@mailwoman/corpus 9.2.0 → 9.3.0
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 +22 -22
- package/data/PROVENANCE.md +7 -7
- package/lib/adapters/ban/adapter.ts +190 -0
- package/lib/adapters/ban/street-decompose.ts +66 -0
- package/lib/adapters/fcc-bdc/adapter.ts +174 -0
- package/lib/adapters/geonames/adapter.ts +199 -0
- package/lib/adapters/geonames-postal/adapter.ts +122 -0
- package/lib/adapters/gnaf/adapter.ts +149 -0
- package/lib/adapters/gnaf/assemble.ts +225 -0
- package/lib/adapters/index.ts +153 -0
- package/lib/adapters/openaddresses/adapter.ts +251 -0
- package/lib/adapters/overture/adapter.ts +162 -0
- package/lib/adapters/state-hi-schools/adapter.ts +170 -0
- package/lib/adapters/state-hi-schools/workbook.ts +35 -0
- package/lib/adapters/synth-po-box/adapter.ts +204 -0
- package/lib/adapters/tiger/adapter.ts +252 -0
- package/lib/adapters/tiger/street-decompose.ts +83 -0
- package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +167 -0
- package/lib/adapters/usgov-imls-pls/adapter.ts +143 -0
- package/lib/adapters/usgov-irs-bmf/adapter.ts +151 -0
- package/lib/adapters/usgov-nad/adapter.ts +334 -0
- package/lib/adapters/usgov-nppes/adapter.ts +151 -0
- package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +193 -0
- package/lib/adapters/utils/index.ts +307 -0
- package/lib/adapters/wof-admin-jp/adapter.ts +214 -0
- package/lib/adapters/wof-admin-json/adapter.ts +231 -0
- package/lib/adapters/wof-json-rows.ts +129 -0
- package/lib/adapters/wof-postalcode-json/adapter.ts +176 -0
- package/lib/build.ts +378 -0
- package/lib/env.ts +50 -0
- package/lib/index.ts +13 -0
- package/lib/name-prone-us-suffixes.ts +12 -0
- package/lib/recipes/anchor-absorption.ts +101 -0
- package/lib/recipes/bare-country.ts +95 -0
- package/lib/recipes/boundary-stress.ts +100 -0
- package/lib/recipes/cn-organizational-units.ts +199 -0
- package/lib/recipes/country-balanced.ts +509 -0
- package/lib/recipes/cz-pcfirst-preposition.ts +111 -0
- package/lib/recipes/fr-admin-split.ts +242 -0
- package/lib/recipes/fr-bare-street.ts +170 -0
- package/lib/recipes/fr-fragment.ts +333 -0
- package/lib/recipes/fr-lieudit.ts +301 -0
- package/lib/recipes/fr-order.ts +245 -0
- package/lib/recipes/german.ts +359 -0
- package/lib/recipes/house-venue.ts +92 -0
- package/lib/recipes/index.ts +97 -0
- package/lib/recipes/intersection.ts +618 -0
- package/lib/recipes/locale.ts +599 -0
- package/lib/recipes/nl-postcode.ts +115 -0
- package/lib/recipes/no-fragment.ts +219 -0
- package/lib/recipes/no-street-led.ts +141 -0
- package/lib/recipes/no-street.ts +90 -0
- package/lib/recipes/po-box-cedex.ts +976 -0
- package/lib/recipes/po-box.ts +123 -0
- package/lib/recipes/reviewed-postcode-tail.ts +190 -0
- package/lib/recipes/scaffold.ts +469 -0
- package/lib/recipes/si-bare-village.ts +97 -0
- package/lib/recipes/street-affix.ts +804 -0
- package/lib/recipes/street-bare.ts +100 -0
- package/lib/recipes/street.ts +81 -0
- package/lib/recipes/sub-venue-sources.ts +877 -0
- package/lib/recipes/sub-venue.ts +997 -0
- package/lib/recipes/trailing-region.ts +183 -0
- package/lib/recipes/unit.ts +304 -0
- package/lib/runner.ts +312 -0
- package/lib/synthesizers/anchor-absorption.ts +288 -0
- package/lib/synthesizers/boundary-stress.ts +532 -0
- package/lib/synthesizers/german.ts +260 -0
- package/lib/synthesizers/house-venue.ts +308 -0
- package/lib/synthesizers/intersection.ts +233 -0
- package/lib/synthesizers/no-street.ts +327 -0
- package/lib/synthesizers/po-box.ts +323 -0
- package/lib/synthesizers/street.ts +269 -0
- package/lib/synthesizers/utils.ts +993 -0
- package/lib/test-kit/corpus-recipe.ts +86 -0
- package/lib/test-kit/index.ts +100 -0
- package/lib/tools/align-slice.ts +68 -0
- package/lib/tools/audit.ts +403 -0
- package/lib/tools/corpus-stats.ts +136 -0
- package/lib/tools/fetch/ban.ts +289 -0
- package/lib/tools/fetch/download.ts +262 -0
- package/lib/tools/fetch/geonames-dump.ts +257 -0
- package/lib/tools/fetch/geonames-postal.ts +180 -0
- package/lib/tools/fetch/hrsa.ts +59 -0
- package/lib/tools/fetch/imls-pls.ts +149 -0
- package/lib/tools/fetch/index.ts +147 -0
- package/lib/tools/fetch/nad.ts +341 -0
- package/lib/tools/fetch/nppes.ts +165 -0
- package/lib/tools/fetch/openaddresses.ts +347 -0
- package/lib/tools/fetch/ourairports.ts +170 -0
- package/lib/tools/fetch/ppd.ts +121 -0
- package/lib/tools/fetch/state-hi-schools.ts +161 -0
- package/lib/tools/fetch/state-sources.ts +146 -0
- package/lib/tools/fetch/tiger-full.ts +308 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +384 -0
- package/lib/tools/golden-expand.ts +574 -0
- package/lib/tools/golden-promote.ts +337 -0
- package/lib/tools/golden-relabel-street.ts +683 -0
- package/lib/tools/index.ts +28 -0
- package/lib/tools/ingest-csv.ts +378 -0
- package/lib/tools/jsonl-to-parquet.ts +207 -0
- package/lib/tools/lint-slice-vocab.ts +388 -0
- package/lib/tools/lint-slice.ts +496 -0
- package/lib/tools/overlay-manifest.ts +148 -0
- package/lib/tools/overture-subvenue.ts +209 -0
- package/lib/tools/postcode-triples.ts +363 -0
- package/lib/tools/slice-kryptonite.ts +137 -0
- package/lib/tools/slice-translit.ts +218 -0
- package/lib/tools/sub-venue/harvest.ts +234 -0
- package/lib/tools/sub-venue/head-nouns.ts +245 -0
- package/lib/tools/sub-venue/surfaces.ts +95 -0
- package/lib/tools/sub-venue/table.ts +281 -0
- package/lib/tools/sub-venue/wikidata.ts +85 -0
- package/lib/tools/sub-venue-lexicon.ts +429 -0
- package/lib/tools/sub-venue-promotions.ts +330 -0
- package/lib/types.ts +247 -0
- package/lib/utils/align.ts +330 -0
- package/lib/utils/golden.ts +189 -0
- package/lib/utils/index.ts +14 -0
- package/lib/utils/parquet.ts +582 -0
- package/lib/utils/slice-stats.ts +95 -0
- package/lib/utils/split.ts +279 -0
- package/lib/utils/tokenize.ts +120 -0
- package/lib/utils/wof-json.ts +247 -0
- package/out/adapters/ban/adapter.d.ts.map +1 -0
- package/out/adapters/ban/adapter.js +149 -0
- package/out/adapters/ban/adapter.js.map +1 -0
- package/out/adapters/ban/street-decompose.d.ts.map +1 -0
- package/out/adapters/ban/street-decompose.js +51 -0
- package/out/adapters/ban/street-decompose.js.map +1 -0
- package/out/adapters/fcc-bdc/adapter.d.ts.map +1 -0
- package/out/adapters/fcc-bdc/adapter.js +144 -0
- package/out/adapters/fcc-bdc/adapter.js.map +1 -0
- package/out/adapters/geonames/adapter.d.ts.map +1 -0
- package/out/adapters/geonames/adapter.js +176 -0
- package/out/adapters/geonames/adapter.js.map +1 -0
- package/out/adapters/geonames-postal/adapter.d.ts +54 -0
- package/out/adapters/geonames-postal/adapter.d.ts.map +1 -0
- package/out/adapters/geonames-postal/adapter.js +107 -0
- package/out/adapters/geonames-postal/adapter.js.map +1 -0
- package/out/adapters/gnaf/adapter.d.ts +49 -0
- package/out/adapters/gnaf/adapter.d.ts.map +1 -0
- package/out/adapters/gnaf/adapter.js +124 -0
- package/out/adapters/gnaf/adapter.js.map +1 -0
- package/out/adapters/gnaf/assemble.d.ts +65 -0
- package/out/adapters/gnaf/assemble.d.ts.map +1 -0
- package/out/adapters/gnaf/assemble.js +154 -0
- package/out/adapters/gnaf/assemble.js.map +1 -0
- package/out/adapters/index.d.ts +51 -0
- package/out/adapters/index.d.ts.map +1 -0
- package/out/adapters/index.js +95 -0
- package/out/adapters/index.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -0
- package/out/adapters/openaddresses/adapter.js +186 -0
- package/out/adapters/openaddresses/adapter.js.map +1 -0
- package/out/adapters/overture/adapter.d.ts +48 -0
- package/out/adapters/overture/adapter.d.ts.map +1 -0
- package/out/adapters/overture/adapter.js +125 -0
- package/out/adapters/overture/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/adapter.d.ts +46 -0
- package/out/adapters/state-hi-schools/adapter.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/adapter.js +145 -0
- package/out/adapters/state-hi-schools/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/workbook.d.ts +29 -0
- package/out/adapters/state-hi-schools/workbook.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/workbook.js +20 -0
- package/out/adapters/state-hi-schools/workbook.js.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
- package/out/adapters/synth-po-box/adapter.d.ts.map +1 -0
- package/out/adapters/synth-po-box/adapter.js +140 -0
- package/out/adapters/synth-po-box/adapter.js.map +1 -0
- package/out/adapters/tiger/adapter.d.ts +55 -0
- package/out/adapters/tiger/adapter.d.ts.map +1 -0
- package/out/adapters/tiger/adapter.js +201 -0
- package/out/adapters/tiger/adapter.js.map +1 -0
- package/out/adapters/tiger/street-decompose.d.ts.map +1 -0
- package/out/adapters/tiger/street-decompose.js +68 -0
- package/out/adapters/tiger/street-decompose.js.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +56 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js +132 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts +36 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.js +114 -0
- package/out/adapters/usgov-imls-pls/adapter.js.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts +37 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.js +120 -0
- package/out/adapters/usgov-irs-bmf/adapter.js.map +1 -0
- package/out/adapters/usgov-nad/adapter.d.ts +48 -0
- package/out/adapters/usgov-nad/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nad/adapter.js +249 -0
- package/out/adapters/usgov-nad/adapter.js.map +1 -0
- package/out/adapters/usgov-nppes/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nppes/adapter.js +118 -0
- package/out/adapters/usgov-nppes/adapter.js.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +154 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -0
- package/out/adapters/utils/index.d.ts +191 -0
- package/out/adapters/utils/index.d.ts.map +1 -0
- package/out/adapters/utils/index.js +206 -0
- package/out/adapters/utils/index.js.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.js +161 -0
- package/out/adapters/wof-admin-jp/adapter.js.map +1 -0
- package/out/adapters/wof-admin-json/adapter.d.ts +79 -0
- package/out/adapters/wof-admin-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-json/adapter.js +197 -0
- package/out/adapters/wof-admin-json/adapter.js.map +1 -0
- package/out/adapters/wof-json-rows.d.ts +62 -0
- package/out/adapters/wof-json-rows.d.ts.map +1 -0
- package/out/adapters/wof-json-rows.js +83 -0
- package/out/adapters/wof-json-rows.js.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts +65 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.js +151 -0
- package/out/adapters/wof-postalcode-json/adapter.js.map +1 -0
- package/out/build.d.ts +132 -0
- package/out/build.d.ts.map +1 -0
- package/out/build.js +245 -0
- package/out/build.js.map +1 -0
- package/out/codex/us-fips-state.d.ts.map +1 -0
- package/out/codex/us-fips-state.js.map +1 -0
- package/out/env.d.ts +46 -0
- package/out/env.d.ts.map +1 -0
- package/out/env.js +46 -0
- package/out/env.js.map +1 -0
- package/out/index.d.ts +13 -0
- package/out/index.d.ts.map +1 -0
- package/out/index.js +13 -0
- package/out/index.js.map +1 -0
- package/out/name-prone-us-suffixes.d.ts +12 -0
- package/out/name-prone-us-suffixes.d.ts.map +1 -0
- package/out/name-prone-us-suffixes.js +12 -0
- package/out/name-prone-us-suffixes.js.map +1 -0
- package/out/recipes/anchor-absorption.d.ts +20 -0
- package/out/recipes/anchor-absorption.d.ts.map +1 -0
- package/out/recipes/anchor-absorption.js +81 -0
- package/out/recipes/anchor-absorption.js.map +1 -0
- package/out/recipes/bare-country.d.ts +25 -0
- package/out/recipes/bare-country.d.ts.map +1 -0
- package/out/recipes/bare-country.js +87 -0
- package/out/recipes/bare-country.js.map +1 -0
- package/out/recipes/boundary-stress.d.ts +20 -0
- package/out/recipes/boundary-stress.d.ts.map +1 -0
- package/out/recipes/boundary-stress.js +83 -0
- package/out/recipes/boundary-stress.js.map +1 -0
- package/out/recipes/cn-organizational-units.d.ts +36 -0
- package/out/recipes/cn-organizational-units.d.ts.map +1 -0
- package/out/recipes/cn-organizational-units.js +159 -0
- package/out/recipes/cn-organizational-units.js.map +1 -0
- package/out/recipes/country-balanced.d.ts +32 -0
- package/out/recipes/country-balanced.d.ts.map +1 -0
- package/out/recipes/country-balanced.js +393 -0
- package/out/recipes/country-balanced.js.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts +22 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.js +100 -0
