@mailwoman/corpus 9.4.0 → 10.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +134 -32
- package/data/PROVENANCE.md +623 -17
- package/data/address-source-register.json +14249 -0
- package/data/builds/v0.7.0-de-holdout/inputs.json +22 -0
- package/data/builds/v0.8.0-registers/inputs.json +92 -0
- package/data/license-decisions.json +1603 -0
- package/data/licenses/PROVENANCE.md +65 -0
- package/data/licenses/cdla-permissive-2.0.md +43 -0
- package/data/licenses/geonames-publication.md +34 -0
- package/data/licenses/licence-ouverte-2.0.md +36 -0
- package/data/licenses/national-address-database.md +46 -0
- package/data/licenses/nlod-2.0.md +90 -0
- package/data/licenses/sirene-publication.md +38 -0
- package/data/licenses/whosonfirst-licenses.md +65 -0
- package/data/source-resolutions.json +804 -0
- package/data/sub-venue-lexicon.json +1 -1
- package/data/training-manifests/v0.7.0-de-holdout.effective.json +477 -0
- package/data/training-manifests/v0.7.0-de-holdout.json +78 -0
- package/lib/adapters/cordis/adapter.ts +785 -0
- package/lib/adapters/dedup-key.ts +40 -0
- package/lib/adapters/errors.ts +21 -0
- package/lib/adapters/geonames/adapter.ts +43 -53
- package/lib/adapters/geonames/postal/adapter.ts +116 -0
- package/lib/adapters/gleif/adapter.ts +828 -0
- package/lib/adapters/libpostal-dictionary.ts +39 -0
- package/lib/adapters/openaddresses/adapter.ts +54 -61
- package/lib/adapters/osm/adapter.ts +356 -0
- package/lib/adapters/overture/adapter.ts +65 -41
- package/lib/adapters/po-box/adapter.ts +202 -0
- package/lib/adapters/registry.ts +79 -0
- package/lib/adapters/sha256-stream.ts +49 -0
- package/lib/adapters/source-id.ts +49 -0
- package/lib/adapters/street-line.ts +135 -0
- package/lib/adapters/wof/admin/json/adapter.ts +254 -0
- package/lib/adapters/wof/json-rows.ts +211 -0
- package/lib/adapters/wof/postalcode-json/adapter.ts +194 -0
- package/lib/adapters.ts +230 -0
- package/lib/au/adapters/gnaf/adapter.ts +144 -0
- package/lib/au/adapters/gnaf/assemble.ts +205 -0
- package/lib/be/adapters/brussels/adapter.ts +566 -0
- package/lib/be/adapters/vlaanderen/adapter.ts +670 -0
- package/lib/be/adapters/wallonie/adapter.ts +537 -0
- package/lib/be/tools/fetch/brussels.ts +239 -0
- package/lib/be/tools/fetch/wallonie.ts +274 -0
- package/lib/build/adapters.ts +110 -0
- package/lib/build/align.ts +364 -0
- package/lib/build/checkpoint.ts +131 -0
- package/lib/build/eligibility.ts +96 -0
- package/lib/build/heap.ts +53 -0
- package/lib/build/inputs.ts +81 -0
- package/lib/build/rows.ts +21 -0
- package/lib/build/types.ts +232 -0
- package/lib/build.ts +127 -315
- package/lib/cn/recipes/organizational-units.ts +178 -0
- package/lib/cz/adapters/cuzk/adapter.ts +317 -0
- package/lib/cz/recipes/pcfirst-preposition.ts +125 -0
- package/lib/cz/tools/fetch/cuzk.ts +699 -0
- package/lib/de/recipes/locale.ts +370 -0
- package/lib/directory.ts +31 -0
- package/lib/dk/adapters/inspire/adapter.ts +345 -0
- package/lib/dk/tools/fetch/inspire.ts +321 -0
- package/lib/ee/adapters/ads/adapter.ts +246 -0
- package/lib/ee/tools/fetch/ads.ts +270 -0
- package/lib/env.ts +6 -2
- package/lib/es/adapters/bizkaia/adapter.ts +388 -0
- package/lib/es/adapters/catastro/adapter.ts +343 -0
- package/lib/es/adapters/gipuzkoa/adapter.ts +263 -0
- package/lib/es/adapters/navarra/adapter.ts +289 -0
- package/lib/es/cadastre.ts +194 -0
- package/lib/es/tools/fetch/bizkaia.ts +748 -0
- package/lib/es/tools/fetch/catastro.ts +754 -0
- package/lib/es/tools/fetch/gipuzkoa.ts +336 -0
- package/lib/es/tools/fetch/navarra.ts +488 -0
- package/lib/fi/adapters/ryhti/adapter.ts +323 -0
- package/lib/fi/tools/fetch/ryhti.ts +476 -0
- package/lib/fingerprints.ts +154 -0
- package/lib/fr/adapters/annuaire-education/adapter.ts +598 -0
- package/lib/fr/adapters/ban/adapter.ts +187 -0
- package/lib/fr/adapters/finess/adapter.ts +618 -0
- package/lib/fr/adapters/finess/postal-lines.ts +157 -0
- package/lib/fr/adapters/finess/voie-type.ts +200 -0
- package/lib/fr/insee-country.ts +62 -0
- package/lib/fr/recipes/admin-split.ts +221 -0
- package/lib/fr/recipes/bare-street.ts +158 -0
- package/lib/fr/recipes/fragment.ts +251 -0
- package/lib/fr/recipes/lieudit.ts +310 -0
- package/lib/fr/recipes/order.ts +219 -0
- package/lib/fr/street-decompose.ts +67 -0
- package/lib/fr/tools/fetch/annuaire-education.ts +306 -0
- package/lib/fr/tools/fetch/ban.ts +298 -0
- package/lib/fr/tools/fetch/finess.ts +352 -0
- package/lib/gauntlet-inputs.ts +92 -0
- package/lib/index.ts +10 -4
- package/lib/inspire/address.ts +457 -0
- package/lib/inspire/archive.ts +44 -0
- package/lib/inspire/errors.ts +71 -0
- package/lib/inspire/stream.ts +262 -0
- package/lib/international/recipes/locale.ts +556 -0
- package/lib/it/adapters/anac/adapter.ts +522 -0
- package/lib/it/tools/fetch/anac.ts +394 -0
- package/lib/jp/adapters/wof-admin/adapter.ts +224 -0
- package/lib/jp/tools/fetch/houjin.ts +139 -0
- package/lib/kr/adapters/juso/label-rows.ts +239 -0
- package/lib/kr/adapters/localdata/align.ts +288 -0
- package/lib/kr/adapters/localdata/key-index.ts +177 -0
- package/lib/kr/adapters/localdata/permit-rows.ts +193 -0
- package/lib/kr/tools/fetch/juso.ts +170 -0
- package/lib/kr/tools/fetch/localdata.ts +205 -0
- package/lib/lu/adapters/bd-adresses/adapter.ts +240 -0
- package/lib/lu/tools/fetch/bd-adresses.ts +351 -0
- package/lib/lv/adapters/varis/adapter.ts +499 -0
- package/lib/lv/tools/fetch/varis.ts +214 -0
- package/lib/nl/adapters/kadaster/adapter.ts +386 -0
- package/lib/nl/recipes/postcode.ts +139 -0
- package/lib/nl/tools/fetch/kadaster.ts +298 -0
- package/lib/no/adapters/matrikkelen/adapter.ts +187 -0
- package/lib/no/recipes/fragment.ts +189 -0
- package/lib/no/recipes/street/led.ts +154 -0
- package/lib/no/recipes/street.ts +109 -0
- package/lib/no/tools/fetch/matrikkelen.ts +519 -0
- package/lib/parquet/duckdb.ts +144 -0
- package/lib/parquet/readers.ts +86 -0
- package/lib/parquet/schema.ts +214 -0
- package/lib/parquet/shuffle.ts +59 -0
- package/lib/parquet/span-sql.ts +54 -0
- package/lib/parquet/streams.ts +113 -0
- package/lib/parquet/writers.ts +451 -0
- package/lib/pl/adapters/emuia/adapter.ts +202 -0
- package/lib/pl/tools/fetch/emuia.ts +360 -0
- package/lib/recipes/anchor-absorption.ts +30 -19
- package/lib/recipes/bare/country.ts +87 -0
- package/lib/recipes/bare/postcode/eval.ts +99 -0
- package/lib/recipes/bare/postcode.ts +346 -0
- package/lib/recipes/boundary-stress.ts +36 -19
- package/lib/recipes/country-balanced.ts +67 -87
- package/lib/recipes/house-venue.ts +31 -13
- package/lib/recipes/intersection.ts +83 -61
- package/lib/recipes/po/box/cedex/au-nz.ts +82 -0
- package/lib/recipes/po/box/cedex/ca.ts +59 -0
- package/lib/recipes/po/box/cedex/fr.ts +77 -0
- package/lib/recipes/po/box/cedex/phrases.ts +109 -0
- package/lib/recipes/po/box/cedex/recipe.ts +215 -0
- package/lib/recipes/po/box/cedex/sources.ts +189 -0
- package/lib/recipes/po/box/cedex/types.ts +35 -0
- package/lib/recipes/po/box/cedex/us.ts +74 -0
- package/lib/recipes/po/box/cedex/vocabulary.ts +106 -0
- package/lib/recipes/po/box/cedex.ts +9 -0
- package/lib/recipes/po/box.ts +149 -0
- package/lib/recipes/scaffold.ts +258 -182
- package/lib/recipes/sources.ts +399 -0
- package/lib/recipes/street/affix.ts +707 -0
- package/lib/recipes/street/bare.ts +115 -0
- package/lib/recipes/street.ts +32 -8
- package/lib/recipes/sub/venue/context.ts +156 -0
- package/lib/recipes/sub/venue/render.ts +170 -0
- package/lib/recipes/sub/venue/sources.ts +588 -0
- package/lib/recipes/sub/venue.ts +801 -0
- package/lib/recipes/trailing-region.ts +70 -81
- package/lib/recipes/unit/sources.ts +44 -0
- package/lib/recipes/unit.ts +102 -90
- package/lib/recipes.ts +106 -0
- package/lib/registers.ts +278 -0
- package/lib/ro/adapters/retea-scolara/adapter.ts +264 -0
- package/lib/ro/tools/fetch/retea-scolara.ts +187 -0
- package/lib/runner.ts +220 -84
- package/lib/sg/recipes/register.ts +264 -0
- package/lib/sg/tools/fetch/acra.ts +174 -0
- package/lib/si/recipes/bare-village.ts +116 -0
- package/lib/sk/adapters/inspire/adapter.ts +395 -0
- package/lib/sk/tools/fetch/inspire.ts +402 -0
- package/lib/source-register/effective-manifest.ts +659 -0
- package/lib/source-register/register.ts +539 -0
- package/lib/source-register/training-manifest.ts +218 -0
- package/lib/source-register/types.ts +590 -0
- package/lib/source-register.ts +71 -0
- package/lib/south-asia/recipes/register.ts +233 -0
- package/lib/subvenue/harvest.ts +251 -0
- package/lib/subvenue/promotions.ts +293 -0
- package/lib/subvenue/surfaces.ts +94 -0
- package/lib/subvenue/table.ts +264 -0
- package/lib/surfaces/locale.ts +246 -0
- package/lib/synthesizers/anchor-absorption.ts +55 -91
- package/lib/synthesizers/boundary-stress.ts +49 -131
- package/lib/synthesizers/house-venue.ts +44 -102
- package/lib/synthesizers/intersection.ts +37 -26
- package/lib/synthesizers/no-street.ts +70 -119
- package/lib/synthesizers/po-box.ts +90 -105
- package/lib/synthesizers/street.ts +47 -35
- package/lib/synthesizers/utils.ts +65 -219
- package/lib/test-kit/corpus-recipe.ts +45 -28
- package/lib/test-kit.ts +116 -0
- package/lib/tools/align-canonical.ts +64 -0
- package/lib/tools/audit.ts +114 -118
- package/lib/tools/corpus-stats.ts +46 -32
- package/lib/tools/fetch/atom.ts +164 -0
- package/lib/tools/fetch/cordis.ts +318 -0
- package/lib/tools/fetch/download/manifest.ts +114 -0
- package/lib/tools/fetch/download/network.ts +250 -0
- package/lib/tools/fetch/download/retry.ts +174 -0
- package/lib/tools/fetch/download.ts +4 -471
- package/lib/tools/fetch/geonames/dump.ts +275 -0
- package/lib/tools/fetch/geonames/postal.ts +145 -0
- package/lib/tools/fetch/gleif.ts +360 -0
- package/lib/tools/fetch/header.ts +69 -0
- package/lib/tools/fetch/inspire-addresses.ts +495 -0
- package/lib/tools/fetch/openaddresses.ts +20 -109
- package/lib/tools/fetch/ourairports.ts +16 -49
- package/lib/tools/fetch/ppd.ts +10 -10
- package/lib/tools/fetch/vlaanderen-ad.ts +435 -0
- package/lib/tools/fetch/wfs-harvest.ts +943 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +43 -143
- package/lib/tools/fetch/zip-archive.ts +100 -0
- package/lib/tools/fetch.ts +143 -0
- package/lib/tools/golden/expand.ts +605 -0
- package/lib/tools/golden/promote.ts +349 -0
- package/lib/tools/golden/relabel-street/directory.ts +367 -0
- package/lib/tools/golden/relabel-street/row.ts +283 -0
- package/lib/tools/golden/relabel-street.ts +9 -0
- package/lib/tools/ingest-csv.ts +45 -50
- package/lib/tools/jsonl-to-parquet.ts +59 -98
- package/lib/tools/lint/recipe-output/vocab.ts +366 -0
- package/lib/tools/lint/recipe-output.ts +482 -0
- package/lib/tools/migrate/overlay-parquet.ts +173 -0
- package/lib/tools/migrate/recipe-output.ts +153 -0
- package/lib/tools/migrate/source-names.ts +161 -0
- package/lib/tools/overlay/kryptonite.ts +144 -0
- package/lib/tools/overlay/manifest.ts +407 -0
- package/lib/tools/overlay/merge-source.ts +138 -0
- package/lib/tools/overlay/split-slice.ts +144 -0
- package/lib/tools/overlay/translit.ts +234 -0
- package/lib/tools/overture-subvenue.ts +18 -91
- package/lib/tools/postcode-triples.ts +362 -167
- package/lib/tools/source-register/build.ts +819 -0
- package/lib/tools/sub/venue/head-nouns.ts +208 -0
- package/lib/tools/sub/venue/lexicon.ts +394 -0
- package/lib/tools/sub/venue/wikidata.ts +88 -0
- package/lib/tools.ts +31 -0
- package/lib/tw/tools/fetch/gcis.ts +181 -0
- package/lib/types.ts +304 -101
- package/lib/us/adapters/fcc-bdc/adapter.ts +158 -0
- package/lib/us/adapters/state/hi-schools/adapter.ts +171 -0
- package/lib/us/adapters/state/hi-schools/workbook.ts +40 -0
- package/lib/us/adapters/state/ia-contractors/adapter.ts +148 -0
- package/lib/us/adapters/state/ny-notaries/adapter.ts +132 -0
- package/lib/us/adapters/state/tx-notaries/adapter.ts +155 -0
- package/lib/us/adapters/tiger/adapter.ts +225 -0
- package/lib/us/adapters/tiger/street-decompose.ts +73 -0
- package/lib/us/adapters/usgov/hrsa-fqhc/adapter.ts +171 -0
- package/lib/us/adapters/usgov/imls-pls/adapter.ts +140 -0
- package/lib/us/adapters/usgov/irs-bmf/adapter.ts +154 -0
- package/lib/us/adapters/usgov/nad/adapter.ts +263 -0
- package/lib/us/adapters/usgov/nppes/adapter.ts +180 -0
- package/lib/us/adapters/usgov/samhsa-treatment-locator/adapter.ts +195 -0
- package/lib/us/fips-state.ts +122 -0
- package/lib/us/tools/fetch/hrsa.ts +58 -0
- package/lib/us/tools/fetch/imls-pls.ts +131 -0
- package/lib/us/tools/fetch/nad.ts +359 -0
- package/lib/us/tools/fetch/nppes.ts +153 -0
- package/lib/us/tools/fetch/state/hi-schools.ts +167 -0
- package/lib/us/tools/fetch/state/sources.ts +146 -0
- package/lib/us/tools/fetch/tiger-full.ts +256 -0
- package/lib/utils/align.ts +43 -53
- package/lib/utils/cooccurrence-stats.ts +101 -0
- package/lib/utils/golden.ts +39 -50
- package/lib/utils/license.ts +238 -26
- package/lib/utils/split.ts +205 -88
- package/lib/utils/tokenize.ts +22 -34
- package/lib/utils/wof-json.ts +134 -87
- package/lib/utils.ts +13 -0
- package/lib/ve/recipes/reviewed-postcode-tail.ts +217 -0
- package/out/adapters/cordis/adapter.d.ts +324 -0
- package/out/adapters/cordis/adapter.d.ts.map +1 -0
- package/out/adapters/cordis/adapter.js +616 -0
- package/out/adapters/cordis/adapter.js.map +1 -0
- package/out/adapters/dedup-key.d.ts +30 -0
- package/out/adapters/dedup-key.d.ts.map +1 -0
- package/out/adapters/dedup-key.js +35 -0
- package/out/adapters/dedup-key.js.map +1 -0
- package/out/adapters/errors.d.ts +17 -0
- package/out/adapters/errors.d.ts.map +1 -0
- package/out/adapters/errors.js +20 -0
- package/out/adapters/errors.js.map +1 -0
- package/out/adapters/geonames/adapter.d.ts +26 -28
- package/out/adapters/geonames/adapter.d.ts.map +1 -1
- package/out/adapters/geonames/adapter.js +40 -50
- package/out/adapters/geonames/adapter.js.map +1 -1
- package/out/adapters/geonames/postal/adapter.d.ts +41 -0
- package/out/adapters/geonames/postal/adapter.d.ts.map +1 -0
- package/out/adapters/geonames/postal/adapter.js +102 -0
- package/out/adapters/geonames/postal/adapter.js.map +1 -0
- package/out/adapters/gleif/adapter.d.ts +293 -0
- package/out/adapters/gleif/adapter.d.ts.map +1 -0
- package/out/adapters/gleif/adapter.js +684 -0
- package/out/adapters/gleif/adapter.js.map +1 -0
- package/out/adapters/libpostal-dictionary.d.ts +22 -0
- package/out/adapters/libpostal-dictionary.d.ts.map +1 -0
- package/out/adapters/libpostal-dictionary.js +36 -0
- package/out/adapters/libpostal-dictionary.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts +28 -43
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -1
- package/out/adapters/openaddresses/adapter.js +37 -51
- package/out/adapters/openaddresses/adapter.js.map +1 -1
- package/out/adapters/osm/adapter.d.ts +101 -0
- package/out/adapters/osm/adapter.d.ts.map +1 -0
- package/out/adapters/osm/adapter.js +260 -0
- package/out/adapters/osm/adapter.js.map +1 -0
- package/out/adapters/overture/adapter.d.ts +14 -30
- package/out/adapters/overture/adapter.d.ts.map +1 -1
- package/out/adapters/overture/adapter.js +57 -41
- package/out/adapters/overture/adapter.js.map +1 -1
- package/out/adapters/po-box/adapter.d.ts +63 -0
- package/out/adapters/po-box/adapter.d.ts.map +1 -0
- package/out/adapters/po-box/adapter.js +139 -0
- package/out/adapters/po-box/adapter.js.map +1 -0
- package/out/adapters/registry.d.ts +55 -0
- package/out/adapters/registry.d.ts.map +1 -0
- package/out/adapters/registry.js +43 -0
- package/out/adapters/registry.js.map +1 -0
- package/out/adapters/sha256-stream.d.ts +26 -0
- package/out/adapters/sha256-stream.d.ts.map +1 -0
- package/out/adapters/sha256-stream.js +34 -0
- package/out/adapters/sha256-stream.js.map +1 -0
- package/out/adapters/source-id.d.ts +33 -0
- package/out/adapters/source-id.d.ts.map +1 -0
- package/out/adapters/source-id.js +42 -0
- package/out/adapters/source-id.js.map +1 -0
- package/out/adapters/street-line.d.ts +102 -0
- package/out/adapters/street-line.d.ts.map +1 -0
- package/out/adapters/street-line.js +117 -0
- package/out/adapters/street-line.js.map +1 -0
- package/out/adapters/wof/admin/json/adapter.d.ts +88 -0
- package/out/adapters/wof/admin/json/adapter.d.ts.map +1 -0
- package/out/adapters/wof/admin/json/adapter.js +220 -0
- package/out/adapters/wof/admin/json/adapter.js.map +1 -0
- package/out/adapters/wof/json-rows.d.ts +89 -0
- package/out/adapters/wof/json-rows.d.ts.map +1 -0
- package/out/adapters/wof/json-rows.js +135 -0
- package/out/adapters/wof/json-rows.js.map +1 -0
- package/out/adapters/wof/postalcode-json/adapter.d.ts +49 -0
- package/out/adapters/wof/postalcode-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof/postalcode-json/adapter.js +165 -0
- package/out/adapters/wof/postalcode-json/adapter.js.map +1 -0
- package/out/adapters.d.ts +75 -0
- package/out/adapters.d.ts.map +1 -0
- package/out/adapters.js +167 -0
- package/out/adapters.js.map +1 -0
- package/out/au/adapters/gnaf/adapter.d.ts +37 -0
- package/out/au/adapters/gnaf/adapter.d.ts.map +1 -0
- package/out/au/adapters/gnaf/adapter.js +119 -0
- package/out/au/adapters/gnaf/adapter.js.map +1 -0
- package/out/au/adapters/gnaf/assemble.d.ts +54 -0
- package/out/au/adapters/gnaf/assemble.d.ts.map +1 -0
- package/out/au/adapters/gnaf/assemble.js +134 -0
- package/out/au/adapters/gnaf/assemble.js.map +1 -0
- package/out/be/adapters/brussels/adapter.d.ts +212 -0
- package/out/be/adapters/brussels/adapter.d.ts.map +1 -0
- package/out/be/adapters/brussels/adapter.js +435 -0
- package/out/be/adapters/brussels/adapter.js.map +1 -0
- package/out/be/adapters/vlaanderen/adapter.d.ts +233 -0
- package/out/be/adapters/vlaanderen/adapter.d.ts.map +1 -0
- package/out/be/adapters/vlaanderen/adapter.js +416 -0
- package/out/be/adapters/vlaanderen/adapter.js.map +1 -0
- package/out/be/adapters/wallonie/adapter.d.ts +196 -0
- package/out/be/adapters/wallonie/adapter.d.ts.map +1 -0
