@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
|
@@ -1,258 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `fr-order` shard recipe — French reversed-order coverage (#560). Reads REAL OpenAddresses FR
|
|
7
|
-
* tuples (`fr/countrywide.csv` from the cached zip), then for each row picks — by
|
|
8
|
-
* `--reversed-fraction` (default 0.5) — whether to render in CANONICAL French order
|
|
9
|
-
* (number-street, postcode-city) or one of four REVERSED / postcode-first variants the
|
|
10
|
-
* v4.4.0→v0.5.0 regression exposed (the model misses house_number in every reversed one):
|
|
11
|
-
*
|
|
12
|
-
* - A: "47110 Sainte-Livrade-sur-Lot, 69 Allée du Bugatel" (postcode city, HN street)
|
|
13
|
-
* - B: "Sainte-Livrade-sur-Lot, 47110, 619 Impasse de la Rose" (city, postcode, HN street)
|
|
14
|
-
* - C: "Sainte-Livrade-sur-Lot 59 bis Rue des Ecuries 47110" (city HN street postcode — NO commas)
|
|
15
|
-
* - D: "47110, 6 rue de la république, Sainte-Livrade-sur-Lot" (postcode, HN street, city)
|
|
16
|
-
*
|
|
17
|
-
* Sub-modes ride alongside order: `bis`/`ter`/`quater` ordinal suffixes in house_number, and
|
|
18
|
-
* ALL-CAPS locality. `--golden` emits a held-out reversed-order eval slice with a different
|
|
19
|
-
* seed.
|
|
20
|
-
*
|
|
21
|
-
* The inline synthesis (the OA-CSV reader, the ordinal/all-caps tables, the canonical + reversed
|
|
22
|
-
* renderers) is ported faithfully from scripts/build-fr-order-shard.mjs. This is a
|
|
23
|
-
* `generate`-mode recipe that still reads REAL tuples off disk — `--count` bounds the OUTPUT, not
|
|
24
|
-
* the input. The passed `random` (the framework LCG) is consumed in the exact call order the
|
|
25
|
-
* legacy script used.
|
|
26
|
-
*
|
|
27
|
-
* NOT ported (diagnostic-only, no effect on emitted bytes): the post-run `runSpanCheck` self-check
|
|
28
|
-
* (it reads the finished file back with a separate PRNG and prints to stderr; the recipe's output
|
|
29
|
-
* stream is still open during `run`), and the dead `renderReversed` helper (the legacy `main`
|
|
30
|
-
* inlined the variant logic and never called it).
|
|
31
|
-
*/
|
|
32
|
-
|
|
33
|
-
import { isPresent } from "@mailwoman/core/objects"
|
|
34
|
-
import type { ComponentTag } from "@mailwoman/core/types"
|
|
35
|
-
import { dataRootPath } from "@mailwoman/core/utils"
|
|
36
|
-
|
|
37
|
-
import { stableSourceID } from "#adapters/utils"
|
|
38
|
-
import type { CanonicalRow } from "#types"
|
|
39
|
-
import { alignRow } from "#utils"
|
|
40
|
-
|
|
41
|
-
import { makeMulberry32, readZippedCSVRecords, type ShardRecipe } from "./scaffold.ts"
|
|
42
|
-
|
|
43
|
-
/* oxlint-disable sister-software/no-unnamed-threshold -- the bare decimals below are weighted-sampler
|
|
44
|
-
cutoffs, not thresholds: `const r = random()` followed by a cascade of `r < 0.4` branches IS the
|
|
45
|
-
output distribution, and reading the cascade top-to-bottom is how you see it. Naming each cutoff
|
|
46
|
-
would hide the distribution behind a wall of identifiers. Genuine thresholds in these files are
|
|
47
|
-
extracted as named constants above. */
|
|
48
|
-
|
|
49
|
-
const SOURCE = { zip: dataRootPath("oa-cache", "fr__countrywide.zip"), csv: "fr/countrywide.csv" }
|
|
50
|
-
|
|
51
|
-
/**
|
|
52
|
-
* Ordinal suffixes used in French house numbers (BAN corpus), to cover the "8 bis" sub-mode.
|
|
53
|
-
*/
|
|
54
|
-
const ORDINAL_SUFFIXES: readonly string[] = ["bis", "ter", "quater"]
|
|
55
|
-
/**
|
|
56
|
-
* Probability that a row gets an ordinal suffix injected (matches the golden's ~10-15% rate).
