@mailwoman/corpus 9.1.0 → 9.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +24 -24
- package/data/PROVENANCE.md +20 -7
- package/data/reviewed-ve-postcode-tuples.json +74 -0
- package/lib/adapters/ban/adapter.ts +190 -0
- package/lib/adapters/ban/street-decompose.ts +66 -0
- package/lib/adapters/fcc-bdc/adapter.ts +174 -0
- package/lib/adapters/geonames/adapter.ts +199 -0
- package/lib/adapters/geonames-postal/adapter.ts +122 -0
- package/lib/adapters/gnaf/adapter.ts +149 -0
- package/lib/adapters/gnaf/assemble.ts +225 -0
- package/lib/adapters/index.ts +153 -0
- package/lib/adapters/openaddresses/adapter.ts +251 -0
- package/lib/adapters/overture/adapter.ts +162 -0
- package/lib/adapters/state-hi-schools/adapter.ts +170 -0
- package/lib/adapters/state-hi-schools/workbook.ts +35 -0
- package/lib/adapters/state-ia-contractors/adapter.ts +144 -0
- package/lib/adapters/state-ny-notaries/adapter.ts +141 -0
- package/lib/adapters/state-tx-notaries/adapter.ts +157 -0
- package/lib/adapters/synth-po-box/adapter.ts +204 -0
- package/lib/adapters/tiger/adapter.ts +252 -0
- package/lib/adapters/tiger/street-decompose.ts +83 -0
- package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +167 -0
- package/lib/adapters/usgov-imls-pls/adapter.ts +143 -0
- package/lib/adapters/usgov-irs-bmf/adapter.ts +151 -0
- package/lib/adapters/usgov-nad/adapter.ts +334 -0
- package/lib/adapters/usgov-nppes/adapter.ts +151 -0
- package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +193 -0
- package/lib/adapters/utils/index.ts +307 -0
- package/lib/adapters/wof-admin-jp/adapter.ts +214 -0
- package/lib/adapters/wof-admin-json/adapter.ts +231 -0
- package/lib/adapters/wof-json-rows.ts +129 -0
- package/lib/adapters/wof-postalcode-json/adapter.ts +176 -0
- package/lib/build.ts +378 -0
- package/lib/env.ts +50 -0
- package/lib/index.ts +13 -0
- package/lib/name-prone-us-suffixes.ts +12 -0
- package/lib/recipes/anchor-absorption.ts +101 -0
- package/lib/recipes/bare-country.ts +95 -0
- package/lib/recipes/boundary-stress.ts +100 -0
- package/lib/recipes/cn-organizational-units.ts +199 -0
- package/lib/recipes/country-balanced.ts +509 -0
- package/lib/recipes/cz-pcfirst-preposition.ts +111 -0
- package/lib/recipes/fr-admin-split.ts +242 -0
- package/lib/recipes/fr-bare-street.ts +170 -0
- package/lib/recipes/fr-fragment.ts +333 -0
- package/lib/recipes/fr-lieudit.ts +301 -0
- package/lib/recipes/fr-order.ts +245 -0
- package/lib/recipes/german.ts +359 -0
- package/lib/recipes/house-venue.ts +92 -0
- package/lib/recipes/index.ts +97 -0
- package/lib/recipes/intersection.ts +618 -0
- package/lib/recipes/locale.ts +599 -0
- package/lib/recipes/nl-postcode.ts +115 -0
- package/lib/recipes/no-fragment.ts +219 -0
- package/lib/recipes/no-street-led.ts +141 -0
- package/lib/recipes/no-street.ts +90 -0
- package/lib/recipes/po-box-cedex.ts +976 -0
- package/lib/recipes/po-box.ts +123 -0
- package/lib/recipes/reviewed-postcode-tail.ts +190 -0
- package/lib/recipes/scaffold.ts +469 -0
- package/lib/recipes/si-bare-village.ts +97 -0
- package/lib/recipes/street-affix.ts +804 -0
- package/lib/recipes/street-bare.ts +100 -0
- package/lib/recipes/street.ts +81 -0
- package/lib/recipes/sub-venue-sources.ts +877 -0
- package/lib/recipes/sub-venue.ts +997 -0
- package/lib/recipes/trailing-region.ts +183 -0
- package/lib/recipes/unit.ts +304 -0
- package/lib/runner.ts +312 -0
- package/lib/synthesizers/anchor-absorption.ts +288 -0
- package/lib/synthesizers/boundary-stress.ts +532 -0
- package/lib/synthesizers/german.ts +260 -0
- package/lib/synthesizers/house-venue.ts +308 -0
- package/lib/synthesizers/intersection.ts +233 -0
- package/lib/synthesizers/no-street.ts +327 -0
- package/lib/synthesizers/po-box.ts +323 -0
- package/lib/synthesizers/street.ts +269 -0
- package/lib/synthesizers/utils.ts +993 -0
- package/lib/test-kit/corpus-recipe.ts +86 -0
- package/lib/test-kit/index.ts +100 -0
- package/lib/tools/align-slice.ts +68 -0
- package/lib/tools/audit.ts +403 -0
- package/lib/tools/corpus-stats.ts +136 -0
- package/lib/tools/fetch/ban.ts +289 -0
- package/lib/tools/fetch/download.ts +262 -0
- package/lib/tools/fetch/geonames-dump.ts +257 -0
- package/lib/tools/fetch/geonames-postal.ts +180 -0
- package/lib/tools/fetch/hrsa.ts +59 -0
- package/lib/tools/fetch/imls-pls.ts +149 -0
- package/lib/tools/fetch/index.ts +147 -0
- package/lib/tools/fetch/nad.ts +341 -0
- package/lib/tools/fetch/nppes.ts +165 -0
- package/lib/tools/fetch/openaddresses.ts +347 -0
- package/lib/tools/fetch/ourairports.ts +170 -0
- package/lib/tools/fetch/ppd.ts +121 -0
- package/lib/tools/fetch/state-hi-schools.ts +161 -0
- package/lib/tools/fetch/state-sources.ts +146 -0
- package/lib/tools/fetch/tiger-full.ts +308 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +384 -0
- package/lib/tools/golden-expand.ts +574 -0
- package/lib/tools/golden-promote.ts +337 -0
- package/lib/tools/golden-relabel-street.ts +683 -0
- package/lib/tools/index.ts +28 -0
- package/lib/tools/ingest-csv.ts +378 -0
- package/lib/tools/jsonl-to-parquet.ts +207 -0
- package/lib/tools/lint-slice-vocab.ts +388 -0
- package/lib/tools/lint-slice.ts +496 -0
- package/lib/tools/overlay-manifest.ts +148 -0
- package/lib/tools/overture-subvenue.ts +209 -0
- package/lib/tools/postcode-triples.ts +363 -0
- package/lib/tools/slice-kryptonite.ts +137 -0
- package/lib/tools/slice-translit.ts +218 -0
- package/lib/tools/sub-venue/harvest.ts +234 -0
- package/lib/tools/sub-venue/head-nouns.ts +245 -0
- package/lib/tools/sub-venue/surfaces.ts +95 -0
- package/lib/tools/sub-venue/table.ts +281 -0
- package/lib/tools/sub-venue/wikidata.ts +85 -0
- package/lib/tools/sub-venue-lexicon.ts +429 -0
- package/lib/tools/sub-venue-promotions.ts +330 -0
- package/lib/types.ts +247 -0
- package/lib/utils/align.ts +330 -0
- package/lib/utils/golden.ts +189 -0
- package/lib/utils/index.ts +14 -0
- package/lib/utils/license.ts +50 -0
- package/lib/utils/parquet.ts +582 -0
- package/lib/utils/slice-stats.ts +95 -0
- package/lib/utils/split.ts +279 -0
- package/lib/utils/tokenize.ts +120 -0
- package/lib/utils/wof-json.ts +247 -0
- package/out/adapters/ban/adapter.d.ts +44 -0
- package/out/adapters/ban/adapter.d.ts.map +1 -0
- package/out/adapters/ban/adapter.js +149 -0
- package/out/adapters/ban/adapter.js.map +1 -0
- package/out/adapters/ban/street-decompose.d.ts.map +1 -0
- package/out/adapters/ban/street-decompose.js +51 -0
- package/out/adapters/ban/street-decompose.js.map +1 -0
- package/out/adapters/fcc-bdc/adapter.d.ts +68 -0
- package/out/adapters/fcc-bdc/adapter.d.ts.map +1 -0
- package/out/adapters/fcc-bdc/adapter.js +144 -0
- package/out/adapters/fcc-bdc/adapter.js.map +1 -0
- package/out/adapters/geonames/adapter.d.ts +46 -0
- package/out/adapters/geonames/adapter.d.ts.map +1 -0
- package/out/adapters/geonames/adapter.js +176 -0
- package/out/adapters/geonames/adapter.js.map +1 -0
- package/out/adapters/geonames-postal/adapter.d.ts +54 -0
- package/out/adapters/geonames-postal/adapter.d.ts.map +1 -0
- package/out/adapters/geonames-postal/adapter.js +107 -0
- package/out/adapters/geonames-postal/adapter.js.map +1 -0
- package/out/adapters/gnaf/adapter.d.ts +49 -0
- package/out/adapters/gnaf/adapter.d.ts.map +1 -0
- package/out/adapters/gnaf/adapter.js +124 -0
- package/out/adapters/gnaf/adapter.js.map +1 -0
- package/out/adapters/gnaf/assemble.d.ts +65 -0
- package/out/adapters/gnaf/assemble.d.ts.map +1 -0
- package/out/adapters/gnaf/assemble.js +154 -0
- package/out/adapters/gnaf/assemble.js.map +1 -0
- package/out/adapters/index.d.ts +51 -0
- package/out/adapters/index.d.ts.map +1 -0
- package/out/adapters/index.js +95 -0
- package/out/adapters/index.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts +72 -0
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -0
- package/out/adapters/openaddresses/adapter.js +186 -0
- package/out/adapters/openaddresses/adapter.js.map +1 -0
- package/out/adapters/overture/adapter.d.ts +48 -0
- package/out/adapters/overture/adapter.d.ts.map +1 -0
- package/out/adapters/overture/adapter.js +125 -0
- package/out/adapters/overture/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/adapter.d.ts +46 -0
- package/out/adapters/state-hi-schools/adapter.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/adapter.js +145 -0
- package/out/adapters/state-hi-schools/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/workbook.d.ts +29 -0
- package/out/adapters/state-hi-schools/workbook.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/workbook.js +20 -0
- package/out/adapters/state-hi-schools/workbook.js.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.d.ts +34 -0
- package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.js +111 -0
- package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.d.ts +32 -0
- package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.js +119 -0
- package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.d.ts +33 -0
- package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.js +125 -0
- package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
- package/out/adapters/synth-po-box/adapter.d.ts +67 -0
- package/out/adapters/synth-po-box/adapter.d.ts.map +1 -0
- package/out/adapters/synth-po-box/adapter.js +140 -0
- package/out/adapters/synth-po-box/adapter.js.map +1 -0
- package/out/adapters/tiger/adapter.d.ts +55 -0
- package/out/adapters/tiger/adapter.d.ts.map +1 -0
- package/out/adapters/tiger/adapter.js +201 -0
- package/out/adapters/tiger/adapter.js.map +1 -0
- package/out/adapters/tiger/street-decompose.d.ts.map +1 -0
- package/out/adapters/tiger/street-decompose.js +68 -0
- package/out/adapters/tiger/street-decompose.js.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +56 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js +132 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts +36 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.js +114 -0
- package/out/adapters/usgov-imls-pls/adapter.js.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts +37 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.js +120 -0
- package/out/adapters/usgov-irs-bmf/adapter.js.map +1 -0
- package/out/adapters/usgov-nad/adapter.d.ts +48 -0
- package/out/adapters/usgov-nad/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nad/adapter.js +249 -0
- package/out/adapters/usgov-nad/adapter.js.map +1 -0
- package/out/adapters/usgov-nppes/adapter.d.ts +39 -0
- package/out/adapters/usgov-nppes/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nppes/adapter.js +118 -0
