@mailwoman/corpus 9.2.0 → 9.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +22 -22
- package/data/PROVENANCE.md +7 -7
- package/lib/adapters/ban/adapter.ts +190 -0
- package/lib/adapters/ban/street-decompose.ts +66 -0
- package/lib/adapters/fcc-bdc/adapter.ts +174 -0
- package/lib/adapters/geonames/adapter.ts +199 -0
- package/lib/adapters/geonames-postal/adapter.ts +122 -0
- package/lib/adapters/gnaf/adapter.ts +149 -0
- package/lib/adapters/gnaf/assemble.ts +225 -0
- package/lib/adapters/index.ts +153 -0
- package/lib/adapters/openaddresses/adapter.ts +251 -0
- package/lib/adapters/overture/adapter.ts +162 -0
- package/lib/adapters/state-hi-schools/adapter.ts +170 -0
- package/lib/adapters/state-hi-schools/workbook.ts +35 -0
- package/lib/adapters/synth-po-box/adapter.ts +204 -0
- package/lib/adapters/tiger/adapter.ts +252 -0
- package/lib/adapters/tiger/street-decompose.ts +83 -0
- package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +167 -0
- package/lib/adapters/usgov-imls-pls/adapter.ts +143 -0
- package/lib/adapters/usgov-irs-bmf/adapter.ts +151 -0
- package/lib/adapters/usgov-nad/adapter.ts +334 -0
- package/lib/adapters/usgov-nppes/adapter.ts +151 -0
- package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +193 -0
- package/lib/adapters/utils/index.ts +307 -0
- package/lib/adapters/wof-admin-jp/adapter.ts +214 -0
- package/lib/adapters/wof-admin-json/adapter.ts +231 -0
- package/lib/adapters/wof-json-rows.ts +129 -0
- package/lib/adapters/wof-postalcode-json/adapter.ts +176 -0
- package/lib/build.ts +378 -0
- package/lib/env.ts +50 -0
- package/lib/index.ts +13 -0
- package/lib/name-prone-us-suffixes.ts +12 -0
- package/lib/recipes/anchor-absorption.ts +101 -0
- package/lib/recipes/bare-country.ts +95 -0
- package/lib/recipes/boundary-stress.ts +100 -0
- package/lib/recipes/cn-organizational-units.ts +199 -0
- package/lib/recipes/country-balanced.ts +509 -0
- package/lib/recipes/cz-pcfirst-preposition.ts +111 -0
- package/lib/recipes/fr-admin-split.ts +242 -0
- package/lib/recipes/fr-bare-street.ts +170 -0
- package/lib/recipes/fr-fragment.ts +333 -0
- package/lib/recipes/fr-lieudit.ts +301 -0
- package/lib/recipes/fr-order.ts +245 -0
- package/lib/recipes/german.ts +359 -0
- package/lib/recipes/house-venue.ts +92 -0
- package/lib/recipes/index.ts +97 -0
- package/lib/recipes/intersection.ts +618 -0
- package/lib/recipes/locale.ts +599 -0
- package/lib/recipes/nl-postcode.ts +115 -0
- package/lib/recipes/no-fragment.ts +219 -0
- package/lib/recipes/no-street-led.ts +141 -0
- package/lib/recipes/no-street.ts +90 -0
- package/lib/recipes/po-box-cedex.ts +976 -0
- package/lib/recipes/po-box.ts +123 -0
- package/lib/recipes/reviewed-postcode-tail.ts +190 -0
- package/lib/recipes/scaffold.ts +469 -0
- package/lib/recipes/si-bare-village.ts +97 -0
- package/lib/recipes/street-affix.ts +804 -0
- package/lib/recipes/street-bare.ts +100 -0
- package/lib/recipes/street.ts +81 -0
- package/lib/recipes/sub-venue-sources.ts +877 -0
- package/lib/recipes/sub-venue.ts +997 -0
- package/lib/recipes/trailing-region.ts +183 -0
- package/lib/recipes/unit.ts +304 -0
- package/lib/runner.ts +312 -0
- package/lib/synthesizers/anchor-absorption.ts +288 -0
- package/lib/synthesizers/boundary-stress.ts +532 -0
- package/lib/synthesizers/german.ts +260 -0
- package/lib/synthesizers/house-venue.ts +308 -0
- package/lib/synthesizers/intersection.ts +233 -0
- package/lib/synthesizers/no-street.ts +327 -0
- package/lib/synthesizers/po-box.ts +323 -0
- package/lib/synthesizers/street.ts +269 -0
- package/lib/synthesizers/utils.ts +993 -0
- package/lib/test-kit/corpus-recipe.ts +86 -0
- package/lib/test-kit/index.ts +100 -0
- package/lib/tools/align-slice.ts +68 -0
- package/lib/tools/audit.ts +403 -0
- package/lib/tools/corpus-stats.ts +136 -0
- package/lib/tools/fetch/ban.ts +289 -0
- package/lib/tools/fetch/download.ts +262 -0
- package/lib/tools/fetch/geonames-dump.ts +257 -0
- package/lib/tools/fetch/geonames-postal.ts +180 -0
- package/lib/tools/fetch/hrsa.ts +59 -0
- package/lib/tools/fetch/imls-pls.ts +149 -0
- package/lib/tools/fetch/index.ts +147 -0
- package/lib/tools/fetch/nad.ts +341 -0
- package/lib/tools/fetch/nppes.ts +165 -0
- package/lib/tools/fetch/openaddresses.ts +347 -0
- package/lib/tools/fetch/ourairports.ts +170 -0
- package/lib/tools/fetch/ppd.ts +121 -0
- package/lib/tools/fetch/state-hi-schools.ts +161 -0
- package/lib/tools/fetch/state-sources.ts +146 -0
- package/lib/tools/fetch/tiger-full.ts +308 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +384 -0
- package/lib/tools/golden-expand.ts +574 -0
- package/lib/tools/golden-promote.ts +337 -0
- package/lib/tools/golden-relabel-street.ts +683 -0
- package/lib/tools/index.ts +28 -0
- package/lib/tools/ingest-csv.ts +378 -0
- package/lib/tools/jsonl-to-parquet.ts +207 -0
- package/lib/tools/lint-slice-vocab.ts +388 -0
- package/lib/tools/lint-slice.ts +496 -0
- package/lib/tools/overlay-manifest.ts +148 -0
- package/lib/tools/overture-subvenue.ts +209 -0
- package/lib/tools/postcode-triples.ts +363 -0
- package/lib/tools/slice-kryptonite.ts +137 -0
- package/lib/tools/slice-translit.ts +218 -0
- package/lib/tools/sub-venue/harvest.ts +234 -0
- package/lib/tools/sub-venue/head-nouns.ts +245 -0
- package/lib/tools/sub-venue/surfaces.ts +95 -0
- package/lib/tools/sub-venue/table.ts +281 -0
- package/lib/tools/sub-venue/wikidata.ts +85 -0
- package/lib/tools/sub-venue-lexicon.ts +429 -0
- package/lib/tools/sub-venue-promotions.ts +330 -0
- package/lib/types.ts +247 -0
- package/lib/utils/align.ts +330 -0
- package/lib/utils/golden.ts +189 -0
- package/lib/utils/index.ts +14 -0
- package/lib/utils/parquet.ts +582 -0
- package/lib/utils/slice-stats.ts +95 -0
- package/lib/utils/split.ts +279 -0
- package/lib/utils/tokenize.ts +120 -0
- package/lib/utils/wof-json.ts +247 -0
- package/out/adapters/ban/adapter.d.ts.map +1 -0
- package/out/adapters/ban/adapter.js +149 -0
- package/out/adapters/ban/adapter.js.map +1 -0
- package/out/adapters/ban/street-decompose.d.ts.map +1 -0
- package/out/adapters/ban/street-decompose.js +51 -0
- package/out/adapters/ban/street-decompose.js.map +1 -0
- package/out/adapters/fcc-bdc/adapter.d.ts.map +1 -0
- package/out/adapters/fcc-bdc/adapter.js +144 -0
- package/out/adapters/fcc-bdc/adapter.js.map +1 -0
- package/out/adapters/geonames/adapter.d.ts.map +1 -0
- package/out/adapters/geonames/adapter.js +176 -0
- package/out/adapters/geonames/adapter.js.map +1 -0
- package/out/adapters/geonames-postal/adapter.d.ts +54 -0
- package/out/adapters/geonames-postal/adapter.d.ts.map +1 -0
- package/out/adapters/geonames-postal/adapter.js +107 -0
- package/out/adapters/geonames-postal/adapter.js.map +1 -0
- package/out/adapters/gnaf/adapter.d.ts +49 -0
- package/out/adapters/gnaf/adapter.d.ts.map +1 -0
- package/out/adapters/gnaf/adapter.js +124 -0
- package/out/adapters/gnaf/adapter.js.map +1 -0
- package/out/adapters/gnaf/assemble.d.ts +65 -0
- package/out/adapters/gnaf/assemble.d.ts.map +1 -0
- package/out/adapters/gnaf/assemble.js +154 -0
- package/out/adapters/gnaf/assemble.js.map +1 -0
- package/out/adapters/index.d.ts +51 -0
- package/out/adapters/index.d.ts.map +1 -0
- package/out/adapters/index.js +95 -0
- package/out/adapters/index.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -0
- package/out/adapters/openaddresses/adapter.js +186 -0
- package/out/adapters/openaddresses/adapter.js.map +1 -0
- package/out/adapters/overture/adapter.d.ts +48 -0
- package/out/adapters/overture/adapter.d.ts.map +1 -0
- package/out/adapters/overture/adapter.js +125 -0
- package/out/adapters/overture/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/adapter.d.ts +46 -0
- package/out/adapters/state-hi-schools/adapter.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/adapter.js +145 -0
- package/out/adapters/state-hi-schools/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/workbook.d.ts +29 -0
- package/out/adapters/state-hi-schools/workbook.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/workbook.js +20 -0
- package/out/adapters/state-hi-schools/workbook.js.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
- package/out/adapters/synth-po-box/adapter.d.ts.map +1 -0
- package/out/adapters/synth-po-box/adapter.js +140 -0
- package/out/adapters/synth-po-box/adapter.js.map +1 -0
- package/out/adapters/tiger/adapter.d.ts +55 -0
- package/out/adapters/tiger/adapter.d.ts.map +1 -0
- package/out/adapters/tiger/adapter.js +201 -0
- package/out/adapters/tiger/adapter.js.map +1 -0
- package/out/adapters/tiger/street-decompose.d.ts.map +1 -0
- package/out/adapters/tiger/street-decompose.js +68 -0
- package/out/adapters/tiger/street-decompose.js.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +56 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js +132 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts +36 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.js +114 -0
- package/out/adapters/usgov-imls-pls/adapter.js.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts +37 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.js +120 -0
- package/out/adapters/usgov-irs-bmf/adapter.js.map +1 -0
- package/out/adapters/usgov-nad/adapter.d.ts +48 -0
- package/out/adapters/usgov-nad/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nad/adapter.js +249 -0
- package/out/adapters/usgov-nad/adapter.js.map +1 -0
- package/out/adapters/usgov-nppes/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nppes/adapter.js +118 -0
- package/out/adapters/usgov-nppes/adapter.js.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +154 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -0
- package/out/adapters/utils/index.d.ts +191 -0
- package/out/adapters/utils/index.d.ts.map +1 -0
- package/out/adapters/utils/index.js +206 -0
- package/out/adapters/utils/index.js.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.js +161 -0
- package/out/adapters/wof-admin-jp/adapter.js.map +1 -0
- package/out/adapters/wof-admin-json/adapter.d.ts +79 -0
- package/out/adapters/wof-admin-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-json/adapter.js +197 -0
- package/out/adapters/wof-admin-json/adapter.js.map +1 -0
- package/out/adapters/wof-json-rows.d.ts +62 -0
- package/out/adapters/wof-json-rows.d.ts.map +1 -0
- package/out/adapters/wof-json-rows.js +83 -0
- package/out/adapters/wof-json-rows.js.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts +65 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.js +151 -0
- package/out/adapters/wof-postalcode-json/adapter.js.map +1 -0
- package/out/build.d.ts +132 -0
- package/out/build.d.ts.map +1 -0
- package/out/build.js +245 -0
- package/out/build.js.map +1 -0
- package/out/codex/us-fips-state.d.ts.map +1 -0
- package/out/codex/us-fips-state.js.map +1 -0
- package/out/env.d.ts +46 -0
- package/out/env.d.ts.map +1 -0
- package/out/env.js +46 -0
- package/out/env.js.map +1 -0
- package/out/index.d.ts +13 -0
- package/out/index.d.ts.map +1 -0
- package/out/index.js +13 -0
- package/out/index.js.map +1 -0
- package/out/name-prone-us-suffixes.d.ts +12 -0
- package/out/name-prone-us-suffixes.d.ts.map +1 -0
- package/out/name-prone-us-suffixes.js +12 -0
- package/out/name-prone-us-suffixes.js.map +1 -0
- package/out/recipes/anchor-absorption.d.ts +20 -0
- package/out/recipes/anchor-absorption.d.ts.map +1 -0
- package/out/recipes/anchor-absorption.js +81 -0
- package/out/recipes/anchor-absorption.js.map +1 -0
- package/out/recipes/bare-country.d.ts +25 -0
- package/out/recipes/bare-country.d.ts.map +1 -0
- package/out/recipes/bare-country.js +87 -0
- package/out/recipes/bare-country.js.map +1 -0
- package/out/recipes/boundary-stress.d.ts +20 -0
- package/out/recipes/boundary-stress.d.ts.map +1 -0
- package/out/recipes/boundary-stress.js +83 -0
- package/out/recipes/boundary-stress.js.map +1 -0
- package/out/recipes/cn-organizational-units.d.ts +36 -0
- package/out/recipes/cn-organizational-units.d.ts.map +1 -0
- package/out/recipes/cn-organizational-units.js +159 -0
- package/out/recipes/cn-organizational-units.js.map +1 -0
- package/out/recipes/country-balanced.d.ts +32 -0
- package/out/recipes/country-balanced.d.ts.map +1 -0
- package/out/recipes/country-balanced.js +393 -0
- package/out/recipes/country-balanced.js.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts +22 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.js +100 -0
- package/out/recipes/cz-pcfirst-preposition.js.map +1 -0
- package/out/recipes/fr-admin-split.d.ts +38 -0
- package/out/recipes/fr-admin-split.d.ts.map +1 -0
- package/out/recipes/fr-admin-split.js +192 -0
- package/out/recipes/fr-admin-split.js.map +1 -0
- package/out/recipes/fr-bare-street.d.ts +28 -0
- package/out/recipes/fr-bare-street.d.ts.map +1 -0
- package/out/recipes/fr-bare-street.js +143 -0
- package/out/recipes/fr-bare-street.js.map +1 -0
- package/out/recipes/fr-fragment.d.ts +77 -0
- package/out/recipes/fr-fragment.d.ts.map +1 -0
- package/out/recipes/fr-fragment.js +276 -0
- package/out/recipes/fr-fragment.js.map +1 -0
- package/out/recipes/fr-lieudit.d.ts +32 -0
- package/out/recipes/fr-lieudit.d.ts.map +1 -0
- package/out/recipes/fr-lieudit.js +227 -0
- package/out/recipes/fr-lieudit.js.map +1 -0
- package/out/recipes/fr-order.d.ts +38 -0
- package/out/recipes/fr-order.d.ts.map +1 -0
- package/out/recipes/fr-order.js +197 -0
- package/out/recipes/fr-order.js.map +1 -0
- package/out/recipes/german.d.ts +44 -0
