@mailwoman/corpus 9.1.0 → 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 +24 -24
- package/data/PROVENANCE.md +20 -7
- package/data/reviewed-ve-postcode-tuples.json +74 -0
- 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/state-ia-contractors/adapter.ts +144 -0
- package/lib/adapters/state-ny-notaries/adapter.ts +141 -0
- package/lib/adapters/state-tx-notaries/adapter.ts +157 -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/license.ts +50 -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 +44 -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 +68 -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 +46 -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 +72 -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 +34 -0
- package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.js +111 -0
- package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.d.ts +32 -0
- package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.js +119 -0
- package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.d.ts +33 -0
- package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.js +125 -0
- package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
- package/out/adapters/synth-po-box/adapter.d.ts +67 -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 +39 -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 +46 -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 +65 -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 +14 -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 +47 -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 +350 -65
- package/out/src/adapters/ban/adapter.d.ts +0 -44
- package/out/src/adapters/ban/adapter.d.ts.map +0 -1
- package/out/src/adapters/ban/adapter.js +0 -148
- 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 +0 -68
- 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 +0 -46
- 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 +0 -72
- 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 -132
- package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.d.ts +0 -34
- package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.js +0 -106
- package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.d.ts +0 -32
- package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.js +0 -125
- package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.d.ts +0 -33
- package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.js +0 -120
- package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.d.ts +0 -67
- 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 -138
- 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 -110
- 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 -123
- 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 +0 -39
- 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 +0 -46
- 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 -155
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
- package/out/src/adapters/utils/index.d.ts +0 -144
- package/out/src/adapters/utils/index.d.ts.map +0 -1
- package/out/src/adapters/utils/index.js +0 -151
- package/out/src/adapters/utils/index.js.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.d.ts +0 -65
- 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 -93
- package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.js +0 -248
- package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -70
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.js +0 -185
- package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
- package/out/src/build.d.ts +0 -131
- package/out/src/build.d.ts.map +0 -1
- package/out/src/build.js +0 -248
- 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 -64
- 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 -83
- package/out/src/shard-recipes/anchor-absorption.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 -405
- 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 -82
- 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 -187
- 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 -82
- 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 -225
- 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 -207
- 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 -83
- 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 -458
- 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/scaffold.d.ts +0 -217
- package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
- package/out/src/shard-recipes/scaffold.js +0 -138
- 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 -709
- package/out/src/shard-recipes/sub-venue.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 -253
- 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 -220
- 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 -707
- 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 -255
- package/out/src/tools/fetch/ban.js.map +0 -1
- package/out/src/tools/fetch/download.d.ts +0 -69
- package/out/src/tools/fetch/download.d.ts.map +0 -1
- package/out/src/tools/fetch/download.js +0 -100
- package/out/src/tools/fetch/download.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 -133
- package/out/src/tools/fetch/index.d.ts.map +0 -1
- package/out/src/tools/fetch/index.js +0 -132
- 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 -225
- 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 -124
- 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 -316
- 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 -123
- package/out/src/tools/fetch/ourairports.js.map +0 -1
- package/out/src/tools/fetch/ppd.d.ts +0 -18
- 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 -178
- package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
- package/out/src/tools/fetch/state-sources.d.ts +0 -22
- package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
- package/out/src/tools/fetch/state-sources.js +0 -115
- 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 -254
- 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 -404
- 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 -307
- 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 -35
- package/out/src/tools/overlay-manifest.d.ts.map +0 -1
- package/out/src/tools/overlay-manifest.js +0 -88
- 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/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 -101
- 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 -197
- package/out/src/tools/shard-translit.js.map +0 -1
- package/out/src/tools/sub-venue-lexicon.d.ts +0 -507
- package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
- package/out/src/tools/sub-venue-lexicon.js +0 -817
- 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 +0 -47
- package/out/src/utils/license.js.map +0 -1
- package/out/src/utils/parquet.d.ts +0 -143
- package/out/src/utils/parquet.d.ts.map +0 -1
- package/out/src/utils/parquet.js +0 -258
- 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 -189
- package/src/adapters/ban/street-decompose.ts +0 -96
- package/src/adapters/fcc-bdc/adapter.ts +0 -173
