@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 +1,250 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* PO box / PMB / Apartado / Boîte Postale synthesizer.
|
|
7
|
+
*
|
|
8
|
+
* Generates BIO-labeled corpus rows where the delivery line is a PO box (mutually exclusive with
|
|
9
|
+
* street + house_number per USPS Pub 28 / DMM 508). Locale-aware: emits idiomatic forms for
|
|
10
|
+
* en-US, en-CA, en-GB, en-AU, fr-FR, fr-CA, es-ES, es-MX, es-AR.
|
|
11
|
+
*
|
|
12
|
+
* Per-DeepSeek design:
|
|
13
|
+
*
|
|
14
|
+
* - PMB ("Private Mailbox" — at CMRAs like UPS Store) shares the `po_box` tag with USPS PO Box.
|
|
15
|
+
* Disambiguation is a downstream heuristic (presence of a street line).
|
|
16
|
+
* - Whole-phrase span ("PO Box 123") not number-only ("123"). Matches existing golden eval.
|
|
17
|
+
* - 10% of outputs receive number-format noise (commas, dashes, embedded spaces) to harden against
|
|
18
|
+
* real-world OCR/transcription input.
|
|
19
|
+
* - PO boxes drop street/house_number/unit/street_prefix/street_suffix from input components.
|
|
20
|
+
*
|
|
21
|
+
* References:
|
|
22
|
+
*
|
|
23
|
+
* - USPS Pub 28 §28C2.040 — Private Mailbox formatting
|
|
24
|
+
* - USPS DMM 508 §4.1.4 / §4.5.4 — PO Box and street-addressed PO Box
|
|
25
|
+
*/
|
|
26
|
+
import { countryToLocale as baseCountryToLocale, pick, tieredNumber } from "#synthesizers/utils";
|
|
27
|
+
/**
|
|
28
|
+
* Digits a box number needs before a thousands comma is plausible (`1,234`).
|
|
29
|
+
*/
|
|
30
|
+
const MIN_DIGITS_FOR_COMMA_GROUPING = 4;
|
|
31
|
+
/**
|
|
32
|
+
* Digits a box number needs before a hyphen group is plausible (`12-34`).
|
|
33
|
+
*/
|
|
34
|
+
const MIN_DIGITS_FOR_HYPHEN_GROUPING = 3;
|
|
35
|
+
/**
|
|
36
|
+
* The per-locale PO-box designator vocabulary (DeepSeek-signed list, see the header). Exported so slice builders
|
|
37
|
+
* (scripts/build-po-box-cedex-slice.mjs) can reuse THIS list as the single source of truth for non-US leaders instead
|
|
38
|
+
* of re-deriving it — the US slice additionally has `@mailwoman/codex/us` `US_PO_BOX_DESIGNATORS`/`isPOBox` as its
|
|
39
|
+
* matcher-side truth.
|
|
40
|
+
*/
|
|
41
|
+
export const PO_BOX_LOCALE_TEMPLATES = [
|
|
42
|
+
{
|
|
43
|
+
locale: "en-US",
|
|
44
|
+
leaders: ["PO Box", "P.O. Box", "P.O.Box", "PO BOX", "POB", "Post Office Box", "Box"],
|
|
45
|
+
pmb: ["PMB", "#"],
|
|
46
|
+
},
|
|
47
|
+
{
|
|
48
|
+
locale: "en-CA",
|
|
49
|
+
leaders: ["PO Box", "P.O. Box", "POB", "Post Office Box"],
|
|
50
|
+
pmb: ["PMB", "#"],
|
|
51
|
+
},
|
|
52
|
+
{
|
|
53
|
+
locale: "en-GB",
|
|
54
|
+
leaders: ["PO Box", "P.O. Box", "Post Office Box"],
|
|
55
|
+
},
|
|
56
|
+
{
|
|
57
|
+
locale: "en-AU",
|
|
58
|
+
leaders: ["PO Box", "P.O. Box", "Post Office Box", "GPO Box", "Locked Bag"],
|
|
59
|
+
},
|
|
60
|
+
{
|
|
61
|
+
locale: "en-NZ",
|
|
62
|
+
leaders: ["PO Box", "P.O. Box", "Post Office Box", "Private Bag", "Private Box"],
|
|
63
|
+
},
|
|
64
|
+
{
|
|
65
|
+
locale: "fr-FR",
|
|
66
|
+
leaders: ["BP", "B.P.", "Boîte Postale", "BP."],
|
|
67
|
+
},
|
|
68
|
+
{
|
|
69
|
+
locale: "fr-CA",
|
|
70
|
+
leaders: ["CP", "C.P.", "Case Postale", "BP", "B.P."],
|
|
71
|
+
},
|
|
72
|
+
{
|
|
73
|
+
locale: "es-ES",
|
|
74
|
+
leaders: ["Apdo.", "Apdo", "Apartado", "Apartado de Correos"],
|
|
75
|
+
},
|
|
76
|
+
{
|
|
77
|
+
locale: "es-MX",
|
|
78
|
+
leaders: ["Apdo.", "Apartado", "Apartado Postal", "AP"],
|
|
79
|
+
},
|
|
80
|
+
{
|
|
81
|
+
locale: "es-AR",
|
|
82
|
+
leaders: ["Casilla", "Casilla de Correo", "CC"],
|
|
83
|
+
},
|
|
84
|
+
];
|
|
85
|
+
const LEADERS_BY_LOCALE = new Map(PO_BOX_LOCALE_TEMPLATES.map((t) => [t.locale, t]));
|
|
86
|
+
/**
|
|
87
|
+
* Inject number-format noise into a box number string. Returns the noisy variant or the original (10% probability of
|
|
88
|
+
* noise per the design).
|
|
89
|
+
*/
|
|
90
|
+
export function maybeNoisifyBoxNumber(num, random) {
|
|
91
|
+
if (random() > 0.1)
|
|
92
|
+
return num;
|
|
93
|
+
const variants = [
|
|
94
|
+
// Thousand-separator comma (real input: "Box 1,234")
|
|
95
|
+
(s) => (s.length >= MIN_DIGITS_FOR_COMMA_GROUPING ? `${s.slice(0, -3)},${s.slice(-3)}` : s),
|
|
96
|
+
// Embedded dash (real input: "PMB-200")
|
|
97
|
+
(s) => (s.length >= MIN_DIGITS_FOR_HYPHEN_GROUPING ? `${s.slice(0, -2)}-${s.slice(-2)}` : s),
|
|
98
|
+
// Embedded spaces (real input from OCR: "1 2 3 4")
|
|
99
|
+
(s) => s.split("").join(" "),
|
|
100
|
+
];
|
|
101
|
+
const f = pick(variants, random);
|
|
102
|
+
return f(num);
|
|
103
|
+
}
|
|
104
|
+
/**
|
|
105
|
+
* Compose a PO box phrase like "PO Box 123" or "PMB 200".
