@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.
- package/README.md +134 -32
- package/data/PROVENANCE.md +623 -17
- package/data/address-source-register.json +14249 -0
- package/data/builds/v0.7.0-de-holdout/inputs.json +22 -0
- package/data/builds/v0.8.0-registers/inputs.json +92 -0
- package/data/license-decisions.json +1603 -0
- package/data/licenses/PROVENANCE.md +65 -0
- package/data/licenses/cdla-permissive-2.0.md +43 -0
- package/data/licenses/geonames-publication.md +34 -0
- package/data/licenses/licence-ouverte-2.0.md +36 -0
- package/data/licenses/national-address-database.md +46 -0
- package/data/licenses/nlod-2.0.md +90 -0
- package/data/licenses/sirene-publication.md +38 -0
- package/data/licenses/whosonfirst-licenses.md +65 -0
- package/data/source-resolutions.json +804 -0
- package/data/sub-venue-lexicon.json +1 -1
- package/data/training-manifests/v0.7.0-de-holdout.effective.json +477 -0
- package/data/training-manifests/v0.7.0-de-holdout.json +78 -0
- package/lib/adapters/cordis/adapter.ts +785 -0
- package/lib/adapters/dedup-key.ts +40 -0
- package/lib/adapters/errors.ts +21 -0
- package/lib/adapters/geonames/adapter.ts +43 -53
- package/lib/adapters/geonames/postal/adapter.ts +116 -0
- package/lib/adapters/gleif/adapter.ts +828 -0
- package/lib/adapters/libpostal-dictionary.ts +39 -0
- package/lib/adapters/openaddresses/adapter.ts +54 -61
- package/lib/adapters/osm/adapter.ts +356 -0
- package/lib/adapters/overture/adapter.ts +65 -41
- package/lib/adapters/po-box/adapter.ts +202 -0
- package/lib/adapters/registry.ts +79 -0
- package/lib/adapters/sha256-stream.ts +49 -0
- package/lib/adapters/source-id.ts +49 -0
- package/lib/adapters/street-line.ts +135 -0
- package/lib/adapters/wof/admin/json/adapter.ts +254 -0
- package/lib/adapters/wof/json-rows.ts +211 -0
- package/lib/adapters/wof/postalcode-json/adapter.ts +194 -0
- package/lib/adapters.ts +230 -0
- package/lib/au/adapters/gnaf/adapter.ts +144 -0
- package/lib/au/adapters/gnaf/assemble.ts +205 -0
- package/lib/be/adapters/brussels/adapter.ts +566 -0
- package/lib/be/adapters/vlaanderen/adapter.ts +670 -0
- package/lib/be/adapters/wallonie/adapter.ts +537 -0
- package/lib/be/tools/fetch/brussels.ts +239 -0
- package/lib/be/tools/fetch/wallonie.ts +274 -0
- package/lib/build/adapters.ts +110 -0
- package/lib/build/align.ts +364 -0
- package/lib/build/checkpoint.ts +131 -0
- package/lib/build/eligibility.ts +96 -0
- package/lib/build/heap.ts +53 -0
- package/lib/build/inputs.ts +81 -0
- package/lib/build/rows.ts +21 -0
- package/lib/build/types.ts +232 -0
- package/lib/build.ts +127 -315
- package/lib/cn/recipes/organizational-units.ts +178 -0
- package/lib/cz/adapters/cuzk/adapter.ts +317 -0
- package/lib/cz/recipes/pcfirst-preposition.ts +125 -0
- package/lib/cz/tools/fetch/cuzk.ts +699 -0
- package/lib/de/recipes/locale.ts +370 -0
- package/lib/directory.ts +31 -0
- package/lib/dk/adapters/inspire/adapter.ts +345 -0
- package/lib/dk/tools/fetch/inspire.ts +321 -0
- package/lib/ee/adapters/ads/adapter.ts +246 -0
- package/lib/ee/tools/fetch/ads.ts +270 -0
- package/lib/env.ts +6 -2
- package/lib/es/adapters/bizkaia/adapter.ts +388 -0
- package/lib/es/adapters/catastro/adapter.ts +343 -0
- package/lib/es/adapters/gipuzkoa/adapter.ts +263 -0
- package/lib/es/adapters/navarra/adapter.ts +289 -0
- package/lib/es/cadastre.ts +194 -0
- package/lib/es/tools/fetch/bizkaia.ts +748 -0
- package/lib/es/tools/fetch/catastro.ts +754 -0
- package/lib/es/tools/fetch/gipuzkoa.ts +336 -0
- package/lib/es/tools/fetch/navarra.ts +488 -0
- package/lib/fi/adapters/ryhti/adapter.ts +323 -0
- package/lib/fi/tools/fetch/ryhti.ts +476 -0
- package/lib/fingerprints.ts +154 -0
- package/lib/fr/adapters/annuaire-education/adapter.ts +598 -0
- package/lib/fr/adapters/ban/adapter.ts +187 -0
- package/lib/fr/adapters/finess/adapter.ts +618 -0
- package/lib/fr/adapters/finess/postal-lines.ts +157 -0
- package/lib/fr/adapters/finess/voie-type.ts +200 -0
- package/lib/fr/insee-country.ts +62 -0
- package/lib/fr/recipes/admin-split.ts +221 -0
- package/lib/fr/recipes/bare-street.ts +158 -0
- package/lib/fr/recipes/fragment.ts +251 -0
- package/lib/fr/recipes/lieudit.ts +310 -0
- package/lib/fr/recipes/order.ts +219 -0
- package/lib/fr/street-decompose.ts +67 -0
- package/lib/fr/tools/fetch/annuaire-education.ts +306 -0
- package/lib/fr/tools/fetch/ban.ts +298 -0
- package/lib/fr/tools/fetch/finess.ts +352 -0
- package/lib/gauntlet-inputs.ts +92 -0
- package/lib/index.ts +10 -4
- package/lib/inspire/address.ts +457 -0
- package/lib/inspire/archive.ts +44 -0
- package/lib/inspire/errors.ts +71 -0
- package/lib/inspire/stream.ts +262 -0
- package/lib/international/recipes/locale.ts +556 -0
- package/lib/it/adapters/anac/adapter.ts +522 -0
- package/lib/it/tools/fetch/anac.ts +394 -0
- package/lib/jp/adapters/wof-admin/adapter.ts +224 -0
- package/lib/jp/tools/fetch/houjin.ts +139 -0
- package/lib/kr/adapters/juso/label-rows.ts +239 -0
- package/lib/kr/adapters/localdata/align.ts +288 -0
- package/lib/kr/adapters/localdata/key-index.ts +177 -0
- package/lib/kr/adapters/localdata/permit-rows.ts +193 -0
- package/lib/kr/tools/fetch/juso.ts +170 -0
- package/lib/kr/tools/fetch/localdata.ts +205 -0
- package/lib/lu/adapters/bd-adresses/adapter.ts +240 -0
- package/lib/lu/tools/fetch/bd-adresses.ts +351 -0
- package/lib/lv/adapters/varis/adapter.ts +499 -0
- package/lib/lv/tools/fetch/varis.ts +214 -0
- package/lib/nl/adapters/kadaster/adapter.ts +386 -0
- package/lib/nl/recipes/postcode.ts +139 -0
- package/lib/nl/tools/fetch/kadaster.ts +298 -0
- package/lib/no/adapters/matrikkelen/adapter.ts +187 -0
- package/lib/no/recipes/fragment.ts +189 -0
- package/lib/no/recipes/street/led.ts +154 -0
- package/lib/no/recipes/street.ts +109 -0
- package/lib/no/tools/fetch/matrikkelen.ts +519 -0
- package/lib/parquet/duckdb.ts +144 -0
- package/lib/parquet/readers.ts +86 -0
- package/lib/parquet/schema.ts +214 -0
- package/lib/parquet/shuffle.ts +59 -0
- package/lib/parquet/span-sql.ts +54 -0
- package/lib/parquet/streams.ts +113 -0
- package/lib/parquet/writers.ts +451 -0
- package/lib/pl/adapters/emuia/adapter.ts +202 -0
- package/lib/pl/tools/fetch/emuia.ts +360 -0
- package/lib/recipes/anchor-absorption.ts +30 -19
- package/lib/recipes/bare/country.ts +87 -0
- package/lib/recipes/bare/postcode/eval.ts +99 -0
- package/lib/recipes/bare/postcode.ts +346 -0
- package/lib/recipes/boundary-stress.ts +36 -19
- package/lib/recipes/country-balanced.ts +67 -87
- package/lib/recipes/house-venue.ts +31 -13
- package/lib/recipes/intersection.ts +83 -61
- package/lib/recipes/po/box/cedex/au-nz.ts +82 -0
- package/lib/recipes/po/box/cedex/ca.ts +59 -0
- package/lib/recipes/po/box/cedex/fr.ts +77 -0
- package/lib/recipes/po/box/cedex/phrases.ts +109 -0
- package/lib/recipes/po/box/cedex/recipe.ts +215 -0
- package/lib/recipes/po/box/cedex/sources.ts +189 -0
- package/lib/recipes/po/box/cedex/types.ts +35 -0
- package/lib/recipes/po/box/cedex/us.ts +74 -0
- package/lib/recipes/po/box/cedex/vocabulary.ts +106 -0
- package/lib/recipes/po/box/cedex.ts +9 -0
- package/lib/recipes/po/box.ts +149 -0
- package/lib/recipes/scaffold.ts +258 -182
- package/lib/recipes/sources.ts +399 -0
- package/lib/recipes/street/affix.ts +707 -0
- package/lib/recipes/street/bare.ts +115 -0
- package/lib/recipes/street.ts +32 -8
- package/lib/recipes/sub/venue/context.ts +156 -0
- package/lib/recipes/sub/venue/render.ts +170 -0
- package/lib/recipes/sub/venue/sources.ts +588 -0
- package/lib/recipes/sub/venue.ts +801 -0
- package/lib/recipes/trailing-region.ts +70 -81
- package/lib/recipes/unit/sources.ts +44 -0
- package/lib/recipes/unit.ts +102 -90
- package/lib/recipes.ts +106 -0
- package/lib/registers.ts +278 -0
- package/lib/ro/adapters/retea-scolara/adapter.ts +264 -0
- package/lib/ro/tools/fetch/retea-scolara.ts +187 -0
- package/lib/runner.ts +220 -84
- package/lib/sg/recipes/register.ts +264 -0
- package/lib/sg/tools/fetch/acra.ts +174 -0
- package/lib/si/recipes/bare-village.ts +116 -0
- package/lib/sk/adapters/inspire/adapter.ts +395 -0
- package/lib/sk/tools/fetch/inspire.ts +402 -0
- package/lib/source-register/effective-manifest.ts +659 -0
- package/lib/source-register/register.ts +539 -0
- package/lib/source-register/training-manifest.ts +218 -0
- package/lib/source-register/types.ts +590 -0
- package/lib/source-register.ts +71 -0
- package/lib/south-asia/recipes/register.ts +233 -0
- package/lib/subvenue/harvest.ts +251 -0
- package/lib/subvenue/promotions.ts +293 -0
- package/lib/subvenue/surfaces.ts +94 -0
- package/lib/subvenue/table.ts +264 -0
- package/lib/surfaces/locale.ts +246 -0
- package/lib/synthesizers/anchor-absorption.ts +55 -91
- package/lib/synthesizers/boundary-stress.ts +49 -131
- package/lib/synthesizers/house-venue.ts +44 -102
- package/lib/synthesizers/intersection.ts +37 -26
- package/lib/synthesizers/no-street.ts +70 -119
- package/lib/synthesizers/po-box.ts +90 -105
- package/lib/synthesizers/street.ts +47 -35
- package/lib/synthesizers/utils.ts +65 -219
- package/lib/test-kit/corpus-recipe.ts +45 -28
- package/lib/test-kit.ts +116 -0
- package/lib/tools/align-canonical.ts +64 -0
- package/lib/tools/audit.ts +114 -118
- package/lib/tools/corpus-stats.ts +46 -32
- package/lib/tools/fetch/atom.ts +164 -0
- package/lib/tools/fetch/cordis.ts +318 -0
- package/lib/tools/fetch/download/manifest.ts +114 -0
- package/lib/tools/fetch/download/network.ts +250 -0
- package/lib/tools/fetch/download/retry.ts +174 -0
- package/lib/tools/fetch/download.ts +4 -471
- package/lib/tools/fetch/geonames/dump.ts +275 -0
- package/lib/tools/fetch/geonames/postal.ts +145 -0
- package/lib/tools/fetch/gleif.ts +360 -0
- package/lib/tools/fetch/header.ts +69 -0
- package/lib/tools/fetch/inspire-addresses.ts +495 -0
- package/lib/tools/fetch/openaddresses.ts +20 -109
- package/lib/tools/fetch/ourairports.ts +16 -49
- package/lib/tools/fetch/ppd.ts +10 -10
- package/lib/tools/fetch/vlaanderen-ad.ts +435 -0
- package/lib/tools/fetch/wfs-harvest.ts +943 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +43 -143
- package/lib/tools/fetch/zip-archive.ts +100 -0
- package/lib/tools/fetch.ts +143 -0
- package/lib/tools/golden/expand.ts +605 -0
- package/lib/tools/golden/promote.ts +349 -0
- package/lib/tools/golden/relabel-street/directory.ts +367 -0
- package/lib/tools/golden/relabel-street/row.ts +283 -0
- package/lib/tools/golden/relabel-street.ts +9 -0
- package/lib/tools/ingest-csv.ts +45 -50
- package/lib/tools/jsonl-to-parquet.ts +59 -98
- package/lib/tools/lint/recipe-output/vocab.ts +366 -0
- package/lib/tools/lint/recipe-output.ts +482 -0
- package/lib/tools/migrate/overlay-parquet.ts +173 -0
- package/lib/tools/migrate/recipe-output.ts +153 -0
- package/lib/tools/migrate/source-names.ts +161 -0
- package/lib/tools/overlay/kryptonite.ts +144 -0
- package/lib/tools/overlay/manifest.ts +407 -0
- package/lib/tools/overlay/merge-source.ts +138 -0
- package/lib/tools/overlay/split-slice.ts +144 -0
- package/lib/tools/overlay/translit.ts +234 -0
- package/lib/tools/overture-subvenue.ts +18 -91
- package/lib/tools/postcode-triples.ts +362 -167
- package/lib/tools/source-register/build.ts +819 -0
- package/lib/tools/sub/venue/head-nouns.ts +208 -0
- package/lib/tools/sub/venue/lexicon.ts +394 -0
- package/lib/tools/sub/venue/wikidata.ts +88 -0
- package/lib/tools.ts +31 -0
- package/lib/tw/tools/fetch/gcis.ts +181 -0
- package/lib/types.ts +304 -101
- package/lib/us/adapters/fcc-bdc/adapter.ts +158 -0
- package/lib/us/adapters/state/hi-schools/adapter.ts +171 -0
- package/lib/us/adapters/state/hi-schools/workbook.ts +40 -0
- package/lib/us/adapters/state/ia-contractors/adapter.ts +148 -0
- package/lib/us/adapters/state/ny-notaries/adapter.ts +132 -0
- package/lib/us/adapters/state/tx-notaries/adapter.ts +155 -0
- package/lib/us/adapters/tiger/adapter.ts +225 -0
- package/lib/us/adapters/tiger/street-decompose.ts +73 -0
- package/lib/us/adapters/usgov/hrsa-fqhc/adapter.ts +171 -0
- package/lib/us/adapters/usgov/imls-pls/adapter.ts +140 -0
- package/lib/us/adapters/usgov/irs-bmf/adapter.ts +154 -0
- package/lib/us/adapters/usgov/nad/adapter.ts +263 -0
- package/lib/us/adapters/usgov/nppes/adapter.ts +180 -0
- package/lib/us/adapters/usgov/samhsa-treatment-locator/adapter.ts +195 -0
- package/lib/us/fips-state.ts +122 -0
- package/lib/us/tools/fetch/hrsa.ts +58 -0
- package/lib/us/tools/fetch/imls-pls.ts +131 -0
- package/lib/us/tools/fetch/nad.ts +359 -0
- package/lib/us/tools/fetch/nppes.ts +153 -0
- package/lib/us/tools/fetch/state/hi-schools.ts +167 -0
- package/lib/us/tools/fetch/state/sources.ts +146 -0
- package/lib/us/tools/fetch/tiger-full.ts +256 -0
- package/lib/utils/align.ts +43 -53
- package/lib/utils/cooccurrence-stats.ts +101 -0
- package/lib/utils/golden.ts +39 -50
- package/lib/utils/license.ts +238 -26
- package/lib/utils/split.ts +205 -88
- package/lib/utils/tokenize.ts +22 -34
- package/lib/utils/wof-json.ts +134 -87
- package/lib/utils.ts +13 -0
- package/lib/ve/recipes/reviewed-postcode-tail.ts +217 -0
- package/out/adapters/cordis/adapter.d.ts +324 -0
- package/out/adapters/cordis/adapter.d.ts.map +1 -0
- package/out/adapters/cordis/adapter.js +616 -0
- package/out/adapters/cordis/adapter.js.map +1 -0
- package/out/adapters/dedup-key.d.ts +30 -0
- package/out/adapters/dedup-key.d.ts.map +1 -0
- package/out/adapters/dedup-key.js +35 -0
- package/out/adapters/dedup-key.js.map +1 -0
- package/out/adapters/errors.d.ts +17 -0
- package/out/adapters/errors.d.ts.map +1 -0
- package/out/adapters/errors.js +20 -0
- package/out/adapters/errors.js.map +1 -0
- package/out/adapters/geonames/adapter.d.ts +26 -28
- package/out/adapters/geonames/adapter.d.ts.map +1 -1
- package/out/adapters/geonames/adapter.js +40 -50
- package/out/adapters/geonames/adapter.js.map +1 -1
- package/out/adapters/geonames/postal/adapter.d.ts +41 -0
- package/out/adapters/geonames/postal/adapter.d.ts.map +1 -0
- package/out/adapters/geonames/postal/adapter.js +102 -0
- package/out/adapters/geonames/postal/adapter.js.map +1 -0
- package/out/adapters/gleif/adapter.d.ts +293 -0
- package/out/adapters/gleif/adapter.d.ts.map +1 -0
- package/out/adapters/gleif/adapter.js +684 -0
- package/out/adapters/gleif/adapter.js.map +1 -0
- package/out/adapters/libpostal-dictionary.d.ts +22 -0
- package/out/adapters/libpostal-dictionary.d.ts.map +1 -0
- package/out/adapters/libpostal-dictionary.js +36 -0
- package/out/adapters/libpostal-dictionary.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts +28 -43
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -1
- package/out/adapters/openaddresses/adapter.js +37 -51
- package/out/adapters/openaddresses/adapter.js.map +1 -1
- package/out/adapters/osm/adapter.d.ts +101 -0
- package/out/adapters/osm/adapter.d.ts.map +1 -0
- package/out/adapters/osm/adapter.js +260 -0
- package/out/adapters/osm/adapter.js.map +1 -0
- package/out/adapters/overture/adapter.d.ts +14 -30
- package/out/adapters/overture/adapter.d.ts.map +1 -1
- package/out/adapters/overture/adapter.js +57 -41
- package/out/adapters/overture/adapter.js.map +1 -1
- package/out/adapters/po-box/adapter.d.ts +63 -0
- package/out/adapters/po-box/adapter.d.ts.map +1 -0
