@mailwoman/corpus 9.2.0 → 9.4.0
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/recipes/anchor-absorption.ts +101 -0
- package/lib/recipes/bare-country.ts +95 -0
- package/lib/recipes/boundary-stress.ts +102 -0
- package/lib/recipes/cn-organizational-units.ts +199 -0
- package/lib/recipes/country-balanced.ts +510 -0
- package/lib/recipes/cz-pcfirst-preposition.ts +112 -0
- package/lib/recipes/fr-admin-split.ts +243 -0
- package/lib/recipes/fr-bare-street.ts +171 -0
- package/lib/recipes/fr-fragment.ts +334 -0
- package/lib/recipes/fr-lieudit.ts +301 -0
- package/lib/recipes/fr-order.ts +246 -0
- package/lib/recipes/german.ts +360 -0
- package/lib/recipes/house-venue.ts +93 -0
- package/lib/recipes/index.ts +97 -0
- package/lib/recipes/intersection.ts +619 -0
- package/lib/recipes/locale.ts +600 -0
- package/lib/recipes/nl-postcode.ts +117 -0
- package/lib/recipes/no-fragment.ts +213 -0
- package/lib/recipes/no-street-led.ts +135 -0
- package/lib/recipes/no-street.ts +91 -0
- package/lib/recipes/po-box-cedex.ts +976 -0
- package/lib/recipes/po-box.ts +124 -0
- package/lib/recipes/reviewed-postcode-tail.ts +190 -0
- package/lib/recipes/scaffold.ts +468 -0
- package/lib/recipes/si-bare-village.ts +99 -0
- package/lib/recipes/street-affix.ts +805 -0
- package/lib/recipes/street-bare.ts +102 -0
- package/lib/recipes/street.ts +83 -0
- package/lib/recipes/sub-venue-sources.ts +878 -0
- package/lib/recipes/sub-venue.ts +998 -0
- package/lib/recipes/trailing-region.ts +178 -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/acra-sg.ts +174 -0
- package/lib/tools/fetch/ban.ts +289 -0
- package/lib/tools/fetch/download.ts +477 -0
- package/lib/tools/fetch/gcis-tw.ts +175 -0
- package/lib/tools/fetch/geonames-dump.ts +257 -0
- package/lib/tools/fetch/geonames-postal.ts +180 -0
- package/lib/tools/fetch/houjin-jp.ts +135 -0
- package/lib/tools/fetch/hrsa.ts +59 -0
- package/lib/tools/fetch/imls-pls.ts +149 -0
- package/lib/tools/fetch/index.ts +174 -0
- package/lib/tools/fetch/juso-kr.ts +165 -0
- package/lib/tools/fetch/localdata-kr.ts +194 -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 +686 -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/recipes/anchor-absorption.d.ts +20 -0
- package/out/recipes/anchor-absorption.d.ts.map +1 -0
- package/out/recipes/anchor-absorption.js +82 -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 +88 -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 +84 -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 +394 -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 +101 -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 +144 -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 +277 -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 +198 -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 +289 -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 +74 -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 +453 -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 +103 -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 +183 -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 +114 -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 +72 -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 +768 -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 +101 -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 +323 -0
- package/out/recipes/scaffold.d.ts.map +1 -0
- package/out/recipes/scaffold.js +174 -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 +89 -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 +87 -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 +70 -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 +654 -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 +726 -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 +158 -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 +231 -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/acra-sg.d.ts +23 -0
- package/out/tools/fetch/acra-sg.d.ts.map +1 -0
- package/out/tools/fetch/acra-sg.js +126 -0
- package/out/tools/fetch/acra-sg.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 +182 -0
- package/out/tools/fetch/download.d.ts.map +1 -0
- package/out/tools/fetch/download.js +318 -0
- package/out/tools/fetch/download.js.map +1 -0
- package/out/tools/fetch/gcis-tw.d.ts +23 -0
- package/out/tools/fetch/gcis-tw.d.ts.map +1 -0
- package/out/tools/fetch/gcis-tw.js +135 -0
- package/out/tools/fetch/gcis-tw.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/houjin-jp.d.ts +24 -0
- package/out/tools/fetch/houjin-jp.d.ts.map +1 -0
- package/out/tools/fetch/houjin-jp.js +102 -0
- package/out/tools/fetch/houjin-jp.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 +171 -0
- package/out/tools/fetch/index.d.ts.map +1 -0
- package/out/tools/fetch/index.js +170 -0
- package/out/tools/fetch/index.js.map +1 -0
- package/out/tools/fetch/juso-kr.d.ts +30 -0
- package/out/tools/fetch/juso-kr.d.ts.map +1 -0
- package/out/tools/fetch/juso-kr.js +120 -0
- package/out/tools/fetch/juso-kr.js.map +1 -0
- package/out/tools/fetch/localdata-kr.d.ts +30 -0
- package/out/tools/fetch/localdata-kr.d.ts.map +1 -0
- package/out/tools/fetch/localdata-kr.js +139 -0
- package/out/tools/fetch/localdata-kr.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 +439 -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
package/out/env.d.ts
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Environment variables the corpus build and its acquisition tooling read.
|
|
7
|
+
*/
|
|
8
|
+
import { z } from "zod";
|
|
9
|
+
/**
|
|
10
|
+
* Corpus build settings.
|
|
11
|
+
*/
|
|
12
|
+
export declare const PublicCorpusEnvSchema: z.ZodObject<{
|
|
13
|
+
MAILWOMAN_RESUME: z.ZodOptional<z.ZodString>;
|
|
14
|
+
}, z.core.$strip>;
|
|
15
|
+
/**
|
|
16
|
+
* Credentials the corpus acquisition and golden-expansion tooling send. Never log their values.
|
|
17
|
+
*/
|
|
18
|
+
export declare const PrivateCorpusEnvSchema: z.ZodObject<{
|
|
19
|
+
OA_BATCH_TOKEN: z.ZodOptional<z.ZodString>;
|
|
20
|
+
DEEPSEEK_API_KEY: z.ZodOptional<z.ZodString>;
|
|
21
|
+
ANTHROPIC_API_KEY: z.ZodOptional<z.ZodString>;
|
|
22
|
+
}, z.core.$strip>;
|
|
23
|
+
/**
|
|
24
|
+
* Live corpus settings over core's, sharing core's getters and cached values.
