@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/runner.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"runner.d.ts","sourceRoot":"","sources":["../lib/runner.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"runner.d.ts","sourceRoot":"","sources":["../lib/runner.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAGH,OAAO,EAAmB,KAAK,WAAW,EAAE,MAAM,4BAA4B,CAAA;AAG9E,OAAO,EAAE,KAAK,eAAe,EAAsB,MAAM,SAAS,CAAA;AAGlE,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,oBAAoB,CAAA;AAGzD,OAAO,KAAK,EAAE,cAAc,EAAgB,aAAa,EAAE,MAAM,QAAQ,CAAA;AAEzE;;GAEG;AACH,MAAM,WAAW,cAAc;IAC9B,SAAS,EAAE,MAAM,CAAA;IAEjB;;OAEG;IACH,OAAO,EAAE,MAAM,CAAA;IAEf,OAAO,EAAE,MAAM,CAAA;IAEf,KAAK,EAAE,MAAM,CAAA;IAEb,UAAU,EAAE,MAAM,CAAA;CAClB;AAED;;;;;;GAMG;AACH,eAAO,MAAM,wBAAwB,KAAK,CAAA;AAE1C;;;;;;GAMG;AACH,eAAO,MAAM,sBAAsB,WAAa,CAAA;AAEhD;;GAEG;AACH,eAAO,MAAM,UAAU;IACtB;;OAEG;aACH,gBAAgB,EAAE,mBAAmB;IAErC;;OAEG;aACH,SAAS,EAAE,YAAY;CACd,CAAA;AAEV,MAAM,MAAM,UAAU,GAAG,CAAC,OAAO,UAAU,CAAC,CAAC,MAAM,OAAO,UAAU,CAAC,CAAA;AAErE,MAAM,WAAW,iBAAiB;IACjC,OAAO,EAAE,aAAa,CAAA;IAEtB,cAAc,EAAE,cAAc,CAAA;IAE9B;;;;;;;;;;;;;;OAcG;IACH,YAAY,CAAC,EAAE,MAAM,CAAA;IAErB;;;;;OAKG;IACH,cAAc,CAAC,EAAE,MAAM,CAAA;IAEvB;;;OAGG;IACH,SAAS,EAAE,eAAe,CAAA;IAE1B;;OAEG;IACH,aAAa,EAAE,MAAM,CAAA;IAErB;;;;;;OAMG;IACH,UAAU,CAAC,EAAE,MAAM,CAAA;IAEnB;;;OAGG;IACH,UAAU,CAAC,EAAE,CAAC,QAAQ,EAAE,cAAc,KAAK,IAAI,CAAA;IAE/C;;;;;OAKG;IACH,aAAa,CAAC,EAAE,MAAM,CAAA;CACtB;AAED;;GAEG;AACH,MAAM,WAAW,kBAAkB;IAClC,UAAU,EAAE,MAAM,CAAA;IAClB,cAAc,EAAE,MAAM,CAAA;IACtB,eAAe,EAAE,MAAM,CAAA;IACvB,WAAW,EAAE,MAAM,CAAA;IACnB,OAAO,EAAE,MAAM,CAAA;IACf,OAAO,EAAE,MAAM,CAAA;IACf,OAAO,EAAE,MAAM,CAAA;IACf;;;;;OAKG;IACH,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IAC/B;;;;;;;;;OASG;IACH,0BAA0B,EAAE,MAAM,GAAG,IAAI,CAAA;IACzC;;;;;;OAMG;IACH,WAAW,EAAE,UAAU,CAAA;IACvB;;;;OAIG;IACH,UAAU,EAAE,MAAM,CAAA;IAClB,KAAK,EAAE,MAAM,CAAA;IACb,MAAM,EAAE,MAAM,CAAA;IACd,UAAU,EAAE,MAAM,CAAA;IAClB,UAAU,EAAE,MAAM,CAAA;IAClB,QAAQ,EAAE,MAAM,CAAA;IAChB,UAAU,EAAE,MAAM,CAAA;CAClB;AAED;;GAEG;AACH,wBAAsB,UAAU,CAAC,IAAI,EAAE,iBAAiB,GAAG,OAAO,CAAC,kBAAkB,CAAC,CA8JrF;AAED;;GAEG;AACH,wBAAsB,cAAc,CACnC,QAAQ,EAAE,eAAe,EACzB,MAAM,EAAE,IAAI,CAAC,iBAAiB,EAAE,SAAS,CAAC,GAAG;IAAE,iBAAiB,CAAC,EAAE,CAAC,CAAC,EAAE,aAAa,KAAK,cAAc,CAAA;CAAE,GACvG,OAAO,CAAC,kBAAkB,EAAE,CAAC,CAgB/B;AAmCD;;;;;;;;;;;GAWG;AACH,wBAAgB,WAAW,CAAC,MAAM,EAAE,WAAW,GAAG,OAAO,CAAC,IAAI,CAAC,CAI9D;AAED;;;GAGG;AACH,wBAAgB,IAAI,CAAC,OAAO,EAAE,WAAW,EAAE,KAAK,EAAE,OAAO,GAAG,OAAO,GAAG,OAAO,CAAC,IAAI,CAAC,CAelF"}
|
package/out/runner.js
CHANGED
|
@@ -3,54 +3,74 @@
|
|
|
3
3
|
* @license AGPL-3.0
|
|
4
4
|
* @author Teffen Ellis, et al.
|
|
5
5
|
*
|
|
6
|
-
* Adapter runner — drives a `CorpusAdapter` to completion and writes
|
|
7
|
-
* per
|
|
8
|
-
*
|
|
9
|
-
* Output layout under `outputDir`:
|
|
10
|
-
*
|
|
11
|
-
* ```
|
|
12
|
-
* <outputDir>/<adapter.id>/
|
|
13
|
-
* canonical.jsonl # one row per line, in emission order
|
|
14
|
-
* MANIFEST.json # adapter id, version, row count, sha256, license, started_at, ended_at
|
|
15
|
-
* ```
|
|
16
|
-
*
|
|
17
|
-
* The runner is responsible for everything an adapter is **not** responsible for:
|
|
18
|
-
*
|
|
19
|
-
* - Stamping `corpus_version` on every row (adapters must NOT set it).
|
|
20
|
-
* - Applying `canonicalDedupKey` and skipping duplicates.
|
|
21
|
-
* - Streaming sha256 over JSONL bytes so the manifest checksum doesn't require a re-read.
|
|
22
|
-
* - Honoring backpressure on the output write stream.
|
|
23
|
-
* - Counting + emitting periodic progress to an optional callback.
|
|
24
|
-
* - Honoring `signal` (delegates to adapter's iteration boundary).
|
|
25
|
-
*
|
|
26
|
-
* The runner does NOT perform alignment, tokenization, synthesis, or slicing into Parquet. Those
|
|
27
|
-
* steps run later, consuming the JSONL slices this writes.
|
|
6
|
+
* Adapter runner — drives a `CorpusAdapter` to completion and writes `canonical.jsonl` plus a
|
|
7
|
+
* `MANIFEST.json` per adapter. It does not align, tokenize, synthesize, or write Parquet.
|
|
28
8
|
*/
|
|
9
|
+
import { isAlpha2CodeShape } from "@mailwoman/codex/country";
|
|
29
10
|
import { openWriteStream } from "@mailwoman/core/fs/streams";
|
|
30
11
|
import { writeLocalJSONFile, makeDirectories } from "@mailwoman/core/fs/writers";
|
|
31
|
-
import {
|
|
32
|
-
import {
|
|
12
|
+
import { stringifyJSON } from "@mailwoman/core/json";
|
|
13
|
+
import { resolvePathBuilder } from "path-ts";
|
|
14
|
+
import { canonicalDedupKey } from "#adapters/dedup-key";
|
|
15
|
+
import { streamingSha256 } from "#adapters/sha256-stream";
|
|
16
|
+
import { FingerprintSet } from "#fingerprints";
|
|
33
17
|
/**
|
|
34
|
-
*
|
|
18
|
+
* Base-2 logarithm of the fingerprint table's slot count.
|
|
35
19
|
*
|
|
36
|
-
*
|
|
37
|
-
*
|
|
38
|
-
*
|
|
20
|
+
* 2^27 slots hold 93,952,409 keys before the load limit.
|
|
21
|
+
* The largest measured adapter has 57,570,829 distinct keys.
|
|
22
|
+
* The table occupies 2.0 GiB outside the V8 heap.
|
|
23
|
+
*/
|
|
24
|
+
export const DEFAULT_DEDUP_SLOTS_LOG2 = 27;
|
|
25
|
+
/**
|
|
26
|
+
* How many distinct dedup keys a `Set`-backed run holds before it stops adding new ones.
