@mailwoman/corpus 10.0.0 → 10.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +120 -34
- package/data/PROVENANCE.md +623 -17
- package/data/address-source-register.json +14249 -0
- package/data/builds/v0.7.0-de-holdout/inputs.json +22 -0
- package/data/builds/v0.8.0-registers/inputs.json +92 -0
- package/data/license-decisions.json +1603 -0
- package/data/licenses/PROVENANCE.md +65 -0
- package/data/licenses/cdla-permissive-2.0.md +43 -0
- package/data/licenses/geonames-publication.md +34 -0
- package/data/licenses/licence-ouverte-2.0.md +36 -0
- package/data/licenses/national-address-database.md +46 -0
- package/data/licenses/nlod-2.0.md +90 -0
- package/data/licenses/sirene-publication.md +38 -0
- package/data/licenses/whosonfirst-licenses.md +65 -0
- package/data/source-resolutions.json +804 -0
- package/data/sub-venue-lexicon.json +1 -1
- package/data/training-manifests/v0.7.0-de-holdout.effective.json +477 -0
- package/data/training-manifests/v0.7.0-de-holdout.json +78 -0
- package/lib/adapters/cordis/adapter.ts +785 -0
- package/lib/adapters/dedup-key.ts +40 -0
- package/lib/adapters/errors.ts +21 -0
- package/lib/adapters/geonames/adapter.ts +42 -52
- package/lib/adapters/geonames/postal/adapter.ts +31 -37
- package/lib/adapters/gleif/adapter.ts +828 -0
- package/lib/adapters/libpostal-dictionary.ts +39 -0
- package/lib/adapters/openaddresses/adapter.ts +51 -55
- package/lib/adapters/osm/adapter.ts +148 -70
- package/lib/adapters/overture/adapter.ts +52 -43
- package/lib/adapters/po-box/adapter.ts +202 -0
- package/lib/adapters/registry.ts +79 -0
- package/lib/adapters/sha256-stream.ts +49 -0
- package/lib/adapters/source-id.ts +49 -0
- package/lib/adapters/street-line.ts +135 -0
- package/lib/adapters/wof/admin/json/adapter.ts +48 -33
- package/lib/adapters/wof/json-rows.ts +56 -26
- package/lib/adapters/wof/postalcode-json/adapter.ts +57 -59
- package/lib/adapters.ts +230 -0
- package/lib/au/adapters/gnaf/adapter.ts +35 -43
- package/lib/au/adapters/gnaf/assemble.ts +31 -51
- package/lib/be/adapters/brussels/adapter.ts +566 -0
- package/lib/be/adapters/vlaanderen/adapter.ts +670 -0
- package/lib/be/adapters/wallonie/adapter.ts +537 -0
- package/lib/be/tools/fetch/brussels.ts +239 -0
- package/lib/be/tools/fetch/wallonie.ts +274 -0
- package/lib/build/adapters.ts +110 -0
- package/lib/build/align.ts +364 -0
- package/lib/build/checkpoint.ts +131 -0
- package/lib/build/eligibility.ts +96 -0
- package/lib/build/heap.ts +53 -0
- package/lib/build/inputs.ts +81 -0
- package/lib/build/rows.ts +21 -0
- package/lib/build/types.ts +232 -0
- package/lib/build.ts +127 -315
- package/lib/cn/recipes/organizational-units.ts +20 -41
- package/lib/cz/adapters/cuzk/adapter.ts +317 -0
- package/lib/cz/recipes/pcfirst-preposition.ts +40 -27
- package/lib/cz/tools/fetch/cuzk.ts +699 -0
- package/lib/de/recipes/locale.ts +68 -58
- package/lib/directory.ts +31 -0
- package/lib/dk/adapters/inspire/adapter.ts +345 -0
- package/lib/dk/tools/fetch/inspire.ts +321 -0
- package/lib/ee/adapters/ads/adapter.ts +246 -0
- package/lib/ee/tools/fetch/ads.ts +270 -0
- package/lib/env.ts +6 -2
- package/lib/es/adapters/bizkaia/adapter.ts +388 -0
- package/lib/es/adapters/catastro/adapter.ts +343 -0
- package/lib/es/adapters/gipuzkoa/adapter.ts +263 -0
- package/lib/es/adapters/navarra/adapter.ts +289 -0
- package/lib/es/cadastre.ts +194 -0
- package/lib/es/tools/fetch/bizkaia.ts +748 -0
- package/lib/es/tools/fetch/catastro.ts +754 -0
- package/lib/es/tools/fetch/gipuzkoa.ts +336 -0
- package/lib/es/tools/fetch/navarra.ts +488 -0
- package/lib/fi/adapters/ryhti/adapter.ts +323 -0
- package/lib/fi/tools/fetch/ryhti.ts +476 -0
- package/lib/fingerprints.ts +154 -0
- package/lib/fr/adapters/annuaire-education/adapter.ts +598 -0
- package/lib/fr/adapters/ban/adapter.ts +87 -59
- package/lib/fr/adapters/finess/adapter.ts +618 -0
- package/lib/fr/adapters/finess/postal-lines.ts +157 -0
- package/lib/fr/adapters/finess/voie-type.ts +200 -0
- package/lib/fr/insee-country.ts +62 -0
- package/lib/fr/recipes/admin-split.ts +38 -60
- package/lib/fr/recipes/bare-street.ts +37 -50
- package/lib/fr/recipes/fragment.ts +59 -142
- package/lib/fr/recipes/lieudit.ts +109 -73
- package/lib/fr/recipes/order.ts +32 -59
- package/lib/fr/{adapters/ban/street-decompose.ts → street-decompose.ts} +4 -3
- package/lib/fr/tools/fetch/annuaire-education.ts +306 -0
- package/lib/fr/tools/fetch/ban.ts +28 -19
- package/lib/fr/tools/fetch/finess.ts +352 -0
- package/lib/gauntlet-inputs.ts +92 -0
- package/lib/index.ts +9 -3
- package/lib/inspire/address.ts +457 -0
- package/lib/inspire/archive.ts +44 -0
- package/lib/inspire/errors.ts +71 -0
- package/lib/inspire/stream.ts +262 -0
- package/lib/international/recipes/locale.ts +134 -176
- package/lib/it/adapters/anac/adapter.ts +522 -0
- package/lib/it/tools/fetch/anac.ts +394 -0
- package/lib/jp/adapters/wof-admin/adapter.ts +27 -17
- package/lib/jp/tools/fetch/houjin.ts +16 -18
- package/lib/kr/adapters/juso/label-rows.ts +24 -44
- package/lib/kr/adapters/localdata/align.ts +20 -31
- package/lib/kr/adapters/localdata/key-index.ts +17 -25
- package/lib/kr/adapters/localdata/permit-rows.ts +33 -26
- package/lib/kr/tools/fetch/juso.ts +19 -21
- package/lib/kr/tools/fetch/localdata.ts +28 -29
- package/lib/lu/adapters/bd-adresses/adapter.ts +240 -0
- package/lib/lu/tools/fetch/bd-adresses.ts +351 -0
- package/lib/lv/adapters/varis/adapter.ts +499 -0
- package/lib/lv/tools/fetch/varis.ts +214 -0
- package/lib/nl/adapters/kadaster/adapter.ts +386 -0
- package/lib/nl/recipes/postcode.ts +46 -24
- package/lib/nl/tools/fetch/kadaster.ts +298 -0
- package/lib/no/adapters/matrikkelen/adapter.ts +187 -0
- package/lib/no/recipes/fragment.ts +34 -58
- package/lib/no/recipes/street/led.ts +44 -25
- package/lib/no/recipes/{street/index.ts → street.ts} +29 -11
- package/lib/no/tools/fetch/matrikkelen.ts +519 -0
- package/lib/parquet/duckdb.ts +144 -0
- package/lib/parquet/readers.ts +86 -0
- package/lib/parquet/schema.ts +214 -0
- package/lib/parquet/shuffle.ts +59 -0
- package/lib/parquet/span-sql.ts +54 -0
- package/lib/parquet/streams.ts +113 -0
- package/lib/parquet/writers.ts +451 -0
- package/lib/pl/adapters/emuia/adapter.ts +202 -0
- package/lib/pl/tools/fetch/emuia.ts +360 -0
- package/lib/recipes/anchor-absorption.ts +30 -19
- package/lib/recipes/bare/country.ts +24 -32
- package/lib/recipes/bare/postcode/eval.ts +1 -1
- package/lib/recipes/bare/postcode.ts +346 -0
- package/lib/recipes/boundary-stress.ts +36 -19
- package/lib/recipes/country-balanced.ts +66 -86
- package/lib/recipes/house-venue.ts +31 -13
- package/lib/recipes/intersection.ts +82 -60
- package/lib/recipes/po/box/cedex/au-nz.ts +3 -3
- package/lib/recipes/po/box/cedex/ca.ts +3 -2
- package/lib/recipes/po/box/cedex/fr.ts +4 -3
- package/lib/recipes/po/box/cedex/phrases.ts +7 -6
- package/lib/recipes/po/box/cedex/recipe.ts +28 -16
- package/lib/recipes/po/box/cedex/sources.ts +3 -3
- package/lib/recipes/po/box/cedex/us.ts +7 -2
- package/lib/recipes/po/{box/index.ts → box.ts} +39 -18
- package/lib/recipes/scaffold.ts +252 -153
- package/lib/recipes/sources.ts +399 -0
- package/lib/recipes/street/affix.ts +54 -154
- package/lib/recipes/street/bare.ts +28 -15
- package/lib/recipes/street.ts +32 -8
- package/lib/recipes/sub/venue/context.ts +30 -23
- package/lib/recipes/sub/venue/render.ts +170 -0
- package/lib/recipes/sub/venue/sources.ts +68 -219
- package/lib/recipes/sub/venue.ts +801 -0
- package/lib/recipes/trailing-region.ts +69 -85
- package/lib/recipes/unit/sources.ts +44 -0
- package/lib/recipes/unit.ts +101 -89
- package/lib/{recipes/index.ts → recipes.ts} +13 -11
- package/lib/registers.ts +278 -0
- package/lib/ro/adapters/retea-scolara/adapter.ts +264 -0
- package/lib/ro/tools/fetch/retea-scolara.ts +187 -0
- package/lib/runner.ts +220 -84
- package/lib/sg/recipes/register.ts +46 -52
- package/lib/sg/tools/fetch/acra.ts +20 -25
- package/lib/si/recipes/bare-village.ts +34 -17
- package/lib/sk/adapters/inspire/adapter.ts +395 -0
- package/lib/sk/tools/fetch/inspire.ts +402 -0
- package/lib/source-register/effective-manifest.ts +659 -0
- package/lib/source-register/register.ts +539 -0
- package/lib/source-register/training-manifest.ts +218 -0
- package/lib/source-register/types.ts +590 -0
- package/lib/source-register.ts +71 -0
- package/lib/south-asia/recipes/register.ts +45 -26
- package/lib/subvenue/harvest.ts +251 -0
- package/lib/{tools/sub/venue → subvenue}/promotions.ts +33 -70
- package/lib/subvenue/surfaces.ts +94 -0
- package/lib/subvenue/table.ts +264 -0
- package/lib/surfaces/locale.ts +246 -0
- package/lib/synthesizers/anchor-absorption.ts +55 -91
- package/lib/synthesizers/boundary-stress.ts +49 -131
- package/lib/synthesizers/house-venue.ts +44 -102
- package/lib/synthesizers/intersection.ts +37 -26
- package/lib/synthesizers/no-street.ts +70 -119
- package/lib/synthesizers/po-box.ts +90 -105
- package/lib/synthesizers/street.ts +46 -34
- package/lib/synthesizers/utils.ts +64 -218
- package/lib/test-kit/corpus-recipe.ts +45 -28
- package/lib/test-kit.ts +116 -0
- package/lib/tools/align-canonical.ts +64 -0
- package/lib/tools/audit.ts +113 -118
- package/lib/tools/corpus-stats.ts +44 -30
- package/lib/tools/fetch/atom.ts +164 -0
- package/lib/tools/fetch/cordis.ts +318 -0
- package/lib/tools/fetch/download/manifest.ts +34 -22
- package/lib/tools/fetch/download/network.ts +55 -31
- package/lib/tools/fetch/download/retry.ts +26 -25
- package/lib/tools/fetch/geonames/dump.ts +72 -54
- package/lib/tools/fetch/geonames/postal.ts +27 -62
- package/lib/tools/fetch/gleif.ts +360 -0
- package/lib/tools/fetch/header.ts +69 -0
- package/lib/tools/fetch/inspire-addresses.ts +495 -0
- package/lib/tools/fetch/openaddresses.ts +22 -111
- package/lib/tools/fetch/ourairports.ts +18 -51
- package/lib/tools/fetch/ppd.ts +10 -8
- package/lib/tools/fetch/vlaanderen-ad.ts +435 -0
- package/lib/tools/fetch/wfs-harvest.ts +943 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +45 -145
- package/lib/tools/fetch/zip-archive.ts +100 -0
- package/lib/tools/fetch.ts +143 -0
- package/lib/tools/golden/expand.ts +74 -43
- package/lib/tools/golden/promote.ts +41 -32
- package/lib/tools/golden/relabel-street/directory.ts +63 -36
- package/lib/tools/golden/relabel-street/row.ts +28 -106
- package/lib/tools/ingest-csv.ts +45 -48
- package/lib/tools/jsonl-to-parquet.ts +59 -98
- package/lib/tools/lint/recipe-output/vocab.ts +366 -0
- package/lib/tools/lint/{slice/index.ts → recipe-output.ts} +107 -121
- package/lib/tools/migrate/overlay-parquet.ts +173 -0
- package/lib/tools/migrate/recipe-output.ts +153 -0
- package/lib/tools/migrate/source-names.ts +161 -0
- package/lib/tools/{slice → overlay}/kryptonite.ts +43 -36
- package/lib/tools/overlay/manifest.ts +407 -0
- package/lib/tools/overlay/merge-source.ts +138 -0
- package/lib/tools/overlay/split-slice.ts +144 -0
- package/lib/tools/{slice → overlay}/translit.ts +74 -58
- package/lib/tools/overture-subvenue.ts +17 -90
- package/lib/tools/postcode-triples.ts +281 -210
- package/lib/tools/source-register/build.ts +819 -0
- package/lib/tools/sub/venue/head-nouns.ts +38 -75
- package/lib/tools/sub/venue/lexicon.ts +71 -106
- package/lib/tools/sub/venue/wikidata.ts +13 -10
- package/lib/tools.ts +31 -0
- package/lib/tw/tools/fetch/gcis.ts +17 -16
- package/lib/types.ts +304 -101
- package/lib/us/adapters/fcc-bdc/adapter.ts +26 -41
- package/lib/us/adapters/state/hi-schools/adapter.ts +28 -17
- package/lib/us/adapters/state/hi-schools/workbook.ts +7 -2
- package/lib/us/adapters/state/ia-contractors/adapter.ts +27 -15
- package/lib/us/adapters/state/ny-notaries/adapter.ts +24 -25
- package/lib/us/adapters/state/tx-notaries/adapter.ts +21 -15
- package/lib/us/adapters/tiger/adapter.ts +19 -44
- package/lib/us/adapters/tiger/street-decompose.ts +7 -17
- package/lib/us/adapters/usgov/hrsa-fqhc/adapter.ts +49 -34
- package/lib/us/adapters/usgov/imls-pls/adapter.ts +25 -19
- package/lib/us/adapters/usgov/irs-bmf/adapter.ts +32 -23
- package/lib/us/adapters/usgov/nad/adapter.ts +51 -112
- package/lib/us/adapters/usgov/nppes/adapter.ts +72 -35
- package/lib/us/adapters/usgov/samhsa-treatment-locator/adapter.ts +43 -30
- package/lib/us/fips-state.ts +17 -8
- package/lib/us/tools/fetch/hrsa.ts +7 -8
- package/lib/us/tools/fetch/imls-pls.ts +17 -35
- package/lib/us/tools/fetch/nad.ts +50 -32
- package/lib/us/tools/fetch/nppes.ts +23 -35
- package/lib/us/tools/fetch/state/hi-schools.ts +22 -16
- package/lib/us/tools/fetch/state/sources.ts +12 -12
- package/lib/us/tools/fetch/tiger-full.ts +21 -73
- package/lib/utils/align.ts +42 -52
- package/lib/utils/{slice-stats.ts → cooccurrence-stats.ts} +22 -16
- package/lib/utils/golden.ts +34 -49
- package/lib/utils/license.ts +238 -26
- package/lib/utils/split.ts +205 -88
- package/lib/utils/tokenize.ts +22 -34
- package/lib/utils/wof-json.ts +129 -76
- package/lib/{utils/index.ts → utils.ts} +0 -1
- package/lib/ve/recipes/reviewed-postcode-tail.ts +40 -13
- package/out/adapters/cordis/adapter.d.ts +324 -0
- package/out/adapters/cordis/adapter.d.ts.map +1 -0
- package/out/adapters/cordis/adapter.js +616 -0
- package/out/adapters/cordis/adapter.js.map +1 -0
- package/out/adapters/dedup-key.d.ts +30 -0
- package/out/adapters/dedup-key.d.ts.map +1 -0
- package/out/adapters/dedup-key.js +35 -0
- package/out/adapters/dedup-key.js.map +1 -0
- package/out/adapters/errors.d.ts +17 -0
- package/out/adapters/errors.d.ts.map +1 -0
- package/out/adapters/errors.js +20 -0
- package/out/adapters/errors.js.map +1 -0
- package/out/adapters/geonames/adapter.d.ts +26 -28
- package/out/adapters/geonames/adapter.d.ts.map +1 -1
