@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 +1,260 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* `osm`: OpenStreetMap address adapter for the countries no permissive source covers.
|
|
7
|
+
*
|
|
8
|
+
* Every row lists `ODbL-1.0`, whose recorded obligations include share-alike. A build run under
|
|
9
|
+
* `LicensePolicy.ShareAlikeFree` refuses these rows at ingest, so they reach only the open weights.
|
|
10
|
+
* That is why `defaultLicense` is not an option on this adapter.
|
|
11
|
+
*/
|
|
12
|
+
import { formatAddressRow } from "@mailwoman/codex/address/format";
|
|
13
|
+
import { tryParsingJSON } from "@mailwoman/core/json";
|
|
14
|
+
import { extractDelimited } from "@mailwoman/core/scripting/arguments";
|
|
15
|
+
import { stripCombiningMarks } from "@mailwoman/normalize/fold";
|
|
16
|
+
import { TextSpliterator } from "spliterator";
|
|
17
|
+
import { stableSourceID } from "#adapters/source-id";
|
|
18
|
+
import { SourceRegister } from "#registers";
|
|
19
|
+
import { AddressRole, countDropped, SurfaceOrigin, } from "#types";
|
|
20
|
+
/**
|
|
21
|
+
* Registry id for this adapter, stamped into every row it emits.
|
|
22
|
+
*/
|
|
23
|
+
export const OSM_ADAPTER_ID = "osm";
|
|
24
|
+
/**
|
|
25
|
+
* OpenStreetMap's license.
|
|
26
|
+
*
|
|
27
|
+
* Its recorded obligations include share-alike, so a build run under
|
|
28
|
+
* `LicensePolicy.ShareAlikeFree` refuses every row carrying it.
|
|
29
|
+
*/
|
|
30
|
+
export const OSM_LICENSE = "ODbL-1.0";
|
|
31
|
+
/**
|
|
32
|
+
* The URL of the ODbL license text.
|
|
33
|
+
*/
|
|
34
|
+
export const OSM_LICENSE_URL = "https://opendatacommons.org/licenses/odbl/1-0/";
|
|
35
|
+
/**
|
|
36
|
+
* The attribution OSM requires in redistributed data and derived works.
|
|
37
|
+
*
|
|
38
|
+
* A database built from OSM embeds it, and a model card carries it when OSM-derived
|
|
39
|
+
* rows reached the checkpoint, which the effective training manifest records.
|
|
40
|
+
*/
|
|
41
|
+
export const OSM_ATTRIBUTION = "© OpenStreetMap contributors. Data licensed under the Open Database License (ODbL) 1.0 " +
|
|
42
|
+
`(${OSM_LICENSE_URL}); see https://www.openstreetmap.org/copyright.`;
|
|
43
|
+
const MAX_STREET_WORDS = 8;
|
|
44
|
+
/**
|
|
45
|
+
* Whether `addr:housenumber` holds a street designator — digits with an optional letter,
|
|
46
|
+
* fraction or dash suffix (`12`, `188a`, `14/E`, `1/1146`, `167-c`) or a one-
|
|
47
|
+
* or two-letter block prefix (`B-77`, `L58`, `R 948`) — rather than free text such
|
|
48
|
+
* as `House 34, Road 4, Sector 9`, `Plot #27` or a name.
|
|
49
|
+
*/
|
|
50
|
+
export function housenumberIsDesignator(value) {
|
|
51
|
+
const trimmed = value.trim();
|
|
52
|
+
return /^\d+[A-Za-z]?(?:[/-]\d*[A-Za-z]?)?$/u.test(trimmed) || /^[A-Za-z]{1,2}[-\s]?\d+[A-Za-z]?$/u.test(trimmed);
|
|
53
|
+
}
|
|
54
|
+
/**
|
|
55
|
+
* Whether `addr:street` matches the street-name shape.
|
|
56
|
+
*
|
|
57
|
+
* The value has no comma and contains at most {@link MAX_STREET_WORDS} words.
|
|
58
|
+
* Direction phrases such as `Near Cozy Water Park`, `Opposite Askari Towers` or `Behind …` return false.
|
|
59
|
+
*/
|
|
60
|
+
export function isStreetName(value) {
|
|
61
|
+
const trimmed = value.trim();
|
|
62
|
+
return (trimmed.length > 0 &&
|
|
63
|
+
!trimmed.includes(",") &&
|
|
64
|
+
trimmed.split(/\s+/u).length <= MAX_STREET_WORDS &&
|
|
65
|
+
!/^(?:near|opp(?:osite)?|behind|beside|next to|adjacent)\b/iu.test(trimmed));
|
|
66
|
+
}
|
|
67
|
+
/**
|
|
68
|
+
* Split an `addr:city` carrying a neighborhood ahead of the city (`Mirpur 10, Dhaka` →
|
|
69
|
+
* locality `Dhaka`, head `Mirpur 10`); a value without a comma is only the locality.
|
|
70
|
+
*/
|
|
71
|
+
export function splitCityValue(value) {
|
|
72
|
+
const parts = extractDelimited(value);
|
|
73
|
+
if (parts.length < 2) {
|
|
74
|
+
return { locality: value.trim(), head: null };
|
|
75
|
+
}
|
|
76
|
+
return { locality: parts.at(-1), head: parts.slice(0, -1).join(", ") };
|
|
77
|
+
}
|
|
78
|
+
const PLACEHOLDERS = new Set(["n/a", "na", "none", "-", "nil"]);
|
|
79
|
+
function clean(value) {
|
|
80
|
+
const trimmed = value?.trim() ?? "";
|
|
81
|
+
return trimmed && !PLACEHOLDERS.has(trimmed.toLowerCase()) ? trimmed : null;
|
|
82
|
+
}
|
|
83
|
+
function parseLine(line) {
|
|
84
|
+
const trimmed = line.trim();
|
|
85
|
+
if (!trimmed || trimmed.startsWith("#"))
|
|
86
|
+
return null;
|
|
87
|
+
const parsed = tryParsingJSON(trimmed);
|
|
88
|
+
return parsed && typeof parsed === "object" ? parsed : null;
|
|
89
|
+
}
|
|
90
|
+
/**
|
|
91
|
+
* Maps one jsonl row onto the components the corpus asserts, or returns null when the row is refused.
|
|
92
|
+
*
|
|
93
|
+
* A row with a street-shaped `addr:street` is a street address.
|
|
94
|
+
* A row with no `addr:street` at all is admitted as a streetless premise when its house
|
|
95
|
+
* number is designator-shaped and a tag that maps to `locality` or `dependent_locality`
|
|
96
|
+
* (`addr:city`, `addr:place`, `addr:suburb`, `addr:subdistrict`, `addr:district`)
|
|
97
|
+
* carries the identity the street would have carried.
|
|
98
|
+
*
|
|
99
|
+
* That is OSM's documented scheme for addresses numbered within a named place
|
|
100
|
+
* rather than along a street, and it is the `streetless-premise-identity` shape.
|
|
101
|
+
* A row whose `addr:street` holds a line rather than a name stays refused:
|
|
102
|
+
* the mapper supplied a street, and the value is a line.
|
|
103
|
+
*
|
|
104
|
+
* Each refusal and each discarded component increments its reason in `dropped`.
