@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
|
@@ -1,406 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `country-balanced` shard recipe — the BALANCED, MODEL-FIRST country-coverage shard (#464). The
|
|
7
|
-
* shipped model is STARVED on `country` (P=R=F1=0 on the homograph eval), so this fills the void
|
|
8
|
-
* the way the `unit` shard did, but built to AVOID over-firing "trailing token ⇒ country". Three
|
|
9
|
-
* ingredients, ported faithfully from scripts/build-country-shard-balanced.mjs:
|
|
10
|
-
*
|
|
11
|
-
* 1. Breadth/recall — real OA skeletons (US/DE/FR/IT/NL) with a country token in a varied surface form
|
|
12
|
-
* from `@mailwoman/codex/country` (canonical / endonym / ISO code), + ~30% country-ABSENT
|
|
13
|
-
* negatives (teach O-emission, the precision floor).
|
|
14
|
-
* 2. Homograph CONTRAST pairs — each true country-name homograph (Georgia, Jordan, Lebanon, Mexico,
|
|
15
|
-
* Peru, Turkey) rendered BOTH ways: as `country` (foreign-city context) AND as the US
|
|
16
|
-
* `region`/`locality` (US-ZIP context). Teaches that the label is CONTEXTUAL, not
|
|
17
|
-
* positional.
|
|
18
|
-
* 3. Code-as-region negatives — 2-letter codes that are both a US state abbrev and an ISO country code
|
|
19
|
-
* (CA/GA/IN/MA/PA/AL) in US-ZIP context → must read as `region`, never `country`.
|
|
20
|
-
*
|
|
21
|
-
* `--golden` emits a held-out synthetic val over the VT (US) + Berlin (DE) holdouts. This is a
|
|
22
|
-
* `generate`-mode recipe that still reads REAL tuples off disk — `--count` bounds the OUTPUT, not
|
|
23
|
-
* the input. The passed `random` (the framework LCG) is consumed in the exact call order the
|
|
24
|
-
* legacy script used.
|
|
25
|
-
*/
|
|
26
|
-
import { COUNTRY_SURFACE_FORMS, CountryNames } from "@mailwoman/codex/country";
|
|
27
|
-
import { isPresent } from "@mailwoman/core/objects";
|
|
28
|
-
import { dataRootPath } from "@mailwoman/core/utils";
|
|
29
|
-
import { stableSourceID } from "#adapters/utils";
|
|
30
|
-
import { alignRow } from "#utils";
|
|
31
|
-
import { makeMulberry32, readZippedCSVRecords } from "./scaffold.js";
|
|
32
|
-
// v2: the country TOKEN is decoupled from the skeleton's locale and drawn from a BROAD pool — every
|
|
33
|
-
// ISO canonical name + every curated surface form (endonyms/abbrevs). Surface forms are over-weighted
|
|
34
|
-
// so endonyms/abbrevs ("Deutschland","USA","NL") get strong signal.
|
|
35
|
-
/* oxlint-disable sister-software/no-unnamed-threshold -- the bare decimals below are weighted-sampler
|
|
36
|
-
cutoffs, not thresholds: `const r = random()` followed by a cascade of `r < 0.4` branches IS the
|
|
37
|
-
output distribution, and reading the cascade top-to-bottom is how you see it. Naming each cutoff
|
|
38
|
-
would hide the distribution behind a wall of identifiers. Genuine thresholds in these files are
|
|
39
|
-
extracted as named constants above. */
|
|
40
|
-
const COUNTRY_FORM_POOL = (() => {
|
|
41
|
-
const surface = Object.values(COUNTRY_SURFACE_FORMS).flat(); // endonyms + abbrevs + canonical (curated)
|
|
42
|
-
const names = [...CountryNames];
|
|
43
|
-
// all ~249 ISO canonical English names (breadth)
|
|
44
|
-
return { surface, names };
|
|
45
|
-
})();
|
|
46
|
-
/**
|
|
47
|
-
* Negatives: rows with NO country token → teach golden precision.
|
|
48
|
-
*/
|
|
49
|
-
const COUNTRY_ABSENT_PROB = 0.3;
|
|
50
|
-
/**
|
|
51
|
-
* Multi-locale OA sources. region = implied admin where the extract is single-region (US states, DE Saxony);
|
|
52
|
-
* countrywide extracts (FR/IT/NL) read region from the CSV when present.
|
|
53
|
-
*/
|
|
54
|
-
const SOURCES = [
|
|
55
|
-
{
|
|
56
|
-
zip: dataRootPath("oa-cache", "us__ia__statewide.zip"),
|
|
57
|
-
csv: "us/ia/statewide.csv",
|
|
58
|
-
iso2: "US",
|
|
59
|
-
region: "IA",
|
|
60
|
-
order: "us",
|
|
61
|
-
},
|
|
62
|
-
{ zip: dataRootPath("oa-cache", "us__il__cook.zip"), csv: "us/il/cook.csv", iso2: "US", region: "IL", order: "us" },
|
|
63
|
-
{
|
|
64
|
-
zip: dataRootPath("oa-cache", "us__mt__statewide.zip"),
|
|
65
|
-
csv: "us/mt/statewide.csv",
|
|
66
|
-
iso2: "US",
|
|
67
|
-
region: "MT",
|
|
68
|
-
order: "us",
|
|
69
|
-
},
|
|
70
|
-
{
|
|
71
|
-
zip: dataRootPath("oa-cache", "us__sd__statewide.zip"),
|
|
72
|
-
csv: "us/sd/statewide.csv",
|
|
73
|
-
iso2: "US",
|
|
74
|
-
region: "SD",
|
|
75
|
-
order: "us",
|
|
76
|
-
},
|
|
77
|
-
{
|
|
78
|
-
zip: dataRootPath("oa-cache", "de__sn__statewide.zip"),
|
|
79
|
-
csv: "de/sn/statewide.csv",
|
|
80
|
-
iso2: "DE",
|
|
81
|
-
region: "",
|
|
82
|
-
order: "eu",
|
|
83
|
-
},
|
|
84
|
-
{
|
|
85
|
-
zip: dataRootPath("oa-cache", "fr__countrywide.zip"),
|
|
86
|
-
csv: "fr/countrywide.csv",
|
|
87
|
-
iso2: "FR",
|
|
88
|
-
region: "",
|
|
89
|
-
order: "fr",
|
|
90
|
-
},
|
|
91
|
-
// ES uses the Spanish IGN schema, not the OA standard columns — skipped here (codex still recognizes
|
|
92
|
-
// "España"/"Spain"). A dedicated IGN adapter is a follow-up.
|
|
93
|
-
{
|
|
94
|
-
zip: dataRootPath("oa-cache", "it__countrywide.zip"),
|
|
95
|
-
csv: "it/countrywide.csv",
|
|
96
|
-
iso2: "IT",
|
|
97
|
-
region: "",
|
|
98
|
-
order: "eu",
|
|
99
|
-
},
|
|
100
|
-
{
|
|
101
|
-
zip: dataRootPath("oa-cache", "nl__countrywide.zip"),
|
|
102
|
-
csv: "nl/countrywide.csv",
|
|
103
|
-
iso2: "NL",
|
|
104
|
-
region: "",
|
|
105
|
-
order: "eu",
|
|
106
|
-
},
|
|
107
|
-
];
|
|
108
|
-
/**
|
|
109
|
-
* Held-out for --golden: Vermont (US holdout) + Berlin (DE holdout) — geographic split, never trained.
|
|
110
|
-
*/
|
|
111
|
-
const EVAL_SOURCES = [
|
|
112
|
-
{
|
|
113
|
-
zip: dataRootPath("oa-cache", "us__vt__statewide.zip"),
|
|
114
|
-
csv: "us/vt/statewide.csv",
|
|
115
|
-
iso2: "US",
|
|
116
|
-
region: "VT",
|
|
117
|
-
order: "us",
|
|
118
|
-
},
|
|
119
|
-
{ zip: dataRootPath("oa-cache", "de__berlin.zip"), csv: "de/berlin.csv", iso2: "DE", region: "", order: "eu" },
|
|
120
|
-
];
|
|
121
|
-
/**
|
|
122
|
-
* The countrywide extracts (FR/IT/NL) are GB-scale, so this reads only as far as `limit` distinct tuples: the `break`
|
|
123
|
-
* closes the reader, which releases the archive without inflating the rest of the member.