- package/out/adapters/usgov-nppes/adapter.js.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts +46 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +154 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -0
- package/out/adapters/utils/index.d.ts +191 -0
- package/out/adapters/utils/index.d.ts.map +1 -0
- package/out/adapters/utils/index.js +206 -0
- package/out/adapters/utils/index.js.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.d.ts +65 -0
- package/out/adapters/wof-admin-jp/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.js +161 -0
- package/out/adapters/wof-admin-jp/adapter.js.map +1 -0
- package/out/adapters/wof-admin-json/adapter.d.ts +79 -0
- package/out/adapters/wof-admin-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-json/adapter.js +197 -0
- package/out/adapters/wof-admin-json/adapter.js.map +1 -0
- package/out/adapters/wof-json-rows.d.ts +62 -0
- package/out/adapters/wof-json-rows.d.ts.map +1 -0
- package/out/adapters/wof-json-rows.js +83 -0
- package/out/adapters/wof-json-rows.js.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts +65 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.js +151 -0
- package/out/adapters/wof-postalcode-json/adapter.js.map +1 -0
- package/out/build.d.ts +132 -0
- package/out/build.d.ts.map +1 -0
- package/out/build.js +245 -0
- package/out/build.js.map +1 -0
- package/out/codex/us-fips-state.d.ts.map +1 -0
- package/out/codex/us-fips-state.js.map +1 -0
- package/out/env.d.ts +46 -0
- package/out/env.d.ts.map +1 -0
- package/out/env.js +46 -0
- package/out/env.js.map +1 -0
- package/out/index.d.ts +13 -0
- package/out/index.d.ts.map +1 -0
- package/out/index.js +13 -0
- package/out/index.js.map +1 -0
- package/out/name-prone-us-suffixes.d.ts +12 -0
- package/out/name-prone-us-suffixes.d.ts.map +1 -0
- package/out/name-prone-us-suffixes.js +12 -0
- package/out/name-prone-us-suffixes.js.map +1 -0
- package/out/recipes/anchor-absorption.d.ts +20 -0
- package/out/recipes/anchor-absorption.d.ts.map +1 -0
- package/out/recipes/anchor-absorption.js +81 -0
- package/out/recipes/anchor-absorption.js.map +1 -0
- package/out/recipes/bare-country.d.ts +25 -0
- package/out/recipes/bare-country.d.ts.map +1 -0
- package/out/recipes/bare-country.js +87 -0
- package/out/recipes/bare-country.js.map +1 -0
- package/out/recipes/boundary-stress.d.ts +20 -0
- package/out/recipes/boundary-stress.d.ts.map +1 -0
- package/out/recipes/boundary-stress.js +83 -0
- package/out/recipes/boundary-stress.js.map +1 -0
- package/out/recipes/cn-organizational-units.d.ts +36 -0
- package/out/recipes/cn-organizational-units.d.ts.map +1 -0
- package/out/recipes/cn-organizational-units.js +159 -0
- package/out/recipes/cn-organizational-units.js.map +1 -0
- package/out/recipes/country-balanced.d.ts +32 -0
- package/out/recipes/country-balanced.d.ts.map +1 -0
- package/out/recipes/country-balanced.js +393 -0
- package/out/recipes/country-balanced.js.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts +22 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.js +100 -0
- package/out/recipes/cz-pcfirst-preposition.js.map +1 -0
- package/out/recipes/fr-admin-split.d.ts +38 -0
- package/out/recipes/fr-admin-split.d.ts.map +1 -0
- package/out/recipes/fr-admin-split.js +192 -0
- package/out/recipes/fr-admin-split.js.map +1 -0
- package/out/recipes/fr-bare-street.d.ts +28 -0
- package/out/recipes/fr-bare-street.d.ts.map +1 -0
- package/out/recipes/fr-bare-street.js +143 -0
- package/out/recipes/fr-bare-street.js.map +1 -0
- package/out/recipes/fr-fragment.d.ts +77 -0
- package/out/recipes/fr-fragment.d.ts.map +1 -0
- package/out/recipes/fr-fragment.js +276 -0
- package/out/recipes/fr-fragment.js.map +1 -0
- package/out/recipes/fr-lieudit.d.ts +32 -0
- package/out/recipes/fr-lieudit.d.ts.map +1 -0
- package/out/recipes/fr-lieudit.js +227 -0
- package/out/recipes/fr-lieudit.js.map +1 -0
- package/out/recipes/fr-order.d.ts +38 -0
- package/out/recipes/fr-order.d.ts.map +1 -0
- package/out/recipes/fr-order.js +197 -0
- package/out/recipes/fr-order.js.map +1 -0
- package/out/recipes/german.d.ts +44 -0
- package/out/recipes/german.d.ts.map +1 -0
- package/out/recipes/german.js +288 -0
- package/out/recipes/german.js.map +1 -0
- package/out/recipes/house-venue.d.ts +18 -0
- package/out/recipes/house-venue.d.ts.map +1 -0
- package/out/recipes/house-venue.js +73 -0
- package/out/recipes/house-venue.js.map +1 -0
- package/out/recipes/index.d.ts +24 -0
- package/out/recipes/index.d.ts.map +1 -0
- package/out/recipes/index.js +91 -0
- package/out/recipes/index.js.map +1 -0
- package/out/recipes/intersection.d.ts +42 -0
- package/out/recipes/intersection.d.ts.map +1 -0
- package/out/recipes/intersection.js +452 -0
- package/out/recipes/intersection.js.map +1 -0
- package/out/recipes/locale.d.ts +136 -0
- package/out/recipes/locale.d.ts.map +1 -0
- package/out/recipes/locale.js +460 -0
- package/out/recipes/locale.js.map +1 -0
- package/out/recipes/nl-postcode.d.ts +26 -0
- package/out/recipes/nl-postcode.d.ts.map +1 -0
- package/out/recipes/nl-postcode.js +102 -0
- package/out/recipes/nl-postcode.js.map +1 -0
- package/out/recipes/no-fragment.d.ts +43 -0
- package/out/recipes/no-fragment.d.ts.map +1 -0
- package/out/recipes/no-fragment.js +182 -0
- package/out/recipes/no-fragment.js.map +1 -0
- package/out/recipes/no-street-led.d.ts +24 -0
- package/out/recipes/no-street-led.d.ts.map +1 -0
- package/out/recipes/no-street-led.js +113 -0
- package/out/recipes/no-street-led.js.map +1 -0
- package/out/recipes/no-street.d.ts +18 -0
- package/out/recipes/no-street.d.ts.map +1 -0
- package/out/recipes/no-street.js +71 -0
- package/out/recipes/no-street.js.map +1 -0
- package/out/recipes/po-box-cedex.d.ts +38 -0
- package/out/recipes/po-box-cedex.d.ts.map +1 -0
- package/out/recipes/po-box-cedex.js +767 -0
- package/out/recipes/po-box-cedex.js.map +1 -0
- package/out/recipes/po-box.d.ts +17 -0
- package/out/recipes/po-box.d.ts.map +1 -0
- package/out/recipes/po-box.js +100 -0
- package/out/recipes/po-box.js.map +1 -0
- package/out/recipes/reviewed-postcode-tail.d.ts +47 -0
- package/out/recipes/reviewed-postcode-tail.d.ts.map +1 -0
- package/out/recipes/reviewed-postcode-tail.js +125 -0
- package/out/recipes/reviewed-postcode-tail.js.map +1 -0
- package/out/recipes/scaffold.d.ts +324 -0
- package/out/recipes/scaffold.d.ts.map +1 -0
- package/out/recipes/scaffold.js +186 -0
- package/out/recipes/scaffold.js.map +1 -0
- package/out/recipes/si-bare-village.d.ts +32 -0
- package/out/recipes/si-bare-village.d.ts.map +1 -0
- package/out/recipes/si-bare-village.js +88 -0
- package/out/recipes/si-bare-village.js.map +1 -0
- package/out/recipes/street-affix.d.ts +89 -0
- package/out/recipes/street-affix.d.ts.map +1 -0
- package/out/recipes/street-affix.js +563 -0
- package/out/recipes/street-affix.js.map +1 -0
- package/out/recipes/street-bare.d.ts +25 -0
- package/out/recipes/street-bare.d.ts.map +1 -0
- package/out/recipes/street-bare.js +86 -0
- package/out/recipes/street-bare.js.map +1 -0
- package/out/recipes/street.d.ts +15 -0
- package/out/recipes/street.d.ts.map +1 -0
- package/out/recipes/street.js +69 -0
- package/out/recipes/street.js.map +1 -0
- package/out/recipes/sub-venue-sources.d.ts +229 -0
- package/out/recipes/sub-venue-sources.d.ts.map +1 -0
- package/out/recipes/sub-venue-sources.js +653 -0
- package/out/recipes/sub-venue-sources.js.map +1 -0
- package/out/recipes/sub-venue.d.ts +269 -0
- package/out/recipes/sub-venue.d.ts.map +1 -0
- package/out/recipes/sub-venue.js +725 -0
- package/out/recipes/sub-venue.js.map +1 -0
- package/out/recipes/trailing-region.d.ts +74 -0
- package/out/recipes/trailing-region.d.ts.map +1 -0
- package/out/recipes/trailing-region.js +157 -0
- package/out/recipes/trailing-region.js.map +1 -0
- package/out/recipes/unit.d.ts +29 -0
- package/out/recipes/unit.d.ts.map +1 -0
- package/out/recipes/unit.js +230 -0
- package/out/recipes/unit.js.map +1 -0
- package/out/runner.d.ts +130 -0
- package/out/runner.d.ts.map +1 -0
- package/out/runner.js +185 -0
- package/out/runner.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +63 -0
- package/out/synthesizers/anchor-absorption.d.ts.map +1 -0
- package/out/synthesizers/anchor-absorption.js +221 -0
- package/out/synthesizers/anchor-absorption.js.map +1 -0
- package/out/synthesizers/boundary-stress.d.ts +78 -0
- package/out/synthesizers/boundary-stress.d.ts.map +1 -0
- package/out/synthesizers/boundary-stress.js +455 -0
- package/out/synthesizers/boundary-stress.js.map +1 -0
- package/out/synthesizers/german.d.ts +115 -0
- package/out/synthesizers/german.d.ts.map +1 -0
- package/out/synthesizers/german.js +149 -0
- package/out/synthesizers/german.js.map +1 -0
- package/out/synthesizers/house-venue.d.ts +56 -0
- package/out/synthesizers/house-venue.d.ts.map +1 -0
- package/out/synthesizers/house-venue.js +247 -0
- package/out/synthesizers/house-venue.js.map +1 -0
- package/out/synthesizers/intersection.d.ts +52 -0
- package/out/synthesizers/intersection.d.ts.map +1 -0
- package/out/synthesizers/intersection.js +175 -0
- package/out/synthesizers/intersection.js.map +1 -0
- package/out/synthesizers/no-street.d.ts +72 -0
- package/out/synthesizers/no-street.d.ts.map +1 -0
- package/out/synthesizers/no-street.js +262 -0
- package/out/synthesizers/no-street.js.map +1 -0
- package/out/synthesizers/po-box.d.ts +108 -0
- package/out/synthesizers/po-box.d.ts.map +1 -0
- package/out/synthesizers/po-box.js +250 -0
- package/out/synthesizers/po-box.js.map +1 -0
- package/out/synthesizers/street.d.ts +54 -0
- package/out/synthesizers/street.d.ts.map +1 -0
- package/out/synthesizers/street.js +218 -0
- package/out/synthesizers/street.js.map +1 -0
- package/out/synthesizers/utils.d.ts +241 -0
- package/out/synthesizers/utils.d.ts.map +1 -0
- package/out/synthesizers/utils.js +776 -0
- package/out/synthesizers/utils.js.map +1 -0
- package/out/test-kit/corpus-recipe.d.ts +59 -0
- package/out/test-kit/corpus-recipe.d.ts.map +1 -0
- package/out/test-kit/corpus-recipe.js +39 -0
- package/out/test-kit/corpus-recipe.js.map +1 -0
- package/out/test-kit/index.d.ts +48 -0
- package/out/test-kit/index.d.ts.map +1 -0
- package/out/test-kit/index.js +78 -0
- package/out/test-kit/index.js.map +1 -0
- package/out/tools/align-slice.d.ts +7 -0
- package/out/tools/align-slice.d.ts.map +1 -0
- package/out/tools/align-slice.js +55 -0
- package/out/tools/align-slice.js.map +1 -0
- package/out/tools/audit.d.ts +29 -0
- package/out/tools/audit.d.ts.map +1 -0
- package/out/tools/audit.js +282 -0
- package/out/tools/audit.js.map +1 -0
- package/out/tools/corpus-stats.d.ts +44 -0
