out/adapters/wof/postalcode-json/adapter.js.map +1 -0
  343. package/out/adapters.d.ts +75 -0
  344. package/out/adapters.d.ts.map +1 -0
  345. package/out/adapters.js +167 -0
  346. package/out/adapters.js.map +1 -0
  347. package/out/au/adapters/gnaf/adapter.d.ts +37 -0
  348. package/out/au/adapters/gnaf/adapter.d.ts.map +1 -0
  349. package/out/au/adapters/gnaf/adapter.js +119 -0
  350. package/out/au/adapters/gnaf/adapter.js.map +1 -0
  351. package/out/au/adapters/gnaf/assemble.d.ts +54 -0
  352. package/out/au/adapters/gnaf/assemble.d.ts.map +1 -0
  353. package/out/au/adapters/gnaf/assemble.js +134 -0
  354. package/out/au/adapters/gnaf/assemble.js.map +1 -0
  355. package/out/be/adapters/brussels/adapter.d.ts +212 -0
  356. package/out/be/adapters/brussels/adapter.d.ts.map +1 -0
  357. package/out/be/adapters/brussels/adapter.js +435 -0
  358. package/out/be/adapters/brussels/adapter.js.map +1 -0
  359. package/out/be/adapters/vlaanderen/adapter.d.ts +233 -0
  360. package/out/be/adapters/vlaanderen/adapter.d.ts.map +1 -0
  361. package/out/be/adapters/vlaanderen/adapter.js +416 -0
  362. package/out/be/adapters/vlaanderen/adapter.js.map +1 -0
  363. package/out/be/adapters/wallonie/adapter.d.ts +196 -0
  364. package/out/be/adapters/wallonie/adapter.d.ts.map +1 -0
  365. package/out/be/adapters/wallonie/adapter.js +437 -0
  366. package/out/be/adapters/wallonie/adapter.js.map +1 -0
  367. package/out/be/tools/fetch/brussels.d.ts +119 -0
  368. package/out/be/tools/fetch/brussels.d.ts.map +1 -0
  369. package/out/be/tools/fetch/brussels.js +146 -0
  370. package/out/be/tools/fetch/brussels.js.map +1 -0
  371. package/out/be/tools/fetch/wallonie.d.ts +119 -0
  372. package/out/be/tools/fetch/wallonie.d.ts.map +1 -0
  373. package/out/be/tools/fetch/wallonie.js +167 -0
  374. package/out/be/tools/fetch/wallonie.js.map +1 -0
  375. package/out/build/adapters.d.ts +33 -0
  376. package/out/build/adapters.d.ts.map +1 -0
  377. package/out/build/adapters.js +68 -0
  378. package/out/build/adapters.js.map +1 -0
  379. package/out/build/align.d.ts +73 -0
  380. package/out/build/align.d.ts.map +1 -0
  381. package/out/build/align.js +226 -0
  382. package/out/build/align.js.map +1 -0
  383. package/out/build/checkpoint.d.ts +94 -0
  384. package/out/build/checkpoint.d.ts.map +1 -0
  385. package/out/build/checkpoint.js +59 -0
  386. package/out/build/checkpoint.js.map +1 -0
  387. package/out/build/eligibility.d.ts +47 -0
  388. package/out/build/eligibility.d.ts.map +1 -0
  389. package/out/build/eligibility.js +80 -0
  390. package/out/build/eligibility.js.map +1 -0
  391. package/out/build/heap.d.ts +28 -0
  392. package/out/build/heap.d.ts.map +1 -0
  393. package/out/build/heap.js +47 -0
  394. package/out/build/heap.js.map +1 -0
  395. package/out/build/inputs.d.ts +52 -0
  396. package/out/build/inputs.d.ts.map +1 -0
  397. package/out/build/inputs.js +49 -0
  398. package/out/build/inputs.js.map +1 -0
  399. package/out/build/rows.d.ts +16 -0
  400. package/out/build/rows.d.ts.map +1 -0
  401. package/out/build/rows.js +19 -0
  402. package/out/build/rows.js.map +1 -0
  403. package/out/build/types.d.ts +220 -0
  404. package/out/build/types.d.ts.map +1 -0
  405. package/out/build/types.js +34 -0
  406. package/out/build/types.js.map +1 -0
  407. package/out/build.d.ts +6 -121
  408. package/out/build.d.ts.map +1 -1
  409. package/out/build.js +112 -207
  410. package/out/build.js.map +1 -1
  411. package/out/cn/recipes/organizational-units.d.ts +19 -0
  412. package/out/cn/recipes/organizational-units.d.ts.map +1 -0
  413. package/out/cn/recipes/organizational-units.js +138 -0
  414. package/out/cn/recipes/organizational-units.js.map +1 -0
  415. package/out/cz/adapters/cuzk/adapter.d.ts +52 -0
  416. package/out/cz/adapters/cuzk/adapter.d.ts.map +1 -0
  417. package/out/cz/adapters/cuzk/adapter.js +266 -0
  418. package/out/cz/adapters/cuzk/adapter.js.map +1 -0
  419. package/out/cz/recipes/pcfirst-preposition.d.ts +18 -0
  420. package/out/cz/recipes/pcfirst-preposition.d.ts.map +1 -0
  421. package/out/cz/recipes/pcfirst-preposition.js +110 -0
  422. package/out/cz/recipes/pcfirst-preposition.js.map +1 -0
  423. package/out/cz/tools/fetch/cuzk.d.ts +272 -0
  424. package/out/cz/tools/fetch/cuzk.d.ts.map +1 -0
  425. package/out/cz/tools/fetch/cuzk.js +446 -0
  426. package/out/cz/tools/fetch/cuzk.js.map +1 -0
  427. package/out/de/recipes/locale.d.ts +42 -0
  428. package/out/de/recipes/locale.d.ts.map +1 -0
  429. package/out/de/recipes/locale.js +299 -0
  430. package/out/de/recipes/locale.js.map +1 -0
  431. package/out/directory.d.ts +20 -0
  432. package/out/directory.d.ts.map +1 -0
  433. package/out/directory.js +27 -0
  434. package/out/directory.js.map +1 -0
  435. package/out/dk/adapters/inspire/adapter.d.ts +154 -0
  436. package/out/dk/adapters/inspire/adapter.d.ts.map +1 -0
  437. package/out/dk/adapters/inspire/adapter.js +258 -0
  438. package/out/dk/adapters/inspire/adapter.js.map +1 -0
  439. package/out/dk/tools/fetch/inspire.d.ts +100 -0
  440. package/out/dk/tools/fetch/inspire.d.ts.map +1 -0
  441. package/out/dk/tools/fetch/inspire.js +230 -0
  442. package/out/dk/tools/fetch/inspire.js.map +1 -0
  443. package/out/ee/adapters/ads/adapter.d.ts +109 -0
  444. package/out/ee/adapters/ads/adapter.d.ts.map +1 -0
  445. package/out/ee/adapters/ads/adapter.js +191 -0
  446. package/out/ee/adapters/ads/adapter.js.map +1 -0
  447. package/out/ee/tools/fetch/ads.d.ts +123 -0
  448. package/out/ee/tools/fetch/ads.d.ts.map +1 -0
  449. package/out/ee/tools/fetch/ads.js +195 -0
  450. package/out/ee/tools/fetch/ads.js.map +1 -0
  451. package/out/env.d.ts +7 -3
  452. package/out/env.d.ts.map +1 -1
  453. package/out/env.js +6 -2
  454. package/out/env.js.map +1 -1
  455. package/out/es/adapters/bizkaia/adapter.d.ts +143 -0
  456. package/out/es/adapters/bizkaia/adapter.d.ts.map +1 -0
  457. package/out/es/adapters/bizkaia/adapter.js +332 -0
  458. package/out/es/adapters/bizkaia/adapter.js.map +1 -0
  459. package/out/es/adapters/catastro/adapter.d.ts +104 -0
  460. package/out/es/adapters/catastro/adapter.d.ts.map +1 -0
  461. package/out/es/adapters/catastro/adapter.js +288 -0
  462. package/out/es/adapters/catastro/adapter.js.map +1 -0
  463. package/out/es/adapters/gipuzkoa/adapter.d.ts +91 -0
  464. package/out/es/adapters/gipuzkoa/adapter.d.ts.map +1 -0
  465. package/out/es/adapters/gipuzkoa/adapter.js +225 -0
  466. package/out/es/adapters/gipuzkoa/adapter.js.map +1 -0
  467. package/out/es/adapters/navarra/adapter.d.ts +105 -0
  468. package/out/es/adapters/navarra/adapter.d.ts.map +1 -0
  469. package/out/es/adapters/navarra/adapter.js +241 -0
  470. package/out/es/adapters/navarra/adapter.js.map +1 -0
  471. package/out/es/cadastre.d.ts +109 -0
  472. package/out/es/cadastre.d.ts.map +1 -0
  473. package/out/es/cadastre.js +130 -0
  474. package/out/es/cadastre.js.map +1 -0
  475. package/out/es/tools/fetch/bizkaia.d.ts +278 -0
  476. package/out/es/tools/fetch/bizkaia.d.ts.map +1 -0
  477. package/out/es/tools/fetch/bizkaia.js +477 -0
  478. package/out/es/tools/fetch/bizkaia.js.map +1 -0
  479. package/out/es/tools/fetch/catastro.d.ts +272 -0
  480. package/out/es/tools/fetch/catastro.d.ts.map +1 -0
  481. package/out/es/tools/fetch/catastro.js +486 -0
  482. package/out/es/tools/fetch/catastro.js.map +1 -0
  483. package/out/es/tools/fetch/gipuzkoa.d.ts +162 -0
  484. package/out/es/tools/fetch/gipuzkoa.d.ts.map +1 -0
  485. package/out/es/tools/fetch/gipuzkoa.js +209 -0
  486. package/out/es/tools/fetch/gipuzkoa.js.map +1 -0
  487. package/out/es/tools/fetch/navarra.d.ts +189 -0
  488. package/out/es/tools/fetch/navarra.d.ts.map +1 -0
  489. package/out/es/tools/fetch/navarra.js +316 -0
  490. package/out/es/tools/fetch/navarra.js.map +1 -0
  491. package/out/fi/adapters/ryhti/adapter.d.ts +115 -0
  492. package/out/fi/adapters/ryhti/adapter.d.ts.map +1 -0
  493. package/out/fi/adapters/ryhti/adapter.js +244 -0
  494. package/out/fi/adapters/ryhti/adapter.js.map +1 -0
  495. package/out/fi/tools/fetch/ryhti.d.ts +206 -0
  496. package/out/fi/tools/fetch/ryhti.d.ts.map +1 -0
  497. package/out/fi/tools/fetch/ryhti.js +327 -0
  498. package/out/fi/tools/fetch/ryhti.js.map +1 -0
  499. package/out/fingerprints.d.ts +68 -0
  500. package/out/fingerprints.d.ts.map +1 -0
  501. package/out/fingerprints.js +130 -0
  502. package/out/fingerprints.js.map +1 -0
  503. package/out/fr/adapters/annuaire-education/adapter.d.ts +236 -0
  504. package/out/fr/adapters/annuaire-education/adapter.d.ts.map +1 -0
  505. package/out/fr/adapters/annuaire-education/adapter.js +475 -0
  506. package/out/fr/adapters/annuaire-education/adapter.js.map +1 -0
  507. package/out/fr/adapters/ban/adapter.d.ts +38 -0
  508. package/out/fr/adapters/ban/adapter.d.ts.map +1 -0
  509. package/out/fr/adapters/ban/adapter.js +134 -0
  510. package/out/fr/adapters/ban/adapter.js.map +1 -0
  511. package/out/fr/adapters/finess/adapter.d.ts +276 -0
  512. package/out/fr/adapters/finess/adapter.d.ts.map +1 -0
  513. package/out/fr/adapters/finess/adapter.js +519 -0
  514. package/out/fr/adapters/finess/adapter.js.map +1 -0
  515. package/out/fr/adapters/finess/postal-lines.d.ts +61 -0
  516. package/out/fr/adapters/finess/postal-lines.d.ts.map +1 -0
  517. package/out/fr/adapters/finess/postal-lines.js +114 -0
  518. package/out/fr/adapters/finess/postal-lines.js.map +1 -0
  519. package/out/fr/adapters/finess/voie-type.d.ts +77 -0
  520. package/out/fr/adapters/finess/voie-type.d.ts.map +1 -0
  521. package/out/fr/adapters/finess/voie-type.js +172 -0
  522. package/out/fr/adapters/finess/voie-type.js.map +1 -0
  523. package/out/fr/insee-country.d.ts +45 -0
  524. package/out/fr/insee-country.d.ts.map +1 -0
  525. package/out/fr/insee-country.js +60 -0
  526. package/out/fr/insee-country.js.map +1 -0
  527. package/out/fr/recipes/admin-split.d.ts +15 -0
  528. package/out/fr/recipes/admin-split.d.ts.map +1 -0
  529. package/out/fr/recipes/admin-split.js +170 -0
  530. package/out/fr/recipes/admin-split.js.map +1 -0
  531. package/out/fr/recipes/bare-street.d.ts +13 -0
  532. package/out/fr/recipes/bare-street.d.ts.map +1 -0
  533. package/out/fr/recipes/bare-street.js +129 -0
  534. package/out/fr/recipes/bare-street.js.map +1 -0
  535. package/out/fr/recipes/fragment.d.ts +18 -0
  536. package/out/fr/recipes/fragment.d.ts.map +1 -0
  537. package/out/fr/recipes/fragment.js +197 -0
  538. package/out/fr/recipes/fragment.js.map +1 -0
  539. package/out/fr/recipes/lieudit.d.ts +30 -0
  540. package/out/fr/recipes/lieudit.d.ts.map +1 -0
  541. package/out/fr/recipes/lieudit.js +231 -0
  542. package/out/fr/recipes/lieudit.js.map +1 -0
  543. package/out/fr/recipes/order.d.ts +15 -0
  544. package/out/fr/recipes/order.d.ts.map +1 -0
  545. package/out/fr/recipes/order.js +171 -0
  546. package/out/fr/recipes/order.js.map +1 -0
  547. package/out/fr/street-decompose.d.ts +29 -0
  548. package/out/fr/street-decompose.d.ts.map +1 -0
  549. package/out/fr/street-decompose.js +52 -0
  550. package/out/fr/street-decompose.js.map +1 -0
  551. package/out/fr/tools/fetch/annuaire-education.d.ts +130 -0
  552. package/out/fr/tools/fetch/annuaire-education.d.ts.map +1 -0
  553. package/out/fr/tools/fetch/annuaire-education.js +196 -0
  554. package/out/fr/tools/fetch/annuaire-education.js.map +1 -0
  555. package/out/fr/tools/fetch/ban.d.ts +33 -0
  556. package/out/fr/tools/fetch/ban.d.ts.map +1 -0
  557. package/out/fr/tools/fetch/ban.js +248 -0
  558. package/out/fr/tools/fetch/ban.js.map +1 -0
  559. package/out/fr/tools/fetch/finess.d.ts +145 -0
  560. package/out/fr/tools/fetch/finess.d.ts.map +1 -0
  561. package/out/fr/tools/fetch/finess.js +228 -0
  562. package/out/fr/tools/fetch/finess.js.map +1 -0
  563. package/out/gauntlet-inputs.d.ts +42 -0
  564. package/out/gauntlet-inputs.d.ts.map +1 -0
  565. package/out/gauntlet-inputs.js +78 -0
  566. package/out/gauntlet-inputs.js.map +1 -0
  567. package/out/index.d.ts +10 -4
  568. package/out/index.d.ts.map +1 -1
  569. package/out/index.js +10 -4
  570. package/out/index.js.map +1 -1
  571. package/out/inspire/address.d.ts +251 -0
  572. package/out/inspire/address.d.ts.map +1 -0
  573. package/out/inspire/address.js +384 -0
  574. package/out/inspire/address.js.map +1 -0
  575. package/out/inspire/archive.d.ts +36 -0
  576. package/out/inspire/archive.d.ts.map +1 -0
  577. package/out/inspire/archive.js +42 -0
  578. package/out/inspire/archive.js.map +1 -0
  579. package/out/inspire/errors.d.ts +55 -0
  580. package/out/inspire/errors.d.ts.map +1 -0
  581. package/out/inspire/errors.js +64 -0
  582. package/out/inspire/errors.js.map +1 -0
  583. package/out/inspire/stream.d.ts +137 -0
  584. package/out/inspire/stream.d.ts.map +1 -0
  585. package/out/inspire/stream.js +125 -0
  586. package/out/inspire/stream.js.map +1 -0
  587. package/out/international/recipes/locale.d.ts +90 -0
  588. package/out/international/recipes/locale.d.ts.map +1 -0
  589. package/out/international/recipes/locale.js +419 -0
  590. package/out/international/recipes/locale.js.map +1 -0
  591. package/out/it/adapters/anac/adapter.d.ts +267 -0
  592. package/out/it/adapters/anac/adapter.d.ts.map +1 -0
  593. package/out/it/adapters/anac/adapter.js +429 -0
  594. package/out/it/adapters/anac/adapter.js.map +1 -0
  595. package/out/it/tools/fetch/anac.d.ts +174 -0
  596. package/out/it/tools/fetch/anac.d.ts.map +1 -0
  597. package/out/it/tools/fetch/anac.js +272 -0
  598. package/out/it/tools/fetch/anac.js.map +1 -0
  599. package/out/jp/adapters/wof-admin/adapter.d.ts +68 -0
  600. package/out/jp/adapters/wof-admin/adapter.d.ts.map +1 -0
  601. package/out/jp/adapters/wof-admin/adapter.js +172 -0
  602. package/out/jp/adapters/wof-admin/adapter.js.map +1 -0
  603. package/out/jp/tools/fetch/houjin.d.ts +27 -0
  604. package/out/jp/tools/fetch/houjin.d.ts.map +1 -0
  605. package/out/jp/tools/fetch/houjin.js +106 -0
  606. package/out/jp/tools/fetch/houjin.js.map +1 -0
  607. package/out/kr/adapters/juso/label-rows.d.ts +62 -0
  608. package/out/kr/adapters/juso/label-rows.d.ts.map +1 -0
  609. package/out/kr/adapters/juso/label-rows.js +172 -0
  610. package/out/kr/adapters/juso/label-rows.js.map +1 -0
  611. package/out/kr/adapters/localdata/align.d.ts +31 -0
  612. package/out/kr/adapters/localdata/align.d.ts.map +1 -0
  613. package/out/kr/adapters/localdata/align.js +212 -0
  614. package/out/kr/adapters/localdata/align.js.map +1 -0
  615. package/out/kr/adapters/localdata/key-index.d.ts +62 -0
  616. package/out/kr/adapters/localdata/key-index.d.ts.map +1 -0
  617. package/out/kr/adapters/localdata/key-index.js +127 -0
  618. package/out/kr/adapters/localdata/key-index.js.map +1 -0
  619. package/out/kr/adapters/localdata/permit-rows.d.ts +73 -0
  620. package/out/kr/adapters/localdata/permit-rows.d.ts.map +1 -0
  621. package/out/kr/adapters/localdata/permit-rows.js +136 -0
  622. package/out/kr/adapters/localdata/permit-rows.js.map +1 -0
  623. package/out/kr/tools/fetch/juso.d.ts +33 -0
  624. package/out/kr/tools/fetch/juso.d.ts.map +1 -0
  625. package/out/kr/tools/fetch/juso.js +121 -0
  626. package/out/kr/tools/fetch/juso.js.map +1 -0
  627. package/out/kr/tools/fetch/localdata.d.ts +37 -0