|
|
106
|
+
*
|
|
107
|
+
* Returns both the phrase and the canonical leader+number so the BIO aligner can mark the entire span as `po_box`.
|
|
108
|
+
*/
|
|
109
|
+
export function composePoBoxPhrase(leader, number) {
|
|
110
|
+
return `${leader} ${number}`;
|
|
111
|
+
}
|
|
112
|
+
function defaultPickNumber(random) {
|
|
113
|
+
// 70% of real PO boxes are 1-5 digits; long ones exist (USPS allows up to ~6 digits).
|
|
114
|
+
// Bands: 1-99, 100-999, 1000-9999, 10000-99999 (span 90_000 — the street generator's 89_999 is its own).
|
|
115
|
+
return tieredNumber(random, [
|
|
116
|
+
{ cutoff: 0.3, base: 1, span: 99 },
|
|
117
|
+
{ cutoff: 0.7, base: 100, span: 900 },
|
|
118
|
+
{ cutoff: 0.95, base: 1000, span: 9000 },
|
|
119
|
+
{ base: 10_000, span: 90_000 },
|
|
120
|
+
]);
|
|
121
|
+
}
|
|
122
|
+
/**
|
|
123
|
+
* Generate one PO box row for a base (locality, region, postcode, country) tuple. Picks a locale-appropriate leader and
|
|
124
|
+
* number. Optionally generates a PMB variant when the base tuple includes a street.
|
|
125
|
+
*/
|
|
126
|
+
export function synthesizePoBoxRow(base, opts = {}) {
|
|
127
|
+
const random = opts.random ?? Math.random;
|
|
128
|
+
const pickNumber = opts.pickNumber ?? defaultPickNumber;
|
|
129
|
+
const pmbRatio = opts.pmbRatio ?? 0;
|
|
130
|
+
const locale = countryToLocale(base.country);
|
|
131
|
+
const tpl = LEADERS_BY_LOCALE.get(locale);
|
|
132
|
+
if (!tpl)
|
|
133
|
+
return null;
|
|
134
|
+
const number = maybeNoisifyBoxNumber(pickNumber(random), random);
|
|
135
|
+
const leader = pick(tpl.leaders, random);
|
|
136
|
+
const poBoxPhrase = composePoBoxPhrase(leader, number);
|
|
137
|
+
// PMB variant: requires both a street and a PMB-supporting locale.
|
|
138
|
+
const wantPmb = base.street && tpl.pmb && random() < pmbRatio;
|
|
139
|
+
if (wantPmb) {
|
|
140
|
+
const pmbLeader = pick(tpl.pmb, random);
|
|
141
|
+
const pmbPhrase = composePoBoxPhrase(pmbLeader, number);
|
|
142
|
+
const streetLine = base.houseNumber ? `${base.houseNumber} ${base.street}` : base.street;
|
|
143
|
+
const raw = `${streetLine}, ${pmbPhrase}, ${base.locality}, ${base.region} ${base.postcode}`;
|
|
144
|
+
return {
|
|
145
|
+
raw,
|
|
146
|
+
components: {
|
|
147
|
+
...(base.houseNumber ? { house_number: base.houseNumber } : {}),
|
|
148
|
+
street: base.street,
|
|
149
|
+
po_box: pmbPhrase,
|
|
150
|
+
locality: base.locality,
|
|
151
|
+
region: base.region,
|
|
152
|
+
postcode: base.postcode,
|
|
153
|
+
country: base.country,
|
|
154
|
+
},
|
|
155
|
+
locale,
|
|
156
|
+
template: "pmb-with-street",
|
|
157
|
+
};
|
|
158
|
+
}
|
|
159
|
+
// Standard PO box: replaces the street line entirely. Region-optional — NZ (and other region-less
|
|
160
|
+
// locales) read "Private Bag 12, Auckland 1010" with no region token between locality and postcode.
|
|
161
|
+
const hasRegion = Boolean(base.region && base.region.trim());
|
|
162
|
+
const tail = hasRegion ? `${base.locality}, ${base.region} ${base.postcode}` : `${base.locality} ${base.postcode}`;
|
|
163
|
+
const raw = `${poBoxPhrase}, ${tail}`;
|
|
164
|
+
return {
|
|
165
|
+
raw,
|
|
166
|
+
components: {
|
|
167
|
+
po_box: poBoxPhrase,
|
|
168
|
+
locality: base.locality,
|
|
169
|
+
...(hasRegion ? { region: base.region } : {}),
|
|
170
|
+
postcode: base.postcode,
|
|
171
|
+
country: base.country,
|
|
172
|
+
},
|
|
173
|
+
locale,
|
|
174
|
+
template: "po-box",
|
|
175
|
+
};
|
|
176
|
+
}
|
|
177
|
+
/**
|
|
178
|
+
* The US military/diplomatic PO-box class (#517). A distinct shape the leader-based locale templates can't express: a
|
|
179
|
+
* unit line (`PSC <id> Box <box>`, `CMR <id> Box <box>`, `Unit <id> [Box <box>]`) tagged `po_box`, then the post-office
|
|
180
|
+
* code (APO/FPO/DPO) as the locality and the armed-forces region (AA/AE/AP) as the region, with a theatre-specific ZIP.
|
|
181
|
+
* Authoritative reference + citations: `@mailwoman/codex` `codex/us/military-address.ts`; the small constants are
|
|
182
|
+
* inlined here so the generator is self-contained.
|
|
183
|
+
*/
|
|
184
|
+
const MIL_UNITS = [
|
|
185
|
+
{ code: "PSC", boxRequired: true },
|
|
186
|
+
{ code: "CMR", boxRequired: true },
|
|
187
|
+
{ code: "Unit", boxRequired: false },
|
|
188
|
+
];
|
|
189
|
+
const MIL_PO_CODES = ["APO", "FPO", "DPO"];
|
|
190
|
+
/**
|
|
191
|
+
* Region → plausible ZIP prefix (AE Europe 09xxx, AP Pacific 962-966xx, AA Americas 340xx).
|
|
192
|
+
*/
|
|
193
|
+
const MIL_REGION_ZIP = [
|
|
194
|
+
{ region: "AE", zip: (r) => `09${String(Math.floor(r() * 1000)).padStart(3, "0")}` },
|
|
195
|
+
{ region: "AP", zip: (r) => `96${String(200 + Math.floor(r() * 100)).padStart(3, "0")}` },
|
|
196
|
+
{ region: "AA", zip: (r) => `340${String(Math.floor(r() * 100)).padStart(2, "0")}` },
|
|
197
|
+
];
|
|
198
|
+
/**
|
|
199
|
+
* Generate one US military/diplomatic PO-box row (#517). Self-contained — draws no base tuple.
