@mailwoman/corpus 10.0.0 → 10.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +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 +785 -0
- package/lib/adapters/dedup-key.ts +40 -0
- package/lib/adapters/errors.ts +21 -0
- package/lib/adapters/geonames/adapter.ts +42 -52
- package/lib/adapters/geonames/postal/adapter.ts +31 -37
- package/lib/adapters/gleif/adapter.ts +828 -0
- package/lib/adapters/libpostal-dictionary.ts +39 -0
- package/lib/adapters/openaddresses/adapter.ts +51 -55
- package/lib/adapters/osm/adapter.ts +148 -70
- package/lib/adapters/overture/adapter.ts +52 -43
- package/lib/adapters/po-box/adapter.ts +202 -0
- package/lib/adapters/registry.ts +79 -0
- package/lib/adapters/sha256-stream.ts +49 -0
- package/lib/adapters/source-id.ts +49 -0
- package/lib/adapters/street-line.ts +135 -0
- package/lib/adapters/wof/admin/json/adapter.ts +48 -33
- package/lib/adapters/wof/json-rows.ts +56 -26
- package/lib/adapters/wof/postalcode-json/adapter.ts +57 -59
- package/lib/adapters.ts +230 -0
- package/lib/au/adapters/gnaf/adapter.ts +35 -43
- 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 +670 -0
- package/lib/be/adapters/wallonie/adapter.ts +537 -0
- package/lib/be/tools/fetch/brussels.ts +239 -0
- package/lib/be/tools/fetch/wallonie.ts +274 -0
- package/lib/build/adapters.ts +110 -0
- package/lib/build/align.ts +364 -0
- package/lib/build/checkpoint.ts +131 -0
- package/lib/build/eligibility.ts +96 -0
- package/lib/build/heap.ts +53 -0
- package/lib/build/inputs.ts +81 -0
- package/lib/build/rows.ts +21 -0
- package/lib/build/types.ts +232 -0
- package/lib/build.ts +127 -315
- package/lib/cn/recipes/organizational-units.ts +20 -41
- package/lib/cz/adapters/cuzk/adapter.ts +317 -0
- package/lib/cz/recipes/pcfirst-preposition.ts +40 -27
- package/lib/cz/tools/fetch/cuzk.ts +699 -0
- package/lib/de/recipes/locale.ts +68 -58
- package/lib/directory.ts +31 -0
- package/lib/dk/adapters/inspire/adapter.ts +345 -0
- package/lib/dk/tools/fetch/inspire.ts +321 -0
- package/lib/ee/adapters/ads/adapter.ts +246 -0
- package/lib/ee/tools/fetch/ads.ts +270 -0
- package/lib/env.ts +6 -2
- package/lib/es/adapters/bizkaia/adapter.ts +388 -0
- package/lib/es/adapters/catastro/adapter.ts +343 -0
- package/lib/es/adapters/gipuzkoa/adapter.ts +263 -0
- package/lib/es/adapters/navarra/adapter.ts +289 -0
- package/lib/es/cadastre.ts +194 -0
- package/lib/es/tools/fetch/bizkaia.ts +748 -0
- package/lib/es/tools/fetch/catastro.ts +754 -0
- package/lib/es/tools/fetch/gipuzkoa.ts +336 -0
- package/lib/es/tools/fetch/navarra.ts +488 -0
- package/lib/fi/adapters/ryhti/adapter.ts +323 -0
- package/lib/fi/tools/fetch/ryhti.ts +476 -0
- package/lib/fingerprints.ts +154 -0
- package/lib/fr/adapters/annuaire-education/adapter.ts +598 -0
- package/lib/fr/adapters/ban/adapter.ts +87 -59
- package/lib/fr/adapters/finess/adapter.ts +618 -0
- package/lib/fr/adapters/finess/postal-lines.ts +157 -0
- package/lib/fr/adapters/finess/voie-type.ts +200 -0
- package/lib/fr/insee-country.ts +62 -0
- package/lib/fr/recipes/admin-split.ts +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 +109 -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 +306 -0
- package/lib/fr/tools/fetch/ban.ts +28 -19
- package/lib/fr/tools/fetch/finess.ts +352 -0
- package/lib/gauntlet-inputs.ts +92 -0
- package/lib/index.ts +9 -3
- package/lib/inspire/address.ts +457 -0
- package/lib/inspire/archive.ts +44 -0
- package/lib/inspire/errors.ts +71 -0
- package/lib/inspire/stream.ts +262 -0
- package/lib/international/recipes/locale.ts +134 -176
- package/lib/it/adapters/anac/adapter.ts +522 -0
- package/lib/it/tools/fetch/anac.ts +394 -0
- package/lib/jp/adapters/wof-admin/adapter.ts +27 -17
- package/lib/jp/tools/fetch/houjin.ts +16 -18
- 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 +33 -26
- package/lib/kr/tools/fetch/juso.ts +19 -21
- package/lib/kr/tools/fetch/localdata.ts +28 -29
- package/lib/lu/adapters/bd-adresses/adapter.ts +240 -0
- package/lib/lu/tools/fetch/bd-adresses.ts +351 -0
- package/lib/lv/adapters/varis/adapter.ts +499 -0
- package/lib/lv/tools/fetch/varis.ts +214 -0
- package/lib/nl/adapters/kadaster/adapter.ts +386 -0
- package/lib/nl/recipes/postcode.ts +46 -24
- package/lib/nl/tools/fetch/kadaster.ts +298 -0
- package/lib/no/adapters/matrikkelen/adapter.ts +187 -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 +519 -0
- package/lib/parquet/duckdb.ts +144 -0
- package/lib/parquet/readers.ts +86 -0
- package/lib/parquet/schema.ts +214 -0
- package/lib/parquet/shuffle.ts +59 -0
- package/lib/parquet/span-sql.ts +54 -0
- package/lib/parquet/streams.ts +113 -0
- package/lib/parquet/writers.ts +451 -0
- package/lib/pl/adapters/emuia/adapter.ts +202 -0
- package/lib/pl/tools/fetch/emuia.ts +360 -0
- package/lib/recipes/anchor-absorption.ts +30 -19
- package/lib/recipes/bare/country.ts +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 +36 -19
- package/lib/recipes/country-balanced.ts +66 -86
- package/lib/recipes/house-venue.ts +31 -13
- package/lib/recipes/intersection.ts +82 -60
- 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 +28 -16
- package/lib/recipes/po/box/cedex/sources.ts +3 -3
- 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 +252 -153
- package/lib/recipes/sources.ts +399 -0
- package/lib/recipes/street/affix.ts +54 -154
- package/lib/recipes/street/bare.ts +28 -15
- package/lib/recipes/street.ts +32 -8
- package/lib/recipes/sub/venue/context.ts +30 -23
- package/lib/recipes/sub/venue/render.ts +170 -0
- package/lib/recipes/sub/venue/sources.ts +68 -219
- package/lib/recipes/sub/venue.ts +801 -0
- package/lib/recipes/trailing-region.ts +69 -85
- package/lib/recipes/unit/sources.ts +44 -0
- package/lib/recipes/unit.ts +101 -89
- package/lib/{recipes/index.ts → recipes.ts} +13 -11
- package/lib/registers.ts +278 -0
- package/lib/ro/adapters/retea-scolara/adapter.ts +264 -0
- package/lib/ro/tools/fetch/retea-scolara.ts +187 -0
- package/lib/runner.ts +220 -84
- package/lib/sg/recipes/register.ts +46 -52
- package/lib/sg/tools/fetch/acra.ts +20 -25
- package/lib/si/recipes/bare-village.ts +34 -17
- package/lib/sk/adapters/inspire/adapter.ts +395 -0
- package/lib/sk/tools/fetch/inspire.ts +402 -0
- package/lib/source-register/effective-manifest.ts +659 -0
- package/lib/source-register/register.ts +539 -0
- package/lib/source-register/training-manifest.ts +218 -0
- package/lib/source-register/types.ts +590 -0
- package/lib/source-register.ts +71 -0
- package/lib/south-asia/recipes/register.ts +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 +246 -0
- package/lib/synthesizers/anchor-absorption.ts +55 -91
- package/lib/synthesizers/boundary-stress.ts +49 -131
- package/lib/synthesizers/house-venue.ts +44 -102
- package/lib/synthesizers/intersection.ts +37 -26
- package/lib/synthesizers/no-street.ts +70 -119
- package/lib/synthesizers/po-box.ts +90 -105
- package/lib/synthesizers/street.ts +46 -34
- package/lib/synthesizers/utils.ts +64 -218
- 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 +113 -118
- package/lib/tools/corpus-stats.ts +44 -30
- package/lib/tools/fetch/atom.ts +164 -0
- package/lib/tools/fetch/cordis.ts +318 -0
- package/lib/tools/fetch/download/manifest.ts +34 -22
- package/lib/tools/fetch/download/network.ts +55 -31
- package/lib/tools/fetch/download/retry.ts +26 -25
- package/lib/tools/fetch/geonames/dump.ts +72 -54
- package/lib/tools/fetch/geonames/postal.ts +27 -62
- package/lib/tools/fetch/gleif.ts +360 -0
- package/lib/tools/fetch/header.ts +69 -0
- package/lib/tools/fetch/inspire-addresses.ts +495 -0
- package/lib/tools/fetch/openaddresses.ts +22 -111
- 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 +943 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +45 -145
- package/lib/tools/fetch/zip-archive.ts +100 -0
- package/lib/tools/fetch.ts +143 -0
- package/lib/tools/golden/expand.ts +74 -43
- package/lib/tools/golden/promote.ts +41 -32
- package/lib/tools/golden/relabel-street/directory.ts +63 -36
- package/lib/tools/golden/relabel-street/row.ts +28 -106
- package/lib/tools/ingest-csv.ts +45 -48
- package/lib/tools/jsonl-to-parquet.ts +59 -98
- package/lib/tools/lint/recipe-output/vocab.ts +366 -0
- package/lib/tools/lint/{slice/index.ts → recipe-output.ts} +107 -121
- 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 +43 -36
- package/lib/tools/overlay/manifest.ts +407 -0
- package/lib/tools/overlay/merge-source.ts +138 -0
- package/lib/tools/overlay/split-slice.ts +144 -0
- package/lib/tools/{slice → overlay}/translit.ts +74 -58
- package/lib/tools/overture-subvenue.ts +17 -90
- package/lib/tools/postcode-triples.ts +281 -210
- package/lib/tools/source-register/build.ts +819 -0
- package/lib/tools/sub/venue/head-nouns.ts +38 -75
- package/lib/tools/sub/venue/lexicon.ts +71 -106
- package/lib/tools/sub/venue/wikidata.ts +13 -10
- package/lib/tools.ts +31 -0
- package/lib/tw/tools/fetch/gcis.ts +17 -16
- package/lib/types.ts +304 -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 +7 -2
- 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 +51 -112
- package/lib/us/adapters/usgov/nppes/adapter.ts +72 -35
- package/lib/us/adapters/usgov/samhsa-treatment-locator/adapter.ts +43 -30
- package/lib/us/fips-state.ts +17 -8
- package/lib/us/tools/fetch/hrsa.ts +7 -8
- package/lib/us/tools/fetch/imls-pls.ts +17 -35
- package/lib/us/tools/fetch/nad.ts +50 -32
- package/lib/us/tools/fetch/nppes.ts +23 -35
- package/lib/us/tools/fetch/state/hi-schools.ts +22 -16
- package/lib/us/tools/fetch/state/sources.ts +12 -12
- package/lib/us/tools/fetch/tiger-full.ts +21 -73
- package/lib/utils/align.ts +42 -52
- package/lib/utils/{slice-stats.ts → cooccurrence-stats.ts} +22 -16
- package/lib/utils/golden.ts +34 -49
- package/lib/utils/license.ts +238 -26
- package/lib/utils/split.ts +205 -88
- package/lib/utils/tokenize.ts +22 -34
- package/lib/utils/wof-json.ts +129 -76
- 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 +324 -0
- package/out/adapters/cordis/adapter.d.ts.map +1 -0
- package/out/adapters/cordis/adapter.js +616 -0
- package/out/adapters/cordis/adapter.js.map +1 -0
- package/out/adapters/dedup-key.d.ts +30 -0
- package/out/adapters/dedup-key.d.ts.map +1 -0
- package/out/adapters/dedup-key.js +35 -0
- package/out/adapters/dedup-key.js.map +1 -0
- package/out/adapters/errors.d.ts +17 -0
- package/out/adapters/errors.d.ts.map +1 -0
- package/out/adapters/errors.js +20 -0
- package/out/adapters/errors.js.map +1 -0
- package/out/adapters/geonames/adapter.d.ts +26 -28
- package/out/adapters/geonames/adapter.d.ts.map +1 -1
- package/out/adapters/geonames/adapter.js +39 -49