  628. package/out/kr/tools/fetch/localdata.d.ts.map +1 -0
  629. package/out/kr/tools/fetch/localdata.js +147 -0
  630. package/out/kr/tools/fetch/localdata.js.map +1 -0
  631. package/out/lu/adapters/bd-adresses/adapter.d.ts +109 -0
  632. package/out/lu/adapters/bd-adresses/adapter.d.ts.map +1 -0
  633. package/out/lu/adapters/bd-adresses/adapter.js +196 -0
  634. package/out/lu/adapters/bd-adresses/adapter.js.map +1 -0
  635. package/out/lu/tools/fetch/bd-adresses.d.ts +163 -0
  636. package/out/lu/tools/fetch/bd-adresses.d.ts.map +1 -0
  637. package/out/lu/tools/fetch/bd-adresses.js +223 -0
  638. package/out/lu/tools/fetch/bd-adresses.js.map +1 -0
  639. package/out/lv/adapters/varis/adapter.d.ts +283 -0
  640. package/out/lv/adapters/varis/adapter.d.ts.map +1 -0
  641. package/out/lv/adapters/varis/adapter.js +404 -0
  642. package/out/lv/adapters/varis/adapter.js.map +1 -0
  643. package/out/lv/tools/fetch/varis.d.ts +80 -0
  644. package/out/lv/tools/fetch/varis.d.ts.map +1 -0
  645. package/out/lv/tools/fetch/varis.js +133 -0
  646. package/out/lv/tools/fetch/varis.js.map +1 -0
  647. package/out/nl/adapters/kadaster/adapter.d.ts +125 -0
  648. package/out/nl/adapters/kadaster/adapter.d.ts.map +1 -0
  649. package/out/nl/adapters/kadaster/adapter.js +310 -0
  650. package/out/nl/adapters/kadaster/adapter.js.map +1 -0
  651. package/out/nl/recipes/postcode.d.ts +24 -0
  652. package/out/nl/recipes/postcode.d.ts.map +1 -0
  653. package/out/nl/recipes/postcode.js +121 -0
  654. package/out/nl/recipes/postcode.js.map +1 -0
  655. package/out/nl/tools/fetch/kadaster.d.ts +155 -0
  656. package/out/nl/tools/fetch/kadaster.d.ts.map +1 -0
  657. package/out/nl/tools/fetch/kadaster.js +179 -0
  658. package/out/nl/tools/fetch/kadaster.js.map +1 -0
  659. package/out/no/adapters/matrikkelen/adapter.d.ts +44 -0
  660. package/out/no/adapters/matrikkelen/adapter.d.ts.map +1 -0
  661. package/out/no/adapters/matrikkelen/adapter.js +143 -0
  662. package/out/no/adapters/matrikkelen/adapter.js.map +1 -0
  663. package/out/no/recipes/fragment.d.ts +11 -0
  664. package/out/no/recipes/fragment.d.ts.map +1 -0
  665. package/out/no/recipes/fragment.js +149 -0
  666. package/out/no/recipes/fragment.js.map +1 -0
  667. package/out/no/recipes/street/led.d.ts +21 -0
  668. package/out/no/recipes/street/led.d.ts.map +1 -0
  669. package/out/no/recipes/street/led.js +124 -0
  670. package/out/no/recipes/street/led.js.map +1 -0
  671. package/out/no/recipes/street.d.ts +19 -0
  672. package/out/no/recipes/street.d.ts.map +1 -0
  673. package/out/no/recipes/street.js +88 -0
  674. package/out/no/recipes/street.js.map +1 -0
  675. package/out/no/tools/fetch/matrikkelen.d.ts +251 -0
  676. package/out/no/tools/fetch/matrikkelen.d.ts.map +1 -0
  677. package/out/no/tools/fetch/matrikkelen.js +345 -0
  678. package/out/no/tools/fetch/matrikkelen.js.map +1 -0
  679. package/out/parquet/duckdb.d.ts +100 -0
  680. package/out/parquet/duckdb.d.ts.map +1 -0
  681. package/out/parquet/duckdb.js +92 -0
  682. package/out/parquet/duckdb.js.map +1 -0
  683. package/out/parquet/readers.d.ts +44 -0
  684. package/out/parquet/readers.d.ts.map +1 -0
  685. package/out/parquet/readers.js +69 -0
  686. package/out/parquet/readers.js.map +1 -0
  687. package/out/parquet/schema.d.ts +95 -0
  688. package/out/parquet/schema.d.ts.map +1 -0
  689. package/out/parquet/schema.js +157 -0
  690. package/out/parquet/schema.js.map +1 -0
  691. package/out/parquet/shuffle.d.ts +25 -0
  692. package/out/parquet/shuffle.d.ts.map +1 -0
  693. package/out/parquet/shuffle.js +44 -0
  694. package/out/parquet/shuffle.js.map +1 -0
  695. package/out/parquet/span-sql.d.ts +49 -0
  696. package/out/parquet/span-sql.d.ts.map +1 -0
  697. package/out/parquet/span-sql.js +53 -0
  698. package/out/parquet/span-sql.js.map +1 -0
  699. package/out/parquet/streams.d.ts +47 -0
  700. package/out/parquet/streams.d.ts.map +1 -0
  701. package/out/parquet/streams.js +78 -0
  702. package/out/parquet/streams.js.map +1 -0
  703. package/out/parquet/writers.d.ts +124 -0
  704. package/out/parquet/writers.d.ts.map +1 -0
  705. package/out/parquet/writers.js +251 -0
  706. package/out/parquet/writers.js.map +1 -0
  707. package/out/pl/adapters/emuia/adapter.d.ts +81 -0
  708. package/out/pl/adapters/emuia/adapter.d.ts.map +1 -0
  709. package/out/pl/adapters/emuia/adapter.js +178 -0
  710. package/out/pl/adapters/emuia/adapter.js.map +1 -0
  711. package/out/pl/tools/fetch/emuia.d.ts +165 -0
  712. package/out/pl/tools/fetch/emuia.d.ts.map +1 -0
  713. package/out/pl/tools/fetch/emuia.js +260 -0
  714. package/out/pl/tools/fetch/emuia.js.map +1 -0
  715. package/out/recipes/anchor-absorption.d.ts +9 -9
  716. package/out/recipes/anchor-absorption.d.ts.map +1 -1
  717. package/out/recipes/anchor-absorption.js +29 -19
  718. package/out/recipes/anchor-absorption.js.map +1 -1
  719. package/out/recipes/bare/country.d.ts +7 -0
  720. package/out/recipes/bare/country.d.ts.map +1 -0
  721. package/out/recipes/bare/country.js +77 -0
  722. package/out/recipes/bare/country.js.map +1 -0
  723. package/out/recipes/bare/postcode/eval.d.ts +29 -0
  724. package/out/recipes/bare/postcode/eval.d.ts.map +1 -0
  725. package/out/recipes/bare/postcode/eval.js +85 -0
  726. package/out/recipes/bare/postcode/eval.js.map +1 -0
  727. package/out/recipes/bare/postcode.d.ts +41 -0
  728. package/out/recipes/bare/postcode.d.ts.map +1 -0
  729. package/out/recipes/bare/postcode.js +279 -0
  730. package/out/recipes/bare/postcode.js.map +1 -0
  731. package/out/recipes/boundary-stress.d.ts +8 -8
  732. package/out/recipes/boundary-stress.d.ts.map +1 -1
  733. package/out/recipes/boundary-stress.js +36 -19
  734. package/out/recipes/boundary-stress.js.map +1 -1
  735. package/out/recipes/country-balanced.d.ts +3 -21
  736. package/out/recipes/country-balanced.d.ts.map +1 -1
  737. package/out/recipes/country-balanced.js +58 -76
  738. package/out/recipes/country-balanced.js.map +1 -1
  739. package/out/recipes/house-venue.d.ts +8 -6
  740. package/out/recipes/house-venue.d.ts.map +1 -1
  741. package/out/recipes/house-venue.js +29 -13
  742. package/out/recipes/house-venue.js.map +1 -1
  743. package/out/recipes/intersection.d.ts +20 -20
  744. package/out/recipes/intersection.d.ts.map +1 -1
  745. package/out/recipes/intersection.js +65 -53
  746. package/out/recipes/intersection.js.map +1 -1
  747. package/out/recipes/po/box/cedex/au-nz.d.ts +7 -0
  748. package/out/recipes/po/box/cedex/au-nz.d.ts.map +1 -0
  749. package/out/recipes/po/box/cedex/au-nz.js +56 -0
  750. package/out/recipes/po/box/cedex/au-nz.js.map +1 -0
  751. package/out/recipes/po/box/cedex/ca.d.ts +7 -0
  752. package/out/recipes/po/box/cedex/ca.d.ts.map +1 -0
  753. package/out/recipes/po/box/cedex/ca.js +38 -0
  754. package/out/recipes/po/box/cedex/ca.js.map +1 -0
  755. package/out/recipes/po/box/cedex/fr.d.ts +7 -0
  756. package/out/recipes/po/box/cedex/fr.d.ts.map +1 -0
  757. package/out/recipes/po/box/cedex/fr.js +57 -0
  758. package/out/recipes/po/box/cedex/fr.js.map +1 -0
  759. package/out/recipes/po/box/cedex/phrases.d.ts +8 -0
  760. package/out/recipes/po/box/cedex/phrases.d.ts.map +1 -0
  761. package/out/recipes/po/box/cedex/phrases.js +77 -0
  762. package/out/recipes/po/box/cedex/phrases.js.map +1 -0
  763. package/out/recipes/po/box/cedex/recipe.d.ts +9 -0
  764. package/out/recipes/po/box/cedex/recipe.d.ts.map +1 -0
  765. package/out/recipes/po/box/cedex/recipe.js +163 -0
  766. package/out/recipes/po/box/cedex/recipe.js.map +1 -0
  767. package/out/recipes/po/box/cedex/sources.d.ts +86 -0
  768. package/out/recipes/po/box/cedex/sources.d.ts.map +1 -0
  769. package/out/recipes/po/box/cedex/sources.js +143 -0
  770. package/out/recipes/po/box/cedex/sources.js.map +1 -0
  771. package/out/recipes/po/box/cedex/types.d.ts +31 -0
  772. package/out/recipes/po/box/cedex/types.d.ts.map +1 -0
  773. package/out/recipes/po/box/cedex/types.js +5 -0
  774. package/out/recipes/po/box/cedex/types.js.map +1 -0
  775. package/out/recipes/po/box/cedex/us.d.ts +7 -0
  776. package/out/recipes/po/box/cedex/us.d.ts.map +1 -0
  777. package/out/recipes/po/box/cedex/us.js +54 -0
  778. package/out/recipes/po/box/cedex/us.js.map +1 -0
  779. package/out/recipes/po/box/cedex/vocabulary.d.ts +68 -0
  780. package/out/recipes/po/box/cedex/vocabulary.d.ts.map +1 -0
  781. package/out/recipes/po/box/cedex/vocabulary.js +90 -0
  782. package/out/recipes/po/box/cedex/vocabulary.js.map +1 -0
  783. package/out/recipes/po/box/cedex.d.ts +9 -0
  784. package/out/recipes/po/box/cedex.d.ts.map +1 -0
  785. package/out/recipes/po/box/cedex.js +9 -0
  786. package/out/recipes/po/box/cedex.js.map +1 -0
  787. package/out/recipes/po/box.d.ts +18 -0
  788. package/out/recipes/po/box.d.ts.map +1 -0
  789. package/out/recipes/po/box.js +123 -0
  790. package/out/recipes/po/box.js.map +1 -0
  791. package/out/recipes/scaffold.d.ts +214 -121
  792. package/out/recipes/scaffold.d.ts.map +1 -1
  793. package/out/recipes/scaffold.js +78 -88
  794. package/out/recipes/scaffold.js.map +1 -1
  795. package/out/recipes/sources.d.ts +178 -0
  796. package/out/recipes/sources.d.ts.map +1 -0
  797. package/out/recipes/sources.js +348 -0
  798. package/out/recipes/sources.js.map +1 -0
  799. package/out/recipes/street/affix.d.ts +59 -0
  800. package/out/recipes/street/affix.d.ts.map +1 -0
  801. package/out/recipes/street/affix.js +477 -0
  802. package/out/recipes/street/affix.js.map +1 -0
  803. package/out/recipes/street/bare.d.ts +27 -0
  804. package/out/recipes/street/bare.d.ts.map +1 -0
  805. package/out/recipes/street/bare.js +98 -0
  806. package/out/recipes/street/bare.js.map +1 -0
  807. package/out/recipes/street.d.ts +6 -4
  808. package/out/recipes/street.d.ts.map +1 -1
  809. package/out/recipes/street.js +29 -8
  810. package/out/recipes/street.js.map +1 -1
  811. package/out/recipes/sub/venue/context.d.ts +32 -0
  812. package/out/recipes/sub/venue/context.d.ts.map +1 -0
  813. package/out/recipes/sub/venue/context.js +110 -0
  814. package/out/recipes/sub/venue/context.js.map +1 -0
  815. package/out/recipes/sub/venue/render.d.ts +58 -0
  816. package/out/recipes/sub/venue/render.d.ts.map +1 -0
  817. package/out/recipes/sub/venue/render.js +118 -0
  818. package/out/recipes/sub/venue/render.js.map +1 -0
  819. package/out/recipes/sub/venue/sources.d.ts +166 -0
  820. package/out/recipes/sub/venue/sources.d.ts.map +1 -0
  821. package/out/recipes/sub/venue/sources.js +419 -0
  822. package/out/recipes/sub/venue/sources.js.map +1 -0
  823. package/out/recipes/sub/venue.d.ts +176 -0
  824. package/out/recipes/sub/venue.d.ts.map +1 -0
  825. package/out/recipes/sub/venue.js +562 -0
  826. package/out/recipes/sub/venue.js.map +1 -0
  827. package/out/recipes/trailing-region.d.ts +9 -61
  828. package/out/recipes/trailing-region.d.ts.map +1 -1
  829. package/out/recipes/trailing-region.js +56 -81
  830. package/out/recipes/trailing-region.js.map +1 -1
  831. package/out/recipes/unit/sources.d.ts +28 -0
  832. package/out/recipes/unit/sources.d.ts.map +1 -0
  833. package/out/recipes/unit/sources.js +30 -0
  834. package/out/recipes/unit/sources.js.map +1 -0
  835. package/out/recipes/unit.d.ts +30 -17
  836. package/out/recipes/unit.d.ts.map +1 -1
  837. package/out/recipes/unit.js +90 -79
  838. package/out/recipes/unit.js.map +1 -1
  839. package/out/recipes.d.ts +26 -0
  840. package/out/recipes.d.ts.map +1 -0
  841. package/out/recipes.js +100 -0
  842. package/out/recipes.js.map +1 -0
  843. package/out/registers.d.ts +277 -0
  844. package/out/registers.d.ts.map +1 -0
  845. package/out/registers.js +273 -0
  846. package/out/registers.js.map +1 -0
  847. package/out/ro/adapters/retea-scolara/adapter.d.ts +114 -0
  848. package/out/ro/adapters/retea-scolara/adapter.d.ts.map +1 -0
  849. package/out/ro/adapters/retea-scolara/adapter.js +209 -0
  850. package/out/ro/adapters/retea-scolara/adapter.js.map +1 -0
  851. package/out/ro/tools/fetch/retea-scolara.d.ts +69 -0
  852. package/out/ro/tools/fetch/retea-scolara.d.ts.map +1 -0
  853. package/out/ro/tools/fetch/retea-scolara.js +117 -0
  854. package/out/ro/tools/fetch/retea-scolara.js.map +1 -0
  855. package/out/runner.d.ts +120 -60
  856. package/out/runner.d.ts.map +1 -1
  857. package/out/runner.js +130 -56
  858. package/out/runner.js.map +1 -1
  859. package/out/sg/recipes/register.d.ts +55 -0
  860. package/out/sg/recipes/register.d.ts.map +1 -0
  861. package/out/sg/recipes/register.js +206 -0
  862. package/out/sg/recipes/register.js.map +1 -0
  863. package/out/sg/tools/fetch/acra.d.ts +20 -0
  864. package/out/sg/tools/fetch/acra.d.ts.map +1 -0
  865. package/out/sg/tools/fetch/acra.js +123 -0
  866. package/out/sg/tools/fetch/acra.js.map +1 -0
  867. package/out/si/recipes/bare-village.d.ts +31 -0
  868. package/out/si/recipes/bare-village.d.ts.map +1 -0
  869. package/out/si/recipes/bare-village.js +103 -0
  870. package/out/si/recipes/bare-village.js.map +1 -0
  871. package/out/sk/adapters/inspire/adapter.d.ts +119 -0
  872. package/out/sk/adapters/inspire/adapter.d.ts.map +1 -0
  873. package/out/sk/adapters/inspire/adapter.js +318 -0
  874. package/out/sk/adapters/inspire/adapter.js.map +1 -0
  875. package/out/sk/tools/fetch/inspire.d.ts +195 -0
  876. package/out/sk/tools/fetch/inspire.d.ts.map +1 -0
  877. package/out/sk/tools/fetch/inspire.js +280 -0
  878. package/out/sk/tools/fetch/inspire.js.map +1 -0
  879. package/out/source-register/effective-manifest.d.ts +355 -0
  880. package/out/source-register/effective-manifest.d.ts.map +1 -0
  881. package/out/source-register/effective-manifest.js +355 -0
  882. package/out/source-register/effective-manifest.js.map +1 -0
  883. package/out/source-register/register.d.ts +79 -0
  884. package/out/source-register/register.d.ts.map +1 -0
  885. package/out/source-register/register.js +400 -0
  886. package/out/source-register/register.js.map +1 -0
  887. package/out/source-register/training-manifest.d.ts +111 -0
  888. package/out/source-register/training-manifest.d.ts.map +1 -0
  889. package/out/source-register/training-manifest.js +120 -0
  890. package/out/source-register/training-manifest.js.map +1 -0
  891. package/out/source-register/types.d.ts +539 -0
  892. package/out/source-register/types.d.ts.map +1 -0
  893. package/out/source-register/types.js +263 -0
  894. package/out/source-register/types.js.map +1 -0
  895. package/out/source-register.d.ts +19 -0
  896. package/out/source-register.d.ts.map +1 -0
  897. package/out/source-register.js +16 -0
  898. package/out/source-register.js.map +1 -0
  899. package/out/south-asia/recipes/register.d.ts +54 -0
  900. package/out/south-asia/recipes/register.d.ts.map +1 -0
  901. package/out/south-asia/recipes/register.js +174 -0
  902. package/out/south-asia/recipes/register.js.map +1 -0
  903. package/out/subvenue/harvest.d.ts +117 -0
  904. package/out/subvenue/harvest.d.ts.map +1 -0
  905. package/out/subvenue/harvest.js +172 -0
  906. package/out/subvenue/harvest.js.map +1 -0
  907. package/out/subvenue/promotions.d.ts +65 -0
  908. package/out/subvenue/promotions.d.ts.map +1 -0
  909. package/out/subvenue/promotions.js +226 -0
  910. package/out/subvenue/promotions.js.map +1 -0