|
|
57
|
-
*/
|
|
58
|
-
const ORDINAL_PROB = 0.12
|
|
59
|
-
/**
|
|
60
|
-
* Probability that a locality renders ALL-CAPS (another sub-mode: "SAINTE-LIVRADE-SUR-LOT").
|
|
61
|
-
*/
|
|
62
|
-
const ALLCAPS_PROB = 0.1
|
|
63
|
-
|
|
64
|
-
/**
|
|
65
|
-
* A real FR tuple read out of the cached OA zip.
|
|
66
|
-
*/
|
|
67
|
-
interface FrTuple {
|
|
68
|
-
house_number: string
|
|
69
|
-
street: string
|
|
70
|
-
locality: string
|
|
71
|
-
postcode: string
|
|
72
|
-
}
|
|
73
|
-
|
|
74
|
-
/**
|
|
75
|
-
* Stream FR tuples out of the cached OA zip. The countrywide extract is GB-scale, so this reads only as far as `limit`
|
|
76
|
-
* distinct tuples — the `break` closes the reader and releases the archive. Only keeps rows with a house_number (the
|
|
77
|
-
* shard's core signal) and a postcode (required for reversed-order rendering to be meaningful).
|
|
78
|
-
*/
|
|
79
|
-
async function readTuples(limit: number): Promise<FrTuple[]> {
|
|
80
|
-
const tuples: FrTuple[] = []
|
|
81
|
-
const seen = new Set<string>()
|
|
82
|
-
|
|
83
|
-
for await (const row of readZippedCSVRecords(SOURCE.zip, SOURCE.csv)) {
|
|
84
|
-
if (tuples.length >= limit) break
|
|
85
|
-
const street = row.street ?? ""
|
|
86
|
-
const locality = row.city ?? ""
|
|
87
|
-
const house_number = row.number ?? ""
|
|
88
|
-
const postcode = row.postcode ?? ""
|
|
89
|
-
|
|
90
|
-
// Require all four fields: HN is the signal; postcode drives reversed-order variants.
|
|
91
|
-
if (!street || !locality || !house_number || !postcode) continue
|
|
92
|
-
const key = `${house_number}|${street}|${locality}|${postcode}`.toLowerCase()
|
|
93
|
-
|
|
94
|
-
if (seen.has(key)) continue
|
|
95
|
-
seen.add(key)
|
|
96
|
-
tuples.push({ house_number, street, locality, postcode })
|
|
97
|
-
}
|
|
98
|
-
|
|
99
|
-
return tuples
|
|
100
|
-
}
|
|
101
|
-
|
|
102
|
-
/**
|
|
103
|
-
* Optionally augment a house_number with a French ordinal suffix ("59 bis", "4 ter"). Appended with a space so it forms
|
|
104
|
-
* one multi-token house_number string that alignRow can still locate verbatim.
|
|
105
|
-
*/
|
|
106
|
-
function maybeAddOrdinal(random: () => number, house_number: string): string {
|
|
107
|
-
if (random() >= ORDINAL_PROB) return house_number
|
|
108
|
-
const suffix = ORDINAL_SUFFIXES[Math.floor(random() * ORDINAL_SUFFIXES.length)]!
|
|
109
|
-
|
|
110
|
-
// Vary suffix case: "bis" (lower) vs "BIS" (upper) — a real-world split in the golden.
|
|
111
|
-
return `${house_number} ${random() < 0.5 ? suffix : suffix.toUpperCase()}`
|
|
112
|
-
}
|
|
113
|
-
|
|
114
|
-
/**
|
|
115
|
-
* Render a tuple in CANONICAL French order: "9 Rue de la Promenade, 01200 Villes".
|
|
116
|
-
*/
|
|
117
|
-
function renderCanonical(
|
|
118
|
-
hn: string,
|
|
119
|
-
street: string,
|
|
120
|
-
postcode: string,
|
|
121
|
-
locality: string
|
|
122
|
-
): { raw: string; components: Partial<Record<ComponentTag, string>> } {
|
|
123
|
-
const raw = `${hn} ${street}, ${postcode} ${locality}`
|
|
124
|
-
|
|
125
|
-
return { raw, components: { house_number: hn, street, postcode, locality } }
|
|
126
|
-
}
|
|
127
|
-
|
|
128
|
-
/**
|
|
129
|
-
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
130
|
-
* and `description` below for the surface form it generates.