|
|
105
|
+
*/
|
|
106
|
+
export function componentsForOSMRow(row, dropped) {
|
|
107
|
+
const tally = dropped ?? {};
|
|
108
|
+
const street = clean(row.street);
|
|
109
|
+
const number = clean(row.number);
|
|
110
|
+
const designator = number !== null && housenumberIsDesignator(number);
|
|
111
|
+
if (street && !isStreetName(street)) {
|
|
112
|
+
countDropped(tally, "row:street-not-a-name");
|
|
113
|
+
return null;
|
|
114
|
+
}
|
|
115
|
+
if (!street && !designator) {
|
|
116
|
+
countDropped(tally, number ? "row:streetless-house-number-not-designator" : "row:streetless-no-house-number");
|
|
117
|
+
return null;
|
|
118
|
+
}
|
|
119
|
+
const components = street ? { street } : {};
|
|
120
|
+
if (designator) {
|
|
121
|
+
components.house_number = number;
|
|
122
|
+
}
|
|
123
|
+
else if (number) {
|
|
124
|
+
countDropped(tally, "component:house_number:not-designator");
|
|
125
|
+
}
|
|
126
|
+
const unit = clean(row.unit);
|
|
127
|
+
if (unit) {
|
|
128
|
+
components.unit = unit;
|
|
129
|
+
}
|
|
130
|
+
const postcode = clean(row.postcode);
|
|
131
|
+
if (postcode && /^\d{4,6}$/u.test(postcode)) {
|
|
132
|
+
components.postcode = postcode;
|
|
133
|
+
}
|
|
134
|
+
else if (postcode) {
|
|
135
|
+
countDropped(tally, "component:postcode:not-4-to-6-digits");
|
|
136
|
+
}
|
|
137
|
+
const city = clean(row.city);
|
|
138
|
+
const split = city ? splitCityValue(city) : null;
|
|
139
|
+
if (split) {
|
|
140
|
+
components.locality = split.locality;
|
|
141
|
+
}
|
|
142
|
+
// Dependent-locality candidates in priority order (suburb, subdistrict, district, place, city head);
|
|
143
|
+
// `district` never becomes `region`, because Vietnam's country template
|
|
144
|
+
// renders it only when no city is present.
|
|
145
|
+
const dependent = [row.suburb, row.subdistrict, row.district, row.place, split?.head]
|
|
146
|
+
.map((value) => clean(value ?? undefined))
|
|
147
|
+
.find((value) => value !== null &&
|
|
148
|
+
!value.includes(",") &&
|
|
149
|
+
(street === null || !sameName(value, street)) &&
|
|
150
|
+
(split === null || !sameName(value, split.locality)));
|
|
151
|
+
if (dependent) {
|
|
152
|
+
components.dependent_locality = dependent;
|
|
153
|
+
}
|
|
154
|
+
const province = clean(row.province);
|
|
155
|
+
if (province && (split === null || !sameName(province, split.locality))) {
|
|
156
|
+
components.region = province;
|
|
157
|
+
}
|
|
158
|
+
// A streetless premise is a house number within a named place, so it needs a locality
|
|
159
|
+
// or a dependent locality, from any of the tags that map to them.
|
|
160
|
+
if (!street && !components.locality && !components.dependent_locality) {
|
|
161
|
+
countDropped(tally, "row:streetless-no-locality");
|
|
162
|
+
return null;
|
|
163
|
+
}
|
|
164
|
+
// An address row needs another component alongside the street or the streetless house number.
|
|
165
|
+
// Coarse adapters already teach bare names.
|
|
166
|
+
if (Object.keys(components).length === 1) {
|
|
167
|
+
countDropped(tally, street ? "row:street-only" : "row:house-number-only");
|
|
168
|
+
return null;
|
|
169
|
+
}
|
|
170
|
+
return components;
|
|
171
|
+
}
|
|
172
|
+
/**
|
|
173
|
+
* Vietnamese admin-generic prefixes stripped before name comparison, so a province that
|
|
174
|
+
* repeats the city with a prefix (`Thành phố Hà Nội`) is read as the repeat it is.
|
|
175
|
+
*/
|
|
176
|
+
const NAME_PREFIXES = /^(?:thanh pho|tinh|tp\.?|quan|phuong|huyen|thi xa)\s+/u;
|
|
177
|
+
/**
|
|
178
|
+
* Whether two place names are the same name: case, whitespace, diacritics and a leading
|
|
179
|
+
* admin generic folded (`Bắc Ninh` = `Bac Ninh`; `Hà Nội` = `Thành phố Hà Nội`).
|
|
180
|
+
*/
|
|
181
|
+
export function sameName(a, b) {
|
|
182
|
+
const fold = (value) => stripCombiningMarks(value)
|
|
183
|
+
.replaceAll("đ", "d")
|
|
184
|
+
.replaceAll("Đ", "D")
|
|
185
|
+
.toLowerCase()
|
|
186
|
+
.replaceAll(/\s+/gu, " ")
|
|
187
|
+
.trim()
|
|
188
|
+
.replace(NAME_PREFIXES, "");
|
|
189
|
+
return fold(a) === fold(b);
|
|
190
|
+
}
|
|
191
|
+
export function createOSMAdapter() {
|
|
192
|
+
return {
|
|
193
|
+
id: OSM_ADAPTER_ID,
|
|
194
|
+
defaultLicense: OSM_LICENSE,
|
|
195
|
+
addressRole: AddressRole.Premise,
|
|
196
|
+
register: SourceRegister.OpenStreetMap,
|
|
197
|
+
surface: SurfaceOrigin.Rendered,
|
|
198
|
+
description: "OpenStreetMap addresses (ODbL, share-alike): per-country JSONL from a Geofabrik extract, for the countries no permissive source covers.",
|
|
199
|
+
async *rows(opts) {
|
|
200
|
+
if (!opts.country) {
|
|
201
|
+
throw new Error("osm adapter: --country is required (the JSONL is per-country and rows omit a country field)");
|
|
202
|
+
}
|
|
203
|
+
const country = opts.country;
|
|
204
|
+
let emitted = 0;
|
|
205
|
+
for await (const line of TextSpliterator.fromAsync(opts.inputPath)) {
|
|
206
|
+
if (opts.signal?.aborted)
|
|
207
|
+
break;
|
|
208
|
+
if (opts.limit !== undefined && emitted >= opts.limit)
|
|
209
|
+
break;
|
|
210
|
+
const row = parseLine(line);
|
|
211
|
+
if (!row) {
|
|
212
|
+
if (line.trim() && !line.trim().startsWith("#")) {
|
|
213
|
+
countDropped(opts, "row:unparseable-line");
|
|
214
|
+
}
|
|
215
|
+
continue;
|
|
216
|
+
}
|
|
217
|
+
// A Geofabrik extract's polygon extends past the border, so its records
|
|
218
|
+
// include addresses in the neighboring country.
|
|
219
|
+
// A record whose own `addr:country` names another country is refused.
|
|
220
|
+
// A record without the tag is kept and counted, so the size of the remaining
|
|
221
|
+
// uncertainty is in the manifest rather than assumed to be zero.