  911. package/out/subvenue/surfaces.d.ts +39 -0
  912. package/out/subvenue/surfaces.d.ts.map +1 -0
  913. package/out/subvenue/surfaces.js +75 -0
  914. package/out/subvenue/surfaces.js.map +1 -0
  915. package/out/subvenue/table.d.ts +212 -0
  916. package/out/subvenue/table.d.ts.map +1 -0
  917. package/out/subvenue/table.js +94 -0
  918. package/out/subvenue/table.js.map +1 -0
  919. package/out/surfaces/locale.d.ts +113 -0
  920. package/out/surfaces/locale.d.ts.map +1 -0
  921. package/out/surfaces/locale.js +136 -0
  922. package/out/surfaces/locale.js.map +1 -0
  923. package/out/synthesizers/anchor-absorption.d.ts +22 -31
  924. package/out/synthesizers/anchor-absorption.d.ts.map +1 -1
  925. package/out/synthesizers/anchor-absorption.js +30 -85
  926. package/out/synthesizers/anchor-absorption.js.map +1 -1
  927. package/out/synthesizers/boundary-stress.d.ts +17 -48
  928. package/out/synthesizers/boundary-stress.d.ts.map +1 -1
  929. package/out/synthesizers/boundary-stress.js +27 -121
  930. package/out/synthesizers/boundary-stress.js.map +1 -1
  931. package/out/synthesizers/house-venue.d.ts +22 -25
  932. package/out/synthesizers/house-venue.d.ts.map +1 -1
  933. package/out/synthesizers/house-venue.js +28 -97
  934. package/out/synthesizers/house-venue.js.map +1 -1
  935. package/out/synthesizers/intersection.d.ts +10 -8
  936. package/out/synthesizers/intersection.d.ts.map +1 -1
  937. package/out/synthesizers/intersection.js +33 -26
  938. package/out/synthesizers/intersection.js.map +1 -1
  939. package/out/synthesizers/no-street.d.ts +7 -37
  940. package/out/synthesizers/no-street.d.ts.map +1 -1
  941. package/out/synthesizers/no-street.js +55 -111
  942. package/out/synthesizers/no-street.js.map +1 -1
  943. package/out/synthesizers/po-box.d.ts +46 -45
  944. package/out/synthesizers/po-box.d.ts.map +1 -1
  945. package/out/synthesizers/po-box.js +57 -97
  946. package/out/synthesizers/po-box.js.map +1 -1
  947. package/out/synthesizers/street.d.ts +18 -12
  948. package/out/synthesizers/street.d.ts.map +1 -1
  949. package/out/synthesizers/street.js +37 -30
  950. package/out/synthesizers/street.js.map +1 -1
  951. package/out/synthesizers/utils.d.ts +32 -129
  952. package/out/synthesizers/utils.d.ts.map +1 -1
  953. package/out/synthesizers/utils.js +54 -166
  954. package/out/synthesizers/utils.js.map +1 -1
  955. package/out/test-kit/corpus-recipe.d.ts +29 -23
  956. package/out/test-kit/corpus-recipe.d.ts.map +1 -1
  957. package/out/test-kit/corpus-recipe.js +28 -13
  958. package/out/test-kit/corpus-recipe.js.map +1 -1
  959. package/out/test-kit.d.ts +63 -0
  960. package/out/test-kit.d.ts.map +1 -0
  961. package/out/test-kit.js +88 -0
  962. package/out/test-kit.js.map +1 -0
  963. package/out/tools/align-canonical.d.ts +7 -0
  964. package/out/tools/align-canonical.d.ts.map +1 -0
  965. package/out/tools/align-canonical.js +52 -0
  966. package/out/tools/align-canonical.js.map +1 -0
  967. package/out/tools/audit.d.ts +18 -11
  968. package/out/tools/audit.d.ts.map +1 -1
  969. package/out/tools/audit.js +87 -95
  970. package/out/tools/audit.js.map +1 -1
  971. package/out/tools/corpus-stats.d.ts +24 -15
  972. package/out/tools/corpus-stats.d.ts.map +1 -1
  973. package/out/tools/corpus-stats.js +35 -31
  974. package/out/tools/corpus-stats.js.map +1 -1
  975. package/out/tools/fetch/atom.d.ts +115 -0
  976. package/out/tools/fetch/atom.d.ts.map +1 -0
  977. package/out/tools/fetch/atom.js +84 -0
  978. package/out/tools/fetch/atom.js.map +1 -0
  979. package/out/tools/fetch/cordis.d.ts +123 -0
  980. package/out/tools/fetch/cordis.d.ts.map +1 -0
  981. package/out/tools/fetch/cordis.js +208 -0
  982. package/out/tools/fetch/cordis.js.map +1 -0
  983. package/out/tools/fetch/download/manifest.d.ts +56 -0
  984. package/out/tools/fetch/download/manifest.d.ts.map +1 -0
  985. package/out/tools/fetch/download/manifest.js +81 -0
  986. package/out/tools/fetch/download/manifest.js.map +1 -0
  987. package/out/tools/fetch/download/network.d.ts +126 -0
  988. package/out/tools/fetch/download/network.d.ts.map +1 -0
  989. package/out/tools/fetch/download/network.js +140 -0
  990. package/out/tools/fetch/download/network.js.map +1 -0
  991. package/out/tools/fetch/download/retry.d.ts +46 -0
  992. package/out/tools/fetch/download/retry.d.ts.map +1 -0
  993. package/out/tools/fetch/download/retry.js +136 -0
  994. package/out/tools/fetch/download/retry.js.map +1 -0
  995. package/out/tools/fetch/download.d.ts +4 -176
  996. package/out/tools/fetch/download.d.ts.map +1 -1
  997. package/out/tools/fetch/download.js +4 -312
  998. package/out/tools/fetch/download.js.map +1 -1
  999. package/out/tools/fetch/geonames/dump.d.ts +109 -0
  1000. package/out/tools/fetch/geonames/dump.d.ts.map +1 -0
  1001. package/out/tools/fetch/geonames/dump.js +181 -0
  1002. package/out/tools/fetch/geonames/dump.js.map +1 -0
  1003. package/out/tools/fetch/geonames/postal.d.ts +41 -0
  1004. package/out/tools/fetch/geonames/postal.d.ts.map +1 -0
  1005. package/out/tools/fetch/geonames/postal.js +87 -0
  1006. package/out/tools/fetch/geonames/postal.js.map +1 -0
  1007. package/out/tools/fetch/gleif.d.ts +137 -0
  1008. package/out/tools/fetch/gleif.d.ts.map +1 -0
  1009. package/out/tools/fetch/gleif.js +220 -0
  1010. package/out/tools/fetch/gleif.js.map +1 -0
  1011. package/out/tools/fetch/header.d.ts +41 -0
  1012. package/out/tools/fetch/header.d.ts.map +1 -0
  1013. package/out/tools/fetch/header.js +59 -0
  1014. package/out/tools/fetch/header.js.map +1 -0
  1015. package/out/tools/fetch/inspire-addresses.d.ts +249 -0
  1016. package/out/tools/fetch/inspire-addresses.d.ts.map +1 -0
  1017. package/out/tools/fetch/inspire-addresses.js +276 -0
  1018. package/out/tools/fetch/inspire-addresses.js.map +1 -0
  1019. package/out/tools/fetch/openaddresses.d.ts +0 -3
  1020. package/out/tools/fetch/openaddresses.d.ts.map +1 -1
  1021. package/out/tools/fetch/openaddresses.js +18 -97
  1022. package/out/tools/fetch/openaddresses.js.map +1 -1
  1023. package/out/tools/fetch/ourairports.d.ts +5 -32
  1024. package/out/tools/fetch/ourairports.d.ts.map +1 -1
  1025. package/out/tools/fetch/ourairports.js +13 -46
  1026. package/out/tools/fetch/ourairports.js.map +1 -1
  1027. package/out/tools/fetch/ppd.d.ts +4 -3
  1028. package/out/tools/fetch/ppd.d.ts.map +1 -1
  1029. package/out/tools/fetch/ppd.js +10 -9
  1030. package/out/tools/fetch/ppd.js.map +1 -1
  1031. package/out/tools/fetch/vlaanderen-ad.d.ts +131 -0
  1032. package/out/tools/fetch/vlaanderen-ad.d.ts.map +1 -0
  1033. package/out/tools/fetch/vlaanderen-ad.js +293 -0
  1034. package/out/tools/fetch/vlaanderen-ad.js.map +1 -0
  1035. package/out/tools/fetch/wfs-harvest.d.ts +410 -0
  1036. package/out/tools/fetch/wfs-harvest.d.ts.map +1 -0
  1037. package/out/tools/fetch/wfs-harvest.js +522 -0
  1038. package/out/tools/fetch/wfs-harvest.js.map +1 -0
  1039. package/out/tools/fetch/wikidata-subvenue.d.ts +31 -99
  1040. package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -1
  1041. package/out/tools/fetch/wikidata-subvenue.js +26 -121
  1042. package/out/tools/fetch/wikidata-subvenue.js.map +1 -1
  1043. package/out/tools/fetch/zip-archive.d.ts +54 -0
  1044. package/out/tools/fetch/zip-archive.d.ts.map +1 -0
  1045. package/out/tools/fetch/zip-archive.js +58 -0
  1046. package/out/tools/fetch/zip-archive.js.map +1 -0
  1047. package/out/tools/fetch.d.ts +140 -0
  1048. package/out/tools/fetch.d.ts.map +1 -0
  1049. package/out/tools/fetch.js +136 -0
  1050. package/out/tools/fetch.js.map +1 -0
  1051. package/out/tools/golden/expand.d.ts +105 -0
  1052. package/out/tools/golden/expand.d.ts.map +1 -0
  1053. package/out/tools/golden/expand.js +420 -0
  1054. package/out/tools/golden/expand.js.map +1 -0
  1055. package/out/tools/golden/promote.d.ts +77 -0
  1056. package/out/tools/golden/promote.d.ts.map +1 -0
  1057. package/out/tools/golden/promote.js +248 -0
  1058. package/out/tools/golden/promote.js.map +1 -0
  1059. package/out/tools/golden/relabel-street/directory.d.ts +98 -0
  1060. package/out/tools/golden/relabel-street/directory.d.ts.map +1 -0
  1061. package/out/tools/golden/relabel-street/directory.js +227 -0
  1062. package/out/tools/golden/relabel-street/directory.js.map +1 -0
  1063. package/out/tools/golden/relabel-street/row.d.ts +69 -0
  1064. package/out/tools/golden/relabel-street/row.d.ts.map +1 -0
  1065. package/out/tools/golden/relabel-street/row.js +174 -0
  1066. package/out/tools/golden/relabel-street/row.js.map +1 -0
  1067. package/out/tools/golden/relabel-street.d.ts +9 -0
  1068. package/out/tools/golden/relabel-street.d.ts.map +1 -0
  1069. package/out/tools/golden/relabel-street.js +9 -0
  1070. package/out/tools/golden/relabel-street.js.map +1 -0
  1071. package/out/tools/ingest-csv.d.ts +19 -15
  1072. package/out/tools/ingest-csv.d.ts.map +1 -1
  1073. package/out/tools/ingest-csv.js +39 -45
  1074. package/out/tools/ingest-csv.js.map +1 -1
  1075. package/out/tools/jsonl-to-parquet.d.ts +15 -28
  1076. package/out/tools/jsonl-to-parquet.d.ts.map +1 -1
  1077. package/out/tools/jsonl-to-parquet.js +49 -91
  1078. package/out/tools/jsonl-to-parquet.js.map +1 -1
  1079. package/out/tools/lint/recipe-output/vocab.d.ts +77 -0
  1080. package/out/tools/lint/recipe-output/vocab.d.ts.map +1 -0
  1081. package/out/tools/lint/recipe-output/vocab.js +239 -0
  1082. package/out/tools/lint/recipe-output/vocab.js.map +1 -0
  1083. package/out/tools/lint/recipe-output.d.ts +73 -0
  1084. package/out/tools/lint/recipe-output.d.ts.map +1 -0
  1085. package/out/tools/lint/recipe-output.js +302 -0
  1086. package/out/tools/lint/recipe-output.js.map +1 -0
  1087. package/out/tools/migrate/overlay-parquet.d.ts +30 -0
  1088. package/out/tools/migrate/overlay-parquet.d.ts.map +1 -0
  1089. package/out/tools/migrate/overlay-parquet.js +141 -0
  1090. package/out/tools/migrate/overlay-parquet.js.map +1 -0
  1091. package/out/tools/migrate/recipe-output.d.ts +35 -0
  1092. package/out/tools/migrate/recipe-output.d.ts.map +1 -0
  1093. package/out/tools/migrate/recipe-output.js +124 -0
  1094. package/out/tools/migrate/recipe-output.js.map +1 -0
  1095. package/out/tools/migrate/source-names.d.ts +52 -0
  1096. package/out/tools/migrate/source-names.d.ts.map +1 -0
  1097. package/out/tools/migrate/source-names.js +105 -0
  1098. package/out/tools/migrate/source-names.js.map +1 -0
  1099. package/out/tools/overlay/kryptonite.d.ts +33 -0
  1100. package/out/tools/overlay/kryptonite.d.ts.map +1 -0
  1101. package/out/tools/overlay/kryptonite.js +108 -0
  1102. package/out/tools/overlay/kryptonite.js.map +1 -0
  1103. package/out/tools/overlay/manifest.d.ts +142 -0
  1104. package/out/tools/overlay/manifest.d.ts.map +1 -0
  1105. package/out/tools/overlay/manifest.js +260 -0
  1106. package/out/tools/overlay/manifest.js.map +1 -0
  1107. package/out/tools/overlay/merge-source.d.ts +73 -0
  1108. package/out/tools/overlay/merge-source.d.ts.map +1 -0
  1109. package/out/tools/overlay/merge-source.js +63 -0
  1110. package/out/tools/overlay/merge-source.js.map +1 -0
  1111. package/out/tools/overlay/split-slice.d.ts +66 -0
  1112. package/out/tools/overlay/split-slice.d.ts.map +1 -0
  1113. package/out/tools/overlay/split-slice.js +78 -0
  1114. package/out/tools/overlay/split-slice.js.map +1 -0
  1115. package/out/tools/overlay/translit.d.ts +54 -0
  1116. package/out/tools/overlay/translit.d.ts.map +1 -0
  1117. package/out/tools/overlay/translit.js +177 -0
  1118. package/out/tools/overlay/translit.js.map +1 -0
  1119. package/out/tools/overture-subvenue.d.ts +17 -76
  1120. package/out/tools/overture-subvenue.d.ts.map +1 -1
  1121. package/out/tools/overture-subvenue.js +7 -74
  1122. package/out/tools/overture-subvenue.js.map +1 -1
  1123. package/out/tools/postcode-triples.d.ts +96 -109
  1124. package/out/tools/postcode-triples.d.ts.map +1 -1
  1125. package/out/tools/postcode-triples.js +237 -152
  1126. package/out/tools/postcode-triples.js.map +1 -1
  1127. package/out/tools/source-register/build.d.ts +145 -0
  1128. package/out/tools/source-register/build.d.ts.map +1 -0
  1129. package/out/tools/source-register/build.js +515 -0
  1130. package/out/tools/source-register/build.js.map +1 -0
  1131. package/out/tools/sub/venue/head-nouns.d.ts +21 -0
  1132. package/out/tools/sub/venue/head-nouns.d.ts.map +1 -0
  1133. package/out/tools/sub/venue/head-nouns.js +176 -0
  1134. package/out/tools/sub/venue/head-nouns.js.map +1 -0
  1135. package/out/tools/sub/venue/lexicon.d.ts +129 -0
  1136. package/out/tools/sub/venue/lexicon.d.ts.map +1 -0
  1137. package/out/tools/sub/venue/lexicon.js +239 -0
  1138. package/out/tools/sub/venue/lexicon.js.map +1 -0
  1139. package/out/tools/sub/venue/wikidata.d.ts +28 -0
  1140. package/out/tools/sub/venue/wikidata.d.ts.map +1 -0
  1141. package/out/tools/sub/venue/wikidata.js +65 -0
  1142. package/out/tools/sub/venue/wikidata.js.map +1 -0
  1143. package/out/tools.d.ts +31 -0
  1144. package/out/tools.d.ts.map +1 -0
  1145. package/out/tools.js +31 -0
  1146. package/out/tools.js.map +1 -0
  1147. package/out/tw/tools/fetch/gcis.d.ts +29 -0
  1148. package/out/tw/tools/fetch/gcis.d.ts.map +1 -0
  1149. package/out/tw/tools/fetch/gcis.js +141 -0
  1150. package/out/tw/tools/fetch/gcis.js.map +1 -0
  1151. package/out/types.d.ts +270 -101
  1152. package/out/types.d.ts.map +1 -1
  1153. package/out/types.js +133 -9
  1154. package/out/types.js.map +1 -1
  1155. package/out/us/adapters/fcc-bdc/adapter.d.ts +50 -0
  1156. package/out/us/adapters/fcc-bdc/adapter.d.ts.map +1 -0
  1157. package/out/us/adapters/fcc-bdc/adapter.js +129 -0
  1158. package/out/us/adapters/fcc-bdc/adapter.js.map +1 -0
  1159. package/out/us/adapters/state/hi-schools/adapter.d.ts +47 -0
  1160. package/out/us/adapters/state/hi-schools/adapter.d.ts.map +1 -0
  1161. package/out/us/adapters/state/hi-schools/adapter.js +146 -0
  1162. package/out/us/adapters/state/hi-schools/adapter.js.map +1 -0
  1163. package/out/us/adapters/state/hi-schools/workbook.d.ts +34 -0
  1164. package/out/us/adapters/state/hi-schools/workbook.d.ts.map +1 -0
  1165. package/out/us/adapters/state/hi-schools/workbook.js +22 -0
  1166. package/out/us/adapters/state/hi-schools/workbook.js.map +1 -0
  1167. package/out/us/adapters/state/ia-contractors/adapter.d.ts +41 -0
  1168. package/out/us/adapters/state/ia-contractors/adapter.d.ts.map +1 -0
  1169. package/out/us/adapters/state/ia-contractors/adapter.js +117 -0
  1170. package/out/us/adapters/state/ia-contractors/adapter.js.map +1 -0
  1171. package/out/us/adapters/state/ny-notaries/adapter.d.ts +33 -0
  1172. package/out/us/adapters/state/ny-notaries/adapter.d.ts.map +1 -0
  1173. package/out/us/adapters/state/ny-notaries/adapter.js +114 -0
  1174. package/out/us/adapters/state/ny-notaries/adapter.js.map +1 -0
  1175. package/out/us/adapters/state/tx-notaries/adapter.d.ts +34 -0
  1176. package/out/us/adapters/state/tx-notaries/adapter.d.ts.map +1 -0
  1177. package/out/us/adapters/state/tx-notaries/adapter.js +125 -0
  1178. package/out/us/adapters/state/tx-notaries/adapter.js.map +1 -0
  1179. package/out/us/adapters/tiger/adapter.d.ts +31 -0
  1180. package/out/us/adapters/tiger/adapter.d.ts.map +1 -0
  1181. package/out/us/adapters/tiger/adapter.js +173 -0