|
|
124
|
-
*/
|
|
125
|
-
async function readTuples(source, limit) {
|
|
126
|
-
const tuples = [];
|
|
127
|
-
const seen = new Set();
|
|
128
|
-
for await (const row of readZippedCSVRecords(source.zip, source.csv)) {
|
|
129
|
-
if (tuples.length >= limit)
|
|
130
|
-
break;
|
|
131
|
-
const street = row.street ?? "", locality = row.city ?? "", house_number = row.number ?? "";
|
|
132
|
-
if (!street || !locality || !house_number)
|
|
133
|
-
continue;
|
|
134
|
-
const key = `${house_number}|${street}|${locality}`.toLowerCase();
|
|
135
|
-
if (seen.has(key))
|
|
136
|
-
continue;
|
|
137
|
-
seen.add(key);
|
|
138
|
-
tuples.push({
|
|
139
|
-
house_number,
|
|
140
|
-
street,
|
|
141
|
-
locality,
|
|
142
|
-
region: row.region || source.region,
|
|
143
|
-
postcode: row.postcode ?? "",
|
|
144
|
-
iso2: source.iso2,
|
|
145
|
-
order: source.order,
|
|
146
|
-
});
|
|
147
|
-
}
|
|
148
|
-
return tuples;
|
|
149
|
-
}
|
|
150
|
-
/**
|
|
151
|
-
* Pick a country token from the BROAD pool, or null (a country-absent negative). v2.
|
|
152
|
-
*/
|
|
153
|
-
function pickCountry(random) {
|
|
154
|
-
if (random() < COUNTRY_ABSENT_PROB)
|
|
155
|
-
return null; // negative — teaches "trailing token != always country"
|
|
156
|
-
// 60% curated surface forms (endonym/abbrev variety), 40% broad ISO canonical names (coverage).
|
|
157
|
-
const pool = random() < 0.6 ? COUNTRY_FORM_POOL.surface : COUNTRY_FORM_POOL.names;
|
|
158
|
-
return pool[Math.floor(random() * pool.length)];
|
|
159
|
-
}
|
|
160
|
-
/**
|
|
161
|
-
* Render the address body in native-ish order. `country` null → a country-ABSENT negative row.
|
|
162
|
-
*/
|
|
163
|
-
function renderCountry(random, t, country) {
|
|
164
|
-
const { house_number: hn, street, locality: loc, region: reg, postcode: pc, order } = t;
|
|
165
|
-
const components = { house_number: hn, street, locality: loc };
|
|
166
|
-
if (reg) {
|
|
167
|
-
components.region = reg;
|
|
168
|
-
}
|
|
169
|
-
if (pc) {
|
|
170
|
-
components.postcode = pc;
|
|
171
|
-
}
|
|
172
|
-
let body;
|
|
173
|
-
if (order === "us") {
|
|
174
|
-
const regPc = [reg, pc].filter(isPresent).join(" ");
|
|
175
|
-
body = `${hn} ${street}, ${loc}${regPc ? ", " + regPc : ""}`;
|
|
176
|
-
}
|
|
177
|
-
else if (order === "fr") {
|
|
178
|
-
// French is NUMBER-street, postcode-city: "84 Route de la Fontaine, 75008 Paris".
|
|
179
|
-
body = `${hn} ${street}, ${[pc, loc].filter(isPresent).join(" ")}`;
|
|
180
|
-
}
|
|
181
|
-
else {
|
|
182
|
-
// DE/IT/NL: street-number, postcode-city: "Pariser Platz 1, 10117 Berlin".
|
|
183
|
-
const pcCity = [pc, loc].filter(isPresent).join(" ");
|
|
184
|
-
body = `${street} ${hn}, ${pcCity}`;
|
|
185
|
-
}
|
|
186
|
-
if (!country) {
|
|
187
|
-
// Negative: a normal address, NO country token/component. Teaches that a trailing region/city/
|
|
188
|
-
// postcode is NOT a country (counters the v1 golden over-firing).
|
|
189
|
-
return { fmt: "negative", raw: body, components };
|
|
190
|
-
}
|
|
191
|
-
const withC = { ...components, country };
|
|
192
|
-
const r = random();
|
|
193
|
-
if (r < 0.8)
|
|
194
|
-
return { fmt: "full", raw: `${body}, ${country}`, components: withC };
|
|
195
|
-
if (r < 0.92)
|
|
196
|
-
return { fmt: "full-nl", raw: `${body}\n${country}`, components: withC };
|
|
197
|
-
const bareBody = order === "us" || order === "fr" ? `${hn} ${street}, ${loc}` : `${street} ${hn}, ${loc}`;
|
|
198
|
-
return {
|
|
199
|
-
fmt: "bare",
|
|
200
|
-
raw: `${bareBody}, ${country}`,
|
|
201
|
-
components: { house_number: hn, street, locality: loc, country },
|
|
202
|
-
};
|
|
203
|
-
}
|
|
204
|
-
const HOMOGRAPHS = [
|
|
205
|
-
{
|
|
206
|
-
surface: "Georgia",
|
|
207
|
-
iso2: "GE",
|
|
208
|
-
cities: ["Tbilisi", "Batumi", "Kutaisi", "Rustavi"],
|
|
209
|
-
us: { role: "region", locality: "Atlanta", region: "Georgia", postcodes: ["30309", "31401", "30601", "31201"] },
|
|
210
|
-
},
|
|
211
|
-
{
|
|
212
|
-
surface: "Jordan",
|
|
213
|
-
iso2: "JO",
|
|
214
|
-
cities: ["Amman", "Irbid", "Zarqa", "Aqaba"],
|
|
215
|
-
us: { role: "locality", locality: "Jordan", region: "MN", postcodes: ["55352"] },
|
|
216
|
-
},
|
|
217
|
-
{
|
|
218
|
-
surface: "Lebanon",
|
|
219
|
-
iso2: "LB",
|
|
220
|
-
cities: ["Beirut", "Tripoli", "Sidon", "Byblos"],
|
|
221
|
-
us: { role: "locality", locality: "Lebanon", region: "TN", postcodes: ["37087", "03766", "17042", "45036"] },
|
|
222
|
-
},
|
|
223
|
-
{
|
|
224
|
-
surface: "Mexico",
|
|
225
|
-
iso2: "MX",
|
|
226
|
-
cities: ["Guadalajara", "Monterrey", "Puebla", "Oaxaca"],
|
|
227
|
-
us: { role: "locality", locality: "Mexico", region: "MO", postcodes: ["65265"] },
|
|
228
|
-
},
|
|
229
|
-
{
|
|
230
|
-
surface: "Peru",
|
|
231
|
-
iso2: "PE",
|
|
232
|
-
cities: ["Cusco", "Arequipa", "Trujillo", "Iquitos"],
|
|
233
|
-
us: { role: "locality", locality: "Peru", region: "IL", postcodes: ["61354", "46970"] },
|
|
234
|
-
},
|
|
235
|
-
{
|
|
236
|
-
surface: "Turkey",
|
|
237
|
-
iso2: "TR",
|
|
238
|
-
cities: ["Ankara", "Izmir", "Bursa", "Antalya"],
|
|
239
|
-
us: { role: "locality", locality: "Turkey", region: "TX", postcodes: ["79261", "28393"] },
|
|
240
|
-
},
|
|
241
|
-
];
|
|
242
|
-
const ABBREV_REGIONS = [
|
|
243
|
-
{ code: "CA", localities: ["Los Angeles", "Sacramento", "San Diego"], postcodes: ["90012", "95814", "92101"] }, // California / Canada
|
|
244
|
-
{ code: "GA", localities: ["Atlanta", "Savannah", "Macon"], postcodes: ["30309", "31401", "31201"] }, // Georgia(US) / Georgia
|
|
245
|
-
{ code: "IN", localities: ["Indianapolis", "Fort Wayne"], postcodes: ["46204", "46802"] }, // Indiana / India
|
|
246
|
-
{ code: "MA", localities: ["Boston", "Worcester"], postcodes: ["02108", "01608"] }, // Massachusetts / Morocco
|
|
247
|
-
{ code: "PA", localities: ["Philadelphia", "Pittsburgh"], postcodes: ["19103", "15222"] }, // Pennsylvania / Panama
|
|
248
|
-
{ code: "AL", localities: ["Birmingham", "Montgomery"], postcodes: ["35203", "36104"] }, // Alabama / Albania
|
|
249
|
-
];
|
|
250
|
-
const STREET_POOL = [
|
|
251
|
-
"Main Street",
|
|
252
|
-
"Oak Avenue",
|
|
253
|
-
"Park Road",
|
|
254
|
-
"Elm Street",
|
|
255
|
-
"Hill Road",
|
|
256
|
-
"Market Street",
|
|
257
|
-
"Church Street",
|
|
258
|
-
"King Street",
|
|
259
|
-
"2nd Avenue",
|
|
260
|
-
"Maple Drive",
|
|
261
|
-
];
|
|
262
|
-
const pick = (random, arr) => arr[Math.floor(random() * arr.length)];
|
|
263
|
-
const houseNo = (random) => String(1 + Math.floor(random() * 998));
|
|
264
|
-
/**
|
|
265
|
-
* A homograph CONTRAST row: ~half render the surface as `country` (foreign city), half as the US `region`/`locality`
|
|
266
|
-
* (US ZIP, NO country). Returns iso2 for provenance.