|
|
222
|
+
const tagged = clean(row.country)?.toUpperCase();
|
|
223
|
+
if (tagged && tagged !== country) {
|
|
224
|
+
countDropped(opts, "row:country-tag-mismatch");
|
|
225
|
+
continue;
|
|
226
|
+
}
|
|
227
|
+
if (!tagged) {
|
|
228
|
+
countDropped(opts, "kept:country-untagged");
|
|
229
|
+
}
|
|
230
|
+
const components = componentsForOSMRow(row, opts);
|
|
231
|
+
if (!components)
|
|
232
|
+
continue;
|
|
233
|
+
const rendered = formatAddressRow(components, country, { singleLine: true });
|
|
234
|
+
if (!rendered) {
|
|
235
|
+
countDropped(opts, "row:render-failed");
|
|
236
|
+
continue;
|
|
237
|
+
}
|
|
238
|
+
const { raw, components: aligned } = rendered;
|
|
239
|
+
for (const tag of rendered.unplaced) {
|
|
240
|
+
countDropped(opts, `component:${tag}:not-rendered`);
|
|
241
|
+
}
|
|
242
|
+
yield {
|
|
243
|
+
raw,
|
|
244
|
+
components: aligned,
|
|
245
|
+
country,
|
|
246
|
+
source: OSM_ADAPTER_ID,
|
|
247
|
+
source_id: stableSourceID(OSM_ADAPTER_ID, aligned),
|
|
248
|
+
corpus_version: "",
|
|
249
|
+
license: OSM_LICENSE,
|
|
250
|
+
};
|
|
251
|
+
emitted++;
|
|
252
|
+
}
|
|
253
|
+
},
|
|
254
|
+
};
|
|
255
|
+
}
|
|
256
|
+
/**
|
|
257
|
+
* The configured adapter instance registered with the corpus builder.
|
|
258
|
+
*/
|
|
259
|
+
export const osmAdapter = createOSMAdapter();
|
|
260
|
+
//# sourceMappingURL=adapter.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../lib/adapters/osm/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;GAUG;AAEH,OAAO,EAAE,gBAAgB,EAAE,MAAM,iCAAiC,CAAA;AAClE,OAAO,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAA;AACrD,OAAO,EAAE,gBAAgB,EAAE,MAAM,qCAAqC,CAAA;AACtE,OAAO,EAAE,mBAAmB,EAAE,MAAM,2BAA2B,CAAA;AAC/D,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C,OAAO,EAAE,cAAc,EAAE,MAAM,qBAAqB,CAAA;AACpD,OAAO,EAAE,cAAc,EAAE,MAAM,YAAY,CAAA;AAC3C,OAAO,EACN,WAAW,EAIX,YAAY,EACZ,aAAa,GACb,MAAM,QAAQ,CAAA;AAEf;;GAEG;AACH,MAAM,CAAC,MAAM,cAAc,GAAG,KAAK,CAAA;AAEnC;;;;;GAKG;AACH,MAAM,CAAC,MAAM,WAAW,GAAG,UAAU,CAAA;AAErC;;GAEG;AACH,MAAM,CAAC,MAAM,eAAe,GAAG,gDAAgD,CAAA;AAE/E;;;;;GAKG;AACH,MAAM,CAAC,MAAM,eAAe,GAC3B,yFAAyF;IACzF,IAAI,eAAe,iDAAiD,CAAA;AAmBrE,MAAM,gBAAgB,GAAG,CAAC,CAAA;AAE1B;;;;;GAKG;AACH,MAAM,UAAU,uBAAuB,CAAC,KAAa;IACpD,MAAM,OAAO,GAAG,KAAK,CAAC,IAAI,EAAE,CAAA;IAE5B,OAAO,sCAAsC,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,oCAAoC,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;AAClH,CAAC;AAED;;;;;GAKG;AACH,MAAM,UAAU,YAAY,CAAC,KAAa;IACzC,MAAM,OAAO,GAAG,KAAK,CAAC,IAAI,EAAE,CAAA;IAE5B,OAAO,CACN,OAAO,CAAC,MAAM,GAAG,CAAC;QAClB,CAAC,OAAO,CAAC,QAAQ,CAAC,GAAG,CAAC;QACtB,OAAO,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,MAAM,IAAI,gBAAgB;QAChD,CAAC,4DAA4D,CAAC,IAAI,CAAC,OAAO,CAAC,CAC3E,CAAA;AACF,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,cAAc,CAAC,KAAa;IAC3C,MAAM,KAAK,GAAG,gBAAgB,CAAC,KAAK,CAAC,CAAA;IAErC,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACtB,OAAO,EAAE,QAAQ,EAAE,KAAK,CAAC,IAAI,EAAE,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;IAC9C,CAAC;IAED,OAAO,EAAE,QAAQ,EAAE,KAAK,CAAC,EAAE,CAAC,CAAC,CAAC,CAAE,EAAE,IAAI,EAAE,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAA;AACxE,CAAC;AAED,MAAM,YAAY,GAAG,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,IAAI,EAAE,MAAM,EAAE,GAAG,EAAE,KAAK,CAAC,CAAC,CAAA;AAE/D,SAAS,KAAK,CAAC,KAAyB;IACvC,MAAM,OAAO,GAAG,KAAK,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;IAEnC,OAAO,OAAO,IAAI,CAAC,YAAY,CAAC,GAAG,CAAC,OAAO,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,IAAI,CAAA;AAC5E,CAAC;AAED,SAAS,SAAS,CAAC,IAAY;IAC9B,MAAM,OAAO,GAAG,IAAI,CAAC,IAAI,EAAE,CAAA;IAE3B,IAAI,CAAC,OAAO,IAAI,OAAO,CAAC,UAAU,CAAC,GAAG,CAAC;QAAE,OAAO,IAAI,CAAA;IAEpD,MAAM,MAAM,GAAG,cAAc,CAAC,OAAO,CAAC,CAAA;IAEtC,OAAO,MAAM,IAAI,OAAO,MAAM,KAAK,QAAQ,CAAC,CAAC,CAAE,MAAuB,CAAC,CAAC,CAAC,IAAI,CAAA;AAC9E,CAAC;AAED;;;;;;;;;;;;;;;GAeG;AACH,MAAM,UAAU,mBAAmB,CAClC,GAAiB,EACjB,OAAyC;IAEzC,MAAM,KAAK,GAAG,OAAO,IAAI,EAAE,CAAA;IAC3B,MAAM,MAAM,GAAG,KAAK,CAAC,GAAG,CAAC,MAAM,CAAC,CAAA;IAChC,MAAM,MAAM,GAAG,KAAK,CAAC,GAAG,CAAC,MAAM,CAAC,CAAA;IAChC,MAAM,UAAU,GAAG,MAAM,KAAK,IAAI,IAAI,uBAAuB,CAAC,MAAM,CAAC,CAAA;IAErE,IAAI,MAAM,IAAI,CAAC,YAAY,CAAC,MAAM,CAAC,EAAE,CAAC;QACrC,YAAY,CAAC,KAAK,EAAE,uBAAuB,CAAC,CAAA;QAE5C,OAAO,IAAI,CAAA;IACZ,CAAC;IAED,IAAI,CAAC,MAAM,IAAI,CAAC,UAAU,EAAE,CAAC;QAC5B,YAAY,CAAC,KAAK,EAAE,MAAM,CAAC,CAAC,CAAC,4CAA4C,CAAC,CAAC,CAAC,gCAAgC,CAAC,CAAA;QAE7G,OAAO,IAAI,CAAA;IACZ,CAAC;IAED,MAAM,UAAU,GAA+B,MAAM,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;IAEvE,IAAI,UAAU,EAAE,CAAC;QAChB,UAAU,CAAC,YAAY,GAAG,MAAM,CAAA;IACjC,CAAC;SAAM,IAAI,MAAM,