- package/out/adapters/geonames/adapter.js +39 -49
- package/out/adapters/geonames/adapter.js.map +1 -1
- package/out/adapters/geonames/postal/adapter.d.ts +14 -27
- package/out/adapters/geonames/postal/adapter.d.ts.map +1 -1
- package/out/adapters/geonames/postal/adapter.js +30 -35
- package/out/adapters/geonames/postal/adapter.js.map +1 -1
- package/out/adapters/gleif/adapter.d.ts +293 -0
- package/out/adapters/gleif/adapter.d.ts.map +1 -0
- package/out/adapters/gleif/adapter.js +684 -0
- package/out/adapters/gleif/adapter.js.map +1 -0
- package/out/adapters/libpostal-dictionary.d.ts +22 -0
- package/out/adapters/libpostal-dictionary.d.ts.map +1 -0
- package/out/adapters/libpostal-dictionary.js +36 -0
- package/out/adapters/libpostal-dictionary.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts +28 -43
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -1
- package/out/adapters/openaddresses/adapter.js +34 -46
- package/out/adapters/openaddresses/adapter.js.map +1 -1
- package/out/adapters/osm/adapter.d.ts +48 -42
- package/out/adapters/osm/adapter.d.ts.map +1 -1
- package/out/adapters/osm/adapter.js +116 -67
- package/out/adapters/osm/adapter.js.map +1 -1
- package/out/adapters/overture/adapter.d.ts +11 -37
- package/out/adapters/overture/adapter.d.ts.map +1 -1
- package/out/adapters/overture/adapter.js +45 -42
- package/out/adapters/overture/adapter.js.map +1 -1
- package/out/adapters/po-box/adapter.d.ts +63 -0
- package/out/adapters/po-box/adapter.d.ts.map +1 -0
- package/out/adapters/{synth-po-box → po-box}/adapter.js +45 -46
- package/out/adapters/po-box/adapter.js.map +1 -0
- package/out/adapters/registry.d.ts +55 -0
- package/out/adapters/registry.d.ts.map +1 -0
- package/out/adapters/registry.js +43 -0
- package/out/adapters/registry.js.map +1 -0
- package/out/adapters/sha256-stream.d.ts +26 -0
- package/out/adapters/sha256-stream.d.ts.map +1 -0
- package/out/adapters/sha256-stream.js +34 -0
- package/out/adapters/sha256-stream.js.map +1 -0
- package/out/adapters/source-id.d.ts +33 -0
- package/out/adapters/source-id.d.ts.map +1 -0
- package/out/adapters/source-id.js +42 -0
- package/out/adapters/source-id.js.map +1 -0
- package/out/adapters/street-line.d.ts +102 -0
- package/out/adapters/street-line.d.ts.map +1 -0
- package/out/adapters/street-line.js +117 -0
- package/out/adapters/street-line.js.map +1 -0
- package/out/adapters/wof/admin/json/adapter.d.ts +27 -18
- package/out/adapters/wof/admin/json/adapter.d.ts.map +1 -1
- package/out/adapters/wof/admin/json/adapter.js +47 -31
- package/out/adapters/wof/admin/json/adapter.js.map +1 -1
- package/out/adapters/wof/json-rows.d.ts +35 -19
- package/out/adapters/wof/json-rows.d.ts.map +1 -1
- package/out/adapters/wof/json-rows.js +35 -15
- package/out/adapters/wof/json-rows.js.map +1 -1
- package/out/adapters/wof/postalcode-json/adapter.d.ts +22 -38
- package/out/adapters/wof/postalcode-json/adapter.d.ts.map +1 -1
- package/out/adapters/wof/postalcode-json/adapter.js +55 -57
- package/out/adapters/wof/postalcode-json/adapter.js.map +1 -1
- package/out/adapters.d.ts +75 -0
- package/out/adapters.d.ts.map +1 -0
- package/out/adapters.js +167 -0
- package/out/adapters.js.map +1 -0
- package/out/au/adapters/gnaf/adapter.d.ts +15 -27
- package/out/au/adapters/gnaf/adapter.d.ts.map +1 -1
- package/out/au/adapters/gnaf/adapter.js +34 -42
- package/out/au/adapters/gnaf/adapter.js.map +1 -1
- package/out/au/adapters/gnaf/assemble.d.ts +15 -26
- package/out/au/adapters/gnaf/assemble.d.ts.map +1 -1
- package/out/au/adapters/gnaf/assemble.js +26 -46
- package/out/au/adapters/gnaf/assemble.js.map +1 -1
- package/out/be/adapters/brussels/adapter.d.ts +212 -0
- package/out/be/adapters/brussels/adapter.d.ts.map +1 -0
- package/out/be/adapters/brussels/adapter.js +435 -0
- package/out/be/adapters/brussels/adapter.js.map +1 -0
- package/out/be/adapters/vlaanderen/adapter.d.ts +233 -0
- package/out/be/adapters/vlaanderen/adapter.d.ts.map +1 -0
- package/out/be/adapters/vlaanderen/adapter.js +416 -0
- package/out/be/adapters/vlaanderen/adapter.js.map +1 -0
- package/out/be/adapters/wallonie/adapter.d.ts +196 -0
- package/out/be/adapters/wallonie/adapter.d.ts.map +1 -0
- package/out/be/adapters/wallonie/adapter.js +437 -0
- package/out/be/adapters/wallonie/adapter.js.map +1 -0
- package/out/be/tools/fetch/brussels.d.ts +119 -0
- package/out/be/tools/fetch/brussels.d.ts.map +1 -0
- package/out/be/tools/fetch/brussels.js +146 -0
- package/out/be/tools/fetch/brussels.js.map +1 -0
- package/out/be/tools/fetch/wallonie.d.ts +119 -0
- package/out/be/tools/fetch/wallonie.d.ts.map +1 -0
- package/out/be/tools/fetch/wallonie.js +167 -0
- package/out/be/tools/fetch/wallonie.js.map +1 -0
- package/out/build/adapters.d.ts +33 -0
- package/out/build/adapters.d.ts.map +1 -0
- package/out/build/adapters.js +68 -0
- package/out/build/adapters.js.map +1 -0
- package/out/build/align.d.ts +73 -0
- package/out/build/align.d.ts.map +1 -0
- package/out/build/align.js +226 -0
- package/out/build/align.js.map +1 -0
- package/out/build/checkpoint.d.ts +94 -0
- package/out/build/checkpoint.d.ts.map +1 -0
- package/out/build/checkpoint.js +59 -0
- package/out/build/checkpoint.js.map +1 -0
- package/out/build/eligibility.d.ts +47 -0
- package/out/build/eligibility.d.ts.map +1 -0
- package/out/build/eligibility.js +80 -0
- package/out/build/eligibility.js.map +1 -0
- package/out/build/heap.d.ts +28 -0
- package/out/build/heap.d.ts.map +1 -0
- package/out/build/heap.js +47 -0
- package/out/build/heap.js.map +1 -0
- package/out/build/inputs.d.ts +52 -0
- package/out/build/inputs.d.ts.map +1 -0
- package/out/build/inputs.js +49 -0
- package/out/build/inputs.js.map +1 -0
- package/out/build/rows.d.ts +16 -0
- package/out/build/rows.d.ts.map +1 -0
- package/out/build/rows.js +19 -0
- package/out/build/rows.js.map +1 -0
- package/out/build/types.d.ts +220 -0
- package/out/build/types.d.ts.map +1 -0
- package/out/build/types.js +34 -0
- package/out/build/types.js.map +1 -0
- package/out/build.d.ts +6 -121
- package/out/build.d.ts.map +1 -1
- package/out/build.js +112 -207
- package/out/build.js.map +1 -1
- package/out/cn/recipes/organizational-units.d.ts +5 -22
- package/out/cn/recipes/organizational-units.d.ts.map +1 -1
- package/out/cn/recipes/organizational-units.js +20 -41
- package/out/cn/recipes/organizational-units.js.map +1 -1
- package/out/cz/adapters/cuzk/adapter.d.ts +52 -0
- package/out/cz/adapters/cuzk/adapter.d.ts.map +1 -0
- package/out/cz/adapters/cuzk/adapter.js +266 -0
- package/out/cz/adapters/cuzk/adapter.js.map +1 -0
- package/out/cz/recipes/pcfirst-preposition.d.ts +7 -11
- package/out/cz/recipes/pcfirst-preposition.d.ts.map +1 -1
- package/out/cz/recipes/pcfirst-preposition.js +36 -27
- package/out/cz/recipes/pcfirst-preposition.js.map +1 -1
- package/out/cz/tools/fetch/cuzk.d.ts +272 -0
- package/out/cz/tools/fetch/cuzk.d.ts.map +1 -0
- package/out/cz/tools/fetch/cuzk.js +446 -0
- package/out/cz/tools/fetch/cuzk.js.map +1 -0
- package/out/de/recipes/locale.d.ts +24 -26
- package/out/de/recipes/locale.d.ts.map +1 -1
- package/out/de/recipes/locale.js +66 -56
- package/out/de/recipes/locale.js.map +1 -1
- package/out/directory.d.ts +20 -0
- package/out/directory.d.ts.map +1 -0
- package/out/directory.js +27 -0
- package/out/directory.js.map +1 -0
- package/out/dk/adapters/inspire/adapter.d.ts +154 -0
- package/out/dk/adapters/inspire/adapter.d.ts.map +1 -0
- package/out/dk/adapters/inspire/adapter.js +258 -0
- package/out/dk/adapters/inspire/adapter.js.map +1 -0
- package/out/dk/tools/fetch/inspire.d.ts +100 -0
- package/out/dk/tools/fetch/inspire.d.ts.map +1 -0
- package/out/dk/tools/fetch/inspire.js +230 -0
- package/out/dk/tools/fetch/inspire.js.map +1 -0
- package/out/ee/adapters/ads/adapter.d.ts +109 -0
- package/out/ee/adapters/ads/adapter.d.ts.map +1 -0
- package/out/ee/adapters/ads/adapter.js +191 -0
- package/out/ee/adapters/ads/adapter.js.map +1 -0
- package/out/ee/tools/fetch/ads.d.ts +123 -0
- package/out/ee/tools/fetch/ads.d.ts.map +1 -0
- package/out/ee/tools/fetch/ads.js +195 -0
- package/out/ee/tools/fetch/ads.js.map +1 -0
- package/out/env.d.ts +6 -2
- package/out/env.d.ts.map +1 -1
- package/out/env.js +6 -2
- package/out/env.js.map +1 -1
- package/out/es/adapters/bizkaia/adapter.d.ts +143 -0
- package/out/es/adapters/bizkaia/adapter.d.ts.map +1 -0
- package/out/es/adapters/bizkaia/adapter.js +332 -0
- package/out/es/adapters/bizkaia/adapter.js.map +1 -0
- package/out/es/adapters/catastro/adapter.d.ts +104 -0
- package/out/es/adapters/catastro/adapter.d.ts.map +1 -0
- package/out/es/adapters/catastro/adapter.js +288 -0
- package/out/es/adapters/catastro/adapter.js.map +1 -0
- package/out/es/adapters/gipuzkoa/adapter.d.ts +91 -0
- package/out/es/adapters/gipuzkoa/adapter.d.ts.map +1 -0
- package/out/es/adapters/gipuzkoa/adapter.js +225 -0
- package/out/es/adapters/gipuzkoa/adapter.js.map +1 -0
- package/out/es/adapters/navarra/adapter.d.ts +105 -0
- package/out/es/adapters/navarra/adapter.d.ts.map +1 -0
- package/out/es/adapters/navarra/adapter.js +241 -0
- package/out/es/adapters/navarra/adapter.js.map +1 -0
- package/out/es/cadastre.d.ts +109 -0
- package/out/es/cadastre.d.ts.map +1 -0
- package/out/es/cadastre.js +130 -0
- package/out/es/cadastre.js.map +1 -0
- package/out/es/tools/fetch/bizkaia.d.ts +278 -0
- package/out/es/tools/fetch/bizkaia.d.ts.map +1 -0
- package/out/es/tools/fetch/bizkaia.js +477 -0
- package/out/es/tools/fetch/bizkaia.js.map +1 -0
- package/out/es/tools/fetch/catastro.d.ts +272 -0
- package/out/es/tools/fetch/catastro.d.ts.map +1 -0
- package/out/es/tools/fetch/catastro.js +486 -0
- package/out/es/tools/fetch/catastro.js.map +1 -0
- package/out/es/tools/fetch/gipuzkoa.d.ts +162 -0
- package/out/es/tools/fetch/gipuzkoa.d.ts.map +1 -0
- package/out/es/tools/fetch/gipuzkoa.js +209 -0
- package/out/es/tools/fetch/gipuzkoa.js.map +1 -0
- package/out/es/tools/fetch/navarra.d.ts +189 -0
- package/out/es/tools/fetch/navarra.d.ts.map +1 -0
- package/out/es/tools/fetch/navarra.js +316 -0
- package/out/es/tools/fetch/navarra.js.map +1 -0
- package/out/fi/adapters/ryhti/adapter.d.ts +115 -0
- package/out/fi/adapters/ryhti/adapter.d.ts.map +1 -0
- package/out/fi/adapters/ryhti/adapter.js +244 -0
- package/out/fi/adapters/ryhti/adapter.js.map +1 -0
- package/out/fi/tools/fetch/ryhti.d.ts +206 -0
- package/out/fi/tools/fetch/ryhti.d.ts.map +1 -0
- package/out/fi/tools/fetch/ryhti.js +327 -0
- package/out/fi/tools/fetch/ryhti.js.map +1 -0
- package/out/fingerprints.d.ts +68 -0
- package/out/fingerprints.d.ts.map +1 -0
- package/out/fingerprints.js +130 -0
- package/out/fingerprints.js.map +1 -0
- package/out/fr/adapters/annuaire-education/adapter.d.ts +236 -0
- package/out/fr/adapters/annuaire-education/adapter.d.ts.map +1 -0
- package/out/fr/adapters/annuaire-education/adapter.js +475 -0
- package/out/fr/adapters/annuaire-education/adapter.js.map +1 -0
- package/out/fr/adapters/ban/adapter.d.ts +19 -25
- package/out/fr/adapters/ban/adapter.d.ts.map +1 -1
- package/out/fr/adapters/ban/adapter.js +65 -54
- package/out/fr/adapters/ban/adapter.js.map +1 -1
- package/out/fr/adapters/finess/adapter.d.ts +276 -0
- package/out/fr/adapters/finess/adapter.d.ts.map +1 -0
- package/out/fr/adapters/finess/adapter.js +519 -0
- package/out/fr/adapters/finess/adapter.js.map +1 -0
- package/out/fr/adapters/finess/postal-lines.d.ts +61 -0
- package/out/fr/adapters/finess/postal-lines.d.ts.map +1 -0
- package/out/fr/adapters/finess/postal-lines.js +114 -0
- package/out/fr/adapters/finess/postal-lines.js.map +1 -0
- package/out/fr/adapters/finess/voie-type.d.ts +77 -0
- package/out/fr/adapters/finess/voie-type.d.ts.map +1 -0
- package/out/fr/adapters/finess/voie-type.js +172 -0
- package/out/fr/adapters/finess/voie-type.js.map +1 -0
- package/out/fr/insee-country.d.ts +45 -0
- package/out/fr/insee-country.d.ts.map +1 -0
- package/out/fr/insee-country.js +60 -0
- package/out/fr/insee-country.js.map +1 -0
- package/out/fr/recipes/admin-split.d.ts +4 -27
- package/out/fr/recipes/admin-split.d.ts.map +1 -1
- package/out/fr/recipes/admin-split.js +36 -58
- package/out/fr/recipes/admin-split.js.map +1 -1
- package/out/fr/recipes/bare-street.d.ts +2 -17
- package/out/fr/recipes/bare-street.d.ts.map +1 -1
- package/out/fr/recipes/bare-street.js +35 -50
- package/out/fr/recipes/bare-street.js.map +1 -1
- package/out/fr/recipes/fragment.d.ts +6 -65
- package/out/fr/recipes/fragment.d.ts.map +1 -1
- package/out/fr/recipes/fragment.js +55 -135
- package/out/fr/recipes/fragment.js.map +1 -1
- package/out/fr/recipes/lieudit.d.ts +17 -19
- package/out/fr/recipes/lieudit.d.ts.map +1 -1
- package/out/fr/recipes/lieudit.js +88 -68
- package/out/fr/recipes/lieudit.js.map +1 -1
- package/out/fr/recipes/order.d.ts +4 -27
- package/out/fr/recipes/order.d.ts.map +1 -1
- package/out/fr/recipes/order.js +31 -58
- package/out/fr/recipes/order.js.map +1 -1
- package/out/fr/{adapters/ban/street-decompose.d.ts → street-decompose.d.ts} +3 -2
- package/out/fr/street-decompose.d.ts.map +1 -0
- package/out/fr/{adapters/ban/street-decompose.js → street-decompose.js} +4 -3
- package/out/fr/street-decompose.js.map +1 -0
- package/out/fr/tools/fetch/annuaire-education.d.ts +130 -0
- package/out/fr/tools/fetch/annuaire-education.d.ts.map +1 -0
- package/out/fr/tools/fetch/annuaire-education.js +196 -0
- package/out/fr/tools/fetch/annuaire-education.js.map +1 -0
- package/out/fr/tools/fetch/ban.d.ts +9 -7
- package/out/fr/tools/fetch/ban.d.ts.map +1 -1
- package/out/fr/tools/fetch/ban.js +27 -18
- package/out/fr/tools/fetch/ban.js.map +1 -1
- package/out/fr/tools/fetch/finess.d.ts +145 -0
- package/out/fr/tools/fetch/finess.d.ts.map +1 -0