- package/out/recipes/german.d.ts.map +1 -0
- package/out/recipes/german.js +288 -0
- package/out/recipes/german.js.map +1 -0
- package/out/recipes/house-venue.d.ts +18 -0
- package/out/recipes/house-venue.d.ts.map +1 -0
- package/out/recipes/house-venue.js +73 -0
- package/out/recipes/house-venue.js.map +1 -0
- package/out/recipes/index.d.ts +24 -0
- package/out/recipes/index.d.ts.map +1 -0
- package/out/recipes/index.js +91 -0
- package/out/recipes/index.js.map +1 -0
- package/out/recipes/intersection.d.ts +42 -0
- package/out/recipes/intersection.d.ts.map +1 -0
- package/out/recipes/intersection.js +452 -0
- package/out/recipes/intersection.js.map +1 -0
- package/out/recipes/locale.d.ts +136 -0
- package/out/recipes/locale.d.ts.map +1 -0
- package/out/recipes/locale.js +460 -0
- package/out/recipes/locale.js.map +1 -0
- package/out/recipes/nl-postcode.d.ts +26 -0
- package/out/recipes/nl-postcode.d.ts.map +1 -0
- package/out/recipes/nl-postcode.js +102 -0
- package/out/recipes/nl-postcode.js.map +1 -0
- package/out/recipes/no-fragment.d.ts +43 -0
- package/out/recipes/no-fragment.d.ts.map +1 -0
- package/out/recipes/no-fragment.js +182 -0
- package/out/recipes/no-fragment.js.map +1 -0
- package/out/recipes/no-street-led.d.ts +24 -0
- package/out/recipes/no-street-led.d.ts.map +1 -0
- package/out/recipes/no-street-led.js +113 -0
- package/out/recipes/no-street-led.js.map +1 -0
- package/out/recipes/no-street.d.ts +18 -0
- package/out/recipes/no-street.d.ts.map +1 -0
- package/out/recipes/no-street.js +71 -0
- package/out/recipes/no-street.js.map +1 -0
- package/out/recipes/po-box-cedex.d.ts +38 -0
- package/out/recipes/po-box-cedex.d.ts.map +1 -0
- package/out/recipes/po-box-cedex.js +767 -0
- package/out/recipes/po-box-cedex.js.map +1 -0
- package/out/recipes/po-box.d.ts +17 -0
- package/out/recipes/po-box.d.ts.map +1 -0
- package/out/recipes/po-box.js +100 -0
- package/out/recipes/po-box.js.map +1 -0
- package/out/recipes/reviewed-postcode-tail.d.ts +47 -0
- package/out/recipes/reviewed-postcode-tail.d.ts.map +1 -0
- package/out/recipes/reviewed-postcode-tail.js +125 -0
- package/out/recipes/reviewed-postcode-tail.js.map +1 -0
- package/out/recipes/scaffold.d.ts +324 -0
- package/out/recipes/scaffold.d.ts.map +1 -0
- package/out/recipes/scaffold.js +186 -0
- package/out/recipes/scaffold.js.map +1 -0
- package/out/recipes/si-bare-village.d.ts +32 -0
- package/out/recipes/si-bare-village.d.ts.map +1 -0
- package/out/recipes/si-bare-village.js +88 -0
- package/out/recipes/si-bare-village.js.map +1 -0
- package/out/recipes/street-affix.d.ts +89 -0
- package/out/recipes/street-affix.d.ts.map +1 -0
- package/out/recipes/street-affix.js +563 -0
- package/out/recipes/street-affix.js.map +1 -0
- package/out/recipes/street-bare.d.ts +25 -0
- package/out/recipes/street-bare.d.ts.map +1 -0
- package/out/recipes/street-bare.js +86 -0
- package/out/recipes/street-bare.js.map +1 -0
- package/out/recipes/street.d.ts +15 -0
- package/out/recipes/street.d.ts.map +1 -0
- package/out/recipes/street.js +69 -0
- package/out/recipes/street.js.map +1 -0
- package/out/recipes/sub-venue-sources.d.ts +229 -0
- package/out/recipes/sub-venue-sources.d.ts.map +1 -0
- package/out/recipes/sub-venue-sources.js +653 -0
- package/out/recipes/sub-venue-sources.js.map +1 -0
- package/out/recipes/sub-venue.d.ts +269 -0
- package/out/recipes/sub-venue.d.ts.map +1 -0
- package/out/recipes/sub-venue.js +725 -0
- package/out/recipes/sub-venue.js.map +1 -0
- package/out/recipes/trailing-region.d.ts +74 -0
- package/out/recipes/trailing-region.d.ts.map +1 -0
- package/out/recipes/trailing-region.js +157 -0
- package/out/recipes/trailing-region.js.map +1 -0
- package/out/recipes/unit.d.ts +29 -0
- package/out/recipes/unit.d.ts.map +1 -0
- package/out/recipes/unit.js +230 -0
- package/out/recipes/unit.js.map +1 -0
- package/out/runner.d.ts +130 -0
- package/out/runner.d.ts.map +1 -0
- package/out/runner.js +185 -0
- package/out/runner.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +63 -0
- package/out/synthesizers/anchor-absorption.d.ts.map +1 -0
- package/out/synthesizers/anchor-absorption.js +221 -0
- package/out/synthesizers/anchor-absorption.js.map +1 -0
- package/out/synthesizers/boundary-stress.d.ts +78 -0
- package/out/synthesizers/boundary-stress.d.ts.map +1 -0
- package/out/synthesizers/boundary-stress.js +455 -0
- package/out/synthesizers/boundary-stress.js.map +1 -0
- package/out/synthesizers/german.d.ts +115 -0
- package/out/synthesizers/german.d.ts.map +1 -0
- package/out/synthesizers/german.js +149 -0
- package/out/synthesizers/german.js.map +1 -0
- package/out/synthesizers/house-venue.d.ts +56 -0
- package/out/synthesizers/house-venue.d.ts.map +1 -0
- package/out/synthesizers/house-venue.js +247 -0
- package/out/synthesizers/house-venue.js.map +1 -0
- package/out/synthesizers/intersection.d.ts +52 -0
- package/out/synthesizers/intersection.d.ts.map +1 -0
- package/out/synthesizers/intersection.js +175 -0
- package/out/synthesizers/intersection.js.map +1 -0
- package/out/synthesizers/no-street.d.ts +72 -0
- package/out/synthesizers/no-street.d.ts.map +1 -0
- package/out/synthesizers/no-street.js +262 -0
- package/out/synthesizers/no-street.js.map +1 -0
- package/out/synthesizers/po-box.d.ts +108 -0
- package/out/synthesizers/po-box.d.ts.map +1 -0
- package/out/synthesizers/po-box.js +250 -0
- package/out/synthesizers/po-box.js.map +1 -0
- package/out/synthesizers/street.d.ts +54 -0
- package/out/synthesizers/street.d.ts.map +1 -0
- package/out/synthesizers/street.js +218 -0
- package/out/synthesizers/street.js.map +1 -0
- package/out/synthesizers/utils.d.ts +241 -0
- package/out/synthesizers/utils.d.ts.map +1 -0
- package/out/synthesizers/utils.js +776 -0
- package/out/synthesizers/utils.js.map +1 -0
- package/out/test-kit/corpus-recipe.d.ts +59 -0
- package/out/test-kit/corpus-recipe.d.ts.map +1 -0
- package/out/test-kit/corpus-recipe.js +39 -0
- package/out/test-kit/corpus-recipe.js.map +1 -0
- package/out/test-kit/index.d.ts +48 -0
- package/out/test-kit/index.d.ts.map +1 -0
- package/out/test-kit/index.js +78 -0
- package/out/test-kit/index.js.map +1 -0
- package/out/tools/align-slice.d.ts +7 -0
- package/out/tools/align-slice.d.ts.map +1 -0
- package/out/tools/align-slice.js +55 -0
- package/out/tools/align-slice.js.map +1 -0
- package/out/tools/audit.d.ts +29 -0
- package/out/tools/audit.d.ts.map +1 -0
- package/out/tools/audit.js +282 -0
- package/out/tools/audit.js.map +1 -0
- package/out/tools/corpus-stats.d.ts +44 -0
- package/out/tools/corpus-stats.d.ts.map +1 -0
- package/out/tools/corpus-stats.js +102 -0
- package/out/tools/corpus-stats.js.map +1 -0
- package/out/tools/fetch/ban.d.ts +31 -0
- package/out/tools/fetch/ban.d.ts.map +1 -0
- package/out/tools/fetch/ban.js +239 -0
- package/out/tools/fetch/ban.js.map +1 -0
- package/out/tools/fetch/download.d.ts +117 -0
- package/out/tools/fetch/download.d.ts.map +1 -0
- package/out/tools/fetch/download.js +160 -0
- package/out/tools/fetch/download.js.map +1 -0
- package/out/tools/fetch/geonames-dump.d.ts +91 -0
- package/out/tools/fetch/geonames-dump.d.ts.map +1 -0
- package/out/tools/fetch/geonames-dump.js +171 -0
- package/out/tools/fetch/geonames-dump.js.map +1 -0
- package/out/tools/fetch/geonames-postal.d.ts +76 -0
- package/out/tools/fetch/geonames-postal.d.ts.map +1 -0
- package/out/tools/fetch/geonames-postal.js +126 -0
- package/out/tools/fetch/geonames-postal.js.map +1 -0
- package/out/tools/fetch/hrsa.d.ts +18 -0
- package/out/tools/fetch/hrsa.d.ts.map +1 -0
- package/out/tools/fetch/hrsa.js +46 -0
- package/out/tools/fetch/hrsa.js.map +1 -0
- package/out/tools/fetch/imls-pls.d.ts +25 -0
- package/out/tools/fetch/imls-pls.d.ts.map +1 -0
- package/out/tools/fetch/imls-pls.js +108 -0
- package/out/tools/fetch/imls-pls.js.map +1 -0
- package/out/tools/fetch/index.d.ts +144 -0
- package/out/tools/fetch/index.d.ts.map +1 -0
- package/out/tools/fetch/index.js +143 -0
- package/out/tools/fetch/index.js.map +1 -0
- package/out/tools/fetch/nad.d.ts +70 -0
- package/out/tools/fetch/nad.d.ts.map +1 -0
- package/out/tools/fetch/nad.js +234 -0
- package/out/tools/fetch/nad.js.map +1 -0
- package/out/tools/fetch/nppes.d.ts +26 -0
- package/out/tools/fetch/nppes.d.ts.map +1 -0
- package/out/tools/fetch/nppes.js +126 -0
- package/out/tools/fetch/nppes.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +9 -0
- package/out/tools/fetch/openaddresses.d.ts.map +1 -0
- package/out/tools/fetch/openaddresses.js +279 -0
- package/out/tools/fetch/openaddresses.js.map +1 -0
- package/out/tools/fetch/ourairports.d.ts +45 -0
- package/out/tools/fetch/ourairports.d.ts.map +1 -0
- package/out/tools/fetch/ourairports.js +128 -0
- package/out/tools/fetch/ourairports.js.map +1 -0
- package/out/tools/fetch/ppd.d.ts.map +1 -0
- package/out/tools/fetch/ppd.js +85 -0
- package/out/tools/fetch/ppd.js.map +1 -0
- package/out/tools/fetch/state-hi-schools.d.ts +26 -0
- package/out/tools/fetch/state-hi-schools.d.ts.map +1 -0
- package/out/tools/fetch/state-hi-schools.js +112 -0
- package/out/tools/fetch/state-hi-schools.js.map +1 -0
- package/out/tools/fetch/state-sources.d.ts +26 -0
- package/out/tools/fetch/state-sources.d.ts.map +1 -0
- package/out/tools/fetch/state-sources.js +111 -0
- package/out/tools/fetch/state-sources.js.map +1 -0
- package/out/tools/fetch/tiger-full.d.ts +22 -0
- package/out/tools/fetch/tiger-full.d.ts.map +1 -0
- package/out/tools/fetch/tiger-full.js +217 -0
- package/out/tools/fetch/tiger-full.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +171 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.js +274 -0
- package/out/tools/fetch/wikidata-subvenue.js.map +1 -0
- package/out/tools/gb-title-case.d.ts.map +1 -0
- package/out/tools/gb-title-case.js.map +1 -0
- package/out/tools/golden-expand.d.ts +90 -0
- package/out/tools/golden-expand.d.ts.map +1 -0
- package/out/tools/golden-expand.js +406 -0
- package/out/tools/golden-expand.js.map +1 -0
- package/out/tools/golden-promote.d.ts.map +1 -0
- package/out/tools/golden-promote.js +240 -0
- package/out/tools/golden-promote.js.map +1 -0
- package/out/tools/golden-relabel-street.d.ts +196 -0
- package/out/tools/golden-relabel-street.d.ts.map +1 -0
- package/out/tools/golden-relabel-street.js +440 -0
- package/out/tools/golden-relabel-street.js.map +1 -0
- package/out/tools/index.d.ts +28 -0
- package/out/tools/index.d.ts.map +1 -0
- package/out/tools/index.js +28 -0
- package/out/tools/index.js.map +1 -0
- package/out/tools/ingest-csv.d.ts.map +1 -0
- package/out/tools/ingest-csv.js +265 -0
- package/out/tools/ingest-csv.js.map +1 -0
- package/out/tools/jsonl-to-parquet.d.ts +61 -0
- package/out/tools/jsonl-to-parquet.d.ts.map +1 -0
- package/out/tools/jsonl-to-parquet.js +150 -0
- package/out/tools/jsonl-to-parquet.js.map +1 -0
- package/out/tools/lint-slice-vocab.d.ts +90 -0
- package/out/tools/lint-slice-vocab.d.ts.map +1 -0
- package/out/tools/lint-slice-vocab.js +267 -0
- package/out/tools/lint-slice-vocab.js.map +1 -0
- package/out/tools/lint-slice.d.ts +93 -0
- package/out/tools/lint-slice.d.ts.map +1 -0
- package/out/tools/lint-slice.js +322 -0
- package/out/tools/lint-slice.js.map +1 -0
- package/out/tools/overlay-manifest.d.ts +39 -0
- package/out/tools/overlay-manifest.d.ts.map +1 -0
- package/out/tools/overlay-manifest.js +90 -0
- package/out/tools/overlay-manifest.js.map +1 -0
- package/out/tools/overture-subvenue.d.ts +112 -0
- package/out/tools/overture-subvenue.d.ts.map +1 -0
- package/out/tools/overture-subvenue.js +139 -0
- package/out/tools/overture-subvenue.js.map +1 -0
- package/out/tools/postcode-triples.d.ts +174 -0
- package/out/tools/postcode-triples.d.ts.map +1 -0
- package/out/tools/postcode-triples.js +292 -0
- package/out/tools/postcode-triples.js.map +1 -0
- package/out/tools/slice-kryptonite.d.ts +32 -0
- package/out/tools/slice-kryptonite.d.ts.map +1 -0
- package/out/tools/slice-kryptonite.js +99 -0
- package/out/tools/slice-kryptonite.js.map +1 -0
- package/out/tools/slice-translit.d.ts +51 -0
- package/out/tools/slice-translit.d.ts.map +1 -0
- package/out/tools/slice-translit.js +166 -0
- package/out/tools/slice-translit.js.map +1 -0
- package/out/tools/sub-venue/harvest.d.ts +100 -0
- package/out/tools/sub-venue/harvest.d.ts.map +1 -0
- package/out/tools/sub-venue/harvest.js +168 -0
- package/out/tools/sub-venue/harvest.js.map +1 -0
- package/out/tools/sub-venue/head-nouns.d.ts +50 -0
- package/out/tools/sub-venue/head-nouns.d.ts.map +1 -0
- package/out/tools/sub-venue/head-nouns.js +213 -0
- package/out/tools/sub-venue/head-nouns.js.map +1 -0
- package/out/tools/sub-venue/surfaces.d.ts +45 -0
- package/out/tools/sub-venue/surfaces.d.ts.map +1 -0
- package/out/tools/sub-venue/surfaces.js +77 -0
- package/out/tools/sub-venue/surfaces.js.map +1 -0
- package/out/tools/sub-venue/table.d.ts +229 -0
- package/out/tools/sub-venue/table.d.ts.map +1 -0
- package/out/tools/sub-venue/table.js +108 -0
- package/out/tools/sub-venue/table.js.map +1 -0
- package/out/tools/sub-venue/wikidata.d.ts +26 -0
- package/out/tools/sub-venue/wikidata.d.ts.map +1 -0
- package/out/tools/sub-venue/wikidata.js +62 -0
- package/out/tools/sub-venue/wikidata.js.map +1 -0
- package/out/tools/sub-venue-lexicon.d.ts +156 -0
- package/out/tools/sub-venue-lexicon.d.ts.map +1 -0
- package/out/tools/sub-venue-lexicon.js +283 -0
- package/out/tools/sub-venue-lexicon.js.map +1 -0