|
|
27
|
+
*
|
|
28
|
+
* A V8 `Set` refuses a 16,777,216th entry outright, so this cap was a real bound rather than a preference.
|
|
29
|
+
* It applies only to a run that opts out of the fingerprint table
|
|
30
|
+
* through {@linkcode RunAdapterOptions.dedupMaxSize}.
|
|
31
|
+
*/
|
|
32
|
+
export const DEFAULT_DEDUP_MAX_SIZE = 10_000_000;
|
|
33
|
+
/**
|
|
34
|
+
* Where a run held its dedup keys.
|
|
35
|
+
*/
|
|
36
|
+
export const DedupStore = {
|
|
37
|
+
/**
|
|
38
|
+
* 128-bit fingerprints in a flat `Uint32Array`, bounded by the array the run sized.
|
|
39
|
+
*/
|
|
40
|
+
FingerprintTable: "fingerprint-table",
|
|
41
|
+
/**
|
|
42
|
+
* A V8 `Set` of key strings, capped because V8 refuses a 16,777,216th entry.
|
|
43
|
+
*/
|
|
44
|
+
CappedSet: "capped-set",
|
|
45
|
+
};
|
|
46
|
+
/**
|
|
47
|
+
* Drive a single adapter to completion, writing its jsonl and manifest under `outputDir/<adapter.id>/`.
|
|
39
48
|
*/
|
|
40
49
|
export async function runAdapter(opts) {
|
|
41
|
-
const { adapter,
|
|
50
|
+
const { adapter, outputDir, corpusVersion } = opts;
|
|
51
|
+
// A caller that passes its own map reads the counts back from it.
|
|
52
|
+
// Otherwise the runner supplies one, so every manifest carries the adapter's drop reasons.
|
|
53
|
+
const dropped = opts.adapterOptions.dropped ?? new Map();
|
|
54
|
+
const adapterOptions = { ...opts.adapterOptions, dropped };
|
|
42
55
|
const progressEvery = opts.progressEvery ?? 1000;
|
|
43
|
-
const adapterDir =
|
|
56
|
+
const adapterDir = resolvePathBuilder(outputDir, adapter.id);
|
|
44
57
|
await makeDirectories(adapterDir);
|
|
45
|
-
const jsonlPath =
|
|
46
|
-
const manifestPath =
|
|
58
|
+
const jsonlPath = adapterDir("canonical.jsonl");
|
|
59
|
+
const manifestPath = adapterDir("MANIFEST.json");
|
|
47
60
|
const startedAt = new Date();
|
|
48
61
|
const t0 = performance.now();
|
|
49
62
|
const stream = openWriteStream(jsonlPath, { encoding: "utf8" });
|
|
50
63
|
const hasher = streamingSha256();
|
|
51
|
-
|
|
52
|
-
|
|
64
|
+
// The `Set` path serves callers that cannot accept a fingerprint collision dropping a legitimate row.
|
|
65
|
+
// A test also uses it to reach the capped behavior in three rows.
|
|
66
|
+
// Every other run takes the table.
|
|
67
|
+
// Its entry count is bounded by the array it sized rather than by V8's `Set` limit.
|
|
68
|
+
const capped = opts.dedupMaxSize !== undefined;
|
|
69
|
+
const seen = capped ? new Set() : null;
|
|
70
|
+
const fingerprints = capped ? null : new FingerprintSet(opts.dedupSlotsLog2 ?? DEFAULT_DEDUP_SLOTS_LOG2);
|
|
71
|
+
const dedupMaxSize = opts.dedupMaxSize ?? DEFAULT_DEDUP_MAX_SIZE;
|
|
53
72
|
let dedupExhausted = false;
|
|
73
|
+
let dedupExhaustedAtYielded = null;
|
|
54
74
|
let yielded = 0;
|
|
55
75
|
let written = 0;
|
|
56
76
|
let bytes = 0;
|
|
@@ -70,24 +90,54 @@ export async function runAdapter(opts) {
|
|
|
70
90
|
}
|
|
71
91
|
yielded++;
|
|
72
92
|
assertEmittedRow(adapter, row);
|
|
73
|
-
const stamped = {
|
|
93
|
+
const stamped = {
|
|
94
|
+
...row,
|
|
95
|
+
// The rename is the runner's, after `assertEmittedRow` has held the adapter to emitting its own id.
|
|
96
|
+
source: opts.sourceName ?? row.source,
|
|
97
|
+
corpus_version: corpusVersion,
|
|
98
|
+
addressRole: row.addressRole ?? adapter.addressRole,
|
|
99
|
+
// `register` is nullable and null is a statement rather than an absence,
|
|
100
|
+
// so only an undefined field takes the adapter's declaration.
|
|
101
|
+
register: row.register === undefined ? adapter.register : row.register,
|
|
102
|
+
surface: row.surface ?? adapter.surface,
|
|
103
|
+
};
|
|
74
104
|
const key = canonicalDedupKey(stamped);
|
|
75
|
-
if (
|
|
76
|
-
|
|
105
|
+
if (fingerprints) {
|
|
106
|
+
// The table holds every key the run has seen, so a duplicate is refused wherever it arrives.
|
|
107
|
+
if (!fingerprints.add(key)) {
|
|
77
108
|
if (yielded % progressEvery === 0) {
|
|
78
109
|
emitProgress();
|
|
79
110
|
}
|
|
80
111
|
continue;
|
|
81
112
|
}
|
|
82
|
-
|
|
83
|
-
|
|
84
|
-
|
|
113
|
+
}
|
|
114
|
+
else if (seen) {
|
|
115
|
+
// The membership test runs whether or not the set is full.
|
|
116
|
+
// The cap stops the set from growing.
|
|
117
|
+
// The set still rejects every duplicate of a key it holds.
|
|
118
|
+
// Without the membership test at the cap, duplicates of the first
|
|
119
|
+
// `dedupMaxSize` keys passed through.
|
|
120
|
+
// This ordering keeps those duplicates out.
|
|
121
|
+
if (seen.has(key)) {
|
|
122
|
+
if (yielded % progressEvery === 0) {
|
|
123
|
+
emitProgress();
|
|
124
|
+
}
|
|
125
|
+
continue;
|
|
85
126
|
}
|
|
86
|
-
|
|
87
|
-
seen.
|
|
127
|
+
if (!dedupExhausted) {
|
|
128
|
+
if (seen.size >= dedupMaxSize) {
|
|
129
|
+
dedupExhausted = true;
|
|
130
|
+
dedupExhaustedAtYielded = yielded;
|
|
131
|
+
process.stderr.write(` runner: dedup set full at ${dedupMaxSize.toLocaleString()} keys after ${yielded.toLocaleString()} ` +
|
|
132
|
+
`yielded rows — a later row duplicating a key already held is still dropped, and a duplicate of ` +
|
|
133
|
+
`a key first seen from here on is written\n`);
|
|
134
|
+
}
|
|
135
|
+
else {
|
|
136
|
+
seen.add(key);
|
|
137
|
+
}
|
|
88
138
|
}
|
|
89
139
|
}
|
|
90
|
-
const line = `${
|
|
140
|
+
const line = `${stringifyJSON(stamped)}\n`;
|
|
91
141
|
hasher.update(line);
|
|
92
142
|
bytes += Buffer.byteLength(line, "utf8");
|
|
93
143
|
written++;
|
|
@@ -103,6 +153,9 @@ export async function runAdapter(opts) {
|
|
|
103
153
|
stream.end();
|
|
104
154
|
await once(stream, "close");
|
|
105
155
|
}
|
|
156
|
+
// Every adapter honors `signal` by returning instead, so without this a truncated
|
|
157
|
+
// `canonical.jsonl` would be recorded as a finished run.
|
|
158
|
+
adapterOptions.signal?.throwIfAborted();
|
|
106
159
|
const endedAt = new Date();
|
|
107
160
|
const elapsed_ms = performance.now() - t0;
|
|
108
161
|
emitProgress();
|
|
@@ -114,9 +167,13 @@ export async function runAdapter(opts) {
|
|
|
114
167
|
yielded,
|
|
115
168
|
written,
|
|
116
169
|
deduped: yielded - written,
|
|
170
|
+
dropped: Object.fromEntries([...dropped].toSorted(([a], [b]) => a.localeCompare(b))),
|
|
171
|
+
dedup_exhausted_at_yielded: dedupExhaustedAtYielded,
|
|
172
|
+
dedup_store: fingerprints ? DedupStore.FingerprintTable : DedupStore.CappedSet,
|
|
173
|
+
dedup_keys: fingerprints?.size ?? seen?.size ?? 0,
|
|
117
174
|
bytes,
|
|
118
175
|
sha256: hasher.digest(),
|
|
119
|
-
jsonl_path: jsonlPath,
|
|
176
|
+
jsonl_path: jsonlPath.toString(),
|
|
120
177
|
started_at: startedAt.toISOString(),
|
|
121
178
|
ended_at: endedAt.toISOString(),
|
|
122
179
|
elapsed_ms,
|
|
@@ -125,10 +182,7 @@ export async function runAdapter(opts) {
|
|
|
125
182
|
return manifest;
|
|
126
183
|
}
|
|
127
184
|
/**
|
|
128
|
-
* Drive every adapter in a registry sequentially
|
|
129
|
-
* calling if partial-failure is desired).