|
|
131
|
-
*/
|
|
132
|
-
export const frOrderRecipe: ShardRecipe = {
|
|
133
|
-
name: "fr-order",
|
|
134
|
-
description: "French reversed-order rows (#560): real OA FR tuples rendered canonical + 4 postcode-first variants",
|
|
135
|
-
mode: "generate",
|
|
136
|
-
options: [
|
|
137
|
-
{ flag: "--reversed-fraction <p>", description: "Fraction rendered reversed-order. Default 0.5" },
|
|
138
|
-
{ flag: "--golden", description: "Emit the held-out reversed-order eval slice" },
|
|
139
|
-
],
|
|
140
|
-
async run(opts, write) {
|
|
141
|
-
if (opts.count == null) throw new Error("fr-order recipe requires --count <N>")
|
|
142
|
-
const count = opts.count
|
|
143
|
-
// Legacy build-fr-order-shard.mjs seeded mulberry32 with the raw seed: `const random = mulberry32(opts.seed)`.
|
|
144
|
-
// (The omitted diagnostic runSpanCheck used a separate mulberry32(opts.seed + 1) — not part of generation.)
|
|
145
|
-
const random = makeMulberry32(opts.seed)
|
|
146
|
-
const source = opts.sourceName ?? "synth-fr-order"
|
|
147
|
-
const reversedFraction = opts.reversedFraction ?? 0.5
|
|
148
|
-
|
|
149
|
-
// Over-read from the CSV so the dedup + filter pass can fill `count` rows.
|
|
150
|
-
const poolLimit = Math.max(count * 8, 40_000)
|
|
151
|
-
const pool = await readTuples(poolLimit)
|
|
152
|
-
|
|
153
|
-
console.error(` ${SOURCE.csv}: ${pool.length} unique tuples (capped read)`)
|
|
154
|
-
|
|
155
|
-
if (!pool.length) {
|
|
156
|
-
throw new Error(`No FR tuples found — is ${SOURCE.zip} present?`)
|
|
157
|
-
}
|
|
158
|
-
|
|
159
|
-
let emitted = 0
|
|
160
|
-
let skipped = 0
|
|
161
|
-
let guard = 0
|
|
162
|
-
const N = pool.length
|
|
163
|
-
|
|
164
|
-
while (emitted < count && guard++ < count * 10) {
|
|
165
|
-
const base = pool[Math.floor(random() * N)]!
|
|
166
|
-
const { street, postcode } = base
|
|
167
|
-
const locality = random() < ALLCAPS_PROB ? base.locality.toUpperCase() : base.locality
|
|
168
|
-
const house_number = maybeAddOrdinal(random, base.house_number)
|
|
169
|
-
|
|
170
|
-
// Pick canonical vs reversed by --reversed-fraction.
|
|
171
|
-
const isReversed = random() < reversedFraction
|
|
172
|
-
|
|
173
|
-
let rendered: { raw: string; components: Partial<Record<ComponentTag, string>> }
|
|
174
|
-
|
|
175
|
-
if (isReversed) {
|
|
176
|
-
const variantRoll = random()
|
|
177
|
-
let raw: string
|
|
178
|
-
|
|
179
|
-
if (variantRoll < 0.25) {
|
|
180
|
-
// Variant A: postcode+city as a unit, then HN+street
|
|
181
|
-
raw = `${postcode} ${locality}, ${house_number} ${street}`
|
|
182
|
-
} else if (variantRoll < 0.5) {
|
|
183
|
-
// Variant B: city, then postcode, then HN+street (comma-separated, postcode isolated)
|
|
184
|
-
raw = `${locality}, ${postcode}, ${house_number} ${street}`
|
|
185
|
-
} else if (variantRoll < 0.75) {
|
|
186
|
-
// Variant C: no commas — locality HN street postcode (the "run-together" format)
|
|
187
|
-
raw = `${locality} ${house_number} ${street} ${postcode}`
|
|
188
|
-
} else {
|
|
189
|
-
// Variant D: postcode, HN+street, city (reversed top-to-bottom)
|
|
190
|
-
raw = `${postcode}, ${house_number} ${street}, ${locality}`
|
|
191
|
-
}
|
|
192
|
-
|
|
193
|
-
rendered = { raw, components: { house_number, street, postcode, locality } }
|
|
194
|
-
} else {
|
|
195
|
-
rendered = renderCanonical(house_number, street, postcode, locality)
|
|
196
|
-
}
|
|
197
|
-
|
|
198
|
-
const { raw, components } = rendered
|
|
199
|
-
|
|
200
|
-
// Safety check: every component must appear verbatim in raw (alignment precondition).
