@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
|
@@ -1,176 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `geonames`: GeoNames populated-places consumer (https://www.geonames.org/, CC-BY-4.0).
|
|
7
|
-
*
|
|
8
|
-
* GeoNames is a global gazetteer of ~12M features. This adapter ingests the POPULATED PLACES
|
|
9
|
-
* (`feature_class = "P"`, excluding historical/abandoned/destroyed variants) from a per-country
|
|
10
|
-
* dump file — global locality coverage, including the small towns and villages a coarser admin
|
|
11
|
-
* gazetteer (WOF) lacks. It's the cheapest path to broadening the corpus's LOCALE coverage.
|
|
12
|
-
*
|
|
13
|
-
* Input: a per-country tab-separated dump (e.g. `US.txt` from
|
|
14
|
-
* `https://download.geonames.org/export/dump/`, 19 columns, no header). Two sibling files in the
|
|
15
|
-
* same directory supply human-readable names (downloaded once from the same place):
|
|
16
|
-
*
|
|
17
|
-
* - `admin1CodesASCII.txt` — `<CC>.<admin1_code>` → region name (e.g. `US.VT` → "Vermont").
|
|
18
|
-
* - `countryInfo.txt` — ISO alpha-2 → country name (e.g. `US` → "United States"); `#`-commented. If a
|
|
19
|
-
* sibling is missing, the corresponding component is simply omitted (graceful degradation).
|
|
20
|
-
*
|
|
21
|
-
* Output: per place, up to two hierarchy variants (mirroring `wof-admin`'s with/without-country
|
|
22
|
-
* balance so the model sees both domestic and international order) —
|
|
23
|
-
*
|
|
24
|
-
* 1. `{ locality, region }` → "City, Region"
|
|
25
|
-
* 2. `{ locality, region, country }` → "City, Region, Country" `reconcileComponents` drops any
|
|
26
|
-
* component that didn't survive into the rendered `raw`.
|
|
27
|
-
*
|
|
28
|
-
* License: stamped `"CC-BY-4.0"` per row (GeoNames' terms); provenance is the `geonames-<id>` key.
|
|
29
|
-
*/
|
|
30
|
-
import { existsSync } from "node:fs";
|
|
31
|
-
import { stableSourceID } from "@mailwoman/corpus/adapters/utils";
|
|
32
|
-
import { reconcileComponents } from "@mailwoman/formatter";
|
|
33
|
-
import { dirname, join } from "path-ts";
|
|
34
|
-
import { TSVSpliterator } from "spliterator";
|
|
35
|
-
/**
|
|
36
|
-
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
37
|
-
* it came from.
|
|
38
|
-
*/
|
|
39
|
-
export const GEONAMES_ADAPTER_ID = "geonames";
|
|
40
|
-
/**
|
|
41
|
-
* License carried by this source (CC-BY-4.0), attached to each row so downstream consumers inherit the terms rather
|
|
42
|
-
* than having to look them up.
|
|
43
|
-
*/
|
|
44
|
-
export const GEONAMES_DEFAULT_LICENSE = "CC-BY-4.0";
|
|
45
|
-
/**
|
|
46
|
-
* GeoNames main-table column indices (0-based; see the export README).
|
|
47
|
-
*/
|
|
48
|
-
const COL = {
|
|
49
|
-
geonameid: 0,
|
|
50
|
-
name: 1,
|
|
51
|
-
alternatenames: 3,
|
|
52
|
-
featureClass: 6,
|
|
53
|
-
featureCode: 7,
|
|
54
|
-
country: 8,
|
|
55
|
-
admin1: 10,
|
|
56
|
-
};
|
|
57
|
-
/**
|
|
58
|
-
* Populated-place feature codes that are NOT current real places — skip them.
|
|
59
|
-
*/
|
|
60
|
-
const NON_CURRENT_PPL = new Set(["PPLH", "PPLQ", "PPLW", "PPLCH"]);
|
|
61
|
-
/**
|
|
62
|
-
* Load `admin1CodesASCII.txt` → Map("<CC>.<admin1>" → region name). Empty map if absent.
|
|
63
|
-
*/
|
|
64
|
-
async function loadAdmin1(dir) {
|
|
65
|
-
const map = new Map();
|
|
66
|
-
const fp = join(dir, "admin1CodesASCII.txt");
|
|
67
|
-
if (!existsSync(fp))
|
|
68
|
-
return map;
|
|
69
|
-
// `header: false` — the file is headerless, and the spliterator eats row 1 as a header otherwise.
|
|
70
|
-
for await (const cols of TSVSpliterator.fromAsync(fp, { header: false })) {
|
|
71
|
-
if (cols[0] && cols[1]) {
|
|
72
|
-
map.set(cols[0], cols[1]);
|
|
73
|
-
}
|
|
74
|
-
}
|
|
75
|
-
return map;
|
|
76
|
-
}
|
|
77
|
-
/**
|
|
78
|
-
* Load `countryInfo.txt` → Map(ISO → country name). Empty map if absent. The file is `#`-commented.
|
|
79
|
-
*/
|
|
80
|
-
async function loadCountries(dir) {
|
|
81
|
-
const map = new Map();
|
|
82
|
-
const fp = join(dir, "countryInfo.txt");
|
|
83
|
-
if (!existsSync(fp))
|
|
84
|
-
return map;
|
|
85
|
-
// `header: false` — the file's header IS a `#` comment, so it falls out with the other comments
|
|
86
|
-
// rather than being consumed as column names.
|
|
87
|
-
for await (const cols of TSVSpliterator.fromAsync(fp, { header: false })) {
|
|
88
|
-
if (cols[0]?.startsWith("#"))
|
|
89
|
-
continue;
|
|
90
|
-
// ISO(0), ISO3(1), iso-numeric(2), fips(3), Country(4), ...
|
|
91
|
-
if (cols[0] && cols[4]) {
|
|
92
|
-
map.set(cols[0], cols[4]);
|
|
93
|
-
}
|
|
94
|
-
}
|
|
95
|
-
return map;
|
|
96
|
-
}
|
|
97
|
-
export function createGeonamesAdapter() {
|
|
98
|
-
return {
|
|
99
|
-
id: GEONAMES_ADAPTER_ID,
|
|
100
|
-
defaultLicense: GEONAMES_DEFAULT_LICENSE,
|
|
101
|
-
description: "GeoNames populated places (CC-BY-4.0) — global locality coverage incl. small towns, with region/country names from the sibling admin1/countryInfo files.",
|
|
102
|
-
async *rows(opts) {
|
|
103
|
-
const dir = dirname(opts.inputPath);
|
|
104
|
-
const admin1 = await loadAdmin1(dir);
|
|
105
|
-
const countries = await loadCountries(dir);
|
|
106
|
-
// `header: false` — the per-country dump is headerless.