- package/out/adapters/po-box/adapter.js +139 -0
- package/out/adapters/po-box/adapter.js.map +1 -0
- package/out/adapters/registry.d.ts +55 -0
- package/out/adapters/registry.d.ts.map +1 -0
- package/out/adapters/registry.js +43 -0
- package/out/adapters/registry.js.map +1 -0
- package/out/adapters/sha256-stream.d.ts +26 -0
- package/out/adapters/sha256-stream.d.ts.map +1 -0
- package/out/adapters/sha256-stream.js +34 -0
- package/out/adapters/sha256-stream.js.map +1 -0
- package/out/adapters/source-id.d.ts +33 -0
- package/out/adapters/source-id.d.ts.map +1 -0
- package/out/adapters/source-id.js +42 -0
- package/out/adapters/source-id.js.map +1 -0
- package/out/adapters/street-line.d.ts +102 -0
- package/out/adapters/street-line.d.ts.map +1 -0
- package/out/adapters/street-line.js +117 -0
- package/out/adapters/street-line.js.map +1 -0
- package/out/adapters/wof/admin/json/adapter.d.ts +88 -0
- package/out/adapters/wof/admin/json/adapter.d.ts.map +1 -0
- package/out/adapters/wof/admin/json/adapter.js +220 -0
- package/out/adapters/wof/admin/json/adapter.js.map +1 -0
- package/out/adapters/wof/json-rows.d.ts +89 -0
- package/out/adapters/wof/json-rows.d.ts.map +1 -0
- package/out/adapters/wof/json-rows.js +135 -0
- package/out/adapters/wof/json-rows.js.map +1 -0
- package/out/adapters/wof/postalcode-json/adapter.d.ts +49 -0
- package/out/adapters/wof/postalcode-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof/postalcode-json/adapter.js +165 -0
- package/out/adapters/wof/postalcode-json/adapter.js.map +1 -0
- package/out/adapters.d.ts +75 -0
- package/out/adapters.d.ts.map +1 -0
- package/out/adapters.js +167 -0
- package/out/adapters.js.map +1 -0
- package/out/au/adapters/gnaf/adapter.d.ts +37 -0
- package/out/au/adapters/gnaf/adapter.d.ts.map +1 -0
- package/out/au/adapters/gnaf/adapter.js +119 -0
- package/out/au/adapters/gnaf/adapter.js.map +1 -0
- package/out/au/adapters/gnaf/assemble.d.ts +54 -0
- package/out/au/adapters/gnaf/assemble.d.ts.map +1 -0
- package/out/au/adapters/gnaf/assemble.js +134 -0
- package/out/au/adapters/gnaf/assemble.js.map +1 -0
- package/out/be/adapters/brussels/adapter.d.ts +212 -0
- package/out/be/adapters/brussels/adapter.d.ts.map +1 -0
- package/out/be/adapters/brussels/adapter.js +435 -0
- package/out/be/adapters/brussels/adapter.js.map +1 -0
- package/out/be/adapters/vlaanderen/adapter.d.ts +233 -0
- package/out/be/adapters/vlaanderen/adapter.d.ts.map +1 -0
- package/out/be/adapters/vlaanderen/adapter.js +416 -0
- package/out/be/adapters/vlaanderen/adapter.js.map +1 -0
- package/out/be/adapters/wallonie/adapter.d.ts +196 -0
- package/out/be/adapters/wallonie/adapter.d.ts.map +1 -0
- package/out/be/adapters/wallonie/adapter.js +437 -0
- package/out/be/adapters/wallonie/adapter.js.map +1 -0
- package/out/be/tools/fetch/brussels.d.ts +119 -0
- package/out/be/tools/fetch/brussels.d.ts.map +1 -0
- package/out/be/tools/fetch/brussels.js +146 -0
- package/out/be/tools/fetch/brussels.js.map +1 -0
- package/out/be/tools/fetch/wallonie.d.ts +119 -0
- package/out/be/tools/fetch/wallonie.d.ts.map +1 -0
- package/out/be/tools/fetch/wallonie.js +167 -0
- package/out/be/tools/fetch/wallonie.js.map +1 -0
- package/out/build/adapters.d.ts +33 -0
- package/out/build/adapters.d.ts.map +1 -0
- package/out/build/adapters.js +68 -0
- package/out/build/adapters.js.map +1 -0
- package/out/build/align.d.ts +73 -0
- package/out/build/align.d.ts.map +1 -0
- package/out/build/align.js +226 -0
- package/out/build/align.js.map +1 -0
- package/out/build/checkpoint.d.ts +94 -0
- package/out/build/checkpoint.d.ts.map +1 -0
- package/out/build/checkpoint.js +59 -0
- package/out/build/checkpoint.js.map +1 -0
- package/out/build/eligibility.d.ts +47 -0
- package/out/build/eligibility.d.ts.map +1 -0
- package/out/build/eligibility.js +80 -0
- package/out/build/eligibility.js.map +1 -0
- package/out/build/heap.d.ts +28 -0
- package/out/build/heap.d.ts.map +1 -0
- package/out/build/heap.js +47 -0
- package/out/build/heap.js.map +1 -0
- package/out/build/inputs.d.ts +52 -0
- package/out/build/inputs.d.ts.map +1 -0
- package/out/build/inputs.js +49 -0
- package/out/build/inputs.js.map +1 -0
- package/out/build/rows.d.ts +16 -0
- package/out/build/rows.d.ts.map +1 -0
- package/out/build/rows.js +19 -0
- package/out/build/rows.js.map +1 -0
- package/out/build/types.d.ts +220 -0
- package/out/build/types.d.ts.map +1 -0
- package/out/build/types.js +34 -0
- package/out/build/types.js.map +1 -0
- package/out/build.d.ts +6 -121
- package/out/build.d.ts.map +1 -1
- package/out/build.js +112 -207
- package/out/build.js.map +1 -1
- package/out/cn/recipes/organizational-units.d.ts +19 -0
- package/out/cn/recipes/organizational-units.d.ts.map +1 -0
- package/out/cn/recipes/organizational-units.js +138 -0
- package/out/cn/recipes/organizational-units.js.map +1 -0
- package/out/cz/adapters/cuzk/adapter.d.ts +52 -0
- package/out/cz/adapters/cuzk/adapter.d.ts.map +1 -0
- package/out/cz/adapters/cuzk/adapter.js +266 -0
- package/out/cz/adapters/cuzk/adapter.js.map +1 -0
- package/out/cz/recipes/pcfirst-preposition.d.ts +18 -0
- package/out/cz/recipes/pcfirst-preposition.d.ts.map +1 -0
- package/out/cz/recipes/pcfirst-preposition.js +110 -0
- package/out/cz/recipes/pcfirst-preposition.js.map +1 -0
- package/out/cz/tools/fetch/cuzk.d.ts +272 -0
- package/out/cz/tools/fetch/cuzk.d.ts.map +1 -0
- package/out/cz/tools/fetch/cuzk.js +446 -0
- package/out/cz/tools/fetch/cuzk.js.map +1 -0
- package/out/de/recipes/locale.d.ts +42 -0
- package/out/de/recipes/locale.d.ts.map +1 -0
- package/out/de/recipes/locale.js +299 -0
- package/out/de/recipes/locale.js.map +1 -0
- package/out/directory.d.ts +20 -0
- package/out/directory.d.ts.map +1 -0
- package/out/directory.js +27 -0
- package/out/directory.js.map +1 -0
- package/out/dk/adapters/inspire/adapter.d.ts +154 -0
- package/out/dk/adapters/inspire/adapter.d.ts.map +1 -0
- package/out/dk/adapters/inspire/adapter.js +258 -0
- package/out/dk/adapters/inspire/adapter.js.map +1 -0
- package/out/dk/tools/fetch/inspire.d.ts +100 -0
- package/out/dk/tools/fetch/inspire.d.ts.map +1 -0
- package/out/dk/tools/fetch/inspire.js +230 -0
- package/out/dk/tools/fetch/inspire.js.map +1 -0
- package/out/ee/adapters/ads/adapter.d.ts +109 -0
- package/out/ee/adapters/ads/adapter.d.ts.map +1 -0
- package/out/ee/adapters/ads/adapter.js +191 -0
- package/out/ee/adapters/ads/adapter.js.map +1 -0
- package/out/ee/tools/fetch/ads.d.ts +123 -0
- package/out/ee/tools/fetch/ads.d.ts.map +1 -0
- package/out/ee/tools/fetch/ads.js +195 -0
- package/out/ee/tools/fetch/ads.js.map +1 -0
- package/out/env.d.ts +7 -3
- package/out/env.d.ts.map +1 -1
- package/out/env.js +6 -2
- package/out/env.js.map +1 -1
- package/out/es/adapters/bizkaia/adapter.d.ts +143 -0
- package/out/es/adapters/bizkaia/adapter.d.ts.map +1 -0
- package/out/es/adapters/bizkaia/adapter.js +332 -0
- package/out/es/adapters/bizkaia/adapter.js.map +1 -0
- package/out/es/adapters/catastro/adapter.d.ts +104 -0
- package/out/es/adapters/catastro/adapter.d.ts.map +1 -0
- package/out/es/adapters/catastro/adapter.js +288 -0
- package/out/es/adapters/catastro/adapter.js.map +1 -0
- package/out/es/adapters/gipuzkoa/adapter.d.ts +91 -0
- package/out/es/adapters/gipuzkoa/adapter.d.ts.map +1 -0
- package/out/es/adapters/gipuzkoa/adapter.js +225 -0
- package/out/es/adapters/gipuzkoa/adapter.js.map +1 -0
- package/out/es/adapters/navarra/adapter.d.ts +105 -0
- package/out/es/adapters/navarra/adapter.d.ts.map +1 -0
- package/out/es/adapters/navarra/adapter.js +241 -0
- package/out/es/adapters/navarra/adapter.js.map +1 -0
- package/out/es/cadastre.d.ts +109 -0
- package/out/es/cadastre.d.ts.map +1 -0
- package/out/es/cadastre.js +130 -0
- package/out/es/cadastre.js.map +1 -0
- package/out/es/tools/fetch/bizkaia.d.ts +278 -0
- package/out/es/tools/fetch/bizkaia.d.ts.map +1 -0
- package/out/es/tools/fetch/bizkaia.js +477 -0
- package/out/es/tools/fetch/bizkaia.js.map +1 -0
- package/out/es/tools/fetch/catastro.d.ts +272 -0
- package/out/es/tools/fetch/catastro.d.ts.map +1 -0
- package/out/es/tools/fetch/catastro.js +486 -0
- package/out/es/tools/fetch/catastro.js.map +1 -0
- package/out/es/tools/fetch/gipuzkoa.d.ts +162 -0
- package/out/es/tools/fetch/gipuzkoa.d.ts.map +1 -0
- package/out/es/tools/fetch/gipuzkoa.js +209 -0
- package/out/es/tools/fetch/gipuzkoa.js.map +1 -0
- package/out/es/tools/fetch/navarra.d.ts +189 -0
- package/out/es/tools/fetch/navarra.d.ts.map +1 -0
- package/out/es/tools/fetch/navarra.js +316 -0
- package/out/es/tools/fetch/navarra.js.map +1 -0
- package/out/fi/adapters/ryhti/adapter.d.ts +115 -0
- package/out/fi/adapters/ryhti/adapter.d.ts.map +1 -0
- package/out/fi/adapters/ryhti/adapter.js +244 -0
- package/out/fi/adapters/ryhti/adapter.js.map +1 -0
- package/out/fi/tools/fetch/ryhti.d.ts +206 -0
- package/out/fi/tools/fetch/ryhti.d.ts.map +1 -0
- package/out/fi/tools/fetch/ryhti.js +327 -0
- package/out/fi/tools/fetch/ryhti.js.map +1 -0
- package/out/fingerprints.d.ts +68 -0
- package/out/fingerprints.d.ts.map +1 -0
- package/out/fingerprints.js +130 -0
- package/out/fingerprints.js.map +1 -0
- package/out/fr/adapters/annuaire-education/adapter.d.ts +236 -0
- package/out/fr/adapters/annuaire-education/adapter.d.ts.map +1 -0
- package/out/fr/adapters/annuaire-education/adapter.js +475 -0
- package/out/fr/adapters/annuaire-education/adapter.js.map +1 -0
- package/out/fr/adapters/ban/adapter.d.ts +38 -0
- package/out/fr/adapters/ban/adapter.d.ts.map +1 -0
- package/out/fr/adapters/ban/adapter.js +134 -0
- package/out/fr/adapters/ban/adapter.js.map +1 -0
- package/out/fr/adapters/finess/adapter.d.ts +276 -0
- package/out/fr/adapters/finess/adapter.d.ts.map +1 -0
- package/out/fr/adapters/finess/adapter.js +519 -0
- package/out/fr/adapters/finess/adapter.js.map +1 -0
- package/out/fr/adapters/finess/postal-lines.d.ts +61 -0
- package/out/fr/adapters/finess/postal-lines.d.ts.map +1 -0
- package/out/fr/adapters/finess/postal-lines.js +114 -0
- package/out/fr/adapters/finess/postal-lines.js.map +1 -0
- package/out/fr/adapters/finess/voie-type.d.ts +77 -0
- package/out/fr/adapters/finess/voie-type.d.ts.map +1 -0
- package/out/fr/adapters/finess/voie-type.js +172 -0
- package/out/fr/adapters/finess/voie-type.js.map +1 -0
- package/out/fr/insee-country.d.ts +45 -0
- package/out/fr/insee-country.d.ts.map +1 -0
- package/out/fr/insee-country.js +60 -0
- package/out/fr/insee-country.js.map +1 -0
- package/out/fr/recipes/admin-split.d.ts +15 -0
- package/out/fr/recipes/admin-split.d.ts.map +1 -0
- package/out/fr/recipes/admin-split.js +170 -0
- package/out/fr/recipes/admin-split.js.map +1 -0
- package/out/fr/recipes/bare-street.d.ts +13 -0
- package/out/fr/recipes/bare-street.d.ts.map +1 -0
- package/out/fr/recipes/bare-street.js +129 -0
- package/out/fr/recipes/bare-street.js.map +1 -0
- package/out/fr/recipes/fragment.d.ts +18 -0
- package/out/fr/recipes/fragment.d.ts.map +1 -0
- package/out/fr/recipes/fragment.js +197 -0
- package/out/fr/recipes/fragment.js.map +1 -0
- package/out/fr/recipes/lieudit.d.ts +30 -0
- package/out/fr/recipes/lieudit.d.ts.map +1 -0
- package/out/fr/recipes/lieudit.js +231 -0
- package/out/fr/recipes/lieudit.js.map +1 -0
- package/out/fr/recipes/order.d.ts +15 -0
- package/out/fr/recipes/order.d.ts.map +1 -0
- package/out/fr/recipes/order.js +171 -0
- package/out/fr/recipes/order.js.map +1 -0
- package/out/fr/street-decompose.d.ts +29 -0
- package/out/fr/street-decompose.d.ts.map +1 -0
- package/out/fr/street-decompose.js +52 -0
- package/out/fr/street-decompose.js.map +1 -0
- package/out/fr/tools/fetch/annuaire-education.d.ts +130 -0
- package/out/fr/tools/fetch/annuaire-education.d.ts.map +1 -0
- package/out/fr/tools/fetch/annuaire-education.js +196 -0
- package/out/fr/tools/fetch/annuaire-education.js.map +1 -0
- package/out/fr/tools/fetch/ban.d.ts +33 -0
- package/out/fr/tools/fetch/ban.d.ts.map +1 -0
- package/out/fr/tools/fetch/ban.js +248 -0
- package/out/fr/tools/fetch/ban.js.map +1 -0
- package/out/fr/tools/fetch/finess.d.ts +145 -0
- package/out/fr/tools/fetch/finess.d.ts.map +1 -0
- package/out/fr/tools/fetch/finess.js +228 -0
- package/out/fr/tools/fetch/finess.js.map +1 -0
- package/out/gauntlet-inputs.d.ts +42 -0
- package/out/gauntlet-inputs.d.ts.map +1 -0
- package/out/gauntlet-inputs.js +78 -0
- package/out/gauntlet-inputs.js.map +1 -0
- package/out/index.d.ts +10 -4
- package/out/index.d.ts.map +1 -1
- package/out/index.js +10 -4
- package/out/index.js.map +1 -1
- package/out/inspire/address.d.ts +251 -0
- package/out/inspire/address.d.ts.map +1 -0
- package/out/inspire/address.js +384 -0
- package/out/inspire/address.js.map +1 -0
- package/out/inspire/archive.d.ts +36 -0
- package/out/inspire/archive.d.ts.map +1 -0
- package/out/inspire/archive.js +42 -0
- package/out/inspire/archive.js.map +1 -0
- package/out/inspire/errors.d.ts +55 -0
- package/out/inspire/errors.d.ts.map +1 -0
- package/out/inspire/errors.js +64 -0
- package/out/inspire/errors.js.map +1 -0
- package/out/inspire/stream.d.ts +137 -0
- package/out/inspire/stream.d.ts.map +1 -0
- package/out/inspire/stream.js +125 -0
- package/out/inspire/stream.js.map +1 -0
- package/out/international/recipes/locale.d.ts +90 -0
- package/out/international/recipes/locale.d.ts.map +1 -0
- package/out/international/recipes/locale.js +419 -0
- package/out/international/recipes/locale.js.map +1 -0
- package/out/it/adapters/anac/adapter.d.ts +267 -0
- package/out/it/adapters/anac/adapter.d.ts.map +1 -0
- package/out/it/adapters/anac/adapter.js +429 -0
- package/out/it/adapters/anac/adapter.js.map +1 -0
- package/out/it/tools/fetch/anac.d.ts +174 -0
- package/out/it/tools/fetch/anac.d.ts.map +1 -0
- package/out/it/tools/fetch/anac.js +272 -0
- package/out/it/tools/fetch/anac.js.map +1 -0
- package/out/jp/adapters/wof-admin/adapter.d.ts +68 -0
- package/out/jp/adapters/wof-admin/adapter.d.ts.map +1 -0
- package/out/jp/adapters/wof-admin/adapter.js +172 -0
- package/out/jp/adapters/wof-admin/adapter.js.map +1 -0
- package/out/jp/tools/fetch/houjin.d.ts +27 -0
- package/out/jp/tools/fetch/houjin.d.ts.map +1 -0
- package/out/jp/tools/fetch/houjin.js +106 -0
- package/out/jp/tools/fetch/houjin.js.map +1 -0
- package/out/kr/adapters/juso/label-rows.d.ts +62 -0
- package/out/kr/adapters/juso/label-rows.d.ts.map +1 -0
- package/out/kr/adapters/juso/label-rows.js +172 -0
- package/out/kr/adapters/juso/label-rows.js.map +1 -0
- package/out/kr/adapters/localdata/align.d.ts +31 -0
- package/out/kr/adapters/localdata/align.d.ts.map +1 -0
- package/out/kr/adapters/localdata/align.js +212 -0
- package/out/kr/adapters/localdata/align.js.map +1 -0
- package/out/kr/adapters/localdata/key-index.d.ts +62 -0
- package/out/kr/adapters/localdata/key-index.d.ts.map +1 -0
- package/out/kr/adapters/localdata/key-index.js +127 -0
- package/out/kr/adapters/localdata/key-index.js.map +1 -0
- package/out/kr/adapters/localdata/permit-rows.d.ts +73 -0
- package/out/kr/adapters/localdata/permit-rows.d.ts.map +1 -0
- package/out/kr/adapters/localdata/permit-rows.js +136 -0
- package/out/kr/adapters/localdata/permit-rows.js.map +1 -0
- package/out/kr/tools/fetch/juso.d.ts +33 -0
- package/out/kr/tools/fetch/juso.d.ts.map +1 -0
- package/out/kr/tools/fetch/juso.js +121 -0