|
|
201
|
-
const componentValues = Object.values(components).filter(isPresent)
|
|
202
|
-
|
|
203
|
-
if (!componentValues.every((v) => raw.includes(v))) {
|
|
204
|
-
skipped++
|
|
205
|
-
|
|
206
|
-
continue
|
|
207
|
-
}
|
|
208
|
-
|
|
209
|
-
// --golden: emit per-locale-f1 eval rows ({raw, components, country:"FR"}).
|
|
210
|
-
if (opts.golden) {
|
|
211
|
-
write(JSON.stringify({ raw, components, country: "FR" }) + "\n")
|
|
212
|
-
|
|
213
|
-
emitted++
|
|
214
|
-
|
|
215
|
-
continue
|
|
216
|
-
}
|
|
217
|
-
|
|
218
|
-
const sourceID = stableSourceID(source, {
|
|
219
|
-
street: components.street,
|
|
220
|
-
house_number: components.house_number,
|
|
221
|
-
locality: components.locality,
|
|
222
|
-
postcode: components.postcode,
|
|
223
|
-
})
|
|
224
|
-
|
|
225
|
-
const canonical: CanonicalRow = {
|
|
226
|
-
raw,
|
|
227
|
-
components,
|
|
228
|
-
country: "FR",
|
|
229
|
-
locale: "fr-FR",
|
|
230
|
-
source,
|
|
231
|
-
source_id: sourceID,
|
|
232
|
-
corpus_version: "0.5.0",
|
|
233
|
-
license: "OpenAddresses FR countrywide tuples, rendered canonical + reversed-order — see ingest SOURCE",
|
|
234
|
-
}
|
|
235
|
-
|
|
236
|
-
const aligned = alignRow(canonical)
|
|
237
|
-
|
|
238
|
-
if (aligned.kind !== "labeled" || !aligned.row) {
|
|
239
|
-
skipped++
|
|
240
|
-
|
|
241
|
-
continue
|
|
242
|
-
}
|
|
243
|
-
|
|
244
|
-
write(
|
|
245
|
-
JSON.stringify({
|
|
246
|
-
...aligned.row,
|
|
247
|
-
synth_method: "fr-order",
|
|
248
|
-
synth_order: isReversed ? "reversed" : "canonical",
|
|
249
|
-
synth_base_id: null,
|
|
250
|
-
}) + "\n"
|
|
251
|
-
)
|
|
252
|
-
|
|
253
|
-
emitted++
|
|
254
|
-
}
|
|
255
|
-
|
|
256
|
-
return { emitted, skipped }
|
|
257
|
-
},
|
|
258
|
-
}
|
|
@@ -1,170 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `german` shard recipe — German coverage rows from REAL OpenAddresses tuples (Berlin + Saxony,
|
|
7
|
-
* cached zips). Each sampled tuple is rendered via {@link synthesizeGermanRow} in BOTH orders —
|
|
8
|
-
* `--intl-fraction` (default 0.4) in international order (house-first / postcode-after-city), the
|
|
9
|
-
* rest in idiomatic German order — then aligned to BIO. Generate-mode: it builds a tuple pool
|
|
10
|
-
* from the cached zips, then draws `--count` rows from it with the passed `random` (so the emit
|
|
11
|
-
* stream matches the legacy reservoir-sample loop). Ported from scripts/build-german-shard.mjs.
|
|
12
|
-
*
|
|
13
|
-
* ORDER ROBUSTNESS (2026-06-06): mixing the two renderings stops a native-only shard from teaching
|
|
14
|
-
* German order so well it reads the US/feed-order eval as a "collapse". See
|
|
15
|
-
* docs/articles/evals/resolver-geo/2026-06-06-anchor-pilot.md (the order-artifact correction).
|
|
16
|
-
*/
|
|
17
|
-
|
|
18
|
-
import { dataRootPath } from "@mailwoman/core/utils"
|
|
19
|
-
|
|
20
|
-
import { stableSourceID } from "#adapters/utils"
|
|
21
|
-
import { synthesizeGermanRow, type LocaleBaseTuple } from "#synthesizers/german"
|
|
22
|
-
import { alignRow } from "#utils"
|
|
23
|
-
|
|
24
|
-
import { makeMulberry32, readZippedCSVRecords, type ShardRecipe } from "./scaffold.ts"
|
|
25
|
-
|
|
26
|
-
/**
|
|
27
|
-
* A German OA source (cached zip) + the Bundesland the file covers (OA's REGION column is empty for DE).