- package/out/fr/tools/fetch/finess.js +228 -0
- package/out/fr/tools/fetch/finess.js.map +1 -0
- package/out/gauntlet-inputs.d.ts +42 -0
- package/out/gauntlet-inputs.d.ts.map +1 -0
- package/out/gauntlet-inputs.js +78 -0
- package/out/gauntlet-inputs.js.map +1 -0
- package/out/index.d.ts +9 -3
- package/out/index.d.ts.map +1 -1
- package/out/index.js +9 -3
- package/out/index.js.map +1 -1
- package/out/inspire/address.d.ts +251 -0
- package/out/inspire/address.d.ts.map +1 -0
- package/out/inspire/address.js +384 -0
- package/out/inspire/address.js.map +1 -0
- package/out/inspire/archive.d.ts +36 -0
- package/out/inspire/archive.d.ts.map +1 -0
- package/out/inspire/archive.js +42 -0
- package/out/inspire/archive.js.map +1 -0
- package/out/inspire/errors.d.ts +55 -0
- package/out/inspire/errors.d.ts.map +1 -0
- package/out/inspire/errors.js +64 -0
- package/out/inspire/errors.js.map +1 -0
- package/out/inspire/stream.d.ts +137 -0
- package/out/inspire/stream.d.ts.map +1 -0
- package/out/inspire/stream.js +125 -0
- package/out/inspire/stream.js.map +1 -0
- package/out/international/recipes/locale.d.ts +38 -84
- package/out/international/recipes/locale.d.ts.map +1 -1
- package/out/international/recipes/locale.js +112 -151
- package/out/international/recipes/locale.js.map +1 -1
- package/out/it/adapters/anac/adapter.d.ts +267 -0
- package/out/it/adapters/anac/adapter.d.ts.map +1 -0
- package/out/it/adapters/anac/adapter.js +429 -0
- package/out/it/adapters/anac/adapter.js.map +1 -0
- package/out/it/tools/fetch/anac.d.ts +174 -0
- package/out/it/tools/fetch/anac.d.ts.map +1 -0
- package/out/it/tools/fetch/anac.js +272 -0
- package/out/it/tools/fetch/anac.js.map +1 -0
- package/out/jp/adapters/wof-admin/adapter.d.ts +14 -11
- package/out/jp/adapters/wof-admin/adapter.d.ts.map +1 -1
- package/out/jp/adapters/wof-admin/adapter.js +27 -16
- package/out/jp/adapters/wof-admin/adapter.js.map +1 -1
- package/out/jp/tools/fetch/houjin.d.ts +7 -4
- package/out/jp/tools/fetch/houjin.d.ts.map +1 -1
- package/out/jp/tools/fetch/houjin.js +15 -11
- package/out/jp/tools/fetch/houjin.js.map +1 -1
- package/out/kr/adapters/juso/label-rows.d.ts +17 -31
- package/out/kr/adapters/juso/label-rows.d.ts.map +1 -1
- package/out/kr/adapters/juso/label-rows.js +19 -41
- package/out/kr/adapters/juso/label-rows.js.map +1 -1
- package/out/kr/adapters/localdata/align.d.ts +4 -16
- package/out/kr/adapters/localdata/align.d.ts.map +1 -1
- package/out/kr/adapters/localdata/align.js +19 -30
- package/out/kr/adapters/localdata/align.js.map +1 -1
- package/out/kr/adapters/localdata/key-index.d.ts +13 -22
- package/out/kr/adapters/localdata/key-index.d.ts.map +1 -1
- package/out/kr/adapters/localdata/key-index.js +15 -21
- package/out/kr/adapters/localdata/key-index.js.map +1 -1
- package/out/kr/adapters/localdata/permit-rows.d.ts +21 -14
- package/out/kr/adapters/localdata/permit-rows.d.ts.map +1 -1
- package/out/kr/adapters/localdata/permit-rows.js +30 -25
- package/out/kr/adapters/localdata/permit-rows.js.map +1 -1
- package/out/kr/tools/fetch/juso.d.ts +11 -8
- package/out/kr/tools/fetch/juso.d.ts.map +1 -1
- package/out/kr/tools/fetch/juso.js +15 -14
- package/out/kr/tools/fetch/juso.js.map +1 -1
- package/out/kr/tools/fetch/localdata.d.ts +16 -9
- package/out/kr/tools/fetch/localdata.d.ts.map +1 -1
- package/out/kr/tools/fetch/localdata.js +23 -15
- package/out/kr/tools/fetch/localdata.js.map +1 -1
- package/out/lu/adapters/bd-adresses/adapter.d.ts +109 -0
- package/out/lu/adapters/bd-adresses/adapter.d.ts.map +1 -0
- package/out/lu/adapters/bd-adresses/adapter.js +196 -0
- package/out/lu/adapters/bd-adresses/adapter.js.map +1 -0
- package/out/lu/tools/fetch/bd-adresses.d.ts +163 -0
- package/out/lu/tools/fetch/bd-adresses.d.ts.map +1 -0
- package/out/lu/tools/fetch/bd-adresses.js +223 -0
- package/out/lu/tools/fetch/bd-adresses.js.map +1 -0
- package/out/lv/adapters/varis/adapter.d.ts +283 -0
- package/out/lv/adapters/varis/adapter.d.ts.map +1 -0
- package/out/lv/adapters/varis/adapter.js +404 -0
- package/out/lv/adapters/varis/adapter.js.map +1 -0
- package/out/lv/tools/fetch/varis.d.ts +80 -0
- package/out/lv/tools/fetch/varis.d.ts.map +1 -0
- package/out/lv/tools/fetch/varis.js +133 -0
- package/out/lv/tools/fetch/varis.js.map +1 -0
- package/out/nl/adapters/kadaster/adapter.d.ts +125 -0
- package/out/nl/adapters/kadaster/adapter.d.ts.map +1 -0
- package/out/nl/adapters/kadaster/adapter.js +310 -0
- package/out/nl/adapters/kadaster/adapter.js.map +1 -0
- package/out/nl/recipes/postcode.d.ts +12 -14
- package/out/nl/recipes/postcode.d.ts.map +1 -1
- package/out/nl/recipes/postcode.js +42 -24
- package/out/nl/recipes/postcode.js.map +1 -1
- package/out/nl/tools/fetch/kadaster.d.ts +155 -0
- package/out/nl/tools/fetch/kadaster.d.ts.map +1 -0
- package/out/nl/tools/fetch/kadaster.js +179 -0
- package/out/nl/tools/fetch/kadaster.js.map +1 -0
- package/out/no/adapters/matrikkelen/adapter.d.ts +44 -0
- package/out/no/adapters/matrikkelen/adapter.d.ts.map +1 -0
- package/out/no/adapters/matrikkelen/adapter.js +143 -0
- package/out/no/adapters/matrikkelen/adapter.js.map +1 -0
- package/out/no/recipes/fragment.d.ts +1 -33
- package/out/no/recipes/fragment.d.ts.map +1 -1
- package/out/no/recipes/fragment.js +23 -57
- package/out/no/recipes/fragment.js.map +1 -1
- package/out/no/recipes/street/led.d.ts +9 -12
- package/out/no/recipes/street/led.d.ts.map +1 -1
- package/out/no/recipes/street/led.js +34 -24
- package/out/no/recipes/street/led.js.map +1 -1
- package/out/no/recipes/street.d.ts +19 -0
- package/out/no/recipes/street.d.ts.map +1 -0
- package/out/no/recipes/{street/index.js → street.js} +28 -12
- package/out/no/recipes/street.js.map +1 -0
- package/out/no/tools/fetch/matrikkelen.d.ts +251 -0
- package/out/no/tools/fetch/matrikkelen.d.ts.map +1 -0
- package/out/no/tools/fetch/matrikkelen.js +345 -0
- package/out/no/tools/fetch/matrikkelen.js.map +1 -0
- package/out/parquet/duckdb.d.ts +100 -0
- package/out/parquet/duckdb.d.ts.map +1 -0
- package/out/parquet/duckdb.js +92 -0
- package/out/parquet/duckdb.js.map +1 -0
- package/out/parquet/readers.d.ts +44 -0
- package/out/parquet/readers.d.ts.map +1 -0
- package/out/parquet/readers.js +69 -0
- package/out/parquet/readers.js.map +1 -0
- package/out/parquet/schema.d.ts +95 -0
- package/out/parquet/schema.d.ts.map +1 -0
- package/out/parquet/schema.js +157 -0
- package/out/parquet/schema.js.map +1 -0
- package/out/parquet/shuffle.d.ts +25 -0
- package/out/parquet/shuffle.d.ts.map +1 -0
- package/out/parquet/shuffle.js +44 -0
- package/out/parquet/shuffle.js.map +1 -0
- package/out/parquet/span-sql.d.ts +49 -0
- package/out/parquet/span-sql.d.ts.map +1 -0
- package/out/parquet/span-sql.js +53 -0
- package/out/parquet/span-sql.js.map +1 -0
- package/out/parquet/streams.d.ts +47 -0
- package/out/parquet/streams.d.ts.map +1 -0
- package/out/parquet/streams.js +78 -0
- package/out/parquet/streams.js.map +1 -0
- package/out/parquet/writers.d.ts +124 -0
- package/out/parquet/writers.d.ts.map +1 -0
- package/out/parquet/writers.js +251 -0
- package/out/parquet/writers.js.map +1 -0
- package/out/pl/adapters/emuia/adapter.d.ts +81 -0
- package/out/pl/adapters/emuia/adapter.d.ts.map +1 -0
- package/out/pl/adapters/emuia/adapter.js +178 -0
- package/out/pl/adapters/emuia/adapter.js.map +1 -0
- package/out/pl/tools/fetch/emuia.d.ts +165 -0
- package/out/pl/tools/fetch/emuia.d.ts.map +1 -0
- package/out/pl/tools/fetch/emuia.js +260 -0
- package/out/pl/tools/fetch/emuia.js.map +1 -0
- package/out/recipes/anchor-absorption.d.ts +9 -9
- package/out/recipes/anchor-absorption.d.ts.map +1 -1
- package/out/recipes/anchor-absorption.js +29 -19
- package/out/recipes/anchor-absorption.js.map +1 -1
- package/out/recipes/bare/country.d.ts +2 -20
- package/out/recipes/bare/country.d.ts.map +1 -1
- package/out/recipes/bare/country.js +20 -31
- package/out/recipes/bare/country.js.map +1 -1
- package/out/recipes/bare/postcode/eval.d.ts +1 -1
- package/out/recipes/bare/postcode/eval.js +1 -1
- package/out/recipes/bare/postcode.d.ts +41 -0
- package/out/recipes/bare/postcode.d.ts.map +1 -0
- package/out/recipes/bare/{postcode/index.js → postcode.js} +91 -79
- package/out/recipes/bare/postcode.js.map +1 -0
- package/out/recipes/boundary-stress.d.ts +8 -8
- package/out/recipes/boundary-stress.d.ts.map +1 -1
- package/out/recipes/boundary-stress.js +36 -19
- package/out/recipes/boundary-stress.js.map +1 -1
- package/out/recipes/country-balanced.d.ts +3 -21
- package/out/recipes/country-balanced.d.ts.map +1 -1
- package/out/recipes/country-balanced.js +58 -76
- package/out/recipes/country-balanced.js.map +1 -1
- package/out/recipes/house-venue.d.ts +8 -6
- package/out/recipes/house-venue.d.ts.map +1 -1
- package/out/recipes/house-venue.js +29 -13
- package/out/recipes/house-venue.js.map +1 -1
- package/out/recipes/intersection.d.ts +20 -20
- package/out/recipes/intersection.d.ts.map +1 -1
- package/out/recipes/intersection.js +65 -53
- package/out/recipes/intersection.js.map +1 -1
- package/out/recipes/po/box/cedex/au-nz.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/au-nz.js +3 -3
- package/out/recipes/po/box/cedex/au-nz.js.map +1 -1
- package/out/recipes/po/box/cedex/ca.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/ca.js +2 -2
- package/out/recipes/po/box/cedex/ca.js.map +1 -1
- package/out/recipes/po/box/cedex/fr.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/fr.js +3 -3
- package/out/recipes/po/box/cedex/fr.js.map +1 -1
- package/out/recipes/po/box/cedex/phrases.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/phrases.js +7 -6
- package/out/recipes/po/box/cedex/phrases.js.map +1 -1
- package/out/recipes/po/box/cedex/recipe.d.ts +1 -1
- package/out/recipes/po/box/cedex/recipe.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/recipe.js +25 -15
- package/out/recipes/po/box/cedex/recipe.js.map +1 -1
- package/out/recipes/po/box/cedex/sources.d.ts +12 -12
- package/out/recipes/po/box/cedex/sources.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/sources.js +1 -1
- package/out/recipes/po/box/cedex/sources.js.map +1 -1
- package/out/recipes/po/box/cedex/us.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/us.js +5 -2
- package/out/recipes/po/box/cedex/us.js.map +1 -1
- package/out/recipes/po/box.d.ts +18 -0
- package/out/recipes/po/box.d.ts.map +1 -0
- package/out/recipes/po/{box/index.js → box.js} +37 -19
- package/out/recipes/po/box.js.map +1 -0
- package/out/recipes/scaffold.d.ts +211 -138
- package/out/recipes/scaffold.d.ts.map +1 -1
- package/out/recipes/scaffold.js +72 -63
- package/out/recipes/scaffold.js.map +1 -1
- package/out/recipes/sources.d.ts +178 -0
- package/out/recipes/sources.d.ts.map +1 -0
- package/out/recipes/sources.js +348 -0
- package/out/recipes/sources.js.map +1 -0
- package/out/recipes/street/affix.d.ts +20 -50
- package/out/recipes/street/affix.d.ts.map +1 -1
- package/out/recipes/street/affix.js +45 -133
- package/out/recipes/street/affix.js.map +1 -1
- package/out/recipes/street/bare.d.ts +9 -7
- package/out/recipes/street/bare.d.ts.map +1 -1
- package/out/recipes/street/bare.js +25 -14
- package/out/recipes/street/bare.js.map +1 -1
- package/out/recipes/street.d.ts +6 -4
- package/out/recipes/street.d.ts.map +1 -1
- package/out/recipes/street.js +29 -8
- package/out/recipes/street.js.map +1 -1
- package/out/recipes/sub/venue/context.d.ts +12 -9
- package/out/recipes/sub/venue/context.d.ts.map +1 -1
- package/out/recipes/sub/venue/context.js +21 -17
- package/out/recipes/sub/venue/context.js.map +1 -1
- package/out/recipes/sub/venue/render.d.ts +58 -0
- package/out/recipes/sub/venue/render.d.ts.map +1 -0
- package/out/recipes/sub/venue/render.js +118 -0
- package/out/recipes/sub/venue/render.js.map +1 -0
- package/out/recipes/sub/venue/sources.d.ts +49 -92
- package/out/recipes/sub/venue/sources.d.ts.map +1 -1
- package/out/recipes/sub/venue/sources.js +43 -179
- package/out/recipes/sub/venue/sources.js.map +1 -1
- package/out/recipes/sub/venue.d.ts +176 -0
- package/out/recipes/sub/venue.d.ts.map +1 -0
- package/out/recipes/sub/venue.js +562 -0
- package/out/recipes/sub/venue.js.map +1 -0
- package/out/recipes/trailing-region.d.ts +9 -61
- package/out/recipes/trailing-region.d.ts.map +1 -1
- package/out/recipes/trailing-region.js +55 -85
- package/out/recipes/trailing-region.js.map +1 -1
- package/out/recipes/unit/sources.d.ts +28 -0
- package/out/recipes/unit/sources.d.ts.map +1 -0
- package/out/recipes/unit/sources.js +30 -0
- package/out/recipes/unit/sources.js.map +1 -0
- package/out/recipes/unit.d.ts +30 -17
- package/out/recipes/unit.d.ts.map +1 -1
- package/out/recipes/unit.js +90 -79
- package/out/recipes/unit.js.map +1 -1
- package/out/recipes.d.ts +26 -0
- package/out/recipes.d.ts.map +1 -0
- package/out/{recipes/index.js → recipes.js} +14 -12
- package/out/recipes.js.map +1 -0
- package/out/registers.d.ts +277 -0
- package/out/registers.d.ts.map +1 -0
- package/out/registers.js +273 -0
- package/out/registers.js.map +1 -0
- package/out/ro/adapters/retea-scolara/adapter.d.ts +114 -0
- package/out/ro/adapters/retea-scolara/adapter.d.ts.map +1 -0
- package/out/ro/adapters/retea-scolara/adapter.js +209 -0
- package/out/ro/adapters/retea-scolara/adapter.js.map +1 -0
- package/out/ro/tools/fetch/retea-scolara.d.ts +69 -0
- package/out/ro/tools/fetch/retea-scolara.d.ts.map +1 -0
- package/out/ro/tools/fetch/retea-scolara.js +117 -0
- package/out/ro/tools/fetch/retea-scolara.js.map +1 -0
- package/out/runner.d.ts +120 -60
- package/out/runner.d.ts.map +1 -1
- package/out/runner.js +130 -56
- package/out/runner.js.map +1 -1
- package/out/sg/recipes/register.d.ts +18 -32
- package/out/sg/recipes/register.d.ts.map +1 -1