EAAE,CAAC;QACnB,YAAY,CAAC,KAAK,EAAE,uCAAuC,CAAC,CAAA;IAC7D,CAAC;IAED,MAAM,IAAI,GAAG,KAAK,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;IAE5B,IAAI,IAAI,EAAE,CAAC;QACV,UAAU,CAAC,IAAI,GAAG,IAAI,CAAA;IACvB,CAAC;IAED,MAAM,QAAQ,GAAG,KAAK,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAA;IAEpC,IAAI,QAAQ,IAAI,YAAY,CAAC,IAAI,CAAC,QAAQ,CAAC,EAAE,CAAC;QAC7C,UAAU,CAAC,QAAQ,GAAG,QAAQ,CAAA;IAC/B,CAAC;SAAM,IAAI,QAAQ,EAAE,CAAC;QACrB,YAAY,CAAC,KAAK,EAAE,sCAAsC,CAAC,CAAA;IAC5D,CAAC;IAED,MAAM,IAAI,GAAG,KAAK,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;IAC5B,MAAM,KAAK,GAAG,IAAI,CAAC,CAAC,CAAC,cAAc,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAA;IAEhD,IAAI,KAAK,EAAE,CAAC;QACX,UAAU,CAAC,QAAQ,GAAG,KAAK,CAAC,QAAQ,CAAA;IACrC,CAAC;IAED,qGAAqG;IACrG,wEAAwE;IACxE,2CAA2C;IAC3C,MAAM,SAAS,GAAG,CAAC,GAAG,CAAC,MAAM,EAAE,GAAG,CAAC,WAAW,EAAE,GAAG,CAAC,QAAQ,EAAE,GAAG,CAAC,KAAK,EAAE,KAAK,EAAE,IAAI,CAAC;SACnF,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,KAAK,IAAI,SAAS,CAAC,CAAC;SACzC,IAAI,CACJ,CAAC,KAAK,EAAE,EAAE,CACT,KAAK,KAAK,IAAI;QACd,CAAC,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC;QACpB,CAAC,MAAM,KAAK,IAAI,IAAI,CAAC,QAAQ,CAAC,KAAK,EAAE,MAAM,CAAC,CAAC;QAC7C,CAAC,KAAK,KAAK,IAAI,IAAI,CAAC,QAAQ,CAAC,KAAK,EAAE,KAAK,CAAC,QAAQ,CAAC,CAAC,CACrD,CAAA;IAEF,IAAI,SAAS,EAAE,CAAC;QACf,UAAU,CAAC,kBAAkB,GAAG,SAAS,CAAA;IAC1C,CAAC;IAED,MAAM,QAAQ,GAAG,KAAK,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAA;IAEpC,IAAI,QAAQ,IAAI,CAAC,KAAK,KAAK,IAAI,IAAI,CAAC,QAAQ,CAAC,QAAQ,EAAE,KAAK,CAAC,QAAQ,CAAC,CAAC,EAAE,CAAC;QACzE,UAAU,CAAC,MAAM,GAAG,QAAQ,CAAA;IAC7B,CAAC;IAED,sFAAsF;IACtF,kEAAkE;IAClE,IAAI,CAAC,MAAM,IAAI,CAAC,UAAU,CAAC,QAAQ,IAAI,CAAC,UAAU,CAAC,kBAAkB,EAAE,CAAC;QACvE,YAAY,CAAC,KAAK,EAAE,4BAA4B,CAAC,CAAA;QAEjD,OAAO,IAAI,CAAA;IACZ,CAAC;IAED,8FAA8F;IAC9F,4CAA4C;IAC5C,IAAI,MAAM,CAAC,IAAI,CAAC,UAAU,CAAC,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAC1C,YAAY,CAAC,KAAK,EAAE,MAAM,CAAC,CAAC,CAAC,iBAAiB,CAAC,CAAC,CAAC,uBAAuB,CAAC,CAAA;QAEzE,OAAO,IAAI,CAAA;IACZ,CAAC;IAED,OAAO,UAAU,CAAA;AAClB,CAAC;AAED;;;GAGG;AACH,MAAM,aAAa,GAAG,wDAAwD,CAAA;AAE9E;;;GAGG;AACH,MAAM,UAAU,QAAQ,CAAC,CAAS,EAAE,CAAS;IAC5C,MAAM,IAAI,GAAG,CAAC,KAAa,EAAU,EAAE,CACtC,mBAAmB,CAAC,KAAK,CAAC;SACxB,UAAU,CAAC,GAAG,EAAE,GAAG,CAAC;SACpB,UAAU,CAAC,GAAG,EAAE,GAAG,CAAC;SACpB,WAAW,EAAE;SACb,UAAU,CAAC,OAAO,EAAE,GAAG,CAAC;SACxB,IAAI,EAAE;SACN,OAAO,CAAC,aAAa,EAAE,EAAE,CAAC,CAAA;IAE7B,OAAO,IAAI,CAAC,CAAC,CAAC,KAAK,IAAI,CAAC,CAAC,CAAC,CAAA;AAC3B,CAAC;AAED,MAAM,UAAU,gBAAgB;IAC/B,OAAO;QACN,EAAE,EAAE,cAAc;QAClB,cAAc,EAAE,WAAW;QAC3B,WAAW,EAAE,WAAW,CAAC,OAAO;QAChC,QAAQ,EAAE,cAAc,CAAC,aAAa;QACtC,OAAO,EAAE,aAAa,CAAC,QAAQ;QAC/B,WAAW,EACV,yIAAyI;QAE1I,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,IAAI,CAAC,IAAI,CAAC,OAAO,EAAE,CAAC;gBACnB,MAAM,IAAI,KAAK,CAAC,6FAA6F,CAAC,CAAA;YAC/G,CAAC;YAED,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,CAAA;YAC5B,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,KAAK,EAAE,MAAM,IAAI,IAAI,eAAe,CAAC,SAAS,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,CAAC;gBACpE,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;oBAAE,MAAK;gBAE/B,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;oBAAE,MAAK;gBAE5D,MAAM,GAAG,GAAG,SAAS,CAAC,IAAI,CAAC,CAAA;gBAE3B,IAAI,CAAC,GAAG,EAAE,CAAC;oBACV,IAAI,IAAI,CAAC,IAAI,EAAE,IAAI,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;wBACjD,YAAY,CAAC,IAAI,EAAE,sBAAsB,CAAC,CAAA;oBAC3C,CAAC;oBAED,SAAQ;gBACT,CAAC;gBAED,wEAAwE;gBACxE,gDAAgD;gBAChD,sEAAsE;gBACtE,6EAA6E;gBAC7E,iEAAiE;gBACjE,MAAM,MAAM,GAAG,KAAK,CAAC,GAAG,CAAC,OAAO,CAAC,EAAE,WAAW,EAAE,CAAA;gBAEhD,IAAI,MAAM,IAAI,MAAM,KAAK,OAAO,EAAE,CAAC;oBAClC,YAAY,CAAC,IAAI,EAAE,0BAA0B,CAAC,CAAA;oBAE9C,SAAQ;gBACT,CAAC;gBAED,IAAI,CAAC,MAAM,EAAE,CAAC;oBACb,YAAY,CAAC,IAAI,EAAE,uBAAuB,CAAC,CAAA;gBAC5C,CAAC;gBAED,MAAM,UAAU,GAAG,mBAAmB,CAAC,GAAG,EAAE,IAAI,CAAC,CAAA;gBAEjD,IAAI,CAAC,UAAU;oBAAE,SAAQ;gBAEzB,MAAM,QAAQ,GAAG,gBAAgB,CAAC,UAAU,EAAE,OAAO,EAAE,EAAE,UAAU,EAAE,IAAI,EAAE,CAAC,CAAA;gBAE5E,IAAI,CAAC,QAAQ,EAAE,CAAC;oBACf,YAAY,CAAC,IAAI,EAAE,mBAAmB,CAAC,CAAA;oBAEvC,SAAQ;gBACT,CAAC;gBAED,MAAM,EAAE,GAAG,EAAE,UAAU,EAAE,OAAO,EAAE,GAAG,QAAQ,CAAA;gBAE7C,KAAK,MAAM,GAAG,IAAI,QAAQ,CAAC,QAAQ,EAAE,CAAC;oBACrC,YAAY,CAAC,IAAI,EAAE,aAAa,GAAG,eAAe,CAAC,CAAA;gBACpD,CAAC;gBAED,MAAM;oBACL,GAAG;oBACH,UAAU,EAAE,OAAO;oBACnB,OAAO;oBACP,MAAM,EAAE,cAAc;oBACtB,SAAS,EAAE,cAAc,CAAC,cAAc,EAAE,OAAO,CAAC;oBAClD,cAAc,EAAE,EAAE;oBAClB,OAAO,EAAE,WAAW;iBACpB,CAAA;gBAED,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,UAAU,GAAG,gBAAgB,EAAE,CAAA"}
|
|
@@ -3,43 +3,27 @@
|
|
|
3
3
|
* @license AGPL-3.0
|
|
4
4
|
* @author Teffen Ellis, et al.
