@mailwoman/corpus 10.0.0 → 10.2.0
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 +120 -34
- 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 +791 -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 +31 -37
- package/lib/adapters/gleif/adapter.ts +829 -0
- package/lib/adapters/libpostal-dictionary.ts +37 -0
- package/lib/adapters/openaddresses/adapter.ts +52 -55
- package/lib/adapters/osm/adapter.ts +162 -83
- package/lib/adapters/overture/adapter.ts +52 -43
- package/lib/adapters/po-box/adapter.ts +207 -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 +136 -0
- package/lib/adapters/wof/admin/json/adapter.ts +50 -35
- package/lib/adapters/wof/json-rows.ts +57 -26
- package/lib/adapters/wof/postalcode-json/adapter.ts +63 -61
- package/lib/adapters.ts +230 -0
- package/lib/au/adapters/gnaf/adapter.ts +36 -44
- package/lib/au/adapters/gnaf/assemble.ts +31 -51
- package/lib/be/adapters/brussels/adapter.ts +566 -0
- package/lib/be/adapters/vlaanderen/adapter.ts +667 -0
- package/lib/be/adapters/wallonie/adapter.ts +537 -0
- package/lib/be/tools/fetch/brussels.ts +242 -0
- package/lib/be/tools/fetch/wallonie.ts +275 -0
- package/lib/build/adapters.ts +111 -0
- package/lib/build/align.ts +365 -0
- package/lib/build/checkpoint.ts +133 -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 +234 -0
- package/lib/build.ts +127 -315
- package/lib/cn/recipes/organizational-units.ts +20 -41
- package/lib/cz/adapters/cuzk/adapter.ts +320 -0
- package/lib/cz/recipes/pcfirst-preposition.ts +40 -27
- package/lib/cz/tools/fetch/cuzk.ts +710 -0
- package/lib/de/recipes/locale.ts +69 -59
- package/lib/directory.ts +31 -0
- package/lib/dk/adapters/inspire/adapter.ts +345 -0
- package/lib/dk/tools/fetch/inspire.ts +323 -0
- package/lib/ee/adapters/ads/adapter.ts +240 -0
- package/lib/ee/tools/fetch/ads.ts +272 -0
- package/lib/env.ts +6 -2
- package/lib/es/adapters/bizkaia/adapter.ts +388 -0
- package/lib/es/adapters/catastro/adapter.ts +345 -0
- package/lib/es/adapters/gipuzkoa/adapter.ts +256 -0
- package/lib/es/adapters/navarra/adapter.ts +290 -0
- package/lib/es/cadastre.ts +194 -0
- package/lib/es/tools/fetch/bizkaia.ts +752 -0
- package/lib/es/tools/fetch/catastro.ts +765 -0
- package/lib/es/tools/fetch/gipuzkoa.ts +338 -0
- package/lib/es/tools/fetch/navarra.ts +496 -0
- package/lib/fi/adapters/ryhti/adapter.ts +319 -0
- package/lib/fi/tools/fetch/ryhti.ts +476 -0
- package/lib/fingerprints.ts +154 -0
- package/lib/fr/adapters/annuaire-education/adapter.ts +600 -0
- package/lib/fr/adapters/ban/adapter.ts +87 -59
- package/lib/fr/adapters/finess/adapter.ts +619 -0
- package/lib/fr/adapters/finess/postal-lines.ts +157 -0
- package/lib/fr/adapters/finess/voie-type.ts +201 -0
- package/lib/fr/insee-country.ts +62 -0
- package/lib/fr/recipes/admin-split.ts +38 -60
- package/lib/fr/recipes/bare-street.ts +37 -50
- package/lib/fr/recipes/fragment.ts +59 -142
- package/lib/fr/recipes/lieudit.ts +111 -73
- package/lib/fr/recipes/order.ts +32 -59
- package/lib/fr/{adapters/ban/street-decompose.ts → street-decompose.ts} +4 -3
- package/lib/fr/tools/fetch/annuaire-education.ts +309 -0
- package/lib/fr/tools/fetch/ban.ts +30 -20
- package/lib/fr/tools/fetch/finess.ts +353 -0
- package/lib/gauntlet-inputs.ts +92 -0
- package/lib/index.ts +9 -3
- package/lib/inspire/address.ts +465 -0
- package/lib/inspire/archive.ts +44 -0
- package/lib/inspire/errors.ts +72 -0
- package/lib/inspire/stream.ts +265 -0
- package/lib/international/recipes/locale.ts +146 -184
- package/lib/it/adapters/anac/adapter.ts +527 -0
- package/lib/it/tools/fetch/anac.ts +391 -0
- package/lib/jp/adapters/wof-admin/adapter.ts +29 -23
- package/lib/jp/tools/fetch/houjin.ts +19 -21
- package/lib/kr/adapters/juso/label-rows.ts +24 -44
- package/lib/kr/adapters/localdata/align.ts +20 -31
- package/lib/kr/adapters/localdata/key-index.ts +17 -25
- package/lib/kr/adapters/localdata/permit-rows.ts +34 -27
- package/lib/kr/tools/fetch/juso.ts +19 -21
- package/lib/kr/tools/fetch/localdata.ts +29 -30
- package/lib/lu/adapters/bd-adresses/adapter.ts +240 -0
- package/lib/lu/tools/fetch/bd-adresses.ts +353 -0
- package/lib/lv/adapters/varis/adapter.ts +500 -0
- package/lib/lv/tools/fetch/varis.ts +215 -0
- package/lib/nl/adapters/kadaster/adapter.ts +386 -0
- package/lib/nl/recipes/postcode.ts +46 -24
- package/lib/nl/tools/fetch/kadaster.ts +302 -0
- package/lib/no/adapters/matrikkelen/adapter.ts +188 -0
- package/lib/no/recipes/fragment.ts +34 -58
- package/lib/no/recipes/street/led.ts +44 -25
- package/lib/no/recipes/{street/index.ts → street.ts} +29 -11
- package/lib/no/tools/fetch/matrikkelen.ts +531 -0
- package/lib/parquet/duckdb.ts +147 -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 +452 -0
- package/lib/pl/adapters/emuia/adapter.ts +202 -0
- package/lib/pl/tools/fetch/emuia.ts +361 -0
- package/lib/recipes/anchor-absorption.ts +30 -19
- package/lib/recipes/bare/country.ts +24 -32
- package/lib/recipes/bare/postcode/eval.ts +1 -1
- package/lib/recipes/bare/postcode.ts +346 -0
- package/lib/recipes/boundary-stress.ts +37 -20
- package/lib/recipes/country-balanced.ts +66 -86
- package/lib/recipes/house-venue.ts +36 -14
- package/lib/recipes/intersection.ts +84 -62
- package/lib/recipes/po/box/cedex/au-nz.ts +3 -3
- package/lib/recipes/po/box/cedex/ca.ts +3 -2
- package/lib/recipes/po/box/cedex/fr.ts +4 -3
- package/lib/recipes/po/box/cedex/phrases.ts +7 -6
- package/lib/recipes/po/box/cedex/recipe.ts +31 -19
- package/lib/recipes/po/box/cedex/sources.ts +16 -4
- package/lib/recipes/po/box/cedex/us.ts +7 -2
- package/lib/recipes/po/{box/index.ts → box.ts} +39 -18
- package/lib/recipes/scaffold.ts +267 -158
- package/lib/recipes/sources.ts +412 -0
- package/lib/recipes/street/affix.ts +54 -154
- package/lib/recipes/street/bare.ts +30 -17
- package/lib/recipes/street.ts +35 -9
- package/lib/recipes/sub/venue/context.ts +32 -23
- package/lib/recipes/sub/venue/render.ts +170 -0
- package/lib/recipes/sub/venue/sources.ts +92 -248
- package/lib/recipes/sub/venue.ts +795 -0
- package/lib/recipes/trailing-region.ts +75 -87
- package/lib/recipes/unit/sources.ts +44 -0
- package/lib/recipes/unit.ts +101 -89
- package/lib/recipes/venue.ts +347 -0
- package/lib/{recipes/index.ts → recipes.ts} +15 -11
- package/lib/registers.ts +280 -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 +221 -84
- package/lib/sg/recipes/register.ts +47 -53
- package/lib/sg/tools/fetch/acra.ts +23 -28
- package/lib/si/recipes/bare-village.ts +34 -17
- package/lib/sk/adapters/inspire/adapter.ts +393 -0
- package/lib/sk/tools/fetch/inspire.ts +403 -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 +589 -0
- package/lib/source-register.ts +71 -0
- package/lib/south-asia/recipes/register.ts +45 -26
- package/lib/subvenue/harvest.ts +251 -0
- package/lib/{tools/sub/venue → subvenue}/promotions.ts +33 -70
- package/lib/subvenue/surfaces.ts +94 -0
- package/lib/subvenue/table.ts +264 -0
- package/lib/surfaces/locale.ts +248 -0
- package/lib/synthesizers/anchor-absorption.ts +56 -91
- package/lib/synthesizers/boundary-stress.ts +67 -155
- package/lib/synthesizers/house-venue.ts +65 -127
- package/lib/synthesizers/no-street.ts +71 -119
- package/lib/synthesizers/po-box.ts +93 -105
- package/lib/synthesizers/tail.ts +55 -0
- package/lib/synthesizers/utils.ts +82 -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 +117 -120
- package/lib/tools/corpus-stats.ts +45 -31
- package/lib/tools/fetch/atom.ts +164 -0
- package/lib/tools/fetch/cordis.ts +320 -0
- package/lib/tools/fetch/download/manifest.ts +36 -23
- package/lib/tools/fetch/download/network.ts +55 -31
- package/lib/tools/fetch/download/retry.ts +30 -29
- package/lib/tools/fetch/geonames/dump.ts +75 -55
- package/lib/tools/fetch/geonames/postal.ts +27 -62
- package/lib/tools/fetch/gleif.ts +362 -0
- package/lib/tools/fetch/header.ts +71 -0
- package/lib/tools/fetch/inspire-addresses.ts +500 -0
- package/lib/tools/fetch/openaddresses.ts +23 -112
- package/lib/tools/fetch/ourairports.ts +18 -51
- package/lib/tools/fetch/ppd.ts +10 -8
- package/lib/tools/fetch/vlaanderen-ad.ts +435 -0
- package/lib/tools/fetch/wfs-harvest.ts +954 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +45 -145
- package/lib/tools/fetch/zip-archive.ts +100 -0
- package/lib/tools/fetch.ts +101 -0
- package/lib/tools/golden/expand.ts +75 -44
- package/lib/tools/golden/promote.ts +47 -34
- package/lib/tools/golden/relabel-street/directory.ts +67 -39
- package/lib/tools/golden/relabel-street/row.ts +32 -109
- package/lib/tools/ingest-csv.ts +48 -51
- package/lib/tools/jsonl-to-parquet.ts +59 -98