|
|
200
|
+
*/
|
|
201
|
+
export function synthesizeMilitaryPoBoxRow(opts = {}) {
|
|
202
|
+
const random = opts.random ?? Math.random;
|
|
203
|
+
const unit = pick(MIL_UNITS, random);
|
|
204
|
+
const unitID = String(1 + Math.floor(random() * 9999));
|
|
205
|
+
const { region, zip } = pick(MIL_REGION_ZIP, random);
|
|
206
|
+
const zipStr = zip(random);
|
|
207
|
+
const po = pick(MIL_PO_CODES, random);
|
|
208
|
+
const hasBox = unit.boxRequired || random() < 0.5;
|
|
209
|
+
const unitLine = hasBox ? `${unit.code} ${unitID} Box ${1 + Math.floor(random() * 9999)}` : `${unit.code} ${unitID}`;
|
|
210
|
+
const raw = `${unitLine}, ${po} ${region} ${zipStr}`;
|
|
211
|
+
return {
|
|
212
|
+
raw,
|
|
213
|
+
components: {
|
|
214
|
+
po_box: unitLine,
|
|
215
|
+
locality: po,
|
|
216
|
+
region,
|
|
217
|
+
postcode: zipStr,
|
|
218
|
+
country: "US",
|
|
219
|
+
},
|
|
220
|
+
locale: "en-US",
|
|
221
|
+
template: "military-po-box",
|
|
222
|
+
};
|
|
223
|
+
}
|
|
224
|
+
const PO_BOX_TEMPLATE_LOCALES = new Set(PO_BOX_LOCALE_TEMPLATES.map((t) => t.locale));
|
|
225
|
+
/**
|
|
226
|
+
* Map a country code (ISO-3166-1 alpha-2 or alpha-3, or country display name) to the locale code we have a PO box
|
|
227
|
+
* template for.
|
|
228
|
+
*
|
|
229
|
+
* TEMPLATE-SCOPED on top of the shared `#synthesizers/utils` map: a locale the shared map resolves but
|
|
230
|
+
* {@link PO_BOX_LOCALE_TEMPLATES} does not carry falls back to `en-US`, so `DE` (shared: `de-DE`, no PO-box template)
|
|
231
|
+
* keeps rendering the en-US box vocabulary here.
|
|
232
|
+
*/
|
|
233
|
+
export function countryToLocale(country) {
|
|
234
|
+
const locale = baseCountryToLocale(country);
|
|
235
|
+
return PO_BOX_TEMPLATE_LOCALES.has(locale) ? locale : "en-US";
|
|
236
|
+
}
|
|
237
|
+
/**
|
|
238
|
+
* All locales we synthesize for. Exposed for tests and for source-weight tuning.
|
|
239
|
+
*/
|
|
240
|
+
export function supportedLocales() {
|
|
241
|
+
return PO_BOX_LOCALE_TEMPLATES.map((t) => t.locale);
|
|
242
|
+
}
|
|
243
|
+
/**
|
|
244
|
+
* Locales whose standard PO-box delivery line carries NO region token — the address reads `<po_box>, <locality>
|
|
245
|
+
* <postcode>` with nothing between locality and postcode (#517). NZ is the canonical case (`Private Bag 12, Auckland
|
|
246
|
+
* 1010`). Consumers (e.g. the synth-po-box adapter) use this to avoid discarding region-less input tuples for these
|
|
247
|
+
* locales as "missing region".
|
|
248
|
+
*/
|
|
249
|
+
export const REGION_OPTIONAL_LOCALES = new Set(["en-NZ"]);
|
|
250
|
+
//# sourceMappingURL=po-box.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"po-box.js","sourceRoot":"","sources":["../../lib/synthesizers/po-box.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;GAwBG;AAEH,OAAO,EAAE,eAAe,IAAI,mBAAmB,EAAE,IAAI,EAAE,YAAY,EAAE,MAAM,qBAAqB,CAAA;AAGhG;;GAEG;AACH,MAAM,6BAA6B,GAAG,CAAC,CAAA;AAEvC;;GAEG;AACH,MAAM,8BAA8B,GAAG,CAAC,CAAA;AAsBxC;;;;;GAKG;AACH,MAAM,CAAC,MAAM,uBAAuB,GAAkC;IACrE;QACC,MAAM,EAAE,OAAO;QACf,OAAO,EAAE,CAAC,QAAQ,EAAE,UAAU,EAAE,SAAS,EAAE,QAAQ,EAAE,KAAK,EAAE,iBAAiB,EAAE,KAAK,CAAC;QACrF,GAAG,EAAE,CAAC,KAAK,EAAE,GAAG,CAAC;KACjB;IACD;QACC,MAAM,EAAE,OAAO;QACf,OAAO,EAAE,CAAC,QAAQ,EAAE,UAAU,EAAE,KAAK,EAAE,iBAAiB,CAAC;QACzD,GAAG,EAAE,CAAC,KAAK,EAAE,GAAG,CAAC;KACjB;IACD;QACC,MAAM,EAAE,OAAO;QACf,OAAO,EAAE,CAAC,QAAQ,EAAE,UAAU,EAAE,iBAAiB,CAAC;KAClD;IACD;QACC,MAAM,EAAE,OAAO;QACf,OAAO,EAAE,CAAC,QAAQ,EAAE,UAAU,EAAE,iBAAiB,EAAE,SAAS,EAAE,YAAY,CAAC;KAC3E;IACD;QACC,MAAM,EAAE,OAAO;QACf,OAAO,EAAE,CAAC,QAAQ,EAAE,UAAU,EAAE,iBAAiB,EAAE,aAAa,EAAE,aAAa,CAAC;KAChF;IACD;QACC,MAAM,EAAE,OAAO;QACf,OAAO,EAAE,CAAC,IAAI,EAAE,MAAM,EAAE,eAAe,EAAE,KAAK,CAAC;KAC/C;IACD;QACC,MAAM,EAAE,OAAO;QACf,OAAO,EAAE,CAAC,IAAI,EAAE,MAAM,EAAE,cAAc,EAAE,IAAI,EAAE,MAAM,CAAC;KACrD;IACD;QACC,MAAM,EAAE,OAAO;QACf,OAAO,EAAE,CAAC,OAAO,EAAE,MAAM,EAAE,UAAU,EAAE,qBAAqB,CAAC;KAC7D;IACD;QACC,MAAM,EAAE,OAAO;QACf,OAAO,EAAE,CAAC,OAAO,EAAE,UAAU,EAAE,iBAAiB,EAAE,IAAI,CAAC;KACvD;IACD;QACC,MAAM,EAAE,OAAO;QACf,OAAO,EAAE,CAAC,SAAS,EAAE,mBAAmB,EAAE,IAAI,CAAC;KAC/C;CACD,CAAA;AAED,MAAM,iBAAiB,GAAG,IAAI,GAAG,CAAyB,uBAAuB,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,CAAC,CAAA;AAE5G;;;GAGG;AACH,MAAM,UAAU,qBAAqB,CAAC,GAAW,EAAE,MAAoB;IACtE,IAAI,MAAM,EAAE,GAAG,GAAG;QAAE,OAAO,GAAG,CAAA;IAE9B,MAAM,QAAQ,GAAiC;QAC9C,qDAAqD;QACrD,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,MAAM,IAAI,6BAA6B,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;QAC3F,wCAAwC;QACxC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,MAAM,IAAI,8BAA8B,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;QAC5F,mDAAmD;QACnD,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC;KAC5B,CAAA;IAED,MAAM,CAAC,GAAG,IAAI,CAAC,QAAQ,EAAE,MAAM,CAAC,CAAA;IAEhC,OAAO,CAAC,CAAC,GAAG,CAAC,CAAA;AACd,CAAC;AAED;;;;GAIG;AACH,MAAM,UAAU,kBAAkB,CAAC,MAAc,EAAE,MAAc;IAChE,OAAO,GAAG,MAAM,IAAI,MAAM,EAAE,CAAA;AAC7B,CAAC;AAwBD,SAAS,iBAAiB,CAAC,MAAoB;IAC9C,sFAAsF;IACtF,yGAAyG;IACzG,OAAO,YAAY,CAAC,MAAM,EAAE;QAC3B,EAAE,MAAM,EAAE,GAAG,EAAE,IAAI,EAAE,CAAC,EAAE,IAAI,EAAE,EAAE,EAAE;QAClC,EAAE,MAAM,EAAE,GAAG,EAAE,IAAI,EAAE,GAAG,EAAE,IAAI,EAAE,GAAG,EAAE;QACrC,EAAE,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE;QACxC,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,EAAE;KAC9B,CAAC,CAAA;AACH,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,kBAAkB,CACjC,IAAgE,EAChE,OAA2B,EAAE;IAE7B,MAAM,MAAM,GAAG,IAAI,CAAC,MAAM,IAAI,IAAI,CAAC,MAAM,CAAA;IACzC,MAAM,UAAU,GAAG,IAAI,CAAC,UAAU,IAAI,iBAAiB,CAAA;IACvD,MAAM,QAAQ,GAAG,IAAI,CAAC,QAAQ,IAAI,CAAC,CAAA;IAEnC,MAAM,MAAM,GAAG,eAAe,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;IAC5C,MAAM,GAAG,GAAG,iBAAiB,CAAC,GAAG,CAAC,MAAM,CAAC,CAAA;IAEzC,IAAI,CAAC,GAAG;QAAE,OAAO,IAAI,CAAA;IAErB,MAAM,MAAM,GAAG,qBAAqB,CAAC,UAAU,CAAC,MAAM,CAAC,EAAE,MAAM,CAAC,CAAA;IAChE,MAAM,MAAM,GAAG,IAAI,CAAC,GAAG,CAAC,OAAO,EAAE,MAAM,CAAC,CAAA;IACxC,MAAM,WAAW,GAAG,kBAAkB,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IAEtD,mEAAmE;IACnE,MAAM,OAAO,GAAG,IAAI,CAAC,MAAM,IAAI,GAAG,CAAC,GAAG,IAAI,MAAM,EAAE,GAAG,QAAQ,CAAA;IAE7D,IAAI,OAAO,EAAE,CAAC;QACb,MAAM,SAAS,GAAG,IAAI,CAAC,GAAG,CAAC,GAAI,EAAE,MAAM,CAAC,CAAA;QACxC,MAAM,SAAS,GAAG,kBAAkB,CAAC,SAAS,EAAE,MAAM,CAAC,CAAA;QACvD,MAAM,UAAU,GAAG,IAAI,CAAC,WAAW,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,WAAW,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,MAAO,CAAA;QACzF,MAAM,GAAG,GAAG,GAAG,UAAU,KAAK,SAAS,KAAK,IAAI,CAAC,QAAQ,KAAK,IAAI,CAAC,MAAM,IAAI,IAAI,CAAC,QAAQ,EAAE,CAAA;QAE5F,OAAO;YACN,GAAG;YACH,UAAU,EAAE;gBACX,GAAG,CAAC,IAAI,CAAC,WAAW,CAAC,CAAC,CAAC,EAAE,YAAY,EAAE,IAAI,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;gBAC/D,MAAM,EAAE,IAAI,CAAC,MAAO;gBACpB,MAAM,EAAE,SAAS;gBACjB,QAAQ,EAAE,IAAI,CAAC,QAAQ;gBACvB,MAAM,EAAE,IAAI,CAAC,MAAM;gBACnB,QAAQ,EAAE,IAAI,CAAC,QAAQ;gBACvB,OAAO,EAAE,IAAI,CAAC,OAAO;aACrB;YACD,MAAM;YACN,QAAQ,EAAE,iBAAiB;SAC3B,CAAA;IACF,CAAC;IAED,kGAAkG;IAClG,oGAAoG;IACpG,MAAM,SAAS,GAAG,OAAO,CAAC,IAAI,CAAC,MAAM,IAAI,IAAI,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAA;IAC5D,MAAM,IAAI,GAAG,SAAS,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,QAAQ,KAAK,IAAI,CAAC,MAAM,IAAI,IAAI,CAAC,QAAQ,EAAE,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,QAAQ,IAAI,IAAI,CAAC,QAAQ,EAAE,CAAA;IAClH,MAAM,GAAG,GAAG,GAAG,WAAW,KAAK,IAAI,EAAE,CAAA;IAErC,OAAO;QACN,GAAG;QACH,UAAU,EAAE;YACX,MAAM,EAAE,WAAW;YACnB,QAAQ,EAAE,IAAI,CAAC,QAAQ;YACvB,GAAG,CAAC,SAAS,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,IAAI,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;YAC7C,QAAQ,EAAE,IAAI,CAAC,QAAQ;YACvB,OAAO,EAAE,IAAI,CAAC,OAAO;SACrB;QACD,MAAM;QACN,QAAQ,EAAE,QAAQ;KAClB,CAAA;AACF,CAAC;AAED;;;;;;GAMG;AACH,MAAM,SAAS,GAA0D;IACxE,EAAE,IAAI,EAAE,KAAK,EAAE,WAAW,EAAE,IAAI,EAAE;IAClC,EAAE,IAAI,EAAE,KAAK,EAAE,WAAW,EAAE,IAAI,EAAE;IAClC,EAAE,IAAI,EAAE,MAAM,EAAE,WAAW,EAAE,KAAK,EAAE;CACpC,CAAA;AAED,MAAM,YAAY,GAAG,CAAC,KAAK,EAAE,KAAK,EAAE,KAAK,CAAU,CAAA;AAEnD;;GAEG;AACH,MAAM,cAAc,GAAwE;IAC3F,EAAE,MAAM,EAAE,IAAI,EAAE,GAAG,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,KAAK,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,IAAI,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,EAAE,EAAE;IACpF,EAAE,MAAM,EAAE,IAAI,EAAE,GAAG,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,KAAK,MAAM,CAAC,GAAG,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,GAAG,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,EAAE,EAAE;IACzF,EAAE,MAAM,EAAE,IAAI,EAAE,GAAG,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,MAAM,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,GAAG,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,EAAE,GAAG,CAAC,EAAE,EAAE;CACpF,CAAA;AAED;;GAEG;AACH,MAAM,UAAU,0BAA0B,CAAC,OAA2B,EAAE;IACvE,MAAM,MAAM,GAAG,IAAI,CAAC,MAAM,IAAI,IAAI,CAAC,MAAM,CAAA;IACzC,MAAM,IAAI,GAAG,IAAI,CAAC,SAAS,EAAE,MAAM,CAAC,CAAA;IACpC,MAAM,MAAM,GAAG,MAAM,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,IAAI,CAAC,CAAC,CAAA;IACtD,MAAM,EAAE,MAAM,EAAE,GAAG,EAAE,GAAG,IAAI,CAAC,cAAc,EAAE,MAAM,CAAC,CAAA;IACpD,MAAM,MAAM,GAAG,GAAG,CAAC,MAAM,CAAC,CAAA;IAC1B,MAAM,EAAE,GAAG,IAAI,CAAC,YAAY,EAAE,MAAM,CAAC,CAAA;IACrC,MAAM,MAAM,GAAG,IAAI,CAAC,WAAW,IAAI,MAAM,EAAE,GAAG,GAAG,CAAA;IACjD,MAAM,QAAQ,GAAG,MAAM,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,IAAI,IAAI,MAAM,QAAQ,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,IAAI,IAAI,MAAM,EAAE,CAAA;IACpH,MAAM,GAAG,GAAG,GAAG,QAAQ,KAAK,EAAE,IAAI,MAAM,IAAI,MAAM,EAAE,CAAA;IAEpD,OAAO;QACN,GAAG;QACH,UAAU,EAAE;YACX,MAAM,EAAE,QAAQ;YAChB,QAAQ,EAAE,EAAE;YACZ,MAAM;YACN,QAAQ,EAAE,MAAM;YAChB,OAAO,EAAE,IAAI;SACb;QACD,MAAM,EAAE,OAAO;QACf,QAAQ,EAAE,iBAAiB;KAC3B,CAAA;AACF,CAAC;AAED,MAAM,uBAAuB,GAAwB,IAAI,GAAG,CAAC,uBAAuB,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAA;AAE1G;;;;;;;GAOG;AACH,MAAM,UAAU,eAAe,CAAC,OAAe;IAC9C,MAAM,MAAM,GAAG,mBAAmB,CAAC,OAAO,CAAC,CAAA;IAE3C,OAAO,uBAAuB,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,OAAO,CAAA;AAC9D,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,gBAAgB;IAC/B,OAAO,uBAAuB,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAA;AACpD,CAAC;AAED;;;;;GAKG;AACH,MAAM,CAAC,MAAM,uBAAuB,GAAwB,IAAI,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,CAAA"}