|
|
107
|
-
const rows = TSVSpliterator.fromAsync(opts.inputPath, { header: false });
|
|
108
|
-
let emitted = 0;
|
|
109
|
-
for await (const rec of rows) {
|
|
110
|
-
if (opts.signal?.aborted)
|
|
111
|
-
break;
|
|
112
|
-
if (opts.limit !== undefined && emitted >= opts.limit)
|
|
113
|
-
break;
|
|
114
|
-
if (rec[COL.featureClass] !== "P")
|
|
115
|
-
continue;
|
|
116
|
-
if (NON_CURRENT_PPL.has(rec[COL.featureCode] ?? ""))
|
|
117
|
-
continue;
|
|
118
|
-
const cc = (rec[COL.country] ?? "").trim();
|
|
119
|
-
if (!cc)
|
|
120
|
-
continue;
|
|
121
|
-
if (opts.country && cc !== opts.country)
|
|
122
|
-
continue;
|
|
123
|
-
const locality = (rec[COL.name] ?? "").trim();
|
|
124
|
-
if (!locality)
|
|
125
|
-
continue;
|
|
126
|
-
const geonameid = (rec[COL.geonameid] ?? "").trim();
|
|
127
|
-
const region = admin1.get(`${cc}.${(rec[COL.admin1] ?? "").trim()}`);
|
|
128
|
-
const country = countries.get(cc);
|
|
129
|
-
// Two hierarchy variants (domestic + international order) — but only emit the
|
|
130
|
-
// distinct ones the available names support.
|
|
131
|
-
const variants = [];
|
|
132
|
-
if (region) {
|
|
133
|
-
variants.push({ slot: "lr", comp: { locality, region }, raw: `${locality}, ${region}` });
|
|
134
|
-
if (country) {
|
|
135
|
-
variants.push({
|
|
136
|
-
slot: "lrc",
|
|
137
|
-
comp: { locality, region, country },
|
|
138
|
-
raw: `${locality}, ${region}, ${country}`,
|
|
139
|
-
});
|
|
140
|
-
}
|
|
141
|
-
}
|
|
142
|
-
else if (country) {
|
|
143
|
-
variants.push({ slot: "lc", comp: { locality, country }, raw: `${locality}, ${country}` });
|
|
144
|
-
}
|
|
145
|
-
else {
|
|
146
|
-
variants.push({ slot: "l", comp: { locality }, raw: locality });
|
|
147
|
-
}
|
|
148
|
-
for (const v of variants) {
|
|
149
|
-
if (opts.limit !== undefined && emitted >= opts.limit)
|
|
150
|
-
break;
|
|
151
|
-
const aligned = reconcileComponents(v.comp, v.raw);
|
|
152
|
-
if (!Object.keys(aligned).length)
|
|
153
|
-
continue;
|
|
154
|
-
const sourceID = geonameid
|
|
155
|
-
? `${GEONAMES_ADAPTER_ID}-${geonameid}-${v.slot}`
|
|
156
|
-
: stableSourceID(GEONAMES_ADAPTER_ID, aligned);
|
|
157
|
-
yield {
|
|
158
|
-
raw: v.raw,
|
|
159
|
-
components: aligned,
|
|
160
|
-
country: cc,
|
|
161
|
-
source: GEONAMES_ADAPTER_ID,
|
|
162
|
-
source_id: sourceID,
|
|
163
|
-
corpus_version: "",
|
|
164
|
-
license: GEONAMES_DEFAULT_LICENSE,
|
|
165
|
-
};
|
|
166
|
-
emitted++;
|
|
167
|
-
}
|
|
168
|
-
}
|
|
169
|
-
},
|
|
170
|
-
};
|
|
171
|
-
}
|
|
172
|
-
/**
|
|
173
|
-
* The configured adapter instance registered with the corpus builder.
|
|
174
|
-
*/
|
|
175
|
-
export const geonamesAdapter = createGeonamesAdapter();
|
|
176
|
-
//# sourceMappingURL=adapter.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/geonames/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AAEH,OAAO,EAAE,UAAU,EAAE,MAAM,SAAS,CAAA;AAEpC,OAAO,EAAE,cAAc,EAAE,MAAM,kCAAkC,CAAA;AAEjE,OAAO,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AAC1D,OAAO,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,SAAS,CAAA;AACvC,OAAO,EAAE,cAAc,EAAE,MAAM,aAAa,CAAA;AAE5C;;;GAGG;AACH,MAAM,CAAC,MAAM,mBAAmB,GAAG,UAAU,CAAA;AAC7C;;;GAGG;AACH,MAAM,CAAC,MAAM,wBAAwB,GAAG,WAAW,CAAA;AAEnD;;GAEG;AACH,MAAM,GAAG,GAAG;IACX,SAAS,EAAE,CAAC;IACZ,IAAI,EAAE,CAAC;IACP,cAAc,EAAE,CAAC;IACjB,YAAY,EAAE,CAAC;IACf,WAAW,EAAE,CAAC;IACd,OAAO,EAAE,CAAC;IACV,MAAM,EAAE,EAAE;CACD,CAAA;AAEV;;GAEG;AACH,MAAM,eAAe,GAAG,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,OAAO,CAAC,CAAC,CAAA;AAElE;;GAEG;AACH,KAAK,UAAU,UAAU,CAAC,GAAW;IACpC,MAAM,GAAG,GAAG,IAAI,GAAG,EAAkB,CAAA;IACrC,MAAM,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,sBAAsB,CAAC,CAAA;IAE5C,IAAI,CAAC,UAAU,CAAC,EAAE,CAAC;QAAE,OAAO,GAAG,CAAA;IAE/B,kGAAkG;IAClG,IAAI,KAAK,EAAE,MAAM,IAAI,IAAI,cAAc,CAAC,SAAS,CAAC,EAAE,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC;QAC1E,IAAI,IAAI,CAAC,CAAC,CAAC,IAAI,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC;YACxB,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,CAAC,CAAC,CAAA;QAC1B,CAAC;IACF,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC;AAED;;GAEG;AACH,KAAK,UAAU,aAAa,CAAC,GAAW;IACvC,MAAM,GAAG,GAAG,IAAI,GAAG,EAAkB,CAAA;IACrC,MAAM,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,iBAAiB,CAAC,CAAA;IAEvC,IAAI,CAAC,UAAU,CAAC,EAAE,CAAC;QAAE,OAAO,GAAG,CAAA;IAE/B,gGAAgG;IAChG,8CAA8C;IAC9C,IAAI,KAAK,EAAE,MAAM,IAAI,IAAI,cAAc,CAAC,SAAS,CAAC,EAAE,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC;QAC1E,IAAI,IAAI,CAAC,CAAC,CAAC,EAAE,UAAU,CAAC,GAAG,CAAC;YAAE,SAAQ;QAEtC,4DAA4D;QAC5D,IAAI,IAAI,CAAC,CAAC,CAAC,IAAI,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC;YACxB,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,CAAC,CAAC,CAAA;QAC1B,CAAC;IACF,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC;AAED,MAAM,UAAU,qBAAqB;IACpC,OAAO;QACN,EAAE,EAAE,mBAAmB;QACvB,cAAc,EAAE,wBAAwB;QACxC,WAAW,EACV,0JAA0J;QAE3J,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,MAAM,GAAG,GAAG,OAAO,CAAC,IAAI,CAAC,SAAS,CAAC,CAAA;YACnC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,GAAG,CAAC,CAAA;YACpC,MAAM,SAAS,GAAG,MAAM,aAAa,CAAC,GAAG,CAAC,CAAA;YAE1C,wDAAwD;YACxD,MAAM,IAAI,GAAG,cAAc,CAAC,SAAS,CAAC,IAAI,CAAC,SAAS,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,CAAA;YAExE,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;gBAC9B,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;oBAAE,MAAK;gBAE/B,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;oBAAE,MAAK;gBAE5D,IAAI,GAAG,CAAC,GAAG,CAAC,YAAY,CAAC,KAAK,GAAG;oBAAE,SAAQ;gBAE3C,IAAI,eAAe,CAAC,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,WAAW,CAAC,IAAI,EAAE,CAAC;oBAAE,SAAQ;gBAE7D,MAAM,EAAE,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAE1C,IAAI,CAAC,EAAE;oBAAE,SAAQ;gBAEjB,IAAI,IAAI,CAAC,OAAO,IAAI,EAAE,KAAK,IAAI,CAAC,OAAO;oBAAE,SAAQ;gBAEjD,MAAM,QAAQ,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAE7C,IAAI,CAAC,QAAQ;oBAAE,SAAQ;gBACvB,MAAM,SAAS,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,SAAS,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBACnD,MAAM,MAAM,GAAG,MAAM,CAAC,GAAG,CAAC,GAAG,EAAE,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAA;gBACpE,MAAM,OAAO,GAAG,SAAS,CAAC,GAAG,CAAC,EAAE,CAAC,CAAA;gBAEjC,8EAA8E;gBAC9E,6CAA6C;gBAC7C,MAAM,QAAQ,GAA2E,EAAE,CAAA;gBAE3F,IAAI,MAAM,EAAE,CAAC;oBACZ,QAAQ,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,GAAG,QAAQ,KAAK,MAAM,EAAE,EAAE,CAAC,CAAA;oBAExF,IAAI,OAAO,EAAE,CAAC;wBACb,QAAQ,CAAC,IAAI,CAAC;4BACb,IAAI,EAAE,KAAK;4BACX,IAAI,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,OAAO,EAAE;4BACnC,GAAG,EAAE,GAAG,QAAQ,KAAK,MAAM,KAAK,OAAO,EAAE;yBACzC,CAAC,CAAA;oBACH,CAAC;gBACF,CAAC;qBAAM,IAAI,OAAO,EAAE,CAAC;oBACpB,QAAQ,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,EAAE,QAAQ,EAAE,OAAO,EAAE,EAAE,GAAG,EAAE,GAAG,QAAQ,KAAK,OAAO,EAAE,EAAE,CAAC,CAAA;gBAC3F,CAAC;qBAAM,CAAC;oBACP,QAAQ,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,GAAG,EAAE,IAAI,EAAE,EAAE,QAAQ,EAAE,EAAE,GAAG,EAAE,QAAQ,EAAE,CAAC,CAAA;gBAChE,CAAC;gBAED,KAAK,MAAM,CAAC,IAAI,QAAQ,EAAE,CAAC;oBAC1B,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;wBAAE,MAAK;oBAC5D,MAAM,OAAO,GAAG,mBAAmB,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,GAAG,CAAC,CAAA;oBAElD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM;wBAAE,SAAQ;oBAE1C,MAAM,QAAQ,GAAG,SAAS;wBACzB,CAAC,CAAC,GAAG,mBAAmB,IAAI,SAAS,IAAI,CAAC,CAAC,IAAI,EAAE;wBACjD,CAAC,CAAC,cAAc,CAAC,mBAAmB,EAAE,OAAO,CAAC,CAAA;oBAE/C,MAAM;wBACL,GAAG,EAAE,CAAC,CAAC,GAAG;wBACV,UAAU,EAAE,OAAO;wBACnB,OAAO,EAAE,EAAE;wBACX,MAAM,EAAE,mBAAmB;wBAC3B,SAAS,EAAE,QAAQ;wBACnB,cAAc,EAAE,EAAE;wBAClB,OAAO,EAAE,wBAAwB;qBACjC,CAAA;oBAED,OAAO,EAAE,CAAA;gBACV,CAAC;YACF,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,eAAe,GAAG,qBAAqB,EAAE,CAAA"}
|
|
@@ -1,41 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `geonames-postal`: GeoNames postal-code dump consumer (https://www.geonames.org/, CC-BY-4.0).
|
|
7
|
-
*
|
|
8
|
-
* The GeoNames postal export (`https://download.geonames.org/export/zip/<CC>.zip`) is a clean,
|
|
9
|
-
* per-country `postcode → place → admin1` table with the place + region NAMES inline (no aux-file
|
|
10
|
-
* join needed). It broadens the corpus's postcode→locality→region coverage to ~80 countries, well
|
|
11
|
-
* beyond `wof-postalcode`/the coordinate-first table — forward coverage for the multi-locale
|
|
12
|
-
* goal.
|
|
13
|
-
*
|
|
14
|
-
* Input: a per-country postal dump (`<CC>.txt`, 12 tab-separated columns, no header): country,
|
|
15
|
-
* postcode, place, admin1_name, admin1_code, admin2__, admin3__, lat, lon, accuracy.
|
|
16
|
-
*
|
|
17
|
-
* Output: per row, postcode-FIRST (international) variants — the common order for the non-US
|
|
18
|
-
* locales this fills (US postcodes are already covered by TIGER/WOF, which use postcode-LAST):
|
|
19
|
-
*
|
|
20
|
-
* 1. `{ postcode, locality }` → "AD100 Canillo"
|
|
21
|
-
* 2. `{ postcode, locality, region }` → "AD100 Canillo, Canillo" Prefer configuring this adapter for
|
|
22
|
-
* non-US countries; for US, the postcode-last sources are the right order. License:
|
|
23
|
-
* `"CC-BY-4.0"` per row (attribute "GeoNames").
|
|
24
|
-
*/
|
|
25
|
-
import type { CorpusAdapter } from "@mailwoman/corpus/types";
|
|
26
|
-
/**
|
|
27
|
-
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
28
|
-
* it came from.
|
|
29
|
-
*/
|
|
30
|
-
export declare const GEONAMES_POSTAL_ADAPTER_ID = "geonames-postal";
|
|
31
|
-
/**
|
|
32
|
-
* License carried by this source (CC-BY-4.0), attached to each row so downstream consumers inherit the terms rather
|
|
33
|
-
* than having to look them up.