- package/out/be/adapters/wallonie/adapter.js +437 -0
- package/out/be/adapters/wallonie/adapter.js.map +1 -0
- package/out/be/tools/fetch/brussels.d.ts +119 -0
- package/out/be/tools/fetch/brussels.d.ts.map +1 -0
- package/out/be/tools/fetch/brussels.js +146 -0
- package/out/be/tools/fetch/brussels.js.map +1 -0
- package/out/be/tools/fetch/wallonie.d.ts +119 -0
- package/out/be/tools/fetch/wallonie.d.ts.map +1 -0
- package/out/be/tools/fetch/wallonie.js +167 -0
- package/out/be/tools/fetch/wallonie.js.map +1 -0
- package/out/build/adapters.d.ts +33 -0
- package/out/build/adapters.d.ts.map +1 -0
- package/out/build/adapters.js +68 -0
- package/out/build/adapters.js.map +1 -0
- package/out/build/align.d.ts +73 -0
- package/out/build/align.d.ts.map +1 -0
- package/out/build/align.js +226 -0
- package/out/build/align.js.map +1 -0
- package/out/build/checkpoint.d.ts +94 -0
- package/out/build/checkpoint.d.ts.map +1 -0
- package/out/build/checkpoint.js +59 -0
- package/out/build/checkpoint.js.map +1 -0
- package/out/build/eligibility.d.ts +47 -0
- package/out/build/eligibility.d.ts.map +1 -0
- package/out/build/eligibility.js +80 -0
- package/out/build/eligibility.js.map +1 -0
- package/out/build/heap.d.ts +28 -0
- package/out/build/heap.d.ts.map +1 -0
- package/out/build/heap.js +47 -0
- package/out/build/heap.js.map +1 -0
- package/out/build/inputs.d.ts +52 -0
- package/out/build/inputs.d.ts.map +1 -0
- package/out/build/inputs.js +49 -0
- package/out/build/inputs.js.map +1 -0
- package/out/build/rows.d.ts +16 -0
- package/out/build/rows.d.ts.map +1 -0
- package/out/build/rows.js +19 -0
- package/out/build/rows.js.map +1 -0
- package/out/build/types.d.ts +220 -0
- package/out/build/types.d.ts.map +1 -0
- package/out/build/types.js +34 -0
- package/out/build/types.js.map +1 -0
- package/out/build.d.ts +6 -121
- package/out/build.d.ts.map +1 -1
- package/out/build.js +112 -207
- package/out/build.js.map +1 -1
- package/out/cn/recipes/organizational-units.d.ts +19 -0
- package/out/cn/recipes/organizational-units.d.ts.map +1 -0
- package/out/cn/recipes/organizational-units.js +138 -0
- package/out/cn/recipes/organizational-units.js.map +1 -0
- package/out/cz/adapters/cuzk/adapter.d.ts +52 -0
- package/out/cz/adapters/cuzk/adapter.d.ts.map +1 -0
- package/out/cz/adapters/cuzk/adapter.js +266 -0
- package/out/cz/adapters/cuzk/adapter.js.map +1 -0
- package/out/cz/recipes/pcfirst-preposition.d.ts +18 -0
- package/out/cz/recipes/pcfirst-preposition.d.ts.map +1 -0
- package/out/cz/recipes/pcfirst-preposition.js +110 -0
- package/out/cz/recipes/pcfirst-preposition.js.map +1 -0
- package/out/cz/tools/fetch/cuzk.d.ts +272 -0
- package/out/cz/tools/fetch/cuzk.d.ts.map +1 -0
- package/out/cz/tools/fetch/cuzk.js +446 -0
- package/out/cz/tools/fetch/cuzk.js.map +1 -0
- package/out/de/recipes/locale.d.ts +42 -0
- package/out/de/recipes/locale.d.ts.map +1 -0
- package/out/de/recipes/locale.js +299 -0
- package/out/de/recipes/locale.js.map +1 -0
- package/out/directory.d.ts +20 -0
- package/out/directory.d.ts.map +1 -0
- package/out/directory.js +27 -0
- package/out/directory.js.map +1 -0
- package/out/dk/adapters/inspire/adapter.d.ts +154 -0
- package/out/dk/adapters/inspire/adapter.d.ts.map +1 -0
- package/out/dk/adapters/inspire/adapter.js +258 -0
- package/out/dk/adapters/inspire/adapter.js.map +1 -0
- package/out/dk/tools/fetch/inspire.d.ts +100 -0
- package/out/dk/tools/fetch/inspire.d.ts.map +1 -0
- package/out/dk/tools/fetch/inspire.js +230 -0
- package/out/dk/tools/fetch/inspire.js.map +1 -0
- package/out/ee/adapters/ads/adapter.d.ts +109 -0
- package/out/ee/adapters/ads/adapter.d.ts.map +1 -0
- package/out/ee/adapters/ads/adapter.js +191 -0
- package/out/ee/adapters/ads/adapter.js.map +1 -0
- package/out/ee/tools/fetch/ads.d.ts +123 -0
- package/out/ee/tools/fetch/ads.d.ts.map +1 -0
- package/out/ee/tools/fetch/ads.js +195 -0
- package/out/ee/tools/fetch/ads.js.map +1 -0
- package/out/env.d.ts +7 -3
- package/out/env.d.ts.map +1 -1
- package/out/env.js +6 -2
- package/out/env.js.map +1 -1
- package/out/es/adapters/bizkaia/adapter.d.ts +143 -0
- package/out/es/adapters/bizkaia/adapter.d.ts.map +1 -0
- package/out/es/adapters/bizkaia/adapter.js +332 -0
- package/out/es/adapters/bizkaia/adapter.js.map +1 -0
- package/out/es/adapters/catastro/adapter.d.ts +104 -0
- package/out/es/adapters/catastro/adapter.d.ts.map +1 -0
- package/out/es/adapters/catastro/adapter.js +288 -0
- package/out/es/adapters/catastro/adapter.js.map +1 -0
- package/out/es/adapters/gipuzkoa/adapter.d.ts +91 -0
- package/out/es/adapters/gipuzkoa/adapter.d.ts.map +1 -0
- package/out/es/adapters/gipuzkoa/adapter.js +225 -0
- package/out/es/adapters/gipuzkoa/adapter.js.map +1 -0
- package/out/es/adapters/navarra/adapter.d.ts +105 -0
- package/out/es/adapters/navarra/adapter.d.ts.map +1 -0
- package/out/es/adapters/navarra/adapter.js +241 -0
- package/out/es/adapters/navarra/adapter.js.map +1 -0
- package/out/es/cadastre.d.ts +109 -0
- package/out/es/cadastre.d.ts.map +1 -0
- package/out/es/cadastre.js +130 -0
- package/out/es/cadastre.js.map +1 -0
- package/out/es/tools/fetch/bizkaia.d.ts +278 -0
- package/out/es/tools/fetch/bizkaia.d.ts.map +1 -0
- package/out/es/tools/fetch/bizkaia.js +477 -0
- package/out/es/tools/fetch/bizkaia.js.map +1 -0
- package/out/es/tools/fetch/catastro.d.ts +272 -0
- package/out/es/tools/fetch/catastro.d.ts.map +1 -0
- package/out/es/tools/fetch/catastro.js +486 -0
- package/out/es/tools/fetch/catastro.js.map +1 -0
- package/out/es/tools/fetch/gipuzkoa.d.ts +162 -0
- package/out/es/tools/fetch/gipuzkoa.d.ts.map +1 -0
- package/out/es/tools/fetch/gipuzkoa.js +209 -0
- package/out/es/tools/fetch/gipuzkoa.js.map +1 -0
- package/out/es/tools/fetch/navarra.d.ts +189 -0
- package/out/es/tools/fetch/navarra.d.ts.map +1 -0
- package/out/es/tools/fetch/navarra.js +316 -0
- package/out/es/tools/fetch/navarra.js.map +1 -0
- package/out/fi/adapters/ryhti/adapter.d.ts +115 -0
- package/out/fi/adapters/ryhti/adapter.d.ts.map +1 -0
- package/out/fi/adapters/ryhti/adapter.js +244 -0
- package/out/fi/adapters/ryhti/adapter.js.map +1 -0
- package/out/fi/tools/fetch/ryhti.d.ts +206 -0
- package/out/fi/tools/fetch/ryhti.d.ts.map +1 -0
- package/out/fi/tools/fetch/ryhti.js +327 -0
- package/out/fi/tools/fetch/ryhti.js.map +1 -0
- package/out/fingerprints.d.ts +68 -0
- package/out/fingerprints.d.ts.map +1 -0
- package/out/fingerprints.js +130 -0
- package/out/fingerprints.js.map +1 -0
- package/out/fr/adapters/annuaire-education/adapter.d.ts +236 -0
- package/out/fr/adapters/annuaire-education/adapter.d.ts.map +1 -0
- package/out/fr/adapters/annuaire-education/adapter.js +475 -0
- package/out/fr/adapters/annuaire-education/adapter.js.map +1 -0
- package/out/fr/adapters/ban/adapter.d.ts +38 -0
- package/out/fr/adapters/ban/adapter.d.ts.map +1 -0
- package/out/fr/adapters/ban/adapter.js +134 -0
- package/out/fr/adapters/ban/adapter.js.map +1 -0
- package/out/fr/adapters/finess/adapter.d.ts +276 -0
- package/out/fr/adapters/finess/adapter.d.ts.map +1 -0
- package/out/fr/adapters/finess/adapter.js +519 -0
- package/out/fr/adapters/finess/adapter.js.map +1 -0
- package/out/fr/adapters/finess/postal-lines.d.ts +61 -0
- package/out/fr/adapters/finess/postal-lines.d.ts.map +1 -0
- package/out/fr/adapters/finess/postal-lines.js +114 -0
- package/out/fr/adapters/finess/postal-lines.js.map +1 -0
- package/out/fr/adapters/finess/voie-type.d.ts +77 -0
- package/out/fr/adapters/finess/voie-type.d.ts.map +1 -0
- package/out/fr/adapters/finess/voie-type.js +172 -0
- package/out/fr/adapters/finess/voie-type.js.map +1 -0
- package/out/fr/insee-country.d.ts +45 -0
- package/out/fr/insee-country.d.ts.map +1 -0
- package/out/fr/insee-country.js +60 -0
- package/out/fr/insee-country.js.map +1 -0
- package/out/fr/recipes/admin-split.d.ts +15 -0
- package/out/fr/recipes/admin-split.d.ts.map +1 -0
- package/out/fr/recipes/admin-split.js +170 -0
- package/out/fr/recipes/admin-split.js.map +1 -0
- package/out/fr/recipes/bare-street.d.ts +13 -0
- package/out/fr/recipes/bare-street.d.ts.map +1 -0
- package/out/fr/recipes/bare-street.js +129 -0
- package/out/fr/recipes/bare-street.js.map +1 -0
- package/out/fr/recipes/fragment.d.ts +18 -0
- package/out/fr/recipes/fragment.d.ts.map +1 -0
- package/out/fr/recipes/fragment.js +197 -0
- package/out/fr/recipes/fragment.js.map +1 -0
- package/out/fr/recipes/lieudit.d.ts +30 -0
- package/out/fr/recipes/lieudit.d.ts.map +1 -0
- package/out/fr/recipes/lieudit.js +231 -0
- package/out/fr/recipes/lieudit.js.map +1 -0
- package/out/fr/recipes/order.d.ts +15 -0
- package/out/fr/recipes/order.d.ts.map +1 -0
- package/out/fr/recipes/order.js +171 -0
- package/out/fr/recipes/order.js.map +1 -0
- package/out/fr/street-decompose.d.ts +29 -0
- package/out/fr/street-decompose.d.ts.map +1 -0
- package/out/fr/street-decompose.js +52 -0
- package/out/fr/street-decompose.js.map +1 -0
- package/out/fr/tools/fetch/annuaire-education.d.ts +130 -0
- package/out/fr/tools/fetch/annuaire-education.d.ts.map +1 -0
- package/out/fr/tools/fetch/annuaire-education.js +196 -0
- package/out/fr/tools/fetch/annuaire-education.js.map +1 -0
- package/out/fr/tools/fetch/ban.d.ts +33 -0
- package/out/fr/tools/fetch/ban.d.ts.map +1 -0
- package/out/fr/tools/fetch/ban.js +248 -0
- package/out/fr/tools/fetch/ban.js.map +1 -0
- package/out/fr/tools/fetch/finess.d.ts +145 -0
- package/out/fr/tools/fetch/finess.d.ts.map +1 -0
- package/out/fr/tools/fetch/finess.js +228 -0
- package/out/fr/tools/fetch/finess.js.map +1 -0
- package/out/gauntlet-inputs.d.ts +42 -0
- package/out/gauntlet-inputs.d.ts.map +1 -0
- package/out/gauntlet-inputs.js +78 -0
- package/out/gauntlet-inputs.js.map +1 -0
- package/out/index.d.ts +10 -4
- package/out/index.d.ts.map +1 -1
- package/out/index.js +10 -4
- package/out/index.js.map +1 -1
- package/out/inspire/address.d.ts +251 -0
- package/out/inspire/address.d.ts.map +1 -0
- package/out/inspire/address.js +384 -0
- package/out/inspire/address.js.map +1 -0
- package/out/inspire/archive.d.ts +36 -0
- package/out/inspire/archive.d.ts.map +1 -0
- package/out/inspire/archive.js +42 -0
- package/out/inspire/archive.js.map +1 -0
- package/out/inspire/errors.d.ts +55 -0
- package/out/inspire/errors.d.ts.map +1 -0
- package/out/inspire/errors.js +64 -0
- package/out/inspire/errors.js.map +1 -0
- package/out/inspire/stream.d.ts +137 -0
- package/out/inspire/stream.d.ts.map +1 -0
- package/out/inspire/stream.js +125 -0
- package/out/inspire/stream.js.map +1 -0
- package/out/international/recipes/locale.d.ts +90 -0
- package/out/international/recipes/locale.d.ts.map +1 -0
- package/out/international/recipes/locale.js +419 -0
- package/out/international/recipes/locale.js.map +1 -0
- package/out/it/adapters/anac/adapter.d.ts +267 -0
- package/out/it/adapters/anac/adapter.d.ts.map +1 -0
- package/out/it/adapters/anac/adapter.js +429 -0
- package/out/it/adapters/anac/adapter.js.map +1 -0
- package/out/it/tools/fetch/anac.d.ts +174 -0
- package/out/it/tools/fetch/anac.d.ts.map +1 -0
- package/out/it/tools/fetch/anac.js +272 -0
- package/out/it/tools/fetch/anac.js.map +1 -0
- package/out/jp/adapters/wof-admin/adapter.d.ts +68 -0
- package/out/jp/adapters/wof-admin/adapter.d.ts.map +1 -0
- package/out/jp/adapters/wof-admin/adapter.js +172 -0
- package/out/jp/adapters/wof-admin/adapter.js.map +1 -0
- package/out/jp/tools/fetch/houjin.d.ts +27 -0
- package/out/jp/tools/fetch/houjin.d.ts.map +1 -0
- package/out/jp/tools/fetch/houjin.js +106 -0
- package/out/jp/tools/fetch/houjin.js.map +1 -0
- package/out/kr/adapters/juso/label-rows.d.ts +62 -0
- package/out/kr/adapters/juso/label-rows.d.ts.map +1 -0
- package/out/kr/adapters/juso/label-rows.js +172 -0
- package/out/kr/adapters/juso/label-rows.js.map +1 -0
- package/out/kr/adapters/localdata/align.d.ts +31 -0
- package/out/kr/adapters/localdata/align.d.ts.map +1 -0
- package/out/kr/adapters/localdata/align.js +212 -0
- package/out/kr/adapters/localdata/align.js.map +1 -0
- package/out/kr/adapters/localdata/key-index.d.ts +62 -0
- package/out/kr/adapters/localdata/key-index.d.ts.map +1 -0
- package/out/kr/adapters/localdata/key-index.js +127 -0
- package/out/kr/adapters/localdata/key-index.js.map +1 -0
- package/out/kr/adapters/localdata/permit-rows.d.ts +73 -0
- package/out/kr/adapters/localdata/permit-rows.d.ts.map +1 -0
- package/out/kr/adapters/localdata/permit-rows.js +136 -0
- package/out/kr/adapters/localdata/permit-rows.js.map +1 -0
- package/out/kr/tools/fetch/juso.d.ts +33 -0
- package/out/kr/tools/fetch/juso.d.ts.map +1 -0
- package/out/kr/tools/fetch/juso.js +121 -0
- package/out/kr/tools/fetch/juso.js.map +1 -0
- package/out/kr/tools/fetch/localdata.d.ts +37 -0
- package/out/kr/tools/fetch/localdata.d.ts.map +1 -0
- package/out/kr/tools/fetch/localdata.js +147 -0
- package/out/kr/tools/fetch/localdata.js.map +1 -0
- package/out/lu/adapters/bd-adresses/adapter.d.ts +109 -0
- package/out/lu/adapters/bd-adresses/adapter.d.ts.map +1 -0
- package/out/lu/adapters/bd-adresses/adapter.js +196 -0
- package/out/lu/adapters/bd-adresses/adapter.js.map +1 -0
- package/out/lu/tools/fetch/bd-adresses.d.ts +163 -0
- package/out/lu/tools/fetch/bd-adresses.d.ts.map +1 -0
- package/out/lu/tools/fetch/bd-adresses.js +223 -0
- package/out/lu/tools/fetch/bd-adresses.js.map +1 -0
- package/out/lv/adapters/varis/adapter.d.ts +283 -0
- package/out/lv/adapters/varis/adapter.d.ts.map +1 -0
- package/out/lv/adapters/varis/adapter.js +404 -0
- package/out/lv/adapters/varis/adapter.js.map +1 -0
- package/out/lv/tools/fetch/varis.d.ts +80 -0
- package/out/lv/tools/fetch/varis.d.ts.map +1 -0
- package/out/lv/tools/fetch/varis.js +133 -0
- package/out/lv/tools/fetch/varis.js.map +1 -0
- package/out/nl/adapters/kadaster/adapter.d.ts +125 -0
- package/out/nl/adapters/kadaster/adapter.d.ts.map +1 -0
- package/out/nl/adapters/kadaster/adapter.js +310 -0
- package/out/nl/adapters/kadaster/adapter.js.map +1 -0
- package/out/nl/recipes/postcode.d.ts +24 -0
- package/out/nl/recipes/postcode.d.ts.map +1 -0
- package/out/nl/recipes/postcode.js +121 -0
- package/out/nl/recipes/postcode.js.map +1 -0
- package/out/nl/tools/fetch/kadaster.d.ts +155 -0
- package/out/nl/tools/fetch/kadaster.d.ts.map +1 -0
- package/out/nl/tools/fetch/kadaster.js +179 -0
- package/out/nl/tools/fetch/kadaster.js.map +1 -0
- package/out/no/adapters/matrikkelen/adapter.d.ts +44 -0
- package/out/no/adapters/matrikkelen/adapter.d.ts.map +1 -0
- package/out/no/adapters/matrikkelen/adapter.js +143 -0
- package/out/no/adapters/matrikkelen/adapter.js.map +1 -0
- package/out/no/recipes/fragment.d.ts +11 -0
- package/out/no/recipes/fragment.d.ts.map +1 -0
- package/out/no/recipes/fragment.js +149 -0
- package/out/no/recipes/fragment.js.map +1 -0
- package/out/no/recipes/street/led.d.ts +21 -0
- package/out/no/recipes/street/led.d.ts.map +1 -0
- package/out/no/recipes/street/led.js +124 -0
- package/out/no/recipes/street/led.js.map +1 -0
- package/out/no/recipes/street.d.ts +19 -0
- package/out/no/recipes/street.d.ts.map +1 -0
- package/out/no/recipes/street.js +88 -0
- package/out/no/recipes/street.js.map +1 -0
- package/out/no/tools/fetch/matrikkelen.d.ts +251 -0
- package/out/no/tools/fetch/matrikkelen.d.ts.map +1 -0
- package/out/no/tools/fetch/matrikkelen.js +345 -0
- package/out/no/tools/fetch/matrikkelen.js.map +1 -0
- package/out/parquet/duckdb.d.ts +100 -0
- package/out/parquet/duckdb.d.ts.map +1 -0
- package/out/parquet/duckdb.js +92 -0
- package/out/parquet/duckdb.js.map +1 -0
- package/out/parquet/readers.d.ts +44 -0
- package/out/parquet/readers.d.ts.map +1 -0
- package/out/parquet/readers.js +69 -0
- package/out/parquet/readers.js.map +1 -0
- package/out/parquet/schema.d.ts +95 -0
- package/out/parquet/schema.d.ts.map +1 -0
- package/out/parquet/schema.js +157 -0
- package/out/parquet/schema.js.map +1 -0
- package/out/parquet/shuffle.d.ts +25 -0
- package/out/parquet/shuffle.d.ts.map +1 -0
- package/out/parquet/shuffle.js +44 -0
- package/out/parquet/shuffle.js.map +1 -0
- package/out/parquet/span-sql.d.ts +49 -0
- package/out/parquet/span-sql.d.ts.map +1 -0
- package/out/parquet/span-sql.js +53 -0
- package/out/parquet/span-sql.js.map +1 -0
- package/out/parquet/streams.d.ts +47 -0
- package/out/parquet/streams.d.ts.map +1 -0
- package/out/parquet/streams.js +78 -0
- package/out/parquet/streams.js.map +1 -0
- package/out/parquet/writers.d.ts +124 -0
- package/out/parquet/writers.d.ts.map +1 -0
- package/out/parquet/writers.js +251 -0
- package/out/parquet/writers.js.map +1 -0
- package/out/pl/adapters/emuia/adapter.d.ts +81 -0
- package/out/pl/adapters/emuia/adapter.d.ts.map +1 -0
- package/out/pl/adapters/emuia/adapter.js +178 -0
- package/out/pl/adapters/emuia/adapter.js.map +1 -0
- package/out/pl/tools/fetch/emuia.d.ts +165 -0
- package/out/pl/tools/fetch/emuia.d.ts.map +1 -0
- package/out/pl/tools/fetch/emuia.js +260 -0
- package/out/pl/tools/fetch/emuia.js.map +1 -0
- package/out/recipes/anchor-absorption.d.ts +9 -9
- package/out/recipes/anchor-absorption.d.ts.map +1 -1
- package/out/recipes/anchor-absorption.js +29 -19
- package/out/recipes/anchor-absorption.js.map +1 -1
- package/out/recipes/bare/country.d.ts +7 -0
- package/out/recipes/bare/country.d.ts.map +1 -0
- package/out/recipes/bare/country.js +77 -0
- package/out/recipes/bare/country.js.map +1 -0
- package/out/recipes/bare/postcode/eval.d.ts +29 -0
- package/out/recipes/bare/postcode/eval.d.ts.map +1 -0
- package/out/recipes/bare/postcode/eval.js +85 -0
- package/out/recipes/bare/postcode/eval.js.map +1 -0
- package/out/recipes/bare/postcode.d.ts +41 -0
- package/out/recipes/bare/postcode.d.ts.map +1 -0
- package/out/recipes/bare/postcode.js +279 -0
- package/out/recipes/bare/postcode.js.map +1 -0
- package/out/recipes/boundary-stress.d.ts +8 -8
- package/out/recipes/boundary-stress.d.ts.map +1 -1
- package/out/recipes/boundary-stress.js +36 -19
- package/out/recipes/boundary-stress.js.map +1 -1