|
|
@@ -0,0 +1,54 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Street-decomposition synthesizer for Stage 3 training. Generates address rows where
|
|
7
|
+
* `street_prefix`, `street`, and `street_suffix` are emitted as separate BIO spans (instead of
|
|
8
|
+
* monolithic `street`). Mirrors the PO box synthesizer pattern.
|
|
9
|
+
*
|
|
10
|
+
* Why this exists: TIGER/NAD/BAN adapter changes (committed earlier tonight) emit decomposed
|
|
11
|
+
* components from raw source data, but the v0.4.0 parquet slices on Modal were built BEFORE those
|
|
12
|
+
* changes. Rebuilding the full corpus requires downloading raw TIGER/NAD/BAN data and re-running
|
|
13
|
+
* adapters end-to-end — out of scope for a single night shift. This synthesizer takes (locality,
|
|
14
|
+
* region, postcode) tuples and produces freshly-decomposed Stage 3 training rows, same shape as
|
|
15
|
+
* the PO box pipeline.
|
|
16
|
+
*
|
|
17
|
+
* Note: uses the SAME decomposition logic as TIGER's `decomposeStreet()` so the synthetic
|
|
18
|
+
* distribution matches what the model would see if/when TIGER slices are rebuilt with the new
|
|
19
|
+
* adapter.
|
|
20
|
+
*/
|
|
21
|
+
import type { CanonicalRow } from "#types";
|
|
22
|
+
export interface StreetBaseTuple {
|
|
23
|
+
locality: string;
|
|
24
|
+
region: string;
|
|
25
|
+
postcode: string;
|
|
26
|
+
country: string;
|
|
27
|
+
}
|
|
28
|
+
export interface SynthesizedStreetRow {
|
|
29
|
+
raw: string;
|
|
30
|
+
components: CanonicalRow["components"];
|
|
31
|
+
locale: string;
|
|
32
|
+
}
|
|
33
|
+
export interface StreetSynthesisOpts {
|
|
34
|
+
random?: () => number;
|
|
35
|
+
/**
|
|
36
|
+
* Probability of emitting house_number alongside the street. Default 0.85.
|
|
37
|
+
*/
|
|
38
|
+
includeHouseNumberProb?: number;
|
|
39
|
+
/**
|
|
40
|
+
* Probability of emitting the street BARE — no `, City, ST ZIP` tail and no region/locality/ postcode components
|
|
41
|
+
* (just `street_prefix`/`street`/`street_suffix` + optional `house_number`). Default 0 (preserves the original
|
|
42
|
+
* full-address behavior exactly, including the RNG sequence). Set >0 to teach the model that a bare `10th Ave` /
|
|
43
|
+
* `Main St` is a STREET, not a locality — the functional-test failure cluster (bare streets mislabeled `locality`),
|
|
44
|
+
* the bare-format analogue of the v0.7.x intersection-bare fix.
|
|
45
|
+
*/
|
|
46
|
+
bareProb?: number;
|
|
47
|
+
}
|
|
48
|
+
/**
|
|
49
|
+
* Synthesize a US street address with decomposed Stage 3 components. The street is built from PREFIX + NAME + SUFFIX,
|
|
50
|
+
* then passed through the same `decomposeStreet()` utility the TIGER adapter uses — guarantees the synthetic
|
|
51
|
+
* distribution matches the canonical decomposition logic.
|
|
52
|
+
*/
|
|
53
|
+
export declare function synthesizeStreetRow(base: StreetBaseTuple, opts?: StreetSynthesisOpts): SynthesizedStreetRow | null;
|
|
54
|
+
//# sourceMappingURL=street.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"street.d.ts","sourceRoot":"","sources":["../../lib/synthesizers/street.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;GAmBG;AAMH,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,QAAQ,CAAA;AAwI1C,MAAM,WAAW,eAAe;IAC/B,QAAQ,EAAE,MAAM,CAAA;IAChB,MAAM,EAAE,MAAM,CAAA;IACd,QAAQ,EAAE,MAAM,CAAA;IAChB,OAAO,EAAE,MAAM,CAAA;CACf;AAED,MAAM,WAAW,oBAAoB;IACpC,GAAG,EAAE,MAAM,CAAA;IACX,UAAU,EAAE,YAAY,CAAC,YAAY,CAAC,CAAA;IACtC,MAAM,EAAE,MAAM,CAAA;CACd;AAED,MAAM,WAAW,mBAAmB;IACnC,MAAM,CAAC,EAAE,MAAM,MAAM,CAAA;IACrB;;OAEG;IACH,sBAAsB,CAAC,EAAE,MAAM,CAAA;IAC/B;;;;;;OAMG;IACH,QAAQ,CAAC,EAAE,MAAM,CAAA;CACjB;AAcD;;;;GAIG;AACH,wBAAgB,mBAAmB,CAClC,IAAI,EAAE,eAAe,EACrB,IAAI,GAAE,mBAAwB,GAC5B,oBAAoB,GAAG,IAAI,CA0D7B"}
|
|
@@ -0,0 +1,218 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Street-decomposition synthesizer for Stage 3 training. Generates address rows where
|
|
7
|
+
* `street_prefix`, `street`, and `street_suffix` are emitted as separate BIO spans (instead of
|
|
8
|
+
* monolithic `street`). Mirrors the PO box synthesizer pattern.