- package/src/adapters/geonames/adapter.ts +0 -199
- package/src/adapters/geonames-postal/adapter.ts +0 -118
- package/src/adapters/gnaf/adapter.ts +0 -148
- package/src/adapters/gnaf/assemble.ts +0 -226
- package/src/adapters/index.ts +0 -149
- package/src/adapters/openaddresses/adapter.ts +0 -250
- package/src/adapters/overture/adapter.ts +0 -161
- package/src/adapters/state-hi-schools/adapter.ts +0 -162
- package/src/adapters/state-ia-contractors/adapter.ts +0 -138
- package/src/adapters/state-ny-notaries/adapter.ts +0 -159
- package/src/adapters/state-tx-notaries/adapter.ts +0 -151
- package/src/adapters/synth-po-box/adapter.ts +0 -203
- package/src/adapters/tiger/adapter.ts +0 -252
- package/src/adapters/tiger/street-decompose.ts +0 -111
- package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -181
- package/src/adapters/usgov-imls-pls/adapter.ts +0 -138
- package/src/adapters/usgov-irs-bmf/adapter.ts +0 -161
- package/src/adapters/usgov-nad/adapter.ts +0 -347
- package/src/adapters/usgov-nppes/adapter.ts +0 -157
- package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -202
- package/src/adapters/utils/index.ts +0 -220
- package/src/adapters/wof-admin-jp/adapter.ts +0 -219
- package/src/adapters/wof-admin-json/adapter.ts +0 -294
- package/src/adapters/wof-postalcode-json/adapter.ts +0 -216
- 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 -88
- package/src/parquet-wrapper/schema.ts +0 -88
- package/src/parquet-wrapper/writer.ts +0 -110
- package/src/runner.ts +0 -322
- package/src/shard-recipes/anchor-absorption.ts +0 -103
- package/src/shard-recipes/boundary-stress.ts +0 -104
- package/src/shard-recipes/country-balanced.ts +0 -522
- package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -92
- package/src/shard-recipes/fr-admin-split.ts +0 -237
- package/src/shard-recipes/fr-bare-street.ts +0 -95
- package/src/shard-recipes/fr-fragment.ts +0 -332
- package/src/shard-recipes/fr-lieudit.ts +0 -300
- package/src/shard-recipes/fr-order.ts +0 -256
- package/src/shard-recipes/german.ts +0 -169
- package/src/shard-recipes/house-venue.ts +0 -88
- package/src/shard-recipes/index.ts +0 -89
- package/src/shard-recipes/intersection.ts +0 -629
- package/src/shard-recipes/locale.ts +0 -601
- 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 -919
- package/src/shard-recipes/po-box.ts +0 -123
- package/src/shard-recipes/scaffold.ts +0 -329
- package/src/shard-recipes/si-bare-village.ts +0 -97
- package/src/shard-recipes/street-affix.ts +0 -825
- 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 -895
- package/src/shard-recipes/sub-venue.ts +0 -982
- package/src/shard-recipes/unit.ts +0 -320
- package/src/synthesizers/anchor-absorption.ts +0 -290
- package/src/synthesizers/boundary-stress.ts +0 -531
- package/src/synthesizers/german.ts +0 -250
- package/src/synthesizers/house-venue.ts +0 -316
- 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 -272
- package/src/synthesizers/utils.ts +0 -901
- package/src/tools/align-shard.ts +0 -69
- package/src/tools/audit.ts +0 -399
- package/src/tools/corpus-stats.ts +0 -184
- package/src/tools/fetch/ban.ts +0 -310
- package/src/tools/fetch/download.ts +0 -158
- package/src/tools/fetch/hrsa.ts +0 -68
- package/src/tools/fetch/imls-pls.ts +0 -158
- package/src/tools/fetch/index.ts +0 -136
- package/src/tools/fetch/nad.ts +0 -331
- package/src/tools/fetch/nppes.ts +0 -172
- package/src/tools/fetch/openaddresses.ts +0 -408
- package/src/tools/fetch/ourairports.ts +0 -166
- package/src/tools/fetch/ppd.ts +0 -137
- package/src/tools/fetch/state-hi-schools.ts +0 -228
- package/src/tools/fetch/state-sources.ts +0 -155
- package/src/tools/fetch/tiger-full.ts +0 -361
- package/src/tools/fetch/wikidata-subvenue.ts +0 -386
- package/src/tools/golden-expand.ts +0 -573
- 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 -435
- 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 -145
- package/src/tools/overture-subvenue.ts +0 -215
- package/src/tools/shard-kryptonite.ts +0 -138
- package/src/tools/shard-translit.ts +0 -270
- package/src/tools/sub-venue-lexicon.ts +0 -1250
- package/src/tools/sub-venue-promotions.ts +0 -330
- package/src/types.ts +0 -247
- package/src/utils/align.ts +0 -330
- package/src/utils/golden.ts +0 -176
- package/src/utils/index.ts +0 -14
- package/src/utils/license.ts +0 -50
- package/src/utils/parquet.ts +0 -377
- package/src/utils/split.ts +0 -278
- package/src/utils/tokenize.ts +0 -78
- package/src/utils/wof-json.ts +0 -244
- /package/{src → lib}/codex/us-fips-state.ts +0 -0
- /package/{src → lib}/tools/gb-title-case.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/tiger/street-decompose.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}/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
|
@@ -0,0 +1,83 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
* @file Deterministic canonical-row emission shared by WOF GeoJSON adapters.
|
|
6
|
+
*/
|
|
7
|
+
import { formatAddress, reconcileComponents } from "@mailwoman/formatter";
|
|
8
|
+
import { normalizeNameKey } from "#utils";
|
|
9
|
+
/**
|
|
10
|
+
* Display name for the country, keyed by ISO 3166-1 alpha-2.
|
|
11
|
+
*
|
|
12
|
+
* Must be the **OpenCage-canonical** surface form: the `address-formatter` library expands some country names en route
|
|
13
|
+
* to its output (e.g. `"United States"` → `"United States of America"`). If `components.country` and the formatted
|
|
14
|
+
* `raw` disagree, alignment will fail downstream. Keying off the canonical form keeps the two in lockstep.
|
|
15
|
+
*
|
|
16
|
+
* Phase 1 US + FR only; extend as new locales come online. Missing countries fall back to the country row's `wof:name`,
|
|
17
|
+
* accepting the alignment risk for non-canonicalized names.
|
|
18
|
+
*/
|
|
19
|
+
export const COUNTRY_DISPLAY_NAME = {
|
|
20
|
+
US: "United States of America",
|
|
21
|
+
FR: "France",
|
|
22
|
+
};
|
|
23
|
+
/**
|
|
24
|
+
* BCP-47 locale defaulting for the corpus row's `locale` field. Defaulted by country.
|
|
25
|
+
*/
|
|
26
|
+
export const LOCALE_BY_COUNTRY = {
|
|
27
|
+
US: "en-US",
|
|
28
|
+
FR: "fr-FR",
|
|
29
|
+
};
|
|
30
|
+
/**
|
|
31
|
+
* Build the per-record name-slot list: the canonical `"default"` slot, then every `name:*` variant deduplicated against
|
|
32
|
+
* it so a redundant `"default"`-equivalent row is not emitted under a localized key.
|
|
33
|
+
*/
|
|
34
|
+
export function nameSlotsFor(rec, options = {}) {
|
|
35
|
+
const canonicalSelfName = options.canonicalName?.(rec) ?? rec.name;
|
|
36
|
+
const seen = new Set([canonicalSelfName]);
|
|
37
|
+
const slots = [{ key: "default", value: canonicalSelfName }];
|
|
38
|
+
for (const [rawKey, value] of rec.nameVariants) {
|
|
39
|
+
if (seen.has(value))
|
|
40
|
+
continue;
|
|
41
|
+
seen.add(value);
|
|
42
|
+
slots.push({ key: normalizeNameKey(rawKey), value });
|
|
43
|
+
}
|
|
44
|
+
return slots;
|
|
45
|
+
}
|
|
46
|
+
/**
|
|
47
|
+
* Emit aligned rows in WOF-id order, enforcing the adapter limit across all name and hierarchy variants.