- package/out/kr/tools/fetch/juso.js.map +1 -0
- package/out/kr/tools/fetch/localdata.d.ts +37 -0
- package/out/kr/tools/fetch/localdata.d.ts.map +1 -0
- package/out/kr/tools/fetch/localdata.js +147 -0
- package/out/kr/tools/fetch/localdata.js.map +1 -0
- package/out/lu/adapters/bd-adresses/adapter.d.ts +109 -0
- package/out/lu/adapters/bd-adresses/adapter.d.ts.map +1 -0
- package/out/lu/adapters/bd-adresses/adapter.js +196 -0
- package/out/lu/adapters/bd-adresses/adapter.js.map +1 -0
- package/out/lu/tools/fetch/bd-adresses.d.ts +163 -0
- package/out/lu/tools/fetch/bd-adresses.d.ts.map +1 -0
- package/out/lu/tools/fetch/bd-adresses.js +223 -0
- package/out/lu/tools/fetch/bd-adresses.js.map +1 -0
- package/out/lv/adapters/varis/adapter.d.ts +283 -0
- package/out/lv/adapters/varis/adapter.d.ts.map +1 -0
- package/out/lv/adapters/varis/adapter.js +404 -0
- package/out/lv/adapters/varis/adapter.js.map +1 -0
- package/out/lv/tools/fetch/varis.d.ts +80 -0
- package/out/lv/tools/fetch/varis.d.ts.map +1 -0
- package/out/lv/tools/fetch/varis.js +133 -0
- package/out/lv/tools/fetch/varis.js.map +1 -0
- package/out/nl/adapters/kadaster/adapter.d.ts +125 -0
- package/out/nl/adapters/kadaster/adapter.d.ts.map +1 -0
- package/out/nl/adapters/kadaster/adapter.js +310 -0
- package/out/nl/adapters/kadaster/adapter.js.map +1 -0
- package/out/nl/recipes/postcode.d.ts +24 -0
- package/out/nl/recipes/postcode.d.ts.map +1 -0
- package/out/nl/recipes/postcode.js +121 -0
- package/out/nl/recipes/postcode.js.map +1 -0
- package/out/nl/tools/fetch/kadaster.d.ts +155 -0
- package/out/nl/tools/fetch/kadaster.d.ts.map +1 -0
- package/out/nl/tools/fetch/kadaster.js +179 -0
- package/out/nl/tools/fetch/kadaster.js.map +1 -0
- package/out/no/adapters/matrikkelen/adapter.d.ts +44 -0
- package/out/no/adapters/matrikkelen/adapter.d.ts.map +1 -0
- package/out/no/adapters/matrikkelen/adapter.js +143 -0
- package/out/no/adapters/matrikkelen/adapter.js.map +1 -0
- package/out/no/recipes/fragment.d.ts +11 -0
- package/out/no/recipes/fragment.d.ts.map +1 -0
- package/out/no/recipes/fragment.js +149 -0
- package/out/no/recipes/fragment.js.map +1 -0
- package/out/no/recipes/street/led.d.ts +21 -0
- package/out/no/recipes/street/led.d.ts.map +1 -0
- package/out/no/recipes/street/led.js +124 -0
- package/out/no/recipes/street/led.js.map +1 -0
- package/out/no/recipes/street.d.ts +19 -0
- package/out/no/recipes/street.d.ts.map +1 -0
- package/out/no/recipes/street.js +88 -0
- package/out/no/recipes/street.js.map +1 -0
- package/out/no/tools/fetch/matrikkelen.d.ts +251 -0
- package/out/no/tools/fetch/matrikkelen.d.ts.map +1 -0
- package/out/no/tools/fetch/matrikkelen.js +345 -0
- package/out/no/tools/fetch/matrikkelen.js.map +1 -0
- package/out/parquet/duckdb.d.ts +100 -0
- package/out/parquet/duckdb.d.ts.map +1 -0
- package/out/parquet/duckdb.js +92 -0
- package/out/parquet/duckdb.js.map +1 -0
- package/out/parquet/readers.d.ts +44 -0
- package/out/parquet/readers.d.ts.map +1 -0
- package/out/parquet/readers.js +69 -0
- package/out/parquet/readers.js.map +1 -0
- package/out/parquet/schema.d.ts +95 -0
- package/out/parquet/schema.d.ts.map +1 -0
- package/out/parquet/schema.js +157 -0
- package/out/parquet/schema.js.map +1 -0
- package/out/parquet/shuffle.d.ts +25 -0
- package/out/parquet/shuffle.d.ts.map +1 -0
- package/out/parquet/shuffle.js +44 -0
- package/out/parquet/shuffle.js.map +1 -0
- package/out/parquet/span-sql.d.ts +49 -0
- package/out/parquet/span-sql.d.ts.map +1 -0
- package/out/parquet/span-sql.js +53 -0
- package/out/parquet/span-sql.js.map +1 -0
- package/out/parquet/streams.d.ts +47 -0
- package/out/parquet/streams.d.ts.map +1 -0
- package/out/parquet/streams.js +78 -0
- package/out/parquet/streams.js.map +1 -0
- package/out/parquet/writers.d.ts +124 -0
- package/out/parquet/writers.d.ts.map +1 -0
- package/out/parquet/writers.js +251 -0
- package/out/parquet/writers.js.map +1 -0
- package/out/pl/adapters/emuia/adapter.d.ts +81 -0
- package/out/pl/adapters/emuia/adapter.d.ts.map +1 -0
- package/out/pl/adapters/emuia/adapter.js +178 -0
- package/out/pl/adapters/emuia/adapter.js.map +1 -0
- package/out/pl/tools/fetch/emuia.d.ts +165 -0
- package/out/pl/tools/fetch/emuia.d.ts.map +1 -0
- package/out/pl/tools/fetch/emuia.js +260 -0
- package/out/pl/tools/fetch/emuia.js.map +1 -0
- package/out/recipes/anchor-absorption.d.ts +9 -9
- package/out/recipes/anchor-absorption.d.ts.map +1 -1
- package/out/recipes/anchor-absorption.js +29 -19
- package/out/recipes/anchor-absorption.js.map +1 -1
- package/out/recipes/bare/country.d.ts +7 -0
- package/out/recipes/bare/country.d.ts.map +1 -0
- package/out/recipes/bare/country.js +77 -0
- package/out/recipes/bare/country.js.map +1 -0
- package/out/recipes/bare/postcode/eval.d.ts +29 -0
- package/out/recipes/bare/postcode/eval.d.ts.map +1 -0
- package/out/recipes/bare/postcode/eval.js +85 -0
- package/out/recipes/bare/postcode/eval.js.map +1 -0
- package/out/recipes/bare/postcode.d.ts +41 -0
- package/out/recipes/bare/postcode.d.ts.map +1 -0
- package/out/recipes/bare/postcode.js +279 -0
- package/out/recipes/bare/postcode.js.map +1 -0
- package/out/recipes/boundary-stress.d.ts +8 -8
- package/out/recipes/boundary-stress.d.ts.map +1 -1
- package/out/recipes/boundary-stress.js +36 -19
- package/out/recipes/boundary-stress.js.map +1 -1
- package/out/recipes/country-balanced.d.ts +3 -21
- package/out/recipes/country-balanced.d.ts.map +1 -1
- package/out/recipes/country-balanced.js +58 -76
- package/out/recipes/country-balanced.js.map +1 -1
- package/out/recipes/house-venue.d.ts +8 -6
- package/out/recipes/house-venue.d.ts.map +1 -1
- package/out/recipes/house-venue.js +29 -13
- package/out/recipes/house-venue.js.map +1 -1
- package/out/recipes/intersection.d.ts +20 -20
- package/out/recipes/intersection.d.ts.map +1 -1
- package/out/recipes/intersection.js +65 -53
- package/out/recipes/intersection.js.map +1 -1
- package/out/recipes/po/box/cedex/au-nz.d.ts +7 -0
- package/out/recipes/po/box/cedex/au-nz.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/au-nz.js +56 -0
- package/out/recipes/po/box/cedex/au-nz.js.map +1 -0
- package/out/recipes/po/box/cedex/ca.d.ts +7 -0
- package/out/recipes/po/box/cedex/ca.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/ca.js +38 -0
- package/out/recipes/po/box/cedex/ca.js.map +1 -0
- package/out/recipes/po/box/cedex/fr.d.ts +7 -0
- package/out/recipes/po/box/cedex/fr.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/fr.js +57 -0
- package/out/recipes/po/box/cedex/fr.js.map +1 -0
- package/out/recipes/po/box/cedex/phrases.d.ts +8 -0
- package/out/recipes/po/box/cedex/phrases.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/phrases.js +77 -0
- package/out/recipes/po/box/cedex/phrases.js.map +1 -0
- package/out/recipes/po/box/cedex/recipe.d.ts +9 -0
- package/out/recipes/po/box/cedex/recipe.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/recipe.js +163 -0
- package/out/recipes/po/box/cedex/recipe.js.map +1 -0
- package/out/recipes/po/box/cedex/sources.d.ts +86 -0
- package/out/recipes/po/box/cedex/sources.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/sources.js +143 -0
- package/out/recipes/po/box/cedex/sources.js.map +1 -0
- package/out/recipes/po/box/cedex/types.d.ts +31 -0
- package/out/recipes/po/box/cedex/types.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/types.js +5 -0
- package/out/recipes/po/box/cedex/types.js.map +1 -0
- package/out/recipes/po/box/cedex/us.d.ts +7 -0
- package/out/recipes/po/box/cedex/us.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/us.js +54 -0
- package/out/recipes/po/box/cedex/us.js.map +1 -0
- package/out/recipes/po/box/cedex/vocabulary.d.ts +68 -0
- package/out/recipes/po/box/cedex/vocabulary.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/vocabulary.js +90 -0
- package/out/recipes/po/box/cedex/vocabulary.js.map +1 -0
- package/out/recipes/po/box/cedex.d.ts +9 -0
- package/out/recipes/po/box/cedex.d.ts.map +1 -0
- package/out/recipes/po/box/cedex.js +9 -0
- package/out/recipes/po/box/cedex.js.map +1 -0
- package/out/recipes/po/box.d.ts +18 -0
- package/out/recipes/po/box.d.ts.map +1 -0
- package/out/recipes/po/box.js +123 -0
- package/out/recipes/po/box.js.map +1 -0
- package/out/recipes/scaffold.d.ts +214 -121
- package/out/recipes/scaffold.d.ts.map +1 -1
- package/out/recipes/scaffold.js +78 -88
- package/out/recipes/scaffold.js.map +1 -1
- package/out/recipes/sources.d.ts +178 -0
- package/out/recipes/sources.d.ts.map +1 -0
- package/out/recipes/sources.js +348 -0
- package/out/recipes/sources.js.map +1 -0
- package/out/recipes/street/affix.d.ts +59 -0
- package/out/recipes/street/affix.d.ts.map +1 -0
- package/out/recipes/street/affix.js +477 -0
- package/out/recipes/street/affix.js.map +1 -0
- package/out/recipes/street/bare.d.ts +27 -0
- package/out/recipes/street/bare.d.ts.map +1 -0
- package/out/recipes/street/bare.js +98 -0
- package/out/recipes/street/bare.js.map +1 -0
- package/out/recipes/street.d.ts +6 -4
- package/out/recipes/street.d.ts.map +1 -1
- package/out/recipes/street.js +29 -8
- package/out/recipes/street.js.map +1 -1
- package/out/recipes/sub/venue/context.d.ts +32 -0
- package/out/recipes/sub/venue/context.d.ts.map +1 -0
- package/out/recipes/sub/venue/context.js +110 -0
- package/out/recipes/sub/venue/context.js.map +1 -0
- package/out/recipes/sub/venue/render.d.ts +58 -0
- package/out/recipes/sub/venue/render.d.ts.map +1 -0
- package/out/recipes/sub/venue/render.js +118 -0
- package/out/recipes/sub/venue/render.js.map +1 -0
- package/out/recipes/sub/venue/sources.d.ts +166 -0
- package/out/recipes/sub/venue/sources.d.ts.map +1 -0
- package/out/recipes/sub/venue/sources.js +419 -0
- package/out/recipes/sub/venue/sources.js.map +1 -0
- package/out/recipes/sub/venue.d.ts +176 -0
- package/out/recipes/sub/venue.d.ts.map +1 -0
- package/out/recipes/sub/venue.js +562 -0
- package/out/recipes/sub/venue.js.map +1 -0
- package/out/recipes/trailing-region.d.ts +9 -61
- package/out/recipes/trailing-region.d.ts.map +1 -1
- package/out/recipes/trailing-region.js +56 -81
- package/out/recipes/trailing-region.js.map +1 -1
- package/out/recipes/unit/sources.d.ts +28 -0
- package/out/recipes/unit/sources.d.ts.map +1 -0
- package/out/recipes/unit/sources.js +30 -0
- package/out/recipes/unit/sources.js.map +1 -0
- package/out/recipes/unit.d.ts +30 -17
- package/out/recipes/unit.d.ts.map +1 -1
- package/out/recipes/unit.js +90 -79
- package/out/recipes/unit.js.map +1 -1
- package/out/recipes.d.ts +26 -0
- package/out/recipes.d.ts.map +1 -0
- package/out/recipes.js +100 -0
- package/out/recipes.js.map +1 -0
- package/out/registers.d.ts +277 -0
- package/out/registers.d.ts.map +1 -0
- package/out/registers.js +273 -0
- package/out/registers.js.map +1 -0
- package/out/ro/adapters/retea-scolara/adapter.d.ts +114 -0
- package/out/ro/adapters/retea-scolara/adapter.d.ts.map +1 -0
- package/out/ro/adapters/retea-scolara/adapter.js +209 -0
- package/out/ro/adapters/retea-scolara/adapter.js.map +1 -0
- package/out/ro/tools/fetch/retea-scolara.d.ts +69 -0
- package/out/ro/tools/fetch/retea-scolara.d.ts.map +1 -0
- package/out/ro/tools/fetch/retea-scolara.js +117 -0
- package/out/ro/tools/fetch/retea-scolara.js.map +1 -0
- package/out/runner.d.ts +120 -60
- package/out/runner.d.ts.map +1 -1
- package/out/runner.js +130 -56
- package/out/runner.js.map +1 -1
- package/out/sg/recipes/register.d.ts +55 -0
- package/out/sg/recipes/register.d.ts.map +1 -0
- package/out/sg/recipes/register.js +206 -0
- package/out/sg/recipes/register.js.map +1 -0
- package/out/sg/tools/fetch/acra.d.ts +20 -0
- package/out/sg/tools/fetch/acra.d.ts.map +1 -0
- package/out/sg/tools/fetch/acra.js +123 -0
- package/out/sg/tools/fetch/acra.js.map +1 -0
- package/out/si/recipes/bare-village.d.ts +31 -0
- package/out/si/recipes/bare-village.d.ts.map +1 -0
- package/out/si/recipes/bare-village.js +103 -0
- package/out/si/recipes/bare-village.js.map +1 -0
- package/out/sk/adapters/inspire/adapter.d.ts +119 -0
- package/out/sk/adapters/inspire/adapter.d.ts.map +1 -0
- package/out/sk/adapters/inspire/adapter.js +318 -0
- package/out/sk/adapters/inspire/adapter.js.map +1 -0
- package/out/sk/tools/fetch/inspire.d.ts +195 -0
- package/out/sk/tools/fetch/inspire.d.ts.map +1 -0
- package/out/sk/tools/fetch/inspire.js +280 -0
- package/out/sk/tools/fetch/inspire.js.map +1 -0
- package/out/source-register/effective-manifest.d.ts +355 -0
- package/out/source-register/effective-manifest.d.ts.map +1 -0
- package/out/source-register/effective-manifest.js +355 -0
- package/out/source-register/effective-manifest.js.map +1 -0
- package/out/source-register/register.d.ts +79 -0
- package/out/source-register/register.d.ts.map +1 -0
- package/out/source-register/register.js +400 -0
- package/out/source-register/register.js.map +1 -0
- package/out/source-register/training-manifest.d.ts +111 -0
- package/out/source-register/training-manifest.d.ts.map +1 -0
- package/out/source-register/training-manifest.js +120 -0
- package/out/source-register/training-manifest.js.map +1 -0
- package/out/source-register/types.d.ts +539 -0
- package/out/source-register/types.d.ts.map +1 -0
- package/out/source-register/types.js +263 -0
- package/out/source-register/types.js.map +1 -0
- package/out/source-register.d.ts +19 -0
- package/out/source-register.d.ts.map +1 -0
- package/out/source-register.js +16 -0
- package/out/source-register.js.map +1 -0
- package/out/south-asia/recipes/register.d.ts +54 -0
- package/out/south-asia/recipes/register.d.ts.map +1 -0
- package/out/south-asia/recipes/register.js +174 -0
- package/out/south-asia/recipes/register.js.map +1 -0
- package/out/subvenue/harvest.d.ts +117 -0
- package/out/subvenue/harvest.d.ts.map +1 -0
- package/out/subvenue/harvest.js +172 -0
- package/out/subvenue/harvest.js.map +1 -0
- package/out/subvenue/promotions.d.ts +65 -0
- package/out/subvenue/promotions.d.ts.map +1 -0
- package/out/subvenue/promotions.js +226 -0
- package/out/subvenue/promotions.js.map +1 -0
- package/out/subvenue/surfaces.d.ts +39 -0
- package/out/subvenue/surfaces.d.ts.map +1 -0
- package/out/subvenue/surfaces.js +75 -0
- package/out/subvenue/surfaces.js.map +1 -0
- package/out/subvenue/table.d.ts +212 -0
- package/out/subvenue/table.d.ts.map +1 -0
- package/out/subvenue/table.js +94 -0
- package/out/subvenue/table.js.map +1 -0
- package/out/surfaces/locale.d.ts +113 -0
- package/out/surfaces/locale.d.ts.map +1 -0
- package/out/surfaces/locale.js +136 -0
- package/out/surfaces/locale.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +22 -31
- package/out/synthesizers/anchor-absorption.d.ts.map +1 -1
- package/out/synthesizers/anchor-absorption.js +30 -85
- package/out/synthesizers/anchor-absorption.js.map +1 -1
- package/out/synthesizers/boundary-stress.d.ts +17 -48
- package/out/synthesizers/boundary-stress.d.ts.map +1 -1
- package/out/synthesizers/boundary-stress.js +27 -121
- package/out/synthesizers/boundary-stress.js.map +1 -1
- package/out/synthesizers/house-venue.d.ts +22 -25
- package/out/synthesizers/house-venue.d.ts.map +1 -1
- package/out/synthesizers/house-venue.js +28 -97
- package/out/synthesizers/house-venue.js.map +1 -1
- package/out/synthesizers/intersection.d.ts +10 -8