|
|
9
|
+
*
|
|
10
|
+
* Why this exists: TIGER/NAD/BAN adapter changes (committed earlier tonight) emit decomposed
|
|
11
|
+
* components from raw source data, but the v0.4.0 parquet slices on Modal were built BEFORE those
|
|
12
|
+
* changes. Rebuilding the full corpus requires downloading raw TIGER/NAD/BAN data and re-running
|
|
13
|
+
* adapters end-to-end — out of scope for a single night shift. This synthesizer takes (locality,
|
|
14
|
+
* region, postcode) tuples and produces freshly-decomposed Stage 3 training rows, same shape as
|
|
15
|
+
* the PO box pipeline.
|
|
16
|
+
*
|
|
17
|
+
* Note: uses the SAME decomposition logic as TIGER's `decomposeStreet()` so the synthetic
|
|
18
|
+
* distribution matches what the model would see if/when TIGER slices are rebuilt with the new
|
|
19
|
+
* adapter.
|
|
20
|
+
*/
|
|
21
|
+
import { isPresent } from "@mailwoman/core/objects";
|
|
22
|
+
import { decomposeStreet } from "#adapters/tiger/street-decompose";
|
|
23
|
+
import { pick, tieredNumber } from "#synthesizers/utils";
|
|
24
|
+
// Hand-curated US street name pool. Real frequency-weighted street names — sampled
|
|
25
|
+
// from US Census TIGER 2024 top-1000 by occurrence count. Keep ~50 entries so the
|
|
26
|
+
// synthesis distribution doesn't overfit to a tiny vocabulary.
|
|
27
|
+
/* oxlint-disable sister-software/no-unnamed-threshold -- the bare decimals below are weighted-sampler
|
|
28
|
+
cutoffs, not thresholds: `const r = random()` followed by a cascade of `r < 0.4` branches IS the
|
|
29
|
+
output distribution, and reading the cascade top-to-bottom is how you see it. Naming each cutoff
|
|
30
|
+
would hide the distribution behind a wall of identifiers. Genuine thresholds in these files are
|
|
31
|
+
extracted as named constants above. */
|
|
32
|
+
const STREET_NAMES = [
|
|
33
|
+
"Main",
|
|
34
|
+
"Oak",
|
|
35
|
+
"Maple",
|
|
36
|
+
"Pine",
|
|
37
|
+
"Cedar",
|
|
38
|
+
"Elm",
|
|
39
|
+
"Washington",
|
|
40
|
+
"Lincoln",
|
|
41
|
+
"Jefferson",
|
|
42
|
+
"Park",
|
|
43
|
+
"Lake",
|
|
44
|
+
"Hill",
|
|
45
|
+
"Spring",
|
|
46
|
+
"Center",
|
|
47
|
+
"Church",
|
|
48
|
+
"Mill",
|
|
49
|
+
"School",
|
|
50
|
+
"River",
|
|
51
|
+
"Highland",
|
|
52
|
+
"Sunset",
|
|
53
|
+
"Forest",
|
|
54
|
+
"Meadow",
|
|
55
|
+
"Ridge",
|
|
56
|
+
"Valley",
|
|
57
|
+
"Lakeview",
|
|
58
|
+
"Hillcrest",
|
|
59
|
+
"1st",
|
|
60
|
+
"2nd",
|
|
61
|
+
"3rd",
|
|
62
|
+
"4th",
|
|
63
|
+
"5th",
|
|
64
|
+
"6th",
|
|
65
|
+
"7th",
|
|
66
|
+
"8th",
|
|
67
|
+
"9th",
|
|
68
|
+
"10th",
|
|
69
|
+
"Adams",
|
|
70
|
+
"Madison",
|
|
71
|
+
"Monroe",
|
|
72
|
+
"Jackson",
|
|
73
|
+
"Franklin",
|
|
74
|
+
"Kennedy",
|
|
75
|
+
"Roosevelt",
|
|
76
|
+
"Broadway",
|
|
77
|
+
"Market",
|
|
78
|
+
"Commerce",
|
|
79
|
+
"Industrial",
|
|
80
|
+
"Airport",
|
|
81
|
+
"Hospital",
|
|
82
|
+
"Sherman",
|
|
83
|
+
"Grant",
|
|
84
|
+
"Lee",
|
|
85
|
+
"Custer",
|
|
86
|
+
"Lewis",
|
|
87
|
+
"Clark",
|
|
88
|
+
];
|
|
89
|
+
const STREET_SUFFIXES = [
|
|
90
|
+
"St",
|
|
91
|
+
"Street",
|
|
92
|
+
"Ave",
|
|
93
|
+
"Avenue",
|
|
94
|
+
"Rd",
|
|
95
|
+
"Road",
|
|
96
|
+
"Blvd",
|
|
97
|
+
"Boulevard",
|
|
98
|
+
"Dr",
|
|
99
|
+
"Drive",
|
|
100
|
+
"Ln",
|
|
101
|
+
"Lane",
|
|
102
|
+
"Way",
|
|
103
|
+
"Ct",
|
|
104
|
+
"Court",
|
|
105
|
+
"Pl",
|
|
106
|
+
"Place",
|
|
107
|
+
"Pkwy",
|
|
108
|
+
"Parkway",
|
|
109
|
+
"Ter",
|
|
110
|
+
"Terrace",
|
|
111
|
+
"Cir",
|
|
112
|
+
"Circle",
|
|
113
|
+
"Hwy",
|
|
114
|
+
"Highway",
|
|
115
|
+
];
|
|
116
|
+
const DIRECTIONAL_PREFIXES = [
|
|
117
|
+
"",
|
|
118
|
+
"",
|
|
119
|
+
"",
|
|
120
|
+
"",
|
|
121
|
+
"", // 5 empty entries → 50% no prefix
|
|
122
|
+
"N",
|
|
123
|
+
"S",
|
|
124
|
+
"E",
|
|
125
|
+
"W",
|
|
126
|
+
"NE",
|
|
127
|
+
"NW",
|
|
128
|
+
"SE",
|
|
129
|
+
"SW",
|
|
130
|
+
"North",
|
|
131
|
+
"South",
|
|
132
|
+
"East",
|
|
133
|
+
"West",
|
|
134
|
+
];
|
|
135
|
+
const TRAILING_DIRECTIONALS = [
|
|
136
|
+
"",
|
|
137
|
+
"",
|
|
138
|
+
"",
|
|
139
|
+
"",
|
|
140
|
+
"",
|
|
141
|
+
"",
|
|
142
|
+
"",
|
|
143
|
+
"", // 8 empty → 80% no trailing
|
|
144
|
+
"N",
|
|
145
|
+
"S",
|
|
146
|
+
"E",
|
|
147
|
+
"W",
|
|
148
|
+
"NE",
|
|
149
|
+
"NW",
|
|
150
|
+
"SE",
|
|
151
|
+
"SW",
|
|
152
|
+
];
|
|
153
|
+
function randomHouseNumber(random) {
|
|
154
|
+
// US house number distribution: skewed low. 1-99 (30%), 100-999 (40%),
|
|
155
|
+
// 1000-9999 (25%), 10000+ (5%). The last band's 89_999 span is this file's own
|
|
156
|
+
// (the PO-box generators use 90_000) and is baked into every shipped street slice.