|
|
34
|
-
*/
|
|
35
|
-
export declare const GEONAMES_POSTAL_DEFAULT_LICENSE = "CC-BY-4.0";
|
|
36
|
-
export declare function createGeonamesPostalAdapter(): CorpusAdapter;
|
|
37
|
-
/**
|
|
38
|
-
* The configured adapter instance registered with the corpus builder.
|
|
39
|
-
*/
|
|
40
|
-
export declare const geonamesPostalAdapter: CorpusAdapter;
|
|
41
|
-
//# sourceMappingURL=adapter.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/geonames-postal/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAGH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,yBAAyB,CAAA;AAI1F;;;GAGG;AACH,eAAO,MAAM,0BAA0B,oBAAoB,CAAA;AAC3D;;;GAGG;AACH,eAAO,MAAM,+BAA+B,cAAc,CAAA;AAO1D,wBAAgB,2BAA2B,IAAI,aAAa,CAkE3D;AAED;;GAEG;AACH,eAAO,MAAM,qBAAqB,eAAgC,CAAA"}
|
|
@@ -1,104 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `geonames-postal`: GeoNames postal-code dump consumer (https://www.geonames.org/, CC-BY-4.0).
|
|
7
|
-
*
|
|
8
|
-
* The GeoNames postal export (`https://download.geonames.org/export/zip/<CC>.zip`) is a clean,
|
|
9
|
-
* per-country `postcode → place → admin1` table with the place + region NAMES inline (no aux-file
|
|
10
|
-
* join needed). It broadens the corpus's postcode→locality→region coverage to ~80 countries, well
|
|
11
|
-
* beyond `wof-postalcode`/the coordinate-first table — forward coverage for the multi-locale
|
|
12
|
-
* goal.
|
|
13
|
-
*
|
|
14
|
-
* Input: a per-country postal dump (`<CC>.txt`, 12 tab-separated columns, no header): country,
|
|
15
|
-
* postcode, place, admin1_name, admin1_code, admin2__, admin3__, lat, lon, accuracy.
|
|
16
|
-
*
|
|
17
|
-
* Output: per row, postcode-FIRST (international) variants — the common order for the non-US
|
|
18
|
-
* locales this fills (US postcodes are already covered by TIGER/WOF, which use postcode-LAST):
|
|
19
|
-
*
|
|
20
|
-
* 1. `{ postcode, locality }` → "AD100 Canillo"
|
|
21
|
-
* 2. `{ postcode, locality, region }` → "AD100 Canillo, Canillo" Prefer configuring this adapter for
|
|
22
|
-
* non-US countries; for US, the postcode-last sources are the right order. License:
|
|
23
|
-
* `"CC-BY-4.0"` per row (attribute "GeoNames").
|
|
24
|
-
*/
|
|
25
|
-
import { stableSourceID } from "@mailwoman/corpus/adapters/utils";
|
|
26
|
-
import { reconcileComponents } from "@mailwoman/formatter";
|
|
27
|
-
import { TSVSpliterator } from "spliterator";
|
|
28
|
-
/**
|
|
29
|
-
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
30
|
-
* it came from.
|
|
31
|
-
*/
|
|
32
|
-
export const GEONAMES_POSTAL_ADAPTER_ID = "geonames-postal";
|
|
33
|
-
/**
|
|
34
|
-
* License carried by this source (CC-BY-4.0), attached to each row so downstream consumers inherit the terms rather
|
|
35
|
-
* than having to look them up.
|
|
36
|
-
*/
|
|
37
|
-
export const GEONAMES_POSTAL_DEFAULT_LICENSE = "CC-BY-4.0";
|
|
38
|
-
/**
|
|
39
|
-
* GeoNames postal-dump columns (0-based).
|
|
40
|
-
*/
|
|
41
|
-
const COL = { country: 0, postcode: 1, place: 2, admin1Name: 3 };
|
|
42
|
-
export function createGeonamesPostalAdapter() {
|
|
43
|
-
return {
|
|
44
|
-
id: GEONAMES_POSTAL_ADAPTER_ID,
|
|
45
|
-
defaultLicense: GEONAMES_POSTAL_DEFAULT_LICENSE,
|
|
46
|
-
description: "GeoNames postal codes (CC-BY-4.0) — multi-locale postcode→locality→region, names inline; international postcode-first order.",
|
|
47
|
-
async *rows(opts) {
|
|
48
|
-
// `header: false` — the GeoNames postal dump is headerless, and the spliterator would
|
|
49
|
-
// otherwise consume row 1 as column names and lose its first postcode.
|
|
50
|
-
const rows = TSVSpliterator.fromAsync(opts.inputPath, { header: false });
|
|
51
|
-
let emitted = 0;
|
|
52
|
-
for await (const rec of rows) {
|
|
53
|
-
if (opts.signal?.aborted)
|
|
54
|
-
break;
|
|
55
|
-
if (opts.limit !== undefined && emitted >= opts.limit)
|
|
56
|
-
break;
|
|
57
|
-
const cc = (rec[COL.country] ?? "").trim();
|
|
58
|
-
if (!cc)
|
|
59
|
-
continue;
|
|
60
|
-
if (opts.country && cc !== opts.country)
|
|
61
|
-
continue;
|
|
62
|
-
const postcode = (rec[COL.postcode] ?? "").trim();
|
|
63
|
-
const locality = (rec[COL.place] ?? "").trim();
|
|
64
|
-
if (!postcode || !locality)
|
|
65
|
-
continue;
|
|
66
|
-
const region = (rec[COL.admin1Name] ?? "").trim();
|
|
67
|
-
// Postcode-first (international) variants. Skip the region variant when admin1 just
|
|
68
|
-
// repeats the place (common for city-states / micro-admin) to avoid "X X" noise.
|
|
69
|
-
const variants = [
|
|
70
|
-
{ slot: "pl", comp: { postcode, locality }, raw: `${postcode} ${locality}` },
|
|
71
|
-
];
|
|
72
|
-
if (region && region.toLowerCase() !== locality.toLowerCase()) {
|
|
73
|
-
variants.push({
|
|
74
|
-
slot: "plr",
|
|
75
|
-
comp: { postcode, locality, region },
|
|
76
|
-
raw: `${postcode} ${locality}, ${region}`,
|
|
77
|
-
});
|
|
78
|
-
}
|
|
79
|
-
for (const v of variants) {
|
|
80
|
-
if (opts.limit !== undefined && emitted >= opts.limit)
|
|
81
|
-
break;
|
|
82
|
-
const aligned = reconcileComponents(v.comp, v.raw);
|
|
83
|
-
if (Object.keys(aligned).length < 2)
|
|
84
|
-
continue;
|
|
85
|
-
yield {
|
|
86
|
-
raw: v.raw,
|
|
87
|
-
components: aligned,
|
|
88
|
-
country: cc,
|
|
89
|
-
source: GEONAMES_POSTAL_ADAPTER_ID,
|
|
90
|
-
source_id: `${stableSourceID(GEONAMES_POSTAL_ADAPTER_ID, aligned)}-${v.slot}`,
|
|
91
|
-
corpus_version: "",
|
|
92
|
-
license: GEONAMES_POSTAL_DEFAULT_LICENSE,
|
|
93
|
-
};
|
|
94
|
-
emitted++;
|
|
95
|
-
}
|
|
96
|
-
}
|
|
97
|
-
},
|
|
98
|
-
};
|
|
99
|
-
}
|
|
100
|
-
/**
|
|
101
|
-
* The configured adapter instance registered with the corpus builder.