|
|
130
|
-
*
|
|
131
|
-
* Returns the manifests in registry insertion order.
|
|
185
|
+
* Drive every adapter in a registry sequentially, stopping on the first failure.
|
|
132
186
|
*/
|
|
133
187
|
export async function runAllAdapters(registry, common) {
|
|
134
188
|
const out = [];
|
|
@@ -142,13 +196,9 @@ export async function runAllAdapters(registry, common) {
|
|
|
142
196
|
}
|
|
143
197
|
return out;
|
|
144
198
|
}
|
|
145
|
-
/**
|
|
146
|
-
* Validate an emitted row. Cheap; runs once per row. Catches adapter bugs early so the JSONL doesn't end up
|
|
147
|
-
* half-malformed.
|
|
148
|
-
*/
|
|
149
199
|
function assertEmittedRow(adapter, row) {
|
|
150
200
|
if (row.source !== adapter.id) {
|
|
151
|
-
throw new Error(`adapter ${adapter.id}: row.source must equal adapter.id (got ${
|
|
201
|
+
throw new Error(`adapter ${adapter.id}: row.source must equal adapter.id (got ${stringifyJSON(row.source)})`);
|
|
152
202
|
}
|
|
153
203
|
if (!row.source_id) {
|
|
154
204
|
throw new Error(`adapter ${adapter.id}: row.source_id is empty`);
|
|
@@ -159,14 +209,38 @@ function assertEmittedRow(adapter, row) {
|
|
|
159
209
|
if (!row.country) {
|
|
160
210
|
throw new Error(`adapter ${adapter.id}: row.country is empty for source_id=${row.source_id}`);
|
|
161
211
|
}
|
|
212
|
+
// `country_weights` and every country filter use this value.
|
|
213
|
+
// Validate its ISO 3166-1 alpha-2 shape.
|
|
214
|
+
// `ZZ` and `XK` are legitimate codes even though ISO membership does not list them.
|
|
215
|
+
if (!isAlpha2CodeShape(row.country)) {
|
|
216
|
+
throw new Error(`adapter ${adapter.id}: row.country ${stringifyJSON(row.country)} is not two upper-case letters ` +
|
|
217
|
+
`for source_id=${row.source_id}. ISO 3166-1 alpha-2 is the shape country_weights and every ` +
|
|
218
|
+
`country filter key on, so a code outside it trains on nothing and matches no filter.`);
|
|
219
|
+
}
|
|
162
220
|
if (!row.license) {
|
|
163
221
|
throw new Error(`adapter ${adapter.id}: row.license is empty for source_id=${row.source_id}`);
|
|
164
222
|
}
|
|
165
223
|
}
|
|
166
224
|
/**
|
|
167
|
-
*
|
|
168
|
-
*
|
|
169
|
-
*
|
|
225
|
+
* Resolve once everything written to `stream` so far has reached the file.
|
|
226
|
+
*
|
|
227
|
+
* A zero-length write acts as a barrier.
|
|
228
|
+
* Its callback runs after earlier queued writes.
|
|
229
|
+
*
|
|
230
|
+
* A caller can then record a byte offset for the bytes in the file.
|
|
231
|
+
* `drain` fires only when the buffer was full.
|
|
232
|
+
*
|
|
233
|
+
* `bytesWritten` excludes queued data.
|
|
234
|
+
* Neither value answers when all earlier writes have reached the file.
|
|
235
|
+
*/
|
|
236
|
+
export function flushStream(stream) {
|
|
237
|
+
return new Promise((resolve, reject) => {
|
|
238
|
+
stream.write("", (error) => (error ? reject(error) : resolve()));
|
|
239
|
+
});
|
|
240
|
+
}
|
|
241
|
+
/**
|
|
242
|
+
* Promise-ify a single `drain` or `close` emission, detaching the loser listener
|
|
243
|
+
* so a long-lived stream does not accumulate an orphan handler per wait.
|
|
170
244
|
*/
|
|
171
245
|
export function once(emitter, event) {
|
|
172
246
|
return new Promise((resolve, reject) => {
|
package/out/runner.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"runner.js","sourceRoot":"","sources":["../lib/runner.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"runner.js","sourceRoot":"","sources":["../lib/runner.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAEH,OAAO,EAAE,iBAAiB,EAAE,MAAM,0BAA0B,CAAA;AAC5D,OAAO,EAAE,eAAe,EAAoB,MAAM,4BAA4B,CAAA;AAC9E,OAAO,EAAE,kBAAkB,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAA;AAChF,OAAO,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAA;AACpD,OAAO,EAAwB,kBAAkB,EAAE,MAAM,SAAS,CAAA;AAElE,OAAO,EAAE,iBAAiB,EAAE,MAAM,qBAAqB,CAAA;AAEvD,OAAO,EAAE,eAAe,EAAwB,MAAM,yBAAyB,CAAA;AAC/E,OAAO,EAAE,cAAc,EAAE,MAAM,eAAe,CAAA;AAqB9C;;;;;;GAMG;AACH,MAAM,CAAC,MAAM,wBAAwB,GAAG,EAAE,CAAA;AAE1C;;;;;;GAMG;AACH,MAAM,CAAC,MAAM,sBAAsB,GAAG,UAAU,CAAA;AAEhD;;GAEG;AACH,MAAM,CAAC,MAAM,UAAU,GAAG;IACzB;;OAEG;IACH,gBAAgB,EAAE,mBAAmB;IAErC;;OAEG;IACH,SAAS,EAAE,YAAY;CACd,CAAA;AAwHV;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,UAAU,CAAC,IAAuB;IACvD,MAAM,EAAE,OAAO,EAAE,SAAS,EAAE,aAAa,EAAE,GAAG,IAAI,CAAA;IAClD,kEAAkE;IAClE,2FAA2F;IAC3F,MAAM,OAAO,GAAG,IAAI,CAAC,cAAc,CAAC,OAAO,IAAI,IAAI,GAAG,EAAkB,CAAA;IACxE,MAAM,cAAc,GAAmB,EAAE,GAAG,IAAI,CAAC,cAAc,EAAE,OAAO,EAAE,CAAA;IAC1E,MAAM,aAAa,GAAG,IAAI,CAAC,aAAa,IAAI,IAAI,CAAA;IAEhD,MAAM,UAAU,GAAG,kBAAkB,CAAC,SAAS,EAAE,OAAO,CAAC,EAAE,CAAC,CAAA;IAC5D,MAAM,eAAe,CAAC,UAAU,CAAC,CAAA;IAEjC,MAAM,SAAS,GAAG,UAAU,CAAC,iBAAiB,CAAC,CAAA;IAC/C,MAAM,YAAY,GAAG,UAAU,CAAC,eAAe,CAAC,CAAA;IAEhD,MAAM,SAAS,GAAG,IAAI,IAAI,EAAE,CAAA;IAC5B,MAAM,EAAE,GAAG,WAAW,CAAC,GAAG,EAAE,CAAA;IAE5B,MAAM,MAAM,GAAG,eAAe,CAAC,SAAS,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,CAAC,CAAA;IAC/D,MAAM,MAAM,GAAoB,eAAe,EAAE,CAAA;IAEjD,sGAAsG;IACtG,kEAAkE;IAClE,mCAAmC;IACnC,oFAAoF;IACpF,MAAM,MAAM,GAAG,IAAI,CAAC,YAAY,KAAK,SAAS,CAAA;IAC9C,MAAM,IAAI,GAAG,MAAM,CAAC,CAAC,CAAC,IAAI,GAAG,EAAU,CAAC,CAAC,CAAC,IAAI,CAAA;IAC9C,MAAM,YAAY,GAAG,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,cAAc,CAAC,IAAI,CAAC,cAAc,IAAI,wBAAwB,CAAC,CAAA;IACxG,MAAM,YAAY,GAAG,IAAI,CAAC,YAAY,IAAI,sBAAsB,CAAA;IAChE,IAAI,cAAc,GAAG,KAAK,CAAA;IAC1B,IAAI,uBAAuB,GAAkB,IAAI,CAAA;IAEjD,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,KAAK,GAAG,CAAC,CAAA;IAEb,MAAM,YAAY,GAAG,GAAS,EAAE;QAC/B,IAAI,CAAC,UAAU,EAAE,CAAC;YACjB,SAAS,EAAE,OAAO,CAAC,EAAE;YACrB,OAAO;YACP,OAAO;YACP,KAAK;YACL,UAAU,EAAE,WAAW,CAAC,GAAG,EAAE,GAAG,EAAE;SAClC,CAAC,CAAA;IACH,CAAC,CAAA;IAED,IAAI,CAAC;QACJ,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,OAAO,CAAC,IAAI,CAAC,cAAc,CAAC,EAAE,CAAC;YACtD,IAAI,cAAc,CAAC,MAAM,EAAE,OAAO,EAAE,CAAC;gBACpC,MAAM,IAAI,YAAY,CAAC,+BAA+B,EAAE,YAAY,CAAC,CAAA;YACtE,CAAC;YAED,OAAO,EAAE,CAAA;YACT,gBAAgB,CAAC,OAAO,EAAE,GAAG,CAAC,CAAA;YAE9B,MAAM,OAAO,GAAiB;gBAC7B,GAAG,GAAG;gBACN,oGAAoG;gBACpG,MAAM,EAAE,IAAI,CAAC,UAAU,IAAI,GAAG,CAAC,MAAM;gBACrC,cAAc,EAAE,aAAa;gBAC7B,WAAW,EAAE,GAAG,CAAC,WAAW,IAAI,OAAO,CAAC,WAAW;gBACnD,yEAAyE;gBACzE,8DAA8D;gBAC9D,QAAQ,EAAE,GAAG,CAAC,QAAQ,KAAK,SAAS,CAAC,CAAC,CAAC,OAAO,CAAC,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,QAAQ;gBACtE,OAAO,EAAE,GAAG,CAAC,OAAO,IAAI,OAAO,CAAC,OAAO;aACvC,CAAA;YAED,MAAM,GAAG,GAAG,iBAAiB,CAAC,OAAO,CAAC,CAAA;YAEtC,IAAI,YAAY,EAAE,CAAC;gBAClB,6FAA6F;gBAC7F,IAAI,CAAC,YAAY,CAAC,GAAG,CAAC,GAAG,CAAC,EAAE,CAAC;oBAC5B,IAAI,OAAO,GAAG,aAAa,KAAK,CAAC,EAAE,CAAC;wBACnC,YAAY,EAAE,CAAA;oBACf,CAAC;oBAED,SAAQ;gBACT,CAAC;YACF,CAAC;iBAAM,IAAI,IAAI,EAAE,CAAC;gBACjB,2DAA2D;gBAC3D,sCAAsC;gBACtC,2DAA2D;gBAC3D,kEAAkE;gBAClE,sCAAsC;gBACtC,4CAA4C;gBAC5C,IAAI,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,EAAE,CAAC;oBACnB,IAAI,OAAO,GAAG,aAAa,KAAK,CAAC,EAAE,CAAC;wBACnC,YAAY,EAAE,CAAA;oBACf,CAAC;oBAED,SAAQ;gBACT,CAAC;gBAED,IAAI,CAAC,cAAc,EAAE,CAAC;oBACrB,IAAI,IAAI,CAAC,IAAI,IAAI,YAAY,EAAE,CAAC;wBAC/B,cAAc,GAAG,IAAI,CAAA;wBACrB,uBAAuB,GAAG,OAAO,CAAA;wBAEjC,OAAO,CAAC,MAAM,CAAC,KAAK,CACnB,+BAA+B,YAAY,CAAC,cAAc,EAAE,eAAe,OAAO,CAAC,cAAc,EAAE,GAAG;4BACrG,iGAAiG;4BACjG,4CAA4C,CAC7C,CAAA;oBACF,CAAC;yBAAM,CAAC;wBACP,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;oBACd,CAAC;gBACF,CAAC;YACF,CAAC;YAED,MAAM,IAAI,GAAG,GAAG,aAAa,CAAC,OAAO,CAAC,IAAI,CAAA;YAC1C,MAAM,CAAC,MAAM,CAAC,IAAI,CAAC,CAAA;YACnB,KAAK,IAAI,MAAM,CAAC,UAAU,CAAC,IAAI,EAAE,MAAM,CAAC,CAAA;YAExC,OAAO,EAAE,CAAA;YAET,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC;gBACzB,MAAM,IAAI,CAAC,MAAM,EAAE,OAAO,CAAC,CAAA;YAC5B,CAAC;YAED,IAAI,OAAO,GAAG,aAAa,KAAK,CAAC,EAAE,CAAC;gBACnC,YAAY,EAAE,CAAA;YACf,CAAC;QACF,CAAC;IACF,CAAC;YAAS,CAAC;QACV,MAAM,CAAC,GAAG,EAAE,CAAA;QACZ,MAAM,IAAI,CAAC,MAAM,EAAE,OAAO,CAAC,CAAA;IAC5B,CAAC;IAED,kFAAkF;IAClF,yDAAyD;IACzD,cAAc,CAAC,MAAM,EAAE,cAAc,EAAE,CAAA;IAEvC,MAAM,OAAO,GAAG,IAAI,IAAI,EAAE,CAAA;IAC1B,MAAM,UAAU,GAAG,WAAW,CAAC,GAAG,EAAE,GAAG,EAAE,CAAA;IACzC,YAAY,EAAE,CAAA;IAEd,MAAM,QAAQ,GAAuB;QACpC,UAAU,EAAE,OAAO,CAAC,EAAE;QACtB,cAAc,EAAE,aAAa;QAC7B,eAAe,EAAE,OAAO,CAAC,cAAc;QACvC,WAAW,EAAE,OAAO,CAAC,WAAW;QAChC,OAAO;QACP,OAAO;QACP,OAAO,EAAE,OAAO,GAAG,OAAO;QAC1B,OAAO,EAAE,MAAM,CAAC,WAAW,CAAC,CAAC,GAAG,OAAO,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC,CAAC;QACpF,0BAA0B,EAAE,uBAAuB;QACnD,WAAW,EAAE,YAAY,CAAC,CAAC,CAAC,UAAU,CAAC,gBAAgB,CAAC,CAAC,CAAC,UAAU,CAAC,SAAS;QAC9E,UAAU,EAAE,YAAY,EAAE,IAAI,IAAI,IAAI,EAAE,IAAI,IAAI,CAAC;QACjD,KAAK;QACL,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE;QACvB,UAAU,EAAE,SAAS,CAAC,QAAQ,EAAE;QAChC,UAAU,EAAE,SAAS,CAAC,WAAW,EAAE;QACnC,QAAQ,EAAE,OAAO,CAAC,WAAW,EAAE;QAC/B,UAAU;KACV,CAAA;IAED,MAAM,kBAAkB,CAAC,QAAQ,EAAE,YAAY,CAAC,CAAA;IAEhD,OAAO,QAAQ,CAAA;AAChB,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,cAAc,CACnC,QAAyB,EACzB,MAAyG;IAEzG,MAAM,GAAG,GAAyB,EAAE,CAAA;IAEpC,KAAK,MAAM,OAAO,IAAI,QAAQ,CAAC,IAAI,EAAE,EAAE,CAAC;QACvC,MAAM,cAAc,GAAG,MAAM,CAAC,iBAAiB,EAAE,CAAC,OAAO,CAAC,IAAI,MAAM,CAAC,cAAc,CAAA;QAEnF,GAAG,CAAC,IAAI,CACP,MAAM,UAAU,CAAC;YAChB,GAAG,MAAM;YACT,OAAO;YACP,cAAc;SACd,CAAC,CACF,CAAA;IACF,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC;AAED,SAAS,gBAAgB,CAAC,OAAsB,EAAE,GAAiB;IAClE,IAAI,GAAG,CAAC,MAAM,KAAK,OAAO,CAAC,EAAE,EAAE,CAAC;QAC/B,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,2CAA2C,aAAa,CAAC,GAAG,CAAC,MAAM,CAAC,GAAG,CAAC,CAAA;IAC9G,CAAC;IAED,IAAI,CAAC,GAAG,CAAC,SAAS,EAAE,CAAC;QACpB,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,0BAA0B,CAAC,CAAA;IACjE,CAAC;IAED,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC;QACd,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,oCAAoC,GAAG,CAAC,SAAS,EAAE,CAAC,CAAA;IAC1F,CAAC;IAED,IAAI,CAAC,GAAG,CAAC,OAAO,EAAE,CAAC;QAClB,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,wCAAwC,GAAG,CAAC,SAAS,EAAE,CAAC,CAAA;IAC9F,CAAC;IAED,6DAA6D;IAC7D,yCAAyC;IACzC,oFAAoF;IACpF,IAAI,CAAC,iBAAiB,CAAC,GAAG,CAAC,OAAO,CAAC,EAAE,CAAC;QACrC,MAAM,IAAI,KAAK,CACd,WAAW,OAAO,CAAC,EAAE,iBAAiB,aAAa,CAAC,GAAG,CAAC,OAAO,CAAC,iCAAiC;YAChG,iBAAiB,GAAG,CAAC,SAAS,8DAA8D;YAC5F,sFAAsF,CACvF,CAAA;IACF,CAAC;IAED,IAAI,CAAC,GAAG,CAAC,OAAO,EAAE,CAAC;QAClB,MAAM,IAAI,KAAK,CAAC,WAAW,OAAO,CAAC,EAAE,wCAAwC,GAAG,CAAC,SAAS,EAAE,CAAC,CAAA;IAC9F,CAAC;AACF,CAAC;AAED;;;;;;;;;;;GAWG;AACH,MAAM,UAAU,WAAW,CAAC,MAAmB;IAC9C,OAAO,IAAI,OAAO,CAAC,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE;QACtC,MAAM,CAAC,KAAK,CAAC,EAAE,EAAE,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,OAAO,EAAE,CAAC,CAAC,CAAA;IACjE,CAAC,CAAC,CAAA;AACH,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,IAAI,CAAC,OAAoB,EAAE,KAAwB;IAClE,OAAO,IAAI,OAAO,CAAC,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE;QACtC,MAAM,OAAO,GAAG,GAAS,EAAE;YAC1B,OAAO,CAAC,GAAG,CAAC,OAAO,EAAE,OAAO,CAAC,CAAA;YAC7B,OAAO,EAAE,CAAA;QACV,CAAC,CAAA;QAED,MAAM,OAAO,GAAG,CAAC,GAAU,EAAQ,EAAE;YACpC,OAAO,CAAC,GAAG,CAAC,KAAK,EAAE,OAAO,CAAC,CAAA;YAC3B,MAAM,CAAC,GAAG,CAAC,CAAA;QACZ,CAAC,CAAA;QAED,OAAO,CAAC,IAAI,CAAC,KAAK,EAAE,OAAO,CAAC,CAAA;QAC5B,OAAO,CAAC,IAAI,CAAC,OAAO,EAAE,OAAO,CAAC,CAAA;IAC/B,CAAC,CAAC,CAAA;AACH,CAAC"}
|
|
@@ -0,0 +1,55 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Renders Overture Singapore address rows in the forms that people type, such as HDB block lines and `S(560123)` postcodes.