|
|
157
|
+
return tieredNumber(random, [
|
|
158
|
+
{ cutoff: 0.3, base: 1, span: 99 },
|
|
159
|
+
{ cutoff: 0.7, base: 100, span: 900 },
|
|
160
|
+
{ cutoff: 0.95, base: 1000, span: 9000 },
|
|
161
|
+
{ base: 10_000, span: 89_999 },
|
|
162
|
+
]);
|
|
163
|
+
}
|
|
164
|
+
/**
|
|
165
|
+
* Synthesize a US street address with decomposed Stage 3 components. The street is built from PREFIX + NAME + SUFFIX,
|
|
166
|
+
* then passed through the same `decomposeStreet()` utility the TIGER adapter uses — guarantees the synthetic
|
|
167
|
+
* distribution matches the canonical decomposition logic.
|
|
168
|
+
*/
|
|
169
|
+
export function synthesizeStreetRow(base, opts = {}) {
|
|
170
|
+
const random = opts.random ?? Math.random;
|
|
171
|
+
const includeHN = opts.includeHouseNumberProb ?? 0.85;
|
|
172
|
+
if (base.country !== "US")
|
|
173
|
+
return null;
|
|
174
|
+
const prefix = pick(DIRECTIONAL_PREFIXES, random);
|
|
175
|
+
const name = pick(STREET_NAMES, random);
|
|
176
|
+
const suffix = pick(STREET_SUFFIXES, random);
|
|
177
|
+
const trailing = pick(TRAILING_DIRECTIONALS, random);
|
|
178
|
+
// Build the "full" street string the adapter would receive from TIGER FULLNAME.
|
|
179
|
+
const parts = [prefix, name, suffix, trailing].filter(isPresent);
|
|
180
|
+
const fullStreet = parts.join(" ");
|
|
181
|
+
// Pass through the same decomposeStreet TIGER uses — match the training distribution.
|
|
182
|
+
const decomposed = decomposeStreet(fullStreet);
|
|
183
|
+
// NOTE: country is intentionally omitted. We don't emit "USA" or "US" in the raw
|
|
184
|
+
// string, and the aligner's fuzzy match (edit distance 2) will spuriously match
|
|
185
|
+
// "US" against any 2-char token (e.g. a house number "45" is exactly 2 substitutions
|
|
186
|
+
// from "US"). The PO box synthesizer skips country for the same reason.
|
|
187
|
+
// Bare mode is guarded by `> 0` so the default (bareProb=0) consumes no RNG and reproduces the
|
|
188
|
+
// original full-address output byte-for-byte.
|
|
189
|
+
const bareProb = opts.bareProb ?? 0;
|
|
190
|
+
const bare = bareProb > 0 && random() < bareProb;
|
|
191
|
+
const components = bare
|
|
192
|
+
? {}
|
|
193
|
+
: {
|
|
194
|
+
region: base.region,
|
|
195
|
+
locality: base.locality,
|
|
196
|
+
postcode: base.postcode,
|
|
197
|
+
};
|
|
198
|
+
if (decomposed.prefix) {
|
|
199
|
+
components.street_prefix = decomposed.prefix;
|
|
200
|
+
}
|
|
201
|
+
if (decomposed.street) {
|
|
202
|
+
components.street = decomposed.street;
|
|
203
|
+
}
|
|
204
|
+
if (decomposed.suffix) {
|
|
205
|
+
components.street_suffix = decomposed.suffix;
|
|
206
|
+
}
|
|
207
|
+
let raw;
|
|
208
|
+
if (random() < includeHN) {
|
|
209
|
+
const hn = randomHouseNumber(random);
|
|
210
|
+
components.house_number = hn;
|
|
211
|
+
raw = bare ? `${hn} ${fullStreet}` : `${hn} ${fullStreet}, ${base.locality}, ${base.region} ${base.postcode}`;
|
|
212
|
+
}
|
|
213
|
+
else {
|
|
214
|
+
raw = bare ? fullStreet : `${fullStreet}, ${base.locality}, ${base.region} ${base.postcode}`;
|
|
215
|
+
}
|
|
216
|
+
return { raw, components, locale: "en-US" };
|
|
217
|
+
}
|
|
218
|
+