|
|
267
|
-
*/
|
|
268
|
-
function renderHomograph(random) {
|
|
269
|
-
const h = pick(random, HOMOGRAPHS);
|
|
270
|
-
const hn = houseNo(random), street = pick(random, STREET_POOL);
|
|
271
|
-
if (random() < 0.5) {
|
|
272
|
-
const city = pick(random, h.cities);
|
|
273
|
-
const withStreet = random() < 0.6;
|
|
274
|
-
const raw = withStreet ? `${hn} ${street}, ${city}, ${h.surface}` : `${city}, ${h.surface}`;
|
|
275
|
-
const components = withStreet
|
|
276
|
-
? { house_number: hn, street, locality: city, country: h.surface }
|
|
277
|
-
: { locality: city, country: h.surface };
|
|
278
|
-
return { fmt: "homograph-country", raw, components, iso2: h.iso2 };
|
|
279
|
-
}
|
|
280
|
-
const pc = pick(random, h.us.postcodes);
|
|
281
|
-
if (h.us.role === "region") {
|
|
282
|
-
// surface is the US STATE: "123 Oak Ave, Atlanta, Georgia 30309" → region, no country
|
|
283
|
-
return {
|
|
284
|
-
fmt: "homograph-us-region",
|
|
285
|
-
raw: `${hn} ${street}, ${h.us.locality}, ${h.surface} ${pc}`,
|
|
286
|
-
components: { house_number: hn, street, locality: h.us.locality, region: h.surface, postcode: pc },
|
|
287
|
-
iso2: "US",
|
|
288
|
-
};
|
|
289
|
-
}
|
|
290
|
-
// surface is the US CITY: "123 Oak Ave, Lebanon, TN 37087" → locality, no country
|
|
291
|
-
return {
|
|
292
|
-
fmt: "homograph-us-locality",
|
|
293
|
-
raw: `${hn} ${street}, ${h.surface}, ${h.us.region} ${pc}`,
|
|
294
|
-
components: { house_number: hn, street, locality: h.surface, region: h.us.region, postcode: pc },
|
|
295
|
-
iso2: "US",
|
|
296
|
-
};
|
|
297
|
-
}
|
|
298
|
-
/**
|
|
299
|
-
* An abbrev-as-region negative: "123 Main St, Los Angeles, CA 90012" → region CA, NO country.
|
|
300
|
-
*/
|
|
301
|
-
function renderAbbrevRegion(random) {
|
|
302
|
-
const a = pick(random, ABBREV_REGIONS);
|
|
303
|
-
const hn = houseNo(random), street = pick(random, STREET_POOL), locality = pick(random, a.localities), postcode = pick(random, a.postcodes);
|
|
304
|
-
return {
|
|
305
|
-
fmt: "abbrev-region",
|
|
306
|
-
raw: `${hn} ${street}, ${locality}, ${a.code} ${postcode}`,
|
|
307
|
-
components: { house_number: hn, street, locality, region: a.code, postcode },
|
|
308
|
-
iso2: "US",
|
|
309
|
-
};
|
|
310
|
-
}
|
|
311
|
-
/**
|
|
312
|
-
* Share of rows that are homograph contrast pairs.
|
|
313
|
-
*/
|
|
314
|
-
const HOMOGRAPH_FRAC = 0.22;
|
|
315
|
-
/**
|
|
316
|
-
* Share that are code-as-region negatives (cumulative with HOMOGRAPH_FRAC)
|
|
317
|
-
*/
|
|
318
|
-
const ABBREV_FRAC = 0.08;
|
|
319
|
-
/**
|
|
320
|
-
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
321
|
-
* and `description` below for the surface form it generates.
|
|
322
|
-
*/
|
|
323
|
-
export const countryBalancedRecipe = {
|
|
324
|
-
name: "country-balanced",
|
|
325
|
-
description: "Balanced model-first country rows (#464): OA skeletons + ISO surface forms + homograph contrast pairs",
|
|
326
|
-
mode: "generate",
|
|
327
|
-
options: [{ flag: "--golden", description: "Emit the held-out VT+Berlin eval slice" }],
|
|
328
|
-
async run(opts, write) {
|
|
329
|
-
if (opts.count == null)
|
|
330
|
-
throw new Error("country-balanced recipe requires --count <N>");
|
|
331
|
-
const count = opts.count;
|
|
332
|
-
// Legacy build-country-shard-balanced.mjs seeded mulberry32 with the raw seed: `const random = mulberry32(opts.seed)`.
|
|
333
|
-
const random = makeMulberry32(opts.seed);
|
|
334
|
-
const source = opts.sourceName ?? "synth-country";
|
|
335
|
-
const sources = opts.golden ? EVAL_SOURCES : SOURCES;
|
|
336
|
-
const perSource = Math.ceil((count * 3) / sources.length); // over-read; balance locales
|
|
337
|
-
const pool = [];
|
|
338
|
-
for (const s of sources) {
|
|
339
|
-
const t = await readTuples(s, perSource);
|
|
340
|
-
console.error(` ${s.csv} (${s.iso2}): ${t.length} tuples`);
|
|
341
|
-
for (const x of t) {
|
|
342
|
-
pool.push(x);
|
|
343
|
-
}
|
|
344
|
-
}
|
|
345
|
-
if (!pool.length) {
|
|
346
|
-
throw new Error(`No tuples — are the cached OA zips present in ${dataRootPath("oa-cache")}?`);
|
|
347
|
-
}
|
|
348
|
-
let emitted = 0;
|
|
349
|
-
let skipped = 0;
|
|
350
|
-
let guard = 0;
|
|
351
|
-
const N = pool.length;
|
|
352
|
-
while (emitted < count && guard++ < count * 8) {
|
|
353
|
-
// Mix three row types: homograph contrast (the distinction), code-as-region negatives, and the
|
|
354
|
-
// breadth/recall main path (random ISO form on an OA skeleton, ~30% country-absent).