- 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 +684 -0
- package/out/adapters/gleif/adapter.js.map +1 -0
- package/out/adapters/libpostal-dictionary.d.ts +22 -0
- package/out/adapters/libpostal-dictionary.d.ts.map +1 -0
- package/out/adapters/libpostal-dictionary.js +36 -0
- package/out/adapters/libpostal-dictionary.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts +28 -43
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -1
- package/out/adapters/openaddresses/adapter.js +34 -46
- package/out/adapters/openaddresses/adapter.js.map +1 -1
- package/out/adapters/osm/adapter.d.ts +48 -42
- package/out/adapters/osm/adapter.d.ts.map +1 -1
- package/out/adapters/osm/adapter.js +116 -67
- 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 +63 -0
- package/out/adapters/po-box/adapter.d.ts.map +1 -0
- package/out/adapters/{synth-po-box → po-box}/adapter.js +45 -46
- package/out/adapters/po-box/adapter.js.map +1 -0
- package/out/adapters/registry.d.ts +55 -0
- package/out/adapters/registry.d.ts.map +1 -0
- package/out/adapters/registry.js +43 -0
- package/out/adapters/registry.js.map +1 -0
- package/out/adapters/sha256-stream.d.ts +26 -0
- package/out/adapters/sha256-stream.d.ts.map +1 -0
- package/out/adapters/sha256-stream.js +34 -0
- package/out/adapters/sha256-stream.js.map +1 -0
- package/out/adapters/source-id.d.ts +33 -0
- package/out/adapters/source-id.d.ts.map +1 -0
- package/out/adapters/source-id.js +42 -0
- package/out/adapters/source-id.js.map +1 -0
- package/out/adapters/street-line.d.ts +102 -0
- package/out/adapters/street-line.d.ts.map +1 -0
- package/out/adapters/street-line.js +117 -0
- package/out/adapters/street-line.js.map +1 -0
- package/out/adapters/wof/admin/json/adapter.d.ts +27 -18
- package/out/adapters/wof/admin/json/adapter.d.ts.map +1 -1
- package/out/adapters/wof/admin/json/adapter.js +47 -31
- package/out/adapters/wof/admin/json/adapter.js.map +1 -1
- package/out/adapters/wof/json-rows.d.ts +35 -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 +55 -57
- 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 +34 -42
- 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 +233 -0
- package/out/be/adapters/vlaanderen/adapter.d.ts.map +1 -0
- package/out/be/adapters/vlaanderen/adapter.js +416 -0
- package/out/be/adapters/vlaanderen/adapter.js.map +1 -0
- package/out/be/adapters/wallonie/adapter.d.ts +196 -0
- package/out/be/adapters/wallonie/adapter.d.ts.map +1 -0
- package/out/be/adapters/wallonie/adapter.js +437 -0
- package/out/be/adapters/wallonie/adapter.js.map +1 -0
- package/out/be/tools/fetch/brussels.d.ts +119 -0
- package/out/be/tools/fetch/brussels.d.ts.map +1 -0
- package/out/be/tools/fetch/brussels.js +146 -0
- package/out/be/tools/fetch/brussels.js.map +1 -0
- package/out/be/tools/fetch/wallonie.d.ts +119 -0
- package/out/be/tools/fetch/wallonie.d.ts.map +1 -0
- package/out/be/tools/fetch/wallonie.js +167 -0
- package/out/be/tools/fetch/wallonie.js.map +1 -0
- package/out/build/adapters.d.ts +33 -0
- package/out/build/adapters.d.ts.map +1 -0
- package/out/build/adapters.js +68 -0
- package/out/build/adapters.js.map +1 -0
- package/out/build/align.d.ts +73 -0
- package/out/build/align.d.ts.map +1 -0
- package/out/build/align.js +226 -0
- package/out/build/align.js.map +1 -0
- package/out/build/checkpoint.d.ts +94 -0
- package/out/build/checkpoint.d.ts.map +1 -0
- package/out/build/checkpoint.js +59 -0
- package/out/build/checkpoint.js.map +1 -0
- package/out/build/eligibility.d.ts +47 -0
- package/out/build/eligibility.d.ts.map +1 -0
- package/out/build/eligibility.js +80 -0
- package/out/build/eligibility.js.map +1 -0
- package/out/build/heap.d.ts +28 -0
- package/out/build/heap.d.ts.map +1 -0
- package/out/build/heap.js +47 -0
- package/out/build/heap.js.map +1 -0
- package/out/build/inputs.d.ts +52 -0
- package/out/build/inputs.d.ts.map +1 -0
- package/out/build/inputs.js +49 -0
- package/out/build/inputs.js.map +1 -0
- package/out/build/rows.d.ts +16 -0
- package/out/build/rows.d.ts.map +1 -0
- package/out/build/rows.js +19 -0
- package/out/build/rows.js.map +1 -0
- package/out/build/types.d.ts +220 -0
- package/out/build/types.d.ts.map +1 -0
- package/out/build/types.js +34 -0
- package/out/build/types.js.map +1 -0
- package/out/build.d.ts +6 -121
- package/out/build.d.ts.map +1 -1
- package/out/build.js +112 -207
- package/out/build.js.map +1 -1
- package/out/cn/recipes/organizational-units.d.ts +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 +266 -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 +272 -0
- package/out/cz/tools/fetch/cuzk.d.ts.map +1 -0
- package/out/cz/tools/fetch/cuzk.js +446 -0
- package/out/cz/tools/fetch/cuzk.js.map +1 -0
- package/out/de/recipes/locale.d.ts +24 -26
- package/out/de/recipes/locale.d.ts.map +1 -1
- package/out/de/recipes/locale.js +66 -56
- 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 +154 -0
- package/out/dk/adapters/inspire/adapter.d.ts.map +1 -0
- package/out/dk/adapters/inspire/adapter.js +258 -0
- package/out/dk/adapters/inspire/adapter.js.map +1 -0
- package/out/dk/tools/fetch/inspire.d.ts +100 -0
- package/out/dk/tools/fetch/inspire.d.ts.map +1 -0
- package/out/dk/tools/fetch/inspire.js +230 -0
- package/out/dk/tools/fetch/inspire.js.map +1 -0
- package/out/ee/adapters/ads/adapter.d.ts +109 -0
- package/out/ee/adapters/ads/adapter.d.ts.map +1 -0
- package/out/ee/adapters/ads/adapter.js +191 -0
- package/out/ee/adapters/ads/adapter.js.map +1 -0
- package/out/ee/tools/fetch/ads.d.ts +123 -0
- package/out/ee/tools/fetch/ads.d.ts.map +1 -0
- package/out/ee/tools/fetch/ads.js +195 -0
- package/out/ee/tools/fetch/ads.js.map +1 -0
- package/out/env.d.ts +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 +104 -0
- package/out/es/adapters/catastro/adapter.d.ts.map +1 -0
- package/out/es/adapters/catastro/adapter.js +288 -0
- package/out/es/adapters/catastro/adapter.js.map +1 -0
- package/out/es/adapters/gipuzkoa/adapter.d.ts +91 -0
- package/out/es/adapters/gipuzkoa/adapter.d.ts.map +1 -0
- package/out/es/adapters/gipuzkoa/adapter.js +225 -0
- package/out/es/adapters/gipuzkoa/adapter.js.map +1 -0
- package/out/es/adapters/navarra/adapter.d.ts +105 -0
- package/out/es/adapters/navarra/adapter.d.ts.map +1 -0
- package/out/es/adapters/navarra/adapter.js +241 -0
- package/out/es/adapters/navarra/adapter.js.map +1 -0
- package/out/es/cadastre.d.ts +109 -0
- package/out/es/cadastre.d.ts.map +1 -0
- package/out/es/cadastre.js +130 -0
- package/out/es/cadastre.js.map +1 -0
- package/out/es/tools/fetch/bizkaia.d.ts +278 -0
- package/out/es/tools/fetch/bizkaia.d.ts.map +1 -0
- package/out/es/tools/fetch/bizkaia.js +477 -0
- package/out/es/tools/fetch/bizkaia.js.map +1 -0
- package/out/es/tools/fetch/catastro.d.ts +272 -0
- package/out/es/tools/fetch/catastro.d.ts.map +1 -0
- package/out/es/tools/fetch/catastro.js +486 -0
- package/out/es/tools/fetch/catastro.js.map +1 -0
- package/out/es/tools/fetch/gipuzkoa.d.ts +162 -0
- package/out/es/tools/fetch/gipuzkoa.d.ts.map +1 -0
- package/out/es/tools/fetch/gipuzkoa.js +209 -0
- package/out/es/tools/fetch/gipuzkoa.js.map +1 -0
- package/out/es/tools/fetch/navarra.d.ts +189 -0
- package/out/es/tools/fetch/navarra.d.ts.map +1 -0
- package/out/es/tools/fetch/navarra.js +316 -0
- package/out/es/tools/fetch/navarra.js.map +1 -0
- package/out/fi/adapters/ryhti/adapter.d.ts +115 -0
- package/out/fi/adapters/ryhti/adapter.d.ts.map +1 -0
- package/out/fi/adapters/ryhti/adapter.js +244 -0
- package/out/fi/adapters/ryhti/adapter.js.map +1 -0
- package/out/fi/tools/fetch/ryhti.d.ts +206 -0
- package/out/fi/tools/fetch/ryhti.d.ts.map +1 -0
- package/out/fi/tools/fetch/ryhti.js +327 -0
- package/out/fi/tools/fetch/ryhti.js.map +1 -0
- package/out/fingerprints.d.ts +68 -0
- package/out/fingerprints.d.ts.map +1 -0
- package/out/fingerprints.js +130 -0
- package/out/fingerprints.js.map +1 -0
- package/out/fr/adapters/annuaire-education/adapter.d.ts +236 -0
- package/out/fr/adapters/annuaire-education/adapter.d.ts.map +1 -0
- package/out/fr/adapters/annuaire-education/adapter.js +475 -0
- package/out/fr/adapters/annuaire-education/adapter.js.map +1 -0
- package/out/fr/adapters/ban/adapter.d.ts +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 +276 -0
- package/out/fr/adapters/finess/adapter.d.ts.map +1 -0
- package/out/fr/adapters/finess/adapter.js +519 -0
- package/out/fr/adapters/finess/adapter.js.map +1 -0
- package/out/fr/adapters/finess/postal-lines.d.ts +61 -0
- package/out/fr/adapters/finess/postal-lines.d.ts.map +1 -0
- package/out/fr/adapters/finess/postal-lines.js +114 -0
- package/out/fr/adapters/finess/postal-lines.js.map +1 -0
- package/out/fr/adapters/finess/voie-type.d.ts +77 -0
- package/out/fr/adapters/finess/voie-type.d.ts.map +1 -0
- package/out/fr/adapters/finess/voie-type.js +172 -0
- package/out/fr/adapters/finess/voie-type.js.map +1 -0
- package/out/fr/insee-country.d.ts +45 -0
- package/out/fr/insee-country.d.ts.map +1 -0
- package/out/fr/insee-country.js +60 -0
- package/out/fr/insee-country.js.map +1 -0
- package/out/fr/recipes/admin-split.d.ts +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 +88 -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 +130 -0
- package/out/fr/tools/fetch/annuaire-education.d.ts.map +1 -0
- package/out/fr/tools/fetch/annuaire-education.js +196 -0
- package/out/fr/tools/fetch/annuaire-education.js.map +1 -0
- package/out/fr/tools/fetch/ban.d.ts +9 -7
- package/out/fr/tools/fetch/ban.d.ts.map +1 -1
- package/out/fr/tools/fetch/ban.js +27 -18
- 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 +228 -0
- package/out/fr/tools/fetch/finess.js.map +1 -0
- package/out/gauntlet-inputs.d.ts +42 -0
- package/out/gauntlet-inputs.d.ts.map +1 -0
- package/out/gauntlet-inputs.js +78 -0
- package/out/gauntlet-inputs.js.map +1 -0
- package/out/index.d.ts +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 +251 -0
- package/out/inspire/address.d.ts.map +1 -0
- package/out/inspire/address.js +384 -0
- package/out/inspire/address.js.map +1 -0
- package/out/inspire/archive.d.ts +36 -0
- package/out/inspire/archive.d.ts.map +1 -0
- package/out/inspire/archive.js +42 -0
- package/out/inspire/archive.js.map +1 -0
- package/out/inspire/errors.d.ts +55 -0
- package/out/inspire/errors.d.ts.map +1 -0
- package/out/inspire/errors.js +64 -0
- package/out/inspire/errors.js.map +1 -0
- package/out/inspire/stream.d.ts +137 -0
- package/out/inspire/stream.d.ts.map +1 -0
- package/out/inspire/stream.js +125 -0
- package/out/inspire/stream.js.map +1 -0
- package/out/international/recipes/locale.d.ts +38 -84