  1182. package/out/us/adapters/tiger/adapter.js.map +1 -0
  1183. package/out/us/adapters/tiger/street-decompose.d.ts +23 -0
  1184. package/out/us/adapters/tiger/street-decompose.d.ts.map +1 -0
  1185. package/out/us/adapters/tiger/street-decompose.js +58 -0
  1186. package/out/us/adapters/tiger/street-decompose.js.map +1 -0
  1187. package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts +62 -0
  1188. package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts.map +1 -0
  1189. package/out/us/adapters/usgov/hrsa-fqhc/adapter.js +133 -0
  1190. package/out/us/adapters/usgov/hrsa-fqhc/adapter.js.map +1 -0
  1191. package/out/us/adapters/usgov/imls-pls/adapter.d.ts +37 -0
  1192. package/out/us/adapters/usgov/imls-pls/adapter.d.ts.map +1 -0
  1193. package/out/us/adapters/usgov/imls-pls/adapter.js +113 -0
  1194. package/out/us/adapters/usgov/imls-pls/adapter.js.map +1 -0
  1195. package/out/us/adapters/usgov/irs-bmf/adapter.d.ts +38 -0
  1196. package/out/us/adapters/usgov/irs-bmf/adapter.d.ts.map +1 -0
  1197. package/out/us/adapters/usgov/irs-bmf/adapter.js +126 -0
  1198. package/out/us/adapters/usgov/irs-bmf/adapter.js.map +1 -0
  1199. package/out/us/adapters/usgov/nad/adapter.d.ts +28 -0
  1200. package/out/us/adapters/usgov/nad/adapter.d.ts.map +1 -0
  1201. package/out/us/adapters/usgov/nad/adapter.js +185 -0
  1202. package/out/us/adapters/usgov/nad/adapter.js.map +1 -0
  1203. package/out/us/adapters/usgov/nppes/adapter.d.ts +29 -0
  1204. package/out/us/adapters/usgov/nppes/adapter.d.ts.map +1 -0
  1205. package/out/us/adapters/usgov/nppes/adapter.js +140 -0
  1206. package/out/us/adapters/usgov/nppes/adapter.js.map +1 -0
  1207. package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts +47 -0
  1208. package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts.map +1 -0
  1209. package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js +153 -0
  1210. package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js.map +1 -0
  1211. package/out/us/fips-state.d.ts +50 -0
  1212. package/out/us/fips-state.d.ts.map +1 -0
  1213. package/out/us/fips-state.js +109 -0
  1214. package/out/us/fips-state.js.map +1 -0
  1215. package/out/us/tools/fetch/hrsa.d.ts +18 -0
  1216. package/out/us/tools/fetch/hrsa.d.ts.map +1 -0
  1217. package/out/us/tools/fetch/hrsa.js +45 -0
  1218. package/out/us/tools/fetch/hrsa.js.map +1 -0
  1219. package/out/us/tools/fetch/imls-pls.d.ts +14 -0
  1220. package/out/us/tools/fetch/imls-pls.d.ts.map +1 -0
  1221. package/out/us/tools/fetch/imls-pls.js +91 -0
  1222. package/out/us/tools/fetch/imls-pls.js.map +1 -0
  1223. package/out/us/tools/fetch/nad.d.ts +82 -0
  1224. package/out/us/tools/fetch/nad.d.ts.map +1 -0
  1225. package/out/us/tools/fetch/nad.js +239 -0
  1226. package/out/us/tools/fetch/nad.js.map +1 -0
  1227. package/out/us/tools/fetch/nppes.d.ts +16 -0
  1228. package/out/us/tools/fetch/nppes.d.ts.map +1 -0
  1229. package/out/us/tools/fetch/nppes.js +114 -0
  1230. package/out/us/tools/fetch/nppes.js.map +1 -0
  1231. package/out/us/tools/fetch/state/hi-schools.d.ts +29 -0
  1232. package/out/us/tools/fetch/state/hi-schools.d.ts.map +1 -0
  1233. package/out/us/tools/fetch/state/hi-schools.js +114 -0
  1234. package/out/us/tools/fetch/state/hi-schools.js.map +1 -0
  1235. package/out/us/tools/fetch/state/sources.d.ts +27 -0
  1236. package/out/us/tools/fetch/state/sources.d.ts.map +1 -0
  1237. package/out/us/tools/fetch/state/sources.js +110 -0
  1238. package/out/us/tools/fetch/state/sources.js.map +1 -0
  1239. package/out/us/tools/fetch/tiger-full.d.ts +9 -0
  1240. package/out/us/tools/fetch/tiger-full.d.ts.map +1 -0
  1241. package/out/us/tools/fetch/tiger-full.js +178 -0
  1242. package/out/us/tools/fetch/tiger-full.js.map +1 -0
  1243. package/out/utils/align.d.ts +25 -20
  1244. package/out/utils/align.d.ts.map +1 -1
  1245. package/out/utils/align.js +27 -42
  1246. package/out/utils/align.js.map +1 -1
  1247. package/out/utils/cooccurrence-stats.d.ts +58 -0
  1248. package/out/utils/cooccurrence-stats.d.ts.map +1 -0
  1249. package/out/utils/cooccurrence-stats.js +62 -0
  1250. package/out/utils/cooccurrence-stats.js.map +1 -0
  1251. package/out/utils/golden.d.ts +23 -29
  1252. package/out/utils/golden.d.ts.map +1 -1
  1253. package/out/utils/golden.js +33 -45
  1254. package/out/utils/golden.js.map +1 -1
  1255. package/out/utils/license.d.ts +158 -21
  1256. package/out/utils/license.d.ts.map +1 -1
  1257. package/out/utils/license.js +156 -26
  1258. package/out/utils/license.js.map +1 -1
  1259. package/out/utils/split.d.ts +66 -70
  1260. package/out/utils/split.d.ts.map +1 -1
  1261. package/out/utils/split.js +158 -69
  1262. package/out/utils/split.js.map +1 -1
  1263. package/out/utils/tokenize.d.ts +16 -28
  1264. package/out/utils/tokenize.d.ts.map +1 -1
  1265. package/out/utils/tokenize.js +18 -31
  1266. package/out/utils/tokenize.js.map +1 -1
  1267. package/out/utils/wof-json.d.ts +88 -62
  1268. package/out/utils/wof-json.d.ts.map +1 -1
  1269. package/out/utils/wof-json.js +81 -65
  1270. package/out/utils/wof-json.js.map +1 -1
  1271. package/out/utils.d.ts +13 -0
  1272. package/out/utils.d.ts.map +1 -0
  1273. package/out/utils.js +13 -0
  1274. package/out/utils.js.map +1 -0
  1275. package/out/ve/recipes/reviewed-postcode-tail.d.ts +65 -0
  1276. package/out/ve/recipes/reviewed-postcode-tail.d.ts.map +1 -0
  1277. package/out/ve/recipes/reviewed-postcode-tail.js +146 -0
  1278. package/out/ve/recipes/reviewed-postcode-tail.js.map +1 -0
  1279. package/package.json +46 -330
  1280. package/lib/adapters/ban/adapter.ts +0 -190
  1281. package/lib/adapters/ban/street-decompose.ts +0 -66
  1282. package/lib/adapters/fcc-bdc/adapter.ts +0 -174
  1283. package/lib/adapters/geonames-postal/adapter.ts +0 -122
  1284. package/lib/adapters/gnaf/adapter.ts +0 -149
  1285. package/lib/adapters/gnaf/assemble.ts +0 -225
  1286. package/lib/adapters/index.ts +0 -153
  1287. package/lib/adapters/state-hi-schools/adapter.ts +0 -170
  1288. package/lib/adapters/state-hi-schools/workbook.ts +0 -35
  1289. package/lib/adapters/state-ia-contractors/adapter.ts +0 -144
  1290. package/lib/adapters/state-ny-notaries/adapter.ts +0 -141
  1291. package/lib/adapters/state-tx-notaries/adapter.ts +0 -157
  1292. package/lib/adapters/synth-po-box/adapter.ts +0 -204
  1293. package/lib/adapters/tiger/adapter.ts +0 -252
  1294. package/lib/adapters/tiger/street-decompose.ts +0 -83
  1295. package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +0 -167
  1296. package/lib/adapters/usgov-imls-pls/adapter.ts +0 -143
  1297. package/lib/adapters/usgov-irs-bmf/adapter.ts +0 -151
  1298. package/lib/adapters/usgov-nad/adapter.ts +0 -334
  1299. package/lib/adapters/usgov-nppes/adapter.ts +0 -151
  1300. package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -193
  1301. package/lib/adapters/utils/index.ts +0 -307
  1302. package/lib/adapters/wof-admin-jp/adapter.ts +0 -214
  1303. package/lib/adapters/wof-admin-json/adapter.ts +0 -231
  1304. package/lib/adapters/wof-json-rows.ts +0 -129
  1305. package/lib/adapters/wof-postalcode-json/adapter.ts +0 -176
  1306. package/lib/codex/us-fips-state.ts +0 -113
  1307. package/lib/recipes/bare-country.ts +0 -95
  1308. package/lib/recipes/cn-organizational-units.ts +0 -199
  1309. package/lib/recipes/cz-pcfirst-preposition.ts +0 -112
  1310. package/lib/recipes/fr-admin-split.ts +0 -243
  1311. package/lib/recipes/fr-bare-street.ts +0 -171
  1312. package/lib/recipes/fr-fragment.ts +0 -334
  1313. package/lib/recipes/fr-lieudit.ts +0 -301
  1314. package/lib/recipes/fr-order.ts +0 -246
  1315. package/lib/recipes/german.ts +0 -360
  1316. package/lib/recipes/index.ts +0 -97
  1317. package/lib/recipes/locale.ts +0 -600
  1318. package/lib/recipes/nl-postcode.ts +0 -117
  1319. package/lib/recipes/no-fragment.ts +0 -213
  1320. package/lib/recipes/no-street-led.ts +0 -135
  1321. package/lib/recipes/no-street.ts +0 -91
  1322. package/lib/recipes/po-box-cedex.ts +0 -976
  1323. package/lib/recipes/po-box.ts +0 -124
  1324. package/lib/recipes/reviewed-postcode-tail.ts +0 -190
  1325. package/lib/recipes/si-bare-village.ts +0 -99
  1326. package/lib/recipes/street-affix.ts +0 -805
  1327. package/lib/recipes/street-bare.ts +0 -102
  1328. package/lib/recipes/sub-venue-sources.ts +0 -878
  1329. package/lib/recipes/sub-venue.ts +0 -998
  1330. package/lib/synthesizers/german.ts +0 -260
  1331. package/lib/test-kit/index.ts +0 -100
  1332. package/lib/tools/align-slice.ts +0 -68
  1333. package/lib/tools/fetch/acra-sg.ts +0 -174
  1334. package/lib/tools/fetch/ban.ts +0 -289
  1335. package/lib/tools/fetch/gcis-tw.ts +0 -175
  1336. package/lib/tools/fetch/geonames-dump.ts +0 -257
  1337. package/lib/tools/fetch/geonames-postal.ts +0 -180
  1338. package/lib/tools/fetch/houjin-jp.ts +0 -135
  1339. package/lib/tools/fetch/hrsa.ts +0 -59
  1340. package/lib/tools/fetch/imls-pls.ts +0 -149
  1341. package/lib/tools/fetch/index.ts +0 -174
  1342. package/lib/tools/fetch/juso-kr.ts +0 -165
  1343. package/lib/tools/fetch/localdata-kr.ts +0 -194
  1344. package/lib/tools/fetch/nad.ts +0 -341
  1345. package/lib/tools/fetch/nppes.ts +0 -165
  1346. package/lib/tools/fetch/state-hi-schools.ts +0 -161
  1347. package/lib/tools/fetch/state-sources.ts +0 -146
  1348. package/lib/tools/fetch/tiger-full.ts +0 -308
  1349. package/lib/tools/gb-title-case.ts +0 -69
  1350. package/lib/tools/golden-expand.ts +0 -574
  1351. package/lib/tools/golden-promote.ts +0 -337
  1352. package/lib/tools/golden-relabel-street.ts +0 -686
  1353. package/lib/tools/index.ts +0 -28
  1354. package/lib/tools/lint-slice-vocab.ts +0 -388
  1355. package/lib/tools/lint-slice.ts +0 -496
  1356. package/lib/tools/overlay-manifest.ts +0 -148
  1357. package/lib/tools/slice-kryptonite.ts +0 -137
  1358. package/lib/tools/slice-translit.ts +0 -218
  1359. package/lib/tools/sub-venue/harvest.ts +0 -234
  1360. package/lib/tools/sub-venue/head-nouns.ts +0 -245
  1361. package/lib/tools/sub-venue/surfaces.ts +0 -95
  1362. package/lib/tools/sub-venue/table.ts +0 -281
  1363. package/lib/tools/sub-venue/wikidata.ts +0 -85
  1364. package/lib/tools/sub-venue-lexicon.ts +0 -429
  1365. package/lib/tools/sub-venue-promotions.ts +0 -330
  1366. package/lib/utils/index.ts +0 -14
  1367. package/lib/utils/parquet.ts +0 -582
  1368. package/lib/utils/slice-stats.ts +0 -95
  1369. package/out/adapters/ban/adapter.d.ts +0 -44
  1370. package/out/adapters/ban/adapter.d.ts.map +0 -1
  1371. package/out/adapters/ban/adapter.js +0 -149
  1372. package/out/adapters/ban/adapter.js.map +0 -1
  1373. package/out/adapters/ban/street-decompose.d.ts +0 -28
  1374. package/out/adapters/ban/street-decompose.d.ts.map +0 -1
  1375. package/out/adapters/ban/street-decompose.js +0 -51
  1376. package/out/adapters/ban/street-decompose.js.map +0 -1
  1377. package/out/adapters/fcc-bdc/adapter.d.ts +0 -68
  1378. package/out/adapters/fcc-bdc/adapter.d.ts.map +0 -1
  1379. package/out/adapters/fcc-bdc/adapter.js +0 -144
  1380. package/out/adapters/fcc-bdc/adapter.js.map +0 -1
  1381. package/out/adapters/geonames-postal/adapter.d.ts +0 -54
  1382. package/out/adapters/geonames-postal/adapter.d.ts.map +0 -1
  1383. package/out/adapters/geonames-postal/adapter.js +0 -107
  1384. package/out/adapters/geonames-postal/adapter.js.map +0 -1
  1385. package/out/adapters/gnaf/adapter.d.ts +0 -49
  1386. package/out/adapters/gnaf/adapter.d.ts.map +0 -1
  1387. package/out/adapters/gnaf/adapter.js +0 -124
  1388. package/out/adapters/gnaf/adapter.js.map +0 -1
  1389. package/out/adapters/gnaf/assemble.d.ts +0 -65
  1390. package/out/adapters/gnaf/assemble.d.ts.map +0 -1
  1391. package/out/adapters/gnaf/assemble.js +0 -154
  1392. package/out/adapters/gnaf/assemble.js.map +0 -1
  1393. package/out/adapters/index.d.ts +0 -51
  1394. package/out/adapters/index.d.ts.map +0 -1
  1395. package/out/adapters/index.js +0 -95
  1396. package/out/adapters/index.js.map +0 -1
  1397. package/out/adapters/state-hi-schools/adapter.d.ts +0 -46
  1398. package/out/adapters/state-hi-schools/adapter.d.ts.map +0 -1
  1399. package/out/adapters/state-hi-schools/adapter.js +0 -145
  1400. package/out/adapters/state-hi-schools/adapter.js.map +0 -1
  1401. package/out/adapters/state-hi-schools/workbook.d.ts +0 -29
  1402. package/out/adapters/state-hi-schools/workbook.d.ts.map +0 -1
  1403. package/out/adapters/state-hi-schools/workbook.js +0 -20
  1404. package/out/adapters/state-hi-schools/workbook.js.map +0 -1
  1405. package/out/adapters/state-ia-contractors/adapter.d.ts +0 -34
  1406. package/out/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
  1407. package/out/adapters/state-ia-contractors/adapter.js +0 -111
  1408. package/out/adapters/state-ia-contractors/adapter.js.map +0 -1
  1409. package/out/adapters/state-ny-notaries/adapter.d.ts +0 -32
  1410. package/out/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
  1411. package/out/adapters/state-ny-notaries/adapter.js +0 -119
  1412. package/out/adapters/state-ny-notaries/adapter.js.map +0 -1
  1413. package/out/adapters/state-tx-notaries/adapter.d.ts +0 -33
  1414. package/out/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
  1415. package/out/adapters/state-tx-notaries/adapter.js +0 -125
  1416. package/out/adapters/state-tx-notaries/adapter.js.map +0 -1
  1417. package/out/adapters/synth-po-box/adapter.d.ts +0 -67
  1418. package/out/adapters/synth-po-box/adapter.d.ts.map +0 -1
  1419. package/out/adapters/synth-po-box/adapter.js +0 -140
  1420. package/out/adapters/synth-po-box/adapter.js.map +0 -1
  1421. package/out/adapters/tiger/adapter.d.ts +0 -55
  1422. package/out/adapters/tiger/adapter.d.ts.map +0 -1
  1423. package/out/adapters/tiger/adapter.js +0 -201
  1424. package/out/adapters/tiger/adapter.js.map +0 -1
  1425. package/out/adapters/tiger/street-decompose.d.ts +0 -30
  1426. package/out/adapters/tiger/street-decompose.d.ts.map +0 -1
  1427. package/out/adapters/tiger/street-decompose.js +0 -68
  1428. package/out/adapters/tiger/street-decompose.js.map +0 -1
  1429. package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -56
  1430. package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
  1431. package/out/adapters/usgov-hrsa-fqhc/adapter.js +0 -132
  1432. package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
  1433. package/out/adapters/usgov-imls-pls/adapter.d.ts +0 -36
  1434. package/out/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
  1435. package/out/adapters/usgov-imls-pls/adapter.js +0 -114
  1436. package/out/adapters/usgov-imls-pls/adapter.js.map +0 -1
  1437. package/out/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
  1438. package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
  1439. package/out/adapters/usgov-irs-bmf/adapter.js +0 -120
  1440. package/out/adapters/usgov-irs-bmf/adapter.js.map +0 -1
  1441. package/out/adapters/usgov-nad/adapter.d.ts +0 -48
  1442. package/out/adapters/usgov-nad/adapter.d.ts.map +0 -1
  1443. package/out/adapters/usgov-nad/adapter.js +0 -249
  1444. package/out/adapters/usgov-nad/adapter.js.map +0 -1
  1445. package/out/adapters/usgov-nppes/adapter.d.ts +0 -39
  1446. package/out/adapters/usgov-nppes/adapter.d.ts.map +0 -1