- package/out/recipes/country-balanced.d.ts +3 -21
- package/out/recipes/country-balanced.d.ts.map +1 -1
- package/out/recipes/country-balanced.js +58 -76
- package/out/recipes/country-balanced.js.map +1 -1
- package/out/recipes/house-venue.d.ts +8 -6
- package/out/recipes/house-venue.d.ts.map +1 -1
- package/out/recipes/house-venue.js +29 -13
- package/out/recipes/house-venue.js.map +1 -1
- package/out/recipes/intersection.d.ts +20 -20
- package/out/recipes/intersection.d.ts.map +1 -1
- package/out/recipes/intersection.js +65 -53
- package/out/recipes/intersection.js.map +1 -1
- package/out/recipes/po/box/cedex/au-nz.d.ts +7 -0
- package/out/recipes/po/box/cedex/au-nz.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/au-nz.js +56 -0
- package/out/recipes/po/box/cedex/au-nz.js.map +1 -0
- package/out/recipes/po/box/cedex/ca.d.ts +7 -0
- package/out/recipes/po/box/cedex/ca.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/ca.js +38 -0
- package/out/recipes/po/box/cedex/ca.js.map +1 -0
- package/out/recipes/po/box/cedex/fr.d.ts +7 -0
- package/out/recipes/po/box/cedex/fr.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/fr.js +57 -0
- package/out/recipes/po/box/cedex/fr.js.map +1 -0
- package/out/recipes/po/box/cedex/phrases.d.ts +8 -0
- package/out/recipes/po/box/cedex/phrases.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/phrases.js +77 -0
- package/out/recipes/po/box/cedex/phrases.js.map +1 -0
- package/out/recipes/po/box/cedex/recipe.d.ts +9 -0
- package/out/recipes/po/box/cedex/recipe.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/recipe.js +163 -0
- package/out/recipes/po/box/cedex/recipe.js.map +1 -0
- package/out/recipes/po/box/cedex/sources.d.ts +86 -0
- package/out/recipes/po/box/cedex/sources.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/sources.js +143 -0
- package/out/recipes/po/box/cedex/sources.js.map +1 -0
- package/out/recipes/po/box/cedex/types.d.ts +31 -0
- package/out/recipes/po/box/cedex/types.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/types.js +5 -0
- package/out/recipes/po/box/cedex/types.js.map +1 -0
- package/out/recipes/po/box/cedex/us.d.ts +7 -0
- package/out/recipes/po/box/cedex/us.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/us.js +54 -0
- package/out/recipes/po/box/cedex/us.js.map +1 -0
- package/out/recipes/po/box/cedex/vocabulary.d.ts +68 -0
- package/out/recipes/po/box/cedex/vocabulary.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/vocabulary.js +90 -0
- package/out/recipes/po/box/cedex/vocabulary.js.map +1 -0
- package/out/recipes/po/box/cedex.d.ts +9 -0
- package/out/recipes/po/box/cedex.d.ts.map +1 -0
- package/out/recipes/po/box/cedex.js +9 -0
- package/out/recipes/po/box/cedex.js.map +1 -0
- package/out/recipes/po/box.d.ts +18 -0
- package/out/recipes/po/box.d.ts.map +1 -0
- package/out/recipes/po/box.js +123 -0
- package/out/recipes/po/box.js.map +1 -0
- package/out/recipes/scaffold.d.ts +214 -121
- package/out/recipes/scaffold.d.ts.map +1 -1
- package/out/recipes/scaffold.js +78 -88
- package/out/recipes/scaffold.js.map +1 -1
- package/out/recipes/sources.d.ts +178 -0
- package/out/recipes/sources.d.ts.map +1 -0
- package/out/recipes/sources.js +348 -0
- package/out/recipes/sources.js.map +1 -0
- package/out/recipes/street/affix.d.ts +59 -0
- package/out/recipes/street/affix.d.ts.map +1 -0
- package/out/recipes/street/affix.js +477 -0
- package/out/recipes/street/affix.js.map +1 -0
- package/out/recipes/street/bare.d.ts +27 -0
- package/out/recipes/street/bare.d.ts.map +1 -0
- package/out/recipes/street/bare.js +98 -0
- package/out/recipes/street/bare.js.map +1 -0
- package/out/recipes/street.d.ts +6 -4
- package/out/recipes/street.d.ts.map +1 -1
- package/out/recipes/street.js +29 -8
- package/out/recipes/street.js.map +1 -1
- package/out/recipes/sub/venue/context.d.ts +32 -0
- package/out/recipes/sub/venue/context.d.ts.map +1 -0
- package/out/recipes/sub/venue/context.js +110 -0
- package/out/recipes/sub/venue/context.js.map +1 -0
- package/out/recipes/sub/venue/render.d.ts +58 -0
- package/out/recipes/sub/venue/render.d.ts.map +1 -0
- package/out/recipes/sub/venue/render.js +118 -0
- package/out/recipes/sub/venue/render.js.map +1 -0
- package/out/recipes/sub/venue/sources.d.ts +166 -0
- package/out/recipes/sub/venue/sources.d.ts.map +1 -0
- package/out/recipes/sub/venue/sources.js +419 -0
- package/out/recipes/sub/venue/sources.js.map +1 -0
- package/out/recipes/sub/venue.d.ts +176 -0
- package/out/recipes/sub/venue.d.ts.map +1 -0
- package/out/recipes/sub/venue.js +562 -0
- package/out/recipes/sub/venue.js.map +1 -0
- package/out/recipes/trailing-region.d.ts +9 -61
- package/out/recipes/trailing-region.d.ts.map +1 -1
- package/out/recipes/trailing-region.js +56 -81
- package/out/recipes/trailing-region.js.map +1 -1
- package/out/recipes/unit/sources.d.ts +28 -0
- package/out/recipes/unit/sources.d.ts.map +1 -0
- package/out/recipes/unit/sources.js +30 -0
- package/out/recipes/unit/sources.js.map +1 -0
- package/out/recipes/unit.d.ts +30 -17
- package/out/recipes/unit.d.ts.map +1 -1
- package/out/recipes/unit.js +90 -79
- package/out/recipes/unit.js.map +1 -1
- package/out/recipes.d.ts +26 -0
- package/out/recipes.d.ts.map +1 -0
- package/out/recipes.js +100 -0
- package/out/recipes.js.map +1 -0
- package/out/registers.d.ts +277 -0
- package/out/registers.d.ts.map +1 -0
- package/out/registers.js +273 -0
- package/out/registers.js.map +1 -0
- package/out/ro/adapters/retea-scolara/adapter.d.ts +114 -0
- package/out/ro/adapters/retea-scolara/adapter.d.ts.map +1 -0
- package/out/ro/adapters/retea-scolara/adapter.js +209 -0
- package/out/ro/adapters/retea-scolara/adapter.js.map +1 -0
- package/out/ro/tools/fetch/retea-scolara.d.ts +69 -0
- package/out/ro/tools/fetch/retea-scolara.d.ts.map +1 -0
- package/out/ro/tools/fetch/retea-scolara.js +117 -0
- package/out/ro/tools/fetch/retea-scolara.js.map +1 -0
- package/out/runner.d.ts +120 -60
- package/out/runner.d.ts.map +1 -1
- package/out/runner.js +130 -56
- package/out/runner.js.map +1 -1
- package/out/sg/recipes/register.d.ts +55 -0
- package/out/sg/recipes/register.d.ts.map +1 -0
- package/out/sg/recipes/register.js +206 -0
- package/out/sg/recipes/register.js.map +1 -0
- package/out/sg/tools/fetch/acra.d.ts +20 -0
- package/out/sg/tools/fetch/acra.d.ts.map +1 -0
- package/out/sg/tools/fetch/acra.js +123 -0
- package/out/sg/tools/fetch/acra.js.map +1 -0
- package/out/si/recipes/bare-village.d.ts +31 -0
- package/out/si/recipes/bare-village.d.ts.map +1 -0
- package/out/si/recipes/bare-village.js +103 -0
- package/out/si/recipes/bare-village.js.map +1 -0
- package/out/sk/adapters/inspire/adapter.d.ts +119 -0
- package/out/sk/adapters/inspire/adapter.d.ts.map +1 -0
- package/out/sk/adapters/inspire/adapter.js +318 -0
- package/out/sk/adapters/inspire/adapter.js.map +1 -0
- package/out/sk/tools/fetch/inspire.d.ts +195 -0
- package/out/sk/tools/fetch/inspire.d.ts.map +1 -0
- package/out/sk/tools/fetch/inspire.js +280 -0
- package/out/sk/tools/fetch/inspire.js.map +1 -0
- package/out/source-register/effective-manifest.d.ts +355 -0
- package/out/source-register/effective-manifest.d.ts.map +1 -0
- package/out/source-register/effective-manifest.js +355 -0
- package/out/source-register/effective-manifest.js.map +1 -0
- package/out/source-register/register.d.ts +79 -0
- package/out/source-register/register.d.ts.map +1 -0
- package/out/source-register/register.js +400 -0
- package/out/source-register/register.js.map +1 -0
- package/out/source-register/training-manifest.d.ts +111 -0
- package/out/source-register/training-manifest.d.ts.map +1 -0
- package/out/source-register/training-manifest.js +120 -0
- package/out/source-register/training-manifest.js.map +1 -0
- package/out/source-register/types.d.ts +539 -0
- package/out/source-register/types.d.ts.map +1 -0
- package/out/source-register/types.js +263 -0
- package/out/source-register/types.js.map +1 -0
- package/out/source-register.d.ts +19 -0
- package/out/source-register.d.ts.map +1 -0
- package/out/source-register.js +16 -0
- package/out/source-register.js.map +1 -0
- package/out/south-asia/recipes/register.d.ts +54 -0
- package/out/south-asia/recipes/register.d.ts.map +1 -0
- package/out/south-asia/recipes/register.js +174 -0
- package/out/south-asia/recipes/register.js.map +1 -0
- package/out/subvenue/harvest.d.ts +117 -0
- package/out/subvenue/harvest.d.ts.map +1 -0
- package/out/subvenue/harvest.js +172 -0
- package/out/subvenue/harvest.js.map +1 -0
- package/out/subvenue/promotions.d.ts +65 -0
- package/out/subvenue/promotions.d.ts.map +1 -0
- package/out/subvenue/promotions.js +226 -0
- package/out/subvenue/promotions.js.map +1 -0
- package/out/subvenue/surfaces.d.ts +39 -0
- package/out/subvenue/surfaces.d.ts.map +1 -0
- package/out/subvenue/surfaces.js +75 -0
- package/out/subvenue/surfaces.js.map +1 -0
- package/out/subvenue/table.d.ts +212 -0
- package/out/subvenue/table.d.ts.map +1 -0
- package/out/subvenue/table.js +94 -0
- package/out/subvenue/table.js.map +1 -0
- package/out/surfaces/locale.d.ts +113 -0
- package/out/surfaces/locale.d.ts.map +1 -0
- package/out/surfaces/locale.js +136 -0
- package/out/surfaces/locale.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +22 -31
- package/out/synthesizers/anchor-absorption.d.ts.map +1 -1
- package/out/synthesizers/anchor-absorption.js +30 -85
- package/out/synthesizers/anchor-absorption.js.map +1 -1
- package/out/synthesizers/boundary-stress.d.ts +17 -48
- package/out/synthesizers/boundary-stress.d.ts.map +1 -1
- package/out/synthesizers/boundary-stress.js +27 -121
- package/out/synthesizers/boundary-stress.js.map +1 -1
- package/out/synthesizers/house-venue.d.ts +22 -25
- package/out/synthesizers/house-venue.d.ts.map +1 -1
- package/out/synthesizers/house-venue.js +28 -97
- package/out/synthesizers/house-venue.js.map +1 -1
- package/out/synthesizers/intersection.d.ts +10 -8
- package/out/synthesizers/intersection.d.ts.map +1 -1
- package/out/synthesizers/intersection.js +33 -26
- package/out/synthesizers/intersection.js.map +1 -1
- package/out/synthesizers/no-street.d.ts +7 -37
- package/out/synthesizers/no-street.d.ts.map +1 -1
- package/out/synthesizers/no-street.js +55 -111
- package/out/synthesizers/no-street.js.map +1 -1
- package/out/synthesizers/po-box.d.ts +46 -45
- package/out/synthesizers/po-box.d.ts.map +1 -1
- package/out/synthesizers/po-box.js +57 -97
- package/out/synthesizers/po-box.js.map +1 -1
- package/out/synthesizers/street.d.ts +18 -12
- package/out/synthesizers/street.d.ts.map +1 -1
- package/out/synthesizers/street.js +37 -30
- package/out/synthesizers/street.js.map +1 -1
- package/out/synthesizers/utils.d.ts +32 -129
- package/out/synthesizers/utils.d.ts.map +1 -1
- package/out/synthesizers/utils.js +54 -166
- package/out/synthesizers/utils.js.map +1 -1
- package/out/test-kit/corpus-recipe.d.ts +29 -23
- package/out/test-kit/corpus-recipe.d.ts.map +1 -1
- package/out/test-kit/corpus-recipe.js +28 -13
- package/out/test-kit/corpus-recipe.js.map +1 -1
- package/out/test-kit.d.ts +63 -0
- package/out/test-kit.d.ts.map +1 -0
- package/out/test-kit.js +88 -0
- package/out/test-kit.js.map +1 -0
- package/out/tools/align-canonical.d.ts +7 -0
- package/out/tools/align-canonical.d.ts.map +1 -0
- package/out/tools/align-canonical.js +52 -0
- package/out/tools/align-canonical.js.map +1 -0
- package/out/tools/audit.d.ts +18 -11
- package/out/tools/audit.d.ts.map +1 -1
- package/out/tools/audit.js +87 -95
- package/out/tools/audit.js.map +1 -1
- package/out/tools/corpus-stats.d.ts +24 -15
- package/out/tools/corpus-stats.d.ts.map +1 -1
- package/out/tools/corpus-stats.js +35 -31
- package/out/tools/corpus-stats.js.map +1 -1
- package/out/tools/fetch/atom.d.ts +115 -0
- package/out/tools/fetch/atom.d.ts.map +1 -0
- package/out/tools/fetch/atom.js +84 -0
- package/out/tools/fetch/atom.js.map +1 -0
- package/out/tools/fetch/cordis.d.ts +123 -0
- package/out/tools/fetch/cordis.d.ts.map +1 -0
- package/out/tools/fetch/cordis.js +208 -0
- package/out/tools/fetch/cordis.js.map +1 -0
- package/out/tools/fetch/download/manifest.d.ts +56 -0
- package/out/tools/fetch/download/manifest.d.ts.map +1 -0
- package/out/tools/fetch/download/manifest.js +81 -0
- package/out/tools/fetch/download/manifest.js.map +1 -0
- package/out/tools/fetch/download/network.d.ts +126 -0
- package/out/tools/fetch/download/network.d.ts.map +1 -0
- package/out/tools/fetch/download/network.js +140 -0
- package/out/tools/fetch/download/network.js.map +1 -0
- package/out/tools/fetch/download/retry.d.ts +46 -0
- package/out/tools/fetch/download/retry.d.ts.map +1 -0
- package/out/tools/fetch/download/retry.js +136 -0
- package/out/tools/fetch/download/retry.js.map +1 -0
- package/out/tools/fetch/download.d.ts +4 -176
- package/out/tools/fetch/download.d.ts.map +1 -1
- package/out/tools/fetch/download.js +4 -312
- package/out/tools/fetch/download.js.map +1 -1
- package/out/tools/fetch/geonames/dump.d.ts +109 -0
- package/out/tools/fetch/geonames/dump.d.ts.map +1 -0
- package/out/tools/fetch/geonames/dump.js +181 -0
- package/out/tools/fetch/geonames/dump.js.map +1 -0
- package/out/tools/fetch/geonames/postal.d.ts +41 -0
- package/out/tools/fetch/geonames/postal.d.ts.map +1 -0
- package/out/tools/fetch/geonames/postal.js +87 -0
- package/out/tools/fetch/geonames/postal.js.map +1 -0
- package/out/tools/fetch/gleif.d.ts +137 -0
- package/out/tools/fetch/gleif.d.ts.map +1 -0
- package/out/tools/fetch/gleif.js +220 -0
- package/out/tools/fetch/gleif.js.map +1 -0
- package/out/tools/fetch/header.d.ts +41 -0
- package/out/tools/fetch/header.d.ts.map +1 -0
- package/out/tools/fetch/header.js +59 -0
- package/out/tools/fetch/header.js.map +1 -0
- package/out/tools/fetch/inspire-addresses.d.ts +249 -0
- package/out/tools/fetch/inspire-addresses.d.ts.map +1 -0
- package/out/tools/fetch/inspire-addresses.js +276 -0
- package/out/tools/fetch/inspire-addresses.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +0 -3
- package/out/tools/fetch/openaddresses.d.ts.map +1 -1
- package/out/tools/fetch/openaddresses.js +18 -97
- package/out/tools/fetch/openaddresses.js.map +1 -1
- package/out/tools/fetch/ourairports.d.ts +5 -32
- package/out/tools/fetch/ourairports.d.ts.map +1 -1
- package/out/tools/fetch/ourairports.js +13 -46
- package/out/tools/fetch/ourairports.js.map +1 -1
- package/out/tools/fetch/ppd.d.ts +4 -3
- package/out/tools/fetch/ppd.d.ts.map +1 -1
- package/out/tools/fetch/ppd.js +10 -9
- package/out/tools/fetch/ppd.js.map +1 -1
- package/out/tools/fetch/vlaanderen-ad.d.ts +131 -0
- package/out/tools/fetch/vlaanderen-ad.d.ts.map +1 -0
- package/out/tools/fetch/vlaanderen-ad.js +293 -0
- package/out/tools/fetch/vlaanderen-ad.js.map +1 -0
- package/out/tools/fetch/wfs-harvest.d.ts +410 -0
- package/out/tools/fetch/wfs-harvest.d.ts.map +1 -0
- package/out/tools/fetch/wfs-harvest.js +522 -0
- package/out/tools/fetch/wfs-harvest.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +31 -99
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -1
- package/out/tools/fetch/wikidata-subvenue.js +26 -121
- package/out/tools/fetch/wikidata-subvenue.js.map +1 -1
- package/out/tools/fetch/zip-archive.d.ts +54 -0
- package/out/tools/fetch/zip-archive.d.ts.map +1 -0
- package/out/tools/fetch/zip-archive.js +58 -0
- package/out/tools/fetch/zip-archive.js.map +1 -0
- package/out/tools/fetch.d.ts +140 -0
- package/out/tools/fetch.d.ts.map +1 -0
- package/out/tools/fetch.js +136 -0
- package/out/tools/fetch.js.map +1 -0
- package/out/tools/golden/expand.d.ts +105 -0
- package/out/tools/golden/expand.d.ts.map +1 -0
- package/out/tools/golden/expand.js +420 -0
- package/out/tools/golden/expand.js.map +1 -0
- package/out/tools/golden/promote.d.ts +77 -0
- package/out/tools/golden/promote.d.ts.map +1 -0
- package/out/tools/golden/promote.js +248 -0
- package/out/tools/golden/promote.js.map +1 -0
- package/out/tools/golden/relabel-street/directory.d.ts +98 -0
- package/out/tools/golden/relabel-street/directory.d.ts.map +1 -0
- package/out/tools/golden/relabel-street/directory.js +227 -0
- package/out/tools/golden/relabel-street/directory.js.map +1 -0
- package/out/tools/golden/relabel-street/row.d.ts +69 -0
- package/out/tools/golden/relabel-street/row.d.ts.map +1 -0
- package/out/tools/golden/relabel-street/row.js +174 -0
- package/out/tools/golden/relabel-street/row.js.map +1 -0
- package/out/tools/golden/relabel-street.d.ts +9 -0
- package/out/tools/golden/relabel-street.d.ts.map +1 -0
- package/out/tools/golden/relabel-street.js +9 -0
- package/out/tools/golden/relabel-street.js.map +1 -0
- package/out/tools/ingest-csv.d.ts +19 -15
- package/out/tools/ingest-csv.d.ts.map +1 -1
- package/out/tools/ingest-csv.js +39 -45
- package/out/tools/ingest-csv.js.map +1 -1
- package/out/tools/jsonl-to-parquet.d.ts +15 -28
- package/out/tools/jsonl-to-parquet.d.ts.map +1 -1
- package/out/tools/jsonl-to-parquet.js +49 -91
- package/out/tools/jsonl-to-parquet.js.map +1 -1
- package/out/tools/lint/recipe-output/vocab.d.ts +77 -0
- package/out/tools/lint/recipe-output/vocab.d.ts.map +1 -0
- package/out/tools/lint/recipe-output/vocab.js +239 -0
- package/out/tools/lint/recipe-output/vocab.js.map +1 -0
- package/out/tools/lint/recipe-output.d.ts +73 -0
- package/out/tools/lint/recipe-output.d.ts.map +1 -0
- package/out/tools/lint/recipe-output.js +302 -0
- package/out/tools/lint/recipe-output.js.map +1 -0
- package/out/tools/migrate/overlay-parquet.d.ts +30 -0
- package/out/tools/migrate/overlay-parquet.d.ts.map +1 -0
- package/out/tools/migrate/overlay-parquet.js +141 -0
- package/out/tools/migrate/overlay-parquet.js.map +1 -0
- package/out/tools/migrate/recipe-output.d.ts +35 -0
- package/out/tools/migrate/recipe-output.d.ts.map +1 -0
- package/out/tools/migrate/recipe-output.js +124 -0
- package/out/tools/migrate/recipe-output.js.map +1 -0
- package/out/tools/migrate/source-names.d.ts +52 -0
