@mailwoman/corpus 10.0.0 → 10.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +120 -34
- package/data/PROVENANCE.md +623 -17
- package/data/address-source-register.json +14249 -0
- package/data/builds/v0.7.0-de-holdout/inputs.json +22 -0
- package/data/builds/v0.8.0-registers/inputs.json +92 -0
- package/data/license-decisions.json +1603 -0
- package/data/licenses/PROVENANCE.md +65 -0
- package/data/licenses/cdla-permissive-2.0.md +43 -0
- package/data/licenses/geonames-publication.md +34 -0
- package/data/licenses/licence-ouverte-2.0.md +36 -0
- package/data/licenses/national-address-database.md +46 -0
- package/data/licenses/nlod-2.0.md +90 -0
- package/data/licenses/sirene-publication.md +38 -0
- package/data/licenses/whosonfirst-licenses.md +65 -0
- package/data/source-resolutions.json +804 -0
- package/data/sub-venue-lexicon.json +1 -1
- package/data/training-manifests/v0.7.0-de-holdout.effective.json +477 -0
- package/data/training-manifests/v0.7.0-de-holdout.json +78 -0
- package/lib/adapters/cordis/adapter.ts +791 -0
- package/lib/adapters/dedup-key.ts +40 -0
- package/lib/adapters/errors.ts +21 -0
- package/lib/adapters/geonames/adapter.ts +43 -53
- package/lib/adapters/geonames/postal/adapter.ts +31 -37
- package/lib/adapters/gleif/adapter.ts +829 -0
- package/lib/adapters/libpostal-dictionary.ts +37 -0
- package/lib/adapters/openaddresses/adapter.ts +52 -55
- package/lib/adapters/osm/adapter.ts +162 -83
- package/lib/adapters/overture/adapter.ts +52 -43
- package/lib/adapters/po-box/adapter.ts +207 -0
- package/lib/adapters/registry.ts +79 -0
- package/lib/adapters/sha256-stream.ts +49 -0
- package/lib/adapters/source-id.ts +49 -0
- package/lib/adapters/street-line.ts +136 -0
- package/lib/adapters/wof/admin/json/adapter.ts +50 -35
- package/lib/adapters/wof/json-rows.ts +57 -26
- package/lib/adapters/wof/postalcode-json/adapter.ts +63 -61
- package/lib/adapters.ts +230 -0
- package/lib/au/adapters/gnaf/adapter.ts +36 -44
- package/lib/au/adapters/gnaf/assemble.ts +31 -51
- package/lib/be/adapters/brussels/adapter.ts +566 -0
- package/lib/be/adapters/vlaanderen/adapter.ts +667 -0
- package/lib/be/adapters/wallonie/adapter.ts +537 -0
- package/lib/be/tools/fetch/brussels.ts +242 -0
- package/lib/be/tools/fetch/wallonie.ts +275 -0
- package/lib/build/adapters.ts +111 -0
- package/lib/build/align.ts +365 -0
- package/lib/build/checkpoint.ts +133 -0
- package/lib/build/eligibility.ts +96 -0
- package/lib/build/heap.ts +53 -0
- package/lib/build/inputs.ts +81 -0
- package/lib/build/rows.ts +21 -0
- package/lib/build/types.ts +234 -0
- package/lib/build.ts +127 -315
- package/lib/cn/recipes/organizational-units.ts +20 -41
- package/lib/cz/adapters/cuzk/adapter.ts +320 -0
- package/lib/cz/recipes/pcfirst-preposition.ts +40 -27
- package/lib/cz/tools/fetch/cuzk.ts +710 -0
- package/lib/de/recipes/locale.ts +69 -59
- package/lib/directory.ts +31 -0
- package/lib/dk/adapters/inspire/adapter.ts +345 -0
- package/lib/dk/tools/fetch/inspire.ts +323 -0
- package/lib/ee/adapters/ads/adapter.ts +240 -0
- package/lib/ee/tools/fetch/ads.ts +272 -0
- package/lib/env.ts +6 -2
- package/lib/es/adapters/bizkaia/adapter.ts +388 -0
- package/lib/es/adapters/catastro/adapter.ts +345 -0
- package/lib/es/adapters/gipuzkoa/adapter.ts +256 -0
- package/lib/es/adapters/navarra/adapter.ts +290 -0
- package/lib/es/cadastre.ts +194 -0
- package/lib/es/tools/fetch/bizkaia.ts +752 -0
- package/lib/es/tools/fetch/catastro.ts +765 -0
- package/lib/es/tools/fetch/gipuzkoa.ts +338 -0
- package/lib/es/tools/fetch/navarra.ts +496 -0
- package/lib/fi/adapters/ryhti/adapter.ts +319 -0
- package/lib/fi/tools/fetch/ryhti.ts +476 -0
- package/lib/fingerprints.ts +154 -0
- package/lib/fr/adapters/annuaire-education/adapter.ts +600 -0
- package/lib/fr/adapters/ban/adapter.ts +87 -59
- package/lib/fr/adapters/finess/adapter.ts +619 -0
- package/lib/fr/adapters/finess/postal-lines.ts +157 -0
- package/lib/fr/adapters/finess/voie-type.ts +201 -0
- package/lib/fr/insee-country.ts +62 -0
- package/lib/fr/recipes/admin-split.ts +38 -60
- package/lib/fr/recipes/bare-street.ts +37 -50
- package/lib/fr/recipes/fragment.ts +59 -142
- package/lib/fr/recipes/lieudit.ts +111 -73
- package/lib/fr/recipes/order.ts +32 -59
- package/lib/fr/{adapters/ban/street-decompose.ts → street-decompose.ts} +4 -3
- package/lib/fr/tools/fetch/annuaire-education.ts +309 -0
- package/lib/fr/tools/fetch/ban.ts +30 -20
- package/lib/fr/tools/fetch/finess.ts +353 -0
- package/lib/gauntlet-inputs.ts +92 -0
- package/lib/index.ts +9 -3
- package/lib/inspire/address.ts +465 -0
- package/lib/inspire/archive.ts +44 -0
- package/lib/inspire/errors.ts +72 -0
- package/lib/inspire/stream.ts +265 -0
- package/lib/international/recipes/locale.ts +146 -184
- package/lib/it/adapters/anac/adapter.ts +527 -0
- package/lib/it/tools/fetch/anac.ts +391 -0
- package/lib/jp/adapters/wof-admin/adapter.ts +29 -23
- package/lib/jp/tools/fetch/houjin.ts +19 -21
- package/lib/kr/adapters/juso/label-rows.ts +24 -44
- package/lib/kr/adapters/localdata/align.ts +20 -31
- package/lib/kr/adapters/localdata/key-index.ts +17 -25
- package/lib/kr/adapters/localdata/permit-rows.ts +34 -27
- package/lib/kr/tools/fetch/juso.ts +19 -21
- package/lib/kr/tools/fetch/localdata.ts +29 -30
- package/lib/lu/adapters/bd-adresses/adapter.ts +240 -0
- package/lib/lu/tools/fetch/bd-adresses.ts +353 -0
- package/lib/lv/adapters/varis/adapter.ts +500 -0
- package/lib/lv/tools/fetch/varis.ts +215 -0
- package/lib/nl/adapters/kadaster/adapter.ts +386 -0
- package/lib/nl/recipes/postcode.ts +46 -24
- package/lib/nl/tools/fetch/kadaster.ts +302 -0
- package/lib/no/adapters/matrikkelen/adapter.ts +188 -0
- package/lib/no/recipes/fragment.ts +34 -58
- package/lib/no/recipes/street/led.ts +44 -25
- package/lib/no/recipes/{street/index.ts → street.ts} +29 -11
- package/lib/no/tools/fetch/matrikkelen.ts +531 -0
- package/lib/parquet/duckdb.ts +147 -0
- package/lib/parquet/readers.ts +86 -0
- package/lib/parquet/schema.ts +214 -0
- package/lib/parquet/shuffle.ts +59 -0
- package/lib/parquet/span-sql.ts +54 -0
- package/lib/parquet/streams.ts +113 -0
- package/lib/parquet/writers.ts +452 -0
- package/lib/pl/adapters/emuia/adapter.ts +202 -0
- package/lib/pl/tools/fetch/emuia.ts +361 -0
- package/lib/recipes/anchor-absorption.ts +30 -19
- package/lib/recipes/bare/country.ts +24 -32
- package/lib/recipes/bare/postcode/eval.ts +1 -1
- package/lib/recipes/bare/postcode.ts +346 -0
- package/lib/recipes/boundary-stress.ts +37 -20
- package/lib/recipes/country-balanced.ts +66 -86
- package/lib/recipes/house-venue.ts +36 -14
- package/lib/recipes/intersection.ts +84 -62
- package/lib/recipes/po/box/cedex/au-nz.ts +3 -3
- package/lib/recipes/po/box/cedex/ca.ts +3 -2
- package/lib/recipes/po/box/cedex/fr.ts +4 -3
- package/lib/recipes/po/box/cedex/phrases.ts +7 -6
- package/lib/recipes/po/box/cedex/recipe.ts +31 -19
- package/lib/recipes/po/box/cedex/sources.ts +16 -4
- package/lib/recipes/po/box/cedex/us.ts +7 -2
- package/lib/recipes/po/{box/index.ts → box.ts} +39 -18
- package/lib/recipes/scaffold.ts +267 -158
- package/lib/recipes/sources.ts +412 -0
- package/lib/recipes/street/affix.ts +54 -154
- package/lib/recipes/street/bare.ts +30 -17
- package/lib/recipes/street.ts +35 -9
- package/lib/recipes/sub/venue/context.ts +32 -23
- package/lib/recipes/sub/venue/render.ts +170 -0
- package/lib/recipes/sub/venue/sources.ts +92 -248
- package/lib/recipes/sub/venue.ts +795 -0
- package/lib/recipes/trailing-region.ts +75 -87
- package/lib/recipes/unit/sources.ts +44 -0
- package/lib/recipes/unit.ts +101 -89
- package/lib/recipes/venue.ts +347 -0
- package/lib/{recipes/index.ts → recipes.ts} +15 -11
- package/lib/registers.ts +280 -0
- package/lib/ro/adapters/retea-scolara/adapter.ts +264 -0
- package/lib/ro/tools/fetch/retea-scolara.ts +187 -0
- package/lib/runner.ts +221 -84
- package/lib/sg/recipes/register.ts +47 -53
- package/lib/sg/tools/fetch/acra.ts +23 -28
- package/lib/si/recipes/bare-village.ts +34 -17
- package/lib/sk/adapters/inspire/adapter.ts +393 -0
- package/lib/sk/tools/fetch/inspire.ts +403 -0
- package/lib/source-register/effective-manifest.ts +659 -0
- package/lib/source-register/register.ts +539 -0
- package/lib/source-register/training-manifest.ts +218 -0
- package/lib/source-register/types.ts +589 -0
- package/lib/source-register.ts +71 -0
- package/lib/south-asia/recipes/register.ts +45 -26
- package/lib/subvenue/harvest.ts +251 -0
- package/lib/{tools/sub/venue → subvenue}/promotions.ts +33 -70
- package/lib/subvenue/surfaces.ts +94 -0
- package/lib/subvenue/table.ts +264 -0
- package/lib/surfaces/locale.ts +248 -0
- package/lib/synthesizers/anchor-absorption.ts +56 -91
- package/lib/synthesizers/boundary-stress.ts +67 -155
- package/lib/synthesizers/house-venue.ts +65 -127
- package/lib/synthesizers/no-street.ts +71 -119
- package/lib/synthesizers/po-box.ts +93 -105
- package/lib/synthesizers/tail.ts +55 -0
- package/lib/synthesizers/utils.ts +82 -219
- package/lib/test-kit/corpus-recipe.ts +45 -28
- package/lib/test-kit.ts +116 -0
- package/lib/tools/align-canonical.ts +64 -0
- package/lib/tools/audit.ts +117 -120
- package/lib/tools/corpus-stats.ts +45 -31
- package/lib/tools/fetch/atom.ts +164 -0
- package/lib/tools/fetch/cordis.ts +320 -0
- package/lib/tools/fetch/download/manifest.ts +36 -23
- package/lib/tools/fetch/download/network.ts +55 -31
- package/lib/tools/fetch/download/retry.ts +30 -29
- package/lib/tools/fetch/geonames/dump.ts +75 -55
- package/lib/tools/fetch/geonames/postal.ts +27 -62
- package/lib/tools/fetch/gleif.ts +362 -0
- package/lib/tools/fetch/header.ts +71 -0
- package/lib/tools/fetch/inspire-addresses.ts +500 -0
- package/lib/tools/fetch/openaddresses.ts +23 -112
- package/lib/tools/fetch/ourairports.ts +18 -51
- package/lib/tools/fetch/ppd.ts +10 -8
- package/lib/tools/fetch/vlaanderen-ad.ts +435 -0
- package/lib/tools/fetch/wfs-harvest.ts +954 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +45 -145
- package/lib/tools/fetch/zip-archive.ts +100 -0
- package/lib/tools/fetch.ts +101 -0
- package/lib/tools/golden/expand.ts +75 -44
- package/lib/tools/golden/promote.ts +47 -34
- package/lib/tools/golden/relabel-street/directory.ts +67 -39
- package/lib/tools/golden/relabel-street/row.ts +32 -109
- package/lib/tools/ingest-csv.ts +48 -51
- package/lib/tools/jsonl-to-parquet.ts +59 -98
- package/lib/tools/lint/recipe-output/vocab.ts +371 -0
- package/lib/tools/lint/{slice/index.ts → recipe-output.ts} +130 -126
- package/lib/tools/migrate/overlay-parquet.ts +173 -0
- package/lib/tools/migrate/recipe-output.ts +153 -0
- package/lib/tools/migrate/source-names.ts +161 -0
- package/lib/tools/{slice → overlay}/kryptonite.ts +47 -39
- package/lib/tools/overlay/manifest.ts +409 -0
- package/lib/tools/overlay/merge-source.ts +139 -0
- package/lib/tools/overlay/split-slice.ts +144 -0
- package/lib/tools/overlay/translit.ts +236 -0
- package/lib/tools/overture-subvenue.ts +18 -91
- package/lib/tools/postcode-triples.ts +284 -212
- package/lib/tools/source-register/build.ts +822 -0
- package/lib/tools/sub/venue/head-nouns.ts +38 -75
- package/lib/tools/sub/venue/lexicon.ts +71 -110
- package/lib/tools/sub/venue/wikidata.ts +13 -10
- package/lib/tw/tools/fetch/gcis.ts +21 -20
- package/lib/types.ts +305 -101
- package/lib/us/adapters/fcc-bdc/adapter.ts +26 -41
- package/lib/us/adapters/state/hi-schools/adapter.ts +28 -17
- package/lib/us/adapters/state/hi-schools/workbook.ts +8 -3
- package/lib/us/adapters/state/ia-contractors/adapter.ts +27 -15
- package/lib/us/adapters/state/ny-notaries/adapter.ts +24 -25
- package/lib/us/adapters/state/tx-notaries/adapter.ts +21 -15
- package/lib/us/adapters/tiger/adapter.ts +19 -44
- package/lib/us/adapters/tiger/street-decompose.ts +7 -17
- package/lib/us/adapters/usgov/hrsa-fqhc/adapter.ts +49 -34
- package/lib/us/adapters/usgov/imls-pls/adapter.ts +25 -19
- package/lib/us/adapters/usgov/irs-bmf/adapter.ts +32 -23
- package/lib/us/adapters/usgov/nad/adapter.ts +61 -122
- package/lib/us/adapters/usgov/nppes/adapter.ts +72 -35
- package/lib/us/adapters/usgov/samhsa-treatment-locator/adapter.ts +47 -34
- package/lib/us/fips-state.ts +19 -10
- package/lib/{synthesizers → us/synthesizers}/intersection.ts +45 -35
- package/lib/{synthesizers → us/synthesizers}/street.ts +56 -43
- package/lib/us/tools/fetch/hrsa.ts +7 -8
- package/lib/us/tools/fetch/imls-pls.ts +18 -36
- package/lib/us/tools/fetch/nad.ts +51 -33
- package/lib/us/tools/fetch/nppes.ts +27 -39
- package/lib/us/tools/fetch/state/hi-schools.ts +24 -17
- package/lib/us/tools/fetch/state/sources.ts +12 -12
- package/lib/us/tools/fetch/tiger-full.ts +22 -74
- package/lib/utils/align.ts +52 -59
- package/lib/utils/{slice-stats.ts → cooccurrence-stats.ts} +22 -16
- package/lib/utils/golden.ts +36 -51
- package/lib/utils/license.ts +239 -27
- package/lib/utils/split.ts +209 -88
- package/lib/utils/tokenize.ts +25 -56
- package/lib/utils/wof-json.ts +130 -77
- package/lib/{utils/index.ts → utils.ts} +0 -1
- package/lib/ve/recipes/reviewed-postcode-tail.ts +40 -13
- package/out/adapters/cordis/adapter.d.ts +326 -0
- package/out/adapters/cordis/adapter.d.ts.map +1 -0
- package/out/adapters/cordis/adapter.js +622 -0
- package/out/adapters/cordis/adapter.js.map +1 -0
- package/out/adapters/dedup-key.d.ts +30 -0
- package/out/adapters/dedup-key.d.ts.map +1 -0
- package/out/adapters/dedup-key.js +35 -0
- package/out/adapters/dedup-key.js.map +1 -0
- package/out/adapters/errors.d.ts +17 -0
- package/out/adapters/errors.d.ts.map +1 -0
- package/out/adapters/errors.js +20 -0
- package/out/adapters/errors.js.map +1 -0
- package/out/adapters/geonames/adapter.d.ts +26 -28
- package/out/adapters/geonames/adapter.d.ts.map +1 -1
- package/out/adapters/geonames/adapter.js +40 -50
- package/out/adapters/geonames/adapter.js.map +1 -1
- package/out/adapters/geonames/postal/adapter.d.ts +14 -27
- package/out/adapters/geonames/postal/adapter.d.ts.map +1 -1
- package/out/adapters/geonames/postal/adapter.js +30 -35