|
|
48
|
+
*/
|
|
49
|
+
export function* emitWOFJSONRows(options) {
|
|
50
|
+
const { records, ancestry, adapterOptions, adapterID, localeByCountry, shouldEmit = () => true, nameSlotsFor: slotsForRecord, variantsFor, } = options;
|
|
51
|
+
let emitted = 0;
|
|
52
|
+
for (const id of [...records.keys()].toSorted((a, b) => a - b)) {
|
|
53
|
+
if (adapterOptions.signal?.aborted)
|
|
54
|
+
return;
|
|
55
|
+
const record = records.get(id);
|
|
56
|
+
if (!shouldEmit(record))
|
|
57
|
+
continue;
|
|
58
|
+
for (const slot of slotsForRecord(record)) {
|
|
59
|
+
for (const variant of variantsFor(record, ancestry.get(id) ?? [], slot.value)) {
|
|
60
|
+
if (adapterOptions.limit !== undefined && emitted >= adapterOptions.limit)
|
|
61
|
+
return;
|
|
62
|
+
const raw = formatAddress(variant.components, record.country, { separator: ", " });
|
|
63
|
+
if (!raw)
|
|
64
|
+
continue;
|
|
65
|
+
const components = reconcileComponents(variant.components, raw);
|
|
66
|
+
if (!Object.keys(components).length)
|
|
67
|
+
continue;
|
|
68
|
+
yield {
|
|
69
|
+
raw,
|
|
70
|
+
components,
|
|
71
|
+
country: record.country,
|
|
72
|
+
locale: localeByCountry[record.country],
|
|
73
|
+
source: adapterID,
|
|
74
|
+
source_id: `${adapterID}-${record.id}-${slot.key}-${variant.suffix}`,
|
|
75
|
+
corpus_version: "",
|
|
76
|
+
license: "CC0-1.0",
|
|
77
|
+
};
|
|
78
|
+
emitted++;
|
|
79
|
+
}
|
|
80
|
+
}
|
|
81
|
+
}
|
|
82
|
+
}
|
|
83
|
+
//# sourceMappingURL=wof-json-rows.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"wof-json-rows.js","sourceRoot":"","sources":["../../lib/adapters/wof-json-rows.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAGH,OAAO,EAAE,aAAa,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AAGzE,OAAO,EAAE,gBAAgB,EAAkB,MAAM,QAAQ,CAAA;AAEzD;;;;;;;;;GASG;AACH,MAAM,CAAC,MAAM,oBAAoB,GAA2B;IAC3D,EAAE,EAAE,0BAA0B;IAC9B,EAAE,EAAE,QAAQ;CACZ,CAAA;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,iBAAiB,GAA2B;IACxD,EAAE,EAAE,OAAO;IACX,EAAE,EAAE,OAAO;CACX,CAAA;AAeD;;;GAGG;AACH,MAAM,UAAU,YAAY,CAAC,GAAc,EAAE,UAA2B,EAAE;IACzE,MAAM,iBAAiB,GAAG,OAAO,CAAC,aAAa,EAAE,CAAC,GAAG,CAAC,IAAI,GAAG,CAAC,IAAI,CAAA;IAElE,MAAM,IAAI,GAAG,IAAI,GAAG,CAAS,CAAC,iBAAiB,CAAC,CAAC,CAAA;IACjD,MAAM,KAAK,GAA0C,CAAC,EAAE,GAAG,EAAE,SAAS,EAAE,KAAK,EAAE,iBAAiB,EAAE,CAAC,CAAA;IAEnG,KAAK,MAAM,CAAC,MAAM,EAAE,KAAK,CAAC,IAAI,GAAG,CAAC,YAAY,EAAE,CAAC;QAChD,IAAI,IAAI,CAAC,GAAG,CAAC,KAAK,CAAC;YAAE,SAAQ;QAC7B,IAAI,CAAC,GAAG,CAAC,KAAK,CAAC,CAAA;QACf,KAAK,CAAC,IAAI,CAAC,EAAE,GAAG,EAAE,gBAAgB,CAAC,MAAM,CAAC,EAAE,KAAK,EAAE,CAAC,CAAA;IACrD,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC;AAaD;;GAEG;AACH,MAAM,SAAS,CAAC,CAAC,eAAe,CAAC,OAA+B;IAC/D,MAAM,EACL,OAAO,EACP,QAAQ,EACR,cAAc,EACd,SAAS,EACT,eAAe,EACf,UAAU,GAAG,GAAG,EAAE,CAAC,IAAI,EACvB,YAAY,EAAE,cAAc,EAC5B,WAAW,GACX,GAAG,OAAO,CAAA;IAEX,IAAI,OAAO,GAAG,CAAC,CAAA;IAEf,KAAK,MAAM,EAAE,IAAI,CAAC,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC;QAChE,IAAI,cAAc,CAAC,MAAM,EAAE,OAAO;YAAE,OAAM;QAC1C,MAAM,MAAM,GAAG,OAAO,CAAC,GAAG,CAAC,EAAE,CAAE,CAAA;QAE/B,IAAI,CAAC,UAAU,CAAC,MAAM,CAAC;YAAE,SAAQ;QAEjC,KAAK,MAAM,IAAI,IAAI,cAAc,CAAC,MAAM,CAAC,EAAE,CAAC;YAC3C,KAAK,MAAM,OAAO,IAAI,WAAW,CAAC,MAAM,EAAE,QAAQ,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,EAAE,EAAE,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;gBAC/E,IAAI,cAAc,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,cAAc,CAAC,KAAK;oBAAE,OAAM;gBAEjF,MAAM,GAAG,GAAG,aAAa,CAAC,OAAO,CAAC,UAAU,EAAE,MAAM,CAAC,OAAO,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;gBAElF,IAAI,CAAC,GAAG;oBAAE,SAAQ;gBAClB,MAAM,UAAU,GAAG,mBAAmB,CAAC,OAAO,CAAC,UAAU,EAAE,GAAG,CAAC,CAAA;gBAE/D,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,UAAU,CAAC,CAAC,MAAM;oBAAE,SAAQ;gBAE7C,MAAM;oBACL,GAAG;oBACH,UAAU;oBACV,OAAO,EAAE,MAAM,CAAC,OAAO;oBACvB,MAAM,EAAE,eAAe,CAAC,MAAM,CAAC,OAAO,CAAC;oBACvC,MAAM,EAAE,SAAS;oBACjB,SAAS,EAAE,GAAG,SAAS,IAAI,MAAM,CAAC,EAAE,IAAI,IAAI,CAAC,GAAG,IAAI,OAAO,CAAC,MAAM,EAAE;oBACpE,cAAc,EAAE,EAAE;oBAClB,OAAO,EAAE,SAAS;iBAClB,CAAA;gBAED,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;IACF,CAAC;AACF,CAAC"}
|
|
@@ -0,0 +1,65 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* `wof-postalcode`: Who's On First postalcode GeoJSON-bundle adapter.
|
|
7
|
+
*
|
|
8
|
+
* **Phase 1.5.1 pivot.** Replaces the previous SpatiaLite-backed implementation (formerly at
|
|
9
|
+
* `packages/corpus/lib/adapters/wof-postalcode/`, removed in this same change). The rationale is
|
|
10
|
+
* in `wof-admin-json/adapter.ts` and in `DECISIONS.md` — short version: the SQLite distribution
|
|
11
|
+
* mirror is dead, the live distro tags every postcode row `mz:is_current = -1` which the old
|
|
12
|
+
* `is_current = 1` predicate excluded, and localized `name:*` variants don't ship in the SQLite
|
|
13
|
+
* export at all.