- package/out/tools/corpus-stats.d.ts.map +1 -0
- package/out/tools/corpus-stats.js +102 -0
- package/out/tools/corpus-stats.js.map +1 -0
- package/out/tools/fetch/ban.d.ts +31 -0
- package/out/tools/fetch/ban.d.ts.map +1 -0
- package/out/tools/fetch/ban.js +239 -0
- package/out/tools/fetch/ban.js.map +1 -0
- package/out/tools/fetch/download.d.ts +117 -0
- package/out/tools/fetch/download.d.ts.map +1 -0
- package/out/tools/fetch/download.js +160 -0
- package/out/tools/fetch/download.js.map +1 -0
- package/out/tools/fetch/geonames-dump.d.ts +91 -0
- package/out/tools/fetch/geonames-dump.d.ts.map +1 -0
- package/out/tools/fetch/geonames-dump.js +171 -0
- package/out/tools/fetch/geonames-dump.js.map +1 -0
- package/out/tools/fetch/geonames-postal.d.ts +76 -0
- package/out/tools/fetch/geonames-postal.d.ts.map +1 -0
- package/out/tools/fetch/geonames-postal.js +126 -0
- package/out/tools/fetch/geonames-postal.js.map +1 -0
- package/out/tools/fetch/hrsa.d.ts +18 -0
- package/out/tools/fetch/hrsa.d.ts.map +1 -0
- package/out/tools/fetch/hrsa.js +46 -0
- package/out/tools/fetch/hrsa.js.map +1 -0
- package/out/tools/fetch/imls-pls.d.ts +25 -0
- package/out/tools/fetch/imls-pls.d.ts.map +1 -0
- package/out/tools/fetch/imls-pls.js +108 -0
- package/out/tools/fetch/imls-pls.js.map +1 -0
- package/out/tools/fetch/index.d.ts +144 -0
- package/out/tools/fetch/index.d.ts.map +1 -0
- package/out/tools/fetch/index.js +143 -0
- package/out/tools/fetch/index.js.map +1 -0
- package/out/tools/fetch/nad.d.ts +70 -0
- package/out/tools/fetch/nad.d.ts.map +1 -0
- package/out/tools/fetch/nad.js +234 -0
- package/out/tools/fetch/nad.js.map +1 -0
- package/out/tools/fetch/nppes.d.ts +26 -0
- package/out/tools/fetch/nppes.d.ts.map +1 -0
- package/out/tools/fetch/nppes.js +126 -0
- package/out/tools/fetch/nppes.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +9 -0
- package/out/tools/fetch/openaddresses.d.ts.map +1 -0
- package/out/tools/fetch/openaddresses.js +279 -0
- package/out/tools/fetch/openaddresses.js.map +1 -0
- package/out/tools/fetch/ourairports.d.ts +45 -0
- package/out/tools/fetch/ourairports.d.ts.map +1 -0
- package/out/tools/fetch/ourairports.js +128 -0
- package/out/tools/fetch/ourairports.js.map +1 -0
- package/out/tools/fetch/ppd.d.ts +14 -0
- package/out/tools/fetch/ppd.d.ts.map +1 -0
- package/out/tools/fetch/ppd.js +85 -0
- package/out/tools/fetch/ppd.js.map +1 -0
- package/out/tools/fetch/state-hi-schools.d.ts +26 -0
- package/out/tools/fetch/state-hi-schools.d.ts.map +1 -0
- package/out/tools/fetch/state-hi-schools.js +112 -0
- package/out/tools/fetch/state-hi-schools.js.map +1 -0
- package/out/tools/fetch/state-sources.d.ts +26 -0
- package/out/tools/fetch/state-sources.d.ts.map +1 -0
- package/out/tools/fetch/state-sources.js +111 -0
- package/out/tools/fetch/state-sources.js.map +1 -0
- package/out/tools/fetch/tiger-full.d.ts +22 -0
- package/out/tools/fetch/tiger-full.d.ts.map +1 -0
- package/out/tools/fetch/tiger-full.js +217 -0
- package/out/tools/fetch/tiger-full.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +171 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.js +274 -0
- package/out/tools/fetch/wikidata-subvenue.js.map +1 -0
- package/out/tools/gb-title-case.d.ts.map +1 -0
- package/out/tools/gb-title-case.js.map +1 -0
- package/out/tools/golden-expand.d.ts +90 -0
- package/out/tools/golden-expand.d.ts.map +1 -0
- package/out/tools/golden-expand.js +406 -0
- package/out/tools/golden-expand.js.map +1 -0
- package/out/tools/golden-promote.d.ts.map +1 -0
- package/out/tools/golden-promote.js +240 -0
- package/out/tools/golden-promote.js.map +1 -0
- package/out/tools/golden-relabel-street.d.ts +196 -0
- package/out/tools/golden-relabel-street.d.ts.map +1 -0
- package/out/tools/golden-relabel-street.js +440 -0
- package/out/tools/golden-relabel-street.js.map +1 -0
- package/out/tools/index.d.ts +28 -0
- package/out/tools/index.d.ts.map +1 -0
- package/out/tools/index.js +28 -0
- package/out/tools/index.js.map +1 -0
- package/out/tools/ingest-csv.d.ts.map +1 -0
- package/out/tools/ingest-csv.js +265 -0
- package/out/tools/ingest-csv.js.map +1 -0
- package/out/tools/jsonl-to-parquet.d.ts +61 -0
- package/out/tools/jsonl-to-parquet.d.ts.map +1 -0
- package/out/tools/jsonl-to-parquet.js +150 -0
- package/out/tools/jsonl-to-parquet.js.map +1 -0
- package/out/tools/lint-slice-vocab.d.ts +90 -0
- package/out/tools/lint-slice-vocab.d.ts.map +1 -0
- package/out/tools/lint-slice-vocab.js +267 -0
- package/out/tools/lint-slice-vocab.js.map +1 -0
- package/out/tools/lint-slice.d.ts +93 -0
- package/out/tools/lint-slice.d.ts.map +1 -0
- package/out/tools/lint-slice.js +322 -0
- package/out/tools/lint-slice.js.map +1 -0
- package/out/tools/overlay-manifest.d.ts +39 -0
- package/out/tools/overlay-manifest.d.ts.map +1 -0
- package/out/tools/overlay-manifest.js +90 -0
- package/out/tools/overlay-manifest.js.map +1 -0
- package/out/tools/overture-subvenue.d.ts +112 -0
- package/out/tools/overture-subvenue.d.ts.map +1 -0
- package/out/tools/overture-subvenue.js +139 -0
- package/out/tools/overture-subvenue.js.map +1 -0
- package/out/tools/postcode-triples.d.ts +174 -0
- package/out/tools/postcode-triples.d.ts.map +1 -0
- package/out/tools/postcode-triples.js +292 -0
- package/out/tools/postcode-triples.js.map +1 -0
- package/out/tools/slice-kryptonite.d.ts +32 -0
- package/out/tools/slice-kryptonite.d.ts.map +1 -0
- package/out/tools/slice-kryptonite.js +99 -0
- package/out/tools/slice-kryptonite.js.map +1 -0
- package/out/tools/slice-translit.d.ts +51 -0
- package/out/tools/slice-translit.d.ts.map +1 -0
- package/out/tools/slice-translit.js +166 -0
- package/out/tools/slice-translit.js.map +1 -0
- package/out/tools/sub-venue/harvest.d.ts +100 -0
- package/out/tools/sub-venue/harvest.d.ts.map +1 -0
- package/out/tools/sub-venue/harvest.js +168 -0
- package/out/tools/sub-venue/harvest.js.map +1 -0
- package/out/tools/sub-venue/head-nouns.d.ts +50 -0
- package/out/tools/sub-venue/head-nouns.d.ts.map +1 -0
- package/out/tools/sub-venue/head-nouns.js +213 -0
- package/out/tools/sub-venue/head-nouns.js.map +1 -0
- package/out/tools/sub-venue/surfaces.d.ts +45 -0
- package/out/tools/sub-venue/surfaces.d.ts.map +1 -0
- package/out/tools/sub-venue/surfaces.js +77 -0
- package/out/tools/sub-venue/surfaces.js.map +1 -0
- package/out/tools/sub-venue/table.d.ts +229 -0
- package/out/tools/sub-venue/table.d.ts.map +1 -0
- package/out/tools/sub-venue/table.js +108 -0
- package/out/tools/sub-venue/table.js.map +1 -0
- package/out/tools/sub-venue/wikidata.d.ts +26 -0
- package/out/tools/sub-venue/wikidata.d.ts.map +1 -0
- package/out/tools/sub-venue/wikidata.js +62 -0
- package/out/tools/sub-venue/wikidata.js.map +1 -0
- package/out/tools/sub-venue-lexicon.d.ts +156 -0
- package/out/tools/sub-venue-lexicon.d.ts.map +1 -0
- package/out/tools/sub-venue-lexicon.js +283 -0
- package/out/tools/sub-venue-lexicon.js.map +1 -0
- package/out/tools/sub-venue-promotions.d.ts +94 -0
- package/out/tools/sub-venue-promotions.d.ts.map +1 -0
- package/out/tools/sub-venue-promotions.js +266 -0
- package/out/tools/sub-venue-promotions.js.map +1 -0
- package/out/types.d.ts +221 -0
- package/out/types.d.ts.map +1 -0
- package/out/types.js.map +1 -0
- package/out/utils/align.d.ts +93 -0
- package/out/utils/align.d.ts.map +1 -0
- package/out/utils/align.js +234 -0
- package/out/utils/align.js.map +1 -0
- package/out/utils/golden.d.ts +85 -0
- package/out/utils/golden.d.ts.map +1 -0
- package/out/utils/golden.js +127 -0
- package/out/utils/golden.js.map +1 -0
- package/out/utils/index.d.ts +14 -0
- package/out/utils/index.d.ts.map +1 -0
- package/out/utils/index.js +14 -0
- package/out/utils/index.js.map +1 -0
- package/out/utils/license.d.ts.map +1 -0
- package/out/utils/license.js +47 -0
- package/out/utils/license.js.map +1 -0
- package/out/utils/parquet.d.ts +178 -0
- package/out/utils/parquet.d.ts.map +1 -0
- package/out/utils/parquet.js +371 -0
- package/out/utils/parquet.js.map +1 -0
- package/out/utils/slice-stats.d.ts +52 -0
- package/out/utils/slice-stats.d.ts.map +1 -0
- package/out/utils/slice-stats.js +58 -0
- package/out/utils/slice-stats.js.map +1 -0
- package/out/utils/split.d.ts +128 -0
- package/out/utils/split.d.ts.map +1 -0
- package/out/utils/split.js +204 -0
- package/out/utils/split.js.map +1 -0
- package/out/utils/tokenize.d.ts +64 -0
- package/out/utils/tokenize.d.ts.map +1 -0
- package/out/utils/tokenize.js +82 -0
- package/out/utils/tokenize.js.map +1 -0
- package/out/utils/wof-json.d.ts +113 -0
- package/out/utils/wof-json.d.ts.map +1 -0
- package/out/utils/wof-json.js +173 -0
- package/out/utils/wof-json.js.map +1 -0
- package/package.json +350 -65
- package/out/src/adapters/ban/adapter.d.ts +0 -44
- package/out/src/adapters/ban/adapter.d.ts.map +0 -1
- package/out/src/adapters/ban/adapter.js +0 -148
- package/out/src/adapters/ban/adapter.js.map +0 -1
- package/out/src/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/ban/street-decompose.js +0 -75
- package/out/src/adapters/ban/street-decompose.js.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.d.ts +0 -68
- package/out/src/adapters/fcc-bdc/adapter.d.ts.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.js +0 -144
- package/out/src/adapters/fcc-bdc/adapter.js.map +0 -1
- package/out/src/adapters/geonames/adapter.d.ts +0 -46
- package/out/src/adapters/geonames/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames/adapter.js +0 -176
- package/out/src/adapters/geonames/adapter.js.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.d.ts +0 -41
- package/out/src/adapters/geonames-postal/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.js +0 -104
- package/out/src/adapters/geonames-postal/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/adapter.d.ts +0 -49
- package/out/src/adapters/gnaf/adapter.d.ts.map +0 -1
- package/out/src/adapters/gnaf/adapter.js +0 -124
- package/out/src/adapters/gnaf/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/assemble.d.ts +0 -65
- package/out/src/adapters/gnaf/assemble.d.ts.map +0 -1
- package/out/src/adapters/gnaf/assemble.js +0 -154
- package/out/src/adapters/gnaf/assemble.js.map +0 -1
- package/out/src/adapters/index.d.ts +0 -51
- package/out/src/adapters/index.d.ts.map +0 -1
- package/out/src/adapters/index.js +0 -95
- package/out/src/adapters/index.js.map +0 -1
- package/out/src/adapters/openaddresses/adapter.d.ts +0 -72
- package/out/src/adapters/openaddresses/adapter.d.ts.map +0 -1
- package/out/src/adapters/openaddresses/adapter.js +0 -186
- package/out/src/adapters/openaddresses/adapter.js.map +0 -1