- package/out/international/recipes/locale.d.ts.map +1 -1
- package/out/international/recipes/locale.js +112 -151
- package/out/international/recipes/locale.js.map +1 -1
- package/out/it/adapters/anac/adapter.d.ts +267 -0
- package/out/it/adapters/anac/adapter.d.ts.map +1 -0
- package/out/it/adapters/anac/adapter.js +429 -0
- package/out/it/adapters/anac/adapter.js.map +1 -0
- package/out/it/tools/fetch/anac.d.ts +174 -0
- package/out/it/tools/fetch/anac.d.ts.map +1 -0
- package/out/it/tools/fetch/anac.js +272 -0
- package/out/it/tools/fetch/anac.js.map +1 -0
- package/out/jp/adapters/wof-admin/adapter.d.ts +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 +15 -11
- 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 +30 -25
- 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 +23 -15
- 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 +163 -0
- package/out/lu/tools/fetch/bd-adresses.d.ts.map +1 -0
- package/out/lu/tools/fetch/bd-adresses.js +223 -0
- package/out/lu/tools/fetch/bd-adresses.js.map +1 -0
- package/out/lv/adapters/varis/adapter.d.ts +283 -0
- package/out/lv/adapters/varis/adapter.d.ts.map +1 -0
- package/out/lv/adapters/varis/adapter.js +404 -0
- package/out/lv/adapters/varis/adapter.js.map +1 -0
- package/out/lv/tools/fetch/varis.d.ts +80 -0
- package/out/lv/tools/fetch/varis.d.ts.map +1 -0
- package/out/lv/tools/fetch/varis.js +133 -0
- package/out/lv/tools/fetch/varis.js.map +1 -0
- package/out/nl/adapters/kadaster/adapter.d.ts +125 -0
- package/out/nl/adapters/kadaster/adapter.d.ts.map +1 -0
- package/out/nl/adapters/kadaster/adapter.js +310 -0
- package/out/nl/adapters/kadaster/adapter.js.map +1 -0
- package/out/nl/recipes/postcode.d.ts +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 +155 -0
- package/out/nl/tools/fetch/kadaster.d.ts.map +1 -0
- package/out/nl/tools/fetch/kadaster.js +179 -0
- package/out/nl/tools/fetch/kadaster.js.map +1 -0
- package/out/no/adapters/matrikkelen/adapter.d.ts +44 -0
- package/out/no/adapters/matrikkelen/adapter.d.ts.map +1 -0
- package/out/no/adapters/matrikkelen/adapter.js +143 -0
- package/out/no/adapters/matrikkelen/adapter.js.map +1 -0
- package/out/no/recipes/fragment.d.ts +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 +251 -0
- package/out/no/tools/fetch/matrikkelen.d.ts.map +1 -0
- package/out/no/tools/fetch/matrikkelen.js +345 -0
- package/out/no/tools/fetch/matrikkelen.js.map +1 -0
- package/out/parquet/duckdb.d.ts +100 -0
- package/out/parquet/duckdb.d.ts.map +1 -0
- package/out/parquet/duckdb.js +92 -0
- package/out/parquet/duckdb.js.map +1 -0
- package/out/parquet/readers.d.ts +44 -0
- package/out/parquet/readers.d.ts.map +1 -0
- package/out/parquet/readers.js +69 -0
- package/out/parquet/readers.js.map +1 -0
- package/out/parquet/schema.d.ts +95 -0
- package/out/parquet/schema.d.ts.map +1 -0
- package/out/parquet/schema.js +157 -0
- package/out/parquet/schema.js.map +1 -0
- package/out/parquet/shuffle.d.ts +25 -0
- package/out/parquet/shuffle.d.ts.map +1 -0
- package/out/parquet/shuffle.js +44 -0
- package/out/parquet/shuffle.js.map +1 -0
- package/out/parquet/span-sql.d.ts +49 -0
- package/out/parquet/span-sql.d.ts.map +1 -0
- package/out/parquet/span-sql.js +53 -0
- package/out/parquet/span-sql.js.map +1 -0
- package/out/parquet/streams.d.ts +47 -0
- package/out/parquet/streams.d.ts.map +1 -0
- package/out/parquet/streams.js +78 -0
- package/out/parquet/streams.js.map +1 -0
- package/out/parquet/writers.d.ts +124 -0
- package/out/parquet/writers.d.ts.map +1 -0
- package/out/parquet/writers.js +251 -0
- package/out/parquet/writers.js.map +1 -0
- package/out/pl/adapters/emuia/adapter.d.ts +81 -0
- package/out/pl/adapters/emuia/adapter.d.ts.map +1 -0
- package/out/pl/adapters/emuia/adapter.js +178 -0
- package/out/pl/adapters/emuia/adapter.js.map +1 -0
- package/out/pl/tools/fetch/emuia.d.ts +165 -0
- package/out/pl/tools/fetch/emuia.d.ts.map +1 -0
- package/out/pl/tools/fetch/emuia.js +260 -0
- package/out/pl/tools/fetch/emuia.js.map +1 -0
- package/out/recipes/anchor-absorption.d.ts +9 -9
- package/out/recipes/anchor-absorption.d.ts.map +1 -1
- package/out/recipes/anchor-absorption.js +29 -19
- package/out/recipes/anchor-absorption.js.map +1 -1
- package/out/recipes/bare/country.d.ts +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} +91 -79
- package/out/recipes/bare/postcode.js.map +1 -0
- package/out/recipes/boundary-stress.d.ts +8 -8
- package/out/recipes/boundary-stress.d.ts.map +1 -1
- package/out/recipes/boundary-stress.js +36 -19
- package/out/recipes/boundary-stress.js.map +1 -1
- package/out/recipes/country-balanced.d.ts +3 -21
- package/out/recipes/country-balanced.d.ts.map +1 -1
- package/out/recipes/country-balanced.js +58 -76
- package/out/recipes/country-balanced.js.map +1 -1
- package/out/recipes/house-venue.d.ts +8 -6
- package/out/recipes/house-venue.d.ts.map +1 -1
- package/out/recipes/house-venue.js +29 -13
- package/out/recipes/house-venue.js.map +1 -1
- package/out/recipes/intersection.d.ts +20 -20
- package/out/recipes/intersection.d.ts.map +1 -1
- package/out/recipes/intersection.js +65 -53
- package/out/recipes/intersection.js.map +1 -1
- package/out/recipes/po/box/cedex/au-nz.d.ts.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 +25 -15
- package/out/recipes/po/box/cedex/recipe.js.map +1 -1
- package/out/recipes/po/box/cedex/sources.d.ts +12 -12
- package/out/recipes/po/box/cedex/sources.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/sources.js +1 -1
- 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 +211 -138
- package/out/recipes/scaffold.d.ts.map +1 -1
- package/out/recipes/scaffold.js +72 -63
- package/out/recipes/scaffold.js.map +1 -1
- package/out/recipes/sources.d.ts +178 -0
- package/out/recipes/sources.d.ts.map +1 -0
- package/out/recipes/sources.js +348 -0
- package/out/recipes/sources.js.map +1 -0
- package/out/recipes/street/affix.d.ts +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 +25 -14
- 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 +29 -8
- 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 +21 -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 +49 -92
- package/out/recipes/sub/venue/sources.d.ts.map +1 -1
- package/out/recipes/sub/venue/sources.js +43 -179
- package/out/recipes/sub/venue/sources.js.map +1 -1
- package/out/recipes/sub/venue.d.ts +176 -0
- package/out/recipes/sub/venue.d.ts.map +1 -0
- package/out/recipes/sub/venue.js +562 -0
- package/out/recipes/sub/venue.js.map +1 -0
- package/out/recipes/trailing-region.d.ts +9 -61
- package/out/recipes/trailing-region.d.ts.map +1 -1
- package/out/recipes/trailing-region.js +55 -85
- package/out/recipes/trailing-region.js.map +1 -1
- package/out/recipes/unit/sources.d.ts +28 -0
- package/out/recipes/unit/sources.d.ts.map +1 -0
- package/out/recipes/unit/sources.js +30 -0
- package/out/recipes/unit/sources.js.map +1 -0
- package/out/recipes/unit.d.ts +30 -17
- package/out/recipes/unit.d.ts.map +1 -1
- package/out/recipes/unit.js +90 -79
- package/out/recipes/unit.js.map +1 -1
- package/out/recipes.d.ts +26 -0
- package/out/recipes.d.ts.map +1 -0
- package/out/{recipes/index.js → recipes.js} +14 -12
- package/out/recipes.js.map +1 -0
- package/out/registers.d.ts +277 -0
- package/out/registers.d.ts.map +1 -0
- package/out/registers.js +273 -0
- package/out/registers.js.map +1 -0
- package/out/ro/adapters/retea-scolara/adapter.d.ts +114 -0
- package/out/ro/adapters/retea-scolara/adapter.d.ts.map +1 -0
- package/out/ro/adapters/retea-scolara/adapter.js +209 -0
- package/out/ro/adapters/retea-scolara/adapter.js.map +1 -0
- package/out/ro/tools/fetch/retea-scolara.d.ts +69 -0
- package/out/ro/tools/fetch/retea-scolara.d.ts.map +1 -0
- package/out/ro/tools/fetch/retea-scolara.js +117 -0
- package/out/ro/tools/fetch/retea-scolara.js.map +1 -0
- package/out/runner.d.ts +120 -60
- package/out/runner.d.ts.map +1 -1
- package/out/runner.js +130 -56
- package/out/runner.js.map +1 -1
- package/out/sg/recipes/register.d.ts +18 -32
- package/out/sg/recipes/register.d.ts.map +1 -1
- package/out/sg/recipes/register.js +44 -49
- 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 +16 -19
- 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 +195 -0
- package/out/sk/tools/fetch/inspire.d.ts.map +1 -0
- package/out/sk/tools/fetch/inspire.js +280 -0
- package/out/sk/tools/fetch/inspire.js.map +1 -0
- package/out/source-register/effective-manifest.d.ts +355 -0
- package/out/source-register/effective-manifest.d.ts.map +1 -0
- package/out/source-register/effective-manifest.js +355 -0
- package/out/source-register/effective-manifest.js.map +1 -0
- package/out/source-register/register.d.ts +79 -0
- package/out/source-register/register.d.ts.map +1 -0
- package/out/source-register/register.js +400 -0
- package/out/source-register/register.js.map +1 -0
- package/out/source-register/training-manifest.d.ts +111 -0
- package/out/source-register/training-manifest.d.ts.map +1 -0
- package/out/source-register/training-manifest.js +120 -0
- package/out/source-register/training-manifest.js.map +1 -0
- package/out/source-register/types.d.ts +539 -0
- package/out/source-register/types.d.ts.map +1 -0
- package/out/source-register/types.js +263 -0
- package/out/source-register/types.js.map +1 -0
- package/out/source-register.d.ts +19 -0
- package/out/source-register.d.ts.map +1 -0
- package/out/source-register.js +16 -0
- package/out/source-register.js.map +1 -0
- package/out/south-asia/recipes/register.d.ts +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 +136 -0
- package/out/surfaces/locale.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +21 -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 +17 -48
- package/out/synthesizers/boundary-stress.d.ts.map +1 -1
- package/out/synthesizers/boundary-stress.js +27 -121
- package/out/synthesizers/boundary-stress.js.map +1 -1
- package/out/synthesizers/house-venue.d.ts +22 -25
- package/out/synthesizers/house-venue.d.ts.map +1 -1
- package/out/synthesizers/house-venue.js +28 -97
- package/out/synthesizers/house-venue.js.map +1 -1
- package/out/synthesizers/intersection.d.ts +10 -8
- package/out/synthesizers/intersection.d.ts.map +1 -1
- package/out/synthesizers/intersection.js +33 -26
- package/out/synthesizers/intersection.js.map +1 -1
- package/out/synthesizers/no-street.d.ts +7 -37
- package/out/synthesizers/no-street.d.ts.map +1 -1
- package/out/synthesizers/no-street.js +55 -111
- package/out/synthesizers/no-street.js.map +1 -1
- package/out/synthesizers/po-box.d.ts +46 -45
- package/out/synthesizers/po-box.d.ts.map +1 -1
- package/out/synthesizers/po-box.js +57 -97