|
|
102
|
-
*/
|
|
103
|
-
export const geonamesPostalAdapter = createGeonamesPostalAdapter();
|
|
104
|
-
//# sourceMappingURL=adapter.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/geonames-postal/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAEH,OAAO,EAAE,cAAc,EAAE,MAAM,kCAAkC,CAAA;AAEjE,OAAO,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AAC1D,OAAO,EAAE,cAAc,EAAE,MAAM,aAAa,CAAA;AAE5C;;;GAGG;AACH,MAAM,CAAC,MAAM,0BAA0B,GAAG,iBAAiB,CAAA;AAC3D;;;GAGG;AACH,MAAM,CAAC,MAAM,+BAA+B,GAAG,WAAW,CAAA;AAE1D;;GAEG;AACH,MAAM,GAAG,GAAG,EAAE,OAAO,EAAE,CAAC,EAAE,QAAQ,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,UAAU,EAAE,CAAC,EAAW,CAAA;AAEzE,MAAM,UAAU,2BAA2B;IAC1C,OAAO;QACN,EAAE,EAAE,0BAA0B;QAC9B,cAAc,EAAE,+BAA+B;QAC/C,WAAW,EACV,8HAA8H;QAE/H,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,sFAAsF;YACtF,uEAAuE;YACvE,MAAM,IAAI,GAAG,cAAc,CAAC,SAAS,CAAC,IAAI,CAAC,SAAS,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,CAAA;YAExE,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,IAA+B,EAAE,CAAC;gBACzD,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;oBAAE,MAAK;gBAE/B,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;oBAAE,MAAK;gBAE5D,MAAM,EAAE,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAE1C,IAAI,CAAC,EAAE;oBAAE,SAAQ;gBAEjB,IAAI,IAAI,CAAC,OAAO,IAAI,EAAE,KAAK,IAAI,CAAC,OAAO;oBAAE,SAAQ;gBAEjD,MAAM,QAAQ,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBACjD,MAAM,QAAQ,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAE9C,IAAI,CAAC,QAAQ,IAAI,CAAC,QAAQ;oBAAE,SAAQ;gBACpC,MAAM,MAAM,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,UAAU,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAEjD,oFAAoF;gBACpF,iFAAiF;gBACjF,MAAM,QAAQ,GAA2E;oBACxF,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,EAAE,QAAQ,EAAE,QAAQ,EAAE,EAAE,GAAG,EAAE,GAAG,QAAQ,IAAI,QAAQ,EAAE,EAAE;iBAC5E,CAAA;gBAED,IAAI,MAAM,IAAI,MAAM,CAAC,WAAW,EAAE,KAAK,QAAQ,CAAC,WAAW,EAAE,EAAE,CAAC;oBAC/D,QAAQ,CAAC,IAAI,CAAC;wBACb,IAAI,EAAE,KAAK;wBACX,IAAI,EAAE,EAAE,QAAQ,EAAE,QAAQ,EAAE,MAAM,EAAE;wBACpC,GAAG,EAAE,GAAG,QAAQ,IAAI,QAAQ,KAAK,MAAM,EAAE;qBACzC,CAAC,CAAA;gBACH,CAAC;gBAED,KAAK,MAAM,CAAC,IAAI,QAAQ,EAAE,CAAC;oBAC1B,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;wBAAE,MAAK;oBAC5D,MAAM,OAAO,GAAG,mBAAmB,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,GAAG,CAAC,CAAA;oBAElD,IAAI,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM,GAAG,CAAC;wBAAE,SAAQ;oBAE7C,MAAM;wBACL,GAAG,EAAE,CAAC,CAAC,GAAG;wBACV,UAAU,EAAE,OAAO;wBACnB,OAAO,EAAE,EAAE;wBACX,MAAM,EAAE,0BAA0B;wBAClC,SAAS,EAAE,GAAG,cAAc,CAAC,0BAA0B,EAAE,OAAO,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE;wBAC7E,cAAc,EAAE,EAAE;wBAClB,OAAO,EAAE,+BAA+B;qBACxC,CAAA;oBAED,OAAO,EAAE,CAAA;gBACV,CAAC;YACF,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,qBAAqB,GAAG,2BAA2B,EAAE,CAAA"}
|
|
@@ -1,49 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* G-NAF (Australia) corpus adapter — the parser-teaching half of #208.
|
|
7
|
-
*
|
|
8
|
-
* The model mis-parses Australian addresses in their native postcode-first / house-number-last
|
|
9
|
-
* order: it tags a leading 4-digit postcode as a house number (its US/EU prior) and swaps street
|
|
10
|
-
* ↔ locality with it. `scripts/eval/au-order-probe.ts` proved this is a word-ORDER coverage gap,
|
|
11
|
-
* not capability — the same addresses parse perfectly in canonical order (65% → 87% @25km if the
|
|
12
|
-
* parse were order-robust). EU survives the same eval because its postcodes are
|
|
13
|
-
* format-distinctive (a hyphenated `26-300` reads as a postcode anywhere); a bare AU `3053` only
|
|
14
|
-
* disambiguates by position.
|
|
15
|
-
*
|
|
16
|
-
* So this adapter renders each assembled G-NAF tuple (from {@link ./assemble}) in one of three real
|
|
17
|
-
* AU layouts — real-AU canonical (number-first, postcode-trailing), postcode-first,
|
|
18
|
-
* locality-first — ROTATED by row index (`i % 3`), so the locality + postcode each land in every
|
|
19
|
-
* position across the shard. This is the exact mechanism that fixed #148's v1.9.0 order-overfit
|
|
20
|
-
* for the 16 EU locales (`scripts/rerender-overture-multiorder.mjs`, v1.9.1 → shipped v4.13.0);
|
|
21
|
-
* AU was simply never in that train (`country_weights` had no AU, and `data_loader.py` excludes
|
|
22
|
-
* unlisted countries). Rotating one order per row (rather than emitting all three) keeps this a
|
|
23
|
-
* clean single-variable extension of the proven recipe + matches its source-mass structure. The
|
|
24
|
-
* corpus aligner BIO-labels each (every component surface form occurs verbatim in `raw`, so
|
|
25
|
-
* alignment lands).
|
|
26
|
-
*
|
|
27
|
-
* Input: the assembled component JSONL (one `{house_number,street,locality,region,postcode}` per
|
|
28
|
-
* line). Open G-NAF licence — attribute "Geoscape Australia".