- package/out/sg/recipes/register.js +44 -49
- package/out/sg/recipes/register.js.map +1 -1
- package/out/sg/tools/fetch/acra.d.ts +11 -14
- package/out/sg/tools/fetch/acra.d.ts.map +1 -1
- package/out/sg/tools/fetch/acra.js +16 -19
- package/out/sg/tools/fetch/acra.js.map +1 -1
- package/out/si/recipes/bare-village.d.ts +12 -13
- package/out/si/recipes/bare-village.d.ts.map +1 -1
- package/out/si/recipes/bare-village.js +31 -17
- package/out/si/recipes/bare-village.js.map +1 -1
- package/out/sk/adapters/inspire/adapter.d.ts +119 -0
- package/out/sk/adapters/inspire/adapter.d.ts.map +1 -0
- package/out/sk/adapters/inspire/adapter.js +318 -0
- package/out/sk/adapters/inspire/adapter.js.map +1 -0
- package/out/sk/tools/fetch/inspire.d.ts +195 -0
- package/out/sk/tools/fetch/inspire.d.ts.map +1 -0
- package/out/sk/tools/fetch/inspire.js +280 -0
- package/out/sk/tools/fetch/inspire.js.map +1 -0
- package/out/source-register/effective-manifest.d.ts +355 -0
- package/out/source-register/effective-manifest.d.ts.map +1 -0
- package/out/source-register/effective-manifest.js +355 -0
- package/out/source-register/effective-manifest.js.map +1 -0
- package/out/source-register/register.d.ts +79 -0
- package/out/source-register/register.d.ts.map +1 -0
- package/out/source-register/register.js +400 -0
- package/out/source-register/register.js.map +1 -0
- package/out/source-register/training-manifest.d.ts +111 -0
- package/out/source-register/training-manifest.d.ts.map +1 -0
- package/out/source-register/training-manifest.js +120 -0
- package/out/source-register/training-manifest.js.map +1 -0
- package/out/source-register/types.d.ts +539 -0
- package/out/source-register/types.d.ts.map +1 -0
- package/out/source-register/types.js +263 -0
- package/out/source-register/types.js.map +1 -0
- package/out/source-register.d.ts +19 -0
- package/out/source-register.d.ts.map +1 -0
- package/out/source-register.js +16 -0
- package/out/source-register.js.map +1 -0
- package/out/south-asia/recipes/register.d.ts +20 -17
- package/out/south-asia/recipes/register.d.ts.map +1 -1
- package/out/south-asia/recipes/register.js +44 -24
- package/out/south-asia/recipes/register.js.map +1 -1
- package/out/subvenue/harvest.d.ts +117 -0
- package/out/subvenue/harvest.d.ts.map +1 -0
- package/out/subvenue/harvest.js +172 -0
- package/out/subvenue/harvest.js.map +1 -0
- package/out/subvenue/promotions.d.ts +65 -0
- package/out/subvenue/promotions.d.ts.map +1 -0
- package/out/{tools/sub/venue → subvenue}/promotions.js +15 -55
- package/out/subvenue/promotions.js.map +1 -0
- package/out/subvenue/surfaces.d.ts +39 -0
- package/out/subvenue/surfaces.d.ts.map +1 -0
- package/out/subvenue/surfaces.js +75 -0
- package/out/subvenue/surfaces.js.map +1 -0
- package/out/subvenue/table.d.ts +212 -0
- package/out/subvenue/table.d.ts.map +1 -0
- package/out/subvenue/table.js +94 -0
- package/out/subvenue/table.js.map +1 -0
- package/out/surfaces/locale.d.ts +113 -0
- package/out/surfaces/locale.d.ts.map +1 -0
- package/out/surfaces/locale.js +136 -0
- package/out/surfaces/locale.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +21 -30
- package/out/synthesizers/anchor-absorption.d.ts.map +1 -1
- package/out/synthesizers/anchor-absorption.js +30 -85
- package/out/synthesizers/anchor-absorption.js.map +1 -1
- package/out/synthesizers/boundary-stress.d.ts +17 -48
- package/out/synthesizers/boundary-stress.d.ts.map +1 -1
- package/out/synthesizers/boundary-stress.js +27 -121
- package/out/synthesizers/boundary-stress.js.map +1 -1
- package/out/synthesizers/house-venue.d.ts +22 -25
- package/out/synthesizers/house-venue.d.ts.map +1 -1
- package/out/synthesizers/house-venue.js +28 -97
- package/out/synthesizers/house-venue.js.map +1 -1
- package/out/synthesizers/intersection.d.ts +10 -8
- package/out/synthesizers/intersection.d.ts.map +1 -1
- package/out/synthesizers/intersection.js +33 -26
- package/out/synthesizers/intersection.js.map +1 -1
- package/out/synthesizers/no-street.d.ts +7 -37
- package/out/synthesizers/no-street.d.ts.map +1 -1
- package/out/synthesizers/no-street.js +55 -111
- package/out/synthesizers/no-street.js.map +1 -1
- package/out/synthesizers/po-box.d.ts +46 -45
- package/out/synthesizers/po-box.d.ts.map +1 -1
- package/out/synthesizers/po-box.js +57 -97
- package/out/synthesizers/po-box.js.map +1 -1
- package/out/synthesizers/street.d.ts +18 -12
- package/out/synthesizers/street.d.ts.map +1 -1
- package/out/synthesizers/street.js +36 -29
- package/out/synthesizers/street.js.map +1 -1
- package/out/synthesizers/utils.d.ts +32 -129
- package/out/synthesizers/utils.d.ts.map +1 -1
- package/out/synthesizers/utils.js +54 -166
- package/out/synthesizers/utils.js.map +1 -1
- package/out/test-kit/corpus-recipe.d.ts +29 -23
- package/out/test-kit/corpus-recipe.d.ts.map +1 -1
- package/out/test-kit/corpus-recipe.js +28 -13
- package/out/test-kit/corpus-recipe.js.map +1 -1
- package/out/test-kit.d.ts +63 -0
- package/out/test-kit.d.ts.map +1 -0
- package/out/test-kit.js +88 -0
- package/out/test-kit.js.map +1 -0
- package/out/tools/align-canonical.d.ts +7 -0
- package/out/tools/align-canonical.d.ts.map +1 -0
- package/out/tools/align-canonical.js +52 -0
- package/out/tools/align-canonical.js.map +1 -0
- package/out/tools/audit.d.ts +18 -11
- package/out/tools/audit.d.ts.map +1 -1
- package/out/tools/audit.js +86 -95
- package/out/tools/audit.js.map +1 -1
- package/out/tools/corpus-stats.d.ts +24 -15
- package/out/tools/corpus-stats.d.ts.map +1 -1
- package/out/tools/corpus-stats.js +33 -29
- package/out/tools/corpus-stats.js.map +1 -1
- package/out/tools/fetch/atom.d.ts +115 -0
- package/out/tools/fetch/atom.d.ts.map +1 -0
- package/out/tools/fetch/atom.js +84 -0
- package/out/tools/fetch/atom.js.map +1 -0
- package/out/tools/fetch/cordis.d.ts +123 -0
- package/out/tools/fetch/cordis.d.ts.map +1 -0
- package/out/tools/fetch/cordis.js +208 -0
- package/out/tools/fetch/cordis.js.map +1 -0
- package/out/tools/fetch/download/manifest.d.ts +27 -18
- package/out/tools/fetch/download/manifest.d.ts.map +1 -1
- package/out/tools/fetch/download/manifest.js +20 -13
- package/out/tools/fetch/download/manifest.js.map +1 -1
- package/out/tools/fetch/download/network.d.ts +48 -27
- package/out/tools/fetch/download/network.d.ts.map +1 -1
- package/out/tools/fetch/download/network.js +26 -16
- package/out/tools/fetch/download/network.js.map +1 -1
- package/out/tools/fetch/download/retry.d.ts +16 -15
- package/out/tools/fetch/download/retry.d.ts.map +1 -1
- package/out/tools/fetch/download/retry.js +24 -24
- package/out/tools/fetch/download/retry.js.map +1 -1
- package/out/tools/fetch/{download/index.d.ts → download.d.ts} +1 -1
- package/out/tools/fetch/download.d.ts.map +1 -0
- package/out/tools/fetch/{download/index.js → download.js} +1 -1
- package/out/tools/fetch/download.js.map +1 -0
- package/out/tools/fetch/geonames/dump.d.ts +50 -32
- package/out/tools/fetch/geonames/dump.d.ts.map +1 -1
- package/out/tools/fetch/geonames/dump.js +52 -42
- package/out/tools/fetch/geonames/dump.js.map +1 -1
- package/out/tools/fetch/geonames/postal.d.ts +14 -49
- package/out/tools/fetch/geonames/postal.d.ts.map +1 -1
- package/out/tools/fetch/geonames/postal.js +17 -56
- package/out/tools/fetch/geonames/postal.js.map +1 -1
- package/out/tools/fetch/gleif.d.ts +137 -0
- package/out/tools/fetch/gleif.d.ts.map +1 -0
- package/out/tools/fetch/gleif.js +220 -0
- package/out/tools/fetch/gleif.js.map +1 -0
- package/out/tools/fetch/header.d.ts +41 -0
- package/out/tools/fetch/header.d.ts.map +1 -0
- package/out/tools/fetch/header.js +59 -0
- package/out/tools/fetch/header.js.map +1 -0
- package/out/tools/fetch/inspire-addresses.d.ts +249 -0
- package/out/tools/fetch/inspire-addresses.d.ts.map +1 -0
- package/out/tools/fetch/inspire-addresses.js +276 -0
- package/out/tools/fetch/inspire-addresses.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +1 -4
- package/out/tools/fetch/openaddresses.d.ts.map +1 -1
- package/out/tools/fetch/openaddresses.js +19 -98
- package/out/tools/fetch/openaddresses.js.map +1 -1
- package/out/tools/fetch/ourairports.d.ts +6 -33
- package/out/tools/fetch/ourairports.d.ts.map +1 -1
- package/out/tools/fetch/ourairports.js +14 -47
- package/out/tools/fetch/ourairports.js.map +1 -1
- package/out/tools/fetch/ppd.d.ts +4 -3
- package/out/tools/fetch/ppd.d.ts.map +1 -1
- package/out/tools/fetch/ppd.js +10 -7
- package/out/tools/fetch/ppd.js.map +1 -1
- package/out/tools/fetch/vlaanderen-ad.d.ts +131 -0
- package/out/tools/fetch/vlaanderen-ad.d.ts.map +1 -0
- package/out/tools/fetch/vlaanderen-ad.js +293 -0
- package/out/tools/fetch/vlaanderen-ad.js.map +1 -0
- package/out/tools/fetch/wfs-harvest.d.ts +410 -0
- package/out/tools/fetch/wfs-harvest.d.ts.map +1 -0
- package/out/tools/fetch/wfs-harvest.js +522 -0
- package/out/tools/fetch/wfs-harvest.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +32 -100
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -1
- package/out/tools/fetch/wikidata-subvenue.js +27 -122
- package/out/tools/fetch/wikidata-subvenue.js.map +1 -1
- package/out/tools/fetch/zip-archive.d.ts +54 -0
- package/out/tools/fetch/zip-archive.d.ts.map +1 -0
- package/out/tools/fetch/zip-archive.js +58 -0
- package/out/tools/fetch/zip-archive.js.map +1 -0
- package/out/tools/fetch.d.ts +140 -0
- package/out/tools/fetch.d.ts.map +1 -0
- package/out/tools/fetch.js +136 -0
- package/out/tools/fetch.js.map +1 -0
- package/out/tools/golden/expand.d.ts +28 -13
- package/out/tools/golden/expand.d.ts.map +1 -1
- package/out/tools/golden/expand.js +50 -36
- package/out/tools/golden/expand.js.map +1 -1
- package/out/tools/golden/promote.d.ts +13 -8
- package/out/tools/golden/promote.d.ts.map +1 -1
- package/out/tools/golden/promote.js +33 -28
- package/out/tools/golden/promote.js.map +1 -1
- package/out/tools/golden/relabel-street/directory.d.ts +24 -9
- package/out/tools/golden/relabel-street/directory.d.ts.map +1 -1
- package/out/tools/golden/relabel-street/directory.js +41 -30
- package/out/tools/golden/relabel-street/directory.js.map +1 -1
- package/out/tools/golden/relabel-street/row.d.ts +17 -69
- package/out/tools/golden/relabel-street/row.d.ts.map +1 -1
- package/out/tools/golden/relabel-street/row.js +16 -74
- package/out/tools/golden/relabel-street/row.js.map +1 -1
- package/out/tools/golden/{relabel-street/index.d.ts → relabel-street.d.ts} +1 -1
- package/out/tools/golden/relabel-street.d.ts.map +1 -0
- package/out/tools/golden/{relabel-street/index.js → relabel-street.js} +1 -1
- package/out/tools/golden/relabel-street.js.map +1 -0
- package/out/tools/ingest-csv.d.ts +19 -15
- package/out/tools/ingest-csv.d.ts.map +1 -1
- package/out/tools/ingest-csv.js +39 -43
- package/out/tools/ingest-csv.js.map +1 -1
- package/out/tools/jsonl-to-parquet.d.ts +15 -28
- package/out/tools/jsonl-to-parquet.d.ts.map +1 -1
- package/out/tools/jsonl-to-parquet.js +49 -91
- package/out/tools/jsonl-to-parquet.js.map +1 -1
- package/out/tools/lint/recipe-output/vocab.d.ts +77 -0
- package/out/tools/lint/recipe-output/vocab.d.ts.map +1 -0
- package/out/tools/lint/{slice → recipe-output}/vocab.js +54 -69
- package/out/tools/lint/recipe-output/vocab.js.map +1 -0
- package/out/tools/lint/recipe-output.d.ts +73 -0
- package/out/tools/lint/recipe-output.d.ts.map +1 -0
- package/out/tools/lint/{slice/index.js → recipe-output.js} +76 -96
- package/out/tools/lint/recipe-output.js.map +1 -0
- package/out/tools/migrate/overlay-parquet.d.ts +30 -0
- package/out/tools/migrate/overlay-parquet.d.ts.map +1 -0
- package/out/tools/migrate/overlay-parquet.js +141 -0
- package/out/tools/migrate/overlay-parquet.js.map +1 -0
- package/out/tools/migrate/recipe-output.d.ts +35 -0
- package/out/tools/migrate/recipe-output.d.ts.map +1 -0
- package/out/tools/migrate/recipe-output.js +124 -0
- package/out/tools/migrate/recipe-output.js.map +1 -0
- package/out/tools/migrate/source-names.d.ts +52 -0
- package/out/tools/migrate/source-names.d.ts.map +1 -0
- package/out/tools/migrate/source-names.js +105 -0
- package/out/tools/migrate/source-names.js.map +1 -0
- package/out/tools/overlay/kryptonite.d.ts +33 -0
- package/out/tools/overlay/kryptonite.d.ts.map +1 -0
- package/out/tools/{slice → overlay}/kryptonite.js +37 -28
- package/out/tools/overlay/kryptonite.js.map +1 -0
- package/out/tools/overlay/manifest.d.ts +142 -0
- package/out/tools/overlay/manifest.d.ts.map +1 -0
- package/out/tools/overlay/manifest.js +260 -0
- package/out/tools/overlay/manifest.js.map +1 -0
- package/out/tools/overlay/merge-source.d.ts +73 -0
- package/out/tools/overlay/merge-source.d.ts.map +1 -0
- package/out/tools/overlay/merge-source.js +63 -0
- package/out/tools/overlay/merge-source.js.map +1 -0
- package/out/tools/overlay/split-slice.d.ts +66 -0
- package/out/tools/overlay/split-slice.d.ts.map +1 -0
- package/out/tools/overlay/split-slice.js +78 -0
- package/out/tools/overlay/split-slice.js.map +1 -0
- package/out/tools/overlay/translit.d.ts +54 -0
- package/out/tools/overlay/translit.d.ts.map +1 -0
- package/out/tools/{slice → overlay}/translit.js +59 -48
- package/out/tools/overlay/translit.js.map +1 -0
- package/out/tools/overture-subvenue.d.ts +16 -75
- package/out/tools/overture-subvenue.d.ts.map +1 -1
- package/out/tools/overture-subvenue.js +7 -74
- package/out/tools/overture-subvenue.js.map +1 -1
- package/out/tools/postcode-triples.d.ts +77 -126
- package/out/tools/postcode-triples.d.ts.map +1 -1
- package/out/tools/postcode-triples.js +198 -192
- package/out/tools/postcode-triples.js.map +1 -1
- package/out/tools/source-register/build.d.ts +145 -0
- package/out/tools/source-register/build.d.ts.map +1 -0
- package/out/tools/source-register/build.js +515 -0