- package/out/tools/migrate/source-names.d.ts.map +1 -0
- package/out/tools/migrate/source-names.js +105 -0
- package/out/tools/migrate/source-names.js.map +1 -0
- package/out/tools/overlay/kryptonite.d.ts +33 -0
- package/out/tools/overlay/kryptonite.d.ts.map +1 -0
- package/out/tools/overlay/kryptonite.js +108 -0
- package/out/tools/overlay/kryptonite.js.map +1 -0
- package/out/tools/overlay/manifest.d.ts +142 -0
- package/out/tools/overlay/manifest.d.ts.map +1 -0
- package/out/tools/overlay/manifest.js +260 -0
- package/out/tools/overlay/manifest.js.map +1 -0
- package/out/tools/overlay/merge-source.d.ts +73 -0
- package/out/tools/overlay/merge-source.d.ts.map +1 -0
- package/out/tools/overlay/merge-source.js +63 -0
- package/out/tools/overlay/merge-source.js.map +1 -0
- package/out/tools/overlay/split-slice.d.ts +66 -0
- package/out/tools/overlay/split-slice.d.ts.map +1 -0
- package/out/tools/overlay/split-slice.js +78 -0
- package/out/tools/overlay/split-slice.js.map +1 -0
- package/out/tools/overlay/translit.d.ts +54 -0
- package/out/tools/overlay/translit.d.ts.map +1 -0
- package/out/tools/overlay/translit.js +177 -0
- package/out/tools/overlay/translit.js.map +1 -0
- package/out/tools/overture-subvenue.d.ts +17 -76
- package/out/tools/overture-subvenue.d.ts.map +1 -1
- package/out/tools/overture-subvenue.js +7 -74
- package/out/tools/overture-subvenue.js.map +1 -1
- package/out/tools/postcode-triples.d.ts +96 -109
- package/out/tools/postcode-triples.d.ts.map +1 -1
- package/out/tools/postcode-triples.js +237 -152
- package/out/tools/postcode-triples.js.map +1 -1
- package/out/tools/source-register/build.d.ts +145 -0
- package/out/tools/source-register/build.d.ts.map +1 -0
- package/out/tools/source-register/build.js +515 -0
- package/out/tools/source-register/build.js.map +1 -0
- package/out/tools/sub/venue/head-nouns.d.ts +21 -0
- package/out/tools/sub/venue/head-nouns.d.ts.map +1 -0
- package/out/tools/sub/venue/head-nouns.js +176 -0
- package/out/tools/sub/venue/head-nouns.js.map +1 -0
- package/out/tools/sub/venue/lexicon.d.ts +129 -0
- package/out/tools/sub/venue/lexicon.d.ts.map +1 -0
- package/out/tools/sub/venue/lexicon.js +239 -0
- package/out/tools/sub/venue/lexicon.js.map +1 -0
- package/out/tools/sub/venue/wikidata.d.ts +28 -0
- package/out/tools/sub/venue/wikidata.d.ts.map +1 -0
- package/out/tools/sub/venue/wikidata.js +65 -0
- package/out/tools/sub/venue/wikidata.js.map +1 -0
- package/out/tools.d.ts +31 -0
- package/out/tools.d.ts.map +1 -0
- package/out/tools.js +31 -0
- package/out/tools.js.map +1 -0
- package/out/tw/tools/fetch/gcis.d.ts +29 -0
- package/out/tw/tools/fetch/gcis.d.ts.map +1 -0
- package/out/tw/tools/fetch/gcis.js +141 -0
- package/out/tw/tools/fetch/gcis.js.map +1 -0
- package/out/types.d.ts +270 -101
- package/out/types.d.ts.map +1 -1
- package/out/types.js +133 -9
- package/out/types.js.map +1 -1
- package/out/us/adapters/fcc-bdc/adapter.d.ts +50 -0
- package/out/us/adapters/fcc-bdc/adapter.d.ts.map +1 -0
- package/out/us/adapters/fcc-bdc/adapter.js +129 -0
- package/out/us/adapters/fcc-bdc/adapter.js.map +1 -0
- package/out/us/adapters/state/hi-schools/adapter.d.ts +47 -0
- package/out/us/adapters/state/hi-schools/adapter.d.ts.map +1 -0
- package/out/us/adapters/state/hi-schools/adapter.js +146 -0
- package/out/us/adapters/state/hi-schools/adapter.js.map +1 -0
- package/out/us/adapters/state/hi-schools/workbook.d.ts +34 -0
- package/out/us/adapters/state/hi-schools/workbook.d.ts.map +1 -0
- package/out/us/adapters/state/hi-schools/workbook.js +22 -0
- package/out/us/adapters/state/hi-schools/workbook.js.map +1 -0
- package/out/us/adapters/state/ia-contractors/adapter.d.ts +41 -0
- package/out/us/adapters/state/ia-contractors/adapter.d.ts.map +1 -0
- package/out/us/adapters/state/ia-contractors/adapter.js +117 -0
- package/out/us/adapters/state/ia-contractors/adapter.js.map +1 -0
- package/out/us/adapters/state/ny-notaries/adapter.d.ts +33 -0
- package/out/us/adapters/state/ny-notaries/adapter.d.ts.map +1 -0
- package/out/us/adapters/state/ny-notaries/adapter.js +114 -0
- package/out/us/adapters/state/ny-notaries/adapter.js.map +1 -0
- package/out/us/adapters/state/tx-notaries/adapter.d.ts +34 -0
- package/out/us/adapters/state/tx-notaries/adapter.d.ts.map +1 -0
- package/out/us/adapters/state/tx-notaries/adapter.js +125 -0
- package/out/us/adapters/state/tx-notaries/adapter.js.map +1 -0
- package/out/us/adapters/tiger/adapter.d.ts +31 -0
- package/out/us/adapters/tiger/adapter.d.ts.map +1 -0
- package/out/us/adapters/tiger/adapter.js +173 -0
- package/out/us/adapters/tiger/adapter.js.map +1 -0
- package/out/us/adapters/tiger/street-decompose.d.ts +23 -0
- package/out/us/adapters/tiger/street-decompose.d.ts.map +1 -0
- package/out/us/adapters/tiger/street-decompose.js +58 -0
- package/out/us/adapters/tiger/street-decompose.js.map +1 -0
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts +62 -0
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.js +133 -0
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.js.map +1 -0
- package/out/us/adapters/usgov/imls-pls/adapter.d.ts +37 -0
- package/out/us/adapters/usgov/imls-pls/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/imls-pls/adapter.js +113 -0
- package/out/us/adapters/usgov/imls-pls/adapter.js.map +1 -0
- package/out/us/adapters/usgov/irs-bmf/adapter.d.ts +38 -0
- package/out/us/adapters/usgov/irs-bmf/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/irs-bmf/adapter.js +126 -0
- package/out/us/adapters/usgov/irs-bmf/adapter.js.map +1 -0
- package/out/us/adapters/usgov/nad/adapter.d.ts +28 -0
- package/out/us/adapters/usgov/nad/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/nad/adapter.js +185 -0
- package/out/us/adapters/usgov/nad/adapter.js.map +1 -0
- package/out/us/adapters/usgov/nppes/adapter.d.ts +29 -0
- package/out/us/adapters/usgov/nppes/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/nppes/adapter.js +140 -0
- package/out/us/adapters/usgov/nppes/adapter.js.map +1 -0
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts +47 -0
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js +153 -0
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js.map +1 -0
- package/out/us/fips-state.d.ts +50 -0
- package/out/us/fips-state.d.ts.map +1 -0
- package/out/us/fips-state.js +109 -0
- package/out/us/fips-state.js.map +1 -0
- package/out/us/tools/fetch/hrsa.d.ts +18 -0
- package/out/us/tools/fetch/hrsa.d.ts.map +1 -0
- package/out/us/tools/fetch/hrsa.js +45 -0
- package/out/us/tools/fetch/hrsa.js.map +1 -0
- package/out/us/tools/fetch/imls-pls.d.ts +14 -0
- package/out/us/tools/fetch/imls-pls.d.ts.map +1 -0
- package/out/us/tools/fetch/imls-pls.js +91 -0
- package/out/us/tools/fetch/imls-pls.js.map +1 -0
- package/out/us/tools/fetch/nad.d.ts +82 -0
- package/out/us/tools/fetch/nad.d.ts.map +1 -0
- package/out/us/tools/fetch/nad.js +239 -0
- package/out/us/tools/fetch/nad.js.map +1 -0
- package/out/us/tools/fetch/nppes.d.ts +16 -0
- package/out/us/tools/fetch/nppes.d.ts.map +1 -0
- package/out/us/tools/fetch/nppes.js +114 -0
- package/out/us/tools/fetch/nppes.js.map +1 -0
- package/out/us/tools/fetch/state/hi-schools.d.ts +29 -0
- package/out/us/tools/fetch/state/hi-schools.d.ts.map +1 -0
- package/out/us/tools/fetch/state/hi-schools.js +114 -0
- package/out/us/tools/fetch/state/hi-schools.js.map +1 -0
- package/out/us/tools/fetch/state/sources.d.ts +27 -0
- package/out/us/tools/fetch/state/sources.d.ts.map +1 -0
- package/out/us/tools/fetch/state/sources.js +110 -0
- package/out/us/tools/fetch/state/sources.js.map +1 -0
- package/out/us/tools/fetch/tiger-full.d.ts +9 -0
- package/out/us/tools/fetch/tiger-full.d.ts.map +1 -0
- package/out/us/tools/fetch/tiger-full.js +178 -0
- package/out/us/tools/fetch/tiger-full.js.map +1 -0
- package/out/utils/align.d.ts +25 -20
- package/out/utils/align.d.ts.map +1 -1
- package/out/utils/align.js +27 -42
- package/out/utils/align.js.map +1 -1
- package/out/utils/cooccurrence-stats.d.ts +58 -0
- package/out/utils/cooccurrence-stats.d.ts.map +1 -0
- package/out/utils/cooccurrence-stats.js +62 -0
- package/out/utils/cooccurrence-stats.js.map +1 -0
- package/out/utils/golden.d.ts +23 -29
- package/out/utils/golden.d.ts.map +1 -1
- package/out/utils/golden.js +33 -45
- package/out/utils/golden.js.map +1 -1
- package/out/utils/license.d.ts +158 -21
- package/out/utils/license.d.ts.map +1 -1
- package/out/utils/license.js +156 -26
- package/out/utils/license.js.map +1 -1
- package/out/utils/split.d.ts +66 -70
- package/out/utils/split.d.ts.map +1 -1
- package/out/utils/split.js +158 -69
- package/out/utils/split.js.map +1 -1
- package/out/utils/tokenize.d.ts +16 -28
- package/out/utils/tokenize.d.ts.map +1 -1
- package/out/utils/tokenize.js +18 -31
- package/out/utils/tokenize.js.map +1 -1
- package/out/utils/wof-json.d.ts +88 -62
- package/out/utils/wof-json.d.ts.map +1 -1
- package/out/utils/wof-json.js +81 -65
- package/out/utils/wof-json.js.map +1 -1
- package/out/utils.d.ts +13 -0
- package/out/utils.d.ts.map +1 -0
- package/out/utils.js +13 -0
- package/out/utils.js.map +1 -0
- package/out/ve/recipes/reviewed-postcode-tail.d.ts +65 -0
- package/out/ve/recipes/reviewed-postcode-tail.d.ts.map +1 -0
- package/out/ve/recipes/reviewed-postcode-tail.js +146 -0
- package/out/ve/recipes/reviewed-postcode-tail.js.map +1 -0
- package/package.json +46 -330
- package/lib/adapters/ban/adapter.ts +0 -190
- package/lib/adapters/ban/street-decompose.ts +0 -66
- package/lib/adapters/fcc-bdc/adapter.ts +0 -174
- package/lib/adapters/geonames-postal/adapter.ts +0 -122
- package/lib/adapters/gnaf/adapter.ts +0 -149
- package/lib/adapters/gnaf/assemble.ts +0 -225
- package/lib/adapters/index.ts +0 -153
- package/lib/adapters/state-hi-schools/adapter.ts +0 -170
- package/lib/adapters/state-hi-schools/workbook.ts +0 -35
- package/lib/adapters/state-ia-contractors/adapter.ts +0 -144
- package/lib/adapters/state-ny-notaries/adapter.ts +0 -141
- package/lib/adapters/state-tx-notaries/adapter.ts +0 -157
- package/lib/adapters/synth-po-box/adapter.ts +0 -204
- package/lib/adapters/tiger/adapter.ts +0 -252
- package/lib/adapters/tiger/street-decompose.ts +0 -83
- package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +0 -167
- package/lib/adapters/usgov-imls-pls/adapter.ts +0 -143
- package/lib/adapters/usgov-irs-bmf/adapter.ts +0 -151
- package/lib/adapters/usgov-nad/adapter.ts +0 -334
- package/lib/adapters/usgov-nppes/adapter.ts +0 -151
- package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -193
- package/lib/adapters/utils/index.ts +0 -307
- package/lib/adapters/wof-admin-jp/adapter.ts +0 -214
- package/lib/adapters/wof-admin-json/adapter.ts +0 -231
- package/lib/adapters/wof-json-rows.ts +0 -129
- package/lib/adapters/wof-postalcode-json/adapter.ts +0 -176
- package/lib/codex/us-fips-state.ts +0 -113
- package/lib/recipes/bare-country.ts +0 -95
- package/lib/recipes/cn-organizational-units.ts +0 -199
- package/lib/recipes/cz-pcfirst-preposition.ts +0 -112
- package/lib/recipes/fr-admin-split.ts +0 -243
- package/lib/recipes/fr-bare-street.ts +0 -171
- package/lib/recipes/fr-fragment.ts +0 -334
- package/lib/recipes/fr-lieudit.ts +0 -301
- package/lib/recipes/fr-order.ts +0 -246
- package/lib/recipes/german.ts +0 -360
- package/lib/recipes/index.ts +0 -97
- package/lib/recipes/locale.ts +0 -600
- package/lib/recipes/nl-postcode.ts +0 -117
- package/lib/recipes/no-fragment.ts +0 -213
- package/lib/recipes/no-street-led.ts +0 -135
- package/lib/recipes/no-street.ts +0 -91
- package/lib/recipes/po-box-cedex.ts +0 -976
- package/lib/recipes/po-box.ts +0 -124
- package/lib/recipes/reviewed-postcode-tail.ts +0 -190
- package/lib/recipes/si-bare-village.ts +0 -99
- package/lib/recipes/street-affix.ts +0 -805
- package/lib/recipes/street-bare.ts +0 -102
- package/lib/recipes/sub-venue-sources.ts +0 -878
- package/lib/recipes/sub-venue.ts +0 -998
- package/lib/synthesizers/german.ts +0 -260
- package/lib/test-kit/index.ts +0 -100
- package/lib/tools/align-slice.ts +0 -68
- package/lib/tools/fetch/acra-sg.ts +0 -174
- package/lib/tools/fetch/ban.ts +0 -289
- package/lib/tools/fetch/gcis-tw.ts +0 -175
- package/lib/tools/fetch/geonames-dump.ts +0 -257
- package/lib/tools/fetch/geonames-postal.ts +0 -180
- package/lib/tools/fetch/houjin-jp.ts +0 -135
- package/lib/tools/fetch/hrsa.ts +0 -59
- package/lib/tools/fetch/imls-pls.ts +0 -149
- package/lib/tools/fetch/index.ts +0 -174
- package/lib/tools/fetch/juso-kr.ts +0 -165
- package/lib/tools/fetch/localdata-kr.ts +0 -194
- package/lib/tools/fetch/nad.ts +0 -341
- package/lib/tools/fetch/nppes.ts +0 -165
- package/lib/tools/fetch/state-hi-schools.ts +0 -161
- package/lib/tools/fetch/state-sources.ts +0 -146
- package/lib/tools/fetch/tiger-full.ts +0 -308
- package/lib/tools/gb-title-case.ts +0 -69
- package/lib/tools/golden-expand.ts +0 -574
- package/lib/tools/golden-promote.ts +0 -337
- package/lib/tools/golden-relabel-street.ts +0 -686
- package/lib/tools/index.ts +0 -28
- package/lib/tools/lint-slice-vocab.ts +0 -388
- package/lib/tools/lint-slice.ts +0 -496
- package/lib/tools/overlay-manifest.ts +0 -148
- package/lib/tools/slice-kryptonite.ts +0 -137
- package/lib/tools/slice-translit.ts +0 -218
- package/lib/tools/sub-venue/harvest.ts +0 -234
- package/lib/tools/sub-venue/head-nouns.ts +0 -245
- package/lib/tools/sub-venue/surfaces.ts +0 -95
- package/lib/tools/sub-venue/table.ts +0 -281
- package/lib/tools/sub-venue/wikidata.ts +0 -85
- package/lib/tools/sub-venue-lexicon.ts +0 -429
- package/lib/tools/sub-venue-promotions.ts +0 -330
- package/lib/utils/index.ts +0 -14
- package/lib/utils/parquet.ts +0 -582
- package/lib/utils/slice-stats.ts +0 -95
- package/out/adapters/ban/adapter.d.ts +0 -44
- package/out/adapters/ban/adapter.d.ts.map +0 -1
- package/out/adapters/ban/adapter.js +0 -149
- package/out/adapters/ban/adapter.js.map +0 -1
- package/out/adapters/ban/street-decompose.d.ts +0 -28
- package/out/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/adapters/ban/street-decompose.js +0 -51
- package/out/adapters/ban/street-decompose.js.map +0 -1
- package/out/adapters/fcc-bdc/adapter.d.ts +0 -68
- package/out/adapters/fcc-bdc/adapter.d.ts.map +0 -1
- package/out/adapters/fcc-bdc/adapter.js +0 -144
- package/out/adapters/fcc-bdc/adapter.js.map +0 -1
- package/out/adapters/geonames-postal/adapter.d.ts +0 -54
- package/out/adapters/geonames-postal/adapter.d.ts.map +0 -1
- package/out/adapters/geonames-postal/adapter.js +0 -107
- package/out/adapters/geonames-postal/adapter.js.map +0 -1
- package/out/adapters/gnaf/adapter.d.ts +0 -49
- package/out/adapters/gnaf/adapter.d.ts.map +0 -1
- package/out/adapters/gnaf/adapter.js +0 -124
- package/out/adapters/gnaf/adapter.js.map +0 -1
- package/out/adapters/gnaf/assemble.d.ts +0 -65
- package/out/adapters/gnaf/assemble.d.ts.map +0 -1
- package/out/adapters/gnaf/assemble.js +0 -154
- package/out/adapters/gnaf/assemble.js.map +0 -1
- package/out/adapters/index.d.ts +0 -51
- package/out/adapters/index.d.ts.map +0 -1
- package/out/adapters/index.js +0 -95
- package/out/adapters/index.js.map +0 -1
- package/out/adapters/state-hi-schools/adapter.d.ts +0 -46
- package/out/adapters/state-hi-schools/adapter.d.ts.map +0 -1
- package/out/adapters/state-hi-schools/adapter.js +0 -145
- package/out/adapters/state-hi-schools/adapter.js.map +0 -1
- package/out/adapters/state-hi-schools/workbook.d.ts +0 -29
- package/out/adapters/state-hi-schools/workbook.d.ts.map +0 -1
- package/out/adapters/state-hi-schools/workbook.js +0 -20
- package/out/adapters/state-hi-schools/workbook.js.map +0 -1
- package/out/adapters/state-ia-contractors/adapter.d.ts +0 -34
- package/out/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
- package/out/adapters/state-ia-contractors/adapter.js +0 -111
- package/out/adapters/state-ia-contractors/adapter.js.map +0 -1
- package/out/adapters/state-ny-notaries/adapter.d.ts +0 -32
- package/out/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
- package/out/adapters/state-ny-notaries/adapter.js +0 -119
- package/out/adapters/state-ny-notaries/adapter.js.map +0 -1
- package/out/adapters/state-tx-notaries/adapter.d.ts +0 -33
- package/out/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
- package/out/adapters/state-tx-notaries/adapter.js +0 -125
- package/out/adapters/state-tx-notaries/adapter.js.map +0 -1
- package/out/adapters/synth-po-box/adapter.d.ts +0 -67
- package/out/adapters/synth-po-box/adapter.d.ts.map +0 -1
- package/out/adapters/synth-po-box/adapter.js +0 -140
- package/out/adapters/synth-po-box/adapter.js.map +0 -1
- package/out/adapters/tiger/adapter.d.ts +0 -55
- package/out/adapters/tiger/adapter.d.ts.map +0 -1
- package/out/adapters/tiger/adapter.js +0 -201
- package/out/adapters/tiger/adapter.js.map +0 -1
- package/out/adapters/tiger/street-decompose.d.ts +0 -30
- package/out/adapters/tiger/street-decompose.d.ts.map +0 -1
- package/out/adapters/tiger/street-decompose.js +0 -68
- package/out/adapters/tiger/street-decompose.js.map +0 -1
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -56
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-hrsa-fqhc/adapter.js +0 -132
- package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
- package/out/adapters/usgov-imls-pls/adapter.d.ts +0 -36
- package/out/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-imls-pls/adapter.js +0 -114
- package/out/adapters/usgov-imls-pls/adapter.js.map +0 -1
- package/out/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
- package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-irs-bmf/adapter.js +0 -120
- package/out/adapters/usgov-irs-bmf/adapter.js.map +0 -1
- package/out/adapters/usgov-nad/adapter.d.ts +0 -48
- package/out/adapters/usgov-nad/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-nad/adapter.js +0 -249
- package/out/adapters/usgov-nad/adapter.js.map +0 -1
- package/out/adapters/usgov-nppes/adapter.d.ts +0 -39