- package/lib/tools/lint/recipe-output/vocab.ts +371 -0
- package/lib/tools/lint/{slice/index.ts → recipe-output.ts} +130 -126
- 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/{slice → overlay}/kryptonite.ts +47 -39
- package/lib/tools/overlay/manifest.ts +409 -0
- package/lib/tools/overlay/merge-source.ts +139 -0
- package/lib/tools/overlay/split-slice.ts +144 -0
- package/lib/tools/overlay/translit.ts +236 -0
- package/lib/tools/overture-subvenue.ts +18 -91
- package/lib/tools/postcode-triples.ts +284 -212
- package/lib/tools/source-register/build.ts +822 -0
- package/lib/tools/sub/venue/head-nouns.ts +38 -75
- package/lib/tools/sub/venue/lexicon.ts +71 -110
- package/lib/tools/sub/venue/wikidata.ts +13 -10
- package/lib/tw/tools/fetch/gcis.ts +21 -20
- package/lib/types.ts +305 -101
- package/lib/us/adapters/fcc-bdc/adapter.ts +26 -41
- package/lib/us/adapters/state/hi-schools/adapter.ts +28 -17
- package/lib/us/adapters/state/hi-schools/workbook.ts +8 -3
- package/lib/us/adapters/state/ia-contractors/adapter.ts +27 -15
- package/lib/us/adapters/state/ny-notaries/adapter.ts +24 -25
- package/lib/us/adapters/state/tx-notaries/adapter.ts +21 -15
- package/lib/us/adapters/tiger/adapter.ts +19 -44
- package/lib/us/adapters/tiger/street-decompose.ts +7 -17
- package/lib/us/adapters/usgov/hrsa-fqhc/adapter.ts +49 -34
- package/lib/us/adapters/usgov/imls-pls/adapter.ts +25 -19
- package/lib/us/adapters/usgov/irs-bmf/adapter.ts +32 -23
- package/lib/us/adapters/usgov/nad/adapter.ts +61 -122
- package/lib/us/adapters/usgov/nppes/adapter.ts +72 -35
- package/lib/us/adapters/usgov/samhsa-treatment-locator/adapter.ts +47 -34
- package/lib/us/fips-state.ts +19 -10
- package/lib/{synthesizers → us/synthesizers}/intersection.ts +45 -35
- package/lib/{synthesizers → us/synthesizers}/street.ts +56 -43
- package/lib/us/tools/fetch/hrsa.ts +7 -8
- package/lib/us/tools/fetch/imls-pls.ts +18 -36
- package/lib/us/tools/fetch/nad.ts +51 -33
- package/lib/us/tools/fetch/nppes.ts +27 -39
- package/lib/us/tools/fetch/state/hi-schools.ts +24 -17
- package/lib/us/tools/fetch/state/sources.ts +12 -12
- package/lib/us/tools/fetch/tiger-full.ts +22 -74
- package/lib/utils/align.ts +52 -59
- package/lib/utils/{slice-stats.ts → cooccurrence-stats.ts} +22 -16
- package/lib/utils/golden.ts +36 -51
- package/lib/utils/license.ts +239 -27
- package/lib/utils/split.ts +209 -88
- package/lib/utils/tokenize.ts +25 -56
- package/lib/utils/wof-json.ts +130 -77
- package/lib/{utils/index.ts → utils.ts} +0 -1
- package/lib/ve/recipes/reviewed-postcode-tail.ts +40 -13
- package/out/adapters/cordis/adapter.d.ts +326 -0
- package/out/adapters/cordis/adapter.d.ts.map +1 -0
- package/out/adapters/cordis/adapter.js +622 -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 +14 -27
- package/out/adapters/geonames/postal/adapter.d.ts.map +1 -1
- package/out/adapters/geonames/postal/adapter.js +30 -35
- package/out/adapters/geonames/postal/adapter.js.map +1 -1
- 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 +685 -0
- package/out/adapters/gleif/adapter.js.map +1 -0
- package/out/adapters/libpostal-dictionary.d.ts +20 -0
- package/out/adapters/libpostal-dictionary.d.ts.map +1 -0
- package/out/adapters/libpostal-dictionary.js +34 -0
- package/out/adapters/libpostal-dictionary.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts +29 -43
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -1
- package/out/adapters/openaddresses/adapter.js +34 -46
- package/out/adapters/openaddresses/adapter.js.map +1 -1
- package/out/adapters/osm/adapter.d.ts +59 -52
- package/out/adapters/osm/adapter.d.ts.map +1 -1
- package/out/adapters/osm/adapter.js +119 -69
- package/out/adapters/osm/adapter.js.map +1 -1
- package/out/adapters/overture/adapter.d.ts +11 -37
- package/out/adapters/overture/adapter.d.ts.map +1 -1
- package/out/adapters/overture/adapter.js +45 -42
- package/out/adapters/overture/adapter.js.map +1 -1
- package/out/adapters/po-box/adapter.d.ts +66 -0
- package/out/adapters/po-box/adapter.d.ts.map +1 -0
- package/out/adapters/{synth-po-box → po-box}/adapter.js +48 -47
- 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 +103 -0
- package/out/adapters/street-line.d.ts.map +1 -0
- package/out/adapters/street-line.js +118 -0
- package/out/adapters/street-line.js.map +1 -0
- package/out/adapters/wof/admin/json/adapter.d.ts +27 -18
- package/out/adapters/wof/admin/json/adapter.d.ts.map +1 -1
- package/out/adapters/wof/admin/json/adapter.js +48 -32
- package/out/adapters/wof/admin/json/adapter.js.map +1 -1
- package/out/adapters/wof/json-rows.d.ts +36 -19
- package/out/adapters/wof/json-rows.d.ts.map +1 -1
- package/out/adapters/wof/json-rows.js +35 -15
- package/out/adapters/wof/json-rows.js.map +1 -1
- package/out/adapters/wof/postalcode-json/adapter.d.ts +22 -38
- package/out/adapters/wof/postalcode-json/adapter.d.ts.map +1 -1
- package/out/adapters/wof/postalcode-json/adapter.js +60 -58
- package/out/adapters/wof/postalcode-json/adapter.js.map +1 -1
- 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 +15 -27
- package/out/au/adapters/gnaf/adapter.d.ts.map +1 -1
- package/out/au/adapters/gnaf/adapter.js +35 -43
- package/out/au/adapters/gnaf/adapter.js.map +1 -1
- package/out/au/adapters/gnaf/assemble.d.ts +15 -26
- package/out/au/adapters/gnaf/assemble.d.ts.map +1 -1
- package/out/au/adapters/gnaf/assemble.js +26 -46
- package/out/au/adapters/gnaf/assemble.js.map +1 -1
- 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 +230 -0
- package/out/be/adapters/vlaanderen/adapter.d.ts.map +1 -0
- package/out/be/adapters/vlaanderen/adapter.js +418 -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 +122 -0
- package/out/be/tools/fetch/brussels.d.ts.map +1 -0
- package/out/be/tools/fetch/brussels.js +148 -0
- package/out/be/tools/fetch/brussels.js.map +1 -0
- package/out/be/tools/fetch/wallonie.d.ts +120 -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 +69 -0
- package/out/build/adapters.js.map +1 -0
- package/out/build/align.d.ts +74 -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 +61 -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 +222 -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 +5 -22
- package/out/cn/recipes/organizational-units.d.ts.map +1 -1
- package/out/cn/recipes/organizational-units.js +20 -41
- package/out/cn/recipes/organizational-units.js.map +1 -1
- 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 +269 -0
- package/out/cz/adapters/cuzk/adapter.js.map +1 -0
- package/out/cz/recipes/pcfirst-preposition.d.ts +7 -11
- package/out/cz/recipes/pcfirst-preposition.d.ts.map +1 -1
- package/out/cz/recipes/pcfirst-preposition.js +36 -27
- package/out/cz/recipes/pcfirst-preposition.js.map +1 -1
- package/out/cz/tools/fetch/cuzk.d.ts +281 -0
- package/out/cz/tools/fetch/cuzk.d.ts.map +1 -0
- package/out/cz/tools/fetch/cuzk.js +448 -0
- package/out/cz/tools/fetch/cuzk.js.map +1 -0
- package/out/de/recipes/locale.d.ts +24 -26
- package/out/de/recipes/locale.d.ts.map +1 -1
- package/out/de/recipes/locale.js +67 -57
- package/out/de/recipes/locale.js.map +1 -1
- 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 +153 -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 +101 -0
- package/out/dk/tools/fetch/inspire.d.ts.map +1 -0
- package/out/dk/tools/fetch/inspire.js +232 -0
- package/out/dk/tools/fetch/inspire.js.map +1 -0
- package/out/ee/adapters/ads/adapter.d.ts +102 -0
- package/out/ee/adapters/ads/adapter.d.ts.map +1 -0
- package/out/ee/adapters/ads/adapter.js +185 -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 +197 -0
- package/out/ee/tools/fetch/ads.js.map +1 -0
- package/out/env.d.ts +6 -2
- 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 +103 -0
- package/out/es/adapters/catastro/adapter.d.ts.map +1 -0
- package/out/es/adapters/catastro/adapter.js +290 -0
- package/out/es/adapters/catastro/adapter.js.map +1 -0
- package/out/es/adapters/gipuzkoa/adapter.d.ts +84 -0
- package/out/es/adapters/gipuzkoa/adapter.d.ts.map +1 -0
- package/out/es/adapters/gipuzkoa/adapter.js +218 -0
- package/out/es/adapters/gipuzkoa/adapter.js.map +1 -0
- package/out/es/adapters/navarra/adapter.d.ts +106 -0
- package/out/es/adapters/navarra/adapter.d.ts.map +1 -0
- package/out/es/adapters/navarra/adapter.js +242 -0
- package/out/es/adapters/navarra/adapter.js.map +1 -0
- package/out/es/cadastre.d.ts +110 -0
- package/out/es/cadastre.d.ts.map +1 -0
- package/out/es/cadastre.js +128 -0
- package/out/es/cadastre.js.map +1 -0
- package/out/es/tools/fetch/bizkaia.d.ts +281 -0
- package/out/es/tools/fetch/bizkaia.d.ts.map +1 -0
- package/out/es/tools/fetch/bizkaia.js +478 -0
- package/out/es/tools/fetch/bizkaia.js.map +1 -0