- package/out/synthesizers/intersection.d.ts.map +1 -1
- package/out/synthesizers/intersection.js +33 -26
- package/out/synthesizers/intersection.js.map +1 -1
- package/out/synthesizers/no-street.d.ts +7 -37
- package/out/synthesizers/no-street.d.ts.map +1 -1
- package/out/synthesizers/no-street.js +55 -111
- package/out/synthesizers/no-street.js.map +1 -1
- package/out/synthesizers/po-box.d.ts +46 -45
- package/out/synthesizers/po-box.d.ts.map +1 -1
- package/out/synthesizers/po-box.js +57 -97
- package/out/synthesizers/po-box.js.map +1 -1
- package/out/synthesizers/street.d.ts +18 -12
- package/out/synthesizers/street.d.ts.map +1 -1
- package/out/synthesizers/street.js +37 -30
- package/out/synthesizers/street.js.map +1 -1
- package/out/synthesizers/utils.d.ts +32 -129
- package/out/synthesizers/utils.d.ts.map +1 -1
- package/out/synthesizers/utils.js +54 -166
- package/out/synthesizers/utils.js.map +1 -1
- package/out/test-kit/corpus-recipe.d.ts +29 -23
- package/out/test-kit/corpus-recipe.d.ts.map +1 -1
- package/out/test-kit/corpus-recipe.js +28 -13
- package/out/test-kit/corpus-recipe.js.map +1 -1
- package/out/test-kit.d.ts +63 -0
- package/out/test-kit.d.ts.map +1 -0
- package/out/test-kit.js +88 -0
- package/out/test-kit.js.map +1 -0
- package/out/tools/align-canonical.d.ts +7 -0
- package/out/tools/align-canonical.d.ts.map +1 -0
- package/out/tools/align-canonical.js +52 -0
- package/out/tools/align-canonical.js.map +1 -0
- package/out/tools/audit.d.ts +18 -11
- package/out/tools/audit.d.ts.map +1 -1
- package/out/tools/audit.js +87 -95
- package/out/tools/audit.js.map +1 -1
- package/out/tools/corpus-stats.d.ts +24 -15
- package/out/tools/corpus-stats.d.ts.map +1 -1
- package/out/tools/corpus-stats.js +35 -31
- package/out/tools/corpus-stats.js.map +1 -1
- package/out/tools/fetch/atom.d.ts +115 -0
- package/out/tools/fetch/atom.d.ts.map +1 -0
- package/out/tools/fetch/atom.js +84 -0
- package/out/tools/fetch/atom.js.map +1 -0
- package/out/tools/fetch/cordis.d.ts +123 -0
- package/out/tools/fetch/cordis.d.ts.map +1 -0
- package/out/tools/fetch/cordis.js +208 -0
- package/out/tools/fetch/cordis.js.map +1 -0
- package/out/tools/fetch/download/manifest.d.ts +56 -0
- package/out/tools/fetch/download/manifest.d.ts.map +1 -0
- package/out/tools/fetch/download/manifest.js +81 -0
- package/out/tools/fetch/download/manifest.js.map +1 -0
- package/out/tools/fetch/download/network.d.ts +126 -0
- package/out/tools/fetch/download/network.d.ts.map +1 -0
- package/out/tools/fetch/download/network.js +140 -0
- package/out/tools/fetch/download/network.js.map +1 -0
- package/out/tools/fetch/download/retry.d.ts +46 -0
- package/out/tools/fetch/download/retry.d.ts.map +1 -0
- package/out/tools/fetch/download/retry.js +136 -0
- package/out/tools/fetch/download/retry.js.map +1 -0
- package/out/tools/fetch/download.d.ts +4 -176
- package/out/tools/fetch/download.d.ts.map +1 -1
- package/out/tools/fetch/download.js +4 -312
- package/out/tools/fetch/download.js.map +1 -1
- package/out/tools/fetch/geonames/dump.d.ts +109 -0
- package/out/tools/fetch/geonames/dump.d.ts.map +1 -0
- package/out/tools/fetch/geonames/dump.js +181 -0
- package/out/tools/fetch/geonames/dump.js.map +1 -0
- package/out/tools/fetch/geonames/postal.d.ts +41 -0
- package/out/tools/fetch/geonames/postal.d.ts.map +1 -0
- package/out/tools/fetch/geonames/postal.js +87 -0
- package/out/tools/fetch/geonames/postal.js.map +1 -0
- package/out/tools/fetch/gleif.d.ts +137 -0
- package/out/tools/fetch/gleif.d.ts.map +1 -0
- package/out/tools/fetch/gleif.js +220 -0
- package/out/tools/fetch/gleif.js.map +1 -0
- package/out/tools/fetch/header.d.ts +41 -0
- package/out/tools/fetch/header.d.ts.map +1 -0
- package/out/tools/fetch/header.js +59 -0
- package/out/tools/fetch/header.js.map +1 -0
- package/out/tools/fetch/inspire-addresses.d.ts +249 -0
- package/out/tools/fetch/inspire-addresses.d.ts.map +1 -0
- package/out/tools/fetch/inspire-addresses.js +276 -0
- package/out/tools/fetch/inspire-addresses.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +0 -3
- package/out/tools/fetch/openaddresses.d.ts.map +1 -1
- package/out/tools/fetch/openaddresses.js +18 -97
- package/out/tools/fetch/openaddresses.js.map +1 -1
- package/out/tools/fetch/ourairports.d.ts +5 -32
- package/out/tools/fetch/ourairports.d.ts.map +1 -1
- package/out/tools/fetch/ourairports.js +13 -46
- package/out/tools/fetch/ourairports.js.map +1 -1
- package/out/tools/fetch/ppd.d.ts +4 -3
- package/out/tools/fetch/ppd.d.ts.map +1 -1
- package/out/tools/fetch/ppd.js +10 -9
- package/out/tools/fetch/ppd.js.map +1 -1
- package/out/tools/fetch/vlaanderen-ad.d.ts +131 -0
- package/out/tools/fetch/vlaanderen-ad.d.ts.map +1 -0
- package/out/tools/fetch/vlaanderen-ad.js +293 -0
- package/out/tools/fetch/vlaanderen-ad.js.map +1 -0
- package/out/tools/fetch/wfs-harvest.d.ts +410 -0
- package/out/tools/fetch/wfs-harvest.d.ts.map +1 -0
- package/out/tools/fetch/wfs-harvest.js +522 -0
- package/out/tools/fetch/wfs-harvest.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +31 -99
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -1
- package/out/tools/fetch/wikidata-subvenue.js +26 -121
- package/out/tools/fetch/wikidata-subvenue.js.map +1 -1
- package/out/tools/fetch/zip-archive.d.ts +54 -0
- package/out/tools/fetch/zip-archive.d.ts.map +1 -0
- package/out/tools/fetch/zip-archive.js +58 -0
- package/out/tools/fetch/zip-archive.js.map +1 -0
- package/out/tools/fetch.d.ts +140 -0
- package/out/tools/fetch.d.ts.map +1 -0
- package/out/tools/fetch.js +136 -0
- package/out/tools/fetch.js.map +1 -0
- package/out/tools/golden/expand.d.ts +105 -0
- package/out/tools/golden/expand.d.ts.map +1 -0
- package/out/tools/golden/expand.js +420 -0
- package/out/tools/golden/expand.js.map +1 -0
- package/out/tools/golden/promote.d.ts +77 -0
- package/out/tools/golden/promote.d.ts.map +1 -0
- package/out/tools/golden/promote.js +248 -0
- package/out/tools/golden/promote.js.map +1 -0
- package/out/tools/golden/relabel-street/directory.d.ts +98 -0
- package/out/tools/golden/relabel-street/directory.d.ts.map +1 -0
- package/out/tools/golden/relabel-street/directory.js +227 -0
- package/out/tools/golden/relabel-street/directory.js.map +1 -0
- package/out/tools/golden/relabel-street/row.d.ts +69 -0
- package/out/tools/golden/relabel-street/row.d.ts.map +1 -0
- package/out/tools/golden/relabel-street/row.js +174 -0
- package/out/tools/golden/relabel-street/row.js.map +1 -0
- package/out/tools/golden/relabel-street.d.ts +9 -0
- package/out/tools/golden/relabel-street.d.ts.map +1 -0
- package/out/tools/golden/relabel-street.js +9 -0
- package/out/tools/golden/relabel-street.js.map +1 -0
- package/out/tools/ingest-csv.d.ts +19 -15
- package/out/tools/ingest-csv.d.ts.map +1 -1
- package/out/tools/ingest-csv.js +39 -45
- package/out/tools/ingest-csv.js.map +1 -1
- package/out/tools/jsonl-to-parquet.d.ts +15 -28
- package/out/tools/jsonl-to-parquet.d.ts.map +1 -1
- package/out/tools/jsonl-to-parquet.js +49 -91
- package/out/tools/jsonl-to-parquet.js.map +1 -1
- package/out/tools/lint/recipe-output/vocab.d.ts +77 -0
- package/out/tools/lint/recipe-output/vocab.d.ts.map +1 -0
- package/out/tools/lint/recipe-output/vocab.js +239 -0
- package/out/tools/lint/recipe-output/vocab.js.map +1 -0
- package/out/tools/lint/recipe-output.d.ts +73 -0
- package/out/tools/lint/recipe-output.d.ts.map +1 -0
- package/out/tools/lint/recipe-output.js +302 -0
- package/out/tools/lint/recipe-output.js.map +1 -0
- package/out/tools/migrate/overlay-parquet.d.ts +30 -0
- package/out/tools/migrate/overlay-parquet.d.ts.map +1 -0
- package/out/tools/migrate/overlay-parquet.js +141 -0
- package/out/tools/migrate/overlay-parquet.js.map +1 -0
- package/out/tools/migrate/recipe-output.d.ts +35 -0
- package/out/tools/migrate/recipe-output.d.ts.map +1 -0
- package/out/tools/migrate/recipe-output.js +124 -0
- package/out/tools/migrate/recipe-output.js.map +1 -0
- package/out/tools/migrate/source-names.d.ts +52 -0
- package/out/tools/migrate/source-names.d.ts.map +1 -0
- package/out/tools/migrate/source-names.js +105 -0
- package/out/tools/migrate/source-names.js.map +1 -0
- package/out/tools/overlay/kryptonite.d.ts +33 -0
- package/out/tools/overlay/kryptonite.d.ts.map +1 -0
- package/out/tools/overlay/kryptonite.js +108 -0
- package/out/tools/overlay/kryptonite.js.map +1 -0
- package/out/tools/overlay/manifest.d.ts +142 -0
- package/out/tools/overlay/manifest.d.ts.map +1 -0
- package/out/tools/overlay/manifest.js +260 -0
- package/out/tools/overlay/manifest.js.map +1 -0
- package/out/tools/overlay/merge-source.d.ts +73 -0
- package/out/tools/overlay/merge-source.d.ts.map +1 -0
- package/out/tools/overlay/merge-source.js +63 -0
- package/out/tools/overlay/merge-source.js.map +1 -0
- package/out/tools/overlay/split-slice.d.ts +66 -0
- package/out/tools/overlay/split-slice.d.ts.map +1 -0
- package/out/tools/overlay/split-slice.js +78 -0
- package/out/tools/overlay/split-slice.js.map +1 -0
- package/out/tools/overlay/translit.d.ts +54 -0
- package/out/tools/overlay/translit.d.ts.map +1 -0
- package/out/tools/overlay/translit.js +177 -0
- package/out/tools/overlay/translit.js.map +1 -0
- package/out/tools/overture-subvenue.d.ts +17 -76
- package/out/tools/overture-subvenue.d.ts.map +1 -1
- package/out/tools/overture-subvenue.js +7 -74
- package/out/tools/overture-subvenue.js.map +1 -1
- package/out/tools/postcode-triples.d.ts +96 -109
- package/out/tools/postcode-triples.d.ts.map +1 -1
- package/out/tools/postcode-triples.js +237 -152
- package/out/tools/postcode-triples.js.map +1 -1
- package/out/tools/source-register/build.d.ts +145 -0
- package/out/tools/source-register/build.d.ts.map +1 -0
- package/out/tools/source-register/build.js +515 -0
- package/out/tools/source-register/build.js.map +1 -0
- package/out/tools/sub/venue/head-nouns.d.ts +21 -0
- package/out/tools/sub/venue/head-nouns.d.ts.map +1 -0
- package/out/tools/sub/venue/head-nouns.js +176 -0
- package/out/tools/sub/venue/head-nouns.js.map +1 -0
- package/out/tools/sub/venue/lexicon.d.ts +129 -0
- package/out/tools/sub/venue/lexicon.d.ts.map +1 -0
- package/out/tools/sub/venue/lexicon.js +239 -0
- package/out/tools/sub/venue/lexicon.js.map +1 -0
- package/out/tools/sub/venue/wikidata.d.ts +28 -0
- package/out/tools/sub/venue/wikidata.d.ts.map +1 -0
- package/out/tools/sub/venue/wikidata.js +65 -0
- package/out/tools/sub/venue/wikidata.js.map +1 -0
- package/out/tools.d.ts +31 -0
- package/out/tools.d.ts.map +1 -0
- package/out/tools.js +31 -0
- package/out/tools.js.map +1 -0
- package/out/tw/tools/fetch/gcis.d.ts +29 -0
- package/out/tw/tools/fetch/gcis.d.ts.map +1 -0
- package/out/tw/tools/fetch/gcis.js +141 -0
- package/out/tw/tools/fetch/gcis.js.map +1 -0
- package/out/types.d.ts +270 -101
- package/out/types.d.ts.map +1 -1
- package/out/types.js +133 -9
- package/out/types.js.map +1 -1
- package/out/us/adapters/fcc-bdc/adapter.d.ts +50 -0
- package/out/us/adapters/fcc-bdc/adapter.d.ts.map +1 -0
- package/out/us/adapters/fcc-bdc/adapter.js +129 -0
- package/out/us/adapters/fcc-bdc/adapter.js.map +1 -0
- package/out/us/adapters/state/hi-schools/adapter.d.ts +47 -0
- package/out/us/adapters/state/hi-schools/adapter.d.ts.map +1 -0
- package/out/us/adapters/state/hi-schools/adapter.js +146 -0
- package/out/us/adapters/state/hi-schools/adapter.js.map +1 -0
- package/out/us/adapters/state/hi-schools/workbook.d.ts +34 -0
- package/out/us/adapters/state/hi-schools/workbook.d.ts.map +1 -0
- package/out/us/adapters/state/hi-schools/workbook.js +22 -0
- package/out/us/adapters/state/hi-schools/workbook.js.map +1 -0
- package/out/us/adapters/state/ia-contractors/adapter.d.ts +41 -0
- package/out/us/adapters/state/ia-contractors/adapter.d.ts.map +1 -0
- package/out/us/adapters/state/ia-contractors/adapter.js +117 -0
- package/out/us/adapters/state/ia-contractors/adapter.js.map +1 -0
- package/out/us/adapters/state/ny-notaries/adapter.d.ts +33 -0
- package/out/us/adapters/state/ny-notaries/adapter.d.ts.map +1 -0
- package/out/us/adapters/state/ny-notaries/adapter.js +114 -0
- package/out/us/adapters/state/ny-notaries/adapter.js.map +1 -0
- package/out/us/adapters/state/tx-notaries/adapter.d.ts +34 -0
- package/out/us/adapters/state/tx-notaries/adapter.d.ts.map +1 -0
- package/out/us/adapters/state/tx-notaries/adapter.js +125 -0
- package/out/us/adapters/state/tx-notaries/adapter.js.map +1 -0
- package/out/us/adapters/tiger/adapter.d.ts +31 -0
- package/out/us/adapters/tiger/adapter.d.ts.map +1 -0
- package/out/us/adapters/tiger/adapter.js +173 -0
- package/out/us/adapters/tiger/adapter.js.map +1 -0
- package/out/us/adapters/tiger/street-decompose.d.ts +23 -0
- package/out/us/adapters/tiger/street-decompose.d.ts.map +1 -0
- package/out/us/adapters/tiger/street-decompose.js +58 -0
- package/out/us/adapters/tiger/street-decompose.js.map +1 -0
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts +62 -0
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.js +133 -0
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.js.map +1 -0
- package/out/us/adapters/usgov/imls-pls/adapter.d.ts +37 -0
- package/out/us/adapters/usgov/imls-pls/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/imls-pls/adapter.js +113 -0
- package/out/us/adapters/usgov/imls-pls/adapter.js.map +1 -0
- package/out/us/adapters/usgov/irs-bmf/adapter.d.ts +38 -0
- package/out/us/adapters/usgov/irs-bmf/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/irs-bmf/adapter.js +126 -0
- package/out/us/adapters/usgov/irs-bmf/adapter.js.map +1 -0
- package/out/us/adapters/usgov/nad/adapter.d.ts +28 -0
- package/out/us/adapters/usgov/nad/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/nad/adapter.js +185 -0
- package/out/us/adapters/usgov/nad/adapter.js.map +1 -0
- package/out/us/adapters/usgov/nppes/adapter.d.ts +29 -0
- package/out/us/adapters/usgov/nppes/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/nppes/adapter.js +140 -0
- package/out/us/adapters/usgov/nppes/adapter.js.map +1 -0
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts +47 -0
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js +153 -0
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js.map +1 -0
- package/out/us/fips-state.d.ts +50 -0
- package/out/us/fips-state.d.ts.map +1 -0
- package/out/us/fips-state.js +109 -0
- package/out/us/fips-state.js.map +1 -0
- package/out/us/tools/fetch/hrsa.d.ts +18 -0
- package/out/us/tools/fetch/hrsa.d.ts.map +1 -0
- package/out/us/tools/fetch/hrsa.js +45 -0
- package/out/us/tools/fetch/hrsa.js.map +1 -0
- package/out/us/tools/fetch/imls-pls.d.ts +14 -0
- package/out/us/tools/fetch/imls-pls.d.ts.map +1 -0
- package/out/us/tools/fetch/imls-pls.js +91 -0
- package/out/us/tools/fetch/imls-pls.js.map +1 -0
- package/out/us/tools/fetch/nad.d.ts +82 -0
- package/out/us/tools/fetch/nad.d.ts.map +1 -0
- package/out/us/tools/fetch/nad.js +239 -0
- package/out/us/tools/fetch/nad.js.map +1 -0
- package/out/us/tools/fetch/nppes.d.ts +16 -0
- package/out/us/tools/fetch/nppes.d.ts.map +1 -0
- package/out/us/tools/fetch/nppes.js +114 -0
- package/out/us/tools/fetch/nppes.js.map +1 -0
- package/out/us/tools/fetch/state/hi-schools.d.ts +29 -0
- package/out/us/tools/fetch/state/hi-schools.d.ts.map +1 -0