|
|
25
|
+
*/
|
|
26
|
+
export declare const $public: Record<never, never> & {
|
|
27
|
+
MAILWOMAN_DATA_ROOT: string;
|
|
28
|
+
MAILWOMAN_CONFIG_ROOT: string;
|
|
29
|
+
MAILWOMAN_CACHE_ROOT: string;
|
|
30
|
+
MAILWOMAN_TEMP_ROOT: string;
|
|
31
|
+
MAILWOMAN_DOCS_URL?: string | undefined;
|
|
32
|
+
MAILWOMAN_LICENSE_KEY?: string | undefined;
|
|
33
|
+
MAILWOMAN_LICENSE_URL?: string | undefined;
|
|
34
|
+
MAILWOMAN_COARSE_PLACER_DIR?: string | undefined;
|
|
35
|
+
} & {
|
|
36
|
+
MAILWOMAN_RESUME?: string | undefined;
|
|
37
|
+
};
|
|
38
|
+
/**
|
|
39
|
+
* Live corpus credentials over core's. Never log their values.
|
|
40
|
+
*/
|
|
41
|
+
export declare const $private: Record<never, never> & Record<string, never> & {
|
|
42
|
+
OA_BATCH_TOKEN?: string | undefined;
|
|
43
|
+
DEEPSEEK_API_KEY?: string | undefined;
|
|
44
|
+
ANTHROPIC_API_KEY?: string | undefined;
|
|
45
|
+
};
|
|
46
|
+
//# sourceMappingURL=env.d.ts.map
|
package/out/env.d.ts.map
ADDED
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"env.d.ts","sourceRoot":"","sources":["../lib/env.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAGH,OAAO,EAAE,CAAC,EAAE,MAAM,KAAK,CAAA;AAEvB;;GAEG;AACH,eAAO,MAAM,qBAAqB;;iBAKhC,CAAA;AAEF;;GAEG;AACH,eAAO,MAAM,sBAAsB;;;;iBAejC,CAAA;AAEF;;GAEG;AACH,eAAO,MAAM,OAAO;;;;;;;;;;;CAA6C,CAAA;AAEjE;;GAEG;AACH,eAAO,MAAM,QAAQ;;;;CAA+C,CAAA"}
|
package/out/env.js
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Environment variables the corpus build and its acquisition tooling read.
|
|
7
|
+
*/
|
|
8
|
+
import { $private as corePrivate, $public as corePublic, liveEnv } from "@mailwoman/core/env";
|
|
9
|
+
import { z } from "zod";
|
|
10
|
+
/**
|
|
11
|
+
* Corpus build settings.
|
|
12
|
+
*/
|
|
13
|
+
export const PublicCorpusEnvSchema = z.object({
|
|
14
|
+
MAILWOMAN_RESUME: z.string().optional().meta({
|
|
15
|
+
title: "Build resume",
|
|
16
|
+
description: "Resume-state override used by corpus build tooling.",
|
|
17
|
+
}),
|
|
18
|
+
});
|
|
19
|
+
/**
|
|
20
|
+
* Credentials the corpus acquisition and golden-expansion tooling send. Never log their values.
|
|
21
|
+
*/
|
|
22
|
+
export const PrivateCorpusEnvSchema = z.object({
|
|
23
|
+
// OpenAddresses batch-download API token (`corpus/lib/tools/fetch/openaddresses.ts`).
|
|
24
|
+
OA_BATCH_TOKEN: z.string().optional().meta({
|
|
25
|
+
title: "OpenAddresses batch token",
|
|
26
|
+
description: "API token used by the OpenAddresses batch-download corpus fetcher.",
|
|
27
|
+
}),
|
|
28
|
+
// LLM API keys for the corpus golden-expansion tooling.
|
|
29
|
+
DEEPSEEK_API_KEY: z.string().optional().meta({
|
|
30
|
+
title: "DeepSeek API key",
|
|
31
|
+
description: "API key used by corpus golden-expansion tooling when calling DeepSeek.",
|
|
32
|
+
}),
|
|
33
|
+
ANTHROPIC_API_KEY: z.string().optional().meta({
|
|
34
|
+
title: "Anthropic API key",
|
|
35
|
+
description: "API key used by corpus golden-expansion tooling when calling Anthropic.",
|
|
36
|
+
}),
|
|
37
|
+
});
|
|
38
|
+
/**
|
|
39
|
+
* Live corpus settings over core's, sharing core's getters and cached values.
|
|
40
|
+
*/
|
|
41
|
+
export const $public = liveEnv(PublicCorpusEnvSchema, corePublic);
|
|
42
|
+
/**
|
|
43
|
+
* Live corpus credentials over core's. Never log their values.
|
|
44
|
+
*/
|
|
45
|
+
export const $private = liveEnv(PrivateCorpusEnvSchema, corePrivate);
|
|
46
|
+
//# sourceMappingURL=env.js.map
|
package/out/env.js.map
ADDED
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"env.js","sourceRoot":"","sources":["../lib/env.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH,OAAO,EAAE,QAAQ,IAAI,WAAW,EAAE,OAAO,IAAI,UAAU,EAAE,OAAO,EAAE,MAAM,qBAAqB,CAAA;AAC7F,OAAO,EAAE,CAAC,EAAE,MAAM,KAAK,CAAA;AAEvB;;GAEG;AACH,MAAM,CAAC,MAAM,qBAAqB,GAAG,CAAC,CAAC,MAAM,CAAC;IAC7C,gBAAgB,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE,CAAC,IAAI,CAAC;QAC5C,KAAK,EAAE,cAAc;QACrB,WAAW,EAAE,qDAAqD;KAClE,CAAC;CACF,CAAC,CAAA;AAEF;;GAEG;AACH,MAAM,CAAC,MAAM,sBAAsB,GAAG,CAAC,CAAC,MAAM,CAAC;IAC9C,sFAAsF;IACtF,cAAc,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE,CAAC,IAAI,CAAC;QAC1C,KAAK,EAAE,2BAA2B;QAClC,WAAW,EAAE,oEAAoE;KACjF,CAAC;IACF,wDAAwD;IACxD,gBAAgB,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE,CAAC,IAAI,CAAC;QAC5C,KAAK,EAAE,kBAAkB;QACzB,WAAW,EAAE,wEAAwE;KACrF,CAAC;IACF,iBAAiB,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE,CAAC,IAAI,CAAC;QAC7C,KAAK,EAAE,mBAAmB;QAC1B,WAAW,EAAE,yEAAyE;KACtF,CAAC;CACF,CAAC,CAAA;AAEF;;GAEG;AACH,MAAM,CAAC,MAAM,OAAO,GAAG,OAAO,CAAC,qBAAqB,EAAE,UAAU,CAAC,CAAA;AAEjE;;GAEG;AACH,MAAM,CAAC,MAAM,QAAQ,GAAG,OAAO,CAAC,sBAAsB,EAAE,WAAW,CAAC,CAAA"}
|
package/out/index.d.ts
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*/
|
|
6
|
+
export * from "#adapters/utils/index";
|
|
7
|
+
export * from "#adapters/gnaf/assemble";
|
|
8
|
+
export * from "#adapters/index";
|
|
9
|
+
export * from "#build";
|
|
10
|
+
export * from "#runner";
|
|
11
|
+
export * from "#recipes/index";
|
|
12
|
+
export * from "#types";