- package/out/recipes/cz-pcfirst-preposition.js.map +1 -0
- package/out/recipes/fr-admin-split.d.ts +38 -0
- package/out/recipes/fr-admin-split.d.ts.map +1 -0
- package/out/recipes/fr-admin-split.js +192 -0
- package/out/recipes/fr-admin-split.js.map +1 -0
- package/out/recipes/fr-bare-street.d.ts +28 -0
- package/out/recipes/fr-bare-street.d.ts.map +1 -0
- package/out/recipes/fr-bare-street.js +143 -0
- package/out/recipes/fr-bare-street.js.map +1 -0
- package/out/recipes/fr-fragment.d.ts +77 -0
- package/out/recipes/fr-fragment.d.ts.map +1 -0
- package/out/recipes/fr-fragment.js +276 -0
- package/out/recipes/fr-fragment.js.map +1 -0
- package/out/recipes/fr-lieudit.d.ts +32 -0
- package/out/recipes/fr-lieudit.d.ts.map +1 -0
- package/out/recipes/fr-lieudit.js +227 -0
- package/out/recipes/fr-lieudit.js.map +1 -0
- package/out/recipes/fr-order.d.ts +38 -0
- package/out/recipes/fr-order.d.ts.map +1 -0
- package/out/recipes/fr-order.js +197 -0
- package/out/recipes/fr-order.js.map +1 -0
- package/out/recipes/german.d.ts +44 -0
- package/out/recipes/german.d.ts.map +1 -0
- package/out/recipes/german.js +288 -0
- package/out/recipes/german.js.map +1 -0
- package/out/recipes/house-venue.d.ts +18 -0
- package/out/recipes/house-venue.d.ts.map +1 -0
- package/out/recipes/house-venue.js +73 -0
- package/out/recipes/house-venue.js.map +1 -0
- package/out/recipes/index.d.ts +24 -0
- package/out/recipes/index.d.ts.map +1 -0
- package/out/recipes/index.js +91 -0
- package/out/recipes/index.js.map +1 -0
- package/out/recipes/intersection.d.ts +42 -0
- package/out/recipes/intersection.d.ts.map +1 -0
- package/out/recipes/intersection.js +452 -0
- package/out/recipes/intersection.js.map +1 -0
- package/out/recipes/locale.d.ts +136 -0
- package/out/recipes/locale.d.ts.map +1 -0
- package/out/recipes/locale.js +460 -0
- package/out/recipes/locale.js.map +1 -0
- package/out/recipes/nl-postcode.d.ts +26 -0
- package/out/recipes/nl-postcode.d.ts.map +1 -0
- package/out/recipes/nl-postcode.js +102 -0
- package/out/recipes/nl-postcode.js.map +1 -0
- package/out/recipes/no-fragment.d.ts +43 -0
- package/out/recipes/no-fragment.d.ts.map +1 -0
- package/out/recipes/no-fragment.js +182 -0
- package/out/recipes/no-fragment.js.map +1 -0
- package/out/recipes/no-street-led.d.ts +24 -0
- package/out/recipes/no-street-led.d.ts.map +1 -0
- package/out/recipes/no-street-led.js +113 -0
- package/out/recipes/no-street-led.js.map +1 -0
- package/out/recipes/no-street.d.ts +18 -0
- package/out/recipes/no-street.d.ts.map +1 -0
- package/out/recipes/no-street.js +71 -0
- package/out/recipes/no-street.js.map +1 -0
- package/out/recipes/po-box-cedex.d.ts +38 -0
- package/out/recipes/po-box-cedex.d.ts.map +1 -0
- package/out/recipes/po-box-cedex.js +767 -0
- package/out/recipes/po-box-cedex.js.map +1 -0
- package/out/recipes/po-box.d.ts +17 -0
- package/out/recipes/po-box.d.ts.map +1 -0
- package/out/recipes/po-box.js +100 -0
- package/out/recipes/po-box.js.map +1 -0
- package/out/recipes/reviewed-postcode-tail.d.ts +47 -0
- package/out/recipes/reviewed-postcode-tail.d.ts.map +1 -0
- package/out/recipes/reviewed-postcode-tail.js +125 -0
- package/out/recipes/reviewed-postcode-tail.js.map +1 -0
- package/out/recipes/scaffold.d.ts +324 -0
- package/out/recipes/scaffold.d.ts.map +1 -0
- package/out/recipes/scaffold.js +186 -0
- package/out/recipes/scaffold.js.map +1 -0
- package/out/recipes/si-bare-village.d.ts +32 -0
- package/out/recipes/si-bare-village.d.ts.map +1 -0
- package/out/recipes/si-bare-village.js +88 -0
- package/out/recipes/si-bare-village.js.map +1 -0
- package/out/recipes/street-affix.d.ts +89 -0
- package/out/recipes/street-affix.d.ts.map +1 -0
- package/out/recipes/street-affix.js +563 -0
- package/out/recipes/street-affix.js.map +1 -0
- package/out/recipes/street-bare.d.ts +25 -0
- package/out/recipes/street-bare.d.ts.map +1 -0
- package/out/recipes/street-bare.js +86 -0
- package/out/recipes/street-bare.js.map +1 -0
- package/out/recipes/street.d.ts +15 -0
- package/out/recipes/street.d.ts.map +1 -0
- package/out/recipes/street.js +69 -0
- package/out/recipes/street.js.map +1 -0
- package/out/recipes/sub-venue-sources.d.ts +229 -0
- package/out/recipes/sub-venue-sources.d.ts.map +1 -0
- package/out/recipes/sub-venue-sources.js +653 -0
- package/out/recipes/sub-venue-sources.js.map +1 -0
- package/out/recipes/sub-venue.d.ts +269 -0
- package/out/recipes/sub-venue.d.ts.map +1 -0
- package/out/recipes/sub-venue.js +725 -0
- package/out/recipes/sub-venue.js.map +1 -0
- package/out/recipes/trailing-region.d.ts +74 -0
- package/out/recipes/trailing-region.d.ts.map +1 -0
- package/out/recipes/trailing-region.js +157 -0
- package/out/recipes/trailing-region.js.map +1 -0
- package/out/recipes/unit.d.ts +29 -0
- package/out/recipes/unit.d.ts.map +1 -0
- package/out/recipes/unit.js +230 -0
- package/out/recipes/unit.js.map +1 -0
- package/out/runner.d.ts +130 -0
- package/out/runner.d.ts.map +1 -0
- package/out/runner.js +185 -0
- package/out/runner.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +63 -0
- package/out/synthesizers/anchor-absorption.d.ts.map +1 -0
- package/out/synthesizers/anchor-absorption.js +221 -0
- package/out/synthesizers/anchor-absorption.js.map +1 -0
- package/out/synthesizers/boundary-stress.d.ts +78 -0
- package/out/synthesizers/boundary-stress.d.ts.map +1 -0
- package/out/synthesizers/boundary-stress.js +455 -0
- package/out/synthesizers/boundary-stress.js.map +1 -0
- package/out/synthesizers/german.d.ts +115 -0
- package/out/synthesizers/german.d.ts.map +1 -0
- package/out/synthesizers/german.js +149 -0
- package/out/synthesizers/german.js.map +1 -0
- package/out/synthesizers/house-venue.d.ts +56 -0
- package/out/synthesizers/house-venue.d.ts.map +1 -0
- package/out/synthesizers/house-venue.js +247 -0
- package/out/synthesizers/house-venue.js.map +1 -0
- package/out/synthesizers/intersection.d.ts +52 -0
- package/out/synthesizers/intersection.d.ts.map +1 -0
- package/out/synthesizers/intersection.js +175 -0
- package/out/synthesizers/intersection.js.map +1 -0
- package/out/synthesizers/no-street.d.ts +72 -0
- package/out/synthesizers/no-street.d.ts.map +1 -0
- package/out/synthesizers/no-street.js +262 -0
- package/out/synthesizers/no-street.js.map +1 -0
- package/out/synthesizers/po-box.d.ts +108 -0
- package/out/synthesizers/po-box.d.ts.map +1 -0
- package/out/synthesizers/po-box.js +250 -0
- package/out/synthesizers/po-box.js.map +1 -0
- package/out/synthesizers/street.d.ts +54 -0
- package/out/synthesizers/street.d.ts.map +1 -0
- package/out/synthesizers/street.js +218 -0
- package/out/synthesizers/street.js.map +1 -0
- package/out/synthesizers/utils.d.ts +241 -0
- package/out/synthesizers/utils.d.ts.map +1 -0
- package/out/synthesizers/utils.js +776 -0
- package/out/synthesizers/utils.js.map +1 -0
- package/out/test-kit/corpus-recipe.d.ts +59 -0
- package/out/test-kit/corpus-recipe.d.ts.map +1 -0
- package/out/test-kit/corpus-recipe.js +39 -0
- package/out/test-kit/corpus-recipe.js.map +1 -0
- package/out/test-kit/index.d.ts +48 -0
- package/out/test-kit/index.d.ts.map +1 -0
- package/out/test-kit/index.js +78 -0
- package/out/test-kit/index.js.map +1 -0
- package/out/tools/align-slice.d.ts +7 -0
- package/out/tools/align-slice.d.ts.map +1 -0
- package/out/tools/align-slice.js +55 -0
- package/out/tools/align-slice.js.map +1 -0
- package/out/tools/audit.d.ts +29 -0
- package/out/tools/audit.d.ts.map +1 -0
- package/out/tools/audit.js +282 -0
- package/out/tools/audit.js.map +1 -0
- package/out/tools/corpus-stats.d.ts +44 -0
- package/out/tools/corpus-stats.d.ts.map +1 -0
- package/out/tools/corpus-stats.js +102 -0
- package/out/tools/corpus-stats.js.map +1 -0
- package/out/tools/fetch/ban.d.ts +31 -0
- package/out/tools/fetch/ban.d.ts.map +1 -0
- package/out/tools/fetch/ban.js +239 -0
- package/out/tools/fetch/ban.js.map +1 -0
- package/out/tools/fetch/download.d.ts +117 -0
- package/out/tools/fetch/download.d.ts.map +1 -0
- package/out/tools/fetch/download.js +160 -0
- package/out/tools/fetch/download.js.map +1 -0
- package/out/tools/fetch/geonames-dump.d.ts +91 -0
- package/out/tools/fetch/geonames-dump.d.ts.map +1 -0
- package/out/tools/fetch/geonames-dump.js +171 -0
- package/out/tools/fetch/geonames-dump.js.map +1 -0
- package/out/tools/fetch/geonames-postal.d.ts +76 -0
- package/out/tools/fetch/geonames-postal.d.ts.map +1 -0
- package/out/tools/fetch/geonames-postal.js +126 -0
- package/out/tools/fetch/geonames-postal.js.map +1 -0
- package/out/tools/fetch/hrsa.d.ts +18 -0
- package/out/tools/fetch/hrsa.d.ts.map +1 -0
- package/out/tools/fetch/hrsa.js +46 -0
- package/out/tools/fetch/hrsa.js.map +1 -0
- package/out/tools/fetch/imls-pls.d.ts +25 -0
- package/out/tools/fetch/imls-pls.d.ts.map +1 -0
- package/out/tools/fetch/imls-pls.js +108 -0
- package/out/tools/fetch/imls-pls.js.map +1 -0
- package/out/tools/fetch/index.d.ts +144 -0
- package/out/tools/fetch/index.d.ts.map +1 -0
- package/out/tools/fetch/index.js +143 -0
- package/out/tools/fetch/index.js.map +1 -0
- package/out/tools/fetch/nad.d.ts +70 -0
- package/out/tools/fetch/nad.d.ts.map +1 -0
- package/out/tools/fetch/nad.js +234 -0
- package/out/tools/fetch/nad.js.map +1 -0
- package/out/tools/fetch/nppes.d.ts +26 -0
- package/out/tools/fetch/nppes.d.ts.map +1 -0
- package/out/tools/fetch/nppes.js +126 -0
- package/out/tools/fetch/nppes.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +9 -0
- package/out/tools/fetch/openaddresses.d.ts.map +1 -0
- package/out/tools/fetch/openaddresses.js +279 -0
- package/out/tools/fetch/openaddresses.js.map +1 -0
- package/out/tools/fetch/ourairports.d.ts +45 -0
- package/out/tools/fetch/ourairports.d.ts.map +1 -0
- package/out/tools/fetch/ourairports.js +128 -0
- package/out/tools/fetch/ourairports.js.map +1 -0
- package/out/tools/fetch/ppd.d.ts.map +1 -0
- package/out/tools/fetch/ppd.js +85 -0
- package/out/tools/fetch/ppd.js.map +1 -0
- package/out/tools/fetch/state-hi-schools.d.ts +26 -0
- package/out/tools/fetch/state-hi-schools.d.ts.map +1 -0
- package/out/tools/fetch/state-hi-schools.js +112 -0
- package/out/tools/fetch/state-hi-schools.js.map +1 -0
- package/out/tools/fetch/state-sources.d.ts +26 -0
- package/out/tools/fetch/state-sources.d.ts.map +1 -0
- package/out/tools/fetch/state-sources.js +111 -0
- package/out/tools/fetch/state-sources.js.map +1 -0
- package/out/tools/fetch/tiger-full.d.ts +22 -0
- package/out/tools/fetch/tiger-full.d.ts.map +1 -0
- package/out/tools/fetch/tiger-full.js +217 -0
- package/out/tools/fetch/tiger-full.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +171 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.js +274 -0
- package/out/tools/fetch/wikidata-subvenue.js.map +1 -0
- package/out/tools/gb-title-case.d.ts.map +1 -0
- package/out/tools/gb-title-case.js.map +1 -0
- package/out/tools/golden-expand.d.ts +90 -0
- package/out/tools/golden-expand.d.ts.map +1 -0
- package/out/tools/golden-expand.js +406 -0
- package/out/tools/golden-expand.js.map +1 -0
- package/out/tools/golden-promote.d.ts.map +1 -0
- package/out/tools/golden-promote.js +240 -0
- package/out/tools/golden-promote.js.map +1 -0
- package/out/tools/golden-relabel-street.d.ts +196 -0
- package/out/tools/golden-relabel-street.d.ts.map +1 -0
- package/out/tools/golden-relabel-street.js +440 -0
- package/out/tools/golden-relabel-street.js.map +1 -0
- package/out/tools/index.d.ts +28 -0
- package/out/tools/index.d.ts.map +1 -0
- package/out/tools/index.js +28 -0
- package/out/tools/index.js.map +1 -0
- package/out/tools/ingest-csv.d.ts.map +1 -0
- package/out/tools/ingest-csv.js +265 -0
- package/out/tools/ingest-csv.js.map +1 -0
- package/out/tools/jsonl-to-parquet.d.ts +61 -0
- package/out/tools/jsonl-to-parquet.d.ts.map +1 -0
- package/out/tools/jsonl-to-parquet.js +150 -0
- package/out/tools/jsonl-to-parquet.js.map +1 -0
- package/out/tools/lint-slice-vocab.d.ts +90 -0
- package/out/tools/lint-slice-vocab.d.ts.map +1 -0
- package/out/tools/lint-slice-vocab.js +267 -0
- package/out/tools/lint-slice-vocab.js.map +1 -0
- package/out/tools/lint-slice.d.ts +93 -0
- package/out/tools/lint-slice.d.ts.map +1 -0
- package/out/tools/lint-slice.js +322 -0
- package/out/tools/lint-slice.js.map +1 -0
- package/out/tools/overlay-manifest.d.ts +39 -0