|
|
28
|
-
*/
|
|
29
|
-
interface GermanSource {
|
|
30
|
-
zip: string
|
|
31
|
-
csv: string
|
|
32
|
-
region: string
|
|
33
|
-
}
|
|
34
|
-
|
|
35
|
-
/**
|
|
36
|
-
* `region` is the Bundesland the source covers. OA's REGION column is empty for DE, but the region is implied by the
|
|
37
|
-
* per-state file — the international order needs it for the "City, Region Postcode" tail (v0.9.3 / #327). berlin.csv →
|
|
38
|
-
* Berlin (a city-state, region==locality); sn/statewide → Sachsen.
|
|
39
|
-
*/
|
|
40
|
-
const SOURCES: GermanSource[] = [
|
|
41
|
-
{ zip: dataRootPath("oa-cache", "de__berlin.zip"), csv: "de/berlin.csv", region: "Berlin" },
|
|
42
|
-
{ zip: dataRootPath("oa-cache", "de__sn__statewide.zip"), csv: "de/sn/statewide.csv", region: "Sachsen" },
|
|
43
|
-
]
|
|
44
|
-
|
|
45
|
-
/**
|
|
46
|
-
* Stream real German tuples out of a cached OA zip.
|
|
47
|
-
*/
|
|
48
|
-
async function readGermanTuples(source: GermanSource): Promise<LocaleBaseTuple[]> {
|
|
49
|
-
const tuples: LocaleBaseTuple[] = []
|
|
50
|
-
const seen = new Set<string>()
|
|
51
|
-
|
|
52
|
-
for await (const row of readZippedCSVRecords(source.zip, source.csv)) {
|
|
53
|
-
const street = row.street ?? ""
|
|
54
|
-
const locality = row.city ?? ""
|
|
55
|
-
|
|
56
|
-
if (!street || !locality) continue
|
|
57
|
-
const house_number = row.number ?? ""
|
|
58
|
-
const postcode = row.postcode ?? ""
|
|
59
|
-
// OA's REGION column is empty for DE — fall back to the source's Bundesland (set per file).
|
|
60
|
-
const region = row.region || source.region || ""
|
|
61
|
-
const key = `${house_number}|${street}|${locality}|${postcode}`.toLowerCase()
|
|
62
|
-
|
|
63
|
-
if (seen.has(key)) continue
|
|
64
|
-
seen.add(key)
|
|
65
|
-
tuples.push({ house_number, street, locality, region, postcode })
|
|
66
|
-
}
|
|
67
|
-
|
|
68
|
-
return tuples
|
|
69
|
-
}
|
|
70
|
-
|
|
71
|
-
/**
|
|
72
|
-
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
73
|
-
* and `description` below for the surface form it generates.
|
|
74
|
-
*/
|
|
75
|
-
export const germanRecipe: ShardRecipe = {
|
|
76
|
-
name: "german",
|
|
77
|
-
description: "German coverage rows from real OA tuples (Berlin/Saxony), both orders → synthesizeGermanRow",
|
|
78
|
-
mode: "generate",
|
|
79
|
-
options: [{ flag: "--intl-fraction <f>", description: "Fraction rendered international order. Default 0.4" }],
|
|
80
|
-
async run(opts, write) {
|
|
81
|
-
// Emit PRNG: the legacy build-german-shard.mjs seeded mulberry32(opts.seed).
|
|
82
|
-
const random = makeMulberry32(opts.seed)
|
|
83
|
-
const source = opts.sourceName ?? "synth-german"
|
|
84
|
-
const intlFraction = opts.intlFraction ?? 0.4
|
|
85
|
-
|
|
86
|
-
if (!(intlFraction >= 0 && intlFraction <= 1)) {
|
|
87
|
-
throw new Error(`--intl-fraction must be in [0, 1], got ${intlFraction}`)
|
|
88
|
-
}
|
|
89
|
-
|
|
90
|
-
const count = opts.count ?? 4000
|
|
91
|
-
|
|
92
|
-
// Pool real tuples from every German source, then sample `count` rows from it.
|
|
93
|
-
const pool: LocaleBaseTuple[] = []
|
|
94
|
-
|
|
95
|
-
for (const s of SOURCES) {
|
|
96
|
-
const t = await readGermanTuples(s)
|
|
97
|
-
|
|
98
|
-
console.error(` ${s.csv}: ${t.length} unique tuples`)
|
|
99
|
-
|
|
100
|
-
for (const x of t) {
|
|
101
|
-
pool.push(x)
|
|
102
|
-
} // NOT pool.push(...t) — spreading ~840K args overflows the stack
|
|
103
|
-
}
|
|
104
|
-
|
|
105
|
-
if (!pool.length) {
|
|
106
|
-
throw new Error(`No German tuples found — are the cached zips present in ${dataRootPath("oa-cache")}?`)
|
|
107
|
-
}
|
|
108
|
-
|
|
109
|
-
let emitted = 0
|
|
110
|
-
let skipped = 0
|
|
111
|
-
let guard = 0
|
|
112
|
-
const N = pool.length
|
|
113
|
-
|
|
114
|
-
while (emitted < count && guard++ < count * 6) {
|
|
115
|
-
const base = pool[Math.floor(random() * N)]!