|
|
14
|
+
*
|
|
15
|
+
* Input: a directory containing one or more cloned `whosonfirst-data-postalcode-<cc>` repos plus
|
|
16
|
+
* the relevant `whosonfirst-data-admin-<cc>` repos (postcode records reference admin ancestry by
|
|
17
|
+
* `wof:parent_id`, so the locality / region / country records must be in the same walk for the
|
|
18
|
+
* ancestry chain to resolve). The corpus pipeline clones all four repos under
|
|
19
|
+
* `/data/corpus/sources/wof/repos/` and points the adapter at that root.
|
|
20
|
+
*
|
|
21
|
+
* Per live postalcode record, the adapter emits one row per `(name-variant, hierarchy-variant)`
|
|
22
|
+
* pair:
|
|
23
|
+
*
|
|
24
|
+
* - **Name variants**: canonical `wof:name` (slot key `default`, typically the postcode digits
|
|
25
|
+
* themselves) plus any `name:*` variants on the postcode feature. In practice WOF postcode
|
|
26
|
+
* records rarely carry localized name variants, so this expansion is usually a no-op — but
|
|
27
|
+
* the code path stays symmetric with the admin adapter for consistency.
|
|
28
|
+
* - **Hierarchy variants** (unchanged from the SQLite adapter): self, +locality, +locality+region,
|
|
29
|
+
* +locality+region+country.
|
|
30
|
+
*
|
|
31
|
+
* `source_id` is `wof-postalcode-<wof_id>-<name-slot>-<hierarchy-variant>`. Ancestor names always
|
|
32
|
+
* come from the ancestor's canonical `wof:name`; this adapter does NOT iterate ancestor name
|
|
33
|
+
* variants (e.g. it does not emit `"75008 Париж"` even when Paris has a `name:rus_x_preferred`).
|
|
34
|
+
* That cross-product belongs to a future synthesis pass; emitting it here would multiply row
|
|
35
|
+
* counts ~10× without a clear training-value story.
|
|
36
|
+
*
|
|
37
|
+
* License: CC0.
|
|
38
|
+
*/
|
|
39
|
+
import { type WOFVariantSpec } from "#adapters/wof-json-rows";
|
|
40
|
+
import type { CorpusAdapter } from "#types";
|
|
41
|
+
import { type WOFRecord } from "#utils";
|
|
42
|
+
/**
|
|
43
|
+
* Compute hierarchy variants for a postcode record. `selfName` is the postcode surface form (canonical `wof:name` for
|
|
44
|
+
* the `default` slot, a `name:*` localized variant otherwise).
|
|
45
|
+
*/
|
|
46
|
+
export declare function postcodeVariantsFor(row: WOFRecord, ancestry: WOFRecord[], selfName: string): WOFVariantSpec[];
|
|
47
|
+
/**
|
|
48
|
+
* Build the per-record name-slot list. The `default` slot uses `wof:name` verbatim (postcode digits); subsequent slots
|
|
49
|
+
* come from `name:*` variants dedup'd against the default.
|
|
50
|
+
*/
|
|
51
|
+
export declare function nameSlotsFor(rec: WOFRecord): Array<{
|
|
52
|
+
key: string;
|
|
53
|
+
value: string;
|
|
54
|
+
}>;
|
|
55
|
+
/**
|
|
56
|
+
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
57
|
+
* it came from.
|
|
58
|
+
*/
|
|
59
|
+
export declare const WOF_POSTALCODE_ADAPTER_ID = "wof-postalcode";
|
|
60
|
+
export declare function createWOFPostalcodeAdapter(): CorpusAdapter;
|
|
61
|
+
/**
|
|
62
|
+
* The configured adapter instance registered with the corpus builder.
|
|
63
|
+
*/
|
|
64
|
+
export declare const wofPostalcodeAdapter: CorpusAdapter;
|
|
65
|
+
//# sourceMappingURL=adapter.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../lib/adapters/wof-postalcode-json/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAqCG;AAKH,OAAO,EAKN,KAAK,cAAc,EACnB,MAAM,yBAAyB,CAAA;AAChC,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,QAAQ,CAAA;AACzE,OAAO,EAAoC,KAAK,SAAS,EAAE,MAAM,QAAQ,CAAA;AA0BzE;;;GAGG;AACH,wBAAgB,mBAAmB,CAAC,GAAG,EAAE,SAAS,EAAE,QAAQ,EAAE,SAAS,EAAE,EAAE,QAAQ,EAAE,MAAM,GAAG,cAAc,EAAE,CAqC7G;AAED;;;GAGG;AACH,wBAAgB,YAAY,CAAC,GAAG,EAAE,SAAS,GAAG,KAAK,CAAC;IAAE,GAAG,EAAE,MAAM,CAAC;IAAC,KAAK,EAAE,MAAM,CAAA;CAAE,CAAC,CAElF;AAED;;;GAGG;AACH,eAAO,MAAM,yBAAyB,mBAAmB,CAAA;AAEzD,wBAAgB,0BAA0B,IAAI,aAAa,CAqC1D;AAED;;GAEG;AACH,eAAO,MAAM,oBAAoB,eAA+B,CAAA"}
|
|
@@ -0,0 +1,151 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* `wof-postalcode`: Who's On First postalcode GeoJSON-bundle adapter.
|
|
7
|
+
*
|
|
8
|
+
* **Phase 1.5.1 pivot.** Replaces the previous SpatiaLite-backed implementation (formerly at
|
|
9
|
+
* `packages/corpus/lib/adapters/wof-postalcode/`, removed in this same change). The rationale is
|
|
10
|
+
* in `wof-admin-json/adapter.ts` and in `DECISIONS.md` — short version: the SQLite distribution
|
|
11
|
+
* mirror is dead, the live distro tags every postcode row `mz:is_current = -1` which the old
|
|
12
|
+
* `is_current = 1` predicate excluded, and localized `name:*` variants don't ship in the SQLite
|
|
13
|
+
* export at all.
|
|
14
|
+
*
|
|
15
|
+
* Input: a directory containing one or more cloned `whosonfirst-data-postalcode-<cc>` repos plus
|
|
16
|
+
* the relevant `whosonfirst-data-admin-<cc>` repos (postcode records reference admin ancestry by
|
|
17
|
+
* `wof:parent_id`, so the locality / region / country records must be in the same walk for the
|
|
18
|
+
* ancestry chain to resolve). The corpus pipeline clones all four repos under
|
|
19
|
+
* `/data/corpus/sources/wof/repos/` and points the adapter at that root.