- package/out/es/tools/fetch/catastro.d.ts +280 -0
- package/out/es/tools/fetch/catastro.d.ts.map +1 -0
- package/out/es/tools/fetch/catastro.js +491 -0
- package/out/es/tools/fetch/catastro.js.map +1 -0
- package/out/es/tools/fetch/gipuzkoa.d.ts +164 -0
- package/out/es/tools/fetch/gipuzkoa.d.ts.map +1 -0
- package/out/es/tools/fetch/gipuzkoa.js +210 -0
- package/out/es/tools/fetch/gipuzkoa.js.map +1 -0
- package/out/es/tools/fetch/navarra.d.ts +194 -0
- package/out/es/tools/fetch/navarra.d.ts.map +1 -0
- package/out/es/tools/fetch/navarra.js +321 -0
- package/out/es/tools/fetch/navarra.js.map +1 -0
- package/out/fi/adapters/ryhti/adapter.d.ts +111 -0
- package/out/fi/adapters/ryhti/adapter.d.ts.map +1 -0
- package/out/fi/adapters/ryhti/adapter.js +240 -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 +324 -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 +477 -0
- package/out/fr/adapters/annuaire-education/adapter.js.map +1 -0
- package/out/fr/adapters/ban/adapter.d.ts +19 -25
- package/out/fr/adapters/ban/adapter.d.ts.map +1 -1
- package/out/fr/adapters/ban/adapter.js +65 -54
- package/out/fr/adapters/ban/adapter.js.map +1 -1
- package/out/fr/adapters/finess/adapter.d.ts +277 -0
- package/out/fr/adapters/finess/adapter.d.ts.map +1 -0
- package/out/fr/adapters/finess/adapter.js +520 -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 +173 -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 +4 -27
- package/out/fr/recipes/admin-split.d.ts.map +1 -1
- package/out/fr/recipes/admin-split.js +36 -58
- package/out/fr/recipes/admin-split.js.map +1 -1
- package/out/fr/recipes/bare-street.d.ts +2 -17
- package/out/fr/recipes/bare-street.d.ts.map +1 -1
- package/out/fr/recipes/bare-street.js +35 -50
- package/out/fr/recipes/bare-street.js.map +1 -1
- package/out/fr/recipes/fragment.d.ts +6 -65
- package/out/fr/recipes/fragment.d.ts.map +1 -1
- package/out/fr/recipes/fragment.js +55 -135
- package/out/fr/recipes/fragment.js.map +1 -1
- package/out/fr/recipes/lieudit.d.ts +17 -19
- package/out/fr/recipes/lieudit.d.ts.map +1 -1
- package/out/fr/recipes/lieudit.js +89 -68
- package/out/fr/recipes/lieudit.js.map +1 -1
- package/out/fr/recipes/order.d.ts +4 -27
- package/out/fr/recipes/order.d.ts.map +1 -1
- package/out/fr/recipes/order.js +31 -58
- package/out/fr/recipes/order.js.map +1 -1
- package/out/fr/{adapters/ban/street-decompose.d.ts → street-decompose.d.ts} +3 -2
- package/out/fr/street-decompose.d.ts.map +1 -0
- package/out/fr/{adapters/ban/street-decompose.js → street-decompose.js} +4 -3
- package/out/fr/street-decompose.js.map +1 -0
- package/out/fr/tools/fetch/annuaire-education.d.ts +133 -0
- package/out/fr/tools/fetch/annuaire-education.d.ts.map +1 -0
- package/out/fr/tools/fetch/annuaire-education.js +198 -0
- package/out/fr/tools/fetch/annuaire-education.js.map +1 -0
- package/out/fr/tools/fetch/ban.d.ts +9 -7
- package/out/fr/tools/fetch/ban.d.ts.map +1 -1
- package/out/fr/tools/fetch/ban.js +29 -19
- package/out/fr/tools/fetch/ban.js.map +1 -1
- 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 +229 -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 +9 -3
- package/out/index.d.ts.map +1 -1
- package/out/index.js +9 -3
- package/out/index.js.map +1 -1
- package/out/inspire/address.d.ts +261 -0
- package/out/inspire/address.d.ts.map +1 -0
- package/out/inspire/address.js +395 -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 +56 -0
- package/out/inspire/errors.d.ts.map +1 -0
- package/out/inspire/errors.js +65 -0
- package/out/inspire/errors.js.map +1 -0
- package/out/inspire/stream.d.ts +140 -0
- package/out/inspire/stream.d.ts.map +1 -0
- package/out/inspire/stream.js +123 -0
- package/out/inspire/stream.js.map +1 -0
- package/out/international/recipes/locale.d.ts +40 -86
- package/out/international/recipes/locale.d.ts.map +1 -1
- package/out/international/recipes/locale.js +122 -157
- package/out/international/recipes/locale.js.map +1 -1
- package/out/it/adapters/anac/adapter.d.ts +269 -0
- package/out/it/adapters/anac/adapter.d.ts.map +1 -0
- package/out/it/adapters/anac/adapter.js +434 -0
- package/out/it/adapters/anac/adapter.js.map +1 -0
- package/out/it/tools/fetch/anac.d.ts +171 -0
- package/out/it/tools/fetch/anac.d.ts.map +1 -0
- package/out/it/tools/fetch/anac.js +269 -0
- package/out/it/tools/fetch/anac.js.map +1 -0
- package/out/jp/adapters/wof-admin/adapter.d.ts +14 -11
- package/out/jp/adapters/wof-admin/adapter.d.ts.map +1 -1
- package/out/jp/adapters/wof-admin/adapter.js +27 -16
- package/out/jp/adapters/wof-admin/adapter.js.map +1 -1
- package/out/jp/tools/fetch/houjin.d.ts +7 -4
- package/out/jp/tools/fetch/houjin.d.ts.map +1 -1
- package/out/jp/tools/fetch/houjin.js +17 -13
- package/out/jp/tools/fetch/houjin.js.map +1 -1
- package/out/kr/adapters/juso/label-rows.d.ts +17 -31
- package/out/kr/adapters/juso/label-rows.d.ts.map +1 -1
- package/out/kr/adapters/juso/label-rows.js +19 -41
- package/out/kr/adapters/juso/label-rows.js.map +1 -1
- package/out/kr/adapters/localdata/align.d.ts +4 -16
- package/out/kr/adapters/localdata/align.d.ts.map +1 -1
- package/out/kr/adapters/localdata/align.js +19 -30
- package/out/kr/adapters/localdata/align.js.map +1 -1
- package/out/kr/adapters/localdata/key-index.d.ts +13 -22
- package/out/kr/adapters/localdata/key-index.d.ts.map +1 -1
- package/out/kr/adapters/localdata/key-index.js +15 -21
- package/out/kr/adapters/localdata/key-index.js.map +1 -1
- package/out/kr/adapters/localdata/permit-rows.d.ts +21 -14
- package/out/kr/adapters/localdata/permit-rows.d.ts.map +1 -1
- package/out/kr/adapters/localdata/permit-rows.js +31 -26
- package/out/kr/adapters/localdata/permit-rows.js.map +1 -1
- package/out/kr/tools/fetch/juso.d.ts +11 -8
- package/out/kr/tools/fetch/juso.d.ts.map +1 -1
- package/out/kr/tools/fetch/juso.js +15 -14
- package/out/kr/tools/fetch/juso.js.map +1 -1
- package/out/kr/tools/fetch/localdata.d.ts +16 -9
- package/out/kr/tools/fetch/localdata.d.ts.map +1 -1
- package/out/kr/tools/fetch/localdata.js +24 -16
- package/out/kr/tools/fetch/localdata.js.map +1 -1
- 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 +165 -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 +284 -0
- package/out/lv/adapters/varis/adapter.d.ts.map +1 -0
- package/out/lv/adapters/varis/adapter.js +405 -0
- package/out/lv/adapters/varis/adapter.js.map +1 -0
- package/out/lv/tools/fetch/varis.d.ts +81 -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 +309 -0
- package/out/nl/adapters/kadaster/adapter.js.map +1 -0
- package/out/nl/recipes/postcode.d.ts +12 -14
- package/out/nl/recipes/postcode.d.ts.map +1 -1
- package/out/nl/recipes/postcode.js +42 -24
- package/out/nl/recipes/postcode.js.map +1 -1
- package/out/nl/tools/fetch/kadaster.d.ts +159 -0
- package/out/nl/tools/fetch/kadaster.d.ts.map +1 -0
- package/out/nl/tools/fetch/kadaster.js +182 -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 +1 -33
- package/out/no/recipes/fragment.d.ts.map +1 -1
- package/out/no/recipes/fragment.js +23 -57
- package/out/no/recipes/fragment.js.map +1 -1
- package/out/no/recipes/street/led.d.ts +9 -12
- package/out/no/recipes/street/led.d.ts.map +1 -1
- package/out/no/recipes/street/led.js +34 -24
- package/out/no/recipes/street/led.js.map +1 -1
- package/out/no/recipes/street.d.ts +19 -0
- package/out/no/recipes/street.d.ts.map +1 -0
- package/out/no/recipes/{street/index.js → street.js} +28 -12
- package/out/no/recipes/street.js.map +1 -0
- package/out/no/tools/fetch/matrikkelen.d.ts +263 -0
- package/out/no/tools/fetch/matrikkelen.d.ts.map +1 -0
- package/out/no/tools/fetch/matrikkelen.js +353 -0
- package/out/no/tools/fetch/matrikkelen.js.map +1 -0
- package/out/parquet/duckdb.d.ts +103 -0
- package/out/parquet/duckdb.d.ts.map +1 -0
- package/out/parquet/duckdb.js +93 -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 +252 -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 +166 -0
- package/out/pl/tools/fetch/emuia.d.ts.map +1 -0
- package/out/pl/tools/fetch/emuia.js +261 -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 +2 -20
- package/out/recipes/bare/country.d.ts.map +1 -1
- package/out/recipes/bare/country.js +20 -31
- package/out/recipes/bare/country.js.map +1 -1
- package/out/recipes/bare/postcode/eval.d.ts +1 -1
- package/out/recipes/bare/postcode/eval.js +1 -1
- package/out/recipes/bare/postcode.d.ts +41 -0
- package/out/recipes/bare/postcode.d.ts.map +1 -0
- package/out/recipes/bare/{postcode/index.js → postcode.js} +92 -80
- 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 +37 -20
- 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 +33 -14