  1447. package/out/adapters/usgov-nppes/adapter.js +0 -118
  1448. package/out/adapters/usgov-nppes/adapter.js.map +0 -1
  1449. package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts +0 -46
  1450. package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
  1451. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -154
  1452. package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
  1453. package/out/adapters/utils/index.d.ts +0 -191
  1454. package/out/adapters/utils/index.d.ts.map +0 -1
  1455. package/out/adapters/utils/index.js +0 -206
  1456. package/out/adapters/utils/index.js.map +0 -1
  1457. package/out/adapters/wof-admin-jp/adapter.d.ts +0 -65
  1458. package/out/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
  1459. package/out/adapters/wof-admin-jp/adapter.js +0 -161
  1460. package/out/adapters/wof-admin-jp/adapter.js.map +0 -1
  1461. package/out/adapters/wof-admin-json/adapter.d.ts +0 -79
  1462. package/out/adapters/wof-admin-json/adapter.d.ts.map +0 -1
  1463. package/out/adapters/wof-admin-json/adapter.js +0 -197
  1464. package/out/adapters/wof-admin-json/adapter.js.map +0 -1
  1465. package/out/adapters/wof-json-rows.d.ts +0 -62
  1466. package/out/adapters/wof-json-rows.d.ts.map +0 -1
  1467. package/out/adapters/wof-json-rows.js +0 -83
  1468. package/out/adapters/wof-json-rows.js.map +0 -1
  1469. package/out/adapters/wof-postalcode-json/adapter.d.ts +0 -65
  1470. package/out/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
  1471. package/out/adapters/wof-postalcode-json/adapter.js +0 -151
  1472. package/out/adapters/wof-postalcode-json/adapter.js.map +0 -1
  1473. package/out/codex/us-fips-state.d.ts +0 -41
  1474. package/out/codex/us-fips-state.d.ts.map +0 -1
  1475. package/out/codex/us-fips-state.js +0 -100
  1476. package/out/codex/us-fips-state.js.map +0 -1
  1477. package/out/recipes/bare-country.d.ts +0 -25
  1478. package/out/recipes/bare-country.d.ts.map +0 -1
  1479. package/out/recipes/bare-country.js +0 -88
  1480. package/out/recipes/bare-country.js.map +0 -1
  1481. package/out/recipes/cn-organizational-units.d.ts +0 -36
  1482. package/out/recipes/cn-organizational-units.d.ts.map +0 -1
  1483. package/out/recipes/cn-organizational-units.js +0 -159
  1484. package/out/recipes/cn-organizational-units.js.map +0 -1
  1485. package/out/recipes/cz-pcfirst-preposition.d.ts +0 -22
  1486. package/out/recipes/cz-pcfirst-preposition.d.ts.map +0 -1
  1487. package/out/recipes/cz-pcfirst-preposition.js +0 -101
  1488. package/out/recipes/cz-pcfirst-preposition.js.map +0 -1
  1489. package/out/recipes/fr-admin-split.d.ts +0 -38
  1490. package/out/recipes/fr-admin-split.d.ts.map +0 -1
  1491. package/out/recipes/fr-admin-split.js +0 -192
  1492. package/out/recipes/fr-admin-split.js.map +0 -1
  1493. package/out/recipes/fr-bare-street.d.ts +0 -28
  1494. package/out/recipes/fr-bare-street.d.ts.map +0 -1
  1495. package/out/recipes/fr-bare-street.js +0 -144
  1496. package/out/recipes/fr-bare-street.js.map +0 -1
  1497. package/out/recipes/fr-fragment.d.ts +0 -77
  1498. package/out/recipes/fr-fragment.d.ts.map +0 -1
  1499. package/out/recipes/fr-fragment.js +0 -277
  1500. package/out/recipes/fr-fragment.js.map +0 -1
  1501. package/out/recipes/fr-lieudit.d.ts +0 -32
  1502. package/out/recipes/fr-lieudit.d.ts.map +0 -1
  1503. package/out/recipes/fr-lieudit.js +0 -227
  1504. package/out/recipes/fr-lieudit.js.map +0 -1
  1505. package/out/recipes/fr-order.d.ts +0 -38
  1506. package/out/recipes/fr-order.d.ts.map +0 -1
  1507. package/out/recipes/fr-order.js +0 -198
  1508. package/out/recipes/fr-order.js.map +0 -1
  1509. package/out/recipes/german.d.ts +0 -44
  1510. package/out/recipes/german.d.ts.map +0 -1
  1511. package/out/recipes/german.js +0 -289
  1512. package/out/recipes/german.js.map +0 -1
  1513. package/out/recipes/index.d.ts +0 -24
  1514. package/out/recipes/index.d.ts.map +0 -1
  1515. package/out/recipes/index.js +0 -91
  1516. package/out/recipes/index.js.map +0 -1
  1517. package/out/recipes/locale.d.ts +0 -136
  1518. package/out/recipes/locale.d.ts.map +0 -1
  1519. package/out/recipes/locale.js +0 -460
  1520. package/out/recipes/locale.js.map +0 -1
  1521. package/out/recipes/nl-postcode.d.ts +0 -26
  1522. package/out/recipes/nl-postcode.d.ts.map +0 -1
  1523. package/out/recipes/nl-postcode.js +0 -103
  1524. package/out/recipes/nl-postcode.js.map +0 -1
  1525. package/out/recipes/no-fragment.d.ts +0 -43
  1526. package/out/recipes/no-fragment.d.ts.map +0 -1
  1527. package/out/recipes/no-fragment.js +0 -183
  1528. package/out/recipes/no-fragment.js.map +0 -1
  1529. package/out/recipes/no-street-led.d.ts +0 -24
  1530. package/out/recipes/no-street-led.d.ts.map +0 -1
  1531. package/out/recipes/no-street-led.js +0 -114
  1532. package/out/recipes/no-street-led.js.map +0 -1
  1533. package/out/recipes/no-street.d.ts +0 -18
  1534. package/out/recipes/no-street.d.ts.map +0 -1
  1535. package/out/recipes/no-street.js +0 -72
  1536. package/out/recipes/no-street.js.map +0 -1
  1537. package/out/recipes/po-box-cedex.d.ts +0 -38
  1538. package/out/recipes/po-box-cedex.d.ts.map +0 -1
  1539. package/out/recipes/po-box-cedex.js +0 -768
  1540. package/out/recipes/po-box-cedex.js.map +0 -1
  1541. package/out/recipes/po-box.d.ts +0 -17
  1542. package/out/recipes/po-box.d.ts.map +0 -1
  1543. package/out/recipes/po-box.js +0 -101
  1544. package/out/recipes/po-box.js.map +0 -1
  1545. package/out/recipes/reviewed-postcode-tail.d.ts +0 -47
  1546. package/out/recipes/reviewed-postcode-tail.d.ts.map +0 -1
  1547. package/out/recipes/reviewed-postcode-tail.js +0 -125
  1548. package/out/recipes/reviewed-postcode-tail.js.map +0 -1
  1549. package/out/recipes/si-bare-village.d.ts +0 -32
  1550. package/out/recipes/si-bare-village.d.ts.map +0 -1
  1551. package/out/recipes/si-bare-village.js +0 -89
  1552. package/out/recipes/si-bare-village.js.map +0 -1
  1553. package/out/recipes/street-affix.d.ts +0 -89
  1554. package/out/recipes/street-affix.d.ts.map +0 -1
  1555. package/out/recipes/street-affix.js +0 -563
  1556. package/out/recipes/street-affix.js.map +0 -1
  1557. package/out/recipes/street-bare.d.ts +0 -25
  1558. package/out/recipes/street-bare.d.ts.map +0 -1
  1559. package/out/recipes/street-bare.js +0 -87
  1560. package/out/recipes/street-bare.js.map +0 -1
  1561. package/out/recipes/sub-venue-sources.d.ts +0 -229
  1562. package/out/recipes/sub-venue-sources.d.ts.map +0 -1
  1563. package/out/recipes/sub-venue-sources.js +0 -654
  1564. package/out/recipes/sub-venue-sources.js.map +0 -1
  1565. package/out/recipes/sub-venue.d.ts +0 -269
  1566. package/out/recipes/sub-venue.d.ts.map +0 -1
  1567. package/out/recipes/sub-venue.js +0 -726
  1568. package/out/recipes/sub-venue.js.map +0 -1
  1569. package/out/synthesizers/german.d.ts +0 -115
  1570. package/out/synthesizers/german.d.ts.map +0 -1
  1571. package/out/synthesizers/german.js +0 -149
  1572. package/out/synthesizers/german.js.map +0 -1
  1573. package/out/test-kit/index.d.ts +0 -48
  1574. package/out/test-kit/index.d.ts.map +0 -1
  1575. package/out/test-kit/index.js +0 -78
  1576. package/out/test-kit/index.js.map +0 -1
  1577. package/out/tools/align-slice.d.ts +0 -7
  1578. package/out/tools/align-slice.d.ts.map +0 -1
  1579. package/out/tools/align-slice.js +0 -55
  1580. package/out/tools/align-slice.js.map +0 -1
  1581. package/out/tools/fetch/acra-sg.d.ts +0 -23
  1582. package/out/tools/fetch/acra-sg.d.ts.map +0 -1
  1583. package/out/tools/fetch/acra-sg.js +0 -126
  1584. package/out/tools/fetch/acra-sg.js.map +0 -1
  1585. package/out/tools/fetch/ban.d.ts +0 -31
  1586. package/out/tools/fetch/ban.d.ts.map +0 -1
  1587. package/out/tools/fetch/ban.js +0 -239
  1588. package/out/tools/fetch/ban.js.map +0 -1
  1589. package/out/tools/fetch/gcis-tw.d.ts +0 -23
  1590. package/out/tools/fetch/gcis-tw.d.ts.map +0 -1
  1591. package/out/tools/fetch/gcis-tw.js +0 -135
  1592. package/out/tools/fetch/gcis-tw.js.map +0 -1
  1593. package/out/tools/fetch/geonames-dump.d.ts +0 -91
  1594. package/out/tools/fetch/geonames-dump.d.ts.map +0 -1
  1595. package/out/tools/fetch/geonames-dump.js +0 -171
  1596. package/out/tools/fetch/geonames-dump.js.map +0 -1
  1597. package/out/tools/fetch/geonames-postal.d.ts +0 -76
  1598. package/out/tools/fetch/geonames-postal.d.ts.map +0 -1
  1599. package/out/tools/fetch/geonames-postal.js +0 -126
  1600. package/out/tools/fetch/geonames-postal.js.map +0 -1
  1601. package/out/tools/fetch/houjin-jp.d.ts +0 -24
  1602. package/out/tools/fetch/houjin-jp.d.ts.map +0 -1
  1603. package/out/tools/fetch/houjin-jp.js +0 -102
  1604. package/out/tools/fetch/houjin-jp.js.map +0 -1
  1605. package/out/tools/fetch/hrsa.d.ts +0 -18
  1606. package/out/tools/fetch/hrsa.d.ts.map +0 -1
  1607. package/out/tools/fetch/hrsa.js +0 -46
  1608. package/out/tools/fetch/hrsa.js.map +0 -1
  1609. package/out/tools/fetch/imls-pls.d.ts +0 -25
  1610. package/out/tools/fetch/imls-pls.d.ts.map +0 -1
  1611. package/out/tools/fetch/imls-pls.js +0 -108
  1612. package/out/tools/fetch/imls-pls.js.map +0 -1
  1613. package/out/tools/fetch/index.d.ts +0 -171
  1614. package/out/tools/fetch/index.d.ts.map +0 -1
  1615. package/out/tools/fetch/index.js +0 -170
  1616. package/out/tools/fetch/index.js.map +0 -1
  1617. package/out/tools/fetch/juso-kr.d.ts +0 -30
  1618. package/out/tools/fetch/juso-kr.d.ts.map +0 -1
  1619. package/out/tools/fetch/juso-kr.js +0 -120
  1620. package/out/tools/fetch/juso-kr.js.map +0 -1
  1621. package/out/tools/fetch/localdata-kr.d.ts +0 -30
  1622. package/out/tools/fetch/localdata-kr.d.ts.map +0 -1
  1623. package/out/tools/fetch/localdata-kr.js +0 -139
  1624. package/out/tools/fetch/localdata-kr.js.map +0 -1
  1625. package/out/tools/fetch/nad.d.ts +0 -70
  1626. package/out/tools/fetch/nad.d.ts.map +0 -1
  1627. package/out/tools/fetch/nad.js +0 -234
  1628. package/out/tools/fetch/nad.js.map +0 -1
  1629. package/out/tools/fetch/nppes.d.ts +0 -26
  1630. package/out/tools/fetch/nppes.d.ts.map +0 -1
  1631. package/out/tools/fetch/nppes.js +0 -126
  1632. package/out/tools/fetch/nppes.js.map +0 -1
  1633. package/out/tools/fetch/state-hi-schools.d.ts +0 -26
  1634. package/out/tools/fetch/state-hi-schools.d.ts.map +0 -1
  1635. package/out/tools/fetch/state-hi-schools.js +0 -112
  1636. package/out/tools/fetch/state-hi-schools.js.map +0 -1
  1637. package/out/tools/fetch/state-sources.d.ts +0 -26
  1638. package/out/tools/fetch/state-sources.d.ts.map +0 -1
  1639. package/out/tools/fetch/state-sources.js +0 -111
  1640. package/out/tools/fetch/state-sources.js.map +0 -1
  1641. package/out/tools/fetch/tiger-full.d.ts +0 -22
  1642. package/out/tools/fetch/tiger-full.d.ts.map +0 -1
  1643. package/out/tools/fetch/tiger-full.js +0 -217
  1644. package/out/tools/fetch/tiger-full.js.map +0 -1
  1645. package/out/tools/gb-title-case.d.ts +0 -2
  1646. package/out/tools/gb-title-case.d.ts.map +0 -1
  1647. package/out/tools/gb-title-case.js +0 -65
  1648. package/out/tools/gb-title-case.js.map +0 -1
  1649. package/out/tools/golden-expand.d.ts +0 -90
  1650. package/out/tools/golden-expand.d.ts.map +0 -1
  1651. package/out/tools/golden-expand.js +0 -406
  1652. package/out/tools/golden-expand.js.map +0 -1
  1653. package/out/tools/golden-promote.d.ts +0 -72
  1654. package/out/tools/golden-promote.d.ts.map +0 -1
  1655. package/out/tools/golden-promote.js +0 -240
  1656. package/out/tools/golden-promote.js.map +0 -1
  1657. package/out/tools/golden-relabel-street.d.ts +0 -196
  1658. package/out/tools/golden-relabel-street.d.ts.map +0 -1
  1659. package/out/tools/golden-relabel-street.js +0 -439
  1660. package/out/tools/golden-relabel-street.js.map +0 -1
  1661. package/out/tools/index.d.ts +0 -28
  1662. package/out/tools/index.d.ts.map +0 -1
  1663. package/out/tools/index.js +0 -28
  1664. package/out/tools/index.js.map +0 -1
  1665. package/out/tools/lint-slice-vocab.d.ts +0 -90
  1666. package/out/tools/lint-slice-vocab.d.ts.map +0 -1
  1667. package/out/tools/lint-slice-vocab.js +0 -267
  1668. package/out/tools/lint-slice-vocab.js.map +0 -1
  1669. package/out/tools/lint-slice.d.ts +0 -93
  1670. package/out/tools/lint-slice.d.ts.map +0 -1
  1671. package/out/tools/lint-slice.js +0 -322
  1672. package/out/tools/lint-slice.js.map +0 -1
  1673. package/out/tools/overlay-manifest.d.ts +0 -39
  1674. package/out/tools/overlay-manifest.d.ts.map +0 -1
  1675. package/out/tools/overlay-manifest.js +0 -90
  1676. package/out/tools/overlay-manifest.js.map +0 -1
  1677. package/out/tools/slice-kryptonite.d.ts +0 -32
  1678. package/out/tools/slice-kryptonite.d.ts.map +0 -1
  1679. package/out/tools/slice-kryptonite.js +0 -99
  1680. package/out/tools/slice-kryptonite.js.map +0 -1
  1681. package/out/tools/slice-translit.d.ts +0 -51
  1682. package/out/tools/slice-translit.d.ts.map +0 -1
  1683. package/out/tools/slice-translit.js +0 -166
  1684. package/out/tools/slice-translit.js.map +0 -1
  1685. package/out/tools/sub-venue/harvest.d.ts +0 -100
  1686. package/out/tools/sub-venue/harvest.d.ts.map +0 -1
  1687. package/out/tools/sub-venue/harvest.js +0 -168
  1688. package/out/tools/sub-venue/harvest.js.map +0 -1
  1689. package/out/tools/sub-venue/head-nouns.d.ts +0 -50
  1690. package/out/tools/sub-venue/head-nouns.d.ts.map +0 -1
  1691. package/out/tools/sub-venue/head-nouns.js +0 -213
  1692. package/out/tools/sub-venue/head-nouns.js.map +0 -1
  1693. package/out/tools/sub-venue/surfaces.d.ts +0 -45
  1694. package/out/tools/sub-venue/surfaces.d.ts.map +0 -1
  1695. package/out/tools/sub-venue/surfaces.js +0 -77
  1696. package/out/tools/sub-venue/surfaces.js.map +0 -1
  1697. package/out/tools/sub-venue/table.d.ts +0 -229
  1698. package/out/tools/sub-venue/table.d.ts.map +0 -1
  1699. package/out/tools/sub-venue/table.js +0 -108
  1700. package/out/tools/sub-venue/table.js.map +0 -1
  1701. package/out/tools/sub-venue/wikidata.d.ts +0 -26
  1702. package/out/tools/sub-venue/wikidata.d.ts.map +0 -1
  1703. package/out/tools/sub-venue/wikidata.js +0 -62
  1704. package/out/tools/sub-venue/wikidata.js.map +0 -1
  1705. package/out/tools/sub-venue-lexicon.d.ts +0 -156
  1706. package/out/tools/sub-venue-lexicon.d.ts.map +0 -1
  1707. package/out/tools/sub-venue-lexicon.js +0 -283
  1708. package/out/tools/sub-venue-lexicon.js.map +0 -1
  1709. package/out/tools/sub-venue-promotions.d.ts +0 -94
  1710. package/out/tools/sub-venue-promotions.d.ts.map +0 -1
  1711. package/out/tools/sub-venue-promotions.js +0 -266
  1712. package/out/tools/sub-venue-promotions.js.map +0 -1
  1713. package/out/utils/index.d.ts +0 -14
  1714. package/out/utils/index.d.ts.map +0 -1
  1715. package/out/utils/index.js +0 -14
  1716. package/out/utils/index.js.map +0 -1
  1717. package/out/utils/parquet.d.ts +0 -178
  1718. package/out/utils/parquet.d.ts.map +0 -1
  1719. package/out/utils/parquet.js +0 -371
  1720. package/out/utils/parquet.js.map +0 -1
  1721. package/out/utils/slice-stats.d.ts +0 -52
  1722. package/out/utils/slice-stats.d.ts.map +0 -1
  1723. package/out/utils/slice-stats.js +0 -58
  1724. package/out/utils/slice-stats.js.map +0 -1
@@ -1,371 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * Final output sliceer for the corpus pipeline.