|
|
355
|
-
const roll = random();
|
|
356
|
-
let rendered;
|
|
357
|
-
let rowISO2;
|
|
358
|
-
if (roll < HOMOGRAPH_FRAC) {
|
|
359
|
-
const h = renderHomograph(random);
|
|
360
|
-
rendered = h;
|
|
361
|
-
rowISO2 = h.iso2;
|
|
362
|
-
}
|
|
363
|
-
else if (roll < HOMOGRAPH_FRAC + ABBREV_FRAC) {
|
|
364
|
-
const a = renderAbbrevRegion(random);
|
|
365
|
-
rendered = a;
|
|
366
|
-
rowISO2 = a.iso2;
|
|
367
|
-
}
|
|
368
|
-
else {
|
|
369
|
-
const t = pool[Math.floor(random() * N)];
|
|
370
|
-
const country = pickCountry(random); // may be null → a country-absent negative row
|
|
371
|
-
rendered = renderCountry(random, t, country);
|
|
372
|
-
rowISO2 = t.iso2;
|
|
373
|
-
if (country && !rendered.raw.includes(country)) {
|
|
374
|
-
skipped++;
|
|
375
|
-
continue;
|
|
376
|
-
}
|
|
377
|
-
}
|
|
378
|
-
const { raw, components } = rendered;
|
|
379
|
-
const localeTag = rowISO2 === "US" ? "en-US" : `${rowISO2.toLowerCase()}-${rowISO2}`;
|
|
380
|
-
if (opts.golden) {
|
|
381
|
-
write(JSON.stringify({ raw, components, country: rowISO2 }) + "\n");
|
|
382
|
-
emitted++;
|
|
383
|
-
continue;
|
|
384
|
-
}
|
|
385
|
-
const canonical = {
|
|
386
|
-
raw,
|
|
387
|
-
components,
|
|
388
|
-
country: rowISO2,
|
|
389
|
-
locale: localeTag,
|
|
390
|
-
source,
|
|
391
|
-
source_id: stableSourceID(source, components),
|
|
392
|
-
corpus_version: "0.4.0",
|
|
393
|
-
license: "OpenAddresses multi-locale skeletons + injected ISO-3166 country surface forms (codex)",
|
|
394
|
-
};
|
|
395
|
-
const aligned = alignRow(canonical);
|
|
396
|
-
if (aligned.kind !== "labeled" || !aligned.row) {
|
|
397
|
-
skipped++;
|
|
398
|
-
continue;
|
|
399
|
-
}
|
|
400
|
-
write(JSON.stringify({ ...aligned.row, synth_method: "country", synth_base_id: null }) + "\n");
|
|
401
|
-
emitted++;
|
|
402
|
-
}
|
|
403
|
-
return { emitted, skipped };
|
|
404
|
-
},
|
|
405
|
-
};
|
|
406
|
-
//# sourceMappingURL=country-balanced.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"country-balanced.js","sourceRoot":"","sources":["../../../src/shard-recipes/country-balanced.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;GAwBG;AAEH,OAAO,EAAE,qBAAqB,EAAE,YAAY,EAAE,MAAM,0BAA0B,CAAA;AAC9E,OAAO,EAAE,SAAS,EAAE,MAAM,yBAAyB,CAAA;AAEnD,OAAO,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAA;AAEpD,OAAO,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAA;AAEhD,OAAO,EAAE,QAAQ,EAAE,MAAM,QAAQ,CAAA;AAEjC,OAAO,EAAE,cAAc,EAAE,oBAAoB,EAAoB,MAAM,eAAe,CAAA;AAEtF,oGAAoG;AACpG,sGAAsG;AACtG,oEAAoE;AACpE;;;;yCAIyC;AAEzC,MAAM,iBAAiB,GAAG,CAAC,GAAG,EAAE;IAC/B,MAAM,OAAO,GAAG,MAAM,CAAC,MAAM,CAAC,qBAAqB,CAAC,CAAC,IAAI,EAAE,CAAA,CAAC,2CAA2C;IACvG,MAAM,KAAK,GAAG,CAAC,GAAG,YAAY,CAAC,CAAA;IAE/B,iDAAiD;IACjD,OAAO,EAAE,OAAO,EAAE,KAAK,EAAE,CAAA;AAC1B,CAAC,CAAC,EAAE,CAAA;AAEJ;;GAEG;AACH,MAAM,mBAAmB,GAAG,GAAG,CAAA;AAa/B;;;GAGG;AACH,MAAM,OAAO,GAA6B;IACzC;QACC,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,uBAAuB,CAAC;QACtD,GAAG,EAAE,qBAAqB;QAC1B,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,IAAI;QACZ,KAAK,EAAE,IAAI;KACX;IACD,EAAE,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,kBAAkB,CAAC,EAAE,GAAG,EAAE,gBAAgB,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,KAAK,EAAE,IAAI,EAAE;IACnH;QACC,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,uBAAuB,CAAC;QACtD,GAAG,EAAE,qBAAqB;QAC1B,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,IAAI;QACZ,KAAK,EAAE,IAAI;KACX;IACD;QACC,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,uBAAuB,CAAC;QACtD,GAAG,EAAE,qBAAqB;QAC1B,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,IAAI;QACZ,KAAK,EAAE,IAAI;KACX;IACD;QACC,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,uBAAuB,CAAC;QACtD,GAAG,EAAE,qBAAqB;QAC1B,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,EAAE;QACV,KAAK,EAAE,IAAI;KACX;IACD;QACC,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,qBAAqB,CAAC;QACpD,GAAG,EAAE,oBAAoB;QACzB,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,EAAE;QACV,KAAK,EAAE,IAAI;KACX;IACD,qGAAqG;IACrG,6DAA6D;IAC7D;QACC,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,qBAAqB,CAAC;QACpD,GAAG,EAAE,oBAAoB;QACzB,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,EAAE;QACV,KAAK,EAAE,IAAI;KACX;IACD;QACC,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,qBAAqB,CAAC;QACpD,GAAG,EAAE,oBAAoB;QACzB,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,EAAE;QACV,KAAK,EAAE,IAAI;KACX;CACD,CAAA;AAED;;GAEG;AACH,MAAM,YAAY,GAA6B;IAC9C;QACC,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,uBAAuB,CAAC;QACtD,GAAG,EAAE,qBAAqB;QAC1B,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,IAAI;QACZ,KAAK,EAAE,IAAI;KACX;IACD,EAAE,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,gBAAgB,CAAC,EAAE,GAAG,EAAE,eAAe,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE;CAC9G,CAAA;AAeD;;;GAGG;AACH,KAAK,UAAU,UAAU,CAAC,MAAqB,EAAE,KAAa;IAC7D,MAAM,MAAM,GAAmB,EAAE,CAAA;IACjC,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAA;IAE9B,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,oBAAoB,CAAC,MAAM,CAAC,GAAG,EAAE,MAAM,CAAC,GAAG,CAAC,EAAE,CAAC;QACtE,IAAI,MAAM,CAAC,MAAM,IAAI,KAAK;YAAE,MAAK;QAEjC,MAAM,MAAM,GAAG,GAAG,CAAC,MAAM,IAAI,EAAE,EAC9B,QAAQ,GAAG,GAAG,CAAC,IAAI,IAAI,EAAE,EACzB,YAAY,GAAG,GAAG,CAAC,MAAM,IAAI,EAAE,CAAA;QAEhC,IAAI,CAAC,MAAM,IAAI,CAAC,QAAQ,IAAI,CAAC,YAAY;YAAE,SAAQ;QACnD,MAAM,GAAG,GAAG,GAAG,YAAY,IAAI,MAAM,IAAI,QAAQ,EAAE,CAAC,WAAW,EAAE,CAAA;QAEjE,IAAI,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC;YAAE,SAAQ;QAC3B,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;QAEb,MAAM,CAAC,IAAI,CAAC;YACX,YAAY;YACZ,MAAM;YACN,QAAQ;YACR,MAAM,EAAE,GAAG,CAAC,MAAM,IAAI,MAAM,CAAC,MAAM;YACnC,QAAQ,EAAE,GAAG,CAAC,QAAQ,IAAI,EAAE;YAC5B,IAAI,EAAE,MAAM,CAAC,IAAI;YACjB,KAAK,EAAE,MAAM,CAAC,KAAK;SACnB,CAAC,CAAA;IACH,CAAC;IAED,OAAO,MAAM,CAAA;AACd,CAAC;AAED;;GAEG;AACH,SAAS,WAAW,CAAC,MAAoB;IACxC,IAAI,MAAM,EAAE,GAAG,mBAAmB;QAAE,OAAO,IAAI,CAAA,CAAC,wDAAwD;IACxG,gGAAgG;IAChG,MAAM,IAAI,GAAG,MAAM,