- 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 +67 -55
- package/out/recipes/intersection.js.map +1 -1
- package/out/recipes/po/box/cedex/au-nz.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/au-nz.js +3 -3
- package/out/recipes/po/box/cedex/au-nz.js.map +1 -1
- package/out/recipes/po/box/cedex/ca.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/ca.js +2 -2
- package/out/recipes/po/box/cedex/ca.js.map +1 -1
- package/out/recipes/po/box/cedex/fr.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/fr.js +3 -3
- package/out/recipes/po/box/cedex/fr.js.map +1 -1
- package/out/recipes/po/box/cedex/phrases.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/phrases.js +7 -6
- package/out/recipes/po/box/cedex/phrases.js.map +1 -1
- package/out/recipes/po/box/cedex/recipe.d.ts +1 -1
- package/out/recipes/po/box/cedex/recipe.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/recipe.js +27 -16
- package/out/recipes/po/box/cedex/recipe.js.map +1 -1
- package/out/recipes/po/box/cedex/sources.d.ts +20 -14
- package/out/recipes/po/box/cedex/sources.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/sources.js +2 -2
- package/out/recipes/po/box/cedex/sources.js.map +1 -1
- package/out/recipes/po/box/cedex/us.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/us.js +5 -2
- package/out/recipes/po/box/cedex/us.js.map +1 -1
- package/out/recipes/po/box.d.ts +18 -0
- package/out/recipes/po/box.d.ts.map +1 -0
- package/out/recipes/po/{box/index.js → box.js} +37 -19
- package/out/recipes/po/box.js.map +1 -0
- package/out/recipes/scaffold.d.ts +223 -141
- package/out/recipes/scaffold.d.ts.map +1 -1
- package/out/recipes/scaffold.js +75 -65
- 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 +361 -0
- package/out/recipes/sources.js.map +1 -0
- package/out/recipes/street/affix.d.ts +20 -50
- package/out/recipes/street/affix.d.ts.map +1 -1
- package/out/recipes/street/affix.js +45 -133
- package/out/recipes/street/affix.js.map +1 -1
- package/out/recipes/street/bare.d.ts +9 -7
- package/out/recipes/street/bare.d.ts.map +1 -1
- package/out/recipes/street/bare.js +27 -16
- package/out/recipes/street/bare.js.map +1 -1
- package/out/recipes/street.d.ts +6 -4
- package/out/recipes/street.d.ts.map +1 -1
- package/out/recipes/street.js +32 -9
- package/out/recipes/street.js.map +1 -1
- package/out/recipes/sub/venue/context.d.ts +12 -9
- package/out/recipes/sub/venue/context.d.ts.map +1 -1
- package/out/recipes/sub/venue/context.js +23 -17
- package/out/recipes/sub/venue/context.js.map +1 -1
- 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 +53 -93
- package/out/recipes/sub/venue/sources.d.ts.map +1 -1
- package/out/recipes/sub/venue/sources.js +57 -197
- package/out/recipes/sub/venue/sources.js.map +1 -1
- package/out/recipes/sub/venue.d.ts +173 -0
- package/out/recipes/sub/venue.d.ts.map +1 -0
- package/out/recipes/sub/venue.js +558 -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 +61 -86
- 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/venue.d.ts +119 -0
- package/out/recipes/venue.d.ts.map +1 -0
- package/out/recipes/venue.js +245 -0
- package/out/recipes/venue.js.map +1 -0
- package/out/recipes.d.ts +26 -0
- package/out/recipes.d.ts.map +1 -0
- package/out/{recipes/index.js → recipes.js} +16 -12
- package/out/recipes.js.map +1 -0
- package/out/registers.d.ts +279 -0
- package/out/registers.d.ts.map +1 -0
- package/out/registers.js +275 -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 +121 -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 +18 -32
- package/out/sg/recipes/register.d.ts.map +1 -1
- package/out/sg/recipes/register.js +45 -50
- package/out/sg/recipes/register.js.map +1 -1
- package/out/sg/tools/fetch/acra.d.ts +11 -14
- package/out/sg/tools/fetch/acra.d.ts.map +1 -1
- package/out/sg/tools/fetch/acra.js +18 -21
- package/out/sg/tools/fetch/acra.js.map +1 -1
- package/out/si/recipes/bare-village.d.ts +12 -13
- package/out/si/recipes/bare-village.d.ts.map +1 -1
- package/out/si/recipes/bare-village.js +31 -17
- package/out/si/recipes/bare-village.js.map +1 -1
- 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 +196 -0
- package/out/sk/tools/fetch/inspire.d.ts.map +1 -0
- package/out/sk/tools/fetch/inspire.js +281 -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 +538 -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 +20 -17
- package/out/south-asia/recipes/register.d.ts.map +1 -1
- package/out/south-asia/recipes/register.js +44 -24
- package/out/south-asia/recipes/register.js.map +1 -1
- 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/{tools/sub/venue → subvenue}/promotions.js +15 -55
- 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 +138 -0
- package/out/surfaces/locale.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +22 -30
- 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 +18 -49
- package/out/synthesizers/boundary-stress.d.ts.map +1 -1
- package/out/synthesizers/boundary-stress.js +45 -142
- package/out/synthesizers/boundary-stress.js.map +1 -1
- package/out/synthesizers/house-venue.d.ts +23 -25
- package/out/synthesizers/house-venue.d.ts.map +1 -1
- package/out/synthesizers/house-venue.js +47 -118
- package/out/synthesizers/house-venue.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 +48 -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/tail.d.ts +36 -0
- package/out/synthesizers/tail.d.ts.map +1 -0
- package/out/synthesizers/tail.js +32 -0
- package/out/synthesizers/tail.js.map +1 -0
- package/out/synthesizers/utils.d.ts +33 -129
- package/out/synthesizers/utils.d.ts.map +1 -1
- package/out/synthesizers/utils.js +71 -167
- 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 +19 -11
- package/out/tools/audit.d.ts.map +1 -1
- package/out/tools/audit.js +89 -97
- 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 +34 -30
- 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 +83 -0
- package/out/tools/fetch/atom.js.map +1 -0
- package/out/tools/fetch/cordis.d.ts +124 -0
- package/out/tools/fetch/cordis.d.ts.map +1 -0
- package/out/tools/fetch/cordis.js +210 -0
- package/out/tools/fetch/cordis.js.map +1 -0
- package/out/tools/fetch/download/manifest.d.ts +27 -18
- package/out/tools/fetch/download/manifest.d.ts.map +1 -1
- package/out/tools/fetch/download/manifest.js +22 -14
- package/out/tools/fetch/download/manifest.js.map +1 -1
- package/out/tools/fetch/download/network.d.ts +48 -27
- package/out/tools/fetch/download/network.d.ts.map +1 -1
- package/out/tools/fetch/download/network.js +26 -16
- package/out/tools/fetch/download/network.js.map +1 -1
- package/out/tools/fetch/download/retry.d.ts +16 -15
- package/out/tools/fetch/download/retry.d.ts.map +1 -1
- package/out/tools/fetch/download/retry.js +28 -28
- package/out/tools/fetch/download/retry.js.map +1 -1
- package/out/tools/fetch/{download/index.d.ts → download.d.ts} +1 -1
- package/out/tools/fetch/download.d.ts.map +1 -0
- package/out/tools/fetch/{download/index.js → download.js} +1 -1
- package/out/tools/fetch/download.js.map +1 -0
- package/out/tools/fetch/geonames/dump.d.ts +51 -32
- package/out/tools/fetch/geonames/dump.d.ts.map +1 -1
- package/out/tools/fetch/geonames/dump.js +54 -43
- package/out/tools/fetch/geonames/dump.js.map +1 -1
- package/out/tools/fetch/geonames/postal.d.ts +14 -49
- package/out/tools/fetch/geonames/postal.d.ts.map +1 -1
- package/out/tools/fetch/geonames/postal.js +17 -56
- package/out/tools/fetch/geonames/postal.js.map +1 -1
- package/out/tools/fetch/gleif.d.ts +138 -0
- package/out/tools/fetch/gleif.d.ts.map +1 -0
- package/out/tools/fetch/gleif.js +222 -0
- package/out/tools/fetch/gleif.js.map +1 -0
- package/out/tools/fetch/header.d.ts +43 -0
- package/out/tools/fetch/header.d.ts.map +1 -0
- package/out/tools/fetch/header.js +61 -0
- package/out/tools/fetch/header.js.map +1 -0
- package/out/tools/fetch/inspire-addresses.d.ts +254 -0
- package/out/tools/fetch/inspire-addresses.d.ts.map +1 -0
- package/out/tools/fetch/inspire-addresses.js +277 -0
- package/out/tools/fetch/inspire-addresses.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +1 -4
- package/out/tools/fetch/openaddresses.d.ts.map +1 -1
- package/out/tools/fetch/openaddresses.js +20 -99
- package/out/tools/fetch/openaddresses.js.map +1 -1
- package/out/tools/fetch/ourairports.d.ts +6 -33
- package/out/tools/fetch/ourairports.d.ts.map +1 -1
- package/out/tools/fetch/ourairports.js +14 -47
- 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 -7
- 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 +420 -0
- package/out/tools/fetch/wfs-harvest.d.ts.map +1 -0
- package/out/tools/fetch/wfs-harvest.js +525 -0
