@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
|
@@ -0,0 +1,62 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* The address register's key sets, the only thing a permit string is allowed to align against. The
|
|
7
|
+
* permit registry's address field is an `observation` a clerk typed without validation, so every part
|
|
8
|
+
* of a string — 시도, 시군구, road, 동, 리 — must be one the register lists under its parent.
|
|
9
|
+
*/
|
|
10
|
+
import { type JusoLabelRow } from "#kr/adapters/juso/label-rows";
|
|
11
|
+
/**
|
|
12
|
+
* The key sets keyed as the register nests them, as composite string keys rather than
|
|
13
|
+
* nested maps, because a nested map costs a second lookup on the hot path.
|
|
14
|
+
*/
|
|
15
|
+
export interface KeyIndex {
|
|
16
|
+
regions: Set<string>;
|
|
17
|
+
/**
|
|
18
|
+
* 시도 → its 시군구 names.
|
|
19
|
+
*/
|
|
20
|
+
sigunguByRegion: Map<string, Set<string>>;
|
|
21
|
+
/**
|
|
22
|
+
* 시도 and 시군구 → the unit's road names.
|
|
23
|
+
*/
|
|
24
|
+
roadsByUnit: Map<string, Set<string>>;
|
|
25
|
+
/**
|
|
26
|
+
* 시도 and 시군구 → the unit's 동 and 읍/면 names.
|
|
27
|
+
*/
|
|
28
|
+
dongsByUnit: Map<string, Set<string>>;
|
|
29
|
+
/**
|
|
30
|
+
* 시도, 시군구 and 동 → the 동's 리 names.
|
|
31
|
+
*/
|
|
32
|
+
risByDong: Map<string, Set<string>>;
|
|
33
|
+
}
|
|
34
|
+
/**
|
|
35
|
+
* The parts of a composite key, joined so no two different part lists produce the same key.
|
|
36
|
+
*/
|
|
37
|
+
export declare function unitKey(...parts: readonly string[]): string;
|
|
38
|
+
export declare function emptyKeyIndex(): KeyIndex;
|
|
39
|
+
/**
|
|
40
|
+
* Add one label row's names to the key sets.
|
|
41
|
+
*
|
|
42
|
+
* The 읍/면 joins the unit's 동 set as a road-form token, since the road address
|
|
43
|
+
* writes it between the 시군구 and the road.
|
|
44
|
+
*/
|
|
45
|
+
export declare function indexLabelRow(index: KeyIndex, row: JusoLabelRow): void;
|
|
46
|
+
/**
|
|
47
|
+
* Admit the pre-merger region names as aliases of the register's current one, sharing its
|
|
48
|
+
* sets by reference so a later `indexLabelRow` under either name reaches the same set.
|
|
49
|
+
*/
|
|
50
|
+
export declare function aliasKeyIndex(index: KeyIndex): void;
|
|
51
|
+
/**
|
|
52
|
+
* How many tokens from `start` form one of the region's 시군구 — 2 for `수원시 장안구`, 1 for `종로구`, 0 for none.
|
|
53
|
+
*
|
|
54
|
+
* Two-token first, because `수원시` by itself is also listed and taking it would
|
|
55
|
+
* leave `장안구` to be read as a road.
|
|
56
|
+
*/
|
|
57
|
+
export declare function sigunguSpan(index: KeyIndex, region: string, tokens: readonly string[], start: number): number;
|
|
58
|
+
/**
|
|
59
|
+
* The key sets the permit aligner reads, from one pass over the register rows.
|
|
60
|
+
*/
|
|
61
|
+
export declare function buildKeyIndex(rows: AsyncIterable<JusoLabelRow>): Promise<KeyIndex>;
|
|
62
|
+
//# sourceMappingURL=key-index.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"key-index.d.ts","sourceRoot":"","sources":["../../../../lib/kr/adapters/localdata/key-index.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAEH,OAAO,EAAE,KAAK,YAAY,EAAkB,MAAM,8BAA8B,CAAA;AAWhF;;;GAGG;AACH,MAAM,WAAW,QAAQ;IACxB,OAAO,EAAE,GAAG,CAAC,MAAM,CAAC,CAAA;IACpB;;OAEG;IACH,eAAe,EAAE,GAAG,CAAC,MAAM,EAAE,GAAG,CAAC,MAAM,CAAC,CAAC,CAAA;IACzC;;OAEG;IACH,WAAW,EAAE,GAAG,CAAC,MAAM,EAAE,GAAG,CAAC,MAAM,CAAC,CAAC,CAAA;IACrC;;OAEG;IACH,WAAW,EAAE,GAAG,CAAC,MAAM,EAAE,GAAG,CAAC,MAAM,CAAC,CAAC,CAAA;IACrC;;OAEG;IACH,SAAS,EAAE,GAAG,CAAC,MAAM,EAAE,GAAG,CAAC,MAAM,CAAC,CAAC,CAAA;CACnC;AAED;;GAEG;AACH,wBAAgB,OAAO,CAAC,GAAG,KAAK,EAAE,SAAS,MAAM,EAAE,GAAG,MAAM,CAE3D;AAED,wBAAgB,aAAa,IAAI,QAAQ,CAQxC;AAYD;;;;;GAKG;AACH,wBAAgB,aAAa,CAAC,KAAK,EAAE,QAAQ,EAAE,GAAG,EAAE,YAAY,GAAG,IAAI,CAmBtE;AAED;;;GAGG;AACH,wBAAgB,aAAa,CAAC,KAAK,EAAE,QAAQ,GAAG,IAAI,CAsCnD;AAED;;;;;GAKG;AACH,wBAAgB,WAAW,CAAC,KAAK,EAAE,QAAQ,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,SAAS,MAAM,EAAE,EAAE,KAAK,EAAE,MAAM,GAAG,MAAM,CAY7G;AAED;;GAEG;AACH,wBAAsB,aAAa,CAAC,IAAI,EAAE,aAAa,CAAC,YAAY,CAAC,GAAG,OAAO,CAAC,QAAQ,CAAC,CAUxF"}
|
|
@@ -0,0 +1,127 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* The address register's key sets, the only thing a permit string is allowed to align against. The
|
|
7
|
+
* permit registry's address field is an `observation` a clerk typed without validation, so every part
|
|
8
|
+
* of a string — 시도, 시군구, road, 동, 리 — must be one the register lists under its parent.
|
|
9
|
+
*/
|
|
10
|
+
import { REGION_ALIASES } from "#kr/adapters/juso/label-rows";
|
|
11
|
+
/**
|
|
12
|
+
* The separator between the parts of a composite key, written as an escape
|
|
13
|
+
* so no NUL byte enters the source.
|
|
14
|
+
*
|
|
15
|
+
* A space cannot serve, because a 시군구 is written with one (`수원시 장안구`)
|
|
16
|
+
* and `unitKey("A", "B C")` would collide with `unitKey("A B", "C")`.
|
|
17
|
+
*/
|
|
18
|
+
const UNIT_SEPARATOR = "\0";
|
|
19
|
+
/**
|
|
20
|
+
* The parts of a composite key, joined so no two different part lists produce the same key.
|
|
21
|
+
*/
|
|
22
|
+
export function unitKey(...parts) {
|
|
23
|
+
return parts.join(UNIT_SEPARATOR);
|
|
24
|
+
}
|
|
25
|
+
export function emptyKeyIndex() {
|
|
26
|
+
return {
|
|
27
|
+
regions: new Set(),
|
|
28
|
+
sigunguByRegion: new Map(),
|
|
29
|
+
roadsByUnit: new Map(),
|
|
30
|
+
dongsByUnit: new Map(),
|
|
31
|
+
risByDong: new Map(),
|
|
32
|
+
};
|
|
33
|
+
}
|
|
34
|
+
function add(map, key, value) {
|
|
35
|
+
const existing = map.get(key);
|
|
36
|
+
if (existing) {
|
|
37
|
+
existing.add(value);
|
|
38
|
+
}
|
|
39
|
+
else {
|
|
40
|
+
map.set(key, new Set([value]));
|
|
41
|
+
}
|
|
42
|
+
}
|
|
43
|
+
/**
|
|
44
|
+
* Add one label row's names to the key sets.