- package/out/synthesizers/po-box.js.map +1 -1
- package/out/synthesizers/street.d.ts +18 -12
- package/out/synthesizers/street.d.ts.map +1 -1
- package/out/synthesizers/street.js +36 -29
- package/out/synthesizers/street.js.map +1 -1
- package/out/synthesizers/utils.d.ts +32 -129
- package/out/synthesizers/utils.d.ts.map +1 -1
- package/out/synthesizers/utils.js +54 -166
- package/out/synthesizers/utils.js.map +1 -1
- package/out/test-kit/corpus-recipe.d.ts +29 -23
- package/out/test-kit/corpus-recipe.d.ts.map +1 -1
- package/out/test-kit/corpus-recipe.js +28 -13
- package/out/test-kit/corpus-recipe.js.map +1 -1
- package/out/test-kit.d.ts +63 -0
- package/out/test-kit.d.ts.map +1 -0
- package/out/test-kit.js +88 -0
- package/out/test-kit.js.map +1 -0
- package/out/tools/align-canonical.d.ts +7 -0
- package/out/tools/align-canonical.d.ts.map +1 -0
- package/out/tools/align-canonical.js +52 -0
- package/out/tools/align-canonical.js.map +1 -0
- package/out/tools/audit.d.ts +18 -11
- package/out/tools/audit.d.ts.map +1 -1
- package/out/tools/audit.js +86 -95
- package/out/tools/audit.js.map +1 -1
- package/out/tools/corpus-stats.d.ts +24 -15
- package/out/tools/corpus-stats.d.ts.map +1 -1
- package/out/tools/corpus-stats.js +33 -29
- package/out/tools/corpus-stats.js.map +1 -1
- package/out/tools/fetch/atom.d.ts +115 -0
- package/out/tools/fetch/atom.d.ts.map +1 -0
- package/out/tools/fetch/atom.js +84 -0
- package/out/tools/fetch/atom.js.map +1 -0
- package/out/tools/fetch/cordis.d.ts +123 -0
- package/out/tools/fetch/cordis.d.ts.map +1 -0
- package/out/tools/fetch/cordis.js +208 -0
- package/out/tools/fetch/cordis.js.map +1 -0
- package/out/tools/fetch/download/manifest.d.ts +27 -18
- package/out/tools/fetch/download/manifest.d.ts.map +1 -1
- package/out/tools/fetch/download/manifest.js +20 -13
- 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 +24 -24
- 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 +50 -32
- package/out/tools/fetch/geonames/dump.d.ts.map +1 -1
- package/out/tools/fetch/geonames/dump.js +52 -42
- 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 +137 -0
- package/out/tools/fetch/gleif.d.ts.map +1 -0
- package/out/tools/fetch/gleif.js +220 -0
- package/out/tools/fetch/gleif.js.map +1 -0
- package/out/tools/fetch/header.d.ts +41 -0
- package/out/tools/fetch/header.d.ts.map +1 -0
- package/out/tools/fetch/header.js +59 -0
- package/out/tools/fetch/header.js.map +1 -0
- package/out/tools/fetch/inspire-addresses.d.ts +249 -0
- package/out/tools/fetch/inspire-addresses.d.ts.map +1 -0
- package/out/tools/fetch/inspire-addresses.js +276 -0
- package/out/tools/fetch/inspire-addresses.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +1 -4
- package/out/tools/fetch/openaddresses.d.ts.map +1 -1
- package/out/tools/fetch/openaddresses.js +19 -98
- 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 +410 -0
- package/out/tools/fetch/wfs-harvest.d.ts.map +1 -0
- package/out/tools/fetch/wfs-harvest.js +522 -0
- package/out/tools/fetch/wfs-harvest.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +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 +140 -0
- package/out/tools/fetch.d.ts.map +1 -0
- package/out/tools/fetch.js +136 -0
- package/out/tools/fetch.js.map +1 -0
- package/out/tools/golden/expand.d.ts +28 -13
- package/out/tools/golden/expand.d.ts.map +1 -1
- package/out/tools/golden/expand.js +50 -36
- 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 +33 -28
- package/out/tools/golden/promote.js.map +1 -1
- package/out/tools/golden/relabel-street/directory.d.ts +24 -9
- package/out/tools/golden/relabel-street/directory.d.ts.map +1 -1
- package/out/tools/golden/relabel-street/directory.js +41 -30
- package/out/tools/golden/relabel-street/directory.js.map +1 -1
- package/out/tools/golden/relabel-street/row.d.ts +17 -69
- package/out/tools/golden/relabel-street/row.d.ts.map +1 -1
- package/out/tools/golden/relabel-street/row.js +16 -74
- 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 +39 -43
- package/out/tools/ingest-csv.js.map +1 -1
- package/out/tools/jsonl-to-parquet.d.ts +15 -28
- package/out/tools/jsonl-to-parquet.d.ts.map +1 -1
- package/out/tools/jsonl-to-parquet.js +49 -91
- package/out/tools/jsonl-to-parquet.js.map +1 -1
- package/out/tools/lint/recipe-output/vocab.d.ts +77 -0
- package/out/tools/lint/recipe-output/vocab.d.ts.map +1 -0
- package/out/tools/lint/{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} +76 -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 +37 -28
- package/out/tools/overlay/kryptonite.js.map +1 -0
- package/out/tools/overlay/manifest.d.ts +142 -0
- package/out/tools/overlay/manifest.d.ts.map +1 -0
- package/out/tools/overlay/manifest.js +260 -0
- package/out/tools/overlay/manifest.js.map +1 -0
- package/out/tools/overlay/merge-source.d.ts +73 -0
- package/out/tools/overlay/merge-source.d.ts.map +1 -0
- package/out/tools/overlay/merge-source.js +63 -0
- package/out/tools/overlay/merge-source.js.map +1 -0
- package/out/tools/overlay/split-slice.d.ts +66 -0
- package/out/tools/overlay/split-slice.d.ts.map +1 -0
- package/out/tools/overlay/split-slice.js +78 -0
- package/out/tools/overlay/split-slice.js.map +1 -0
- package/out/tools/overlay/translit.d.ts +54 -0
- package/out/tools/overlay/translit.d.ts.map +1 -0
- package/out/tools/{slice → overlay}/translit.js +59 -48
- package/out/tools/overlay/translit.js.map +1 -0
- package/out/tools/overture-subvenue.d.ts +16 -75
- 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 +77 -126
- package/out/tools/postcode-triples.d.ts.map +1 -1
- package/out/tools/postcode-triples.js +198 -192
- package/out/tools/postcode-triples.js.map +1 -1
- package/out/tools/source-register/build.d.ts +145 -0
- package/out/tools/source-register/build.d.ts.map +1 -0
- package/out/tools/source-register/build.js +515 -0
- package/out/tools/source-register/build.js.map +1 -0
- package/out/tools/sub/venue/head-nouns.d.ts +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 +55 -82
- package/out/tools/sub/venue/lexicon.d.ts.map +1 -1
- package/out/tools/sub/venue/lexicon.js +43 -87
- 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/tools.d.ts +31 -0
- package/out/tools.d.ts.map +1 -0
- package/out/tools.js +31 -0
- package/out/tools.js.map +1 -0
- package/out/tw/tools/fetch/gcis.d.ts +9 -3
- package/out/tw/tools/fetch/gcis.d.ts.map +1 -1
- package/out/tw/tools/fetch/gcis.js +16 -10
- package/out/tw/tools/fetch/gcis.js.map +1 -1
- package/out/types.d.ts +270 -101
- package/out/types.d.ts.map +1 -1
- package/out/types.js +133 -9
- package/out/types.js.map +1 -1
- package/out/us/adapters/fcc-bdc/adapter.d.ts +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 +7 -2
- 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 +51 -105
- 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 +36 -26
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js.map +1 -1
- package/out/us/fips-state.d.ts +17 -8
- 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/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 +16 -33
- 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 +29 -24
- 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 +21 -33
- package/out/us/tools/fetch/nppes.js.map +1 -1
- package/out/us/tools/fetch/state/hi-schools.d.ts +8 -5
- package/out/us/tools/fetch/state/hi-schools.d.ts.map +1 -1
- package/out/us/tools/fetch/state/hi-schools.js +15 -13
- 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 +15 -54
- package/out/us/tools/fetch/tiger-full.js.map +1 -1
- package/out/utils/align.d.ts +24 -19
- package/out/utils/align.d.ts.map +1 -1
- package/out/utils/align.js +27 -42
- package/out/utils/align.js.map +1 -1
- package/out/utils/cooccurrence-stats.d.ts +58 -0
- package/out/utils/cooccurrence-stats.d.ts.map +1 -0
- package/out/utils/cooccurrence-stats.js +62 -0
- package/out/utils/cooccurrence-stats.js.map +1 -0
- package/out/utils/golden.d.ts +21 -31
- package/out/utils/golden.d.ts.map +1 -1
- package/out/utils/golden.js +28 -44
- package/out/utils/golden.js.map +1 -1
- package/out/utils/license.d.ts +158 -21
- package/out/utils/license.d.ts.map +1 -1
- package/out/utils/license.js +156 -26
- package/out/utils/license.js.map +1 -1
- package/out/utils/split.d.ts +66 -70
- package/out/utils/split.d.ts.map +1 -1
- package/out/utils/split.js +158 -69
- package/out/utils/split.js.map +1 -1
- package/out/utils/tokenize.d.ts +16 -28
- package/out/utils/tokenize.d.ts.map +1 -1
- package/out/utils/tokenize.js +18 -31
- package/out/utils/tokenize.js.map +1 -1
- package/out/utils/wof-json.d.ts +88 -62
- package/out/utils/wof-json.d.ts.map +1 -1
- package/out/utils/wof-json.js +76 -55
- 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 +46 -480
- 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/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/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/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
|
@@ -3,37 +3,42 @@
|
|
|
3
3
|
* @license AGPL-3.0
|
|
4
4
|
* @author Teffen Ellis, et al.
|
|
5
5
|
*
|
|
6
|
-
* Build per-script parquet
|
|
7
|
-
* corpus-v0.4.0
|
|
6
|
+
* Build per-script parquet files from the DeepSeek-generated transliteration jsonl and emit the
|
|
7
|
+
* corpus-v0.4.0 manifest that combines them with the existing kryptonite + v0.3.0 files.
|
|
8
8
|
*
|
|
9
|
-
*
|
|
10
|
-
* base
|
|
9
|
+
* This module sits beside `kryptonite.ts`. Both modules use the same composition pattern: take a
|
|
10
|
+
* base manifest, append new parquet files, write a combined manifest. Differences specific to
|
|
11
11
|
* transliteration:
|
|
12
12
|
*
|
|
13
|
-
* - One
|
|
14
|
-
* `source` and write one
|
|
13
|
+
* - One jsonl contains rows from N target scripts (source = `deepseek-translit-<slug>`). We bucket by
|
|
14
|
+
* `source` and write one parquet file per script so `audit.ts` can attribute each file to its
|
|
15
15
|
* synthetic source without relying on filename-prefix inference.
|
|
16
|
-
* - Each
|
|
16
|
+
* - Each file is written to `train/part-translit-<slug>.parquet` (distinct from kryptonite's
|
|
17
17
|
* `part-0000.parquet`, which v0.4.0's first builder already produced).
|
|
18
|
-
* - Inherits the path-canonicalization fix flagged in Thread B's postmortem: v0.3.0
|
|
19
|
-
* rewritten from `$MAILWOMAN_DATA_ROOT/...` to `/data/...` in the combined
|
|
18
|
+
* - Inherits the path-canonicalization fix flagged in Thread B's postmortem: v0.3.0 file paths are
|
|
19
|
+
* rewritten from `$MAILWOMAN_DATA_ROOT/...` to `/data/...` in the combined manifest so
|
|
20
20
|
* all paths share one container-friendly form.