- package/out/tools/sub-venue-promotions.d.ts +94 -0
- package/out/tools/sub-venue-promotions.d.ts.map +1 -0
- package/out/tools/sub-venue-promotions.js +266 -0
- package/out/tools/sub-venue-promotions.js.map +1 -0
- package/out/types.d.ts +221 -0
- package/out/types.d.ts.map +1 -0
- package/out/types.js.map +1 -0
- package/out/utils/align.d.ts +93 -0
- package/out/utils/align.d.ts.map +1 -0
- package/out/utils/align.js +234 -0
- package/out/utils/align.js.map +1 -0
- package/out/utils/golden.d.ts +85 -0
- package/out/utils/golden.d.ts.map +1 -0
- package/out/utils/golden.js +127 -0
- package/out/utils/golden.js.map +1 -0
- package/out/utils/index.d.ts +14 -0
- package/out/utils/index.d.ts.map +1 -0
- package/out/utils/index.js +14 -0
- package/out/utils/index.js.map +1 -0
- package/out/utils/license.d.ts.map +1 -0
- package/out/utils/license.js.map +1 -0
- package/out/utils/parquet.d.ts +178 -0
- package/out/utils/parquet.d.ts.map +1 -0
- package/out/utils/parquet.js +371 -0
- package/out/utils/parquet.js.map +1 -0
- package/out/utils/slice-stats.d.ts +52 -0
- package/out/utils/slice-stats.d.ts.map +1 -0
- package/out/utils/slice-stats.js +58 -0
- package/out/utils/slice-stats.js.map +1 -0
- package/out/utils/split.d.ts +128 -0
- package/out/utils/split.d.ts.map +1 -0
- package/out/utils/split.js +204 -0
- package/out/utils/split.js.map +1 -0
- package/out/utils/tokenize.d.ts +64 -0
- package/out/utils/tokenize.d.ts.map +1 -0
- package/out/utils/tokenize.js +82 -0
- package/out/utils/tokenize.js.map +1 -0
- package/out/utils/wof-json.d.ts +113 -0
- package/out/utils/wof-json.d.ts.map +1 -0
- package/out/utils/wof-json.js +173 -0
- package/out/utils/wof-json.js.map +1 -0
- package/package.json +259 -194
- package/out/src/adapters/ban/adapter.d.ts.map +0 -1
- package/out/src/adapters/ban/adapter.js +0 -149
- package/out/src/adapters/ban/adapter.js.map +0 -1
- package/out/src/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/ban/street-decompose.js +0 -75
- package/out/src/adapters/ban/street-decompose.js.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.d.ts.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.js +0 -144
- package/out/src/adapters/fcc-bdc/adapter.js.map +0 -1
- package/out/src/adapters/geonames/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames/adapter.js +0 -176
- package/out/src/adapters/geonames/adapter.js.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.d.ts +0 -41
- package/out/src/adapters/geonames-postal/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.js +0 -104
- package/out/src/adapters/geonames-postal/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/adapter.d.ts +0 -49
- package/out/src/adapters/gnaf/adapter.d.ts.map +0 -1
- package/out/src/adapters/gnaf/adapter.js +0 -124
- package/out/src/adapters/gnaf/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/assemble.d.ts +0 -65
- package/out/src/adapters/gnaf/assemble.d.ts.map +0 -1
- package/out/src/adapters/gnaf/assemble.js +0 -154
- package/out/src/adapters/gnaf/assemble.js.map +0 -1
- package/out/src/adapters/index.d.ts +0 -51
- package/out/src/adapters/index.d.ts.map +0 -1
- package/out/src/adapters/index.js +0 -95
- package/out/src/adapters/index.js.map +0 -1
- package/out/src/adapters/openaddresses/adapter.d.ts.map +0 -1
- package/out/src/adapters/openaddresses/adapter.js +0 -186
- package/out/src/adapters/openaddresses/adapter.js.map +0 -1
- package/out/src/adapters/overture/adapter.d.ts +0 -48
- package/out/src/adapters/overture/adapter.d.ts.map +0 -1
- package/out/src/adapters/overture/adapter.js +0 -125
- package/out/src/adapters/overture/adapter.js.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.d.ts +0 -47
- package/out/src/adapters/state-hi-schools/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.js +0 -133
- package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.d.ts.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.js +0 -140
- package/out/src/adapters/synth-po-box/adapter.js.map +0 -1
- package/out/src/adapters/tiger/adapter.d.ts +0 -55
- package/out/src/adapters/tiger/adapter.d.ts.map +0 -1
- package/out/src/adapters/tiger/adapter.js +0 -201
- package/out/src/adapters/tiger/adapter.js.map +0 -1
- package/out/src/adapters/tiger/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/tiger/street-decompose.js +0 -90
- package/out/src/adapters/tiger/street-decompose.js.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -47
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +0 -139
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts +0 -36
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.js +0 -114
- package/out/src/adapters/usgov-imls-pls/adapter.js.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.js +0 -124
- package/out/src/adapters/usgov-irs-bmf/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.d.ts +0 -48
- package/out/src/adapters/usgov-nad/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.js +0 -252
- package/out/src/adapters/usgov-nad/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.js +0 -116
- package/out/src/adapters/usgov-nppes/adapter.js.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -156
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
- package/out/src/adapters/utils/index.d.ts +0 -150
- package/out/src/adapters/utils/index.d.ts.map +0 -1
- package/out/src/adapters/utils/index.js +0 -159
- package/out/src/adapters/utils/index.js.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.js +0 -164
- package/out/src/adapters/wof-admin-jp/adapter.js.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.d.ts +0 -82
- package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.js +0 -224
- package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
- package/out/src/adapters/wof-json-rows.d.ts +0 -32
- package/out/src/adapters/wof-json-rows.d.ts.map +0 -1
- package/out/src/adapters/wof-json-rows.js +0 -45
- package/out/src/adapters/wof-json-rows.js.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -65
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.js +0 -160
- package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
- package/out/src/build.d.ts +0 -132
- package/out/src/build.d.ts.map +0 -1
- package/out/src/build.js +0 -251
- package/out/src/build.js.map +0 -1
- package/out/src/codex/us-fips-state.d.ts.map +0 -1
- package/out/src/codex/us-fips-state.js.map +0 -1
- package/out/src/index.d.ts +0 -14
- package/out/src/index.d.ts.map +0 -1
- package/out/src/index.js +0 -14
- package/out/src/index.js.map +0 -1
- package/out/src/name-prone-us-suffixes.d.ts +0 -12
- package/out/src/name-prone-us-suffixes.d.ts.map +0 -1
- package/out/src/name-prone-us-suffixes.js +0 -12
- package/out/src/name-prone-us-suffixes.js.map +0 -1
- package/out/src/parquet-wrapper/index.d.ts +0 -9
- package/out/src/parquet-wrapper/index.d.ts.map +0 -1
- package/out/src/parquet-wrapper/index.js +0 -9
- package/out/src/parquet-wrapper/index.js.map +0 -1
- package/out/src/parquet-wrapper/reader.d.ts +0 -34
- package/out/src/parquet-wrapper/reader.d.ts.map +0 -1
- package/out/src/parquet-wrapper/reader.js +0 -69
- package/out/src/parquet-wrapper/reader.js.map +0 -1
- package/out/src/parquet-wrapper/schema.d.ts +0 -49
- package/out/src/parquet-wrapper/schema.d.ts.map +0 -1
- package/out/src/parquet-wrapper/schema.js +0 -55
- package/out/src/parquet-wrapper/schema.js.map +0 -1
- package/out/src/parquet-wrapper/writer.d.ts +0 -46
- package/out/src/parquet-wrapper/writer.d.ts.map +0 -1
- package/out/src/parquet-wrapper/writer.js +0 -76
- package/out/src/parquet-wrapper/writer.js.map +0 -1
- package/out/src/runner.d.ts +0 -126
- package/out/src/runner.d.ts.map +0 -1
- package/out/src/runner.js +0 -189
- package/out/src/runner.js.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.d.ts +0 -20
- package/out/src/shard-recipes/anchor-absorption.d.ts.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.js +0 -82
- package/out/src/shard-recipes/anchor-absorption.js.map +0 -1
- package/out/src/shard-recipes/bare-country.d.ts +0 -25
- package/out/src/shard-recipes/bare-country.d.ts.map +0 -1
- package/out/src/shard-recipes/bare-country.js +0 -87
- package/out/src/shard-recipes/bare-country.js.map +0 -1
- package/out/src/shard-recipes/boundary-stress.d.ts +0 -20
- package/out/src/shard-recipes/boundary-stress.d.ts.map +0 -1
- package/out/src/shard-recipes/boundary-stress.js +0 -83
- package/out/src/shard-recipes/boundary-stress.js.map +0 -1
- package/out/src/shard-recipes/country-balanced.d.ts +0 -32
- package/out/src/shard-recipes/country-balanced.d.ts.map +0 -1
- package/out/src/shard-recipes/country-balanced.js +0 -406
- package/out/src/shard-recipes/country-balanced.js.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts +0 -22
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.js +0 -100
- package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.d.ts +0 -38
- package/out/src/shard-recipes/fr-admin-split.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.js +0 -188
- package/out/src/shard-recipes/fr-admin-split.js.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.d.ts +0 -28
- package/out/src/shard-recipes/fr-bare-street.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.js +0 -143
- package/out/src/shard-recipes/fr-bare-street.js.map +0 -1
- package/out/src/shard-recipes/fr-fragment.d.ts +0 -77
- package/out/src/shard-recipes/fr-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-fragment.js +0 -276
- package/out/src/shard-recipes/fr-fragment.js.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.d.ts +0 -32
- package/out/src/shard-recipes/fr-lieudit.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.js +0 -226
- package/out/src/shard-recipes/fr-lieudit.js.map +0 -1
- package/out/src/shard-recipes/fr-order.d.ts +0 -38
- package/out/src/shard-recipes/fr-order.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-order.js +0 -208
- package/out/src/shard-recipes/fr-order.js.map +0 -1
- package/out/src/shard-recipes/german.d.ts +0 -23
- package/out/src/shard-recipes/german.d.ts.map +0 -1
- package/out/src/shard-recipes/german.js +0 -132
- package/out/src/shard-recipes/german.js.map +0 -1
- package/out/src/shard-recipes/house-venue.d.ts +0 -18
- package/out/src/shard-recipes/house-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/house-venue.js +0 -74
- package/out/src/shard-recipes/house-venue.js.map +0 -1
- package/out/src/shard-recipes/index.d.ts +0 -24
- package/out/src/shard-recipes/index.d.ts.map +0 -1
- package/out/src/shard-recipes/index.js +0 -89
- package/out/src/shard-recipes/index.js.map +0 -1
- package/out/src/shard-recipes/intersection.d.ts +0 -42
- package/out/src/shard-recipes/intersection.d.ts.map +0 -1
- package/out/src/shard-recipes/intersection.js +0 -460
- package/out/src/shard-recipes/intersection.js.map +0 -1
- package/out/src/shard-recipes/locale.d.ts +0 -135
- package/out/src/shard-recipes/locale.d.ts.map +0 -1
- package/out/src/shard-recipes/locale.js +0 -459
- package/out/src/shard-recipes/locale.js.map +0 -1
- package/out/src/shard-recipes/nl-postcode.d.ts +0 -26
- package/out/src/shard-recipes/nl-postcode.d.ts.map +0 -1
- package/out/src/shard-recipes/nl-postcode.js +0 -102
- package/out/src/shard-recipes/nl-postcode.js.map +0 -1
- package/out/src/shard-recipes/no-fragment.d.ts +0 -43
- package/out/src/shard-recipes/no-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/no-fragment.js +0 -188
- package/out/src/shard-recipes/no-fragment.js.map +0 -1
- package/out/src/shard-recipes/no-street-led.d.ts +0 -24
- package/out/src/shard-recipes/no-street-led.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street-led.js +0 -121
- package/out/src/shard-recipes/no-street-led.js.map +0 -1
- package/out/src/shard-recipes/no-street.d.ts +0 -18
- package/out/src/shard-recipes/no-street.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street.js +0 -72
- package/out/src/shard-recipes/no-street.js.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.d.ts +0 -38
- package/out/src/shard-recipes/po-box-cedex.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.js +0 -726
- package/out/src/shard-recipes/po-box-cedex.js.map +0 -1
- package/out/src/shard-recipes/po-box.d.ts +0 -17
- package/out/src/shard-recipes/po-box.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box.js +0 -101
- package/out/src/shard-recipes/po-box.js.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts +0 -47
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.js +0 -125
- package/out/src/shard-recipes/reviewed-postcode-tail.js.map +0 -1
- package/out/src/shard-recipes/scaffold.d.ts +0 -246
- package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
- package/out/src/shard-recipes/scaffold.js +0 -137
- package/out/src/shard-recipes/scaffold.js.map +0 -1
- package/out/src/shard-recipes/si-bare-village.d.ts +0 -32
- package/out/src/shard-recipes/si-bare-village.d.ts.map +0 -1
- package/out/src/shard-recipes/si-bare-village.js +0 -88
- package/out/src/shard-recipes/si-bare-village.js.map +0 -1
- package/out/src/shard-recipes/street-affix.d.ts +0 -89
- package/out/src/shard-recipes/street-affix.d.ts.map +0 -1
- package/out/src/shard-recipes/street-affix.js +0 -578
- package/out/src/shard-recipes/street-affix.js.map +0 -1
- package/out/src/shard-recipes/street-bare.d.ts +0 -25
- package/out/src/shard-recipes/street-bare.d.ts.map +0 -1
- package/out/src/shard-recipes/street-bare.js +0 -86