|
|
45
|
+
*
|
|
46
|
+
* The 읍/면 joins the unit's 동 set as a road-form token, since the road address
|
|
47
|
+
* writes it between the 시군구 and the road.
|
|
48
|
+
*/
|
|
49
|
+
export function indexLabelRow(index, row) {
|
|
50
|
+
index.regions.add(row.region);
|
|
51
|
+
add(index.sigunguByRegion, row.region, row.sigungu);
|
|
52
|
+
const unit = unitKey(row.region, row.sigungu);
|
|
53
|
+
add(index.roadsByUnit, unit, row.road);
|
|
54
|
+
if (row.eupmyeon) {
|
|
55
|
+
add(index.dongsByUnit, unit, row.eupmyeon);
|
|
56
|
+
}
|
|
57
|
+
if (row.dong) {
|
|
58
|
+
add(index.dongsByUnit, unit, row.dong);
|
|
59
|
+
if (row.ri) {
|
|
60
|
+
add(index.risByDong, unitKey(row.region, row.sigungu, row.dong), row.ri);
|
|
61
|
+
}
|
|
62
|
+
}
|
|
63
|
+
}
|
|
64
|
+
/**
|
|
65
|
+
* Admit the pre-merger region names as aliases of the register's current one, sharing its
|
|
66
|
+
* sets by reference so a later `indexLabelRow` under either name reaches the same set.
|
|
67
|
+
*/
|
|
68
|
+
export function aliasKeyIndex(index) {
|
|
69
|
+
for (const [legacy, current] of Object.entries(REGION_ALIASES)) {
|
|
70
|
+
if (!index.regions.has(current))
|
|
71
|
+
continue;
|
|
72
|
+
index.regions.add(legacy);
|
|
73
|
+
const sigungu = index.sigunguByRegion.get(current);
|
|
74
|
+
if (sigungu) {
|
|
75
|
+
index.sigunguByRegion.set(legacy, sigungu);
|
|
76
|
+
}
|
|
77
|
+
// oxlint-disable no-useless-spread -- each loop writes into the map it reads, so it walks a snapshot.
|
|
78
|
+
for (const [key, roads] of [...index.roadsByUnit]) {
|
|
79
|
+
const [region, unit] = key.split(UNIT_SEPARATOR);
|
|
80
|
+
if (region === current) {
|
|
81
|
+
index.roadsByUnit.set(unitKey(legacy, unit), roads);
|
|
82
|
+
}
|
|
83
|
+
}
|
|
84
|
+
for (const [key, dongs] of [...index.dongsByUnit]) {
|
|
85
|
+
const [region, unit] = key.split(UNIT_SEPARATOR);
|
|
86
|
+
if (region === current) {
|
|
87
|
+
index.dongsByUnit.set(unitKey(legacy, unit), dongs);
|
|
88
|
+
}
|
|
89
|
+
}
|
|
90
|
+
for (const [key, ris] of [...index.risByDong]) {
|
|
91
|
+
const [region, unit, dong] = key.split(UNIT_SEPARATOR);
|
|
92
|
+
if (region === current) {
|
|
93
|
+
index.risByDong.set(unitKey(legacy, unit, dong), ris);
|
|
94
|
+
}
|
|
95
|
+
}
|
|
96
|
+
// oxlint-enable no-useless-spread
|
|
97
|
+
}
|
|
98
|
+
}
|
|
99
|
+
/**
|
|
100
|
+
* How many tokens from `start` form one of the region's 시군구 — 2 for `수원시 장안구`, 1 for `종로구`, 0 for none.
|
|
101
|
+
*
|
|
102
|
+
* Two-token first, because `수원시` by itself is also listed and taking it would
|
|
103
|
+
* leave `장안구` to be read as a road.
|
|
104
|
+
*/
|
|
105
|
+
export function sigunguSpan(index, region, tokens, start) {
|
|
106
|
+
const candidates = index.sigunguByRegion.get(region);
|
|
107
|
+
if (!candidates)
|
|
108
|
+
return 0;
|
|
109
|
+
for (const width of [2, 1]) {
|
|
110
|
+
if (start + width <= tokens.length && candidates.has(tokens.slice(start, start + width).join(" "))) {
|
|
111
|
+
return width;
|
|
112
|
+
}
|
|
113
|
+
}
|
|
114
|
+
return 0;
|
|
115
|
+
}
|
|
116
|
+
/**
|
|
117
|
+
* The key sets the permit aligner reads, from one pass over the register rows.
|
|
118
|
+
*/
|
|
119
|
+
export async function buildKeyIndex(rows) {
|
|
120
|
+
const index = emptyKeyIndex();
|
|
121
|
+
for await (const row of rows) {
|
|
122
|
+
indexLabelRow(index, row);
|
|
123
|
+
}
|
|
124
|
+
aliasKeyIndex(index);
|
|
125
|
+
return index;
|
|
126
|
+
}
|
|
127
|
+
//# sourceMappingURL=key-index.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"key-index.js","sourceRoot":"","sources":["../../../../lib/kr/adapters/localdata/key-index.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAEH,OAAO,EAAqB,cAAc,EAAE,MAAM,8BAA8B,CAAA;AAEhF;;;;;;GAMG;AACH,MAAM,cAAc,GAAG,IAAI,CAAA;AA0B3B;;GAEG;AACH,MAAM,UAAU,OAAO,CAAC,GAAG,KAAwB;IAClD,OAAO,KAAK,CAAC,IAAI,CAAC,cAAc,CAAC,CAAA;AAClC,CAAC;AAED,MAAM,UAAU,aAAa;IAC5B,OAAO;QACN,OAAO,EAAE,IAAI,GAAG,EAAE;QAClB,eAAe,EAAE,IAAI,GAAG,EAAE;QAC1B,WAAW,EAAE,IAAI,GAAG,EAAE;QACtB,WAAW,EAAE,IAAI,GAAG,EAAE;QACtB,SAAS,EAAE,IAAI,GAAG,EAAE;KACpB,CAAA;AACF,CAAC;AAED,SAAS,GAAG,CAAC,GAA6B,EAAE,GAAW,EAAE,KAAa;IACrE,MAAM,QAAQ,GAAG,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;IAE7B,IAAI,QAAQ,EAAE,CAAC;QACd,QAAQ,CAAC,GAAG,CAAC,KAAK,CAAC,CAAA;IACpB,CAAC;SAAM,CAAC;QACP,GAAG,CAAC,GAAG,CAAC,GAAG,EAAE,IAAI,GAAG,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAA;IAC/B,CAAC;AACF,CAAC;AAED;;;;;GAKG;AACH,MAAM,UAAU,aAAa,CAAC,KAAe,EAAE,GAAiB;IAC/D,KAAK,CAAC,OAAO,CAAC,GAAG,CAAC,GAAG,CAAC,MAAM,CAAC,CAAA;IAC7B,GAAG,CAAC,KAAK,CAAC,eAAe,EAAE,GAAG,CAAC,MAAM,EAAE,GAAG,CAAC,OAAO,CAAC,CAAA;IAEnD,MAAM,IAAI,GAAG,OAAO,CAAC,GAAG,CAAC,MAAM,EAAE,GAAG,CAAC,OAAO,CAAC,CAAA;IAE7C,GAAG,CAAC,KAAK,CAAC,WAAW,EAAE,IAAI,EAAE,GAAG,CAAC,IAAI,CAAC,CAAA;IAEtC,IAAI,GAAG,CAAC,QAAQ,EAAE,CAAC;QAClB,GAAG,CAAC,KAAK,CAAC,WAAW,EAAE,IAAI,EAAE,GAAG,CAAC,QAAQ,CAAC,CAAA;IAC3C,CAAC;IAED,IAAI,GAAG,CAAC,IAAI,EAAE,CAAC;QACd,GAAG,CAAC,KAAK,CAAC,WAAW,EAAE,IAAI,EAAE,GAAG,CAAC,IAAI,CAAC,CAAA;QAEtC,IAAI,GAAG,CAAC,EAAE,EAAE,CAAC;YACZ,GAAG,CAAC,KAAK,CAAC,SAAS,EAAE,OAAO,CAAC,GAAG,CAAC,MAAM,EAAE,GAAG,CAAC,OAAO,EAAE,GAAG,CAAC,IAAI,CAAC,EAAE,GAAG,CAAC,EAAE,CAAC,CAAA;QACzE,CAAC;IACF,CAAC;AACF,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,aAAa,CAAC,KAAe;IAC5C,KAAK,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,cAAc,CAAC,EAAE,CAAC;QAChE,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,GAAG,CAAC,OAAO,CAAC;YAAE,SAAQ;QAEzC,KAAK,CAAC,OAAO,CAAC,GAAG,CAAC,MAAM,CAAC,CAAA;QAEzB,MAAM,OAAO,GAAG,KAAK,CAAC,eAAe,CAAC,GAAG,CAAC,OAAO,CAAC,CAAA;QAElD,IAAI,OAAO,EAAE,CAAC;YACb,KAAK,CAAC,eAAe,CAAC,GAAG,CAAC,MAAM,EAAE,OAAO,CAAC,CAAA;QAC3C,CAAC;QAED,sGAAsG;QACtG,KAAK,MAAM,CAAC,GAAG,EAAE,KAAK,CAAC,IAAI,CAAC,GAAG,KAAK,CAAC,WAAW,CAAC,EAAE,CAAC;YACnD,MAAM,CAAC,MAAM,EAAE,IAAI,CAAC,GAAG,GAAG,CAAC,KAAK,CAAC,cAAc,CAAC,CAAA;YAEhD,IAAI,MAAM,KAAK,OAAO,EAAE,CAAC;gBACxB,KAAK,CAAC,WAAW,CAAC,GAAG,CAAC,OAAO,CAAC,MAAM,EAAE,IAAK,CAAC,EAAE,KAAK,CAAC,CAAA;YACrD,CAAC;QACF,CAAC;QAED,KAAK,MAAM,CAAC,GAAG,EAAE,KAAK,CAAC,IAAI,CAAC,GAAG,KAAK,CAAC,WAAW,CAAC,EAAE,CAAC;YACnD,MAAM,CAAC,MAAM,EAAE,IAAI,CAAC,GAAG,GAAG,CAAC,KAAK,CAAC,cAAc,CAAC,CAAA;YAEhD,IAAI,MAAM,KAAK,OAAO,EAAE,CAAC;gBACxB,KAAK,CAAC,WAAW,CAAC,GAAG,CAAC,OAAO,CAAC,MAAM,EAAE,IAAK,CAAC,EAAE,KAAK,CAAC,CAAA;YACrD,CAAC;QACF,CAAC;QAED,KAAK,MAAM,CAAC,GAAG,EAAE,GAAG,CAAC,IAAI,CAAC,GAAG,KAAK,CAAC,SAAS,CAAC,EAAE,CAAC;YAC/C,MAAM,CAAC,MAAM,EAAE,IAAI,EAAE,IAAI,CAAC,GAAG,GAAG,CAAC,KAAK,CAAC,cAAc,CAAC,CAAA;YAEtD,IAAI,MAAM,KAAK,OAAO,EAAE,CAAC;gBACxB,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,OAAO,CAAC,MAAM,EAAE,IAAK,EAAE,IAAK,CAAC,EAAE,GAAG,CAAC,CAAA;YACxD,CAAC;QACF,CAAC;QACD,kCAAkC;IACnC,CAAC;AACF,CAAC;AAED;;;;;GAKG;AACH,MAAM,UAAU,WAAW,CAAC,KAAe,EAAE,MAAc,EAAE,MAAyB,EAAE,KAAa;IACpG,MAAM,UAAU,GAAG,KAAK,CAAC,eAAe,CAAC,GAAG,CAAC,MAAM,CAAC,CAAA;IAEpD,IAAI,CAAC,UAAU;QAAE,OAAO,CAAC,CAAA;IAEzB,KAAK,MAAM,KAAK,IAAI,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC;QAC5B,IAAI,KAAK,GAAG,KAAK,IAAI,MAAM,CAAC,MAAM,IAAI,UAAU,CAAC,GAAG,CAAC,MAAM,CAAC,KAAK,CAAC,KAAK,EAAE,KAAK,GAAG,KAAK,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC;YACpG,OAAO,KAAK,CAAA;QACb,CAAC;IACF,CAAC;IAED,OAAO,CAAC,CAAA;AACT,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,aAAa,CAAC,IAAiC;IACpE,MAAM,KAAK,GAAG,aAAa,EAAE,CAAA;IAE7B,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;QAC9B,aAAa,CAAC,KAAK,EAAE,GAAG,CAAC,CAAA;IAC1B,CAAC;IAED,aAAa,CAAC,KAAK,CAAC,CAAA;IAEpB,OAAO,KAAK,CAAA;AACb,CAAC"}
|
|
@@ -0,0 +1,73 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* The Korean permit registry (지방행정인허가데이터) as an `observation` source. It reads the delivered
|
|
7
|
+
* CSVs and turns an aligned string into a corpus row.
|
|
8
|
+
*
|
|
9
|
+
* The publisher delivers CP949, one file per business category, with both address systems typed by
|
|
10
|
+
* a clerk plus a planar coordinate in epsg:5174 and both postcodes. The adapter separates reading from
|
|
11
|
+
* aligning so the alignment rate per file can be measured before any row enters a corpus.
|
|
12
|
+
*/
|
|
13
|
+
import { type PathBuilderLike } from "path-ts";
|
|
14
|
+
import type { Aligned } from "#kr/adapters/localdata/align";
|
|
15
|
+
/**
|
|
16
|
+
* The source label stored on every row from this adapter.
|
|
17
|
+
* Configs use this label as the `source_weights` key.
|
|
18
|
+
*/
|
|
19
|
+
export declare const SOURCE = "localdata-kr";
|
|
20
|
+
/**
|
|
21
|
+
* Every permit in this registry is Korean.
|
|
22
|
+
* The publisher issues no others.
|
|
23
|
+
*/
|
|
24
|
+
export declare const COUNTRY = "KR";
|
|
25
|
+
/**
|
|
26
|
+
* The 영업상태명 of a business still trading.
|
|
27
|
+
*
|
|
28
|
+
* A closed one's address records somewhere that was.
|
|
29
|
+
*/
|
|
30
|
+
export declare const OPEN_STATUS = "\uC601\uC5C5/\uC815\uC0C1";
|
|
31
|
+
/**
|
|
32
|
+
* One permit, with both address systems as the clerk typed them.
|
|
33
|
+
*/
|
|
34
|
+
export interface PermitRow {
|
|
35
|
+
/**
|
|
36
|
+
* The file's basename: the business category the publisher splits by.
|
|
37
|
+
*/
|
|
38
|
+
category: string;
|
|
39
|
+
name: string;
|
|
40
|
+
status: string;
|
|
41
|
+
roadAddress: string;
|
|
42
|
+
lotAddress: string;
|
|
43
|
+
roadPostcode: string;
|
|
44
|
+
lotPostcode: string;
|
|
45
|
+
x: number | null;
|
|
46
|
+
y: number | null;
|
|
47
|
+
}
|
|
48
|
+
export interface ReadPermitOptions {
|
|
49
|
+
/**
|
|
50
|
+
* Keep only these 영업상태명 values.
|
|
51
|
+
*
|
|
52
|
+
* Empty admits every status.
|
|
53
|
+
*/
|
|
54
|
+
statuses?: readonly string[];
|
|
55
|
+
}
|
|
56
|
+
/**
|
|
57
|
+
* Stream every permit of one CSV.
|
|
58
|
+
*/
|
|
59
|
+
export declare function readPermitFile(path: PathBuilderLike, options?: ReadPermitOptions): AsyncGenerator<PermitRow>;
|
|
60
|
+
/**
|
|
61
|
+
* Stream every permit of every CSV in a directory, in filename order.
|
|
62
|
+
*/
|
|
63
|
+
export declare function readPermitDirectory(directory: PathBuilderLike, options?: ReadPermitOptions): AsyncGenerator<PermitRow>;
|
|
64
|
+
/**
|
|
65
|
+
* One aligned string as a row in the CJK corpus schema.