|
|
5
5
|
*
|
|
6
|
-
*
|
|
7
|
-
*
|
|
8
|
-
* dataset that fixes OpenAddresses' per-country patchiness (OA dropped Spain; OA-DE omits the
|
|
9
|
-
* Bundesland) — it even re-hosts the OA Spain data the standalone OA bucket no longer serves.
|
|
10
|
-
*
|
|
11
|
-
* This adapter consumes a per-country LINE-DELIMITED JSON dump of the corpus-relevant fields (`{
|
|
12
|
-
* street, number, unit, postcode, locality }`), produced by `scripts/ingest-overture-addresses.ts
|
|
13
|
-
* --corpus-jsonl` (which does the DuckDB / S3 heavy lifting and flattens `address_levels` → the
|
|
14
|
-
* municipality locality). The split keeps `@mailwoman/corpus` — a RUNTIME dep of the `mailwoman`
|
|
15
|
-
* CLI — free of the heavy native `@duckdb/node-api`; the adapter just streams JSONL line-by-line,
|
|
16
|
-
* exactly like `openaddresses`.
|
|
17
|
-
*
|
|
18
|
-
* The `street` surface carries the locale's street keyword verbatim (`"CALLE JULAN"`, `"VIA
|
|
19
|
-
* ROMA"`). We map it to `street` whole and let the downstream affix-relabel split `street_prefix`
|
|
20
|
-
* — the same path every other source rides. This slice exists because the model was
|
|
21
|
-
* en-us/fr-trained and never saw non-en/fr street formats (the 2026-06-19 EU parse-blocker
|
|
22
|
-
* measured loc-correct ES 21% / IT 59% / NL 64% vs FR/US ~98%).
|
|
23
|
-
*
|
|
24
|
-
* `--country` is REQUIRED (the JSONL is per-country and the rows omit a country field), matching
|
|
25
|
-
* `openaddresses`. License is Overture's CDLA-Permissive-2.0 (attribution; not share-alike).
|
|
26
|
-
*
|
|
27
|
-
* | Field | ComponentTag | | --------- | ---------------------------------------------- | |
|
|
28
|
-
* `street` | `street` (keyword incl.; affix-relabel splits prefix) | | `number` | `house_number`
|
|
29
|
-
* (skipped when "S-N"/"S/N" = sin número) | | `unit` | `unit` (if non-empty) | | `postcode`|
|
|
30
|
-
* `postcode` | | `locality`| `locality` (Overture address_levels municipality, or postal_city) |
|
|
6
|
+
* `overture`: Overture Maps Addresses adapter. The `street` value keeps the locale's street keyword
|
|
7
|
+
* verbatim. The downstream affix-relabel step splits `street_prefix` from that value.
|
|
31
8
|
*/
|
|
32
|
-
import type
|
|
9
|
+
import { type CorpusAdapter } from "#types";
|
|
33
10
|
/**
|
|
34
|
-
* Registry id
|
|
35
|
-
* it came from.
|
|
11
|
+
* Registry id stamped into every row this adapter emits, so a corpus record traces back to its dataset.
|
|
36
12
|
*/
|
|
37
13
|
export declare const OVERTURE_ADAPTER_ID = "overture";
|
|
38
14
|
/**
|
|
39
|
-
* License
|
|
40
|
-
* rather than
|
|
15
|
+
* License assigned by this source (`cdla-Permissive-2.0`, attribution-only
|
|
16
|
+
* rather than share-alike), attached to every row.
|
|
41
17
|
*/
|
|
42
18
|
export declare const OVERTURE_DEFAULT_LICENSE = "CDLA-Permissive-2.0";
|
|
19
|
+
/**
|
|
20
|
+
* Whether an Overture `unit` value is a secondary-unit designator
|
|
21
|
+
* (a digit or a single bare word) rather than a name.
|
|
22
|
+
*
|
|
23
|
+
* Overture-SG puts an estate name in this field on 91,818 of 142,210 rows and the literal
|
|
24
|
+
* `NIL` on 47,407 more, so a name taught as `unit` would teach a trailing proper name.
|
|
25
|
+
*/
|
|
26
|
+
export declare function unitFieldIsDesignator(value: string): boolean;
|
|
43
27
|
export declare function createOvertureAdapter(): CorpusAdapter;
|
|
44
28
|
/**
|
|
45
29
|
* The configured adapter instance registered with the corpus builder.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../lib/adapters/overture/adapter.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../lib/adapters/overture/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAWH,OAAO,EAAuD,KAAK,aAAa,EAAiB,MAAM,QAAQ,CAAA;AAE/G;;GAEG;AACH,eAAO,MAAM,mBAAmB,aAAa,CAAA;AAC7C;;;GAGG;AACH,eAAO,MAAM,wBAAwB,wBAAwB,CAAA;AAiC7D;;;;;;GAMG;AACH,wBAAgB,qBAAqB,CAAC,KAAK,EAAE,MAAM,GAAG,OAAO,CAM5D;AAYD,wBAAgB,qBAAqB,IAAI,aAAa,CA8FrD;AAED;;GAEG;AACH,eAAO,MAAM,eAAe,eAA0B,CAAA"}
|
|
@@ -3,46 +3,54 @@
|
|
|
3
3
|
* @license AGPL-3.0
|
|
4
4
|
* @author Teffen Ellis, et al.
|
|
5
5
|
*
|
|
6
|
-
*
|
|
7
|
-
*
|
|
8
|
-
* dataset that fixes OpenAddresses' per-country patchiness (OA dropped Spain; OA-DE omits the
|
|
9
|
-
* Bundesland) — it even re-hosts the OA Spain data the standalone OA bucket no longer serves.