|
|
13
|
+
//# sourceMappingURL=index.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../lib/index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,cAAc,uBAAuB,CAAA;AACrC,cAAc,yBAAyB,CAAA;AACvC,cAAc,iBAAiB,CAAA;AAC/B,cAAc,QAAQ,CAAA;AACtB,cAAc,SAAS,CAAA;AACvB,cAAc,gBAAgB,CAAA;AAC9B,cAAc,QAAQ,CAAA"}
|
package/out/index.js
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*/
|
|
6
|
+
export * from "#adapters/utils/index";
|
|
7
|
+
export * from "#adapters/gnaf/assemble";
|
|
8
|
+
export * from "#adapters/index";
|
|
9
|
+
export * from "#build";
|
|
10
|
+
export * from "#runner";
|
|
11
|
+
export * from "#recipes/index";
|
|
12
|
+
export * from "#types";
|
|
13
|
+
//# sourceMappingURL=index.js.map
|
package/out/index.js.map
ADDED
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"index.js","sourceRoot":"","sources":["../lib/index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,cAAc,uBAAuB,CAAA;AACrC,cAAc,yBAAyB,CAAA;AACvC,cAAc,iBAAiB,CAAA;AAC/B,cAAc,QAAQ,CAAA;AACtB,cAAc,SAAS,CAAA;AACvB,cAAc,gBAAgB,CAAA;AAC9B,cAAc,QAAQ,CAAA"}
|
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* `anchor-absorption` slice recipe (#220/#723, Probe A1) — self-generates `--count` rows from
|
|
7
|
+
* {@link synthesizeAnchorAbsorptionRow}'s 6-slice mix (CASE-H / CASE-P-us-rural / CASE-P-de /
|
|
8
|
+
* anchor-fp / locale-ambig / standard), aligns each to BIO, and emits a labeled JSONL. The
|
|
9
|
+
* LEADING 5-digit on CASE-H/anchor-fp/locale-ambig is sampled from the REAL US ZIPs in the
|
|
10
|
+
* postcode-anchor lookup, so the shaped-painted anchor fires on it exactly as inference does —
|
|
11
|
+
* teaching the model to OVERRIDE a present anchor from context. Ported from
|
|
12
|
+
* scripts/build-anchor-absorption-slice.mjs.
|
|
13
|
+
*/
|
|
14
|
+
import { type CorpusRecipe } from "#recipes/scaffold";
|
|
15
|
+
/**
|
|
16
|
+
* Slice recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
17
|
+
* and `description` below for the surface form it generates.
|
|
18
|
+
*/
|
|
19
|
+
export declare const anchorAbsorptionRecipe: CorpusRecipe;
|
|
20
|
+
//# sourceMappingURL=anchor-absorption.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"anchor-absorption.d.ts","sourceRoot":"","sources":["../../lib/recipes/anchor-absorption.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;GAYG;AAOH,OAAO,EAAiB,KAAK,YAAY,EAAE,MAAM,mBAAmB,CAAA;AAyBpE;;;GAGG;AACH,eAAO,MAAM,sBAAsB,EAAE,YAoDpC,CAAA"}
|
|
@@ -0,0 +1,82 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* `anchor-absorption` slice recipe (#220/#723, Probe A1) — self-generates `--count` rows from
|
|
7
|
+
* {@link synthesizeAnchorAbsorptionRow}'s 6-slice mix (CASE-H / CASE-P-us-rural / CASE-P-de /
|
|
8
|
+
* anchor-fp / locale-ambig / standard), aligns each to BIO, and emits a labeled JSONL. The
|
|
9
|
+
* LEADING 5-digit on CASE-H/anchor-fp/locale-ambig is sampled from the REAL US ZIPs in the
|
|
10
|
+
* postcode-anchor lookup, so the shaped-painted anchor fires on it exactly as inference does —
|
|
11
|
+
* teaching the model to OVERRIDE a present anchor from context. Ported from
|
|
12
|
+
* scripts/build-anchor-absorption-slice.mjs.
|
|
13
|
+
*/
|
|
14
|
+
import { dataRootPath } from "@mailwoman/core/data-root";
|
|
15
|
+
import { readLocalJSONFile } from "@mailwoman/core/fs/readers";
|
|
16
|
+
import { makeLcg } from "@mailwoman/core/utils";
|
|
17
|
+
import { sliceSourceID } from "#recipes/scaffold";
|
|
18
|
+
import { synthesizeAnchorAbsorptionRow } from "#synthesizers/anchor-absorption";
|
|
19
|
+
import { alignRow } from "#utils";
|
|
20
|
+
/**
|
|
21
|
+
* The leading-5-digit source: the real US ZIPs in the postcode anchor's pilot lookup. Resolved through the data-root
|
|
22
|
+
* helper (the lab default is `$MAILWOMAN_DATA_ROOT`), never re-hardcoded.
|
|
23
|
+
*/
|
|
24
|
+
const ANCHOR_LOOKUP = dataRootPath("anchor", "pilot-anchor-lookup.json");
|
|
25
|
+
/**
|
|
26
|
+
* The real US ZIPs in the anchor lookup (entries whose value is a `[{ US: … }]` candidate list).
|
|
27
|
+
*/
|
|
28
|
+
async function loadRealUsZips(path) {
|
|
29
|
+
const d = await readLocalJSONFile(path);
|
|
30
|
+
const zips = [];
|
|
31
|
+
for (const [pc, v] of Object.entries(d)) {
|
|
32
|
+
if (Array.isArray(v) && v[0] && typeof v[0] === "object" && "US" in v[0] && /^\d{5}$/.test(pc)) {
|
|
33
|
+
zips.push(pc);
|
|
34
|
+
}
|
|
35
|
+
}
|
|
36
|
+
return zips;
|
|
37
|
+
}
|
|
38
|
+
/**
|
|
39
|
+
* Slice recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
40
|
+
* and `description` below for the surface form it generates.
|
|
41
|
+
*/
|
|
42
|
+
export const anchorAbsorptionRecipe = {
|
|
43
|
+
name: "anchor-absorption",
|
|
44
|
+
description: "Anchor-absorption counter-augmentation (#220/#723): 6-slice mix → synthesizeAnchorAbsorptionRow",
|
|
45
|
+
mode: "generate",
|
|
46
|
+
async run(opts, write) {
|
|
47
|
+
// Emit PRNG: the legacy build-anchor-absorption-slice.mjs seeded an LCG (lcg(opts.seed)).