- package/out/tools/source-register/build.js.map +1 -0
- package/out/tools/sub/venue/head-nouns.d.ts +9 -38
- package/out/tools/sub/venue/head-nouns.d.ts.map +1 -1
- package/out/tools/sub/venue/head-nouns.js +37 -74
- package/out/tools/sub/venue/head-nouns.js.map +1 -1
- package/out/tools/sub/venue/lexicon.d.ts +55 -82
- package/out/tools/sub/venue/lexicon.d.ts.map +1 -1
- package/out/tools/sub/venue/lexicon.js +43 -87
- package/out/tools/sub/venue/lexicon.js.map +1 -1
- package/out/tools/sub/venue/wikidata.d.ts +8 -6
- package/out/tools/sub/venue/wikidata.d.ts.map +1 -1
- package/out/tools/sub/venue/wikidata.js +12 -9
- package/out/tools/sub/venue/wikidata.js.map +1 -1
- package/out/tools.d.ts +31 -0
- package/out/tools.d.ts.map +1 -0
- package/out/tools.js +31 -0
- package/out/tools.js.map +1 -0
- package/out/tw/tools/fetch/gcis.d.ts +9 -3
- package/out/tw/tools/fetch/gcis.d.ts.map +1 -1
- package/out/tw/tools/fetch/gcis.js +16 -10
- package/out/tw/tools/fetch/gcis.js.map +1 -1
- package/out/types.d.ts +270 -101
- package/out/types.d.ts.map +1 -1
- package/out/types.js +133 -9
- package/out/types.js.map +1 -1
- package/out/us/adapters/fcc-bdc/adapter.d.ts +18 -36
- package/out/us/adapters/fcc-bdc/adapter.d.ts.map +1 -1
- package/out/us/adapters/fcc-bdc/adapter.js +25 -38
- package/out/us/adapters/fcc-bdc/adapter.js.map +1 -1
- package/out/us/adapters/state/hi-schools/adapter.d.ts +12 -11
- package/out/us/adapters/state/hi-schools/adapter.d.ts.map +1 -1
- package/out/us/adapters/state/hi-schools/adapter.js +26 -16
- package/out/us/adapters/state/hi-schools/adapter.js.map +1 -1
- package/out/us/adapters/state/hi-schools/workbook.d.ts +7 -2
- package/out/us/adapters/state/hi-schools/workbook.d.ts.map +1 -1
- package/out/us/adapters/state/hi-schools/workbook.js +3 -1
- package/out/us/adapters/state/hi-schools/workbook.js.map +1 -1
- package/out/us/adapters/state/ia-contractors/adapter.d.ts +13 -6
- package/out/us/adapters/state/ia-contractors/adapter.d.ts.map +1 -1
- package/out/us/adapters/state/ia-contractors/adapter.js +27 -14
- package/out/us/adapters/state/ia-contractors/adapter.js.map +1 -1
- package/out/us/adapters/state/ny-notaries/adapter.d.ts +7 -6
- package/out/us/adapters/state/ny-notaries/adapter.d.ts.map +1 -1
- package/out/us/adapters/state/ny-notaries/adapter.js +24 -22
- package/out/us/adapters/state/ny-notaries/adapter.js.map +1 -1
- package/out/us/adapters/state/tx-notaries/adapter.d.ts +8 -7
- package/out/us/adapters/state/tx-notaries/adapter.d.ts.map +1 -1
- package/out/us/adapters/state/tx-notaries/adapter.js +21 -14
- package/out/us/adapters/state/tx-notaries/adapter.js.map +1 -1
- package/out/us/adapters/tiger/adapter.d.ts +10 -34
- package/out/us/adapters/tiger/adapter.d.ts.map +1 -1
- package/out/us/adapters/tiger/adapter.js +18 -42
- package/out/us/adapters/tiger/adapter.js.map +1 -1
- package/out/us/adapters/tiger/street-decompose.d.ts +6 -13
- package/out/us/adapters/tiger/street-decompose.d.ts.map +1 -1
- package/out/us/adapters/tiger/street-decompose.js +7 -17
- package/out/us/adapters/tiger/street-decompose.js.map +1 -1
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts +26 -20
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.js +41 -29
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.js.map +1 -1
- package/out/us/adapters/usgov/imls-pls/adapter.d.ts +8 -7
- package/out/us/adapters/usgov/imls-pls/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/imls-pls/adapter.js +25 -18
- package/out/us/adapters/usgov/imls-pls/adapter.js.map +1 -1
- package/out/us/adapters/usgov/irs-bmf/adapter.d.ts +11 -10
- package/out/us/adapters/usgov/irs-bmf/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/irs-bmf/adapter.js +32 -22
- package/out/us/adapters/usgov/irs-bmf/adapter.js.map +1 -1
- package/out/us/adapters/usgov/nad/adapter.d.ts +11 -31
- package/out/us/adapters/usgov/nad/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/nad/adapter.js +51 -105
- package/out/us/adapters/usgov/nad/adapter.js.map +1 -1
- package/out/us/adapters/usgov/nppes/adapter.d.ts +12 -22
- package/out/us/adapters/usgov/nppes/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/nppes/adapter.js +62 -32
- package/out/us/adapters/usgov/nppes/adapter.js.map +1 -1
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts +16 -15
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js +36 -26
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js.map +1 -1
- package/out/us/fips-state.d.ts +17 -8
- package/out/us/fips-state.d.ts.map +1 -1
- package/out/us/fips-state.js +17 -8
- package/out/us/fips-state.js.map +1 -1
- package/out/us/tools/fetch/hrsa.d.ts +3 -3
- package/out/us/tools/fetch/hrsa.d.ts.map +1 -1
- package/out/us/tools/fetch/hrsa.js +6 -7
- package/out/us/tools/fetch/hrsa.js.map +1 -1
- package/out/us/tools/fetch/imls-pls.d.ts +5 -16
- package/out/us/tools/fetch/imls-pls.d.ts.map +1 -1
- package/out/us/tools/fetch/imls-pls.js +16 -33
- package/out/us/tools/fetch/imls-pls.js.map +1 -1
- package/out/us/tools/fetch/nad.d.ts +22 -10
- package/out/us/tools/fetch/nad.d.ts.map +1 -1
- package/out/us/tools/fetch/nad.js +29 -24
- package/out/us/tools/fetch/nad.js.map +1 -1
- package/out/us/tools/fetch/nppes.d.ts +6 -16
- package/out/us/tools/fetch/nppes.d.ts.map +1 -1
- package/out/us/tools/fetch/nppes.js +21 -33
- package/out/us/tools/fetch/nppes.js.map +1 -1
- package/out/us/tools/fetch/state/hi-schools.d.ts +8 -5
- package/out/us/tools/fetch/state/hi-schools.d.ts.map +1 -1
- package/out/us/tools/fetch/state/hi-schools.js +15 -13
- package/out/us/tools/fetch/state/hi-schools.js.map +1 -1
- package/out/us/tools/fetch/state/sources.d.ts +8 -7
- package/out/us/tools/fetch/state/sources.d.ts.map +1 -1
- package/out/us/tools/fetch/state/sources.js +8 -9
- package/out/us/tools/fetch/state/sources.js.map +1 -1
- package/out/us/tools/fetch/tiger-full.d.ts +1 -14
- package/out/us/tools/fetch/tiger-full.d.ts.map +1 -1
- package/out/us/tools/fetch/tiger-full.js +15 -54
- package/out/us/tools/fetch/tiger-full.js.map +1 -1
- package/out/utils/align.d.ts +24 -19
- package/out/utils/align.d.ts.map +1 -1
- package/out/utils/align.js +27 -42
- package/out/utils/align.js.map +1 -1
- package/out/utils/cooccurrence-stats.d.ts +58 -0
- package/out/utils/cooccurrence-stats.d.ts.map +1 -0
- package/out/utils/cooccurrence-stats.js +62 -0
- package/out/utils/cooccurrence-stats.js.map +1 -0
- package/out/utils/golden.d.ts +21 -31
- package/out/utils/golden.d.ts.map +1 -1
- package/out/utils/golden.js +28 -44
- package/out/utils/golden.js.map +1 -1
- package/out/utils/license.d.ts +158 -21
- package/out/utils/license.d.ts.map +1 -1
- package/out/utils/license.js +156 -26
- package/out/utils/license.js.map +1 -1
- package/out/utils/split.d.ts +66 -70
- package/out/utils/split.d.ts.map +1 -1
- package/out/utils/split.js +158 -69
- package/out/utils/split.js.map +1 -1
- package/out/utils/tokenize.d.ts +16 -28
- package/out/utils/tokenize.d.ts.map +1 -1
- package/out/utils/tokenize.js +18 -31
- package/out/utils/tokenize.js.map +1 -1
- package/out/utils/wof-json.d.ts +88 -62
- package/out/utils/wof-json.d.ts.map +1 -1
- package/out/utils/wof-json.js +76 -55
- package/out/utils/wof-json.js.map +1 -1
- package/out/{utils/index.js → utils.d.ts} +1 -2
- package/out/utils.d.ts.map +1 -0
- package/out/{utils/index.d.ts → utils.js} +1 -2
- package/out/utils.js.map +1 -0
- package/out/ve/recipes/reviewed-postcode-tail.d.ts +25 -7
- package/out/ve/recipes/reviewed-postcode-tail.d.ts.map +1 -1
- package/out/ve/recipes/reviewed-postcode-tail.js +33 -12
- package/out/ve/recipes/reviewed-postcode-tail.js.map +1 -1
- package/package.json +46 -480
- package/lib/adapters/index.ts +0 -160
- package/lib/adapters/synth-po-box/adapter.ts +0 -204
- package/lib/adapters/utils/index.ts +0 -307
- package/lib/recipes/bare/postcode/index.ts +0 -327
- package/lib/recipes/sub/venue/index.ts +0 -997
- package/lib/synthesizers/locale.ts +0 -261
- package/lib/test-kit/index.ts +0 -100
- package/lib/tools/align-slice.ts +0 -68
- package/lib/tools/fetch/index.ts +0 -174
- package/lib/tools/gb-title-case.ts +0 -69
- package/lib/tools/index.ts +0 -28
- package/lib/tools/lint/slice/vocab.ts +0 -376
- package/lib/tools/overlay-manifest.ts +0 -215
- package/lib/tools/sub/venue/harvest.ts +0 -234
- package/lib/tools/sub/venue/surfaces.ts +0 -95
- package/lib/tools/sub/venue/table.ts +0 -281
- package/lib/utils/parquet.ts +0 -582
- package/out/adapters/index.d.ts +0 -51
- package/out/adapters/index.d.ts.map +0 -1
- package/out/adapters/index.js +0 -97
- package/out/adapters/index.js.map +0 -1
- package/out/adapters/synth-po-box/adapter.d.ts +0 -67
- package/out/adapters/synth-po-box/adapter.d.ts.map +0 -1
- package/out/adapters/synth-po-box/adapter.js.map +0 -1
- package/out/adapters/utils/index.d.ts +0 -191
- package/out/adapters/utils/index.d.ts.map +0 -1
- package/out/adapters/utils/index.js +0 -206
- package/out/adapters/utils/index.js.map +0 -1
- package/out/fr/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/fr/adapters/ban/street-decompose.js.map +0 -1
- package/out/no/recipes/street/index.d.ts +0 -18
- package/out/no/recipes/street/index.d.ts.map +0 -1
- package/out/no/recipes/street/index.js.map +0 -1
- package/out/recipes/bare/postcode/index.d.ts +0 -62
- package/out/recipes/bare/postcode/index.d.ts.map +0 -1
- package/out/recipes/bare/postcode/index.js.map +0 -1
- package/out/recipes/index.d.ts +0 -24
- package/out/recipes/index.d.ts.map +0 -1
- package/out/recipes/index.js.map +0 -1
- package/out/recipes/po/box/index.d.ts +0 -17
- package/out/recipes/po/box/index.d.ts.map +0 -1
- package/out/recipes/po/box/index.js.map +0 -1
- package/out/recipes/sub/venue/index.d.ts +0 -270
- package/out/recipes/sub/venue/index.d.ts.map +0 -1
- package/out/recipes/sub/venue/index.js +0 -728
- package/out/recipes/sub/venue/index.js.map +0 -1
- package/out/synthesizers/locale.d.ts +0 -116
- package/out/synthesizers/locale.d.ts.map +0 -1
- package/out/synthesizers/locale.js +0 -150
- package/out/synthesizers/locale.js.map +0 -1
- package/out/test-kit/index.d.ts +0 -48
- package/out/test-kit/index.d.ts.map +0 -1
- package/out/test-kit/index.js +0 -78
- package/out/test-kit/index.js.map +0 -1
- package/out/tools/align-slice.d.ts +0 -7
- package/out/tools/align-slice.d.ts.map +0 -1
- package/out/tools/align-slice.js +0 -55
- package/out/tools/align-slice.js.map +0 -1
- package/out/tools/fetch/download/index.d.ts.map +0 -1
- package/out/tools/fetch/download/index.js.map +0 -1
- package/out/tools/fetch/index.d.ts +0 -171
- package/out/tools/fetch/index.d.ts.map +0 -1
- package/out/tools/fetch/index.js +0 -170
- package/out/tools/fetch/index.js.map +0 -1
- package/out/tools/gb-title-case.d.ts +0 -2
- package/out/tools/gb-title-case.d.ts.map +0 -1
- package/out/tools/gb-title-case.js +0 -65
- package/out/tools/gb-title-case.js.map +0 -1
- package/out/tools/golden/relabel-street/index.d.ts.map +0 -1
- package/out/tools/golden/relabel-street/index.js.map +0 -1
- package/out/tools/index.d.ts +0 -28
- package/out/tools/index.d.ts.map +0 -1
- package/out/tools/index.js +0 -28
- package/out/tools/index.js.map +0 -1
- package/out/tools/lint/slice/index.d.ts +0 -93
- package/out/tools/lint/slice/index.d.ts.map +0 -1
- package/out/tools/lint/slice/index.js.map +0 -1
- package/out/tools/lint/slice/vocab.d.ts +0 -90
- package/out/tools/lint/slice/vocab.d.ts.map +0 -1
- package/out/tools/lint/slice/vocab.js.map +0 -1
- package/out/tools/overlay-manifest.d.ts +0 -89
- package/out/tools/overlay-manifest.d.ts.map +0 -1
- package/out/tools/overlay-manifest.js +0 -131
- package/out/tools/overlay-manifest.js.map +0 -1
- package/out/tools/slice/kryptonite.d.ts +0 -32
- package/out/tools/slice/kryptonite.d.ts.map +0 -1
- package/out/tools/slice/kryptonite.js.map +0 -1
- package/out/tools/slice/translit.d.ts +0 -51
- package/out/tools/slice/translit.d.ts.map +0 -1
- package/out/tools/slice/translit.js.map +0 -1
- package/out/tools/sub/venue/harvest.d.ts +0 -100
- package/out/tools/sub/venue/harvest.d.ts.map +0 -1
- package/out/tools/sub/venue/harvest.js +0 -168
- package/out/tools/sub/venue/harvest.js.map +0 -1
- package/out/tools/sub/venue/promotions.d.ts +0 -94
- package/out/tools/sub/venue/promotions.d.ts.map +0 -1
- package/out/tools/sub/venue/promotions.js.map +0 -1
- package/out/tools/sub/venue/surfaces.d.ts +0 -45
- package/out/tools/sub/venue/surfaces.d.ts.map +0 -1
- package/out/tools/sub/venue/surfaces.js +0 -77
- package/out/tools/sub/venue/surfaces.js.map +0 -1
- package/out/tools/sub/venue/table.d.ts +0 -229
- package/out/tools/sub/venue/table.d.ts.map +0 -1
- package/out/tools/sub/venue/table.js +0 -108
- package/out/tools/sub/venue/table.js.map +0 -1
- package/out/utils/index.d.ts.map +0 -1
- package/out/utils/index.js.map +0 -1
- package/out/utils/parquet.d.ts +0 -178
- package/out/utils/parquet.d.ts.map +0 -1
- package/out/utils/parquet.js +0 -371
- package/out/utils/parquet.js.map +0 -1
- package/out/utils/slice-stats.d.ts +0 -52
- package/out/utils/slice-stats.d.ts.map +0 -1
- package/out/utils/slice-stats.js +0 -58
- package/out/utils/slice-stats.js.map +0 -1
- /package/lib/tools/fetch/{download/index.ts → download.ts} +0 -0
- /package/lib/tools/golden/{relabel-street/index.ts → relabel-street.ts} +0 -0
|
@@ -3,48 +3,28 @@
|
|
|
3
3
|
* @license AGPL-3.0
|
|
4
4
|
* @author Teffen Ellis, et al.
|
|
5
5
|
*
|
|
6
|
-
*
|
|
7
|
-
*
|
|
8
|
-
*
|
|
9
|
-
* self-validation proved moves the resolved coordinate (collision communes −61%; see
|
|
10
|
-
* docs/articles/evals/experiments/2026-06-19-fr-admin-split-prevalidation.md). Ported from
|
|
11
|
-
* scripts/build-fr-admin-split-slice.mjs.