|
|
10
|
-
*
|
|
11
|
-
* This adapter consumes a per-country LINE-DELIMITED JSON dump of the corpus-relevant fields (`{
|
|
12
|
-
* street, number, unit, postcode, locality }`), produced by `scripts/ingest-overture-addresses.ts
|
|
13
|
-
* --corpus-jsonl` (which does the DuckDB / S3 heavy lifting and flattens `address_levels` → the
|
|
14
|
-
* municipality locality). The split keeps `@mailwoman/corpus` — a RUNTIME dep of the `mailwoman`
|
|
15
|
-
* CLI — free of the heavy native `@duckdb/node-api`; the adapter just streams JSONL line-by-line,
|
|
16
|
-
* exactly like `openaddresses`.
|
|
17
|
-
*
|
|
18
|
-
* The `street` surface carries the locale's street keyword verbatim (`"CALLE JULAN"`, `"VIA
|
|
19
|
-
* ROMA"`). We map it to `street` whole and let the downstream affix-relabel split `street_prefix`
|
|
20
|
-
* — the same path every other source rides. This slice exists because the model was
|
|
21
|
-
* en-us/fr-trained and never saw non-en/fr street formats (the 2026-06-19 EU parse-blocker
|
|
22
|
-
* measured loc-correct ES 21% / IT 59% / NL 64% vs FR/US ~98%).
|
|
23
|
-
*
|
|
24
|
-
* `--country` is REQUIRED (the JSONL is per-country and the rows omit a country field), matching
|
|
25
|
-
* `openaddresses`. License is Overture's CDLA-Permissive-2.0 (attribution; not share-alike).
|
|
26
|
-
*
|
|
27
|
-
* | Field | ComponentTag | | --------- | ---------------------------------------------- | |
|
|
28
|
-
* `street` | `street` (keyword incl.; affix-relabel splits prefix) | | `number` | `house_number`
|
|
29
|
-
* (skipped when "S-N"/"S/N" = sin número) | | `unit` | `unit` (if non-empty) | | `postcode`|
|
|
30
|
-
* `postcode` | | `locality`| `locality` (Overture address_levels municipality, or postal_city) |
|
|
6
|
+
* `overture`: Overture Maps Addresses adapter. The `street` value keeps the locale's street keyword
|
|
7
|
+
* verbatim. The downstream affix-relabel step splits `street_prefix` from that value.
|
|
31
8
|
*/
|
|
9
|
+
import { formatAddressRow } from "@mailwoman/codex/address/format";
|
|
10
|
+
import { COUNTRY_SURFACE_FORMS } from "@mailwoman/codex/country";
|
|
32
11
|
import { tryParsingJSON } from "@mailwoman/core/json";
|
|
33
|
-
import {
|
|
12
|
+
import { sample } from "@mailwoman/core/random";
|
|
13
|
+
import { mulberry32 as makeMulberry32 } from "@mailwoman/core/utils";
|
|
34
14
|
import { TextSpliterator } from "spliterator";
|
|
35
|
-
import { stableSourceID } from "#adapters/
|
|
15
|
+
import { stableSourceID } from "#adapters/source-id";
|
|
16
|
+
import { SourceRegister } from "#registers";
|
|
17
|
+
import { AddressRole, SurfaceOrigin } from "#types";
|
|
36
18
|
/**
|
|
37
|
-
* Registry id
|
|
38
|
-
* it came from.
|
|
19
|
+
* Registry id stamped into every row this adapter emits, so a corpus record traces back to its dataset.
|
|
39
20
|
*/
|
|
40
21
|
export const OVERTURE_ADAPTER_ID = "overture";
|
|
41
22
|
/**
|
|
42
|
-
* License
|
|
43
|
-
* rather than
|
|
23
|
+
* License assigned by this source (`cdla-Permissive-2.0`, attribution-only
|
|
24
|
+
* rather than share-alike), attached to every row.
|
|
44
25
|
*/
|
|
45
26
|
export const OVERTURE_DEFAULT_LICENSE = "CDLA-Permissive-2.0";
|
|
27
|
+
const DEFAULT_COUNTRY_SEED = 20_260_922;
|
|
28
|
+
/**
|
|
29
|
+
* One attested written form of a country's name.
|
|
30
|
+
*
|
|
31
|
+
* Raises rather than returning empty when the codex has no entry, so a requested
|
|
32
|
+
* fraction cannot silently produce no country rows.
|
|
33
|
+
*/
|
|
34
|
+
function countrySurfaceForm(country, random) {
|
|
35
|
+
const forms = COUNTRY_SURFACE_FORMS[country];
|
|
36
|
+
if (!forms?.length) {
|
|
37
|
+
throw new Error(`No COUNTRY_SURFACE_FORMS entry for ${country} — add it to codex/country/country.ts before using --country-fraction`);
|
|
38
|
+
}
|
|
39
|
+
return sample(forms, random);
|
|
40
|
+
}
|
|
41
|
+
/**
|
|
42
|
+
* Whether an Overture `unit` value is a secondary-unit designator
|
|
43
|
+
* (a digit or a single bare word) rather than a name.
|
|
44
|
+
*
|
|
45
|
+
* Overture-SG puts an estate name in this field on 91,818 of 142,210 rows and the literal
|
|
46
|
+
* `NIL` on 47,407 more, so a name taught as `unit` would teach a trailing proper name.
|
|
47
|
+
*/
|
|
48
|
+
export function unitFieldIsDesignator(value) {
|
|
49
|
+
const trimmed = value.trim();
|
|
50
|
+
if (!trimmed || trimmed.toUpperCase() === "NIL")
|
|
51
|
+
return false;
|
|
52
|
+
return /\d/u.test(trimmed) || !/\s/u.test(trimmed);
|
|
53
|
+
}
|
|
46
54
|
function parseLine(line) {
|
|
47
55
|
const t = line.trim();
|
|
48
56
|
if (!t || t.startsWith("#"))
|
|
@@ -54,15 +62,20 @@ export function createOvertureAdapter() {
|
|
|
54
62
|
return {
|
|
55
63
|
id: OVERTURE_ADAPTER_ID,
|
|
56
64
|
defaultLicense: OVERTURE_DEFAULT_LICENSE,
|
|
65
|
+
addressRole: AddressRole.Premise,
|
|
66
|
+
// Overture rows include their own `sources[].dataset` and `sources[].license`,
|
|
67
|
+
// so this declares the aggregator rather than asserting a national grant.
|
|
68
|
+
register: SourceRegister.Overture,
|
|
69
|
+
surface: SurfaceOrigin.Rendered,
|
|
57
70
|
description: "Overture Maps Addresses (global): per-country JSONL of street/number/postcode/locality.",
|
|
58
71
|
async *rows(opts) {
|
|
59
72
|
if (!opts.country) {
|
|
60
73
|
throw new Error("overture adapter: --country is required (the Overture JSONL is per-country and rows omit a country field)");
|
|
61
74
|
}
|
|
62
75
|
const country = opts.country;
|
|
63
|
-
|
|
64
|
-
|
|
65
|
-
// including on an early `break`.
|
|
76
|
+
const countryFraction = opts.countryFraction ?? 0;
|
|
77
|
+
const random = makeMulberry32(opts.seed ?? DEFAULT_COUNTRY_SEED);
|
|
78
|
+
// The path string lets `TextSpliterator` own and dispose the file handle, including on an early `break`.