- package/out/src/shard-recipes/street-bare.js.map +0 -1
- package/out/src/shard-recipes/street.d.ts +0 -15
- package/out/src/shard-recipes/street.d.ts.map +0 -1
- package/out/src/shard-recipes/street.js +0 -69
- package/out/src/shard-recipes/street.js.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.d.ts +0 -228
- package/out/src/shard-recipes/sub-venue-sources.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.js +0 -664
- package/out/src/shard-recipes/sub-venue-sources.js.map +0 -1
- package/out/src/shard-recipes/sub-venue.d.ts +0 -269
- package/out/src/shard-recipes/sub-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue.js +0 -710
- package/out/src/shard-recipes/sub-venue.js.map +0 -1
- package/out/src/shard-recipes/trailing-region.d.ts +0 -74
- package/out/src/shard-recipes/trailing-region.d.ts.map +0 -1
- package/out/src/shard-recipes/trailing-region.js +0 -157
- package/out/src/shard-recipes/trailing-region.js.map +0 -1
- package/out/src/shard-recipes/unit.d.ts +0 -29
- package/out/src/shard-recipes/unit.d.ts.map +0 -1
- package/out/src/shard-recipes/unit.js +0 -243
- package/out/src/shard-recipes/unit.js.map +0 -1
- package/out/src/synthesizers/anchor-absorption.d.ts +0 -63
- package/out/src/synthesizers/anchor-absorption.d.ts.map +0 -1
- package/out/src/synthesizers/anchor-absorption.js +0 -223
- package/out/src/synthesizers/anchor-absorption.js.map +0 -1
- package/out/src/synthesizers/boundary-stress.d.ts +0 -78
- package/out/src/synthesizers/boundary-stress.d.ts.map +0 -1
- package/out/src/synthesizers/boundary-stress.js +0 -455
- package/out/src/synthesizers/boundary-stress.js.map +0 -1
- package/out/src/synthesizers/german.d.ts +0 -107
- package/out/src/synthesizers/german.d.ts.map +0 -1
- package/out/src/synthesizers/german.js +0 -148
- package/out/src/synthesizers/german.js.map +0 -1
- package/out/src/synthesizers/house-venue.d.ts +0 -56
- package/out/src/synthesizers/house-venue.d.ts.map +0 -1
- package/out/src/synthesizers/house-venue.js +0 -267
- package/out/src/synthesizers/house-venue.js.map +0 -1
- package/out/src/synthesizers/intersection.d.ts +0 -52
- package/out/src/synthesizers/intersection.d.ts.map +0 -1
- package/out/src/synthesizers/intersection.js +0 -175
- package/out/src/synthesizers/intersection.js.map +0 -1
- package/out/src/synthesizers/no-street.d.ts +0 -72
- package/out/src/synthesizers/no-street.d.ts.map +0 -1
- package/out/src/synthesizers/no-street.js +0 -282
- package/out/src/synthesizers/no-street.js.map +0 -1
- package/out/src/synthesizers/po-box.d.ts +0 -104
- package/out/src/synthesizers/po-box.d.ts.map +0 -1
- package/out/src/synthesizers/po-box.js +0 -266
- package/out/src/synthesizers/po-box.js.map +0 -1
- package/out/src/synthesizers/street.d.ts +0 -54
- package/out/src/synthesizers/street.d.ts.map +0 -1
- package/out/src/synthesizers/street.js +0 -221
- package/out/src/synthesizers/street.js.map +0 -1
- package/out/src/synthesizers/utils.d.ts +0 -203
- package/out/src/synthesizers/utils.d.ts.map +0 -1
- package/out/src/synthesizers/utils.js +0 -708
- package/out/src/synthesizers/utils.js.map +0 -1
- package/out/src/tools/align-shard.d.ts +0 -8
- package/out/src/tools/align-shard.d.ts.map +0 -1
- package/out/src/tools/align-shard.js +0 -56
- package/out/src/tools/align-shard.js.map +0 -1
- package/out/src/tools/audit.d.ts +0 -28
- package/out/src/tools/audit.d.ts.map +0 -1
- package/out/src/tools/audit.js +0 -285
- package/out/src/tools/audit.js.map +0 -1
- package/out/src/tools/corpus-stats.d.ts +0 -44
- package/out/src/tools/corpus-stats.d.ts.map +0 -1
- package/out/src/tools/corpus-stats.js +0 -138
- package/out/src/tools/corpus-stats.js.map +0 -1
- package/out/src/tools/fetch/ban.d.ts +0 -31
- package/out/src/tools/fetch/ban.d.ts.map +0 -1
- package/out/src/tools/fetch/ban.js +0 -239
- package/out/src/tools/fetch/ban.js.map +0 -1
- package/out/src/tools/fetch/download.d.ts +0 -78
- package/out/src/tools/fetch/download.d.ts.map +0 -1
- package/out/src/tools/fetch/download.js +0 -116
- package/out/src/tools/fetch/download.js.map +0 -1
- package/out/src/tools/fetch/geonames-dump.d.ts +0 -87
- package/out/src/tools/fetch/geonames-dump.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-dump.js +0 -178
- package/out/src/tools/fetch/geonames-dump.js.map +0 -1
- package/out/src/tools/fetch/geonames-postal.d.ts +0 -76
- package/out/src/tools/fetch/geonames-postal.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-postal.js +0 -125
- package/out/src/tools/fetch/geonames-postal.js.map +0 -1
- package/out/src/tools/fetch/hrsa.d.ts +0 -18
- package/out/src/tools/fetch/hrsa.d.ts.map +0 -1
- package/out/src/tools/fetch/hrsa.js +0 -46
- package/out/src/tools/fetch/hrsa.js.map +0 -1
- package/out/src/tools/fetch/imls-pls.d.ts +0 -25
- package/out/src/tools/fetch/imls-pls.d.ts.map +0 -1
- package/out/src/tools/fetch/imls-pls.js +0 -108
- package/out/src/tools/fetch/imls-pls.js.map +0 -1
- package/out/src/tools/fetch/index.d.ts +0 -144
- package/out/src/tools/fetch/index.d.ts.map +0 -1
- package/out/src/tools/fetch/index.js +0 -143
- package/out/src/tools/fetch/index.js.map +0 -1
- package/out/src/tools/fetch/nad.d.ts +0 -70
- package/out/src/tools/fetch/nad.d.ts.map +0 -1
- package/out/src/tools/fetch/nad.js +0 -234
- package/out/src/tools/fetch/nad.js.map +0 -1
- package/out/src/tools/fetch/nppes.d.ts +0 -26
- package/out/src/tools/fetch/nppes.d.ts.map +0 -1
- package/out/src/tools/fetch/nppes.js +0 -126
- package/out/src/tools/fetch/nppes.js.map +0 -1
- package/out/src/tools/fetch/openaddresses.d.ts +0 -61
- package/out/src/tools/fetch/openaddresses.d.ts.map +0 -1
- package/out/src/tools/fetch/openaddresses.js +0 -317
- package/out/src/tools/fetch/openaddresses.js.map +0 -1
- package/out/src/tools/fetch/ourairports.d.ts +0 -45
- package/out/src/tools/fetch/ourairports.d.ts.map +0 -1
- package/out/src/tools/fetch/ourairports.js +0 -128
- package/out/src/tools/fetch/ourairports.js.map +0 -1
- package/out/src/tools/fetch/ppd.d.ts.map +0 -1
- package/out/src/tools/fetch/ppd.js +0 -100
- package/out/src/tools/fetch/ppd.js.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.d.ts +0 -25
- package/out/src/tools/fetch/state-hi-schools.d.ts.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.js +0 -162
- package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
- package/out/src/tools/fetch/state-sources.d.ts +0 -26
- package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
- package/out/src/tools/fetch/state-sources.js +0 -111
- package/out/src/tools/fetch/state-sources.js.map +0 -1
- package/out/src/tools/fetch/tiger-full.d.ts +0 -42
- package/out/src/tools/fetch/tiger-full.d.ts.map +0 -1
- package/out/src/tools/fetch/tiger-full.js +0 -248
- package/out/src/tools/fetch/tiger-full.js.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.d.ts +0 -171
- package/out/src/tools/fetch/wikidata-subvenue.d.ts.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.js +0 -275
- package/out/src/tools/fetch/wikidata-subvenue.js.map +0 -1
- package/out/src/tools/gb-title-case.d.ts.map +0 -1
- package/out/src/tools/gb-title-case.js.map +0 -1
- package/out/src/tools/golden-expand.d.ts +0 -90
- package/out/src/tools/golden-expand.d.ts.map +0 -1
- package/out/src/tools/golden-expand.js +0 -413
- package/out/src/tools/golden-expand.js.map +0 -1
- package/out/src/tools/golden-promote.d.ts.map +0 -1
- package/out/src/tools/golden-promote.js +0 -244
- package/out/src/tools/golden-promote.js.map +0 -1
- package/out/src/tools/golden-relabel-street.d.ts +0 -196
- package/out/src/tools/golden-relabel-street.d.ts.map +0 -1
- package/out/src/tools/golden-relabel-street.js +0 -440
- package/out/src/tools/golden-relabel-street.js.map +0 -1
- package/out/src/tools/index.d.ts +0 -28
- package/out/src/tools/index.d.ts.map +0 -1
- package/out/src/tools/index.js +0 -28
- package/out/src/tools/index.js.map +0 -1
- package/out/src/tools/ingest-csv.d.ts.map +0 -1
- package/out/src/tools/ingest-csv.js +0 -296
- package/out/src/tools/ingest-csv.js.map +0 -1
- package/out/src/tools/jsonl-to-parquet.d.ts +0 -61
- package/out/src/tools/jsonl-to-parquet.d.ts.map +0 -1
- package/out/src/tools/jsonl-to-parquet.js +0 -164
- package/out/src/tools/jsonl-to-parquet.js.map +0 -1
- package/out/src/tools/lint-shard-vocab.d.ts +0 -90
- package/out/src/tools/lint-shard-vocab.d.ts.map +0 -1
- package/out/src/tools/lint-shard-vocab.js +0 -281
- package/out/src/tools/lint-shard-vocab.js.map +0 -1
- package/out/src/tools/lint-shard.d.ts +0 -93
- package/out/src/tools/lint-shard.d.ts.map +0 -1
- package/out/src/tools/lint-shard.js +0 -354
- package/out/src/tools/lint-shard.js.map +0 -1
- package/out/src/tools/overlay-manifest.d.ts +0 -39
- package/out/src/tools/overlay-manifest.d.ts.map +0 -1
- package/out/src/tools/overlay-manifest.js +0 -98
- package/out/src/tools/overlay-manifest.js.map +0 -1
- package/out/src/tools/overture-subvenue.d.ts +0 -112
- package/out/src/tools/overture-subvenue.d.ts.map +0 -1
- package/out/src/tools/overture-subvenue.js +0 -144
- package/out/src/tools/overture-subvenue.js.map +0 -1
- package/out/src/tools/postcode-triples.d.ts +0 -175
- package/out/src/tools/postcode-triples.d.ts.map +0 -1
- package/out/src/tools/postcode-triples.js +0 -304
- package/out/src/tools/postcode-triples.js.map +0 -1
- package/out/src/tools/shard-kryptonite.d.ts +0 -32
- package/out/src/tools/shard-kryptonite.d.ts.map +0 -1
- package/out/src/tools/shard-kryptonite.js +0 -100
- package/out/src/tools/shard-kryptonite.js.map +0 -1
- package/out/src/tools/shard-translit.d.ts +0 -51
- package/out/src/tools/shard-translit.d.ts.map +0 -1
- package/out/src/tools/shard-translit.js +0 -175
- package/out/src/tools/shard-translit.js.map +0 -1
- package/out/src/tools/sub-venue/harvest.d.ts +0 -100
- package/out/src/tools/sub-venue/harvest.d.ts.map +0 -1
- package/out/src/tools/sub-venue/harvest.js +0 -168
- package/out/src/tools/sub-venue/harvest.js.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.d.ts +0 -50
- package/out/src/tools/sub-venue/head-nouns.d.ts.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.js +0 -210
- package/out/src/tools/sub-venue/head-nouns.js.map +0 -1
- package/out/src/tools/sub-venue/surfaces.d.ts +0 -45
- package/out/src/tools/sub-venue/surfaces.d.ts.map +0 -1
- package/out/src/tools/sub-venue/surfaces.js +0 -77
- package/out/src/tools/sub-venue/surfaces.js.map +0 -1
- package/out/src/tools/sub-venue/table.d.ts +0 -229
- package/out/src/tools/sub-venue/table.d.ts.map +0 -1
- package/out/src/tools/sub-venue/table.js +0 -108
- package/out/src/tools/sub-venue/table.js.map +0 -1
- package/out/src/tools/sub-venue/wikidata.d.ts +0 -26
- package/out/src/tools/sub-venue/wikidata.d.ts.map +0 -1
- package/out/src/tools/sub-venue/wikidata.js +0 -62
- package/out/src/tools/sub-venue/wikidata.js.map +0 -1
- package/out/src/tools/sub-venue-lexicon.d.ts +0 -156
- package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
- package/out/src/tools/sub-venue-lexicon.js +0 -282
- package/out/src/tools/sub-venue-lexicon.js.map +0 -1
- package/out/src/tools/sub-venue-promotions.d.ts +0 -94
- package/out/src/tools/sub-venue-promotions.d.ts.map +0 -1
- package/out/src/tools/sub-venue-promotions.js +0 -266
- package/out/src/tools/sub-venue-promotions.js.map +0 -1
- package/out/src/types.d.ts +0 -221
- package/out/src/types.d.ts.map +0 -1
- package/out/src/types.js.map +0 -1
- package/out/src/utils/align.d.ts +0 -93
- package/out/src/utils/align.d.ts.map +0 -1
- package/out/src/utils/align.js +0 -234
- package/out/src/utils/align.js.map +0 -1
- package/out/src/utils/golden.d.ts +0 -69
- package/out/src/utils/golden.d.ts.map +0 -1
- package/out/src/utils/golden.js +0 -127
- package/out/src/utils/golden.js.map +0 -1
- package/out/src/utils/index.d.ts +0 -14
- package/out/src/utils/index.d.ts.map +0 -1
- package/out/src/utils/index.js +0 -14
- package/out/src/utils/index.js.map +0 -1
- package/out/src/utils/license.d.ts.map +0 -1
- package/out/src/utils/license.js.map +0 -1
- package/out/src/utils/parquet.d.ts +0 -162
- package/out/src/utils/parquet.d.ts.map +0 -1
- package/out/src/utils/parquet.js +0 -262
- package/out/src/utils/parquet.js.map +0 -1
- package/out/src/utils/split.d.ts +0 -127
- package/out/src/utils/split.d.ts.map +0 -1
- package/out/src/utils/split.js +0 -204
- package/out/src/utils/split.js.map +0 -1
- package/out/src/utils/tokenize.d.ts +0 -56
- package/out/src/utils/tokenize.d.ts.map +0 -1
- package/out/src/utils/tokenize.js +0 -48
- package/out/src/utils/tokenize.js.map +0 -1
- package/out/src/utils/wof-json.d.ts +0 -109
- package/out/src/utils/wof-json.d.ts.map +0 -1
- package/out/src/utils/wof-json.js +0 -173
- package/out/src/utils/wof-json.js.map +0 -1
- package/src/adapters/ban/adapter.ts +0 -191
- package/src/adapters/ban/street-decompose.ts +0 -96
- package/src/adapters/fcc-bdc/adapter.ts +0 -174
- package/src/adapters/geonames/adapter.ts +0 -200
- package/src/adapters/geonames-postal/adapter.ts +0 -119
- package/src/adapters/gnaf/adapter.ts +0 -149
- package/src/adapters/gnaf/assemble.ts +0 -226
- package/src/adapters/index.ts +0 -149
- package/src/adapters/openaddresses/adapter.ts +0 -251
- package/src/adapters/overture/adapter.ts +0 -162
- package/src/adapters/state-hi-schools/adapter.ts +0 -164
- package/src/adapters/synth-po-box/adapter.ts +0 -204
- package/src/adapters/tiger/adapter.ts +0 -253
- package/src/adapters/tiger/street-decompose.ts +0 -111