|
|
116
|
-
// Per-row order: `--intl-fraction` of rows render house-first / postcode-after-city (the US/feed
|
|
117
|
-
// layout), the rest in idiomatic German order. Same components either way.
|
|
118
|
-
const order = random() < intlFraction ? "international" : "native"
|
|
119
|
-
const synth = synthesizeGermanRow(base, { random, order })
|
|
120
|
-
|
|
121
|
-
if (!synth) {
|
|
122
|
-
skipped++
|
|
123
|
-
|
|
124
|
-
continue
|
|
125
|
-
}
|
|
126
|
-
|
|
127
|
-
// --golden: emit per-locale-f1 eval rows ({raw, components}) instead of aligned BIO. `order`
|
|
128
|
-
// rides along so the eval can stratify native vs international.
|
|
129
|
-
if (opts.golden) {
|
|
130
|
-
write(JSON.stringify({ raw: synth.raw, components: synth.components, country: "DE", order }) + "\n")
|
|
131
|
-
|
|
132
|
-
emitted++
|
|
133
|
-
|
|
134
|
-
continue
|
|
135
|
-
}
|
|
136
|
-
|
|
137
|
-
const sourceID = stableSourceID(source, {
|
|
138
|
-
street: synth.components.street,
|
|
139
|
-
house_number: synth.components.house_number,
|
|
140
|
-
locality: synth.components.locality,
|
|
141
|
-
postcode: synth.components.postcode,
|
|
142
|
-
})
|
|
143
|
-
|
|
144
|
-
const canonical = {
|
|
145
|
-
raw: synth.raw,
|
|
146
|
-
components: synth.components,
|
|
147
|
-
country: "DE",
|
|
148
|
-
locale: synth.locale,
|
|
149
|
-
source,
|
|
150
|
-
source_id: sourceID,
|
|
151
|
-
corpus_version: "0.4.0",
|
|
152
|
-
license: `OpenAddresses DE (Berlin/Saxony) tuples, rendered ${order}-order — see ingest SOURCES`,
|
|
153
|
-
}
|
|
154
|
-
|
|
155
|
-
const aligned = alignRow(canonical as Parameters<typeof alignRow>[0])
|
|
156
|
-
|
|
157
|
-
if (aligned.kind !== "labeled" || !aligned.row) {
|
|
158
|
-
skipped++
|
|
159
|
-
|
|
160
|
-
continue
|
|
161
|
-
}
|
|
162
|
-
|
|
163
|
-
write(JSON.stringify({ ...aligned.row, synth_method: "german", synth_order: order, synth_base_id: null }) + "\n")
|
|
164
|
-
|
|
165
|
-
emitted++
|
|
166
|
-
}
|
|
167
|
-
|
|
168
|
-
return { emitted, skipped }
|
|
169
|
-
},
|
|
170
|
-
}
|
|
@@ -1,88 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `house-venue` shard recipe — synthetic house_number+venue+street co-occurrence rows: tuples →
|
|
7
|
-
* {@link synthesizeHouseVenueRow} → aligned LabeledRow. The v0.6.3 corrective companion to the
|
|
8
|
-
* no-street shard: every row carries BOTH house_number AND venue, restoring the house_number
|
|
9
|
-
* signal that no-street's distributional shift cost the model. Ported from
|
|
10
|
-
* scripts/build-house-venue-shard.mjs.
|
|
11
|
-
*/
|
|
12
|
-
|
|
13
|
-
import { synthesizeHouseVenueRow, type HouseVenueBaseTuple } from "#synthesizers/house-venue"
|
|
14
|
-
|
|
15
|
-
import { alignAndWrite, makeLcg, readTuples, shardSourceID, type ShardRecipe } from "./scaffold.ts"
|
|
16
|
-
|
|
17
|
-
const LICENSE = "Synthetic — derived from CC-BY / public-domain input tuples"
|
|
18
|
-
|
|
19
|
-
/**
|
|
20
|
-
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
21
|
-
* and `description` below for the surface form it generates.