|
|
29
|
-
*/
|
|
30
|
-
import type { CorpusAdapter } from "@mailwoman/corpus/types";
|
|
31
|
-
/**
|
|
32
|
-
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
33
|
-
* it came from.
|
|
34
|
-
*/
|
|
35
|
-
export declare const GNAF_ADAPTER_ID = "gnaf";
|
|
36
|
-
/**
|
|
37
|
-
* Open G-NAF is freely redistributable with attribution to Geoscape Australia (CC-BY-style).
|
|
38
|
-
*/
|
|
39
|
-
export declare const GNAF_DEFAULT_LICENSE = "CC-BY-4.0";
|
|
40
|
-
/**
|
|
41
|
-
* Build the G-NAF adapter. `inputPath` is the assembled component JSONL (see {@link ./assemble}); it is country-pinned
|
|
42
|
-
* to AU regardless of `opts.country` (G-NAF is Australia-only).
|
|
43
|
-
*/
|
|
44
|
-
export declare function createGNAFAdapter(): CorpusAdapter;
|
|
45
|
-
/**
|
|
46
|
-
* The configured adapter instance registered with the corpus builder.
|
|
47
|
-
*/
|
|
48
|
-
export declare const gnafAdapter: CorpusAdapter;
|
|
49
|
-
//# sourceMappingURL=adapter.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/gnaf/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AAIH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,yBAAyB,CAAA;AAI1F;;;GAGG;AACH,eAAO,MAAM,eAAe,SAAS,CAAA;AACrC;;GAEG;AACH,eAAO,MAAM,oBAAoB,cAAc,CAAA;AA4B/C;;;GAGG;AACH,wBAAgB,iBAAiB,IAAI,aAAa,CAkEjD;AAED;;GAEG;AACH,eAAO,MAAM,WAAW,eAAsB,CAAA"}
|
|
@@ -1,124 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* G-NAF (Australia) corpus adapter — the parser-teaching half of #208.
|
|
7
|
-
*
|
|
8
|
-
* The model mis-parses Australian addresses in their native postcode-first / house-number-last
|
|
9
|
-
* order: it tags a leading 4-digit postcode as a house number (its US/EU prior) and swaps street
|
|
10
|
-
* ↔ locality with it. `scripts/eval/au-order-probe.ts` proved this is a word-ORDER coverage gap,
|
|
11
|
-
* not capability — the same addresses parse perfectly in canonical order (65% → 87% @25km if the
|
|
12
|
-
* parse were order-robust). EU survives the same eval because its postcodes are
|
|
13
|
-
* format-distinctive (a hyphenated `26-300` reads as a postcode anywhere); a bare AU `3053` only
|
|
14
|
-
* disambiguates by position.
|
|
15
|
-
*
|
|
16
|
-
* So this adapter renders each assembled G-NAF tuple (from {@link ./assemble}) in one of three real
|
|
17
|
-
* AU layouts — real-AU canonical (number-first, postcode-trailing), postcode-first,
|
|
18
|
-
* locality-first — ROTATED by row index (`i % 3`), so the locality + postcode each land in every
|
|
19
|
-
* position across the shard. This is the exact mechanism that fixed #148's v1.9.0 order-overfit
|
|
20
|
-
* for the 16 EU locales (`scripts/rerender-overture-multiorder.mjs`, v1.9.1 → shipped v4.13.0);
|
|
21
|
-
* AU was simply never in that train (`country_weights` had no AU, and `data_loader.py` excludes
|
|
22
|
-
* unlisted countries). Rotating one order per row (rather than emitting all three) keeps this a
|
|
23
|
-
* clean single-variable extension of the proven recipe + matches its source-mass structure. The
|
|
24
|
-
* corpus aligner BIO-labels each (every component surface form occurs verbatim in `raw`, so
|
|
25
|
-
* alignment lands).
|
|
26
|
-
*
|
|
27
|
-
* Input: the assembled component JSONL (one `{house_number,street,locality,region,postcode}` per
|
|
28
|
-
* line). Open G-NAF licence — attribute "Geoscape Australia".
|
|
29
|
-
*/
|
|
30
|
-
import { tryParsingJSON } from "@mailwoman/core/objects";
|
|
31
|
-
import { stableSourceID } from "@mailwoman/corpus/adapters/utils";
|
|
32
|
-
import { reconcileComponents } from "@mailwoman/formatter";
|
|
33
|
-
import { TextSpliterator } from "spliterator";
|
|
34
|
-
/**
|
|
35
|
-
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
36
|
-
* it came from.
|
|
37
|
-
*/
|
|
38
|
-
export const GNAF_ADAPTER_ID = "gnaf";
|
|
39
|
-
/**
|
|
40
|
-
* Open G-NAF is freely redistributable with attribution to Geoscape Australia (CC-BY-style).
|
|
41
|
-
*/
|
|
42
|
-
export const GNAF_DEFAULT_LICENSE = "CC-BY-4.0";
|
|
43
|
-
/**
|
|
44
|
-
* The address layouts an AU address actually arrives in. The model already handles postcode-TRAILING (canonical); the
|
|
45
|
-
* two postcode-LEADING forms are the ones it fails, so they carry the lever. We keep the canonical form too so the
|
|
46
|
-
* retrain doesn't forget it.
|
|
47
|
-
*/
|
|
48
|
-
function renderOrders(c) {
|
|
49
|
-
const region = c.region ? ` ${c.region}` : "";
|
|
50
|
-
return [
|
|
51
|
-
// real-AU canonical: number-first, street, suburb [state] postcode — "50 Barry Street, Carlton NSW 2000"
|
|
52
|
-
`${c.house_number} ${c.street}, ${c.locality}${region} ${c.postcode}`,
|
|
53
|
-
// postcode-first (the dominant failure): "2000 Carlton, Barry Street 50"
|
|
54
|
-
`${c.postcode} ${c.locality}, ${c.street} ${c.house_number}`,
|
|
55
|
-
// locality-first: "Carlton, 2000, Barry Street 50"
|
|
56
|
-
`${c.locality}, ${c.postcode}, ${c.street} ${c.house_number}`,
|
|
57
|
-
];
|
|
58
|
-
}
|
|
59
|
-
/**
|
|
60
|
-
* Build the G-NAF adapter. `inputPath` is the assembled component JSONL (see {@link ./assemble}); it is country-pinned
|
|
61
|
-
* to AU regardless of `opts.country` (G-NAF is Australia-only).