|
|
48
|
+
const random = makeLcg(opts.seed);
|
|
49
|
+
const source = opts.sourceName ?? "synth-anchor-absorption";
|
|
50
|
+
const count = opts.count ?? 50_000;
|
|
51
|
+
const realZips = await loadRealUsZips(ANCHOR_LOOKUP);
|
|
52
|
+
console.error(`Loaded ${realZips.length} real US ZIPs from the anchor lookup (the leading-5-digit source).`);
|
|
53
|
+
let written = 0;
|
|
54
|
+
let quarantined = 0;
|
|
55
|
+
const byTemplate = {};
|
|
56
|
+
for (let i = 0; i < count; i++) {
|
|
57
|
+
const synth = synthesizeAnchorAbsorptionRow({ random, realZips });
|
|
58
|
+
const country = synth.locale.split("-")[1];
|
|
59
|
+
// "en-US" -> "US", "de-DE" -> "DE"
|
|
60
|
+
const canonical = {
|
|
61
|
+
raw: synth.raw,
|
|
62
|
+
components: synth.components,
|
|
63
|
+
country,
|
|
64
|
+
locale: synth.locale,
|
|
65
|
+
source,
|
|
66
|
+
source_id: sliceSourceID(source, { v: String(i) }),
|
|
67
|
+
};
|
|
68
|
+
const aligned = alignRow(canonical);
|
|
69
|
+
if (aligned.kind !== "labeled") {
|
|
70
|
+
quarantined++;
|
|
71
|
+
continue;
|
|
72
|
+
}
|
|
73
|
+
write(JSON.stringify({ ...aligned.row, synth_method: "anchor-absorption", synth_template: synth.template }) + "\n");
|
|
74
|
+
written++;
|
|
75
|
+
byTemplate[synth.template] = (byTemplate[synth.template] ?? 0) + 1;
|
|
76
|
+
}
|
|
77
|
+
console.error(`\nwrote ${written} rows (${quarantined} quarantined)`);
|
|
78
|
+
console.error(" by slice:", JSON.stringify(byTemplate));
|
|
79
|
+
return { emitted: written, skipped: quarantined };
|
|
80
|
+
},
|
|
81
|
+
};
|
|
82
|
+
//# sourceMappingURL=anchor-absorption.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"anchor-absorption.js","sourceRoot":"","sources":["../../lib/recipes/anchor-absorption.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;GAYG;AAEH,OAAO,EAAE,YAAY,EAAE,MAAM,2BAA2B,CAAA;AACxD,OAAO,EAAE,iBAAiB,EAAE,MAAM,4BAA4B,CAAA;AAC9D,OAAO,EAAE,OAAO,EAAE,MAAM,uBAAuB,CAAA;AAG/C,OAAO,EAAE,aAAa,EAAqB,MAAM,mBAAmB,CAAA;AACpE,OAAO,EAAE,6BAA6B,EAAE,MAAM,iCAAiC,CAAA;AAC/E,OAAO,EAAE,QAAQ,EAAE,MAAM,QAAQ,CAAA;AACjC;;;GAGG;AACH,MAAM,aAAa,GAAG,YAAY,CAAC,QAAQ,EAAE,0BAA0B,CAAC,CAAA;AAExE;;GAEG;AACH,KAAK,UAAU,cAAc,CAAC,IAAqB;IAClD,MAAM,CAAC,GAAG,MAAM,iBAAiB,CAA0B,IAAI,CAAC,CAAA;IAChE,MAAM,IAAI,GAAa,EAAE,CAAA;IAEzB,KAAK,MAAM,CAAC,EAAE,EAAE,CAAC,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,CAAC;QACzC,IAAI,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,OAAO,CAAC,CAAC,CAAC,CAAC,KAAK,QAAQ,IAAI,IAAI,IAAK,CAAC,CAAC,CAAC,CAAY,IAAI,SAAS,CAAC,IAAI,CAAC,EAAE,CAAC,EAAE,CAAC;YAC5G,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAA;QACd,CAAC;IACF,CAAC;IAED,OAAO,IAAI,CAAA;AACZ,CAAC;AAED;;;GAGG;AACH,MAAM,CAAC,MAAM,sBAAsB,GAAiB;IACnD,IAAI,EAAE,mBAAmB;IACzB,WAAW,EAAE,iGAAiG;IAC9G,IAAI,EAAE,UAAU;IAChB,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,0FAA0F;QAC1F,MAAM,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACjC,MAAM,MAAM,GAAG,IAAI,CAAC,UAAU,IAAI,yBAAyB,CAAA;QAC3D,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,IAAI,MAAM,CAAA;QAClC,MAAM,QAAQ,GAAG,MAAM,cAAc,CAAC,aAAa,CAAC,CAAA;QAEpD,OAAO,CAAC,KAAK,CAAC,UAAU,QAAQ,CAAC,MAAM,oEAAoE,CAAC,CAAA;QAE5G,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,WAAW,GAAG,CAAC,CAAA;QACnB,MAAM,UAAU,GAA2B,EAAE,CAAA;QAE7C,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,KAAK,EAAE,CAAC,EAAE,EAAE,CAAC;YAChC,MAAM,KAAK,GAAG,6BAA6B,CAAC,EAAE,MAAM,EAAE,QAAQ,EAAE,CAAC,CAAA;YACjE,MAAM,OAAO,GAAG,KAAK,CAAC,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAA;YAE1C,mCAAmC;YACnC,MAAM,SAAS,GAAG;gBACjB,GAAG,EAAE,KAAK,CAAC,GAAG;gBACd,UAAU,EAAE,KAAK,CAAC,UAAU;gBAC5B,OAAO;gBACP,MAAM,EAAE,KAAK,CAAC,MAAM;gBACpB,MAAM;gBACN,SAAS,EAAE,aAAa,CAAC,MAAM,EAAE,EAAE,CAAC,EAAE,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC;aAClD,CAAA;YAED,MAAM,OAAO,GAAG,QAAQ,CAAC,SAA2C,CAAC,CAAA;YAErE,IAAI,OAAO,CAAC,IAAI,KAAK,SAAS,EAAE,CAAC;gBAChC,WAAW,EAAE,CAAA;gBAEb,SAAQ;YACT,CAAC;YAED,KAAK,CACJ,IAAI,CAAC,SAAS,CAAC,EAAE,GAAG,OAAO,CAAC,GAAG,EAAE,YAAY,EAAE,mBAAmB,EAAE,cAAc,EAAE,KAAK,CAAC,QAAQ,EAAE,CAAC,GAAG,IAAI,CAC5G,CAAA;YAED,OAAO,EAAE,CAAA;YACT,UAAU,CAAC,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC,UAAU,CAAC,KAAK,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAA;QACnE,CAAC;QAED,OAAO,CAAC,KAAK,CAAC,WAAW,OAAO,UAAU,WAAW,eAAe,CAAC,CAAA;QACrE,OAAO,CAAC,KAAK,CAAC,aAAa,EAAE,IAAI,CAAC,SAAS,CAAC,UAAU,CAAC,CAAC,CAAA;QAExD,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,WAAW,EAAE,CAAA;IAClD,CAAC;CACD,CAAA"}
|
|
@@ -0,0 +1,25 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* `bare-country` — the country name as the WHOLE query. Addresses almost never consist of one bare
|
|
7
|
+
* country name, so the class is out of the model's training distribution and the tag is a coin
|
|
8
|
+
* flip: measured on the 2026-08-13 panel, France/Germany/United States/New Zealand parsed
|
|
9
|
+
* `country` while Japan/China/Nigeria/Australia/Deutschland parsed `locality`. The retrieval-side
|
|
10
|
+
* bare-country race (#1651) covers the answer either way; this slice closes the PARSE half so the
|
|
11
|
+
* tag itself is right.