- package/out/adapters/usgov-nppes/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-nppes/adapter.js +0 -118
- package/out/adapters/usgov-nppes/adapter.js.map +0 -1
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts +0 -46
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -154
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
- package/out/adapters/utils/index.d.ts +0 -191
- package/out/adapters/utils/index.d.ts.map +0 -1
- package/out/adapters/utils/index.js +0 -206
- package/out/adapters/utils/index.js.map +0 -1
- package/out/adapters/wof-admin-jp/adapter.d.ts +0 -65
- package/out/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
- package/out/adapters/wof-admin-jp/adapter.js +0 -161
- package/out/adapters/wof-admin-jp/adapter.js.map +0 -1
- package/out/adapters/wof-admin-json/adapter.d.ts +0 -79
- package/out/adapters/wof-admin-json/adapter.d.ts.map +0 -1
- package/out/adapters/wof-admin-json/adapter.js +0 -197
- package/out/adapters/wof-admin-json/adapter.js.map +0 -1
- package/out/adapters/wof-json-rows.d.ts +0 -62
- package/out/adapters/wof-json-rows.d.ts.map +0 -1
- package/out/adapters/wof-json-rows.js +0 -83
- package/out/adapters/wof-json-rows.js.map +0 -1
- package/out/adapters/wof-postalcode-json/adapter.d.ts +0 -65
- package/out/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
- package/out/adapters/wof-postalcode-json/adapter.js +0 -151
- package/out/adapters/wof-postalcode-json/adapter.js.map +0 -1
- package/out/codex/us-fips-state.d.ts +0 -41
- package/out/codex/us-fips-state.d.ts.map +0 -1
- package/out/codex/us-fips-state.js +0 -100
- package/out/codex/us-fips-state.js.map +0 -1
- package/out/recipes/bare-country.d.ts +0 -25
- package/out/recipes/bare-country.d.ts.map +0 -1
- package/out/recipes/bare-country.js +0 -88
- package/out/recipes/bare-country.js.map +0 -1
- package/out/recipes/cn-organizational-units.d.ts +0 -36
- package/out/recipes/cn-organizational-units.d.ts.map +0 -1
- package/out/recipes/cn-organizational-units.js +0 -159
- package/out/recipes/cn-organizational-units.js.map +0 -1
- package/out/recipes/cz-pcfirst-preposition.d.ts +0 -22
- package/out/recipes/cz-pcfirst-preposition.d.ts.map +0 -1
- package/out/recipes/cz-pcfirst-preposition.js +0 -101
- package/out/recipes/cz-pcfirst-preposition.js.map +0 -1
- package/out/recipes/fr-admin-split.d.ts +0 -38
- package/out/recipes/fr-admin-split.d.ts.map +0 -1
- package/out/recipes/fr-admin-split.js +0 -192
- package/out/recipes/fr-admin-split.js.map +0 -1
- package/out/recipes/fr-bare-street.d.ts +0 -28
- package/out/recipes/fr-bare-street.d.ts.map +0 -1
- package/out/recipes/fr-bare-street.js +0 -144
- package/out/recipes/fr-bare-street.js.map +0 -1
- package/out/recipes/fr-fragment.d.ts +0 -77
- package/out/recipes/fr-fragment.d.ts.map +0 -1
- package/out/recipes/fr-fragment.js +0 -277
- package/out/recipes/fr-fragment.js.map +0 -1
- package/out/recipes/fr-lieudit.d.ts +0 -32
- package/out/recipes/fr-lieudit.d.ts.map +0 -1
- package/out/recipes/fr-lieudit.js +0 -227
- package/out/recipes/fr-lieudit.js.map +0 -1
- package/out/recipes/fr-order.d.ts +0 -38
- package/out/recipes/fr-order.d.ts.map +0 -1
- package/out/recipes/fr-order.js +0 -198
- package/out/recipes/fr-order.js.map +0 -1
- package/out/recipes/german.d.ts +0 -44
- package/out/recipes/german.d.ts.map +0 -1
- package/out/recipes/german.js +0 -289
- package/out/recipes/german.js.map +0 -1
- package/out/recipes/index.d.ts +0 -24
- package/out/recipes/index.d.ts.map +0 -1
- package/out/recipes/index.js +0 -91
- package/out/recipes/index.js.map +0 -1
- package/out/recipes/locale.d.ts +0 -136
- package/out/recipes/locale.d.ts.map +0 -1
- package/out/recipes/locale.js +0 -460
- package/out/recipes/locale.js.map +0 -1
- package/out/recipes/nl-postcode.d.ts +0 -26
- package/out/recipes/nl-postcode.d.ts.map +0 -1
- package/out/recipes/nl-postcode.js +0 -103
- package/out/recipes/nl-postcode.js.map +0 -1
- package/out/recipes/no-fragment.d.ts +0 -43
- package/out/recipes/no-fragment.d.ts.map +0 -1
- package/out/recipes/no-fragment.js +0 -183
- package/out/recipes/no-fragment.js.map +0 -1
- package/out/recipes/no-street-led.d.ts +0 -24
- package/out/recipes/no-street-led.d.ts.map +0 -1
- package/out/recipes/no-street-led.js +0 -114
- package/out/recipes/no-street-led.js.map +0 -1
- package/out/recipes/no-street.d.ts +0 -18
- package/out/recipes/no-street.d.ts.map +0 -1
- package/out/recipes/no-street.js +0 -72
- package/out/recipes/no-street.js.map +0 -1
- package/out/recipes/po-box-cedex.d.ts +0 -38
- package/out/recipes/po-box-cedex.d.ts.map +0 -1
- package/out/recipes/po-box-cedex.js +0 -768
- package/out/recipes/po-box-cedex.js.map +0 -1
- package/out/recipes/po-box.d.ts +0 -17
- package/out/recipes/po-box.d.ts.map +0 -1
- package/out/recipes/po-box.js +0 -101
- package/out/recipes/po-box.js.map +0 -1
- package/out/recipes/reviewed-postcode-tail.d.ts +0 -47
- package/out/recipes/reviewed-postcode-tail.d.ts.map +0 -1
- package/out/recipes/reviewed-postcode-tail.js +0 -125
- package/out/recipes/reviewed-postcode-tail.js.map +0 -1
- package/out/recipes/si-bare-village.d.ts +0 -32
- package/out/recipes/si-bare-village.d.ts.map +0 -1
- package/out/recipes/si-bare-village.js +0 -89
- package/out/recipes/si-bare-village.js.map +0 -1
- package/out/recipes/street-affix.d.ts +0 -89
- package/out/recipes/street-affix.d.ts.map +0 -1
- package/out/recipes/street-affix.js +0 -563
- package/out/recipes/street-affix.js.map +0 -1
- package/out/recipes/street-bare.d.ts +0 -25
- package/out/recipes/street-bare.d.ts.map +0 -1
- package/out/recipes/street-bare.js +0 -87
- package/out/recipes/street-bare.js.map +0 -1
- package/out/recipes/sub-venue-sources.d.ts +0 -229
- package/out/recipes/sub-venue-sources.d.ts.map +0 -1
- package/out/recipes/sub-venue-sources.js +0 -654
- package/out/recipes/sub-venue-sources.js.map +0 -1
- package/out/recipes/sub-venue.d.ts +0 -269
- package/out/recipes/sub-venue.d.ts.map +0 -1
- package/out/recipes/sub-venue.js +0 -726
- package/out/recipes/sub-venue.js.map +0 -1
- package/out/synthesizers/german.d.ts +0 -115
- package/out/synthesizers/german.d.ts.map +0 -1
- package/out/synthesizers/german.js +0 -149
- package/out/synthesizers/german.js.map +0 -1
- package/out/test-kit/index.d.ts +0 -48
- package/out/test-kit/index.d.ts.map +0 -1
- package/out/test-kit/index.js +0 -78
- package/out/test-kit/index.js.map +0 -1
- package/out/tools/align-slice.d.ts +0 -7
- package/out/tools/align-slice.d.ts.map +0 -1
- package/out/tools/align-slice.js +0 -55
- package/out/tools/align-slice.js.map +0 -1
- package/out/tools/fetch/acra-sg.d.ts +0 -23
- package/out/tools/fetch/acra-sg.d.ts.map +0 -1
- package/out/tools/fetch/acra-sg.js +0 -126
- package/out/tools/fetch/acra-sg.js.map +0 -1
- package/out/tools/fetch/ban.d.ts +0 -31
- package/out/tools/fetch/ban.d.ts.map +0 -1
- package/out/tools/fetch/ban.js +0 -239
- package/out/tools/fetch/ban.js.map +0 -1
- package/out/tools/fetch/gcis-tw.d.ts +0 -23
- package/out/tools/fetch/gcis-tw.d.ts.map +0 -1
- package/out/tools/fetch/gcis-tw.js +0 -135
- package/out/tools/fetch/gcis-tw.js.map +0 -1
- package/out/tools/fetch/geonames-dump.d.ts +0 -91
- package/out/tools/fetch/geonames-dump.d.ts.map +0 -1
- package/out/tools/fetch/geonames-dump.js +0 -171
- package/out/tools/fetch/geonames-dump.js.map +0 -1
- package/out/tools/fetch/geonames-postal.d.ts +0 -76
- package/out/tools/fetch/geonames-postal.d.ts.map +0 -1
- package/out/tools/fetch/geonames-postal.js +0 -126
- package/out/tools/fetch/geonames-postal.js.map +0 -1
- package/out/tools/fetch/houjin-jp.d.ts +0 -24
- package/out/tools/fetch/houjin-jp.d.ts.map +0 -1
- package/out/tools/fetch/houjin-jp.js +0 -102
- package/out/tools/fetch/houjin-jp.js.map +0 -1
- package/out/tools/fetch/hrsa.d.ts +0 -18
- package/out/tools/fetch/hrsa.d.ts.map +0 -1
- package/out/tools/fetch/hrsa.js +0 -46
- package/out/tools/fetch/hrsa.js.map +0 -1
- package/out/tools/fetch/imls-pls.d.ts +0 -25
- package/out/tools/fetch/imls-pls.d.ts.map +0 -1
- package/out/tools/fetch/imls-pls.js +0 -108
- package/out/tools/fetch/imls-pls.js.map +0 -1
- package/out/tools/fetch/index.d.ts +0 -171
- package/out/tools/fetch/index.d.ts.map +0 -1
- package/out/tools/fetch/index.js +0 -170
- package/out/tools/fetch/index.js.map +0 -1
- package/out/tools/fetch/juso-kr.d.ts +0 -30
- package/out/tools/fetch/juso-kr.d.ts.map +0 -1
- package/out/tools/fetch/juso-kr.js +0 -120
- package/out/tools/fetch/juso-kr.js.map +0 -1
- package/out/tools/fetch/localdata-kr.d.ts +0 -30
- package/out/tools/fetch/localdata-kr.d.ts.map +0 -1
- package/out/tools/fetch/localdata-kr.js +0 -139
- package/out/tools/fetch/localdata-kr.js.map +0 -1
- package/out/tools/fetch/nad.d.ts +0 -70
- package/out/tools/fetch/nad.d.ts.map +0 -1
- package/out/tools/fetch/nad.js +0 -234
- package/out/tools/fetch/nad.js.map +0 -1
- package/out/tools/fetch/nppes.d.ts +0 -26
- package/out/tools/fetch/nppes.d.ts.map +0 -1
- package/out/tools/fetch/nppes.js +0 -126
- package/out/tools/fetch/nppes.js.map +0 -1
- package/out/tools/fetch/state-hi-schools.d.ts +0 -26
- package/out/tools/fetch/state-hi-schools.d.ts.map +0 -1
- package/out/tools/fetch/state-hi-schools.js +0 -112
- package/out/tools/fetch/state-hi-schools.js.map +0 -1
- package/out/tools/fetch/state-sources.d.ts +0 -26
- package/out/tools/fetch/state-sources.d.ts.map +0 -1
- package/out/tools/fetch/state-sources.js +0 -111
- package/out/tools/fetch/state-sources.js.map +0 -1
- package/out/tools/fetch/tiger-full.d.ts +0 -22
- package/out/tools/fetch/tiger-full.d.ts.map +0 -1
- package/out/tools/fetch/tiger-full.js +0 -217
- package/out/tools/fetch/tiger-full.js.map +0 -1
- package/out/tools/gb-title-case.d.ts +0 -2
- package/out/tools/gb-title-case.d.ts.map +0 -1
- package/out/tools/gb-title-case.js +0 -65
- package/out/tools/gb-title-case.js.map +0 -1
- package/out/tools/golden-expand.d.ts +0 -90
- package/out/tools/golden-expand.d.ts.map +0 -1
- package/out/tools/golden-expand.js +0 -406
- package/out/tools/golden-expand.js.map +0 -1
- package/out/tools/golden-promote.d.ts +0 -72
- package/out/tools/golden-promote.d.ts.map +0 -1
- package/out/tools/golden-promote.js +0 -240
- package/out/tools/golden-promote.js.map +0 -1
- package/out/tools/golden-relabel-street.d.ts +0 -196
- package/out/tools/golden-relabel-street.d.ts.map +0 -1
- package/out/tools/golden-relabel-street.js +0 -439
- package/out/tools/golden-relabel-street.js.map +0 -1
- package/out/tools/index.d.ts +0 -28
- package/out/tools/index.d.ts.map +0 -1
- package/out/tools/index.js +0 -28
- package/out/tools/index.js.map +0 -1
- package/out/tools/lint-slice-vocab.d.ts +0 -90
- package/out/tools/lint-slice-vocab.d.ts.map +0 -1
- package/out/tools/lint-slice-vocab.js +0 -267
- package/out/tools/lint-slice-vocab.js.map +0 -1
- package/out/tools/lint-slice.d.ts +0 -93
- package/out/tools/lint-slice.d.ts.map +0 -1
- package/out/tools/lint-slice.js +0 -322
- package/out/tools/lint-slice.js.map +0 -1
- package/out/tools/overlay-manifest.d.ts +0 -39
- package/out/tools/overlay-manifest.d.ts.map +0 -1
- package/out/tools/overlay-manifest.js +0 -90
- package/out/tools/overlay-manifest.js.map +0 -1
- package/out/tools/slice-kryptonite.d.ts +0 -32
- package/out/tools/slice-kryptonite.d.ts.map +0 -1
- package/out/tools/slice-kryptonite.js +0 -99
- package/out/tools/slice-kryptonite.js.map +0 -1
- package/out/tools/slice-translit.d.ts +0 -51
- package/out/tools/slice-translit.d.ts.map +0 -1
- package/out/tools/slice-translit.js +0 -166
- package/out/tools/slice-translit.js.map +0 -1
- package/out/tools/sub-venue/harvest.d.ts +0 -100
- package/out/tools/sub-venue/harvest.d.ts.map +0 -1
- package/out/tools/sub-venue/harvest.js +0 -168
- package/out/tools/sub-venue/harvest.js.map +0 -1
- package/out/tools/sub-venue/head-nouns.d.ts +0 -50
- package/out/tools/sub-venue/head-nouns.d.ts.map +0 -1
- package/out/tools/sub-venue/head-nouns.js +0 -213
- package/out/tools/sub-venue/head-nouns.js.map +0 -1
- package/out/tools/sub-venue/surfaces.d.ts +0 -45
- package/out/tools/sub-venue/surfaces.d.ts.map +0 -1
- package/out/tools/sub-venue/surfaces.js +0 -77
- package/out/tools/sub-venue/surfaces.js.map +0 -1
- package/out/tools/sub-venue/table.d.ts +0 -229
- package/out/tools/sub-venue/table.d.ts.map +0 -1
- package/out/tools/sub-venue/table.js +0 -108
- package/out/tools/sub-venue/table.js.map +0 -1
- package/out/tools/sub-venue/wikidata.d.ts +0 -26
- package/out/tools/sub-venue/wikidata.d.ts.map +0 -1
- package/out/tools/sub-venue/wikidata.js +0 -62
- package/out/tools/sub-venue/wikidata.js.map +0 -1
- package/out/tools/sub-venue-lexicon.d.ts +0 -156
- package/out/tools/sub-venue-lexicon.d.ts.map +0 -1
- package/out/tools/sub-venue-lexicon.js +0 -283
- package/out/tools/sub-venue-lexicon.js.map +0 -1
- package/out/tools/sub-venue-promotions.d.ts +0 -94
- package/out/tools/sub-venue-promotions.d.ts.map +0 -1
- package/out/tools/sub-venue-promotions.js +0 -266
- package/out/tools/sub-venue-promotions.js.map +0 -1
- package/out/utils/index.d.ts +0 -14
- package/out/utils/index.d.ts.map +0 -1
- package/out/utils/index.js +0 -14
- package/out/utils/index.js.map +0 -1
- package/out/utils/parquet.d.ts +0 -178
- package/out/utils/parquet.d.ts.map +0 -1
- package/out/utils/parquet.js +0 -371
- package/out/utils/parquet.js.map +0 -1
- package/out/utils/slice-stats.d.ts +0 -52
- package/out/utils/slice-stats.d.ts.map +0 -1
- package/out/utils/slice-stats.js +0 -58
- package/out/utils/slice-stats.js.map +0 -1
|
@@ -0,0 +1,178 @@
|
|
|
1
|
+
import { APIClient, pluckResponseData } from "@mailwoman/core/api";
|
|
2
|
+
/**
|
|
3
|
+
* @copyright Sister Software
|
|
4
|
+
* @license AGPL-3.0
|
|
5
|
+
* @author Teffen Ellis, et al.
|
|
6
|
+
*
|
|
7
|
+
* Fetch the full TIGER 2024 addrfeat dataset for all US counties from
|
|
8
|
+
* `https://www2.census.gov/geo/tiger/TIGER2024/addrfeat/`, where files use the pattern
|
|
9
|
+
* `tl_2024_<statefips><countyfips>_addrfeat.zip`.
|
|
10
|
+
*
|
|
11
|
+
* Each state's ZIPs land in `<outRoot>/tiger/addrfeat/state-<statefips>/` with a per-state
|
|
12
|
+
* `manifest.json` recording filename, sha256 and bytes so re-runs skip already-verified files.
|
|
13
|
+
* Extraction and ogr2ogr ingestion happen later, in the `tiger` adapter.
|
|
14
|
+
*/
|
|
15
|
+
/* oxlint-disable sister-software/prefer-region-over-marks -- these markers label steps inside one
|
|
16
|
+
procedure rather than sections of declarations. A region there folds no element a reader wants folded. */
|
|
17
|
+
import { BYTES_PER_KIB, ByteFormatter } from "@mailwoman/core/fs/formatters";
|
|
18
|
+
import { statPath, pathExists } from "@mailwoman/core/fs/readers";
|
|
19
|
+
import { makeDirectories, removePathIfPresent } from "@mailwoman/core/fs/writers";
|
|
20
|
+
import { sha256File } from "@mailwoman/core/hash";
|
|
21
|
+
import { isoSeconds } from "@mailwoman/core/utils";
|
|
22
|
+
import { sleep } from "@mailwoman/core/utils/sleep";
|
|
23
|
+
import { readManifest, streamDownload, writeManifest } from "#tools/fetch/download";
|
|
24
|
+
const HTTP_OK = 200;
|
|
25
|
+
const HTTP_REDIRECT = 300;
|
|
26
|
+
const TIGER_BASE_URL = "https://www2.census.gov/geo/tiger/TIGER2024/ADDRFEAT";
|
|
27
|
+
async function readCountyManifest(manifestPath) {
|
|
28
|
+
const map = new Map();
|
|
29
|
+
const parsed = await readManifest(manifestPath);
|
|
30
|
+
for (const c of parsed?.counties ?? []) {
|
|
31
|
+
if (c.filename) {
|
|
32
|
+
map.set(c.filename, { filename: c.filename, sha256: c.sha256, bytes: c.bytes });
|
|
33
|
+
}
|
|
34
|
+
}
|
|
35
|
+
return map;
|
|
36
|
+
}
|
|
37
|
+
async function fileMatchesSha(path, expectedSha, expectedBytes) {
|
|
38
|
+
if (!(await pathExists(path)))
|
|
39
|
+
return false;
|
|
40
|
+
if ((await statPath(path)).size !== expectedBytes)
|
|
41
|
+
return false;
|
|
42
|
+
return (await sha256File(path)) === expectedSha;
|
|
43
|
+
}
|
|
44
|
+
async function downloadCounty(url, dest) {
|
|
45
|
+
const filename = dest.basename();
|
|
46
|
+
const status = await streamDownload(url, dest, { timeoutMs: 600_000, retries: 3, retryDelayMs: 5000 });
|
|
47
|
+
if (status < HTTP_OK || status >= HTTP_REDIRECT) {
|
|
48
|
+
return { ok: false, filename, reason: `HTTP ${status}` };
|
|
49
|
+
}
|
|
50
|
+
const bytes = (await statPath(dest)).size;
|
|
51
|
+
if (bytes < BYTES_PER_KIB) {
|
|
52
|
+
await removePathIfPresent(dest);
|
|
53
|
+
return { ok: false, filename, reason: `too small (${bytes} bytes)` };
|
|
54
|
+
}
|
|
55
|
+
const sha256 = await sha256File(dest);
|
|
56
|
+
return { ok: true, filename, sha256, bytes };
|
|
57
|
+
}
|
|
58
|
+
export async function fetchTigerFull(options, report) {
|
|
59
|
+
const skipStateFips = (options.skipStateFips ?? "50").split(/\s+/).filter((value) => value.length);
|
|
60
|
+
const rateSleepMs = Math.round((options.rateSleep ?? 0.2) * 1000);
|
|
61
|
+
const maxParallel = options.maxParallel ?? 4;
|
|
62
|
+
const dryRun = options.dryRun ?? false;
|
|
63
|
+
const addrfeatDir = options.outRoot("tiger", "addrfeat");
|
|
64
|
+
await makeDirectories(addrfeatDir);
|
|
65
|
+
// MARK: Step 1 — discover the county file list
|
|
66
|
+
report?.(`=== Fetching TIGER 2024 ADDRFEAT directory listing...`);
|
|
67
|
+
const listingRes = await new APIClient({
|
|
68
|
+
displayName: "tiger-listing",
|
|
69
|
+
retry: true,
|
|
70
|
+
axios: { headers: { "Accept-Encoding": "gzip, br" } },
|
|
71
|
+
})
|
|
72
|
+
.fetch({ url: `${TIGER_BASE_URL}/`, responseType: "text", timeout: 60_000 })
|
|
73
|
+
.then(pluckResponseData);
|
|
74
|
+
const html = listingRes;
|
|
75
|
+
const allZips = [...new Set(html.match(/tl_2024_[0-9]{5}_addrfeat\.zip/g))].toSorted();
|
|
76
|
+
const totalCounties = allZips.length;
|
|
77
|
+
report?.(` Found ${totalCounties} county ZIPs in the TIGER 2024 ADDRFEAT index.`);
|
|
78
|
+
// `tl_2024_SSCCC_addrfeat.zip`: SS is the 2-digit state FIPS at chars 8-9.