- package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -183
- package/src/adapters/usgov-imls-pls/adapter.ts +0 -143
- package/src/adapters/usgov-irs-bmf/adapter.ts +0 -163
- package/src/adapters/usgov-nad/adapter.ts +0 -348
- package/src/adapters/usgov-nppes/adapter.ts +0 -159
- package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -204
- package/src/adapters/utils/index.ts +0 -233
- package/src/adapters/wof-admin-jp/adapter.ts +0 -216
- package/src/adapters/wof-admin-json/adapter.ts +0 -256
- package/src/adapters/wof-json-rows.ts +0 -79
- package/src/adapters/wof-postalcode-json/adapter.ts +0 -183
- package/src/build.ts +0 -386
- package/src/index.ts +0 -14
- package/src/name-prone-us-suffixes.ts +0 -12
- package/src/parquet-wrapper/index.ts +0 -9
- package/src/parquet-wrapper/reader.ts +0 -97
- package/src/parquet-wrapper/schema.ts +0 -88
- package/src/parquet-wrapper/writer.ts +0 -110
- package/src/runner.ts +0 -317
- package/src/shard-recipes/anchor-absorption.ts +0 -103
- package/src/shard-recipes/bare-country.ts +0 -95
- package/src/shard-recipes/boundary-stress.ts +0 -101
- package/src/shard-recipes/country-balanced.ts +0 -524
- package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -111
- package/src/shard-recipes/fr-admin-split.ts +0 -239
- package/src/shard-recipes/fr-bare-street.ts +0 -170
- package/src/shard-recipes/fr-fragment.ts +0 -332
- package/src/shard-recipes/fr-lieudit.ts +0 -302
- package/src/shard-recipes/fr-order.ts +0 -258
- package/src/shard-recipes/german.ts +0 -170
- package/src/shard-recipes/house-venue.ts +0 -88
- package/src/shard-recipes/index.ts +0 -95
- package/src/shard-recipes/intersection.ts +0 -630
- package/src/shard-recipes/locale.ts +0 -599
- package/src/shard-recipes/nl-postcode.ts +0 -115
- package/src/shard-recipes/no-fragment.ts +0 -219
- package/src/shard-recipes/no-street-led.ts +0 -143
- package/src/shard-recipes/no-street.ts +0 -86
- package/src/shard-recipes/po-box-cedex.ts +0 -920
- package/src/shard-recipes/po-box.ts +0 -119
- package/src/shard-recipes/reviewed-postcode-tail.ts +0 -189
- package/src/shard-recipes/scaffold.ts +0 -360
- package/src/shard-recipes/si-bare-village.ts +0 -97
- package/src/shard-recipes/street-affix.ts +0 -826
- package/src/shard-recipes/street-bare.ts +0 -101
- package/src/shard-recipes/street.ts +0 -82
- package/src/shard-recipes/sub-venue-sources.ts +0 -885
- package/src/shard-recipes/sub-venue.ts +0 -984
- package/src/shard-recipes/trailing-region.ts +0 -183
- package/src/shard-recipes/unit.ts +0 -321
- package/src/synthesizers/anchor-absorption.ts +0 -290
- package/src/synthesizers/boundary-stress.ts +0 -531
- package/src/synthesizers/german.ts +0 -251
- package/src/synthesizers/house-venue.ts +0 -330
- package/src/synthesizers/intersection.ts +0 -232
- package/src/synthesizers/no-street.ts +0 -349
- package/src/synthesizers/po-box.ts +0 -339
- package/src/synthesizers/street.ts +0 -274
- package/src/synthesizers/utils.ts +0 -903
- package/src/tools/align-shard.ts +0 -70
- package/src/tools/audit.ts +0 -399
- package/src/tools/corpus-stats.ts +0 -184
- package/src/tools/fetch/ban.ts +0 -290
- package/src/tools/fetch/download.ts +0 -176
- package/src/tools/fetch/geonames-dump.ts +0 -267
- package/src/tools/fetch/geonames-postal.ts +0 -180
- package/src/tools/fetch/hrsa.ts +0 -68
- package/src/tools/fetch/imls-pls.ts +0 -158
- package/src/tools/fetch/index.ts +0 -147
- package/src/tools/fetch/nad.ts +0 -342
- package/src/tools/fetch/nppes.ts +0 -174
- package/src/tools/fetch/openaddresses.ts +0 -404
- package/src/tools/fetch/ourairports.ts +0 -171
- package/src/tools/fetch/ppd.ts +0 -137
- package/src/tools/fetch/state-hi-schools.ts +0 -208
- package/src/tools/fetch/state-sources.ts +0 -155
- package/src/tools/fetch/tiger-full.ts +0 -354
- package/src/tools/fetch/wikidata-subvenue.ts +0 -386
- package/src/tools/golden-expand.ts +0 -584
- package/src/tools/golden-promote.ts +0 -353
- package/src/tools/golden-relabel-street.ts +0 -685
- package/src/tools/index.ts +0 -28
- package/src/tools/ingest-csv.ts +0 -422
- package/src/tools/jsonl-to-parquet.ts +0 -221
- package/src/tools/lint-shard-vocab.ts +0 -409
- package/src/tools/lint-shard.ts +0 -543
- package/src/tools/overlay-manifest.ts +0 -157
- package/src/tools/overture-subvenue.ts +0 -215
- package/src/tools/postcode-triples.ts +0 -375
- package/src/tools/shard-kryptonite.ts +0 -139
- package/src/tools/shard-translit.ts +0 -245
- package/src/tools/sub-venue/harvest.ts +0 -235
- package/src/tools/sub-venue/head-nouns.ts +0 -242
- package/src/tools/sub-venue/surfaces.ts +0 -95
- package/src/tools/sub-venue/table.ts +0 -281
- package/src/tools/sub-venue/wikidata.ts +0 -85
- package/src/tools/sub-venue-lexicon.ts +0 -431
- package/src/tools/sub-venue-promotions.ts +0 -330
- package/src/types.ts +0 -247
- package/src/utils/align.ts +0 -331
- package/src/utils/golden.ts +0 -176
- package/src/utils/index.ts +0 -14
- package/src/utils/parquet.ts +0 -391
- package/src/utils/split.ts +0 -279
- package/src/utils/tokenize.ts +0 -78
- package/src/utils/wof-json.ts +0 -244
- /package/{src → lib}/adapters/state-ia-contractors/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-ny-notaries/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-tx-notaries/adapter.ts +0 -0
- /package/{src → lib}/codex/us-fips-state.ts +0 -0
- /package/{src → lib}/tools/gb-title-case.ts +0 -0
- /package/{src → lib}/utils/license.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/fcc-bdc/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/geonames/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/openaddresses/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/synth-po-box/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/tiger/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-nppes/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-samhsa-treatment-locator/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/wof-admin-jp/adapter.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.js +0 -0
- /package/out/{src/tools → tools}/fetch/ppd.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.js +0 -0
- /package/out/{src/tools → tools}/golden-promote.d.ts +0 -0
- /package/out/{src/tools → tools}/ingest-csv.d.ts +0 -0
- /package/out/{src/types.js → types.js} +0 -0
- /package/out/{src/utils → utils}/license.d.ts +0 -0
- /package/out/{src/utils → utils}/license.js +0 -0
|
@@ -0,0 +1,154 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* `usgov-samhsa-treatment-locator`: SAMHSA Behavioral Health Treatment Services Locator CSV
|
|
7
|
+
* consumer.
|
|
8
|
+
*
|
|
9
|
+
* SAMHSA's Treatment Locator (`findtreatment.gov`) is the federal directory of substance-use and
|
|
10
|
+
* mental-health treatment facilities. The published CSV carries the facility name, an optional
|
|
11
|
+
* secondary name (typically the organizational parent), and the postal address quad split into
|
|
12
|
+
* primary + secondary street lines. Phase 1.6 §1.2 (#22) selects this source for the same reason
|
|
13
|
+
* it selects HRSA: facility names are hand-typed venue strings and the addresses pass through
|
|
14
|
+
* enough human + system hands to accumulate the suite-designator + sub-tenant chaos ("Suite C,
|
|
15
|
+
* behind main building") that pure gazetteer data does not.
|
|
16
|
+
*
|
|
17
|
+
* SAMHSA's two-line address shape is the key adapter-specific concern. `street1` typically carries
|
|
18
|
+
* the canonical postal address (`"123 Main St"`); `street2` carries the suite / unit / "second
|
|
19
|
+
* floor" surface form. The adapter joins them with `", "` into a single `street` component (Phase
|
|
20
|
+
* 1 keeps `unit` as a deferred slot since the OpenCage template doesn't have a clean rendering
|
|
21
|
+
* for it). Operators wanting a different join policy can subclass the factory.
|
|
22
|
+
*
|
|
23
|
+
* Column names below match the canonical SAMHSA Behavioral Health Treatment Services Locator CSV
|
|
24
|
+
* export header. Operators substituting a closely-related extract should rename columns to match;
|
|
25
|
+
* the README has the mapping cheatsheet.
|
|
26
|
+
*
|
|
27
|
+
* License: stamped `"Public Domain"` per the SAMHSA Open Data Foundry's federal-government
|
|
28
|
+
* distribution terms.
|
|
29
|
+
*/
|
|
30
|
+
import { reconcileComponents } from "@mailwoman/formatter";
|
|
31
|
+
import { CSVSpliterator } from "spliterator";
|
|
32
|
+
import { composeRaw, splitStreetLine, stableSourceID } from "#adapters/utils";
|
|
33
|
+
import { lookupStateAbbreviation } from "#codex/us-fips-state";
|
|
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 USGOV_SAMHSA_ADAPTER_ID = "usgov-samhsa-treatment-locator";
|
|
39
|
+
/**
|
|
40
|
+
* License carried by this source (Public Domain), attached to each row so downstream consumers inherit the terms rather
|
|
41
|
+
* than having to look them up.
|
|
42
|
+
*/
|
|
43
|
+
export const USGOV_SAMHSA_DEFAULT_LICENSE = "Public Domain";
|
|
44
|
+
/**
|
|
45
|
+
* Join the SAMHSA two-line street: primary street + optional secondary line (suite / unit / floor / "behind main
|
|
46
|
+
* building") on `", "`. The combined value is the `street` component surface form. Phase 1 does not break this out into
|
|
47
|
+
* the `unit` component — see the file-level comment.
|
|
48
|
+
*/
|
|
49
|
+
function joinTwoLineStreet(street1, street2) {
|
|
50
|
+
const s1 = street1.trim();
|
|
51
|
+
const s2 = (street2 ?? "").trim();
|
|
52
|
+
if (!s1 && !s2)
|
|
53
|
+
return "";
|
|
54
|
+
if (!s2)
|
|
55
|
+
return s1;
|
|
56
|
+
if (!s1)
|
|
57
|
+
return s2;
|
|
58
|
+
return `${s1}, ${s2}`;
|
|
59
|
+
}
|
|
60
|
+
/**
|
|
61
|
+
* Combine `name1` + optional `name2` into a single venue surface form. SAMHSA conventions:
|
|
62
|
+
*
|
|
63
|
+
* - `name1` is the program / clinic name ("Mountain Plains Counseling Services").
|
|
64
|
+
* - `name2` is the parent organization ("Catholic Charities of Wyoming"), if any.
|
|
65
|
+
*
|
|
66
|
+
* Both render together as `"<name1> - <name2>"` when both are present — geocoder users typically type either form, so
|
|
67
|
+
* the model benefits from the joined surface.
|
|
68
|
+
*/
|
|
69
|
+
function composeVenue(name1, name2) {
|
|
70
|
+
const n1 = name1.trim();
|
|
71
|
+
const n2 = (name2 ?? "").trim();
|
|
72
|
+
if (!n1 && !n2)
|
|
73
|
+
return "";
|
|
74
|
+
if (!n2)
|
|
75
|
+
return n1;
|
|
76
|
+
if (!n1)
|
|
77
|
+
return n2;
|
|
78
|
+
return `${n1} - ${n2}`;
|
|
79
|
+
}
|
|
80
|
+
export function createUsgovSamhsaTreatmentLocatorAdapter() {
|
|
81
|
+
return {
|
|
82
|
+
id: USGOV_SAMHSA_ADAPTER_ID,
|
|
83
|
+
defaultLicense: USGOV_SAMHSA_DEFAULT_LICENSE,
|
|
84
|
+
description: "SAMHSA Behavioral Health Treatment Services Locator (public-domain). Adversarial source: venue + two-line address co-occurrence, hand-entered.",
|
|
85
|
+
async *rows(opts) {
|
|
86
|
+
if (opts.country && opts.country !== "US") {
|
|
87
|
+
throw new Error(`usgov-samhsa adapter: only US supported, got country=${opts.country}`);
|
|
88
|
+
}
|
|
89
|
+
const rows = CSVSpliterator.fromAsync(opts.inputPath, {
|
|
90
|
+
mode: "object",
|
|
91
|
+
normalizeKeys: false,
|
|
92
|
+
enableQuoteHandling: true,
|
|
93
|
+
});
|
|
94
|
+
let emitted = 0;
|
|
95
|
+
for await (const record of rows) {
|
|
96
|
+
if (opts.signal?.aborted)
|
|
97
|
+
break;
|
|
98
|
+
if (opts.limit !== undefined && emitted >= opts.limit)
|
|
99
|
+
break;
|
|
100
|
+
const venue = composeVenue(record.name1 ?? "", record.name2);
|
|
101
|
+
const street = joinTwoLineStreet(record.street1 ?? "", record.street2);
|
|
102
|
+
const split = splitStreetLine(street);
|
|
103
|
+
const city = (record.city ?? "").trim();
|
|
104
|
+
const stateAbbr = (record.state ?? "").trim();
|
|
105
|
+
const postcode = (record.zip ?? "").trim();
|
|
106
|
+
if (!venue || !split || !city || !postcode)
|
|
107
|
+
continue;
|
|
108
|
+
const state = lookupStateAbbreviation(stateAbbr);
|
|
109
|
+
if (!state)
|
|
110
|
+
continue;
|
|
111
|
+
// venue first — same kryptonite-defending insertion order as HRSA.
|
|
112
|
+
const components = {
|
|
113
|
+
venue,
|
|
114
|
+
...(split.house_number ? { house_number: split.house_number } : {}),
|
|
115
|
+
street: split.street,
|
|
116
|
+
locality: city,
|
|
117
|
+
region: state.abbreviation,
|
|
118
|
+
postcode,
|
|
119
|
+
};
|
|
120
|
+
const raw = composeRaw({
|
|
121
|
+
venue,
|
|
122
|
+
houseNumber: split.house_number,
|
|
123
|
+
street: split.street,
|
|
124
|
+
locality: city,
|
|
125
|
+
region: state.abbreviation,
|
|
126
|
+
postcode,
|
|
127
|
+
});
|
|
128
|
+
if (!raw)
|
|
129
|
+
continue;
|
|
130
|
+
const aligned = reconcileComponents(components, raw);
|
|
131
|
+
if (!Object.keys(aligned).length)
|
|
132
|
+
continue;
|
|
133
|
+
const frID = (record.frid ?? "").trim();
|
|
134
|
+
const sourceID = frID ? `${USGOV_SAMHSA_ADAPTER_ID}-${frID}` : stableSourceID(USGOV_SAMHSA_ADAPTER_ID, aligned);
|
|
135
|
+
yield {
|
|
136
|
+
raw,
|
|
137
|
+
components: aligned,
|
|
138
|
+
country: "US",
|
|
139
|
+
locale: "en-US",
|
|
140
|
+
source: USGOV_SAMHSA_ADAPTER_ID,
|
|
141
|
+
source_id: sourceID,
|
|
142
|
+
corpus_version: "",
|
|
143
|
+
license: USGOV_SAMHSA_DEFAULT_LICENSE,
|
|
144
|
+
};
|
|
145
|
+
emitted++;
|
|
146
|
+
}
|
|
147
|
+
},
|
|
148
|
+
};
|
|
149
|
+
}
|
|
150
|
+
/**
|
|
151
|
+
* The configured adapter instance registered with the corpus builder.