|
|
66
79
|
const lines = TextSpliterator.fromAsync(opts.inputPath);
|
|
67
80
|
let emitted = 0;
|
|
68
81
|
for await (const line of lines) {
|
|
@@ -78,7 +91,7 @@ export function createOvertureAdapter() {
|
|
|
78
91
|
const unit = r.unit?.trim() ?? "";
|
|
79
92
|
const postcode = r.postcode?.trim() ?? "";
|
|
80
93
|
const locality = r.locality?.trim() ?? "";
|
|
81
|
-
// Only useful with a street + (postcode
|
|
94
|
+
// Only useful with a street + (postcode or locality); point-only rows quarantine anyway.
|
|
82
95
|
if (!street)
|
|
83
96
|
continue;
|
|
84
97
|
if (!postcode && !locality)
|
|
@@ -89,7 +102,7 @@ export function createOvertureAdapter() {
|
|
|
89
102
|
components.house_number = number;
|
|
90
103
|
}
|
|
91
104
|
components.street = street;
|
|
92
|
-
if (unit) {
|
|
105
|
+
if (unitFieldIsDesignator(unit)) {
|
|
93
106
|
components.unit = unit;
|
|
94
107
|
}
|
|
95
108
|
if (postcode) {
|
|
@@ -98,12 +111,15 @@ export function createOvertureAdapter() {
|
|
|
98
111
|
if (locality) {
|
|
99
112
|
components.locality = locality;
|
|
100
113
|
}
|
|
101
|
-
|
|
102
|
-
|
|
103
|
-
|
|
104
|
-
|
|
105
|
-
|
|
114
|
+
// Overture rows are country-implicit, so the surface form goes into `components`
|
|
115
|
+
// and each country's layout decides where the country lands in the rendered string.
|
|
116
|
+
if (countryFraction > 0 && random() < countryFraction) {
|
|
117
|
+
components.country = countrySurfaceForm(country, random);
|
|
118
|
+
}
|
|
119
|
+
const rendered = formatAddressRow(components, country, { singleLine: true });
|
|
120
|
+
if (!rendered)
|
|
106
121
|
continue;
|
|
122
|
+
const { raw, components: aligned } = rendered;
|
|
107
123
|
yield {
|
|
108
124
|
raw,
|
|
109
125
|
components: aligned,
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../lib/adapters/overture/adapter.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../lib/adapters/overture/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAEH,OAAO,EAAE,gBAAgB,EAAE,MAAM,iCAAiC,CAAA;AAClE,OAAO,EAAE,qBAAqB,EAAE,MAAM,0BAA0B,CAAA;AAChE,OAAO,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAA;AACrD,OAAO,EAAE,MAAM,EAAE,MAAM,wBAAwB,CAAA;AAC/C,OAAO,EAAE,UAAU,IAAI,cAAc,EAAE,MAAM,uBAAuB,CAAA;AACpE,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C,OAAO,EAAE,cAAc,EAAE,MAAM,qBAAqB,CAAA;AACpD,OAAO,EAAE,cAAc,EAAE,MAAM,YAAY,CAAA;AAC3C,OAAO,EAAE,WAAW,EAA8D,aAAa,EAAE,MAAM,QAAQ,CAAA;AAE/G;;GAEG;AACH,MAAM,CAAC,MAAM,mBAAmB,GAAG,UAAU,CAAA;AAC7C;;;GAGG;AACH,MAAM,CAAC,MAAM,wBAAwB,GAAG,qBAAqB,CAAA;AAE7D,MAAM,oBAAoB,GAAG,UAAU,CAAA;AAEvC;;;;;GAKG;AACH,SAAS,kBAAkB,CAAC,OAAe,EAAE,MAAoB;IAChE,MAAM,KAAK,GAAG,qBAAqB,CAAC,OAA6C,CAAC,CAAA;IAElF,IAAI,CAAC,KAAK,EAAE,MAAM,EAAE,CAAC;QACpB,MAAM,IAAI,KAAK,CACd,sCAAsC,OAAO,uEAAuE,CACpH,CAAA;IACF,CAAC;IAED,OAAO,MAAM,CAAC,KAAK,EAAE,MAAM,CAAC,CAAA;AAC7B,CAAC;AAaD;;;;;;GAMG;AACH,MAAM,UAAU,qBAAqB,CAAC,KAAa;IAClD,MAAM,OAAO,GAAG,KAAK,CAAC,IAAI,EAAE,CAAA;IAE5B,IAAI,CAAC,OAAO,IAAI,OAAO,CAAC,WAAW,EAAE,KAAK,KAAK;QAAE,OAAO,KAAK,CAAA;IAE7D,OAAO,KAAK,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;AACnD,CAAC;AAED,SAAS,SAAS,CAAC,IAAY;IAC9B,MAAM,CAAC,GAAG,IAAI,CAAC,IAAI,EAAE,CAAA;IAErB,IAAI,CAAC,CAAC,IAAI,CAAC,CAAC,UAAU,CAAC,GAAG,CAAC;QAAE,OAAO,IAAI,CAAA;IAExC,MAAM,CAAC,GAAG,cAAc,CAAC,CAAC,CAAC,CAAA;IAE3B,OAAO,CAAC,IAAI,OAAO,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAE,CAAuB,CAAC,CAAC,CAAC,IAAI,CAAA;AACpE,CAAC;AAED,MAAM,UAAU,qBAAqB;IACpC,OAAO;QACN,EAAE,EAAE,mBAAmB;QACvB,cAAc,EAAE,wBAAwB;QACxC,WAAW,EAAE,WAAW,CAAC,OAAO;QAChC,+EAA+E;QAC/E,0EAA0E;QAC1E,QAAQ,EAAE,cAAc,CAAC,QAAQ;QACjC,OAAO,EAAE,aAAa,CAAC,QAAQ;QAC/B,WAAW,EAAE,yFAAyF;QAEtG,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,IAAI,CAAC,IAAI,CAAC,OAAO,EAAE,CAAC;gBACnB,MAAM,IAAI,KAAK,CACd,2GAA2G,CAC3G,CAAA;YACF,CAAC;YAED,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,CAAA;YAC5B,MAAM,eAAe,GAAG,IAAI,CAAC,eAAe,IAAI,CAAC,CAAA;YACjD,MAAM,MAAM,GAAG,cAAc,CAAC,IAAI,CAAC,IAAI,IAAI,oBAAoB,CAAC,CAAA;YAEhE,yGAAyG;YACzG,MAAM,KAAK,GAAG,eAAe,CAAC,SAAS,CAAC,IAAI,CAAC,SAAS,CAAC,CAAA;YAEvD,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,KAAK,EAAE,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;gBAChC,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;oBAAE,MAAK;gBAE/B,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;oBAAE,MAAK;gBAE5D,MAAM,CAAC,GAAG,SAAS,CAAC,IAAI,CAAC,CAAA;gBAEzB,IAAI,CAAC,CAAC;oBAAE,SAAQ;gBAEhB,MAAM,MAAM,GAAG,CAAC,CAAC,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;gBACrC,MAAM,MAAM,GAAG,CAAC,CAAC,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;gBACrC,MAAM,IAAI,GAAG,CAAC,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;gBACjC,MAAM,QAAQ,GAAG,CAAC,CAAC,QAAQ,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;gBACzC,MAAM,QAAQ,GAAG,CAAC,CAAC,QAAQ,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;gBAEzC,yFAAyF;gBACzF,IAAI,CAAC,MAAM;oBAAE,SAAQ;gBAErB,IAAI,CAAC,QAAQ,IAAI,CAAC,QAAQ;oBAAE,SAAQ;gBAEpC,MAAM,UAAU,GAA+B,EAAE,CAAA;gBAEjD,8EAA8E;gBAC9E,IAAI,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,EAAE,CAAC;oBACxB,UAAU,CAAC,YAAY,GAAG,MAAM,CAAA;gBACjC,CAAC;gBAED,UAAU,CAAC,MAAM,GAAG,MAAM,CAAA;gBAE1B,IAAI,qBAAqB,CAAC,IAAI,CAAC,EAAE,CAAC;oBACjC,UAAU,CAAC,IAAI,GAAG,IAAI,CAAA;gBACvB,CAAC;gBAED,IAAI,QAAQ,EAAE,CAAC;oBACd,UAAU,CAAC,QAAQ,GAAG,QAAQ,CAAA;gBAC/B,CAAC;gBAED,IAAI,QAAQ,EAAE,CAAC;oBACd,UAAU,CAAC,QAAQ,GAAG,QAAQ,CAAA;gBAC/B,CAAC;gBAED,iFAAiF;gBACjF,oFAAoF;gBACpF,IAAI,eAAe,GAAG,CAAC,IAAI,MAAM,EAAE,GAAG,eAAe,EAAE,CAAC;oBACvD,UAAU,CAAC,OAAO,GAAG,kBAAkB,CAAC,OAAO,EAAE,MAAM,CAAC,CAAA;gBACzD,CAAC;gBAED,MAAM,QAAQ,GAAG,gBAAgB,CAAC,UAAU,EAAE,OAAO,EAAE,EAAE,UAAU,EAAE,IAAI,EAAE,CAAC,CAAA;gBAE5E,IAAI,CAAC,QAAQ;oBAAE,SAAQ;gBAEvB,MAAM,EAAE,GAAG,EAAE,UAAU,EAAE,OAAO,EAAE,GAAG,QAAQ,CAAA;gBAE7C,MAAM;oBACL,GAAG;oBACH,UAAU,EAAE,OAAO;oBACnB,OAAO;oBACP,MAAM,EAAE,mBAAmB;oBAC3B,SAAS,EAAE,cAAc,CAAC,mBAAmB,EAAE,OAAO,CAAC;oBACvD,cAAc,EAAE,EAAE;oBAClB,OAAO,EAAE,wBAAwB;iBACjC,CAAA;gBAED,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,eAAe,GAAG,qBAAqB,EAAE,CAAA"}
|
|
@@ -0,0 +1,63 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* PO box / PMB / Apartado / BP synthesizer adapter. It emits {@linkcode PO_BOX_ADAPTER_ID}.
|
|
7
|
+
*
|
|
8
|
+
* A PO box delivery line is mutually exclusive with a street line (USPS Pub 28 / DMM 508), so rows
|
|
9
|
+
* are generated fresh from a tuple rather than by mutating a street row.
|
|
10
|
+
*/
|
|
11
|
+
import { type PoBoxBaseTuple } from "#synthesizers/po-box";
|
|
12
|
+
import { type CorpusAdapter } from "#types";
|
|
13
|
+
/**
|
|
14
|
+
* Registry id stamped into every row this adapter emits, so a corpus record traces back to its dataset.
|
|
15
|
+
*
|
|
16
|
+
* The value comes from `RECIPE_SOURCES` because `recipes/po/box/index.ts` writes rows under the same id.
|
|
17
|
+
* Two producers of one id have to spell it the same way, or a rewrite of a corpus through that table
|
|
18
|
+
* moves the recipe's rows and leaves this adapter's behind under a name the table no longer answers for.
|
|
19
|
+
*/
|
|
20
|
+
export declare const PO_BOX_ADAPTER_ID: string;
|
|
21
|
+
/**
|
|
22
|
+
* License for synthetic PO-box rows.
|
|
23
|
+
*
|
|
24
|
+
* They inherit the terms of the real tuples used to derive them.
|
|
25
|
+
*
|
|
26
|
+
* The value is stored in each row's `license` column and read by `licenseNamedIn`,
|
|
27
|
+
* so it stays byte-for-byte.
|
|
28
|
+
*/
|
|
29
|
+
export declare const PO_BOX_LICENSE = "Synthetic \u2014 derived from CC-BY / public-domain input tuples";
|
|
30
|
+
export interface PoBoxInputRow extends PoBoxBaseTuple {
|
|
31
|
+
street?: string;
|
|
32
|
+
houseNumber?: string;
|
|
33
|
+
}
|
|
34
|
+
export interface PoBoxAdapterOptions {
|
|
35
|
+
/**
|
|
36
|
+
* How many PO box variants to emit per input tuple, each picking a different leader
|
|
37
|
+
* (and possibly a different number or noise level); default 1.
|
|
38
|
+
*/
|
|
39
|
+
variantsPerInput?: number;
|
|
40
|
+
/**
|
|
41
|
+
* Probability (0..1) of emitting a PMB-with-street variant when the input has
|
|
42
|
+
* a street and the locale supports PMB.
|
|
43
|
+
* The default is 0.15.
|
|
44
|
+
*/
|
|
45
|
+
pmbRatio?: number;
|
|
46
|
+
/**
|
|
47
|
+
* Deterministic seed for reproducible synthesis.
|
|
48
|
+
* The default is `Date.now()`.
|
|
49
|
+
*/
|
|
50
|
+
seed?: number;
|
|
51
|
+
/**
|
|
52
|
+
* Probability (0..1) per input tuple of additionally emitting one self-contained US
|
|
53
|
+
* military/diplomatic PO-box row, so military volume scales with the input stream.
|
|
54
|
+
* The default is 0.
|
|
55
|
+
*/
|
|
56
|
+
militaryRatio?: number;
|
|
57
|
+
}
|
|
58
|
+
export declare function createPoBoxAdapter(opts?: PoBoxAdapterOptions): CorpusAdapter;
|
|
59
|
+
/**
|
|
60
|
+
* The configured adapter instance registered with the corpus builder.
|
|
61
|
+
*/
|
|
62
|
+
export declare const poBoxAdapter: CorpusAdapter;
|
|
63
|
+
//# sourceMappingURL=adapter.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../lib/adapters/po-box/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAQH,OAAO,EAKN,KAAK,cAAc,EACnB,MAAM,sBAAsB,CAAA;AAC7B,OAAO,EAAuD,KAAK,aAAa,EAAiB,MAAM,QAAQ,CAAA;AAE/G;;;;;;GAMG;AACH,eAAO,MAAM,iBAAiB,QAAsC,CAAA;AACpE;;;;;;;GAOG;AACH,eAAO,MAAM,cAAc,qEAAgE,CAAA;AAE3F,MAAM,WAAW,aAAc,SAAQ,cAAc;IACpD,MAAM,CAAC,EAAE,MAAM,CAAA;IACf,WAAW,CAAC,EAAE,MAAM,CAAA;CACpB;AAED,MAAM,WAAW,mBAAmB;IACnC;;;OAGG;IACH,gBAAgB,CAAC,EAAE,MAAM,CAAA;IACzB;;;;OAIG;IACH,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB;;;OAGG;IACH,IAAI,CAAC,EAAE,MAAM,CAAA;IACb;;;;OAIG;IACH,aAAa,CAAC,EAAE,MAAM,CAAA;CACtB;AAED,wBAAgB,kBAAkB,CAAC,IAAI,GAAE,mBAAwB,GAAG,aAAa,CA0HhF;AAED;;GAEG;AACH,eAAO,MAAM,YAAY,eAAuB,CAAA"}
|