|
|
79
|
+
const stateFiles = new Map();
|
|
80
|
+
for (const fname of allZips) {
|
|
81
|
+
const stateFips = fname.slice(8, 10);
|
|
82
|
+
const list = stateFiles.get(stateFips) ?? [];
|
|
83
|
+
list.push(fname);
|
|
84
|
+
stateFiles.set(stateFips, list);
|
|
85
|
+
}
|
|
86
|
+
report?.(` Spans ${stateFiles.size} state/territory FIPS codes.`);
|
|
87
|
+
// MARK: Step 2 — download the county ZIPs
|
|
88
|
+
let totalFetched = 0;
|
|
89
|
+
let totalSkipped = 0;
|
|
90
|
+
let totalSkippedState = 0;
|
|
91
|
+
let totalFailed = 0;
|
|
92
|
+
let totalBytesFetched = 0;
|
|
93
|
+
const failedCodes = [];
|
|
94
|
+
const sortedStates = [...stateFiles.keys()].toSorted();
|
|
95
|
+
for (const stateFips of sortedStates) {
|
|
96
|
+
const countyFiles = stateFiles.get(stateFips) ?? [];
|
|
97
|
+
if (skipStateFips.includes(stateFips)) {
|
|
98
|
+
report?.(`--- State ${stateFips} — SKIPPED (in --skip-state-fips, ${countyFiles.length} counties)`);
|
|
99
|
+
totalSkippedState += countyFiles.length;
|
|
100
|
+
continue;
|
|
101
|
+
}
|
|
102
|
+
const stateDir = addrfeatDir(`state-${stateFips}`);
|
|
103
|
+
await makeDirectories(stateDir);
|
|
104
|
+
const manifestPath = stateDir("MANIFEST.json");
|
|
105
|
+
const manifest = await readCountyManifest(manifestPath);
|
|
106
|
+
report?.(`--- State ${stateFips} — ${countyFiles.length} counties`);
|
|
107
|
+
const pending = [];
|
|
108
|
+
for (const fname of countyFiles) {
|
|
109
|
+
const dest = stateDir(fname);
|
|
110
|
+
const url = `${TIGER_BASE_URL}/${fname}`;
|
|
111
|
+
const known = manifest.get(fname);
|
|
112
|
+
if (known && (await fileMatchesSha(dest, known.sha256, known.bytes))) {
|
|
113
|
+
report?.(` skip (verified) ${fname}`);
|
|
114
|
+
totalSkipped++;
|
|
115
|
+
continue;
|
|
116
|
+
}
|
|
117
|
+
if (dryRun) {
|
|
118
|
+
report?.(` would fetch: ${url}`);
|
|
119
|
+
totalFetched++;
|
|
120
|
+
continue;
|
|
121
|
+
}
|
|
122
|
+
pending.push({ url, dest });
|
|
123
|
+
}
|
|
124
|
+
if (dryRun)
|
|
125
|
+
continue;
|
|
126
|
+
if (!pending.length)
|
|
127
|
+
continue;
|
|
128
|
+
const results = Array.from({ length: pending.length });
|
|
129
|
+
let cursor = 0;
|
|
130
|
+
const workers = Array.from({ length: Math.min(maxParallel, pending.length) }, async () => {
|
|
131
|
+
while (true) {
|
|
132
|
+
const i = cursor++;
|
|
133
|
+
if (i >= pending.length)
|
|
134
|
+
return;
|
|
135
|
+
const item = pending[i];
|
|
136
|
+
await sleep(rateSleepMs);
|
|
137
|
+
results[i] = await downloadCounty(item.url, item.dest);
|
|
138
|
+
}
|
|
139
|
+
});
|
|
140
|
+
await Promise.all(workers);
|
|
141
|
+
for (const result of results) {
|
|
142
|
+
if (result.ok) {
|
|
143
|
+
report?.(` ok ${result.filename} ${ByteFormatter.formatIEC(result.bytes)} sha256=${result.sha256.slice(0, 12)}...`);
|
|
144
|
+
manifest.set(result.filename, { filename: result.filename, sha256: result.sha256, bytes: result.bytes });
|
|
145
|
+
totalFetched++;
|
|
146
|
+
totalBytesFetched += result.bytes;
|
|
147
|
+
}
|
|
148
|
+
else {
|
|
149
|
+
report?.(` FAIL ${result.filename} -- ${result.reason}`);
|
|
150
|
+
totalFailed++;
|
|
151
|
+
failedCodes.push(result.filename);
|
|
152
|
+
}
|
|
153
|
+
}
|
|
154
|
+
const counties = [...manifest.values()].toSorted((a, b) => a.filename.localeCompare(b.filename));
|
|
155
|
+
const manifestDoc = {
|
|
156
|
+
state_fips: stateFips,
|
|
157
|
+
updated_at: isoSeconds(),
|
|
158
|
+
tiger_base_url: TIGER_BASE_URL,
|
|
159
|
+
counties,
|
|
160
|
+
};
|
|
161
|
+
await writeManifest(manifestPath, manifestDoc);
|
|
162
|
+
}
|
|
163
|
+
// MARK: Summary
|
|
164
|
+
report?.(`=== Summary ===`);
|
|
165
|
+
report?.(` Total counties in index : ${totalCounties}`);
|
|
166
|
+
report?.(` State(s) fully skipped : ${totalSkippedState} (--skip-state-fips "${skipStateFips.join(" ")}")`);
|
|
167
|
+
report?.(` Counties already present : ${totalSkipped}`);
|
|
168
|
+
report?.(` Counties fetched this run : ${totalFetched}`);
|
|
169
|
+
report?.(` Counties failed : ${totalFailed}`);
|
|
170
|
+
if (totalBytesFetched > 0) {
|
|
171
|
+
report?.(` Bytes fetched this run : ${ByteFormatter.formatIEC(totalBytesFetched)} (${totalBytesFetched})`);
|
|
172
|
+
}
|
|
173
|
+
if (totalFailed > 0) {
|
|
174
|
+
report?.(`WARNING: ${totalFailed} download(s) failed. Re-run to retry.`);
|
|
175
|
+
}
|
|
176
|
+
return { fetched: totalFetched, skipped: totalSkipped + totalSkippedState, failed: totalFailed, failedCodes };
|
|
177
|
+
}
|
|
178
|
+
//# sourceMappingURL=tiger-full.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"tiger-full.js","sourceRoot":"","sources":["../../../../lib/us/tools/fetch/tiger-full.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,SAAS,EAAE,iBAAiB,EAAE,MAAM,qBAAqB,CAAA;AAClE;;;;;;;;;;;;GAYG;AACH;4GAC4G;AAC5G,OAAO,EAAE,aAAa,EAAE,aAAa,EAAE,MAAM,+BAA+B,CAAA;AAC5E,OAAO,EAAE,QAAQ,EAAE,UAAU,EAAE,MAAM,4BAA4B,CAAA;AACjE,OAAO,EAAE,eAAe,EAAE,mBAAmB,EAAE,MAAM,4BAA4B,CAAA;AACjF,OAAO,EAAE,UAAU,EAAE,MAAM,sBAAsB,CAAA;AACjD,OAAO,EAAE,UAAU,EAAE,MAAM,uBAAuB,CAAA;AAClD,OAAO,EAAE,KAAK,EAAE,MAAM,6BAA6B,CAAA;AAInD,OAAO,EAAE,YAAY,EAAE,cAAc,EAAE,aAAa,EAAE,MAAM,uBAAuB,CAAA;AAEnF,MAAM,OAAO,GAAG,GAAG,CAAA;AACnB,MAAM,aAAa,GAAG,GAAG,CAAA;AAEzB,MAAM,cAAc,GAAG,sDAAsD,CAAA;AAe7E,KAAK,UAAU,kBAAkB,CAAC,YAAyB;IAC1D,MAAM,GAAG,GAAG,IAAI,GAAG,EAAuB,CAAA;IAC1C,MAAM,MAAM,GAAG,MAAM,YAAY,CAA+B,YAAY,CAAC,CAAA;IAE7E,KAAK,MAAM,CAAC,IAAI,MAAM,EAAE,QAAQ,IAAI,EAAE,EAAE,CAAC;QACxC,IAAI,CAAC,CAAC,QAAQ,EAAE,CAAC;YAChB,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,QAAQ,EAAE,EAAE,QAAQ,EAAE,CAAC,CAAC,QAAQ,EAAE,MAAM,EAAE,CAAC,CAAC,MAAM,EAAE,KAAK,EAAE,CAAC,CAAC,KAAK,EAAE,CAAC,CAAA;QAChF,CAAC;IACF,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC;AAED,KAAK,UAAU,cAAc,CAAC,IAAiB,EAAE,WAAmB,EAAE,aAAqB;IAC1F,IAAI,CAAC,CAAC,MAAM,UAAU,CAAC,IAAI,CAAC,CAAC;QAAE,OAAO,KAAK,CAAA;IAE3C,IAAI,CAAC,MAAM,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,KAAK,aAAa;QAAE,OAAO,KAAK,CAAA;IAE/D,OAAO,CAAC,MAAM,UAAU,CAAC,IAAI,CAAC,CAAC,KAAK,WAAW,CAAA;AAChD,CAAC;AAMD,KAAK,UAAU,cAAc,CAAC,GAAW,EAAE,IAAiB;IAC3D,MAAM,QAAQ,GAAG,IAAI,CAAC,QAAQ,EAAE,CAAA;IAChC,MAAM,MAAM,GAAG,MAAM,cAAc,CAAC,GAAG,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,YAAY,EAAE,IAAI,EAAE,CAAC,CAAA;IAEtG,IAAI,MAAM,GAAG,OAAO,IAAI,MAAM,IAAI,aAAa,EAAE,CAAC;QACjD,OAAO,EAAE,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,MAAM,EAAE,QAAQ,MAAM,EAAE,EAAE,CAAA;IACzD,CAAC;IAED,MAAM,KAAK,GAAG,CAAC,MAAM,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,CAAA;IAEzC,IAAI,KAAK,GAAG,aAAa,EAAE,CAAC;QAC3B,MAAM,mBAAmB,CAAC,IAAI,CAAC,CAAA;QAE/B,OAAO,EAAE,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,MAAM,EAAE,cAAc,KAAK,SAAS,EAAE,CAAA;IACrE,CAAC;IAED,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,IAAI,CAAC,CAAA;IAErC,OAAO,EAAE,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,MAAM,EAAE,KAAK,EAAE,CAAA;AAC7C,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,cAAc,CACnC,OAA8B,EAC9B,MAA+B;IAE/B,MAAM,aAAa,GAAG,CAAC,OAAO,CAAC,aAAa,IAAI,IAAI,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,MAAM,CAAC,CAAA;IAClG,MAAM,WAAW,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,OAAO,CAAC,SAAS,IAAI,GAAG,CAAC,GAAG,IAAI,CAAC,CAAA;IACjE,MAAM,WAAW,GAAG,OAAO,CAAC,WAAW,IAAI,CAAC,CAAA;IAC5C,MAAM,MAAM,GAAG,OAAO,CAAC,MAAM,IAAI,KAAK,CAAA;IAEtC,MAAM,WAAW,GAAG,OAAO,CAAC,OAAO,CAAC,OAAO,EAAE,UAAU,CAAC,CAAA;IACxD,MAAM,eAAe,CAAC,WAAW,CAAC,CAAA;IAElC,+CAA+C;IAE/C,MAAM,EAAE,CAAC,uDAAuD,CAAC,CAAA;IAEjE,MAAM,UAAU,GAAG,MAAM,IAAI,SAAS,CAAC;QACtC,WAAW,EAAE,eAAe;QAC5B,KAAK,EAAE,IAAI;QACX,KAAK,EAAE,EAAE,OAAO,EAAE,EAAE,iBAAiB,EAAE,UAAU,EAAE,EAAE;KACrD,CAAC;SACA,KAAK,CAAS,EAAE,GAAG,EAAE,GAAG,cAAc,GAAG,EAAE,YAAY,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC;SACnF,IAAI,CAAC,iBAAiB,CAAC,CAAA;IAEzB,MAAM,IAAI,GAAG,UAAU,CAAA;IACvB,MAAM,OAAO,GAAG,CAAC,GAAG,IAAI,GAAG,CAAC,IAAI,CAAC,KAAK,CAAC,iCAAiC,CAAC,CAAC,CAAC,CAAC,QAAQ,EAAE,CAAA;IACtF,MAAM,aAAa,GAAG,OAAO,CAAC,MAAM,CAAA;IACpC,MAAM,EAAE,CAAC,WAAW,aAAa,gDAAgD,CAAC,CAAA;IAElF,2EAA2E;IAC3E,MAAM,UAAU,GAAG,IAAI,GAAG,EAAoB,CAAA;IAE9C,KAAK,MAAM,KAAK,IAAI,OAAO,EAAE,CAAC;QAC7B,MAAM,SAAS,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,EAAE,CAAC,CAAA;QACpC,MAAM,IAAI,GAAG,UAAU,CAAC,GAAG,CAAC,SAAS,CAAC,IAAI,EAAE,CAAA;QAC5C,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;QAChB,UAAU,CAAC,GAAG,CAAC,SAAS,EAAE,IAAI,CAAC,CAAA;IAChC,CAAC;IAED,MAAM,EAAE,CAAC,WAAW,UAAU,CAAC,IAAI,8BAA8B,CAAC,CAAA;IAElE,0CAA0C;IAE1C,IAAI,YAAY,GAAG,CAAC,CAAA;IACpB,IAAI,YAAY,GAAG,CAAC,CAAA;IACpB,IAAI,iBAAiB,GAAG,CAAC,CAAA;IACzB,IAAI,WAAW,GAAG,CAAC,CAAA;IACnB,IAAI,iBAAiB,GAAG,CAAC,CAAA;IACzB,MAAM,WAAW,GAAa,EAAE,CAAA;IAEhC,MAAM,YAAY,GAAG,CAAC,GAAG,UAAU,CAAC,IAAI,EAAE,CAAC,CAAC,QAAQ,EAAE,CAAA;IAEtD,KAAK,MAAM,SAAS,IAAI,YAAY,EAAE,CAAC;QACtC,MAAM,WAAW,GAAG,UAAU,CAAC,GAAG,CAAC,SAAS,CAAC,IAAI,EAAE,CAAA;QAEnD,IAAI,aAAa,CAAC,QAAQ,CAAC,SAAS,CAAC,EAAE,CAAC;YACvC,MAAM,EAAE,CAAC,aAAa,SAAS,qCAAqC,WAAW,CAAC,MAAM,YAAY,CAAC,CAAA;YACnG,iBAAiB,IAAI,WAAW,CAAC,MAAM,CAAA;YAEvC,SAAQ;QACT,CAAC;QAED,MAAM,QAAQ,GAAG,WAAW,CAAC,SAAS,SAAS,EAAE,CAAC,CAAA;QAClD,MAAM,eAAe,CAAC,QAAQ,CAAC,CAAA;QAC/B,MAAM,YAAY,GAAG,QAAQ,CAAC,eAAe,CAAC,CAAA;QAE9C,MAAM,QAAQ,GAAG,MAAM,kBAAkB,CAAC,YAAY,CAAC,CAAA;QAEvD,MAAM,EAAE,CAAC,aAAa,SAAS,MAAM,WAAW,CAAC,MAAM,WAAW,CAAC,CAAA;QAEnE,MAAM,OAAO,GAA8C,EAAE,CAAA;QAE7D,KAAK,MAAM,KAAK,IAAI,WAAW,EAAE,CAAC;YACjC,MAAM,IAAI,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAA;YAC5B,MAAM,GAAG,GAAG,GAAG,cAAc,IAAI,KAAK,EAAE,CAAA;YACxC,MAAM,KAAK,GAAG,QAAQ,CAAC,GAAG,CAAC,KAAK,CAAC,CAAA;YAEjC,IAAI,KAAK,IAAI,CAAC,MAAM,cAAc,CAAC,IAAI,EAAE,KAAK,CAAC,MAAM,EAAE,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC;gBACtE,MAAM,EAAE,CAAC,qBAAqB,KAAK,EAAE,CAAC,CAAA;gBAEtC,YAAY,EAAE,CAAA;gBAEd,SAAQ;YACT,CAAC;YAED,IAAI,MAAM,EAAE,CAAC;gBACZ,MAAM,EAAE,CAAC,kBAAkB,GAAG,EAAE,CAAC,CAAA;gBAEjC,YAAY,EAAE,CAAA;gBAEd,SAAQ;YACT,CAAC;YAED,OAAO,CAAC,IAAI,CAAC,EAAE,GAAG,EAAE,IAAI,EAAE,CAAC,CAAA;QAC5B,CAAC;QAED,IAAI,MAAM;YAAE,SAAQ;QAEpB,IAAI,CAAC,OAAO,CAAC,MAAM;YAAE,SAAQ;QAE7B,MAAM,OAAO,GAAmB,KAAK,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,OAAO,CAAC,MAAM,EAAE,CAAC,CAAA;QACtE,IAAI,MAAM,GAAG,CAAC,CAAA;QAEd,MAAM,OAAO,GAAG,KAAK,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,IAAI,CAAC,GAAG,CAAC,WAAW,EAAE,OAAO,CAAC,MAAM,CAAC,EAAE,EAAE,KAAK,IAAI,EAAE;YACxF,OAAO,IAAI,EAAE,CAAC;gBACb,MAAM,CAAC,GAAG,MAAM,EAAE,CAAA;gBAElB,IAAI,CAAC,IAAI,OAAO,CAAC,MAAM;oBAAE,OAAM;gBAC/B,MAAM,IAAI,GAAG,OAAO,CAAC,CAAC,CAAE,CAAA;gBACxB,MAAM,KAAK,CAAC,WAAW,CAAC,CAAA;gBACxB,OAAO,CAAC,CAAC,CAAC,GAAG,MAAM,cAAc,CAAC,IAAI,CAAC,GAAG,EAAE,IAAI,CAAC,IAAI,CAAC,CAAA;YACvD,CAAC;QACF,CAAC,CAAC,CAAA;QAEF,MAAM,OAAO,CAAC,GAAG,CAAC,OAAO,CAAC,CAAA;QAE1B,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;YAC9B,IAAI,MAAM,CAAC,EAAE,EAAE,CAAC;gBACf,MAAM,EAAE,CACP,QAAQ,MAAM,CAAC,QAAQ,KAAK,aAAa,CAAC,SAAS,CAAC,MAAM,CAAC,KAAK,CAAC,YAAY,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,EAAE,CAAC,KAAK,CAC5G,CAAA;gBAED,QAAQ,CAAC,GAAG,CAAC,MAAM,CAAC,QAAQ,EAAE,EAAE,QAAQ,EAAE,MAAM,CAAC,QAAQ,EAAE,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,KAAK,EAAE,MAAM,CAAC,KAAK,EAAE,CAAC,CAAA;gBAExG,YAAY,EAAE,CAAA;gBACd,iBAAiB,IAAI,MAAM,CAAC,KAAK,CAAA;YAClC,CAAC;iBAAM,CAAC;gBACP,MAAM,EAAE,CAAC,UAAU,MAAM,CAAC,QAAQ,OAAO,MAAM,CAAC,MAAM,EAAE,CAAC,CAAA;gBAEzD,WAAW,EAAE,CAAA;gBACb,WAAW,CAAC,IAAI,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAA;YAClC,CAAC;QACF,CAAC;QAED,MAAM,QAAQ,GAAG,CAAC,GAAG,QAAQ,CAAC,MAAM,EAAE,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,CAAC,aAAa,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAA;QAEhG,MAAM,WAAW,GAAG;YACnB,UAAU,EAAE,SAAS;YACrB,UAAU,EAAE,UAAU,EAAE;YACxB,cAAc,EAAE,cAAc;YAC9B,QAAQ;SACR,CAAA;QAED,MAAM,aAAa,CAAC,YAAY,EAAE,WAAW,CAAC,CAAA;IAC/C,CAAC;IAED,gBAAgB;IAEhB,MAAM,EAAE,CAAC,iBAAiB,CAAC,CAAA;IAC3B,MAAM,EAAE,CAAC,iCAAiC,aAAa,EAAE,CAAC,CAAA;IAC1D,MAAM,EAAE,CAAC,iCAAiC,iBAAiB,wBAAwB,aAAa,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;IAC/G,MAAM,EAAE,CAAC,iCAAiC,YAAY,EAAE,CAAC,CAAA;IACzD,MAAM,EAAE,CAAC,iCAAiC,YAAY,EAAE,CAAC,CAAA;IACzD,MAAM,EAAE,CAAC,iCAAiC,WAAW,EAAE,CAAC,CAAA;IAExD,IAAI,iBAAiB,GAAG,CAAC,EAAE,CAAC;QAC3B,MAAM,EAAE,CAAC,iCAAiC,aAAa,CAAC,SAAS,CAAC,iBAAiB,CAAC,KAAK,iBAAiB,GAAG,CAAC,CAAA;IAC/G,CAAC;IAED,IAAI,WAAW,GAAG,CAAC,EAAE,CAAC;QACrB,MAAM,EAAE,CAAC,YAAY,WAAW,uCAAuC,CAAC,CAAA;IACzE,CAAC;IAED,OAAO,EAAE,OAAO,EAAE,YAAY,EAAE,OAAO,EAAE,YAAY,GAAG,iBAAiB,EAAE,MAAM,EAAE,WAAW,EAAE,WAAW,EAAE,CAAA;AAC9G,CAAC"}
|
package/out/utils/align.d.ts
CHANGED
|
@@ -19,20 +19,19 @@
|
|
|
19
19
|
* character range. First token in a component span → `B-<tag>`; subsequent tokens →
|
|
20
20
|
* `I-<tag>`; no overlap → `O`.