|
|
22
|
-
*/
|
|
23
|
-
export const houseVenueRecipe: ShardRecipe = {
|
|
24
|
-
name: "house-venue",
|
|
25
|
-
description: "House_number+venue co-occurrence rows: tuples → synthesizeHouseVenueRow → aligned LabeledRow",
|
|
26
|
-
mode: "tuples",
|
|
27
|
-
async run(opts, write) {
|
|
28
|
-
if (!opts.input) throw new Error("house-venue recipe requires --input <tuples.jsonl>")
|
|
29
|
-
// Legacy build-house-venue-shard.mjs seeded the LCG via makeRandom(opts.seed) (s = seed).
|
|
30
|
-
const random = makeLcg(opts.seed)
|
|
31
|
-
const source = opts.sourceName ?? "synth-house-venue"
|
|
32
|
-
let read = 0
|
|
33
|
-
let emitted = 0
|
|
34
|
-
let skipped = 0
|
|
35
|
-
|
|
36
|
-
for await (const tuple of readTuples(opts.input)) {
|
|
37
|
-
read++
|
|
38
|
-
|
|
39
|
-
// FR renders without a region (postcode-before-locality tail — the run-2 contingency), so
|
|
40
|
-
// an empty region is valid there and stays required everywhere else.
|
|
41
|
-
if (!tuple.locality || !tuple.postcode || !tuple.country || (!tuple.region && tuple.country !== "FR")) {
|
|
42
|
-
skipped++
|
|
43
|
-
|
|
44
|
-
continue
|
|
45
|
-
}
|
|
46
|
-
|
|
47
|
-
for (let v = 0; v < opts.variants; v++) {
|
|
48
|
-
const synth = synthesizeHouseVenueRow(tuple as HouseVenueBaseTuple, { random })
|
|
49
|
-
|
|
50
|
-
if (!synth) {
|
|
51
|
-
skipped++
|
|
52
|
-
|
|
53
|
-
continue
|
|
54
|
-
}
|
|
55
|
-
|
|
56
|
-
const ok = alignAndWrite(
|
|
57
|
-
write,
|
|
58
|
-
{
|
|
59
|
-
raw: synth.raw,
|
|
60
|
-
components: synth.components,
|
|
61
|
-
country: tuple.country,
|
|
62
|
-
locale: synth.locale,
|
|
63
|
-
source,
|
|
64
|
-
source_id: shardSourceID(source, {
|
|
65
|
-
locality: tuple.locality,
|
|
66
|
-
region: tuple.region,
|
|
67
|
-
postcode: tuple.postcode,
|
|
68
|
-
country: tuple.country,
|
|
69
|
-
template: synth.template,
|
|
70
|
-
v: String(v),
|
|
71
|
-
}),
|
|
72
|
-
corpus_version: "0.4.0",
|
|
73
|
-
license: LICENSE,
|
|
74
|
-
},
|
|
75
|
-
synth.template
|
|
76
|
-
)
|
|
77
|
-
|
|
78
|
-
if (ok) {
|
|
79
|
-
emitted++
|
|
80
|
-
} else {
|
|
81
|
-
skipped++
|
|
82
|
-
}
|
|
83
|
-
}
|
|
84
|
-
}
|
|
85
|
-
|
|
86
|
-
return { read, emitted, skipped }
|
|
87
|
-
},
|
|
88
|
-
}
|
|
@@ -1,95 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* The synthetic-corpus SHARD RECIPE registry. Each recipe ({@link ShardRecipe}) is what one legacy
|
|
7
|
-
* `build-*-shard.mjs` script used to be; the `mailwoman corpus shard <recipe>` command dispatches
|
|
8
|
-
* to them. A new shard is a new entry here, not a new script.