|
|
62
|
-
*/
|
|
63
|
-
export function createGNAFAdapter() {
|
|
64
|
-
return {
|
|
65
|
-
id: GNAF_ADAPTER_ID,
|
|
66
|
-
defaultLicense: GNAF_DEFAULT_LICENSE,
|
|
67
|
-
description: "G-NAF (Australia): assembled address tuples rendered in multiple word orders (canonical / postcode-first / locality-first) — teaches the model AU's postcode-first layout.",
|
|
68
|
-
async *rows(opts) {
|
|
69
|
-
let emitted = 0;
|
|
70
|
-
let idx = 0;
|
|
71
|
-
// Input is the assembled component JSONL (one tuple per line). TextSpliterator auto-disposes on
|
|
72
|
-
// loop completion and on an early `break` (abort / limit), so the old explicit handle teardown is
|
|
73
|
-
// gone; the parse tolerates a trailing CR on CRLF sources and the `!line.trim()` guard skips blanks.
|
|
74
|
-
// The render order rotates (i % 3), matching v1.9.1's rerender.
|
|
75
|
-
for await (const line of TextSpliterator.fromAsync(opts.inputPath)) {
|
|
76
|
-
if (opts.signal?.aborted)
|
|
77
|
-
break;
|
|
78
|
-
if (opts.limit !== undefined && emitted >= opts.limit)
|
|
79
|
-
break;
|
|
80
|
-
if (!line.trim())
|
|
81
|
-
continue;
|
|
82
|
-
const t = tryParsingJSON(line);
|
|
83
|
-
if (t === null)
|
|
84
|
-
continue;
|
|
85
|
-
if (!t.house_number || !t.street || !t.locality || !t.postcode)
|
|
86
|
-
continue;
|
|
87
|
-
const orders = renderOrders(t);
|
|
88
|
-
const order = idx % orders.length;
|
|
89
|
-
idx++;
|
|
90
|
-
const raw = orders[order];
|
|
91
|
-
const components = {
|
|
92
|
-
house_number: t.house_number,
|
|
93
|
-
street: t.street,
|
|
94
|
-
locality: t.locality,
|
|
95
|
-
postcode: t.postcode,
|
|
96
|
-
};
|
|
97
|
-
// region (state) rides only the canonical render (order 0); the postcode-leading layouts
|
|
98
|
-
// omit it (matching the eval's serialization) so it never breaks verbatim alignment.
|
|
99
|
-
if (order === 0 && t.region) {
|
|
100
|
-
components.region = t.region;
|
|
101
|
-
}
|
|
102
|
-
const aligned = reconcileComponents(components, raw);
|
|
103
|
-
if (!Object.keys(aligned).length)
|
|
104
|
-
continue;
|
|
105
|
-
yield {
|
|
106
|
-
raw,
|
|
107
|
-
components: aligned,
|
|
108
|
-
country: "AU",
|
|
109
|
-
locale: "en-AU",
|
|
110
|
-
source: GNAF_ADAPTER_ID,
|
|
111
|
-
source_id: `${stableSourceID(GNAF_ADAPTER_ID, aligned)}-o${order}`,
|
|
112
|
-
corpus_version: "",
|
|
113
|
-
license: GNAF_DEFAULT_LICENSE,
|
|
114
|
-
};
|
|
115
|
-
emitted++;
|
|
116
|
-
}
|
|
117
|
-
},
|
|
118
|
-
};
|
|
119
|
-
}
|
|
120
|
-
/**
|
|
121
|
-
* The configured adapter instance registered with the corpus builder.
|
|
122
|
-
*/
|
|
123
|
-
export const gnafAdapter = createGNAFAdapter();
|
|
124
|
-
//# sourceMappingURL=adapter.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/gnaf/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AAEH,OAAO,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAA;AACxD,OAAO,EAAE,cAAc,EAAE,MAAM,kCAAkC,CAAA;AAEjE,OAAO,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AAC1D,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C;;;GAGG;AACH,MAAM,CAAC,MAAM,eAAe,GAAG,MAAM,CAAA;AACrC;;GAEG;AACH,MAAM,CAAC,MAAM,oBAAoB,GAAG,WAAW,CAAA;AAU/C;;;;GAIG;AACH,SAAS,YAAY,CAAC,CAAY;IACjC,MAAM,MAAM,GAAG,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;IAE7C,OAAO;QACN,yGAAyG;QACzG,GAAG,CAAC,CAAC,YAAY,IAAI,CAAC,CAAC,MAAM,KAAK,CAAC,CAAC,QAAQ,GAAG,MAAM,IAAI,CAAC,CAAC,QAAQ,EAAE;QACrE,yEAAyE;QACzE,GAAG,CAAC,CAAC,QAAQ,IAAI,CAAC,CAAC,QAAQ,KAAK,CAAC,CAAC,MAAM,IAAI,CAAC,CAAC,YAAY,EAAE;QAC5D,mDAAmD;QACnD,GAAG,CAAC,CAAC,QAAQ,KAAK,CAAC,CAAC,QAAQ,KAAK,CAAC,CAAC,MAAM,IAAI,CAAC,CAAC,YAAY,EAAE;KAC7D,CAAA;AACF,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,iBAAiB;IAChC,OAAO;QACN,EAAE,EAAE,eAAe;QACnB,cAAc,EAAE,oBAAoB;QACpC,WAAW,EACV,4KAA4K;QAE7K,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,IAAI,OAAO,GAAG,CAAC,CAAA;YACf,IAAI,GAAG,GAAG,CAAC,CAAA;YAEX,gGAAgG;YAChG,kGAAkG;YAClG,qGAAqG;YACrG,gEAAgE;YAChE,IAAI,KAAK,EAAE,MAAM,IAAI,IAAI,eAAe,CAAC,SAAS,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,CAAC;gBACpE,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;oBAAE,MAAK;gBAE/B,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;oBAAE,MAAK;gBAE5D,IAAI,CAAC,IAAI,CAAC,IAAI,EAAE;oBAAE,SAAQ;gBAE1B,MAAM,CAAC,GAAG,cAAc,CAAY,IAAI,CAAC,CAAA;gBAEzC,IAAI,CAAC,KAAK,IAAI;oBAAE,SAAQ;gBAExB,IAAI,CAAC,CAAC,CAAC,YAAY,IAAI,CAAC,CAAC,CAAC,MAAM,IAAI,CAAC,CAAC,CAAC,QAAQ,IAAI,CAAC,CAAC,CAAC,QAAQ;oBAAE,SAAQ;gBAExE,MAAM,MAAM,GAAG,YAAY,CAAC,CAAC,CAAC,CAAA;gBAC9B,MAAM,KAAK,GAAG,GAAG,GAAG,MAAM,CAAC,MAAM,CAAA;gBAEjC,GAAG,EAAE,CAAA;gBACL,MAAM,GAAG,GAAG,MAAM,CAAC,KAAK,CAAE,CAAA;gBAE1B,MAAM,UAAU,GAA+B;oBAC9C,YAAY,EAAE,CAAC,CAAC,YAAY;oBAC5B,MAAM,EAAE,CAAC,CAAC,MAAM;oBAChB,QAAQ,EAAE,CAAC,CAAC,QAAQ;oBACpB,QAAQ,EAAE,CAAC,CAAC,QAAQ;iBACpB,CAAA;gBAED,yFAAyF;gBACzF,qFAAqF;gBACrF,IAAI,KAAK,KAAK,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,CAAC;oBAC7B,UAAU,CAAC,MAAM,GAAG,CAAC,CAAC,MAAM,CAAA;gBAC7B,CAAC;gBAED,MAAM,OAAO,GAAG,mBAAmB,CAAC,UAAU,EAAE,GAAG,CAAC,CAAA;gBAEpD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM;oBAAE,SAAQ;gBAE1C,MAAM;oBACL,GAAG;oBACH,UAAU,EAAE,OAAO;oBACnB,OAAO,EAAE,IAAI;oBACb,MAAM,EAAE,OAAO;oBACf,MAAM,EAAE,eAAe;oBACvB,SAAS,EAAE,GAAG,cAAc,CAAC,eAAe,EAAE,OAAO,CAAC,KAAK,KAAK,EAAE;oBAClE,cAAc,EAAE,EAAE;oBAClB,OAAO,EAAE,oBAAoB;iBAC7B,CAAA;gBAED,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,WAAW,GAAG,iBAAiB,EAAE,CAAA"}
|
|
@@ -1,65 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Assemble a sampled, component-labeled Australian address set from G-NAF (the Geocoded National
|
|
7
|
-
* Address File — Geoscape Australia, Open G-NAF licence; any derived artifact must attribute
|
|
8
|
-
* "Geoscape Australia"). G-NAF is a relational PSV distribution (~16.9M addresses);
|
|
9
|
-
* reconstructing a street address joins three tables — ADDRESS_DETAIL (number, postcode, the
|
|
10
|
-
* PIDs) → STREET_LOCALITY (street name + type) → LOCALITY (suburb). State is the per-file prefix
|
|
11
|
-
* (ACT/NSW/…).