- package/out/us/tools/fetch/state/hi-schools.js +114 -0
- package/out/us/tools/fetch/state/hi-schools.js.map +1 -0
- package/out/us/tools/fetch/state/sources.d.ts +27 -0
- package/out/us/tools/fetch/state/sources.d.ts.map +1 -0
- package/out/us/tools/fetch/state/sources.js +110 -0
- package/out/us/tools/fetch/state/sources.js.map +1 -0
- package/out/us/tools/fetch/tiger-full.d.ts +9 -0
- package/out/us/tools/fetch/tiger-full.d.ts.map +1 -0
- package/out/us/tools/fetch/tiger-full.js +178 -0
- package/out/us/tools/fetch/tiger-full.js.map +1 -0
- package/out/utils/align.d.ts +25 -20
- package/out/utils/align.d.ts.map +1 -1
- package/out/utils/align.js +27 -42
- package/out/utils/align.js.map +1 -1
- package/out/utils/cooccurrence-stats.d.ts +58 -0
- package/out/utils/cooccurrence-stats.d.ts.map +1 -0
- package/out/utils/cooccurrence-stats.js +62 -0
- package/out/utils/cooccurrence-stats.js.map +1 -0
- package/out/utils/golden.d.ts +23 -29
- package/out/utils/golden.d.ts.map +1 -1
- package/out/utils/golden.js +33 -45
- package/out/utils/golden.js.map +1 -1
- package/out/utils/license.d.ts +158 -21
- package/out/utils/license.d.ts.map +1 -1
- package/out/utils/license.js +156 -26
- package/out/utils/license.js.map +1 -1
- package/out/utils/split.d.ts +66 -70
- package/out/utils/split.d.ts.map +1 -1
- package/out/utils/split.js +158 -69
- package/out/utils/split.js.map +1 -1
- package/out/utils/tokenize.d.ts +16 -28
- package/out/utils/tokenize.d.ts.map +1 -1
- package/out/utils/tokenize.js +18 -31
- package/out/utils/tokenize.js.map +1 -1
- package/out/utils/wof-json.d.ts +88 -62
- package/out/utils/wof-json.d.ts.map +1 -1
- package/out/utils/wof-json.js +81 -65
- package/out/utils/wof-json.js.map +1 -1
- package/out/utils.d.ts +13 -0
- package/out/utils.d.ts.map +1 -0
- package/out/utils.js +13 -0
- package/out/utils.js.map +1 -0
- package/out/ve/recipes/reviewed-postcode-tail.d.ts +65 -0
- package/out/ve/recipes/reviewed-postcode-tail.d.ts.map +1 -0
- package/out/ve/recipes/reviewed-postcode-tail.js +146 -0
- package/out/ve/recipes/reviewed-postcode-tail.js.map +1 -0
- package/package.json +46 -330
- package/lib/adapters/ban/adapter.ts +0 -190
- package/lib/adapters/ban/street-decompose.ts +0 -66
- package/lib/adapters/fcc-bdc/adapter.ts +0 -174
- package/lib/adapters/geonames-postal/adapter.ts +0 -122
- package/lib/adapters/gnaf/adapter.ts +0 -149
- package/lib/adapters/gnaf/assemble.ts +0 -225
- package/lib/adapters/index.ts +0 -153
- package/lib/adapters/state-hi-schools/adapter.ts +0 -170
- package/lib/adapters/state-hi-schools/workbook.ts +0 -35
- package/lib/adapters/state-ia-contractors/adapter.ts +0 -144
- package/lib/adapters/state-ny-notaries/adapter.ts +0 -141
- package/lib/adapters/state-tx-notaries/adapter.ts +0 -157
- package/lib/adapters/synth-po-box/adapter.ts +0 -204
- package/lib/adapters/tiger/adapter.ts +0 -252
- package/lib/adapters/tiger/street-decompose.ts +0 -83
- package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +0 -167
- package/lib/adapters/usgov-imls-pls/adapter.ts +0 -143
- package/lib/adapters/usgov-irs-bmf/adapter.ts +0 -151
- package/lib/adapters/usgov-nad/adapter.ts +0 -334
- package/lib/adapters/usgov-nppes/adapter.ts +0 -151
- package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -193
- package/lib/adapters/utils/index.ts +0 -307
- package/lib/adapters/wof-admin-jp/adapter.ts +0 -214
- package/lib/adapters/wof-admin-json/adapter.ts +0 -231
- package/lib/adapters/wof-json-rows.ts +0 -129
- package/lib/adapters/wof-postalcode-json/adapter.ts +0 -176
- package/lib/codex/us-fips-state.ts +0 -113
- package/lib/recipes/bare-country.ts +0 -95
- package/lib/recipes/cn-organizational-units.ts +0 -199
- package/lib/recipes/cz-pcfirst-preposition.ts +0 -112
- package/lib/recipes/fr-admin-split.ts +0 -243
- package/lib/recipes/fr-bare-street.ts +0 -171
- package/lib/recipes/fr-fragment.ts +0 -334
- package/lib/recipes/fr-lieudit.ts +0 -301
- package/lib/recipes/fr-order.ts +0 -246
- package/lib/recipes/german.ts +0 -360
- package/lib/recipes/index.ts +0 -97
- package/lib/recipes/locale.ts +0 -600
- package/lib/recipes/nl-postcode.ts +0 -117
- package/lib/recipes/no-fragment.ts +0 -213
- package/lib/recipes/no-street-led.ts +0 -135
- package/lib/recipes/no-street.ts +0 -91
- package/lib/recipes/po-box-cedex.ts +0 -976
- package/lib/recipes/po-box.ts +0 -124
- package/lib/recipes/reviewed-postcode-tail.ts +0 -190
- package/lib/recipes/si-bare-village.ts +0 -99
- package/lib/recipes/street-affix.ts +0 -805
- package/lib/recipes/street-bare.ts +0 -102
- package/lib/recipes/sub-venue-sources.ts +0 -878
- package/lib/recipes/sub-venue.ts +0 -998
- package/lib/synthesizers/german.ts +0 -260
- package/lib/test-kit/index.ts +0 -100
- package/lib/tools/align-slice.ts +0 -68
- package/lib/tools/fetch/acra-sg.ts +0 -174
- package/lib/tools/fetch/ban.ts +0 -289
- package/lib/tools/fetch/gcis-tw.ts +0 -175
- package/lib/tools/fetch/geonames-dump.ts +0 -257
- package/lib/tools/fetch/geonames-postal.ts +0 -180
- package/lib/tools/fetch/houjin-jp.ts +0 -135
- package/lib/tools/fetch/hrsa.ts +0 -59
- package/lib/tools/fetch/imls-pls.ts +0 -149
- package/lib/tools/fetch/index.ts +0 -174
- package/lib/tools/fetch/juso-kr.ts +0 -165
- package/lib/tools/fetch/localdata-kr.ts +0 -194
- package/lib/tools/fetch/nad.ts +0 -341
- package/lib/tools/fetch/nppes.ts +0 -165
- package/lib/tools/fetch/state-hi-schools.ts +0 -161
- package/lib/tools/fetch/state-sources.ts +0 -146
- package/lib/tools/fetch/tiger-full.ts +0 -308
- package/lib/tools/gb-title-case.ts +0 -69
- package/lib/tools/golden-expand.ts +0 -574
- package/lib/tools/golden-promote.ts +0 -337
- package/lib/tools/golden-relabel-street.ts +0 -686
- package/lib/tools/index.ts +0 -28
- package/lib/tools/lint-slice-vocab.ts +0 -388
- package/lib/tools/lint-slice.ts +0 -496
- package/lib/tools/overlay-manifest.ts +0 -148
- package/lib/tools/slice-kryptonite.ts +0 -137
- package/lib/tools/slice-translit.ts +0 -218
- package/lib/tools/sub-venue/harvest.ts +0 -234
- package/lib/tools/sub-venue/head-nouns.ts +0 -245
- package/lib/tools/sub-venue/surfaces.ts +0 -95
- package/lib/tools/sub-venue/table.ts +0 -281
- package/lib/tools/sub-venue/wikidata.ts +0 -85
- package/lib/tools/sub-venue-lexicon.ts +0 -429
- package/lib/tools/sub-venue-promotions.ts +0 -330
- package/lib/utils/index.ts +0 -14
- package/lib/utils/parquet.ts +0 -582
- package/lib/utils/slice-stats.ts +0 -95
- package/out/adapters/ban/adapter.d.ts +0 -44
- package/out/adapters/ban/adapter.d.ts.map +0 -1
- package/out/adapters/ban/adapter.js +0 -149
- package/out/adapters/ban/adapter.js.map +0 -1
- package/out/adapters/ban/street-decompose.d.ts +0 -28
- package/out/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/adapters/ban/street-decompose.js +0 -51
- package/out/adapters/ban/street-decompose.js.map +0 -1
- package/out/adapters/fcc-bdc/adapter.d.ts +0 -68
- package/out/adapters/fcc-bdc/adapter.d.ts.map +0 -1
- package/out/adapters/fcc-bdc/adapter.js +0 -144
- package/out/adapters/fcc-bdc/adapter.js.map +0 -1
- package/out/adapters/geonames-postal/adapter.d.ts +0 -54
- package/out/adapters/geonames-postal/adapter.d.ts.map +0 -1
- package/out/adapters/geonames-postal/adapter.js +0 -107
- package/out/adapters/geonames-postal/adapter.js.map +0 -1
- package/out/adapters/gnaf/adapter.d.ts +0 -49
- package/out/adapters/gnaf/adapter.d.ts.map +0 -1
- package/out/adapters/gnaf/adapter.js +0 -124
- package/out/adapters/gnaf/adapter.js.map +0 -1
- package/out/adapters/gnaf/assemble.d.ts +0 -65
- package/out/adapters/gnaf/assemble.d.ts.map +0 -1
- package/out/adapters/gnaf/assemble.js +0 -154
- package/out/adapters/gnaf/assemble.js.map +0 -1
- package/out/adapters/index.d.ts +0 -51
- package/out/adapters/index.d.ts.map +0 -1
- package/out/adapters/index.js +0 -95
- package/out/adapters/index.js.map +0 -1
- package/out/adapters/state-hi-schools/adapter.d.ts +0 -46
- package/out/adapters/state-hi-schools/adapter.d.ts.map +0 -1
- package/out/adapters/state-hi-schools/adapter.js +0 -145
- package/out/adapters/state-hi-schools/adapter.js.map +0 -1
- package/out/adapters/state-hi-schools/workbook.d.ts +0 -29
- package/out/adapters/state-hi-schools/workbook.d.ts.map +0 -1
- package/out/adapters/state-hi-schools/workbook.js +0 -20
- package/out/adapters/state-hi-schools/workbook.js.map +0 -1
- package/out/adapters/state-ia-contractors/adapter.d.ts +0 -34
- package/out/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
- package/out/adapters/state-ia-contractors/adapter.js +0 -111
- package/out/adapters/state-ia-contractors/adapter.js.map +0 -1
- package/out/adapters/state-ny-notaries/adapter.d.ts +0 -32
- package/out/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
- package/out/adapters/state-ny-notaries/adapter.js +0 -119
- package/out/adapters/state-ny-notaries/adapter.js.map +0 -1
- package/out/adapters/state-tx-notaries/adapter.d.ts +0 -33
- package/out/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
- package/out/adapters/state-tx-notaries/adapter.js +0 -125
- package/out/adapters/state-tx-notaries/adapter.js.map +0 -1
- package/out/adapters/synth-po-box/adapter.d.ts +0 -67
- package/out/adapters/synth-po-box/adapter.d.ts.map +0 -1
- package/out/adapters/synth-po-box/adapter.js +0 -140
- package/out/adapters/synth-po-box/adapter.js.map +0 -1
- package/out/adapters/tiger/adapter.d.ts +0 -55
- package/out/adapters/tiger/adapter.d.ts.map +0 -1
- package/out/adapters/tiger/adapter.js +0 -201
- package/out/adapters/tiger/adapter.js.map +0 -1
- package/out/adapters/tiger/street-decompose.d.ts +0 -30
- package/out/adapters/tiger/street-decompose.d.ts.map +0 -1
- package/out/adapters/tiger/street-decompose.js +0 -68
- package/out/adapters/tiger/street-decompose.js.map +0 -1
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -56
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-hrsa-fqhc/adapter.js +0 -132
- package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
- package/out/adapters/usgov-imls-pls/adapter.d.ts +0 -36
- package/out/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-imls-pls/adapter.js +0 -114
- package/out/adapters/usgov-imls-pls/adapter.js.map +0 -1
- package/out/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
- package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-irs-bmf/adapter.js +0 -120
- package/out/adapters/usgov-irs-bmf/adapter.js.map +0 -1
- package/out/adapters/usgov-nad/adapter.d.ts +0 -48
- package/out/adapters/usgov-nad/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-nad/adapter.js +0 -249
- package/out/adapters/usgov-nad/adapter.js.map +0 -1
- package/out/adapters/usgov-nppes/adapter.d.ts +0 -39
- package/out/adapters/usgov-nppes/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-nppes/adapter.js +0 -118
- package/out/adapters/usgov-nppes/adapter.js.map +0 -1
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts +0 -46
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -154
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
- package/out/adapters/utils/index.d.ts +0 -191
- package/out/adapters/utils/index.d.ts.map +0 -1
- package/out/adapters/utils/index.js +0 -206
- package/out/adapters/utils/index.js.map +0 -1
- package/out/adapters/wof-admin-jp/adapter.d.ts +0 -65
- package/out/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
- package/out/adapters/wof-admin-jp/adapter.js +0 -161
- package/out/adapters/wof-admin-jp/adapter.js.map +0 -1
- package/out/adapters/wof-admin-json/adapter.d.ts +0 -79
- package/out/adapters/wof-admin-json/adapter.d.ts.map +0 -1
- package/out/adapters/wof-admin-json/adapter.js +0 -197
- package/out/adapters/wof-admin-json/adapter.js.map +0 -1
- package/out/adapters/wof-json-rows.d.ts +0 -62
- package/out/adapters/wof-json-rows.d.ts.map +0 -1
- package/out/adapters/wof-json-rows.js +0 -83
- package/out/adapters/wof-json-rows.js.map +0 -1
- package/out/adapters/wof-postalcode-json/adapter.d.ts +0 -65
- package/out/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
- package/out/adapters/wof-postalcode-json/adapter.js +0 -151
- package/out/adapters/wof-postalcode-json/adapter.js.map +0 -1
- package/out/codex/us-fips-state.d.ts +0 -41
- package/out/codex/us-fips-state.d.ts.map +0 -1
- package/out/codex/us-fips-state.js +0 -100
- package/out/codex/us-fips-state.js.map +0 -1
- package/out/recipes/bare-country.d.ts +0 -25
- package/out/recipes/bare-country.d.ts.map +0 -1
- package/out/recipes/bare-country.js +0 -88
- package/out/recipes/bare-country.js.map +0 -1
- package/out/recipes/cn-organizational-units.d.ts +0 -36
- package/out/recipes/cn-organizational-units.d.ts.map +0 -1
- package/out/recipes/cn-organizational-units.js +0 -159
- package/out/recipes/cn-organizational-units.js.map +0 -1
- package/out/recipes/cz-pcfirst-preposition.d.ts +0 -22
- package/out/recipes/cz-pcfirst-preposition.d.ts.map +0 -1
- package/out/recipes/cz-pcfirst-preposition.js +0 -101
- package/out/recipes/cz-pcfirst-preposition.js.map +0 -1
- package/out/recipes/fr-admin-split.d.ts +0 -38
- package/out/recipes/fr-admin-split.d.ts.map +0 -1
- package/out/recipes/fr-admin-split.js +0 -192
- package/out/recipes/fr-admin-split.js.map +0 -1
- package/out/recipes/fr-bare-street.d.ts +0 -28
- package/out/recipes/fr-bare-street.d.ts.map +0 -1
- package/out/recipes/fr-bare-street.js +0 -144
- package/out/recipes/fr-bare-street.js.map +0 -1
- package/out/recipes/fr-fragment.d.ts +0 -77
- package/out/recipes/fr-fragment.d.ts.map +0 -1
- package/out/recipes/fr-fragment.js +0 -277
- package/out/recipes/fr-fragment.js.map +0 -1
- package/out/recipes/fr-lieudit.d.ts +0 -32
- package/out/recipes/fr-lieudit.d.ts.map +0 -1
- package/out/recipes/fr-lieudit.js +0 -227
- package/out/recipes/fr-lieudit.js.map +0 -1
- package/out/recipes/fr-order.d.ts +0 -38
- package/out/recipes/fr-order.d.ts.map +0 -1
- package/out/recipes/fr-order.js +0 -198
- package/out/recipes/fr-order.js.map +0 -1
- package/out/recipes/german.d.ts +0 -44
- package/out/recipes/german.d.ts.map +0 -1
- package/out/recipes/german.js +0 -289
- package/out/recipes/german.js.map +0 -1
- package/out/recipes/index.d.ts +0 -24
- package/out/recipes/index.d.ts.map +0 -1
- package/out/recipes/index.js +0 -91
- package/out/recipes/index.js.map +0 -1
- package/out/recipes/locale.d.ts +0 -136
- package/out/recipes/locale.d.ts.map +0 -1
- package/out/recipes/locale.js +0 -460
- package/out/recipes/locale.js.map +0 -1
- package/out/recipes/nl-postcode.d.ts +0 -26
- package/out/recipes/nl-postcode.d.ts.map +0 -1
- package/out/recipes/nl-postcode.js +0 -103
- package/out/recipes/nl-postcode.js.map +0 -1
- package/out/recipes/no-fragment.d.ts +0 -43
- package/out/recipes/no-fragment.d.ts.map +0 -1
- package/out/recipes/no-fragment.js +0 -183
- package/out/recipes/no-fragment.js.map +0 -1
- package/out/recipes/no-street-led.d.ts +0 -24
- package/out/recipes/no-street-led.d.ts.map +0 -1
- package/out/recipes/no-street-led.js +0 -114
- package/out/recipes/no-street-led.js.map +0 -1
- package/out/recipes/no-street.d.ts +0 -18
- package/out/recipes/no-street.d.ts.map +0 -1
- package/out/recipes/no-street.js +0 -72
- package/out/recipes/no-street.js.map +0 -1
- package/out/recipes/po-box-cedex.d.ts +0 -38
- package/out/recipes/po-box-cedex.d.ts.map +0 -1