|
|
20
|
+
*
|
|
21
|
+
* Per live postalcode record, the adapter emits one row per `(name-variant, hierarchy-variant)`
|
|
22
|
+
* pair:
|
|
23
|
+
*
|
|
24
|
+
* - **Name variants**: canonical `wof:name` (slot key `default`, typically the postcode digits
|
|
25
|
+
* themselves) plus any `name:*` variants on the postcode feature. In practice WOF postcode
|
|
26
|
+
* records rarely carry localized name variants, so this expansion is usually a no-op — but
|
|
27
|
+
* the code path stays symmetric with the admin adapter for consistency.
|
|
28
|
+
* - **Hierarchy variants** (unchanged from the SQLite adapter): self, +locality, +locality+region,
|
|
29
|
+
* +locality+region+country.
|
|
30
|
+
*
|
|
31
|
+
* `source_id` is `wof-postalcode-<wof_id>-<name-slot>-<hierarchy-variant>`. Ancestor names always
|
|
32
|
+
* come from the ancestor's canonical `wof:name`; this adapter does NOT iterate ancestor name
|
|
33
|
+
* variants (e.g. it does not emit `"75008 Париж"` even when Paris has a `name:rus_x_preferred`).
|
|
34
|
+
* That cross-product belongs to a future synthesis pass; emitting it here would multiply row
|
|
35
|
+
* counts ~10× without a clear training-value story.
|
|
36
|
+
*
|
|
37
|
+
* License: CC0.
|
|
38
|
+
*/
|
|
39
|
+
import { COUNTRY_DISPLAY_NAME, emitWOFJSONRows, LOCALE_BY_COUNTRY, nameSlotsFor as wofNameSlotsFor, } from "#adapters/wof-json-rows";
|
|
40
|
+
import { buildAncestryIndex, walkFeatures } from "#utils";
|
|
41
|
+
/**
|
|
42
|
+
* Map a WOF placetype to a Mailwoman `ComponentTag`, or `undefined` to skip.
|
|
43
|
+
*
|
|
44
|
+
* Per-adapter deliberately (the admin adapter carries its own): each table is a record FILTER for its adapter's
|
|
45
|
+
* emission set — this one keeps `postalcode` plus the ancestry placetypes its variants render — not a shared
|
|
46
|
+
* vocabulary.
|
|
47
|
+
*/
|
|
48
|
+
function placetypeToTag(placetype) {
|
|
49
|
+
switch (placetype) {
|
|
50
|
+
case "country":
|
|
51
|
+
case "nation":
|
|
52
|
+
return "country";
|
|
53
|
+
case "macroregion":
|
|
54
|
+
case "region":
|
|
55
|
+
return "region";
|
|
56
|
+
case "locality":
|
|
57
|
+
return "locality";
|
|
58
|
+
case "postalcode":
|
|
59
|
+
return "postcode";
|
|
60
|
+
default:
|
|
61
|
+
return undefined;
|
|
62
|
+
}
|
|
63
|
+
}
|
|
64
|
+
/**
|
|
65
|
+
* Compute hierarchy variants for a postcode record. `selfName` is the postcode surface form (canonical `wof:name` for
|
|
66
|
+
* the `default` slot, a `name:*` localized variant otherwise).
|
|
67
|
+
*/
|
|
68
|
+
export function postcodeVariantsFor(row, ancestry, selfName) {
|
|
69
|
+
if (placetypeToTag(row.placetype) !== "postcode")
|
|
70
|
+
return [];
|
|
71
|
+
const locality = ancestry.find((a) => placetypeToTag(a.placetype) === "locality");
|
|
72
|
+
const region = ancestry.find((a) => placetypeToTag(a.placetype) === "region");
|
|
73
|
+
const country = ancestry.find((a) => placetypeToTag(a.placetype) === "country");
|
|
74
|
+
const countryDisplay = COUNTRY_DISPLAY_NAME[row.country] ?? country?.name ?? row.country;
|
|
75
|
+
const variants = [{ suffix: "self", components: { postcode: selfName } }];
|
|
76
|
+
if (locality) {
|
|
77
|
+
variants.push({
|
|
78
|
+
suffix: "with-locality",
|
|
79
|
+
components: { postcode: selfName, locality: locality.name },
|
|
80
|
+
});
|
|
81
|
+
}
|
|
82
|
+
if (locality && region) {
|
|
83
|
+
variants.push({
|
|
84
|
+
suffix: "with-locality-region",
|
|
85
|
+
components: { postcode: selfName, locality: locality.name, region: region.name },
|
|
86
|
+
});
|
|
87
|
+
}
|
|
88
|
+
if (locality && region && country) {
|
|
89
|
+
variants.push({
|
|
90
|
+
suffix: "with-locality-region-country",
|
|
91
|
+
components: {
|
|
92
|
+
postcode: selfName,
|
|
93
|
+
locality: locality.name,
|
|
94
|
+
region: region.name,
|
|
95
|
+
country: countryDisplay,
|
|
96
|
+
},
|
|
97
|
+
});
|
|
98
|
+
}
|
|
99
|
+
return variants;
|
|
100
|
+
}
|
|
101
|
+
/**
|
|
102
|
+
* Build the per-record name-slot list. The `default` slot uses `wof:name` verbatim (postcode digits); subsequent slots
|
|
103
|
+
* come from `name:*` variants dedup'd against the default.
|
|
104
|
+
*/
|
|
105
|
+
export function nameSlotsFor(rec) {
|
|
106
|
+
return wofNameSlotsFor(rec);
|
|
107
|
+
}
|
|
108
|
+
/**
|
|
109
|
+
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
110
|
+
* it came from.
|
|
111
|
+
*/
|
|
112
|
+
export const WOF_POSTALCODE_ADAPTER_ID = "wof-postalcode";
|
|
113
|
+
export function createWOFPostalcodeAdapter() {
|
|
114
|
+
return {
|
|
115
|
+
id: WOF_POSTALCODE_ADAPTER_ID,
|
|
116
|
+
defaultLicense: "CC0-1.0",
|
|
117
|
+
description: "Who's On First postalcode GeoJSON bundles (postcode → locality/region pairs). Ancestor names from sibling admin repos.",
|
|
118
|
+
async *rows(opts) {
|
|
119
|
+
// Pass 1: full walk. We keep every record whose placetype maps to a ComponentTag — the
|
|
120
|
+
// postcode adapter needs locality / region / country admin records in the index so it
|
|
121
|
+
// can resolve postcode ancestry, even though it only emits rows for postcode records.