//# sourceMappingURL=street.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"street.js","sourceRoot":"","sources":["../../lib/synthesizers/street.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;GAmBG;AAEH,OAAO,EAAE,SAAS,EAAE,MAAM,yBAAyB,CAAA;AAEnD,OAAO,EAAE,eAAe,EAAE,MAAM,kCAAkC,CAAA;AAClE,OAAO,EAAE,IAAI,EAAE,YAAY,EAAE,MAAM,qBAAqB,CAAA;AAGxD,mFAAmF;AACnF,kFAAkF;AAClF,+DAA+D;AAC/D;;;;yCAIyC;AAEzC,MAAM,YAAY,GAAG;IACpB,MAAM;IACN,KAAK;IACL,OAAO;IACP,MAAM;IACN,OAAO;IACP,KAAK;IACL,YAAY;IACZ,SAAS;IACT,WAAW;IACX,MAAM;IACN,MAAM;IACN,MAAM;IACN,QAAQ;IACR,QAAQ;IACR,QAAQ;IACR,MAAM;IACN,QAAQ;IACR,OAAO;IACP,UAAU;IACV,QAAQ;IACR,QAAQ;IACR,QAAQ;IACR,OAAO;IACP,QAAQ;IACR,UAAU;IACV,WAAW;IACX,KAAK;IACL,KAAK;IACL,KAAK;IACL,KAAK;IACL,KAAK;IACL,KAAK;IACL,KAAK;IACL,KAAK;IACL,KAAK;IACL,MAAM;IACN,OAAO;IACP,SAAS;IACT,QAAQ;IACR,SAAS;IACT,UAAU;IACV,SAAS;IACT,WAAW;IACX,UAAU;IACV,QAAQ;IACR,UAAU;IACV,YAAY;IACZ,SAAS;IACT,UAAU;IACV,SAAS;IACT,OAAO;IACP,KAAK;IACL,QAAQ;IACR,OAAO;IACP,OAAO;CACE,CAAA;AAEV,MAAM,eAAe,GAAG;IACvB,IAAI;IACJ,QAAQ;IACR,KAAK;IACL,QAAQ;IACR,IAAI;IACJ,MAAM;IACN,MAAM;IACN,WAAW;IACX,IAAI;IACJ,OAAO;IACP,IAAI;IACJ,MAAM;IACN,KAAK;IACL,IAAI;IACJ,OAAO;IACP,IAAI;IACJ,OAAO;IACP,MAAM;IACN,SAAS;IACT,KAAK;IACL,SAAS;IACT,KAAK;IACL,QAAQ;IACR,KAAK;IACL,SAAS;CACA,CAAA;AAEV,MAAM,oBAAoB,GAAG;IAC5B,EAAE;IACF,EAAE;IACF,EAAE;IACF,EAAE;IACF,EAAE,EAAE,kCAAkC;IACtC,GAAG;IACH,GAAG;IACH,GAAG;IACH,GAAG;IACH,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,OAAO;IACP,OAAO;IACP,MAAM;IACN,MAAM;CACG,CAAA;AAEV,MAAM,qBAAqB,GAAG;IAC7B,EAAE;IACF,EAAE;IACF,EAAE;IACF,EAAE;IACF,EAAE;IACF,EAAE;IACF,EAAE;IACF,EAAE,EAAE,4BAA4B;IAChC,GAAG;IACH,GAAG;IACH,GAAG;IACH,GAAG;IACH,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;CACK,CAAA;AA+BV,SAAS,iBAAiB,CAAC,MAAoB;IAC9C,uEAAuE;IACvE,+EAA+E;IAC/E,mFAAmF;IACnF,OAAO,YAAY,CAAC,MAAM,EAAE;QAC3B,EAAE,MAAM,EAAE,GAAG,EAAE,IAAI,EAAE,CAAC,EAAE,IAAI,EAAE,EAAE,EAAE;QAClC,EAAE,MAAM,EAAE,GAAG,EAAE,IAAI,EAAE,GAAG,EAAE,IAAI,EAAE,GAAG,EAAE;QACrC,EAAE,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE;QACxC,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,EAAE;KAC9B,CAAC,CAAA;AACH,CAAC;AAED;;;;GAIG;AACH,MAAM,UAAU,mBAAmB,CAClC,IAAqB,EACrB,OAA4B,EAAE;IAE9B,MAAM,MAAM,GAAG,IAAI,CAAC,MAAM,IAAI,IAAI,CAAC,MAAM,CAAA;IACzC,MAAM,SAAS,GAAG,IAAI,CAAC,sBAAsB,IAAI,IAAI,CAAA;IAErD,IAAI,IAAI,CAAC,OAAO,KAAK,IAAI;QAAE,OAAO,IAAI,CAAA;IAEtC,MAAM,MAAM,GAAG,IAAI,CAAC,oBAAoB,EAAE,MAAM,CAAC,CAAA;IACjD,MAAM,IAAI,GAAG,IAAI,CAAC,YAAY,EAAE,MAAM,CAAC,CAAA;IACvC,MAAM,MAAM,GAAG,IAAI,CAAC,eAAe,EAAE,MAAM,CAAC,CAAA;IAC5C,MAAM,QAAQ,GAAG,IAAI,CAAC,qBAAqB,EAAE,MAAM,CAAC,CAAA;IAEpD,gFAAgF;IAChF,MAAM,KAAK,GAAG,CAAC,MAAM,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAA;IAChE,MAAM,UAAU,GAAG,KAAK,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;IAElC,sFAAsF;IACtF,MAAM,UAAU,GAAG,eAAe,CAAC,UAAU,CAAC,CAAA;IAE9C,iFAAiF;IACjF,gFAAgF;IAChF,qFAAqF;IACrF,wEAAwE;IACxE,+FAA+F;IAC/F,8CAA8C;IAC9C,MAAM,QAAQ,GAAG,IAAI,CAAC,QAAQ,IAAI,CAAC,CAAA;IACnC,MAAM,IAAI,GAAG,QAAQ,GAAG,CAAC,IAAI,MAAM,EAAE,GAAG,QAAQ,CAAA;IAEhD,MAAM,UAAU,GAA+B,IAAI;QAClD,CAAC,CAAC,EAAE;QACJ,CAAC,CAAC;YACA,MAAM,EAAE,IAAI,CAAC,MAAM;YACnB,QAAQ,EAAE,IAAI,CAAC,QAAQ;YACvB,QAAQ,EAAE,IAAI,CAAC,QAAQ;SACvB,CAAA;IAEH,IAAI,UAAU,CAAC,MAAM,EAAE,CAAC;QACvB,UAAU,CAAC,aAAa,GAAG,UAAU,CAAC,MAAM,CAAA;IAC7C,CAAC;IAED,IAAI,UAAU,CAAC,MAAM,EAAE,CAAC;QACvB,UAAU,CAAC,MAAM,GAAG,UAAU,CAAC,MAAM,CAAA;IACtC,CAAC;IAED,IAAI,UAAU,CAAC,MAAM,EAAE,CAAC;QACvB,UAAU,CAAC,aAAa,GAAG,UAAU,CAAC,MAAM,CAAA;IAC7C,CAAC;IAED,IAAI,GAAW,CAAA;IAEf,IAAI,MAAM,EAAE,GAAG,SAAS,EAAE,CAAC;QAC1B,MAAM,EAAE,GAAG,iBAAiB,CAAC,MAAM,CAAC,CAAA;QACpC,UAAU,CAAC,YAAY,GAAG,EAAE,CAAA;QAC5B,GAAG,GAAG,IAAI,CAAC,CAAC,CAAC,GAAG,EAAE,IAAI,UAAU,EAAE,CAAC,CAAC,CAAC,GAAG,EAAE,IAAI,UAAU,KAAK,IAAI,CAAC,QAAQ,KAAK,IAAI,CAAC,MAAM,IAAI,IAAI,CAAC,QAAQ,EAAE,CAAA;IAC9G,CAAC;SAAM,CAAC;QACP,GAAG,GAAG,IAAI,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,GAAG,UAAU,KAAK,IAAI,CAAC,QAAQ,KAAK,IAAI,CAAC,MAAM,IAAI,IAAI,CAAC,QAAQ,EAAE,CAAA;IAC7F,CAAC;IAED,OAAO,EAAE,GAAG,EAAE,UAAU,EAAE,MAAM,EAAE,OAAO,EAAE,CAAA;AAC5C,CAAC"}
|