|
|
12
|
+
*
|
|
13
|
+
* Source is the codex country table — every ISO canonical English name plus the curated surface
|
|
14
|
+
* forms (endonyms and long-form names). The 2–3 letter CODES are deliberately excluded: a bare
|
|
15
|
+
* `JP` or `GER` is an abbreviation register with its own ambiguity surface (`IN`, `DE`, `TO` are
|
|
16
|
+
* English words), and teaching it here would be an unmeasured claim. Case augmentation is the
|
|
17
|
+
* loader's job, as everywhere.
|
|
18
|
+
*/
|
|
19
|
+
import { type CorpusRecipe } from "#recipes/scaffold";
|
|
20
|
+
/**
|
|
21
|
+
* Slice recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
22
|
+
* and `description` below for the surface form it generates.
|
|
23
|
+
*/
|
|
24
|
+
export declare const bareCountryRecipe: CorpusRecipe;
|
|
25
|
+
//# sourceMappingURL=bare-country.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"bare-country.d.ts","sourceRoot":"","sources":["../../lib/recipes/bare-country.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;GAiBG;AAKH,OAAO,EAAiB,KAAK,YAAY,EAAiB,MAAM,mBAAmB,CAAA;AA+BnF;;;GAGG;AACH,eAAO,MAAM,iBAAiB,EAAE,YAqC/B,CAAA"}
|
|
@@ -0,0 +1,88 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* `bare-country` — the country name as the WHOLE query. Addresses almost never consist of one bare
|
|
7
|
+
* country name, so the class is out of the model's training distribution and the tag is a coin
|
|
8
|
+
* flip: measured on the 2026-08-13 panel, France/Germany/United States/New Zealand parsed
|
|
9
|
+
* `country` while Japan/China/Nigeria/Australia/Deutschland parsed `locality`. The retrieval-side
|
|
10
|
+
* bare-country race (#1651) covers the answer either way; this slice closes the PARSE half so the
|
|
11
|
+
* tag itself is right.
|
|
12
|
+
*
|
|
13
|
+
* Source is the codex country table — every ISO canonical English name plus the curated surface
|
|
14
|
+
* forms (endonyms and long-form names). The 2–3 letter CODES are deliberately excluded: a bare
|
|
15
|
+
* `JP` or `GER` is an abbreviation register with its own ambiguity surface (`IN`, `DE`, `TO` are
|
|
16
|
+
* English words), and teaching it here would be an unmeasured claim. Case augmentation is the
|
|
17
|
+
* loader's job, as everywhere.
|
|
18
|
+
*/
|
|
19
|
+
import { COUNTRY_SURFACE_FORMS, CountryNames, matchCountry } from "@mailwoman/codex/country";
|
|
20
|
+
import { mulberry32 as makeMulberry32 } from "@mailwoman/core/utils";
|
|
21
|
+
import { alignAndWrite, sliceSourceID } from "#recipes/scaffold";
|
|
22
|
+
/**
|
|
23
|
+
* Surfaces shorter than this are the code register (`JP`, `GER`), not a name — excluded (see the module doc).
|
|
24
|
+
*/
|
|
25
|
+
const MIN_NAME_LENGTH = 4;
|
|
26
|
+
/**
|
|
27
|
+
* Every (surface, iso2) pair the slice emits: the ISO canonical names plus each country's curated surface forms,
|
|
28
|
+
* deduplicated on the surface string (a form shared across countries — none known — would keep its first bearer).
|
|
29
|
+
*/
|
|
30
|
+
function* bareCountrySurfaces() {
|
|
31
|
+
const seen = new Set();
|
|
32
|
+
for (const [iso2, forms] of Object.entries(COUNTRY_SURFACE_FORMS)) {
|
|
33
|
+
for (const surface of forms) {
|
|
34
|
+
if (surface.length < MIN_NAME_LENGTH || seen.has(surface))
|
|
35
|
+
continue;
|
|
36
|
+
seen.add(surface);
|
|
37
|
+
yield { surface, iso2 };
|
|
38
|
+
}
|
|
39
|
+
}
|
|
40
|
+
for (const name of CountryNames) {
|
|
41
|
+
if (name.length < MIN_NAME_LENGTH || seen.has(name))
|
|
42
|
+
continue;
|
|
43
|
+
const matched = matchCountry(name);
|
|
44
|
+
if (!matched)
|
|
45
|
+
continue;
|
|
46
|
+
seen.add(name);
|
|
47
|
+
yield { surface: name, iso2: matched.iso2 };
|
|
48
|
+
}
|
|
49
|
+
}
|
|
50
|
+
/**
|
|
51
|
+
* Slice recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
52
|
+
* and `description` below for the surface form it generates.
|
|
53
|
+
*/
|
|
54
|
+
export const bareCountryRecipe = {
|
|
55
|
+
name: "bare-country",
|
|
56
|
+
description: "The country name as the whole query (#1651 parse half): ISO names + curated endonyms, no codes",
|
|
57
|
+
mode: "generate",
|
|
58
|
+
async run(opts, write) {
|
|
59
|
+
// Seeded for parity with the other recipes; the surfaces themselves drive the content.