|
|
7
|
+
*/
|
|
8
|
+
import { type CorpusRecipe } from "#recipes/scaffold";
|
|
9
|
+
/**
|
|
10
|
+
* Abbreviates the first street generic that the street contains, such as
|
|
11
|
+
* `Ang Mo Kio Avenue 3` to `Ang Mo Kio Ave 3`.
|
|
12
|
+
*/
|
|
13
|
+
export declare function abbreviateSGStreet(street: string): string;
|
|
14
|
+
/**
|
|
15
|
+
* Reports whether the source `unit` value looks like a building name that can lead a line.
|
|
16
|
+
*
|
|
17
|
+
* The check rejects `NIL`, single words, values with a digit or parenthesis, plus estate names.
|
|
18
|
+
*/
|
|
19
|
+
export declare function isBuildingName(unit: string): boolean;
|
|
20
|
+
interface SGRow {
|
|
21
|
+
street: string;
|
|
22
|
+
number: string;
|
|
23
|
+
unit: string;
|
|
24
|
+
postcode: string;
|
|
25
|
+
}
|
|
26
|
+
/**
|
|
27
|
+
* The four typed forms that this recipe renders.
|
|
28
|
+
*/
|
|
29
|
+
export type SGRegister = "official" | "block" | "bracket_postcode" | "building_led";
|
|
30
|
+
/**
|
|
31
|
+
* One rendered line with its components, each of which is a substring of `raw`.
|
|
32
|
+
*/
|
|
33
|
+
export interface SGRegisterRendering {
|
|
34
|
+
raw: string;
|
|
35
|
+
components: Record<string, string>;
|
|
36
|
+
register: SGRegister;
|
|
37
|
+
}
|
|
38
|
+
/**
|
|
39
|
+
* Renders one source row in a sampled or requested form.
|
|
40
|
+
*
|
|
41
|
+
* All randomness comes from `random`.
|
|
42
|
+
* A requested `building_led` form falls back to `official` when the row's `unit` is not a building name.
|
|
43
|
+
*
|
|
44
|
+
* A requested `block` form falls back to `bracket_postcode` when the row's number is not a block number.
|
|
45
|
+
* `Blk` and the `S(` and `)` around a postcode stay untagged.
|
|
46
|
+
*/
|
|
47
|
+
export declare function renderSGRegister(row: SGRow, random: () => number, register?: SGRegister): SGRegisterRendering;
|
|
48
|
+
/**
|
|
49
|
+
* Renders each Overture Singapore corpus row from `--input` once in a sampled typed form.
|
|
50
|
+
*
|
|
51
|
+
* The recipe skips rows without a street, a block-style number, or a six-digit postcode.
|
|
52
|
+
*/
|
|
53
|
+
export declare const sgRegisterRecipe: CorpusRecipe;
|
|
54
|
+
export {};
|
|
55
|
+
//# sourceMappingURL=register.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"register.d.ts","sourceRoot":"","sources":["../../../lib/sg/recipes/register.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAMH,OAAO,EAAiB,KAAK,YAAY,EAA8B,MAAM,mBAAmB,CAAA;AAqDhG;;;GAGG;AACH,wBAAgB,kBAAkB,CAAC,MAAM,EAAE,MAAM,GAAG,MAAM,CAQzD;AAED;;;;GAIG;AACH,wBAAgB,cAAc,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAMpD;AAED,UAAU,KAAK;IACd,MAAM,EAAE,MAAM,CAAA;IACd,MAAM,EAAE,MAAM,CAAA;IACd,IAAI,EAAE,MAAM,CAAA;IACZ,QAAQ,EAAE,MAAM,CAAA;CAChB;AAED;;GAEG;AACH,MAAM,MAAM,UAAU,GAAG,UAAU,GAAG,OAAO,GAAG,kBAAkB,GAAG,cAAc,CAAA;AAEnF;;GAEG;AACH,MAAM,WAAW,mBAAmB;IACnC,GAAG,EAAE,MAAM,CAAA;IACX,UAAU,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IAClC,QAAQ,EAAE,UAAU,CAAA;CACpB;AAED;;;;;;;;GAQG;AACH,wBAAgB,gBAAgB,CAAC,GAAG,EAAE,KAAK,EAAE,MAAM,EAAE,MAAM,MAAM,EAAE,QAAQ,CAAC,EAAE,UAAU,GAAG,mBAAmB,CA2C7G;AAED;;;;GAIG;AACH,eAAO,MAAM,gBAAgB,EAAE,YA2F9B,CAAA"}
|
|
@@ -0,0 +1,206 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Renders Overture Singapore address rows in the forms that people type, such as HDB block lines and `S(560123)` postcodes.
|
|
7
|
+
*/
|
|
8
|
+
import { stringifyJSON } from "@mailwoman/core/json";
|
|
9
|
+
import { mulberry32 as makeMulberry32 } from "@mailwoman/core/utils";
|
|
10
|
+
import { titleCaseIfUpper } from "spliterator";
|
|
11
|
+
import { alignAndWrite, readTuples, recipeSourceID } from "#recipes/scaffold";
|
|
12
|
+
import { defaultRecipeSource } from "#recipes/sources";
|
|
13
|
+
import { SourceRegister } from "#registers";
|
|
14
|
+
import { SurfaceOrigin } from "#types";
|
|
15
|
+
const SOURCE = defaultRecipeSource("synth-sg-register");
|
|
16
|
+
/**
|
|
17
|
+
* Street generics and their typed abbreviations.
|
|
18
|
+
*/
|
|
19
|
+
const GENERIC_ABBREVIATIONS = [
|
|
20
|
+
["Avenue", "Ave"],
|
|
21
|
+
["Road", "Rd"],
|
|
22
|
+
["Street", "St"],
|
|
23
|
+
["Drive", "Dr"],
|
|
24
|
+
["Crescent", "Cres"],
|
|
25
|
+
["Lane", "Ln"],
|
|
26
|
+
["Boulevard", "Blvd"],
|
|
27
|
+
["Terrace", "Ter"],
|
|
28
|
+
["Place", "Pl"],
|
|
29
|
+
["Close", "Cl"],
|
|
30
|
+
["Walk", "Wk"],
|
|
31
|
+
];
|
|
32
|
+
/**
|
|
33
|
+
* Name endings that mark an estate or area in the source `unit` field.
|
|
34
|
+
*
|
|
35
|
+
* People do not write an estate name before an address line, so the recipe
|
|
36
|
+
* renders only building names as a `venue`.