|
|
12
|
-
*
|
|
13
|
-
* Streaming + in-memory join via the house {@link PSVSpliterator} (pipe-separated; `mode: "object"`
|
|
14
|
-
* keys each row by its header) — NOT raw `read_csv` SQL, which a flat-file join doesn't need and
|
|
15
|
-
* which the #183–190 cleanup retired. The two lookup tables (STREET_LOCALITY ~765k rows, LOCALITY
|
|
16
|
-
* ~16k) fit as Maps; ADDRESS_DETAIL is streamed once and reservoir-sampled, so memory stays
|
|
17
|
-
* bounded (the OOM lesson from the Overture ingest).
|
|
18
|
-
*
|
|
19
|
-
* No coordinates: the output feeds the PARSER ({@link ../gnaf/adapter}, #208) — teaching the model
|
|
20
|
-
* AU's postcode-first / house-number-last word order, the gap `scripts/eval/au-order-probe.ts`
|
|
21
|
-
* pinned (65%→87% if the parse were order-robust). The parser needs the address string +
|
|
22
|
-
* component labels, not lat/lon.
|
|
23
|
-
*
|
|
24
|
-
* Output: component tuples as JSONL, consumed by the `gnaf` corpus adapter (which renders them in
|
|
25
|
-
* multiple orders + the corpus aligner BIO-labels them). An optional held-out eval set is
|
|
26
|
-
* excluded by (street, locality, postcode) so the training shard never overlaps the benchmark.
|
|
27
|
-
*/
|
|
28
|
-
export interface GNAFAssembleOptions {
|
|
29
|
-
/**
|
|
30
|
-
* G-NAF `Standard` directory (holds the per-state `*_psv.psv` tables).
|
|
31
|
-
*/
|
|
32
|
-
standardDir: string;
|
|
33
|
-
/**
|
|
34
|
-
* Target sample size (uniform reservoir → population-proportional across states).
|
|
35
|
-
*/
|
|
36
|
-
sampleSize: number;
|
|
37
|
-
/**
|
|
38
|
-
* Output JSONL path.
|
|
39
|
-
*/
|
|
40
|
-
out: string;
|
|
41
|
-
/**
|
|
42
|
-
* Optional held-out eval JSONL (rows with a `components` field) — its (street,locality,postcode) are excluded.
|
|
43
|
-
*/
|
|
44
|
-
holdoutPath?: string;
|
|
45
|
-
/**
|
|
46
|
-
* Progress sink (the CLI passes a setter).
|
|
47
|
-
*/
|
|
48
|
-
onProgress?: (message: string) => void;
|
|
49
|
-
}
|
|
50
|
-
export interface GNAFAssembleResult {
|
|
51
|
-
written: number;
|
|
52
|
-
seen: number;
|
|
53
|
-
heldOut: number;
|
|
54
|
-
byState: Record<string, number>;
|
|
55
|
-
}
|
|
56
|
-
/**
|
|
57
|
-
* UPPERCASE → Title Case, preserving intra-word apostrophes/hyphens (O'Brien, Coff's Harbour).
|
|
58
|
-
*/
|
|
59
|
-
export declare function titlecase(s: string): string;
|
|
60
|
-
/**
|
|
61
|
-
* Holdout/dedup key: a street within a locality+postcode (house-number-agnostic — conservative).
|
|
62
|
-
*/
|
|
63
|
-
export declare function gnafHoldoutKey(street: string, locality: string, postcode: string): string;
|
|
64
|
-
export declare function assembleGNAF(opts: GNAFAssembleOptions): Promise<GNAFAssembleResult>;
|
|
65
|
-
//# sourceMappingURL=assemble.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"assemble.d.ts","sourceRoot":"","sources":["../../../../src/adapters/gnaf/assemble.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;GA0BG;AASH,MAAM,WAAW,mBAAmB;IACnC;;OAEG;IACH,WAAW,EAAE,MAAM,CAAA;IACnB;;OAEG;IACH,UAAU,EAAE,MAAM,CAAA;IAClB;;OAEG;IACH,GAAG,EAAE,MAAM,CAAA;IACX;;OAEG;IACH,WAAW,CAAC,EAAE,MAAM,CAAA;IACpB;;OAEG;IACH,UAAU,CAAC,EAAE,CAAC,OAAO,EAAE,MAAM,KAAK,IAAI,CAAA;CACtC;AAED,MAAM,WAAW,kBAAkB;IAClC,OAAO,EAAE,MAAM,CAAA;IACf,IAAI,EAAE,MAAM,CAAA;IACZ,OAAO,EAAE,MAAM,CAAA;IACf,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;CAC/B;AAED;;GAEG;AACH,wBAAgB,SAAS,CAAC,CAAC,EAAE,MAAM,GAAG,MAAM,CAK3C;AAED;;GAEG;AACH,wBAAgB,cAAc,CAAC,MAAM,EAAE,MAAM,EAAE,QAAQ,EAAE,MAAM,EAAE,QAAQ,EAAE,MAAM,GAAG,MAAM,CAEzF;AA8CD,wBAAsB,YAAY,CAAC,IAAI,EAAE,mBAAmB,GAAG,OAAO,CAAC,kBAAkB,CAAC,CAmGzF"}
|