- package/out/adapters/geonames/postal/adapter.js.map +1 -1
- package/out/adapters/gleif/adapter.d.ts +293 -0
- package/out/adapters/gleif/adapter.d.ts.map +1 -0
- package/out/adapters/gleif/adapter.js +685 -0
- package/out/adapters/gleif/adapter.js.map +1 -0
- package/out/adapters/libpostal-dictionary.d.ts +20 -0
- package/out/adapters/libpostal-dictionary.d.ts.map +1 -0
- package/out/adapters/libpostal-dictionary.js +34 -0
- package/out/adapters/libpostal-dictionary.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts +29 -43
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -1
- package/out/adapters/openaddresses/adapter.js +34 -46
- package/out/adapters/openaddresses/adapter.js.map +1 -1
- package/out/adapters/osm/adapter.d.ts +59 -52
- package/out/adapters/osm/adapter.d.ts.map +1 -1
- package/out/adapters/osm/adapter.js +119 -69
- package/out/adapters/osm/adapter.js.map +1 -1
- package/out/adapters/overture/adapter.d.ts +11 -37
- package/out/adapters/overture/adapter.d.ts.map +1 -1
- package/out/adapters/overture/adapter.js +45 -42
- package/out/adapters/overture/adapter.js.map +1 -1
- package/out/adapters/po-box/adapter.d.ts +66 -0
- package/out/adapters/po-box/adapter.d.ts.map +1 -0
- package/out/adapters/{synth-po-box → po-box}/adapter.js +48 -47
- package/out/adapters/po-box/adapter.js.map +1 -0
- package/out/adapters/registry.d.ts +55 -0
- package/out/adapters/registry.d.ts.map +1 -0
- package/out/adapters/registry.js +43 -0
- package/out/adapters/registry.js.map +1 -0
- package/out/adapters/sha256-stream.d.ts +26 -0
- package/out/adapters/sha256-stream.d.ts.map +1 -0
- package/out/adapters/sha256-stream.js +34 -0
- package/out/adapters/sha256-stream.js.map +1 -0
- package/out/adapters/source-id.d.ts +33 -0
- package/out/adapters/source-id.d.ts.map +1 -0
- package/out/adapters/source-id.js +42 -0
- package/out/adapters/source-id.js.map +1 -0
- package/out/adapters/street-line.d.ts +103 -0
- package/out/adapters/street-line.d.ts.map +1 -0
- package/out/adapters/street-line.js +118 -0
- package/out/adapters/street-line.js.map +1 -0
- package/out/adapters/wof/admin/json/adapter.d.ts +27 -18
- package/out/adapters/wof/admin/json/adapter.d.ts.map +1 -1
- package/out/adapters/wof/admin/json/adapter.js +48 -32
- package/out/adapters/wof/admin/json/adapter.js.map +1 -1
- package/out/adapters/wof/json-rows.d.ts +36 -19
- package/out/adapters/wof/json-rows.d.ts.map +1 -1
- package/out/adapters/wof/json-rows.js +35 -15
- package/out/adapters/wof/json-rows.js.map +1 -1
- package/out/adapters/wof/postalcode-json/adapter.d.ts +22 -38
- package/out/adapters/wof/postalcode-json/adapter.d.ts.map +1 -1
- package/out/adapters/wof/postalcode-json/adapter.js +60 -58
- package/out/adapters/wof/postalcode-json/adapter.js.map +1 -1
- package/out/adapters.d.ts +75 -0
- package/out/adapters.d.ts.map +1 -0
- package/out/adapters.js +167 -0
- package/out/adapters.js.map +1 -0
- package/out/au/adapters/gnaf/adapter.d.ts +15 -27
- package/out/au/adapters/gnaf/adapter.d.ts.map +1 -1
- package/out/au/adapters/gnaf/adapter.js +35 -43
- package/out/au/adapters/gnaf/adapter.js.map +1 -1
- package/out/au/adapters/gnaf/assemble.d.ts +15 -26
- package/out/au/adapters/gnaf/assemble.d.ts.map +1 -1
- package/out/au/adapters/gnaf/assemble.js +26 -46
- package/out/au/adapters/gnaf/assemble.js.map +1 -1
- package/out/be/adapters/brussels/adapter.d.ts +212 -0
- package/out/be/adapters/brussels/adapter.d.ts.map +1 -0
- package/out/be/adapters/brussels/adapter.js +435 -0
- package/out/be/adapters/brussels/adapter.js.map +1 -0
- package/out/be/adapters/vlaanderen/adapter.d.ts +230 -0
- package/out/be/adapters/vlaanderen/adapter.d.ts.map +1 -0
- package/out/be/adapters/vlaanderen/adapter.js +418 -0
- package/out/be/adapters/vlaanderen/adapter.js.map +1 -0
- package/out/be/adapters/wallonie/adapter.d.ts +196 -0
- package/out/be/adapters/wallonie/adapter.d.ts.map +1 -0
- package/out/be/adapters/wallonie/adapter.js +437 -0
- package/out/be/adapters/wallonie/adapter.js.map +1 -0
- package/out/be/tools/fetch/brussels.d.ts +122 -0
- package/out/be/tools/fetch/brussels.d.ts.map +1 -0
- package/out/be/tools/fetch/brussels.js +148 -0
- package/out/be/tools/fetch/brussels.js.map +1 -0
- package/out/be/tools/fetch/wallonie.d.ts +120 -0
- package/out/be/tools/fetch/wallonie.d.ts.map +1 -0
- package/out/be/tools/fetch/wallonie.js +167 -0
- package/out/be/tools/fetch/wallonie.js.map +1 -0
- package/out/build/adapters.d.ts +33 -0
- package/out/build/adapters.d.ts.map +1 -0
- package/out/build/adapters.js +69 -0
- package/out/build/adapters.js.map +1 -0
- package/out/build/align.d.ts +74 -0
- package/out/build/align.d.ts.map +1 -0
- package/out/build/align.js +226 -0
- package/out/build/align.js.map +1 -0
- package/out/build/checkpoint.d.ts +94 -0
- package/out/build/checkpoint.d.ts.map +1 -0
- package/out/build/checkpoint.js +61 -0
- package/out/build/checkpoint.js.map +1 -0
- package/out/build/eligibility.d.ts +47 -0
- package/out/build/eligibility.d.ts.map +1 -0
- package/out/build/eligibility.js +80 -0
- package/out/build/eligibility.js.map +1 -0
- package/out/build/heap.d.ts +28 -0
- package/out/build/heap.d.ts.map +1 -0
- package/out/build/heap.js +47 -0
- package/out/build/heap.js.map +1 -0
- package/out/build/inputs.d.ts +52 -0
- package/out/build/inputs.d.ts.map +1 -0
- package/out/build/inputs.js +49 -0
- package/out/build/inputs.js.map +1 -0
- package/out/build/rows.d.ts +16 -0
- package/out/build/rows.d.ts.map +1 -0
- package/out/build/rows.js +19 -0
- package/out/build/rows.js.map +1 -0
- package/out/build/types.d.ts +222 -0
- package/out/build/types.d.ts.map +1 -0
- package/out/build/types.js +34 -0
- package/out/build/types.js.map +1 -0
- package/out/build.d.ts +6 -121
- package/out/build.d.ts.map +1 -1
- package/out/build.js +112 -207
- package/out/build.js.map +1 -1
- package/out/cn/recipes/organizational-units.d.ts +5 -22
- package/out/cn/recipes/organizational-units.d.ts.map +1 -1
- package/out/cn/recipes/organizational-units.js +20 -41
- package/out/cn/recipes/organizational-units.js.map +1 -1
- package/out/cz/adapters/cuzk/adapter.d.ts +52 -0
- package/out/cz/adapters/cuzk/adapter.d.ts.map +1 -0
- package/out/cz/adapters/cuzk/adapter.js +269 -0
- package/out/cz/adapters/cuzk/adapter.js.map +1 -0
- package/out/cz/recipes/pcfirst-preposition.d.ts +7 -11
- package/out/cz/recipes/pcfirst-preposition.d.ts.map +1 -1
- package/out/cz/recipes/pcfirst-preposition.js +36 -27
- package/out/cz/recipes/pcfirst-preposition.js.map +1 -1
- package/out/cz/tools/fetch/cuzk.d.ts +281 -0
- package/out/cz/tools/fetch/cuzk.d.ts.map +1 -0
- package/out/cz/tools/fetch/cuzk.js +448 -0
- package/out/cz/tools/fetch/cuzk.js.map +1 -0
- package/out/de/recipes/locale.d.ts +24 -26
- package/out/de/recipes/locale.d.ts.map +1 -1
- package/out/de/recipes/locale.js +67 -57
- package/out/de/recipes/locale.js.map +1 -1
- package/out/directory.d.ts +20 -0
- package/out/directory.d.ts.map +1 -0
- package/out/directory.js +27 -0
- package/out/directory.js.map +1 -0
- package/out/dk/adapters/inspire/adapter.d.ts +153 -0
- package/out/dk/adapters/inspire/adapter.d.ts.map +1 -0
- package/out/dk/adapters/inspire/adapter.js +258 -0
- package/out/dk/adapters/inspire/adapter.js.map +1 -0
- package/out/dk/tools/fetch/inspire.d.ts +101 -0
- package/out/dk/tools/fetch/inspire.d.ts.map +1 -0
- package/out/dk/tools/fetch/inspire.js +232 -0
- package/out/dk/tools/fetch/inspire.js.map +1 -0
- package/out/ee/adapters/ads/adapter.d.ts +102 -0
- package/out/ee/adapters/ads/adapter.d.ts.map +1 -0
- package/out/ee/adapters/ads/adapter.js +185 -0
- package/out/ee/adapters/ads/adapter.js.map +1 -0
- package/out/ee/tools/fetch/ads.d.ts +123 -0
- package/out/ee/tools/fetch/ads.d.ts.map +1 -0
- package/out/ee/tools/fetch/ads.js +197 -0
- package/out/ee/tools/fetch/ads.js.map +1 -0
- package/out/env.d.ts +6 -2
- package/out/env.d.ts.map +1 -1
- package/out/env.js +6 -2
- package/out/env.js.map +1 -1
- package/out/es/adapters/bizkaia/adapter.d.ts +143 -0
- package/out/es/adapters/bizkaia/adapter.d.ts.map +1 -0
- package/out/es/adapters/bizkaia/adapter.js +332 -0
- package/out/es/adapters/bizkaia/adapter.js.map +1 -0
- package/out/es/adapters/catastro/adapter.d.ts +103 -0
- package/out/es/adapters/catastro/adapter.d.ts.map +1 -0
- package/out/es/adapters/catastro/adapter.js +290 -0
- package/out/es/adapters/catastro/adapter.js.map +1 -0
- package/out/es/adapters/gipuzkoa/adapter.d.ts +84 -0
- package/out/es/adapters/gipuzkoa/adapter.d.ts.map +1 -0
- package/out/es/adapters/gipuzkoa/adapter.js +218 -0
- package/out/es/adapters/gipuzkoa/adapter.js.map +1 -0
- package/out/es/adapters/navarra/adapter.d.ts +106 -0
- package/out/es/adapters/navarra/adapter.d.ts.map +1 -0
- package/out/es/adapters/navarra/adapter.js +242 -0
- package/out/es/adapters/navarra/adapter.js.map +1 -0
- package/out/es/cadastre.d.ts +110 -0
- package/out/es/cadastre.d.ts.map +1 -0
- package/out/es/cadastre.js +128 -0
- package/out/es/cadastre.js.map +1 -0
- package/out/es/tools/fetch/bizkaia.d.ts +281 -0
- package/out/es/tools/fetch/bizkaia.d.ts.map +1 -0
- package/out/es/tools/fetch/bizkaia.js +478 -0
- package/out/es/tools/fetch/bizkaia.js.map +1 -0
- package/out/es/tools/fetch/catastro.d.ts +280 -0
- package/out/es/tools/fetch/catastro.d.ts.map +1 -0
- package/out/es/tools/fetch/catastro.js +491 -0
- package/out/es/tools/fetch/catastro.js.map +1 -0
- package/out/es/tools/fetch/gipuzkoa.d.ts +164 -0
- package/out/es/tools/fetch/gipuzkoa.d.ts.map +1 -0
- package/out/es/tools/fetch/gipuzkoa.js +210 -0
- package/out/es/tools/fetch/gipuzkoa.js.map +1 -0
- package/out/es/tools/fetch/navarra.d.ts +194 -0
- package/out/es/tools/fetch/navarra.d.ts.map +1 -0
- package/out/es/tools/fetch/navarra.js +321 -0
- package/out/es/tools/fetch/navarra.js.map +1 -0
- package/out/fi/adapters/ryhti/adapter.d.ts +111 -0
- package/out/fi/adapters/ryhti/adapter.d.ts.map +1 -0
- package/out/fi/adapters/ryhti/adapter.js +240 -0
- package/out/fi/adapters/ryhti/adapter.js.map +1 -0
- package/out/fi/tools/fetch/ryhti.d.ts +206 -0
- package/out/fi/tools/fetch/ryhti.d.ts.map +1 -0
- package/out/fi/tools/fetch/ryhti.js +324 -0
- package/out/fi/tools/fetch/ryhti.js.map +1 -0
- package/out/fingerprints.d.ts +68 -0
- package/out/fingerprints.d.ts.map +1 -0
- package/out/fingerprints.js +130 -0
- package/out/fingerprints.js.map +1 -0
- package/out/fr/adapters/annuaire-education/adapter.d.ts +236 -0
- package/out/fr/adapters/annuaire-education/adapter.d.ts.map +1 -0
- package/out/fr/adapters/annuaire-education/adapter.js +477 -0
- package/out/fr/adapters/annuaire-education/adapter.js.map +1 -0
- package/out/fr/adapters/ban/adapter.d.ts +19 -25
- package/out/fr/adapters/ban/adapter.d.ts.map +1 -1
- package/out/fr/adapters/ban/adapter.js +65 -54
- package/out/fr/adapters/ban/adapter.js.map +1 -1
- package/out/fr/adapters/finess/adapter.d.ts +277 -0
- package/out/fr/adapters/finess/adapter.d.ts.map +1 -0
- package/out/fr/adapters/finess/adapter.js +520 -0
- package/out/fr/adapters/finess/adapter.js.map +1 -0
- package/out/fr/adapters/finess/postal-lines.d.ts +61 -0
- package/out/fr/adapters/finess/postal-lines.d.ts.map +1 -0
- package/out/fr/adapters/finess/postal-lines.js +114 -0
- package/out/fr/adapters/finess/postal-lines.js.map +1 -0
- package/out/fr/adapters/finess/voie-type.d.ts +77 -0
- package/out/fr/adapters/finess/voie-type.d.ts.map +1 -0
- package/out/fr/adapters/finess/voie-type.js +173 -0
- package/out/fr/adapters/finess/voie-type.js.map +1 -0
- package/out/fr/insee-country.d.ts +45 -0
- package/out/fr/insee-country.d.ts.map +1 -0
- package/out/fr/insee-country.js +60 -0
- package/out/fr/insee-country.js.map +1 -0
- package/out/fr/recipes/admin-split.d.ts +4 -27
- package/out/fr/recipes/admin-split.d.ts.map +1 -1
- package/out/fr/recipes/admin-split.js +36 -58
- package/out/fr/recipes/admin-split.js.map +1 -1
- package/out/fr/recipes/bare-street.d.ts +2 -17
- package/out/fr/recipes/bare-street.d.ts.map +1 -1
- package/out/fr/recipes/bare-street.js +35 -50
- package/out/fr/recipes/bare-street.js.map +1 -1
- package/out/fr/recipes/fragment.d.ts +6 -65
- package/out/fr/recipes/fragment.d.ts.map +1 -1
- package/out/fr/recipes/fragment.js +55 -135
- package/out/fr/recipes/fragment.js.map +1 -1
- package/out/fr/recipes/lieudit.d.ts +17 -19
- package/out/fr/recipes/lieudit.d.ts.map +1 -1
- package/out/fr/recipes/lieudit.js +89 -68
- package/out/fr/recipes/lieudit.js.map +1 -1
- package/out/fr/recipes/order.d.ts +4 -27
- package/out/fr/recipes/order.d.ts.map +1 -1
- package/out/fr/recipes/order.js +31 -58
- package/out/fr/recipes/order.js.map +1 -1
- package/out/fr/{adapters/ban/street-decompose.d.ts → street-decompose.d.ts} +3 -2
- package/out/fr/street-decompose.d.ts.map +1 -0
- package/out/fr/{adapters/ban/street-decompose.js → street-decompose.js} +4 -3
- package/out/fr/street-decompose.js.map +1 -0
- package/out/fr/tools/fetch/annuaire-education.d.ts +133 -0
- package/out/fr/tools/fetch/annuaire-education.d.ts.map +1 -0
- package/out/fr/tools/fetch/annuaire-education.js +198 -0
- package/out/fr/tools/fetch/annuaire-education.js.map +1 -0
- package/out/fr/tools/fetch/ban.d.ts +9 -7
- package/out/fr/tools/fetch/ban.d.ts.map +1 -1
- package/out/fr/tools/fetch/ban.js +29 -19
- package/out/fr/tools/fetch/ban.js.map +1 -1
- package/out/fr/tools/fetch/finess.d.ts +145 -0
- package/out/fr/tools/fetch/finess.d.ts.map +1 -0
- package/out/fr/tools/fetch/finess.js +229 -0
- package/out/fr/tools/fetch/finess.js.map +1 -0
- package/out/gauntlet-inputs.d.ts +42 -0
- package/out/gauntlet-inputs.d.ts.map +1 -0
- package/out/gauntlet-inputs.js +78 -0
- package/out/gauntlet-inputs.js.map +1 -0
- package/out/index.d.ts +9 -3
- package/out/index.d.ts.map +1 -1
- package/out/index.js +9 -3
- package/out/index.js.map +1 -1
- package/out/inspire/address.d.ts +261 -0
- package/out/inspire/address.d.ts.map +1 -0
- package/out/inspire/address.js +395 -0
- package/out/inspire/address.js.map +1 -0
- package/out/inspire/archive.d.ts +36 -0
- package/out/inspire/archive.d.ts.map +1 -0
- package/out/inspire/archive.js +42 -0