|
|
12
|
-
*
|
|
13
|
-
* Failure shapes (the model currently mis-handles all of these):
|
|
14
|
-
*
|
|
15
|
-
* - `Thauron, Creuse` → région dropped to null (the comma+full-name miss)
|
|
16
|
-
* - `Montredon, Lozère` → région = "ère" (the diacritic subword split, #727)
|
|
17
|
-
* - (AU analog) `CANBERRA ACT` → the space-delimited admin fuse
|
|
18
|
-
*
|
|
19
|
-
* The département is the essential admin unit for FR postal geography and maps to the `region`
|
|
20
|
-
* component tag in our schema. We derive it DETERMINISTICALLY from the real postcode via codex
|
|
21
|
-
* `departementForCodePostal` (first two digits = département) — salvage-first, no re-derived
|
|
22
|
-
* table.
|
|
23
|
-
*
|
|
24
|
-
* Data (`--communes`, opts.communes): REAL BAN (Base Adresse Nationale) commune+postcode+coord
|
|
25
|
-
* tuples, one per line, TAB-separated `commune <TAB> postcode <TAB> lon <TAB> lat`. Build the
|
|
26
|
-
* input TSV once from the BAN staging CSV (see the legacy script header). Anchor-ON by
|
|
27
|
-
* construction: rows carry a REAL postcode token in `raw` + a `postcode` component, so the
|
|
28
|
-
* training loader paints the anchor feature onto that span automatically. The trailing-postcode
|
|
29
|
-
* anchor REINFORCES the FR split (FR postcode is trailing, unlike German PLZ-leading — the v0.9.2
|
|
30
|
-
* scar is positional, not universal).
|
|
6
|
+
* Generate French training rows that distinguish a département (`region`) from a commune
|
|
7
|
+
* (`locality`). Forms include bare, comma-separated and space-separated names.
|
|
8
|
+
* Derive the département from each real BAN postcode. Input rows are tab-separated commune, postcode, longitude and latitude.
|
|
31
9
|
*/
|
|
32
10
|
import { departementForCodePostal } from "@mailwoman/codex/fr";
|
|
33
11
|
import { tempRootPath } from "@mailwoman/core/data-root";
|
|
12
|
+
import { stringifyJSON } from "@mailwoman/core/json";
|
|
34
13
|
import { mulberry32 as makeMulberry32 } from "@mailwoman/core/utils";
|
|
35
14
|
import { CSVSpliterator, Delimiters } from "spliterator";
|
|
36
|
-
import { stableSourceID } from "#adapters/
|
|
15
|
+
import { stableSourceID } from "#adapters/source-id";
|
|
16
|
+
import { defaultRecipeSource } from "#recipes/sources";
|
|
17
|
+
import { SourceRegister } from "#registers";
|
|
18
|
+
import { SurfaceOrigin } from "#types";
|
|
37
19
|
import { alignRow } from "#utils";
|
|
38
20
|
const DEFAULT_COMMUNES = tempRootPath("reg", "fr-communes.tsv");
|
|
39
21
|
const LICENSE = "BAN (Base Adresse Nationale) commune+postcode tuples, rendered admin-split — see ingest SOURCE";
|
|
40
22
|
/**
|
|
41
|
-
* Read
|
|
23
|
+
* Read commune tuples and derive the département from each postcode.
|
|
42
24
|
*/
|
|
43
25
|
async function readCommunes(path) {
|
|
44
26
|
const rows = [];
|
|
45
|
-
// The TSV
|
|
46
|
-
// spending it on column names. Source is repo-generated (LF); even under CRLF only the trailing `lat`
|
|
47
|
-
// column carries a CR, and it's consumed via `Number()` (whitespace-trimming), so it stays harmless.
|
|
27
|
+
// The TSV has no header row.
|
|
48
28
|
for await (const [commune, postcode, lon, lat] of CSVSpliterator.fromAsync(path, {
|
|
49
29
|
columnDelimiter: Delimiters.Tab,
|
|
50
30
|
header: false,
|
|
@@ -53,26 +33,22 @@ async function readCommunes(path) {
|
|
|
53
33
|
continue;
|
|
54
34
|
const dep = departementForCodePostal(postcode);
|
|
55
35
|
if (!dep)
|
|
56
|
-
continue; //
|
|
57
|
-
// Substring invariant: a département whose name isn't a clean token (none are) or a commune
|
|
58
|
-
// containing the département name would confuse alignment — both are vanishingly rare here.
|
|
36
|
+
continue; // Skip postcodes without a mapped département.
|
|
59
37
|
rows.push({ commune, postcode, departement: dep.name, lon, lat });
|
|
60
38
|
}
|
|
61
39
|
return rows;
|
|
62
40
|
}
|
|
63
|
-
//
|
|
41
|
+
// Share of communes rendered in uppercase.
|
|
64
42
|
const UPPER_LOCALITY_SHARE = 0.1;
|
|
65
|
-
//
|
|
43
|
+
// Cumulative cutoffs for the five address layouts.
|
|
66
44
|
const BARE_COMMA_CUTOFF = 0.25;
|
|
67
45
|
const BARE_COMMA_PC_CUTOFF = 0.5;
|
|
68
46
|
const SPACE_PC_CUTOFF = 0.7;
|
|
69
47
|
const CANONICAL_PC_FIRST_CUTOFF = 0.85;
|
|
70
|
-
//
|
|
48
|
+
// Share of rows with an explicit country component.
|
|
71
49
|
const APPEND_COUNTRY_SHARE = 0.2;
|
|
72
50
|
/**
|
|
73
|
-
* Render one
|
|
74
|
-
* space, is `region` — never folded into `locality`. Variants 1-3 are the failure class; 4-5 are canonical-FR
|
|
75
|
-
* preservation so the model doesn't over-fire region on every trailing token (and the bare commune still resolves).
|
|
51
|
+
* Render one address layout, splitting the département from the commune where present.
|
|
76
52
|
*/
|
|
77
53
|
function render(random, c) {
|
|
78
54
|
const r = random();
|
|
@@ -81,11 +57,11 @@ function render(random, c) {
|
|
|
81
57
|
const pc = c.postcode;
|
|
82
58
|
let out;
|
|
83
59
|
if (r < BARE_COMMA_CUTOFF) {
|
|
84
|
-
//
|
|
60
|
+
// Bare comma form without postcode.
|
|
85
61
|
out = { raw: `${loc}, ${dep}`, components: { locality: loc, region: dep }, order: "bare-comma" };
|
|
86
62
|
}
|
|
87
63
|
else if (r < BARE_COMMA_PC_CUTOFF) {
|
|
88
|
-
//
|
|
64
|
+
// Comma form with postcode.
|
|
89
65
|
out = {
|
|
90
66
|
raw: `${loc}, ${dep} ${pc}`,
|
|
91
67
|
components: { locality: loc, region: dep, postcode: pc },
|
|
@@ -93,21 +69,18 @@ function render(random, c) {
|
|
|
93
69
|
};
|
|
94
70
|
}
|
|
95
71
|
else if (r < SPACE_PC_CUTOFF) {
|
|
96
|
-
//
|
|
72
|
+
// Space-delimited region with postcode.
|
|
97
73
|
out = { raw: `${loc} ${dep} ${pc}`, components: { locality: loc, region: dep, postcode: pc }, order: "space-pc" };
|
|
98
74
|
}
|
|
99
75
|
else if (r < CANONICAL_PC_FIRST_CUTOFF) {
|
|
100
|
-
//
|
|
76
|
+
// Canonical postcode-first form without département.
|
|
101
77
|
out = { raw: `${pc} ${loc}`, components: { postcode: pc, locality: loc }, order: "canonical-pc-first" };
|
|
102
78
|
}
|
|
103
79
|
else {
|
|
104
|
-
//
|
|
80
|
+
// Commune and postcode without département.
|
|
105
81
|
out = { raw: `${loc} ${pc}`, components: { locality: loc, postcode: pc }, order: "commune-pc" };
|
|
106
82
|
}
|
|
107
|
-
//
|
|
108
|
-
// token, so the model under-emitted country on FR (fr.country −3.5pp). ~20% of rows now append an
|
|
109
|
-
// explicit "France" + a `country` component — the model relearns to emit country WHEN the token is
|
|
110
|
-
// present without over-firing it on the (still-majority) country-less rows. Substring invariant holds.
|
|
83
|
+
// Add an explicit France suffix to a subset of rows to retain country-token examples.
|
|
111
84
|
if (random() < APPEND_COUNTRY_SHARE) {
|
|
112
85
|
out = {
|
|
113
86
|
raw: `${out.raw}, France`,
|
|
@@ -118,8 +91,7 @@ function render(random, c) {
|
|
|
118
91
|
return out;
|
|
119
92
|
}
|
|
120
93
|
/**
|
|
121
|
-
*
|
|
122
|
-
* and `description` below for the surface form it generates.
|
|
94
|
+
* Recipe registered with the corpus builder.
|
|
123
95
|
*/
|
|
124
96
|
export const frAdminSplitRecipe = {
|
|
125
97
|
name: "fr-admin-split",
|
|
@@ -129,10 +101,10 @@ export const frAdminSplitRecipe = {
|
|
|
129
101
|
{ flag: "--communes <tsv>", description: "BAN commune+postcode+coord TSV. Default /tmp/reg/fr-communes.tsv" },
|
|
130
102
|
],
|
|
131
103
|
async run(opts, write) {
|
|
132
|
-
//
|
|
104
|
+
// Preserve the legacy generator and seed behavior.
|
|
133
105
|
const random = makeMulberry32(opts.seed);
|
|
134
106
|
const count = opts.count ?? 60_000;
|
|
135
|
-
const source = opts.sourceName ?? "synth-fr-admin-split";
|
|
107
|
+
const source = opts.sourceName ?? defaultRecipeSource("synth-fr-admin-split");
|
|
136
108
|
const communesPath = opts.communes ?? DEFAULT_COMMUNES;
|
|
137
109
|
const pool = await readCommunes(communesPath);
|
|
138
110
|
console.error(` ${communesPath}: ${pool.length} communes with derived département`);
|
|
@@ -147,15 +119,15 @@ export const frAdminSplitRecipe = {
|
|
|
147
119
|
while (emitted < count && guard++ < count * 12) {
|
|
148
120
|
const base = pool[Math.floor(random() * N)];
|
|
149
121
|
const { raw, components, order } = render(random, base);
|
|
150
|
-
//
|
|
122
|
+
// Ensure every component appears verbatim in the rendered address.
|
|
151
123
|
const values = Object.values(components).filter((v) => Boolean(v));
|
|
152
124
|
if (!values.every((v) => raw.includes(v))) {
|
|
153
125
|
skipped++;
|
|
154
126
|
continue;
|
|
155
127
|
}
|
|
156
128
|
if (opts.golden) {
|
|
157
|
-
//
|
|
158
|
-
write(
|
|
129
|
+
// Golden rows include the source coordinates.
|
|
130
|
+
write(stringifyJSON({ raw, components, country: "FR", lat: Number(base.lat), lon: Number(base.lon) }));
|
|
159
131
|
emitted++;
|
|
160
132
|
orderCounts[order] = (orderCounts[order] ?? 0) + 1;
|
|
161
133
|
continue;
|
|
@@ -180,12 +152,18 @@ export const frAdminSplitRecipe = {
|
|
|
180
152
|
skipped++;
|
|
181
153
|
continue;
|
|
182
154
|
}
|
|
183
|
-
write(
|
|
184
|
-
|
|
155
|
+
write(stringifyJSON({
|
|
156
|
+
...aligned.row,
|
|
157
|
+
recipe: "fr-admin-split",
|
|
158
|
+
order,
|
|
159
|
+
base_source_id: null,
|
|
160
|
+
register: SourceRegister.BaseAdresseNationale,
|
|
161
|
+
surface: SurfaceOrigin.Composed,
|
|
162
|
+
}));
|
|
185
163
|
emitted++;
|
|
186
164
|
orderCounts[order] = (orderCounts[order] ?? 0) + 1;
|
|
187
165
|
}
|
|
188
|
-
console.error(` emitted=${emitted} skipped=${skipped} order-mix=${
|
|
166
|
+
console.error(` emitted=${emitted} skipped=${skipped} order-mix=${stringifyJSON(orderCounts)}`);
|
|
189
167
|
return { emitted, skipped };
|
|
190
168
|
},
|
|
191
169
|
};
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"admin-split.js","sourceRoot":"","sources":["../../../lib/fr/recipes/admin-split.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"admin-split.js","sourceRoot":"","sources":["../../../lib/fr/recipes/admin-split.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAGH,OAAO,EAAE,wBAAwB,EAAE,MAAM,qBAAqB,CAAA;AAC9D,OAAO,EAAE,YAAY,EAAE,MAAM,2BAA2B,CAAA;AACxD,OAAO,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAA;AACpD,OAAO,EAAE,UAAU,IAAI,cAAc,EAAE,MAAM,uBAAuB,CAAA;AACpE,OAAO,EAAE,cAAc,EAAE,UAAU,EAAE,MAAM,aAAa,CAAA;AAExD,OAAO,EAAE,cAAc,EAAE,MAAM,qBAAqB,CAAA;AAEpD,OAAO,EAAE,mBAAmB,EAAE,MAAM,kBAAkB,CAAA;AACtD,OAAO,EAAE,cAAc,EAAE,MAAM,YAAY,CAAA;AAC3C,OAAO,EAAE,aAAa,EAAE,MAAM,QAAQ,CAAA;AAEtC,OAAO,EAAE,QAAQ,EAAE,MAAM,QAAQ,CAAA;AAEjC,MAAM,gBAAgB,GAAG,YAAY,CAAC,KAAK,EAAE,iBAAiB,CAAC,CAAA;AAC/D,MAAM,OAAO,GAAG,gGAAgG,CAAA;AAsBhH;;GAEG;AACH,KAAK,UAAU,YAAY,CAAC,IAAY;IACvC,MAAM,IAAI,GAAiB,EAAE,CAAA;IAE7B,6BAA6B;IAC7B,IAAI,KAAK,EAAE,MAAM,CAAC,OAAO,EAAE,QAAQ,EAAE,GAAG,EAAE,GAAG,CAAC,IAAI,cAAc,CAAC,SAAS,CAAC,IAAI,EAAE;QAChF,eAAe,EAAE,UAAU,CAAC,GAAG;QAC/B,MAAM,EAAE,KAAK;KACb,CAAC,EAAE,CAAC;QACJ,IAAI,CAAC,OAAO,IAAI,CAAC,QAAQ;YAAE,SAAQ;QACnC,MAAM,GAAG,GAAG,wBAAwB,CAAC,QAAQ,CAAC,CAAA;QAE9C,IAAI,CAAC,GAAG;YAAE,SAAQ,CAAC,+CAA+C;QAClE,IAAI,CAAC,IAAI,CAAC,EAAE,OAAO,EAAE,QAAQ,EAAE,WAAW,EAAE,GAAG,CAAC,IAAI,EAAE,GAAG,EAAE,GAAG,EAAE,CAAC,CAAA;IAClE,CAAC;IAED,OAAO,IAAI,CAAA;AACZ,CAAC;AAED,2CAA2C;AAC3C,MAAM,oBAAoB,GAAG,GAAG,CAAA;AAChC,mDAAmD;AACnD,MAAM,iBAAiB,GAAG,IAAI,CAAA;AAC9B,MAAM,oBAAoB,GAAG,GAAG,CAAA;AAChC,MAAM,eAAe,GAAG,GAAG,CAAA;AAC3B,MAAM,yBAAyB,GAAG,IAAI,CAAA;AACtC,oDAAoD;AACpD,MAAM,oBAAoB,GAAG,GAAG,CAAA;AAEhC;;GAEG;AACH,SAAS,MAAM,CAAC,MAAoB,EAAE,CAAa;IAClD,MAAM,CAAC,GAAG,MAAM,EAAE,CAAA;IAClB,MAAM,GAAG,GAAG,MAAM,EAAE,GAAG,oBAAoB,CAAC,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,OAAO,CAAA;IACjF,MAAM,GAAG,GAAG,CAAC,CAAC,WAAW,CAAA;IACzB,MAAM,EAAE,GAAG,CAAC,CAAC,QAAQ,CAAA;IACrB,IAAI,GAAsB,CAAA;IAE1B,IAAI,CAAC,GAAG,iBAAiB,EAAE,CAAC;QAC3B,oCAAoC;QACpC,GAAG,GAAG,EAAE,GAAG,EAAE,GAAG,GAAG,KAAK,GAAG,EAAE,EAAE,UAAU,EAAE,EAAE,QAAQ,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,CAAA;IACjG,CAAC;SAAM,IAAI,CAAC,GAAG,oBAAoB,EAAE,CAAC;QACrC,4BAA4B;QAC5B,GAAG,GAAG;YACL,GAAG,EAAE,GAAG,GAAG,KAAK,GAAG,IAAI,EAAE,EAAE;YAC3B,UAAU,EAAE,EAAE,QAAQ,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE,QAAQ,EAAE,EAAE,EAAE;YACxD,KAAK,EAAE,eAAe;SACtB,CAAA;IACF,CAAC;SAAM,IAAI,CAAC,GAAG,eAAe,EAAE,CAAC;QAChC,wCAAwC;QACxC,GAAG,GAAG,EAAE,GAAG,EAAE,GAAG,GAAG,IAAI,GAAG,IAAI,EAAE,EAAE,EAAE,UAAU,EAAE,EAAE,QAAQ,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE,QAAQ,EAAE,EAAE,EAAE,EAAE,KAAK,EAAE,UAAU,EAAE,CAAA;IAClH,CAAC;SAAM,IAAI,CAAC,GAAG,yBAAyB,EAAE,CAAC;QAC1C,qDAAqD;QACrD,GAAG,