|
|
21
21
|
*
|
|
22
|
-
* See docs/engineering/
|
|
23
|
-
* reproducibility
|
|
22
|
+
* See docs/records/engineering/CORPUS_V0_4_0_GENERATION.mdx for prompts, model and the
|
|
23
|
+
* reproducibility interface.
|
|
24
24
|
*
|
|
25
25
|
* Invoke via `mailwoman corpus slice translit \
|
|
26
26
|
* --jsonl /data/corpus/versioned/v0.4.0/transliteration/canonical-transliteration.jsonl \
|
|
27
|
-
* --base-manifest /data/corpus/versioned/v0.4.0/corpus-v0.4.0/
|
|
27
|
+
* --base-manifest /data/corpus/versioned/v0.4.0/corpus-v0.4.0/manifest.json \
|
|
28
28
|
* --out-dir /data/corpus/versioned/v0.4.0`
|
|
29
29
|
*/
|
|
30
|
-
import {
|
|
30
|
+
import { dataRootPath } from "@mailwoman/core/data-root";
|
|
31
|
+
import { delimitedSource } from "@mailwoman/core/fs/delimited";
|
|
31
32
|
import { pathExists, readLocalJSONFile, tryStat } from "@mailwoman/core/fs/readers";
|
|
32
33
|
import { writeLocalJSONFile, writeLocalTextFile, makeDirectories } from "@mailwoman/core/fs/writers";
|
|
33
34
|
import { sha256File } from "@mailwoman/core/hash";
|
|
34
|
-
import {
|
|
35
|
+
import { PathBuilder } from "path-ts";
|
|
35
36
|
import { JSONSpliterator } from "spliterator";
|
|
36
|
-
import {
|
|
37
|
+
import { corpusDirectoryName } from "#directory";
|
|
38
|
+
import { PARQUET_COLUMNS, PARQUET_COMPRESSION, ROW_GROUP_SIZE, rowToParquet } from "#parquet/schema";
|
|
39
|
+
import { writeParquetFile } from "#parquet/writers";
|
|
40
|
+
import { requireSurface } from "#types";
|
|
41
|
+
import { alignRow } from "#utils";
|
|
37
42
|
function toCanonicalRow(raw, corpusVersion) {
|
|
38
43
|
return {
|
|
39
44
|
raw: raw["raw"],
|
|
@@ -44,14 +49,18 @@ function toCanonicalRow(raw, corpusVersion) {
|
|
|
44
49
|
source_id: raw["source_id"],
|
|
45
50
|
corpus_version: corpusVersion,
|
|
46
51
|
license: raw["license"] ?? "Synthetic (DeepSeek-v4-flash, AGPL-compatible)",
|
|
47
|
-
|
|
52
|
+
recipe: raw["recipe"],
|
|
53
|
+
register: raw["register"] ?? null,
|
|
54
|
+
surface: requireSurface(raw, "translit"),
|
|
48
55
|
};
|
|
49
56
|
}
|
|
50
57
|
/**
|
|
51
|
-
* Write one
|
|
52
|
-
*
|
|
58
|
+
* Write one parquet file for a single source slug.
|
|
59
|
+
*
|
|
60
|
+
* @returns The populated ParquetFileDescriptor + a list of quarantine reasons
|
|
61
|
+
* for rows that failed alignment.
|
|
53
62
|
*/
|
|
54
|
-
async function
|
|
63
|
+
async function writeOneFile(rows, outPath, source) {
|
|
55
64
|
let firstSourceID = "";
|
|
56
65
|
let lastSourceID = "";
|
|
57
66
|
for (const row of rows) {
|
|
@@ -60,45 +69,46 @@ async function writeOneSlice(rows, outPath, source) {
|
|
|
60
69
|
}
|
|
61
70
|
lastSourceID = row.source_id;
|
|
62
71
|
}
|
|
63
|
-
await
|
|
72
|
+
await writeParquetFile(rows.map(rowToParquet), outPath);
|
|
64
73
|
const fileStat = await tryStat(outPath);
|
|
65
74
|
const sha256 = await sha256File(outPath);
|
|
66
75
|
return {
|
|
67
76
|
split: "train",
|
|
68
77
|
path: outPath,
|
|
69
78
|
format: "parquet",
|
|
70
|
-
compression:
|
|
79
|
+
compression: PARQUET_COMPRESSION,
|
|
71
80
|
rows: rows.length,
|
|
72
81
|
bytes: fileStat?.size ?? 0,
|
|
73
82
|
sha256,
|
|
74
83
|
first_source_id: firstSourceID,
|
|
75
84
|
last_source_id: lastSourceID,
|
|
76
|
-
// Stamp source so audit.ts attributes the
|
|
85
|
+
// Stamp source so audit.ts attributes the file without falling back to filename-prefix inference.
|
|
77
86
|
source,
|
|
78
87
|
};
|
|
79
88
|
}
|
|
80
|
-
function
|
|
89
|
+
function canonicalizeFilePath(path, legacyPrefix, canonicalPrefix) {
|
|
81
90
|
if (path.startsWith(legacyPrefix))
|
|
82
91
|
return canonicalPrefix + path.slice(legacyPrefix.length);
|
|
83
92
|
return path;
|
|
84
93
|
}
|
|
85
|
-
export async function
|
|
94
|
+
export async function buildTranslitOverlay(options, report) {
|
|
86
95
|
const corpusVersion = options.corpusVersion ?? "0.4.0";
|
|
87
|
-
// This is a portable manifest namespace
|
|
96
|
+
// This is a portable manifest namespace rather than a host filesystem default.
|
|
88
97
|
const canonicalPathPrefix = options.canonicalPathPrefix ?? "/data/";
|
|
89
|
-
const legacyPathPrefix = options.legacyPathPrefix ?? `${
|
|
98
|
+
const legacyPathPrefix = options.legacyPathPrefix ?? `${dataRootPath()}/`;
|
|
90
99
|
if (!(await pathExists(options.jsonl)))
|
|
91
100
|
throw new Error(`jsonl not found: ${options.jsonl}`);
|
|
92
101
|
if (!(await pathExists(options.baseManifest)))
|
|
93
102
|
throw new Error(`base-manifest not found: ${options.baseManifest}`);
|
|
94
|
-
const corpusDir =
|
|
95
|
-
const trainDir =
|
|
103
|
+
const corpusDir = PathBuilder.from(options.outDir)(corpusDirectoryName(corpusVersion));
|
|
104
|
+
const trainDir = corpusDir("train");
|
|
96
105
|
await makeDirectories(trainDir);
|
|
97
|
-
// Bucket canonical rows by source.
|
|
106
|
+
// Bucket canonical rows by source.
|
|
107
|
+
// Quarantined rows are logged.
|
|
98
108
|
const buckets = new Map();
|
|
99
109
|
const quarantine = [];
|
|
100
110
|
let totalIn = 0;
|
|
101
|
-
for await (const raw of JSONSpliterator.fromAsync(options.jsonl)) {
|
|
111
|
+
for await (const raw of JSONSpliterator.fromAsync(delimitedSource(options.jsonl))) {
|
|
102
112
|
totalIn++;
|
|
103
113
|
const canon = toCanonicalRow(raw, corpusVersion);
|
|
104
114
|
const result = alignRow(canon);
|
|
@@ -115,36 +125,37 @@ export async function buildTranslitSlice(options, report) {
|
|
|
115
125
|
}
|
|
116
126
|
}
|
|
117
127
|
report?.(`read ${totalIn} rows; ${quarantine.length} quarantined; ${buckets.size} script buckets`);
|
|
118
|
-
const
|
|
128
|
+
const newFiles = [];
|
|
119
129
|
const sortedKeys = [...buckets.keys()].toSorted();
|
|
120
130
|
for (const source of sortedKeys) {
|
|
121
131
|
const rows = buckets.get(source);
|
|
122
132
|
const slug = source.startsWith("deepseek-translit-") ? source.slice("deepseek-translit-".length) : source;
|
|
123
|
-
|
|
124
|
-
const
|
|
125
|
-
|
|
133
|
+
// A string, because the manifest records it.
|
|
134
|
+
const outPath = trainDir(`part-translit-${slug}.parquet`).toString();
|
|
135
|
+
const descriptor = await writeOneFile(rows, outPath, source);
|
|
136
|
+
newFiles.push(descriptor);
|
|
126
137
|
report?.(` ${source}: ${descriptor.rows} rows → ${outPath} (${descriptor.bytes} bytes)`);
|
|
127
138
|
}
|
|
128
139
|
if (quarantine.length) {
|
|
129
|
-
const qPath =
|
|
130
|
-
await writeLocalTextFile(quarantine
|
|
140
|
+
const qPath = corpusDir("quarantine-transliteration.tsv");
|
|
141
|
+
await writeLocalTextFile(quarantine, qPath);
|
|
131
142
|
report?.(`quarantine log → ${qPath} (${quarantine.length} rows)`);
|
|
132
143
|
}
|
|
133
|
-
// Compose final
|
|
134
|
-
// the new translit
|
|
135
|
-
// there by Thread B).
|
|
144
|
+
// Compose final manifest: rewrite the base's file paths from the data root → /data/...
|
|
145
|
+
// And append the new translit files.
|
|
146
|
+
// The kryptonite file already lives in the base manifest (it was written there by Thread B).
|
|
136
147
|
const base = await readLocalJSONFile(options.baseManifest);
|
|
137
|
-
const rewrittenBase = base.slices.map((
|
|
138
|
-
...
|
|
139
|
-
path:
|
|
148
|
+
const rewrittenBase = base.slices.map((file) => ({
|
|
149
|
+
...file,
|
|
150
|
+
path: canonicalizeFilePath(file.path, legacyPathPrefix, canonicalPathPrefix),
|
|
140
151
|
}));
|
|
141
|
-
const newTrainRows =
|
|
152
|
+
const newTrainRows = newFiles.reduce((sum, file) => sum + file.rows, 0);
|
|
142
153
|
const combined = {
|
|
143
154
|
corpus_version: corpusVersion,
|
|
144
155
|
schema: PARQUET_COLUMNS,
|
|
145
156
|
rows_per_slice: base.rows_per_slice,
|
|
146
157
|
row_group_size: base.row_group_size ?? ROW_GROUP_SIZE,
|
|
147
|
-
slices: [...rewrittenBase, ...