- package/out/src/adapters/overture/adapter.d.ts +0 -48
- package/out/src/adapters/overture/adapter.d.ts.map +0 -1
- package/out/src/adapters/overture/adapter.js +0 -125
- package/out/src/adapters/overture/adapter.js.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.d.ts +0 -47
- package/out/src/adapters/state-hi-schools/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.js +0 -132
- package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.d.ts +0 -34
- package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.js +0 -106
- package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.d.ts +0 -32
- package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.js +0 -125
- package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.d.ts +0 -33
- package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.js +0 -120
- package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.d.ts +0 -67
- package/out/src/adapters/synth-po-box/adapter.d.ts.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.js +0 -140
- package/out/src/adapters/synth-po-box/adapter.js.map +0 -1
- package/out/src/adapters/tiger/adapter.d.ts +0 -55
- package/out/src/adapters/tiger/adapter.d.ts.map +0 -1
- package/out/src/adapters/tiger/adapter.js +0 -201
- package/out/src/adapters/tiger/adapter.js.map +0 -1
- package/out/src/adapters/tiger/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/tiger/street-decompose.js +0 -90
- package/out/src/adapters/tiger/street-decompose.js.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -47
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +0 -138
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts +0 -36
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.js +0 -110
- package/out/src/adapters/usgov-imls-pls/adapter.js.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.js +0 -123
- package/out/src/adapters/usgov-irs-bmf/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.d.ts +0 -48
- package/out/src/adapters/usgov-nad/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.js +0 -252
- package/out/src/adapters/usgov-nad/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.d.ts +0 -39
- package/out/src/adapters/usgov-nppes/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.js +0 -116
- package/out/src/adapters/usgov-nppes/adapter.js.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts +0 -46
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -155
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
- package/out/src/adapters/utils/index.d.ts +0 -144
- package/out/src/adapters/utils/index.d.ts.map +0 -1
- package/out/src/adapters/utils/index.js +0 -151
- package/out/src/adapters/utils/index.js.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.d.ts +0 -65
- package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.js +0 -164
- package/out/src/adapters/wof-admin-jp/adapter.js.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.d.ts +0 -93
- package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.js +0 -248
- package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -70
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.js +0 -185
- package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
- package/out/src/build.d.ts +0 -131
- package/out/src/build.d.ts.map +0 -1
- package/out/src/build.js +0 -248
- package/out/src/build.js.map +0 -1
- package/out/src/codex/us-fips-state.d.ts.map +0 -1
- package/out/src/codex/us-fips-state.js.map +0 -1
- package/out/src/index.d.ts +0 -14
- package/out/src/index.d.ts.map +0 -1
- package/out/src/index.js +0 -14
- package/out/src/index.js.map +0 -1
- package/out/src/name-prone-us-suffixes.d.ts +0 -12
- package/out/src/name-prone-us-suffixes.d.ts.map +0 -1
- package/out/src/name-prone-us-suffixes.js +0 -12
- package/out/src/name-prone-us-suffixes.js.map +0 -1
- package/out/src/parquet-wrapper/index.d.ts +0 -9
- package/out/src/parquet-wrapper/index.d.ts.map +0 -1
- package/out/src/parquet-wrapper/index.js +0 -9
- package/out/src/parquet-wrapper/index.js.map +0 -1
- package/out/src/parquet-wrapper/reader.d.ts +0 -34
- package/out/src/parquet-wrapper/reader.d.ts.map +0 -1
- package/out/src/parquet-wrapper/reader.js +0 -64
- package/out/src/parquet-wrapper/reader.js.map +0 -1
- package/out/src/parquet-wrapper/schema.d.ts +0 -49
- package/out/src/parquet-wrapper/schema.d.ts.map +0 -1
- package/out/src/parquet-wrapper/schema.js +0 -55
- package/out/src/parquet-wrapper/schema.js.map +0 -1
- package/out/src/parquet-wrapper/writer.d.ts +0 -46
- package/out/src/parquet-wrapper/writer.d.ts.map +0 -1
- package/out/src/parquet-wrapper/writer.js +0 -76
- package/out/src/parquet-wrapper/writer.js.map +0 -1
- package/out/src/runner.d.ts +0 -126
- package/out/src/runner.d.ts.map +0 -1
- package/out/src/runner.js +0 -189
- package/out/src/runner.js.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.d.ts +0 -20
- package/out/src/shard-recipes/anchor-absorption.d.ts.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.js +0 -83
- package/out/src/shard-recipes/anchor-absorption.js.map +0 -1
- package/out/src/shard-recipes/boundary-stress.d.ts +0 -20
- package/out/src/shard-recipes/boundary-stress.d.ts.map +0 -1
- package/out/src/shard-recipes/boundary-stress.js +0 -83
- package/out/src/shard-recipes/boundary-stress.js.map +0 -1
- package/out/src/shard-recipes/country-balanced.d.ts +0 -32
- package/out/src/shard-recipes/country-balanced.d.ts.map +0 -1
- package/out/src/shard-recipes/country-balanced.js +0 -405
- package/out/src/shard-recipes/country-balanced.js.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts +0 -22
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.js +0 -82
- package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.d.ts +0 -38
- package/out/src/shard-recipes/fr-admin-split.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.js +0 -187
- package/out/src/shard-recipes/fr-admin-split.js.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.d.ts +0 -28
- package/out/src/shard-recipes/fr-bare-street.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.js +0 -82
- package/out/src/shard-recipes/fr-bare-street.js.map +0 -1
- package/out/src/shard-recipes/fr-fragment.d.ts +0 -77
- package/out/src/shard-recipes/fr-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-fragment.js +0 -276
- package/out/src/shard-recipes/fr-fragment.js.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.d.ts +0 -32
- package/out/src/shard-recipes/fr-lieudit.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.js +0 -225
- package/out/src/shard-recipes/fr-lieudit.js.map +0 -1
- package/out/src/shard-recipes/fr-order.d.ts +0 -38
- package/out/src/shard-recipes/fr-order.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-order.js +0 -207
- package/out/src/shard-recipes/fr-order.js.map +0 -1
- package/out/src/shard-recipes/german.d.ts +0 -23
- package/out/src/shard-recipes/german.d.ts.map +0 -1
- package/out/src/shard-recipes/german.js +0 -132
- package/out/src/shard-recipes/german.js.map +0 -1
- package/out/src/shard-recipes/house-venue.d.ts +0 -18
- package/out/src/shard-recipes/house-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/house-venue.js +0 -74
- package/out/src/shard-recipes/house-venue.js.map +0 -1
- package/out/src/shard-recipes/index.d.ts +0 -24
- package/out/src/shard-recipes/index.d.ts.map +0 -1
- package/out/src/shard-recipes/index.js +0 -83
- package/out/src/shard-recipes/index.js.map +0 -1
- package/out/src/shard-recipes/intersection.d.ts +0 -42
- package/out/src/shard-recipes/intersection.d.ts.map +0 -1
- package/out/src/shard-recipes/intersection.js +0 -460
- package/out/src/shard-recipes/intersection.js.map +0 -1
- package/out/src/shard-recipes/locale.d.ts +0 -135
- package/out/src/shard-recipes/locale.d.ts.map +0 -1
- package/out/src/shard-recipes/locale.js +0 -458
- package/out/src/shard-recipes/locale.js.map +0 -1
- package/out/src/shard-recipes/nl-postcode.d.ts +0 -26
- package/out/src/shard-recipes/nl-postcode.d.ts.map +0 -1
- package/out/src/shard-recipes/nl-postcode.js +0 -102
- package/out/src/shard-recipes/nl-postcode.js.map +0 -1
- package/out/src/shard-recipes/no-fragment.d.ts +0 -43
- package/out/src/shard-recipes/no-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/no-fragment.js +0 -188
- package/out/src/shard-recipes/no-fragment.js.map +0 -1
- package/out/src/shard-recipes/no-street-led.d.ts +0 -24
- package/out/src/shard-recipes/no-street-led.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street-led.js +0 -121
- package/out/src/shard-recipes/no-street-led.js.map +0 -1
- package/out/src/shard-recipes/no-street.d.ts +0 -18
- package/out/src/shard-recipes/no-street.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street.js +0 -72
- package/out/src/shard-recipes/no-street.js.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.d.ts +0 -38
- package/out/src/shard-recipes/po-box-cedex.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.js +0 -726
- package/out/src/shard-recipes/po-box-cedex.js.map +0 -1
- package/out/src/shard-recipes/po-box.d.ts +0 -17
- package/out/src/shard-recipes/po-box.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box.js +0 -101
- package/out/src/shard-recipes/po-box.js.map +0 -1
- package/out/src/shard-recipes/scaffold.d.ts +0 -217
- package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
- package/out/src/shard-recipes/scaffold.js +0 -138
- package/out/src/shard-recipes/scaffold.js.map +0 -1
- package/out/src/shard-recipes/si-bare-village.d.ts +0 -32
- package/out/src/shard-recipes/si-bare-village.d.ts.map +0 -1
- package/out/src/shard-recipes/si-bare-village.js +0 -88
- package/out/src/shard-recipes/si-bare-village.js.map +0 -1
- package/out/src/shard-recipes/street-affix.d.ts +0 -89
- package/out/src/shard-recipes/street-affix.d.ts.map +0 -1
- package/out/src/shard-recipes/street-affix.js +0 -578
- package/out/src/shard-recipes/street-affix.js.map +0 -1
- package/out/src/shard-recipes/street-bare.d.ts +0 -25
- package/out/src/shard-recipes/street-bare.d.ts.map +0 -1
- package/out/src/shard-recipes/street-bare.js +0 -86
- package/out/src/shard-recipes/street-bare.js.map +0 -1
- package/out/src/shard-recipes/street.d.ts +0 -15
- package/out/src/shard-recipes/street.d.ts.map +0 -1
- package/out/src/shard-recipes/street.js +0 -69
- package/out/src/shard-recipes/street.js.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.d.ts +0 -228
- package/out/src/shard-recipes/sub-venue-sources.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.js +0 -664
- package/out/src/shard-recipes/sub-venue-sources.js.map +0 -1