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,IAAI,GAAG,EAAE,EAAE,UAAU,EAAE,EAAE,QAAQ,EAAE,EAAE,EAAE,QAAQ,EAAE,GAAG,EAAE,EAAE,KAAK,EAAE,oBAAoB,EAAE,CAAA;IACxG,CAAC;SAAM,CAAC;QACP,4CAA4C;QAC5C,GAAG,GAAG,EAAE,GAAG,EAAE,GAAG,GAAG,IAAI,EAAE,EAAE,EAAE,UAAU,EAAE,EAAE,QAAQ,EAAE,GAAG,EAAE,QAAQ,EAAE,EAAE,EAAE,EAAE,KAAK,EAAE,YAAY,EAAE,CAAA;IAChG,CAAC;IAED,sFAAsF;IACtF,IAAI,MAAM,EAAE,GAAG,oBAAoB,EAAE,CAAC;QACrC,GAAG,GAAG;YACL,GAAG,EAAE,GAAG,GAAG,CAAC,GAAG,UAAU;YACzB,UAAU,EAAE,EAAE,GAAG,GAAG,CAAC,UAAU,EAAE,OAAO,EAAE,QAAQ,EAAE;YACpD,KAAK,EAAE,GAAG,GAAG,CAAC,KAAK,KAAK;SACxB,CAAA;IACF,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAAiB;IAC/C,IAAI,EAAE,gBAAgB;IACtB,WAAW,EAAE,mGAAmG;IAChH,IAAI,EAAE,UAAU;IAChB,OAAO,EAAE;QACR,EAAE,IAAI,EAAE,kBAAkB,EAAE,WAAW,EAAE,kEAAkE,EAAE;KAC7G;IACD,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,mDAAmD;QACnD,MAAM,MAAM,GAAG,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACxC,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,IAAI,MAAM,CAAA;QAClC,MAAM,MAAM,GAAG,IAAI,CAAC,UAAU,IAAI,mBAAmB,CAAC,sBAAsB,CAAC,CAAA;QAC7E,MAAM,YAAY,GAAG,IAAI,CAAC,QAAQ,IAAI,gBAAgB,CAAA;QAEtD,MAAM,IAAI,GAAG,MAAM,YAAY,CAAC,YAAY,CAAC,CAAA;QAE7C,OAAO,CAAC,KAAK,CAAC,KAAK,YAAY,KAAK,IAAI,CAAC,MAAM,oCAAoC,CAAC,CAAA;QAEpF,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,CAAC;YAClB,MAAM,IAAI,KAAK,CAAC,qEAAqE,CAAC,CAAA;QACvF,CAAC;QAED,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,KAAK,GAAG,CAAC,CAAA;QACb,MAAM,WAAW,GAA2B,EAAE,CAAA;QAC9C,MAAM,CAAC,GAAG,IAAI,CAAC,MAAM,CAAA;QAErB,OAAO,OAAO,GAAG,KAAK,IAAI,KAAK,EAAE,GAAG,KAAK,GAAG,EAAE,EAAE,CAAC;YAChD,MAAM,IAAI,GAAG,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,CAAE,CAAA;YAC5C,MAAM,EAAE,GAAG,EAAE,UAAU,EAAE,KAAK,EAAE,GAAG,MAAM,CAAC,MAAM,EAAE,IAAI,CAAC,CAAA;YAEvD,mEAAmE;YACnE,MAAM,MAAM,GAAG,MAAM,CAAC,MAAM,CAAC,UAAU,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAe,EAAE,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,CAAA;YAE/E,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC;gBAC3C,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC;gBACjB,8CAA8C;gBAC9C,KAAK,CAAC,aAAa,CAAC,EAAE,GAAG,EAAE,UAAU,EAAE,OAAO,EAAE,IAAI,EAAE,GAAG,EAAE,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,GAAG,EAAE,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC,CAAA;gBAEtG,OAAO,EAAE,CAAA;gBACT,WAAW,CAAC,KAAK,CAAC,GAAG,CAAC,WAAW,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAA;gBAElD,SAAQ;YACT,CAAC;YAED,MAAM,QAAQ,GAAG,cAAc,CAAC,MAAM,EAAE;gBACvC,QAAQ,EAAE,UAAU,CAAC,QAAQ;gBAC7B,MAAM,EAAE,UAAU,CAAC,MAAM;gBACzB,QAAQ,EAAE,UAAU,CAAC,QAAQ;aAC7B,CAAC,CAAA;YAEF,MAAM,SAAS,GAAiB;gBAC/B,GAAG;gBACH,UAAU;gBACV,OAAO,EAAE,IAAI;gBACb,MAAM,EAAE,OAAO;gBACf,MAAM;gBACN,SAAS,EAAE,QAAQ;gBACnB,cAAc,EAAE,OAAO;gBACvB,OAAO,EAAE,OAAO;aAChB,CAAA;YAED,MAAM,OAAO,GAAG,QAAQ,CAAC,SAAS,CAAC,CAAA;YAEnC,IAAI,OAAO,CAAC,IAAI,KAAK,SAAS,IAAI,CAAC,OAAO,CAAC,GAAG,EAAE,CAAC;gBAChD,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,KAAK,CACJ,aAAa,CAAC;gBACb,GAAG,OAAO,CAAC,GAAG;gBACd,MAAM,EAAE,gBAAgB;gBACxB,KAAK;gBACL,cAAc,EAAE,IAAI;gBACpB,QAAQ,EAAE,cAAc,CAAC,oBAAoB;gBAC7C,OAAO,EAAE,aAAa,CAAC,QAAQ;aAC/B,CAAC,CACF,CAAA;YAED,OAAO,EAAE,CAAA;YACT,WAAW,CAAC,KAAK,CAAC,GAAG,CAAC,WAAW,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAA;QACnD,CAAC;QAED,OAAO,CAAC,KAAK,CAAC,aAAa,OAAO,YAAY,OAAO,cAAc,aAAa,CAAC,WAAW,CAAC,EAAE,CAAC,CAAA;QAEhG,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;IAC5B,CAAC;CACD,CAAA"}
|
|
@@ -3,26 +3,11 @@
|
|
|
3
3
|
* @license AGPL-3.0
|
|
4
4
|
* @author Teffen Ellis, et al.
|
|
5
5
|
*
|
|
6
|
-
*
|
|
7
|
-
* other comprehensive FR source) is postcode-COMPLETE, so the model learned the French
|
|
8
|
-
* street→locality boundary as "the token after the 5-digit postcode," never as "comma + city." Strip
|
|
9
|
-
* the postcode and it leaks the street's proper-noun tokens into the following locality ("Rue René
|
|
10
|
-
* Cassin, Paris" → street="Rue Ren", locality="Cassin"). This recipe mints the MISSING distribution:
|
|
11
|
-
* the BARE comma form, NO postcode, real `(street, number, city)` tuples from BAN (Licence Ouverte —
|
|
12
|
-
* permissive; the model stays clean of ODbL, unlike the opt-in OSM rooftop slices).
|
|
13
|
-
*
|
|
14
|
-
* Each tuple → `<n> <Rue/Avenue/…> <proper-noun name>, <City>` with the FR prefix split
|
|
15
|
-
* ({@link decomposeFrStreet}: "Rue" → street_prefix, the rest → street). Tuples whose street carries
|
|
16
|
-
* no recognized FR type word are skipped — the failing class is precisely the prefix-led street.
|
|
17
|
-
*
|
|
18
|
-
* ⚠ Convention loss-mask: this recipe TEACHES FR `street_prefix`. The conventions loss-mask forbids it
|
|
19
|
-
* for FR and will `-inf` these gold labels (the v1.6.0 ~7M-loss blow-up). Disable that mask for any
|
|
20
|
-
* run including this slice.
|
|
6
|
+
* Generate postcode-free French examples from BAN with separate street-prefix labels.
|
|
21
7
|
*/
|
|
22
8
|
import { type CorpusRecipe } from "#recipes/scaffold";
|
|
23
9
|
/**
|
|
24
|
-
*
|
|
25
|
-
* and `description` below for the surface form it generates.
|
|
10
|
+
* Register the French bare-street recipe.
|
|
26
11
|
*/
|
|
27
12
|
export declare const frBareStreetRecipe: CorpusRecipe;
|
|
28
13
|
//# sourceMappingURL=bare-street.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"bare-street.d.ts","sourceRoot":"","sources":["../../../lib/fr/recipes/bare-street.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"bare-street.d.ts","sourceRoot":"","sources":["../../../lib/fr/recipes/bare-street.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAMH,OAAO,EAA6B,KAAK,YAAY,EAAkB,MAAM,mBAAmB,CAAA;AAmChG;;GAEG;AACH,eAAO,MAAM,kBAAkB,EAAE,YA2GhC,CAAA"}
|
|
@@ -3,46 +3,48 @@
|
|
|
3
3
|
* @license AGPL-3.0
|
|
4
4
|
* @author Teffen Ellis, et al.
|
|
5
5
|
*
|
|
6
|
-
*
|
|
7
|
-
* other comprehensive FR source) is postcode-COMPLETE, so the model learned the French
|
|
8
|
-
* street→locality boundary as "the token after the 5-digit postcode," never as "comma + city." Strip
|
|
9
|
-
* the postcode and it leaks the street's proper-noun tokens into the following locality ("Rue René
|
|
10
|
-
* Cassin, Paris" → street="Rue Ren", locality="Cassin"). This recipe mints the MISSING distribution:
|
|
11
|
-
* the BARE comma form, NO postcode, real `(street, number, city)` tuples from BAN (Licence Ouverte —
|
|
12
|
-
* permissive; the model stays clean of ODbL, unlike the opt-in OSM rooftop slices).
|
|
13
|
-
*
|
|
14
|
-
* Each tuple → `<n> <Rue/Avenue/…> <proper-noun name>, <City>` with the FR prefix split
|
|
15
|
-
* ({@link decomposeFrStreet}: "Rue" → street_prefix, the rest → street). Tuples whose street carries
|
|
16
|
-
* no recognized FR type word are skipped — the failing class is precisely the prefix-led street.
|
|
17
|
-
*
|
|
18
|
-
* ⚠ Convention loss-mask: this recipe TEACHES FR `street_prefix`. The conventions loss-mask forbids it
|
|
19
|
-
* for FR and will `-inf` these gold labels (the v1.6.0 ~7M-loss blow-up). Disable that mask for any
|
|
20
|
-
* run including this slice.
|
|
6
|
+
* Generate postcode-free French examples from BAN with separate street-prefix labels.
|
|
21
7
|
*/
|
|
22
8
|
import { FR_VOIE_TYPES } from "@mailwoman/codex/fr";
|
|
23
9
|
import { mulberry32 as makeMulberry32 } from "@mailwoman/core/utils";
|
|
24
|
-
import { decomposeFrStreet } from "#fr/
|
|
25
|
-
import { alignAndWrite, readTuples,
|
|
10
|
+
import { decomposeFrStreet } from "#fr/street-decompose";
|
|
11
|
+
import { alignAndWrite, readTuples, recipeSourceID } from "#recipes/scaffold";
|
|
12
|
+
import { defaultRecipeSource } from "#recipes/sources";
|
|
13
|
+
import { SourceRegister } from "#registers";
|
|
14
|
+
import { SurfaceOrigin } from "#types";
|
|
15
|
+
/**
|
|
16
|
+
* Shared provenance for postcode-free BAN rows.
|
|
17
|
+
*/
|
|
18
|
+
/**
|
|
19
|
+
* Resolved once, because `source_id` includes the source as its prefix and a pair
|
|
20
|
+
* that disagreed would name a source no row of this output declares.
|
|
21
|
+
*/
|
|
22
|
+
const FR_BARE_STREET_SOURCE = defaultRecipeSource("synth-fr-bare-street");
|
|
23
|
+
const FR_BARE_STREET_PROVENANCE = {
|
|
24
|
+
register: SourceRegister.BaseAdresseNationale,
|
|
25
|
+
surface: SurfaceOrigin.Composed,
|
|
26
|
+
// The BAN record behind each row exists.
|
|
27
|
+
// The tuple file has no `sourceID` to identify it.
|
|
28
|
+
// The extraction must emit that ID to populate this field (#2359).
|
|
29
|
+
baseSourceID: null,
|
|
30
|
+
};
|
|
26
31
|
/**
|
|
27
|
-
*
|
|
28
|
-
* entry. Types with no attested abbreviation stay canonical in the abbreviated form.
|
|
32
|
+
* First abbreviation listed for each street type.
|
|
29
33
|
*/
|
|
30
34
|
const FR_VOIE_ABBREV = Object.fromEntries(Object.entries(FR_VOIE_TYPES).flatMap(([canonical, abbrevs]) => (abbrevs[0] ? [[canonical, abbrevs[0]]] : [])));
|
|
31
35
|
/**
|
|
32
|
-
*
|
|
33
|
-
* counterweight to the locality-terminated comma-free forms (see the cycle comment).
|
|
36
|
+
* Index of the street-only form.
|
|
34
37
|
*/
|
|
35
38
|
const BARE_STREET_ONLY_FORM = 3;
|
|
36
39
|
/**
|
|
37
|
-
*
|
|
38
|
-
* and `description` below for the surface form it generates.
|
|
40
|
+
* Register the French bare-street recipe.
|
|
39
41
|
*/
|
|
40
42
|
export const frBareStreetRecipe = {
|
|
41
43
|
name: "fr-bare-street",
|
|
42
44
|
description: "FR bare street+city, NO postcode (#251): comma / comma-free / abbreviated-voie surfaces over one label set",
|
|
43
45
|
mode: "tuples",
|
|
44
46
|
async run(opts, write) {
|
|
45
|
-
//
|
|
47
|
+
// Preserve the recipe's seeded initialization.
|
|
46
48
|
makeMulberry32(opts.seed);
|
|
47
49
|
let read = 0;
|
|
48
50
|
let emitted = 0;
|
|
@@ -57,11 +59,7 @@ export const frBareStreetRecipe = {
|
|
|
57
59
|
continue;
|
|
58
60
|
}
|
|
59
61
|
const { prefix, street } = decomposeFrStreet(fullStreet);
|
|
60
|
-
//
|
|
61
|
-
// exercise — but as a BARE surface it is exactly the non-voie-led counterweight the v4.5.1
|
|
62
|
-
// probe showed missing ('Savile Row'-shaped spans still fell to the trailing-locality
|
|
63
|
-
// prior; the voie-led bare form protected only voie-led spans). Alternate rows emit the
|
|
64
|
-
// whole span as a bare street; the rest skip as before.
|
|
62
|
+
// Retain some multiword streets without a recognized type as counterexamples.
|
|
65
63
|
if (!prefix || !street) {
|
|
66
64
|
if (read % 2 === 0 && fullStreet.split(" ").length >= 2) {
|
|
67
65
|
const bare = {
|
|
@@ -69,8 +67,8 @@ export const frBareStreetRecipe = {
|
|
|
69
67
|
components: { street: fullStreet },
|
|
70
68
|
country: "FR",
|
|
71
69
|
locale: "fr-FR",
|
|
72
|
-
source:
|
|
73
|
-
source_id:
|
|
70
|
+
source: FR_BARE_STREET_SOURCE,
|
|
71
|
+
source_id: recipeSourceID(FR_BARE_STREET_SOURCE, {
|
|
74
72
|
street: fullStreet,
|
|
75
73
|
f: "bare-nonvoie",
|
|
76
74
|
v: String(read),
|
|
@@ -78,7 +76,7 @@ export const frBareStreetRecipe = {
|
|
|
78
76
|
corpus_version: "0.9.4",
|
|
79
77
|
license: "Synthetic — fr-bare-street; (street, number, city) from BAN (Base Adresse Nationale, Licence Ouverte)",
|
|
80
78
|
};
|
|
81
|
-
if (alignAndWrite(write, bare, "fr-bare-street")) {
|
|
79
|
+
if (alignAndWrite(write, bare, "fr-bare-street", FR_BARE_STREET_PROVENANCE)) {
|
|
82
80
|
emitted++;
|
|
83
81
|
}
|
|
84
82
|
else {
|
|
@@ -89,26 +87,13 @@ export const frBareStreetRecipe = {
|
|
|
89
87
|
skipped++;
|
|
90
88
|
continue;
|
|
91
89
|
}
|
|
92
|
-
//
|
|
93
|
-
// original change; the COMMA-FREE form is the colloquial register users actually type
|
|
94
|
-
// ('12 rue de Rome Paris' — the street↔locality boundary with NO delimiter, the fr-fr
|
|
95
|
-
// panel's named loss); the ABBREVIATED form is the typeahead register the geocoder-tester
|
|
96
|
-
// FR slice attests at scale; and the BARE-STREET-ONLY form is the absence counterweight —
|
|
97
|
-
// without it, every delimiter-free surface in the mix ENDS in a locality, the model learns
|
|
98
|
-
// "trailing span = locality" as categorical, and bare street names across locales flip to
|
|
99
|
-
// locality wholesale (the v4.5.0 no-promote's measured erosion: 'Calle de Alcalá',
|
|
100
|
-
// 'Madison Square West', and COMER's fork all fell to that prior). Tags are identical
|
|
101
|
-
// where present; each component VALUE is the span as written (BIO alignment binds value
|
|
102
|
-
// to surface); the bare form carries NO number and NO locality because the surface has
|
|
103
|
-
// neither.