|
|
158
|
+
slices: [...rewrittenBase, ...newFiles],
|
|
148
159
|
counts: {
|
|
149
160
|
train: base.counts.train + newTrainRows,
|
|
150
161
|
val: base.counts.val,
|
|
@@ -152,15 +163,15 @@ export async function buildTranslitSlice(options, report) {
|
|
|
152
163
|
},
|
|
153
164
|
total_rows: base.total_rows + newTrainRows,
|
|
154
165
|
};
|
|
155
|
-
const combinedPath =
|
|
166
|
+
const combinedPath = corpusDir("MANIFEST.json");
|
|
156
167
|
await writeLocalJSONFile(combined, combinedPath);
|
|
157
168
|
report?.(`wrote combined manifest → ${combinedPath}`);
|
|
158
169
|
report?.(` total_rows=${combined.total_rows} (base=${base.total_rows}, added=${newTrainRows})`);
|
|
159
|
-
report?.(`
|
|
160
|
-
report?.(` compression=${
|
|
170
|
+
report?.(` files=${combined.slices.length} (base=${base.slices.length}, added=${newFiles.length})`);
|
|
171
|
+
report?.(` compression=${PARQUET_COMPRESSION}`);
|
|
161
172
|
const pathFix = rewrittenBase.filter((s, i) => s.path !== base.slices[i].path).length;
|
|
162
173
|
if (pathFix > 0) {
|
|
163
|
-
report?.(` path-canonicalized base
|
|
174
|
+
report?.(` path-canonicalized base files: ${pathFix} (legacy '${legacyPathPrefix}' → '${canonicalPathPrefix}')`);
|
|
164
175
|
}
|
|
165
176
|
}
|
|
166
177
|
//# sourceMappingURL=translit.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"translit.js","sourceRoot":"","sources":["../../../lib/tools/overlay/translit.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AAEH,OAAO,EAAE,YAAY,EAAE,MAAM,2BAA2B,CAAA;AACxD,OAAO,EAAE,eAAe,EAAE,MAAM,8BAA8B,CAAA;AAC9D,OAAO,EAAE,UAAU,EAAE,iBAAiB,EAAE,OAAO,EAAE,MAAM,4BAA4B,CAAA;AACnF,OAAO,EAAE,kBAAkB,EAAE,kBAAkB,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAA;AACpG,OAAO,EAAE,UAAU,EAAE,MAAM,sBAAsB,CAAA;AACjD,OAAO,EAAE,WAAW,EAAwB,MAAM,SAAS,CAAA;AAC3D,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C,OAAO,EAAE,mBAAmB,EAAE,MAAM,YAAY,CAAA;AAChD,OAAO,EAAE,eAAe,EAAE,mBAAmB,EAAE,cAAc,EAAE,YAAY,EAAE,MAAM,iBAAiB,CAAA;AAEpG,OAAO,EAAE,gBAAgB,EAAE,MAAM,kBAAkB,CAAA;AACnD,OAAO,EAAsC,cAAc,EAAE,MAAM,QAAQ,CAAA;AAC3E,OAAO,EAAE,QAAQ,EAAE,MAAM,QAAQ,CAAA;AAyBjC,SAAS,cAAc,CAAC,GAA4B,EAAE,aAAqB;IAC1E,OAAO;QACN,GAAG,EAAE,GAAG,CAAC,KAAK,CAAW;QACzB,UAAU,EAAE,GAAG,CAAC,YAAY,CAA2B;QACvD,OAAO,EAAG,GAAG,CAAC,SAAS,CAAY,IAAI,IAAI;QAC3C,MAAM,EAAG,GAAG,CAAC,QAAQ,CAAY,IAAI,SAAS;QAC9C,MAAM,EAAE,GAAG,CAAC,QAAQ,CAAW;QAC/B,SAAS,EAAE,GAAG,CAAC,WAAW,CAAW;QACrC,cAAc,EAAE,aAAa;QAC7B,OAAO,EAAG,GAAG,CAAC,SAAS,CAAY,IAAI,gDAAgD;QACvF,MAAM,EAAE,GAAG,CAAC,QAAQ,CAA2B;QAC/C,QAAQ,EAAG,GAAG,CAAC,UAAU,CAAmB,IAAI,IAAI;QACpD,OAAO,EAAE,cAAc,CAAC,GAAG,EAAE,UAAU,CAAC;KACxC,CAAA;AACF,CAAC;AAED;;;;;GAKG;AACH,KAAK,UAAU,YAAY,CAC1B,IAA2B,EAC3B,OAAe,EACf,MAAc;IAEd,IAAI,aAAa,GAAG,EAAE,CAAA;IACtB,IAAI,YAAY,GAAG,EAAE,CAAA;IAErB,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;QACxB,IAAI,aAAa,KAAK,EAAE,EAAE,CAAC;YAC1B,aAAa,GAAG,GAAG,CAAC,SAAS,CAAA;QAC9B,CAAC;QAED,YAAY,GAAG,GAAG,CAAC,SAAS,CAAA;IAC7B,CAAC;IAED,MAAM,gBAAgB,CAAC,IAAI,CAAC,GAAG,CAAC,YAAY,CAAC,EAAE,OAAO,CAAC,CAAA;IAEvD,MAAM,QAAQ,GAAG,MAAM,OAAO,CAAC,OAAO,CAAC,CAAA;IACvC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,OAAO,CAAC,CAAA;IAExC,OAAO;QACN,KAAK,EAAE,OAAO;QACd,IAAI,EAAE,OAAO;QACb,MAAM,EAAE,SAAS;QACjB,WAAW,EAAE,mBAAmB;QAChC,IAAI,EAAE,IAAI,CAAC,MAAM;QACjB,KAAK,EAAE,QAAQ,EAAE,IAAI,IAAI,CAAC;QAC1B,MAAM;QACN,eAAe,EAAE,aAAa;QAC9B,cAAc,EAAE,YAAY;QAC5B,kGAAkG;QAClG,MAAM;KACN,CAAA;AACF,CAAC;AAED,SAAS,oBAAoB,CAAC,IAAY,EAAE,YAAoB,EAAE,eAAuB;IACxF,IAAI,IAAI,CAAC,UAAU,CAAC,YAAY,CAAC;QAAE,OAAO,eAAe,GAAG,IAAI,CAAC,KAAK,CAAC,YAAY,CAAC,MAAM,CAAC,CAAA;IAE3F,OAAO,IAAI,CAAA;AACZ,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,oBAAoB,CACzC,OAA+B,EAC/B,MAA+B;IAE/B,MAAM,aAAa,GAAG,OAAO,CAAC,aAAa,IAAI,OAAO,CAAA;IACtD,+EAA+E;IAC/E,MAAM,mBAAmB,GAAG,OAAO,CAAC,mBAAmB,IAAI,QAAQ,CAAA;IACnE,MAAM,gBAAgB,GAAG,OAAO,CAAC,gBAAgB,IAAI,GAAG,YAAY,EAAE,GAAG,CAAA;IAEzE,IAAI,CAAC,CAAC,MAAM,UAAU,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC;QAAE,MAAM,IAAI,KAAK,CAAC,oBAAoB,OAAO,CAAC,KAAK,EAAE,CAAC,CAAA;IAE5F,IAAI,CAAC,CAAC,MAAM,UAAU,CAAC,OAAO,CAAC,YAAY,CAAC,CAAC;QAAE,MAAM,IAAI,KAAK,CAAC,4BAA4B,OAAO,CAAC,YAAY,EAAE,CAAC,CAAA;IAElH,MAAM,SAAS,GAAG,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC,mBAAmB,CAAC,aAAa,CAAC,CAAC,CAAA;IACtF,MAAM,QAAQ,GAAG,SAAS,CAAC,OAAO,CAAC,CAAA;IACnC,MAAM,eAAe,CAAC,QAAQ,CAAC,CAAA;IAE/B,mCAAmC;IACnC,+BAA+B;IAC/B,MAAM,OAAO,GAAG,IAAI,GAAG,EAAwB,CAAA;IAC/C,MAAM,UAAU,GAAa,EAAE,CAAA;IAC/B,IAAI,OAAO,GAAG,CAAC,CAAA;IAEf,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,eAAe,CAAC,SAAS,CAA0B,eAAe,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC;QAC5G,OAAO,EAAE,CAAA;QACT,MAAM,KAAK,GAAG,cAAc,CAAC,GAAG,EAAE,aAAa,CAAC,CAAA;QAChD,MAAM,MAAM,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAA;QAE9B,IAAI,MAAM,CAAC,IAAI,KAAK,SAAS,EAAE,CAAC;YAC/B,UAAU,CAAC,IAAI,CAAC,GAAG,KAAK,CAAC,SAAS,KAAK,MAAM,CAAC,GAAG,CAAC,MAAM,EAAE,CAAC,CAAA;YAE3D,SAAQ;QACT,CAAC;QAED,MAAM,MAAM,GAAG,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,MAAM,CAAC,CAAA;QAExC,IAAI,MAAM,EAAE,CAAC;YACZ,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,CAAA;QACxB,CAAC;aAAM,CAAC;YACP,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,MAAM,EAAE,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAA;QACxC,CAAC;IACF,CAAC;IAED,MAAM,EAAE,CAAC,QAAQ,OAAO,UAAU,UAAU,CAAC,MAAM,iBAAiB,OAAO,CAAC,IAAI,iBAAiB,CAAC,CAAA;IAElG,MAAM,QAAQ,GAA4B,EAAE,CAAA;IAC5C,MAAM,UAAU,GAAG,CAAC,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,QAAQ,EAAE,CAAA;IAEjD,KAAK,MAAM,MAAM,IAAI,UAAU,EAAE,CAAC;QACjC,MAAM,IAAI,GAAG,OAAO,CAAC,GAAG,CAAC,MAAM,CAAE,CAAA;QACjC,MAAM,IAAI,GAAG,MAAM,CAAC,UAAU,CAAC,oBAAoB,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,oBAAoB,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAA;QACzG,6CAA6C;QAC7C,MAAM,OAAO,GAAG,QAAQ,CAAC,iBAAiB,IAAI,UAAU,CAAC,CAAC,QAAQ,EAAE,CAAA;QACpE,MAAM,UAAU,GAAG,MAAM,YAAY,CAAC,IAAI,EAAE,OAAO,EAAE,MAAM,CAAC,CAAA;QAC5D,QAAQ,CAAC,IAAI,CAAC,UAAU,CAAC,CAAA;QACzB,MAAM,EAAE,CAAC,KAAK,MAAM,KAAK,UAAU,CAAC,IAAI,WAAW,OAAO,KAAK,UAAU,CAAC,KAAK,SAAS,CAAC,CAAA;IAC1F,CAAC;IAED,IAAI,UAAU,CAAC,MAAM,EAAE,CAAC;QACvB,MAAM,KAAK,GAAG,SAAS,CAAC,gCAAgC,CAAC,CAAA;QACzD,MAAM,kBAAkB,CAAC,UAAU,EAAE,KAAK,CAAC,CAAA;QAC3C,MAAM,EAAE,CAAC,oBAAoB,KAAK,KAAK,UAAU,CAAC,MAAM,QAAQ,CAAC,CAAA;IAClE,CAAC;IAED,uFAAuF;IACvF,qCAAqC;IACrC,6FAA6F;IAC7F,MAAM,IAAI,GAAG,MAAM,iBAAiB,CAAkB,OAAO,CAAC,YAAY,CAAC,CAAA;IAE3E,MAAM,aAAa,GAAG,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC;QAChD,GAAG,IAAI;QACP,IAAI,EAAE,oBAAoB,CAAC,IAAI,CAAC,IAAI,EAAE,gBAAgB,EAAE,mBAAmB,CAAC;KAC5E,CAAC,CAAC,CAAA;IAEH,MAAM,YAAY,GAAG,QAAQ,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,IAAI,EAAE,EAAE,CAAC,GAAG,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC,CAAC,CAAA;IAEvE,MAAM,QAAQ,GAAoB;QACjC,cAAc,EAAE,aAAa;QAC7B,MAAM,EAAE,eAAe;QACvB,cAAc,EAAE,IAAI,CAAC,cAAc;QACnC,cAAc,EAAE,IAAI,CAAC,cAAc,IAAI,cAAc;QACrD,MAAM,EAAE,CAAC,GAAG,aAAa,EAAE,GAAG,QAAQ,CAAC;QACvC,MAAM,EAAE;YACP,KAAK,EAAE,IAAI,CAAC,MAAM,CAAC,KAAK,GAAG,YAAY;YACvC,GAAG,EAAE,IAAI,CAAC,MAAM,CAAC,GAAG;YACpB,IAAI,EAAE,IAAI,CAAC,MAAM,CAAC,IAAI;SACtB;QACD,UAAU,EAAE,IAAI,CAAC,UAAU,GAAG,YAAY;KAC1C,CAAA;IAED,MAAM,YAAY,GAAG,SAAS,CAAC,eAAe,CAAC,CAAA;IAC/C,MAAM,kBAAkB,CAAC,QAAQ,EAAE,YAAY,CAAC,CAAA;IAChD,MAAM,EAAE,CAAC,6BAA6B,YAAY,EAAE,CAAC,CAAA;IACrD,MAAM,EAAE,CAAC,gBAAgB,QAAQ,CAAC,UAAU,UAAU,IAAI,CAAC,UAAU,WAAW,YAAY,GAAG,CAAC,CAAA;IAChG,MAAM,EAAE,CAAC,WAAW,QAAQ,CAAC,MAAM,CAAC,MAAM,UAAU,IAAI,CAAC,MAAM,CAAC,MAAM,WAAW,QAAQ,CAAC,MAAM,GAAG,CAAC,CAAA;IACpG,MAAM,EAAE,CAAC,iBAAiB,mBAAmB,EAAE,CAAC,CAAA;IAChD,MAAM,OAAO,GAAG,aAAa,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,KAAK,IAAI,CAAC,MAAM,CAAC,CAAC,CAAE,CAAC,IAAI,CAAC,CAAC,MAAM,CAAA;IAEtF,IAAI,OAAO,GAAG,CAAC,EAAE,CAAC;QACjB,MAAM,EAAE,CAAC,oCAAoC,OAAO,aAAa,gBAAgB,QAAQ,mBAAmB,IAAI,CAAC,CAAA;IAClH,CAAC;AACF,CAAC"}
|
|
@@ -3,110 +3,51 @@
|
|
|
3
3
|
* @license AGPL-3.0
|
|
4
4
|
* @author Teffen Ellis, et al.