|
|
122
|
+
const byID = new Map();
|
|
123
|
+
for await (const rec of walkFeatures(opts.inputPath, { signal: opts.signal })) {
|
|
124
|
+
if (opts.signal?.aborted)
|
|
125
|
+
return;
|
|
126
|
+
if (opts.country && rec.country !== opts.country)
|
|
127
|
+
continue;
|
|
128
|
+
if (!placetypeToTag(rec.placetype))
|
|
129
|
+
continue;
|
|
130
|
+
byID.set(rec.id, rec);
|
|
131
|
+
}
|
|
132
|
+
const ancestry = buildAncestryIndex(byID);
|
|
133
|
+
// Pass 2: emit postcode rows only, sorted by id for determinism.
|
|
134
|
+
yield* emitWOFJSONRows({
|
|
135
|
+
records: byID,
|
|
136
|
+
ancestry,
|
|
137
|
+
adapterOptions: opts,
|
|
138
|
+
adapterID: WOF_POSTALCODE_ADAPTER_ID,
|
|
139
|
+
localeByCountry: LOCALE_BY_COUNTRY,
|
|
140
|
+
shouldEmit: (record) => placetypeToTag(record.placetype) === "postcode",
|
|
141
|
+
nameSlotsFor,
|
|
142
|
+
variantsFor: postcodeVariantsFor,
|
|
143
|
+
});
|
|
144
|
+
},
|
|
145
|
+
};
|
|
146
|
+
}
|
|
147
|
+
/**
|
|
148
|
+
* The configured adapter instance registered with the corpus builder.
|
|
149
|
+
*/
|
|
150
|
+
export const wofPostalcodeAdapter = createWOFPostalcodeAdapter();
|
|
151
|
+
//# sourceMappingURL=adapter.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../lib/adapters/wof-postalcode-json/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAqCG;AAKH,OAAO,EACN,oBAAoB,EACpB,eAAe,EACf,iBAAiB,EACjB,YAAY,IAAI,eAAe,GAE/B,MAAM,yBAAyB,CAAA;AAEhC,OAAO,EAAE,kBAAkB,EAAE,YAAY,EAAkB,MAAM,QAAQ,CAAA;AAEzE;;;;;;GAMG;AACH,SAAS,cAAc,CAAC,SAAwC;IAC/D,QAAQ,SAAS,EAAE,CAAC;QACnB,KAAK,SAAS,CAAC;QACf,KAAK,QAAQ;YACZ,OAAO,SAAS,CAAA;QACjB,KAAK,aAAa,CAAC;QACnB,KAAK,QAAQ;YACZ,OAAO,QAAQ,CAAA;QAChB,KAAK,UAAU;YACd,OAAO,UAAU,CAAA;QAClB,KAAK,YAAY;YAChB,OAAO,UAAU,CAAA;QAClB;YACC,OAAO,SAAS,CAAA;IAClB,CAAC;AACF,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,mBAAmB,CAAC,GAAc,EAAE,QAAqB,EAAE,QAAgB;IAC1F,IAAI,cAAc,CAAC,GAAG,CAAC,SAAS,CAAC,KAAK,UAAU;QAAE,OAAO,EAAE,CAAA;IAE3D,MAAM,QAAQ,GAAG,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,cAAc,CAAC,CAAC,CAAC,SAAS,CAAC,KAAK,UAAU,CAAC,CAAA;IACjF,MAAM,MAAM,GAAG,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,cAAc,CAAC,CAAC,CAAC,SAAS,CAAC,KAAK,QAAQ,CAAC,CAAA;IAC7E,MAAM,OAAO,GAAG,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,cAAc,CAAC,CAAC,CAAC,SAAS,CAAC,KAAK,SAAS,CAAC,CAAA;IAC/E,MAAM,cAAc,GAAG,oBAAoB,CAAC,GAAG,CAAC,OAAO,CAAC,IAAI,OAAO,EAAE,IAAI,IAAI,GAAG,CAAC,OAAO,CAAA;IAExF,MAAM,QAAQ,GAAqB,CAAC,EAAE,MAAM,EAAE,MAAM,EAAE,UAAU,EAAE,EAAE,QAAQ,EAAE,QAAQ,EAAE,EAAE,CAAC,CAAA;IAE3F,IAAI,QAAQ,EAAE,CAAC;QACd,QAAQ,CAAC,IAAI,CAAC;YACb,MAAM,EAAE,eAAe;YACvB,UAAU,EAAE,EAAE,QAAQ,EAAE,QAAQ,EAAE,QAAQ,EAAE,QAAQ,CAAC,IAAI,EAAE;SAC3D,CAAC,CAAA;IACH,CAAC;IAED,IAAI,QAAQ,IAAI,MAAM,EAAE,CAAC;QACxB,QAAQ,CAAC,IAAI,CAAC;YACb,MAAM,EAAE,sBAAsB;YAC9B,UAAU,EAAE,EAAE,QAAQ,EAAE,QAAQ,EAAE,QAAQ,EAAE,QAAQ,CAAC,IAAI,EAAE,MAAM,EAAE,MAAM,CAAC,IAAI,EAAE;SAChF,CAAC,CAAA;IACH,CAAC;IAED,IAAI,QAAQ,IAAI,MAAM,IAAI,OAAO,EAAE,CAAC;QACnC,QAAQ,CAAC,IAAI,CAAC;YACb,MAAM,EAAE,8BAA8B;YACtC,UAAU,EAAE;gBACX,QAAQ,EAAE,QAAQ;gBAClB,QAAQ,EAAE,QAAQ,CAAC,IAAI;gBACvB,MAAM,EAAE,MAAM,CAAC,IAAI;gBACnB,OAAO,EAAE,cAAc;aACvB;SACD,CAAC,CAAA;IACH,CAAC;IAED,OAAO,QAAQ,CAAA;AAChB,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,YAAY,CAAC,GAAc;IAC1C,OAAO,eAAe,CAAC,GAAG,CAAC,CAAA;AAC5B,CAAC;AAED;;;GAGG;AACH,MAAM,CAAC,MAAM,yBAAyB,GAAG,gBAAgB,CAAA;AAEzD,MAAM,UAAU,0BAA0B;IACzC,OAAO;QACN,EAAE,EAAE,yBAAyB;QAC7B,cAAc,EAAE,SAAS;QACzB,WAAW,EACV,wHAAwH;QAEzH,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,uFAAuF;YACvF,sFAAsF;YACtF,sFAAsF;YACtF,MAAM,IAAI,GAAG,IAAI,GAAG,EAAqB,CAAA;YAEzC,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,YAAY,CAAC,IAAI,CAAC,SAAS,EAAE,EAAE,MAAM,EAAE,IAAI,CAAC,MAAM,EAAE,CAAC,EAAE,CAAC;gBAC/E,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;oBAAE,OAAM;gBAEhC,IAAI,IAAI,CAAC,OAAO,IAAI,GAAG,CAAC,OAAO,KAAK,IAAI,CAAC,OAAO;oBAAE,SAAQ;gBAE1D,IAAI,CAAC,cAAc,CAAC,GAAG,CAAC,SAAS,CAAC;oBAAE,SAAQ;gBAC5C,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,EAAE,EAAE,GAAG,CAAC,CAAA;YACtB,CAAC;YAED,MAAM,QAAQ,GAAG,kBAAkB,CAAC,IAAI,CAAC,CAAA;YAEzC,iEAAiE;YACjE,KAAK,CAAC,CAAC,eAAe,CAAC;gBACtB,OAAO,EAAE,IAAI;gBACb,QAAQ;gBACR,cAAc,EAAE,IAAI;gBACpB,SAAS,EAAE,yBAAyB;gBACpC,eAAe,EAAE,iBAAiB;gBAClC,UAAU,EAAE,CAAC,MAAM,EAAE,EAAE,CAAC,cAAc,CAAC,MAAM,CAAC,SAAS,CAAC,KAAK,UAAU;gBACvE,YAAY;gBACZ,WAAW,EAAE,mBAAmB;aAChC,CAAC,CAAA;QACH,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,oBAAoB,GAAG,0BAA0B,EAAE,CAAA"}
|
package/out/build.d.ts
ADDED
|
@@ -0,0 +1,132 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* End-to-end corpus build (Phase 1 task #10 in the plan).