- package/out/recipes/po-box-cedex.js +0 -768
- package/out/recipes/po-box-cedex.js.map +0 -1
- package/out/recipes/po-box.d.ts +0 -17
- package/out/recipes/po-box.d.ts.map +0 -1
- package/out/recipes/po-box.js +0 -101
- package/out/recipes/po-box.js.map +0 -1
- package/out/recipes/reviewed-postcode-tail.d.ts +0 -47
- package/out/recipes/reviewed-postcode-tail.d.ts.map +0 -1
- package/out/recipes/reviewed-postcode-tail.js +0 -125
- package/out/recipes/reviewed-postcode-tail.js.map +0 -1
- package/out/recipes/si-bare-village.d.ts +0 -32
- package/out/recipes/si-bare-village.d.ts.map +0 -1
- package/out/recipes/si-bare-village.js +0 -89
- package/out/recipes/si-bare-village.js.map +0 -1
- package/out/recipes/street-affix.d.ts +0 -89
- package/out/recipes/street-affix.d.ts.map +0 -1
- package/out/recipes/street-affix.js +0 -563
- package/out/recipes/street-affix.js.map +0 -1
- package/out/recipes/street-bare.d.ts +0 -25
- package/out/recipes/street-bare.d.ts.map +0 -1
- package/out/recipes/street-bare.js +0 -87
- package/out/recipes/street-bare.js.map +0 -1
- package/out/recipes/sub-venue-sources.d.ts +0 -229
- package/out/recipes/sub-venue-sources.d.ts.map +0 -1
- package/out/recipes/sub-venue-sources.js +0 -654
- package/out/recipes/sub-venue-sources.js.map +0 -1
- package/out/recipes/sub-venue.d.ts +0 -269
- package/out/recipes/sub-venue.d.ts.map +0 -1
- package/out/recipes/sub-venue.js +0 -726
- package/out/recipes/sub-venue.js.map +0 -1
- package/out/synthesizers/german.d.ts +0 -115
- package/out/synthesizers/german.d.ts.map +0 -1
- package/out/synthesizers/german.js +0 -149
- package/out/synthesizers/german.js.map +0 -1
- package/out/test-kit/index.d.ts +0 -48
- package/out/test-kit/index.d.ts.map +0 -1
- package/out/test-kit/index.js +0 -78
- package/out/test-kit/index.js.map +0 -1
- package/out/tools/align-slice.d.ts +0 -7
- package/out/tools/align-slice.d.ts.map +0 -1
- package/out/tools/align-slice.js +0 -55
- package/out/tools/align-slice.js.map +0 -1
- package/out/tools/fetch/acra-sg.d.ts +0 -23
- package/out/tools/fetch/acra-sg.d.ts.map +0 -1
- package/out/tools/fetch/acra-sg.js +0 -126
- package/out/tools/fetch/acra-sg.js.map +0 -1
- package/out/tools/fetch/ban.d.ts +0 -31
- package/out/tools/fetch/ban.d.ts.map +0 -1
- package/out/tools/fetch/ban.js +0 -239
- package/out/tools/fetch/ban.js.map +0 -1
- package/out/tools/fetch/gcis-tw.d.ts +0 -23
- package/out/tools/fetch/gcis-tw.d.ts.map +0 -1
- package/out/tools/fetch/gcis-tw.js +0 -135
- package/out/tools/fetch/gcis-tw.js.map +0 -1
- package/out/tools/fetch/geonames-dump.d.ts +0 -91
- package/out/tools/fetch/geonames-dump.d.ts.map +0 -1
- package/out/tools/fetch/geonames-dump.js +0 -171
- package/out/tools/fetch/geonames-dump.js.map +0 -1
- package/out/tools/fetch/geonames-postal.d.ts +0 -76
- package/out/tools/fetch/geonames-postal.d.ts.map +0 -1
- package/out/tools/fetch/geonames-postal.js +0 -126
- package/out/tools/fetch/geonames-postal.js.map +0 -1
- package/out/tools/fetch/houjin-jp.d.ts +0 -24
- package/out/tools/fetch/houjin-jp.d.ts.map +0 -1
- package/out/tools/fetch/houjin-jp.js +0 -102
- package/out/tools/fetch/houjin-jp.js.map +0 -1
- package/out/tools/fetch/hrsa.d.ts +0 -18
- package/out/tools/fetch/hrsa.d.ts.map +0 -1
- package/out/tools/fetch/hrsa.js +0 -46
- package/out/tools/fetch/hrsa.js.map +0 -1
- package/out/tools/fetch/imls-pls.d.ts +0 -25
- package/out/tools/fetch/imls-pls.d.ts.map +0 -1
- package/out/tools/fetch/imls-pls.js +0 -108
- package/out/tools/fetch/imls-pls.js.map +0 -1
- package/out/tools/fetch/index.d.ts +0 -171
- package/out/tools/fetch/index.d.ts.map +0 -1
- package/out/tools/fetch/index.js +0 -170
- package/out/tools/fetch/index.js.map +0 -1
- package/out/tools/fetch/juso-kr.d.ts +0 -30
- package/out/tools/fetch/juso-kr.d.ts.map +0 -1
- package/out/tools/fetch/juso-kr.js +0 -120
- package/out/tools/fetch/juso-kr.js.map +0 -1
- package/out/tools/fetch/localdata-kr.d.ts +0 -30
- package/out/tools/fetch/localdata-kr.d.ts.map +0 -1
- package/out/tools/fetch/localdata-kr.js +0 -139
- package/out/tools/fetch/localdata-kr.js.map +0 -1
- package/out/tools/fetch/nad.d.ts +0 -70
- package/out/tools/fetch/nad.d.ts.map +0 -1
- package/out/tools/fetch/nad.js +0 -234
- package/out/tools/fetch/nad.js.map +0 -1
- package/out/tools/fetch/nppes.d.ts +0 -26
- package/out/tools/fetch/nppes.d.ts.map +0 -1
- package/out/tools/fetch/nppes.js +0 -126
- package/out/tools/fetch/nppes.js.map +0 -1
- package/out/tools/fetch/state-hi-schools.d.ts +0 -26
- package/out/tools/fetch/state-hi-schools.d.ts.map +0 -1
- package/out/tools/fetch/state-hi-schools.js +0 -112
- package/out/tools/fetch/state-hi-schools.js.map +0 -1
- package/out/tools/fetch/state-sources.d.ts +0 -26
- package/out/tools/fetch/state-sources.d.ts.map +0 -1
- package/out/tools/fetch/state-sources.js +0 -111
- package/out/tools/fetch/state-sources.js.map +0 -1
- package/out/tools/fetch/tiger-full.d.ts +0 -22
- package/out/tools/fetch/tiger-full.d.ts.map +0 -1
- package/out/tools/fetch/tiger-full.js +0 -217
- package/out/tools/fetch/tiger-full.js.map +0 -1
- package/out/tools/gb-title-case.d.ts +0 -2
- package/out/tools/gb-title-case.d.ts.map +0 -1
- package/out/tools/gb-title-case.js +0 -65
- package/out/tools/gb-title-case.js.map +0 -1
- package/out/tools/golden-expand.d.ts +0 -90
- package/out/tools/golden-expand.d.ts.map +0 -1
- package/out/tools/golden-expand.js +0 -406
- package/out/tools/golden-expand.js.map +0 -1
- package/out/tools/golden-promote.d.ts +0 -72
- package/out/tools/golden-promote.d.ts.map +0 -1
- package/out/tools/golden-promote.js +0 -240
- package/out/tools/golden-promote.js.map +0 -1
- package/out/tools/golden-relabel-street.d.ts +0 -196
- package/out/tools/golden-relabel-street.d.ts.map +0 -1
- package/out/tools/golden-relabel-street.js +0 -439
- package/out/tools/golden-relabel-street.js.map +0 -1
- package/out/tools/index.d.ts +0 -28
- package/out/tools/index.d.ts.map +0 -1
- package/out/tools/index.js +0 -28
- package/out/tools/index.js.map +0 -1
- package/out/tools/lint-slice-vocab.d.ts +0 -90
- package/out/tools/lint-slice-vocab.d.ts.map +0 -1
- package/out/tools/lint-slice-vocab.js +0 -267
- package/out/tools/lint-slice-vocab.js.map +0 -1
- package/out/tools/lint-slice.d.ts +0 -93
- package/out/tools/lint-slice.d.ts.map +0 -1
- package/out/tools/lint-slice.js +0 -322
- package/out/tools/lint-slice.js.map +0 -1
- package/out/tools/overlay-manifest.d.ts +0 -39
- package/out/tools/overlay-manifest.d.ts.map +0 -1
- package/out/tools/overlay-manifest.js +0 -90
- package/out/tools/overlay-manifest.js.map +0 -1
- package/out/tools/slice-kryptonite.d.ts +0 -32
- package/out/tools/slice-kryptonite.d.ts.map +0 -1
- package/out/tools/slice-kryptonite.js +0 -99
- package/out/tools/slice-kryptonite.js.map +0 -1
- package/out/tools/slice-translit.d.ts +0 -51
- package/out/tools/slice-translit.d.ts.map +0 -1
- package/out/tools/slice-translit.js +0 -166
- package/out/tools/slice-translit.js.map +0 -1
- package/out/tools/sub-venue/harvest.d.ts +0 -100
- package/out/tools/sub-venue/harvest.d.ts.map +0 -1
- package/out/tools/sub-venue/harvest.js +0 -168
- package/out/tools/sub-venue/harvest.js.map +0 -1
- package/out/tools/sub-venue/head-nouns.d.ts +0 -50
- package/out/tools/sub-venue/head-nouns.d.ts.map +0 -1
- package/out/tools/sub-venue/head-nouns.js +0 -213
- package/out/tools/sub-venue/head-nouns.js.map +0 -1
- package/out/tools/sub-venue/surfaces.d.ts +0 -45
- package/out/tools/sub-venue/surfaces.d.ts.map +0 -1
- package/out/tools/sub-venue/surfaces.js +0 -77
- package/out/tools/sub-venue/surfaces.js.map +0 -1
- package/out/tools/sub-venue/table.d.ts +0 -229
- package/out/tools/sub-venue/table.d.ts.map +0 -1
- package/out/tools/sub-venue/table.js +0 -108
- package/out/tools/sub-venue/table.js.map +0 -1
- package/out/tools/sub-venue/wikidata.d.ts +0 -26
- package/out/tools/sub-venue/wikidata.d.ts.map +0 -1
- package/out/tools/sub-venue/wikidata.js +0 -62
- package/out/tools/sub-venue/wikidata.js.map +0 -1
- package/out/tools/sub-venue-lexicon.d.ts +0 -156
- package/out/tools/sub-venue-lexicon.d.ts.map +0 -1
- package/out/tools/sub-venue-lexicon.js +0 -283
- package/out/tools/sub-venue-lexicon.js.map +0 -1
- package/out/tools/sub-venue-promotions.d.ts +0 -94
- package/out/tools/sub-venue-promotions.d.ts.map +0 -1
- package/out/tools/sub-venue-promotions.js +0 -266
- package/out/tools/sub-venue-promotions.js.map +0 -1
- package/out/utils/index.d.ts +0 -14
- package/out/utils/index.d.ts.map +0 -1
- package/out/utils/index.js +0 -14
- package/out/utils/index.js.map +0 -1
- package/out/utils/parquet.d.ts +0 -178
- package/out/utils/parquet.d.ts.map +0 -1
- package/out/utils/parquet.js +0 -371
- package/out/utils/parquet.js.map +0 -1
- package/out/utils/slice-stats.d.ts +0 -52
- package/out/utils/slice-stats.d.ts.map +0 -1
- package/out/utils/slice-stats.js +0 -58
- package/out/utils/slice-stats.js.map +0 -1
package/out/build.d.ts
CHANGED
|
@@ -2,131 +2,16 @@
|
|
|
2
2
|
* @copyright Sister Software
|
|
3
3
|
* @license AGPL-3.0
|
|
4
4
|
* @author Teffen Ellis, et al.
|
|
5
|
+
* @file The corpus build, as the four phases it runs in order: adapters, align, split, parquet.
|
|
5
6
|
*
|
|
6
|
-
*
|
|
7
|
-
*
|
|
8
|
-
* `buildCorpus(opts)` orchestrates every stage of the pipeline:
|
|
9
|
-
*
|
|
10
|
-
* 1. **Adapter runs** — drives every adapter in turn (via `runAdapter`), writing
|
|
11
|
-
* `<intermediate>/<adapter.id>/canonical.jsonl` slices.
|
|
12
|
-
* 2. **Synthesis** — optional. For each canonical row, every applicable augmentation in the row's
|
|
13
|
-
* country-default policy emits an augmented row alongside the original.
|
|
14
|
-
* 3. **Alignment** — every row (original + augmented) is aligned via `alignRow`. Successes go to
|
|
15
|
-
* `labeled.jsonl`; quarantines are appended to `quarantine.jsonl` with reasons.
|
|
16
|
-
* 4. **Splits** — `splitRows` partitions labeled `source_id`s into train/val/test by locality holdout.
|
|
17
|
-
* Manifest written to `splits/SPLIT_MANIFEST.json` + per-split `train.txt` / `val.txt` /
|
|
18
|
-
* `test.txt`.
|
|
19
|
-
* 5. **Parquet slices** — `writeSlices` streams labeled rows into 1M-row `.parquet` slices per split
|
|
20
|
-
* under `corpus-v<version>/{train,val,test}/part-NNNN.parquet` (SNAPPY-compressed, 50k-row
|
|
21
|
-
* row groups), with per-slice checksums + per-stage manifest in
|
|
22
|
-
* `corpus-v<version>/MANIFEST.json`.
|
|
23
|
-
* 6. **Top-level manifest** — `<outputDir>/MANIFEST.json` ties every per-stage manifest together with
|
|
24
|
-
* a top-level corpus_version, built_at, and aggregate counts.
|
|
25
|
-
*
|
|
26
|
-
* Output layout:
|
|
27
|
-
*
|
|
28
|
-
* ```
|
|
29
|
-
* <outputDir>/
|
|
30
|
-
* MANIFEST.json
|
|
31
|
-
* intermediate/
|
|
32
|
-
* <adapter.id>/canonical.jsonl # one per adapter
|
|
33
|
-
* labeled.jsonl # post-alignment, pre-slice
|
|
34
|
-
* quarantine.jsonl # rows that failed alignment
|
|
35
|
-
* splits/
|
|
36
|
-
* SPLIT_MANIFEST.json
|
|
37
|
-
* train.txt / val.txt / test.txt
|
|
38
|
-
* corpus-v<version>/
|
|
39
|
-
* MANIFEST.json
|
|
40
|
-
* train/part-NNNN.parquet
|
|
41
|
-
* val/part-NNNN.parquet
|
|
42
|
-
* test/part-NNNN.parquet
|
|
43
|
-
* ```
|
|
44
|
-
*
|
|
45
|
-
* The intermediate files live alongside the final slices for reproducibility + debugging. Operators
|
|
46
|
-
* can `rm -rf intermediate/` after the build if disk is tight; the final `corpus-v<version>/` is
|
|
47
|
-
* self-contained.
|
|
48
|
-
*/
|
|
49
|
-
import { type AdapterRunManifest } from "#runner";
|
|
50
|
-
import type { AdapterOptions, CorpusAdapter } from "#types";
|
|
51
|
-
import { type SliceManifest } from "#utils/parquet";
|
|
52
|
-
import { type SplitManifest } from "#utils/split";
|
|
53
|
-
/**
|
|
54
|
-
* Stage tags surfaced to `onProgress`.
|
|
55
|
-
*/
|
|
56
|
-
export type BuildStage = "adapter-run" | "align" | "split" | "slice" | "manifest";
|
|
57
|
-
/**
|
|
58
|
-
* Per-invocation options for `buildCorpus`.
|
|
7
|
+
* Each phase is its own module. This module defines their sequence and shared paths.
|
|
8
|
+
* It assembles the manifest from the phase reports.
|
|
59
9
|
*/
|
|
60
|
-
|
|
61
|
-
|
|
62
|
-
|
|
63
|
-
*/
|
|
64
|
-
outputDir: string;
|
|
65
|
-
/**
|
|
66
|
-
* Corpus version (e.g. `"0.1.0"`). Stamped onto every row + into the output dir name.
|
|
67
|
-
*/
|
|
68
|
-
corpusVersion: string;
|
|
69
|
-
/**
|
|
70
|
-
* Adapters to drive, in order. Defaults to `defaultAdapterRegistry.list()`. Pass an explicit list to filter (e.g.
|
|
71
|
-
* `[wofAdminAdapter]` for a smoke run).
|
|
72
|
-
*/
|
|
73
|
-
adapters?: readonly CorpusAdapter[];
|
|
74
|
-
/**
|
|
75
|
-
* Per-adapter `AdapterOptions` — looked up by adapter id. Adapters whose id is missing from this map are skipped (and
|
|
76
|
-
* noted in the manifest).
|
|
77
|
-
*/
|
|
78
|
-
adapterInputs: Record<string, AdapterOptions>;
|
|
79
|
-
/**
|
|
80
|
-
* Enable synthesis pass. Default `true`. Set `false` for fixture-driven smoke tests.
|
|
81
|
-
*/
|
|
82
|
-
synthesize?: boolean;
|
|
83
|
-
/**
|
|
84
|
-
* Forwarded to `writeSlices`. Default 1_000_000.
|
|
85
|
-
*/
|
|
86
|
-
rowsPerSlice?: number;
|
|
87
|
-
/**
|
|
88
|
-
* Progress hook. Errors thrown abort the build.
|
|
89
|
-
*/
|
|
90
|
-
onProgress?: (stage: BuildStage, message: string) => void;
|
|
91
|
-
/**
|
|
92
|
-
* License kinds to PURPOSELY exclude from this build (#26). Compiled patterns (see `compileLicenseExcludes` /
|
|
93
|
-
* `SHARE_ALIKE_PATTERN` in `license.ts`); a row whose `license` matches any is dropped at ingest. Default (omitted)
|
|
94
|
-
* includes EVERYTHING — exclusion is a deliberate act, not a silent default. A proprietary-weights build passes the
|
|
95
|
-
* share-alike set (`--exclude-share-alike`).
|
|
96
|
-
*/
|
|
97
|
-
excludeLicenses?: readonly RegExp[];
|
|
98
|
-
}
|
|
99
|
-
/**
|
|
100
|
-
* Top-level manifest tying every stage together.
|
|
101
|
-
*/
|
|
102
|
-
export interface BuildCorpusManifest {
|
|
103
|
-
corpus_version: string;
|
|
104
|
-
built_at: string;
|
|
105
|
-
adapters: AdapterRunManifest[];
|
|
106
|
-
skipped_adapters: string[];
|
|
107
|
-
splits: {
|
|
108
|
-
counts: SplitManifest["counts"];
|
|
109
|
-
holdouts: SplitManifest["holdouts"];
|
|
110
|
-
};
|
|
111
|
-
slices: {
|
|
112
|
-
counts: SliceManifest["counts"];
|
|
113
|
-
total_rows: number;
|
|
114
|
-
};
|
|
115
|
-
quarantine_count: number;
|
|
116
|
-
total_aligned_rows: number;
|
|
117
|
-
/**
|
|
118
|
-
* Resolved license set across all INCLUDED rows (license string → row count), + the count dropped by
|
|
119
|
-
* `excludeLicenses` (#26). The model card derives its data-attribution table from `licenses`.
|
|
120
|
-
*/
|
|
121
|
-
licenses: Record<string, number>;
|
|
122
|
-
excluded_by_license: number;
|
|
123
|
-
}
|
|
10
|
+
import { type BuildCorpusManifest, type BuildCorpusOptions } from "#build/types";
|
|
11
|
+
export * from "#build/heap";
|
|
12
|
+
export * from "#build/types";
|
|
124
13
|
/**
|
|
125
14
|
* Drive the full corpus build to completion.
|
|
126
|
-
*
|
|
127
|
-
* Memory profile: the function maintains an in-memory `Map<source_id, SplitName>` to bridge the align → slice hand-off.