- package/out/tools/fetch/wfs-harvest.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +32 -100
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -1
- package/out/tools/fetch/wikidata-subvenue.js +27 -122
- 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 +99 -0
- package/out/tools/fetch.d.ts.map +1 -0
- package/out/tools/fetch.js +95 -0
- package/out/tools/fetch.js.map +1 -0
- package/out/tools/golden/expand.d.ts +28 -13
- package/out/tools/golden/expand.d.ts.map +1 -1
- package/out/tools/golden/expand.js +51 -37
- package/out/tools/golden/expand.js.map +1 -1
- package/out/tools/golden/promote.d.ts +13 -8
- package/out/tools/golden/promote.d.ts.map +1 -1
- package/out/tools/golden/promote.js +38 -30
- package/out/tools/golden/promote.js.map +1 -1
- package/out/tools/golden/relabel-street/directory.d.ts +25 -10
- package/out/tools/golden/relabel-street/directory.d.ts.map +1 -1
- package/out/tools/golden/relabel-street/directory.js +44 -32
- package/out/tools/golden/relabel-street/directory.js.map +1 -1
- package/out/tools/golden/relabel-street/row.d.ts +18 -69
- package/out/tools/golden/relabel-street/row.d.ts.map +1 -1
- package/out/tools/golden/relabel-street/row.js +19 -77
- package/out/tools/golden/relabel-street/row.js.map +1 -1
- package/out/tools/golden/{relabel-street/index.d.ts → relabel-street.d.ts} +1 -1
- package/out/tools/golden/relabel-street.d.ts.map +1 -0
- package/out/tools/golden/{relabel-street/index.js → relabel-street.js} +1 -1
- 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 +42 -46
- 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 +82 -0
- package/out/tools/lint/recipe-output/vocab.d.ts.map +1 -0
- package/out/tools/lint/{slice → recipe-output}/vocab.js +54 -69
- 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/{slice/index.js → recipe-output.js} +93 -96
- 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/{slice → overlay}/kryptonite.js +39 -29
- package/out/tools/overlay/kryptonite.js.map +1 -0
- package/out/tools/overlay/manifest.d.ts +143 -0
- package/out/tools/overlay/manifest.d.ts.map +1 -0
- package/out/tools/overlay/manifest.js +261 -0
- package/out/tools/overlay/manifest.js.map +1 -0
- package/out/tools/overlay/merge-source.d.ts +74 -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 +55 -0
- package/out/tools/overlay/translit.d.ts.map +1 -0
- package/out/tools/{slice → overlay}/translit.js +61 -49
- 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 +78 -127
- package/out/tools/postcode-triples.d.ts.map +1 -1
- package/out/tools/postcode-triples.js +200 -193
- package/out/tools/postcode-triples.js.map +1 -1
- package/out/tools/source-register/build.d.ts +147 -0
- package/out/tools/source-register/build.d.ts.map +1 -0
- package/out/tools/source-register/build.js +517 -0
- package/out/tools/source-register/build.js.map +1 -0
- package/out/tools/sub/venue/head-nouns.d.ts +9 -38
- package/out/tools/sub/venue/head-nouns.d.ts.map +1 -1
- package/out/tools/sub/venue/head-nouns.js +37 -74
- package/out/tools/sub/venue/head-nouns.js.map +1 -1
- package/out/tools/sub/venue/lexicon.d.ts +53 -84
- package/out/tools/sub/venue/lexicon.d.ts.map +1 -1
- package/out/tools/sub/venue/lexicon.js +42 -90
- package/out/tools/sub/venue/lexicon.js.map +1 -1
- package/out/tools/sub/venue/wikidata.d.ts +8 -6
- package/out/tools/sub/venue/wikidata.d.ts.map +1 -1
- package/out/tools/sub/venue/wikidata.js +12 -9
- package/out/tools/sub/venue/wikidata.js.map +1 -1
- package/out/tw/tools/fetch/gcis.d.ts +9 -3
- package/out/tw/tools/fetch/gcis.d.ts.map +1 -1
- package/out/tw/tools/fetch/gcis.js +19 -13
- package/out/tw/tools/fetch/gcis.js.map +1 -1
- package/out/types.d.ts +271 -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 +18 -36
- package/out/us/adapters/fcc-bdc/adapter.d.ts.map +1 -1
- package/out/us/adapters/fcc-bdc/adapter.js +25 -38
- package/out/us/adapters/fcc-bdc/adapter.js.map +1 -1
- package/out/us/adapters/state/hi-schools/adapter.d.ts +12 -11
- package/out/us/adapters/state/hi-schools/adapter.d.ts.map +1 -1
- package/out/us/adapters/state/hi-schools/adapter.js +26 -16
- package/out/us/adapters/state/hi-schools/adapter.js.map +1 -1
- package/out/us/adapters/state/hi-schools/workbook.d.ts +8 -3
- package/out/us/adapters/state/hi-schools/workbook.d.ts.map +1 -1
- package/out/us/adapters/state/hi-schools/workbook.js +3 -1
- package/out/us/adapters/state/hi-schools/workbook.js.map +1 -1
- package/out/us/adapters/state/ia-contractors/adapter.d.ts +13 -6
- package/out/us/adapters/state/ia-contractors/adapter.d.ts.map +1 -1
- package/out/us/adapters/state/ia-contractors/adapter.js +27 -14
- package/out/us/adapters/state/ia-contractors/adapter.js.map +1 -1
- package/out/us/adapters/state/ny-notaries/adapter.d.ts +7 -6
- package/out/us/adapters/state/ny-notaries/adapter.d.ts.map +1 -1
- package/out/us/adapters/state/ny-notaries/adapter.js +24 -22
- package/out/us/adapters/state/ny-notaries/adapter.js.map +1 -1
- package/out/us/adapters/state/tx-notaries/adapter.d.ts +8 -7
- package/out/us/adapters/state/tx-notaries/adapter.d.ts.map +1 -1
- package/out/us/adapters/state/tx-notaries/adapter.js +21 -14
- package/out/us/adapters/state/tx-notaries/adapter.js.map +1 -1
- package/out/us/adapters/tiger/adapter.d.ts +10 -34
- package/out/us/adapters/tiger/adapter.d.ts.map +1 -1
- package/out/us/adapters/tiger/adapter.js +18 -42
- package/out/us/adapters/tiger/adapter.js.map +1 -1
- package/out/us/adapters/tiger/street-decompose.d.ts +6 -13
- package/out/us/adapters/tiger/street-decompose.d.ts.map +1 -1
- package/out/us/adapters/tiger/street-decompose.js +7 -17
- package/out/us/adapters/tiger/street-decompose.js.map +1 -1
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts +26 -20
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.js +41 -29
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.js.map +1 -1
- package/out/us/adapters/usgov/imls-pls/adapter.d.ts +8 -7
- package/out/us/adapters/usgov/imls-pls/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/imls-pls/adapter.js +25 -18
- package/out/us/adapters/usgov/imls-pls/adapter.js.map +1 -1
- package/out/us/adapters/usgov/irs-bmf/adapter.d.ts +11 -10
- package/out/us/adapters/usgov/irs-bmf/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/irs-bmf/adapter.js +32 -22
- package/out/us/adapters/usgov/irs-bmf/adapter.js.map +1 -1
- package/out/us/adapters/usgov/nad/adapter.d.ts +11 -31
- package/out/us/adapters/usgov/nad/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/nad/adapter.js +57 -111
- package/out/us/adapters/usgov/nad/adapter.js.map +1 -1
- package/out/us/adapters/usgov/nppes/adapter.d.ts +12 -22
- package/out/us/adapters/usgov/nppes/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/nppes/adapter.js +62 -32
- package/out/us/adapters/usgov/nppes/adapter.js.map +1 -1
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts +16 -15
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js +38 -28
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js.map +1 -1
- package/out/us/fips-state.d.ts +19 -10
- package/out/us/fips-state.d.ts.map +1 -1
- package/out/us/fips-state.js +17 -8
- package/out/us/fips-state.js.map +1 -1
- package/out/{synthesizers → us/synthesizers}/intersection.d.ts +10 -8
- package/out/us/synthesizers/intersection.d.ts.map +1 -0
- package/out/{synthesizers → us/synthesizers}/intersection.js +46 -35
- package/out/us/synthesizers/intersection.js.map +1 -0
- package/out/{synthesizers → us/synthesizers}/street.d.ts +19 -12
- package/out/us/synthesizers/street.d.ts.map +1 -0
- package/out/{synthesizers → us/synthesizers}/street.js +45 -38
- package/out/us/synthesizers/street.js.map +1 -0
- package/out/us/tools/fetch/hrsa.d.ts +3 -3
- package/out/us/tools/fetch/hrsa.d.ts.map +1 -1
- package/out/us/tools/fetch/hrsa.js +6 -7
- package/out/us/tools/fetch/hrsa.js.map +1 -1
- package/out/us/tools/fetch/imls-pls.d.ts +5 -16
- package/out/us/tools/fetch/imls-pls.d.ts.map +1 -1
- package/out/us/tools/fetch/imls-pls.js +17 -34
- package/out/us/tools/fetch/imls-pls.js.map +1 -1
- package/out/us/tools/fetch/nad.d.ts +22 -10
- package/out/us/tools/fetch/nad.d.ts.map +1 -1
- package/out/us/tools/fetch/nad.js +30 -25
- package/out/us/tools/fetch/nad.js.map +1 -1
- package/out/us/tools/fetch/nppes.d.ts +6 -16
- package/out/us/tools/fetch/nppes.d.ts.map +1 -1
- package/out/us/tools/fetch/nppes.js +24 -36
- package/out/us/tools/fetch/nppes.js.map +1 -1
- package/out/us/tools/fetch/state/hi-schools.d.ts +9 -5
- package/out/us/tools/fetch/state/hi-schools.d.ts.map +1 -1
- package/out/us/tools/fetch/state/hi-schools.js +16 -14
- package/out/us/tools/fetch/state/hi-schools.js.map +1 -1