|
|
152
|
+
*/
|
|
153
|
+
export const usgovSamhsaTreatmentLocatorAdapter = createUsgovSamhsaTreatmentLocatorAdapter();
|
|
154
|
+
//# sourceMappingURL=adapter.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../lib/adapters/usgov-samhsa-treatment-locator/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AAEH,OAAO,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AAC1D,OAAO,EAAE,cAAc,EAAE,MAAM,aAAa,CAAA;AAE5C,OAAO,EAAE,UAAU,EAAE,eAAe,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAA;AAC7E,OAAO,EAAE,uBAAuB,EAAE,MAAM,sBAAsB,CAAA;AAG9D;;;GAGG;AACH,MAAM,CAAC,MAAM,uBAAuB,GAAG,gCAAgC,CAAA;AACvE;;;GAGG;AACH,MAAM,CAAC,MAAM,4BAA4B,GAAG,eAAe,CAAA;AAoB3D;;;;GAIG;AACH,SAAS,iBAAiB,CAAC,OAAe,EAAE,OAA2B;IACtE,MAAM,EAAE,GAAG,OAAO,CAAC,IAAI,EAAE,CAAA;IACzB,MAAM,EAAE,GAAG,CAAC,OAAO,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;IAEjC,IAAI,CAAC,EAAE,IAAI,CAAC,EAAE;QAAE,OAAO,EAAE,CAAA;IAEzB,IAAI,CAAC,EAAE;QAAE,OAAO,EAAE,CAAA;IAElB,IAAI,CAAC,EAAE;QAAE,OAAO,EAAE,CAAA;IAElB,OAAO,GAAG,EAAE,KAAK,EAAE,EAAE,CAAA;AACtB,CAAC;AAED;;;;;;;;GAQG;AACH,SAAS,YAAY,CAAC,KAAa,EAAE,KAAyB;IAC7D,MAAM,EAAE,GAAG,KAAK,CAAC,IAAI,EAAE,CAAA;IACvB,MAAM,EAAE,GAAG,CAAC,KAAK,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;IAE/B,IAAI,CAAC,EAAE,IAAI,CAAC,EAAE;QAAE,OAAO,EAAE,CAAA;IAEzB,IAAI,CAAC,EAAE;QAAE,OAAO,EAAE,CAAA;IAElB,IAAI,CAAC,EAAE;QAAE,OAAO,EAAE,CAAA;IAElB,OAAO,GAAG,EAAE,MAAM,EAAE,EAAE,CAAA;AACvB,CAAC;AAED,MAAM,UAAU,wCAAwC;IACvD,OAAO;QACN,EAAE,EAAE,uBAAuB;QAC3B,cAAc,EAAE,4BAA4B;QAC5C,WAAW,EACV,gJAAgJ;QAEjJ,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,IAAI,IAAI,CAAC,OAAO,IAAI,IAAI,CAAC,OAAO,KAAK,IAAI,EAAE,CAAC;gBAC3C,MAAM,IAAI,KAAK,CAAC,wDAAwD,IAAI,CAAC,OAAO,EAAE,CAAC,CAAA;YACxF,CAAC;YAED,MAAM,IAAI,GAAG,cAAc,CAAC,SAAS,CAAC,IAAI,CAAC,SAAS,EAAE;gBACrD,IAAI,EAAE,QAAQ;gBACd,aAAa,EAAE,KAAK;gBACpB,mBAAmB,EAAE,IAAI;aACzB,CAAC,CAAA;YAEF,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,KAAK,EAAE,MAAM,MAAM,IAAI,IAAoC,EAAE,CAAC;gBACjE,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,KAAK,GAAG,YAAY,CAAC,MAAM,CAAC,KAAK,IAAI,EAAE,EAAE,MAAM,CAAC,KAAK,CAAC,CAAA;gBAC5D,MAAM,MAAM,GAAG,iBAAiB,CAAC,MAAM,CAAC,OAAO,IAAI,EAAE,EAAE,MAAM,CAAC,OAAO,CAAC,CAAA;gBACtE,MAAM,KAAK,GAAG,eAAe,CAAC,MAAM,CAAC,CAAA;gBACrC,MAAM,IAAI,GAAG,CAAC,MAAM,CAAC,IAAI,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBACvC,MAAM,SAAS,GAAG,CAAC,MAAM,CAAC,KAAK,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAC7C,MAAM,QAAQ,GAAG,CAAC,MAAM,CAAC,GAAG,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAE1C,IAAI,CAAC,KAAK,IAAI,CAAC,KAAK,IAAI,CAAC,IAAI,IAAI,CAAC,QAAQ;oBAAE,SAAQ;gBACpD,MAAM,KAAK,GAAG,uBAAuB,CAAC,SAAS,CAAC,CAAA;gBAEhD,IAAI,CAAC,KAAK;oBAAE,SAAQ;gBAEpB,mEAAmE;gBACnE,MAAM,UAAU,GAA+B;oBAC9C,KAAK;oBACL,GAAG,CAAC,KAAK,CAAC,YAAY,CAAC,CAAC,CAAC,EAAE,YAAY,EAAE,KAAK,CAAC,YAAY,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;oBACnE,MAAM,EAAE,KAAK,CAAC,MAAM;oBACpB,QAAQ,EAAE,IAAI;oBACd,MAAM,EAAE,KAAK,CAAC,YAAY;oBAC1B,QAAQ;iBACR,CAAA;gBAED,MAAM,GAAG,GAAG,UAAU,CAAC;oBACtB,KAAK;oBACL,WAAW,EAAE,KAAK,CAAC,YAAY;oBAC/B,MAAM,EAAE,KAAK,CAAC,MAAM;oBACpB,QAAQ,EAAE,IAAI;oBACd,MAAM,EAAE,KAAK,CAAC,YAAY;oBAC1B,QAAQ;iBACR,CAAC,CAAA;gBAEF,IAAI,CAAC,GAAG;oBAAE,SAAQ;gBAElB,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,IAAI,GAAG,CAAC,MAAM,CAAC,IAAI,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAEvC,MAAM,QAAQ,GAAG,IAAI,CAAC,CAAC,CAAC,GAAG,uBAAuB,IAAI,IAAI,EAAE,CAAC,CAAC,CAAC,cAAc,CAAC,uBAAuB,EAAE,OAAO,CAAC,CAAA;gBAE/G,MAAM;oBACL,GAAG;oBACH,UAAU,EAAE,OAAO;oBACnB,OAAO,EAAE,IAAI;oBACb,MAAM,EAAE,OAAO;oBACf,MAAM,EAAE,uBAAuB;oBAC/B,SAAS,EAAE,QAAQ;oBACnB,cAAc,EAAE,EAAE;oBAClB,OAAO,EAAE,4BAA4B;iBACrC,CAAA;gBAED,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,kCAAkC,GAAG,wCAAwC,EAAE,CAAA"}
|
|
@@ -0,0 +1,191 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Adapter framework helpers — the pieces every corpus adapter and the runner share.
|
|
7
|
+
*
|
|
8
|
+
* This file does **not** define `CorpusAdapter` (that lives in `./types.ts`, which is the single
|
|
9
|
+
* canonical schema module). It exposes:
|
|
10
|
+
*
|
|
11
|
+
* - `AdapterRegistry`: a tiny lookup table the CLI + build pipeline use to find adapters by id.
|
|
12
|
+
* - `InMemoryAdapterRegistry`: the default implementation.
|
|
13
|
+
* - `stableSourceID(adapterID, components)`: deterministic content-addressed id for adapters whose
|
|
14
|
+
* source data has no native primary key (CSV, GeoJSON).
|
|
15
|
+
* - `HOUSE_NUMBER_PREFIX` + `splitStreetLine(line)`: the one house-number/street split every
|
|
16
|
+
* US CSV adapter uses.
|
|
17
|
+
* - `composeRaw(parts)`: the envelope-style raw line every US CSV adapter renders.
|
|
18
|
+
* - `canonicalDedupKey(row)`: normalized signature used to drop near-identical rows during a run.
|
|
19
|
+
* Adapter-internal dedup; cross-adapter dedup is the runner's job.
|
|
20
|
+
* - `streamingSha256()`: thin wrapper around `node:crypto` so the runner can hash JSONL output as it
|
|
21
|
+
* streams (avoids re-reading the slice for the manifest checksum).
|
|
22
|
+
* - `loadLibpostalDictionary(language, filename)`: the curated libpostal dictionary reader the
|
|
23
|
+
* street-decompose modules share — the one read this module performs; everything else here is
|
|
24
|
+
* pure, and other side-effecting code goes in `./runner.ts`.
|
|
25
|
+
*/
|
|
26
|
+
import type { ComponentTag } from "@mailwoman/core/types";
|
|
27
|
+
import type { CanonicalRow, CorpusAdapter } from "#types";
|
|
28
|
+
/**
|
|
29
|
+
* Lookup table for corpus adapters.
|
|
30
|
+
*
|
|
31
|
+
* The CLI's `npx mailwoman corpus run <adapter-id>` resolves `<adapter-id>` against this registry; the same registry is
|
|
32
|
+
* iterated by the `corpus build` pipeline. Adapters do not self-register at module load — they're added explicitly so
|
|
33
|
+
* the dependency graph stays traceable.
|
|
34
|
+
*/
|
|
35
|
+
export interface AdapterRegistry {
|
|
36
|
+
/**
|
|
37
|
+
* Add an adapter. Throws if `adapter.id` is already registered.
|
|
38
|
+
*/
|
|
39
|
+
register(adapter: CorpusAdapter): void;
|
|
40
|
+
/**
|
|
41
|
+
* Return the adapter for `id`, or `undefined`.
|
|
42
|
+
*/
|
|
43
|
+
get(id: string): CorpusAdapter | undefined;
|
|
44
|
+
/**
|
|
45
|
+
* All registered adapters, in insertion order.
|
|
46
|
+
*/
|
|
47
|
+
list(): readonly CorpusAdapter[];
|
|
48
|
+
/**
|
|
49
|
+
* Convenience: ids only, in insertion order.
|
|
50
|
+
*/
|
|
51
|
+
ids(): readonly string[];
|
|
52
|
+
}
|
|
53
|
+
/**
|
|
54
|
+
* Default in-memory registry. The runner constructs one per invocation; the CLI re-uses a shared singleton
|
|
55
|
+
* (`defaultAdapterRegistry`) populated by `./adapters/index.ts` as adapters come online.
|
|
56
|
+
*/
|
|
57
|
+
export declare class InMemoryAdapterRegistry implements AdapterRegistry {
|
|
58
|
+
#private;
|
|
59
|
+
register(adapter: CorpusAdapter): void;
|
|
60
|
+
get(id: string): CorpusAdapter | undefined;
|
|
61
|
+
list(): readonly CorpusAdapter[];
|
|
62
|
+
ids(): readonly string[];
|
|
63
|
+
}
|
|
64
|
+
/**
|
|
65
|
+
* Process-wide default registry. Populated by `./adapters/index.ts` as adapters are built; imported by the CLI. Tests
|
|
66
|
+
* should construct their own `InMemoryAdapterRegistry` to avoid cross-test pollution.
|
|
67
|
+
*/
|
|
68
|
+
export declare const defaultAdapterRegistry: InMemoryAdapterRegistry;
|
|
69
|
+
/**
|
|
70
|
+
* Deterministic content-addressed source id.
|
|
71
|
+
*
|
|
72
|
+
* For adapters whose upstream source has no native primary key (CSV rows, GeoJSON features), the runner expects a
|
|
73
|
+
* stable id so dedup, holdout manifests, and resumability work across reruns. This helper produces one by hashing the
|
|
74
|
+
* adapter id and a canonical serialization of the components dict (keys sorted, values verbatim).
|
|
75
|
+
*
|
|
76
|
+
* Output format: `<adapterID>-<first-12-hex-chars-of-sha256>`. 48 bits of entropy is enough for ~17M rows per adapter
|
|
77
|
+
* before the expected collision count exceeds 1 (birthday paradox); adapters with more rows should extend the prefix
|
|
78
|
+
* length.
|
|
79
|
+
*/
|
|
80
|
+
export declare function stableSourceID(adapterID: string, components: Partial<Record<ComponentTag, string>>): string;
|
|
81
|
+
/**
|
|
82
|
+
* {@link stableSourceID} over arbitrary disambiguator keys — a variant index, a slot number, anything that is not a
|
|
83
|
+
* `ComponentTag`. Every key handed in is sorted and hashed either way; only the key vocabulary differs, and the narrow
|
|
84
|
+
* signature above is what stops an adapter hashing a misspelled component name.
|
|
85
|
+
*/
|
|
86
|
+
export declare function stableSourceIDFromParts(adapterID: string, parts: Readonly<Record<string, string | undefined>>): string;
|
|
87
|
+
/**
|
|
88
|
+
* Leading house number on a US-style street line: digits, an optional hyphenated range (Queens `40-12`), an optional
|
|
89
|
+
* single alpha suffix (`101A`), then whitespace, then the rest.
|
|
90
|
+
*
|
|
91
|
+
* This decides where the house number ends and the street begins for every US CSV adapter, so an edge case fixed here
|
|
92
|
+
* is fixed for all of them.
|
|
93
|
+
*
|
|
94
|
+
* The remainder must stay `(\S.*)` and must NOT become `(.+)`: `\s+` and `.` both match a tab, so `\s+(.+)$` lets the
|
|
95
|
+
* engine split a run of tabs between the two groups every possible way before failing — quadratic backtracking on
|
|
96
|
+
* attacker-shaped input. Requiring a non-space start removes the overlap. Group 2 is trimmed by the caller either way,
|
|
97
|
+
* so the two forms are indistinguishable on real input; only the failure cost differs.
|
|
98
|
+
*/
|
|
99
|
+
export declare const HOUSE_NUMBER_PREFIX: RegExp;
|
|
100
|
+
/**
|
|
101
|
+
* A street line split into its house number and the remainder.
|
|
102
|
+
*/
|
|
103
|
+
export interface SplitStreetLine {
|
|
104
|
+
house_number?: string;
|
|
105
|
+
street: string;
|
|
106
|
+
}
|
|
107
|
+
/**
|
|
108
|
+
* Split a US-style street line on {@link HOUSE_NUMBER_PREFIX}.
|
|
109
|
+
*
|
|
110
|
+
* The US CSV sources follow USPS Publication 28 conventions with hand-entry drift. The leading digit run is the house
|
|
111
|
+
* number (`"123 Main St"`, `"6450 W Indian School Rd"`), and the regex tolerates one trailing letter (`"123A Main St"`)
|
|
112
|
+
* plus an optional hyphenated half (`"40-12 Bell Blvd"`, common in NYC and suburban garden-apartment numbering; Hawaii
|
|
113
|
+
* uses it island-wide — `"47-470 Hui Aeko Place"`).
|
|
114
|
+
*
|
|
115
|
+
* Returns `null` for blank input. Anything that does not match the prefix shape (`"PO Box 1234"`, `"RR 2 Box 67"`, `"HC
|
|
116
|
+
* 1"`) becomes a single `street` value rather than being mangled — the model sees the original surface form and
|
|
117
|
+
* downstream classifiers pick it up. Callers that need those forms recognized as something other than a street (see
|
|
118
|
+
* `usgov-irs-bmf`) test for them BEFORE calling this.
|
|
119
|
+
*/
|
|
120
|
+
export declare function splitStreetLine(line: string): SplitStreetLine | null;
|
|
121
|
+
/**
|
|
122
|
+
* Parts of the envelope-style raw line {@link composeRaw} renders. Every field is dropped when empty, so a caller only
|
|
123
|
+
* supplies what its source carries.
|
|
124
|
+
*/
|
|
125
|
+
export interface ComposeRawParts {
|
|
126
|
+
venue?: string;
|
|
127
|
+
houseNumber?: string;
|
|
128
|
+
street?: string;
|
|
129
|
+
/**
|
|
130
|
+
* A street line already joined by the caller (e.g. a PO-box phrase) — used INSTEAD of `houseNumber`/`street`/`unit`
|
|
131
|
+
* when present.