EAAE,GAAG,GAAG,CAAC,CAAC,CAAC,iBAAiB,CAAC,OAAO,CAAC,CAAC,CAAC,iBAAiB,CAAC,KAAK,CAAA;IAEjF,OAAO,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,IAAI,CAAC,MAAM,CAAC,CAAE,CAAA;AACjD,CAAC;AAED;;GAEG;AACH,SAAS,aAAa,CACrB,MAAoB,EACpB,CAAe,EACf,OAAsB;IAEtB,MAAM,EAAE,YAAY,EAAE,EAAE,EAAE,MAAM,EAAE,QAAQ,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE,QAAQ,EAAE,EAAE,EAAE,KAAK,EAAE,GAAG,CAAC,CAAA;IACvF,MAAM,UAAU,GAA0C,EAAE,YAAY,EAAE,EAAE,EAAE,MAAM,EAAE,QAAQ,EAAE,GAAG,EAAE,CAAA;IAErG,IAAI,GAAG,EAAE,CAAC;QACT,UAAU,CAAC,MAAM,GAAG,GAAG,CAAA;IACxB,CAAC;IAED,IAAI,EAAE,EAAE,CAAC;QACR,UAAU,CAAC,QAAQ,GAAG,EAAE,CAAA;IACzB,CAAC;IAED,IAAI,IAAY,CAAA;IAEhB,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;QACpB,MAAM,KAAK,GAAG,CAAC,GAAG,EAAE,EAAE,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;QACnD,IAAI,GAAG,GAAG,EAAE,IAAI,MAAM,KAAK,GAAG,GAAG,KAAK,CAAC,CAAC,CAAC,IAAI,GAAG,KAAK,CAAC,CAAC,CAAC,EAAE,EAAE,CAAA;IAC7D,CAAC;SAAM,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;QAC3B,kFAAkF;QAClF,IAAI,GAAG,GAAG,EAAE,IAAI,MAAM,KAAK,CAAC,EAAE,EAAE,GAAG,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,CAAA;IACnE,CAAC;SAAM,CAAC;QACP,2EAA2E;QAC3E,MAAM,MAAM,GAAG,CAAC,EAAE,EAAE,GAAG,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;QACpD,IAAI,GAAG,GAAG,MAAM,IAAI,EAAE,KAAK,MAAM,EAAE,CAAA;IACpC,CAAC;IAED,IAAI,CAAC,OAAO,EAAE,CAAC;QACd,+FAA+F;QAC/F,kEAAkE;QAClE,OAAO,EAAE,GAAG,EAAE,UAAU,EAAE,GAAG,EAAE,IAAI,EAAE,UAAU,EAAE,CAAA;IAClD,CAAC;IAED,MAAM,KAAK,GAA0C,EAAE,GAAG,UAAU,EAAE,OAAO,EAAE,CAAA;IAC/E,MAAM,CAAC,GAAG,MAAM,EAAE,CAAA;IAElB,IAAI,CAAC,GAAG,GAAG;QAAE,OAAO,EAAE,GAAG,EAAE,MAAM,EAAE,GAAG,EAAE,GAAG,IAAI,KAAK,OAAO,EAAE,EAAE,UAAU,EAAE,KAAK,EAAE,CAAA;IAElF,IAAI,CAAC,GAAG,IAAI;QAAE,OAAO,EAAE,GAAG,EAAE,SAAS,EAAE,GAAG,EAAE,GAAG,IAAI,KAAK,OAAO,EAAE,EAAE,UAAU,EAAE,KAAK,EAAE,CAAA;IACtF,MAAM,QAAQ,GAAG,KAAK,KAAK,IAAI,IAAI,KAAK,KAAK,IAAI,CAAC,CAAC,CAAC,GAAG,EAAE,IAAI,MAAM,KAAK,GAAG,EAAE,CAAC,CAAC,CAAC,GAAG,MAAM,IAAI,EAAE,KAAK,GAAG,EAAE,CAAA;IAEzG,OAAO;QACN,GAAG,EAAE,MAAM;QACX,GAAG,EAAE,GAAG,QAAQ,KAAK,OAAO,EAAE;QAC9B,UAAU,EAAE,EAAE,YAAY,EAAE,EAAE,EAAE,MAAM,EAAE,QAAQ,EAAE,GAAG,EAAE,OAAO,EAAE;KAChE,CAAA;AACF,CAAC;AAaD,MAAM,UAAU,GAAyB;IACxC;QACC,OAAO,EAAE,SAAS;QAClB,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,CAAC,SAAS,EAAE,QAAQ,EAAE,SAAS,EAAE,SAAS,CAAC;QACnD,EAAE,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,QAAQ,EAAE,SAAS,EAAE,MAAM,EAAE,SAAS,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC,EAAE;KAC/G;IACD;QACC,OAAO,EAAE,QAAQ;QACjB,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC;QAC5C,EAAE,EAAE,EAAE,IAAI,EAAE,UAAU,EAAE,QAAQ,EAAE,QAAQ,EAAE,MAAM,EAAE,IAAI,EAAE,SAAS,EAAE,CAAC,OAAO,CAAC,EAAE;KAChF;IACD;QACC,OAAO,EAAE,SAAS;QAClB,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,CAAC,QAAQ,EAAE,SAAS,EAAE,OAAO,EAAE,QAAQ,CAAC;QAChD,EAAE,EAAE,EAAE,IAAI,EAAE,UAAU,EAAE,QAAQ,EAAE,SAAS,EAAE,MAAM,EAAE,IAAI,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC,EAAE;KAC5G;IACD;QACC,OAAO,EAAE,QAAQ;QACjB,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,CAAC,aAAa,EAAE,WAAW,EAAE,QAAQ,EAAE,QAAQ,CAAC;QACxD,EAAE,EAAE,EAAE,IAAI,EAAE,UAAU,EAAE,QAAQ,EAAE,QAAQ,EAAE,MAAM,EAAE,IAAI,EAAE,SAAS,EAAE,CAAC,OAAO,CAAC,EAAE;KAChF;IACD;QACC,OAAO,EAAE,MAAM;QACf,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,CAAC,OAAO,EAAE,UAAU,EAAE,UAAU,EAAE,SAAS,CAAC;QACpD,EAAE,EAAE,EAAE,IAAI,EAAE,UAAU,EAAE,QAAQ,EAAE,MAAM,EAAE,MAAM,EAAE,IAAI,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,CAAC,EAAE;KACvF;IACD;QACC,OAAO,EAAE,QAAQ;QACjB,IAAI,EAAE,IAAI;QACV,MAAM,EAAE,CAAC,QAAQ,EAAE,OAAO,EAAE,OAAO,EAAE,SAAS,CAAC;QAC/C,EAAE,EAAE,EAAE,IAAI,EAAE,UAAU,EAAE,QAAQ,EAAE,QAAQ,EAAE,MAAM,EAAE,IAAI,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,CAAC,EAAE;KACzF;CACD,CAAA;AASD,MAAM,cAAc,GAA4B;IAC/C,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE,CAAC,aAAa,EAAE,YAAY,EAAE,WAAW,CAAC,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC,EAAE,EAAE,sBAAsB;IACtI,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE,CAAC,SAAS,EAAE,UAAU,EAAE,OAAO,CAAC,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC,EAAE,EAAE,wBAAwB;IAC9H,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE,CAAC,cAAc,EAAE,YAAY,CAAC,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,CAAC,EAAE,EAAE,kBAAkB;IAC7G,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE,CAAC,QAAQ,EAAE,WAAW,CAAC,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,CAAC,EAAE,EAAE,0BAA0B;IAC9G,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE,CAAC,cAAc,EAAE,YAAY,CAAC,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,CAAC,EAAE,EAAE,wBAAwB;IACnH,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE,CAAC,YAAY,EAAE,YAAY,CAAC,EAAE,SAAS,EAAE,CAAC,OAAO,EAAE,OAAO,CAAC,EAAE,EAAE,oBAAoB;CAC7G,CAAA;AAED,MAAM,WAAW,GAAsB;IACtC,aAAa;IACb,YAAY;IACZ,WAAW;IACX,YAAY;IACZ,WAAW;IACX,eAAe;IACf,eAAe;IACf,aAAa;IACb,YAAY;IACZ,aAAa;CACb,CAAA;AAED,MAAM,IAAI,GAAG,CAAI,MAAoB,EAAE,GAAiB,EAAK,EAAE,CAAC,GAAG,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,GAAG,CAAC,MAAM,CAAC,CAAE,CAAA;AACvG,MAAM,OAAO,GAAG,CAAC,MAAoB,EAAU,EAAE,CAAC,MAAM,CAAC,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,GAAG,CAAC,CAAC,CAAA;AAExF;;;GAGG;AACH,SAAS,eAAe,CAAC,MAAoB;IAM5C,MAAM,CAAC,GAAG,IAAI,CAAC,MAAM,EAAE,UAAU,CAAC,CAAA;IAElC,MAAM,EAAE,GAAG,OAAO,CAAC,MAAM,CAAC,EACzB,MAAM,GAAG,IAAI,CAAC,MAAM,EAAE,WAAW,CAAC,CAAA;IAEnC,IAAI,MAAM,EAAE,GAAG,GAAG,EAAE,CAAC;QACpB,MAAM,IAAI,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC,CAAC,MAAM,CAAC,CAAA;QACnC,MAAM,UAAU,GAAG,MAAM,EAAE,GAAG,GAAG,CAAA;QACjC,MAAM,GAAG,GAAG,UAAU,CAAC,CAAC,CAAC,GAAG,EAAE,IAAI,MAAM,KAAK,IAAI,KAAK,CAAC,CAAC,OAAO,EAAE,CAAC,CAAC,CAAC,GAAG,IAAI,KAAK,CAAC,CAAC,OAAO,EAAE,CAAA;QAE3F,MAAM,UAAU,GAA0C,UAAU;YACnE,CAAC,CAAC,EAAE,YAAY,EAAE,EAAE,EAAE,MAAM,EAAE,QAAQ,EAAE,IAAI,EAAE,OAAO,EAAE,CAAC,CAAC,OAAO,EAAE;YAClE,CAAC,CAAC,EAAE,QAAQ,EAAE,IAAI,EAAE,OAAO,EAAE,CAAC,CAAC,OAAO,EAAE,CAAA;QAEzC,OAAO,EAAE,GAAG,EAAE,mBAAmB,EAAE,GAAG,EAAE,UAAU,EAAE,