- package/out/src/shard-recipes/sub-venue.d.ts +0 -269
- package/out/src/shard-recipes/sub-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue.js +0 -709
- package/out/src/shard-recipes/sub-venue.js.map +0 -1
- package/out/src/shard-recipes/unit.d.ts +0 -29
- package/out/src/shard-recipes/unit.d.ts.map +0 -1
- package/out/src/shard-recipes/unit.js +0 -243
- package/out/src/shard-recipes/unit.js.map +0 -1
- package/out/src/synthesizers/anchor-absorption.d.ts +0 -63
- package/out/src/synthesizers/anchor-absorption.d.ts.map +0 -1
- package/out/src/synthesizers/anchor-absorption.js +0 -223
- package/out/src/synthesizers/anchor-absorption.js.map +0 -1
- package/out/src/synthesizers/boundary-stress.d.ts +0 -78
- package/out/src/synthesizers/boundary-stress.d.ts.map +0 -1
- package/out/src/synthesizers/boundary-stress.js +0 -455
- package/out/src/synthesizers/boundary-stress.js.map +0 -1
- package/out/src/synthesizers/german.d.ts +0 -107
- package/out/src/synthesizers/german.d.ts.map +0 -1
- package/out/src/synthesizers/german.js +0 -148
- package/out/src/synthesizers/german.js.map +0 -1
- package/out/src/synthesizers/house-venue.d.ts +0 -56
- package/out/src/synthesizers/house-venue.d.ts.map +0 -1
- package/out/src/synthesizers/house-venue.js +0 -253
- package/out/src/synthesizers/house-venue.js.map +0 -1
- package/out/src/synthesizers/intersection.d.ts +0 -52
- package/out/src/synthesizers/intersection.d.ts.map +0 -1
- package/out/src/synthesizers/intersection.js +0 -175
- package/out/src/synthesizers/intersection.js.map +0 -1
- package/out/src/synthesizers/no-street.d.ts +0 -72
- package/out/src/synthesizers/no-street.d.ts.map +0 -1
- package/out/src/synthesizers/no-street.js +0 -282
- package/out/src/synthesizers/no-street.js.map +0 -1
- package/out/src/synthesizers/po-box.d.ts +0 -104
- package/out/src/synthesizers/po-box.d.ts.map +0 -1
- package/out/src/synthesizers/po-box.js +0 -266
- package/out/src/synthesizers/po-box.js.map +0 -1
- package/out/src/synthesizers/street.d.ts +0 -54
- package/out/src/synthesizers/street.d.ts.map +0 -1
- package/out/src/synthesizers/street.js +0 -220
- package/out/src/synthesizers/street.js.map +0 -1
- package/out/src/synthesizers/utils.d.ts +0 -203
- package/out/src/synthesizers/utils.d.ts.map +0 -1
- package/out/src/synthesizers/utils.js +0 -707
- package/out/src/synthesizers/utils.js.map +0 -1
- package/out/src/tools/align-shard.d.ts +0 -8
- package/out/src/tools/align-shard.d.ts.map +0 -1
- package/out/src/tools/align-shard.js +0 -56
- package/out/src/tools/align-shard.js.map +0 -1
- package/out/src/tools/audit.d.ts +0 -28
- package/out/src/tools/audit.d.ts.map +0 -1
- package/out/src/tools/audit.js +0 -285
- package/out/src/tools/audit.js.map +0 -1
- package/out/src/tools/corpus-stats.d.ts +0 -44
- package/out/src/tools/corpus-stats.d.ts.map +0 -1
- package/out/src/tools/corpus-stats.js +0 -138
- package/out/src/tools/corpus-stats.js.map +0 -1
- package/out/src/tools/fetch/ban.d.ts +0 -31
- package/out/src/tools/fetch/ban.d.ts.map +0 -1
- package/out/src/tools/fetch/ban.js +0 -255
- package/out/src/tools/fetch/ban.js.map +0 -1
- package/out/src/tools/fetch/download.d.ts +0 -69
- package/out/src/tools/fetch/download.d.ts.map +0 -1
- package/out/src/tools/fetch/download.js +0 -100
- package/out/src/tools/fetch/download.js.map +0 -1
- package/out/src/tools/fetch/hrsa.d.ts +0 -18
- package/out/src/tools/fetch/hrsa.d.ts.map +0 -1
- package/out/src/tools/fetch/hrsa.js +0 -46
- package/out/src/tools/fetch/hrsa.js.map +0 -1
- package/out/src/tools/fetch/imls-pls.d.ts +0 -25
- package/out/src/tools/fetch/imls-pls.d.ts.map +0 -1
- package/out/src/tools/fetch/imls-pls.js +0 -108
- package/out/src/tools/fetch/imls-pls.js.map +0 -1
- package/out/src/tools/fetch/index.d.ts +0 -133
- package/out/src/tools/fetch/index.d.ts.map +0 -1
- package/out/src/tools/fetch/index.js +0 -132
- package/out/src/tools/fetch/index.js.map +0 -1
- package/out/src/tools/fetch/nad.d.ts +0 -70
- package/out/src/tools/fetch/nad.d.ts.map +0 -1
- package/out/src/tools/fetch/nad.js +0 -225
- package/out/src/tools/fetch/nad.js.map +0 -1
- package/out/src/tools/fetch/nppes.d.ts +0 -26
- package/out/src/tools/fetch/nppes.d.ts.map +0 -1
- package/out/src/tools/fetch/nppes.js +0 -124
- package/out/src/tools/fetch/nppes.js.map +0 -1
- package/out/src/tools/fetch/openaddresses.d.ts +0 -61
- package/out/src/tools/fetch/openaddresses.d.ts.map +0 -1
- package/out/src/tools/fetch/openaddresses.js +0 -316
- package/out/src/tools/fetch/openaddresses.js.map +0 -1
- package/out/src/tools/fetch/ourairports.d.ts +0 -45
- package/out/src/tools/fetch/ourairports.d.ts.map +0 -1
- package/out/src/tools/fetch/ourairports.js +0 -123
- package/out/src/tools/fetch/ourairports.js.map +0 -1
- package/out/src/tools/fetch/ppd.d.ts +0 -18
- package/out/src/tools/fetch/ppd.d.ts.map +0 -1
- package/out/src/tools/fetch/ppd.js +0 -100
- package/out/src/tools/fetch/ppd.js.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.d.ts +0 -25
- package/out/src/tools/fetch/state-hi-schools.d.ts.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.js +0 -178
- package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
- package/out/src/tools/fetch/state-sources.d.ts +0 -22
- package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
- package/out/src/tools/fetch/state-sources.js +0 -115
- package/out/src/tools/fetch/state-sources.js.map +0 -1
- package/out/src/tools/fetch/tiger-full.d.ts +0 -42
- package/out/src/tools/fetch/tiger-full.d.ts.map +0 -1
- package/out/src/tools/fetch/tiger-full.js +0 -254
- package/out/src/tools/fetch/tiger-full.js.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.d.ts +0 -171
- package/out/src/tools/fetch/wikidata-subvenue.d.ts.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.js +0 -275
- package/out/src/tools/fetch/wikidata-subvenue.js.map +0 -1
- package/out/src/tools/gb-title-case.d.ts.map +0 -1
- package/out/src/tools/gb-title-case.js.map +0 -1
- package/out/src/tools/golden-expand.d.ts +0 -90
- package/out/src/tools/golden-expand.d.ts.map +0 -1
- package/out/src/tools/golden-expand.js +0 -404
- package/out/src/tools/golden-expand.js.map +0 -1
- package/out/src/tools/golden-promote.d.ts.map +0 -1
- package/out/src/tools/golden-promote.js +0 -244
- package/out/src/tools/golden-promote.js.map +0 -1
- package/out/src/tools/golden-relabel-street.d.ts +0 -196
- package/out/src/tools/golden-relabel-street.d.ts.map +0 -1
- package/out/src/tools/golden-relabel-street.js +0 -440
- package/out/src/tools/golden-relabel-street.js.map +0 -1
- package/out/src/tools/index.d.ts +0 -28
- package/out/src/tools/index.d.ts.map +0 -1
- package/out/src/tools/index.js +0 -28
- package/out/src/tools/index.js.map +0 -1
- package/out/src/tools/ingest-csv.d.ts.map +0 -1
- package/out/src/tools/ingest-csv.js +0 -307
- package/out/src/tools/ingest-csv.js.map +0 -1
- package/out/src/tools/jsonl-to-parquet.d.ts +0 -61
- package/out/src/tools/jsonl-to-parquet.d.ts.map +0 -1
- package/out/src/tools/jsonl-to-parquet.js +0 -164
- package/out/src/tools/jsonl-to-parquet.js.map +0 -1
- package/out/src/tools/lint-shard-vocab.d.ts +0 -90
- package/out/src/tools/lint-shard-vocab.d.ts.map +0 -1
- package/out/src/tools/lint-shard-vocab.js +0 -281
- package/out/src/tools/lint-shard-vocab.js.map +0 -1
- package/out/src/tools/lint-shard.d.ts +0 -93
- package/out/src/tools/lint-shard.d.ts.map +0 -1
- package/out/src/tools/lint-shard.js +0 -354
- package/out/src/tools/lint-shard.js.map +0 -1
- package/out/src/tools/overlay-manifest.d.ts +0 -35
- package/out/src/tools/overlay-manifest.d.ts.map +0 -1
- package/out/src/tools/overlay-manifest.js +0 -88
- package/out/src/tools/overlay-manifest.js.map +0 -1
- package/out/src/tools/overture-subvenue.d.ts +0 -112
- package/out/src/tools/overture-subvenue.d.ts.map +0 -1
- package/out/src/tools/overture-subvenue.js +0 -144
- package/out/src/tools/overture-subvenue.js.map +0 -1
- package/out/src/tools/shard-kryptonite.d.ts +0 -32
- package/out/src/tools/shard-kryptonite.d.ts.map +0 -1
- package/out/src/tools/shard-kryptonite.js +0 -101
- package/out/src/tools/shard-kryptonite.js.map +0 -1
- package/out/src/tools/shard-translit.d.ts +0 -51
- package/out/src/tools/shard-translit.d.ts.map +0 -1
- package/out/src/tools/shard-translit.js +0 -197
- package/out/src/tools/shard-translit.js.map +0 -1
- package/out/src/tools/sub-venue-lexicon.d.ts +0 -507
- package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
- package/out/src/tools/sub-venue-lexicon.js +0 -817
- package/out/src/tools/sub-venue-lexicon.js.map +0 -1
- package/out/src/tools/sub-venue-promotions.d.ts +0 -94
- package/out/src/tools/sub-venue-promotions.d.ts.map +0 -1
- package/out/src/tools/sub-venue-promotions.js +0 -266
- package/out/src/tools/sub-venue-promotions.js.map +0 -1
- package/out/src/types.d.ts +0 -221
- package/out/src/types.d.ts.map +0 -1
- package/out/src/types.js.map +0 -1
- package/out/src/utils/align.d.ts +0 -93
- package/out/src/utils/align.d.ts.map +0 -1
- package/out/src/utils/align.js +0 -234
- package/out/src/utils/align.js.map +0 -1
- package/out/src/utils/golden.d.ts +0 -69
- package/out/src/utils/golden.d.ts.map +0 -1
- package/out/src/utils/golden.js +0 -127
- package/out/src/utils/golden.js.map +0 -1
- package/out/src/utils/index.d.ts +0 -14
- package/out/src/utils/index.d.ts.map +0 -1
- package/out/src/utils/index.js +0 -14
- package/out/src/utils/index.js.map +0 -1
- package/out/src/utils/license.d.ts.map +0 -1
- package/out/src/utils/license.js +0 -47
- package/out/src/utils/license.js.map +0 -1
- package/out/src/utils/parquet.d.ts +0 -143
- package/out/src/utils/parquet.d.ts.map +0 -1
- package/out/src/utils/parquet.js +0 -258
- package/out/src/utils/parquet.js.map +0 -1
- package/out/src/utils/split.d.ts +0 -127
- package/out/src/utils/split.d.ts.map +0 -1
- package/out/src/utils/split.js +0 -204
- package/out/src/utils/split.js.map +0 -1
- package/out/src/utils/tokenize.d.ts +0 -56
- package/out/src/utils/tokenize.d.ts.map +0 -1
- package/out/src/utils/tokenize.js +0 -48
- package/out/src/utils/tokenize.js.map +0 -1
- package/out/src/utils/wof-json.d.ts +0 -109
- package/out/src/utils/wof-json.d.ts.map +0 -1
- package/out/src/utils/wof-json.js +0 -173
- package/out/src/utils/wof-json.js.map +0 -1
- package/src/adapters/ban/adapter.ts +0 -189
- package/src/adapters/ban/street-decompose.ts +0 -96
- package/src/adapters/fcc-bdc/adapter.ts +0 -173
- package/src/adapters/geonames/adapter.ts +0 -199
- package/src/adapters/geonames-postal/adapter.ts +0 -118
- package/src/adapters/gnaf/adapter.ts +0 -148