|
|
60
|
+
makeMulberry32(opts.seed);
|
|
61
|
+
let read = 0;
|
|
62
|
+
let emitted = 0;
|
|
63
|
+
let skipped = 0;
|
|
64
|
+
for (const { surface, iso2 } of bareCountrySurfaces()) {
|
|
65
|
+
read++;
|
|
66
|
+
const components = { country: surface };
|
|
67
|
+
const source_id = sliceSourceID("synth-bare-country", { country: surface, cc: iso2, v: String(read) });
|
|
68
|
+
const canonical = {
|
|
69
|
+
raw: surface,
|
|
70
|
+
components,
|
|
71
|
+
country: iso2,
|
|
72
|
+
locale: "und",
|
|
73
|
+
source: "synth-bare-country",
|
|
74
|
+
source_id,
|
|
75
|
+
corpus_version: "0.11.0",
|
|
76
|
+
license: "Synthetic — bare-country; surfaces from the codex country table (ISO 3166 + curated forms)",
|
|
77
|
+
};
|
|
78
|
+
if (alignAndWrite(write, canonical, "bare-country")) {
|
|
79
|
+
emitted++;
|
|
80
|
+
}
|
|
81
|
+
else {
|
|
82
|
+
skipped++;
|
|
83
|
+
}
|
|
84
|
+
}
|
|
85
|
+
return { read, emitted, skipped };
|
|
86
|
+
},
|
|
87
|
+
};
|
|
88
|
+
//# sourceMappingURL=bare-country.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"bare-country.js","sourceRoot":"","sources":["../../lib/recipes/bare-country.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;GAiBG;AAEH,OAAO,EAAE,qBAAqB,EAAE,YAAY,EAAE,YAAY,EAAE,MAAM,0BAA0B,CAAA;AAC5F,OAAO,EAAE,UAAU,IAAI,cAAc,EAAE,MAAM,uBAAuB,CAAA;AAEpE,OAAO,EAAE,aAAa,EAAqB,aAAa,EAAE,MAAM,mBAAmB,CAAA;AACnF;;GAEG;AACH,MAAM,eAAe,GAAG,CAAC,CAAA;AAEzB;;;GAGG;AACH,QAAQ,CAAC,CAAC,mBAAmB;IAC5B,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAA;IAE9B,KAAK,MAAM,CAAC,IAAI,EAAE,KAAK,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,qBAAqB,CAAC,EAAE,CAAC;QACnE,KAAK,MAAM,OAAO,IAAI,KAAK,EAAE,CAAC;YAC7B,IAAI,OAAO,CAAC,MAAM,GAAG,eAAe,IAAI,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC;gBAAE,SAAQ;YACnE,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,CAAA;YACjB,MAAM,EAAE,OAAO,EAAE,IAAI,EAAE,CAAA;QACxB,CAAC;IACF,CAAC;IAED,KAAK,MAAM,IAAI,IAAI,YAAY,EAAE,CAAC;QACjC,IAAI,IAAI,CAAC,MAAM,GAAG,eAAe,IAAI,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC;YAAE,SAAQ;QAC7D,MAAM,OAAO,GAAG,YAAY,CAAC,IAAI,CAAC,CAAA;QAElC,IAAI,CAAC,OAAO;YAAE,SAAQ;QACtB,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;QACd,MAAM,EAAE,OAAO,EAAE,IAAI,EAAE,IAAI,EAAE,OAAO,CAAC,IAAI,EAAE,CAAA;IAC5C,CAAC;AACF,CAAC;AAED;;;GAGG;AACH,MAAM,CAAC,MAAM,iBAAiB,GAAiB;IAC9C,IAAI,EAAE,cAAc;IACpB,WAAW,EAAE,gGAAgG;IAC7G,IAAI,EAAE,UAAU;IAChB,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,uFAAuF;QACvF,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,KAAK,MAAM,EAAE,OAAO,EAAE,IAAI,EAAE,IAAI,mBAAmB,EAAE,EAAE,CAAC;YACvD,IAAI,EAAE,CAAA;YAEN,MAAM,UAAU,GAA2B,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;YAC/D,MAAM,SAAS,GAAG,aAAa,CAAC,oBAAoB,EAAE,EAAE,OAAO,EAAE,OAAO,EAAE,EAAE,EAAE,IAAI,EAAE,CAAC,EAAE,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC,CAAA;YAEtG,MAAM,SAAS,GAAG;gBACjB,GAAG,EAAE,OAAO;gBACZ,UAAU;gBACV,OAAO,EAAE,IAAI;gBACb,MAAM,EAAE,KAAK;gBACb,MAAM,EAAE,oBAAoB;gBAC5B,SAAS;gBACT,cAAc,EAAE,QAAQ;gBACxB,OAAO,EAAE,4FAA4F;aACrG,CAAA;YAED,IAAI,aAAa,CAAC,KAAK,EAAE,SAAS,EAAE,cAAc,CAAC,EAAE,CAAC;gBACrD,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"}
|
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* `boundary-stress` slice recipe (#375) — the boundary-instability augmentation. Self-generates
|
|
7
|
+
* `--count` rows from {@link synthesizeBoundaryStressRow}'s weighted template mix (the v1.7.0,
|
|
8
|
+
* DeepSeek-tuned 2026-06-18 composition), aligns each to BIO, and emits a labeled JSONL. The
|
|
9
|
+
* change for the taxonomy's #1 parser family (the boundary-wobble class). Ported from
|
|
10
|
+
* scripts/build-boundary-stress-slice.mjs.
|
|
11
|
+
*
|
|
12
|
+
* `synthesizeBoundaryStressRow` is NOT re-exported from the corpus index — imported directly here.
|
|
13
|
+
*/
|
|
14
|
+
import { type CorpusRecipe } from "#recipes/scaffold";
|
|
15
|
+
/**
|
|
16
|
+
* Slice recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
17
|
+
* and `description` below for the surface form it generates.
|
|
18
|
+
*/
|
|
19
|
+
export declare const boundaryStressRecipe: CorpusRecipe;
|
|
20
|
+
//# sourceMappingURL=boundary-stress.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"boundary-stress.d.ts","sourceRoot":"","sources":["../../lib/recipes/boundary-stress.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;GAYG;AAIH,OAAO,EAAE,KAAK,YAAY,EAAiB,MAAM,mBAAmB,CAAA;AAoCpE;;;GAGG;AACH,eAAO,MAAM,oBAAoB,EAAE,YA6ClC,CAAA"}
|
|
@@ -0,0 +1,84 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* `boundary-stress` slice recipe (#375) — the boundary-instability augmentation. Self-generates
|
|
7
|
+
* `--count` rows from {@link synthesizeBoundaryStressRow}'s weighted template mix (the v1.7.0,
|
|
8
|
+
* DeepSeek-tuned 2026-06-18 composition), aligns each to BIO, and emits a labeled JSONL. The
|
|
9
|
+
* change for the taxonomy's #1 parser family (the boundary-wobble class). Ported from
|
|
10
|
+
* scripts/build-boundary-stress-slice.mjs.