|
|
128
|
-
* For Phase 1 fixture-scale runs (≤ 10⁴ rows) this is trivial. For real 5M+ runs, the map fits comfortably in a few
|
|
129
|
-
* hundred MB; the canonical.jsonl and labeled.jsonl payloads stream and never sit in memory.
|
|
130
15
|
*/
|
|
131
16
|
export declare function buildCorpus(opts: BuildCorpusOptions): Promise<BuildCorpusManifest>;
|
|
132
17
|
//# sourceMappingURL=build.d.ts.map
|
package/out/build.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"build.d.ts","sourceRoot":"","sources":["../lib/build.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"build.d.ts","sourceRoot":"","sources":["../lib/build.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAYH,OAAO,EAAwC,KAAK,mBAAmB,EAAE,KAAK,kBAAkB,EAAE,MAAM,cAAc,CAAA;AAUtH,cAAc,aAAa,CAAA;AAC3B,cAAc,cAAc,CAAA;AAE5B;;GAEG;AACH,wBAAsB,WAAW,CAAC,IAAI,EAAE,kBAAkB,GAAG,OAAO,CAAC,mBAAmB,CAAC,CAyJxF"}
|
package/out/build.js
CHANGED
|
@@ -2,244 +2,149 @@
|
|
|
2
2
|
* @copyright Sister Software
|
|
3
3
|
* @license AGPL-3.0
|
|
4
4
|
* @author Teffen Ellis, et al.
|
|
5
|
+
* @file The corpus build, as the four phases it runs in order: adapters, align, split, parquet.
|
|
5
6
|
*
|
|
6
|
-
*
|
|
7
|
-
*
|
|
8
|
-
* `buildCorpus(opts)` orchestrates every stage of the pipeline:
|
|
9
|
-
*
|
|
10
|
-
* 1. **Adapter runs** — drives every adapter in turn (via `runAdapter`), writing
|
|
11
|
-
* `<intermediate>/<adapter.id>/canonical.jsonl` slices.
|
|
12
|
-
* 2. **Synthesis** — optional. For each canonical row, every applicable augmentation in the row's
|
|
13
|
-
* country-default policy emits an augmented row alongside the original.
|
|
14
|
-
* 3. **Alignment** — every row (original + augmented) is aligned via `alignRow`. Successes go to
|
|
15
|
-
* `labeled.jsonl`; quarantines are appended to `quarantine.jsonl` with reasons.
|
|
16
|
-
* 4. **Splits** — `splitRows` partitions labeled `source_id`s into train/val/test by locality holdout.
|
|
17
|
-
* Manifest written to `splits/SPLIT_MANIFEST.json` + per-split `train.txt` / `val.txt` /
|
|
18
|
-
* `test.txt`.
|
|
19
|
-
* 5. **Parquet slices** — `writeSlices` streams labeled rows into 1M-row `.parquet` slices per split
|
|
20
|
-
* under `corpus-v<version>/{train,val,test}/part-NNNN.parquet` (SNAPPY-compressed, 50k-row
|
|
21
|
-
* row groups), with per-slice checksums + per-stage manifest in
|
|
22
|
-
* `corpus-v<version>/MANIFEST.json`.
|
|
23
|
-
* 6. **Top-level manifest** — `<outputDir>/MANIFEST.json` ties every per-stage manifest together with
|
|
24
|
-
* a top-level corpus_version, built_at, and aggregate counts.
|
|
25
|
-
*
|
|
26
|
-
* Output layout:
|
|
27
|
-
*
|
|
28
|
-
* ```
|
|
29
|
-
* <outputDir>/
|
|
30
|
-
* MANIFEST.json
|
|
31
|
-
* intermediate/
|
|
32
|
-
* <adapter.id>/canonical.jsonl # one per adapter
|
|
33
|
-
* labeled.jsonl # post-alignment, pre-slice
|
|
34
|
-
* quarantine.jsonl # rows that failed alignment
|
|
35
|
-
* splits/
|
|
36
|
-
* SPLIT_MANIFEST.json
|
|
37
|
-
* train.txt / val.txt / test.txt
|
|
38
|
-
* corpus-v<version>/
|
|
39
|
-
* MANIFEST.json
|
|
40
|
-
* train/part-NNNN.parquet
|
|
41
|
-
* val/part-NNNN.parquet
|
|
42
|
-
* test/part-NNNN.parquet
|
|
43
|
-
* ```
|
|
44
|
-
*
|
|
45
|
-
* The intermediate files live alongside the final slices for reproducibility + debugging. Operators
|
|
46
|
-
* can `rm -rf intermediate/` after the build if disk is tight; the final `corpus-v<version>/` is
|
|
47
|
-
* self-contained.
|
|
7
|
+
* Each phase is its own module. This module defines their sequence and shared paths.
|
|
8
|
+
* It assembles the manifest from the phase reports.
|
|
48
9
|
*/
|
|
49
|
-
import {
|
|
50
|
-
import {
|
|
51
|
-
import {
|
|
52
|
-
import {
|
|
53
|
-
import {
|
|
54
|
-
import {
|
|
10
|
+
import { makeDirectories, writeLocalJSONFile } from "@mailwoman/core/fs/writers";
|
|
11
|
+
import { mulberry32 as makeMulberry32 } from "@mailwoman/core/utils";
|
|
12
|
+
import { heapLimitBytes } from "@mailwoman/core/utils/system";
|
|
13
|
+
import { PathBuilder } from "path-ts";
|
|
14
|
+
import { defaultAdapterRegistry } from "#adapters/registry";
|
|
15
|
+
import { runAdapterPhase } from "#build/adapters";
|
|
16
|
+
import { runAlignPhase } from "#build/align";
|
|
17
|
+
import { readRegisterDecisions, readSourceEligibility } from "#build/eligibility";
|
|
18
|
+
import { streamJSONL } from "#build/rows";
|
|
19
|
+
import { BuildProfile, TRAINING_MANIFEST_FILE } from "#build/types";
|
|
55
20
|
import { $public } from "#env";
|
|
56
|
-
import {
|
|
57
|
-
import {
|
|
58
|
-
import {
|
|
59
|
-
import {
|
|
60
|
-
import {
|
|
61
|
-
import { defaultHoldouts,
|
|
21
|
+
import { ROWS_PER_FILE } from "#parquet/schema";
|
|
22
|
+
import { DEFAULT_SHUFFLE_SEED, DEFAULT_SHUFFLE_WINDOW, shuffleWithinWindow } from "#parquet/shuffle";
|
|
23
|
+
import { writeParquetSplits } from "#parquet/writers";
|
|
24
|
+
import { freezeTrainingManifest } from "#source-register/training-manifest";
|
|
25
|
+
import { LicensePolicy } from "#utils/license";
|
|
26
|
+
import { defaultHoldouts, writeSplitManifestsFromLabeledFiles } from "#utils/split";
|
|
27
|
+
export * from "#build/heap";
|
|
28
|
+
export * from "#build/types";
|
|
62
29
|
/**
|
|
63
30
|
* Drive the full corpus build to completion.
|
|
64
|
-
*
|
|
65
|
-
* Memory profile: the function maintains an in-memory `Map<source_id, SplitName>` to bridge the align → slice hand-off.
|
|
66
|
-
* For Phase 1 fixture-scale runs (≤ 10⁴ rows) this is trivial. For real 5M+ runs, the map fits comfortably in a few
|
|
67
|
-
* hundred MB; the canonical.jsonl and labeled.jsonl payloads stream and never sit in memory.
|
|
68
31
|
*/
|
|
69
32
|
export async function buildCorpus(opts) {
|
|
70
33
|
const adapters = opts.adapters ?? defaultAdapterRegistry.list();
|
|
71
34
|
const synthesize = opts.synthesize ?? true;
|
|
72
|
-
const
|
|
35
|
+
const rowsPerFile = opts.rowsPerFile ?? ROWS_PER_FILE;
|
|
36
|
+
const shuffleWindow = opts.shuffleWindow ?? DEFAULT_SHUFFLE_WINDOW;
|
|
37
|
+
const shuffleSeed = opts.shuffleSeed ?? DEFAULT_SHUFFLE_SEED;
|
|
38
|
+
const profile = opts.profile ?? BuildProfile.Exploratory;
|
|
39
|
+
const licensePolicy = opts.licensePolicy ?? LicensePolicy.All;
|
|
73
40
|
const built_at = new Date().toISOString();
|
|
74
|
-
|
|
75
|
-
|
|
76
|
-
|
|
77
|
-
|
|
78
|
-
|
|
79
|
-
const
|
|
80
|
-
|
|
81
|
-
|
|
82
|
-
|
|
83
|
-
|
|
84
|
-
|
|
85
|
-
|
|
86
|
-
|
|
87
|
-
|
|
88
|
-
|
|
89
|
-
// canonical is fully flushed, so its presence guarantees completeness; row order is identical,
|
|
90
|
-
// so downstream holdout-split determinism is preserved. Recovers an align-phase crash without
|
|
91
|
-
// redoing the (expensive) emit phase. Default (unset) re-emits, preserving correctness. (2026-06-12.)
|
|
92
|
-
const adapterDir = join(intermediateDir, adapter.id);
|
|
93
|
-
const cachedManifest = join(adapterDir, "MANIFEST.json");
|
|
94
|
-
if ($public.MAILWOMAN_RESUME === "1" &&
|
|
95
|
-
(await pathExists(cachedManifest)) &&
|
|
96
|
-
(await pathExists(join(adapterDir, "canonical.jsonl")))) {
|
|
97
|
-
const cached = await readLocalJSONFile(cachedManifest);
|
|
98
|
-
opts.onProgress?.("adapter-run", `resumed ${adapter.id} (reused ${cached.yielded} canonical rows)`);
|
|
99
|
-
adapterRuns.push(cached);
|
|
100
|
-
continue;
|
|
101
|
-
}
|
|
102
|
-
opts.onProgress?.("adapter-run", `running ${adapter.id}`);
|
|
103
|
-
const m = await runAdapter({
|
|
104
|
-
adapter,
|
|
105
|
-
adapterOptions,
|
|
106
|
-
outputDir: intermediateDir,
|
|
107
|
-
corpusVersion: opts.corpusVersion,
|
|
108
|
-
});
|
|
109
|
-
adapterRuns.push(m);
|
|
110
|
-
}
|
|
111
|
-
// 2 + 3. Synthesis + alignment: stream every canonical.jsonl, optionally augment, align,
|
|
112
|
-
// and route each labeled row directly to its split-specific JSONL (`labeled-{train,val,test}.
|
|
113
|
-
// jsonl`). Memory cost is O(1) — the prior in-memory `splitInputs` array + `splitByIDMap`
|
|
114
|
-
// + `SplitManifest.{train,val,test}` arrays are gone; per-row split is decided inline via
|
|
115
|
-
// `splitForRow` (a pure function of source_id + region + holdout policy).
|
|
41
|
+
// The build reports heap state when it aborts with SIGABRT.
|
|
42
|
+
// These aborts arrive twelve minutes into the adapter phase.
|
|
43
|
+
const heapLimit = heapLimitBytes();
|
|
44
|
+
const configured = adapters.filter((adapter) => opts.adapterInputs[adapter.id]).map((adapter) => adapter.id);
|
|
45
|
+
opts.onProgress?.("adapter-run", `heap limit ${(heapLimit / 1024 / 1024 / 1024).toFixed(1)} GiB, ${configured.length} adapters configured`);
|
|
46
|
+
const outputDir = PathBuilder.from(opts.outputDir);
|
|
47
|
+
const intermediateDir = outputDir("intermediate");
|
|
48
|
+
await makeDirectories(outputDir, intermediateDir);
|
|
49
|
+
const { runs: adapterRuns, skipped } = await runAdapterPhase({
|
|
50
|
+
adapters,
|
|
51
|
+
adapterInputs: opts.adapterInputs,
|
|
52
|
+
corpusVersion: opts.corpusVersion,
|
|
53
|
+
intermediateDir,
|
|
54
|
+
onProgress: opts.onProgress,
|
|
55
|
+
});
|
|
116
56
|
const labeledPaths = {
|
|
117
|
-
train:
|
|
118
|
-
val:
|
|
119
|
-
test:
|
|
120
|
-
};
|
|
121
|
-
const labeledStreams = {
|
|
122
|
-
train: openWriteStream(labeledPaths.train, { encoding: "utf8" }),
|
|
123
|
-
val: openWriteStream(labeledPaths.val, { encoding: "utf8" }),
|
|
124
|
-
test: openWriteStream(labeledPaths.test, { encoding: "utf8" }),
|
|
57
|
+
train: intermediateDir("labeled-train.jsonl"),
|
|
58
|
+
val: intermediateDir("labeled-val.jsonl"),
|
|
59
|
+
test: intermediateDir("labeled-test.jsonl"),
|
|
125
60
|
};
|
|
126
|
-
const quarantinePath = join(intermediateDir, "quarantine.jsonl");
|
|
127
|
-
const quarantineStream = openWriteStream(quarantinePath, { encoding: "utf8" });
|
|
128
|
-
let aligned = 0;
|
|
129
|
-
let quarantined = 0;
|
|
130
|
-
const counts = { train: 0, val: 0, test: 0 };
|
|
131
61
|
const holdouts = defaultHoldouts();
|
|
132
|
-
|
|
133
|
-
|
|
134
|
-
|
|
135
|
-
|
|
136
|
-
|
|
137
|
-
|
|
138
|
-
|
|
139
|
-
|
|
140
|
-
|
|
141
|
-
|
|
142
|
-
|
|
143
|
-
|
|
144
|
-
|
|
145
|
-
|
|
146
|
-
|
|
147
|
-
|
|
148
|
-
// set reflects what the corpus actually CONTAINED, and `excluded_by_license` what was removed.
|
|
149
|
-
if (licenseExcluded(row.license, excludeLicenses)) {
|
|
150
|
-
excludedByLicense++;
|
|
151
|
-
continue;
|
|
152
|
-
}
|
|
153
|
-
const fanned = [row];
|
|
154
|
-
if (synthesize) {
|
|
155
|
-
for (const aug of synthesizeRow(row, defaultAugmentationsForCountry(row.country))) {
|
|
156
|
-
fanned.push(aug);
|
|
157
|
-
}
|
|
158
|
-
}
|
|
159
|
-
for (const r of fanned) {
|
|
160
|
-
let result;
|
|
161
|
-
try {
|
|
162
|
-
result = alignRow(r);
|
|
163
|
-
}
|
|
164
|
-
catch (error) {
|
|
165
|
-
// Last-resort robustness (2026-06-12): no single row may crash a multi-hour build.
|
|
166
|
-
// alignRow's targeted paths normalize/quarantine known issues with specific reasons;
|
|
167
|
-
// this catches any UNKNOWN throw (e.g. assertSpanInvariants on an unforeseen span
|
|
168
|
-
// shape) → quarantine + continue. A spike in `align-threw` reasons is a finding.
|
|
169
|
-
writeQuarantine(r, `align-threw:${error.message.slice(0, 160)}`);
|
|
170
|
-
quarantined++;
|
|
171
|
-
continue;
|
|
172
|
-
}
|
|
173
|
-
if (result.kind === "labeled") {
|
|
174
|
-
const split = splitForRow(result.row, holdouts);
|
|
175
|
-
labeledStreams[split].write(`${JSON.stringify(result.row)}\n`);
|
|
176
|
-
counts[split]++;
|
|
177
|
-
aligned++;
|
|
178
|
-
}
|
|
179
|
-
else {
|
|
180
|
-
writeQuarantine(r, result.row.reason);
|
|
181
|
-
quarantined++;
|
|
182
|
-
}
|
|
183
|
-
}
|
|
184
|
-
}
|
|
185
|
-
}
|
|
186
|
-
for (const s of Object.values(labeledStreams)) {
|
|
187
|
-
s.end();
|
|
188
|
-
}
|
|
189
|
-
quarantineStream.end();
|
|
190
|
-
await Promise.all([...Object.values(labeledStreams).map((s) => once(s, "close")), once(quarantineStream, "close")]);
|
|
191
|
-
// 4. Splits — manifest derived by streaming the per-split labeled files; no in-memory
|
|
192
|
-
// source-id arrays. `sort(1)` from coreutils produces the deterministic per-split .txt
|
|
193
|
-
// manifests with disk spill for splits that exceed in-memory thresholds.
|
|
194
|
-
opts.onProgress?.("split", `splitting ${aligned} aligned rows`);
|
|
195
|
-
const splitsDir = join(opts.outputDir, "splits");
|
|
62
|
+
const registerDecisions = await readRegisterDecisions();
|
|
63
|
+
const align = await runAlignPhase({
|
|
64
|
+
adapterRuns,
|
|
65
|
+
corpusVersion: opts.corpusVersion,
|
|
66
|
+
synthesize,
|
|
67
|
+
profile,
|
|
68
|
+
licensePolicy,
|
|
69
|
+
excludeLicenses: opts.excludeLicenses ?? [],
|
|
70
|
+
holdouts,
|
|
71
|
+
eligibility: profile === BuildProfile.ReleaseEligible ? await readSourceEligibility() : null,
|
|
72
|
+
labeledPaths,
|
|
73
|
+
quarantinePath: intermediateDir("quarantine.jsonl"),
|
|
74
|
+
checkpointPath: intermediateDir("align-checkpoint.json"),
|
|
75
|
+
onProgress: opts.onProgress,
|
|
76
|
+
});
|
|
77
|
+
opts.onProgress?.("split", `splitting ${align.aligned} aligned rows`);
|
|
196
78
|
const splitCounts = await writeSplitManifestsFromLabeledFiles({
|
|
197
79
|
labeledPaths,
|
|
198
|
-
outputDir:
|
|
80
|
+
outputDir: outputDir("splits"),
|
|
199
81
|
corpusVersion: opts.corpusVersion,
|
|
200
|
-
counts,
|
|
82
|
+
counts: align.counts,
|
|
201
83
|
holdouts,
|
|
202
84
|
});
|
|
203
|
-
|
|
204
|
-
//
|
|
205
|
-
|
|
206
|
-
const
|
|
207
|
-
|
|
208
|
-
|
|
209
|
-
|
|
85
|
+
opts.onProgress?.("parquet", "writing parquet files");
|
|
86
|
+
// Each split gets its own generator seeded from one base, so a split's row order does
|
|
87
|
+
// not depend on how many rows the earlier splits happened to contain.