- package/src/adapters/gnaf/assemble.ts +0 -226
- package/src/adapters/index.ts +0 -149
- package/src/adapters/openaddresses/adapter.ts +0 -250
- package/src/adapters/overture/adapter.ts +0 -161
- package/src/adapters/state-hi-schools/adapter.ts +0 -162
- package/src/adapters/state-ia-contractors/adapter.ts +0 -138
- package/src/adapters/state-ny-notaries/adapter.ts +0 -159
- package/src/adapters/state-tx-notaries/adapter.ts +0 -151
- package/src/adapters/synth-po-box/adapter.ts +0 -203
- package/src/adapters/tiger/adapter.ts +0 -252
- package/src/adapters/tiger/street-decompose.ts +0 -111
- package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -181
- package/src/adapters/usgov-imls-pls/adapter.ts +0 -138
- package/src/adapters/usgov-irs-bmf/adapter.ts +0 -161
- package/src/adapters/usgov-nad/adapter.ts +0 -347
- package/src/adapters/usgov-nppes/adapter.ts +0 -157
- package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -202
- package/src/adapters/utils/index.ts +0 -220
- package/src/adapters/wof-admin-jp/adapter.ts +0 -219
- package/src/adapters/wof-admin-json/adapter.ts +0 -294
- package/src/adapters/wof-postalcode-json/adapter.ts +0 -216
- package/src/build.ts +0 -386
- package/src/index.ts +0 -14
- package/src/name-prone-us-suffixes.ts +0 -12
- package/src/parquet-wrapper/index.ts +0 -9
- package/src/parquet-wrapper/reader.ts +0 -88
- package/src/parquet-wrapper/schema.ts +0 -88
- package/src/parquet-wrapper/writer.ts +0 -110
- package/src/runner.ts +0 -322
- package/src/shard-recipes/anchor-absorption.ts +0 -103
- package/src/shard-recipes/boundary-stress.ts +0 -104
- package/src/shard-recipes/country-balanced.ts +0 -522
- package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -92
- package/src/shard-recipes/fr-admin-split.ts +0 -237
- package/src/shard-recipes/fr-bare-street.ts +0 -95
- package/src/shard-recipes/fr-fragment.ts +0 -332
- package/src/shard-recipes/fr-lieudit.ts +0 -300
- package/src/shard-recipes/fr-order.ts +0 -256
- package/src/shard-recipes/german.ts +0 -169
- package/src/shard-recipes/house-venue.ts +0 -88
- package/src/shard-recipes/index.ts +0 -89
- package/src/shard-recipes/intersection.ts +0 -629
- package/src/shard-recipes/locale.ts +0 -601
- package/src/shard-recipes/nl-postcode.ts +0 -115
- package/src/shard-recipes/no-fragment.ts +0 -219
- package/src/shard-recipes/no-street-led.ts +0 -143
- package/src/shard-recipes/no-street.ts +0 -86
- package/src/shard-recipes/po-box-cedex.ts +0 -919
- package/src/shard-recipes/po-box.ts +0 -123
- package/src/shard-recipes/scaffold.ts +0 -329
- package/src/shard-recipes/si-bare-village.ts +0 -97
- package/src/shard-recipes/street-affix.ts +0 -825
- package/src/shard-recipes/street-bare.ts +0 -101
- package/src/shard-recipes/street.ts +0 -82
- package/src/shard-recipes/sub-venue-sources.ts +0 -895
- package/src/shard-recipes/sub-venue.ts +0 -982
- package/src/shard-recipes/unit.ts +0 -320
- package/src/synthesizers/anchor-absorption.ts +0 -290
- package/src/synthesizers/boundary-stress.ts +0 -531
- package/src/synthesizers/german.ts +0 -250
- package/src/synthesizers/house-venue.ts +0 -316
- package/src/synthesizers/intersection.ts +0 -232
- package/src/synthesizers/no-street.ts +0 -349
- package/src/synthesizers/po-box.ts +0 -339
- package/src/synthesizers/street.ts +0 -272
- package/src/synthesizers/utils.ts +0 -901
- package/src/tools/align-shard.ts +0 -69
- package/src/tools/audit.ts +0 -399
- package/src/tools/corpus-stats.ts +0 -184
- package/src/tools/fetch/ban.ts +0 -310
- package/src/tools/fetch/download.ts +0 -158
- package/src/tools/fetch/hrsa.ts +0 -68
- package/src/tools/fetch/imls-pls.ts +0 -158
- package/src/tools/fetch/index.ts +0 -136
- package/src/tools/fetch/nad.ts +0 -331
- package/src/tools/fetch/nppes.ts +0 -172
- package/src/tools/fetch/openaddresses.ts +0 -408
- package/src/tools/fetch/ourairports.ts +0 -166
- package/src/tools/fetch/ppd.ts +0 -137
- package/src/tools/fetch/state-hi-schools.ts +0 -228
- package/src/tools/fetch/state-sources.ts +0 -155
- package/src/tools/fetch/tiger-full.ts +0 -361
- package/src/tools/fetch/wikidata-subvenue.ts +0 -386
- package/src/tools/golden-expand.ts +0 -573
- package/src/tools/golden-promote.ts +0 -353
- package/src/tools/golden-relabel-street.ts +0 -685
- package/src/tools/index.ts +0 -28
- package/src/tools/ingest-csv.ts +0 -435
- package/src/tools/jsonl-to-parquet.ts +0 -221
- package/src/tools/lint-shard-vocab.ts +0 -409
- package/src/tools/lint-shard.ts +0 -543
- package/src/tools/overlay-manifest.ts +0 -145
- package/src/tools/overture-subvenue.ts +0 -215
- package/src/tools/shard-kryptonite.ts +0 -138
- package/src/tools/shard-translit.ts +0 -270
- package/src/tools/sub-venue-lexicon.ts +0 -1250
- package/src/tools/sub-venue-promotions.ts +0 -330
- package/src/types.ts +0 -247
- package/src/utils/align.ts +0 -330
- package/src/utils/golden.ts +0 -176
- package/src/utils/index.ts +0 -14
- package/src/utils/license.ts +0 -50
- package/src/utils/parquet.ts +0 -377
- package/src/utils/split.ts +0 -278
- package/src/utils/tokenize.ts +0 -78
- package/src/utils/wof-json.ts +0 -244
- /package/{src → lib}/codex/us-fips-state.ts +0 -0
- /package/{src → lib}/tools/gb-title-case.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/tiger/street-decompose.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.js +0 -0
- /package/out/{src/tools → tools}/gb-title-case.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.js +0 -0
- /package/out/{src/tools → tools}/golden-promote.d.ts +0 -0
- /package/out/{src/tools → tools}/ingest-csv.d.ts +0 -0
- /package/out/{src/types.js → types.js} +0 -0
- /package/out/{src/utils → utils}/license.d.ts +0 -0
|
@@ -1,123 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `po-box` shard recipe — synthetic PO box rows: tuples → {@link synthesizePoBoxRow} → aligned
|
|
7
|
-
* LabeledRow, plus optional self-contained US military/diplomatic rows (#517) at
|
|
8
|
-
* `--military-ratio`. Region is required EXCEPT region-less locales (NZ). Ported from
|
|
9
|
-
* scripts/build-po-box-shard.mjs.
|
|
10
|
-
*/
|
|
11
|
-
|
|
12
|
-
import {
|
|
13
|
-
synthesizeMilitaryPoBoxRow,
|
|
14
|
-
synthesizePoBoxRow,
|
|
15
|
-
type PoBoxBaseTuple,
|
|
16
|
-
} from "@mailwoman/corpus/synthesizers/po-box"
|
|
17
|
-
|
|
18
|
-
import { alignAndWrite, makeLcg, readTuples, shardSourceID, type ShardRecipe } from "./scaffold.ts"
|
|
19
|
-
|
|
20
|
-
const LICENSE = "Synthetic — derived from CC-BY / public-domain input tuples"
|
|
21
|
-
|
|
22
|
-
/**
|
|
23
|
-
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
24
|
-
* and `description` below for the surface form it generates.
|
|
25
|
-
*/
|
|
26
|
-
export const poBoxRecipe: ShardRecipe = {
|
|
27
|
-
name: "po-box",
|
|
28
|
-
description: "PO box rows: tuples → synthesizePoBoxRow (+ optional US military/diplomatic rows)",
|
|
29
|
-
mode: "tuples",
|
|
30
|
-
options: [
|
|
31
|
-
{ flag: "--pmb-ratio <p>", description: "P(private-mailbox layout). Default 0.15" },
|
|
32
|
-
{ flag: "--military-ratio <p>", description: "P(emit one US military/diplomatic row per input, #517). Default 0" },
|
|
33
|
-
],
|
|
34
|
-
async run(opts, write) {
|
|
35
|
-
if (!opts.input) throw new Error("po-box recipe requires --input <tuples.jsonl>")
|
|
36
|
-
const random = makeLcg(opts.seed)
|
|
37
|
-
const pmbRatio = opts.pmbRatio ?? 0.15
|
|
38
|
-
const militaryRatio = opts.militaryRatio ?? 0
|
|
39
|
-
let read = 0
|
|
40
|
-
let emitted = 0
|
|
41
|
-
let skipped = 0
|
|
42
|
-
|
|
43
|
-
for await (const tuple of readTuples(opts.input)) {
|
|
44
|
-
read++
|
|
45
|
-
// Region required EXCEPT region-less locales (NZ: "Private Bag 12, Auckland 1010", #517).
|
|
46
|
-
const regionOptional = ["NZ", "NZL", "NEW ZEALAND"].includes(String(tuple.country || "").toUpperCase())
|
|
47
|
-
|
|
48
|
-
if (!tuple.locality || !tuple.postcode || !tuple.country || (!tuple.region && !regionOptional)) {
|
|
49
|
-
skipped++
|
|
50
|
-
|
|
51
|
-
continue
|
|
52
|
-
}
|
|
53
|
-
|
|
54
|
-
for (let v = 0; v < opts.variants; v++) {
|
|
55
|
-
const synth = synthesizePoBoxRow(tuple as PoBoxBaseTuple, { random, pmbRatio })
|
|
56
|
-
|
|
57
|
-
if (!synth) continue
|
|
58
|
-
|
|
59
|
-
const ok = alignAndWrite(
|
|
60
|
-
write,
|
|
61
|
-
{
|
|
62
|
-
raw: synth.raw,
|
|
63
|
-
components: synth.components,
|
|
64
|
-
country: tuple.country,
|
|
65
|
-
locale: synth.locale,
|
|
66
|
-
source: "synth-po-box",
|
|
67
|
-
source_id: shardSourceID("synth-po-box", {
|
|
68
|
-
locality: tuple.locality,
|
|
69
|
-
region: tuple.region,
|
|
70
|
-
postcode: tuple.postcode,
|
|
71
|
-
country: tuple.country,
|
|
72
|
-
v: String(v),
|
|
73
|
-
}),
|
|
74
|
-
corpus_version: "0.4.0",
|
|
75
|
-
license: LICENSE,
|
|
76
|
-
},
|
|
77
|
-
synth.template
|
|
78
|
-
)
|
|
79
|
-
|
|
80
|
-
if (ok) {
|
|
81
|
-
emitted++
|
|
82
|
-
} else {
|
|
83
|
-
skipped++
|
|
84
|
-
}
|
|
85
|
-
}
|
|
86
|
-
|
|
87
|
-
// US military/diplomatic rows (#517): self-contained, one per input line at --military-ratio.
|
|
88
|
-
// Default 0 → byte-stable (random() not called when off). US-only.
|
|
89
|
-
if (militaryRatio > 0 && random() < militaryRatio) {
|
|
90
|
-
const mil = synthesizeMilitaryPoBoxRow({ random })
|
|
91
|
-
|
|
92
|
-
const ok = alignAndWrite(
|
|
93
|
-
write,
|
|
94
|
-
{
|
|
95
|
-
raw: mil.raw,
|
|
96
|
-
components: mil.components,
|
|
97
|
-
country: "US",
|
|
98
|
-
locale: mil.locale,
|
|
99
|
-
source: "synth-po-box",
|
|
100
|
-
source_id: shardSourceID("synth-po-box", {
|
|
101
|
-
po_box: mil.components.po_box,
|
|
102
|
-
locality: mil.components.locality,
|
|
103
|
-
region: mil.components.region,
|
|
104
|
-
postcode: mil.components.postcode,
|
|
105
|
-
v: `mil${emitted}`,
|
|
106
|
-
}),
|
|
107
|
-
corpus_version: "0.4.0",
|
|
108
|
-
license: LICENSE,
|
|
109
|
-
},
|
|
110
|
-
mil.template
|
|
111
|
-
)
|
|
112
|
-
|
|
113
|
-
if (ok) {
|
|
114
|
-
emitted++
|
|
115
|
-
} else {
|
|
116
|
-
skipped++
|
|
117
|
-
}
|
|
118
|
-
}
|
|
119
|
-
}
|
|
120
|
-
|
|
121
|
-
return { read, emitted, skipped }
|
|
122
|
-
},
|
|
123
|
-
}
|
|
@@ -1,329 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Shared scaffolding for the synthetic-corpus SHARD RECIPES — the common bits the 16
|
|
7
|
-
* `build-*-shard.mjs` scripts each re-implemented: the seeded LCG PRNG, the tuple reader, and the
|
|
8
|
-
* canonical → `alignRow` → `LabeledRow` JSONL emit step. A recipe ({@link ShardRecipe}) supplies
|
|
9
|
-
* only its synthesis + filter; the `mailwoman corpus shard <recipe>` command supplies the I/O.