- package/out/tools/overlay-manifest.d.ts.map +1 -0
- package/out/tools/overlay-manifest.js +90 -0
- package/out/tools/overlay-manifest.js.map +1 -0
- package/out/tools/overture-subvenue.d.ts +112 -0
- package/out/tools/overture-subvenue.d.ts.map +1 -0
- package/out/tools/overture-subvenue.js +139 -0
- package/out/tools/overture-subvenue.js.map +1 -0
- package/out/tools/postcode-triples.d.ts +174 -0
- package/out/tools/postcode-triples.d.ts.map +1 -0
- package/out/tools/postcode-triples.js +292 -0
- package/out/tools/postcode-triples.js.map +1 -0
- package/out/tools/slice-kryptonite.d.ts +32 -0
- package/out/tools/slice-kryptonite.d.ts.map +1 -0
- package/out/tools/slice-kryptonite.js +99 -0
- package/out/tools/slice-kryptonite.js.map +1 -0
- package/out/tools/slice-translit.d.ts +51 -0
- package/out/tools/slice-translit.d.ts.map +1 -0
- package/out/tools/slice-translit.js +166 -0
- package/out/tools/slice-translit.js.map +1 -0
- package/out/tools/sub-venue/harvest.d.ts +100 -0
- package/out/tools/sub-venue/harvest.d.ts.map +1 -0
- package/out/tools/sub-venue/harvest.js +168 -0
- package/out/tools/sub-venue/harvest.js.map +1 -0
- package/out/tools/sub-venue/head-nouns.d.ts +50 -0
- package/out/tools/sub-venue/head-nouns.d.ts.map +1 -0
- package/out/tools/sub-venue/head-nouns.js +213 -0
- package/out/tools/sub-venue/head-nouns.js.map +1 -0
- package/out/tools/sub-venue/surfaces.d.ts +45 -0
- package/out/tools/sub-venue/surfaces.d.ts.map +1 -0
- package/out/tools/sub-venue/surfaces.js +77 -0
- package/out/tools/sub-venue/surfaces.js.map +1 -0
- package/out/tools/sub-venue/table.d.ts +229 -0
- package/out/tools/sub-venue/table.d.ts.map +1 -0
- package/out/tools/sub-venue/table.js +108 -0
- package/out/tools/sub-venue/table.js.map +1 -0
- package/out/tools/sub-venue/wikidata.d.ts +26 -0
- package/out/tools/sub-venue/wikidata.d.ts.map +1 -0
- package/out/tools/sub-venue/wikidata.js +62 -0
- package/out/tools/sub-venue/wikidata.js.map +1 -0
- package/out/tools/sub-venue-lexicon.d.ts +156 -0
- package/out/tools/sub-venue-lexicon.d.ts.map +1 -0
- package/out/tools/sub-venue-lexicon.js +283 -0
- package/out/tools/sub-venue-lexicon.js.map +1 -0
- package/out/tools/sub-venue-promotions.d.ts +94 -0
- package/out/tools/sub-venue-promotions.d.ts.map +1 -0
- package/out/tools/sub-venue-promotions.js +266 -0
- package/out/tools/sub-venue-promotions.js.map +1 -0
- package/out/types.d.ts +221 -0
- package/out/types.d.ts.map +1 -0
- package/out/types.js.map +1 -0
- package/out/utils/align.d.ts +93 -0
- package/out/utils/align.d.ts.map +1 -0
- package/out/utils/align.js +234 -0
- package/out/utils/align.js.map +1 -0
- package/out/utils/golden.d.ts +85 -0
- package/out/utils/golden.d.ts.map +1 -0
- package/out/utils/golden.js +127 -0
- package/out/utils/golden.js.map +1 -0
- package/out/utils/index.d.ts +14 -0
- package/out/utils/index.d.ts.map +1 -0
- package/out/utils/index.js +14 -0
- package/out/utils/index.js.map +1 -0
- package/out/utils/license.d.ts.map +1 -0
- package/out/utils/license.js.map +1 -0
- package/out/utils/parquet.d.ts +178 -0
- package/out/utils/parquet.d.ts.map +1 -0
- package/out/utils/parquet.js +371 -0
- package/out/utils/parquet.js.map +1 -0
- package/out/utils/slice-stats.d.ts +52 -0
- package/out/utils/slice-stats.d.ts.map +1 -0
- package/out/utils/slice-stats.js +58 -0
- package/out/utils/slice-stats.js.map +1 -0
- package/out/utils/split.d.ts +128 -0
- package/out/utils/split.d.ts.map +1 -0
- package/out/utils/split.js +204 -0
- package/out/utils/split.js.map +1 -0
- package/out/utils/tokenize.d.ts +64 -0
- package/out/utils/tokenize.d.ts.map +1 -0
- package/out/utils/tokenize.js +82 -0
- package/out/utils/tokenize.js.map +1 -0
- package/out/utils/wof-json.d.ts +113 -0
- package/out/utils/wof-json.d.ts.map +1 -0
- package/out/utils/wof-json.js +173 -0
- package/out/utils/wof-json.js.map +1 -0
- package/package.json +259 -194
- package/out/src/adapters/ban/adapter.d.ts.map +0 -1
- package/out/src/adapters/ban/adapter.js +0 -149
- package/out/src/adapters/ban/adapter.js.map +0 -1
- package/out/src/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/ban/street-decompose.js +0 -75
- package/out/src/adapters/ban/street-decompose.js.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.d.ts.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.js +0 -144
- package/out/src/adapters/fcc-bdc/adapter.js.map +0 -1
- package/out/src/adapters/geonames/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames/adapter.js +0 -176
- package/out/src/adapters/geonames/adapter.js.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.d.ts +0 -41
- package/out/src/adapters/geonames-postal/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.js +0 -104
- package/out/src/adapters/geonames-postal/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/adapter.d.ts +0 -49
- package/out/src/adapters/gnaf/adapter.d.ts.map +0 -1
- package/out/src/adapters/gnaf/adapter.js +0 -124
- package/out/src/adapters/gnaf/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/assemble.d.ts +0 -65
- package/out/src/adapters/gnaf/assemble.d.ts.map +0 -1
- package/out/src/adapters/gnaf/assemble.js +0 -154
- package/out/src/adapters/gnaf/assemble.js.map +0 -1
- package/out/src/adapters/index.d.ts +0 -51
- package/out/src/adapters/index.d.ts.map +0 -1
- package/out/src/adapters/index.js +0 -95
- package/out/src/adapters/index.js.map +0 -1
- package/out/src/adapters/openaddresses/adapter.d.ts.map +0 -1
- package/out/src/adapters/openaddresses/adapter.js +0 -186
- package/out/src/adapters/openaddresses/adapter.js.map +0 -1
- package/out/src/adapters/overture/adapter.d.ts +0 -48
- package/out/src/adapters/overture/adapter.d.ts.map +0 -1
- package/out/src/adapters/overture/adapter.js +0 -125
- package/out/src/adapters/overture/adapter.js.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.d.ts +0 -47
- package/out/src/adapters/state-hi-schools/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.js +0 -133
- package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.d.ts.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.js +0 -140
- package/out/src/adapters/synth-po-box/adapter.js.map +0 -1
- package/out/src/adapters/tiger/adapter.d.ts +0 -55
- package/out/src/adapters/tiger/adapter.d.ts.map +0 -1
- package/out/src/adapters/tiger/adapter.js +0 -201
- package/out/src/adapters/tiger/adapter.js.map +0 -1
- package/out/src/adapters/tiger/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/tiger/street-decompose.js +0 -90
- package/out/src/adapters/tiger/street-decompose.js.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -47
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +0 -139
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts +0 -36
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.js +0 -114
- package/out/src/adapters/usgov-imls-pls/adapter.js.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.js +0 -124
- package/out/src/adapters/usgov-irs-bmf/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.d.ts +0 -48
- package/out/src/adapters/usgov-nad/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.js +0 -252
- package/out/src/adapters/usgov-nad/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.js +0 -116
- package/out/src/adapters/usgov-nppes/adapter.js.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -156
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
- package/out/src/adapters/utils/index.d.ts +0 -150
- package/out/src/adapters/utils/index.d.ts.map +0 -1
- package/out/src/adapters/utils/index.js +0 -159
- package/out/src/adapters/utils/index.js.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.js +0 -164
- package/out/src/adapters/wof-admin-jp/adapter.js.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.d.ts +0 -82
- package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.js +0 -224
- package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
- package/out/src/adapters/wof-json-rows.d.ts +0 -32
- package/out/src/adapters/wof-json-rows.d.ts.map +0 -1
- package/out/src/adapters/wof-json-rows.js +0 -45
- package/out/src/adapters/wof-json-rows.js.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -65
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.js +0 -160
- package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
- package/out/src/build.d.ts +0 -132
- package/out/src/build.d.ts.map +0 -1
- package/out/src/build.js +0 -251
- package/out/src/build.js.map +0 -1
- package/out/src/codex/us-fips-state.d.ts.map +0 -1
- package/out/src/codex/us-fips-state.js.map +0 -1
- package/out/src/index.d.ts +0 -14
- package/out/src/index.d.ts.map +0 -1
- package/out/src/index.js +0 -14
- package/out/src/index.js.map +0 -1
- package/out/src/name-prone-us-suffixes.d.ts +0 -12
- package/out/src/name-prone-us-suffixes.d.ts.map +0 -1
- package/out/src/name-prone-us-suffixes.js +0 -12
- package/out/src/name-prone-us-suffixes.js.map +0 -1
- package/out/src/parquet-wrapper/index.d.ts +0 -9
- package/out/src/parquet-wrapper/index.d.ts.map +0 -1
- package/out/src/parquet-wrapper/index.js +0 -9
- package/out/src/parquet-wrapper/index.js.map +0 -1
- package/out/src/parquet-wrapper/reader.d.ts +0 -34
- package/out/src/parquet-wrapper/reader.d.ts.map +0 -1
- package/out/src/parquet-wrapper/reader.js +0 -69
- package/out/src/parquet-wrapper/reader.js.map +0 -1
- package/out/src/parquet-wrapper/schema.d.ts +0 -49
- package/out/src/parquet-wrapper/schema.d.ts.map +0 -1
- package/out/src/parquet-wrapper/schema.js +0 -55
- package/out/src/parquet-wrapper/schema.js.map +0 -1
- package/out/src/parquet-wrapper/writer.d.ts +0 -46
- package/out/src/parquet-wrapper/writer.d.ts.map +0 -1
- package/out/src/parquet-wrapper/writer.js +0 -76
- package/out/src/parquet-wrapper/writer.js.map +0 -1
- package/out/src/runner.d.ts +0 -126
- package/out/src/runner.d.ts.map +0 -1
- package/out/src/runner.js +0 -189
- package/out/src/runner.js.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.d.ts +0 -20
- package/out/src/shard-recipes/anchor-absorption.d.ts.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.js +0 -82
- package/out/src/shard-recipes/anchor-absorption.js.map +0 -1
- package/out/src/shard-recipes/bare-country.d.ts +0 -25
- package/out/src/shard-recipes/bare-country.d.ts.map +0 -1
- package/out/src/shard-recipes/bare-country.js +0 -87
- package/out/src/shard-recipes/bare-country.js.map +0 -1
- package/out/src/shard-recipes/boundary-stress.d.ts +0 -20
- package/out/src/shard-recipes/boundary-stress.d.ts.map +0 -1
- package/out/src/shard-recipes/boundary-stress.js +0 -83
- package/out/src/shard-recipes/boundary-stress.js.map +0 -1
- package/out/src/shard-recipes/country-balanced.d.ts +0 -32
- package/out/src/shard-recipes/country-balanced.d.ts.map +0 -1
- package/out/src/shard-recipes/country-balanced.js +0 -406
- package/out/src/shard-recipes/country-balanced.js.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts +0 -22
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.js +0 -100
- package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.d.ts +0 -38
- package/out/src/shard-recipes/fr-admin-split.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.js +0 -188
- package/out/src/shard-recipes/fr-admin-split.js.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.d.ts +0 -28
- package/out/src/shard-recipes/fr-bare-street.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.js +0 -143
- package/out/src/shard-recipes/fr-bare-street.js.map +0 -1
- package/out/src/shard-recipes/fr-fragment.d.ts +0 -77
- package/out/src/shard-recipes/fr-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-fragment.js +0 -276
- package/out/src/shard-recipes/fr-fragment.js.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.d.ts +0 -32
- package/out/src/shard-recipes/fr-lieudit.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.js +0 -226
- package/out/src/shard-recipes/fr-lieudit.js.map +0 -1
- package/out/src/shard-recipes/fr-order.d.ts +0 -38
- package/out/src/shard-recipes/fr-order.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-order.js +0 -208
- package/out/src/shard-recipes/fr-order.js.map +0 -1
- package/out/src/shard-recipes/german.d.ts +0 -23
- package/out/src/shard-recipes/german.d.ts.map +0 -1
- package/out/src/shard-recipes/german.js +0 -132
- package/out/src/shard-recipes/german.js.map +0 -1