7
- *
8
- * Phase 1 (#9) shipped JSONL slices + a Python (PyArrow) converter as the path to binary Parquet —
9
- * bridging until the JS toolchain caught up. Phase 1.5 (#18 §4) replaced that with a native JS
10
- * writer. The build pipeline no longer touches Python at all in its hot path; the only remaining
11
- * Python is the one-shot `train_tokenizer.py` SentencePiece step.
12
- *
13
- * Compression: `SNAPPY`. The plan in #18 §4 specified `zstd`; parquet-wasm supports SNAPPY,
14
- * which is the standard ML-corpus default (and PyArrow's default). Documented in
15
- * `DECISIONS.md`.
16
- *
17
- * Layout under `<outputDir>`:
18
- *
19
- * ```
20
- * corpus-v<version>/
21
- * MANIFEST.json
22
- * train/
23
- * part-0000.parquet
24
- * part-0001.parquet
25
- * ...
26
- * val/
27
- * part-0000.parquet
28
- * test/
29
- * part-0000.parquet
30
- * ```
31
- *
32
- * Each slice caps at `rowsPerSlice` (default 1_000_000); within a slice, DuckDB writes row
33
- * groups every `ROW_GROUP_SIZE` (50_000) rows per the issue spec. The MANIFEST captures every
34
- * slice's path, row count, byte size, and SHA-256 (computed by re-reading the slice once after
35
- * close — cheap relative to writing it).
36
- */
37
- import { tryStat } from "@mailwoman/core/fs/readers";
38
- import { openWriteStream } from "@mailwoman/core/fs/streams";
39
- import { temporaryDirectory } from "@mailwoman/core/fs/temporary";
40
- import { writeLocalBuffer, writeLocalJSONFile, makeDirectories } from "@mailwoman/core/fs/writers";
41
- import { sha256File } from "@mailwoman/core/hash";
42
- import { once } from "@mailwoman/core/utils/events";
43
- import { Field, Int32, List, Table as ArrowTable, tableToIPC, Utf8, vectorFromArray } from "apache-arrow";
44
- import { Compression, Table as WasmTable, WriterPropertiesBuilder, writeParquet } from "parquet-wasm";
45
- import { join } from "path-ts";
46
- /**
47
- * Row groups are written at this cadence within a slice.
48
- */
49
- export const ROW_GROUP_SIZE = 50_000;
50
- /**
51
- * Escape `value` for a single-quoted SQL string literal; the caller supplies the quotes.
52
- */
53
- export function escapeSQLString(value) {
54
- return value.replaceAll("'", "''");
55
- }
56
- /**
57
- * Open an in-memory DuckDB connection. `@duckdb/node-api` is an optional peer — lazy import (the pipeline convention),
58
- * so the heavy native module loads only on the paths that read or write Parquet through DuckDB.
59
- */
60
- export async function connectDuckDB() {
61
- const { DuckDBInstance } = await import("@duckdb/node-api");
62
- const instance = await DuckDBInstance.create();
63
- return await instance.connect();
64
- }
65
- /**
66
- * Snappy is the codec selected for corpus slices.
67
- */
68
- export const SLICE_COMPRESSION = "SNAPPY";
69
- /**
70
- * Column names emitted into every slice. Matches `ParquetRow`.
71
- */
72
- export const PARQUET_COLUMNS = [
73
- "raw",
74
- "tokens",
75
- "labels",
76
- "span_starts",
77
- "span_ends",
78
- "span_tags",
79
- "country",
80
- "locale",
81
- "source",
82
- "source_id",
83
- "corpus_version",
84
- "license",
85
- "synth_method",
86
- "synth_base_id",
87
- ];
88
- /* oxlint-disable unicorn/text-encoding-identifier-case -- `"UTF8"` below is a ParquetType enum member,
89
- not a text-encoding identifier. Lowercasing it does not type-check against ParquetSchemaDefinition,
90
- and the rule has no way to tell the two apart. */
91
- /**
92
- * Parquet schema for `LabeledRow` per #18 §4. Optional fields use `optional: true`; repeated UTF8 columns capture
93
- * tokens/labels arrays. Compression is per-column SNAPPY.
94
- */
95
- export const LABELED_ROW_SCHEMA = {
96
- raw: { type: "UTF8", compression: SLICE_COMPRESSION },
97
- tokens: { type: "UTF8", repeated: true, compression: SLICE_COMPRESSION },
98
- labels: { type: "UTF8", repeated: true, compression: SLICE_COMPRESSION },
99
- // v0.5.0 char-offset label spans (#519): parallel arrays over `raw` (UTF-16 code units,
100
- // [start, end) exclusive-end, sorted, non-overlapping). INT32 — raw is a short address string,
101
- // and INT32 round-trips as `number` where parquetjs INT64 would surface bigint.
102
- span_starts: { type: "INT32", repeated: true, compression: SLICE_COMPRESSION },
103
- span_ends: { type: "INT32", repeated: true, compression: SLICE_COMPRESSION },
104
- span_tags: { type: "UTF8", repeated: true, compression: SLICE_COMPRESSION },
105
- country: { type: "UTF8", compression: SLICE_COMPRESSION },
106
- locale: { type: "UTF8", compression: SLICE_COMPRESSION, optional: true },
107
- source: { type: "UTF8", compression: SLICE_COMPRESSION },
108
- source_id: { type: "UTF8", compression: SLICE_COMPRESSION },
109
- corpus_version: { type: "UTF8", compression: SLICE_COMPRESSION },
110
- license: { type: "UTF8", compression: SLICE_COMPRESSION },
111
- synth_method: { type: "UTF8", compression: SLICE_COMPRESSION, optional: true },
112
- synth_base_id: { type: "UTF8", compression: SLICE_COMPRESSION, optional: true },
113
- };
114
- const stringListType = new List(new Field("item", new Utf8(), true));
115
- const int32ListType = new List(new Field("item", new Int32(), true));
116
- const PARQUET_COLUMN_TYPES = {
117
- raw: "VARCHAR",
118
- tokens: "VARCHAR[]",
119
- labels: "VARCHAR[]",
120
- span_starts: "INTEGER[]",
121
- span_ends: "INTEGER[]",
122
- span_tags: "VARCHAR[]",
123
- country: "VARCHAR",
124
- locale: "VARCHAR",
125
- source: "VARCHAR",
126
- source_id: "VARCHAR",
127
- corpus_version: "VARCHAR",
128
- license: "VARCHAR",
129
- synth_method: "VARCHAR",
130
- synth_base_id: "VARCHAR",
131
- };
132
- function parquetTable(rows) {
133
- return new ArrowTable({
134
- raw: vectorFromArray(rows.map((row) => row.raw), new Utf8()),
135
- tokens: vectorFromArray(rows.map((row) => row.tokens), stringListType),
136
- labels: vectorFromArray(rows.map((row) => row.labels), stringListType),
137
- span_starts: vectorFromArray(rows.map((row) => row.span_starts), int32ListType),
138
- span_ends: vectorFromArray(rows.map((row) => row.span_ends), int32ListType),
139
- span_tags: vectorFromArray(rows.map((row) => row.span_tags), stringListType),
140
- country: vectorFromArray(rows.map((row) => row.country), new Utf8()),
141
- locale: vectorFromArray(rows.map((row) => row.locale ?? null), new Utf8()),
142
- source: vectorFromArray(rows.map((row) => row.source), new Utf8()),
143
- source_id: vectorFromArray(rows.map((row) => row.source_id), new Utf8()),
144
- corpus_version: vectorFromArray(rows.map((row) => row.corpus_version), new Utf8()),
145
- license: vectorFromArray(rows.map((row) => row.license), new Utf8()),
146
- synth_method: vectorFromArray(rows.map((row) => row.synth_method ?? null), new Utf8()),
147
- synth_base_id: vectorFromArray(rows.map((row) => row.synth_base_id ?? null), new Utf8()),
148
- });
149
- }
150
- export async function writeParquetRows(rows, path) {
151
- const arrow = parquetTable(rows);
152
- const wasmTable = WasmTable.fromIPCStream(tableToIPC(arrow, "stream"));
153
- const properties = new WriterPropertiesBuilder()
154
- .setCompression(Compression.SNAPPY)
155
- .setCreatedBy("mailwoman")
156
- .setMaxRowGroupSize(ROW_GROUP_SIZE)
157
- .build();
158
- // parquet-wasm serializes key-value metadata through a hash map, whose order is not stable between writes.
159
- // Slice identity and provenance live in MANIFEST.json, so omitting file metadata preserves deterministic bytes.
160
- await writeLocalBuffer(writeParquet(wasmTable, properties), path);
161
- }
162
- function normalizeDuckDBValue(value) {
163
- if (value && typeof value === "object" && "items" in value && Array.isArray(value.items)) {
164
- return value.items.map(normalizeDuckDBValue);
165
- }
166
- if (Array.isArray(value))
167
- return value.map(normalizeDuckDBValue);
168
- return value;
169
- }
170
- /**
171
- * Stream rows from a local Parquet file in DuckDB-managed chunks.
172
- *
173
- * DuckDB opens the path itself and exposes its DataChunks through `fetchChunk()`. Rows are converted and yielded one
174
- * chunk at a time; the complete Parquet file and complete result set are never copied into JavaScript memory.
175
- */
176
- export async function* streamParquetRows(path, columns, options) {
177
- const db = await connectDuckDB();
178
- const projection = columns?.length ? columns.map(escapeSQLIdentifier).join(", ") : "*";
179
- const limit = options?.limit;
180
- const limitClause = limit === undefined ? "" : ` LIMIT ${validateLimit(limit)}`;
181
- const sql = `SELECT ${projection} FROM read_parquet('${escapeSQLString(path)}')${limitClause}`;
182
- try {
183
- const stream = await db.stream(sql);
184
- const columnNames = stream.columnNames();
185
- for (let chunk = await stream.fetchChunk(); chunk && chunk.rowCount > 0; chunk = await stream.fetchChunk()) {
186
- const rows = chunk.getRowObjects(columnNames);
187
- for (const row of rows) {
188
- yield Object.fromEntries(Object.entries(row).map(([key, value]) => [key, normalizeDuckDBValue(value)]));
189
- }
190
- }
191
- }
192
- catch (error) {
193
- if (columns && /Binder Error|Referenced column|does not exist/.test(String(error))) {
194
- const missing = String(error).match(/(?:Referenced column|field named) ["']([^"']+)["']/)?.[1] ?? columns.join(", ");
195
- throw new Error(`Parquet projection requested column absent from the file schema: ${missing}`, {
196
- cause: error,
197
- });
198
- }
199
- throw error;
200
- }
201
- finally {
202
- db.closeSync();
203
- }
204
- }
205
- function escapeSQLIdentifier(value) {
206
- return `"${value.replaceAll('"', '""')}"`;
207
- }
208
- function validateLimit(value) {
209
- if (!Number.isSafeInteger(value) || value < 0)
210
- throw new Error(`Parquet row limit must be a non-negative integer: ${value}`);
211
- return value;
212
- }
213
- async function writeStagedParquet(stagePath, outputPath) {
214
- const db = await connectDuckDB();
215
- const columns = [...PARQUET_COLUMNS];
216
- const columnsLiteral = "{" + columns.map((column) => `'${column}': '${PARQUET_COLUMN_TYPES[column]}'`).join(", ") + "}";
217
- const selectList = columns.map(escapeSQLIdentifier).join(", ");
218
- try {
219
- await db.run("SET preserve_insertion_order=true");
220
- await db.run(`COPY (SELECT ${selectList} FROM read_json('${escapeSQLString(stagePath)}', ` +
221
- `columns = ${columnsLiteral}, format = 'newline_delimited')) ` +
222
- `TO '${escapeSQLString(outputPath)}' (FORMAT PARQUET, COMPRESSION SNAPPY, ROW_GROUP_SIZE ${ROW_GROUP_SIZE})`);
223
- }
224
- finally {
225
- db.closeSync();
226
- }
227
- }
228
- async function writeStagedRow(stage, row) {
229
- if (!stage.write(JSON.stringify(row) + "\n")) {
230
- await once(stage, "drain");
231
- }
232
- }
233
- /**
234
- * Project a labeled row to the Parquet schema.
235
- *
236
- * The span triple is REQUIRED here (#519): `alignRow` emits it on every labeled row, so a row arriving without it came
237
- * from a producer that hasn't migrated — writing it would silently drop the v0.5.0 labels from the slice (the "builders
238
- * before parquet = silent loss" hazard). Loud failure, naming the row, instead.
239
- */
240
- export function rowToParquet(row) {
241
- const { span_starts, span_ends, span_tags } = row;
242
- if (span_starts === undefined || span_ends === undefined || span_tags === undefined) {
243
- throw new Error(`rowToParquet: row is missing the char-offset span triple (#519) — ` +
244
- `span_starts=${span_starts !== undefined} span_ends=${span_ends !== undefined} span_tags=${span_tags !== undefined} ` +
245
- `(source=${row.source}, source_id=${row.source_id}). ` +
246
- `Every parquet-bound row must carry span_starts/span_ends/span_tags; ` +
247
- `producers that emit tokens/labels only have not migrated to the v0.5.0 format.`);
248
- }
249
- if (span_starts.length !== span_ends.length || span_starts.length !== span_tags.length) {
250
- throw new Error(`rowToParquet: span triple arrays are not parallel — ` +
251
- `starts=${span_starts.length} ends=${span_ends.length} tags=${span_tags.length} ` +
252
- `(source=${row.source}, source_id=${row.source_id})`);
253
- }
254
- return {
255
- raw: row.raw,
256
- tokens: row.tokens,
257
- labels: row.labels,
258
- span_starts,
259
- span_ends,
260
- span_tags,
261
- country: row.country,
262
- locale: row.locale ?? null,
263
- source: row.source,
264
- source_id: row.source_id,
265
- corpus_version: row.corpus_version,
266
- license: row.license,
267
- synth_method: row.synth?.method ?? null,
268
- synth_base_id: row.synth?.base_source_id ?? null,
269
- };
270
- }
271
- /**
272
- * Stream labeled rows into `.parquet` slices, one set of slices per split. Splits are processed sequentially so that
273
- * only one slice is open at a time. Rows are staged to newline-delimited JSON with backpressure, then DuckDB writes the
274
- * Parquet file from disk.
275
- *
276
- * Callers pass per-split `AsyncIterable<LabeledRow>` (`PerSplitRows`); the prior `splitFor(sourceID)` callback is gone
277
- * because pre-partitioning at the caller eliminates the O(n) `Map<source_id, SplitName>` it required. See `buildCorpus`
278
- * for the new wire-up.