|
|
10
|
-
*/
|
|
11
|
-
|
|
12
|
-
import { existsSync } from "node:fs"
|
|
13
|
-
|
|
14
|
-
import { readZipEntry } from "@mailwoman/core/fs/zip"
|
|
15
|
-
import { tryParsingJSON } from "@mailwoman/core/objects"
|
|
16
|
-
import { stableSourceID } from "@mailwoman/corpus/adapters/utils"
|
|
17
|
-
import { alignRow } from "@mailwoman/corpus/utils"
|
|
18
|
-
import type { PathBuilderLike } from "path-ts"
|
|
19
|
-
import type { AsyncChunkIterator, AsyncDataResource } from "spliterator"
|
|
20
|
-
import { AsyncSequence, CSVSpliterator } from "spliterator"
|
|
21
|
-
|
|
22
|
-
/**
|
|
23
|
-
* {@link stableSourceID}, but accepting arbitrary disambiguator keys (e.g. a variant index `v`) that aren't
|
|
24
|
-
* `ComponentTag`s. `stableSourceID` sorts + hashes EVERY key it's given, so passing extra keys is how the legacy
|
|
25
|
-
* builders kept per-variant ids unique — the strict typing is just too narrow for that. Centralizes the one cast.
|
|
26
|
-
*/
|
|
27
|
-
export function shardSourceID(adapterID: string, parts: Record<string, string | undefined>): string {
|
|
28
|
-
return stableSourceID(adapterID, parts as unknown as Parameters<typeof stableSourceID>[1])
|
|
29
|
-
}
|
|
30
|
-
|
|
31
|
-
/**
|
|
32
|
-
* A (locality, region, postcode, country) source tuple — the input to tuples-mode recipes.
|
|
33
|
-
*/
|
|
34
|
-
export interface ShardTuple {
|
|
35
|
-
locality?: string
|
|
36
|
-
region?: string
|
|
37
|
-
postcode?: string
|
|
38
|
-
country?: string
|
|
39
|
-
[k: string]: unknown
|
|
40
|
-
}
|
|
41
|
-
|
|
42
|
-
/**
|
|
43
|
-
* The two seeded generators the legacy `build-*-shard` scripts used, re-exported from their home in
|
|
44
|
-
* `@mailwoman/core/utils` so a recipe keeps importing everything it needs from this one scaffold module.
|
|
45
|
-
*
|
|
46
|
-
* - `makeLcg` (`s = s*1664525 + 1013904223 mod 2^32`) — what the street/po-box/anchor builders seeded.
|
|
47
|
-
* - `makeMulberry32` — what the MAJORITY of them used (german, locale, boundary-stress, unit, fr-order, country-balanced,
|
|
48
|
-
* intersection, fr-admin-split, street-affix, street-bare, po-box-cedex).
|
|
49
|
-
*
|
|
50
|
-
* A recipe must seed the same one its `.mjs` did, the same way it did (usually `seed`, but some derive a per-stream
|
|
51
|
-
* seed), or `--seed N` stops being byte-reproducible.
|
|
52
|
-
*/
|
|
53
|
-
export { makeLcg, mulberry32 as makeMulberry32, makeLcg as makeRandom } from "@mailwoman/core/utils"
|
|
54
|
-
|
|
55
|
-
/**
|
|
56
|
-
* One CSV record, keyed by its lower-cased header name, every value trimmed. A column the header does not declare reads
|
|
57
|
-
* as `undefined`; a column the header declares but this record does not reach reads as `""`.
|
|
58
|
-
*/
|
|
59
|
-
export type CSVRecord = Record<string, string | undefined>
|
|
60
|
-
|
|
61
|
-
/**
|
|
62
|
-
* Quote handling spans the ROW split, not only the column split: a newline inside a quoted field belongs to a single
|
|
63
|
-
* record, so the record boundaries can only be found by a scanner that already knows where the quotes are. Find the
|
|
64
|
-
* lines first and unquote afterwards and such a record splits in two — the first half short by however many columns
|
|
65
|
-
* followed the newline, which is how a `street` value comes to be read as `city`.
|
|
66
|
-
*
|
|
67
|
-
* `header: false` keeps the first record in the stream, so this module owns the lower-casing rather than
|
|
68
|
-
* `normalizeKeys` — see {@link toHeader}.
|
|
69
|
-
*/
|
|
70
|
-
const CSV_INIT = { header: false, enableQuoteHandling: true } as const
|
|
71
|
-
|
|
72
|
-
/**
|
|
73
|
-
* Header names are lower-cased on the way in. `normalizeKeys` will not do it: it leaves an ALL CAPS header alone, and
|
|
74
|
-
* OpenAddresses ships `LON,LAT,NUMBER,STREET` while other extracts ship the same names lower-case. A recipe names its
|
|
75
|
-
* columns in lower case either way.
|
|
76
|
-
*/
|
|
77
|
-
function toHeader(cells: readonly string[]): string[] {
|
|
78
|
-
return cells.map((name) => name.trim().toLowerCase())
|
|
79
|
-
}
|
|
80
|
-
|
|
81
|
-
/**
|
|
82
|
-
* Line breaks inside a value become single spaces. A quote-aware parse is the first thing here able to return a value
|
|
83
|
-
* CONTAINING one — `us/ia/statewide.csv` has 12, all unit designators like `"#2\n#2"` — and every consumer synthesizes
|
|
84
|
-
* one-line address text from these cells with no guard, because until that parse landed no value could carry one.
|
|
85
|
-
* Collapsing keeps the record (the address is fine; the source's line break is not part of it) without emitting a
|
|
86
|
-
* training row with a newline inside it.
|
|
87
|
-
*
|
|
88
|
-
* Only `\r` and `\n`, deliberately — NOT `\s`. Runs of spaces and tabs pass through exactly as the source wrote them
|
|
89
|
-
* (OA's IA extract writes `NORTH`, three spaces, `MAIN STREET`), because those could always appear and every shard
|
|
90
|
-
* built to date contains them. Widening this to `\s+` silently rewrites values on rows with no line break at all.
|
|
91
|
-
* `scaffold.test.ts` pins both halves, against both readers.
|
|
92
|
-
*/
|
|
93
|
-
function toRecord(header: readonly string[], cells: readonly string[]): CSVRecord {
|
|
94
|
-
const record: CSVRecord = {}
|
|
95
|
-
|
|
96
|
-
for (let i = 0; i < header.length; i++) {
|
|
97
|
-
record[header[i]!] = (cells[i] ?? "").replaceAll(/[\r\n]+/g, " ").trim()
|
|
98
|
-
}
|
|
99
|
-
|
|
100
|
-
return record
|
|
101
|
-
}
|
|
102
|
-
|
|
103
|
-
/**
|
|
104
|
-
* Read a CSV as header-keyed records.
|
|
105
|
-
*
|
|
106
|
-
* Returns the spliterator's own {@linkcode AsyncSequence}, so a caller composes `take`/`drop`/`filter` onto it — those
|
|
107
|
-
* ops fuse into one pull loop, and a `take` that is satisfied closes the source's file handle on the way out. Wrapping
|
|
108
|
-
* this in an `async function*` costs an async frame per row and takes those ops away; don't.
|
|
109
|
-
*
|
|
110
|
-
* A source at or below the spliterator's 128 KiB bulk threshold is read whole and parsed by the synchronous engine, so
|
|
111
|
-
* this is also the right reader for small sources — there is no buffered variant to reach for.
|
|
112
|
-
*/
|
|
113
|
-
export function readCSVRecords(source: AsyncDataResource | AsyncChunkIterator): AsyncSequence<CSVRecord> {
|
|
114
|
-
let header: string[] | null = null
|
|
115
|
-
|
|
116
|
-
return CSVSpliterator.fromAsync<string[]>(source, CSV_INIT)
|
|
117
|
-
.filter((cells) => {
|
|
118
|
-
if (header) return true
|
|
119
|
-
|
|
120
|
-
header = toHeader(cells)
|
|
121
|
-
|
|
122
|
-
return false
|
|
123
|
-
})
|
|
124
|
-
.map((cells) => toRecord(header!, cells))
|
|
125
|
-
}
|
|
126
|
-
|
|
127
|
-
/**
|
|
128
|
-
* {@link readCSVRecords} over one member of a zip archive — what every recipe reading a cached OA source wants.
|
|
129
|
-
*
|
|
130
|
-
* A source a checkout has not cached yields nothing, after saying so. A lab holds the archives for the countries it has
|
|
131
|
-
* built, so a recipe naming ten sources routinely finds three, and the `unzip -p` subprocesses these replaced behaved
|
|
132
|
-
* the same way by accident — a non-zero exit warned and returned no rows. A recipe that ends up with NO tuples at all
|
|
133
|
-
* still throws; that is the case where the cache, not the recipe, is the problem.
|
|
134
|
-
*/
|
|
135
|
-
export function readZippedCSVRecords(archivePath: PathBuilderLike, entryName: string): AsyncSequence<CSVRecord> {
|
|
136
|
-
if (!existsSync(String(archivePath))) {
|
|
137
|
-
console.error(` WARN: ${archivePath} is not cached — skipping ${entryName}`)
|
|
138
|
-
|
|
139
|
-
return AsyncSequence.from<CSVRecord>([])
|
|
140
|
-
}
|
|
141
|
-
|
|
142
|
-
return readCSVRecords(readZipEntry(archivePath, entryName))
|
|
143
|
-
}
|
|
144
|
-
|
|
145
|
-
/**
|
|
146
|
-
* Stream-parse a tuples JSONL file, yielding each parsed object (blank/invalid lines skipped).
|
|
147
|
-
*/
|
|
148
|
-
export async function* readTuples(input: string): AsyncGenerator<ShardTuple> {
|
|
149
|
-
// TextSpliterator (not JSONSpliterator) so a malformed line is SKIPPED, not thrown — the
|
|
150
|
-
// per-line tryParsingJSON below is the tolerance this reader has always had.
|
|
151
|
-
const { TextSpliterator } = await import("spliterator")
|
|
152
|
-
|
|
153
|
-
for await (const line of TextSpliterator.fromAsync(input)) {
|
|
154
|
-
const trimmed = line.trim()
|
|
155
|
-
|
|
156
|
-
if (!trimmed) continue
|
|
157
|
-
|
|
158
|
-
const tuple = tryParsingJSON<ShardTuple>(trimmed)
|
|
159
|
-
|
|
160
|
-
if (tuple !== null) {
|
|
161
|
-
yield tuple
|
|
162
|
-
}
|
|
163
|
-
}
|
|
164
|
-
}
|
|
165
|
-
|
|
166
|
-
/**
|
|
167
|
-
* A canonical row as the recipes assemble it, before `alignRow` turns it into a `LabeledRow`.
|
|
168
|
-
*/
|
|
169
|
-
export interface CanonicalShardRow {
|
|
170
|
-
raw: string
|
|
171
|
-
components: Record<string, string>
|
|
172
|
-
country: string
|
|
173
|
-
locale?: string
|
|
174
|
-
source: string
|
|
175
|
-
source_id: string
|
|
176
|
-
corpus_version?: string
|
|
177
|
-
license?: string
|
|
178
|
-
}
|
|
179
|
-
|
|
180
|
-
/**
|
|
181
|
-
* Run a canonical row through `alignRow` and, on success, write the `LabeledRow` (+ `synth_method` / `synth_base_id`)
|
|
182
|
-
* as one JSONL line. Returns true if emitted, false if alignment quarantined it.
|
|
183
|
-
*/
|
|
184
|
-
export function alignAndWrite(
|
|
185
|
-
write: (line: string) => void,
|
|
186
|
-
canonical: CanonicalShardRow,
|
|
187
|
-
synthMethod: string,
|
|
188
|
-
synthBaseID: string | null = null
|
|
189
|
-
): boolean {
|
|
190
|
-
const aligned = alignRow(canonical as Parameters<typeof alignRow>[0])
|
|
191
|
-
|
|
192
|
-
if (!aligned.row) return false
|
|
193
|
-
write(JSON.stringify({ ...aligned.row, synth_method: synthMethod, synth_base_id: synthBaseID }) + "\n")
|
|
194
|
-
|
|
195
|
-
return true
|
|
196
|
-
}
|
|
197
|
-
|
|
198
|
-
/**
|
|
199
|
-
* Parsed options a recipe's `run` receives. Common fields + the union of recipe-specific flags.