|
|
132
|
+
*/
|
|
133
|
+
streetLine?: string;
|
|
134
|
+
unit?: string;
|
|
135
|
+
locality: string;
|
|
136
|
+
region?: string;
|
|
137
|
+
postcode: string;
|
|
138
|
+
}
|
|
139
|
+
/**
|
|
140
|
+
* Compose the envelope-style raw address line the US CSV adapters share:
|
|
141
|
+
*
|
|
142
|
+
* `"<venue>, <house> <street> <unit>, <city>, <state> <postcode>"`
|
|
143
|
+
*
|
|
144
|
+
* The venue leads (US conventional addressee-then-address ordering) so a downstream model sees the
|
|
145
|
+
* venue-prefix-then-address shape users actually type into geocoders. Empty segments drop out rather than leaving a
|
|
146
|
+
* dangling separator.
|
|
147
|
+
*/
|
|
148
|
+
export declare function composeRaw(parts: ComposeRawParts): string;
|
|
149
|
+
/**
|
|
150
|
+
* Load one curated libpostal dictionary (`core/data/libpostal/dictionaries/<language>/<filename>`) as a lower-cased
|
|
151
|
+
* form set. libpostal format: `canonical|abbr|abbr|...` — every form is indexed.
|
|
152
|
+
*
|
|
153
|
+
* `resourceDictionaryPath` already resolves both layouts — `core/data/...` from source and from the packaged `out/`
|
|
154
|
+
* tree. The candidate list this replaced named it TWICE and then guessed a third path off `process.cwd()`, and
|
|
155
|
+
* swallowed every error while probing, so a corrupt dictionary reported as a missing one.
|
|
156
|
+
*
|
|
157
|
+
* The largest libpostal dictionary is 8.4 KB, and each caller runs this once per process at module load.
|
|
158
|
+
*/
|
|
159
|
+
export declare function loadLibpostalDictionary(language: string, filename: string): Promise<Set<string>>;
|
|
160
|
+
/**
|
|
161
|
+
* Canonical dedup key for a row.
|
|
162
|
+
*
|
|
163
|
+
* Two rows that share this key are treated as duplicates and only the first wins. The key is built from `country`, the
|
|
164
|
+
* sorted `components` dict, and a normalized `raw` (lower-cased, whitespace collapsed). License and provenance fields
|
|
165
|
+
* are intentionally excluded so the same address from multiple adapters is recognized as a duplicate.
|
|
166
|
+
*
|
|
167
|
+
* Synthetic rows are never deduplicated against natural rows: `synth.method` is folded into the key when present,
|
|
168
|
+
* ensuring each augmentation variant survives.
|
|
169
|
+
*/
|
|
170
|
+
export declare function canonicalDedupKey(row: CanonicalRow): string;
|
|
171
|
+
/**
|
|
172
|
+
* Streaming SHA-256 hasher.
|
|
173
|
+
*
|
|
174
|
+
* The runner feeds every JSONL line into one of these so the per-slice checksum can be recorded in `MANIFEST.json`
|
|
175
|
+
* without a second pass over the slice. Implementation is a one-line wrapper, but giving it a name keeps the runner's
|
|
176
|
+
* hash-tracking intent obvious.
|
|
177
|
+
*/
|
|
178
|
+
export interface StreamingHasher {
|
|
179
|
+
update(chunk: string | Uint8Array): void;
|
|
180
|
+
digest(): string;
|
|
181
|
+
}
|
|
182
|
+
/**
|
|
183
|
+
* Default `StreamingHasher` (SHA-256, hex).
|
|
184
|
+
*/
|
|
185
|
+
/**
|
|
186
|
+
* @see {@link StreamingHasher} — this is the incremental counterpart to `sha256Hex`, not a copy of
|
|
187
|
+
* it. `@mailwoman/core/utils` exposes one-shot digests (`sha256Hex`) and whole-file digests
|
|
188
|
+
* (`sha256File`); the runner needs neither, because it hashes JSONL lines as they stream past.
|
|
189
|
+
*/
|
|
190
|
+
export declare function streamingSha256(): StreamingHasher;
|
|
191
|
+
//# sourceMappingURL=index.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../lib/adapters/utils/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;GAwBG;AAMH,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAA;AAGzD,OAAO,KAAK,EAAE,YAAY,EAAE,aAAa,EAAE,MAAM,QAAQ,CAAA;AAEzD;;;;;;GAMG;AACH,MAAM,WAAW,eAAe;IAC/B;;OAEG;IACH,QAAQ,CAAC,OAAO,EAAE,aAAa,GAAG,IAAI,CAAA;IAEtC;;OAEG;IACH,GAAG,CAAC,EAAE,EAAE,MAAM,GAAG,aAAa,GAAG,SAAS,CAAA;IAE1C;;OAEG;IACH,IAAI,IAAI,SAAS,aAAa,EAAE,CAAA;IAEhC;;OAEG;IACH,GAAG,IAAI,SAAS,MAAM,EAAE,CAAA;CACxB;AAED;;;GAGG;AACH,qBAAa,uBAAwB,YAAW,eAAe;;IAG9D,QAAQ,CAAC,OAAO,EAAE,aAAa,GAAG,IAAI;IAQtC,GAAG,CAAC,EAAE,EAAE,MAAM,GAAG,aAAa,GAAG,SAAS;IAI1C,IAAI,IAAI,SAAS,aAAa,EAAE;IAIhC,GAAG,IAAI,SAAS,MAAM,EAAE;CAGxB;AAED;;;GAGG;AACH,eAAO,MAAM,sBAAsB,yBAAgC,CAAA;AAEnE;;;;;;;;;;GAUG;AACH,wBAAgB,cAAc,CAAC,SAAS,EAAE,MAAM,EAAE,UAAU,EAAE,OAAO,CAAC,MAAM,CAAC,YAAY,EAAE,MAAM,CAAC,CAAC,GAAG,MAAM,CAE3G;AAED;;;;GAIG;AACH,wBAAgB,uBAAuB,CACtC,SAAS,EAAE,MAAM,EACjB,KAAK,EAAE,QAAQ,CAAC,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,SAAS,CAAC,CAAC,GACjD,MAAM,CAQR;AAED;;;;;;;;;;;GAWG;AACH,eAAO,MAAM,mBAAmB,QAAuC,CAAA;AAEvE;;GAEG;AACH,MAAM,WAAW,eAAe;IAC/B,YAAY,CAAC,EAAE,MAAM,CAAA;IACrB,MAAM,EAAE,MAAM,CAAA;CACd;AAED;;;;;;;;;;;;GAYG;AACH,wBAAgB,eAAe,CAAC,IAAI,EAAE,MAAM,GAAG,eAAe,GAAG,IAAI,CAUpE;AAED;;;GAGG;AACH,MAAM,WAAW,eAAe;IAC/B,KAAK,CAAC,EAAE,MAAM,CAAA;IACd,WAAW,CAAC,EAAE,MAAM,CAAA;IACpB,MAAM,CAAC,EAAE,MAAM,CAAA;IACf;;;OAGG;IACH,UAAU,CAAC,EAAE,MAAM,CAAA;IACnB,IAAI,CAAC,EAAE,MAAM,CAAA;IACb,QAAQ,EAAE,MAAM,CAAA;IAChB,MAAM,CAAC,EAAE,MAAM,CAAA;IACf,QAAQ,EAAE,MAAM,CAAA;CAChB;AAED;;;;;;;;GAQG;AACH,wBAAgB,UAAU,CAAC,KAAK,EAAE,eAAe,GAAG,MAAM,CASzD;AAED;;;;;;;;;GASG;AACH,wBAAsB,uBAAuB,CAAC,QAAQ,EAAE,MAAM,EAAE,QAAQ,EAAE,MAAM,GAAG,OAAO,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAmBtG;AAED;;;;;;;;;GASG;AACH,wBAAgB,iBAAiB,CAAC,GAAG,EAAE,YAAY,GAAG,MAAM,CAO3D;AAED;;;;;;GAMG;AACH,MAAM,WAAW,eAAe;IAC/B,MAAM,CAAC,KAAK,EAAE,MAAM,GAAG,UAAU,GAAG,IAAI,CAAA;IACxC,MAAM,IAAI,MAAM,CAAA;CAChB;AAED;;GAEG;AACH;;;;GAIG;AACH,wBAAgB,eAAe,IAAI,eAAe,CAmBjD"}
|
|
@@ -0,0 +1,206 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Adapter framework helpers — the pieces every corpus adapter and the runner share.
|
|
7
|
+
*
|
|
8
|
+
* This file does **not** define `CorpusAdapter` (that lives in `./types.ts`, which is the single
|
|
9
|
+
* canonical schema module). It exposes:
|
|
10
|
+
*
|
|
11
|
+
* - `AdapterRegistry`: a tiny lookup table the CLI + build pipeline use to find adapters by id.
|
|
12
|
+
* - `InMemoryAdapterRegistry`: the default implementation.
|
|
13
|
+
* - `stableSourceID(adapterID, components)`: deterministic content-addressed id for adapters whose
|
|
14
|
+
* source data has no native primary key (CSV, GeoJSON).
|
|
15
|
+
* - `HOUSE_NUMBER_PREFIX` + `splitStreetLine(line)`: the one house-number/street split every
|
|
16
|
+
* US CSV adapter uses.
|
|
17
|
+
* - `composeRaw(parts)`: the envelope-style raw line every US CSV adapter renders.
|
|
18
|
+
* - `canonicalDedupKey(row)`: normalized signature used to drop near-identical rows during a run.
|
|
19
|
+
* Adapter-internal dedup; cross-adapter dedup is the runner's job.
|
|
20
|
+
* - `streamingSha256()`: thin wrapper around `node:crypto` so the runner can hash JSONL output as it
|
|
21
|
+
* streams (avoids re-reading the slice for the manifest checksum).
|
|
22
|
+
* - `loadLibpostalDictionary(language, filename)`: the curated libpostal dictionary reader the
|
|
23
|
+
* street-decompose modules share — the one read this module performs; everything else here is
|
|
24
|
+
* pure, and other side-effecting code goes in `./runner.ts`.
|
|
25
|
+
*/
|
|
26
|
+
import { readLocalTextFile } from "@mailwoman/core/fs/readers";
|
|
27
|
+
import { sha256Hex, createHash } from "@mailwoman/core/hash";
|
|
28
|
+
import { isPresent } from "@mailwoman/core/objects";
|
|
29
|
+
import { resourceDictionaryPath } from "@mailwoman/core/paths";
|
|
30
|
+
import { TextSpliterator } from "spliterator";
|
|
31
|
+
/**
|
|
32
|
+
* Default in-memory registry. The runner constructs one per invocation; the CLI re-uses a shared singleton
|
|
33
|
+
* (`defaultAdapterRegistry`) populated by `./adapters/index.ts` as adapters come online.
|
|
34
|
+
*/
|
|
35
|
+
export class InMemoryAdapterRegistry {
|
|
36
|
+
#byID = new Map();
|
|
37
|
+
register(adapter) {
|
|
38
|
+
if (this.#byID.has(adapter.id)) {
|
|
39
|
+
throw new Error(`AdapterRegistry: id ${JSON.stringify(adapter.id)} already registered`);
|
|
40
|
+
}
|
|
41
|
+
this.#byID.set(adapter.id, adapter);
|
|
42
|
+
}
|
|
43
|
+
get(id) {
|
|
44
|
+
return this.#byID.get(id);
|
|
45
|
+
}
|
|
46
|
+
list() {
|
|
47
|
+
return Array.from(this.#byID.values());
|
|
48
|
+
}
|
|
49
|
+
ids() {
|
|
50
|
+
return Array.from(this.#byID.keys());
|
|
51
|
+
}
|
|
52
|
+
}
|
|
53
|
+
/**
|
|
54
|
+
* Process-wide default registry. Populated by `./adapters/index.ts` as adapters are built; imported by the CLI. Tests
|
|
55
|
+
* should construct their own `InMemoryAdapterRegistry` to avoid cross-test pollution.
|
|
56
|
+
*/
|
|
57
|
+
export const defaultAdapterRegistry = new InMemoryAdapterRegistry();
|
|
58
|
+
/**
|
|
59
|
+
* Deterministic content-addressed source id.
|
|
60
|
+
*
|
|
61
|
+
* For adapters whose upstream source has no native primary key (CSV rows, GeoJSON features), the runner expects a
|
|
62
|
+
* stable id so dedup, holdout manifests, and resumability work across reruns. This helper produces one by hashing the
|
|
63
|
+
* adapter id and a canonical serialization of the components dict (keys sorted, values verbatim).
|
|
64
|
+
*
|
|
65
|
+
* Output format: `<adapterID>-<first-12-hex-chars-of-sha256>`. 48 bits of entropy is enough for ~17M rows per adapter
|
|
66
|
+
* before the expected collision count exceeds 1 (birthday paradox); adapters with more rows should extend the prefix
|
|
67
|
+
* length.
|
|
68
|
+
*/
|
|
69
|
+
export function stableSourceID(adapterID, components) {
|
|
70
|
+
return stableSourceIDFromParts(adapterID, components);
|
|
71
|
+
}
|
|
72
|
+
/**
|
|
73
|
+
* {@link stableSourceID} over arbitrary disambiguator keys — a variant index, a slot number, anything that is not a
|
|
74
|
+
* `ComponentTag`. Every key handed in is sorted and hashed either way; only the key vocabulary differs, and the narrow
|
|
75
|
+
* signature above is what stops an adapter hashing a misspelled component name.
|
|
76
|
+
*/
|
|
77
|
+
export function stableSourceIDFromParts(adapterID, parts) {
|
|
78
|
+
const sortedKeys = Object.keys(parts).toSorted();
|
|
79
|
+
const payload = sortedKeys.map((k) => `${k}=${parts[k] ?? ""}`).join("\u001F");
|
|
80
|
+
// One `update` over the joined string, not three chained ones — identical byte stream either way,
|
|
81
|
+
// but the separator has to stay inline or every id in every slice changes.
|
|
82
|
+
const digest = sha256Hex(`${adapterID}\u001E${payload}`);
|
|
83
|
+
return `${adapterID}-${digest.slice(0, 12)}`;
|
|
84
|
+
}
|
|
85
|
+
/**
|
|
86
|
+
* Leading house number on a US-style street line: digits, an optional hyphenated range (Queens `40-12`), an optional
|
|
87
|
+
* single alpha suffix (`101A`), then whitespace, then the rest.
|
|
88
|
+
*
|
|
89
|
+
* This decides where the house number ends and the street begins for every US CSV adapter, so an edge case fixed here
|
|
90
|
+
* is fixed for all of them.
|
|
91
|
+
*
|
|
92
|
+
* The remainder must stay `(\S.*)` and must NOT become `(.+)`: `\s+` and `.` both match a tab, so `\s+(.+)$` lets the
|
|
93
|
+
* engine split a run of tabs between the two groups every possible way before failing — quadratic backtracking on
|
|
94
|
+
* attacker-shaped input. Requiring a non-space start removes the overlap. Group 2 is trimmed by the caller either way,
|
|
95
|
+
* so the two forms are indistinguishable on real input; only the failure cost differs.
|
|
96
|
+
*/
|
|
97
|
+
export const HOUSE_NUMBER_PREFIX = /^(\d+(?:-\d+)?[A-Za-z]?)\s+(\S.*)$/;
|
|
98
|
+
/**
|
|
99
|
+
* Split a US-style street line on {@link HOUSE_NUMBER_PREFIX}.
|
|
100
|
+
*
|
|
101
|
+
* The US CSV sources follow USPS Publication 28 conventions with hand-entry drift. The leading digit run is the house
|
|
102
|
+
* number (`"123 Main St"`, `"6450 W Indian School Rd"`), and the regex tolerates one trailing letter (`"123A Main St"`)
|
|
103
|
+
* plus an optional hyphenated half (`"40-12 Bell Blvd"`, common in NYC and suburban garden-apartment numbering; Hawaii
|
|
104
|
+
* uses it island-wide — `"47-470 Hui Aeko Place"`).