|
|
66
|
+
*
|
|
67
|
+
* The token labels are derived from the spans rather than stored beside them:
|
|
68
|
+
* a token is `B-<tag>` when its first character falls inside a span, `O` otherwise.
|
|
69
|
+
* A span covering several tokens labels only the token where it starts.
|
|
70
|
+
* The char-path trainer reads this label from each span.
|
|
71
|
+
*/
|
|
72
|
+
export declare function alignedToCJKRow(aligned: Aligned): Record<string, unknown>;
|
|
73
|
+
//# sourceMappingURL=permit-rows.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"permit-rows.d.ts","sourceRoot":"","sources":["../../../../lib/kr/adapters/localdata/permit-rows.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;GAWG;AAGH,OAAO,EAAqB,KAAK,eAAe,EAAsB,MAAM,SAAS,CAAA;AAIrF,OAAO,KAAK,EAAE,OAAO,EAAE,MAAM,8BAA8B,CAAA;AAE3D;;;GAGG;AACH,eAAO,MAAM,MAAM,iBAAiB,CAAA;AAEpC;;;GAGG;AACH,eAAO,MAAM,OAAO,OAAO,CAAA;AAE3B;;;;GAIG;AACH,eAAO,MAAM,WAAW,8BAAU,CAAA;AASlC;;GAEG;AACH,MAAM,WAAW,SAAS;IACzB;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAA;IAChB,IAAI,EAAE,MAAM,CAAA;IACZ,MAAM,EAAE,MAAM,CAAA;IACd,WAAW,EAAE,MAAM,CAAA;IACnB,UAAU,EAAE,MAAM,CAAA;IAClB,YAAY,EAAE,MAAM,CAAA;IACpB,WAAW,EAAE,MAAM,CAAA;IACnB,CAAC,EAAE,MAAM,GAAG,IAAI,CAAA;IAChB,CAAC,EAAE,MAAM,GAAG,IAAI,CAAA;CAChB;AA2BD,MAAM,WAAW,iBAAiB;IACjC;;;;OAIG;IACH,QAAQ,CAAC,EAAE,SAAS,MAAM,EAAE,CAAA;CAC5B;AAED;;GAEG;AACH,wBAAuB,cAAc,CACpC,IAAI,EAAE,eAAe,EACrB,OAAO,GAAE,iBAAsB,GAC7B,cAAc,CAAC,SAAS,CAAC,CA4B3B;AAED;;GAEG;AACH,wBAAuB,mBAAmB,CACzC,SAAS,EAAE,eAAe,EAC1B,OAAO,GAAE,iBAAsB,GAC7B,cAAc,CAAC,SAAS,CAAC,CAM3B;AAED;;;;;;;GAOG;AACH,wBAAgB,eAAe,CAAC,OAAO,EAAE,OAAO,GAAG,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAoCzE"}
|
|
@@ -0,0 +1,136 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* The Korean permit registry (지방행정인허가데이터) as an `observation` source. It reads the delivered
|
|
7
|
+
* CSVs and turns an aligned string into a corpus row.
|
|
8
|
+
*
|
|
9
|
+
* The publisher delivers CP949, one file per business category, with both address systems typed by
|
|
10
|
+
* a clerk plus a planar coordinate in epsg:5174 and both postcodes. The adapter separates reading from
|
|
11
|
+
* aligning so the alignment rate per file can be measured before any row enters a corpus.
|
|
12
|
+
*/
|
|
13
|
+
import { decodeByteStream, openReadStream } from "@mailwoman/core/fs/streams";
|
|
14
|
+
import { basename, extname, resolvePathBuilder } from "path-ts";
|
|
15
|
+
import { CSVSpliterator } from "spliterator";
|
|
16
|
+
import { Globerator } from "spliterator/node/fs";
|
|
17
|
+
/**
|
|
18
|
+
* The source label stored on every row from this adapter.
|
|
19
|
+
* Configs use this label as the `source_weights` key.
|
|
20
|
+
*/
|
|
21
|
+
export const SOURCE = "localdata-kr";
|
|
22
|
+
/**
|
|
23
|
+
* Every permit in this registry is Korean.
|
|
24
|
+
* The publisher issues no others.
|
|
25
|
+
*/
|
|
26
|
+
export const COUNTRY = "KR";
|
|
27
|
+
/**
|
|
28
|
+
* The 영업상태명 of a business still trading.
|
|
29
|
+
*
|
|
30
|
+
* A closed one's address records somewhere that was.
|
|
31
|
+
*/
|
|
32
|
+
export const OPEN_STATUS = "영업/정상";
|
|
33
|
+
/**
|
|
34
|
+
* The publisher's encoding.
|
|
35
|
+
*
|
|
36
|
+
* `cp949` rather than `euc-kr` for the reason `decodeByteStream` states.
|
|
37
|
+
*/
|
|
38
|
+
const ENCODING = "cp949";
|
|
39
|
+
/**
|
|
40
|
+
* The first of these column spellings present in the row, trimmed, or the empty string.
|
|
41
|
+
*
|
|
42
|
+
* The publisher's older and newer exports name the same field differently — `도로명주소`
|
|
43
|
+
* against `도로명전체주소`, `좌표정보(X)` against `좌표정보(x)` — and a directory holds both vintages,
|
|
44
|
+
* so each field names every spelling it has been delivered under.
|
|
45
|
+
*/
|
|
46
|
+
function firstColumn(row, ...names) {
|
|
47
|
+
for (const name of names) {
|
|
48
|
+
const value = row[name];
|
|
49
|
+
if (value !== undefined && value !== null)
|
|
50
|
+
return String(value).trim();
|
|
51
|
+
}
|
|
52
|
+
return "";
|
|
53
|
+
}
|
|
54
|
+
function toNumber(value) {
|
|
55
|
+
if (!value.trim())
|
|
56
|
+
return null;
|
|
57
|
+
const parsed = Number(value);
|
|
58
|
+
return Number.isFinite(parsed) ? parsed : null;
|
|
59
|
+
}
|
|
60
|
+
/**
|
|
61
|
+
* Stream every permit of one CSV.
|
|
62
|
+
*/
|
|
63
|
+
export async function* readPermitFile(path, options = {}) {
|
|
64
|
+
const wanted = new Set(options.statuses ?? [OPEN_STATUS]);
|
|
65
|
+
const file = path.toString();
|
|
66
|
+
const category = basename(file, extname(file));
|
|
67
|
+
const bytes = openReadStream(path);
|
|
68
|
+
for await (const row of CSVSpliterator.fromAsync(decodeByteStream(bytes, ENCODING))) {
|
|
69
|
+
const status = firstColumn(row, "영업상태명");
|
|
70
|
+
if (wanted.size && !wanted.has(status))
|
|
71
|
+
continue;
|
|
72
|
+
const roadAddress = firstColumn(row, "도로명주소", "도로명전체주소");
|
|
73
|
+
const lotAddress = firstColumn(row, "지번주소", "소재지전체주소");
|
|
74
|
+
if (!roadAddress && !lotAddress)
|
|
75
|
+
continue;
|
|
76
|
+
yield {
|
|
77
|
+
category,
|
|
78
|
+
name: firstColumn(row, "사업장명"),
|
|
79
|
+
status,
|
|
80
|
+
roadAddress,
|
|
81
|
+
lotAddress,
|
|
82
|
+
roadPostcode: firstColumn(row, "도로명우편번호"),
|
|
83
|
+
lotPostcode: firstColumn(row, "소재지우편번호"),
|
|
84
|
+
x: toNumber(firstColumn(row, "좌표정보(X)", "좌표정보(x)")),
|
|
85
|
+
y: toNumber(firstColumn(row, "좌표정보(Y)", "좌표정보(y)")),
|
|
86
|
+
};
|
|
87
|
+
}
|
|
88
|
+
}
|
|
89
|
+
/**
|
|
90
|
+
* Stream every permit of every CSV in a directory, in filename order.