|
|
11
|
+
*
|
|
12
|
+
* `synthesizeBoundaryStressRow` is NOT re-exported from the corpus index — imported directly here.
|
|
13
|
+
*/
|
|
14
|
+
import { mulberry32 as makeMulberry32 } from "@mailwoman/core/utils";
|
|
15
|
+
import { sliceSourceID } from "#recipes/scaffold";
|
|
16
|
+
import { synthesizeBoundaryStressRow } from "#synthesizers/boundary-stress";
|
|
17
|
+
import { alignRow } from "#utils";
|
|
18
|
+
/**
|
|
19
|
+
* Revised composition (v1.7.0, DeepSeek-tuned 2026-06-18): `bare-locality` ~11% (recover the 84% locality drop on bare
|
|
20
|
+
* "City, STATE" rows WITHOUT becoming a locality-first majority), and house-number-before:after = 7:3 (FR's dominant
|
|
21
|
+
* order is number-BEFORE; 30% after breaks the order-bias shortcut without risking FR hn-before accuracy). The three
|
|
22
|
+
* original non-number shapes keep the bulk. Weights sum to 1.0. Key order is required — it drives the cumulative
|
|
23
|
+
* thresholds below.
|
|
24
|
+
*/
|
|
25
|
+
const WEIGHTS = {
|
|
26
|
+
"street-eats-affix": 0.22,
|
|
27
|
+
"comma-less-city-state": 0.22,
|
|
28
|
+
"fr-prefix": 0.18,
|
|
29
|
+
"bare-locality": 0.11,
|
|
30
|
+
"house-number-before-street": 0.189,
|
|
31
|
+
"house-number-after-street": 0.081,
|
|
32
|
+
};
|
|
33
|
+
const CUM = (() => {
|
|
34
|
+
let acc = 0;
|
|
35
|
+
return Object.entries(WEIGHTS).map(([t, w]) => [t, (acc += w)]);
|
|
36
|
+
})();
|
|
37
|
+
function pickTemplate(r) {
|
|
38
|
+
const x = r();
|
|
39
|
+
for (const [t, c] of CUM)
|
|
40
|
+
if (x <= c)
|
|
41
|
+
return t;
|
|
42
|
+
return CUM.at(-1)[0];
|
|
43
|
+
}
|
|
44
|
+
/**
|
|
45
|
+
* Slice recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
46
|
+
* and `description` below for the surface form it generates.
|
|
47
|
+
*/
|
|
48
|
+
export const boundaryStressRecipe = {
|
|
49
|
+
name: "boundary-stress",
|
|
50
|
+
description: "Boundary-instability rows (#375): weighted template mix → synthesizeBoundaryStressRow → aligned BIO",
|
|
51
|
+
mode: "generate",
|
|
52
|
+
async run(opts, write) {
|
|
53
|
+
// Emit PRNG: the legacy build-boundary-stress-slice.mjs seeded mulberry32(opts.seed).
|
|
54
|
+
const random = makeMulberry32(opts.seed);
|
|
55
|
+
const count = opts.count ?? 20_000;
|
|
56
|
+
let emitted = 0;
|
|
57
|
+
let skipped = 0;
|
|
58
|
+
for (let i = 0; i < count; i++) {
|
|
59
|
+
const row = synthesizeBoundaryStressRow(undefined, { random, forceTemplate: pickTemplate(random) });
|
|
60
|
+
const country = row.locale.split("-")[1] ?? "US";
|
|
61
|
+
const source_id = sliceSourceID("synth-boundary-stress", { ...row.components, v: String(i) });
|
|
62
|
+
const canonical = {
|
|
63
|
+
raw: row.raw,
|
|
64
|
+
components: row.components,
|
|
65
|
+
country,
|
|
66
|
+
locale: row.locale,
|
|
67
|
+
source: "synth-boundary-stress",
|
|
68
|
+
source_id,
|
|
69
|
+
corpus_version: "0.6.0",
|
|
70
|
+
license: "Synthetic — boundary-stress; derived from public-domain locality/region tuples",
|
|
71
|
+
};
|
|
72
|
+
const aligned = alignRow(canonical);
|
|
73
|
+
if (aligned.kind !== "labeled") {
|
|
74
|
+
skipped++;
|
|
75
|
+
continue;
|
|
76
|
+
}
|
|
77
|
+
// Match the base corpus parquet schema: flat synth_method / synth_base_id, not a nested `synth`.