|
|
105
|
+
*
|
|
106
|
+
* Returns `null` for blank input. Anything that does not match the prefix shape (`"PO Box 1234"`, `"RR 2 Box 67"`, `"HC
|
|
107
|
+
* 1"`) becomes a single `street` value rather than being mangled — the model sees the original surface form and
|
|
108
|
+
* downstream classifiers pick it up. Callers that need those forms recognized as something other than a street (see
|
|
109
|
+
* `usgov-irs-bmf`) test for them BEFORE calling this.
|
|
110
|
+
*/
|
|
111
|
+
export function splitStreetLine(line) {
|
|
112
|
+
const trimmed = line.trim();
|
|
113
|
+
if (!trimmed)
|
|
114
|
+
return null;
|
|
115
|
+
const match = HOUSE_NUMBER_PREFIX.exec(trimmed);
|
|
116
|
+
if (match)
|
|
117
|
+
return { house_number: match[1], street: match[2].trim() };
|
|
118
|
+
return { street: trimmed };
|
|
119
|
+
}
|
|
120
|
+
/**
|
|
121
|
+
* Compose the envelope-style raw address line the US CSV adapters share:
|
|
122
|
+
*
|
|
123
|
+
* `"<venue>, <house> <street> <unit>, <city>, <state> <postcode>"`
|
|
124
|
+
*
|
|
125
|
+
* The venue leads (US conventional addressee-then-address ordering) so a downstream model sees the
|
|
126
|
+
* venue-prefix-then-address shape users actually type into geocoders. Empty segments drop out rather than leaving a
|
|
127
|
+
* dangling separator.
|
|
128
|
+
*/
|
|
129
|
+
export function composeRaw(parts) {
|
|
130
|
+
const streetLine = parts.streetLine ?? [parts.houseNumber, parts.street, parts.unit].filter(isPresent).join(" ").trim();
|
|
131
|
+
const tail = [parts.locality.trim(), [parts.region, parts.postcode].filter(isPresent).join(" ").trim()]
|
|
132
|
+
.filter(isPresent)
|
|
133
|
+
.join(", ");
|
|
134
|
+
return [parts.venue, streetLine || undefined, tail].filter(isPresent).join(", ");
|
|
135
|
+
}
|
|
136
|
+
/**
|
|
137
|
+
* Load one curated libpostal dictionary (`core/data/libpostal/dictionaries/<language>/<filename>`) as a lower-cased
|
|
138
|
+
* form set. libpostal format: `canonical|abbr|abbr|...` — every form is indexed.
|
|
139
|
+
*
|
|
140
|
+
* `resourceDictionaryPath` already resolves both layouts — `core/data/...` from source and from the packaged `out/`
|
|
141
|
+
* tree. The candidate list this replaced named it TWICE and then guessed a third path off `process.cwd()`, and
|
|
142
|
+
* swallowed every error while probing, so a corrupt dictionary reported as a missing one.
|
|
143
|
+
*
|
|
144
|
+
* The largest libpostal dictionary is 8.4 KB, and each caller runs this once per process at module load.
|
|
145
|
+
*/
|
|
146
|
+
export async function loadLibpostalDictionary(language, filename) {
|
|
147
|
+
const text = await readLocalTextFile(resourceDictionaryPath("libpostal", language, filename));
|
|
148
|
+
const set = new Set();
|
|
149
|
+
for (const line of TextSpliterator.from(text)) {
|
|
150
|
+
const trimmed = line.trim();
|
|
151
|
+
if (!trimmed || trimmed.startsWith("#"))
|
|
152
|
+
continue;
|
|
153
|
+
for (const form of trimmed.split("|")) {
|
|
154
|
+
const f = form.trim().toLowerCase();
|
|
155
|
+
if (f) {
|
|
156
|
+
set.add(f);
|
|
157
|
+
}
|
|
158
|
+
}
|
|
159
|
+
}
|
|
160
|
+
return set;
|
|
161
|
+
}
|
|
162
|
+
/**
|
|
163
|
+
* Canonical dedup key for a row.
|
|
164
|
+
*
|
|
165
|
+
* Two rows that share this key are treated as duplicates and only the first wins. The key is built from `country`, the
|
|
166
|
+
* sorted `components` dict, and a normalized `raw` (lower-cased, whitespace collapsed). License and provenance fields
|
|
167
|
+
* are intentionally excluded so the same address from multiple adapters is recognized as a duplicate.
|
|
168
|
+
*
|
|
169
|
+
* Synthetic rows are never deduplicated against natural rows: `synth.method` is folded into the key when present,
|
|
170
|
+
* ensuring each augmentation variant survives.
|
|
171
|
+
*/
|
|
172
|
+
export function canonicalDedupKey(row) {
|
|
173
|
+
const sortedKeys = Object.keys(row.components).toSorted();
|
|
174
|
+
const compPart = sortedKeys.map((k) => `${k}=${row.components[k] ?? ""}`).join("\u001F");
|
|
175
|
+
const rawNorm = row.raw.toLowerCase().replaceAll(/\s+/g, " ").trim();
|
|
176
|
+
const synthPart = row.synth ? `\u001E${row.synth.method}` : "";
|
|
177
|
+
return `${row.country}\u001E${rawNorm}\u001E${compPart}${synthPart}`;
|
|
178
|
+
}
|
|
179
|
+
/**
|
|
180
|
+
* Default `StreamingHasher` (SHA-256, hex).
|
|
181
|
+
*/
|
|
182
|
+
/**
|
|
183
|
+
* @see {@link StreamingHasher} — this is the incremental counterpart to `sha256Hex`, not a copy of
|
|
184
|
+
* it. `@mailwoman/core/utils` exposes one-shot digests (`sha256Hex`) and whole-file digests
|
|
185
|
+
* (`sha256File`); the runner needs neither, because it hashes JSONL lines as they stream past.
|
|
186
|
+
*/
|
|
187
|
+
export function streamingSha256() {
|
|
188
|
+
const h = createHash("sha256");
|
|
189
|
+
let finalized = false;
|
|
190
|
+
let digestHex = "";
|
|
191
|
+
return {
|
|
192
|
+
update(chunk) {
|
|
193
|
+
if (finalized)
|
|
194
|
+
throw new Error("streamingSha256: update() called after digest()");
|
|
195
|
+
h.update(typeof chunk === "string" ? chunk : chunk);
|
|
196
|
+
},
|
|
197
|
+
digest() {
|
|
198
|
+
if (!finalized) {
|
|
199
|
+
digestHex = h.digest("hex");
|
|
200
|
+
finalized = true;
|
|
201
|
+
}
|
|
202
|
+
return digestHex;
|
|
203
|
+
},
|
|
204
|
+
};
|
|
205
|
+
}
|
|
206
|
+
//# sourceMappingURL=index.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../lib/adapters/utils/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;GAwBG;AAEH,OAAO,EAAE,iBAAiB,EAAE,MAAM,4BAA4B,CAAA;AAC9D,OAAO,EAAE,SAAS,EAAE,UAAU,EAAa,MAAM,sBAAsB,CAAA;AACvE,OAAO,EAAE,SAAS,EAAE,MAAM,yBAAyB,CAAA;AACnD,OAAO,EAAE,sBAAsB,EAAE,MAAM,uBAAuB,CAAA;AAE9D,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAiC7C;;;GAGG;AACH,MAAM,OAAO,uBAAuB;IACnC,KAAK,GAAG,IAAI,GAAG,EAAyB,CAAA;IAExC,QAAQ,CAAC,OAAsB;QAC9B,IAAI,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,OAAO,CAAC,EAAE,CAAC,EAAE,CAAC;YAChC,MAAM,IAAI,KAAK,CAAC,uBAAuB,IAAI,CAAC,SAAS,CAAC,OAAO,CAAC,EAAE,CAAC,qBAAqB,CAAC,CAAA;QACxF,CAAC;QAED,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,OAAO,CAAC,EAAE,EAAE,OAAO,CAAC,CAAA;IACpC,CAAC;IAED,GAAG,CAAC,EAAU;QACb,OAAO,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC,CAAA;IAC1B,CAAC;IAED,IAAI;QACH,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,CAAC,CAAA;IACvC,CAAC;IAED,GAAG;QACF,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,CAAA;IACrC,CAAC;CACD;AAED;;;GAGG;AACH,MAAM,CAAC,MAAM,sBAAsB,GAAG,IAAI,uBAAuB,EAAE,CAAA;AAEnE;;;;;;;;;;GAUG;AACH,MAAM,UAAU,cAAc,CAAC,SAAiB,EAAE,UAAiD;IAClG,OAAO,uBAAuB,CAAC,SAAS,EAAE,UAAU,CAAC,CAAA;AACtD,CAAC;AAED;;;;GAIG;AACH,MAAM,UAAU,uBAAuB,CACtC,SAAiB,EACjB,KAAmD;IAEnD,MAAM,UAAU,GAAG,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,QAAQ,EAAE,CAAA;IAChD,MAAM,OAAO,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,GAAG,CAAC,IAAI,KAAK,CAAC,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAA;IAC9E,kGAAkG;IAClG,2EAA2E;IAC3E,MAAM,MAAM,GAAG,SAAS,CAAC,GAAG,SAAS,SAAS,OAAO,EAAE,CAAC,CAAA;IAExD,OAAO,GAAG,SAAS,IAAI,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,EAAE,CAAC,EAAE,CAAA;AAC7C,CAAC;AAED;;;;;;;;;;;GAWG;AACH,MAAM,CAAC,MAAM,mBAAmB,GAAG,oCAAoC,CAAA;AAUvE;;;;;;;;;;;;GAYG;AACH,MAAM,UAAU,eAAe,CAAC,IAAY;IAC3C,MAAM,OAAO,GAAG,IAAI,CAAC,IAAI,EAAE,CAAA;IAE3B,IAAI,CAAC,OAAO;QAAE,OAAO,IAAI,CAAA;IAEzB,MAAM,KAAK,GAAG,mBAAmB,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;IAE/C,IAAI,KAAK;QAAE,OAAO,EAAE,YAAY,EAAE,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,KAAK,CAAC,CAAC,CAAE,CAAC,IAAI,EAAE,EAAE,CAAA;IAEtE,OAAO,EAAE,MAAM,EAAE,OAAO,EAAE,CAAA;AAC3B,CAAC;AAqBD;;;;;;;;GAQG;AACH,MAAM,UAAU,UAAU,CAAC,KAAsB;IAChD,MAAM,UAAU,GACf,KAAK,CAAC,UAAU,IAAI,CAAC,KAAK,CAAC,WAAW,EAAE,KAAK,CAAC,MAAM,EAAE,KAAK,CAAC,IAAI,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;IAErG,MAAM,IAAI,GAAG,CAAC,KAAK,CAAC,QAAQ,CAAC,IAAI,EAAE,EAAE,CAAC,KAAK,CAAC,MAAM,EAAE,KAAK,CAAC,QAAQ,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC;SACrG,MAAM,CAAC,SAAS,CAAC;SACjB,IAAI,CAAC,IAAI,CAAC,CAAA;IAEZ,OAAO,CAAC,KAAK,CAAC,KAAK,EAAE,UAAU,IAAI,SAAS,EAAE,IAAI,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;AACjF,CAAC;AAED;;;;;;;;;GASG;AACH,MAAM,CAAC,KAAK,UAAU,uBAAuB,CAAC,QAAgB,EAAE,QAAgB;IAC/E,MAAM,IAAI,GAAG,MAAM,iBAAiB,CAAC,sBAAsB,CAAC,WAAW,EAAE,QAAQ,EAAE,QAAQ,CAAC,CAAC,CAAA;IAC7F,MAAM,GAAG,GAAG,IAAI,GAAG,EAAU,CAAA;IAE7B,KAAK,MAAM,IAAI,IAAI,eAAe,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;QAC/C,MAAM,OAAO,GAAG,IAAI,CAAC,IAAI,EAAE,CAAA;QAE3B,IAAI,CAAC,OAAO,IAAI,OAAO,CAAC,UAAU,CAAC,GAAG,CAAC;YAAE,SAAQ;QAEjD,KAAK,MAAM,IAAI,IAAI,OAAO,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC;YACvC,MAAM,CAAC,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAA;YAEnC,IAAI,CAAC,EAAE,CAAC;gBACP,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,CAAA;YACX,CAAC;QACF,CAAC;IACF,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC;AAED;;;;;;;;;GASG;AACH,MAAM,UAAU,iBAAiB,CAAC,GAAiB;IAClD,MAAM,UAAU,GAAG,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC,QAAQ,EAAoB,CAAA;IAC3E,MAAM,QAAQ,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,GAAG,CAAC,IAAI,GAAG,CAAC,UAAU,CAAC,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAA;IACxF,MAAM,OAAO,GAAG,GAAG,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC,UAAU,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;IACpE,MAAM,SAAS,GAAG,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,SAAS,GAAG,CAAC,KAAK,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;IAE9D,OAAO,GAAG,GAAG,CAAC,OAAO,SAAS,OAAO,SAAS,QAAQ,GAAG,SAAS,EAAE,CAAA;AACrE,CAAC;AAcD;;GAEG;AACH;;;;GAIG;AACH,MAAM,UAAU,eAAe;IAC9B,MAAM,CAAC,GAAS,UAAU,CAAC,QAAQ,CAAC,CAAA;IACpC,IAAI,SAAS,GAAG,KAAK,CAAA;IACrB,IAAI,SAAS,GAAG,EAAE,CAAA;IAElB,OAAO;QACN,MAAM,CAAC,KAAK;YACX,IAAI,SAAS;gBAAE,MAAM,IAAI,KAAK,CAAC,iDAAiD,CAAC,CAAA;YACjF,CAAC,CAAC,MAAM,CAAC,OAAO,KAAK,KAAK,QAAQ,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAA;QACpD,CAAC;QACD,MAAM;YACL,IAAI,CAAC,SAAS,EAAE,CAAC;gBAChB,SAAS,GAAG,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAA;gBAC3B,SAAS,GAAG,IAAI,CAAA;YACjB,CAAC;YAED,OAAO,SAAS,CAAA;QACjB,CAAC;KACD,CAAA;AACF,CAAC"}
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../lib/adapters/wof-admin-jp/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA6BG;AAOH,OAAO,KAAK,EAAkB,YAAY,EAAE,aAAa,EAAE,MAAM,QAAQ,CAAA;AAOzE;;;GAGG;AACH,eAAO,MAAM,uBAAuB,iBAAiB,CAAA;AAErD,UAAU,QAAQ;IACjB,EAAE,EAAE,MAAM,CAAA;IACV,IAAI,EAAE,MAAM,CAAA;IACZ,SAAS,EAAE,MAAM,CAAA;IACjB,SAAS,EAAE,MAAM,CAAA;IACjB,OAAO,EAAE,MAAM,CAAA;CACf;AAoCD;;;;;;GAMG;AACH,wBAAgB,mBAAmB,CAClC,KAAK,EAAE,QAAQ,EAAE,EACjB,QAAQ,EAAE,GAAG,CAAC,MAAM,EAAE,MAAM,CAAC,GAC3B;IACF,GAAG,EAAE,MAAM,CAAA;IACX,UAAU,EAAE,YAAY,CAAC,YAAY,CAAC,CAAA;CACtC,GAAG,IAAI,CAyBP;AAED;;;GAGG;AACH,wBAAgB,uBAAuB,IAAI,aAAa,CAyEvD;AAED;;GAEG;AACH,eAAO,MAAM,iBAAiB,eAA4B,CAAA"}
|