|
|
9
|
-
*/
|
|
10
|
-
|
|
11
|
-
import { anchorAbsorptionRecipe } from "./anchor-absorption.ts"
|
|
12
|
-
import { bareCountryRecipe } from "./bare-country.ts"
|
|
13
|
-
import { boundaryStressRecipe } from "./boundary-stress.ts"
|
|
14
|
-
import { countryBalancedRecipe } from "./country-balanced.ts"
|
|
15
|
-
import { czPcFirstPrepositionRecipe } from "./cz-pcfirst-preposition.ts"
|
|
16
|
-
import { frAdminSplitRecipe } from "./fr-admin-split.ts"
|
|
17
|
-
import { frBareStreetRecipe } from "./fr-bare-street.ts"
|
|
18
|
-
import { frFragmentRecipe } from "./fr-fragment.ts"
|
|
19
|
-
import { frLieuditRecipe } from "./fr-lieudit.ts"
|
|
20
|
-
import { frOrderRecipe } from "./fr-order.ts"
|
|
21
|
-
import { germanRecipe } from "./german.ts"
|
|
22
|
-
import { houseVenueRecipe } from "./house-venue.ts"
|
|
23
|
-
import { intersectionRecipe } from "./intersection.ts"
|
|
24
|
-
import { localeRecipe } from "./locale.ts"
|
|
25
|
-
import { nlPostcodeRecipe } from "./nl-postcode.ts"
|
|
26
|
-
import { noFragmentRecipe } from "./no-fragment.ts"
|
|
27
|
-
import { noStreetLedRecipe } from "./no-street-led.ts"
|
|
28
|
-
import { noStreetRecipe } from "./no-street.ts"
|
|
29
|
-
import { poBoxCedexRecipe } from "./po-box-cedex.ts"
|
|
30
|
-
import { poBoxRecipe } from "./po-box.ts"
|
|
31
|
-
import { reviewedPostcodeTailRecipe } from "./reviewed-postcode-tail.ts"
|
|
32
|
-
import type { ShardRecipe } from "./scaffold.ts"
|
|
33
|
-
import { siBareVillageRecipe } from "./si-bare-village.ts"
|
|
34
|
-
import { streetAffixRecipe, suffixBoundaryRecipe } from "./street-affix.ts"
|
|
35
|
-
import { streetBareRecipe } from "./street-bare.ts"
|
|
36
|
-
import { streetRecipe } from "./street.ts"
|
|
37
|
-
import { subVenueRecipe } from "./sub-venue.ts"
|
|
38
|
-
import { trailingRegionRecipe } from "./trailing-region.ts"
|
|
39
|
-
import { unitRecipe } from "./unit.ts"
|
|
40
|
-
|
|
41
|
-
export * from "./scaffold.ts"
|
|
42
|
-
|
|
43
|
-
/**
|
|
44
|
-
* Every registered recipe, in display order.
|
|
45
|
-
*/
|
|
46
|
-
const RECIPES: readonly ShardRecipe[] = [
|
|
47
|
-
bareCountryRecipe,
|
|
48
|
-
trailingRegionRecipe,
|
|
49
|
-
reviewedPostcodeTailRecipe,
|
|
50
|
-
streetRecipe,
|
|
51
|
-
streetBareRecipe,
|
|
52
|
-
streetAffixRecipe,
|
|
53
|
-
suffixBoundaryRecipe,
|
|
54
|
-
noStreetRecipe,
|
|
55
|
-
houseVenueRecipe,
|
|
56
|
-
poBoxRecipe,
|
|
57
|
-
poBoxCedexRecipe,
|
|
58
|
-
unitRecipe,
|
|
59
|
-
intersectionRecipe,
|
|
60
|
-
germanRecipe,
|
|
61
|
-
localeRecipe,
|
|
62
|
-
frOrderRecipe,
|
|
63
|
-
frAdminSplitRecipe,
|
|
64
|
-
frBareStreetRecipe,
|
|
65
|
-
frFragmentRecipe,
|
|
66
|
-
frLieuditRecipe,
|
|
67
|
-
czPcFirstPrepositionRecipe,
|
|
68
|
-
nlPostcodeRecipe,
|
|
69
|
-
noStreetLedRecipe,
|
|
70
|
-
noFragmentRecipe,
|
|
71
|
-
siBareVillageRecipe,
|
|
72
|
-
countryBalancedRecipe,
|
|
73
|
-
boundaryStressRecipe,
|
|
74
|
-
anchorAbsorptionRecipe,
|
|
75
|
-
subVenueRecipe,
|
|
76
|
-
]
|
|
77
|
-
|
|
78
|
-
/**
|
|
79
|
-
* Recipe name → recipe.
|
|
80
|
-
*/
|
|
81
|
-
export const SHARD_RECIPES: ReadonlyMap<string, ShardRecipe> = new Map(RECIPES.map((r) => [r.name, r]))
|
|
82
|
-
|
|
83
|
-
/**
|
|
84
|
-
* Look up a recipe by its `<recipe>` name.
|
|
85
|
-
*/
|
|
86
|
-
export function getShardRecipe(name: string): ShardRecipe | undefined {
|
|
87
|
-
return SHARD_RECIPES.get(name)
|
|
88
|
-
}
|
|
89
|
-
|
|
90
|
-
/**
|
|
91
|
-
* All recipes (for `--list` / help).
|
|
92
|
-
*/
|
|
93
|
-
export function listShardRecipes(): readonly ShardRecipe[] {
|
|
94
|
-
return RECIPES
|
|
95
|
-
}
|