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;IACnE,CAAC;IAED,MAAM,EAAE,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC,CAAC,EAAE,CAAC,SAAS,CAAC,CAAA;IAEvC,IAAI,CAAC,CAAC,EAAE,CAAC,IAAI,KAAK,QAAQ,EAAE,CAAC;QAC5B,sFAAsF;QACtF,OAAO;YACN,GAAG,EAAE,qBAAqB;YAC1B,GAAG,EAAE,GAAG,EAAE,IAAI,MAAM,KAAK,CAAC,CAAC,EAAE,CAAC,QAAQ,KAAK,CAAC,CAAC,OAAO,IAAI,EAAE,EAAE;YAC5D,UAAU,EAAE,EAAE,YAAY,EAAE,EAAE,EAAE,MAAM,EAAE,QAAQ,EAAE,CAAC,CAAC,EAAE,CAAC,QAAQ,EAAE,MAAM,EAAE,CAAC,CAAC,OAAO,EAAE,QAAQ,EAAE,EAAE,EAAE;YAClG,IAAI,EAAE,IAAI;SACV,CAAA;IACF,CAAC;IAED,kFAAkF;IAClF,OAAO;QACN,GAAG,EAAE,uBAAuB;QAC5B,GAAG,EAAE,GAAG,EAAE,IAAI,MAAM,KAAK,CAAC,CAAC,OAAO,KAAK,CAAC,CAAC,EAAE,CAAC,MAAM,IAAI,EAAE,EAAE;QAC1D,UAAU,EAAE,EAAE,YAAY,EAAE,EAAE,EAAE,MAAM,EAAE,QAAQ,EAAE,CAAC,CAAC,OAAO,EAAE,MAAM,EAAE,CAAC,CAAC,EAAE,CAAC,MAAM,EAAE,QAAQ,EAAE,EAAE,EAAE;QAChG,IAAI,EAAE,IAAI;KACV,CAAA;AACF,CAAC;AAED;;GAEG;AACH,SAAS,kBAAkB,CAAC,MAAoB;IAM/C,MAAM,CAAC,GAAG,IAAI,CAAC,MAAM,EAAE,cAAc,CAAC,CAAA;IAEtC,MAAM,EAAE,GAAG,OAAO,CAAC,MAAM,CAAC,EACzB,MAAM,GAAG,IAAI,CAAC,MAAM,EAAE,WAAW,CAAC,EAClC,QAAQ,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC,CAAC,UAAU,CAAC,EACrC,QAAQ,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC,CAAC,SAAS,CAAC,CAAA;IAErC,OAAO;QACN,GAAG,EAAE,eAAe;QACpB,GAAG,EAAE,GAAG,EAAE,IAAI,MAAM,KAAK,QAAQ,KAAK,CAAC,CAAC,IAAI,IAAI,QAAQ,EAAE;QAC1D,UAAU,EAAE,EAAE,YAAY,EAAE,EAAE,EAAE,MAAM,EAAE,QAAQ,EAAE,MAAM,EAAE,CAAC,CAAC,IAAI,EAAE,QAAQ,EAAE;QAC5E,IAAI,EAAE,IAAI;KACV,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,cAAc,GAAG,IAAI,CAAA;AAC3B;;GAEG;AACH,MAAM,WAAW,GAAG,IAAI,CAAA;AAExB;;;GAGG;AACH,MAAM,CAAC,MAAM,qBAAqB,GAAgB;IACjD,IAAI,EAAE,kBAAkB;IACxB,WAAW,EAAE,uGAAuG;IACpH,IAAI,EAAE,UAAU;IAChB,OAAO,EAAE,CAAC,EAAE,IAAI,EAAE,UAAU,EAAE,WAAW,EAAE,wCAAwC,EAAE,CAAC;IACtF,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,IAAI,IAAI,CAAC,KAAK,IAAI,IAAI;YAAE,MAAM,IAAI,KAAK,CAAC,8CAA8C,CAAC,CAAA;QACvF,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAA;QACxB,uHAAuH;QACvH,MAAM,MAAM,GAAG,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACxC,MAAM,MAAM,GAAG,IAAI,CAAC,UAAU,IAAI,eAAe,CAAA;QACjD,MAAM,OAAO,GAAG,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,OAAO,CAAA;QACpD,MAAM,SAAS,GAAG,IAAI,CAAC,IAAI,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,GAAG,OAAO,CAAC,MAAM,CAAC,CAAA,CAAC,6BAA6B;QAEvF,MAAM,IAAI,GAAmB,EAAE,CAAA;QAE/B,KAAK,MAAM,CAAC,IAAI,OAAO,EAAE,CAAC;YACzB,MAAM,CAAC,GAAG,MAAM,UAAU,CAAC,CAAC,EAAE,SAAS,CAAC,CAAA;YAExC,OAAO,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,GAAG,KAAK,CAAC,CAAC,IAAI,MAAM,CAAC,CAAC,MAAM,SAAS,CAAC,CAAA;YAE3D,KAAK,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC;gBACnB,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;YACb,CAAC;QACF,CAAC;QAED,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,CAAC;YAClB,MAAM,IAAI,KAAK,CAAC,iDAAiD,YAAY,CAAC,UAAU,CAAC,GAAG,CAAC,CAAA;QAC9F,CAAC;QAED,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,KAAK,GAAG,CAAC,CAAA;QACb,MAAM,CAAC,GAAG,IAAI,CAAC,MAAM,CAAA;QAErB,OAAO,OAAO,GAAG,KAAK,IAAI,KAAK,EAAE,GAAG,KAAK,GAAG,CAAC,EAAE,CAAC;YAC/C,+FAA+F;YAC/F,qFAAqF;YACrF,MAAM,IAAI,GAAG,MAAM,EAAE,CAAA;YACrB,IAAI,QAAyF,CAAA;YAC7F,IAAI,OAAe,CAAA;YAEnB,IAAI,IAAI,GAAG,cAAc,EAAE,CAAC;gBAC3B,MAAM,CAAC,GAAG,eAAe,CAAC,MAAM,CAAC,CAAA;gBACjC,QAAQ,GAAG,CAAC,CAAA;gBACZ,OAAO,GAAG,CAAC,CAAC,IAAI,CAAA;YACjB,CAAC;iBAAM,IAAI,IAAI,GAAG,cAAc,GAAG,WAAW,EAAE,CAAC;gBAChD,MAAM,CAAC,GAAG,kBAAkB,CAAC,MAAM,CAAC,CAAA;gBACpC,QAAQ,GAAG,CAAC,CAAA;gBACZ,OAAO,GAAG,CAAC,CAAC,IAAI,CAAA;YACjB,CAAC;iBAAM,CAAC;gBACP,MAAM,CAAC,GAAG,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,CAAE,CAAA;gBACzC,MAAM,OAAO,GAAG,WAAW,CAAC,MAAM,CAAC,CAAA,CAAC,8CAA8C;gBAClF,QAAQ,GAAG,aAAa,CAAC,MAAM,EAAE,CAAC,EAAE,OAAO,CAAC,CAAA;gBAC5C,OAAO,GAAG,CAAC,CAAC,IAAI,CAAA;gBAEhB,IAAI,OAAO,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,QAAQ,CAAC,OAAO,CAAC,EAAE,CAAC;oBAChD,OAAO,EAAE,CAAA;oBAET,SAAQ;gBACT,CAAC;YACF,CAAC;YAED,MAAM,EAAE,GAAG,EAAE,UAAU,EAAE,GAAG,QAAQ,CAAA;YACpC,MAAM,SAAS,GAAG,OAAO,KAAK,IAAI,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,GAAG,OAAO,CAAC,WAAW,EAAE,IAAI,OAAO,EAAE,CAAA;YAEpF,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC;gBACjB,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,GAAG,EAAE,UAAU,EAAE,OAAO,EAAE,OAAO,EAAE,CAAC,GAAG,IAAI,CAAC,CAAA;gBAEnE,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,MAAM,SAAS,GAAiB;gBAC/B,GAAG;gBACH,UAAU;gBACV,OAAO,EAAE,OAAO;gBAChB,MAAM,EAAE,SAAS;gBACjB,MAAM;gBACN,SAAS,EAAE,cAAc,CAAC,MAAM,EAAE,UAAU,CAAC;gBAC7C,cAAc,EAAE,OAAO;gBACvB,OAAO,EAAE,wFAAwF;aACjG,CAAA;YAED,MAAM,OAAO,GAAG,QAAQ,CAAC,SAAS,CAAC,CAAA;YAEnC,IAAI,OAAO,CAAC,IAAI,KAAK,SAAS,IAAI,CAAC,OAAO,CAAC,GAAG,EAAE,CAAC;gBAChD,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,GAAG,OAAO,CAAC,GAAG,EAAE,YAAY,EAAE,SAAS,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,GAAG,IAAI,CAAC,CAAA;YAE9F,OAAO,EAAE,CAAA;QACV,CAAC;QAED,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;IAC5B,CAAC;CACD,CAAA"}
|
|
@@ -1,22 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `cz-pcfirst-preposition` — the Czech pc-first prepositional-locality shard, fourth orthography
|
|
7
|
-
* of the #901 leading-name-boundary family. The #897 close-out read all 8 residual CZ rows as one
|
|
8
|
-
* class: a LEADING postcode mis-assigned as house_number while the multi-word "nad/pod/u X"
|
|
9
|
-
* locality shatters ("51244 Rokytnice nad Jizerou, Dolní Rokytnice 111" → street
|
|
10
|
-
* 'RokytnicenadJizerou' + house_number '51244'). That leading-5-digit confusion is the
|
|
11
|
-
* anchor-pollution class whose decode-time OVERRIDE was correctly killed in #723 — this shard is
|
|
12
|
-
* the model-first fix as DATA: real prepositional localities in the order that breaks, so the
|
|
13
|
-
* model learns that a leading postcode before a multi-word name is a postcode. pc-first leads the
|
|
14
|
-
* cycle (the lesson); canonical and city-first keep the polarity balanced (the v1.9.9 lesson).