- package/out/inspire/archive.js.map +1 -0
- package/out/inspire/errors.d.ts +56 -0
- package/out/inspire/errors.d.ts.map +1 -0
- package/out/inspire/errors.js +65 -0
- package/out/inspire/errors.js.map +1 -0
- package/out/inspire/stream.d.ts +140 -0
- package/out/inspire/stream.d.ts.map +1 -0
- package/out/inspire/stream.js +123 -0
- package/out/inspire/stream.js.map +1 -0
- package/out/international/recipes/locale.d.ts +40 -86
- package/out/international/recipes/locale.d.ts.map +1 -1
- package/out/international/recipes/locale.js +122 -157
- package/out/international/recipes/locale.js.map +1 -1
- package/out/it/adapters/anac/adapter.d.ts +269 -0
- package/out/it/adapters/anac/adapter.d.ts.map +1 -0
- package/out/it/adapters/anac/adapter.js +434 -0
- package/out/it/adapters/anac/adapter.js.map +1 -0
- package/out/it/tools/fetch/anac.d.ts +171 -0
- package/out/it/tools/fetch/anac.d.ts.map +1 -0
- package/out/it/tools/fetch/anac.js +269 -0
- package/out/it/tools/fetch/anac.js.map +1 -0
- package/out/jp/adapters/wof-admin/adapter.d.ts +14 -11
- package/out/jp/adapters/wof-admin/adapter.d.ts.map +1 -1
- package/out/jp/adapters/wof-admin/adapter.js +27 -16
- package/out/jp/adapters/wof-admin/adapter.js.map +1 -1
- package/out/jp/tools/fetch/houjin.d.ts +7 -4
- package/out/jp/tools/fetch/houjin.d.ts.map +1 -1
- package/out/jp/tools/fetch/houjin.js +17 -13
- package/out/jp/tools/fetch/houjin.js.map +1 -1
- package/out/kr/adapters/juso/label-rows.d.ts +17 -31
- package/out/kr/adapters/juso/label-rows.d.ts.map +1 -1
- package/out/kr/adapters/juso/label-rows.js +19 -41
- package/out/kr/adapters/juso/label-rows.js.map +1 -1
- package/out/kr/adapters/localdata/align.d.ts +4 -16
- package/out/kr/adapters/localdata/align.d.ts.map +1 -1
- package/out/kr/adapters/localdata/align.js +19 -30
- package/out/kr/adapters/localdata/align.js.map +1 -1
- package/out/kr/adapters/localdata/key-index.d.ts +13 -22
- package/out/kr/adapters/localdata/key-index.d.ts.map +1 -1
- package/out/kr/adapters/localdata/key-index.js +15 -21
- package/out/kr/adapters/localdata/key-index.js.map +1 -1
- package/out/kr/adapters/localdata/permit-rows.d.ts +21 -14
- package/out/kr/adapters/localdata/permit-rows.d.ts.map +1 -1
- package/out/kr/adapters/localdata/permit-rows.js +31 -26
- package/out/kr/adapters/localdata/permit-rows.js.map +1 -1
- package/out/kr/tools/fetch/juso.d.ts +11 -8
- package/out/kr/tools/fetch/juso.d.ts.map +1 -1
- package/out/kr/tools/fetch/juso.js +15 -14
- package/out/kr/tools/fetch/juso.js.map +1 -1
- package/out/kr/tools/fetch/localdata.d.ts +16 -9
- package/out/kr/tools/fetch/localdata.d.ts.map +1 -1
- package/out/kr/tools/fetch/localdata.js +24 -16
- package/out/kr/tools/fetch/localdata.js.map +1 -1
- package/out/lu/adapters/bd-adresses/adapter.d.ts +109 -0
- package/out/lu/adapters/bd-adresses/adapter.d.ts.map +1 -0
- package/out/lu/adapters/bd-adresses/adapter.js +196 -0
- package/out/lu/adapters/bd-adresses/adapter.js.map +1 -0
- package/out/lu/tools/fetch/bd-adresses.d.ts +165 -0
- package/out/lu/tools/fetch/bd-adresses.d.ts.map +1 -0
- package/out/lu/tools/fetch/bd-adresses.js +223 -0
- package/out/lu/tools/fetch/bd-adresses.js.map +1 -0
- package/out/lv/adapters/varis/adapter.d.ts +284 -0
- package/out/lv/adapters/varis/adapter.d.ts.map +1 -0
- package/out/lv/adapters/varis/adapter.js +405 -0
- package/out/lv/adapters/varis/adapter.js.map +1 -0
- package/out/lv/tools/fetch/varis.d.ts +81 -0
- package/out/lv/tools/fetch/varis.d.ts.map +1 -0
- package/out/lv/tools/fetch/varis.js +133 -0
- package/out/lv/tools/fetch/varis.js.map +1 -0
- package/out/nl/adapters/kadaster/adapter.d.ts +125 -0
- package/out/nl/adapters/kadaster/adapter.d.ts.map +1 -0
- package/out/nl/adapters/kadaster/adapter.js +309 -0
- package/out/nl/adapters/kadaster/adapter.js.map +1 -0
- package/out/nl/recipes/postcode.d.ts +12 -14
- package/out/nl/recipes/postcode.d.ts.map +1 -1
- package/out/nl/recipes/postcode.js +42 -24
- package/out/nl/recipes/postcode.js.map +1 -1
- package/out/nl/tools/fetch/kadaster.d.ts +159 -0
- package/out/nl/tools/fetch/kadaster.d.ts.map +1 -0
- package/out/nl/tools/fetch/kadaster.js +182 -0
- package/out/nl/tools/fetch/kadaster.js.map +1 -0
- package/out/no/adapters/matrikkelen/adapter.d.ts +44 -0
- package/out/no/adapters/matrikkelen/adapter.d.ts.map +1 -0
- package/out/no/adapters/matrikkelen/adapter.js +143 -0
- package/out/no/adapters/matrikkelen/adapter.js.map +1 -0
- package/out/no/recipes/fragment.d.ts +1 -33
- package/out/no/recipes/fragment.d.ts.map +1 -1
- package/out/no/recipes/fragment.js +23 -57
- package/out/no/recipes/fragment.js.map +1 -1
- package/out/no/recipes/street/led.d.ts +9 -12
- package/out/no/recipes/street/led.d.ts.map +1 -1
- package/out/no/recipes/street/led.js +34 -24
- package/out/no/recipes/street/led.js.map +1 -1
- package/out/no/recipes/street.d.ts +19 -0
- package/out/no/recipes/street.d.ts.map +1 -0
- package/out/no/recipes/{street/index.js → street.js} +28 -12
- package/out/no/recipes/street.js.map +1 -0
- package/out/no/tools/fetch/matrikkelen.d.ts +263 -0
- package/out/no/tools/fetch/matrikkelen.d.ts.map +1 -0
- package/out/no/tools/fetch/matrikkelen.js +353 -0
- package/out/no/tools/fetch/matrikkelen.js.map +1 -0
- package/out/parquet/duckdb.d.ts +103 -0
- package/out/parquet/duckdb.d.ts.map +1 -0
- package/out/parquet/duckdb.js +93 -0
- package/out/parquet/duckdb.js.map +1 -0
- package/out/parquet/readers.d.ts +44 -0
- package/out/parquet/readers.d.ts.map +1 -0
- package/out/parquet/readers.js +69 -0
- package/out/parquet/readers.js.map +1 -0
- package/out/parquet/schema.d.ts +95 -0
- package/out/parquet/schema.d.ts.map +1 -0
- package/out/parquet/schema.js +157 -0
- package/out/parquet/schema.js.map +1 -0
- package/out/parquet/shuffle.d.ts +25 -0
- package/out/parquet/shuffle.d.ts.map +1 -0
- package/out/parquet/shuffle.js +44 -0
- package/out/parquet/shuffle.js.map +1 -0
- package/out/parquet/span-sql.d.ts +49 -0
- package/out/parquet/span-sql.d.ts.map +1 -0
- package/out/parquet/span-sql.js +53 -0
- package/out/parquet/span-sql.js.map +1 -0
- package/out/parquet/streams.d.ts +47 -0
- package/out/parquet/streams.d.ts.map +1 -0
- package/out/parquet/streams.js +78 -0
- package/out/parquet/streams.js.map +1 -0
- package/out/parquet/writers.d.ts +124 -0
- package/out/parquet/writers.d.ts.map +1 -0
- package/out/parquet/writers.js +252 -0
- package/out/parquet/writers.js.map +1 -0
- package/out/pl/adapters/emuia/adapter.d.ts +81 -0
- package/out/pl/adapters/emuia/adapter.d.ts.map +1 -0
- package/out/pl/adapters/emuia/adapter.js +178 -0
- package/out/pl/adapters/emuia/adapter.js.map +1 -0
- package/out/pl/tools/fetch/emuia.d.ts +166 -0
- package/out/pl/tools/fetch/emuia.d.ts.map +1 -0
- package/out/pl/tools/fetch/emuia.js +261 -0
- package/out/pl/tools/fetch/emuia.js.map +1 -0
- package/out/recipes/anchor-absorption.d.ts +9 -9
- package/out/recipes/anchor-absorption.d.ts.map +1 -1
- package/out/recipes/anchor-absorption.js +29 -19
- package/out/recipes/anchor-absorption.js.map +1 -1
- package/out/recipes/bare/country.d.ts +2 -20
- package/out/recipes/bare/country.d.ts.map +1 -1
- package/out/recipes/bare/country.js +20 -31
- package/out/recipes/bare/country.js.map +1 -1
- package/out/recipes/bare/postcode/eval.d.ts +1 -1
- package/out/recipes/bare/postcode/eval.js +1 -1
- package/out/recipes/bare/postcode.d.ts +41 -0
- package/out/recipes/bare/postcode.d.ts.map +1 -0
- package/out/recipes/bare/{postcode/index.js → postcode.js} +92 -80
- package/out/recipes/bare/postcode.js.map +1 -0
- package/out/recipes/boundary-stress.d.ts +8 -8
- package/out/recipes/boundary-stress.d.ts.map +1 -1
- package/out/recipes/boundary-stress.js +37 -20
- package/out/recipes/boundary-stress.js.map +1 -1
- package/out/recipes/country-balanced.d.ts +3 -21
- package/out/recipes/country-balanced.d.ts.map +1 -1
- package/out/recipes/country-balanced.js +58 -76
- package/out/recipes/country-balanced.js.map +1 -1
- package/out/recipes/house-venue.d.ts +8 -6
- package/out/recipes/house-venue.d.ts.map +1 -1
- package/out/recipes/house-venue.js +33 -14
- package/out/recipes/house-venue.js.map +1 -1
- package/out/recipes/intersection.d.ts +20 -20
- package/out/recipes/intersection.d.ts.map +1 -1
- package/out/recipes/intersection.js +67 -55
- package/out/recipes/intersection.js.map +1 -1
- package/out/recipes/po/box/cedex/au-nz.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/au-nz.js +3 -3
- package/out/recipes/po/box/cedex/au-nz.js.map +1 -1
- package/out/recipes/po/box/cedex/ca.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/ca.js +2 -2
- package/out/recipes/po/box/cedex/ca.js.map +1 -1
- package/out/recipes/po/box/cedex/fr.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/fr.js +3 -3
- package/out/recipes/po/box/cedex/fr.js.map +1 -1
- package/out/recipes/po/box/cedex/phrases.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/phrases.js +7 -6
- package/out/recipes/po/box/cedex/phrases.js.map +1 -1
- package/out/recipes/po/box/cedex/recipe.d.ts +1 -1
- package/out/recipes/po/box/cedex/recipe.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/recipe.js +27 -16
- package/out/recipes/po/box/cedex/recipe.js.map +1 -1
- package/out/recipes/po/box/cedex/sources.d.ts +20 -14
- package/out/recipes/po/box/cedex/sources.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/sources.js +2 -2
- package/out/recipes/po/box/cedex/sources.js.map +1 -1
- package/out/recipes/po/box/cedex/us.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/us.js +5 -2
- package/out/recipes/po/box/cedex/us.js.map +1 -1
- package/out/recipes/po/box.d.ts +18 -0
- package/out/recipes/po/box.d.ts.map +1 -0
- package/out/recipes/po/{box/index.js → box.js} +37 -19
- package/out/recipes/po/box.js.map +1 -0
- package/out/recipes/scaffold.d.ts +223 -141
- package/out/recipes/scaffold.d.ts.map +1 -1
- package/out/recipes/scaffold.js +75 -65
- package/out/recipes/scaffold.js.map +1 -1
- package/out/recipes/sources.d.ts +178 -0
- package/out/recipes/sources.d.ts.map +1 -0
- package/out/recipes/sources.js +361 -0
- package/out/recipes/sources.js.map +1 -0
- package/out/recipes/street/affix.d.ts +20 -50
- package/out/recipes/street/affix.d.ts.map +1 -1
- package/out/recipes/street/affix.js +45 -133
- package/out/recipes/street/affix.js.map +1 -1
- package/out/recipes/street/bare.d.ts +9 -7
- package/out/recipes/street/bare.d.ts.map +1 -1
- package/out/recipes/street/bare.js +27 -16
- package/out/recipes/street/bare.js.map +1 -1
- package/out/recipes/street.d.ts +6 -4
- package/out/recipes/street.d.ts.map +1 -1
- package/out/recipes/street.js +32 -9
- package/out/recipes/street.js.map +1 -1
- package/out/recipes/sub/venue/context.d.ts +12 -9
- package/out/recipes/sub/venue/context.d.ts.map +1 -1
- package/out/recipes/sub/venue/context.js +23 -17
- package/out/recipes/sub/venue/context.js.map +1 -1
- package/out/recipes/sub/venue/render.d.ts +58 -0
- package/out/recipes/sub/venue/render.d.ts.map +1 -0
- package/out/recipes/sub/venue/render.js +118 -0
- package/out/recipes/sub/venue/render.js.map +1 -0
- package/out/recipes/sub/venue/sources.d.ts +53 -93
- package/out/recipes/sub/venue/sources.d.ts.map +1 -1
- package/out/recipes/sub/venue/sources.js +57 -197
- package/out/recipes/sub/venue/sources.js.map +1 -1
- package/out/recipes/sub/venue.d.ts +173 -0
- package/out/recipes/sub/venue.d.ts.map +1 -0
- package/out/recipes/sub/venue.js +558 -0
- package/out/recipes/sub/venue.js.map +1 -0
- package/out/recipes/trailing-region.d.ts +9 -61
- package/out/recipes/trailing-region.d.ts.map +1 -1
- package/out/recipes/trailing-region.js +61 -86
- package/out/recipes/trailing-region.js.map +1 -1
- package/out/recipes/unit/sources.d.ts +28 -0
- package/out/recipes/unit/sources.d.ts.map +1 -0
- package/out/recipes/unit/sources.js +30 -0
- package/out/recipes/unit/sources.js.map +1 -0
- package/out/recipes/unit.d.ts +30 -17
- package/out/recipes/unit.d.ts.map +1 -1
- package/out/recipes/unit.js +90 -79
- package/out/recipes/unit.js.map +1 -1
- package/out/recipes/venue.d.ts +119 -0
- package/out/recipes/venue.d.ts.map +1 -0
- package/out/recipes/venue.js +245 -0
- package/out/recipes/venue.js.map +1 -0
- package/out/recipes.d.ts +26 -0
- package/out/recipes.d.ts.map +1 -0
- package/out/{recipes/index.js → recipes.js} +16 -12
- package/out/recipes.js.map +1 -0
- package/out/registers.d.ts +279 -0
- package/out/registers.d.ts.map +1 -0
- package/out/registers.js +275 -0
- package/out/registers.js.map +1 -0
- package/out/ro/adapters/retea-scolara/adapter.d.ts +114 -0
- package/out/ro/adapters/retea-scolara/adapter.d.ts.map +1 -0
- package/out/ro/adapters/retea-scolara/adapter.js +209 -0
- package/out/ro/adapters/retea-scolara/adapter.js.map +1 -0
- package/out/ro/tools/fetch/retea-scolara.d.ts +69 -0
- package/out/ro/tools/fetch/retea-scolara.d.ts.map +1 -0
- package/out/ro/tools/fetch/retea-scolara.js +117 -0
- package/out/ro/tools/fetch/retea-scolara.js.map +1 -0
- package/out/runner.d.ts +121 -60
- package/out/runner.d.ts.map +1 -1
- package/out/runner.js +130 -56
- package/out/runner.js.map +1 -1
- package/out/sg/recipes/register.d.ts +18 -32
- package/out/sg/recipes/register.d.ts.map +1 -1
- package/out/sg/recipes/register.js +45 -50
- package/out/sg/recipes/register.js.map +1 -1
- package/out/sg/tools/fetch/acra.d.ts +11 -14
- package/out/sg/tools/fetch/acra.d.ts.map +1 -1
- package/out/sg/tools/fetch/acra.js +18 -21
- package/out/sg/tools/fetch/acra.js.map +1 -1
- package/out/si/recipes/bare-village.d.ts +12 -13
- package/out/si/recipes/bare-village.d.ts.map +1 -1
- package/out/si/recipes/bare-village.js +31 -17
- package/out/si/recipes/bare-village.js.map +1 -1
- package/out/sk/adapters/inspire/adapter.d.ts +119 -0
- package/out/sk/adapters/inspire/adapter.d.ts.map +1 -0
- package/out/sk/adapters/inspire/adapter.js +318 -0
- package/out/sk/adapters/inspire/adapter.js.map +1 -0
- package/out/sk/tools/fetch/inspire.d.ts +196 -0
- package/out/sk/tools/fetch/inspire.d.ts.map +1 -0
- package/out/sk/tools/fetch/inspire.js +281 -0
- package/out/sk/tools/fetch/inspire.js.map +1 -0