279
- */
280
- export async function writeSlices(perSplit, opts) {
281
- const rowsPerSlice = opts.rowsPerSlice ?? 1_000_000;
282
- const corpusDir = join(opts.outputDir, `corpus-v${opts.corpusVersion}`);
283
- await makeDirectories(corpusDir);
284
- const slices = [];
285
- const counts = { train: 0, val: 0, test: 0 };
286
- let totalRows = 0;
287
- for (const split of ["train", "val", "test"]) {
288
- const rows = perSplit[split];
289
- if (!rows)
290
- continue;
291
- await using staging = await temporaryDirectory(`mailwoman-parquet-${split}-`);
292
- let sliceIndex = 0;
293
- let path = "";
294
- let stagePath = "";
295
- let sliceRows = 0;
296
- let stage = null;
297
- let firstSourceID = "";
298
- let lastSourceID = "";
299
- const openSlice = async () => {
300
- const splitDir = join(corpusDir, split);
301
- await makeDirectories(splitDir);
302
- path = join(splitDir, `part-${String(sliceIndex).padStart(4, "0")}.parquet`);
303
- stagePath = staging.resolve(`part-${String(sliceIndex).padStart(4, "0")}.ndjson`);
304
- stage = staging.use(openWriteStream(stagePath));
305
- sliceRows = 0;
306
- firstSourceID = "";
307
- lastSourceID = "";
308
- };
309
- const closeSlice = async () => {
310
- const activeStage = stage;
311
- if (!activeStage)
312
- return;
313
- await new Promise((resolve, reject) => {
314
- activeStage.end((error) => (error ? reject(error) : resolve()));
315
- });
316
- if (sliceRows) {
317
- await writeStagedParquet(stagePath, path);
318
- const fileStat = await tryStat(path);
319
- const sha256 = await sha256File(path);
320
- slices.push({
321
- split,
322
- path,
323
- format: "parquet",
324
- compression: SLICE_COMPRESSION,
325
- rows: sliceRows,
326
- bytes: fileStat?.size ?? 0,
327
- sha256,
328
- first_source_id: firstSourceID,
329
- last_source_id: lastSourceID,
330
- });
331
- }
332
- stage = null;
333
- sliceRows = 0;
334
- };
335
- for await (const row of rows) {
336
- if (!path) {
337
- await openSlice();
338
- }
339
- const pq = rowToParquet(row);
340
- if (!stage)
341
- throw new Error("Parquet slice writer was not opened");
342
- await writeStagedRow(stage, pq);
343
- sliceRows++;
344
- if (sliceRows === 1) {
345
- firstSourceID = row.source_id;
346
- }
347
- lastSourceID = row.source_id;
348
- counts[split]++;
349
- totalRows++;
350
- if (sliceRows >= rowsPerSlice) {
351
- await closeSlice();
352
- sliceIndex++;
353
- path = "";
354
- }
355
- }
356
- await closeSlice();
357
- }
358
- slices.sort((a, b) => (a.split === b.split ? a.path.localeCompare(b.path) : a.split.localeCompare(b.split)));
359
- const manifest = {
360
- corpus_version: opts.corpusVersion,
361
- schema: PARQUET_COLUMNS,
362
- rows_per_slice: rowsPerSlice,
363
- row_group_size: ROW_GROUP_SIZE,
364
- slices,
365
- counts,
366
- total_rows: totalRows,
367
- };
368
- await writeLocalJSONFile(manifest, corpusDir, "MANIFEST.json");
369
- return manifest;
370
- }
371
- //# sourceMappingURL=parquet.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"parquet.js","sourceRoot":"","sources":["../../lib/utils/parquet.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAmCG;AAEH,OAAO,EAAE,OAAO,EAAE,MAAM,4BAA4B,CAAA;AACpD,OAAO,EAAE,eAAe,EAAoB,MAAM,4BAA4B,CAAA;AAC9E,OAAO,EAAE,kBAAkB,EAAE,MAAM,8BAA8B,CAAA;AACjE,OAAO,EAAE,gBAAgB,EAAE,kBAAkB,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAA;AAClG,OAAO,EAAE,UAAU,EAAE,MAAM,sBAAsB,CAAA;AACjD,OAAO,EAAE,IAAI,EAAE,MAAM,8BAA8B,CAAA;AACnD,OAAO,EAAE,KAAK,EAAE,KAAK,EAAE,IAAI,EAAE,KAAK,IAAI,UAAU,EAAE,UAAU,EAAE,IAAI,EAAE,eAAe,EAAE,MAAM,cAAc,CAAA;AACzG,OAAO,EAAE,WAAW,EAAE,KAAK,IAAI,SAAS,EAAE,uBAAuB,EAAE,YAAY,EAAE,MAAM,cAAc,CAAA;AACrG,OAAO,EAAE,IAAI,EAAwB,MAAM,SAAS,CAAA;AAKpD;;GAEG;AACH,MAAM,CAAC,MAAM,cAAc,GAAG,MAAM,CAAA;AAEpC;;GAEG;AACH,MAAM,UAAU,eAAe,CAAC,KAAa;IAC5C,OAAO,KAAK,CAAC,UAAU,CAAC,GAAG,EAAE,IAAI,CAAC,CAAA;AACnC,CAAC;AAQD;;;GAGG;AACH,MAAM,CAAC,KAAK,UAAU,aAAa;IAClC,MAAM,EAAE,cAAc,EAAE,GAAG,MAAM,MAAM,CAAC,kBAAkB,CAAC,CAAA;IAC3D,MAAM,QAAQ,GAAG,MAAM,cAAc,CAAC,MAAM,EAAE,CAAA;IAE9C,OAAO,MAAM,QAAQ,CAAC,OAAO,EAAE,CAAA;AAChC,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,iBAAiB,GAAG,QAAiB,CAAA;AAmClD;;GAEG;AACH,MAAM,CAAC,MAAM,eAAe,GAAG;IAC9B,KAAK;IACL,QAAQ;IACR,QAAQ;IACR,aAAa;IACb,WAAW;IACX,WAAW;IACX,SAAS;IACT,QAAQ;IACR,QAAQ;IACR,WAAW;IACX,gBAAgB;IAChB,SAAS;IACT,cAAc;IACd,eAAe;CACN,CAAA;AAEV;;oDAEoD;AAEpD;;;GAGG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAAwC;IACtE,GAAG,EAAE,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,iBAAiB,EAAE;IACrD,MAAM,EAAE,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,IAAI,EAAE,WAAW,EAAE,iBAAiB,EAAE;IACxE,MAAM,EAAE,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,IAAI,EAAE,WAAW,EAAE,iBAAiB,EAAE;IACxE,wFAAwF;IACxF,+FAA+F;IAC/F,gFAAgF;IAChF,WAAW,EAAE,EAAE,IAAI,EAAE,OAAO,EAAE,QAAQ,EAAE,IAAI,EAAE,WAAW,EAAE,iBAAiB,EAAE;IAC9E,SAAS,EAAE,EAAE,IAAI,EAAE,OAAO,EAAE,QAAQ,EAAE,IAAI,EAAE,WAAW,EAAE,iBAAiB,EAAE;IAC5E,SAAS,EAAE,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,IAAI,EAAE,WAAW,EAAE,iBAAiB,EAAE;IAC3E,OAAO,EAAE,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,iBAAiB,EAAE;IACzD,MAAM,EAAE,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,iBAAiB,EAAE,QAAQ,EAAE,IAAI,EAAE;IACxE,MAAM,EAAE,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,iBAAiB,EAAE;IACxD,SAAS,EAAE,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,iBAAiB,EAAE;IAC3D,cAAc,EAAE,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,iBAAiB,EAAE;IAChE,OAAO,EAAE,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,iBAAiB,EAAE;IACzD,YAAY,EAAE,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,iBAAiB,EAAE,QAAQ,EAAE,IAAI,EAAE;IAC9E,aAAa,EAAE,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,iBAAiB,EAAE,QAAQ,EAAE,IAAI,EAAE;CAC/E,CAAA;AAED,MAAM,cAAc,GAAG,IAAI,IAAI,CAAC,IAAI,KAAK,CAAC,MAAM,EAAE,IAAI,IAAI,EAAE,EAAE,IAAI,CAAC,CAAC,CAAA;AACpE,MAAM,aAAa,GAAG,IAAI,IAAI,CAAC,IAAI,KAAK,CAAC,MAAM,EAAE,IAAI,KAAK,EAAE,EAAE,IAAI,CAAC,CAAC,CAAA;AAEpE,MAAM,oBAAoB,GAAqD;IAC9E,GAAG,EAAE,SAAS;IACd,MAAM,EAAE,WAAW;IACnB,MAAM,EAAE,WAAW;IACnB,WAAW,EAAE,WAAW;IACxB,SAAS,EAAE,WAAW;IACtB,SAAS,EAAE,WAAW;IACtB,OAAO,EAAE,SAAS;IAClB,MAAM,EAAE,SAAS;IACjB,MAAM,EAAE,SAAS;IACjB,SAAS,EAAE,SAAS;IACpB,cAAc,EAAE,SAAS;IACzB,OAAO,EAAE,SAAS;IAClB,YAAY,EAAE,SAAS;IACvB,aAAa,EAAE,SAAS;CACxB,CAAA;AAED,SAAS,YAAY,CAAC,IAA2B;IAChD,OAAO,IAAI,UAAU,CAAC;QACrB,GAAG,EAAE,eAAe,CACnB,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,GAAG,CAAC,GAAG,CAAC,EAC1B,IAAI,IAAI,EAAE,CACV;QACD,MAAM,EAAE,eAAe,CACtB,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,GAAG,CAAC,MAAM,CAAC,EAC7B,cAAc,CACd;QACD,MAAM,EAAE,eAAe,CACtB,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,GAAG,CAAC,MAAM,CAAC,EAC7B,cAAc,CACd;QACD,WAAW,EAAE,eAAe,CAC3B,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,GAAG,CAAC,WAAW,CAAC,EAClC,aAAa,CACb;QACD,SAAS,EAAE,eAAe,CACzB,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,GAAG,CAAC,SAAS,CAAC,EAChC,aAAa,CACb;QACD,SAAS,EAAE,eAAe,CACzB,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,GAAG,CAAC,SAAS,CAAC,EAChC,cAAc,CACd;QACD,OAAO,EAAE,eAAe,CACvB,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,GAAG,CAAC,OAAO,CAAC,EAC9B,IAAI,IAAI,EAAE,CACV;QACD,MAAM,EAAE,eAAe,CACtB,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,GAAG,CAAC,MAAM,IAAI,IAAI,CAAC,EACrC,IAAI,IAAI,EAAE,CACV;QACD,MAAM,EAAE,eAAe,CACtB,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,GAAG,CAAC,MAAM,CAAC,EAC7B,IAAI,IAAI,EAAE,CACV;QACD,SAAS,EAAE,eAAe,CACzB,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,GAAG,CAAC,SAAS,CAAC,EAChC,IAAI,IAAI,EAAE,CACV;QACD,cAAc,EAAE,eAAe,CAC9B,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,GAAG,CAAC,cAAc,CAAC,EACrC,IAAI,IAAI,EAAE,CACV;QACD,OAAO,EAAE,eAAe,CACvB,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,GAAG,CAAC,OAAO,CAAC,EAC9B,IAAI,IAAI,EAAE,CACV;QACD,YAAY,EAAE,eAAe,CAC5B,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,GAAG,CAAC,YAAY,IAAI,IAAI,CAAC,EAC3C,IAAI,IAAI,EAAE,CACV;QACD,aAAa,EAAE,eAAe,CAC7B,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,GAAG,CAAC,aAAa,IAAI,IAAI,CAAC,EAC5C,IAAI,IAAI,EAAE,CACV;KACD,CAAC,CAAA;AACH,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,gBAAgB,CAAC,IAA2B,EAAE,IAAY;IAC/E,MAAM,KAAK,GAAG,YAAY,CAAC,IAAI,CAAC,CAAA;IAChC,MAAM,SAAS,GAAG,SAAS,CAAC,aAAa,CAAC,UAAU,CAAC,KAAK,EAAE,QAAQ,CAAC,CAAC,CAAA;IAEtE,MAAM,UAAU,GAAG,IAAI,uBAAuB,EAAE;SAC9C,cAAc,CAAC,WAAW,CAAC,MAAM,CAAC;SAClC,YAAY,CAAC,WAAW,CAAC;SACzB,kBAAkB,CAAC,cAAc,CAAC;SAClC,KAAK,EAAE,CAAA;IAET,2GAA2G;IAC3G,gHAAgH;IAChH,MAAM,gBAAgB,CAAC,YAAY,CAAC,SAAS,EAAE,UAAU,CAAC,EAAE,IAAI,CAAC,CAAA;AAClE,CAAC;AAED,SAAS,oBAAoB,CAAC,KAAc;IAC3C,IAAI,KAAK,IAAI,OAAO,KAAK,KAAK,QAAQ,IAAI,OAAO,IAAI,KAAK,IAAI,KAAK,CAAC,OAAO,CAAC,KAAK,CAAC,KAAK,CAAC,EAAE,CAAC;QAC1F,OAAO,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,oBAAoB,CAAC,CAAA;IAC7C,CAAC;IAED,IAAI,KAAK,CAAC,OAAO,CAAC,KAAK,CAAC;QAAE,OAAO,KAAK,CAAC,GAAG,CAAC,oBAAoB,CAAC,CAAA;IAEhE,OAAO,KAAK,CAAA;AACb,CAAC;AAED;;;;;GAKG;AACH,MAAM,CAAC,KAAK,SAAS,CAAC,CAAC,iBAAiB,CACvC,IAAY,EACZ,OAA2B,EAC3B,OAA4B;IAE5B,MAAM,EAAE,GAAG,MAAM,aAAa,EAAE,CAAA;IAChC,MAAM,UAAU,GAAG,OAAO,EAAE,MAAM,CAAC,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,mBAAmB,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,GAAG,CAAA;IACtF,MAAM,KAAK,GAAG,OAAO,EAAE,KAAK,CAAA;IAC5B,MAAM,WAAW,GAAG,KAAK,KAAK,SAAS,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,UAAU,aAAa,CAAC,KAAK,CAAC,EAAE,CAAA;IAC/E,MAAM,GAAG,GAAG,UAAU,UAAU,uBAAuB,eAAe,CAAC,IAAI,CAAC,KAAK,WAAW,EAAE,CAAA;IAE9F,IAAI,CAAC;QACJ,MAAM,MAAM,GAAG,MAAM,EAAE,CAAC,MAAM,CAAC,GAAG,CAAC,CAAA;QACnC,MAAM,WAAW,GAAG,MAAM,CAAC,WAAW,EAAE,CAAA;QAExC,KAAK,IAAI,KAAK,GAAG,MAAM,MAAM,CAAC,UAAU,EAAE,EAAE,KAAK,IAAI,KAAK,CAAC,QAAQ,GAAG,CAAC,EAAE,KAAK,GAAG,MAAM,MAAM,CAAC,UAAU,EAAE,EAAE,CAAC;YAC5G,MAAM,IAAI,GAAG,KAAK,CAAC,aAAa,CAAC,WAAW,CAA8B,CAAA;YAE1E,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;gBACxB,MAAM,MAAM,CAAC,WAAW,CAAC,MAAM,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,GAAG,EAAE,KAAK,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,EAAE,oBAAoB,CAAC,KAAK,CAAC,CAAC,CAAC,CAAM,CAAA;YAC7G,CAAC;QACF,CAAC;IACF,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QAChB,IAAI,OAAO,IAAI,+CAA+C,CAAC,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC;YACpF,MAAM,OAAO,GACZ,MAAM,CAAC,KAAK,CAAC,CAAC,KAAK,CAAC,oDAAoD,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;YAErG,MAAM,IAAI,KAAK,CAAC,oEAAoE,OAAO,EAAE,EAAE;gBAC9F,KAAK,EAAE,KAAK;aACZ,CAAC,CAAA;QACH,CAAC;QAED,MAAM,KAAK,CAAA;IACZ,CAAC;YAAS,CAAC;QACV,EAAE,CAAC,SAAS,EAAE,CAAA;IACf,CAAC;AACF,CAAC;AAED,SAAS,mBAAmB,CAAC,KAAa;IACzC,OAAO,IAAI,KAAK,CAAC,UAAU,CAAC,GAAG,EAAE,IAAI,CAAC,GAAG,CAAA;AAC1C,CAAC;AAED,SAAS,aAAa,CAAC,KAAa;IACnC,IAAI,CAAC,MAAM,CAAC,aAAa,CAAC,KAAK,CAAC,IAAI,KAAK,GAAG,CAAC;QAC5C,MAAM,IAAI,KAAK,CAAC,qDAAqD,KAAK,EAAE,CAAC,CAAA;IAE9E,OAAO,KAAK,CAAA;AACb,CAAC;AAED,KAAK,UAAU,kBAAkB,CAAC,SAAiB,EAAE,UAAkB;IACtE,MAAM,EAAE,GAAG,MAAM,aAAa,EAAE,CAAA;IAChC,MAAM,OAAO,GAAG,CAAC,GAAG,eAAe,CAAC,CAAA;IAEpC,MAAM,cAAc,GACnB,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,IAAI,MAAM,OAAO,oBAAoB,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,GAAG,CAAA;IAEjG,MAAM,UAAU,GAAG,OAAO,CAAC,GAAG,CAAC,mBAAmB,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;IAE9D,IAAI,CAAC;QACJ,MAAM,EAAE,CAAC,GAAG,CAAC,mCAAmC,CAAC,CAAA;QAEjD,MAAM,EAAE,CAAC,GAAG,CACX,gBAAgB,UAAU,oBAAoB,eAAe,CAAC,SAAS,CAAC,KAAK;YAC5E,aAAa,cAAc,mCAAmC;YAC9D,OAAO,eAAe,CAAC,UAAU,CAAC,yDAAyD,cAAc,GAAG,CAC7G,CAAA;IACF,CAAC;YAAS,CAAC;QACV,EAAE,CAAC,SAAS,EAAE,CAAA;IACf,CAAC;AACF,CAAC;AAED,KAAK,UAAU,cAAc,CAAC,KAAkB,EAAE,GAAe;IAChE,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,GAAG,CAAC,GAAG,IAAI,CAAC,EAAE,CAAC;QAC9C,MAAM,IAAI,CAAC,KAAK,EAAE,OAAO,CAAC,CAAA;IAC3B,CAAC;AACF,CAAC;AA0DD;;;;;;GAMG;AACH,MAAM,UAAU,YAAY,CAAC,GAAe;IAC3C,MAAM,EAAE,WAAW,EAAE,SAAS,EAAE,SAAS,EAAE,GAAG,GAAG,CAAA;