|
|
91
|
+
*/
|
|
92
|
+
export async function* readPermitDirectory(directory, options = {}) {
|
|
93
|
+
const files = await Globerator.files("csv", { cwd: directory, absolute: false, recursive: false }).toSorted();
|
|
94
|
+
for (const name of files) {
|
|
95
|
+
yield* readPermitFile(resolvePathBuilder(directory, name), options);
|
|
96
|
+
}
|
|
97
|
+
}
|
|
98
|
+
/**
|
|
99
|
+
* One aligned string as a row in the CJK corpus schema.
|
|
100
|
+
*
|
|
101
|
+
* The token labels are derived from the spans rather than stored beside them:
|
|
102
|
+
* a token is `B-<tag>` when its first character falls inside a span, `O` otherwise.
|
|
103
|
+
* A span covering several tokens labels only the token where it starts.
|
|
104
|
+
* The char-path trainer reads this label from each span.
|
|
105
|
+
*/
|
|
106
|
+
export function alignedToCJKRow(aligned) {
|
|
107
|
+
const raw = aligned.raw;
|
|
108
|
+
const tokens = [];
|
|
109
|
+
const labels = [];
|
|
110
|
+
let cursor = 0;
|
|
111
|
+
for (const token of raw.split(/\s+/u).filter((piece) => piece.length)) {
|
|
112
|
+
const index = raw.indexOf(token, cursor);
|
|
113
|
+
cursor = index + token.length;
|
|
114
|
+
let label = "O";
|
|
115
|
+
for (let span = 0; span < aligned.spanStarts.length; span += 1) {
|
|
116
|
+
if (aligned.spanStarts[span] <= index && index < aligned.spanEnds[span]) {
|
|
117
|
+
label = `B-${aligned.spanTags[span]}`;
|
|
118
|
+
break;
|
|
119
|
+
}
|
|
120
|
+
}
|
|
121
|
+
tokens.push(token);
|
|
122
|
+
labels.push(label);
|
|
123
|
+
}
|
|
124
|
+
return {
|
|
125
|
+
raw,
|
|
126
|
+
tokens,
|
|
127
|
+
labels,
|
|
128
|
+
span_starts: [...aligned.spanStarts],
|
|
129
|
+
span_ends: [...aligned.spanEnds],
|
|
130
|
+
span_tags: [...aligned.spanTags],
|
|
131
|
+
country: COUNTRY,
|
|
132
|
+
source: SOURCE,
|
|
133
|
+
register: aligned.register,
|
|
134
|
+
};
|
|
135
|
+
}
|
|
136
|
+
//# sourceMappingURL=permit-rows.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"permit-rows.js","sourceRoot":"","sources":["../../../../lib/kr/adapters/localdata/permit-rows.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;GAWG;AAEH,OAAO,EAAE,gBAAgB,EAAE,cAAc,EAAE,MAAM,4BAA4B,CAAA;AAC7E,OAAO,EAAE,QAAQ,EAAE,OAAO,EAAwB,kBAAkB,EAAE,MAAM,SAAS,CAAA;AACrF,OAAO,EAAE,cAAc,EAAE,MAAM,aAAa,CAAA;AAC5C,OAAO,EAAE,UAAU,EAAE,MAAM,qBAAqB,CAAA;AAIhD;;;GAGG;AACH,MAAM,CAAC,MAAM,MAAM,GAAG,cAAc,CAAA;AAEpC;;;GAGG;AACH,MAAM,CAAC,MAAM,OAAO,GAAG,IAAI,CAAA;AAE3B;;;;GAIG;AACH,MAAM,CAAC,MAAM,WAAW,GAAG,OAAO,CAAA;AAElC;;;;GAIG;AACH,MAAM,QAAQ,GAAG,OAAO,CAAA;AAoBxB;;;;;;GAMG;AACH,SAAS,WAAW,CAAC,GAAuC,EAAE,GAAG,KAAwB;IACxF,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QAC1B,MAAM,KAAK,GAAG,GAAG,CAAC,IAAI,CAAC,CAAA;QAEvB,IAAI,KAAK,KAAK,SAAS,IAAI,KAAK,KAAK,IAAI;YAAE,OAAO,MAAM,CAAC,KAAK,CAAC,CAAC,IAAI,EAAE,CAAA;IACvE,CAAC;IAED,OAAO,EAAE,CAAA;AACV,CAAC;AAED,SAAS,QAAQ,CAAC,KAAa;IAC9B,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE;QAAE,OAAO,IAAI,CAAA;IAE9B,MAAM,MAAM,GAAG,MAAM,CAAC,KAAK,CAAC,CAAA;IAE5B,OAAO,MAAM,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAA;AAC/C,CAAC;AAWD;;GAEG;AACH,MAAM,CAAC,KAAK,SAAS,CAAC,CAAC,cAAc,CACpC,IAAqB,EACrB,OAAO,GAAsB,EAAE;IAE/B,MAAM,MAAM,GAAG,IAAI,GAAG,CAAC,OAAO,CAAC,QAAQ,IAAI,CAAC,WAAW,CAAC,CAAC,CAAA;IACzD,MAAM,IAAI,GAAG,IAAI,CAAC,QAAQ,EAAE,CAAA;IAC5B,MAAM,QAAQ,GAAG,QAAQ,CAAC,IAAI,EAAE,OAAO,CAAC,IAAI,CAAC,CAAC,CAAA;IAC9C,MAAM,KAAK,GAAG,cAAc,CAAC,IAAI,CAAC,CAAA;IAElC,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,cAAc,CAAC,SAAS,CAAyB,gBAAgB,CAAC,KAAK,EAAE,QAAQ,CAAC,CAAC,EAAE,CAAC;QAC7G,MAAM,MAAM,GAAG,WAAW,CAAC,GAAG,EAAE,OAAO,CAAC,CAAA;QAExC,IAAI,MAAM,CAAC,IAAI,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,MAAM,CAAC;YAAE,SAAQ;QAEhD,MAAM,WAAW,GAAG,WAAW,CAAC,GAAG,EAAE,OAAO,EAAE,SAAS,CAAC,CAAA;QACxD,MAAM,UAAU,GAAG,WAAW,CAAC,GAAG,EAAE,MAAM,EAAE,SAAS,CAAC,CAAA;QAEtD,IAAI,CAAC,WAAW,IAAI,CAAC,UAAU;YAAE,SAAQ;QAEzC,MAAM;YACL,QAAQ;YACR,IAAI,EAAE,WAAW,CAAC,GAAG,EAAE,MAAM,CAAC;YAC9B,MAAM;YACN,WAAW;YACX,UAAU;YACV,YAAY,EAAE,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC;YACzC,WAAW,EAAE,WAAW,CAAC,GAAG,EAAE,SAAS,CAAC;YACxC,CAAC,EAAE,QAAQ,CAAC,WAAW,CAAC,GAAG,EAAE,SAAS,EAAE,SAAS,CAAC,CAAC;YACnD,CAAC,EAAE,QAAQ,CAAC,WAAW,CAAC,GAAG,EAAE,SAAS,EAAE,SAAS,CAAC,CAAC;SACnD,CAAA;IACF,CAAC;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,SAAS,CAAC,CAAC,mBAAmB,CACzC,SAA0B,EAC1B,OAAO,GAAsB,EAAE;IAE/B,MAAM,KAAK,GAAG,MAAM,UAAU,CAAC,KAAK,CAAC,KAAK,EAAE,EAAE,GAAG,EAAE,SAAS,EAAE,QAAQ,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,CAAC,CAAC,QAAQ,EAAE,CAAA;IAE7G,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QAC1B,KAAK,CAAC,CAAC,cAAc,CAAC,kBAAkB,CAAC,SAAS,EAAE,IAAI,CAAC,EAAE,OAAO,CAAC,CAAA;IACpE,CAAC;AACF,CAAC;AAED;;;;;;;GAOG;AACH,MAAM,UAAU,eAAe,CAAC,OAAgB;IAC/C,MAAM,GAAG,GAAG,OAAO,CAAC,GAAG,CAAA;IACvB,MAAM,MAAM,GAAa,EAAE,CAAA;IAC3B,MAAM,MAAM,GAAa,EAAE,CAAA;IAC3B,IAAI,MAAM,GAAG,CAAC,CAAA;IAEd,KAAK,MAAM,KAAK,IAAI,GAAG,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,MAAM,CAAC,EAAE,CAAC;QACvE,MAAM,KAAK,GAAG,GAAG,CAAC,OAAO,CAAC,KAAK,EAAE,MAAM,CAAC,CAAA;QAExC,MAAM,GAAG,KAAK,GAAG,KAAK,CAAC,MAAM,CAAA;QAE7B,IAAI,KAAK,GAAG,GAAG,CAAA;QAEf,KAAK,IAAI,IAAI,GAAG,CAAC,EAAE,IAAI,GAAG,OAAO,CAAC,UAAU,CAAC,MAAM,EAAE,IAAI,IAAI,CAAC,EAAE,CAAC;YAChE,IAAI,OAAO,CAAC,UAAU,CAAC,IAAI,CAAE,IAAI,KAAK,IAAI,KAAK,GAAG,OAAO,CAAC,QAAQ,CAAC,IAAI,CAAE,EAAE,CAAC;gBAC3E,KAAK,GAAG,KAAK,OAAO,CAAC,QAAQ,CAAC,IAAI,CAAC,EAAE,CAAA;gBAErC,MAAK;YACN,CAAC;QACF,CAAC;QAED,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;QAClB,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;IACnB,CAAC;IAED,OAAO;QACN,GAAG;QACH,MAAM;QACN,MAAM;QACN,WAAW,EAAE,CAAC,GAAG,OAAO,CAAC,UAAU,CAAC;QACpC,SAAS,EAAE,CAAC,GAAG,OAAO,CAAC,QAAQ,CAAC;QAChC,SAAS,EAAE,CAAC,GAAG,OAAO,CAAC,QAAQ,CAAC;QAChC,OAAO,EAAE,OAAO;QAChB,MAAM,EAAE,MAAM;QACd,QAAQ,EAAE,OAAO,CAAC,QAAQ;KAC1B,CAAA;AACF,CAAC"}