- package/out/source-register/effective-manifest.d.ts +355 -0
- package/out/source-register/effective-manifest.d.ts.map +1 -0
- package/out/source-register/effective-manifest.js +355 -0
- package/out/source-register/effective-manifest.js.map +1 -0
- package/out/source-register/register.d.ts +79 -0
- package/out/source-register/register.d.ts.map +1 -0
- package/out/source-register/register.js +400 -0
- package/out/source-register/register.js.map +1 -0
- package/out/source-register/training-manifest.d.ts +111 -0
- package/out/source-register/training-manifest.d.ts.map +1 -0
- package/out/source-register/training-manifest.js +120 -0
- package/out/source-register/training-manifest.js.map +1 -0
- package/out/source-register/types.d.ts +538 -0
- package/out/source-register/types.d.ts.map +1 -0
- package/out/source-register/types.js +263 -0
- package/out/source-register/types.js.map +1 -0
- package/out/source-register.d.ts +19 -0
- package/out/source-register.d.ts.map +1 -0
- package/out/source-register.js +16 -0
- package/out/source-register.js.map +1 -0
- package/out/south-asia/recipes/register.d.ts +20 -17
- package/out/south-asia/recipes/register.d.ts.map +1 -1
- package/out/south-asia/recipes/register.js +44 -24
- package/out/south-asia/recipes/register.js.map +1 -1
- package/out/subvenue/harvest.d.ts +117 -0
- package/out/subvenue/harvest.d.ts.map +1 -0
- package/out/subvenue/harvest.js +172 -0
- package/out/subvenue/harvest.js.map +1 -0
- package/out/subvenue/promotions.d.ts +65 -0
- package/out/subvenue/promotions.d.ts.map +1 -0
- package/out/{tools/sub/venue → subvenue}/promotions.js +15 -55
- package/out/subvenue/promotions.js.map +1 -0
- package/out/subvenue/surfaces.d.ts +39 -0
- package/out/subvenue/surfaces.d.ts.map +1 -0
- package/out/subvenue/surfaces.js +75 -0
- package/out/subvenue/surfaces.js.map +1 -0
- package/out/subvenue/table.d.ts +212 -0
- package/out/subvenue/table.d.ts.map +1 -0
- package/out/subvenue/table.js +94 -0
- package/out/subvenue/table.js.map +1 -0
- package/out/surfaces/locale.d.ts +113 -0
- package/out/surfaces/locale.d.ts.map +1 -0
- package/out/surfaces/locale.js +138 -0
- package/out/surfaces/locale.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +22 -30
- package/out/synthesizers/anchor-absorption.d.ts.map +1 -1
- package/out/synthesizers/anchor-absorption.js +30 -85
- package/out/synthesizers/anchor-absorption.js.map +1 -1
- package/out/synthesizers/boundary-stress.d.ts +18 -49
- package/out/synthesizers/boundary-stress.d.ts.map +1 -1
- package/out/synthesizers/boundary-stress.js +45 -142
- package/out/synthesizers/boundary-stress.js.map +1 -1
- package/out/synthesizers/house-venue.d.ts +23 -25
- package/out/synthesizers/house-venue.d.ts.map +1 -1
- package/out/synthesizers/house-venue.js +47 -118
- package/out/synthesizers/house-venue.js.map +1 -1
- package/out/synthesizers/no-street.d.ts +7 -37
- package/out/synthesizers/no-street.d.ts.map +1 -1
- package/out/synthesizers/no-street.js +55 -111
- package/out/synthesizers/no-street.js.map +1 -1
- package/out/synthesizers/po-box.d.ts +48 -45
- package/out/synthesizers/po-box.d.ts.map +1 -1
- package/out/synthesizers/po-box.js +57 -97
- package/out/synthesizers/po-box.js.map +1 -1
- package/out/synthesizers/tail.d.ts +36 -0
- package/out/synthesizers/tail.d.ts.map +1 -0
- package/out/synthesizers/tail.js +32 -0
- package/out/synthesizers/tail.js.map +1 -0
- package/out/synthesizers/utils.d.ts +33 -129
- package/out/synthesizers/utils.d.ts.map +1 -1
- package/out/synthesizers/utils.js +71 -167
- package/out/synthesizers/utils.js.map +1 -1
- package/out/test-kit/corpus-recipe.d.ts +29 -23
- package/out/test-kit/corpus-recipe.d.ts.map +1 -1
- package/out/test-kit/corpus-recipe.js +28 -13
- package/out/test-kit/corpus-recipe.js.map +1 -1
- package/out/test-kit.d.ts +63 -0
- package/out/test-kit.d.ts.map +1 -0
- package/out/test-kit.js +88 -0
- package/out/test-kit.js.map +1 -0
- package/out/tools/align-canonical.d.ts +7 -0
- package/out/tools/align-canonical.d.ts.map +1 -0
- package/out/tools/align-canonical.js +52 -0
- package/out/tools/align-canonical.js.map +1 -0
- package/out/tools/audit.d.ts +19 -11
- package/out/tools/audit.d.ts.map +1 -1
- package/out/tools/audit.js +89 -97
- package/out/tools/audit.js.map +1 -1
- package/out/tools/corpus-stats.d.ts +24 -15
- package/out/tools/corpus-stats.d.ts.map +1 -1
- package/out/tools/corpus-stats.js +34 -30
- package/out/tools/corpus-stats.js.map +1 -1
- package/out/tools/fetch/atom.d.ts +115 -0
- package/out/tools/fetch/atom.d.ts.map +1 -0
- package/out/tools/fetch/atom.js +83 -0
- package/out/tools/fetch/atom.js.map +1 -0
- package/out/tools/fetch/cordis.d.ts +124 -0
- package/out/tools/fetch/cordis.d.ts.map +1 -0
- package/out/tools/fetch/cordis.js +210 -0
- package/out/tools/fetch/cordis.js.map +1 -0
- package/out/tools/fetch/download/manifest.d.ts +27 -18
- package/out/tools/fetch/download/manifest.d.ts.map +1 -1
- package/out/tools/fetch/download/manifest.js +22 -14
- package/out/tools/fetch/download/manifest.js.map +1 -1
- package/out/tools/fetch/download/network.d.ts +48 -27
- package/out/tools/fetch/download/network.d.ts.map +1 -1
- package/out/tools/fetch/download/network.js +26 -16
- package/out/tools/fetch/download/network.js.map +1 -1
- package/out/tools/fetch/download/retry.d.ts +16 -15
- package/out/tools/fetch/download/retry.d.ts.map +1 -1
- package/out/tools/fetch/download/retry.js +28 -28
- package/out/tools/fetch/download/retry.js.map +1 -1
- package/out/tools/fetch/{download/index.d.ts → download.d.ts} +1 -1
- package/out/tools/fetch/download.d.ts.map +1 -0
- package/out/tools/fetch/{download/index.js → download.js} +1 -1
- package/out/tools/fetch/download.js.map +1 -0
- package/out/tools/fetch/geonames/dump.d.ts +51 -32
- package/out/tools/fetch/geonames/dump.d.ts.map +1 -1
- package/out/tools/fetch/geonames/dump.js +54 -43
- package/out/tools/fetch/geonames/dump.js.map +1 -1
- package/out/tools/fetch/geonames/postal.d.ts +14 -49
- package/out/tools/fetch/geonames/postal.d.ts.map +1 -1
- package/out/tools/fetch/geonames/postal.js +17 -56
- package/out/tools/fetch/geonames/postal.js.map +1 -1
- package/out/tools/fetch/gleif.d.ts +138 -0
- package/out/tools/fetch/gleif.d.ts.map +1 -0
- package/out/tools/fetch/gleif.js +222 -0
- package/out/tools/fetch/gleif.js.map +1 -0
- package/out/tools/fetch/header.d.ts +43 -0
- package/out/tools/fetch/header.d.ts.map +1 -0
- package/out/tools/fetch/header.js +61 -0
- package/out/tools/fetch/header.js.map +1 -0
- package/out/tools/fetch/inspire-addresses.d.ts +254 -0
- package/out/tools/fetch/inspire-addresses.d.ts.map +1 -0
- package/out/tools/fetch/inspire-addresses.js +277 -0
- package/out/tools/fetch/inspire-addresses.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +1 -4
- package/out/tools/fetch/openaddresses.d.ts.map +1 -1
- package/out/tools/fetch/openaddresses.js +20 -99
- package/out/tools/fetch/openaddresses.js.map +1 -1
- package/out/tools/fetch/ourairports.d.ts +6 -33
- package/out/tools/fetch/ourairports.d.ts.map +1 -1
- package/out/tools/fetch/ourairports.js +14 -47
- package/out/tools/fetch/ourairports.js.map +1 -1
- package/out/tools/fetch/ppd.d.ts +4 -3
- package/out/tools/fetch/ppd.d.ts.map +1 -1
- package/out/tools/fetch/ppd.js +10 -7
- package/out/tools/fetch/ppd.js.map +1 -1
- package/out/tools/fetch/vlaanderen-ad.d.ts +131 -0
- package/out/tools/fetch/vlaanderen-ad.d.ts.map +1 -0
- package/out/tools/fetch/vlaanderen-ad.js +293 -0
- package/out/tools/fetch/vlaanderen-ad.js.map +1 -0
- package/out/tools/fetch/wfs-harvest.d.ts +420 -0
- package/out/tools/fetch/wfs-harvest.d.ts.map +1 -0
- package/out/tools/fetch/wfs-harvest.js +525 -0
- package/out/tools/fetch/wfs-harvest.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +32 -100
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -1
- package/out/tools/fetch/wikidata-subvenue.js +27 -122
- package/out/tools/fetch/wikidata-subvenue.js.map +1 -1
- package/out/tools/fetch/zip-archive.d.ts +54 -0
- package/out/tools/fetch/zip-archive.d.ts.map +1 -0
- package/out/tools/fetch/zip-archive.js +58 -0
- package/out/tools/fetch/zip-archive.js.map +1 -0
- package/out/tools/fetch.d.ts +99 -0
- package/out/tools/fetch.d.ts.map +1 -0
- package/out/tools/fetch.js +95 -0
- package/out/tools/fetch.js.map +1 -0
- package/out/tools/golden/expand.d.ts +28 -13
- package/out/tools/golden/expand.d.ts.map +1 -1
- package/out/tools/golden/expand.js +51 -37
- package/out/tools/golden/expand.js.map +1 -1
- package/out/tools/golden/promote.d.ts +13 -8
- package/out/tools/golden/promote.d.ts.map +1 -1
- package/out/tools/golden/promote.js +38 -30
- package/out/tools/golden/promote.js.map +1 -1
- package/out/tools/golden/relabel-street/directory.d.ts +25 -10
- package/out/tools/golden/relabel-street/directory.d.ts.map +1 -1
- package/out/tools/golden/relabel-street/directory.js +44 -32
- package/out/tools/golden/relabel-street/directory.js.map +1 -1
- package/out/tools/golden/relabel-street/row.d.ts +18 -69
- package/out/tools/golden/relabel-street/row.d.ts.map +1 -1
- package/out/tools/golden/relabel-street/row.js +19 -77
- package/out/tools/golden/relabel-street/row.js.map +1 -1
- package/out/tools/golden/{relabel-street/index.d.ts → relabel-street.d.ts} +1 -1
- package/out/tools/golden/relabel-street.d.ts.map +1 -0
- package/out/tools/golden/{relabel-street/index.js → relabel-street.js} +1 -1
- package/out/tools/golden/relabel-street.js.map +1 -0
- package/out/tools/ingest-csv.d.ts +19 -15
- package/out/tools/ingest-csv.d.ts.map +1 -1
- package/out/tools/ingest-csv.js +42 -46
- package/out/tools/ingest-csv.js.map +1 -1
- package/out/tools/jsonl-to-parquet.d.ts +15 -28
- package/out/tools/jsonl-to-parquet.d.ts.map +1 -1
- package/out/tools/jsonl-to-parquet.js +49 -91
- package/out/tools/jsonl-to-parquet.js.map +1 -1
- package/out/tools/lint/recipe-output/vocab.d.ts +82 -0
- package/out/tools/lint/recipe-output/vocab.d.ts.map +1 -0
- package/out/tools/lint/{slice → recipe-output}/vocab.js +54 -69
- package/out/tools/lint/recipe-output/vocab.js.map +1 -0
- package/out/tools/lint/recipe-output.d.ts +73 -0
- package/out/tools/lint/recipe-output.d.ts.map +1 -0
- package/out/tools/lint/{slice/index.js → recipe-output.js} +93 -96
- package/out/tools/lint/recipe-output.js.map +1 -0
- package/out/tools/migrate/overlay-parquet.d.ts +30 -0
- package/out/tools/migrate/overlay-parquet.d.ts.map +1 -0
- package/out/tools/migrate/overlay-parquet.js +141 -0
- package/out/tools/migrate/overlay-parquet.js.map +1 -0
- package/out/tools/migrate/recipe-output.d.ts +35 -0
- package/out/tools/migrate/recipe-output.d.ts.map +1 -0
- package/out/tools/migrate/recipe-output.js +124 -0
- package/out/tools/migrate/recipe-output.js.map +1 -0
- package/out/tools/migrate/source-names.d.ts +52 -0
- package/out/tools/migrate/source-names.d.ts.map +1 -0
- package/out/tools/migrate/source-names.js +105 -0
- package/out/tools/migrate/source-names.js.map +1 -0
- package/out/tools/overlay/kryptonite.d.ts +33 -0
- package/out/tools/overlay/kryptonite.d.ts.map +1 -0
- package/out/tools/{slice → overlay}/kryptonite.js +39 -29
- package/out/tools/overlay/kryptonite.js.map +1 -0
- package/out/tools/overlay/manifest.d.ts +143 -0
- package/out/tools/overlay/manifest.d.ts.map +1 -0
- package/out/tools/overlay/manifest.js +261 -0
- package/out/tools/overlay/manifest.js.map +1 -0
- package/out/tools/overlay/merge-source.d.ts +74 -0
- package/out/tools/overlay/merge-source.d.ts.map +1 -0
- package/out/tools/overlay/merge-source.js +63 -0
- package/out/tools/overlay/merge-source.js.map +1 -0
- package/out/tools/overlay/split-slice.d.ts +66 -0
- package/out/tools/overlay/split-slice.d.ts.map +1 -0
- package/out/tools/overlay/split-slice.js +78 -0
- package/out/tools/overlay/split-slice.js.map +1 -0
- package/out/tools/overlay/translit.d.ts +55 -0
- package/out/tools/overlay/translit.d.ts.map +1 -0
- package/out/tools/{slice → overlay}/translit.js +61 -49
- package/out/tools/overlay/translit.js.map +1 -0
- package/out/tools/overture-subvenue.d.ts +17 -76
- package/out/tools/overture-subvenue.d.ts.map +1 -1
- package/out/tools/overture-subvenue.js +7 -74
- package/out/tools/overture-subvenue.js.map +1 -1
- package/out/tools/postcode-triples.d.ts +78 -127
- package/out/tools/postcode-triples.d.ts.map +1 -1
- package/out/tools/postcode-triples.js +200 -193
- package/out/tools/postcode-triples.js.map +1 -1
- package/out/tools/source-register/build.d.ts +147 -0
- package/out/tools/source-register/build.d.ts.map +1 -0
- package/out/tools/source-register/build.js +517 -0
- package/out/tools/source-register/build.js.map +1 -0
- package/out/tools/sub/venue/head-nouns.d.ts +9 -38
- package/out/tools/sub/venue/head-nouns.d.ts.map +1 -1
- package/out/tools/sub/venue/head-nouns.js +37 -74
- package/out/tools/sub/venue/head-nouns.js.map +1 -1
- package/out/tools/sub/venue/lexicon.d.ts +53 -84
- package/out/tools/sub/venue/lexicon.d.ts.map +1 -1
- package/out/tools/sub/venue/lexicon.js +42 -90
- package/out/tools/sub/venue/lexicon.js.map +1 -1
- package/out/tools/sub/venue/wikidata.d.ts +8 -6
- package/out/tools/sub/venue/wikidata.d.ts.map +1 -1
- package/out/tools/sub/venue/wikidata.js +12 -9
- package/out/tools/sub/venue/wikidata.js.map +1 -1
- package/out/tw/tools/fetch/gcis.d.ts +9 -3
- package/out/tw/tools/fetch/gcis.d.ts.map +1 -1
- package/out/tw/tools/fetch/gcis.js +19 -13
- package/out/tw/tools/fetch/gcis.js.map +1 -1
- package/out/types.d.ts +271 -101
- package/out/types.d.ts.map +1 -1
- package/out/types.js +133 -9
- package/out/types.js.map +1 -1
- package/out/us/adapters/fcc-bdc/adapter.d.ts +18 -36
- package/out/us/adapters/fcc-bdc/adapter.d.ts.map +1 -1
- package/out/us/adapters/fcc-bdc/adapter.js +25 -38
- package/out/us/adapters/fcc-bdc/adapter.js.map +1 -1
- package/out/us/adapters/state/hi-schools/adapter.d.ts +12 -11
- package/out/us/adapters/state/hi-schools/adapter.d.ts.map +1 -1
- package/out/us/adapters/state/hi-schools/adapter.js +26 -16
- package/out/us/adapters/state/hi-schools/adapter.js.map +1 -1