|
|
7
|
+
*
|
|
8
|
+
* `buildCorpus(opts)` orchestrates every stage of the pipeline:
|
|
9
|
+
*
|
|
10
|
+
* 1. **Adapter runs** — drives every adapter in turn (via `runAdapter`), writing
|
|
11
|
+
* `<intermediate>/<adapter.id>/canonical.jsonl` slices.
|
|
12
|
+
* 2. **Synthesis** — optional. For each canonical row, every applicable augmentation in the row's
|
|
13
|
+
* country-default policy emits an augmented row alongside the original.
|
|
14
|
+
* 3. **Alignment** — every row (original + augmented) is aligned via `alignRow`. Successes go to
|
|
15
|
+
* `labeled.jsonl`; quarantines are appended to `quarantine.jsonl` with reasons.
|
|
16
|
+
* 4. **Splits** — `splitRows` partitions labeled `source_id`s into train/val/test by locality holdout.
|
|
17
|
+
* Manifest written to `splits/SPLIT_MANIFEST.json` + per-split `train.txt` / `val.txt` /
|
|
18
|
+
* `test.txt`.
|
|
19
|
+
* 5. **Parquet slices** — `writeSlices` streams labeled rows into 1M-row `.parquet` slices per split
|
|
20
|
+
* under `corpus-v<version>/{train,val,test}/part-NNNN.parquet` (SNAPPY-compressed, 50k-row
|
|
21
|
+
* row groups), with per-slice checksums + per-stage manifest in
|
|
22
|
+
* `corpus-v<version>/MANIFEST.json`.
|
|
23
|
+
* 6. **Top-level manifest** — `<outputDir>/MANIFEST.json` ties every per-stage manifest together with
|
|
24
|
+
* a top-level corpus_version, built_at, and aggregate counts.
|
|
25
|
+
*
|
|
26
|
+
* Output layout:
|
|
27
|
+
*
|
|
28
|
+
* ```
|
|
29
|
+
* <outputDir>/
|
|
30
|
+
* MANIFEST.json
|
|
31
|
+
* intermediate/
|
|
32
|
+
* <adapter.id>/canonical.jsonl # one per adapter
|
|
33
|
+
* labeled.jsonl # post-alignment, pre-slice
|
|
34
|
+
* quarantine.jsonl # rows that failed alignment
|
|
35
|
+
* splits/
|
|
36
|
+
* SPLIT_MANIFEST.json
|
|
37
|
+
* train.txt / val.txt / test.txt
|
|
38
|
+
* corpus-v<version>/
|
|
39
|
+
* MANIFEST.json
|
|
40
|
+
* train/part-NNNN.parquet
|
|
41
|
+
* val/part-NNNN.parquet
|
|
42
|
+
* test/part-NNNN.parquet
|
|
43
|
+
* ```
|
|
44
|
+
*
|
|
45
|
+
* The intermediate files live alongside the final slices for reproducibility + debugging. Operators
|
|
46
|
+
* can `rm -rf intermediate/` after the build if disk is tight; the final `corpus-v<version>/` is
|
|
47
|
+
* self-contained.
|
|
48
|
+
*/
|
|
49
|
+
import { type AdapterRunManifest } from "#runner";
|
|
50
|
+
import type { AdapterOptions, CorpusAdapter } from "#types";
|
|
51
|
+
import { type SliceManifest } from "#utils/parquet";
|
|
52
|
+
import { type SplitManifest } from "#utils/split";
|
|
53
|
+
/**
|
|
54
|
+
* Stage tags surfaced to `onProgress`.
|
|
55
|
+
*/
|
|
56
|
+
export type BuildStage = "adapter-run" | "align" | "split" | "slice" | "manifest";
|
|
57
|
+
/**
|
|
58
|
+
* Per-invocation options for `buildCorpus`.
|
|
59
|
+
*/
|
|
60
|
+
export interface BuildCorpusOptions {
|
|
61
|
+
/**
|
|
62
|
+
* Root output directory. All build artifacts land beneath it.
|
|
63
|
+
*/
|
|
64
|
+
outputDir: string;
|
|
65
|
+
/**
|
|
66
|
+
* Corpus version (e.g. `"0.1.0"`). Stamped onto every row + into the output dir name.
|
|
67
|
+
*/
|
|
68
|
+
corpusVersion: string;
|
|
69
|
+
/**
|
|
70
|
+
* Adapters to drive, in order. Defaults to `defaultAdapterRegistry.list()`. Pass an explicit list to filter (e.g.
|
|
71
|
+
* `[wofAdminAdapter]` for a smoke run).
|
|
72
|
+
*/
|
|
73
|
+
adapters?: readonly CorpusAdapter[];
|
|
74
|
+
/**
|
|
75
|
+
* Per-adapter `AdapterOptions` — looked up by adapter id. Adapters whose id is missing from this map are skipped (and
|
|
76
|
+
* noted in the manifest).
|
|
77
|
+
*/
|
|
78
|
+
adapterInputs: Record<string, AdapterOptions>;
|
|
79
|
+
/**
|
|
80
|
+
* Enable synthesis pass. Default `true`. Set `false` for fixture-driven smoke tests.