|
|
21
21
|
* 5. Emit the located char spans verbatim as `span_starts[]` / `span_ends[]` / `span_tags[]` (the
|
|
22
|
-
* v0.5.0 char-offset format
|
|
23
|
-
* rebuild deletes; during the transition both representations ride on every labeled row.
|
|
22
|
+
* v0.5.0 char-offset format).
|
|
24
23
|
*
|
|
25
24
|
* Structural invariants the function preserves (the span ones loudly — a violation throws rather
|
|
26
|
-
* than quarantines, because it indicates a bug here
|
|
25
|
+
* than quarantines, because it indicates a bug here rather than bad source data):
|
|
27
26
|
*
|
|
28
27
|
* - `tokens.length === labels.length` always.
|
|
29
28
|
* - Each component contributes at most one contiguous BIO run (no `B-tag … O … I-tag` gaps). This is
|
|
30
29
|
* enforced by greedy first-match span assignment + ordered token iteration.
|
|
31
30
|
* - The span triple is sorted ascending by start and non-overlapping.
|
|
32
|
-
* - `raw` is NFC-normalized (asserted per row
|
|
31
|
+
* - `raw` is NFC-normalized (asserted per row. a non-NFC raw makes char offsets ambiguous downstream
|
|
33
32
|
* — NFD `é` occupies two code units where NFC `é` occupies one — and silently so).
|
|
34
33
|
*/
|
|
35
|
-
import type { ComponentTag } from "@mailwoman/
|
|
34
|
+
import type { ComponentTag } from "@mailwoman/codex/component";
|
|
36
35
|
import type { CanonicalRow, LabeledRow, QuarantinedRow } from "#types";
|
|
37
36
|
import { type Tokenizer } from "#utils/tokenize";
|
|
38
37
|
/**
|
|
@@ -40,20 +39,27 @@ import { type Tokenizer } from "#utils/tokenize";
|
|
|
40
39
|
*/
|
|
41
40
|
export interface AlignOptions {
|
|
42
41
|
/**
|
|
43
|
-
* Tokenizer to use.
|
|
42
|
+
* Tokenizer to use.
|
|
43
|
+
*
|
|
44
|
+
* Defaults to `whitespaceTokenizer()`.
|
|
44
45
|
*/
|
|
45
46
|
tokenizer?: Tokenizer;
|
|
46
47
|
/**
|
|
47
|
-
* Max Levenshtein edit distance to accept when a verbatim substring match fails.
|
|
48
|
-
*
|
|
48
|
+
* Max Levenshtein edit distance to accept when a verbatim substring match fails.
|
|
49
|
+
*
|
|
50
|
+
* Set `0` to require verbatim matches only.
|
|
51
|
+
* Default `2`.
|
|
49
52
|
*
|
|
50
|
-
* Distance is computed against same-length windows in `raw`, so the threshold
|
|
51
|
-
* value length.
|
|
53
|
+
* Distance is computed against same-length windows in `raw`, so the threshold
|
|
54
|
+
* scales naturally with the component value length.
|
|
52
55
|
*/
|
|
53
56
|
maxEditDistance?: number;
|
|
54
57
|
/**
|
|
55
|
-
* Case-insensitive comparison for substring search.
|
|
56
|
-
*
|
|
58
|
+
* Case-insensitive comparison for substring search.
|
|
59
|
+
*
|
|
60
|
+
* Default `true`.
|
|
61
|
+
* The retained span in `raw` is the original case.
|
|
62
|
+
* Only matching is case-insensitive.
|
|
57
63
|
*/
|
|
58
64
|
caseInsensitive?: boolean;
|
|
59
65
|
}
|
|
@@ -68,8 +74,7 @@ export type AlignmentResult = {
|
|
|
68
74
|
row: QuarantinedRow;
|
|
69
75
|
};
|
|
70
76
|
/**
|
|
71
|
-
* One located char-offset label span over a row's `raw` ([start, end) in UTF-16 code units). The element type behind
|
|
72
|
-
* the parallel `span_starts[]`/`span_ends[]`/`span_tags[]` triple on `LabeledRow` (#519).
|
|
77
|
+
* One located char-offset label span over a row's `raw` ([start, end) in UTF-16 code units). The element type behind the parallel `span_starts[]`/`span_ends[]`/`span_tags[]` triple on `LabeledRow`.
|
|
73
78
|
*/
|
|
74
79
|
export interface ComponentSpan {
|
|
75
80
|
tag: ComponentTag;
|
|
@@ -81,13 +86,13 @@ export interface ComponentSpan {
|
|
|
81
86
|
*/
|
|
82
87
|
export declare function alignRow(row: CanonicalRow, opts?: AlignOptions): AlignmentResult;
|
|
83
88
|
/**
|
|
84
|
-
* Enforce the
|
|
89
|
+
* Enforce the span-triple invariants: in-bounds, sorted ascending by start, non-overlapping.
|
|
90
|
+
*
|
|
91
|
+
* For `alignRow`: `claimed`-span bookkeeping in `locateSpan` already makes overlap impossible
|
|
92
|
+
* and the caller sorts, so a violation here is a bug in this file rather than bad source data.
|
|
93
|
+
* Throw rather than quarantine, so the corruption cannot ride into a corpus.
|
|
85
94
|
*
|
|
86
|
-
*
|
|
87
|
-
* a violation here is a bug in this file, not bad source data: throw (naming the row) rather than quarantine, so the
|
|
88
|
-
* corruption can't ride into a corpus. Exported for every OTHER span producer (`composeAdversarialRow`'s offset
|
|
89
|
-
* arithmetic, future synthesis paths) — any code that emits the triple without going through `alignRow` must pass its
|
|
90
|
-
* output through this.
|
|
95
|
+
* Any code that emits the triple without going through `alignRow` must pass its output through this.
|
|
91
96
|
*/
|
|
92
97
|
export declare function assertSpanInvariants(spans: readonly ComponentSpan[], row: Pick<CanonicalRow, "raw" | "source" | "source_id">): void;
|
|
93
98
|
//# sourceMappingURL=align.d.ts.map
|
package/out/utils/align.d.ts.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"align.d.ts","sourceRoot":"","sources":["../../lib/utils/align.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"align.d.ts","sourceRoot":"","sources":["../../lib/utils/align.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAgCG;AAEH,OAAO,KAAK,EAAY,YAAY,EAAE,MAAM,4BAA4B,CAAA;AAGxE,OAAO,KAAK,EAAE,YAAY,EAAE,UAAU,EAAE,cAAc,EAAE,MAAM,QAAQ,CAAA;AACtE,OAAO,EAAuC,KAAK,SAAS,EAAE,MAAM,iBAAiB,CAAA;AAErF;;GAEG;AACH,MAAM,WAAW,YAAY;IAC5B;;;;OAIG;IACH,SAAS,CAAC,EAAE,SAAS,CAAA;IAErB;;;;;;;;OAQG;IACH,eAAe,CAAC,EAAE,MAAM,CAAA;IAExB;;;;;;OAMG;IACH,eAAe,CAAC,EAAE,OAAO,CAAA;CACzB;AAED;;GAEG;AACH,MAAM,MAAM,eAAe,GAAG;IAAE,IAAI,EAAE,SAAS,CAAC;IAAC,GAAG,EAAE,UAAU,CAAA;CAAE,GAAG;IAAE,IAAI,EAAE,aAAa,CAAC;IAAC,GAAG,EAAE,cAAc,CAAA;CAAE,CAAA;AAEjH;;GAEG;AACH,MAAM,WAAW,aAAa;IAC7B,GAAG,EAAE,YAAY,CAAA;IACjB,KAAK,EAAE,MAAM,CAAA;IACb,GAAG,EAAE,MAAM,CAAA;CACX;AAED;;GAEG;AACH,wBAAgB,QAAQ,CAAC,GAAG,EAAE,YAAY,EAAE,IAAI,GAAE,YAAiB,GAAG,eAAe,CA2EpF;AAED;;;;;;;;GAQG;AACH,wBAAgB,oBAAoB,CACnC,KAAK,EAAE,SAAS,aAAa,EAAE,EAC/B,GAAG,EAAE,IAAI,CAAC,YAAY,EAAE,KAAK,GAAG,QAAQ,GAAG,WAAW,CAAC,GACrD,IAAI,CA4BN"}
|
package/out/utils/align.js
CHANGED
|
@@ -19,17 +19,16 @@
|
|
|
19
19
|
* character range. First token in a component span → `B-<tag>`; subsequent tokens →
|
|
20
20
|
* `I-<tag>`; no overlap → `O`.
|
|
21
21
|
* 5. Emit the located char spans verbatim as `span_starts[]` / `span_ends[]` / `span_tags[]` (the
|
|
22
|
-
* v0.5.0 char-offset format
|
|
23
|
-
* rebuild deletes; during the transition both representations ride on every labeled row.
|
|
22
|
+
* v0.5.0 char-offset format).
|
|
24
23
|
*
|
|
25
24
|
* Structural invariants the function preserves (the span ones loudly — a violation throws rather
|
|
26
|
-
* than quarantines, because it indicates a bug here
|
|
25
|
+
* than quarantines, because it indicates a bug here rather than bad source data):
|
|
27
26
|
*
|
|
28
27
|
* - `tokens.length === labels.length` always.
|
|
29
28
|
* - Each component contributes at most one contiguous BIO run (no `B-tag … O … I-tag` gaps). This is
|
|
30
29
|
* enforced by greedy first-match span assignment + ordered token iteration.
|
|
31
30
|
* - The span triple is sorted ascending by start and non-overlapping.
|
|
32
|
-
* - `raw` is NFC-normalized (asserted per row
|
|
31
|
+
* - `raw` is NFC-normalized (asserted per row. a non-NFC raw makes char offsets ambiguous downstream
|
|
33
32
|
* — NFD `é` occupies two code units where NFC `é` occupies one — and silently so).
|
|
34
33
|
*/
|
|
35
34
|
import { distance as levenshteinDistance } from "fastest-levenshtein";
|
|
@@ -44,10 +43,6 @@ export function alignRow(row, opts = {}) {
|
|
|
44
43
|
if (!row.raw) {
|
|
45
44
|
return { kind: "quarantined", row: { row, reason: "raw-empty" } };
|
|
46
45
|
}
|
|
47
|
-
// #519 NFC handling — relaxed from a hard throw to normalization (2026-06-12, DeepSeek-validated):
|
|
48
|
-
// one non-NFC row (e.g. a non-Latin name variant like "দক্ষিণ কোরিয়া") must not crash a multi-hour
|
|
49
|
-
// build. Normalize `raw` AND every component value to NFC, compute spans over the NFC raw, and
|
|
50
|
-
// store the NFC raw — preserving the #519 single-normalization-form principle while keeping the row.
|
|
51
46
|
const raw = row.raw.normalize("NFC");
|
|
52
47
|
const components = { ...row.components };
|
|
53
48
|
for (const key of Object.keys(components)) {
|
|
@@ -59,10 +54,9 @@ export function alignRow(row, opts = {}) {
|
|
|
59
54
|
const componentSpans = [];
|
|
60
55
|
const claimed = [];
|
|
61
56
|
const haystack = caseInsensitive ? raw.toLowerCase() : raw;
|
|
62
|
-
// Longest value first: a short component must not claim a word that a longer,
|
|
63
|
-
// component owns
|
|
64
|
-
//
|
|
65
|
-
// re-sorted by start below.
|
|
57
|
+
// Longest value first: a short component must not claim a word that a longer,
|
|
58
|
+
// more specific component owns.
|
|
59
|
+
// Emit order is unaffected, since spans are re-sorted by start below.
|
|
66
60
|
const entries = Object.entries(components).toSorted((a, b) => (b[1]?.length ?? 0) - (a[1]?.length ?? 0));
|
|
67
61
|
for (const [tag, value] of entries) {
|
|
68
62
|
if (!value)
|
|
@@ -75,12 +69,8 @@ export function alignRow(row, opts = {}) {
|
|
|
75
69
|
row: { row, reason: `component-not-found:${tag}` },
|
|
76
70
|
};
|
|
77
71
|
}
|
|
78
|
-
//
|
|
79
|
-
//
|
|
80
|
-
// yielding a span past the end. An out-of-bounds offset can never be a valid char span —
|
|
81
|
-
// quarantine the row rather than crash assertSpanInvariants and take down a multi-hour build.
|
|
82
|
-
// (If this class proves large in the quarantine report, locateSpan's boundary logic needs a
|
|
83
|
-
// combining-mark fix to KEEP these non-Latin rows.)
|
|
72
|
+
// An out-of-bounds offset can never be a valid char span, so quarantine the row
|
|
73
|
+
// rather than crash assertSpanInvariants and take down a multi-hour build.
|
|
84
74
|
if (span.start < 0 || span.end > raw.length || span.start >= span.end) {
|
|
85
75
|
return {
|
|
86
76
|
kind: "quarantined",
|
|
@@ -100,8 +90,6 @@ export function alignRow(row, opts = {}) {
|
|
|
100
90
|
components,
|
|
101
91
|
tokens: tokens.map((t) => t.text),
|
|
102
92
|
labels,
|
|
103
|
-
// The v0.5.0 char-offset triple (#519): the located spans, emitted verbatim. The token
|
|
104
|
-
// quantization above is what the rebuild deletes; both ride during the transition.
|
|
105
93
|
span_starts: componentSpans.map((s) => s.start),
|
|
106
94
|
span_ends: componentSpans.map((s) => s.end),
|
|
107
95
|
span_tags: componentSpans.map((s) => s.tag),
|
|
@@ -109,13 +97,13 @@ export function alignRow(row, opts = {}) {
|
|
|
109
97
|
return { kind: "labeled", row: labeled };
|
|
110
98
|
}
|
|
111
99
|
/**
|
|
112
|
-
* Enforce the
|
|
100
|
+
* Enforce the span-triple invariants: in-bounds, sorted ascending by start, non-overlapping.
|
|
113
101
|
*
|
|
114
|
-
* For `alignRow`: `claimed`-span bookkeeping in `locateSpan` already makes overlap impossible
|
|
115
|
-
* a violation here is a bug in this file
|
|
116
|
-
* corruption
|
|
117
|
-
*
|
|
118
|
-
* output through this.
|
|
102
|
+
* For `alignRow`: `claimed`-span bookkeeping in `locateSpan` already makes overlap impossible
|
|
103
|
+
* and the caller sorts, so a violation here is a bug in this file rather than bad source data.
|
|
104
|
+
* Throw rather than quarantine, so the corruption cannot ride into a corpus.
|
|
105
|
+
*
|
|
106
|
+
* Any code that emits the triple without going through `alignRow` must pass its output through this.
|
|
119
107
|
*/
|
|
120
108
|
export function assertSpanInvariants(spans, row) {
|
|
121
109
|
for (let i = 0; i < spans.length; i++) {
|
|
@@ -138,22 +126,23 @@ export function assertSpanInvariants(spans, row) {
|
|
|
138
126
|
}
|
|
139
127
|
}
|
|
140
128
|
/**
|
|
141
|
-
* Locate `needle` in `haystack` (both already normalized for case if requested),
|
|
142
|
-
*
|
|
143
|
-
*
|
|
129
|
+
* Locate `needle` in `haystack` (both already normalized for case if requested),
|
|
130
|
+
* preferring verbatim substring match.
|
|
131
|
+
*
|
|
132
|
+
* Falls back to a fuzzy window scan when verbatim fails and `maxEditDistance > 0`.
|
|
133
|
+
* Already-claimed spans are skipped so two components don't grab overlapping ranges.
|
|
144
134
|
*
|
|
145
|
-
*
|
|
135
|
+
* @returns The span in the original `raw` (not the lower-cased `haystack`).
|
|
146
136
|
*/
|
|
147
137
|
function locateSpan(args) {
|
|
148
138
|
const { haystack, needle, claimed, maxEditDistance } = args;
|
|
149
139
|
if (!needle.length)
|
|
150
140
|
return undefined;
|
|
151
|
-
// Pass 1: verbatim substring.
|
|
152
|
-
//
|
|
153
|
-
//
|
|
141
|
+
// Pass 1: verbatim substring.
|
|
142
|
+
// Word-boundary-aligned matches are preferred over intra-word ones, so a short
|
|
143
|
+
// value cannot claim the inside of an earlier word.
|
|
154
144
|
// Intra-word matches stay allowed as the fallback because they are essential for affix
|
|
155
|
-
// supervision (street_suffix "straße" inside "Hauptstraße" has no boundary-aligned occurrence
|
|
156
|
-
// sub-word spans are the point of the char-offset format).
|
|
145
|
+
// supervision (street_suffix "straße" inside "Hauptstraße" has no boundary-aligned occurrence).
|
|
157
146
|
let intraWord;
|
|
158
147
|
let from = 0;
|
|
159
148
|
while (true) {
|
|
@@ -172,15 +161,14 @@ function locateSpan(args) {
|
|
|
172
161
|
return intraWord;
|
|
173
162
|
if (maxEditDistance <= 0)
|
|
174
163
|
return undefined;
|
|
175
|
-
// Pass 2: fuzzy sliding-window.
|
|
176
|
-
// across haystack, compute Levenshtein, pick the leftmost window under the threshold.
|
|
164
|
+
// Pass 2: fuzzy sliding-window.
|
|
177
165
|
const len = needle.length;
|
|
178
166
|
for (let i = 0; i + len <= haystack.length; i++) {
|
|
179
167
|
if (overlapsClaimed(i, i + len, claimed))
|
|
180
168
|
continue;
|
|
181
169
|
const window = haystack.slice(i, i + len);
|
|
182
170
|
if (window === needle)
|
|
183
|
-
return { start: i, end: i + len };
|
|
171
|
+
return { start: i, end: i + len };
|
|
184
172
|
const d = levenshteinDistance(window, needle);
|
|
185
173
|
if (d <= maxEditDistance)
|
|
186
174
|
return { start: i, end: i + len };
|
|
@@ -204,14 +192,11 @@ function overlapsClaimed(start, end, claimed) {
|
|
|
204
192
|
return false;
|
|
205
193
|
}
|
|
206
194
|
/**
|
|
207
|
-
* Assign BIO labels to tokens
|
|
208
|
-
* find the first component span that contains the token's start offset; if the token is the first one inside that span
|
|
209
|
-
* emit `B-<tag>`, else `I-<tag>`.
|
|
195
|
+
* Assign BIO labels to tokens from component spans sorted by start offset.