- package/out/us/adapters/state/hi-schools/workbook.d.ts +8 -3
- package/out/us/adapters/state/hi-schools/workbook.d.ts.map +1 -1
- package/out/us/adapters/state/hi-schools/workbook.js +3 -1
- package/out/us/adapters/state/hi-schools/workbook.js.map +1 -1
- package/out/us/adapters/state/ia-contractors/adapter.d.ts +13 -6
- package/out/us/adapters/state/ia-contractors/adapter.d.ts.map +1 -1
- package/out/us/adapters/state/ia-contractors/adapter.js +27 -14
- package/out/us/adapters/state/ia-contractors/adapter.js.map +1 -1
- package/out/us/adapters/state/ny-notaries/adapter.d.ts +7 -6
- package/out/us/adapters/state/ny-notaries/adapter.d.ts.map +1 -1
- package/out/us/adapters/state/ny-notaries/adapter.js +24 -22
- package/out/us/adapters/state/ny-notaries/adapter.js.map +1 -1
- package/out/us/adapters/state/tx-notaries/adapter.d.ts +8 -7
- package/out/us/adapters/state/tx-notaries/adapter.d.ts.map +1 -1
- package/out/us/adapters/state/tx-notaries/adapter.js +21 -14
- package/out/us/adapters/state/tx-notaries/adapter.js.map +1 -1
- package/out/us/adapters/tiger/adapter.d.ts +10 -34
- package/out/us/adapters/tiger/adapter.d.ts.map +1 -1
- package/out/us/adapters/tiger/adapter.js +18 -42
- package/out/us/adapters/tiger/adapter.js.map +1 -1
- package/out/us/adapters/tiger/street-decompose.d.ts +6 -13
- package/out/us/adapters/tiger/street-decompose.d.ts.map +1 -1
- package/out/us/adapters/tiger/street-decompose.js +7 -17
- package/out/us/adapters/tiger/street-decompose.js.map +1 -1
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts +26 -20
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.js +41 -29
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.js.map +1 -1
- package/out/us/adapters/usgov/imls-pls/adapter.d.ts +8 -7
- package/out/us/adapters/usgov/imls-pls/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/imls-pls/adapter.js +25 -18
- package/out/us/adapters/usgov/imls-pls/adapter.js.map +1 -1
- package/out/us/adapters/usgov/irs-bmf/adapter.d.ts +11 -10
- package/out/us/adapters/usgov/irs-bmf/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/irs-bmf/adapter.js +32 -22
- package/out/us/adapters/usgov/irs-bmf/adapter.js.map +1 -1
- package/out/us/adapters/usgov/nad/adapter.d.ts +11 -31
- package/out/us/adapters/usgov/nad/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/nad/adapter.js +57 -111
- package/out/us/adapters/usgov/nad/adapter.js.map +1 -1
- package/out/us/adapters/usgov/nppes/adapter.d.ts +12 -22
- package/out/us/adapters/usgov/nppes/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/nppes/adapter.js +62 -32
- package/out/us/adapters/usgov/nppes/adapter.js.map +1 -1
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts +16 -15
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js +38 -28
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js.map +1 -1
- package/out/us/fips-state.d.ts +19 -10
- package/out/us/fips-state.d.ts.map +1 -1
- package/out/us/fips-state.js +17 -8
- package/out/us/fips-state.js.map +1 -1
- package/out/{synthesizers → us/synthesizers}/intersection.d.ts +10 -8
- package/out/us/synthesizers/intersection.d.ts.map +1 -0
- package/out/{synthesizers → us/synthesizers}/intersection.js +46 -35
- package/out/us/synthesizers/intersection.js.map +1 -0
- package/out/{synthesizers → us/synthesizers}/street.d.ts +19 -12
- package/out/us/synthesizers/street.d.ts.map +1 -0
- package/out/{synthesizers → us/synthesizers}/street.js +45 -38
- package/out/us/synthesizers/street.js.map +1 -0
- package/out/us/tools/fetch/hrsa.d.ts +3 -3
- package/out/us/tools/fetch/hrsa.d.ts.map +1 -1
- package/out/us/tools/fetch/hrsa.js +6 -7
- package/out/us/tools/fetch/hrsa.js.map +1 -1
- package/out/us/tools/fetch/imls-pls.d.ts +5 -16
- package/out/us/tools/fetch/imls-pls.d.ts.map +1 -1
- package/out/us/tools/fetch/imls-pls.js +17 -34
- package/out/us/tools/fetch/imls-pls.js.map +1 -1
- package/out/us/tools/fetch/nad.d.ts +22 -10
- package/out/us/tools/fetch/nad.d.ts.map +1 -1
- package/out/us/tools/fetch/nad.js +30 -25
- package/out/us/tools/fetch/nad.js.map +1 -1
- package/out/us/tools/fetch/nppes.d.ts +6 -16
- package/out/us/tools/fetch/nppes.d.ts.map +1 -1
- package/out/us/tools/fetch/nppes.js +24 -36
- package/out/us/tools/fetch/nppes.js.map +1 -1
- package/out/us/tools/fetch/state/hi-schools.d.ts +9 -5
- package/out/us/tools/fetch/state/hi-schools.d.ts.map +1 -1
- package/out/us/tools/fetch/state/hi-schools.js +16 -14
- package/out/us/tools/fetch/state/hi-schools.js.map +1 -1
- package/out/us/tools/fetch/state/sources.d.ts +8 -7
- package/out/us/tools/fetch/state/sources.d.ts.map +1 -1
- package/out/us/tools/fetch/state/sources.js +8 -9
- package/out/us/tools/fetch/state/sources.js.map +1 -1
- package/out/us/tools/fetch/tiger-full.d.ts +1 -14
- package/out/us/tools/fetch/tiger-full.d.ts.map +1 -1
- package/out/us/tools/fetch/tiger-full.js +16 -55
- package/out/us/tools/fetch/tiger-full.js.map +1 -1
- package/out/utils/align.d.ts +26 -19
- package/out/utils/align.d.ts.map +1 -1
- package/out/utils/align.js +32 -47
- package/out/utils/align.js.map +1 -1
- package/out/utils/cooccurrence-stats.d.ts +58 -0
- package/out/utils/cooccurrence-stats.d.ts.map +1 -0
- package/out/utils/cooccurrence-stats.js +62 -0
- package/out/utils/cooccurrence-stats.js.map +1 -0
- package/out/utils/golden.d.ts +21 -31
- package/out/utils/golden.d.ts.map +1 -1
- package/out/utils/golden.js +30 -46
- package/out/utils/golden.js.map +1 -1
- package/out/utils/license.d.ts +159 -22
- package/out/utils/license.d.ts.map +1 -1
- package/out/utils/license.js +156 -26
- package/out/utils/license.js.map +1 -1
- package/out/utils/split.d.ts +66 -70
- package/out/utils/split.d.ts.map +1 -1
- package/out/utils/split.js +162 -69
- package/out/utils/split.js.map +1 -1
- package/out/utils/tokenize.d.ts +15 -44
- package/out/utils/tokenize.d.ts.map +1 -1
- package/out/utils/tokenize.js +18 -31
- package/out/utils/tokenize.js.map +1 -1
- package/out/utils/wof-json.d.ts +88 -62
- package/out/utils/wof-json.d.ts.map +1 -1
- package/out/utils/wof-json.js +77 -56
- package/out/utils/wof-json.js.map +1 -1
- package/out/{utils/index.js → utils.d.ts} +1 -2
- package/out/utils.d.ts.map +1 -0
- package/out/{utils/index.d.ts → utils.js} +1 -2
- package/out/utils.js.map +1 -0
- package/out/ve/recipes/reviewed-postcode-tail.d.ts +25 -7
- package/out/ve/recipes/reviewed-postcode-tail.d.ts.map +1 -1
- package/out/ve/recipes/reviewed-postcode-tail.js +33 -12
- package/out/ve/recipes/reviewed-postcode-tail.js.map +1 -1
- package/package.json +45 -488
- package/lib/adapters/index.ts +0 -160
- package/lib/adapters/synth-po-box/adapter.ts +0 -204
- package/lib/adapters/utils/index.ts +0 -307
- package/lib/recipes/bare/postcode/index.ts +0 -327
- package/lib/recipes/sub/venue/index.ts +0 -997
- package/lib/synthesizers/locale.ts +0 -261
- package/lib/test-kit/index.ts +0 -100
- package/lib/tools/align-slice.ts +0 -68
- package/lib/tools/fetch/index.ts +0 -174
- package/lib/tools/gb-title-case.ts +0 -69
- package/lib/tools/index.ts +0 -28
- package/lib/tools/lint/slice/vocab.ts +0 -376
- package/lib/tools/overlay-manifest.ts +0 -215
- package/lib/tools/slice/translit.ts +0 -218
- package/lib/tools/sub/venue/harvest.ts +0 -234
- package/lib/tools/sub/venue/surfaces.ts +0 -95
- package/lib/tools/sub/venue/table.ts +0 -281
- package/lib/utils/parquet.ts +0 -582
- package/out/adapters/index.d.ts +0 -51
- package/out/adapters/index.d.ts.map +0 -1
- package/out/adapters/index.js +0 -97
- package/out/adapters/index.js.map +0 -1
- package/out/adapters/synth-po-box/adapter.d.ts +0 -67
- package/out/adapters/synth-po-box/adapter.d.ts.map +0 -1
- package/out/adapters/synth-po-box/adapter.js.map +0 -1
- package/out/adapters/utils/index.d.ts +0 -191
- package/out/adapters/utils/index.d.ts.map +0 -1
- package/out/adapters/utils/index.js +0 -206
- package/out/adapters/utils/index.js.map +0 -1
- package/out/fr/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/fr/adapters/ban/street-decompose.js.map +0 -1
- package/out/no/recipes/street/index.d.ts +0 -18
- package/out/no/recipes/street/index.d.ts.map +0 -1
- package/out/no/recipes/street/index.js.map +0 -1
- package/out/recipes/bare/postcode/index.d.ts +0 -62
- package/out/recipes/bare/postcode/index.d.ts.map +0 -1
- package/out/recipes/bare/postcode/index.js.map +0 -1
- package/out/recipes/index.d.ts +0 -24
- package/out/recipes/index.d.ts.map +0 -1
- package/out/recipes/index.js.map +0 -1
- package/out/recipes/po/box/index.d.ts +0 -17
- package/out/recipes/po/box/index.d.ts.map +0 -1
- package/out/recipes/po/box/index.js.map +0 -1
- package/out/recipes/sub/venue/index.d.ts +0 -270
- package/out/recipes/sub/venue/index.d.ts.map +0 -1
- package/out/recipes/sub/venue/index.js +0 -728
- package/out/recipes/sub/venue/index.js.map +0 -1
- package/out/synthesizers/intersection.d.ts.map +0 -1
- package/out/synthesizers/intersection.js.map +0 -1
- package/out/synthesizers/locale.d.ts +0 -116
- package/out/synthesizers/locale.d.ts.map +0 -1
- package/out/synthesizers/locale.js +0 -150
- package/out/synthesizers/locale.js.map +0 -1
- package/out/synthesizers/street.d.ts.map +0 -1
- package/out/synthesizers/street.js.map +0 -1
- package/out/test-kit/index.d.ts +0 -48
- package/out/test-kit/index.d.ts.map +0 -1
- package/out/test-kit/index.js +0 -78
- package/out/test-kit/index.js.map +0 -1
- package/out/tools/align-slice.d.ts +0 -7
- package/out/tools/align-slice.d.ts.map +0 -1
- package/out/tools/align-slice.js +0 -55
- package/out/tools/align-slice.js.map +0 -1
- package/out/tools/fetch/download/index.d.ts.map +0 -1
- package/out/tools/fetch/download/index.js.map +0 -1
- package/out/tools/fetch/index.d.ts +0 -171
- package/out/tools/fetch/index.d.ts.map +0 -1
- package/out/tools/fetch/index.js +0 -170
- package/out/tools/fetch/index.js.map +0 -1
- package/out/tools/gb-title-case.d.ts +0 -2
- package/out/tools/gb-title-case.d.ts.map +0 -1
- package/out/tools/gb-title-case.js +0 -65
- package/out/tools/gb-title-case.js.map +0 -1
- package/out/tools/golden/relabel-street/index.d.ts.map +0 -1
- package/out/tools/golden/relabel-street/index.js.map +0 -1
- package/out/tools/index.d.ts +0 -28
- package/out/tools/index.d.ts.map +0 -1
- package/out/tools/index.js +0 -28
- package/out/tools/index.js.map +0 -1
- package/out/tools/lint/slice/index.d.ts +0 -93
- package/out/tools/lint/slice/index.d.ts.map +0 -1
- package/out/tools/lint/slice/index.js.map +0 -1
- package/out/tools/lint/slice/vocab.d.ts +0 -90
- package/out/tools/lint/slice/vocab.d.ts.map +0 -1
- package/out/tools/lint/slice/vocab.js.map +0 -1
- package/out/tools/overlay-manifest.d.ts +0 -89
- package/out/tools/overlay-manifest.d.ts.map +0 -1
- package/out/tools/overlay-manifest.js +0 -131
- package/out/tools/overlay-manifest.js.map +0 -1
- package/out/tools/slice/kryptonite.d.ts +0 -32
- package/out/tools/slice/kryptonite.d.ts.map +0 -1
- package/out/tools/slice/kryptonite.js.map +0 -1
- package/out/tools/slice/translit.d.ts +0 -51
- package/out/tools/slice/translit.d.ts.map +0 -1
- package/out/tools/slice/translit.js.map +0 -1
- package/out/tools/sub/venue/harvest.d.ts +0 -100
- package/out/tools/sub/venue/harvest.d.ts.map +0 -1
- package/out/tools/sub/venue/harvest.js +0 -168
- package/out/tools/sub/venue/harvest.js.map +0 -1
- package/out/tools/sub/venue/promotions.d.ts +0 -94
- package/out/tools/sub/venue/promotions.d.ts.map +0 -1
- package/out/tools/sub/venue/promotions.js.map +0 -1
- package/out/tools/sub/venue/surfaces.d.ts +0 -45
- package/out/tools/sub/venue/surfaces.d.ts.map +0 -1
- package/out/tools/sub/venue/surfaces.js +0 -77
- package/out/tools/sub/venue/surfaces.js.map +0 -1
- package/out/tools/sub/venue/table.d.ts +0 -229
- package/out/tools/sub/venue/table.d.ts.map +0 -1
- package/out/tools/sub/venue/table.js +0 -108
- package/out/tools/sub/venue/table.js.map +0 -1
- package/out/utils/index.d.ts.map +0 -1
- package/out/utils/index.js.map +0 -1
- package/out/utils/parquet.d.ts +0 -178
- package/out/utils/parquet.d.ts.map +0 -1
- package/out/utils/parquet.js +0 -371
- package/out/utils/parquet.js.map +0 -1
- package/out/utils/slice-stats.d.ts +0 -52
- package/out/utils/slice-stats.d.ts.map +0 -1
- package/out/utils/slice-stats.js +0 -58
- package/out/utils/slice-stats.js.map +0 -1
- /package/lib/tools/fetch/{download/index.ts → download.ts} +0 -0
- /package/lib/tools/golden/{relabel-street/index.ts → relabel-street.ts} +0 -0
|
@@ -3,36 +3,13 @@
|
|
|
3
3
|
* @license AGPL-3.0
|
|
4
4
|
* @author Teffen Ellis, et al.
|
|
5
5
|
*
|
|
6
|
-
*
|
|
7
|
-
*
|
|
8
|
-
* The v0.6.2 step-20K diagnostic showed that adding synth-no-street counter-distribution regressed
|
|
9
|
-
* house_number recall by ~4-5pp. DeepSeek's turn-8 root-cause:
|
|
10
|
-
*
|
|
11
|
-
* 1. Direct: `5th Avenue Theatre`-style adversarial venues teach the model that tokens like "5th"
|
|
12
|
-
* belong to venues, not house_numbers. (Fixed in `no-street.ts` by removing
|
|
13
|
-
* digit+ordinal venue patterns.)
|
|
14
|
-
* 2. Distributional dilution: synth-no-street adds 122K rows where house_number is absent. The model's
|
|
15
|
-
* training distribution shifts toward "house_number is rare," and it under-emits the tag at
|
|
16
|
-
* inference.
|
|
17
|
-
*
|
|
18
|
-
* This synthesizer fixes #2 directly. Each emitted row has ALL of: house_number, street, venue,
|
|
19
|
-
* locality, region, postcode — a counter-example to "house_number is rare." Used as a companion
|
|
20
|
-
* slice to synth-no-street; the v0.6.3 config weights synth-no-street at 0.5 and
|
|
21
|
-
* synth-house-venue at 1.0 to recover the lost house_number signal.
|
|
22
|
-
*
|
|
23
|
-
* Real-world shape: business cards, mailing labels, store directories — `"123 Main St, Sunrise
|
|
24
|
-
* Bakery, Springfield, IL 62701"` is a perfectly ordinary address form.
|
|
25
|
-
*
|
|
26
|
-
* Venue pool: PLAIN_VENUES from `no-street.ts` (re-exported here). Adversarial venues
|
|
27
|
-
* are deliberately NOT used here — the point is to teach co-occurrence, not to re-introduce
|
|
28
|
-
* decompose-mode pressure.