- package/out/us/tools/fetch/state/sources.d.ts +8 -7
- package/out/us/tools/fetch/state/sources.d.ts.map +1 -1
- package/out/us/tools/fetch/state/sources.js +8 -9
- package/out/us/tools/fetch/state/sources.js.map +1 -1
- package/out/us/tools/fetch/tiger-full.d.ts +1 -14
- package/out/us/tools/fetch/tiger-full.d.ts.map +1 -1
- package/out/us/tools/fetch/tiger-full.js +16 -55
- package/out/us/tools/fetch/tiger-full.js.map +1 -1
- package/out/utils/align.d.ts +26 -19
- package/out/utils/align.d.ts.map +1 -1
- package/out/utils/align.js +32 -47
- 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 +21 -31
- package/out/utils/golden.d.ts.map +1 -1
- package/out/utils/golden.js +30 -46
- package/out/utils/golden.js.map +1 -1
- package/out/utils/license.d.ts +159 -22
- 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 +162 -69
- package/out/utils/split.js.map +1 -1
- package/out/utils/tokenize.d.ts +15 -44
- 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 +77 -56
- package/out/utils/wof-json.js.map +1 -1
- package/out/{utils/index.js → utils.d.ts} +1 -2
- package/out/utils.d.ts.map +1 -0
- package/out/{utils/index.d.ts → utils.js} +1 -2
- package/out/utils.js.map +1 -0
- package/out/ve/recipes/reviewed-postcode-tail.d.ts +25 -7
- package/out/ve/recipes/reviewed-postcode-tail.d.ts.map +1 -1
- package/out/ve/recipes/reviewed-postcode-tail.js +33 -12
- package/out/ve/recipes/reviewed-postcode-tail.js.map +1 -1
- package/package.json +45 -488
- package/lib/adapters/index.ts +0 -160
- package/lib/adapters/synth-po-box/adapter.ts +0 -204
- package/lib/adapters/utils/index.ts +0 -307
- package/lib/recipes/bare/postcode/index.ts +0 -327
- package/lib/recipes/sub/venue/index.ts +0 -997
- package/lib/synthesizers/locale.ts +0 -261
- package/lib/test-kit/index.ts +0 -100
- package/lib/tools/align-slice.ts +0 -68
- package/lib/tools/fetch/index.ts +0 -174
- package/lib/tools/gb-title-case.ts +0 -69
- package/lib/tools/index.ts +0 -28
- package/lib/tools/lint/slice/vocab.ts +0 -376
- package/lib/tools/overlay-manifest.ts +0 -215
- package/lib/tools/slice/translit.ts +0 -218
- package/lib/tools/sub/venue/harvest.ts +0 -234
- package/lib/tools/sub/venue/surfaces.ts +0 -95
- package/lib/tools/sub/venue/table.ts +0 -281
- package/lib/utils/parquet.ts +0 -582
- package/out/adapters/index.d.ts +0 -51
- package/out/adapters/index.d.ts.map +0 -1
- package/out/adapters/index.js +0 -97
- package/out/adapters/index.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.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/fr/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/fr/adapters/ban/street-decompose.js.map +0 -1
- package/out/no/recipes/street/index.d.ts +0 -18
- package/out/no/recipes/street/index.d.ts.map +0 -1
- package/out/no/recipes/street/index.js.map +0 -1
- package/out/recipes/bare/postcode/index.d.ts +0 -62
- package/out/recipes/bare/postcode/index.d.ts.map +0 -1
- package/out/recipes/bare/postcode/index.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.map +0 -1
- package/out/recipes/po/box/index.d.ts +0 -17
- package/out/recipes/po/box/index.d.ts.map +0 -1
- package/out/recipes/po/box/index.js.map +0 -1
- package/out/recipes/sub/venue/index.d.ts +0 -270
- package/out/recipes/sub/venue/index.d.ts.map +0 -1
- package/out/recipes/sub/venue/index.js +0 -728
- package/out/recipes/sub/venue/index.js.map +0 -1
- package/out/synthesizers/intersection.d.ts.map +0 -1
- package/out/synthesizers/intersection.js.map +0 -1
- package/out/synthesizers/locale.d.ts +0 -116
- package/out/synthesizers/locale.d.ts.map +0 -1
- package/out/synthesizers/locale.js +0 -150
- package/out/synthesizers/locale.js.map +0 -1
- package/out/synthesizers/street.d.ts.map +0 -1
- package/out/synthesizers/street.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/download/index.d.ts.map +0 -1
- package/out/tools/fetch/download/index.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/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/relabel-street/index.d.ts.map +0 -1
- package/out/tools/golden/relabel-street/index.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/index.d.ts +0 -93
- package/out/tools/lint/slice/index.d.ts.map +0 -1
- package/out/tools/lint/slice/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.map +0 -1
- package/out/tools/overlay-manifest.d.ts +0 -89
- package/out/tools/overlay-manifest.d.ts.map +0 -1
- package/out/tools/overlay-manifest.js +0 -131
- 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.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.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/promotions.d.ts +0 -94
- package/out/tools/sub/venue/promotions.d.ts.map +0 -1
- package/out/tools/sub/venue/promotions.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/utils/index.d.ts.map +0 -1
- package/out/utils/index.js.map +0 -1
- package/out/utils/parquet.d.ts +0 -178
- package/out/utils/parquet.d.ts.map +0 -1
- package/out/utils/parquet.js +0 -371
- package/out/utils/parquet.js.map +0 -1
- package/out/utils/slice-stats.d.ts +0 -52
- package/out/utils/slice-stats.d.ts.map +0 -1
- package/out/utils/slice-stats.js +0 -58
- package/out/utils/slice-stats.js.map +0 -1
- /package/lib/tools/fetch/{download/index.ts → download.ts} +0 -0
- /package/lib/tools/golden/{relabel-street/index.ts → relabel-street.ts} +0 -0
|
@@ -3,66 +3,60 @@
|
|
|
3
3
|
* @license AGPL-3.0
|
|
4
4
|
* @author Teffen Ellis, et al.
|
|
5
5
|
*
|
|
6
|
-
*
|
|
7
|
-
* theme has no rows for Pakistan, Bangladesh or Vietnam (the three parquets are 532-byte headers), and the Latin
|
|
8
|
-
* model has never seen their formats: the Islamabad sector line, the Dhaka trailing postcode, the `Đường`-led street.
|
|
6
|
+
* `osm`: OpenStreetMap address adapter for the countries no permissive source covers.
|
|
9
7
|
*
|
|
10
|
-
*
|
|
11
|
-
*
|
|
12
|
-
*
|
|
13
|
-
*
|
|
14
|
-
* ⚠ ODbL. Every row carries `license: "ODbL-1.0"`, which `SHARE_ALIKE_PATTERN` matches: a proprietary-weights build
|
|
15
|
-
* passes `--exclude-share-alike` and drops these rows at ingest, so they reach the open weights only. That is the
|
|
16
|
-
* whole licensing contract of this adapter, and the reason `defaultLicense` is not an option.
|
|
17
|
-
*
|
|
18
|
-
* The mapping keeps to what a person types on the envelope. Mappers put free text in `addr:housenumber` (`House 34,
|
|
19
|
-
* Road 4, Sector 9`, `Near Askari Towers 2`) and in `addr:street`; a house number is kept only in a designator shape,
|
|
20
|
-
* and a street with a comma or more than eight words is skipped as a line rather than a name. `addr:city` in
|
|
21
|
-
* Bangladesh often carries the neighborhood too (`Mirpur 10, Dhaka`): the last comma-separated part is the locality
|
|
22
|
-
* and the head becomes the dependent locality when no `addr:suburb` names one. `addr:district` is NOT mapped on its
|
|
23
|
-
* own: for Vietnam it is the quận below the city, which the country template renders only when no city is present,
|
|
24
|
-
* so a mapped district with a city would be a component with no span to align to and the row would quarantine.
|
|
25
|
-
*
|
|
26
|
-
* | JSONL field | ComponentTag |
|
|
27
|
-
* | ------------------------------------------ | --------------------------------------------------------- |
|
|
28
|
-
* | `number` | `house_number` when designator-shaped (`12`, `14/E`, `B-77`) |
|
|
29
|
-
* | `street` | `street` (keyword included; affix-relabel splits it) |
|
|
30
|
-
* | `unit` | `unit` |
|
|
31
|
-
* | `postcode` | `postcode` when 4–6 digits |
|
|
32
|
-
* | `city` (tail after the last comma) | `locality` |
|
|
33
|
-
* | `suburb` ?? `subdistrict` ?? `district` ?? `place` ?? city head | `dependent_locality` |
|
|
34
|
-
* | `province` | `region`, unless it repeats the locality |
|
|
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.
|
|
35
11
|
*/
|
|
36
|
-
import { formatAddressRow } from "@mailwoman/codex/address
|
|
12
|
+
import { formatAddressRow } from "@mailwoman/codex/address/format";
|
|
37
13
|
import { tryParsingJSON } from "@mailwoman/core/json";
|
|
14
|
+
import { extractDelimited } from "@mailwoman/core/scripting/arguments";
|
|
38
15
|
import { stripCombiningMarks } from "@mailwoman/normalize/fold";
|
|
39
16
|
import { TextSpliterator } from "spliterator";
|
|
40
|
-
import { stableSourceID } from "#adapters/
|
|
17
|
+
import { stableSourceID } from "#adapters/source-id";
|
|
18
|
+
import { SourceRegister } from "#registers";
|
|
19
|
+
import { AddressRole, countDropped, SurfaceOrigin, } from "#types";
|
|
41
20
|
/**
|
|
42
21
|
* Registry id for this adapter, stamped into every row it emits.