|
|
88
|
+
const shuffled = (path, salt) => shuffleWithinWindow(streamJSONL(path), makeMulberry32(shuffleSeed + salt), shuffleWindow);
|
|
89
|
+
opts.onProgress?.("parquet", shuffleWindow > 1
|
|
90
|
+
? `shuffling each split within a ${shuffleWindow.toLocaleString("en-US")}-row window, seed ${shuffleSeed}`
|
|
91
|
+
: "writing rows in arrival order (shuffle window disabled)");
|
|
92
|
+
const parquetManifest = await writeParquetSplits({
|
|
93
|
+
train: shuffled(labeledPaths.train, 0),
|
|
94
|
+
val: shuffled(labeledPaths.val, 1),
|
|
95
|
+
test: shuffled(labeledPaths.test, 2),
|
|
210
96
|
}, {
|
|
211
|
-
outputDir
|
|
97
|
+
outputDir,
|
|
212
98
|
corpusVersion: opts.corpusVersion,
|
|
213
|
-
|
|
99
|
+
rowsPerFile,
|
|
100
|
+
resume: $public.MAILWOMAN_RESUME === "1",
|
|
214
101
|
});
|
|
215
|
-
|
|
216
|
-
|
|
217
|
-
const
|
|
102
|
+
const licenseSummary = [...align.licenseCounts.entries()].toSorted((a, b) => b[1] - a[1]);
|
|
103
|
+
const refusedValues = align.licenses.refusedValues();
|
|
104
|
+
const refusalTally = [...align.refusedByKind.entries()].map(([kind, rows]) => `${kind}=${rows}`).join(", ");
|
|
218
105
|
opts.onProgress?.("manifest", `license set: ${licenseSummary.map(([l, c]) => `${l}=${c}`).join(", ")}` +
|
|
219
|
-
|
|
220
|
-
|
|
221
|
-
|
|
222
|
-
|
|
106
|
+
` | policy ${licensePolicy}` +
|
|
107
|
+
(align.excludedByLicense > 0
|
|
108
|
+
? ` | refused ${align.excludedByLicense} rows over ${refusedValues.size} values (${refusalTally})`
|
|
109
|
+
: ` | refused 0 rows`) +
|
|
110
|
+
` | admitted ${align.admittedUnresolved} rows whose license resolves to no expression`);
|
|
223
111
|
opts.onProgress?.("manifest", "writing top-level MANIFEST.json");
|
|
112
|
+
// Frozen from what this build observed rather than re-derived later, because the register moves
|
|
113
|
+
// as terms are reviewed and a re-derived record would describe a build that never happened.
|
|
114
|
+
const trainingManifest = freezeTrainingManifest({
|
|
115
|
+
corpusVersion: opts.corpusVersion,
|
|
116
|
+
builtAt: built_at,
|
|
117
|
+
profile,
|
|
118
|
+
rowsBySource: align.rowsBySource,
|
|
119
|
+
decisionsByLicense: registerDecisions,
|
|
120
|
+
refused: align.ineligibleSources,
|
|
121
|
+
});
|
|
122
|
+
await writeLocalJSONFile(trainingManifest, outputDir(TRAINING_MANIFEST_FILE));
|
|
224
123
|
const manifest = {
|
|
225
124
|
corpus_version: opts.corpusVersion,
|
|
226
125
|
built_at,
|
|
227
126
|
adapters: adapterRuns,
|
|
228
127
|
skipped_adapters: skipped,
|
|
229
128
|
splits: { counts: splitCounts, holdouts },
|
|
230
|
-
slices: { counts:
|
|
231
|
-
quarantine_count: quarantined,
|
|
232
|
-
total_aligned_rows: aligned,
|
|
129
|
+
slices: { counts: parquetManifest.counts, total_rows: parquetManifest.total_rows },
|
|
130
|
+
quarantine_count: align.quarantined,
|
|
131
|
+
total_aligned_rows: align.aligned,
|
|
233
132
|
licenses: Object.fromEntries(licenseSummary),
|
|
234
|
-
|
|
133
|
+
licenses_cover: "the rows this build aligned from its adapters. An overlay parquet assembled afterwards carries its " +
|
|
134
|
+
"own licenses, and the overlay corpus's own MANIFEST.json states no license set at all, so a reader " +
|
|
135
|
+
"attributing an overlay corpus reads this set plus each overlay's own record rather than this set alone.",
|
|
136
|
+
excluded_by_license: align.excludedByLicense,
|
|
137
|
+
license_policy: licensePolicy,
|
|
138
|
+
refused_by_license_kind: Object.fromEntries(align.refusedByKind),
|
|
139
|
+
refused_license_values: Object.fromEntries(refusedValues),
|
|
140
|
+
refused_rows_by_source: Object.fromEntries(align.refusedBySource),
|
|
141
|
+
admitted_unresolved_license_rows: align.admittedUnresolved,
|
|
142
|
+
profile,
|
|
143
|
+
excluded_by_eligibility: align.excludedByEligibility,
|
|
144
|
+
ineligible_sources: Object.fromEntries(align.ineligibleSources),
|
|
145
|
+
training_manifest_digest: trainingManifest.contentDigest,
|
|
235
146
|
};
|
|
236
|
-
await writeLocalJSONFile(manifest,
|
|
147
|
+
await writeLocalJSONFile(manifest, outputDir("MANIFEST.json"));
|
|
237
148
|
return manifest;
|
|
238
149
|
}
|
|
239
|
-
async function* streamJSONL(path) {
|
|
240
|
-
// JSONSpliterator yields already-parsed rows (skipEmpty is on by default, so blank
|
|
241
|
-
// lines are dropped at the row level) and throws SyntaxError on a malformed row —
|
|
242
|
-
// same fail-loud behavior as the prior readline + bare `JSON.parse`.
|
|
243
|
-
yield* JSONSpliterator.fromAsync(path);
|
|
244
|
-
}
|
|
245
150
|
//# sourceMappingURL=build.js.map
|
package/out/build.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"build.js","sourceRoot":"","sources":["../lib/build.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"build.js","sourceRoot":"","sources":["../lib/build.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAEH,OAAO,EAAE,eAAe,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAA;AAChF,OAAO,EAAE,UAAU,IAAI,cAAc,EAAE,MAAM,uBAAuB,CAAA;AACpE,OAAO,EAAE,cAAc,EAAE,MAAM,8BAA8B,CAAA;AAC7D,OAAO,EAAE,WAAW,EAAwB,MAAM,SAAS,CAAA;AAE3D,OAAO,EAAE,sBAAsB,EAAE,MAAM,oBAAoB,CAAA;AAC3D,OAAO,EAAE,eAAe,EAAE,MAAM,iBAAiB,CAAA;AACjD,OAAO,EAAE,aAAa,EAAE,MAAM,cAAc,CAAA;AAC5C,OAAO,EAAE,qBAAqB,EAAE,qBAAqB,EAAE,MAAM,oBAAoB,CAAA;AACjF,OAAO,EAAE,WAAW,EAAE,MAAM,aAAa,CAAA;AACzC,OAAO,EAAE,YAAY,EAAE,sBAAsB,EAAqD,MAAM,cAAc,CAAA;AACtH,OAAO,EAAE,OAAO,EAAE,MAAM,MAAM,CAAA;AAC9B,OAAO,EAAE,aAAa,EAAE,MAAM,iBAAiB,CAAA;AAC/C,OAAO,EAAE,oBAAoB,EAAE,sBAAsB,EAAE,mBAAmB,EAAE,MAAM,kBAAkB,CAAA;AACpG,OAAO,EAAE,kBAAkB,EAAE,MAAM,kBAAkB,CAAA;AACrD,OAAO,EAAE,sBAAsB,EAAE,MAAM,oCAAoC,CAAA;AAE3E,OAAO,EAAE,aAAa,EAAE,MAAM,gBAAgB,CAAA;AAC9C,OAAO,EAAE,eAAe,EAAE,mCAAmC,EAAkB,MAAM,cAAc,CAAA;AAEnG,cAAc,aAAa,CAAA;AAC3B,cAAc,cAAc,CAAA;AAE5B;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,WAAW,CAAC,IAAwB;IACzD,MAAM,QAAQ,GAAG,IAAI,CAAC,QAAQ,IAAI,sBAAsB,CAAC,IAAI,EAAE,CAAA;IAC/D,MAAM,UAAU,GAAG,IAAI,CAAC,UAAU,IAAI,IAAI,CAAA;IAC1C,MAAM,WAAW,GAAG,IAAI,CAAC,WAAW,IAAI,aAAa,CAAA;IACrD,MAAM,aAAa,GAAG,IAAI,CAAC,aAAa,IAAI,sBAAsB,CAAA;IAClE,MAAM,WAAW,GAAG,IAAI,CAAC,WAAW,IAAI,oBAAoB,CAAA;IAC5D,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,IAAI,YAAY,CAAC,WAAW,CAAA;IACxD,MAAM,aAAa,GAAG,IAAI,CAAC,aAAa,IAAI,aAAa,CAAC,GAAG,CAAA;IAC7D,MAAM,QAAQ,GAAG,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE,CAAA;IAEzC,4DAA4D;IAC5D,6DAA6D;IAC7D,MAAM,SAAS,GAAG,cAAc,EAAE,CAAA;IAClC,MAAM,UAAU,GAAG,QAAQ,CAAC,MAAM,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,IAAI,CAAC,aAAa,CAAC,OAAO,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,OAAO,CAAC,EAAE,CAAC,CAAA;IAE5G,IAAI,CAAC,UAAU,EAAE,CAChB,aAAa,EACb,cAAc,CAAC,SAAS,GAAG,IAAI,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,SAAS,UAAU,CAAC,MAAM,sBAAsB,CACzG,CAAA;IAED,MAAM,SAAS,GAAG,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,CAAC,CAAA;IAClD,MAAM,eAAe,GAAG,SAAS,CAAC,cAAc,CAAC,CAAA;IAEjD,MAAM,eAAe,CAAC,SAAS,EAAE,eAAe,CAAC,CAAA;IAEjD,MAAM,EAAE,IAAI,EAAE,WAAW,EAAE,OAAO,EAAE,GAAG,MAAM,eAAe,CAAC;QAC5D,QAAQ;QACR,aAAa,EAAE,IAAI,CAAC,aAAa;QACjC,aAAa,EAAE,IAAI,CAAC,aAAa;QACjC,eAAe;QACf,UAAU,EAAE,IAAI,CAAC,UAAU;KAC3B,CAAC,CAAA;IAEF,MAAM,YAAY,GAAmC;QACpD,KAAK,EAAE,eAAe,CAAC,qBAAqB,CAAC;QAC7C,GAAG,EAAE,eAAe,CAAC,mBAAmB,CAAC;QACzC,IAAI,EAAE,eAAe,CAAC,oBAAoB,CAAC;KAC3C,CAAA;IAED,MAAM,QAAQ,GAAG,eAAe,EAAE,CAAA;IAClC,MAAM,iBAAiB,GAAG,MAAM,qBAAqB,EAAE,CAAA;IAEvD,MAAM,KAAK,GAAG,MAAM,aAAa,CAAC;QACjC,WAAW;QACX,aAAa,EAAE,IAAI,CAAC,aAAa;QACjC,UAAU;QACV,OAAO;QACP,aAAa;QACb,eAAe,EAAE,IAAI,CAAC,eAAe,IAAI,EAAE;QAC3C,QAAQ;QACR,WAAW,EAAE,OAAO,KAAK,YAAY,CAAC,eAAe,CAAC,CAAC,CAAC,MAAM,qBAAqB,EAAE,CAAC,CAAC,CAAC,IAAI;QAC5F,YAAY;QACZ,cAAc,EAAE,eAAe,CAAC,kBAAkB,CAAC;QACnD,cAAc,EAAE,eAAe,CAAC,uBAAuB,CAAC;QACxD,UAAU,EAAE,IAAI,CAAC,UAAU;KAC3B,CAAC,CAAA;IAEF,IAAI,CAAC,UAAU,EAAE,CAAC,OAAO,EAAE,aAAa,KAAK,CAAC,OAAO,eAAe,CAAC,CAAA;IAErE,MAAM,WAAW,GAAG,MAAM,mCAAmC,CAAC;QAC7D,YAAY;QACZ,SAAS,EAAE,SAAS,CAAC,QAAQ,CAAC;QAC9B,aAAa,EAAE,IAAI,CAAC,aAAa;QACjC,MAAM,EAAE,KAAK,CAAC,MAAM;QACpB,QAAQ;KACR,CAAC,CAAA;IAEF,IAAI,CAAC,UAAU,EAAE,CAAC,SAAS,EAAE,uBAAuB,CAAC,CAAA;IAErD,sFAAsF;IACtF,sEAAsE;IACtE,MAAM,QAAQ,GAAG,CAAC,IAAqB,EAAE,IAAY,EAAE,EAAE,CACxD,mBAAmB,CAAC,WAAW,CAAa,IAAI,CAAC,EAAE,cAAc,CAAC,WAAW,GAAG,IAAI,CAAC,EAAE,aAAa,CAAC,CAAA;IAEtG,IAAI,CAAC,UAAU,EAAE,CAChB,SAAS,EACT,aAAa,GAAG,CAAC;QAChB,CAAC,CAAC,iCAAiC,aAAa,CAAC,cAAc,CAAC,OAAO,CAAC,qBAAqB,WAAW,EAAE;QAC1G,CAAC,CAAC,yDAAyD,CAC5D,CAAA;IAED,MAAM,eAAe,GAAG,MAAM,kBAAkB,CAC/C;QACC,KAAK,EAAE,QAAQ,CAAC,YAAY,CAAC,KAAK,EAAE,CAAC,CAAC;QACtC,GAAG,EAAE,QAAQ,CAAC,YAAY,CAAC,GAAG,EAAE,CAAC,CAAC;QAClC,IAAI,EAAE,QAAQ,CAAC,YAAY,CAAC,IAAI,EAAE,CAAC,CAAC;KACpC,EACD;QACC,SAAS;QACT,aAAa,EAAE,IAAI,CAAC,aAAa;QACjC,WAAW;QACX,MAAM,EAAE,OAAO,CAAC,gBAAgB,KAAK,GAAG;KACxC,CACD,CAAA;IAED,MAAM,cAAc,GAAG,CAAC,GAAG,KAAK,CAAC,aAAa,CAAC,OAAO,EAAE,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAA;IACzF,MAAM,aAAa,GAAG,KAAK,CAAC,QAAQ,CAAC,aAAa,EAAE,CAAA;IACpD,MAAM,YAAY,GAAG,CAAC,GAAG,KAAK,CAAC,aAAa,CAAC,OAAO,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,EAAE,IAAI,CAAC,EAAE,EAAE,CAAC,GAAG,IAAI,IAAI,IAAI,EAAE,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;IAE3G,IAAI,CAAC,UAAU,EAAE,CAChB,UAAU,EACV,gBAAgB,cAAc,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE;QACvE,aAAa,aAAa,EAAE;QAC5B,CAAC,KAAK,CAAC,iBAAiB,GAAG,CAAC;YAC3B,CAAC,CAAC,cAAc,KAAK,CAAC,iBAAiB,cAAc,aAAa,CAAC,IAAI,YAAY,YAAY,GAAG;YAClG,CAAC,CAAC,mBAAmB,CAAC;QACvB,eAAe,KAAK,CAAC,kBAAkB,+CAA+C,CACvF,CAAA;IAED,IAAI,CAAC,UAAU,EAAE,CAAC,UAAU,EAAE,iCAAiC,CAAC,CAAA;IAEhE,gGAAgG;IAChG,4FAA4F;IAC5F,MAAM,gBAAgB,GAAG,sBAAsB,CAAC;QAC/C,aAAa,EAAE,IAAI,CAAC,aAAa;QACjC,OAAO,EAAE,QAAQ;QACjB,OAAO;QACP,YAAY,EAAE,KAAK,CAAC,YAAY;QAChC,kBAAkB,EAAE,iBAAiB;QACrC,OAAO,EAAE,KAAK,CAAC,iBAAiB;KAChC,CAAC,CAAA;IAEF,MAAM,kBAAkB,CAAC,gBAAgB,EAAE,SAAS,CAAC,sBAAsB,CAAC,CAAC,CAAA;IAE7E,MAAM,QAAQ,GAAwB;QACrC,cAAc,EAAE,IAAI,CAAC,aAAa;QAClC,QAAQ;QACR,QAAQ,EAAE,WAAW;QACrB,gBAAgB,EAAE,OAAO;QACzB,MAAM,EAAE,EAAE,MAAM,EAAE,WAAW,EAAE,QAAQ,EAAE;QACzC,MAAM,EAAE,EAAE,MAAM,EAAE,eAAe,CAAC,MAAM,EAAE,UAAU,EAAE,eAAe,CAAC,UAAU,EAAE;QAClF,gBAAgB,EAAE,KAAK,CAAC,WAAW;QACnC,kBAAkB,EAAE,KAAK,CAAC,OAAO;QACjC,QAAQ,EAAE,MAAM,CAAC,WAAW,CAAC,cAAc,CAAC;QAC5C,cAAc,EACb,qGAAqG;YACrG,qGAAqG;YACrG,yGAAyG;QAC1G,mBAAmB,EAAE,KAAK,CAAC,iBAAiB;QAC5C,cAAc,EAAE,aAAa;QAC7B,uBAAuB,EAAE,MAAM,CAAC,WAAW,CAAC,KAAK,CAAC,aAAa,CAAC;QAChE,sBAAsB,EAAE,MAAM,CAAC,WAAW,CAAC,aAAa,CAAC;QACzD,sBAAsB,EAAE,MAAM,CAAC,WAAW,CAAC,KAAK,CAAC,eAAe,CAAC;QACjE,gCAAgC,EAAE,KAAK,CAAC,kBAAkB;QAC1D,OAAO;QACP,uBAAuB,EAAE,KAAK,CAAC,qBAAqB;QACpD,kBAAkB,EAAE,MAAM,CAAC,WAAW,CAAC,KAAK,CAAC,iBAAiB,CAAC;QAC/D,wBAAwB,EAAE,gBAAgB,CAAC,aAAa;KACxD,CAAA;IAED,MAAM,kBAAkB,CAAC,QAAQ,EAAE,SAAS,CAAC,eAAe,CAAC,CAAC,CAAA;IAE9D,OAAO,QAAQ,CAAA;AAChB,CAAC"}
|
|
@@ -0,0 +1,19 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
* @file Labels Chinese rows whose settlement ends in an organizational unit chain.
|
|
6
|
+
*
|
|
7
|
+
* The unit grammar tags the whole chain as `locality_unit` and its head unit as `dependent_locality`. Input is JSONL
|
|
8
|
+
* with `{ raw, country }`. Rows are aligned per character for the CJK model.
|
|
9
|
+
*/
|
|
10
|
+
import { type CorpusRecipe } from "#recipes/scaffold";
|
|
11
|
+
/**
|
|
12
|
+
* Labels the components of a row, or returns `null` when the row has no unit chain.
|
|
13
|
+
*/
|
|
14
|
+
export declare function labelCNOrganizationalRow(raw: string): Record<string, string> | null;
|
|
15
|
+
/**
|
|
16
|
+
* The recipe registered with the corpus builder.
|
|
17
|
+
*/
|
|
18
|
+
export declare const cnOrganizationalUnitsRecipe: CorpusRecipe;
|
|
19
|
+
//# sourceMappingURL=organizational-units.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"organizational-units.d.ts","sourceRoot":"","sources":["../../../lib/cn/recipes/organizational-units.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAMH,OAAO,EAAE,KAAK,YAAY,EAA8B,MAAM,mBAAmB,CAAA;AAkBjF;;GAEG;AACH,wBAAgB,wBAAwB,CAAC,GAAG,EAAE,MAAM,GAAG,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GAAG,IAAI,CA8CnF;AAmBD;;GAEG;AACH,eAAO,MAAM,2BAA2B,EAAE,YA0EzC,CAAA"}
|