|
|
5
5
|
*
|
|
6
|
-
*
|
|
7
|
-
*
|
|
8
|
-
* {@link SubVenueHarvestRow}s the lexicon builder consumes exactly like an OSM extract.
|
|
6
|
+
* Read selected Overture Places categories from `poi.db` and return candidate sub-venue names with
|
|
7
|
+
* country and category provenance.
|
|
9
8
|
*
|
|
10
|
-
*
|
|
11
|
-
*
|
|
12
|
-
* extract, 3 of which are a street called CONCOURSE WAY. Overture's `airport_terminal` category is
|
|
13
|
-
* curated venue-interior naming; OSM's `aeroway=terminal` is a building footprint that usually
|
|
14
|
-
* carries the AIRPORT's name. The two sources fail differently, so both are read.
|
|
15
|
-
*
|
|
16
|
-
* ── THE CATEGORY SET IS MEASURED, NOT GUESSED ────────────────────────────────────────────────────
|
|
17
|
-
* A full scan of all 13,681,698 rows (2026-08-05, poi.db vintage 2026-05-20.0) counted, per
|
|
18
|
-
* category, how many named rows carry a designator token. The ranking is NOT what a category name
|
|
19
|
-
* predicts — `gas_station` leads the whole table with 12,996 hits, every one of them the token
|
|
20
|
-
* `station` inside "Holiday Station" / "Chevron Station Seward", and `shoe_store` contributes 708
|
|
21
|
-
* hits of `wing` because Red Wing sells boots. {@link OVERTURE_SUBVENUE_CATEGORIES} is the four
|
|
22
|
-
* categories whose hits survived reading the distribution; the rejects are listed below it so nobody
|
|
23
|
-
* re-proposes them.
|
|
24
|
-
*
|
|
25
|
-
* ── poi.db IS FOUR COUNTRIES ─────────────────────────────────────────────────────────────────────
|
|
26
|
-
* Measured the same day: US 11,521,612 / CA 794,418 / FR 721,352 / MX 644,316, and nothing else. The
|
|
27
|
-
* shipped layer is not a world gazetteer, so Overture can attest en-US, en-CA, fr-FR and es-MX
|
|
28
|
-
* surfaces and NOTHING ELSE. Every non-Latin designator the corpus task asks for — `ターミナル`,
|
|
29
|
-
* `Halle`, `Flügel` — has to come from the OSM leg. Do not read a zero count here as evidence of
|
|
30
|
-
* absence in the world; it is evidence of absence in four countries.
|
|
31
|
-
*
|
|
32
|
-
* ── The row shape fits; the PROVENANCE STAMP did not ─────────────────────────────────────────────
|
|
33
|
-
* Wave 1's `OSMSubVenueRow` was written to accept a non-OSM row, and it does: an Overture row is
|
|
34
|
-
* `{ designatorID, name }` with no `ref` and no `localizedNames`. What did NOT fit is
|
|
35
|
-
* `extractAttestedPhrases`, which hardcoded `osm:name` as the surface's `source`. Feeding Overture
|
|
36
|
-
* rows through it unchanged would have labelled every Overture surface as OSM-attested — a
|
|
37
|
-
* provenance lie, and under ODbL a consequential one. Hence the `source`/`region` options on that
|
|
38
|
-
* function and the source-neutral {@link SubVenueHarvestRow} name.
|
|
9
|
+
* `poi.db` covers four countries — US, CA, FR and MX — so a zero count here is absence in four countries rather
|
|
10
|
+
* than evidence of absence in the world. Every non-Latin designator comes from the OSM leg.
|
|
39
11
|
*/
|
|
12
|
+
import type { PathBuilderLike } from "path-ts";
|
|
40
13
|
import type { SubVenueHarvestRow } from "#tools/sub/venue/lexicon";
|
|
41
14
|
/**
|
|
42
|
-
* Overture
|
|
43
|
-
*
|
|
44
|
-
* Each entry carries the 2026-08-05 full-scan measurement in a comment: `rows` is the category's total, `hits` is how
|
|
45
|
-
* many of its named rows contain any designator token, and the token list is the top of that distribution.
|
|
46
|
-
*
|
|
47
|
-
* REJECTED, with the number that rejected them — do not re-add without a fresh census:
|
|
48
|
-
*
|
|
49
|
-
* - `gas_station` (12,996 hits) — all `station` inside a brand name (Holiday Station, Chevron Station Seward).
|
|
50
|
-
* - `fire_station` (10,377) — same, plus 330 `hall` from fire halls, which are venues rather than sub-venues.
|
|
51
|
-
* - `town_hall` (5,528) — `City Hall` is a whole building, the `venue` tier, not interior structure.
|
|
52
|
-
* - `building_supply_store` (4,030) — `building` inside "Allied Building Products".
|
|
53
|
-
* - `jehovahs_witness_place_of_worship` (2,334) — every hit is "Kingdom Hall of Jehovah's Witnesses".
|
|
54
|
-
* - `shoe_store` (909, of which 708 `wing`) — Red Wing. This one is a CONFOUND BOARD entry, not a source.
|
|
55
|
-
* - `college_university` (3,697) — 2,082 `campus`, but the row names the whole institution; `campus_building` is the
|
|
56
|
-
* interior slice and is kept instead.
|
|
57
|
-
* - `airport` (6,000 rows, 4,302 hits) — 4,071 of them are the token `airport` in the aerodrome's own name. Venue tier,
|
|
58
|
-
* already covered by OurAirports, and it drowns the interior signal.
|
|
59
|
-
* - `transport_interchange` (1 row), `rail_facility_or_service` (81 rows, 2 hits) — too small to matter.
|
|
60
|
-
* - `public_transit_facility_or_service` (2,274 rows, 185 hits) — 161 are `station` naming the station itself.
|
|
15
|
+
* Overture categories selected for sub-venue designator evidence.
|
|
61
16
|
*/
|
|
62
17
|
export declare const OVERTURE_SUBVENUE_CATEGORIES: Readonly<Record<string, string>>;
|
|
63
18
|
/**
|
|
64
|
-
*
|
|
65
|
-
* `sources[]`.
|
|
66
|
-
*
|
|
67
|
-
* Read off the database rather than passed in, because a vintage a caller types is a vintage that goes stale silently.
|
|
68
|
-
* The layer-contract tables are part of every layer database by construction — see `docs/engineering/reference/
|
|
69
|
-
* layer-contract.mdx` — so there is no version of poi.db where this is absent.
|
|
19
|
+
* Read the Overture release recorded in the POI layer manifest.
|
|
70
20
|
*/
|
|
71
|
-
export declare function readOvertureLayerVintage(databasePath:
|
|
21
|
+
export declare function readOvertureLayerVintage(databasePath: PathBuilderLike): Promise<string>;
|
|
72
22
|
export interface ReadOvertureSubVenuesOptions {
|
|
73
23
|
/**
|
|
74
|
-
* Path to `poi.db`.
|
|
24
|
+
* Path to `poi.db`.
|
|
75
25
|
*/
|
|
76
|
-
databasePath:
|
|
26
|
+
databasePath: PathBuilderLike;
|
|
77
27
|
/**
|
|
78
|
-
* Category
|
|
28
|
+
* Category-to-designator mapping.
|
|
79
29
|
*/
|
|
80
30
|
categories?: Readonly<Record<string, string>>;
|
|
81
31
|
/**
|
|
82
|
-
*
|
|
32
|
+
* Optional ISO alpha-2 country filter.
|
|
83
33
|
*/
|
|
84
34
|
countries?: readonly string[];
|
|
85
35
|
}
|
|
86
36
|
/**
|
|
87
|
-
*
|
|
88
|
-
* OSM extract does not (a Geofabrik extract's country is a property of the invocation, so OSM rows carry `country:
|
|
89
|
-
* ""`).
|
|
37
|
+
* Overture sub-venue row with its country and category provenance.
|
|
90
38
|
*/
|
|
91
39
|
export interface OvertureSubVenueRow extends SubVenueHarvestRow {
|
|
92
40
|
/**
|
|
93
|
-
* ISO
|
|
41
|
+
* ISO alpha-2 code from the Overture partition.
|
|
94
42
|
*/
|
|
95
43
|
country: string;
|
|
96
44
|
/**
|
|
97
|
-
*
|
|
45
|
+
* Overture category used to select the row.
|
|
98
46
|
*/
|
|
99
47
|
category: string;
|
|
100
48
|
}
|
|
101
49
|
/**
|
|
102
|
-
* Read
|
|
103
|
-
*
|
|
104
|
-
* Cold path, already async, no interface constraint — so Kysely, per the repo's inline-SQL rule.
|
|
105
|
-
*
|
|
106
|
-
* `category_id` is the SECOND component of poi.db's clustered `(h3_cell, category_id, …)` primary key, which reads like
|
|
107
|
-
* a full 13.7M-row scan and is not one: SQLite skip-scans the leading `h3_cell` and the whole four-category read
|
|
108
|
-
* returned 9,219 rows in **1.4 s** on the shipped layer (2026-08-05). A JS-side scan of every row to survey the same
|
|
109
|
-
* question took 52 s, which is the number to remember if you are tempted to filter in JS instead.
|
|
50
|
+
* Read POI rows with names in selected sub-venue categories, optionally filtered by country.
|
|
110
51
|
*/
|
|
111
52
|
export declare function readOvertureSubVenues(options: ReadOvertureSubVenuesOptions): Promise<OvertureSubVenueRow[]>;
|
|
112
53
|
//# sourceMappingURL=overture-subvenue.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"overture-subvenue.d.ts","sourceRoot":"","sources":["../../lib/tools/overture-subvenue.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"overture-subvenue.d.ts","sourceRoot":"","sources":["../../lib/tools/overture-subvenue.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;GAUG;AAGH,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,SAAS,CAAA;AAE9C,OAAO,KAAK,EAAE,kBAAkB,EAAE,MAAM,0BAA0B,CAAA;AAElE;;GAEG;AACH,eAAO,MAAM,4BAA4B,EAAE,QAAQ,CAAC,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAKzE,CAAA;AAqBD;;GAEG;AACH,wBAAsB,wBAAwB,CAAC,YAAY,EAAE,eAAe,GAAG,OAAO,CAAC,MAAM,CAAC,CAU7F;AAED,MAAM,WAAW,4BAA4B;IAC5C;;OAEG;IACH,YAAY,EAAE,eAAe,CAAA;IAC7B;;OAEG;IACH,UAAU,CAAC,EAAE,QAAQ,CAAC,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC,CAAA;IAC7C;;OAEG;IACH,SAAS,CAAC,EAAE,SAAS,MAAM,EAAE,CAAA;CAC7B;AAED;;GAEG;AACH,MAAM,WAAW,mBAAoB,SAAQ,kBAAkB;IAC9D;;OAEG;IACH,OAAO,EAAE,MAAM,CAAA;IACf;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAA;CAChB;AAED;;GAEG;AACH,wBAAsB,qBAAqB,CAAC,OAAO,EAAE,4BAA4B,GAAG,OAAO,CAAC,mBAAmB,EAAE,CAAC,CA0CjH"}
|
|
@@ -3,84 +3,24 @@
|
|
|
3
3
|
* @license AGPL-3.0
|
|
4
4
|
* @author Teffen Ellis, et al.
|
|
5
5
|
*
|
|
6
|
-
*
|
|
7
|
-
*
|
|
8
|
-
* {@link SubVenueHarvestRow}s the lexicon builder consumes exactly like an OSM extract.
|
|
6
|
+
* Read selected Overture Places categories from `poi.db` and return candidate sub-venue names with
|
|
7
|
+
* country and category provenance.
|
|
9
8
|
*
|
|
10
|
-
*
|
|
11
|
-
*
|
|
12
|
-
* extract, 3 of which are a street called CONCOURSE WAY. Overture's `airport_terminal` category is
|
|
13
|
-
* curated venue-interior naming; OSM's `aeroway=terminal` is a building footprint that usually
|
|
14
|
-
* carries the AIRPORT's name. The two sources fail differently, so both are read.