|
|
29
|
-
*/
|
|
30
|
-
import { countryToLocale, pick } from "#synthesizers/utils";
|
|
31
|
-
//#region Venue pool
|
|
32
|
-
/**
|
|
33
|
-
* PLAIN venue names, carrying no street-typing tokens. This slice teaches house_number + venue coexistence, NOT
|
|
34
|
-
* decompose-mode pressure — adversarial venue names live in `no-street.ts`.
|
|
6
|
+
* Generates addresses in which a house number, a street and a venue appear together.
|
|
35
7
|
*/
|
|
8
|
+
import { sample } from "@mailwoman/core/random";
|
|
9
|
+
import { layoutAdminTail } from "#synthesizers/tail";
|
|
10
|
+
import { countryToLocale } from "#synthesizers/utils";
|
|
11
|
+
// #region Venue pool
|
|
12
|
+
// Venue names in this pool avoid street-like words.
|
|
36
13
|
const PLAIN_VENUES = [
|
|
37
14
|
"Bob's Pizza",
|
|
38
15
|
"Acme Corporation",
|
|
@@ -41,9 +18,7 @@ const PLAIN_VENUES = [
|
|
|
41
18
|
"Maple Leaf Cafe",
|
|
42
19
|
"Riverside Garden Center",
|
|
43
20
|
"Tech Solutions Inc",
|
|
44
|
-
//
|
|
45
|
-
// international/English names at FR addresses, but native forms must appear too — the register
|
|
46
|
-
// mixes both in real Paris data.
|
|
21
|
+
// French addresses include both English and French venue names, so the pool includes both.
|
|
47
22
|
"Café de la Poste",
|
|
48
23
|
"Boulangerie Saint-Michel",
|
|
49
24
|
"Le Petit Bistrot",
|
|
@@ -66,12 +41,7 @@ const PLAIN_VENUES = [
|
|
|
66
41
|
"Pinecrest Veterinary",
|
|
67
42
|
"Westwood Realty",
|
|
68
43
|
];
|
|
69
|
-
|
|
70
|
-
* GB-flavored venue names (#1366): institutional forms (Club/Centre/House/Arms/Station), the "Ye" archaic register, and
|
|
71
|
-
* brand–dash–place compounds — INCLUDING directional-led names, because the target class is venues that open with
|
|
72
|
-
* compass words ("New North Health Centre", "Southfields Station") and the base model reads those as locality/street
|
|
73
|
-
* evidence. The six #1366 gauntlet fixtures' own venue names are deliberately ABSENT — the fixtures stay held-out.
|
|
74
|
-
*/
|
|
44
|
+
// This pool must exclude the venue names in the held-out gauntlet fixtures.
|
|
75
45
|
const GB_VENUES = [
|
|
76
46
|
"Ye Olde Cheshire Cheese",
|
|
77
47
|
"Ye Old Mitre",
|
|
@@ -102,11 +72,8 @@ const GB_VENUES = [
|
|
|
102
72
|
"Imperial Dry Cleaners",
|
|
103
73
|
"Golden Dragon 金龍饭店",
|
|
104
74
|
];
|
|
105
|
-
|
|
106
|
-
|
|
107
|
-
/**
|
|
108
|
-
* Stand-in streets for tuples that carried no `street` field. Plain names, no typing-token ambiguity.
|
|
109
|
-
*/
|
|
75
|
+
// #endregion
|
|
76
|
+
// #region Fallback street pool
|
|
110
77
|
const FALLBACK_STREETS = [
|
|
111
78
|
"Main St",
|
|
112
79
|
"Oak Ave",
|
|
@@ -124,39 +91,21 @@ const FALLBACK_STREETS = [
|
|
|
124
91
|
"River Ln",
|
|
125
92
|
"Forest Blvd",
|
|
126
93
|
];
|
|
127
|
-
|
|
128
|
-
|
|
94
|
+
// #endregion
|
|
95
|
+
// #region House-number generator
|
|
129
96
|
function randomHouseNumber(random) {
|
|
130
|
-
//
|
|
131
|
-
// `data/eval/falsehoods/numbers.jsonl` as known edge cases, not training material.
|
|
97
|
+
// Each digit count from one to four is equally likely.
|
|
132
98
|
const digits = Math.floor(random() * 4) + 1;
|
|
133
99
|
const max = Math.pow(10, digits);
|
|
134
100
|
const n = Math.floor(random() * max) + 1;
|
|
135
101
|
return String(n);
|
|
136
102
|
}
|
|
137
|
-
|
|
138
|
-
|
|
139
|
-
/**
|
|
140
|
-
* Fraction of GB rows drawing from {@link GB_VENUES} instead of the shared pool. 0.7 mirrors the register mix in real
|
|
141
|
-
* GB listings data (institutional names dominate, international/generic names still appear) — pre-registered in the
|
|
142
|
-
* #1366 memo.
|
|
143
|
-
*/
|
|
103
|
+
// #endregion
|
|
104
|
+
// #region Synthesis
|
|
144
105
|
const GB_VENUE_POOL_RATE = 0.7;
|
|
145
|
-
/**
|
|
146
|
-
* Fraction of GB rows whose house number widens into a range ("287-293"). Real GB venue addresses frequently span
|
|
147
|
-
* buildings; 0.15 keeps ranges a minority register — pre-registered in the #1366 memo.
|
|
148
|
-
*/
|
|
149
106
|
const GB_RANGE_NUMBER_RATE = 0.15;
|
|
150
|
-
/**
|
|
151
|
-
* Fraction of rows (EVERY template order) rendered with a trailing country surface, tagged `country`. The 2026-08-01
|
|
152
|
-
* operator probe set proved the mechanism: the FR control row ("…, 75004 Paris, France") fails on a model trained only
|
|
153
|
-
* on country-less venue rows while its country-less twin passes — a trailing country makes the whole template OOD
|
|
154
|
-
* (Addendum 3 of the #1366 pre-registration). 0.3 keeps the country-less register dominant.
|
|
155
|
-
*/
|
|
156
107
|
const COUNTRY_APPEND_RATE = 0.3;
|
|
157
|
-
|
|
158
|
-
* Trailing country surfaces by tuple country — the register mixes formal and short forms where both are common.
|
|
159
|
-
*/
|
|
108
|
+
// Repeated entries weight the sample toward the more common form.
|
|
160
109
|
const COUNTRY_SURFACES = {
|
|
161
110
|
US: ["United States", "USA"],
|
|
162
111
|
GB: ["United Kingdom", "United Kingdom", "United Kingdom", "UK"],
|
|
@@ -165,83 +114,63 @@ const COUNTRY_SURFACES = {
|
|
|
165
114
|
AU: ["Australia"],
|
|
166
115
|
DE: ["Germany", "Deutschland"],
|
|
167
116
|
};
|
|
117
|
+
/**
|
|
118
|
+
* Synthesizes one row with a house number, a street, a venue and the tuple's admin tail,
|
|
119
|
+
* rendered through the country's codex layout.
|
|
120
|
+
* A country with no layout yields `null`.
|
|
121
|
+
*
|
|
122
|
+
* GB rows sometimes use British venue names and ranged house numbers.
|
|
123
|
+
*/
|
|
168
124
|
export function synthesizeHouseVenueRow(base, opts = {}) {
|
|
169
125
|
const random = opts.random ?? Math.random;
|
|
170
126
|
const locale = countryToLocale(base.country);
|
|
171
127
|
const template = opts.forceTemplate ?? (random() < 0.5 ? "venue-after-street" : "venue-before-street");
|
|
172
|
-
//
|
|
173
|
-
//
|
|
174
|
-
|
|
175
|
-
|
|
176
|
-
|
|
177
|
-
// keeps the original US-order tail, which is itself the `after_region` surface — `Springfield, IL
|
|
178
|
-
// 02101` and `Bengaluru, Karnataka 560038` are the same shape.
|
|
179
|
-
const frOrder = base.country === "FR";
|
|
180
|
-
const gbOrder = base.country === "GB";
|
|
181
|
-
// VE writes the code on the LOCALITY segment with the region still after it — `…, Barcelona 6001, Anzoátegui,
|
|
182
|
-
// Venezuela`, the four `ve_city_postcode_trailing_state` board rows. That is neither GB's form (which drops the
|
|
183
|
-
// region) nor the default (which puts the region before the code), so it needs its own branch.
|
|
184
|
-
//
|
|
185
|
-
// It belongs HERE rather than in a standalone admin slice, and that is measured: three trailing-region slices
|
|
186
|
-
// carrying only admin segments all graded DO-NOT-SHIP, and the way they failed was by damaging the classes they did
|
|
187
|
-
// not contain — v4.8.0 turned `Ye Three Lords, 27 Minories, London EC3N 1DE` into `locality: "Ye Three Lords"`,
|
|
188
|
-
// losing the venue and the street. Every row this synthesizer emits carries a venue, a street AND a house number,
|
|
189
|
-
// so the surface is taught with the alternatives present rather than against them.
|
|
190
|
-
const veOrder = base.country === "VE";
|
|
191
|
-
// GB rows draw from the GB pool 70% of the time (institutional/archaic/brand-dash-place forms,
|
|
192
|
-
// incl. directional-led names — the #1366 target class) and the shared pool otherwise; real GB
|
|
193
|
-
// registers mix both. Other locales keep the shared pool (which already carries the FR flavor).
|
|
194
|
-
const venue = gbOrder && random() < GB_VENUE_POOL_RATE ? pick(GB_VENUES, random) : pick(PLAIN_VENUES, random);
|
|
195
|
-
const street = base.street ?? pick(FALLBACK_STREETS, random);
|
|
128
|
+
// country-branch: the British venue pool and the ranged house number are GB English data.
|
|
129
|
+
// A per-country venue pool from the Overture names file would replace the branch.
|
|
130
|
+
const gbPools = base.country === "GB";
|
|
131
|
+
const venue = gbPools && random() < GB_VENUE_POOL_RATE ? sample(GB_VENUES, random) : sample(PLAIN_VENUES, random);
|
|
132
|
+
const street = base.street ?? sample(FALLBACK_STREETS, random);
|
|
196
133
|
let houseNumber = base.houseNumber ?? randomHouseNumber(random);
|
|
197
|
-
|
|
198
|
-
// 15% of GB rows widen the number into a range (same parity, small span — the register's real
|
|
199
|
-
// shape). Pre-registered in the #1366 memo; the base pool's no-ranges stance stays for other
|
|
200
|
-
// locales.
|
|
201
|
-
if (gbOrder && random() < GB_RANGE_NUMBER_RATE && /^\d+$/.test(houseNumber)) {
|
|
134
|
+
if (gbPools && random() < GB_RANGE_NUMBER_RATE && /^\d+$/.test(houseNumber)) {
|
|
202
135
|
const start = Number.parseInt(houseNumber, 10);
|
|
203
136
|
const span = (1 + Math.floor(random() * 4)) * 2;
|
|
204
137
|
houseNumber = `${start}-${start + span}`;
|
|
205
138
|
}
|
|
139
|
+
const countrySurfaces = COUNTRY_SURFACES[base.country];
|
|
140
|
+
const countrySurface = countrySurfaces && random() < COUNTRY_APPEND_RATE ? sample(countrySurfaces, random) : undefined;
|
|
141
|
+
// The layout decides the tail's order and which parts it prints: FR prints no region,
|
|
142
|
+
// VE keeps the region after the postcode, GB puts the postcode after the locality.
|
|
143
|
+
const tail = layoutAdminTail(base.country, {
|
|
144
|
+
locality: base.locality,
|
|
145
|
+
region: base.region,
|
|
146
|
+
postcode: base.postcode,
|
|
147
|
+
country: countrySurface,
|
|
148
|
+
});
|
|
149
|
+
if (!tail)
|
|
150
|
+
return null;
|
|
206
151
|
const components = {
|
|
207
152
|
house_number: houseNumber,
|
|
208
153
|
street,
|
|
209
154
|
venue,
|
|
210
|
-
|
|
211
|
-
...(frOrder || gbOrder ? {} : { region: base.region }),
|
|
212
|
-
postcode: base.postcode,
|
|
155
|
+
...tail.components,
|
|
213
156
|
};
|
|
214
|
-
let tail = frOrder
|
|
215
|
-
? `${base.postcode} ${base.locality}`
|
|
216
|
-
: gbOrder
|
|
217
|
-
? `${base.locality} ${base.postcode}`
|
|
218
|
-
: veOrder
|
|
219
|
-
? `${base.locality} ${base.postcode}, ${base.region}`
|
|
220
|
-
: `${base.locality}, ${base.region} ${base.postcode}`;
|
|
221
|
-
// Trailing country surface (Addendum 3): appended AFTER the tail in every order, tagged.
|
|
222
|
-
const countrySurfaces = COUNTRY_SURFACES[base.country];
|
|
223
|
-
if (countrySurfaces && random() < COUNTRY_APPEND_RATE) {
|
|
224
|
-
const countrySurface = pick(countrySurfaces, random);
|
|
225
|
-
components.country = countrySurface;
|
|
226
|
-
tail = `${tail}, ${countrySurface}`;
|
|
227
|
-
}
|
|
228
157
|
let raw;
|
|
229
158
|
switch (template) {
|
|
230
159
|
case "venue-after-street":
|
|
231
|
-
raw = `${houseNumber} ${street}, ${venue}, ${tail}`;
|
|
160
|
+
raw = `${houseNumber} ${street}, ${venue}, ${tail.raw}`;
|
|
232
161
|
break;
|
|
233
162
|
case "venue-before-street":
|
|
234
|
-
raw = `${venue}, ${houseNumber} ${street}, ${tail}`;
|
|
163
|
+
raw = `${venue}, ${houseNumber} ${street}, ${tail.raw}`;
|
|
235
164
|
break;
|
|
236
165
|
}
|
|
237
166
|
return { raw, components, locale, template };
|
|
238
167
|
}
|
|
239
168
|
/**
|
|
240
|
-
*
|
|
241
|
-
*
|
|
169
|
+
* Reports whether the components include both `house_number` and `venue`,
|
|
170
|
+
* which every row from this synthesizer does.