|
|
15
|
-
*/
|
|
16
|
-
import { type ShardRecipe } from "./scaffold.ts";
|
|
17
|
-
/**
|
|
18
|
-
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
19
|
-
* and `description` below for the surface form it generates.
|
|
20
|
-
*/
|
|
21
|
-
export declare const czPcFirstPrepositionRecipe: ShardRecipe;
|
|
22
|
-
//# sourceMappingURL=cz-pcfirst-preposition.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"cz-pcfirst-preposition.d.ts","sourceRoot":"","sources":["../../../src/shard-recipes/cz-pcfirst-preposition.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;GAcG;AAEH,OAAO,EAA6C,KAAK,WAAW,EAAiB,MAAM,eAAe,CAAA;AAS1G;;;GAGG;AACH,eAAO,MAAM,0BAA0B,EAAE,WAiFxC,CAAA"}
|
|
@@ -1,100 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `cz-pcfirst-preposition` — the Czech pc-first prepositional-locality shard, fourth orthography
|
|
7
|
-
* of the #901 leading-name-boundary family. The #897 close-out read all 8 residual CZ rows as one
|
|
8
|
-
* class: a LEADING postcode mis-assigned as house_number while the multi-word "nad/pod/u X"
|
|
9
|
-
* locality shatters ("51244 Rokytnice nad Jizerou, Dolní Rokytnice 111" → street
|
|
10
|
-
* 'RokytnicenadJizerou' + house_number '51244'). That leading-5-digit confusion is the
|
|
11
|
-
* anchor-pollution class whose decode-time OVERRIDE was correctly killed in #723 — this shard is
|
|
12
|
-
* the model-first fix as DATA: real prepositional localities in the order that breaks, so the
|
|
13
|
-
* model learns that a leading postcode before a multi-word name is a postcode. pc-first leads the
|
|
14
|
-
* cycle (the lesson); canonical and city-first keep the polarity balanced (the v1.9.9 lesson).
|
|
15
|
-
*/
|
|
16
|
-
import { alignAndWrite, makeMulberry32, readTuples, shardSourceID } from "./scaffold.js";
|
|
17
|
-
/**
|
|
18
|
-
* The order-cycle slot for the STREET-LESS form (`«city» «pc», Česko`) — the exact surface of the
|
|
19
|
-
* `cz-full-praha-100-00` board row, whose absence from the street-bearing orders was the v4.5.0 no-promote's measured
|
|
20
|
-
* gap.
|
|
21
|
-
*/
|
|
22
|
-
const STREETLESS_ORDER = 3;
|
|
23
|
-
/**
|
|
24
|
-
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
25
|
-
* and `description` below for the surface form it generates.
|
|
26
|
-
*/
|
|
27
|
-
export const czPcFirstPrepositionRecipe = {
|
|
28
|
-
name: "cz-pcfirst-preposition",
|
|
29
|
-
description: "CZ pc-first + prepositional locality (#901 family): '«pc» «city nad X», «st» «n»' — the #723 class as data",
|
|
30
|
-
mode: "tuples",
|
|
31
|
-
async run(opts, write) {
|
|
32
|
-
makeMulberry32(opts.seed);
|
|
33
|
-
let read = 0;
|
|
34
|
-
let emitted = 0;
|
|
35
|
-
let skipped = 0;
|
|
36
|
-
for await (const t of readTuples(opts.input)) {
|
|
37
|
-
read++;
|
|
38
|
-
const street = String(t.street ?? "").trim();
|
|
39
|
-
const city = String(t.locality ?? "").trim();
|
|
40
|
-
const number = String(t.number ?? "").trim();
|
|
41
|
-
const postcode = String(t.postcode ?? "").trim();
|
|
42
|
-
if (!street || !city || !number || !postcode) {
|
|
43
|
-
skipped++;
|
|
44
|
-
continue;
|
|
45
|
-
}
|
|
46
|
-
const order = read % 4;
|
|
47
|
-
// The OFFICIAL Czech rendering spaces the PSČ as `NNN NN` ('512 44'); OpenAddresses stores it
|
|
48
|
-
// unspaced ('51244'), and a model trained only on the source form reads the spaced surface as
|
|
49
|
-
// house_number + garbage (the 'Praha 100 00' mangle). Alternate the two renderings so both
|
|
50
|
-
// orthographies are attested — the LABEL is the postcode either way.
|
|
51
|
-
const spaced = read % 2 === 0 && /^\d{5}$/.test(postcode);
|
|
52
|
-
const postcodeSurface = spaced ? `${postcode.slice(0, 3)} ${postcode.slice(3)}` : postcode;
|
|
53
|
-
let raw;
|
|
54
|
-
const components = order === STREETLESS_ORDER
|
|
55
|
-
? { locality: city, postcode: postcodeSurface, country: "Česko" }
|
|
56
|
-
: { street, house_number: number, postcode: postcodeSurface, locality: city };
|
|
57
|
-
if (order === 0) {
|
|
58
|
-
raw = `${postcodeSurface} ${city}, ${street} ${number}`;
|
|
59
|
-
}
|
|
60
|
-
else if (order === 1) {
|
|
61
|
-
raw = `${street} ${number}, ${postcodeSurface} ${city}`;
|
|
62
|
-
}
|
|
63
|
-
else if (order === 2) {
|
|
64
|
-
raw = `${city}, ${postcodeSurface}, ${street} ${number}`;
|
|
65
|
-
}
|
|
66
|
-
else {
|
|
67
|
-
// order === STREETLESS_ORDER: the street-less form — `«city» «pc», Česko` — the exact surface of the
|
|
68
|
-
// cz-full-praha-100-00 board row. The v4.5.0 no-promote receipt measured the gap: every
|
|
69
|
-
// prior order was street-bearing, so the model never saw a spaced PSČ beside a bare
|
|
70
|
-
// locality and mangled 'Praha 100 00, Czechia' into house_number spans. Street/number
|
|
71
|
-
// stay OUT of the components for this form (they are not in the surface).