|
|
43
22
|
*/
|
|
44
23
|
export const OSM_ADAPTER_ID = "osm";
|
|
45
24
|
/**
|
|
46
|
-
* OpenStreetMap's license.
|
|
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.
|
|
47
29
|
*/
|
|
48
30
|
export const OSM_LICENSE = "ODbL-1.0";
|
|
49
31
|
/**
|
|
50
|
-
*
|
|
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.
|
|
39
|
+
* A model card holds it when OSM-derived rows reach the checkpoint.
|
|
40
|
+
* The effective training manifest records those rows.
|
|
51
41
|
*/
|
|
42
|
+
export const OSM_ATTRIBUTION = "© OpenStreetMap contributors. Data licensed under the Open Database License (ODbL) 1.0 " +
|
|
43
|
+
`(${OSM_LICENSE_URL}); see https://www.openstreetmap.org/copyright.`;
|
|
52
44
|
const MAX_STREET_WORDS = 8;
|
|
53
45
|
/**
|
|
54
|
-
* Whether `addr:housenumber` holds a designator
|
|
55
|
-
*
|
|
56
|
-
* (`B-77`, `L58`, `R 948
|
|
57
|
-
*
|
|
46
|
+
* Whether `addr:housenumber` holds a street designator — digits with an optional letter,
|
|
47
|
+
* fraction or dash suffix (`12`, `188a`, `14/E`, `1/1146`, `167-c`) or a one-
|
|
48
|
+
* or two-letter block prefix (`B-77`, `L58`, `R 948`) — rather than free text such
|
|
49
|
+
* as `House 34, Road 4, Sector 9`, `Plot #27` or a name.
|
|
58
50
|
*/
|
|
59
51
|
export function housenumberIsDesignator(value) {
|
|
60
52
|
const trimmed = value.trim();
|
|
61
53
|
return /^\d+[A-Za-z]?(?:[/-]\d*[A-Za-z]?)?$/u.test(trimmed) || /^[A-Za-z]{1,2}[-\s]?\d+[A-Za-z]?$/u.test(trimmed);
|
|
62
54
|
}
|
|
63
55
|
/**
|
|
64
|
-
* Whether `addr:street`
|
|
65
|
-
*
|
|
56
|
+
* Whether `addr:street` matches the street-name shape.
|
|
57
|
+
*
|
|
58
|
+
* The value has no comma and contains at most {@link MAX_STREET_WORDS} words.
|
|
59
|
+
* Direction phrases such as `Near Cozy Water Park`, `Opposite Askari Towers` or `Behind …` return false.
|
|
66
60
|
*/
|
|
67
61
|
export function isStreetName(value) {
|
|
68
62
|
const trimmed = value.trim();
|
|
@@ -72,21 +66,16 @@ export function isStreetName(value) {
|
|
|
72
66
|
!/^(?:near|opp(?:osite)?|behind|beside|next to|adjacent)\b/iu.test(trimmed));
|
|
73
67
|
}
|
|
74
68
|
/**
|
|
75
|
-
* Split an `addr:city`
|
|
76
|
-
* `Mirpur 10`)
|
|
69
|
+
* Split an `addr:city` carrying a neighborhood ahead of the city (`Mirpur 10, Dhaka` →
|
|
70
|
+
* locality `Dhaka`, head `Mirpur 10`); a value without a comma is only the locality.
|
|
77
71
|
*/
|
|
78
72
|
export function splitCityValue(value) {
|
|
79
|
-
const parts = value
|
|
80
|
-
|
|
81
|
-
.map((part) => part.trim())
|
|
82
|
-
.filter((part) => part.length > 0);
|
|
83
|
-
if (parts.length < 2)
|
|
73
|
+
const parts = extractDelimited(value);
|
|
74
|
+
if (parts.length < 2) {
|
|
84
75
|
return { locality: value.trim(), head: null };
|
|
76
|
+
}
|
|
85
77
|
return { locality: parts.at(-1), head: parts.slice(0, -1).join(", ") };
|
|
86
78
|
}
|
|
87
|
-
/**
|
|
88
|
-
* Values mappers write for "none".
|
|
89
|
-
*/
|
|
90
79
|
const PLACEHOLDERS = new Set(["n/a", "na", "none", "-", "nil"]);
|
|
91
80
|
function clean(value) {
|
|
92
81
|
const trimmed = value?.trim() ?? "";
|
|
@@ -100,17 +89,41 @@ function parseLine(line) {
|
|
|
100
89
|
return parsed && typeof parsed === "object" ? parsed : null;
|
|
101
90
|
}
|
|
102
91
|
/**
|
|
103
|
-
*
|
|
92
|
+
* Maps one jsonl row onto the components the corpus asserts, or returns null when the row is refused.
|
|
93
|
+
*
|
|
94
|
+
* A row with a street-shaped `addr:street` is a street address.
|
|
95
|
+
* A row with no `addr:street` at all is admitted as a streetless premise when its house
|
|
96
|
+
* number is designator-shaped and a tag that maps to `locality` or `dependent_locality`
|
|
97
|
+
* (`addr:city`, `addr:place`, `addr:suburb`, `addr:subdistrict`, `addr:district`)
|
|
98
|
+
* holds the identity the street would have held.
|
|
99
|
+
*
|
|
100
|
+
* That is OSM's documented scheme for addresses numbered within a place rather than
|
|
101
|
+
* along a street, and it is the `streetless-premise-identity` shape.
|
|
102
|
+
* A row whose `addr:street` holds a line rather than a name stays refused:
|
|
103
|
+
* the mapper supplied a street, and the value is a line.
|
|
104
|
+
*
|
|
105
|
+
* Each refusal and each discarded component increments its reason in `dropped`.
|
|
104
106
|
*/
|
|
105
|
-
export function componentsForOSMRow(row) {
|
|
107
|
+
export function componentsForOSMRow(row, dropped) {
|
|
108
|
+
const tally = dropped ?? {};
|
|
106
109
|
const street = clean(row.street);
|
|
107
|
-
if (!street || !isStreetName(street))
|
|
108
|
-
return null;
|
|
109
|
-
const components = { street };
|
|
110
110
|
const number = clean(row.number);
|
|
111
|
-
|
|
111
|
+
const designator = number !== null && housenumberIsDesignator(number);
|
|
112
|
+
if (street && !isStreetName(street)) {
|
|
113
|
+
countDropped(tally, "row:street-not-a-name");
|
|
114
|
+
return null;
|
|
115
|
+
}
|
|
116
|
+
if (!street && !designator) {
|
|
117
|
+
countDropped(tally, number ? "row:streetless-house-number-not-designator" : "row:streetless-no-house-number");
|
|
118
|
+
return null;
|
|
119
|
+
}
|
|
120
|
+
const components = street ? { street } : {};
|
|
121
|
+
if (designator) {
|
|
112
122
|
components.house_number = number;
|
|
113
123
|
}
|
|
124
|
+
else if (number) {
|
|
125
|
+
countDropped(tally, "component:house_number:not-designator");
|
|
126
|
+
}
|
|
114
127
|
const unit = clean(row.unit);
|
|
115
128
|
if (unit) {
|
|
116
129
|
components.unit = unit;
|
|
@@ -119,40 +132,52 @@ export function componentsForOSMRow(row) {
|
|
|
119
132
|
if (postcode && /^\d{4,6}$/u.test(postcode)) {
|
|
120
133
|
components.postcode = postcode;
|
|
121
134
|
}
|
|
135
|
+
else if (postcode) {
|
|
136
|
+
countDropped(tally, "component:postcode:not-4-to-6-digits");
|
|
137
|
+
}
|
|
122
138
|
const city = clean(row.city);
|
|
123
139
|
const split = city ? splitCityValue(city) : null;
|
|
124
140
|
if (split) {
|
|
125
141
|
components.locality = split.locality;
|
|
126
142
|
}
|
|
127
|
-
//
|
|
143
|
+
// Dependent-locality candidates in priority order (suburb, subdistrict, district, place, city head);
|
|
144
|
+
// `district` never becomes `region`, because Vietnam's country template
|
|
145
|
+
// renders it only when no city is present.
|
|
128
146
|
const dependent = [row.suburb, row.subdistrict, row.district, row.place, split?.head]
|
|
129
|
-
.map((value) => clean(value
|
|
147
|
+
.map((value) => clean(value))
|
|
130
148
|
.find((value) => value !== null &&
|
|
131
149
|
!value.includes(",") &&
|
|
132
|
-
!sameName(value, street) &&
|
|
150
|
+
(street === null || !sameName(value, street)) &&
|
|
133
151
|
(split === null || !sameName(value, split.locality)));
|
|
134
152
|
if (dependent) {
|
|
135
153
|
components.dependent_locality = dependent;
|
|
136
154
|
}
|
|
137
155
|
const province = clean(row.province);
|
|
138
|
-
if (province && (split
|
|
156
|
+
if (province && (!split || !sameName(province, split.locality))) {
|
|
139
157
|
components.region = province;
|
|
140
158
|
}
|
|
141
|
-
// A
|
|
142
|
-
//
|
|
143
|
-
|
|
144
|
-
|
|
159
|
+
// A streetless premise is a house number within a place that has a name, so it needs
|
|
160
|
+
// a locality or a dependent locality, from any of the tags that map to them.
|
|
161
|
+
if (!street && !components.locality && !components.dependent_locality) {
|
|
162
|
+
countDropped(tally, "row:streetless-no-locality");
|
|
163
|
+
return null;
|
|
164
|
+
}
|
|
165
|
+
// An address row needs another component alongside the street or the streetless house number.
|
|
166
|
+
// Coarse adapters already teach bare names.
|
|
167
|
+
if (Object.keys(components).length === 1) {
|
|
168
|
+
countDropped(tally, street ? "row:street-only" : "row:house-number-only");
|
|
145
169
|
return null;
|
|
170
|
+
}
|
|
146
171
|
return components;
|
|
147
172
|
}
|
|
148
173
|
/**
|
|
149
|
-
*
|
|
150
|
-
*
|
|
174
|
+
* Vietnamese admin-generic prefixes stripped before name comparison, so a province that
|
|
175
|
+
* repeats the city with a prefix (`Thành phố Hà Nội`) is read as the repeat it is.