|
|
@@ -0,0 +1,33 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Fetch the Korean road-name address register (도로명주소 주소DB) from the ministry's address-industry
|
|
7
|
+
* portal, business.juso.go.kr. The ministry assigns the road names and building numbers it publishes, so
|
|
8
|
+
* this source asserts `address` on `premise` rows: about 6,000,000
|
|
9
|
+
* road-name addresses and 8,000,000 lot-number (지번) records, split by the publisher into four
|
|
10
|
+
* pipe-delimited CP949 text files per region (도로명코드 / 주소 / 지번 / 부가정보), with the postcode in
|
|
11
|
+
* the supplementary file. No coordinates. The public-data portal labels it "이용허락범위 제한 없음"
|
|
12
|
+
* (no restriction on the scope of use). It is a direct download with no application step — the
|
|
13
|
+
* distinction that matters against the ministry's entrance-coordinate products. Those products are provided
|
|
14
|
+
* only after a purpose-of-use review (`docs/superpowers/plans/counsel-dossier.md` §4).
|
|
15
|
+
*
|
|
16
|
+
* The portal is a single-page app. the file behind it is reached in two calls. `selectAttrbDBDwldList`
|
|
17
|
+
* lists the monthly full files for one product (`rtlDtaDtlSn` 8 is the 주소DB, 2 the English
|
|
18
|
+
* road-name DB), and `/api/jst/download` streams one by the parameters in the listing. The
|
|
19
|
+
* English DB accompanies it as the Latin-script half of the same register.
|
|
20
|
+
*
|
|
21
|
+
* Invoke via `mailwoman corpus fetch juso-kr --out-root <path>`.
|
|
22
|
+
*/
|
|
23
|
+
import type { BaseFetchOptions, FetchSummary } from "#tools/fetch/download";
|
|
24
|
+
export interface FetchJusoKROptions extends BaseFetchOptions {
|
|
25
|
+
/**
|
|
26
|
+
* The month to fetch as `yyyymm`.
|
|
27
|
+
*
|
|
28
|
+
* Defaults to the latest month the portal lists as present.
|
|
29
|
+
*/
|
|
30
|
+
month?: string;
|
|
31
|
+
}
|
|
32
|
+
export declare function fetchJusoKR(options: FetchJusoKROptions, report?: (line: string) => void): Promise<FetchSummary>;
|
|
33
|
+
//# sourceMappingURL=juso.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"juso.d.ts","sourceRoot":"","sources":["../../../../lib/kr/tools/fetch/juso.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;GAqBG;AAMH,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAA4C,MAAM,uBAAuB,CAAA;AAqCrH,MAAM,WAAW,kBAAmB,SAAQ,gBAAgB;IAC3D;;;;OAIG;IACH,KAAK,CAAC,EAAE,MAAM,CAAA;CACd;AAsCD,wBAAsB,WAAW,CAAC,OAAO,EAAE,kBAAkB,EAAE,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAAG,OAAO,CAAC,YAAY,CAAC,CA4DrH"}
|
|
@@ -0,0 +1,121 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Fetch the Korean road-name address register (도로명주소 주소DB) from the ministry's address-industry
|
|
7
|
+
* portal, business.juso.go.kr. The ministry assigns the road names and building numbers it publishes, so
|
|
8
|
+
* this source asserts `address` on `premise` rows: about 6,000,000
|
|
9
|
+
* road-name addresses and 8,000,000 lot-number (지번) records, split by the publisher into four
|
|
10
|
+
* pipe-delimited CP949 text files per region (도로명코드 / 주소 / 지번 / 부가정보), with the postcode in
|
|
11
|
+
* the supplementary file. No coordinates. The public-data portal labels it "이용허락범위 제한 없음"
|
|
12
|
+
* (no restriction on the scope of use). It is a direct download with no application step — the
|
|
13
|
+
* distinction that matters against the ministry's entrance-coordinate products. Those products are provided
|
|
14
|
+
* only after a purpose-of-use review (`docs/superpowers/plans/counsel-dossier.md` §4).
|
|
15
|
+
*
|
|
16
|
+
* The portal is a single-page app. the file behind it is reached in two calls. `selectAttrbDBDwldList`
|
|
17
|
+
* lists the monthly full files for one product (`rtlDtaDtlSn` 8 is the 주소DB, 2 the English
|
|
18
|
+
* road-name DB), and `/api/jst/download` streams one by the parameters in the listing. The
|
|
19
|
+
* English DB accompanies it as the Latin-script half of the same register.
|
|
20
|
+
*
|
|
21
|
+
* Invoke via `mailwoman corpus fetch juso-kr --out-root <path>`.
|
|
22
|
+
*/
|
|
23
|
+
import { makeDirectories } from "@mailwoman/core/fs/writers";
|
|
24
|
+
import { sha256File } from "@mailwoman/core/hash";
|
|
25
|
+
import { stringifyJSON } from "@mailwoman/core/json";
|
|
26
|
+
import { resumableDownload, writeManifest } from "#tools/fetch/download";
|
|
27
|
+
const SLUG = "juso-kr";
|
|
28
|
+
const PORTAL = "https://business.juso.go.kr";
|
|
29
|
+
const LIST_URL = `${PORTAL}/api/jst/selectAttrbDBDwldList`;
|
|
30
|
+
const DOWNLOAD_URL = `${PORTAL}/api/jst/download`;
|
|
31
|
+
const REFERER = `${PORTAL}/jst/jstAddressDownload?menu=30`;
|
|
32
|
+
/**
|
|
33
|
+
* The portal's product ids for the two registers this module fetches.
|
|
34
|
+
*/
|
|
35
|
+
const PRODUCTS = [
|
|
36
|
+
{ sn: "8", name: "주소DB" },
|
|
37
|
+
{ sn: "2", name: "도로명주소 영문" },
|
|
38
|
+
];
|
|
39
|
+
const LICENSE = "이용허락범위 제한 없음 (data.go.kr label for 행정안전부_도로명주소 주소DB); 공공누리 attribution to 행정안전부";
|
|
40
|
+
const ATTRIBUTION = "행정안전부 (Ministry of the Interior and Safety), 도로명주소 (juso.go.kr)";
|
|
41
|
+
const BROWSER_HEADERS = {
|
|
42
|
+
"user-agent": "Mozilla/5.0 (X11; Linux x86_64) mailwoman-corpus-fetch",
|
|
43
|
+
referer: REFERER,
|
|
44
|
+
};
|
|
45
|
+
/**
|
|
46
|
+
* The monthly full files the portal lists for one product over the twelve months ending at `year`/`month`.