|
|
242
171
|
*/
|
|
243
172
|
export function hasHouseNumberAndVenue(components) {
|
|
244
173
|
return components.house_number !== undefined && components.venue !== undefined;
|
|
245
174
|
}
|
|
246
|
-
|
|
175
|
+
// #endregion
|
|
247
176
|
//# sourceMappingURL=house-venue.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"house-venue.js","sourceRoot":"","sources":["../../lib/synthesizers/house-venue.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"house-venue.js","sourceRoot":"","sources":["../../lib/synthesizers/house-venue.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH,OAAO,EAAE,MAAM,EAAE,MAAM,wBAAwB,CAAA;AAE/C,OAAO,EAAE,eAAe,EAAE,MAAM,oBAAoB,CAAA;AACpD,OAAO,EAAE,eAAe,EAAE,MAAM,qBAAqB,CAAA;AAuCrD,qBAAqB;AAErB,oDAAoD;AACpD,MAAM,YAAY,GAA0B;IAC3C,aAAa;IACb,kBAAkB;IAClB,aAAa;IACb,gBAAgB;IAChB,iBAAiB;IACjB,yBAAyB;IACzB,oBAAoB;IACpB,2FAA2F;IAC3F,kBAAkB;IAClB,0BAA0B;IAC1B,kBAAkB;IAClB,qBAAqB;IACrB,aAAa;IACb,iBAAiB;IACjB,oBAAoB;IACpB,oBAAoB;IACpB,oBAAoB;IACpB,mBAAmB;IACnB,oBAAoB;IACpB,qBAAqB;IACrB,sBAAsB;IACtB,iBAAiB;IACjB,eAAe;IACf,sBAAsB;IACtB,oBAAoB;IACpB,yBAAyB;IACzB,4BAA4B;IAC5B,sBAAsB;IACtB,iBAAiB;CACjB,CAAA;AAED,4EAA4E;AAC5E,MAAM,SAAS,GAA0B;IACxC,yBAAyB;IACzB,cAAc;IACd,cAAc;IACd,oBAAoB;IACpB,iBAAiB;IACjB,gBAAgB;IAChB,eAAe;IACf,uBAAuB;IACvB,8BAA8B;IAC9B,mBAAmB;IACnB,2BAA2B;IAC3B,kBAAkB;IAClB,sBAAsB;IACtB,2BAA2B;IAC3B,kBAAkB;IAClB,wBAAwB;IACxB,4BAA4B;IAC5B,6BAA6B;IAC7B,0BAA0B;IAC1B,6BAA6B;IAC7B,2BAA2B;IAC3B,wBAAwB;IACxB,6BAA6B;IAC7B,qBAAqB;IACrB,sBAAsB;IACtB,cAAc;IACd,uBAAuB;IACvB,oBAAoB;CACpB,CAAA;AAED,aAAa;AAEb,+BAA+B;AAE/B,MAAM,gBAAgB,GAA0B;IAC/C,SAAS;IACT,SAAS;IACT,SAAS;IACT,QAAQ;IACR,UAAU;IACV,YAAY;IACZ,UAAU;IACV,WAAW;IACX,YAAY;IACZ,WAAW;IACX,UAAU;IACV,SAAS;IACT,SAAS;IACT,UAAU;IACV,aAAa;CACb,CAAA;AAED,aAAa;AAEb,iCAAiC;AAEjC,SAAS,iBAAiB,CAAC,MAAoB;IAC9C,uDAAuD;IACvD,MAAM,MAAM,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,GAAG,CAAC,CAAA;IAC3C,MAAM,GAAG,GAAG,IAAI,CAAC,GAAG,CAAC,EAAE,EAAE,MAAM,CAAC,CAAA;IAChC,MAAM,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,GAAG,CAAC,GAAG,CAAC,CAAA;IAExC,OAAO,MAAM,CAAC,CAAC,CAAC,CAAA;AACjB,CAAC;AAED,aAAa;AAEb,oBAAoB;AAEpB,MAAM,kBAAkB,GAAG,GAAG,CAAA;AAE9B,MAAM,oBAAoB,GAAG,IAAI,CAAA;AAEjC,MAAM,mBAAmB,GAAG,GAAG,CAAA;AAE/B,kEAAkE;AAClE,MAAM,gBAAgB,GAAoD;IACzE,EAAE,EAAE,CAAC,eAAe,EAAE,KAAK,CAAC;IAC5B,EAAE,EAAE,CAAC,gBAAgB,EAAE,gBAAgB,EAAE,gBAAgB,EAAE,IAAI,CAAC;IAChE,EAAE,EAAE,CAAC,QAAQ,CAAC;IACd,EAAE,EAAE,CAAC,QAAQ,CAAC;IACd,EAAE,EAAE,CAAC,WAAW,CAAC;IACjB,EAAE,EAAE,CAAC,SAAS,EAAE,aAAa,CAAC;CAC9B,CAAA;AAED;;;;;;GAMG;AACH,MAAM,UAAU,uBAAuB,CACtC,IAAyB,EACzB,IAAI,GAA4B,EAAE;IAElC,MAAM,MAAM,GAAG,IAAI,CAAC,MAAM,IAAI,IAAI,CAAC,MAAM,CAAA;IACzC,MAAM,MAAM,GAAG,eAAe,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;IAC5C,MAAM,QAAQ,GAAG,IAAI,CAAC,aAAa,IAAI,CAAC,MAAM,EAAE,GAAG,GAAG,CAAC,CAAC,CAAC,oBAAoB,CAAC,CAAC,CAAC,qBAAqB,CAAC,CAAA;IAEtG,0FAA0F;IAC1F,kFAAkF;IAClF,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,KAAK,IAAI,CAAA;IAErC,MAAM,KAAK,GAAG,OAAO,IAAI,MAAM,EAAE,GAAG,kBAAkB,CAAC,CAAC,CAAC,MAAM,CAAC,SAAS,EAAE,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,YAAY,EAAE,MAAM,CAAC,CAAA;IACjH,MAAM,MAAM,GAAG,IAAI,CAAC,MAAM,IAAI,MAAM,CAAC,gBAAgB,EAAE,MAAM,CAAC,CAAA;IAC9D,IAAI,WAAW,GAAG,IAAI,CAAC,WAAW,IAAI,iBAAiB,CAAC,MAAM,CAAC,CAAA;IAE/D,IAAI,OAAO,IAAI,MAAM,EAAE,GAAG,oBAAoB,IAAI,OAAO,CAAC,IAAI,CAAC,WAAW,CAAC,EAAE,CAAC;QAC7E,MAAM,KAAK,GAAG,MAAM,CAAC,QAAQ,CAAC,WAAW,EAAE,EAAE,CAAC,CAAA;QAC9C,MAAM,IAAI,GAAG,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,CAAC,GAAG,CAAC,CAAA;QAE/C,WAAW,GAAG,GAAG,KAAK,IAAI,KAAK,GAAG,IAAI,EAAE,CAAA;IACzC,CAAC;IAED,MAAM,eAAe,GAAG,gBAAgB,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;IACtD,MAAM,cAAc,GAAG,eAAe,IAAI,MAAM,EAAE,GAAG,mBAAmB,CAAC,CAAC,CAAC,MAAM,CAAC,eAAe,EAAE,MAAM,CAAC,CAAC,CAAC,CAAC,SAAS,CAAA;IAEtH,sFAAsF;IACtF,mFAAmF;IACnF,MAAM,IAAI,GAAG,eAAe,CAAC,IAAI,CAAC,OAAO,EAAE;QAC1C,QAAQ,EAAE,IAAI,CAAC,QAAQ;QACvB,MAAM,EAAE,IAAI,CAAC,MAAM;QACnB,QAAQ,EAAE,IAAI,CAAC,QAAQ;QACvB,OAAO,EAAE,cAAc;KACvB,CAAC,CAAA;IAEF,IAAI,CAAC,IAAI;QAAE,OAAO,IAAI,CAAA;IAEtB,MAAM,UAAU,GAA+B;QAC9C,YAAY,EAAE,WAAW;QACzB,MAAM;QACN,KAAK;QACL,GAAG,IAAI,CAAC,UAAU;KAClB,CAAA;IAED,IAAI,GAAW,CAAA;IAEf,QAAQ,QAAQ,EAAE,CAAC;QAClB,KAAK,oBAAoB;YACxB,GAAG,GAAG,GAAG,WAAW,IAAI,MAAM,KAAK,KAAK,KAAK,IAAI,CAAC,GAAG,EAAE,CAAA;YACvD,MAAK;QACN,KAAK,qBAAqB;YACzB,GAAG,GAAG,GAAG,KAAK,KAAK,WAAW,IAAI,MAAM,KAAK,IAAI,CAAC,GAAG,EAAE,CAAA;YACvD,MAAK;IACP,CAAC;IAED,OAAO,EAAE,GAAG,EAAE,UAAU,EAAE,MAAM,EAAE,QAAQ,EAAE,CAAA;AAC7C,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,sBAAsB,CAAC,UAAsC;IAC5E,OAAO,UAAU,CAAC,YAAY,KAAK,SAAS,IAAI,UAAU,CAAC,KAAK,KAAK,SAAS,CAAA;AAC/E,CAAC;AAED,aAAa"}
|
|
@@ -3,38 +3,9 @@
|
|
|
3
3
|
* @license AGPL-3.0
|
|
4
4
|
* @author Teffen Ellis, et al.
|
|
5
5
|
*
|
|
6
|
-
*
|
|
7
|
-
*
|
|
8
|
-
*
|
|
9
|
-
* region, postcode, country}.
|
|
10
|
-
*
|
|
11
|
-
* Rationale: the [2026-05-28 night-2
|
|
12
|
-
* postmortem](../../docs/articles/evals/night-shifts/2026-05-28-night-2-postmortem.md) and the [layer-1
|
|
13
|
-
* eval](../../docs/articles/evals/experiments/2026-05-28-layer-1-morphology-fst.md) showed that synth-street
|
|
14
|
-
* pushed the model into a high-confidence "decompose mode" that leaked into `dependent_locality`.
|
|
15
|
-
* Per DeepSeek's turn-2 recipe, the model needs explicit counter-examples: addresses where the
|
|
16
|
-
* model should NOT emit street labels. This synthesizer is that source.
|
|
17
|
-
*
|
|
18
|
-
* Six row templates, each producing a {raw, components} pair with no street-side tags:
|
|
19
|
-
*
|
|
20
|
-
* 1. **Plain venue + locality + region + postcode** `"Bob's Pizza, Boston, MA 02101"`
|
|
21
|
-
* 2. **Adversarial venue (containing street-typing words)** `"Wall Street Industries, NY 10005"`,
|
|
22
|
-
* `"5th Avenue Theater, Seattle, WA"`, `"Highway 61 Diner, Memphis TN"`. These are the rows
|
|
23
|
-
* that v0.6.1's decompose-mode would mis-tag as street_prefix/suffix; explicit negative
|
|
24
|
-
* training kills that signal.
|
|
25
|
-
* 3. **Locality + region + postcode (minimal)** — `"Boston, MA 02101"`
|
|
26
|
-
* 4. **Locality + region** — `"Boston, MA"`
|
|
27
|
-
* 5. **Postcode-only** — `"02101"`
|
|
28
|
-
* 6. **Country-only** — `"United States"`, `"France"` (rare in real data, but the model has seen these
|
|
29
|
-
* and should not hallucinate streets on them).
|
|
30
|
-
*
|
|
31
|
-
* Output is a `CanonicalRow` with no street-side components. Alignment will produce BIO labels
|
|
32
|
-
* where every token is one of {`B-venue`, `I-venue`, `B-locality`, `I-locality`, `B-region`,
|
|
33
|
-
* `B-postcode`, `B-country`, `I-country`, `O`} — explicitly never any street tag. That IS the
|
|
34
|
-
* counter-example signal the model is missing.
|
|
35
|
-
*
|
|
36
|
-
* This complements (does not replace) the existing US-base-tuple source used by
|
|
37
|
-
* `po-box.ts`; the same `NoStreetBaseTuple` shape is consumed.
|
|
6
|
+
* Generate addresses without street components as counterexamples for street-heavy training data.
|
|
7
|
+
* Templates cover venues, localities, postcodes or countries. Some venue names contain
|
|
8
|
+
* street-like words. Output components never include street-side tags.
|
|
38
9
|
*/
|
|
39
10
|
import type { CanonicalRow } from "#types";
|
|
40
11
|
export interface NoStreetBaseTuple {
|
|
@@ -58,14 +29,13 @@ export interface SynthesizedNoStreetRow {
|
|
|
58
29
|
template: NoStreetTemplate;
|
|
59
30
|
}
|
|
60
31
|
/**
|
|
61
|
-
* Generate one no-street
|
|
62
|
-
* by weighted random; the venue templates are the critical counter-distribution against synth-street's decompose-mode
|
|
63
|
-
* pressure.
|
|
32
|
+
* Generate one no-street row from a base tuple with locality, region, postcode or country.
|
|
64
33
|
*/
|
|
65
34
|
export declare function synthesizeNoStreetRow(base: NoStreetBaseTuple, opts?: NoStreetSynthesisOpts): SynthesizedNoStreetRow | null;
|
|
66
35
|
/**
|
|
67
|
-
* Convenience: assert at type-level that a synthesized row
|
|
68
|
-
*
|
|
36
|
+
* Convenience: assert at type-level that a synthesized row has no street-side components.
|
|
37
|
+
*
|
|
38
|
+
* Used by tests + downstream consumers who want to check the interface behavior at runtime.
|
|
69
39
|
*/
|
|
70
40
|
export declare const STREET_SIDE_TAGS: readonly ["street", "street_prefix", "street_prefix_particle", "street_suffix", "house_number", "intersection_a", "intersection_b", "unit"];
|
|
71
41
|
export declare function hasAnyStreetSideTag(components: CanonicalRow["components"]): boolean;
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"no-street.d.ts","sourceRoot":"","sources":["../../lib/synthesizers/no-street.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"no-street.d.ts","sourceRoot":"","sources":["../../lib/synthesizers/no-street.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAQH,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,QAAQ,CAAA;AAU1C,MAAM,WAAW,iBAAiB;IACjC,QAAQ,EAAE,MAAM,CAAA;IAChB,MAAM,EAAE,MAAM,CAAA;IACd,QAAQ,EAAE,MAAM,CAAA;IAChB,OAAO,EAAE,MAAM,CAAA;CACf;AAED,MAAM,MAAM,gBAAgB,GACzB,aAAa,GACb,mBAAmB,GACnB,0BAA0B,GAC1B,iBAAiB,GACjB,eAAe,GACf,cAAc,CAAA;AAEjB,MAAM,WAAW,qBAAqB;IACrC,MAAM,CAAC,EAAE,MAAM,MAAM,CAAA;IACrB;;OAEG;IACH,aAAa,CAAC,EAAE,gBAAgB,CAAA;CAChC;AAED,MAAM,WAAW,sBAAsB;IACtC,GAAG,EAAE,MAAM,CAAA;IACX,UAAU,EAAE,YAAY,CAAC,YAAY,CAAC,CAAA;IACtC,MAAM,EAAE,MAAM,CAAA;IACd,QAAQ,EAAE,gBAAgB,CAAA;CAC1B;AA+FD;;GAEG;AACH,wBAAgB,qBAAqB,CACpC,IAAI,EAAE,iBAAiB,EACvB,IAAI,GAAE,qBAA0B,GAC9B,sBAAsB,GAAG,IAAI,CAyE/B;AA0BD;;;;GAIG;AACH,eAAO,MAAM,gBAAgB,YAC5B,QAAQ,EACR,eAAe,EACf,wBAAwB,EACxB,eAAe,EACf,cAAc,EACd,gBAAgB,EAChB,gBAAgB,EAChB,MAAM,CACG,CAAA;AAEV,wBAAgB,mBAAmB,CAAC,UAAU,EAAE,YAAY,CAAC,YAAY,CAAC,GAAG,OAAO,CAMnF"}
|
|
@@ -3,45 +3,18 @@
|
|
|
3
3
|
* @license AGPL-3.0
|
|
4
4
|
* @author Teffen Ellis, et al.
|
|
5
5
|
*
|
|
6
|
-
*
|
|
7
|
-
*
|
|
8
|
-
*
|
|
9
|
-
* region, postcode, country}.
|
|
10
|
-
*
|
|
11
|
-
* Rationale: the [2026-05-28 night-2
|
|
12
|
-
* postmortem](../../docs/articles/evals/night-shifts/2026-05-28-night-2-postmortem.md) and the [layer-1
|
|
13
|
-
* eval](../../docs/articles/evals/experiments/2026-05-28-layer-1-morphology-fst.md) showed that synth-street
|
|
14
|
-
* pushed the model into a high-confidence "decompose mode" that leaked into `dependent_locality`.
|
|
15
|
-
* Per DeepSeek's turn-2 recipe, the model needs explicit counter-examples: addresses where the
|
|
16
|
-
* model should NOT emit street labels. This synthesizer is that source.
|
|
17
|
-
*
|
|
18
|
-
* Six row templates, each producing a {raw, components} pair with no street-side tags:
|
|
19
|
-
*
|
|
20
|
-
* 1. **Plain venue + locality + region + postcode** `"Bob's Pizza, Boston, MA 02101"`
|
|
21
|
-
* 2. **Adversarial venue (containing street-typing words)** `"Wall Street Industries, NY 10005"`,
|
|
22
|
-
* `"5th Avenue Theater, Seattle, WA"`, `"Highway 61 Diner, Memphis TN"`. These are the rows
|
|
23
|
-
* that v0.6.1's decompose-mode would mis-tag as street_prefix/suffix; explicit negative
|
|
24
|
-
* training kills that signal.
|
|
25
|
-
* 3. **Locality + region + postcode (minimal)** — `"Boston, MA 02101"`
|
|
26
|
-
* 4. **Locality + region** — `"Boston, MA"`
|
|
27
|
-
* 5. **Postcode-only** — `"02101"`
|
|
28
|
-
* 6. **Country-only** — `"United States"`, `"France"` (rare in real data, but the model has seen these
|
|
29
|
-
* and should not hallucinate streets on them).
|
|
30
|
-
*
|
|
31
|
-
* Output is a `CanonicalRow` with no street-side components. Alignment will produce BIO labels
|
|
32
|
-
* where every token is one of {`B-venue`, `I-venue`, `B-locality`, `I-locality`, `B-region`,
|
|
33
|
-
* `B-postcode`, `B-country`, `I-country`, `O`} — explicitly never any street tag. That IS the
|
|
34
|
-
* counter-example signal the model is missing.
|
|
35
|
-
*
|
|
36
|
-
* This complements (does not replace) the existing US-base-tuple source used by
|
|
37
|
-
* `po-box.ts`; the same `NoStreetBaseTuple` shape is consumed.
|
|
6
|
+
* Generate addresses without street components as counterexamples for street-heavy training data.
|
|
7
|
+
* Templates cover venues, localities, postcodes or countries. Some venue names contain
|
|
8
|
+
* street-like words. Output components never include street-side tags.
|
|
38
9
|
*/
|
|
39
|
-
import {
|
|
40
|
-
|
|
41
|
-
|
|
10
|
+
import { formatAddressRow } from "@mailwoman/codex/address/format";
|
|
11
|
+
import { countryCodeForTable } from "@mailwoman/codex/country";
|
|
12
|
+
import { sample } from "@mailwoman/core/random";
|
|
13
|
+
import { countryToLocale } from "#synthesizers/utils";
|
|
14
|
+
// #endregion
|
|
15
|
+
// #region Venue name pools
|
|
42
16
|
/**
|
|
43
|
-
*
|
|
44
|
-
* venue detection.
|
|
17
|
+
* Venue names without street-like words.
|
|
45
18
|
*/
|
|
46
19
|
const PLAIN_VENUES = [
|
|
47
20
|
"Bob's Pizza",
|
|
@@ -66,15 +39,10 @@ const PLAIN_VENUES = [
|
|
|
66
39
|
"Westwood Realty",
|
|
67
40
|
];
|
|
68
41
|
/**
|
|
69
|
-
*
|
|
70
|
-
* Court, Plaza, Park, ...) but are themselves venues, not streets. The model must learn that these are venues despite
|
|
71
|
-
* the street-typing tokens.
|
|
42
|
+
* Venue names containing street-like words.
|
|
72
43
|
*
|
|
73
|
-
*
|
|
74
|
-
*
|
|
75
|
-
* — tokens like "5th" (which should be `B-house_number` in real addresses) were being labeled `B-venue` because
|
|
76
|
-
* adversarial venues placed them in venue position. v0.6.3 omits these patterns; the `synth-house-venue` slice
|
|
77
|
-
* separately teaches that house_number and venue coexist.
|
|
44
|
+
* Avoid leading digit-plus-ordinal forms because they can confuse house-number labels.
|
|
45
|
+
* `invented-house-venue` covers house-number and venue co-occurrence.
|
|
78
46
|
*/
|
|
79
47
|
const ADVERSARIAL_VENUES = [
|
|
80
48
|
"Wall Street Industries",
|
|
@@ -106,9 +74,10 @@ const ADVERSARIAL_VENUES = [
|
|
|
106
74
|
"Beach Boulevard Diner",
|
|
107
75
|
"Garden Lane Florist",
|
|
108
76
|
];
|
|
109
|
-
// Compile-time guard: every venue must
|
|
110
|
-
// confuses house_number recognition.
|
|
111
|
-
//
|
|
77
|
+
// Compile-time guard: every venue must not start with the digit+ordinal pattern
|
|
78
|
+
// that confuses house_number recognition.