|
|
37
|
+
*/
|
|
38
|
+
const ESTATE_TAILS = ["ESTATE", "CONSERVATION AREA", "HILLS", "PARK", "GARDENS", "GARDEN", "HEIGHTS", "GROVE", "VILLE"];
|
|
39
|
+
// The official form receives the probability left after the block, bracketed-postcode and building-led forms.
|
|
40
|
+
const P_BLOCK = 0.4;
|
|
41
|
+
const P_BRACKET_POSTCODE = 0.25;
|
|
42
|
+
const P_BUILDING_LED = 0.15;
|
|
43
|
+
const P_ABBREVIATE = 0.35;
|
|
44
|
+
const P_UPPER = 0.1;
|
|
45
|
+
// The source rarely includes a floor-unit, so the recipe synthesizes one within these bounds.
|
|
46
|
+
const FLOOR_MAX = 30;
|
|
47
|
+
const UNIT_MAX = 399;
|
|
48
|
+
/**
|
|
49
|
+
* The draw value that selects each form in {@link renderSGRegister} when a caller requests that form.
|
|
50
|
+
*/
|
|
51
|
+
const REGISTER_DRAW = {
|
|
52
|
+
block: 0,
|
|
53
|
+
bracket_postcode: P_BLOCK,
|
|
54
|
+
building_led: P_BLOCK + P_BRACKET_POSTCODE,
|
|
55
|
+
official: 1,
|
|
56
|
+
};
|
|
57
|
+
/**
|
|
58
|
+
* Abbreviates the first street generic that the street contains, such as
|
|
59
|
+
* `Ang Mo Kio Avenue 3` to `Ang Mo Kio Ave 3`.
|
|
60
|
+
*/
|
|
61
|
+
export function abbreviateSGStreet(street) {
|
|
62
|
+
for (const [full, short] of GENERIC_ABBREVIATIONS) {
|
|
63
|
+
const pattern = new RegExp(`\\b${full}\\b`, "u");
|
|
64
|
+
if (pattern.test(street))
|
|
65
|
+
return street.replace(pattern, short);
|
|
66
|
+
}
|
|
67
|
+
return street;
|
|
68
|
+
}
|
|
69
|
+
/**
|
|
70
|
+
* Reports whether the source `unit` value looks like a building name that can lead a line.
|
|
71
|
+
*
|
|
72
|
+
* The check rejects `NIL`, single words, values with a digit or parenthesis, plus estate names.
|
|
73
|
+
*/
|
|
74
|
+
export function isBuildingName(unit) {
|
|
75
|
+
const value = unit.trim().toUpperCase();
|
|
76
|
+
if (!value || value === "NIL" || /[\d()]/u.test(value) || !/\s/u.test(value))
|
|
77
|
+
return false;
|
|
78
|
+
return !ESTATE_TAILS.some((tail) => value.endsWith(tail));
|
|
79
|
+
}
|
|
80
|
+
/**
|
|
81
|
+
* Renders one source row in a sampled or requested form.
|
|
82
|
+
*
|
|
83
|
+
* All randomness comes from `random`.
|
|
84
|
+
* A requested `building_led` form falls back to `official` when the row's `unit` is not a building name.
|
|
85
|
+
*
|
|
86
|
+
* A requested `block` form falls back to `bracket_postcode` when the row's number is not a block number.
|
|
87
|
+
* `Blk` and the `S(` and `)` around a postcode stay untagged.
|
|
88
|
+
*/
|
|
89
|
+
export function renderSGRegister(row, random, register) {
|
|
90
|
+
const street0 = titleCaseIfUpper(row.street);
|
|
91
|
+
const street = random() < P_ABBREVIATE ? abbreviateSGStreet(street0) : street0;
|
|
92
|
+
const drawn = random();
|
|
93
|
+
const building = isBuildingName(row.unit) ? titleCaseIfUpper(row.unit) : null;
|
|
94
|
+
const draw = register === undefined ? drawn : REGISTER_DRAW[register];
|
|
95
|
+
let raw;
|
|
96
|
+
let rendered;
|
|
97
|
+
const components = { house_number: row.number, street, postcode: row.postcode };
|
|
98
|
+
if (draw < P_BLOCK && /^\d+[A-Z]?$/u.test(row.number)) {
|
|
99
|
+
const floor = String(1 + Math.floor(random() * FLOOR_MAX)).padStart(2, "0");
|
|
100
|
+
const unitNo = String(1 + Math.floor(random() * UNIT_MAX)).padStart(2, "0");
|
|
101
|
+
const unit = `#${floor}-${unitNo}`;
|
|
102
|
+
raw = `Blk ${row.number} ${street} ${unit} Singapore ${row.postcode}`;
|
|
103
|
+
components.unit = unit;
|
|
104
|
+
components.locality = "Singapore";
|
|
105
|
+
rendered = "block";
|
|
106
|
+
}
|
|
107
|
+
else if (draw < P_BLOCK + P_BRACKET_POSTCODE) {
|
|
108
|
+
raw = `${row.number} ${street} S(${row.postcode})`;
|
|
109
|
+
rendered = "bracket_postcode";
|
|
110
|
+
}
|
|
111
|
+
else if (draw < P_BLOCK + P_BRACKET_POSTCODE + P_BUILDING_LED && building) {
|
|
112
|
+
raw = `${building}, ${row.number} ${street}, Singapore ${row.postcode}`;
|
|
113
|
+
components.venue = building;
|
|
114
|
+
components.locality = "Singapore";
|
|
115
|
+
rendered = "building_led";
|
|
116
|
+
}
|
|
117
|
+
else {
|
|
118
|
+
raw = `${row.number} ${street} Singapore ${row.postcode}`;
|
|
119
|
+
components.locality = "Singapore";
|
|
120
|
+
rendered = "official";
|
|
121
|
+
}
|
|
122
|
+
if (random() < P_UPPER) {
|
|
123
|
+
raw = raw.toUpperCase();
|
|
124
|
+
for (const key of Object.keys(components)) {
|
|
125
|
+
components[key] = components[key].toUpperCase();
|
|
126
|
+
}
|
|
127
|
+
}
|
|
128
|
+
return { raw, components, register: rendered };
|
|
129
|
+
}
|
|
130
|
+
/**
|
|
131
|
+
* Renders each Overture Singapore corpus row from `--input` once in a sampled typed form.
|
|
132
|
+
*
|
|
133
|
+
* The recipe skips rows without a street, a block-style number, or a six-digit postcode.
|
|
134
|
+
*/
|
|
135
|
+
export const sgRegisterRecipe = {
|
|
136
|
+
name: "sg-register",
|
|
137
|
+
description: "Singapore typed registers over the Overture-SG rows: the HDB block line with a #NN-NN unit, the S(NNNNNN) postcode, the building-led line",
|
|
138
|
+
mode: "tuples",
|
|
139
|
+
options: [
|
|
140
|
+
{ flag: "--count", description: "Rows to emit (default: every input row once)" },
|
|
141
|
+
{ flag: "--input", description: "The Overture-SG corpus JSONL ({ street, number, unit, postcode, locality })" },
|
|
142
|
+
],
|
|
143
|
+
async run(opts, write) {
|
|
144
|
+
if (!opts.input) {
|
|
145
|
+
throw new Error("sg-register: --input <overture-sg.corpus.jsonl> is required");
|
|
146
|
+
}
|
|
147
|
+
const random = makeMulberry32(opts.seed);
|
|
148
|
+
const source = opts.sourceName ?? SOURCE;
|
|
149
|
+
const registers = {};
|
|
150
|
+
let read = 0;
|
|
151
|
+
let emitted = 0;
|
|
152
|
+
let skipped = 0;
|
|
153
|
+
let quarantined = 0;
|
|
154
|
+
for await (const tuple of readTuples(opts.input)) {
|
|
155
|
+
read++;
|
|
156
|
+
if (opts.count !== undefined && emitted >= opts.count)
|
|
157
|
+
break;
|
|
158
|
+
const street = typeof tuple["street"] === "string" ? tuple["street"].trim() : "";
|
|
159
|
+
const number = typeof tuple["number"] === "string" ? tuple["number"].trim() : "";
|
|
160
|
+
const postcode = typeof tuple["postcode"] === "string" ? tuple["postcode"].trim() : "";
|
|
161
|
+
const unit = typeof tuple["unit"] === "string" ? tuple["unit"].trim() : "";
|
|
162
|
+
if (!street || !/^\d+[A-Z]?$/u.test(number) || !/^\d{6}$/u.test(postcode)) {
|
|
163
|
+
skipped++;
|
|
164
|
+
continue;
|
|
165
|
+
}
|
|
166
|
+
const rendering = renderSGRegister({ street, number, unit, postcode }, random);
|
|
167
|
+
if (opts.golden) {
|
|
168
|
+
const golden = { raw: rendering.raw, components: rendering.components, country: "SG", locale: "en-SG" };
|
|
169
|
+
write(stringifyJSON(golden));
|
|
170
|
+
emitted++;
|
|
171
|
+
registers[rendering.register] = (registers[rendering.register] ?? 0) + 1;
|
|
172
|
+
continue;
|
|
173
|
+
}
|
|
174
|
+
const ok = alignAndWrite(write, {
|
|
175
|
+
raw: rendering.raw,
|
|
176
|
+
components: rendering.components,
|
|
177
|
+
country: "SG",
|
|
178
|
+
locale: "en-SG",
|
|
179
|
+
source,
|
|
180
|
+
source_id: recipeSourceID(source, { raw: rendering.raw }),
|
|
181
|
+
corpus_version: "0.1.0",
|
|
182
|
+
license: "CDLA-Permissive-2.0 — Overture Maps addresses over the Singapore Open Data Licence 1.0 (OneMap / Singapore Land Authority)",
|
|
183
|
+
}, `sg-register:${rendering.register}`,
|
|
184
|
+
// The values come from Overture and the recipe chose only their arrangement,
|
|
185
|
+
// so the Overture record behind each row is what `baseSourceID` names
|
|
186
|
+
// when the tuples file includes its id.