|
|
90
|
+
// Rotate comma-separated, compact, abbreviated and street-only variants.
|
|
104
91
|
const form = read % 4;
|
|
105
92
|
const prefixSurface = form >= 2 ? (FR_VOIE_ABBREV[prefix.toLowerCase()] ?? prefix) : prefix;
|
|
106
93
|
const components = form === BARE_STREET_ONLY_FORM
|
|
107
94
|
? { street_prefix: prefix, street }
|
|
108
95
|
: { house_number: number, street_prefix: prefixSurface, street, locality };
|
|
109
|
-
//
|
|
110
|
-
// THREE-slot middle surface — the dependent-locality counterweight (the v4.5.1 erosion's
|
|
111
|
-
// untouched half: the two-slot comma-free endings squeezed the middle tag out).
|
|
96
|
+
// Include a neighborhood in the comma-separated form when available.
|
|
112
97
|
const hood = String(t.neighbourhood ?? "").trim();
|
|
113
98
|
if (form === 0 && hood) {
|
|
114
99
|
components.dependent_locality = hood;
|
|
@@ -120,18 +105,18 @@ export const frBareStreetRecipe = {
|
|
|
120
105
|
: form === BARE_STREET_ONLY_FORM
|
|
121
106
|
? `${prefix} ${street}`
|
|
122
107
|
: `${number} ${prefixSurface} ${street} ${locality}`;
|
|
123
|
-
const source_id =
|
|
108
|
+
const source_id = recipeSourceID(FR_BARE_STREET_SOURCE, { ...components, f: String(form), v: String(read) });
|
|
124
109
|
const canonical = {
|
|
125
110
|
raw,
|
|
126
111
|
components,
|
|
127
112
|
country: "FR",
|
|
128
113
|
locale: "fr-FR",
|
|
129
|
-
source:
|
|
114
|
+
source: FR_BARE_STREET_SOURCE,
|
|
130
115
|
source_id,
|
|
131
116
|
corpus_version: "0.9.4",
|
|
132
117
|
license: "Synthetic — fr-bare-street; (street, number, city) from BAN (Base Adresse Nationale, Licence Ouverte)",
|
|
133
118
|
};
|
|
134
|
-
if (alignAndWrite(write, canonical, "fr-bare-street")) {
|
|
119
|
+
if (alignAndWrite(write, canonical, "fr-bare-street", FR_BARE_STREET_PROVENANCE)) {
|
|
135
120
|
emitted++;
|
|
136
121
|
}
|
|
137
122
|
else {
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"bare-street.js","sourceRoot":"","sources":["../../../lib/fr/recipes/bare-street.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"bare-street.js","sourceRoot":"","sources":["../../../lib/fr/recipes/bare-street.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH,OAAO,EAAE,aAAa,EAAE,MAAM,qBAAqB,CAAA;AACnD,OAAO,EAAE,UAAU,IAAI,cAAc,EAAE,MAAM,uBAAuB,CAAA;AAEpE,OAAO,EAAE,iBAAiB,EAAE,MAAM,sBAAsB,CAAA;AACxD,OAAO,EAAE,aAAa,EAAE,UAAU,EAAqB,cAAc,EAAE,MAAM,mBAAmB,CAAA;AAChG,OAAO,EAAE,mBAAmB,EAAE,MAAM,kBAAkB,CAAA;AACtD,OAAO,EAAE,cAAc,EAAE,MAAM,YAAY,CAAA;AAC3C,OAAO,EAAE,aAAa,EAAE,MAAM,QAAQ,CAAA;AAEtC;;GAEG;AACH;;;GAGG;AACH,MAAM,qBAAqB,GAAG,mBAAmB,CAAC,sBAAsB,CAAC,CAAA;AAEzE,MAAM,yBAAyB,GAAG;IACjC,QAAQ,EAAE,cAAc,CAAC,oBAAoB;IAC7C,OAAO,EAAE,aAAa,CAAC,QAAQ;IAC/B,yCAAyC;IACzC,mDAAmD;IACnD,mEAAmE;IACnE,YAAY,EAAE,IAAI;CAClB,CAAA;AAED;;GAEG;AACH,MAAM,cAAc,GAA2B,MAAM,CAAC,WAAW,CAChE,MAAM,CAAC,OAAO,CAAC,aAAa,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,SAAS,EAAE,OAAO,CAAC,EAAE,EAAE,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,SAAS,EAAE,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAC9G,CAAA;AAED;;GAEG;AACH,MAAM,qBAAqB,GAAG,CAAC,CAAA;AAE/B;;GAEG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAAiB;IAC/C,IAAI,EAAE,gBAAgB;IACtB,WAAW,EACV,4GAA4G;IAC7G,IAAI,EAAE,QAAQ;IACd,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,+CAA+C;QAC/C,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACzB,IAAI,IAAI,GAAG,CAAC,CAAA;QACZ,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QAEf,IAAI,KAAK,EAAE,MAAM,CAAC,IAAI,UAAU,CAAC,IAAI,CAAC,KAAM,CAAC,EAAE,CAAC;YAC/C,IAAI,EAAE,CAAA;YACN,MAAM,UAAU,GAAG,MAAM,CAAC,CAAC,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAChD,MAAM,MAAM,GAAG,MAAM,CAAC,CAAC,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAC5C,MAAM,QAAQ,GAAG,MAAM,CAAC,CAAC,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAEhD,IAAI,CAAC,UAAU,IAAI,CAAC,MAAM,IAAI,CAAC,QAAQ,EAAE,CAAC;gBACzC,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,GAAG,iBAAiB,CAAC,UAAU,CAAC,CAAA;YAExD,8EAA8E;YAC9E,IAAI,CAAC,MAAM,IAAI,CAAC,MAAM,EAAE,CAAC;gBACxB,IAAI,IAAI,GAAG,CAAC,KAAK,CAAC,IAAI,UAAU,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,MAAM,IAAI,CAAC,EAAE,CAAC;oBACzD,MAAM,IAAI,GAAG;wBACZ,GAAG,EAAE,UAAU;wBACf,UAAU,EAAE,EAAE,MAAM,EAAE,UAAU,EAA4B;wBAC5D,OAAO,EAAE,IAAI;wBACb,MAAM,EAAE,OAAO;wBACf,MAAM,EAAE,qBAAqB;wBAC7B,SAAS,EAAE,cAAc,CAAC,qBAAqB,EAAE;4BAChD,MAAM,EAAE,UAAU;4BAClB,CAAC,EAAE,cAAc;4BACjB,CAAC,EAAE,MAAM,CAAC,IAAI,CAAC;yBACf,CAAC;wBACF,cAAc,EAAE,OAAO;wBACvB,OAAO,EACN,uGAAuG;qBACxG,CAAA;oBAED,IAAI,aAAa,CAAC,KAAK,EAAE,IAAI,EAAE,gBAAgB,EAAE,yBAAyB,CAAC,EAAE,CAAC;wBAC7E,OAAO,EAAE,CAAA;oBACV,CAAC;yBAAM,CAAC;wBACP,OAAO,EAAE,CAAA;oBACV,CAAC;oBAED,SAAQ;gBACT,CAAC;gBAED,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,yEAAyE;YACzE,MAAM,IAAI,GAAG,IAAI,GAAG,CAAC,CAAA;YACrB,MAAM,aAAa,GAAG,IAAI,IAAI,CAAC,CAAC,CAAC,CAAC,CAAC,cAAc,CAAC,MAAM,CAAC,WAAW,EAAE,CAAC,IAAI,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAA;YAE3F,MAAM,UAAU,GACf,IAAI,KAAK,qBAAqB;gBAC7B,CAAC,CAAC,EAAE,aAAa,EAAE,MAAM,EAAE,MAAM,EAAE;gBACnC,CAAC,CAAC,EAAE,YAAY,EAAE,MAAM,EAAE,aAAa,EAAE,aAAa,EAAE,MAAM,EAAE,QAAQ,EAAE,CAAA;YAE5E,qEAAqE;YACrE,MAAM,IAAI,GAAG,MAAM,CAAC,CAAC,CAAC,aAAa,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAEjD,IAAI,IAAI,KAAK,CAAC,IAAI,IAAI,EAAE,CAAC;gBACxB,UAAU,CAAC,kBAAkB,GAAG,IAAI,CAAA;YACrC,CAAC;YAED,MAAM,GAAG,GACR,IAAI,KAAK,CAAC;gBACT,CAAC,CAAC,IAAI;oBACL,CAAC,CAAC,GAAG,MAAM,IAAI,MAAM,IAAI,MAAM,KAAK,IAAI,KAAK,QAAQ,EAAE;oBACvD,CAAC,CAAC,GAAG,MAAM,IAAI,MAAM,IAAI,MAAM,KAAK,QAAQ,EAAE;gBAC/C,CAAC,CAAC,IAAI,KAAK,qBAAqB;oBAC/B,CAAC,CAAC,GAAG,MAAM,IAAI,MAAM,EAAE;oBACvB,CAAC,CAAC,GAAG,MAAM,IAAI,aAAa,IAAI,MAAM,IAAI,QAAQ,EAAE,CAAA;YAEvD,MAAM,SAAS,GAAG,cAAc,CAAC,qBAAqB,EAAE,EAAE,GAAG,UAAU,EAAE,CAAC,EAAE,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC,CAAA;YAE5G,MAAM,SAAS,GAAG;gBACjB,GAAG;gBACH,UAAU;gBACV,OAAO,EAAE,IAAI;gBACb,MAAM,EAAE,OAAO;gBACf,MAAM,EAAE,qBAAqB;gBAC7B,SAAS;gBACT,cAAc,EAAE,OAAO;gBACvB,OAAO,EACN,uGAAuG;aACxG,CAAA;YAED,IAAI,aAAa,CAAC,KAAK,EAAE,SAAS,EAAE,gBAAgB,EAAE,yBAAyB,CAAC,EAAE,CAAC;gBAClF,OAAO,EAAE,CAAA;YACV,CAAC;iBAAM,CAAC;gBACP,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;QAED,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;IAClC,CAAC;CACD,CAAA"}
|
|
@@ -3,75 +3,16 @@
|
|
|
3
3
|
* @license AGPL-3.0
|
|
4
4
|
* @author Teffen Ellis, et al.
|
|
5
5
|
*
|
|
6
|
-
*
|
|
6
|
+
* Generates French street fragments without a postcode from BAN tuples.
|
|
7
7
|
*
|
|
8
|
-
* The
|
|
9
|
-
*
|
|
10
|
-
*
|
|
11
|
-
*
|
|
12
|
-
*
|
|
13
|
-
* ```
|
|
14
|
-
* "Rue Montmartre" -> locality="Rue Montmartre"
|
|
15
|
-
* "Allee Poque" -> locality="Allee Poque"
|
|
16
|
-
* ```
|
|
17
|
-
*
|
|
18
|
-
* `Rue` can only mean street in French. The model is not mislabelling an ambiguous toponym; it is
|
|
19
|
-
* mislabelling `Rue`.
|
|
20
|
-
*
|
|
21
|
-
* WHY THE EXISTING RECIPE DOESN'T COVER THIS. {@link frBareStreetRecipe} (#251) mints
|
|
22
|
-
* `<n> Rue <name>, <City>` — the bare COMMA form, no postcode. It targets postcode-anchoring
|
|
23
|
-
* imbalance, and every row it emits still carries a house number AND a locality. It cannot teach
|
|
24
|
-
* the class above, because it never shows the model a street standing alone.
|
|
25
|
-
*
|
|
26
|
-
* WHAT THIS MINTS. Five street forms — the first three carry NO house number and NO locality, which
|
|
27
|
-
* is the whole point — plus the counter-distribution:
|
|
28
|
-
*
|
|
29
|
-
* 1. `bare-street` "Rue Montmartre"
|
|
30
|
-
* 2. `street-particle` "Rue de la Paix"
|
|
31
|
-
* 3. `date-name` "Allee du 11 Novembre 1918"
|
|
32
|
-
* 4. `street-housenumber` "12 Rue Montmartre" — the anchor, so the licence isn't UNLEARNED
|
|
33
|
-
* 5. `alnum-housenumber` "12 bis Rue Montmartre"
|
|
34
|
-
* 6. `bare-locality` "Mery-sur-Oise" — NEGATIVE: a bare toponym that IS a locality
|
|
35
|
-
*
|
|
36
|
-
* The **admin/street homonym** class (`Rue de Rome`) is deliberately NOT a separate form. Homonym
|
|
37
|
-
* streets are already in the register and fall into 1–3 naturally; there is nothing different to
|
|
38
|
-
* teach about them, because the lesson is identical — the designator makes it a street. The
|
|
39
|
-
* fragment board scores them separately (they need measuring, not minting), and the recipe would
|
|
40
|
-
* need a second pass over the commune set to label them, buying a `synth_method` string and no
|
|
41
|
-
* training signal.
|
|
42
|
-
*
|
|
43
|
-
* FORM 7 IS NOT OPTIONAL. T1c's standing prediction: the board's `bare-locality` cell reads 0.980
|
|
44
|
-
* for the WRONG REASON — the model calls everything without a house number a locality, and on bare
|
|
45
|
-
* localities that is accidentally right. Teach bare streets alone and the model has every incentive
|
|
46
|
-
* to flip that default rather than learn the distinction, trading a 0.215 for a 0.980. The slice
|
|
47
|
-
* must show BOTH bare forms so the discriminating evidence is the designator, which is the only
|
|
48
|
-
* thing that actually distinguishes them. This is the same counter-distribution principle
|
|
49
|
-
* {@link noStreetRecipe} established after synth-street pushed the model into "decompose mode".
|
|
50
|
-
*
|
|
51
|
-
* SPLIT. `--exclude-surfaces` takes the fragment board's reserved surface list
|
|
52
|
-
* (`mailwoman/eval-harness/fixtures/ban-fragments-fr.surfaces.txt`). Every listed surface is
|
|
53
|
-
* skipped — source-disjoint by normalized street SURFACE, never by record row. Row-disjoint leaks
|
|
54
|
-
* the surface across the boundary and measures memorization of `Rue de Rivoli` while claiming
|
|
55
|
-
* generalization to unseen streets. The recipe REFUSES to run without the list rather than
|
|
56
|
-
* silently minting a contaminated slice.
|
|
57
|
-
*
|
|
58
|
-
* MIX. The slice is ~145K rows off a 120K-tuple draw; the intended corpus mix is **5–10%**, set at
|
|
59
|
-
* assembly time by slice weight rather than by row count. Keep the cap: a slice that fixes fragments
|
|
60
|
-
* by degrading full addresses has moved the failure, not fixed it — which is what
|
|
61
|
-
* `street-housenumber` / `alnum-housenumber` on the fragment board and the global parity floor are
|
|
62
|
-
* there to catch. `date-name` is ~0.5% of the slice because BAN only holds ~1,418 date-name streets
|
|
63
|
-
* after filtering and the tuple extractor already takes every one; if that class needs more, the
|
|
64
|
-
* change is slice weight, not invented data.
|
|
65
|
-
*
|
|
66
|
-
* ⚠ Convention loss-mask: like {@link frBareStreetRecipe}, this recipe TEACHES FR `street_prefix`.
|
|
67
|
-
* The conventions loss-mask forbids it for FR and will `-inf` these gold labels (the v1.6.0 ~7M-loss
|
|
68
|
-
* blow-up). Disable that mask for any run including this slice.
|
|
8
|
+
* The output mixes designator-led streets with bare commune names as counterexamples.
|
|
9
|
+
* Some streets include a house number.
|
|
10
|
+
* `--exclude-surfaces` keeps streets on the fragment evaluation board out of training. A model trained on
|
|
11
|
+
* these rows needs the French `street_prefix` loss mask disabled.
|
|
69
12
|
*/
|
|
70
13
|
import { type CorpusRecipe } from "#recipes/scaffold";
|
|
71
|
-
export declare function frTitleCase(value: string): string;
|
|
72
14
|
/**
|
|
73
|
-
*
|
|
74
|
-
* and `description` below for the surface form it generates.
|
|
15
|
+
* The recipe registered with the corpus builder.
|
|
75
16
|
*/
|
|
76
17
|
export declare const frFragmentRecipe: CorpusRecipe;
|
|
77
18
|
//# sourceMappingURL=fragment.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"fragment.d.ts","sourceRoot":"","sources":["../../../lib/fr/recipes/fragment.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"fragment.d.ts","sourceRoot":"","sources":["../../../lib/fr/recipes/fragment.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;GAWG;AAQH,OAAO,EAA6B,KAAK,YAAY,EAAkB,MAAM,mBAAmB,CAAA;AA4DhG;;GAEG;AACH,eAAO,MAAM,gBAAgB,EAAE,YAwK9B,CAAA"}
|