|
|
72
|
-
raw = `${city} ${postcodeSurface}, Česko`;
|
|
73
|
-
}
|
|
74
|
-
const source_id = shardSourceID("synth-cz-pcfirst-preposition", {
|
|
75
|
-
...components,
|
|
76
|
-
o: String(order),
|
|
77
|
-
s: spaced ? "1" : "0",
|
|
78
|
-
v: String(read),
|
|
79
|
-
});
|
|
80
|
-
const canonical = {
|
|
81
|
-
raw,
|
|
82
|
-
components,
|
|
83
|
-
country: "CZ",
|
|
84
|
-
locale: "cs-CZ",
|
|
85
|
-
source: "synth-cz-pcfirst-preposition",
|
|
86
|
-
source_id,
|
|
87
|
-
corpus_version: "0.10.0",
|
|
88
|
-
license: "Synthetic — cz-pcfirst-preposition; (street, number, postcode, city) from OpenAddresses CZ (per-source attribution in the model card)",
|
|
89
|
-
};
|
|
90
|
-
if (alignAndWrite(write, canonical, "cz-pcfirst-preposition")) {
|
|
91
|
-
emitted++;
|
|
92
|
-
}
|
|
93
|
-
else {
|
|
94
|
-
skipped++;
|
|
95
|
-
}
|
|
96
|
-
}
|
|
97
|
-
return { read, emitted, skipped };
|
|
98
|
-
},
|
|
99
|
-
};
|
|
100
|
-
//# sourceMappingURL=cz-pcfirst-preposition.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"cz-pcfirst-preposition.js","sourceRoot":"","sources":["../../../src/shard-recipes/cz-pcfirst-preposition.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;GAcG;AAEH,OAAO,EAAE,aAAa,EAAE,cAAc,EAAE,UAAU,EAAoB,aAAa,EAAE,MAAM,eAAe,CAAA;AAE1G;;;;GAIG;AACH,MAAM,gBAAgB,GAAG,CAAC,CAAA;AAE1B;;;GAGG;AACH,MAAM,CAAC,MAAM,0BAA0B,GAAgB;IACtD,IAAI,EAAE,wBAAwB;IAC9B,WAAW,EACV,4GAA4G;IAC7G,IAAI,EAAE,QAAQ;IACd,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACzB,IAAI,IAAI,GAAG,CAAC,CAAA;QACZ,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QAEf,IAAI,KAAK,EAAE,MAAM,CAAC,IAAI,UAAU,CAAC,IAAI,CAAC,KAAM,CAAC,EAAE,CAAC;YAC/C,IAAI,EAAE,CAAA;YACN,MAAM,MAAM,GAAG,MAAM,CAAC,CAAC,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAC5C,MAAM,IAAI,GAAG,MAAM,CAAC,CAAC,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAC5C,MAAM,MAAM,GAAG,MAAM,CAAC,CAAC,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAC5C,MAAM,QAAQ,GAAG,MAAM,CAAC,CAAC,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAEhD,IAAI,CAAC,MAAM,IAAI,CAAC,IAAI,IAAI,CAAC,MAAM,IAAI,CAAC,QAAQ,EAAE,CAAC;gBAC9C,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,MAAM,KAAK,GAAG,IAAI,GAAG,CAAC,CAAA;YACtB,8FAA8F;YAC9F,8FAA8F;YAC9F,2FAA2F;YAC3F,qEAAqE;YACrE,MAAM,MAAM,GAAG,IAAI,GAAG,CAAC,KAAK,CAAC,IAAI,SAAS,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAA;YACzD,MAAM,eAAe,GAAG,MAAM,CAAC,CAAC,CAAC,GAAG,QAAQ,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,QAAQ,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,QAAQ,CAAA;YAC1F,IAAI,GAAW,CAAA;YAEf,MAAM,UAAU,GACf,KAAK,KAAK,gBAAgB;gBACzB,CAAC,CAAC,EAAE,QAAQ,EAAE,IAAI,EAAE,QAAQ,EAAE,eAAe,EAAE,OAAO,EAAE,OAAO,EAAE;gBACjE,CAAC,CAAC,EAAE,MAAM,EAAE,YAAY,EAAE,MAAM,EAAE,QAAQ,EAAE,eAAe,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAA;YAE/E,IAAI,KAAK,KAAK,CAAC,EAAE,CAAC;gBACjB,GAAG,GAAG,GAAG,eAAe,IAAI,IAAI,KAAK,MAAM,IAAI,MAAM,EAAE,CAAA;YACxD,CAAC;iBAAM,IAAI,KAAK,KAAK,CAAC,EAAE,CAAC;gBACxB,GAAG,GAAG,GAAG,MAAM,IAAI,MAAM,KAAK,eAAe,IAAI,IAAI,EAAE,CAAA;YACxD,CAAC;iBAAM,IAAI,KAAK,KAAK,CAAC,EAAE,CAAC;gBACxB,GAAG,GAAG,GAAG,IAAI,KAAK,eAAe,KAAK,MAAM,IAAI,MAAM,EAAE,CAAA;YACzD,CAAC;iBAAM,CAAC;gBACP,qGAAqG;gBACrG,wFAAwF;gBACxF,oFAAoF;gBACpF,sFAAsF;gBACtF,0EAA0E;gBAC1E,GAAG,GAAG,GAAG,IAAI,IAAI,eAAe,SAAS,CAAA;YAC1C,CAAC;YAED,MAAM,SAAS,GAAG,aAAa,CAAC,8BAA8B,EAAE;gBAC/D,GAAG,UAAU;gBACb,CAAC,EAAE,MAAM,CAAC,KAAK,CAAC;gBAChB,CAAC,EAAE,MAAM,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,GAAG;gBACrB,CAAC,EAAE,MAAM,CAAC,IAAI,CAAC;aACf,CAAC,CAAA;YAEF,MAAM,SAAS,GAAG;gBACjB,GAAG;gBACH,UAAU;gBACV,OAAO,EAAE,IAAI;gBACb,MAAM,EAAE,OAAO;gBACf,MAAM,EAAE,8BAA8B;gBACtC,SAAS;gBACT,cAAc,EAAE,QAAQ;gBACxB,OAAO,EACN,uIAAuI;aACxI,CAAA;YAED,IAAI,aAAa,CAAC,KAAK,EAAE,SAAS,EAAE,wBAAwB,CAAC,EAAE,CAAC;gBAC/D,OAAO,EAAE,CAAA;YACV,CAAC;iBAAM,CAAC;gBACP,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;QAED,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;IAClC,CAAC;CACD,CAAA"}
|
|
@@ -1,38 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `fr-admin-split` shard recipe — the FR admin-split coverage shard (night 2026-06-19,
|
|
7
|
-
* surpass-v1.5.0). Teaches the model to SPLIT the département out of the locality on
|
|
8
|
-
* bare/space/comma-delimited French place rows — the admin-deciding failure class the pre-GPU
|
|
9
|
-
* self-validation proved moves the resolved coordinate (collision communes −61%; see
|
|
10
|
-
* docs/articles/evals/experiments/2026-06-19-fr-admin-split-prevalidation.md). Ported from
|
|
11
|
-
* scripts/build-fr-admin-split-shard.mjs.
|
|
12
|
-
*
|
|
13
|
-
* Failure shapes (the model currently mis-handles all of these):
|
|
14
|
-
*
|
|
15
|
-
* - `Thauron, Creuse` → région dropped to null (the comma+full-name miss)
|
|
16
|
-
* - `Montredon, Lozère` → région = "ère" (the diacritic subword split, #727)
|
|
17
|
-
* - (AU analog) `CANBERRA ACT` → the space-delimited admin fuse
|
|
18
|
-
*
|
|
19
|
-
* The département is the essential admin unit for FR postal geography and maps to the `region`
|
|
20
|
-
* component tag in our schema. We derive it DETERMINISTICALLY from the real postcode via codex
|
|
21
|
-
* `departementForCodePostal` (first two digits = département) — salvage-first, no re-derived
|
|
22
|
-
* table.
|
|
23
|
-
*
|
|
24
|
-
* Data (`--communes`, opts.communes): REAL BAN (Base Adresse Nationale) commune+postcode+coord
|
|
25
|
-
* tuples, one per line, TAB-separated `commune <TAB> postcode <TAB> lon <TAB> lat`. Build the
|
|
26
|
-
* input TSV once from the BAN staging CSV (see the legacy script header). Anchor-ON by
|
|
27
|
-
* construction: rows carry a REAL postcode token in `raw` + a `postcode` component, so the
|
|
28
|
-
* training loader paints the anchor feature onto that span automatically. The trailing-postcode
|
|
29
|
-
* anchor REINFORCES the FR split (FR postcode is trailing, unlike German PLZ-leading — the v0.9.2
|
|
30
|
-
* scar is positional, not universal).
|
|
31
|
-
*/
|
|
32
|
-
import { type ShardRecipe } from "./scaffold.ts";
|
|
33
|
-
/**
|
|
34
|
-
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
35
|
-
* and `description` below for the surface form it generates.
|
|
36
|
-
*/
|
|
37
|
-
export declare const frAdminSplitRecipe: ShardRecipe;
|
|
38
|
-
//# sourceMappingURL=fr-admin-split.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"fr-admin-split.d.ts","sourceRoot":"","sources":["../../../src/shard-recipes/fr-admin-split.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8BG;AAWH,OAAO,EAAkB,KAAK,WAAW,EAAE,MAAM,eAAe,CAAA;AAwGhE;;;GAGG;AACH,eAAO,MAAM,kBAAkB,EAAE,WAyFhC,CAAA"}
|