IAEjD,IAAI,WAAW,KAAK,SAAS,IAAI,SAAS,KAAK,SAAS,IAAI,SAAS,KAAK,SAAS,EAAE,CAAC;QACrF,MAAM,IAAI,KAAK,CACd,oEAAoE;YACnE,eAAe,WAAW,KAAK,SAAS,cAAc,SAAS,KAAK,SAAS,cAAc,SAAS,KAAK,SAAS,GAAG;YACrH,WAAW,GAAG,CAAC,MAAM,eAAe,GAAG,CAAC,SAAS,KAAK;YACtD,sEAAsE;YACtE,gFAAgF,CACjF,CAAA;IACF,CAAC;IAED,IAAI,WAAW,CAAC,MAAM,KAAK,SAAS,CAAC,MAAM,IAAI,WAAW,CAAC,MAAM,KAAK,SAAS,CAAC,MAAM,EAAE,CAAC;QACxF,MAAM,IAAI,KAAK,CACd,sDAAsD;YACrD,UAAU,WAAW,CAAC,MAAM,SAAS,SAAS,CAAC,MAAM,SAAS,SAAS,CAAC,MAAM,GAAG;YACjF,WAAW,GAAG,CAAC,MAAM,eAAe,GAAG,CAAC,SAAS,GAAG,CACrD,CAAA;IACF,CAAC;IAED,OAAO;QACN,GAAG,EAAE,GAAG,CAAC,GAAG;QACZ,MAAM,EAAE,GAAG,CAAC,MAAM;QAClB,MAAM,EAAE,GAAG,CAAC,MAAM;QAClB,WAAW;QACX,SAAS;QACT,SAAS;QACT,OAAO,EAAE,GAAG,CAAC,OAAO;QACpB,MAAM,EAAE,GAAG,CAAC,MAAM,IAAI,IAAI;QAC1B,MAAM,EAAE,GAAG,CAAC,MAAM;QAClB,SAAS,EAAE,GAAG,CAAC,SAAS;QACxB,cAAc,EAAE,GAAG,CAAC,cAAc;QAClC,OAAO,EAAE,GAAG,CAAC,OAAO;QACpB,YAAY,EAAE,GAAG,CAAC,KAAK,EAAE,MAAM,IAAI,IAAI;QACvC,aAAa,EAAE,GAAG,CAAC,KAAK,EAAE,cAAc,IAAI,IAAI;KAChD,CAAA;AACF,CAAC;AAED;;;;;;;;GAQG;AACH,MAAM,CAAC,KAAK,UAAU,WAAW,CAAC,QAAsB,EAAE,IAAwB;IACjF,MAAM,YAAY,GAAG,IAAI,CAAC,YAAY,IAAI,SAAS,CAAA;IACnD,MAAM,SAAS,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,WAAW,IAAI,CAAC,aAAa,EAAE,CAAC,CAAA;IACvE,MAAM,eAAe,CAAC,SAAS,CAAC,CAAA;IAEhC,MAAM,MAAM,GAAsB,EAAE,CAAA;IACpC,MAAM,MAAM,GAA8B,EAAE,KAAK,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,IAAI,EAAE,CAAC,EAAE,CAAA;IACvE,IAAI,SAAS,GAAG,CAAC,CAAA;IAEjB,KAAK,MAAM,KAAK,IAAI,CAAC,OAAO,EAAE,KAAK,EAAE,MAAM,CAAU,EAAE,CAAC;QACvD,MAAM,IAAI,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAA;QAE5B,IAAI,CAAC,IAAI;YAAE,SAAQ;QAEnB,YAAY,OAAO,GAAG,MAAM,kBAAkB,CAAC,qBAAqB,KAAK,GAAG,CAAC,CAAA;QAE7E,IAAI,UAAU,GAAG,CAAC,CAAA;QAClB,IAAI,IAAI,GAAG,EAAE,CAAA;QACb,IAAI,SAAS,GAAG,EAAE,CAAA;QAClB,IAAI,SAAS,GAAG,CAAC,CAAA;QACjB,IAAI,KAAK,GAAuB,IAAI,CAAA;QACpC,IAAI,aAAa,GAAG,EAAE,CAAA;QACtB,IAAI,YAAY,GAAG,EAAE,CAAA;QAErB,MAAM,SAAS,GAAG,KAAK,IAAmB,EAAE;YAC3C,MAAM,QAAQ,GAAG,IAAI,CAAC,SAAS,EAAE,KAAK,CAAC,CAAA;YACvC,MAAM,eAAe,CAAC,QAAQ,CAAC,CAAA;YAC/B,IAAI,GAAG,IAAI,CAAC,QAAQ,EAAE,QAAQ,MAAM,CAAC,UAAU,CAAC,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,UAAU,CAAC,CAAA;YAE5E,SAAS,GAAG,OAAO,CAAC,OAAO,CAAC,QAAQ,MAAM,CAAC,UAAU,CAAC,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,SAAS,CAAC,CAAA;YACjF,KAAK,GAAG,OAAO,CAAC,GAAG,CAAC,eAAe,CAAC,SAAS,CAAC,CAAC,CAAA;YAC/C,SAAS,GAAG,CAAC,CAAA;YACb,aAAa,GAAG,EAAE,CAAA;YAClB,YAAY,GAAG,EAAE,CAAA;QAClB,CAAC,CAAA;QAED,MAAM,UAAU,GAAG,KAAK,IAAmB,EAAE;YAC5C,MAAM,WAAW,GAAG,KAAK,CAAA;YAEzB,IAAI,CAAC,WAAW;gBAAE,OAAM;YAExB,MAAM,IAAI,OAAO,CAAO,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE;gBAC3C,WAAW,CAAC,GAAG,CAAC,CAAC,KAAoB,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,OAAO,EAAE,CAAC,CAAC,CAAA;YAC/E,CAAC,CAAC,CAAA;YAEF,IAAI,SAAS,EAAE,CAAC;gBACf,MAAM,kBAAkB,CAAC,SAAS,EAAE,IAAI,CAAC,CAAA;gBAEzC,MAAM,QAAQ,GAAG,MAAM,OAAO,CAAC,IAAI,CAAC,CAAA;gBACpC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,IAAI,CAAC,CAAA;gBAErC,MAAM,CAAC,IAAI,CAAC;oBACX,KAAK;oBACL,IAAI;oBACJ,MAAM,EAAE,SAAS;oBACjB,WAAW,EAAE,iBAAiB;oBAC9B,IAAI,EAAE,SAAS;oBACf,KAAK,EAAE,QAAQ,EAAE,IAAI,IAAI,CAAC;oBAC1B,MAAM;oBACN,eAAe,EAAE,aAAa;oBAC9B,cAAc,EAAE,YAAY;iBAC5B,CAAC,CAAA;YACH,CAAC;YAED,KAAK,GAAG,IAAI,CAAA;YACZ,SAAS,GAAG,CAAC,CAAA;QACd,CAAC,CAAA;QAED,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;YAC9B,IAAI,CAAC,IAAI,EAAE,CAAC;gBACX,MAAM,SAAS,EAAE,CAAA;YAClB,CAAC;YAED,MAAM,EAAE,GAAG,YAAY,CAAC,GAAG,CAAC,CAAA;YAE5B,IAAI,CAAC,KAAK;gBAAE,MAAM,IAAI,KAAK,CAAC,qCAAqC,CAAC,CAAA;YAClE,MAAM,cAAc,CAAC,KAAK,EAAE,EAAE,CAAC,CAAA;YAE/B,SAAS,EAAE,CAAA;YAEX,IAAI,SAAS,KAAK,CAAC,EAAE,CAAC;gBACrB,aAAa,GAAG,GAAG,CAAC,SAAS,CAAA;YAC9B,CAAC;YAED,YAAY,GAAG,GAAG,CAAC,SAAS,CAAA;YAE5B,MAAM,CAAC,KAAK,CAAC,EAAE,CAAA;YAEf,SAAS,EAAE,CAAA;YAEX,IAAI,SAAS,IAAI,YAAY,EAAE,CAAC;gBAC/B,MAAM,UAAU,EAAE,CAAA;gBAElB,UAAU,EAAE,CAAA;gBACZ,IAAI,GAAG,EAAE,CAAA;YACV,CAAC;QACF,CAAC;QAED,MAAM,UAAU,EAAE,CAAA;IACnB,CAAC;IAED,MAAM,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,KAAK,KAAK,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,aAAa,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,aAAa,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAA;IAE5G,MAAM,QAAQ,GAAkB;QAC/B,cAAc,EAAE,IAAI,CAAC,aAAa;QAClC,MAAM,EAAE,eAAe;QACvB,cAAc,EAAE,YAAY;QAC5B,cAAc,EAAE,cAAc;QAC9B,MAAM;QACN,MAAM;QACN,UAAU,EAAE,SAAS;KACrB,CAAA;IAED,MAAM,kBAAkB,CAAC,QAAQ,EAAE,SAAS,EAAE,eAAe,CAAC,CAAA;IAE9D,OAAO,QAAQ,CAAA;AAChB,CAAC"}
@@ -1,52 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * Token/label co-occurrence accounting shared by the corpus-stats builder (`tools/corpus-stats.ts`)
7
- * and the slice linter (`tools/lint-slice.ts`). The two sides MUST agree on the bigram key format:
8
- * the linter looks its slice's bigrams up in the stats file's `bigrams` table, and a key built with
9
- * a different separator never matches — which silently blanks the bigram-collision check.
10
- */
11
- /**
12
- * Separator inside a bigram key (`tok1␟tok2`) and a label-bigram value (`lab1␟lab2`): U+001F UNIT SEPARATOR, a
13
- * character no address token contains. Render a key for humans with `key.split(SLICE_STATS_SEP).join(" ")`.
14
- */
15
- export declare const SLICE_STATS_SEP = "\u001F";
16
- /**
17
- * Nested tally: outer key → (inner key → count). Token → label counts, or bigram key → label-bigram counts.
18
- */
19
- type CooccurrenceTable = Map<string, Map<string, number>>;
20
- /**
21
- * The token + bigram co-occurrence tables one pass over labeled rows accumulates.
22
- */
23
- export interface CooccurrenceStats {
24
- tokens: CooccurrenceTable;
25
- bigrams: CooccurrenceTable;
26
- }
27
- /**
28
- * An empty pair of tables for {@link accumulateCooccurrences}.
29
- */
30
- export declare function createCooccurrenceStats(): CooccurrenceStats;
31
- /**
32
- * Fold one row's parallel `tokens`/`labels` into the tables. The caller has already checked the arrays are the same
33
- * length.
34
- */
35
- export declare function accumulateCooccurrences(stats: CooccurrenceStats, tokens: readonly string[], labels: readonly string[]): void;
36
- /**
37
- * A slice row projected to the two columns the co-occurrence pass reads.
38
- */
39
- export interface TokenLabelRow {
40
- tokens: string[];
41
- labels: string[];
42
- [key: string]: unknown;
43
- }
44
- /**
45
- * Stream a slice's `tokens`/`labels` columns.
46
- *
47
- * Projected rather than read whole: parquet is columnar, so the unused columns are never touched. `limit` stops the
48
- * iteration rather than filtering afterwards, so a capped run reads only the row groups it needs.
49
- */
50
- export declare function streamTokenLabelRows(slicePath: string, limit?: number): AsyncIterable<TokenLabelRow>;
51
- export {};
52
- //# sourceMappingURL=slice-stats.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"slice-stats.d.ts","sourceRoot":"","sources":["../../lib/utils/slice-stats.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAIH;;;GAGG;AACH,eAAO,MAAM,eAAe,WAAM,CAAA;AAElC;;GAEG;AACH,KAAK,iBAAiB,GAAG,GAAG,CAAC,MAAM,EAAE,GAAG,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC,CAAA;AAEzD;;GAEG;AACH,MAAM,WAAW,iBAAiB;IACjC,MAAM,EAAE,iBAAiB,CAAA;IACzB,OAAO,EAAE,iBAAiB,CAAA;CAC1B;AAED;;GAEG;AACH,wBAAgB,uBAAuB,IAAI,iBAAiB,CAE3D;AAaD;;;GAGG;AACH,wBAAgB,uBAAuB,CACtC,KAAK,EAAE,iBAAiB,EACxB,MAAM,EAAE,SAAS,MAAM,EAAE,EACzB,MAAM,EAAE,SAAS,MAAM,EAAE,GACvB,IAAI,CAWN;AAED;;GAEG;AACH,MAAM,WAAW,aAAa;IAC7B,MAAM,EAAE,MAAM,EAAE,CAAA;IAChB,MAAM,EAAE,MAAM,EAAE,CAAA;IAChB,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAA;CACtB;AAED;;;;;GAKG;AACH,wBAAuB,oBAAoB,CAAC,SAAS,EAAE,MAAM,EAAE,KAAK,CAAC,EAAE,MAAM,GAAG,aAAa,CAAC,aAAa,CAAC,CAQ3G"}
@@ -1,58 +0,0 @@
1
- /**
2
- * @copyright Sister Software
3
- * @license AGPL-3.0
4
- * @author Teffen Ellis, et al.
5
- *
6
- * Token/label co-occurrence accounting shared by the corpus-stats builder (`tools/corpus-stats.ts`)
7
- * and the slice linter (`tools/lint-slice.ts`). The two sides MUST agree on the bigram key format:
8
- * the linter looks its slice's bigrams up in the stats file's `bigrams` table, and a key built with
9
- * a different separator never matches — which silently blanks the bigram-collision check.
10
- */
11
- import { streamParquetRows } from "#utils/parquet";
12
- /**
13
- * Separator inside a bigram key (`tok1␟tok2`) and a label-bigram value (`lab1␟lab2`): U+001F UNIT SEPARATOR, a
14
- * character no address token contains. Render a key for humans with `key.split(SLICE_STATS_SEP).join(" ")`.
15
- */
16
- export const SLICE_STATS_SEP = "";
17
- /**
18
- * An empty pair of tables for {@link accumulateCooccurrences}.
19
- */
20
- export function createCooccurrenceStats() {
21
- return { tokens: new Map(), bigrams: new Map() };
22
- }
23
- function bump(table, key, sub) {
24
- let counter = table.get(key);
25
- if (!counter) {
26
- counter = new Map();
27
- table.set(key, counter);
28
- }
29
- counter.set(sub, (counter.get(sub) ?? 0) + 1);
30
- }
31
- /**
32
- * Fold one row's parallel `tokens`/`labels` into the tables. The caller has already checked the arrays are the same
33
- * length.
34
- */
35
- export function accumulateCooccurrences(stats, tokens, labels) {
36
- for (let i = 0; i < tokens.length; i++) {
37
- const tk = tokens[i];
38
- const lb = labels[i];
39
- bump(stats.tokens, tk, lb);
40
- if (i + 1 < tokens.length) {
41
- bump(stats.bigrams, tk + SLICE_STATS_SEP + tokens[i + 1], lb + SLICE_STATS_SEP + labels[i + 1]);
42
- }
43
- }
44
- }
45
- /**
46
- * Stream a slice's `tokens`/`labels` columns.
47
- *
48
- * Projected rather than read whole: parquet is columnar, so the unused columns are never touched. `limit` stops the
49
- * iteration rather than filtering afterwards, so a capped run reads only the row groups it needs.
50
- */
51
- export async function* streamTokenLabelRows(slicePath, limit) {
52
- let emitted = 0;
53
- for await (const row of streamParquetRows(slicePath, ["tokens", "labels"], { limit })) {
54
- yield row;
55
- emitted++;
56
- }
57
- }
58
- //# sourceMappingURL=slice-stats.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"slice-stats.js","sourceRoot":"","sources":["../../lib/utils/slice-stats.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAEH,OAAO,EAAE,iBAAiB,EAAE,MAAM,gBAAgB,CAAA;AAElD;;;GAGG;AACH,MAAM,CAAC,MAAM,eAAe,GAAG,GAAG,CAAA;AAelC;;GAEG;AACH,MAAM,UAAU,uBAAuB;IACtC,OAAO,EAAE,MAAM,EAAE,IAAI,GAAG,EAAE,EAAE,OAAO,EAAE,IAAI,GAAG,EAAE,EAAE,CAAA;AACjD,CAAC;AAED,SAAS,IAAI,CAAC,KAAwB,EAAE,GAAW,EAAE,GAAW;IAC/D,IAAI,OAAO,GAAG,KAAK,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;IAE5B,IAAI,CAAC,OAAO,EAAE,CAAC;QACd,OAAO,GAAG,IAAI,GAAG,EAAE,CAAA;QACnB,KAAK,CAAC,GAAG,CAAC,GAAG,EAAE,OAAO,CAAC,CAAA;IACxB,CAAC;IAED,OAAO,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,OAAO,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAA;AAC9C,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,uBAAuB,CACtC,KAAwB,EACxB,MAAyB,EACzB,MAAyB;IAEzB,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,MAAM,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QACxC,MAAM,EAAE,GAAG,MAAM,CAAC,CAAC,CAAE,CAAA;QACrB,MAAM,EAAE,GAAG,MAAM,CAAC,CAAC,CAAE,CAAA;QAErB,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,EAAE,EAAE,EAAE,CAAC,CAAA;QAE1B,IAAI,CAAC,GAAG,CAAC,GAAG,MAAM,CAAC,MAAM,EAAE,CAAC;YAC3B,IAAI,CAAC,KAAK,CAAC,OAAO,EAAE,EAAE,GAAG,eAAe,GAAG,MAAM,CAAC,CAAC,GAAG,CAAC,CAAE,EAAE,EAAE,GAAG,eAAe,GAAG,MAAM,CAAC,CAAC,GAAG,CAAC,CAAE,CAAC,CAAA;QAClG,CAAC;IACF,CAAC;AACF,CAAC;AAWD;;;;;GAKG;AACH,MAAM,CAAC,KAAK,SAAS,CAAC,CAAC,oBAAoB,CAAC,SAAiB,EAAE,KAAc;IAC5E,IAAI,OAAO,GAAG,CAAC,CAAA;IAEf,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,iBAAiB,CAAgB,SAAS,EAAE,CAAC,QAAQ,EAAE,QAAQ,CAAC,EAAE,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC;QACtG,MAAM,GAAG,CAAA;QAET,OAAO,EAAE,CAAA;IACV,CAAC;AACF,CAAC"}