|
|
151
176
|
*/
|
|
152
177
|
const NAME_PREFIXES = /^(?:thanh pho|tinh|tp\.?|quan|phuong|huyen|thi xa)\s+/u;
|
|
153
178
|
/**
|
|
154
|
-
* Whether two place names are the same name: case, whitespace, diacritics and a leading
|
|
155
|
-
* Ninh` = `Bac Ninh`; `Hà Nội` = `Thành phố Hà Nội`).
|
|
179
|
+
* Whether two place names are the same name: case, whitespace, diacritics and a leading
|
|
180
|
+
* admin generic folded (`Bắc Ninh` = `Bac Ninh`; `Hà Nội` = `Thành phố Hà Nội`).
|
|
156
181
|
*/
|
|
157
182
|
export function sameName(a, b) {
|
|
158
183
|
const fold = (value) => stripCombiningMarks(value)
|
|
@@ -168,6 +193,9 @@ export function createOSMAdapter() {
|
|
|
168
193
|
return {
|
|
169
194
|
id: OSM_ADAPTER_ID,
|
|
170
195
|
defaultLicense: OSM_LICENSE,
|
|
196
|
+
addressRole: AddressRole.Premise,
|
|
197
|
+
register: SourceRegister.OpenStreetMap,
|
|
198
|
+
surface: SurfaceOrigin.Rendered,
|
|
171
199
|
description: "OpenStreetMap addresses (ODbL, share-alike): per-country JSONL from a Geofabrik extract, for the countries no permissive source covers.",
|
|
172
200
|
async *rows(opts) {
|
|
173
201
|
if (!opts.country) {
|
|
@@ -181,15 +209,37 @@ export function createOSMAdapter() {
|
|
|
181
209
|
if (opts.limit !== undefined && emitted >= opts.limit)
|
|
182
210
|
break;
|
|
183
211
|
const row = parseLine(line);
|
|
184
|
-
if (!row)
|
|
212
|
+
if (!row) {
|
|
213
|
+
if (line.trim() && !line.trim().startsWith("#")) {
|
|
214
|
+
countDropped(opts, "row:unparseable-line");
|
|
215
|
+
}
|
|
216
|
+
continue;
|
|
217
|
+
}
|
|
218
|
+
// A Geofabrik extract's polygon extends past the border, so its records
|
|
219
|
+
// include addresses in the neighboring country.
|
|
220
|
+
// A record whose own `addr:country` names another country is refused.
|
|
221
|
+
// A record without the tag is kept and counted, so the size of the remaining
|
|
222
|
+
// uncertainty is in the manifest rather than assumed to be zero.
|
|
223
|
+
const tagged = clean(row.country)?.toUpperCase();
|
|
224
|
+
if (tagged && tagged !== country) {
|
|
225
|
+
countDropped(opts, "row:country-tag-mismatch");
|
|
185
226
|
continue;
|
|
186
|
-
|
|
227
|
+
}
|
|
228
|
+
if (!tagged) {
|
|
229
|
+
countDropped(opts, "kept:country-untagged");
|
|
230
|
+
}
|
|
231
|
+
const components = componentsForOSMRow(row, opts);
|
|
187
232
|
if (!components)
|
|
188
233
|
continue;
|
|
189
234
|
const rendered = formatAddressRow(components, country, { singleLine: true });
|
|
190
|
-
if (!rendered)
|
|
235
|
+
if (!rendered) {
|
|
236
|
+
countDropped(opts, "row:render-failed");
|
|
191
237
|
continue;
|
|
238
|
+
}
|
|
192
239
|
const { raw, components: aligned } = rendered;
|
|
240
|
+
for (const tag of rendered.unplaced) {
|
|
241
|
+
countDropped(opts, `component:${tag}:not-rendered`);
|
|
242
|
+
}
|
|
193
243
|
yield {
|
|
194
244
|
raw,
|
|
195
245
|
components: aligned,
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../lib/adapters/osm/adapter.ts"],"names":[],"mappings":"AAAA
|
|
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;;;;;;GAMG;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,KAAgC;IAC9C,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,CAAC,CAAC;SAC5B,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,CAAC,KAAK,IAAI,CAAC,QAAQ,CAAC,QAAQ,EAAE,KAAK,CAAC,QAAQ,CAAC,CAAC,EAAE,CAAC;QACjE,UAAU,CAAC,MAAM,GAAG,QAAQ,CAAA;IAC7B,CAAC;IAED,qFAAqF;IACrF,6EAA6E;IAC7E,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"}
|
|
@@ -3,51 +3,25 @@
|
|
|
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";
|
|
43
19
|
/**
|
|
44
|
-
* Whether an Overture `unit` value is a secondary-unit designator
|
|
45
|
-
* (
|
|
46
|
-
*
|
|
47
|
-
*
|
|
48
|
-
*
|
|
49
|
-
* `#NNN`-unit defect the corpus exists to cure. Such a value is dropped here; a register recipe that wants the building
|
|
50
|
-
* name as a `venue` reads the JSONL itself.
|
|
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.
|
|
51
25
|
*/
|
|
52
26
|
export declare function unitFieldIsDesignator(value: string): boolean;
|
|
53
27
|
export declare function createOvertureAdapter(): CorpusAdapter;
|
|
@@ -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"}
|
|
@@ -3,54 +3,47 @@
|
|
|
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 { formatAddressRow } from "@mailwoman/codex/address
|
|
9
|
+
import { formatAddressRow } from "@mailwoman/codex/address/format";
|
|
10
|
+
import { COUNTRY_SURFACE_FORMS } from "@mailwoman/codex/country";
|
|
33
11
|
import { tryParsingJSON } from "@mailwoman/core/json";
|
|
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
|
+
}
|
|
46
41
|
/**
|
|
47
|
-
* Whether an Overture `unit` value is a secondary-unit designator
|
|
48
|
-
* (
|
|
49
|
-
*
|
|
50
|
-
*
|
|
51
|
-
*
|
|
52
|
-
* `#NNN`-unit defect the corpus exists to cure. Such a value is dropped here; a register recipe that wants the building
|
|
53
|
-
* name as a `venue` reads the JSONL itself.
|
|
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.
|
|
54
47
|
*/
|
|
55
48
|
export function unitFieldIsDesignator(value) {
|
|
56
49
|
const trimmed = value.trim();
|
|
@@ -69,15 +62,20 @@ export function createOvertureAdapter() {
|
|
|
69
62
|
return {
|
|
70
63
|
id: OVERTURE_ADAPTER_ID,
|
|
71
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,
|
|
72
70
|
description: "Overture Maps Addresses (global): per-country JSONL of street/number/postcode/locality.",
|
|
73
71
|
async *rows(opts) {
|
|
74
72
|
if (!opts.country) {
|
|
75
73
|
throw new Error("overture adapter: --country is required (the Overture JSONL is per-country and rows omit a country field)");
|
|
76
74
|
}
|
|
77
75
|
const country = opts.country;
|
|
78
|
-
|
|
79
|
-
|
|
80
|
-
// 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`.
|
|
81
79
|
const lines = TextSpliterator.fromAsync(opts.inputPath);
|
|
82
80
|
let emitted = 0;
|
|
83
81
|
for await (const line of lines) {
|
|
@@ -93,7 +91,7 @@ export function createOvertureAdapter() {
|
|
|
93
91
|
const unit = r.unit?.trim() ?? "";
|
|
94
92
|
const postcode = r.postcode?.trim() ?? "";
|
|
95
93
|
const locality = r.locality?.trim() ?? "";
|
|
96
|
-
// Only useful with a street + (postcode
|
|
94
|
+
// Only useful with a street + (postcode or locality); point-only rows quarantine anyway.
|
|
97
95
|
if (!street)
|
|
98
96
|
continue;
|
|
99
97
|
if (!postcode && !locality)
|
|
@@ -113,6 +111,11 @@ export function createOvertureAdapter() {
|
|
|
113
111
|
if (locality) {
|
|
114
112
|
components.locality = locality;
|
|
115
113
|
}
|
|
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
|
+
}
|
|
116
119
|
const rendered = formatAddressRow(components, country, { singleLine: true });
|
|
117
120
|
if (!rendered)
|
|
118
121
|
continue;
|
|
@@ -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 +1,66 @@
|
|
|
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
|
+
*
|
|
44
|
+
* @defaultValue `0.15`
|
|
45
|
+
*/
|
|
46
|
+
pmbRatio?: number;
|
|
47
|
+
/**
|
|
48
|
+
* Deterministic seed for reproducible synthesis.
|
|
49
|
+
*
|
|
50
|
+
* @defaultValue `Date.now()`
|
|
51
|
+
*/
|
|
52
|
+
seed?: number;
|
|
53
|
+
/**
|
|
54
|
+
* Probability (0..1) per input tuple of additionally emitting one self-contained US
|
|
55
|
+
* military/diplomatic PO-box row, so military volume scales with the input stream.
|
|
56
|
+
*
|
|
57
|
+
* @defaultValue `0`
|
|
58
|
+
*/
|
|
59
|
+
militaryRatio?: number;
|
|
60
|
+
}
|
|
61
|
+
export declare function createPoBoxAdapter(opts?: PoBoxAdapterOptions): CorpusAdapter;
|
|
62
|
+
/**
|
|
63
|
+
* The configured adapter instance registered with the corpus builder.
|
|
64
|
+
*/
|
|
65
|
+
export declare const poBoxAdapter: CorpusAdapter;
|
|
66
|
+
//# 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;;;;;OAKG;IACH,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB;;;;OAIG;IACH,IAAI,CAAC,EAAE,MAAM,CAAA;IACb;;;;;OAKG;IACH,aAAa,CAAC,EAAE,MAAM,CAAA;CACtB;AAED,wBAAgB,kBAAkB,CAAC,IAAI,GAAE,mBAAwB,GAAG,aAAa,CA4HhF;AAED;;GAEG;AACH,eAAO,MAAM,YAAY,eAAuB,CAAA"}
|