|
|
210
196
|
*/
|
|
211
197
|
function labelTokens(tokens, spans) {
|
|
212
198
|
const out = [];
|
|
213
199
|
const seenSpan = new Set();
|
|
214
|
-
// index into `spans`
|
|
215
200
|
for (const token of tokens) {
|
|
216
201
|
let assigned = "O";
|
|
217
202
|
for (let i = 0; i < spans.length; i++) {
|
package/out/utils/align.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"align.js","sourceRoot":"","sources":["../../lib/utils/align.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"align.js","sourceRoot":"","sources":["../../lib/utils/align.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAgCG;AAGH,OAAO,EAAE,QAAQ,IAAI,mBAAmB,EAAE,MAAM,qBAAqB,CAAA;AAGrE,OAAO,EAAE,mBAAmB,EAAkC,MAAM,iBAAiB,CAAA;AAgDrF;;GAEG;AACH,MAAM,UAAU,QAAQ,CAAC,GAAiB,EAAE,IAAI,GAAiB,EAAE;IAClE,MAAM,SAAS,GAAG,IAAI,CAAC,SAAS,IAAI,mBAAmB,EAAE,CAAA;IACzD,MAAM,eAAe,GAAG,IAAI,CAAC,eAAe,IAAI,CAAC,CAAA;IACjD,MAAM,eAAe,GAAG,IAAI,CAAC,eAAe,IAAI,IAAI,CAAA;IAEpD,IAAI,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC;QACd,OAAO,EAAE,IAAI,EAAE,aAAa,EAAE,GAAG,EAAE,EAAE,GAAG,EAAE,MAAM,EAAE,WAAW,EAAE,EAAE,CAAA;IAClE,CAAC;IAED,MAAM,GAAG,GAAG,GAAG,CAAC,GAAG,CAAC,SAAS,CAAC,KAAK,CAAC,CAAA;IACpC,MAAM,UAAU,GAAG,EAAE,GAAG,GAAG,CAAC,UAAU,EAAE,CAAA;IAExC,KAAK,MAAM,GAAG,IAAI,MAAM,CAAC,IAAI,CAAC,UAAU,CAAC,EAAE,CAAC;QAC3C,MAAM,CAAC,GAAG,UAAU,CAAC,GAA8B,CAAC,CAAA;QAEpD,IAAI,OAAO,CAAC,KAAK,QAAQ,EAAE,CAAC;YAC3B,UAAU,CAAC,GAA8B,CAAC,GAAG,CAAC,CAAC,SAAS,CAAC,KAAK,CAAC,CAAA;QAChE,CAAC;IACF,CAAC;IAED,MAAM,cAAc,GAAoB,EAAE,CAAA;IAC1C,MAAM,OAAO,GAA4B,EAAE,CAAA;IAE3C,MAAM,QAAQ,GAAG,eAAe,CAAC,CAAC,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,GAAG,CAAA;IAE1D,8EAA8E;IAC9E,gCAAgC;IAChC,sEAAsE;IACtE,MAAM,OAAO,GAAI,MAAM,CAAC,OAAO,CAAC,UAAU,CAA+C,CAAC,QAAQ,CACjG,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,MAAM,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,MAAM,IAAI,CAAC,CAAC,CACnD,CAAA;IAED,KAAK,MAAM,CAAC,GAAG,EAAE,KAAK,CAAC,IAAI,OAAO,EAAE,CAAC;QACpC,IAAI,CAAC,KAAK;YAAE,SAAQ;QAEpB,MAAM,MAAM,GAAG,eAAe,CAAC,CAAC,CAAC,KAAK,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,KAAK,CAAA;QAC5D,MAAM,IAAI,GAAG,UAAU,CAAC,EAAE,QAAQ,EAAE,MAAM,EAAE,GAAG,EAAE,OAAO,EAAE,eAAe,EAAE,CAAC,CAAA;QAE5E,IAAI,CAAC,IAAI,EAAE,CAAC;YACX,OAAO;gBACN,IAAI,EAAE,aAAa;gBACnB,GAAG,EAAE,EAAE,GAAG,EAAE,MAAM,EAAE,uBAAuB,GAAG,EAAE,EAAE;aAClD,CAAA;QACF,CAAC;QAED,gFAAgF;QAChF,2EAA2E;QAC3E,IAAI,IAAI,CAAC,KAAK,GAAG,CAAC,IAAI,IAAI,CAAC,GAAG,GAAG,GAAG,CAAC,MAAM,IAAI,IAAI,CAAC,KAAK,IAAI,IAAI,CAAC,GAAG,EAAE,CAAC;YACvE,OAAO;gBACN,IAAI,EAAE,aAAa;gBACnB,GAAG,EAAE,EAAE,GAAG,EAAE,MAAM,EAAE,sBAAsB,GAAG,EAAE,EAAE;aACjD,CAAA;QACF,CAAC;QAED,cAAc,CAAC,IAAI,CAAC,EAAE,GAAG,EAAE,KAAK,EAAE,IAAI,CAAC,KAAK,EAAE,GAAG,EAAE,IAAI,CAAC,GAAG,EAAE,CAAC,CAAA;QAC9D,OAAO,CAAC,IAAI,CAAC,CAAC,IAAI,CAAC,KAAK,EAAE,IAAI,CAAC,GAAG,CAAC,CAAC,CAAA;IACrC,CAAC;IAED,cAAc,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,KAAK,CAAC,CAAA;IAChD,oBAAoB,CAAC,cAAc,EAAE,EAAE,GAAG,GAAG,EAAE,GAAG,EAAE,CAAC,CAAA;IACrD,MAAM,MAAM,GAAG,SAAS,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAA;IACtC,MAAM,MAAM,GAAG,WAAW,CAAC,MAAM,EAAE,cAAc,CAAC,CAAA;IAElD,MAAM,OAAO,GAAe;QAC3B,GAAG,GAAG;QACN,GAAG;QACH,UAAU;QACV,MAAM,EAAE,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC;QACjC,MAAM;QACN,WAAW,EAAE,cAAc,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,KAAK,CAAC;QAC/C,SAAS,EAAE,cAAc,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC;QAC3C,SAAS,EAAE,cAAc,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC;KAC3C,CAAA;IAED,OAAO,EAAE,IAAI,EAAE,SAAS,EAAE,GAAG,EAAE,OAAO,EAAE,CAAA;AACzC,CAAC;AAED;;;;;;;;GAQG;AACH,MAAM,UAAU,oBAAoB,CACnC,KAA+B,EAC/B,GAAuD;IAEvD,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QACvC,MAAM,CAAC,GAAG,KAAK,CAAC,CAAC,CAAE,CAAA;QAEnB,IAAI,CAAC,CAAC,CAAC,CAAC,KAAK,IAAI,CAAC,IAAI,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,GAAG,IAAI,CAAC,CAAC,GAAG,IAAI,GAAG,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC;YACnE,MAAM,IAAI,KAAK,CACd,wCAAwC,GAAG,CAAC,MAAM,eAAe,GAAG,CAAC,SAAS,KAAK;gBAClF,GAAG,CAAC,CAAC,GAAG,KAAK,CAAC,CAAC,KAAK,KAAK,CAAC,CAAC,GAAG,wBAAwB,GAAG,CAAC,GAAG,CAAC,MAAM,EAAE,CACvE,CAAA;QACF,CAAC;QAED,IAAI,CAAC,KAAK,CAAC;YAAE,SAAQ;QACrB,MAAM,IAAI,GAAG,KAAK,CAAC,CAAC,GAAG,CAAC,CAAE,CAAA;QAE1B,IAAI,CAAC,CAAC,KAAK,GAAG,IAAI,CAAC,KAAK,EAAE,CAAC;YAC1B,MAAM,IAAI,KAAK,CACd,sCAAsC,GAAG,CAAC,MAAM,eAAe,GAAG,CAAC,SAAS,KAAK;gBAChF,GAAG,IAAI,CAAC,GAAG,KAAK,IAAI,CAAC,KAAK,KAAK,IAAI,CAAC,GAAG,cAAc,CAAC,CAAC,GAAG,KAAK,CAAC,CAAC,KAAK,KAAK,CAAC,CAAC,GAAG,GAAG,CACpF,CAAA;QACF,CAAC;QAED,IAAI,CAAC,CAAC,KAAK,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC;YACxB,MAAM,IAAI,KAAK,CACd,mCAAmC,GAAG,CAAC,MAAM,eAAe,GAAG,CAAC,SAAS,KAAK;gBAC7E,GAAG,IAAI,CAAC,GAAG,KAAK,IAAI,CAAC,KAAK,KAAK,IAAI,CAAC,GAAG,cAAc,CAAC,CAAC,GAAG,KAAK,CAAC,CAAC,KAAK,KAAK,CAAC,CAAC,GAAG,GAAG,CACpF,CAAA;QACF,CAAC;IACF,CAAC;AACF,CAAC;AAED;;;;;;;;GAQG;AACH,SAAS,UAAU,CAAC,IAMnB;IACA,MAAM,EAAE,QAAQ,EAAE,MAAM,EAAE,OAAO,EAAE,eAAe,EAAE,GAAG,IAAI,CAAA;IAE3D,IAAI,CAAC,MAAM,CAAC,MAAM;QAAE,OAAO,SAAS,CAAA;IAEpC,8BAA8B;IAC9B,+EAA+E;IAC/E,oDAAoD;IACpD,uFAAuF;IACvF,gGAAgG;IAChG,IAAI,SAAqD,CAAA;IACzD,IAAI,IAAI,GAAG,CAAC,CAAA;IAEZ,OAAO,IAAI,EAAE,CAAC;QACb,MAAM,GAAG,GAAG,QAAQ,CAAC,OAAO,CAAC,MAAM,EAAE,IAAI,CAAC,CAAA;QAE1C,IAAI,GAAG,KAAK,CAAC,CAAC;YAAE,MAAK;QACrB,MAAM,GAAG,GAAG,GAAG,GAAG,MAAM,CAAC,MAAM,CAAA;QAE/B,IAAI,CAAC,eAAe,CAAC,GAAG,EAAE,GAAG,EAAE,OAAO,CAAC,EAAE,CAAC;YACzC,IAAI,iBAAiB,CAAC,QAAQ,EAAE,GAAG,EAAE,GAAG,CAAC;gBAAE,OAAO,EAAE,KAAK,EAAE,GAAG,EAAE,GAAG,EAAE,CAAA;YACrE,SAAS,KAAK,EAAE,KAAK,EAAE,GAAG,EAAE,GAAG,EAAE,CAAA;QAClC,CAAC;QAED,IAAI,GAAG,GAAG,GAAG,CAAC,CAAA;IACf,CAAC;IAED,IAAI,SAAS;QAAE,OAAO,SAAS,CAAA;IAE/B,IAAI,eAAe,IAAI,CAAC;QAAE,OAAO,SAAS,CAAA;IAE1C,gCAAgC;IAChC,MAAM,GAAG,GAAG,MAAM,CAAC,MAAM,CAAA;IAEzB,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,GAAG,IAAI,QAAQ,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QACjD,IAAI,eAAe,CAAC,CAAC,EAAE,CAAC,GAAG,GAAG,EAAE,OAAO,CAAC;YAAE,SAAQ;QAClD,MAAM,MAAM,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,GAAG,GAAG,CAAC,CAAA;QAEzC,IAAI,MAAM,KAAK,MAAM;YAAE,OAAO,EAAE,KAAK,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,GAAG,GAAG,EAAE,CAAA;QACxD,MAAM,CAAC,GAAG,mBAAmB,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;QAE7C,IAAI,CAAC,IAAI,eAAe;YAAE,OAAO,EAAE,KAAK,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,GAAG,GAAG,EAAE,CAAA;IAC5D,CAAC;IAED,OAAO,SAAS,CAAA;AACjB,CAAC;AAED,MAAM,SAAS,GAAG,eAAe,CAAA;AAEjC;;GAEG;AACH,SAAS,iBAAiB,CAAC,QAAgB,EAAE,KAAa,EAAE,GAAW;IACtE,MAAM,MAAM,GAAG,KAAK,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,IAAI,CAAC,QAAQ,CAAC,KAAK,GAAG,CAAC,CAAE,CAAC,CAAA;IACnE,MAAM,KAAK,GAAG,GAAG,KAAK,QAAQ,CAAC,MAAM,IAAI,CAAC,SAAS,CAAC,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAE,CAAC,CAAA;IAExE,OAAO,MAAM,IAAI,KAAK,CAAA;AACvB,CAAC;AAED,SAAS,eAAe,CAAC,KAAa,EAAE,GAAW,EAAE,OAAgC;IACpF,KAAK,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,OAAO,EAAE,CAAC;QAC9B,IAAI,KAAK,GAAG,CAAC,IAAI,CAAC,GAAG,GAAG;YAAE,OAAO,IAAI,CAAA;IACtC,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC;AAED;;GAEG;AACH,SAAS,WAAW,CAAC,MAA4B,EAAE,KAA+B;IACjF,MAAM,GAAG,GAAe,EAAE,CAAA;IAC1B,MAAM,QAAQ,GAAG,IAAI,GAAG,EAAU,CAAA;IAElC,KAAK,MAAM,KAAK,IAAI,MAAM,EAAE,CAAC;QAC5B,IAAI,QAAQ,GAAa,GAAG,CAAA;QAE5B,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;YACvC,MAAM,CAAC,GAAG,KAAK,CAAC,CAAC,CAAE,CAAA;YAEnB,IAAI,KAAK,CAAC,KAAK,IAAI,CAAC,CAAC,KAAK,IAAI,KAAK,CAAC,GAAG,IAAI,CAAC,CAAC,GAAG,EAAE,CAAC;gBAClD,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC;oBACtB,QAAQ,GAAG,KAAK,CAAC,CAAC,GAAG,EAAc,CAAA;oBACnC,QAAQ,CAAC,GAAG,CAAC,CAAC,CAAC,CAAA;gBAChB,CAAC;qBAAM,CAAC;oBACP,QAAQ,GAAG,KAAK,CAAC,CAAC,GAAG,EAAc,CAAA;gBACpC,CAAC;gBAED,MAAK;YACN,CAAC;QACF,CAAC;QAED,GAAG,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAA;IACnB,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC"}
|
|
@@ -0,0 +1,58 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Token/label co-occurrence accounting shared by the corpus-stats builder (`tools/corpus-stats.ts`)
|
|
7
|
+
* and the recipe-output linter (`tools/lint/recipe-output/index.ts`). The two sides must agree on the bigram key
|
|
8
|
+
* format: the linter looks its recipe output's bigrams up in the stats file's `bigrams` table. A key built with
|
|
9
|
+
* a different separator never matches — which silently blanks the bigram-collision check.
|
|
10
|
+
*/
|
|
11
|
+
/**
|
|
12
|
+
* Separator inside a bigram key (`tok1␟tok2`) and a label-bigram value (`lab1␟lab2`):
|
|
13
|
+
* U+001F unit separator, a character no address token contains.
|
|
14
|
+
*
|
|
15
|
+
* Render a key for humans with `key.split(COOCCURRENCE_KEY_SEP).join(" ")`.
|
|
16
|
+
*/
|
|
17
|
+
export declare const COOCCURRENCE_KEY_SEP = "\u001F";
|
|
18
|
+
/**
|
|
19
|
+
* Nested tally: outer key → (inner key → count).
|
|
20
|
+
*
|
|
21
|
+
* Token → label counts, or bigram key → label-bigram counts.
|
|
22
|
+
*/
|
|
23
|
+
type CooccurrenceTable = Map<string, Map<string, number>>;
|
|
24
|
+
/**
|
|
25
|
+
* The token + bigram co-occurrence tables one pass over labeled rows accumulates.
|
|
26
|
+
*/
|
|
27
|
+
export interface CooccurrenceStats {
|
|
28
|
+
tokens: CooccurrenceTable;
|
|
29
|
+
bigrams: CooccurrenceTable;
|
|
30
|
+
}
|
|
31
|
+
/**
|
|
32
|
+
* An empty pair of tables for {@link accumulateCooccurrences}.
|
|
33
|
+
*/
|
|
34
|
+
export declare function createCooccurrenceStats(): CooccurrenceStats;
|
|
35
|
+
/**
|
|
36
|
+
* Fold one row's parallel `tokens`/`labels` into the tables.
|
|
37
|
+
*
|
|
38
|
+
* The caller has already checked the arrays are the same length.
|
|
39
|
+
*/
|
|
40
|
+
export declare function accumulateCooccurrences(stats: CooccurrenceStats, tokens: readonly string[], labels: readonly string[]): void;
|
|
41
|
+
/**
|
|
42
|
+
* A parquet row projected to the two columns the co-occurrence pass reads.
|
|
43
|
+
*/
|
|
44
|
+
export interface TokenLabelRow {
|
|
45
|
+
tokens: string[];
|
|
46
|
+
labels: string[];
|
|
47
|
+
[key: string]: unknown;
|
|
48
|
+
}
|
|
49
|
+
/**
|
|
50
|
+
* Stream a parquet file's `tokens`/`labels` columns.
|
|
51
|
+
*
|
|
52
|
+
* Projected rather than read whole: parquet is columnar, so the unused columns are never touched.
|
|
53
|
+
* `limit` stops the iteration rather than filtering afterwards, so a capped
|
|
54
|
+
* run reads only the row groups it needs.
|
|
55
|
+
*/
|
|
56
|
+
export declare function streamTokenLabelRows(parquetPath: string, limit?: number): AsyncIterable<TokenLabelRow>;
|
|
57
|
+
export {};
|
|
58
|
+
//# sourceMappingURL=cooccurrence-stats.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"cooccurrence-stats.d.ts","sourceRoot":"","sources":["../../lib/utils/cooccurrence-stats.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAIH;;;;;GAKG;AACH,eAAO,MAAM,oBAAoB,WAAM,CAAA;AAEvC;;;;GAIG;AACH,KAAK,iBAAiB,GAAG,GAAG,CAAC,MAAM,EAAE,GAAG,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC,CAAA;AAEzD;;GAEG;AACH,MAAM,WAAW,iBAAiB;IACjC,MAAM,EAAE,iBAAiB,CAAA;IACzB,OAAO,EAAE,iBAAiB,CAAA;CAC1B;AAED;;GAEG;AACH,wBAAgB,uBAAuB,IAAI,iBAAiB,CAE3D;AAaD;;;;GAIG;AACH,wBAAgB,uBAAuB,CACtC,KAAK,EAAE,iBAAiB,EACxB,MAAM,EAAE,SAAS,MAAM,EAAE,EACzB,MAAM,EAAE,SAAS,MAAM,EAAE,GACvB,IAAI,CAWN;AAED;;GAEG;AACH,MAAM,WAAW,aAAa;IAC7B,MAAM,EAAE,MAAM,EAAE,CAAA;IAChB,MAAM,EAAE,MAAM,EAAE,CAAA;IAChB,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAA;CACtB;AAED;;;;;;GAMG;AACH,wBAAuB,oBAAoB,CAAC,WAAW,EAAE,MAAM,EAAE,KAAK,CAAC,EAAE,MAAM,GAAG,aAAa,CAAC,aAAa,CAAC,CAQ7G"}
|
|
@@ -0,0 +1,62 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Token/label co-occurrence accounting shared by the corpus-stats builder (`tools/corpus-stats.ts`)
|
|
7
|
+
* and the recipe-output linter (`tools/lint/recipe-output/index.ts`). The two sides must agree on the bigram key
|
|
8
|
+
* format: the linter looks its recipe output's bigrams up in the stats file's `bigrams` table. A key built with
|
|
9
|
+
* a different separator never matches — which silently blanks the bigram-collision check.
|
|
10
|
+
*/
|
|
11
|
+
import { openParquetRowStream } from "#parquet/streams";
|
|
12
|
+
/**
|
|
13
|
+
* Separator inside a bigram key (`tok1␟tok2`) and a label-bigram value (`lab1␟lab2`):
|
|
14
|
+
* U+001F unit separator, a character no address token contains.
|
|
15
|
+
*
|
|
16
|
+
* Render a key for humans with `key.split(COOCCURRENCE_KEY_SEP).join(" ")`.
|
|
17
|
+
*/
|
|
18
|
+
export const COOCCURRENCE_KEY_SEP = "";
|
|
19
|
+
/**
|
|
20
|
+
* An empty pair of tables for {@link accumulateCooccurrences}.
|
|
21
|
+
*/
|
|
22
|
+
export function createCooccurrenceStats() {
|
|
23
|
+
return { tokens: new Map(), bigrams: new Map() };
|
|
24
|
+
}
|
|
25
|
+
function bump(table, key, sub) {
|
|
26
|
+
let counter = table.get(key);
|
|
27
|
+
if (!counter) {
|
|
28
|
+
counter = new Map();
|
|
29
|
+
table.set(key, counter);
|
|
30
|
+
}
|
|
31
|
+
counter.set(sub, (counter.get(sub) ?? 0) + 1);
|
|
32
|
+
}
|
|
33
|
+
/**
|
|
34
|
+
* Fold one row's parallel `tokens`/`labels` into the tables.
|
|
35
|
+
*
|
|
36
|
+
* The caller has already checked the arrays are the same length.
|
|
37
|
+
*/
|
|
38
|
+
export function accumulateCooccurrences(stats, tokens, labels) {
|
|
39
|
+
for (let i = 0; i < tokens.length; i++) {
|
|
40
|
+
const tk = tokens[i];
|
|
41
|
+
const lb = labels[i];
|
|
42
|
+
bump(stats.tokens, tk, lb);
|
|
43
|
+
if (i + 1 < tokens.length) {
|
|
44
|
+
bump(stats.bigrams, tk + COOCCURRENCE_KEY_SEP + tokens[i + 1], lb + COOCCURRENCE_KEY_SEP + labels[i + 1]);
|
|
45
|
+
}
|
|
46
|
+
}
|
|
47
|
+
}
|
|
48
|
+
/**
|
|
49
|
+
* Stream a parquet file's `tokens`/`labels` columns.
|
|
50
|
+
*
|
|
51
|
+
* Projected rather than read whole: parquet is columnar, so the unused columns are never touched.
|
|
52
|
+
* `limit` stops the iteration rather than filtering afterwards, so a capped
|
|
53
|
+
* run reads only the row groups it needs.
|
|
54
|
+
*/
|
|
55
|
+
export async function* streamTokenLabelRows(parquetPath, limit) {
|
|
56
|
+
let emitted = 0;
|
|
57
|
+
for await (const row of openParquetRowStream(parquetPath, { columns: ["tokens", "labels"], limit })) {
|
|
58
|
+
yield row;
|
|
59
|
+
emitted++;
|
|
60
|
+
}
|
|
61
|
+
}
|
|
62
|
+
//# sourceMappingURL=cooccurrence-stats.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"cooccurrence-stats.js","sourceRoot":"","sources":["../../lib/utils/cooccurrence-stats.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAEH,OAAO,EAAE,oBAAoB,EAAE,MAAM,kBAAkB,CAAA;AAEvD;;;;;GAKG;AACH,MAAM,CAAC,MAAM,oBAAoB,GAAG,GAAG,CAAA;AAiBvC;;GAEG;AACH,MAAM,UAAU,uBAAuB;IACtC,OAAO,EAAE,MAAM,EAAE,IAAI,GAAG,EAAE,EAAE,OAAO,EAAE,IAAI,GAAG,EAAE,EAAE,CAAA;AACjD,CAAC;AAED,SAAS,IAAI,CAAC,KAAwB,EAAE,GAAW,EAAE,GAAW;IAC/D,IAAI,OAAO,GAAG,KAAK,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;IAE5B,IAAI,CAAC,OAAO,EAAE,CAAC;QACd,OAAO,GAAG,IAAI,GAAG,EAAE,CAAA;QACnB,KAAK,CAAC,GAAG,CAAC,GAAG,EAAE,OAAO,CAAC,CAAA;IACxB,CAAC;IAED,OAAO,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,OAAO,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAA;AAC9C,CAAC;AAED;;;;GAIG;AACH,MAAM,UAAU,uBAAuB,CACtC,KAAwB,EACxB,MAAyB,EACzB,MAAyB;IAEzB,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,MAAM,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QACxC,MAAM,EAAE,GAAG,MAAM,CAAC,CAAC,CAAE,CAAA;QACrB,MAAM,EAAE,GAAG,MAAM,CAAC,CAAC,CAAE,CAAA;QAErB,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,EAAE,EAAE,EAAE,CAAC,CAAA;QAE1B,IAAI,CAAC,GAAG,CAAC,GAAG,MAAM,CAAC,MAAM,EAAE,CAAC;YAC3B,IAAI,CAAC,KAAK,CAAC,OAAO,EAAE,EAAE,GAAG,oBAAoB,GAAG,MAAM,CAAC,CAAC,GAAG,CAAC,CAAE,EAAE,EAAE,GAAG,oBAAoB,GAAG,MAAM,CAAC,CAAC,GAAG,CAAC,CAAE,CAAC,CAAA;QAC5G,CAAC;IACF,CAAC;AACF,CAAC;AAWD;;;;;;GAMG;AACH,MAAM,CAAC,KAAK,SAAS,CAAC,CAAC,oBAAoB,CAAC,WAAmB,EAAE,KAAc;IAC9E,IAAI,OAAO,GAAG,CAAC,CAAA;IAEf,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,oBAAoB,CAAgB,WAAW,EAAE,EAAE,OAAO,EAAE,CAAC,QAAQ,EAAE,QAAQ,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC;QACpH,MAAM,GAAG,CAAA;QAET,OAAO,EAAE,CAAA;IACV,CAAC;AACF,CAAC"}
|