- package/out/src/shard-recipes/house-venue.d.ts +0 -18
- package/out/src/shard-recipes/house-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/house-venue.js +0 -74
- package/out/src/shard-recipes/house-venue.js.map +0 -1
- package/out/src/shard-recipes/index.d.ts +0 -24
- package/out/src/shard-recipes/index.d.ts.map +0 -1
- package/out/src/shard-recipes/index.js +0 -89
- package/out/src/shard-recipes/index.js.map +0 -1
- package/out/src/shard-recipes/intersection.d.ts +0 -42
- package/out/src/shard-recipes/intersection.d.ts.map +0 -1
- package/out/src/shard-recipes/intersection.js +0 -460
- package/out/src/shard-recipes/intersection.js.map +0 -1
- package/out/src/shard-recipes/locale.d.ts +0 -135
- package/out/src/shard-recipes/locale.d.ts.map +0 -1
- package/out/src/shard-recipes/locale.js +0 -459
- package/out/src/shard-recipes/locale.js.map +0 -1
- package/out/src/shard-recipes/nl-postcode.d.ts +0 -26
- package/out/src/shard-recipes/nl-postcode.d.ts.map +0 -1
- package/out/src/shard-recipes/nl-postcode.js +0 -102
- package/out/src/shard-recipes/nl-postcode.js.map +0 -1
- package/out/src/shard-recipes/no-fragment.d.ts +0 -43
- package/out/src/shard-recipes/no-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/no-fragment.js +0 -188
- package/out/src/shard-recipes/no-fragment.js.map +0 -1
- package/out/src/shard-recipes/no-street-led.d.ts +0 -24
- package/out/src/shard-recipes/no-street-led.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street-led.js +0 -121
- package/out/src/shard-recipes/no-street-led.js.map +0 -1
- package/out/src/shard-recipes/no-street.d.ts +0 -18
- package/out/src/shard-recipes/no-street.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street.js +0 -72
- package/out/src/shard-recipes/no-street.js.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.d.ts +0 -38
- package/out/src/shard-recipes/po-box-cedex.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.js +0 -726
- package/out/src/shard-recipes/po-box-cedex.js.map +0 -1
- package/out/src/shard-recipes/po-box.d.ts +0 -17
- package/out/src/shard-recipes/po-box.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box.js +0 -101
- package/out/src/shard-recipes/po-box.js.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts +0 -47
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.js +0 -125
- package/out/src/shard-recipes/reviewed-postcode-tail.js.map +0 -1
- package/out/src/shard-recipes/scaffold.d.ts +0 -246
- package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
- package/out/src/shard-recipes/scaffold.js +0 -137
- package/out/src/shard-recipes/scaffold.js.map +0 -1
- package/out/src/shard-recipes/si-bare-village.d.ts +0 -32
- package/out/src/shard-recipes/si-bare-village.d.ts.map +0 -1
- package/out/src/shard-recipes/si-bare-village.js +0 -88
- package/out/src/shard-recipes/si-bare-village.js.map +0 -1
- package/out/src/shard-recipes/street-affix.d.ts +0 -89
- package/out/src/shard-recipes/street-affix.d.ts.map +0 -1
- package/out/src/shard-recipes/street-affix.js +0 -578
- package/out/src/shard-recipes/street-affix.js.map +0 -1
- package/out/src/shard-recipes/street-bare.d.ts +0 -25
- package/out/src/shard-recipes/street-bare.d.ts.map +0 -1
- package/out/src/shard-recipes/street-bare.js +0 -86
- package/out/src/shard-recipes/street-bare.js.map +0 -1
- package/out/src/shard-recipes/street.d.ts +0 -15
- package/out/src/shard-recipes/street.d.ts.map +0 -1
- package/out/src/shard-recipes/street.js +0 -69
- package/out/src/shard-recipes/street.js.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.d.ts +0 -228
- package/out/src/shard-recipes/sub-venue-sources.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.js +0 -664
- package/out/src/shard-recipes/sub-venue-sources.js.map +0 -1
- package/out/src/shard-recipes/sub-venue.d.ts +0 -269
- package/out/src/shard-recipes/sub-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue.js +0 -710
- package/out/src/shard-recipes/sub-venue.js.map +0 -1
- package/out/src/shard-recipes/trailing-region.d.ts +0 -74
- package/out/src/shard-recipes/trailing-region.d.ts.map +0 -1
- package/out/src/shard-recipes/trailing-region.js +0 -157
- package/out/src/shard-recipes/trailing-region.js.map +0 -1
- package/out/src/shard-recipes/unit.d.ts +0 -29
- package/out/src/shard-recipes/unit.d.ts.map +0 -1
- package/out/src/shard-recipes/unit.js +0 -243
- package/out/src/shard-recipes/unit.js.map +0 -1
- package/out/src/synthesizers/anchor-absorption.d.ts +0 -63
- package/out/src/synthesizers/anchor-absorption.d.ts.map +0 -1
- package/out/src/synthesizers/anchor-absorption.js +0 -223
- package/out/src/synthesizers/anchor-absorption.js.map +0 -1
- package/out/src/synthesizers/boundary-stress.d.ts +0 -78
- package/out/src/synthesizers/boundary-stress.d.ts.map +0 -1
- package/out/src/synthesizers/boundary-stress.js +0 -455
- package/out/src/synthesizers/boundary-stress.js.map +0 -1
- package/out/src/synthesizers/german.d.ts +0 -107
- package/out/src/synthesizers/german.d.ts.map +0 -1
- package/out/src/synthesizers/german.js +0 -148
- package/out/src/synthesizers/german.js.map +0 -1
- package/out/src/synthesizers/house-venue.d.ts +0 -56
- package/out/src/synthesizers/house-venue.d.ts.map +0 -1
- package/out/src/synthesizers/house-venue.js +0 -267
- package/out/src/synthesizers/house-venue.js.map +0 -1
- package/out/src/synthesizers/intersection.d.ts +0 -52
- package/out/src/synthesizers/intersection.d.ts.map +0 -1
- package/out/src/synthesizers/intersection.js +0 -175
- package/out/src/synthesizers/intersection.js.map +0 -1
- package/out/src/synthesizers/no-street.d.ts +0 -72
- package/out/src/synthesizers/no-street.d.ts.map +0 -1
- package/out/src/synthesizers/no-street.js +0 -282
- package/out/src/synthesizers/no-street.js.map +0 -1
- package/out/src/synthesizers/po-box.d.ts +0 -104
- package/out/src/synthesizers/po-box.d.ts.map +0 -1
- package/out/src/synthesizers/po-box.js +0 -266
- package/out/src/synthesizers/po-box.js.map +0 -1
- package/out/src/synthesizers/street.d.ts +0 -54
- package/out/src/synthesizers/street.d.ts.map +0 -1
- package/out/src/synthesizers/street.js +0 -221
- package/out/src/synthesizers/street.js.map +0 -1
- package/out/src/synthesizers/utils.d.ts +0 -203
- package/out/src/synthesizers/utils.d.ts.map +0 -1
- package/out/src/synthesizers/utils.js +0 -708
- package/out/src/synthesizers/utils.js.map +0 -1
- package/out/src/tools/align-shard.d.ts +0 -8
- package/out/src/tools/align-shard.d.ts.map +0 -1
- package/out/src/tools/align-shard.js +0 -56
- package/out/src/tools/align-shard.js.map +0 -1
- package/out/src/tools/audit.d.ts +0 -28
- package/out/src/tools/audit.d.ts.map +0 -1
- package/out/src/tools/audit.js +0 -285
- package/out/src/tools/audit.js.map +0 -1
- package/out/src/tools/corpus-stats.d.ts +0 -44
- package/out/src/tools/corpus-stats.d.ts.map +0 -1
- package/out/src/tools/corpus-stats.js +0 -138
- package/out/src/tools/corpus-stats.js.map +0 -1
- package/out/src/tools/fetch/ban.d.ts +0 -31
- package/out/src/tools/fetch/ban.d.ts.map +0 -1
- package/out/src/tools/fetch/ban.js +0 -239
- package/out/src/tools/fetch/ban.js.map +0 -1
- package/out/src/tools/fetch/download.d.ts +0 -78
- package/out/src/tools/fetch/download.d.ts.map +0 -1
- package/out/src/tools/fetch/download.js +0 -116
- package/out/src/tools/fetch/download.js.map +0 -1
- package/out/src/tools/fetch/geonames-dump.d.ts +0 -87
- package/out/src/tools/fetch/geonames-dump.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-dump.js +0 -178
- package/out/src/tools/fetch/geonames-dump.js.map +0 -1
- package/out/src/tools/fetch/geonames-postal.d.ts +0 -76
- package/out/src/tools/fetch/geonames-postal.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-postal.js +0 -125
- package/out/src/tools/fetch/geonames-postal.js.map +0 -1
- package/out/src/tools/fetch/hrsa.d.ts +0 -18
- package/out/src/tools/fetch/hrsa.d.ts.map +0 -1
- package/out/src/tools/fetch/hrsa.js +0 -46
- package/out/src/tools/fetch/hrsa.js.map +0 -1
- package/out/src/tools/fetch/imls-pls.d.ts +0 -25
- package/out/src/tools/fetch/imls-pls.d.ts.map +0 -1
- package/out/src/tools/fetch/imls-pls.js +0 -108
- package/out/src/tools/fetch/imls-pls.js.map +0 -1
- package/out/src/tools/fetch/index.d.ts +0 -144
- package/out/src/tools/fetch/index.d.ts.map +0 -1
- package/out/src/tools/fetch/index.js +0 -143
- package/out/src/tools/fetch/index.js.map +0 -1
- package/out/src/tools/fetch/nad.d.ts +0 -70
- package/out/src/tools/fetch/nad.d.ts.map +0 -1
- package/out/src/tools/fetch/nad.js +0 -234
- package/out/src/tools/fetch/nad.js.map +0 -1
- package/out/src/tools/fetch/nppes.d.ts +0 -26
- package/out/src/tools/fetch/nppes.d.ts.map +0 -1
- package/out/src/tools/fetch/nppes.js +0 -126
- package/out/src/tools/fetch/nppes.js.map +0 -1
- package/out/src/tools/fetch/openaddresses.d.ts +0 -61
- package/out/src/tools/fetch/openaddresses.d.ts.map +0 -1
- package/out/src/tools/fetch/openaddresses.js +0 -317
- package/out/src/tools/fetch/openaddresses.js.map +0 -1
- package/out/src/tools/fetch/ourairports.d.ts +0 -45
- package/out/src/tools/fetch/ourairports.d.ts.map +0 -1
- package/out/src/tools/fetch/ourairports.js +0 -128
- package/out/src/tools/fetch/ourairports.js.map +0 -1
- package/out/src/tools/fetch/ppd.d.ts.map +0 -1
- package/out/src/tools/fetch/ppd.js +0 -100
- package/out/src/tools/fetch/ppd.js.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.d.ts +0 -25
- package/out/src/tools/fetch/state-hi-schools.d.ts.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.js +0 -162
- package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
- package/out/src/tools/fetch/state-sources.d.ts +0 -26
- package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
- package/out/src/tools/fetch/state-sources.js +0 -111
- package/out/src/tools/fetch/state-sources.js.map +0 -1
- package/out/src/tools/fetch/tiger-full.d.ts +0 -42
- package/out/src/tools/fetch/tiger-full.d.ts.map +0 -1
- package/out/src/tools/fetch/tiger-full.js +0 -248
- package/out/src/tools/fetch/tiger-full.js.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.d.ts +0 -171
- package/out/src/tools/fetch/wikidata-subvenue.d.ts.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.js +0 -275
- package/out/src/tools/fetch/wikidata-subvenue.js.map +0 -1
- package/out/src/tools/gb-title-case.d.ts.map +0 -1
- package/out/src/tools/gb-title-case.js.map +0 -1
- package/out/src/tools/golden-expand.d.ts +0 -90
- package/out/src/tools/golden-expand.d.ts.map +0 -1
- package/out/src/tools/golden-expand.js +0 -413
- package/out/src/tools/golden-expand.js.map +0 -1
- package/out/src/tools/golden-promote.d.ts.map +0 -1
- package/out/src/tools/golden-promote.js +0 -244
- package/out/src/tools/golden-promote.js.map +0 -1
- package/out/src/tools/golden-relabel-street.d.ts +0 -196
- package/out/src/tools/golden-relabel-street.d.ts.map +0 -1
- package/out/src/tools/golden-relabel-street.js +0 -440
- package/out/src/tools/golden-relabel-street.js.map +0 -1
- package/out/src/tools/index.d.ts +0 -28
- package/out/src/tools/index.d.ts.map +0 -1
- package/out/src/tools/index.js +0 -28
- package/out/src/tools/index.js.map +0 -1
- package/out/src/tools/ingest-csv.d.ts.map +0 -1
- package/out/src/tools/ingest-csv.js +0 -296
- package/out/src/tools/ingest-csv.js.map +0 -1
- package/out/src/tools/jsonl-to-parquet.d.ts +0 -61
- package/out/src/tools/jsonl-to-parquet.d.ts.map +0 -1
- package/out/src/tools/jsonl-to-parquet.js +0 -164
- package/out/src/tools/jsonl-to-parquet.js.map +0 -1
- package/out/src/tools/lint-shard-vocab.d.ts +0 -90
- package/out/src/tools/lint-shard-vocab.d.ts.map +0 -1
- package/out/src/tools/lint-shard-vocab.js +0 -281
- package/out/src/tools/lint-shard-vocab.js.map +0 -1
- package/out/src/tools/lint-shard.d.ts +0 -93
- package/out/src/tools/lint-shard.d.ts.map +0 -1
- package/out/src/tools/lint-shard.js +0 -354
- package/out/src/tools/lint-shard.js.map +0 -1
- package/out/src/tools/overlay-manifest.d.ts +0 -39
- package/out/src/tools/overlay-manifest.d.ts.map +0 -1
- package/out/src/tools/overlay-manifest.js +0 -98
- package/out/src/tools/overlay-manifest.js.map +0 -1
- package/out/src/tools/overture-subvenue.d.ts +0 -112
- package/out/src/tools/overture-subvenue.d.ts.map +0 -1
- package/out/src/tools/overture-subvenue.js +0 -144
- package/out/src/tools/overture-subvenue.js.map +0 -1