|
|
187
|
+
{
|
|
188
|
+
register: SourceRegister.Overture,
|
|
189
|
+
surface: SurfaceOrigin.Composed,
|
|
190
|
+
baseSourceID: tuple.sourceID ?? null,
|
|
191
|
+
});
|
|
192
|
+
if (ok) {
|
|
193
|
+
emitted++;
|
|
194
|
+
registers[rendering.register] = (registers[rendering.register] ?? 0) + 1;
|
|
195
|
+
}
|
|
196
|
+
else {
|
|
197
|
+
quarantined++;
|
|
198
|
+
}
|
|
199
|
+
}
|
|
200
|
+
console.error(` sg-register: ${emitted} emitted (${Object.entries(registers)
|
|
201
|
+
.map(([k, v]) => `${k} ${v}`)
|
|
202
|
+
.join(", ")}), ${skipped} skipped, ${quarantined} quarantined of ${read} read`);
|
|
203
|
+
return { read, emitted, skipped };
|
|
204
|
+
},
|
|
205
|
+
};
|
|
206
|
+
//# sourceMappingURL=register.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"register.js","sourceRoot":"","sources":["../../../lib/sg/recipes/register.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH,OAAO,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAA;AACpD,OAAO,EAAE,UAAU,IAAI,cAAc,EAAE,MAAM,uBAAuB,CAAA;AACpE,OAAO,EAAE,gBAAgB,EAAE,MAAM,aAAa,CAAA;AAE9C,OAAO,EAAE,aAAa,EAAqB,UAAU,EAAE,cAAc,EAAE,MAAM,mBAAmB,CAAA;AAChG,OAAO,EAAE,mBAAmB,EAAE,MAAM,kBAAkB,CAAA;AACtD,OAAO,EAAE,cAAc,EAAE,MAAM,YAAY,CAAA;AAC3C,OAAO,EAAE,aAAa,EAAE,MAAM,QAAQ,CAAA;AAEtC,MAAM,MAAM,GAAG,mBAAmB,CAAC,mBAAmB,CAAC,CAAA;AAEvD;;GAEG;AACH,MAAM,qBAAqB,GAA0D;IACpF,CAAC,QAAQ,EAAE,KAAK,CAAC;IACjB,CAAC,MAAM,EAAE,IAAI,CAAC;IACd,CAAC,QAAQ,EAAE,IAAI,CAAC;IAChB,CAAC,OAAO,EAAE,IAAI,CAAC;IACf,CAAC,UAAU,EAAE,MAAM,CAAC;IACpB,CAAC,MAAM,EAAE,IAAI,CAAC;IACd,CAAC,WAAW,EAAE,MAAM,CAAC;IACrB,CAAC,SAAS,EAAE,KAAK,CAAC;IAClB,CAAC,OAAO,EAAE,IAAI,CAAC;IACf,CAAC,OAAO,EAAE,IAAI,CAAC;IACf,CAAC,MAAM,EAAE,IAAI,CAAC;CACd,CAAA;AAED;;;;;GAKG;AACH,MAAM,YAAY,GAAG,CAAC,QAAQ,EAAE,mBAAmB,EAAE,OAAO,EAAE,MAAM,EAAE,SAAS,EAAE,QAAQ,EAAE,SAAS,EAAE,OAAO,EAAE,OAAO,CAAC,CAAA;AAEvH,8GAA8G;AAC9G,MAAM,OAAO,GAAG,GAAG,CAAA;AACnB,MAAM,kBAAkB,GAAG,IAAI,CAAA;AAC/B,MAAM,cAAc,GAAG,IAAI,CAAA;AAC3B,MAAM,YAAY,GAAG,IAAI,CAAA;AACzB,MAAM,OAAO,GAAG,GAAG,CAAA;AAEnB,8FAA8F;AAC9F,MAAM,SAAS,GAAG,EAAE,CAAA;AACpB,MAAM,QAAQ,GAAG,GAAG,CAAA;AAEpB;;GAEG;AACH,MAAM,aAAa,GAA+B;IACjD,KAAK,EAAE,CAAC;IACR,gBAAgB,EAAE,OAAO;IACzB,YAAY,EAAE,OAAO,GAAG,kBAAkB;IAC1C,QAAQ,EAAE,CAAC;CACX,CAAA;AAED;;;GAGG;AACH,MAAM,UAAU,kBAAkB,CAAC,MAAc;IAChD,KAAK,MAAM,CAAC,IAAI,EAAE,KAAK,CAAC,IAAI,qBAAqB,EAAE,CAAC;QACnD,MAAM,OAAO,GAAG,IAAI,MAAM,CAAC,MAAM,IAAI,KAAK,EAAE,GAAG,CAAC,CAAA;QAEhD,IAAI,OAAO,CAAC,IAAI,CAAC,MAAM,CAAC;YAAE,OAAO,MAAM,CAAC,OAAO,CAAC,OAAO,EAAE,KAAK,CAAC,CAAA;IAChE,CAAC;IAED,OAAO,MAAM,CAAA;AACd,CAAC;AAED;;;;GAIG;AACH,MAAM,UAAU,cAAc,CAAC,IAAY;IAC1C,MAAM,KAAK,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAA;IAEvC,IAAI,CAAC,KAAK,IAAI,KAAK,KAAK,KAAK,IAAI,SAAS,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC;QAAE,OAAO,KAAK,CAAA;IAE1F,OAAO,CAAC,YAAY,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAA;AAC1D,CAAC;AAuBD;;;;;;;;GAQG;AACH,MAAM,UAAU,gBAAgB,CAAC,GAAU,EAAE,MAAoB,EAAE,QAAqB;IACvF,MAAM,OAAO,GAAG,gBAAgB,CAAC,GAAG,CAAC,MAAM,CAAC,CAAA;IAC5C,MAAM,MAAM,GAAG,MAAM,EAAE,GAAG,YAAY,CAAC,CAAC,CAAC,kBAAkB,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,OAAO,CAAA;IAC9E,MAAM,KAAK,GAAG,MAAM,EAAE,CAAA;IACtB,MAAM,QAAQ,GAAG,cAAc,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,gBAAgB,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAA;IAC7E,MAAM,IAAI,GAAG,QAAQ,KAAK,SAAS,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,aAAa,CAAC,QAAQ,CAAC,CAAA;IAErE,IAAI,GAAW,CAAA;IACf,IAAI,QAAoB,CAAA;IACxB,MAAM,UAAU,GAA2B,EAAE,YAAY,EAAE,GAAG,CAAC,MAAM,EAAE,MAAM,EAAE,QAAQ,EAAE,GAAG,CAAC,QAAQ,EAAE,CAAA;IAEvG,IAAI,IAAI,GAAG,OAAO,IAAI,cAAc,CAAC,IAAI,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC;QACvD,MAAM,KAAK,GAAG,MAAM,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,SAAS,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAA;QAC3E,MAAM,MAAM,GAAG,MAAM,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,QAAQ,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,CAAA;QAC3E,MAAM,IAAI,GAAG,IAAI,KAAK,IAAI,MAAM,EAAE,CAAA;QAElC,GAAG,GAAG,OAAO,GAAG,CAAC,MAAM,IAAI,MAAM,IAAI,IAAI,cAAc,GAAG,CAAC,QAAQ,EAAE,CAAA;QACrE,UAAU,CAAC,IAAI,GAAG,IAAI,CAAA;QACtB,UAAU,CAAC,QAAQ,GAAG,WAAW,CAAA;QACjC,QAAQ,GAAG,OAAO,CAAA;IACnB,CAAC;SAAM,IAAI,IAAI,GAAG,OAAO,GAAG,kBAAkB,EAAE,CAAC;QAChD,GAAG,GAAG,GAAG,GAAG,CAAC,MAAM,IAAI,MAAM,MAAM,GAAG,CAAC,QAAQ,GAAG,CAAA;QAClD,QAAQ,GAAG,kBAAkB,CAAA;IAC9B,CAAC;SAAM,IAAI,IAAI,GAAG,OAAO,GAAG,kBAAkB,GAAG,cAAc,IAAI,QAAQ,EAAE,CAAC;QAC7E,GAAG,GAAG,GAAG,QAAQ,KAAK,GAAG,CAAC,MAAM,IAAI,MAAM,eAAe,GAAG,CAAC,QAAQ,EAAE,CAAA;QACvE,UAAU,CAAC,KAAK,GAAG,QAAQ,CAAA;QAC3B,UAAU,CAAC,QAAQ,GAAG,WAAW,CAAA;QACjC,QAAQ,GAAG,cAAc,CAAA;IAC1B,CAAC;SAAM,CAAC;QACP,GAAG,GAAG,GAAG,GAAG,CAAC,MAAM,IAAI,MAAM,cAAc,GAAG,CAAC,QAAQ,EAAE,CAAA;QACzD,UAAU,CAAC,QAAQ,GAAG,WAAW,CAAA;QACjC,QAAQ,GAAG,UAAU,CAAA;IACtB,CAAC;IAED,IAAI,MAAM,EAAE,GAAG,OAAO,EAAE,CAAC;QACxB,GAAG,GAAG,GAAG,CAAC,WAAW,EAAE,CAAA;QAEvB,KAAK,MAAM,GAAG,IAAI,MAAM,CAAC,IAAI,CAAC,UAAU,CAAC,EAAE,CAAC;YAC3C,UAAU,CAAC,GAAG,CAAC,GAAG,UAAU,CAAC,GAAG,CAAE,CAAC,WAAW,EAAE,CAAA;QACjD,CAAC;IACF,CAAC;IAED,OAAO,EAAE,GAAG,EAAE,UAAU,EAAE,QAAQ,EAAE,QAAQ,EAAE,CAAA;AAC/C,CAAC;AAED;;;;GAIG;AACH,MAAM,CAAC,MAAM,gBAAgB,GAAiB;IAC7C,IAAI,EAAE,aAAa;IACnB,WAAW,EACV,2IAA2I;IAC5I,IAAI,EAAE,QAAQ;IACd,OAAO,EAAE;QACR,EAAE,IAAI,EAAE,SAAS,EAAE,WAAW,EAAE,8CAA8C,EAAE;QAChF,EAAE,IAAI,EAAE,SAAS,EAAE,WAAW,EAAE,6EAA6E,EAAE;KAC/G;IACD,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,IAAI,CAAC,IAAI,CAAC,KAAK,EAAE,CAAC;YACjB,MAAM,IAAI,KAAK,CAAC,6DAA6D,CAAC,CAAA;QAC/E,CAAC;QAED,MAAM,MAAM,GAAG,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACxC,MAAM,MAAM,GAAG,IAAI,CAAC,UAAU,IAAI,MAAM,CAAA;QACxC,MAAM,SAAS,GAA2B,EAAE,CAAA;QAC5C,IAAI,IAAI,GAAG,CAAC,CAAA;QACZ,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,WAAW,GAAG,CAAC,CAAA;QAEnB,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,UAAU,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;YAClD,IAAI,EAAE,CAAA;YAEN,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;gBAAE,MAAK;YAE5D,MAAM,MAAM,GAAG,OAAO,KAAK,CAAC,QAAQ,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;YAChF,MAAM,MAAM,GAAG,OAAO,KAAK,CAAC,QAAQ,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;YAChF,MAAM,QAAQ,GAAG,OAAO,KAAK,CAAC,UAAU,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,UAAU,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;YACtF,MAAM,IAAI,GAAG,OAAO,KAAK,CAAC,MAAM,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;YAE1E,IAAI,CAAC,MAAM,IAAI,CAAC,cAAc,CAAC,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,UAAU,CAAC,IAAI,CAAC,QAAQ,CAAC,EAAE,CAAC;gBAC3E,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,MAAM,SAAS,GAAG,gBAAgB,CAAC,EAAE,MAAM,EAAE,MAAM,EAAE,IAAI,EAAE,QAAQ,EAAE,EAAE,MAAM,CAAC,CAAA;YAE9E,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC;gBACjB,MAAM,MAAM,GAAG,EAAE,GAAG,EAAE,SAAS,CAAC,GAAG,EAAE,UAAU,EAAE,SAAS,CAAC,UAAU,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,EAAE,OAAO,EAAE,CAAA;gBAEvG,KAAK,CAAC,aAAa,CAAC,MAAM,CAAC,CAAC,CAAA;gBAE5B,OAAO,EAAE,CAAA;gBACT,SAAS,CAAC,SAAS,CAAC,QAAQ,CAAC,GAAG,CAAC,SAAS,CAAC,SAAS,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAA;gBAExE,SAAQ;YACT,CAAC;YAED,MAAM,EAAE,GAAG,aAAa,CACvB,KAAK,EACL;gBACC,GAAG,EAAE,SAAS,CAAC,GAAG;gBAClB,UAAU,EAAE,SAAS,CAAC,UAAU;gBAChC,OAAO,EAAE,IAAI;gBACb,MAAM,EAAE,OAAO;gBACf,MAAM;gBACN,SAAS,EAAE,cAAc,CAAC,MAAM,EAAE,EAAE,GAAG,EAAE,SAAS,CAAC,GAAG,EAAE,CAAC;gBACzD,cAAc,EAAE,OAAO;gBACvB,OAAO,EACN,4HAA4H;aAC7H,EACD,eAAe,SAAS,CAAC,QAAQ,EAAE;YACnC,6EAA6E;YAC7E,sEAAsE;YACtE,wCAAwC;YACxC;gBACC,QAAQ,EAAE,cAAc,CAAC,QAAQ;gBACjC,OAAO,EAAE,aAAa,CAAC,QAAQ;gBAC/B,YAAY,EAAE,KAAK,CAAC,QAAQ,IAAI,IAAI;aACpC,CACD,CAAA;YAED,IAAI,EAAE,EAAE,CAAC;gBACR,OAAO,EAAE,CAAA;gBACT,SAAS,CAAC,SAAS,CAAC,QAAQ,CAAC,GAAG,CAAC,SAAS,CAAC,SAAS,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAA;YACzE,CAAC;iBAAM,CAAC;gBACP,WAAW,EAAE,CAAA;YACd,CAAC;QACF,CAAC;QAED,OAAO,CAAC,KAAK,CACZ,kBAAkB,OAAO,aAAa,MAAM,CAAC,OAAO,CAAC,SAAS,CAAC;aAC7D,GAAG,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC;aAC5B,IAAI,CAAC,IAAI,CAAC,MAAM,OAAO,aAAa,WAAW,mBAAmB,IAAI,OAAO,CAC/E,CAAA;QAED,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;IAClC,CAAC;CACD,CAAA"}
|
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Fetches Singapore ACRA corporate-entity CSVs from data.gov.sg.
|
|
7
|
+
* The publisher includes fielded addresses in these files.
|
|
8
|
+
*/
|
|
9
|
+
import type { BaseFetchOptions, FetchSummary } from "#tools/fetch/download";
|
|
10
|
+
/**
|
|
11
|
+
* Options for {@link fetchACRASG}.
|
|
12
|
+
*/
|
|
13
|
+
export type FetchACRASGOptions = BaseFetchOptions;
|
|
14
|
+
/**
|
|
15
|
+
* Downloads every dataset in the ACRA collection and writes a collection manifest after each file.
|
|
16
|
+
*
|
|
17
|
+
* The function skips a file that the previous manifest lists and that still exists on disk.
|
|
18
|
+
*/
|
|
19
|
+
export declare function fetchACRASG(options: FetchACRASGOptions, report?: (line: string) => void): Promise<FetchSummary>;
|
|
20
|
+
//# sourceMappingURL=acra.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"acra.d.ts","sourceRoot":"","sources":["../../../../lib/sg/tools/fetch/acra.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAQH,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAA4C,MAAM,uBAAuB,CAAA;AAiBrH;;GAEG;AACH,MAAM,MAAM,kBAAkB,GAAG,gBAAgB,CAAA;AA8CjD;;;;GAIG;AACH,wBAAsB,WAAW,CAAC,OAAO,EAAE,kBAAkB,EAAE,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAAG,OAAO,CAAC,YAAY,CAAC,CAuFrH"}
|