|
|
81
|
+
*/
|
|
82
|
+
synthesize?: boolean;
|
|
83
|
+
/**
|
|
84
|
+
* Forwarded to `writeSlices`. Default 1_000_000.
|
|
85
|
+
*/
|
|
86
|
+
rowsPerSlice?: number;
|
|
87
|
+
/**
|
|
88
|
+
* Progress hook. Errors thrown abort the build.
|
|
89
|
+
*/
|
|
90
|
+
onProgress?: (stage: BuildStage, message: string) => void;
|
|
91
|
+
/**
|
|
92
|
+
* License kinds to PURPOSELY exclude from this build (#26). Compiled patterns (see `compileLicenseExcludes` /
|
|
93
|
+
* `SHARE_ALIKE_PATTERN` in `license.ts`); a row whose `license` matches any is dropped at ingest. Default (omitted)
|
|
94
|
+
* includes EVERYTHING — exclusion is a deliberate act, not a silent default. A proprietary-weights build passes the
|
|
95
|
+
* share-alike set (`--exclude-share-alike`).
|
|
96
|
+
*/
|
|
97
|
+
excludeLicenses?: readonly RegExp[];
|
|
98
|
+
}
|
|
99
|
+
/**
|
|
100
|
+
* Top-level manifest tying every stage together.
|
|
101
|
+
*/
|
|
102
|
+
export interface BuildCorpusManifest {
|
|
103
|
+
corpus_version: string;
|
|
104
|
+
built_at: string;
|
|
105
|
+
adapters: AdapterRunManifest[];
|
|
106
|
+
skipped_adapters: string[];
|
|
107
|
+
splits: {
|
|
108
|
+
counts: SplitManifest["counts"];
|
|
109
|
+
holdouts: SplitManifest["holdouts"];
|
|
110
|
+
};
|
|
111
|
+
slices: {
|
|
112
|
+
counts: SliceManifest["counts"];
|
|
113
|
+
total_rows: number;
|
|
114
|
+
};
|
|
115
|
+
quarantine_count: number;
|
|
116
|
+
total_aligned_rows: number;
|
|
117
|
+
/**
|
|
118
|
+
* Resolved license set across all INCLUDED rows (license string → row count), + the count dropped by
|
|
119
|
+
* `excludeLicenses` (#26). The model card derives its data-attribution table from `licenses`.
|
|
120
|
+
*/
|
|
121
|
+
licenses: Record<string, number>;
|
|
122
|
+
excluded_by_license: number;
|
|
123
|
+
}
|
|
124
|
+
/**
|
|
125
|
+
* Drive the full corpus build to completion.
|
|
126
|
+
*
|
|
127
|
+
* Memory profile: the function maintains an in-memory `Map<source_id, SplitName>` to bridge the align → slice hand-off.
|
|
128
|
+
* For Phase 1 fixture-scale runs (≤ 10⁴ rows) this is trivial. For real 5M+ runs, the map fits comfortably in a few
|
|
129
|
+
* hundred MB; the canonical.jsonl and labeled.jsonl payloads stream and never sit in memory.
|
|
130
|
+
*/
|
|
131
|
+
export declare function buildCorpus(opts: BuildCorpusOptions): Promise<BuildCorpusManifest>;
|
|
132
|
+
//# sourceMappingURL=build.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"build.d.ts","sourceRoot":"","sources":["../lib/build.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA+CG;AAUH,OAAO,EAAoB,KAAK,kBAAkB,EAAE,MAAM,SAAS,CAAA;AAEnE,OAAO,KAAK,EAAE,cAAc,EAAgB,aAAa,EAAc,MAAM,QAAQ,CAAA;AAGrF,OAAO,EAAe,KAAK,aAAa,EAAE,MAAM,gBAAgB,CAAA;AAChE,OAAO,EAIN,KAAK,aAAa,EAElB,MAAM,cAAc,CAAA;AAErB;;GAEG;AACH,MAAM,MAAM,UAAU,GAAG,aAAa,GAAG,OAAO,GAAG,OAAO,GAAG,OAAO,GAAG,UAAU,CAAA;AAEjF;;GAEG;AACH,MAAM,WAAW,kBAAkB;IAClC;;OAEG;IACH,SAAS,EAAE,MAAM,CAAA;IAEjB;;OAEG;IACH,aAAa,EAAE,MAAM,CAAA;IAErB;;;OAGG;IACH,QAAQ,CAAC,EAAE,SAAS,aAAa,EAAE,CAAA;IAEnC;;;OAGG;IACH,aAAa,EAAE,MAAM,CAAC,MAAM,EAAE,cAAc,CAAC,CAAA;IAE7C;;OAEG;IACH,UAAU,CAAC,EAAE,OAAO,CAAA;IAEpB;;OAEG;IACH,YAAY,CAAC,EAAE,MAAM,CAAA;IAErB;;OAEG;IACH,UAAU,CAAC,EAAE,CAAC,KAAK,EAAE,UAAU,EAAE,OAAO,EAAE,MAAM,KAAK,IAAI,CAAA;IAEzD;;;;;OAKG;IACH,eAAe,CAAC,EAAE,SAAS,MAAM,EAAE,CAAA;CACnC;AAED;;GAEG;AACH,MAAM,WAAW,mBAAmB;IACnC,cAAc,EAAE,MAAM,CAAA;IACtB,QAAQ,EAAE,MAAM,CAAA;IAChB,QAAQ,EAAE,kBAAkB,EAAE,CAAA;IAC9B,gBAAgB,EAAE,MAAM,EAAE,CAAA;IAC1B,MAAM,EAAE;QAAE,MAAM,EAAE,aAAa,CAAC,QAAQ,CAAC,CAAC;QAAC,QAAQ,EAAE,aAAa,CAAC,UAAU,CAAC,CAAA;KAAE,CAAA;IAChF,MAAM,EAAE;QAAE,MAAM,EAAE,aAAa,CAAC,QAAQ,CAAC,CAAC;QAAC,UAAU,EAAE,MAAM,CAAA;KAAE,CAAA;IAC/D,gBAAgB,EAAE,MAAM,CAAA;IACxB,kBAAkB,EAAE,MAAM,CAAA;IAC1B;;;OAGG;IACH,QAAQ,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IAChC,mBAAmB,EAAE,MAAM,CAAA;CAC3B;AAED;;;;;;GAMG;AACH,wBAAsB,WAAW,CAAC,IAAI,EAAE,kBAAkB,GAAG,OAAO,CAAC,mBAAmB,CAAC,CAyNxF"}
|