|
|
200
|
-
*/
|
|
201
|
-
export interface ShardRecipeOpts {
|
|
202
|
-
output: string
|
|
203
|
-
seed: number
|
|
204
|
-
variants: number
|
|
205
|
-
input?: string
|
|
206
|
-
count?: number
|
|
207
|
-
golden?: boolean
|
|
208
|
-
sourceName?: string
|
|
209
|
-
// recipe-specific (each recipe reads only what it needs):
|
|
210
|
-
houseNumberProb?: number
|
|
211
|
-
pmbRatio?: number
|
|
212
|
-
militaryRatio?: number
|
|
213
|
-
reversedFraction?: number
|
|
214
|
-
edgesDir?: string
|
|
215
|
-
country?: string
|
|
216
|
-
intlFraction?: number
|
|
217
|
-
/**
|
|
218
|
-
* `locale`: fraction of rows that append an explicit country surface form + a `country` component. Default 0.
|
|
219
|
-
*/
|
|
220
|
-
countryFraction?: number
|
|
221
|
-
/**
|
|
222
|
-
* `locale`: tri-state override of the per-part `districtAsLocality` mapping for this invocation. `undefined` (flag
|
|
223
|
-
* absent) leaves each `COUNTRY_SOURCES` part's own value untouched — every existing locale build stays
|
|
224
|
-
* byte-identical. `true`/`false` forces that value on every part read this run. ES's pedanía shard
|
|
225
|
-
* (`synth-es-pedania`) additionally uses `true` to select {@link LocaleCountrySource.pedaniaParts} instead of the
|
|
226
|
-
* default `parts` — see `locale.ts`.
|
|
227
|
-
*/
|
|
228
|
-
districtAsLocality?: boolean
|
|
229
|
-
bareProb?: number
|
|
230
|
-
hnProb?: number
|
|
231
|
-
communes?: string
|
|
232
|
-
/**
|
|
233
|
-
* `fr-lieudit`: BAN `adresses-<dept>.csv` directory. Default `$MAILWOMAN_DATA_ROOT/corpus/sources/ban`.
|
|
234
|
-
*/
|
|
235
|
-
banDir?: string
|
|
236
|
-
multilocaleCount?: number
|
|
237
|
-
/**
|
|
238
|
-
* `fr-fragment` / `no-fragment` / `no-street-led`: the eval board's reserved street-surface list. REQUIRED for those
|
|
239
|
-
* recipes — a shard that trains on its own eval set measures memorization. See their docstrings.
|
|
240
|
-
*/
|
|
241
|
-
excludeSurfaces?: string
|
|
242
|
-
/**
|
|
243
|
-
* `no-fragment`: share of rows that are counter-distribution (bare locality OR bare postcode).
|
|
244
|
-
*/
|
|
245
|
-
counterProb?: number
|
|
246
|
-
/**
|
|
247
|
-
* `no-fragment` knob 3: emit N copies of each street+number row whose number has >= longNumberMinDigits digits
|
|
248
|
-
* (oversample the failing long-number class). Default 1 = no boost.
|
|
249
|
-
*/
|
|
250
|
-
longNumberBoost?: number
|
|
251
|
-
/**
|
|
252
|
-
* `no-fragment` knob 3: minimum digit count for a number to count as "long" and be boosted. Default 3.
|
|
253
|
-
*/
|
|
254
|
-
longNumberMinDigits?: number
|
|
255
|
-
/**
|
|
256
|
-
* `sub-venue`: the sub-venue lexicon JSON. Default = the committed `corpus/data/sub-venue-lexicon.json`, resolved
|
|
257
|
-
* through the package manifest so it works from the source tree and from `out/`.
|
|
258
|
-
*/
|
|
259
|
-
lexicon?: string
|
|
260
|
-
/**
|
|
261
|
-
* `sub-venue`: directory of `sub-venue-extract` JSONLs, one per region. Default
|
|
262
|
-
* `$MAILWOMAN_DATA_ROOT/sub-venue/extracts`.
|
|
263
|
-
*/
|
|
264
|
-
extractsDir?: string
|
|
265
|
-
/**
|
|
266
|
-
* `sub-venue`: the `poi.db` spatial layer, read for the en-US and fr-FR venue + confound pools (the two of poi.db's
|
|
267
|
-
* four countries this shard has legs for). Default `$MAILWOMAN_DATA_ROOT/poi/poi.db`.
|
|
268
|
-
*/
|
|
269
|
-
poiDb?: string
|
|
270
|
-
/**
|
|
271
|
-
* `sub-venue`: GB/US/FR address-context tuples JSONL. Default the house-venue v3 tuples
|
|
272
|
-
* (`$MAILWOMAN_DATA_ROOT/corpus/intermediate/house-venue-tuples-v3.jsonl`); DE and ES read OpenAddresses directly.
|
|
273
|
-
*/
|
|
274
|
-
subVenueTuples?: string
|
|
275
|
-
/**
|
|
276
|
-
* `sub-venue`: share of emitted rows that are confound NEGATIVES. Default 0.3.
|
|
277
|
-
*/
|
|
278
|
-
negativeFraction?: number
|
|
279
|
-
}
|
|
280
|
-
|
|
281
|
-
/**
|
|
282
|
-
* Tally a recipe returns.
|
|
283
|
-
*/
|
|
284
|
-
export interface ShardStats {
|
|
285
|
-
read?: number
|
|
286
|
-
emitted: number
|
|
287
|
-
skipped: number
|
|
288
|
-
/**
|
|
289
|
-
* Rows dropped because their street SURFACE is reserved by an eval board (`--exclude-surfaces`). Separate from
|
|
290
|
-
* `skipped` on purpose: a nonzero value is the audit trail that the train/eval split actually fired. Zero when a
|
|
291
|
-
* recipe has no board split.
|
|
292
|
-
*/
|
|
293
|
-
contaminated?: number
|
|
294
|
-
}
|
|
295
|
-
|
|
296
|
-
/**
|
|
297
|
-
* A single declared recipe-specific option flag (for the command's --help).
|
|
298
|
-
*/
|
|
299
|
-
export interface ShardRecipeOption {
|
|
300
|
-
flag: string
|
|
301
|
-
description: string
|
|
302
|
-
}
|
|
303
|
-
|
|
304
|
-
/**
|
|
305
|
-
* A shard recipe: its identity, input mode, and its synthesis `run`.
|
|
306
|
-
*/
|
|
307
|
-
export interface ShardRecipe {
|
|
308
|
-
/**
|
|
309
|
-
* Recipe id, e.g. "street", "po-box" — the `<recipe>` positional.
|
|
310
|
-
*/
|
|
311
|
-
name: string
|
|
312
|
-
/**
|
|
313
|
-
* One-line description for `--list` / help.
|
|
314
|
-
*/
|
|
315
|
-
description: string
|
|
316
|
-
/**
|
|
317
|
-
* `tuples` reads `--input` JSONL; `generate` self-generates `--count` rows.
|
|
318
|
-
*/
|
|
319
|
-
mode: "tuples" | "generate"
|
|
320
|
-
/**
|
|
321
|
-
* Recipe-specific flags this recipe honors (documentation only).
|
|
322
|
-
*/
|
|
323
|
-
options?: ShardRecipeOption[]
|
|
324
|
-
/**
|
|
325
|
-
* Do the build: create the recipe's PRNG from `opts.seed` (its LEGACY generator — `makeLcg` or `makeMulberry32` — for
|
|
326
|
-
* byte-reproducibility), synthesize, and emit each row via `write`.
|
|
327
|
-
*/
|
|
328
|
-
run(opts: ShardRecipeOpts, write: (line: string) => void): Promise<ShardStats>
|
|
329
|
-
}
|
|
@@ -1,97 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `si-bare-village` — the Slovenian no-street counter-shard (#901 run-2). Slovenia's rural
|
|
7
|
-
* addressing has NO street line: the village name is the street-level token and repeats as the
|
|
8
|
-
* locality ("Zabiče 8, 6250 Zabiče"). The v1.9.8 gate FALSIFIED the fr-bare-street shard alone on
|
|
9
|
-
* exactly this class (SI resolve −3.4pp; "Apače 108" split into street "Apače 10" + house "8") —
|
|
10
|
-
* the bare-street boundary lesson generalizes onto a form where the leading name must keep its
|
|
11
|
-
* number whole and the trailing mention must stay locality-bound. This shard is the paired
|
|
12
|
-
* counter-distribution: same lesson ("name before number, comma, then admin"), opposite polarity
|
|
13
|
-
* on the trailing mention.
|
|
14
|
-
*
|
|
15
|
-
* Three real-order templates cycle per tuple (mirrors the coord-golden orders so the eval and the
|
|
16
|
-
* training distribution agree):
|
|
17
|
-
*
|
|
18
|
-
* 1. canonical "«V» «n», «pc» «V»"
|
|
19
|
-
* 2. bare "«V» «n», «V»" (no postcode — the anchor-free form, the fr-bare lesson)
|
|
20
|
-
* 3. pc-first "«pc» «V», «V» «n»"
|
|
21
|
-
*
|
|
22
|
-
* Gold spans: leading «V» = street (matches OA ground truth — the village IS the address line),
|
|
23
|
-
* «n» = house_number (NEVER split mid-digits), «pc» = postcode (never swallowing the neighbor),
|
|
24
|
-
* trailing «V» = locality (the binding the resolver needs).
|
|
25
|
-
*/
|
|
26
|
-
|
|
27
|
-
import { alignAndWrite, makeMulberry32, readTuples, type ShardRecipe, shardSourceID } from "./scaffold.ts"
|
|
28
|
-
|
|
29
|
-
/**
|
|
30
|
-
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
31
|
-
* and `description` below for the surface form it generates.
|
|
32
|
-
*/
|
|
33
|
-
export const siBareVillageRecipe: ShardRecipe = {
|
|
34
|
-
name: "si-bare-village",
|
|
35
|
-
description: "SI no-street village form (#901 run-2): '«V» «n», «pc» «V»' — the fr-bare-street counter-distribution",
|
|
36
|
-
mode: "tuples",
|
|
37
|
-
async run(opts, write) {
|
|
38
|
-
makeMulberry32(opts.seed)
|
|
39
|
-
let read = 0
|
|
40
|
-
let emitted = 0
|
|
41
|
-
let skipped = 0
|
|
42
|
-
|
|
43
|
-
for await (const t of readTuples(opts.input!)) {
|
|
44
|
-
read++
|
|
45
|
-
const village = String(t.locality ?? "").trim()
|
|
46
|
-
const number = String(t.number ?? "").trim()
|
|
47
|
-
const postcode = String(t.postcode ?? "").trim()
|
|
48
|
-
|
|
49
|
-
if (!village || !number || !postcode) {
|
|
50
|
-
skipped++
|
|
51
|
-
|
|
52
|
-
continue
|
|
53
|
-
}
|
|
54
|
-
|
|
55
|
-
const order = read % 3
|
|
56
|
-
let raw: string
|
|
57
|
-
|
|
58
|
-
const components: Record<string, string> = {
|
|
59
|
-
street: village,
|
|
60
|
-
house_number: number,
|
|
61
|
-
locality: village,
|
|
62
|
-
}
|
|
63
|
-
|
|
64
|
-
if (order === 0) {
|
|
65
|
-
components.postcode = postcode
|
|
66
|
-
raw = `${village} ${number}, ${postcode} ${village}`
|
|
67
|
-
} else if (order === 1) {
|
|
68
|
-
raw = `${village} ${number}, ${village}`
|
|
69
|
-
} else {
|
|
70
|
-
components.postcode = postcode
|
|
71
|
-
raw = `${postcode} ${village}, ${village} ${number}`
|
|
72
|
-
}
|
|
73
|
-
|
|
74
|
-
const source_id = shardSourceID("synth-si-bare-village", { ...components, o: String(order), v: String(read) })
|
|
75
|
-
|
|
76
|
-
const canonical = {
|
|
77
|
-
raw,
|
|
78
|
-
components,
|
|
79
|
-
country: "SI",
|
|
80
|
-
locale: "sl-SI",
|
|
81
|
-
source: "synth-si-bare-village",
|
|
82
|
-
source_id,
|
|
83
|
-
corpus_version: "0.9.9",
|
|
84
|
-
license:
|
|
85
|
-
"Synthetic — si-bare-village; (village, number, postcode) from OpenAddresses SI (per-source attribution in the model card)",
|
|
86
|
-
}
|
|
87
|
-
|
|
88
|
-
if (alignAndWrite(write, canonical, "si-bare-village")) {
|
|
89
|
-
emitted++
|
|
90
|
-
} else {
|
|
91
|
-
skipped++
|
|
92
|
-
}
|
|
93
|
-
}
|
|
94
|
-
|
|
95
|
-
return { read, emitted, skipped }
|
|
96
|
-
},
|
|
97
|
-
}
|