|
|
47
|
+
*/
|
|
48
|
+
async function listMonthlyFiles(sn, year, month) {
|
|
49
|
+
const res = await fetch(LIST_URL, {
|
|
50
|
+
method: "POST",
|
|
51
|
+
headers: { ...BROWSER_HEADERS, accept: "application/json", "content-type": "application/json;charset=UTF-8" },
|
|
52
|
+
body: stringifyJSON({ rtlDtaDtlSn: sn, year, month, expand: "Y" }),
|
|
53
|
+
});
|
|
54
|
+
if (!res.ok)
|
|
55
|
+
throw new Error(`juso-kr: listing product ${sn} answered HTTP ${res.status}`);
|
|
56
|
+
const json = (await res.json());
|
|
57
|
+
return (json.results?.allMonthFileList ?? []).filter((file) => file.isExist === "Y");
|
|
58
|
+
}
|
|
59
|
+
function downloadURL(file, regYmd) {
|
|
60
|
+
const query = new URLSearchParams({
|
|
61
|
+
reqType: file.fileTypeNm,
|
|
62
|
+
ctprvnCd: file.ctpvClsfCd,
|
|
63
|
+
stdde: file.crtrYm,
|
|
64
|
+
fileName: file.fileNm,
|
|
65
|
+
realFileName: file.tmprFileNm,
|
|
66
|
+
intFileNo: file.fileSn ?? "0",
|
|
67
|
+
intNum: file.atflNo ?? "0",
|
|
68
|
+
regYmd,
|
|
69
|
+
});
|
|
70
|
+
return `${DOWNLOAD_URL}?${query.toString()}`;
|
|
71
|
+
}
|
|
72
|
+
export async function fetchJusoKR(options, report) {
|
|
73
|
+
const destDir = options.outRoot(SLUG);
|
|
74
|
+
await makeDirectories(destDir);
|
|
75
|
+
const now = new Date();
|
|
76
|
+
const files = [];
|
|
77
|
+
const failedCodes = [];
|
|
78
|
+
for (const product of PRODUCTS) {
|
|
79
|
+
const listed = await listMonthlyFiles(product.sn, now.getFullYear(), now.getMonth() + 1);
|
|
80
|
+
const file = options.month ? listed.find((entry) => entry.crtrYm === options.month) : listed.at(-1);
|
|
81
|
+
if (!file) {
|
|
82
|
+
report?.(` ✗ ${product.name}: no full file listed${options.month ? ` for ${options.month}` : ""}`);
|
|
83
|
+
failedCodes.push(product.name);
|
|
84
|
+
continue;
|
|
85
|
+
}
|
|
86
|
+
const url = downloadURL(file, String(now.getFullYear()));
|
|
87
|
+
const dest = destDir(file.tmprFileNm);
|
|
88
|
+
report?.(`=== ${SLUG} / ${product.name} ${file.crtrYm} → ${file.tmprFileNm}`);
|
|
89
|
+
let bytes;
|
|
90
|
+
try {
|
|
91
|
+
// The portal drops a connection every few megabytes and answers Range with 206,
|
|
92
|
+
// so the transfer resumes from what landed rather than starting the 181 MB over.
|
|
93
|
+
bytes = await resumableDownload({ url, dest, headers: BROWSER_HEADERS, report });
|
|
94
|
+
}
|
|
95
|
+
catch (error) {
|
|
96
|
+
report?.(` ✗ ${error.message}`);
|
|
97
|
+
failedCodes.push(product.name);
|
|
98
|
+
continue;
|
|
99
|
+
}
|
|
100
|
+
const sha = await sha256File(dest);
|
|
101
|
+
files.push({
|
|
102
|
+
source_url: url,
|
|
103
|
+
downloaded_at: new Date().toISOString(),
|
|
104
|
+
filename: file.tmprFileNm,
|
|
105
|
+
sha256: sha,
|
|
106
|
+
bytes,
|
|
107
|
+
});
|
|
108
|
+
report?.(` ✓ ${(bytes / 1024 / 1024).toFixed(1)} MB sha256=${sha}`);
|
|
109
|
+
}
|
|
110
|
+
const manifest = {
|
|
111
|
+
source: SLUG,
|
|
112
|
+
source_url: REFERER,
|
|
113
|
+
license: LICENSE,
|
|
114
|
+
attribution: ATTRIBUTION,
|
|
115
|
+
downloaded_at: new Date().toISOString(),
|
|
116
|
+
files,
|
|
117
|
+
};
|
|
118
|
+
await writeManifest(destDir("MANIFEST.json"), manifest);
|
|
119
|
+
return { fetched: files.length, skipped: 0, failed: failedCodes.length, failedCodes };
|
|
120
|
+
}
|
|
121
|
+
//# sourceMappingURL=juso.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"juso.js","sourceRoot":"","sources":["../../../../lib/kr/tools/fetch/juso.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;GAqBG;AAEH,OAAO,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAA;AAC5D,OAAO,EAAE,UAAU,EAAE,MAAM,sBAAsB,CAAA;AACjD,OAAO,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAA;AAGpD,OAAO,EAAE,iBAAiB,EAAE,aAAa,EAAE,MAAM,uBAAuB,CAAA;AAExE,MAAM,IAAI,GAAG,SAAS,CAAA;AACtB,MAAM,MAAM,GAAG,6BAA6B,CAAA;AAC5C,MAAM,QAAQ,GAAG,GAAG,MAAM,gCAAgC,CAAA;AAC1D,MAAM,YAAY,GAAG,GAAG,MAAM,mBAAmB,CAAA;AACjD,MAAM,OAAO,GAAG,GAAG,MAAM,iCAAiC,CAAA;AAE1D;;GAEG;AACH,MAAM,QAAQ,GAAG;IAChB,EAAE,EAAE,EAAE,GAAG,EAAE,IAAI,EAAE,MAAM,EAAE;IACzB,EAAE,EAAE,EAAE,GAAG,EAAE,IAAI,EAAE,UAAU,EAAE;CACpB,CAAA;AAEV,MAAM,OAAO,GACZ,iFAAiF,CAAA;AAElF,MAAM,WAAW,GAAG,iEAAiE,CAAA;AA0BrF,MAAM,eAAe,GAAG;IACvB,YAAY,EAAE,wDAAwD;IACtE,OAAO,EAAE,OAAO;CAChB,CAAA;AAED;;GAEG;AACH,KAAK,UAAU,gBAAgB,CAAC,EAAU,EAAE,IAAY,EAAE,KAAa;IACtE,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,QAAQ,EAAE;QACjC,MAAM,EAAE,MAAM;QACd,OAAO,EAAE,EAAE,GAAG,eAAe,EAAE,MAAM,EAAE,kBAAkB,EAAE,cAAc,EAAE,gCAAgC,EAAE;QAC7G,IAAI,EAAE,aAAa,CAAC,EAAE,WAAW,EAAE,EAAE,EAAE,IAAI,EAAE,KAAK,EAAE,MAAM,EAAE,GAAG,EAAE,CAAC;KAClE,CAAC,CAAA;IAEF,IAAI,CAAC,GAAG,CAAC,EAAE;QAAE,MAAM,IAAI,KAAK,CAAC,4BAA4B,EAAE,kBAAkB,GAAG,CAAC,MAAM,EAAE,CAAC,CAAA;IAC1F,MAAM,IAAI,GAAG,CAAC,MAAM,GAAG,CAAC,IAAI,EAAE,CAAiB,CAAA;IAE/C,OAAO,CAAC,IAAI,CAAC,OAAO,EAAE,gBAAgB,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,OAAO,KAAK,GAAG,CAAC,CAAA;AACrF,CAAC;AAED,SAAS,WAAW,CAAC,IAAgB,EAAE,MAAc;IACpD,MAAM,KAAK,GAAG,IAAI,eAAe,CAAC;QACjC,OAAO,EAAE,IAAI,CAAC,UAAU;QACxB,QAAQ,EAAE,IAAI,CAAC,UAAU;QACzB,KAAK,EAAE,IAAI,CAAC,MAAM;QAClB,QAAQ,EAAE,IAAI,CAAC,MAAM;QACrB,YAAY,EAAE,IAAI,CAAC,UAAU;QAC7B,SAAS,EAAE,IAAI,CAAC,MAAM,IAAI,GAAG;QAC7B,MAAM,EAAE,IAAI,CAAC,MAAM,IAAI,GAAG;QAC1B,MAAM;KACN,CAAC,CAAA;IAEF,OAAO,GAAG,YAAY,IAAI,KAAK,CAAC,QAAQ,EAAE,EAAE,CAAA;AAC7C,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,WAAW,CAAC,OAA2B,EAAE,MAA+B;IAC7F,MAAM,OAAO,GAAG,OAAO,CAAC,OAAO,CAAC,IAAI,CAAC,CAAA;IACrC,MAAM,eAAe,CAAC,OAAO,CAAC,CAAA;IAE9B,MAAM,GAAG,GAAG,IAAI,IAAI,EAAE,CAAA;IACtB,MAAM,KAAK,GAAqB,EAAE,CAAA;IAClC,MAAM,WAAW,GAAa,EAAE,CAAA;IAEhC,KAAK,MAAM,OAAO,IAAI,QAAQ,EAAE,CAAC;QAChC,MAAM,MAAM,GAAG,MAAM,gBAAgB,CAAC,OAAO,CAAC,EAAE,EAAE,GAAG,CAAC,WAAW,EAAE,EAAE,GAAG,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC,CAAA;QACxF,MAAM,IAAI,GAAG,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,MAAM,KAAK,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,CAAA;QAEnG,IAAI,CAAC,IAAI,EAAE,CAAC;YACX,MAAM,EAAE,CAAC,OAAO,OAAO,CAAC,IAAI,wBAAwB,OAAO,CAAC,KAAK,CAAC,CAAC,CAAC,QAAQ,OAAO,CAAC,KAAK,EAAE,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAA;YACnG,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAA;YAE9B,SAAQ;QACT,CAAC;QAED,MAAM,GAAG,GAAG,WAAW,CAAC,IAAI,EAAE,MAAM,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC,CAAC,CAAA;QACxD,MAAM,IAAI,GAAG,OAAO,CAAC,IAAI,CAAC,UAAU,CAAC,CAAA;QACrC,MAAM,EAAE,CAAC,OAAO,IAAI,MAAM,OAAO,CAAC,IAAI,IAAI,IAAI,CAAC,MAAM,MAAM,IAAI,CAAC,UAAU,EAAE,CAAC,CAAA;QAC7E,IAAI,KAAa,CAAA;QAEjB,IAAI,CAAC;YACJ,gFAAgF;YAChF,iFAAiF;YACjF,KAAK,GAAG,MAAM,iBAAiB,CAAC,EAAE,GAAG,EAAE,IAAI,EAAE,OAAO,EAAE,eAAe,EAAE,MAAM,EAAE,CAAC,CAAA;QACjF,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,MAAM,EAAE,CAAC,OAAQ,KAAe,CAAC,OAAO,EAAE,CAAC,CAAA;YAC3C,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,CAAA;YAE9B,SAAQ;QACT,CAAC;QAED,MAAM,GAAG,GAAG,MAAM,UAAU,CAAC,IAAI,CAAC,CAAA;QAElC,KAAK,CAAC,IAAI,CAAC;YACV,UAAU,EAAE,GAAG;YACf,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;YACvC,QAAQ,EAAE,IAAI,CAAC,UAAU;YACzB,MAAM,EAAE,GAAG;YACX,KAAK;SACL,CAAC,CAAA;QAEF,MAAM,EAAE,CAAC,OAAO,CAAC,KAAK,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe,GAAG,EAAE,CAAC,CAAA;IACtE,CAAC;IAED,MAAM,QAAQ,GAA6B;QAC1C,MAAM,EAAE,IAAI;QACZ,UAAU,EAAE,OAAO;QACnB,OAAO,EAAE,OAAO;QAChB,WAAW,EAAE,WAAW;QACxB,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;QACvC,KAAK;KACL,CAAA;IAED,MAAM,aAAa,CAAC,OAAO,CAAC,eAAe,CAAC,EAAE,QAAQ,CAAC,CAAA;IAEvD,OAAO,EAAE,OAAO,EAAE,KAAK,CAAC,MAAM,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,WAAW,CAAC,MAAM,EAAE,WAAW,EAAE,CAAA;AACtF,CAAC"}
|
|
@@ -0,0 +1,37 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Fetch Korea's local-government permit registry (지방행정인허가데이터): one CSV per permit category,
|
|
7
|
+
* every business a local authority has licensed, about 195 categories. Each row includes both address
|
|
8
|
+
* forms of the same premises — `소재지전체주소` (the lot-number form, 지번) and `도로명전체주소` (the
|
|
9
|
+
* road-name form) — plus both postcodes and a planar coordinate (`좌표정보(x/y)`, epsg:5174). That
|
|
10
|
+
* The two formats together provide the cheapest dual-format signal in Korean addresses.
|
|
11
|
+
* The coordinate supplies the board's coordinate half. That role gives this source its weight.
|
|
12
|
+
*
|
|
13
|
+
* What it asserts differs by field. The local authority grants the permit, so the permit identifier is an
|
|
14
|
+
* `identity` assertion. The address is an `observation`: a clerk typed it, in both address systems, with
|
|
15
|
+
* no validation. The registry attests only that it received the string. Both sit on `premise` rows —
|
|
16
|
+
* the address of the licensed premises. One verdict over the source would discard the permit identity.
|
|
17
|
+
*
|
|
18
|
+
* The public-data portal labels the category files "이용허락범위 제한 없음" and links them to
|
|
19
|
+
* `file.localdata.go.kr`, which serves them behind a session: the category page sets the xsrf cookie,
|
|
20
|
+
* `/file/validate/download-count` is the portal's own rate check (429 when it wants a pause), and
|
|
21
|
+
* `/file/download/<slug>/info` streams the CSV. The files are CP949 as delivered. the adapter
|
|
22
|
+
* decodes. The restaurant category by itself is about 700 MB.
|
|
23
|
+
*
|
|
24
|
+
* Invoke via `mailwoman corpus fetch localdata-kr --out-root <path>`, optionally with
|
|
25
|
+
* `--categories general_restaurants,rest_cafes`.
|
|
26
|
+
*/
|
|
27
|
+
import type { BaseFetchOptions, FetchSummary } from "#tools/fetch/download";
|
|
28
|
+
export interface FetchLocaldataKROptions extends BaseFetchOptions {
|
|
29
|
+
/**
|
|
30
|
+
* Category slugs to fetch (the path segment of `/file/<slug>/info`).
|
|
31
|
+
*
|
|
32
|
+
* Defaults to every category the portal lists.
|
|
33
|
+
*/
|
|
34
|
+
categories?: string[];
|
|
35
|
+
}
|
|
36
|
+
export declare function fetchLocaldataKR(options: FetchLocaldataKROptions, report?: (line: string) => void): Promise<FetchSummary>;
|
|
37
|
+
//# sourceMappingURL=localdata.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"localdata.d.ts","sourceRoot":"","sources":["../../../../lib/kr/tools/fetch/localdata.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;GAyBG;AAQH,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAA4C,MAAM,uBAAuB,CAAA;AAWrH,MAAM,WAAW,uBAAwB,SAAQ,gBAAgB;IAChE;;;;OAIG;IACH,UAAU,CAAC,EAAE,MAAM,EAAE,CAAA;CACrB;AAyDD,wBAAsB,gBAAgB,CACrC,OAAO,EAAE,uBAAuB,EAChC,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,YAAY,CAAC,CA6FvB"}
|