|
|
78
|
+
write(JSON.stringify({ ...aligned.row, synth_method: `boundary-stress:${row.template}`, synth_base_id: null }) + "\n");
|
|
79
|
+
emitted++;
|
|
80
|
+
}
|
|
81
|
+
return { emitted, skipped };
|
|
82
|
+
},
|
|
83
|
+
};
|
|
84
|
+
//# sourceMappingURL=boundary-stress.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"boundary-stress.js","sourceRoot":"","sources":["../../lib/recipes/boundary-stress.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;GAYG;AAEH,OAAO,EAAE,UAAU,IAAI,cAAc,EAAE,MAAM,uBAAuB,CAAA;AAEpE,OAAO,EAAqB,aAAa,EAAE,MAAM,mBAAmB,CAAA;AACpE,OAAO,EAA+B,2BAA2B,EAAE,MAAM,+BAA+B,CAAA;AACxG,OAAO,EAAE,QAAQ,EAAE,MAAM,QAAQ,CAAA;AAEjC;;;;;;GAMG;AACH,MAAM,OAAO,GAA2C;IACvD,mBAAmB,EAAE,IAAI;IACzB,uBAAuB,EAAE,IAAI;IAC7B,WAAW,EAAE,IAAI;IACjB,eAAe,EAAE,IAAI;IACrB,4BAA4B,EAAE,KAAK;IACnC,2BAA2B,EAAE,KAAK;CAClC,CAAA;AAED,MAAM,GAAG,GAA4C,CAAC,GAAG,EAAE;IAC1D,IAAI,GAAG,GAAG,CAAC,CAAA;IAEX,OAAQ,MAAM,CAAC,OAAO,CAAC,OAAO,CAA6C,CAAC,GAAG,CAC9E,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,CAAC,CAAqC,CAC/D,CAAA;AACF,CAAC,CAAC,EAAE,CAAA;AAEJ,SAAS,YAAY,CAAC,CAAe;IACpC,MAAM,CAAC,GAAG,CAAC,EAAE,CAAA;IAEb,KAAK,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,GAAG;QAAE,IAAI,CAAC,IAAI,CAAC;YAAE,OAAO,CAAC,CAAA;IAE9C,OAAO,GAAG,CAAC,EAAE,CAAC,CAAC,CAAC,CAAE,CAAC,CAAC,CAAC,CAAA;AACtB,CAAC;AAED;;;GAGG;AACH,MAAM,CAAC,MAAM,oBAAoB,GAAiB;IACjD,IAAI,EAAE,iBAAiB;IACvB,WAAW,EAAE,qGAAqG;IAClH,IAAI,EAAE,UAAU;IAChB,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,sFAAsF;QACtF,MAAM,MAAM,GAAG,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACxC,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,IAAI,MAAM,CAAA;QAClC,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QAEf,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,KAAK,EAAE,CAAC,EAAE,EAAE,CAAC;YAChC,MAAM,GAAG,GAAG,2BAA2B,CAAC,SAAS,EAAE,EAAE,MAAM,EAAE,aAAa,EAAE,YAAY,CAAC,MAAM,CAAC,EAAE,CAAC,CAAA;YACnG,MAAM,OAAO,GAAG,GAAG,CAAC,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,IAAI,IAAI,CAAA;YAChD,MAAM,SAAS,GAAG,aAAa,CAAC,uBAAuB,EAAE,EAAE,GAAG,GAAG,CAAC,UAAU,EAAE,CAAC,EAAE,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,CAAA;YAE7F,MAAM,SAAS,GAAG;gBACjB,GAAG,EAAE,GAAG,CAAC,GAAG;gBACZ,UAAU,EAAE,GAAG,CAAC,UAAU;gBAC1B,OAAO;gBACP,MAAM,EAAE,GAAG,CAAC,MAAM;gBAClB,MAAM,EAAE,uBAAuB;gBAC/B,SAAS;gBACT,cAAc,EAAE,OAAO;gBACvB,OAAO,EAAE,gFAAgF;aACzF,CAAA;YAED,MAAM,OAAO,GAAG,QAAQ,CAAC,SAA2C,CAAC,CAAA;YAErE,IAAI,OAAO,CAAC,IAAI,KAAK,SAAS,EAAE,CAAC;gBAChC,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,iGAAiG;YACjG,KAAK,CACJ,IAAI,CAAC,SAAS,CAAC,EAAE,GAAG,OAAO,CAAC,GAAG,EAAE,YAAY,EAAE,mBAAmB,GAAG,CAAC,QAAQ,EAAE,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,GAAG,IAAI,CAC/G,CAAA;YAED,OAAO,EAAE,CAAA;QACV,CAAC;QAED,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;IAC5B,CAAC;CACD,CAAA"}
|
|
@@ -0,0 +1,36 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
* @file `cn-organizational-units` recipe (#2034) — real CN address strings whose settlement is an ORGANIZATIONAL
|
|
6
|
+
* ladder (`赵光三分场二十九队`: the Zhaoguang farm, No. 3 sub-farm, No. 29 production team), labeled by rule and aligned
|
|
7
|
+
* character by character for the CJK sibling model.
|
|
8
|
+
*
|
|
9
|
+
* THE LABELS ARE A READING OF THE SUFFIX, NOT A GUESS. Every generic that ends an ordinal unit (`分场`, `大队`, `队`,
|
|
10
|
+
* `连`, `团`, `组`, `场部`) is in `@mailwoman/core/locale/zh-cn-units`' one table, and the same table reads the span back
|
|
11
|
+
* after decode. The whole ordinal chain is ONE `locality_unit` span; the named head it belongs to (`赵光`, `孟定农场`) is
|
|
12
|
+
* `dependent_locality`; a province, city or county written in front of it takes `region`, `locality`, `subregion`; a
|
|
13
|
+
* Latin admin tail (`, Heilongjiang, China`) takes `region` and `country`. A row with no chain is skipped, not labeled:
|
|
14
|
+
* `红卫大队` is a village name whose generic carries no ordinal, and `苗辽林场` is a named forest farm.
|
|
15
|
+
*
|
|
16
|
+
* WHERE THE ROWS COME FROM. `--input` is a JSONL of `{ raw, country }` rows — the shape of `data/coarse-placer/*.jsonl`,
|
|
17
|
+
* whose 50,000 CN rows hold 328 with unit vocabulary. That file is a local artifact and carries no per-row source; the
|
|
18
|
+
* `<name>, <admin1>, <country>` shape is the corpus's GeoNames adapter's, so the rows are stamped with GeoNames'
|
|
19
|
+
* licence and the inference is stated in the `license` field rather than hidden behind it.
|
|
20
|
+
*
|
|
21
|
+
* FOR THE CJK MODEL ONLY. The tokenizer is {@link cjkAwareTokenizer}: one token per Han character, because the
|
|
22
|
+
* whitespace tokenizer reads `三分场八队` as one word and could never give it two labels. The Latin model never trains
|
|
23
|
+
* on this recipe's rows; its label set has no `locality_unit`.
|
|
24
|
+
*/
|
|
25
|
+
import { type CorpusRecipe } from "#recipes/scaffold";
|
|
26
|
+
/**
|
|
27
|
+
* The components a row's string supports, every value a verbatim substring of `raw`, or `null` when the string carries
|
|
28
|
+
* no organizational chain and so teaches nothing this recipe exists for.
|
|
29
|
+
*/
|
|
30
|
+
export declare function labelCNOrganizationalRow(raw: string): Record<string, string> | null;
|
|
31
|
+
/**
|
|
32
|
+
* Slice recipe registered with the corpus builder — see the file header for the rows it labels and why every label is a
|
|
33
|
+
* reading of a generic rather than a guess.
|
|
34
|
+
*/
|
|
35
|
+
export declare const cnOrganizationalUnitsRecipe: CorpusRecipe;
|
|
36
|
+
//# sourceMappingURL=cn-organizational-units.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"cn-organizational-units.d.ts","sourceRoot":"","sources":["../../lib/recipes/cn-organizational-units.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAIH,OAAO,EAAE,KAAK,YAAY,EAA6B,MAAM,mBAAmB,CAAA;AAmBhF;;;GAGG;AACH,wBAAgB,wBAAwB,CAAC,GAAG,EAAE,MAAM,GAAG,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GAAG,IAAI,CAkDnF;AAmBD;;;GAGG;AACH,eAAO,MAAM,2BAA2B,EAAE,YA2EzC,CAAA"}
|