- package/out/src/tools/postcode-triples.d.ts +0 -175
- package/out/src/tools/postcode-triples.d.ts.map +0 -1
- package/out/src/tools/postcode-triples.js +0 -304
- package/out/src/tools/postcode-triples.js.map +0 -1
- package/out/src/tools/shard-kryptonite.d.ts +0 -32
- package/out/src/tools/shard-kryptonite.d.ts.map +0 -1
- package/out/src/tools/shard-kryptonite.js +0 -100
- package/out/src/tools/shard-kryptonite.js.map +0 -1
- package/out/src/tools/shard-translit.d.ts +0 -51
- package/out/src/tools/shard-translit.d.ts.map +0 -1
- package/out/src/tools/shard-translit.js +0 -175
- package/out/src/tools/shard-translit.js.map +0 -1
- package/out/src/tools/sub-venue/harvest.d.ts +0 -100
- package/out/src/tools/sub-venue/harvest.d.ts.map +0 -1
- package/out/src/tools/sub-venue/harvest.js +0 -168
- package/out/src/tools/sub-venue/harvest.js.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.d.ts +0 -50
- package/out/src/tools/sub-venue/head-nouns.d.ts.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.js +0 -210
- package/out/src/tools/sub-venue/head-nouns.js.map +0 -1
- package/out/src/tools/sub-venue/surfaces.d.ts +0 -45
- package/out/src/tools/sub-venue/surfaces.d.ts.map +0 -1
- package/out/src/tools/sub-venue/surfaces.js +0 -77
- package/out/src/tools/sub-venue/surfaces.js.map +0 -1
- package/out/src/tools/sub-venue/table.d.ts +0 -229
- package/out/src/tools/sub-venue/table.d.ts.map +0 -1
- package/out/src/tools/sub-venue/table.js +0 -108
- package/out/src/tools/sub-venue/table.js.map +0 -1
- package/out/src/tools/sub-venue/wikidata.d.ts +0 -26
- package/out/src/tools/sub-venue/wikidata.d.ts.map +0 -1
- package/out/src/tools/sub-venue/wikidata.js +0 -62
- package/out/src/tools/sub-venue/wikidata.js.map +0 -1
- package/out/src/tools/sub-venue-lexicon.d.ts +0 -156
- package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
- package/out/src/tools/sub-venue-lexicon.js +0 -282
- package/out/src/tools/sub-venue-lexicon.js.map +0 -1
- package/out/src/tools/sub-venue-promotions.d.ts +0 -94
- package/out/src/tools/sub-venue-promotions.d.ts.map +0 -1
- package/out/src/tools/sub-venue-promotions.js +0 -266
- package/out/src/tools/sub-venue-promotions.js.map +0 -1
- package/out/src/types.d.ts +0 -221
- package/out/src/types.d.ts.map +0 -1
- package/out/src/types.js.map +0 -1
- package/out/src/utils/align.d.ts +0 -93
- package/out/src/utils/align.d.ts.map +0 -1
- package/out/src/utils/align.js +0 -234
- package/out/src/utils/align.js.map +0 -1
- package/out/src/utils/golden.d.ts +0 -69
- package/out/src/utils/golden.d.ts.map +0 -1
- package/out/src/utils/golden.js +0 -127
- package/out/src/utils/golden.js.map +0 -1
- package/out/src/utils/index.d.ts +0 -14
- package/out/src/utils/index.d.ts.map +0 -1
- package/out/src/utils/index.js +0 -14
- package/out/src/utils/index.js.map +0 -1
- package/out/src/utils/license.d.ts.map +0 -1
- package/out/src/utils/license.js.map +0 -1
- package/out/src/utils/parquet.d.ts +0 -162
- package/out/src/utils/parquet.d.ts.map +0 -1
- package/out/src/utils/parquet.js +0 -262
- package/out/src/utils/parquet.js.map +0 -1
- package/out/src/utils/split.d.ts +0 -127
- package/out/src/utils/split.d.ts.map +0 -1
- package/out/src/utils/split.js +0 -204
- package/out/src/utils/split.js.map +0 -1
- package/out/src/utils/tokenize.d.ts +0 -56
- package/out/src/utils/tokenize.d.ts.map +0 -1
- package/out/src/utils/tokenize.js +0 -48
- package/out/src/utils/tokenize.js.map +0 -1
- package/out/src/utils/wof-json.d.ts +0 -109
- package/out/src/utils/wof-json.d.ts.map +0 -1
- package/out/src/utils/wof-json.js +0 -173
- package/out/src/utils/wof-json.js.map +0 -1
- package/src/adapters/ban/adapter.ts +0 -191
- package/src/adapters/ban/street-decompose.ts +0 -96
- package/src/adapters/fcc-bdc/adapter.ts +0 -174
- package/src/adapters/geonames/adapter.ts +0 -200
- package/src/adapters/geonames-postal/adapter.ts +0 -119
- package/src/adapters/gnaf/adapter.ts +0 -149
- package/src/adapters/gnaf/assemble.ts +0 -226
- package/src/adapters/index.ts +0 -149
- package/src/adapters/openaddresses/adapter.ts +0 -251
- package/src/adapters/overture/adapter.ts +0 -162
- package/src/adapters/state-hi-schools/adapter.ts +0 -164
- package/src/adapters/synth-po-box/adapter.ts +0 -204
- package/src/adapters/tiger/adapter.ts +0 -253
- package/src/adapters/tiger/street-decompose.ts +0 -111
- package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -183
- package/src/adapters/usgov-imls-pls/adapter.ts +0 -143
- package/src/adapters/usgov-irs-bmf/adapter.ts +0 -163
- package/src/adapters/usgov-nad/adapter.ts +0 -348
- package/src/adapters/usgov-nppes/adapter.ts +0 -159
- package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -204
- package/src/adapters/utils/index.ts +0 -233
- package/src/adapters/wof-admin-jp/adapter.ts +0 -216
- package/src/adapters/wof-admin-json/adapter.ts +0 -256
- package/src/adapters/wof-json-rows.ts +0 -79
- package/src/adapters/wof-postalcode-json/adapter.ts +0 -183
- package/src/build.ts +0 -386
- package/src/index.ts +0 -14
- package/src/name-prone-us-suffixes.ts +0 -12
- package/src/parquet-wrapper/index.ts +0 -9
- package/src/parquet-wrapper/reader.ts +0 -97
- package/src/parquet-wrapper/schema.ts +0 -88
- package/src/parquet-wrapper/writer.ts +0 -110
- package/src/runner.ts +0 -317
- package/src/shard-recipes/anchor-absorption.ts +0 -103
- package/src/shard-recipes/bare-country.ts +0 -95
- package/src/shard-recipes/boundary-stress.ts +0 -101
- package/src/shard-recipes/country-balanced.ts +0 -524
- package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -111
- package/src/shard-recipes/fr-admin-split.ts +0 -239
- package/src/shard-recipes/fr-bare-street.ts +0 -170
- package/src/shard-recipes/fr-fragment.ts +0 -332
- package/src/shard-recipes/fr-lieudit.ts +0 -302
- package/src/shard-recipes/fr-order.ts +0 -258
- package/src/shard-recipes/german.ts +0 -170
- package/src/shard-recipes/house-venue.ts +0 -88
- package/src/shard-recipes/index.ts +0 -95
- package/src/shard-recipes/intersection.ts +0 -630
- package/src/shard-recipes/locale.ts +0 -599
- package/src/shard-recipes/nl-postcode.ts +0 -115
- package/src/shard-recipes/no-fragment.ts +0 -219
- package/src/shard-recipes/no-street-led.ts +0 -143
- package/src/shard-recipes/no-street.ts +0 -86
- package/src/shard-recipes/po-box-cedex.ts +0 -920
- package/src/shard-recipes/po-box.ts +0 -119
- package/src/shard-recipes/reviewed-postcode-tail.ts +0 -189
- package/src/shard-recipes/scaffold.ts +0 -360
- package/src/shard-recipes/si-bare-village.ts +0 -97
- package/src/shard-recipes/street-affix.ts +0 -826
- package/src/shard-recipes/street-bare.ts +0 -101
- package/src/shard-recipes/street.ts +0 -82
- package/src/shard-recipes/sub-venue-sources.ts +0 -885
- package/src/shard-recipes/sub-venue.ts +0 -984
- package/src/shard-recipes/trailing-region.ts +0 -183
- package/src/shard-recipes/unit.ts +0 -321
- package/src/synthesizers/anchor-absorption.ts +0 -290
- package/src/synthesizers/boundary-stress.ts +0 -531
- package/src/synthesizers/german.ts +0 -251
- package/src/synthesizers/house-venue.ts +0 -330
- package/src/synthesizers/intersection.ts +0 -232
- package/src/synthesizers/no-street.ts +0 -349
- package/src/synthesizers/po-box.ts +0 -339
- package/src/synthesizers/street.ts +0 -274
- package/src/synthesizers/utils.ts +0 -903
- package/src/tools/align-shard.ts +0 -70
- package/src/tools/audit.ts +0 -399
- package/src/tools/corpus-stats.ts +0 -184
- package/src/tools/fetch/ban.ts +0 -290
- package/src/tools/fetch/download.ts +0 -176
- package/src/tools/fetch/geonames-dump.ts +0 -267
- package/src/tools/fetch/geonames-postal.ts +0 -180
- package/src/tools/fetch/hrsa.ts +0 -68
- package/src/tools/fetch/imls-pls.ts +0 -158
- package/src/tools/fetch/index.ts +0 -147
- package/src/tools/fetch/nad.ts +0 -342
- package/src/tools/fetch/nppes.ts +0 -174
- package/src/tools/fetch/openaddresses.ts +0 -404
- package/src/tools/fetch/ourairports.ts +0 -171
- package/src/tools/fetch/ppd.ts +0 -137
- package/src/tools/fetch/state-hi-schools.ts +0 -208
- package/src/tools/fetch/state-sources.ts +0 -155
- package/src/tools/fetch/tiger-full.ts +0 -354
- package/src/tools/fetch/wikidata-subvenue.ts +0 -386
- package/src/tools/golden-expand.ts +0 -584
- package/src/tools/golden-promote.ts +0 -353
- package/src/tools/golden-relabel-street.ts +0 -685
- package/src/tools/index.ts +0 -28
- package/src/tools/ingest-csv.ts +0 -422
- package/src/tools/jsonl-to-parquet.ts +0 -221
- package/src/tools/lint-shard-vocab.ts +0 -409
- package/src/tools/lint-shard.ts +0 -543
- package/src/tools/overlay-manifest.ts +0 -157
- package/src/tools/overture-subvenue.ts +0 -215
- package/src/tools/postcode-triples.ts +0 -375
- package/src/tools/shard-kryptonite.ts +0 -139
- package/src/tools/shard-translit.ts +0 -245
- package/src/tools/sub-venue/harvest.ts +0 -235
- package/src/tools/sub-venue/head-nouns.ts +0 -242
- package/src/tools/sub-venue/surfaces.ts +0 -95
- package/src/tools/sub-venue/table.ts +0 -281
- package/src/tools/sub-venue/wikidata.ts +0 -85
- package/src/tools/sub-venue-lexicon.ts +0 -431
- package/src/tools/sub-venue-promotions.ts +0 -330
- package/src/types.ts +0 -247
- package/src/utils/align.ts +0 -331
- package/src/utils/golden.ts +0 -176
- package/src/utils/index.ts +0 -14
- package/src/utils/parquet.ts +0 -391
- package/src/utils/split.ts +0 -279
- package/src/utils/tokenize.ts +0 -78
- package/src/utils/wof-json.ts +0 -244
- /package/{src → lib}/adapters/state-ia-contractors/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-ny-notaries/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-tx-notaries/adapter.ts +0 -0
- /package/{src → lib}/codex/us-fips-state.ts +0 -0
- /package/{src → lib}/tools/gb-title-case.ts +0 -0
- /package/{src → lib}/utils/license.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/fcc-bdc/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/geonames/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/openaddresses/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/synth-po-box/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/tiger/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-nppes/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-samhsa-treatment-locator/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/wof-admin-jp/adapter.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.js +0 -0
- /package/out/{src/tools → tools}/fetch/ppd.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.js +0 -0
- /package/out/{src/tools → tools}/golden-promote.d.ts +0 -0
- /package/out/{src/tools → tools}/ingest-csv.d.ts +0 -0
- /package/out/{src/types.js → types.js} +0 -0
- /package/out/{src/utils → utils}/license.d.ts +0 -0
- /package/out/{src/utils → utils}/license.js +0 -0