|
|
15
|
-
*
|
|
16
|
-
* ── THE CATEGORY SET IS MEASURED, NOT GUESSED ────────────────────────────────────────────────────
|
|
17
|
-
* A full scan of all 13,681,698 rows (2026-08-05, poi.db vintage 2026-05-20.0) counted, per
|
|
18
|
-
* category, how many named rows carry a designator token. The ranking is NOT what a category name
|
|
19
|
-
* predicts — `gas_station` leads the whole table with 12,996 hits, every one of them the token
|
|
20
|
-
* `station` inside "Holiday Station" / "Chevron Station Seward", and `shoe_store` contributes 708
|
|
21
|
-
* hits of `wing` because Red Wing sells boots. {@link OVERTURE_SUBVENUE_CATEGORIES} is the four
|
|
22
|
-
* categories whose hits survived reading the distribution; the rejects are listed below it so nobody
|
|
23
|
-
* re-proposes them.
|
|
24
|
-
*
|
|
25
|
-
* ── poi.db IS FOUR COUNTRIES ─────────────────────────────────────────────────────────────────────
|
|
26
|
-
* Measured the same day: US 11,521,612 / CA 794,418 / FR 721,352 / MX 644,316, and nothing else. The
|
|
27
|
-
* shipped layer is not a world gazetteer, so Overture can attest en-US, en-CA, fr-FR and es-MX
|
|
28
|
-
* surfaces and NOTHING ELSE. Every non-Latin designator the corpus task asks for — `ターミナル`,
|
|
29
|
-
* `Halle`, `Flügel` — has to come from the OSM leg. Do not read a zero count here as evidence of
|
|
30
|
-
* absence in the world; it is evidence of absence in four countries.
|
|
31
|
-
*
|
|
32
|
-
* ── The row shape fits; the PROVENANCE STAMP did not ─────────────────────────────────────────────
|
|
33
|
-
* Wave 1's `OSMSubVenueRow` was written to accept a non-OSM row, and it does: an Overture row is
|
|
34
|
-
* `{ designatorID, name }` with no `ref` and no `localizedNames`. What did NOT fit is
|
|
35
|
-
* `extractAttestedPhrases`, which hardcoded `osm:name` as the surface's `source`. Feeding Overture
|
|
36
|
-
* rows through it unchanged would have labelled every Overture surface as OSM-attested — a
|
|
37
|
-
* provenance lie, and under ODbL a consequential one. Hence the `source`/`region` options on that
|
|
38
|
-
* function and the source-neutral {@link SubVenueHarvestRow} name.
|
|
9
|
+
* `poi.db` covers four countries — US, CA, FR and MX — so a zero count here is absence in four countries rather
|
|
10
|
+
* than evidence of absence in the world. Every non-Latin designator comes from the OSM leg.
|
|
39
11
|
*/
|
|
40
12
|
import { DatabaseClient } from "@mailwoman/sqlite/client";
|
|
41
13
|
/**
|
|
42
|
-
* Overture
|
|
43
|
-
*
|
|
44
|
-
* Each entry carries the 2026-08-05 full-scan measurement in a comment: `rows` is the category's total, `hits` is how
|
|
45
|
-
* many of its named rows contain any designator token, and the token list is the top of that distribution.
|
|
46
|
-
*
|
|
47
|
-
* REJECTED, with the number that rejected them — do not re-add without a fresh census:
|
|
48
|
-
*
|
|
49
|
-
* - `gas_station` (12,996 hits) — all `station` inside a brand name (Holiday Station, Chevron Station Seward).
|
|
50
|
-
* - `fire_station` (10,377) — same, plus 330 `hall` from fire halls, which are venues rather than sub-venues.
|
|
51
|
-
* - `town_hall` (5,528) — `City Hall` is a whole building, the `venue` tier, not interior structure.
|
|
52
|
-
* - `building_supply_store` (4,030) — `building` inside "Allied Building Products".
|
|
53
|
-
* - `jehovahs_witness_place_of_worship` (2,334) — every hit is "Kingdom Hall of Jehovah's Witnesses".
|
|
54
|
-
* - `shoe_store` (909, of which 708 `wing`) — Red Wing. This one is a CONFOUND BOARD entry, not a source.
|
|
55
|
-
* - `college_university` (3,697) — 2,082 `campus`, but the row names the whole institution; `campus_building` is the
|
|
56
|
-
* interior slice and is kept instead.
|
|
57
|
-
* - `airport` (6,000 rows, 4,302 hits) — 4,071 of them are the token `airport` in the aerodrome's own name. Venue tier,
|
|
58
|
-
* already covered by OurAirports, and it drowns the interior signal.
|
|
59
|
-
* - `transport_interchange` (1 row), `rail_facility_or_service` (81 rows, 2 hits) — too small to matter.
|
|
60
|
-
* - `public_transit_facility_or_service` (2,274 rows, 185 hits) — 161 are `station` naming the station itself.
|
|
14
|
+
* Overture categories selected for sub-venue designator evidence.
|
|
61
15
|
*/
|
|
62
16
|
export const OVERTURE_SUBVENUE_CATEGORIES = {
|
|
63
|
-
// 1,022 rows / 669 hits — terminal 266, concourse 19, gate 13, hall 4. The densest interior naming
|
|
64
|
-
// in the layer and the reason this reader exists.
|
|
65
17
|
airport_terminal: "terminal",
|
|
66
|
-
// 7,366 rows / 3,382 hits — hall 2,134, building 1,019, campus 209. US academic halls and numbered
|
|
67
|
-
// campus buildings: "UAA Cuddy Hall", "UAA Science Building". The row is a building ON a campus, so
|
|
68
|
-
// `campus` is its CONTEXT designator; the phrase found inside the name decides the record it
|
|
69
|
-
// attests, which for these rows is mostly `hall`.
|
|
70
18
|
campus_building: "campus",
|
|
71
|
-
// 443 rows / 301 hits — pier 282, terminal 17.
|
|
72
19
|
pier: "pier",
|
|
73
|
-
// 388 rows / 66 hits — airport 36, terminal 20, concourse 5, gate 3. Small, but the hits are almost
|
|
74
|
-
// all genuine ("Delta Sky Club Concourse B").
|
|
75
20
|
airport_lounge: "terminal",
|
|
76
21
|
};
|
|
77
22
|
/**
|
|
78
|
-
*
|
|
79
|
-
* `sources[]`.
|
|
80
|
-
*
|
|
81
|
-
* Read off the database rather than passed in, because a vintage a caller types is a vintage that goes stale silently.
|
|
82
|
-
* The layer-contract tables are part of every layer database by construction — see `docs/engineering/reference/
|
|
83
|
-
* layer-contract.mdx` — so there is no version of poi.db where this is absent.
|
|
23
|
+
* Read the Overture release recorded in the POI layer manifest.
|
|
84
24
|
*/
|
|
85
25
|
export async function readOvertureLayerVintage(databasePath) {
|
|
86
26
|
using kdb = new DatabaseClient(databasePath, { readOnly: true });
|
|
@@ -92,14 +32,7 @@ export async function readOvertureLayerVintage(databasePath) {
|
|
|
92
32
|
return row?.source_vintage ?? "";
|
|
93
33
|
}
|
|
94
34
|
/**
|
|
95
|
-
* Read
|
|
96
|
-
*
|
|
97
|
-
* Cold path, already async, no interface constraint — so Kysely, per the repo's inline-SQL rule.
|
|
98
|
-
*
|
|
99
|
-
* `category_id` is the SECOND component of poi.db's clustered `(h3_cell, category_id, …)` primary key, which reads like
|
|
100
|
-
* a full 13.7M-row scan and is not one: SQLite skip-scans the leading `h3_cell` and the whole four-category read
|
|
101
|
-
* returned 9,219 rows in **1.4 s** on the shipped layer (2026-08-05). A JS-side scan of every row to survey the same
|
|
102
|
-
* question took 52 s, which is the number to remember if you are tempted to filter in JS instead.
|
|
35
|
+
* Read POI rows with names in selected sub-venue categories, optionally filtered by country.
|
|
103
36
|
*/
|
|
104
37
|
export async function readOvertureSubVenues(options) {
|
|
105
38
|
const categories = options.categories ?? OVERTURE_SUBVENUE_CATEGORIES;
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"overture-subvenue.js","sourceRoot":"","sources":["../../lib/tools/overture-subvenue.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"overture-subvenue.js","sourceRoot":"","sources":["../../lib/tools/overture-subvenue.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;GAUG;AAEH,OAAO,EAAE,cAAc,EAAE,MAAM,0BAA0B,CAAA;AAKzD;;GAEG;AACH,MAAM,CAAC,MAAM,4BAA4B,GAAqC;IAC7E,gBAAgB,EAAE,UAAU;IAC5B,eAAe,EAAE,QAAQ;IACzB,IAAI,EAAE,MAAM;IACZ,cAAc,EAAE,UAAU;CAC1B,CAAA;AAqBD;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,wBAAwB,CAAC,YAA6B;IAC3E,MAAM,GAAG,GAAG,IAAI,cAAc,CAAkB,YAAY,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAA;IAEjF,MAAM,GAAG,GAAG,MAAM,GAAG;SACnB,UAAU,CAAC,gBAAgB,CAAC;SAC5B,MAAM,CAAC,gBAAgB,CAAC;SACxB,KAAK,CAAC,MAAM,EAAE,GAAG,EAAE,KAAK,CAAC;SACzB,gBAAgB,EAAE,CAAA;IAEpB,OAAO,GAAG,EAAE,cAAc,IAAI,EAAE,CAAA;AACjC,CAAC;AA+BD;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,qBAAqB,CAAC,OAAqC;IAChF,MAAM,UAAU,GAAG,OAAO,CAAC,UAAU,IAAI,4BAA4B,CAAA;IAErE,MAAM,GAAG,GAAG,IAAI,cAAc,CAAkB,OAAO,CAAC,YAAY,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAA;IAEzF,MAAM,KAAK,GAAG,MAAM,GAAG;SACrB,UAAU,CAAC,oBAAoB,CAAC;SAChC,MAAM,CAAC,CAAC,IAAI,EAAE,UAAU,CAAC,CAAC;SAC1B,KAAK,CAAC,UAAU,EAAE,IAAI,EAAE,MAAM,CAAC,IAAI,CAAC,UAAU,CAAC,CAAC;SAChD,OAAO,EAAE,CAAA;IAEX,IAAI,CAAC,KAAK,CAAC,MAAM;QAAE,OAAO,EAAE,CAAA;IAE5B,MAAM,cAAc,GAAG,IAAI,GAAG,EAAkB,CAAA;IAChD,MAAM,YAAY,GAAG,IAAI,GAAG,EAAkB,CAAA;IAE9C,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QAC1B,MAAM,UAAU,GAAG,UAAU,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAA;QAE5C,IAAI,CAAC,UAAU;YAAE,SAAQ;QACzB,cAAc,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,EAAE,UAAU,CAAC,CAAA;QACvC,YAAY,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,EAAE,IAAI,CAAC,QAAQ,CAAC,CAAA;IACzC,CAAC;IAED,IAAI,KAAK,GAAG,GAAG;SACb,UAAU,CAAC,KAAK,CAAC;SACjB,MAAM,CAAC,CAAC,aAAa,EAAE,MAAM,EAAE,SAAS,CAAC,CAAC;SAC1C,KAAK,CAAC,aAAa,EAAE,IAAI,EAAE,CAAC,GAAG,cAAc,CAAC,IAAI,EAAE,CAAC,CAAC;SACtD,KAAK,CAAC,MAAM,EAAE,QAAQ,EAAE,IAAI,CAAC,CAAA;IAE/B,IAAI,OAAO,CAAC,SAAS,EAAE,MAAM,EAAE,CAAC;QAC/B,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,SAAS,EAAE,IAAI,EAAE,CAAC,GAAG,OAAO,CAAC,SAAS,CAAC,CAAC,CAAA;IAC7D,CAAC;IAED,MAAM,IAAI,GAAG,MAAM,KAAK,CAAC,OAAO,EAAE,CAAA;IAElC,OAAO,IAAI,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,CAAC;QACzB,YAAY,EAAE,cAAc,CAAC,GAAG,CAAC,GAAG,CAAC,WAAW,CAAE;QAClD,IAAI,EAAE,GAAG,CAAC,IAAI;QACd,OAAO,EAAE,GAAG,CAAC,OAAO;QACpB,QAAQ,EAAE,YAAY,CAAC,GAAG,CAAC,GAAG,CAAC,WAAW,CAAE;KAC5C,CAAC,CAAC,CAAA;AACJ,CAAC"}
|