|
|
79
|
+
// If a future contributor adds a "5th Avenue Theatre"- style entry,
|
|
80
|
+
// this assertion will fire at module load time.
|
|
112
81
|
for (const v of ADVERSARIAL_VENUES) {
|
|
113
82
|
if (/^\d+(st|nd|rd|th)\b/i.test(v)) {
|
|
114
83
|
throw new Error(`ADVERSARIAL_VENUES entry "${v}" starts with digit+ordinal; this pattern confuses ` +
|
|
@@ -123,76 +92,51 @@ const COUNTRY_NAMES = new Map([
|
|
|
123
92
|
["CA", ["Canada"]],
|
|
124
93
|
["AU", ["Australia"]],
|
|
125
94
|
]);
|
|
126
|
-
|
|
127
|
-
|
|
95
|
+
// #endregion
|
|
96
|
+
// #region Synthesis
|
|
128
97
|
/**
|
|
129
|
-
* Generate one no-street
|
|
130
|
-
* by weighted random; the venue templates are the critical counter-distribution against synth-street's decompose-mode
|
|
131
|
-
* pressure.
|
|
98
|
+
* Generate one no-street row from a base tuple with locality, region, postcode or country.
|
|
132
99
|
*/
|
|
133
100
|
export function synthesizeNoStreetRow(base, opts = {}) {
|
|
134
101
|
const random = opts.random ?? Math.random;
|
|
135
102
|
const locale = countryToLocale(base.country);
|
|
136
103
|
const template = opts.forceTemplate ?? pickTemplate(random);
|
|
104
|
+
// Address layouts are keyed by ISO alpha-2 codes.
|
|
105
|
+
const iso2 = countryCodeForTable(base.country);
|
|
106
|
+
if (!iso2)
|
|
107
|
+
return null;
|
|
108
|
+
/**
|
|
109
|
+
* Render components with the country's address layout and return only fields present in the output.
|
|
110
|
+
*/
|
|
111
|
+
const render = (extra, carry) => {
|
|
112
|
+
const dict = { ...extra };
|
|
113
|
+
if (carry.locality && base.locality) {
|
|
114
|
+
dict.locality = base.locality;
|
|
115
|
+
}
|
|
116
|
+
if (carry.region && base.region?.trim()) {
|
|
117
|
+
dict.region = base.region;
|
|
118
|
+
}
|
|
119
|
+
if (carry.postcode && base.postcode) {
|
|
120
|
+
dict.postcode = base.postcode;
|
|
121
|
+
}
|
|
122
|
+
const rendered = formatAddressRow(dict, iso2, { singleLine: true });
|
|
123
|
+
if (!rendered)
|
|
124
|
+
return null;
|
|
125
|
+
return { raw: rendered.raw, components: rendered.components, locale, template };
|
|
126
|
+
};
|
|
137
127
|
switch (template) {
|
|
138
128
|
case "venue-plain": {
|
|
139
|
-
|
|
140
|
-
const raw = `${venue}, ${base.locality}, ${base.region} ${base.postcode}`;
|
|
141
|
-
return {
|
|
142
|
-
raw,
|
|
143
|
-
components: {
|
|
144
|
-
venue,
|
|
145
|
-
locality: base.locality,
|
|
146
|
-
region: base.region,
|
|
147
|
-
postcode: base.postcode,
|
|
148
|
-
},
|
|
149
|
-
locale,
|
|
150
|
-
template,
|
|
151
|
-
};
|
|
129
|
+
return render({ venue: sample(PLAIN_VENUES, random) }, { locality: true, region: true, postcode: true });
|
|
152
130
|
}
|
|
153
131
|
case "venue-adversarial": {
|
|
154
|
-
// The
|
|
155
|
-
|
|
156
|
-
// the OUTER template picker uses to bias toward this template versus the plain one;
|
|
157
|
-
// once we're inside this branch the choice is already made.
|
|
158
|
-
const venue = pick(ADVERSARIAL_VENUES, random);
|
|
159
|
-
const raw = `${venue}, ${base.locality}, ${base.region} ${base.postcode}`;
|
|
160
|
-
return {
|
|
161
|
-
raw,
|
|
162
|
-
components: {
|
|
163
|
-
venue,
|
|
164
|
-
locality: base.locality,
|
|
165
|
-
region: base.region,
|
|
166
|
-
postcode: base.postcode,
|
|
167
|
-
},
|
|
168
|
-
locale,
|
|
169
|
-
template,
|
|
170
|
-
};
|
|
132
|
+
// The template picker already selected the adversarial venue form.
|
|
133
|
+
return render({ venue: sample(ADVERSARIAL_VENUES, random) }, { locality: true, region: true, postcode: true });
|
|
171
134
|
}
|
|
172
135
|
case "locality-region-postcode": {
|
|
173
|
-
|
|
174
|
-
return {
|
|
175
|
-
raw,
|
|
176
|
-
components: {
|
|
177
|
-
locality: base.locality,
|
|
178
|
-
region: base.region,
|
|
179
|
-
postcode: base.postcode,
|
|
180
|
-
},
|
|
181
|
-
locale,
|
|
182
|
-
template,
|
|
183
|
-
};
|
|
136
|
+
return render({}, { locality: true, region: true, postcode: true });
|
|
184
137
|
}
|
|
185
138
|
case "locality-region": {
|
|
186
|
-
|
|
187
|
-
return {
|
|
188
|
-
raw,
|
|
189
|
-
components: {
|
|
190
|
-
locality: base.locality,
|
|
191
|
-
region: base.region,
|
|
192
|
-
},
|
|
193
|
-
locale,
|
|
194
|
-
template,
|
|
195
|
-
};
|
|
139
|
+
return render({}, { locality: true, region: true });
|
|
196
140
|
}
|
|
197
141
|
case "postcode-only": {
|
|
198
142
|
return {
|
|
@@ -204,7 +148,7 @@ export function synthesizeNoStreetRow(base, opts = {}) {
|
|
|
204
148
|
}
|
|
205
149
|
case "country-only": {
|
|
206
150
|
const names = COUNTRY_NAMES.get(base.country) ?? [base.country];
|
|
207
|
-
const country =
|
|
151
|
+
const country = sample(names, random);
|
|
208
152
|
return {
|
|
209
153
|
raw: country,
|
|
210
154
|
components: { country },
|
|
@@ -215,14 +159,13 @@ export function synthesizeNoStreetRow(base, opts = {}) {
|
|
|
215
159
|
}
|
|
216
160
|
}
|
|
217
161
|
/**
|
|
218
|
-
*
|
|
219
|
-
* the minimal templates as long-tail noise.
|
|
162
|
+
* Select a template, favoring venue examples over minimal address forms.
|
|
220
163
|
*/
|
|
221
164
|
function pickTemplate(random) {
|
|
222
165
|
const r = random();
|
|
223
166
|
if (r < 0.35)
|
|
224
167
|
return "venue-adversarial";
|
|
225
|
-
// 35% — the critical
|
|
168
|
+
// 35% — the critical pattern
|
|
226
169
|
if (r < 0.6)
|
|
227
170
|
return "venue-plain";
|
|
228
171
|
// 25%
|
|
@@ -238,8 +181,9 @@ function pickTemplate(random) {
|
|
|
238
181
|
return "country-only"; // 2%
|
|
239
182
|
}
|
|
240
183
|
/**
|
|
241
|
-
* Convenience: assert at type-level that a synthesized row
|
|
242
|
-
*
|
|
184
|
+
* Convenience: assert at type-level that a synthesized row has no street-side components.
|
|
185
|
+
*
|
|
186
|
+
* Used by tests + downstream consumers who want to check the interface behavior at runtime.
|
|
243
187
|
*/
|
|
244
188
|
export const STREET_SIDE_TAGS = [
|
|
245
189
|
"street",
|
|
@@ -258,5 +202,5 @@ export function hasAnyStreetSideTag(components) {
|
|
|
258
202
|
}
|
|
259
203
|
return false;
|
|
260
204
|
}
|
|
261
|
-
|
|
205
|
+
// #endregion
|
|
262
206
|
//# sourceMappingURL=no-street.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"no-street.js","sourceRoot":"","sources":["../../lib/synthesizers/no-street.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"no-street.js","sourceRoot":"","sources":["../../lib/synthesizers/no-street.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAEH,OAAO,EAAE,gBAAgB,EAAE,MAAM,iCAAiC,CAAA;AAElE,OAAO,EAAE,mBAAmB,EAAE,MAAM,0BAA0B,CAAA;AAC9D,OAAO,EAAE,MAAM,EAAE,MAAM,wBAAwB,CAAA;AAE/C,OAAO,EAAE,eAAe,EAAE,MAAM,qBAAqB,CAAA;AAyCrD,aAAa;AAEb,2BAA2B;AAE3B;;GAEG;AACH,MAAM,YAAY,GAA0B;IAC3C,aAAa;IACb,kBAAkB;IAClB,aAAa;IACb,gBAAgB;IAChB,iBAAiB;IACjB,yBAAyB;IACzB,oBAAoB;IACpB,oBAAoB;IACpB,mBAAmB;IACnB,oBAAoB;IACpB,qBAAqB;IACrB,sBAAsB;IACtB,iBAAiB;IACjB,eAAe;IACf,sBAAsB;IACtB,oBAAoB;IACpB,yBAAyB;IACzB,4BAA4B;IAC5B,sBAAsB;IACtB,iBAAiB;CACjB,CAAA;AAED;;;;;GAKG;AACH,MAAM,kBAAkB,GAA0B;IACjD,wBAAwB;IACxB,kBAAkB;IAClB,aAAa;IACb,oBAAoB;IACpB,0BAA0B;IAC1B,uBAAuB;IACvB,oBAAoB;IACpB,0BAA0B;IAC1B,kBAAkB;IAClB,0BAA0B;IAC1B,2BAA2B;IAC3B,eAAe;IACf,mBAAmB;IACnB,uBAAuB;IACvB,8BAA8B;IAC9B,4BAA4B;IAC5B,uBAAuB;IACvB,2BAA2B;IAC3B,aAAa;IACb,kBAAkB;IAClB,0BAA0B;IAC1B,gCAAgC;IAChC,+BAA+B;IAC/B,qBAAqB;IACrB,mBAAmB;IACnB,qBAAqB;IACrB,uBAAuB;IACvB,qBAAqB;CACrB,CAAA;AAED,gFAAgF;AAChF,0CAA0C;AAC1C,oEAAoE;AACpE,gDAAgD;AAChD,KAAK,MAAM,CAAC,IAAI,kBAAkB,EAAE,CAAC;IACpC,IAAI,sBAAsB,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC;QACpC,MAAM,IAAI,KAAK,CACd,6BAA6B,CAAC,qDAAqD;YAClF,+EAA+E,CAChF,CAAA;IACF,CAAC;AACF,CAAC;AAED,MAAM,aAAa,GAAG,IAAI,GAAG,CAAgC;IAC5D,CAAC,IAAI,EAAE,CAAC,eAAe,EAAE,KAAK,EAAE,QAAQ,EAAE,0BAA0B,CAAC,CAAC;IACtE,CAAC,IAAI,EAAE,CAAC,QAAQ,CAAC,CAAC;IAClB,CAAC,IAAI,EAAE,CAAC,SAAS,EAAE,aAAa,CAAC,CAAC;IAClC,CAAC,IAAI,EAAE,CAAC,gBAAgB,EAAE,IAAI,EAAE,eAAe,CAAC,CAAC;IACjD,CAAC,IAAI,EAAE,CAAC,QAAQ,CAAC,CAAC;IAClB,CAAC,IAAI,EAAE,CAAC,WAAW,CAAC,CAAC;CACrB,CAAC,CAAA;AAEF,aAAa;AAEb,oBAAoB;AAEpB;;GAEG;AACH,MAAM,UAAU,qBAAqB,CACpC,IAAuB,EACvB,IAAI,GAA0B,EAAE;IAEhC,MAAM,MAAM,GAAG,IAAI,CAAC,MAAM,IAAI,IAAI,CAAC,MAAM,CAAA;IACzC,MAAM,MAAM,GAAG,eAAe,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;IAE5C,MAAM,QAAQ,GAAqB,IAAI,CAAC,aAAa,IAAI,YAAY,CAAC,MAAM,CAAC,CAAA;IAE7E,kDAAkD;IAClD,MAAM,IAAI,GAAG,mBAAmB,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;IAE9C,IAAI,CAAC,IAAI;QAAE,OAAO,IAAI,CAAA;IAEtB;;OAEG;IACH,MAAM,MAAM,GAAG,CACd,KAAoB,EACpB,KAAmE,EACnC,EAAE;QAClC,MAAM,IAAI,GAAkB,EAAE,GAAG,KAAK,EAAE,CAAA;QAExC,IAAI,KAAK,CAAC,QAAQ,IAAI,IAAI,CAAC,QAAQ,EAAE,CAAC;YACrC,IAAI,CAAC,QAAQ,GAAG,IAAI,CAAC,QAAQ,CAAA;QAC9B,CAAC;QAED,IAAI,KAAK,CAAC,MAAM,IAAI,IAAI,CAAC,MAAM,EAAE,IAAI,EAAE,EAAE,CAAC;YACzC,IAAI,CAAC,MAAM,GAAG,IAAI,CAAC,MAAM,CAAA;QAC1B,CAAC;QAED,IAAI,KAAK,CAAC,QAAQ,IAAI,IAAI,CAAC,QAAQ,EAAE,CAAC;YACrC,IAAI,CAAC,QAAQ,GAAG,IAAI,CAAC,QAAQ,CAAA;QAC9B,CAAC;QAED,MAAM,QAAQ,GAAG,gBAAgB,CAAC,IAAI,EAAE,IAAI,EAAE,EAAE,UAAU,EAAE,IAAI,EAAE,CAAC,CAAA;QAEnE,IAAI,CAAC,QAAQ;YAAE,OAAO,IAAI,CAAA;QAE1B,OAAO,EAAE,GAAG,EAAE,QAAQ,CAAC,GAAG,EAAE,UAAU,EAAE,QAAQ,CAAC,UAAU,EAAE,MAAM,EAAE,QAAQ,EAAE,CAAA;IAChF,CAAC,CAAA;IAED,QAAQ,QAAQ,EAAE,CAAC;QAClB,KAAK,aAAa,EAAE,CAAC;YACpB,OAAO,MAAM,CAAC,EAAE,KAAK,EAAE,MAAM,CAAC,YAAY,EAAE,MAAM,CAAC,EAAE,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAA;QACzG,CAAC;QACD,KAAK,mBAAmB,EAAE,CAAC;YAC1B,mEAAmE;YACnE,OAAO,MAAM,CAAC,EAAE,KAAK,EAAE,MAAM,CAAC,kBAAkB,EAAE,MAAM,CAAC,EAAE,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAA;QAC/G,CAAC;QACD,KAAK,0BAA0B,EAAE,CAAC;YACjC,OAAO,MAAM,CAAC,EAAE,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAA;QACpE,CAAC;QACD,KAAK,iBAAiB,EAAE,CAAC;YACxB,OAAO,MAAM,CAAC,EAAE,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,CAAC,CAAA;QACpD,CAAC;QACD,KAAK,eAAe,EAAE,CAAC;YACtB,OAAO;gBACN,GAAG,EAAE,IAAI,CAAC,QAAQ;gBAClB,UAAU,EAAE,EAAE,QAAQ,EAAE,IAAI,CAAC,QAAQ,EAAE;gBACvC,MAAM;gBACN,QAAQ;aACR,CAAA;QACF,CAAC;QACD,KAAK,cAAc,EAAE,CAAC;YACrB,MAAM,KAAK,GAAG,aAAa,CAAC,GAAG,CAAC,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;YAC/D,MAAM,OAAO,GAAG,MAAM,CAAC,KAAK,EAAE,MAAM,CAAC,CAAA;YAErC,OAAO;gBACN,GAAG,EAAE,OAAO;gBACZ,UAAU,EAAE,EAAE,OAAO,EAAE;gBACvB,MAAM;gBACN,QAAQ;aACR,CAAA;QACF,CAAC;IACF,CAAC;AACF,CAAC;AAED;;GAEG;AACH,SAAS,YAAY,CAAC,MAAoB;IACzC,MAAM,CAAC,GAAG,MAAM,EAAE,CAAA;IAElB,IAAI,CAAC,GAAG,IAAI;QAAE,OAAO,mBAAmB,CAAA;IAExC,6BAA6B;IAC7B,IAAI,CAAC,GAAG,GAAG;QAAE,OAAO,aAAa,CAAA;IAEjC,MAAM;IACN,IAAI,CAAC,GAAG,GAAG;QAAE,OAAO,0BAA0B,CAAA;IAE9C,MAAM;IACN,IAAI,CAAC,GAAG,IAAI;QAAE,OAAO,iBAAiB,CAAA;IAEtC,MAAM;IACN,IAAI,CAAC,GAAG,IAAI;QAAE,OAAO,eAAe,CAAA;IAEpC,KAAK;IACL,OAAO,cAAc,CAAA,CAAC,KAAK;AAC5B,CAAC;AAED;;;;GAIG;AACH,MAAM,CAAC,MAAM,gBAAgB,GAAG;IAC/B,QAAQ;IACR,eAAe;IACf,wBAAwB;IACxB,eAAe;IACf,cAAc;IACd,gBAAgB;IAChB,gBAAgB;IAChB,MAAM;CACG,CAAA;AAEV,MAAM,UAAU,mBAAmB,CAAC,UAAsC;IACzE,KAAK,MAAM,CAAC,IAAI,gBAAgB,EAAE,CAAC;QAClC,IAAI,UAAU,CAAC,CAAC,CAAC;YAAE,OAAO,IAAI,CAAA;IAC/B,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC;AAED,aAAa"}
|