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"sub-venue-sources.js","sourceRoot":"","sources":["../../lib/recipes/sub-venue-sources.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;GAyBG;AAEH,OAAO,EAAE,YAAY,EAAE,MAAM,2BAA2B,CAAA;AACxD,OAAO,EAAE,iBAAiB,EAAE,MAAM,4BAA4B,CAAA;AAC9D,OAAO,EAAE,iBAAiB,EAAE,MAAM,kCAAkC,CAAA;AAEpE,OAAO,EAAE,cAAc,EAAE,MAAM,0BAA0B,CAAA;AAGzD,OAAO,EAAE,UAAU,IAAI,gBAAgB,EAAmB,MAAM,iBAAiB,CAAA;AACjF,OAAO,EAAE,cAAc,EAAE,UAAU,IAAI,eAAe,EAAE,MAAM,mBAAmB,CAAA;AAEjF,OAAO,EAAE,IAAI,EAAE,YAAY,EAAE,MAAM,qBAAqB,CAAA;AACxD,OAAO,EACN,kBAAkB,EAClB,iBAAiB,EAEjB,mBAAmB,GAEnB,MAAM,QAAQ,CAAA;AAEf,iBAAiB;AAEjB;;GAEG;AACH,MAAM,UAAU,kBAAkB;IACjC,OAAO,iBAAiB,CAAC,+CAA+C,CAAC,CAAA;AAC1E,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,mBAAmB,CAAC,OAAe,kBAAkB,EAAE;IAC5E,OAAO,MAAM,iBAAiB,CAAuB,IAAI,CAAC,CAAA;AAC3D,CAAC;AAED,YAAY;AAEZ,sBAAsB;AAEtB;;;;GAIG;AACH,MAAM,qBAAqB,GAAG,EAAE,CAAA;AAEhC;;;GAGG;AACH,MAAM,eAAe,GAAG,CAAC,CAAA;AAEzB;;;GAGG;AACH,MAAM,mBAAmB,GAAG,CAAC,CAAA;AAE7B;;;;GAIG;AACH,MAAM,UAAU,WAAW,CAAC,IAAY;IACvC,IAAI,IAAI,CAAC,MAAM,GAAG,eAAe,IAAI,IAAI,CAAC,MAAM,GAAG,qBAAqB;QAAE,OAAO,KAAK,CAAA;IAEtF,2GAA2G;IAC3G,IAAI,gBAAgB,CAAC,IAAI,CAAC,IAAI,CAAC;QAAE,OAAO,KAAK,CAAA;IAE7C,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC;QAAE,OAAO,KAAK,CAAA;IAEtC,yFAAyF;IACzF,IAAI,CAAC,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,IAAI,IAAI,KAAK,IAAI,CAAC,WAAW,EAAE;QAAE,OAAO,KAAK,CAAA;IAEpE,OAAO,IAAI,CAAA;AACZ,CAAC;AAED;;;;;;;;;;;;;;GAcG;AACH,MAAM,oBAAoB,GAAwB,IAAI,GAAG,CAAC;IACzD,KAAK;IACL,QAAQ;IACR,MAAM;IACN,MAAM;IACN,QAAQ;IACR,OAAO;IACP,KAAK;IACL,OAAO;IACP,UAAU;IACV,KAAK;IACL,KAAK;IACL,UAAU;IACV,SAAS;IACT,MAAM;IACN,IAAI;IACJ,MAAM;IACN,KAAK;IACL,KAAK;IACL,WAAW;IACX,QAAQ;IACR,SAAS;IACT,OAAO;IACP,OAAO;IACP,OAAO;IACP,MAAM;IACN,OAAO;IACP,UAAU;IACV,OAAO;IACP,QAAQ;IACR,SAAS;IACT,UAAU;IACV,WAAW;IACX,OAAO;IACP,OAAO;IACP,QAAQ;IACR,KAAK;IACL,QAAQ;IACR,SAAS;IACT,KAAK;IACL,OAAO;IACP,OAAO;CACP,CAAC,CAAA;AAEF;;;;;;;;GAQG;AACH,MAAM,iBAAiB,GAAwB,IAAI,GAAG,CAAC;IACtD,QAAQ;IACR,MAAM;IACN,MAAM;IACN,QAAQ;IACR,OAAO;IACP,OAAO;IACP,UAAU;IACV,MAAM;IACN,SAAS;IACT,MAAM;IACN,KAAK;IACL,OAAO;IACP,SAAS;IACT,OAAO;IACP,MAAM;IACN,KAAK;IACL,QAAQ;IACR,WAAW;CACX,CAAC,CAAA;AAEF,MAAM,kBAAkB,GAAG,qDAAqD,CAAA;AAEhF;;GAEG;AACH,MAAM,UAAU,eAAe,CAAC,IAAY;IAC3C,IAAI,CAAC,WAAW,CAAC,IAAI,CAAC;QAAE,OAAO,KAAK,CAAA;IACpC,MAAM,KAAK,GAAG,IAAI,CAAC,WAAW,EAAE,CAAC,KAAK,CAAC,YAAY,CAAC,IAAI,EAAE,CAAA;IAE1D,IAAI,CAAC,KAAK,CAAC,MAAM;QAAE,OAAO,KAAK,CAAA;IAE/B,IAAI,oBAAoB,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAE,CAAC;QAAE,OAAO,KAAK,CAAA;IACrD,MAAM,IAAI,GAAG,KAAK,CAAC,EAAE,CAAC,CAAC,CAAC,CAAE,CAAA;IAE1B,OAAO,CAAC,iBAAiB,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,kBAAkB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;AACtE,CAAC;AAoBD;;;GAGG;AACH,MAAM,UAAU,SAAS,CAAC,MAAc;IACvC,OAAO,MAAM,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,WAAW,EAAE,GAAG,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,CAAA;AACxD,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,cAAc,CAAC,SAAiB,EAAE,MAAc;IAC/D,IAAI,IAAI,GAAG,CAAC,CAAA;IAEZ,SAAS,CAAC;QACT,MAAM,EAAE,GAAG,SAAS,CAAC,OAAO,CAAC,MAAM,EAAE,IAAI,CAAC,CAAA;QAE1C,IAAI,EAAE,KAAK,CAAC,CAAC;YAAE,OAAO,KAAK,CAAA;QAC3B,MAAM,MAAM,GAAG,EAAE,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,SAAS,CAAC,EAAE,GAAG,CAAC,CAAE,CAAA;QACjD,MAAM,KAAK,GAAG,SAAS,CAAC,EAAE,GAAG,MAAM,CAAC,MAAM,CAAC,IAAI,EAAE,CAAA;QAEjD,IAAI,CAAC,eAAe,CAAC,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,eAAe,CAAC,IAAI,CAAC,KAAK,CAAC;YAAE,OAAO,IAAI,CAAA;QAC9E,IAAI,GAAG,EAAE,GAAG,CAAC,CAAA;IACd,CAAC;AACF,CAAC;AAED;;;;;GAKG;AACH,MAAM,wBAAwB,GAAwB,IAAI,GAAG,CAAC;IAC7D,OAAO;IACP,QAAQ;IACR,cAAc;IACd,cAAc;IACd,OAAO;CACP,CAAC,CAAA;AAEF;;;;;;;;;GASG;AACH,MAAM,oBAAoB,GAAG,sEAAsE,CAAA;AAEnG;;;;;GAKG;AACH,MAAM,UAAU,gBAAgB,CAAC,KAAa;IAC7C,MAAM,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,CAAA;IAEjC,IAAI,KAAK,CAAC,MAAM,GAAG,CAAC,IAAI,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC;QAAE,OAAO,KAAK,CAAA;IAE3D,OAAO,KAAK,CAAC,KAAK,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,oBAAoB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAA;AAC9D,CAAC;AAED;;;;;;;;;;;GAWG;AACH,MAAM,UAAU,gBAAgB,CAC/B,SAAiB,EACjB,QAAyB,EACzB,YAA+B,EAAE,EACjC,OAAO,GAAG,KAAK;IAEf,IAAI,CAAC,cAAc,CAAC,SAAS,EAAE,QAAQ,CAAC,MAAM,CAAC;QAAE,OAAO,KAAK,CAAA;IAE7D,MAAM,OAAO,GAAG,QAAQ,CAAC,MAAM,CAAC,UAAU,CAAC,qBAAqB,EAAE,MAAM,CAAC,GAAG,CAAA,KAAK,CAAC,CAAA;IAClF,MAAM,YAAY,GAAG,IAAI,MAAM,CAAC,wBAAwB,OAAO,YAAY,EAAE,GAAG,CAAC,CAAA;IACjF,MAAM,QAAQ,GAAG,YAAY,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;IAElD,IAAI,QAAQ,IAAI,wBAAwB,CAAC,GAAG,CAAC,kBAAkB,CAAC,QAAQ,CAAC,CAAC,IAAI,gBAAgB,CAAC,QAAQ,CAAC;QAAE,OAAO,IAAI,CAAA;IAErH,IAAI,QAAQ,CAAC,kBAAkB;QAAE,OAAO,KAAK,CAAA;IAE7C,IAAI,CAAC,OAAO,IAAI,CAAC,QAAQ,CAAC,gBAAgB;QAAE,OAAO,KAAK,CAAA;IAExD,OAAO,SAAS,CAAC,IAAI,CAAC,CAAC,QAAQ,EAAE,EAAE,CAClC,IAAI,MAAM,CAAC,wBAAwB,QAAQ,OAAO,OAAO,oBAAoB,EAAE,GAAG,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,CACnG,CAAA;AACF,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,oBAAoB,CACnC,SAAiB,EACjB,QAAyB,EACzB,YAA+B,EAAE,EACjC,OAAO,GAAG,KAAK;IAEf,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,MAAM,GAAG,mBAAmB;QAAE,OAAO,KAAK,CAAA;IAE9E,OAAO,gBAAgB,CAAC,SAAS,EAAE,QAAQ,EAAE,SAAS,EAAE,OAAO,CAAC,CAAA;AACjE,CAAC;AAED;;;;;;;;;;;GAWG;AACH,MAAM,UAAU,mBAAmB,CAClC,MAAc,EACd,OAA6B,EAC7B,aAA2C,mBAAmB;IAE9D,MAAM,QAAQ,GAAG,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;IAEtC,MAAM,QAAQ,GAAG,IAAI,GAAG,CACvB,UAAU,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,QAAQ,IAAI,CAAC,CAAC,MAAM,KAAK,MAAM,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,GAAG,CAAC,CAAC,YAAY,IAAI,CAAC,CAAC,MAAM,EAAE,CAAC,CACpH,CAAA;IAED,MAAM,GAAG,GAAG,IAAI,GAAG,EAA2B,CAAA;IAE9C,IAAI,QAAQ,KAAK,IAAI,EAAE,CAAC;QACvB,KAAK,MAAM,UAAU,IAAI,OAAO,CAAC,WAAW,EAAE,CAAC;YAC9C,IAAI,CAAC,UAAU,CAAC,OAAO;gBAAE,SAAQ;YACjC,MAAM,GAAG,GAAG,GAAG,UAAU,CAAC,EAAE,IAAI,UAAU,CAAC,EAAE,EAAE,CAAA;YAE/C,IAAI,QAAQ,CAAC,GAAG,CAAC,GAAG,CAAC;gBAAE,SAAQ;YAE/B,GAAG,CAAC,GAAG,CAAC,GAAG,EAAE;gBACZ,YAAY,EAAE,UAAU,CAAC,EAAE;gBAC3B,MAAM,EAAE,UAAU,CAAC,EAAE;gBACrB,OAAO,EAAE,SAAS,CAAC,UAAU,CAAC,EAAE,CAAC;gBACjC,kBAAkB,EAAE,KAAK;gBACzB,gBAAgB,EAAE,UAAU,CAAC,gBAAgB;aAC7C,CAAC,CAAA;QACH,CAAC;IACF,CAAC;IAED,KAAK,MAAM,SAAS,IAAI,UAAU,EAAE,CAAC;QACpC,IAAI,SAAS,CAAC,QAAQ,KAAK,SAAS,IAAI,SAAS,CAAC,MAAM,KAAK,MAAM;YAAE,SAAQ;QAC7E,MAAM,UAAU,GAAG,OAAO,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,KAAK,SAAS,CAAC,YAAY,CAAC,CAAA;QACnF,MAAM,GAAG,GAAG,GAAG,SAAS,CAAC,YAAY,IAAI,SAAS,CAAC,MAAM,EAAE,CAAA;QAE3D,IAAI,QAAQ,CAAC,GAAG,CAAC,GAAG,CAAC;YAAE,SAAQ;QAE/B,GAAG,CAAC,GAAG,CAAC,GAAG,EAAE;YACZ,YAAY,EAAE,SAAS,CAAC,YAAY;YACpC,MAAM,EAAE,SAAS,CAAC,MAAM;YACxB,OAAO,EAAE,SAAS,CAAC,SAAS,CAAC,MAAM,CAAC;YACpC,kBAAkB,EAAE,SAAS,CAAC,KAAK,KAAK,qBAAqB;YAC7D,2FAA2F;YAC3F,0FAA0F;YAC1F,gBAAgB,EAAE,OAAO,CAAC,UAAU,EAAE,gBAAgB,CAAC,IAAI,SAAS,CAAC,KAAK,KAAK,qBAAqB;SACpG,CAAC,CAAA;IACH,CAAC;IAED,OAAO,CAAC,GAAG,GAAG,CAAC,MAAM,EAAE,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,aAAa,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAA;AAC9E,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,kBAAkB,CACjC,MAAc,EACd,aAA2C,mBAAmB;IAE9D,OAAO,UAAU,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,QAAQ,IAAI,CAAC,CAAC,MAAM,KAAK,MAAM,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAA;AACrG,CAAC;AAoBD;;;;;;GAMG;AACH,MAAM,6BAA6B,GAAsB,CAAC,MAAM,EAAE,UAAU,EAAE,QAAQ,CAAC,CAAA;AAEvF;;;;;;GAMG;AACH,MAAM,0BAA0B,GAAG,EAAE,CAAA;AAErC;;GAEG;AACH,MAAM,UAAU,oBAAoB,CAAC,OAA6B,EAAE,MAAc;IACjF,MAAM,YAAY,GAAG,IAAI,GAAG,EAAyB,CAAA;IACrD,MAAM,MAAM,GAAkB,EAAE,CAAA;IAEhC,KAAK,MAAM,GAAG,IAAI,OAAO,CAAC,gBAAgB,EAAE,CAAC;QAC5C,IAAI,GAAG,CAAC,MAAM,KAAK,MAAM;YAAE,SAAQ;QAEnC,IAAI,CAAC,wBAAwB,CAAC,GAAG,CAAC,GAAG,CAAC,KAAK,CAAC;YAAE,SAAQ;QACtD,MAAM,QAAQ,GAAG,GAAG,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,gBAAgB,CAAC,CAAC,CAAC,CAAC,CAAA;QAEhE,IAAI,CAAC,QAAQ,CAAC,MAAM;YAAE,SAAQ;QAC9B,MAAM,MAAM,GAAgB,EAAE,KAAK,EAAE,GAAG,CAAC,KAAK,EAAE,YAAY,EAAE,GAAG,CAAC,YAAY,EAAE,QAAQ,EAAE,CAAA;QAC1F,MAAM,IAAI,GAAG,YAAY,CAAC,GAAG,CAAC,GAAG,CAAC,YAAY,CAAC,CAAA;QAE/C,IAAI,IAAI,EAAE,CAAC;YACV,IAAI,CAAC,IAAI,CAAC,MAAM,CAAC,CAAA;QAClB,CAAC;aAAM,CAAC;YACP,YAAY,CAAC,GAAG,CAAC,GAAG,CAAC,YAAY,EAAE,CAAC,MAAM,CAAC,CAAC,CAAA;QAC7C,CAAC;QAED,IAAI,6BAA6B,CAAC,QAAQ,CAAC,GAAG,CAAC,YAAY,CAAC,EAAE,CAAC;YAC9D,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,CAAA;QACpB,CAAC;IACF,CAAC;IAED,OAAO,EAAE,YAAY,EAAE,MAAM,EAAE,CAAA;AAChC,CAAC;AAED;;;;;;GAMG;AACH,MAAM,UAAU,gBAAgB,CAAC,KAAsB,EAAE,YAAoB,EAAE,MAAoB;IAClG,MAAM,GAAG,GAAG,KAAK,CAAC,YAAY,CAAC,GAAG,CAAC,YAAY,CAAC,IAAI,EAAE,CAAA;IACtD,MAAM,QAAQ,GAAG,GAAG,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,CAAC,EAAE,EAAE,CAAC,GAAG,GAAG,CAAC,CAAC,YAAY,EAAE,CAAC,CAAC,CAAA;IAChE,MAAM,OAAO,GAAG,QAAQ,IAAI,0BAA0B,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,KAAK,CAAC,MAAM,CAAA;IAE3E,IAAI,CAAC,OAAO,CAAC,MAAM;QAAE,OAAO,IAAI,CAAA;IAEhC,4GAA4G;IAC5G,MAAM,MAAM,GAAG,YAAY,CAAC,OAAO,EAAE,MAAM,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,YAAY,EAAE,EAAE,SAAS,EAAE,KAAK,EAAE,CAAC,CAAA;IAEzF,OAAO,IAAI,CAAC,MAAM,CAAC,QAAQ,EAAE,MAAM,CAAC,CAAA;AACrC,CAAC;AA2CD;;;GAGG;AACH,MAAM,CAAC,MAAM,gBAAgB,GAAc;IAC1C,MAAM,EAAE,EAAE;IACV,QAAQ,EAAE,EAAE;IACZ,cAAc,EAAE,EAAE;IAClB,WAAW,EAAE,EAAE;IACf,gBAAgB,EAAE,EAAE;CACpB,CAAA;AAaD;;;GAGG;AACH,SAAS,kBAAkB,CAAC,GAAW,EAAE,IAAY,EAAE,iBAAoC;IAC1F,OAAO,iBAAiB,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,cAAc,CAAC,GAAG,EAAE,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,UAAU,CAAC,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAA;AACtH,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,gBAAgB,CAAC,IAAY,EAAE,KAAgB;IACpE,MAAM,IAAI,GAAG,MAAM,iBAAiB,CAAC,IAAI,CAAC,CAAA;IAC1C,MAAM,MAAM,GAAG,IAAI,GAAG,EAAU,CAAA;IAChC,MAAM,QAAQ,GAAG,IAAI,GAAG,EAAU,CAAA;IAClC,MAAM,cAAc,GAAG,IAAI,GAAG,EAAU,CAAA;IACxC,MAAM,WAAW,GAAG,IAAI,GAAG,EAAU,CAAA;IACrC,MAAM,gBAAgB,GAAG,IAAI,GAAG,EAAU,CAAA;IAE1C,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;QACxB,MAAM,IAAI,GAAG,CAAC,GAAG,CAAC,IAAI,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;QAEpC,IAAI,CAAC,IAAI,IAAI,CAAC,WAAW,CAAC,IAAI,CAAC;YAAE,SAAQ;QACzC,MAAM,GAAG,GAAG,IAAI,CAAC,WAAW,EAAE,CAAA;QAC9B,MAAM,SAAS,GAAG,eAAe,CAAC,IAAI,CAAC,CAAA;QAEvC,IAAI,GAAG,CAAC,IAAI,KAAK,OAAO,IAAI,SAAS,EAAE,CAAC;YACvC,MAAM,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;QACjB,CAAC;QAED,KAAK,MAAM,QAAQ,IAAI,KAAK,CAAC,QAAQ,EAAE,CAAC;YACvC,IAAI,CAAC,cAAc,CAAC,GAAG,EAAE,QAAQ,CAAC,MAAM,CAAC;gBAAE,SAAQ;YAEnD,IAAI,CAAC,gBAAgB,CAAC,GAAG,EAAE,QAAQ,EAAE,KAAK,CAAC,SAAS,EAAE,KAAK,CAAC,OAAO,CAAC,EAAE,CAAC;gBACtE,IAAI,SAAS,EAAE,CAAC;oBACf,gBAAgB,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;gBAC3B,CAAC;YACF,CAAC;iBAAM,IAAI,oBAAoB,CAAC,GAAG,EAAE,QAAQ,EAAE,KAAK,CAAC,SAAS,EAAE,KAAK,CAAC,OAAO,CAAC,EAAE,CAAC;gBAChF,QAAQ,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;YACnB,CAAC;QACF,CAAC;QAED,IAAI,CAAC,SAAS;YAAE,SAAQ;QAExB,IAAI,KAAK,CAAC,eAAe,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,cAAc,CAAC,GAAG,EAAE,MAAM,CAAC,CAAC,EAAE,CAAC;YACzE,cAAc,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;QACzB,CAAC;QAED,IAAI,kBAAkB,CAAC,GAAG,EAAE,IAAI,EAAE,KAAK,CAAC,iBAAiB,CAAC,EAAE,CAAC;YAC5D,WAAW,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;QACtB,CAAC;IACF,CAAC;IAED,OAAO;QACN,MAAM,EAAE,CAAC,GAAG,MAAM,CAAC;QACnB,QAAQ,EAAE,CAAC,GAAG,QAAQ,CAAC;QACvB,cAAc,EAAE,CAAC,GAAG,cAAc,CAAC;QACnC,WAAW,EAAE,CAAC,GAAG,WAAW,CAAC;QAC7B,gBAAgB,EAAE,CAAC,GAAG,gBAAgB,CAAC;KACvC,CAAA;AACF,CAAC;AAED;;;;;;;;;GASG;AACH,MAAM,oBAAoB,GAAsB;IAC/C,SAAS;IACT,kBAAkB;IAClB,eAAe;IACf,UAAU;IACV,oBAAoB;CACpB,CAAA;AAED,MAAM,uBAAuB,GAAsB;IAClD,YAAY;IACZ,iBAAiB;IACjB,kBAAkB;IAClB,WAAW;IACX,mBAAmB;IACnB,0BAA0B;IAC1B,cAAc;CACd,CAAA;AAED;;;;;GAKG;AACH,MAAM,UAAU,YAAY,CAAC,MAAuB,EAAE,OAAe,EAAE,KAAgB;IACtF,MAAM,EAAE,GAAG,IAAI,cAAc,CAAc,MAAM,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAA;IAEtE,MAAM,KAAK,GAAG,EAAE,CAAC,OAAO,CAAC,6CAA6C,CAAC,CAAC,GAAG,EAGzE,CAAA;IAEF,MAAM,MAAM,GAAG,IAAI,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,QAAQ,EAAE,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;IAC5D,MAAM,QAAQ,GAAG,oBAAoB,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,EAAgB,EAAE,CAAC,EAAE,IAAI,IAAI,CAAC,CAAA;IACxG,MAAM,WAAW,GAAG,uBAAuB,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,EAAE,EAAgB,EAAE,CAAC,EAAE,IAAI,IAAI,CAAC,CAAA;IAC9G,MAAM,MAAM,GAAG,CAAC,GAAG,QAAQ,EAAE,GAAG,WAAW,CAAC,CAAA;IAE5C,IAAI,CAAC,MAAM,CAAC,MAAM;QAAE,MAAM,IAAI,KAAK,CAAC,aAAa,MAAM,sCAAsC,CAAC,CAAA;IAE9F,+FAA+F;IAC/F,2FAA2F;IAC3F,qEAAqE;IACrE,MAAM,IAAI,GAAG,EAAE;SACb,OAAO,CACP,gGAAgG,MAAM,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,GAAG,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,GAAG,CAClI;SACA,GAAG,CAAC,OAAO,EAAE,GAAG,MAAM,CAAiD,CAAA;IAEzE,MAAM,QAAQ,GAAG,IAAI,GAAG,CAAC,QAAQ,CAAC,CAAA;IAClC,MAAM,MAAM,GAAG,IAAI,GAAG,EAAU,CAAA;IAChC,MAAM,cAAc,GAAG,IAAI,GAAG,EAAU,CAAA;IACxC,MAAM,WAAW,GAAG,IAAI,GAAG,EAAU,CAAA;IAErC,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;QACxB,MAAM,IAAI,GAAG,GAAG,CAAC,IAAI,CAAC,IAAI,EAAE,CAAA;QAE5B,IAAI,CAAC,eAAe,CAAC,IAAI,CAAC;YAAE,SAAQ;QACpC,MAAM,GAAG,GAAG,IAAI,CAAC,WAAW,EAAE,CAAA;QAE9B,IAAI,QAAQ,CAAC,GAAG,CAAC,GAAG,CAAC,WAAW,CAAC,EAAE,CAAC;YACnC,MAAM,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;QACjB,CAAC;QAED,IAAI,KAAK,CAAC,eAAe,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,cAAc,CAAC,GAAG,EAAE,MAAM,CAAC,CAAC,EAAE,CAAC;YACzE,cAAc,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;QACzB,CAAC;QAED,IAAI,kBAAkB,CAAC,GAAG,EAAE,IAAI,EAAE,KAAK,CAAC,iBAAiB,CAAC,EAAE,CAAC;YAC5D,WAAW,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;QACtB,CAAC;IACF,CAAC;IAED,OAAO;QACN,MAAM,EAAE,CAAC,GAAG,MAAM,CAAC;QACnB,QAAQ,EAAE,EAAE;QACZ,cAAc,EAAE,CAAC,GAAG,cAAc,CAAC;QACnC,WAAW,EAAE,CAAC,GAAG,WAAW,CAAC;QAC7B,gBAAgB,EAAE,EAAE;KACpB,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,cAAc,CAAC,CAAY,EAAE,CAAY;IACxD,OAAO;QACN,MAAM,EAAE,CAAC,GAAG,CAAC,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,MAAM,CAAC;QAClC,QAAQ,EAAE,CAAC,GAAG,CAAC,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC,QAAQ,CAAC;QACxC,cAAc,EAAE,CAAC,GAAG,CAAC,CAAC,cAAc,EAAE,GAAG,CAAC,CAAC,cAAc,CAAC;QAC1D,WAAW,EAAE,CAAC,GAAG,CAAC,CAAC,WAAW,EAAE,GAAG,CAAC,CAAC,WAAW,CAAC;QACjD,gBAAgB,EAAE,CAAC,GAAG,CAAC,CAAC,gBAAgB,EAAE,GAAG,CAAC,CAAC,gBAAgB,CAAC;KAChE,CAAA;AACF,CAAC;AAED,YAAY;AAEZ,yBAAyB;AAEzB;;;;;;;;GAQG;AACH,MAAM,aAAa,GAAoD;IACtE,EAAE,EAAE;QACH,EAAE,GAAG,EAAE,YAAY,CAAC,eAAe,EAAE,YAAY,CAAC,EAAE,GAAG,EAAE,eAAe,EAAE,MAAM,EAAE,QAAQ,EAAE;QAC5F,EAAE,GAAG,EAAE,YAAY,CAAC,eAAe,EAAE,YAAY,CAAC,EAAE,GAAG,EAAE,qBAAqB,EAAE,MAAM,EAAE,SAAS,EAAE;KACnG;IACD,EAAE,EAAE,CAAC,EAAE,IAAI,EAAE,YAAY,CAAC,eAAe,EAAE,WAAW,EAAE,IAAI,EAAE,iBAAiB,CAAC,EAAE,CAAC;CACnF,CAAA;AAED;;;;GAIG;AACH,MAAM,CAAC,KAAK,UAAU,iBAAiB,CACtC,UAA2B,EAC3B,IAAY;IAEZ,MAAM,SAAS,GAAG,IAAI,GAAG,EAA6B,CAAA;IAEtD,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,eAAe,CAAC,UAAU,CAAC,EAAE,CAAC;QACvD,MAAM,OAAO,GAAG,MAAM,CAAC,KAAK,CAAC,OAAO,IAAI,EAAE,CAAC,CAAA;QAE3C,IAAI,CAAC,OAAO,IAAI,CAAC,KAAK,CAAC,QAAQ,IAAI,CAAC,KAAK,CAAC,MAAM;YAAE,SAAQ;QAE1D,MAAM,MAAM,GAAoB;YAC/B,YAAY,EAAE,MAAM,CAAC,KAAK,CAAC,WAAW,IAAI,KAAK,CAAC,YAAY,IAAI,EAAE,CAAC;YACnE,MAAM,EAAE,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC;YAC5B,QAAQ,EAAE,MAAM,CAAC,KAAK,CAAC,QAAQ,CAAC;YAChC,MAAM,EAAE,MAAM,CAAC,KAAK,CAAC,MAAM,IAAI,EAAE,CAAC;YAClC,QAAQ,EAAE,MAAM,CAAC,KAAK,CAAC,QAAQ,IAAI,EAAE,CAAC;SACtC,CAAA;QAED,MAAM,IAAI,GAAG,SAAS,CAAC,GAAG,CAAC,OAAO,CAAC,CAAA;QAEnC,IAAI,IAAI,EAAE,CAAC;YACV,IAAI,CAAC,IAAI,CAAC,MAAM,CAAC,CAAA;QAClB,CAAC;aAAM,CAAC;YACP,SAAS,CAAC,GAAG,CAAC,OAAO,EAAE,CAAC,MAAM,CAAC,CAAC,CAAA;QACjC,CAAC;IACF,CAAC;IAED,KAAK,MAAM,CAAC,OAAO,EAAE,KAAK,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,aAAa,CAAC,EAAE,CAAC;QAC9D,IAAI,SAAS,CAAC,GAAG,CAAC,OAAO,CAAC;YAAE,SAAQ;QACpC,MAAM,MAAM,GAAsB,EAAE,CAAA;QAEpC,KAAK,MAAM,CAAC,KAAK,EAAE,IAAI,CAAC,IAAI,KAAK,CAAC,OAAO,EAAE,EAAE,CAAC;YAC7C,wFAAwF;YACxF,uEAAuE;YACvE,MAAM,YAAY,GAAG,cAAc,CAAC,IAAI,GAAG,KAAK,CAAC,CAAA;YAEjD,KAAK,MAAM,KAAK,IAAI,MAAM,gBAAgB,CAAC,IAAI,EAAE,YAAY,CAAC,EAAE,CAAC;gBAChE,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;YACnB,CAAC;QACF,CAAC;QAED,SAAS,CAAC,GAAG,CAAC,OAAO,EAAE,MAAM,CAAC,CAAA;IAC/B,CAAC;IAED,OAAO,SAAS,CAAA;AACjB,CAAC;AAgBD;;;GAGG;AACH,MAAM,4BAA4B,GAAG,CAAC,CAAA;AAEtC,MAAM,UAAU,oBAAoB,CACnC,OAAmC,EACnC,iBAAoC,EACpC,SAA4B,EAC5B,OAAe;IAEf,MAAM,aAAa,GAAG,IAAI,GAAG,CAAC,iBAAiB,CAAC,CAAA;IAChD,MAAM,WAAW,GAAG,IAAI,GAAG,CAAC,SAAS,CAAC,CAAA;IACtC,MAAM,UAAU,GAAsB,EAAE,CAAA;IACxC,MAAM,kBAAkB,GAAsB,EAAE,CAAA;IAChD,MAAM,UAAU,GAAsB,EAAE,CAAA;IAExC,KAAK,MAAM,KAAK,IAAI,OAAO,EAAE,CAAC;QAC7B,MAAM,MAAM,GAAG,KAAK,CAAC,MAAM,CAAC,WAAW,EAAE,CAAC,KAAK,CAAC,YAAY,CAAC,IAAI,EAAE,CAAA;QACnE,IAAI,YAAY,GAAG,KAAK,CAAA;QACxB,IAAI,MAAM,GAAG,KAAK,CAAA;QAElB,KAAK,MAAM,CAAC,KAAK,EAAE,KAAK,CAAC,IAAI,MAAM,CAAC,OAAO,EAAE,EAAE,CAAC;YAC/C,IAAI,aAAa,CAAC,GAAG,CAAC,KAAK,CAAC,EAAE,CAAC;gBAC9B,YAAY,GAAG,IAAI,CAAA;YACpB,CAAC;YAED,IAAI,KAAK,GAAG,CAAC,GAAG,MAAM,CAAC,MAAM,IAAI,WAAW,CAAC,GAAG,CAAC,KAAK,CAAC,IAAI,aAAa,CAAC,GAAG,CAAC,MAAM,CAAC,KAAK,GAAG,CAAC,CAAE,CAAC,EAAE,CAAC;gBAClG,MAAM,GAAG,IAAI,CAAA;YACd,CAAC;YAED,IAAI,OAAO,KAAK,IAAI,IAAI,KAAK,CAAC,MAAM,IAAI,4BAA4B,IAAI,KAAK,CAAC,QAAQ,CAAC,MAAM,CAAC,EAAE,CAAC;gBAChG,UAAU,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;YACvB,CAAC;QACF,CAAC;QAED,IAAI,MAAM,EAAE,CAAC;YACZ,kBAAkB,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;QAC/B,CAAC;aAAM,IAAI,YAAY,EAAE,CAAC;YACzB,UAAU,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;QACvB,CAAC;IACF,CAAC;IAED,OAAO,EAAE,UAAU,EAAE,kBAAkB,EAAE,UAAU,EAAE,CAAA;AACtD,CAAC;AAED,YAAY"}
|
|
@@ -0,0 +1,269 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* `sub-venue` slice recipe (#35 step 4) — teach the `unit` tag the venue-INTERIOR shapes it was
|
|
7
|
+
* never taught, so the modifier+designator class wins at the shipped `venueStructureBiasScale` of
|
|
8
|
+
* 6.0 instead of needing ~11 nats. `docs/engineering/sub-venue-corpus-task.mdx` is the spec; the
|
|
9
|
+
* vocabulary is `corpus/data/sub-venue-lexicon.json` (v0.2.0) and the curation ledger is
|
|
10
|
+
* `corpus/src/tools/sub-venue-promotions.ts`. The READ half — promotions, identifier
|
|
11
|
+
* distributions, name pools — is `sub-venue-sources.ts`; this file renders lines and emits rows.
|
|
12
|
+
*
|
|
13
|
+
* ── WHY THIS SYNTHESIZES RATHER THAN HARVESTS ────────────────────────────────────────────────────
|
|
14
|
+
* Wave 1's lesson, and the reason the spec's "get real data first" instruction is honoured in a
|
|
15
|
+
* shape it did not anticipate: the attested SURFACE STRINGS are thin. 87 GB features attest
|
|
16
|
+
* `terminal`, 29 attest `wing`, 4 attest `concourse` (3 of which are a street called CONCOURSE WAY).
|
|
17
|
+
* You cannot train a tag on 29 strings. What the five extracts DO carry at volume is the three
|
|
18
|
+
* things a generator needs — 45,000+ real venue names across four countries, a per-region
|
|
19
|
+
* identifier DISTRIBUTION measured over 2,868 gate/terminal/campus refs, and the confound
|
|
20
|
+
* population that becomes the negatives. So the bulk is `designator × per-region-identifier ×
|
|
21
|
+
* modifier` sampled per locale, and the attested strings ride along as seasoning
|
|
22
|
+
* ({@link ATTESTED_FRACTION}) rather than as the corpus.
|
|
23
|
+
*
|
|
24
|
+
* ── THE PER-REGION IDENTIFIER RULE, AND WHY IT IS NOT COSMETIC ───────────────────────────────────
|
|
25
|
+
* `Gate A12` is a rendering, not a string anyone wrote down: all but 13 of Great Britain's 658
|
|
26
|
+
* `aeroway=gate` features are unnamed and carry only a `ref`. The lexicon therefore ships a
|
|
27
|
+
* distribution, and it differs by country far more than the shared English vocabulary suggests —
|
|
28
|
+
* GB gates are 71% bare digits and JP 89%, FR and DE are ~60% letter-digit (`A37`, `B05`), and ES
|
|
29
|
+
* gives a THIRD of its gates a range (`B18-B20`), which no other country does at that rate. A
|
|
30
|
+
* generator that samples Great Britain's shape into a Spanish line produces a plausible string that
|
|
31
|
+
* is wrong about Spain, so every leg samples its own region.
|
|
32
|
+
*
|
|
33
|
+
* ── ONLY PROMOTED (designator, locale) PAIRS PRODUCE POSITIVES ───────────────────────────────────
|
|
34
|
+
* A promotion names a designator, a phrase AND a locale, because the same token is a designator in
|
|
35
|
+
* one language and a disaster in another: `hall` is 0-of-3,273 in Great Britain and 35-of-40 in
|
|
36
|
+
* France; `wing` is 23-of-29 in Great Britain and 4-of-3,358 in the United States. A REJECTED pair
|
|
37
|
+
* generates NEGATIVES in that locale instead — en-US `wing` rows are Red Wing, not units.
|
|
38
|
+
*
|
|
39
|
+
* `shape: "identifier-required"` is honoured as the ledger's docstring demands: de-DE `halle` is
|
|
40
|
+
* emitted only as `Halle <identifier>`, never bare and never after a modifier, because its 168-hit
|
|
41
|
+
* confound includes the CITY Halle (Saale) and only the identifier-bearing shape separates them.
|
|
42
|
+
* {@link buildSubVenueForm} enforces it and `sub-venue.test.ts` pins it.
|
|
43
|
+
*
|
|
44
|
+
* ── LABELS ───────────────────────────────────────────────────────────────────────────────────────
|
|
45
|
+
* Sub-venue is `unit`; the container is `venue`. That is the spec's wording and it invents nothing:
|
|
46
|
+
* `block` / `sub_block` exist in the `ComponentTag` union but are JP-char-model-only and outside
|
|
47
|
+
* `ACTIVE_TAGS` (STAGE3), so they are not reachable from a Latin slice.
|
|
48
|
+
*
|
|
49
|
+
* ── WHAT IS DELIBERATELY NOT HERE ────────────────────────────────────────────────────────────────
|
|
50
|
+
* 1. **A modifier+designator form outside English.** `VENUE_STRUCTURE_MODIFIERS` is an English
|
|
51
|
+
* list, and the extracts say the localized modifier surfaces do not exist to copy: `aile` in
|
|
52
|
+
* France is 0 hits, `ala` in Spain 0, `flügel` in Germany 0. Generating `Terminal Sud` would
|
|
53
|
+
* be inventing a vocabulary with no confound board behind it, which is the exact failure the
|
|
54
|
+
* promotion ledger exists to prevent. Non-English legs get designator+identifier only.
|
|
55
|
+
* 2. **A ja-JP leg.** `ターミナル` is promoted (1,213 real of 1,215). The one non-Latin
|
|
56
|
+
* surface the task named, but Japanese addresses train through `build_jp_slice.py` against the
|
|
57
|
+
* `stage3-jp` 47-label head, where the interior tags are `block`/`sub_block`/`building_number`
|
|
58
|
+
* — a different model, a different label set, and a different builder. A katakana `unit` row
|
|
59
|
+
* in this (Latin) feed would in any case be dropped by `country_weights`, which carries no
|
|
60
|
+
* `JP` key. The JP extract is harvested and ready; the leg belongs to the JP slice.
|
|
61
|
+
*/
|
|
62
|
+
import type { ComponentTag } from "@mailwoman/core/types";
|
|
63
|
+
import { type CorpusRecipe } from "#recipes/scaffold";
|
|
64
|
+
import { type IdentifierModel, type PromotedSurface } from "#recipes/sub-venue-sources";
|
|
65
|
+
import type { LocaleBaseTuple } from "#synthesizers/german";
|
|
66
|
+
export * from "#recipes/sub-venue-sources";
|
|
67
|
+
/**
|
|
68
|
+
* One locale's leg of the slice.
|
|
69
|
+
*
|
|
70
|
+
* `positiveShare` / `negativeShare` are relative weights, normalized at run time — they do not have to sum to 1.
|
|
71
|
+
*/
|
|
72
|
+
export interface SubVenueLeg {
|
|
73
|
+
locale: string;
|
|
74
|
+
country: string;
|
|
75
|
+
/**
|
|
76
|
+
* ISO 3166-1 alpha-2 key into the lexicon's `identifierShapes` AND the extract filename. The two axes are the same
|
|
77
|
+
* axis: a distribution is measured in a region's own extract.
|
|
78
|
+
*/
|
|
79
|
+
region: string;
|
|
80
|
+
/**
|
|
81
|
+
* Extract filename under `--extracts-dir`. Absent = no OSM extract for this leg (en-US), which then draws its venue
|
|
82
|
+
* and confound pools from `poi.db` instead.
|
|
83
|
+
*/
|
|
84
|
+
extract?: string;
|
|
85
|
+
/**
|
|
86
|
+
* May this leg use the English `<modifier> <designator>` grammar? See the module docstring's exclusion 1.
|
|
87
|
+
*/
|
|
88
|
+
english: boolean;
|
|
89
|
+
positiveShare: number;
|
|
90
|
+
negativeShare: number;
|
|
91
|
+
/**
|
|
92
|
+
* Ca-ES only — keep context tuples whose postcode starts with one of these. Catalan-language territories by postal
|
|
93
|
+
* prefix (07 Illes Balears, 08 Barcelona, 17 Girona, 25 Lleida, 43 Tarragona) rather than by a REGION string, whose
|
|
94
|
+
* spelling in the OA export is not something to guess at.
|
|
95
|
+
*/
|
|
96
|
+
postcodePrefixes?: readonly string[];
|
|
97
|
+
}
|
|
98
|
+
/**
|
|
99
|
+
* The legs, and the numbers behind the shares.
|
|
100
|
+
*
|
|
101
|
+
* En-GB and en-US carry the most because they are where the eval board lives (28 of the 30 confound rows are GB or US
|
|
102
|
+
* addresses) and because the English shipped vocabulary is the only one with a modifier grammar — the target class.
|
|
103
|
+
* fr-FR, de-DE and es-ES exist because the ledger promoted surfaces there (169, 19+32 and 190 real hits respectively)
|
|
104
|
+
* and a slice that skipped them would leave every non-English promotion untrained. ca-ES is small on purpose: its
|
|
105
|
+
* promotion is 15 hits and its line differs from es-ES only in the Catalan street vocabulary the postal-prefix filter
|
|
106
|
+
* selects for.
|
|
107
|
+
*
|
|
108
|
+
* The negative shares invert that ordering where the confound mass does. en-US carries the largest negative share
|
|
109
|
+
* because its confound population is the largest measured anywhere in the ledger — 3,354 `wing` (Red Wing boots 676,
|
|
110
|
+
* chicken wings 759), 2,330 `pier` (Pier 1 Imports, which IS the designator+identifier shape), 27,081 `hall`.
|
|
111
|
+
*/
|
|
112
|
+
export declare const SUBVENUE_LEGS: readonly SubVenueLeg[];
|
|
113
|
+
/**
|
|
114
|
+
* En-US has no OSM extract, so its identifier distribution has to be borrowed. GB is the borrow, and the leg's `region`
|
|
115
|
+
* says so literally rather than in a comment: the two English-speaking aviation systems number their gates the same way
|
|
116
|
+
* (GB 71% bare digit) and poi.db — the only US source in reach — carries names, not refs, so it cannot supply a
|
|
117
|
+
* distribution of its own. Recorded here because it is the one place a leg's `region` is not its own country.
|
|
118
|
+
*/
|
|
119
|
+
export declare const US_IDENTIFIER_REGION_BORROWED_FROM = "GB";
|
|
120
|
+
/**
|
|
121
|
+
* The row count this slice is built at, and the arithmetic behind it. `--count` overrides; this is the number to use
|
|
122
|
+
* absent a reason.
|
|
123
|
+
*
|
|
124
|
+
* The training sampler (`corpus-python/src/mailwoman_train/data_loader.py`, `_raw_row_stream`) draws SOURCES from a
|
|
125
|
+
* multinomial over `source_weights` and yields the next row from that source's iterator. Two consequences set the
|
|
126
|
+
* size:
|
|
127
|
+
*
|
|
128
|
+
* 1. A source's share of an epoch is `weight / Σweights`, independent of how many rows it has.
|
|
129
|
+
* 2. **A source that exhausts is DELETED from the multinomial** — there is no cycling. Under-size the slice and its
|
|
130
|
+
* nominal dose is fiction for the rest of the epoch.
|
|
131
|
+
*
|
|
132
|
+
* Measured against the shipped `v4.1.0-gb-venue-l1e4-2k` weight table: 33 sources summing to 144.5. At the dose the B11
|
|
133
|
+
* GB-venue exercise settled on for a hard rare class — 12.0, the value `synth-fr-bare-street`, `synth-si-bare-village`,
|
|
134
|
+
* `synth-cz-pcfirst-preposition`, `synth-fr-fragment` and `synth-no-fragment` all carry — the share is `12 / 156.5 =
|
|
135
|
+
* 7.67%`, and `train_rows_per_epoch` is 1,000,000. So the epoch draws **76,677 rows** from this slice, and anything
|
|
136
|
+
* smaller runs dry mid-epoch. 120,000 clears that with room for a config that drops a source or raises the dose. (For
|
|
137
|
+
* contrast: `synth-fr-bare-street` is 10,803 rows at dose 12.0, so it exhausts 14% into its own nominal share every
|
|
138
|
+
* epoch — a precedent for the dose, not for the size.)
|
|
139
|
+
*/
|
|
140
|
+
export declare const RECOMMENDED_ROW_COUNT = 120000;
|
|
141
|
+
/**
|
|
142
|
+
* Surfaces reserved by `mailwoman/eval-harness/fixtures/venue-structure-confounds.jsonl` — the 30-row board this slice
|
|
143
|
+
* has to hold. A row containing any of these is DROPPED and counted in `contaminated`.
|
|
144
|
+
*
|
|
145
|
+
* The `--exclude-surfaces` precedent from `fr-fragment` / `no-fragment`, applied by hand rather than by file because
|
|
146
|
+
* the board lives in `mailwoman/` and `@mailwoman/corpus` cannot reach across that workspace boundary at run time. Keep
|
|
147
|
+
* it in sync when the board grows; a slice that trains on its own eval set measures memorization.
|
|
148
|
+
*
|
|
149
|
+
* Note what this costs and why it is still right: reserving `east gate` / `west gate` removes the two GB surfaces the
|
|
150
|
+
* board uses for its `modifier-designator-street` class, so the slice teaches that class from the OTHER real ones its
|
|
151
|
+
* sources carry (`North Gate`, `South Gate`, `East Hall`, `West Hall`, `Lower Hall`, `East Campus`, …). The class is
|
|
152
|
+
* taught; the board's own strings are not.
|
|
153
|
+
*/
|
|
154
|
+
export declare const BOARD_RESERVED_SURFACES: readonly string[];
|
|
155
|
+
/**
|
|
156
|
+
* Does this row's text collide with a board-reserved surface?
|
|
157
|
+
*/
|
|
158
|
+
export declare function isBoardReserved(raw: string): boolean;
|
|
159
|
+
/**
|
|
160
|
+
* One labelled piece of the line. Pieces inside a group are space-joined; groups are joined by the register's
|
|
161
|
+
* separator.
|
|
162
|
+
*/
|
|
163
|
+
interface Piece {
|
|
164
|
+
text: string;
|
|
165
|
+
tag?: ComponentTag;
|
|
166
|
+
}
|
|
167
|
+
type Group = Piece[];
|
|
168
|
+
/**
|
|
169
|
+
* Surface register. Every eval in this repo gets a lowercase leg because lowercase is the register users type — Google
|
|
170
|
+
* Maps taught them — so every slice has to carry one.
|
|
171
|
+
*/
|
|
172
|
+
declare const Register: {
|
|
173
|
+
readonly Canonical: "canonical";
|
|
174
|
+
readonly CommaFree: "comma-free";
|
|
175
|
+
readonly Lower: "lower";
|
|
176
|
+
readonly Upper: "upper";
|
|
177
|
+
};
|
|
178
|
+
type Register = (typeof Register)[keyof typeof Register];
|
|
179
|
+
/**
|
|
180
|
+
* Join groups into `raw` + `components`, applying the register to BOTH so alignment still finds every value.
|
|
181
|
+
*/
|
|
182
|
+
export declare function renderGroups(groups: Group[], register: Register): {
|
|
183
|
+
raw: string;
|
|
184
|
+
components: Partial<Record<ComponentTag, string>>;
|
|
185
|
+
};
|
|
186
|
+
/**
|
|
187
|
+
* The street + tail groups for a country, in that country's own order.
|
|
188
|
+
*
|
|
189
|
+
* DE/ES/FR put the postcode before the locality and DE/ES put the house number after the street; GB and US keep the
|
|
190
|
+
* anglophone order and US carries a region. These are the same orders `synthesizers/german.ts` renders, restated here
|
|
191
|
+
* because this recipe assembles its groups piece-by-piece (it has to, to place a sub-venue group in front of them).
|
|
192
|
+
*/
|
|
193
|
+
export declare function addressGroups(country: string, tuple: LocaleBaseTuple, withStreet: boolean): Group[];
|
|
194
|
+
/**
|
|
195
|
+
* A sub-venue string plus how it was made, for the composition report.
|
|
196
|
+
*/
|
|
197
|
+
export interface SubVenueForm {
|
|
198
|
+
text: string;
|
|
199
|
+
form: "designator-identifier" | "modifier-designator" | "attested";
|
|
200
|
+
designatorID: string;
|
|
201
|
+
}
|
|
202
|
+
/**
|
|
203
|
+
* Build one sub-venue string for a leg.
|
|
204
|
+
*
|
|
205
|
+
* The `identifier-required` guard is here and not at the call site on purpose: it is the one rule in this file that a
|
|
206
|
+
* refactor must not be able to route around. A promotion carrying `shape: "identifier-required"` can only ever leave
|
|
207
|
+
* this function as `<Phrase> <identifier>`, and returns `null` rather than a bare or modified form.
|
|
208
|
+
*/
|
|
209
|
+
export declare function buildSubVenueForm(leg: SubVenueLeg, promoted: readonly PromotedSurface[], model: IdentifierModel, modifiers: readonly string[], attested: readonly string[], random: () => number): SubVenueForm | null;
|
|
210
|
+
/**
|
|
211
|
+
* Alias kept for readers of the arc's earlier drafts.
|
|
212
|
+
*
|
|
213
|
+
* @deprecated Use {@link buildSubVenueForm}.
|
|
214
|
+
*/
|
|
215
|
+
export declare const buildPositiveForms: typeof buildSubVenueForm;
|
|
216
|
+
/**
|
|
217
|
+
* Negative classes, named so the composition report can count them and a failure can be attributed.
|
|
218
|
+
*/
|
|
219
|
+
export declare const NegativeClass: {
|
|
220
|
+
/**
|
|
221
|
+
* A locale-REJECTED surface in the venue slot: Red Wing Shoes, Village Hall, Porte de Champerret.
|
|
222
|
+
*/
|
|
223
|
+
readonly RejectedVenue: "rejected-venue";
|
|
224
|
+
/**
|
|
225
|
+
* The designator inside a longer proper name, whole string tagged `venue`: Lochaline Ferry Terminal.
|
|
226
|
+
*/
|
|
227
|
+
readonly LongerName: "longer-name";
|
|
228
|
+
/**
|
|
229
|
+
* A real street whose name carries a designator token: Pier Road, Egg Hall, Orchard Gate.
|
|
230
|
+
*/
|
|
231
|
+
readonly DesignatorStreet: "designator-street";
|
|
232
|
+
/**
|
|
233
|
+
* A real street of the `<modifier> <designator>` shape — the class that would otherwise be read as a sub-venue.
|
|
234
|
+
*/
|
|
235
|
+
readonly ModifierDesignatorStreet: "modifier-designator-street";
|
|
236
|
+
/**
|
|
237
|
+
* A GB single-token `-gate` street: Eastgate, Southgate, Moorgate, Stonegate.
|
|
238
|
+
*/
|
|
239
|
+
readonly GateSuffixStreet: "gate-suffix-street";
|
|
240
|
+
/**
|
|
241
|
+
* A PROMOTED phrase outside the shape its promotion covers — `Halle Rosengarten`, `PHOENIX Halle`. The other half of
|
|
242
|
+
* an `identifier-required` ruling; see `LegPools.unpromotedShapes`.
|
|
243
|
+
*/
|
|
244
|
+
readonly UnpromotedShape: "unpromoted-shape";
|
|
245
|
+
};
|
|
246
|
+
export type NegativeClass = (typeof NegativeClass)[keyof typeof NegativeClass];
|
|
247
|
+
/**
|
|
248
|
+
* Per-leg composition tallies the build prints and the report quotes.
|
|
249
|
+
*/
|
|
250
|
+
export interface SubVenueLegStats {
|
|
251
|
+
locale: string;
|
|
252
|
+
positives: number;
|
|
253
|
+
negatives: number;
|
|
254
|
+
byForm: Record<string, number>;
|
|
255
|
+
byDesignator: Record<string, number>;
|
|
256
|
+
byNegativeClass: Record<string, number>;
|
|
257
|
+
byRegister: Record<string, number>;
|
|
258
|
+
poolSizes: Record<string, number>;
|
|
259
|
+
}
|
|
260
|
+
/**
|
|
261
|
+
* Split `total` across `shares` (which need not sum to 1), largest-remainder so the parts sum exactly.
|
|
262
|
+
*/
|
|
263
|
+
export declare function allocate(total: number, shares: readonly number[]): number[];
|
|
264
|
+
/**
|
|
265
|
+
* Slice recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
266
|
+
* and `description` below for the surface form it generates.
|
|
267
|
+
*/
|
|
268
|
+
export declare const subVenueRecipe: CorpusRecipe;
|
|
269
|
+
//# sourceMappingURL=sub-venue.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"sub-venue.d.ts","sourceRoot":"","sources":["../../lib/recipes/sub-venue.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4DG;AAIH,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAA;AAGzD,OAAO,EAAiC,KAAK,YAAY,EAAE,MAAM,mBAAmB,CAAA;AACpF,OAAO,EAKN,KAAK,eAAe,EAKpB,KAAK,eAAe,EASpB,MAAM,4BAA4B,CAAA;AACnC,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,sBAAsB,CAAA;AAK3D,cAAc,4BAA4B,CAAA;AAI1C;;;;GAIG;AACH,MAAM,WAAW,WAAW;IAC3B,MAAM,EAAE,MAAM,CAAA;IACd,OAAO,EAAE,MAAM,CAAA;IACf;;;OAGG;IACH,MAAM,EAAE,MAAM,CAAA;IACd;;;OAGG;IACH,OAAO,CAAC,EAAE,MAAM,CAAA;IAChB;;OAEG;IACH,OAAO,EAAE,OAAO,CAAA;IAChB,aAAa,EAAE,MAAM,CAAA;IACrB,aAAa,EAAE,MAAM,CAAA;IACrB;;;;OAIG;IACH,gBAAgB,CAAC,EAAE,SAAS,MAAM,EAAE,CAAA;CACpC;AAED;;;;;;;;;;;;;GAaG;AACH,eAAO,MAAM,aAAa,EAAE,SAAS,WAAW,EAgD/C,CAAA;AAED;;;;;GAKG;AACH,eAAO,MAAM,kCAAkC,OAAO,CAAA;AAMtD;;;;;;;;;;;;;;;;;;;GAmBG;AACH,eAAO,MAAM,qBAAqB,SAAU,CAAA;AAgC5C;;;;;;;;;;;;GAYG;AACH,eAAO,MAAM,uBAAuB,EAAE,SAAS,MAAM,EAkCpD,CAAA;AAED;;GAEG;AACH,wBAAgB,eAAe,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAIpD;AAMD;;;GAGG;AACH,UAAU,KAAK;IACd,IAAI,EAAE,MAAM,CAAA;IACZ,GAAG,CAAC,EAAE,YAAY,CAAA;CAClB;AAED,KAAK,KAAK,GAAG,KAAK,EAAE,CAAA;AAEpB;;;GAGG;AACH,QAAA,MAAM,QAAQ;;;;;CAKJ,CAAA;AAEV,KAAK,QAAQ,GAAG,CAAC,OAAO,QAAQ,CAAC,CAAC,MAAM,OAAO,QAAQ,CAAC,CAAA;AAmBxD;;GAEG;AACH,wBAAgB,YAAY,CAC3B,MAAM,EAAE,KAAK,EAAE,EACf,QAAQ,EAAE,QAAQ,GAChB;IAAE,GAAG,EAAE,MAAM,CAAC;IAAC,UAAU,EAAE,OAAO,CAAC,MAAM,CAAC,YAAY,EAAE,MAAM,CAAC,CAAC,CAAA;CAAE,CA2BpE;AAED;;;;;;GAMG;AACH,wBAAgB,aAAa,CAAC,OAAO,EAAE,MAAM,EAAE,KAAK,EAAE,eAAe,EAAE,UAAU,EAAE,OAAO,GAAG,KAAK,EAAE,CAwDnG;AAMD;;GAEG;AACH,MAAM,WAAW,YAAY;IAC5B,IAAI,EAAE,MAAM,CAAA;IACZ,IAAI,EAAE,uBAAuB,GAAG,qBAAqB,GAAG,UAAU,CAAA;IAClE,YAAY,EAAE,MAAM,CAAA;CACpB;AAED;;;;;;GAMG;AACH,wBAAgB,iBAAiB,CAChC,GAAG,EAAE,WAAW,EAChB,QAAQ,EAAE,SAAS,eAAe,EAAE,EACpC,KAAK,EAAE,eAAe,EACtB,SAAS,EAAE,SAAS,MAAM,EAAE,EAC5B,QAAQ,EAAE,SAAS,MAAM,EAAE,EAC3B,MAAM,EAAE,MAAM,MAAM,GAClB,YAAY,GAAG,IAAI,CAiCrB;AAED;;;;GAIG;AACH,eAAO,MAAM,kBAAkB,0BAAoB,CAAA;AAMnD;;GAEG;AACH,eAAO,MAAM,aAAa;IACzB;;OAEG;;IAEH;;OAEG;;IAEH;;OAEG;;IAEH;;OAEG;;IAEH;;OAEG;;IAEH;;;OAGG;;CAEM,CAAA;AAEV,MAAM,MAAM,aAAa,GAAG,CAAC,OAAO,aAAa,CAAC,CAAC,MAAM,OAAO,aAAa,CAAC,CAAA;AA+B9E;;GAEG;AACH,MAAM,WAAW,gBAAgB;IAChC,MAAM,EAAE,MAAM,CAAA;IACd,SAAS,EAAE,MAAM,CAAA;IACjB,SAAS,EAAE,MAAM,CAAA;IACjB,MAAM,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IAC9B,YAAY,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IACpC,eAAe,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IACvC,UAAU,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IAClC,SAAS,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;CACjC;AA6MD;;GAEG;AACH,wBAAgB,QAAQ,CAAC,KAAK,EAAE,MAAM,EAAE,MAAM,EAAE,SAAS,MAAM,EAAE,GAAG,MAAM,EAAE,CAiB3E;AA6DD;;;GAGG;AACH,eAAO,MAAM,cAAc,EAAE,YAiG5B,CAAA"}
|