@mailwoman/corpus 9.2.0 → 9.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +22 -22
- package/data/PROVENANCE.md +7 -7
- package/lib/adapters/ban/adapter.ts +190 -0
- package/lib/adapters/ban/street-decompose.ts +66 -0
- package/lib/adapters/fcc-bdc/adapter.ts +174 -0
- package/lib/adapters/geonames/adapter.ts +199 -0
- package/lib/adapters/geonames-postal/adapter.ts +122 -0
- package/lib/adapters/gnaf/adapter.ts +149 -0
- package/lib/adapters/gnaf/assemble.ts +225 -0
- package/lib/adapters/index.ts +153 -0
- package/lib/adapters/openaddresses/adapter.ts +251 -0
- package/lib/adapters/overture/adapter.ts +162 -0
- package/lib/adapters/state-hi-schools/adapter.ts +170 -0
- package/lib/adapters/state-hi-schools/workbook.ts +35 -0
- package/lib/adapters/synth-po-box/adapter.ts +204 -0
- package/lib/adapters/tiger/adapter.ts +252 -0
- package/lib/adapters/tiger/street-decompose.ts +83 -0
- package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +167 -0
- package/lib/adapters/usgov-imls-pls/adapter.ts +143 -0
- package/lib/adapters/usgov-irs-bmf/adapter.ts +151 -0
- package/lib/adapters/usgov-nad/adapter.ts +334 -0
- package/lib/adapters/usgov-nppes/adapter.ts +151 -0
- package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +193 -0
- package/lib/adapters/utils/index.ts +307 -0
- package/lib/adapters/wof-admin-jp/adapter.ts +214 -0
- package/lib/adapters/wof-admin-json/adapter.ts +231 -0
- package/lib/adapters/wof-json-rows.ts +129 -0
- package/lib/adapters/wof-postalcode-json/adapter.ts +176 -0
- package/lib/build.ts +378 -0
- package/lib/env.ts +50 -0
- package/lib/index.ts +13 -0
- package/lib/name-prone-us-suffixes.ts +12 -0
- package/lib/recipes/anchor-absorption.ts +101 -0
- package/lib/recipes/bare-country.ts +95 -0
- package/lib/recipes/boundary-stress.ts +100 -0
- package/lib/recipes/cn-organizational-units.ts +199 -0
- package/lib/recipes/country-balanced.ts +509 -0
- package/lib/recipes/cz-pcfirst-preposition.ts +111 -0
- package/lib/recipes/fr-admin-split.ts +242 -0
- package/lib/recipes/fr-bare-street.ts +170 -0
- package/lib/recipes/fr-fragment.ts +333 -0
- package/lib/recipes/fr-lieudit.ts +301 -0
- package/lib/recipes/fr-order.ts +245 -0
- package/lib/recipes/german.ts +359 -0
- package/lib/recipes/house-venue.ts +92 -0
- package/lib/recipes/index.ts +97 -0
- package/lib/recipes/intersection.ts +618 -0
- package/lib/recipes/locale.ts +599 -0
- package/lib/recipes/nl-postcode.ts +115 -0
- package/lib/recipes/no-fragment.ts +219 -0
- package/lib/recipes/no-street-led.ts +141 -0
- package/lib/recipes/no-street.ts +90 -0
- package/lib/recipes/po-box-cedex.ts +976 -0
- package/lib/recipes/po-box.ts +123 -0
- package/lib/recipes/reviewed-postcode-tail.ts +190 -0
- package/lib/recipes/scaffold.ts +469 -0
- package/lib/recipes/si-bare-village.ts +97 -0
- package/lib/recipes/street-affix.ts +804 -0
- package/lib/recipes/street-bare.ts +100 -0
- package/lib/recipes/street.ts +81 -0
- package/lib/recipes/sub-venue-sources.ts +877 -0
- package/lib/recipes/sub-venue.ts +997 -0
- package/lib/recipes/trailing-region.ts +183 -0
- package/lib/recipes/unit.ts +304 -0
- package/lib/runner.ts +312 -0
- package/lib/synthesizers/anchor-absorption.ts +288 -0
- package/lib/synthesizers/boundary-stress.ts +532 -0
- package/lib/synthesizers/german.ts +260 -0
- package/lib/synthesizers/house-venue.ts +308 -0
- package/lib/synthesizers/intersection.ts +233 -0
- package/lib/synthesizers/no-street.ts +327 -0
- package/lib/synthesizers/po-box.ts +323 -0
- package/lib/synthesizers/street.ts +269 -0
- package/lib/synthesizers/utils.ts +993 -0
- package/lib/test-kit/corpus-recipe.ts +86 -0
- package/lib/test-kit/index.ts +100 -0
- package/lib/tools/align-slice.ts +68 -0
- package/lib/tools/audit.ts +403 -0
- package/lib/tools/corpus-stats.ts +136 -0
- package/lib/tools/fetch/ban.ts +289 -0
- package/lib/tools/fetch/download.ts +262 -0
- package/lib/tools/fetch/geonames-dump.ts +257 -0
- package/lib/tools/fetch/geonames-postal.ts +180 -0
- package/lib/tools/fetch/hrsa.ts +59 -0
- package/lib/tools/fetch/imls-pls.ts +149 -0
- package/lib/tools/fetch/index.ts +147 -0
- package/lib/tools/fetch/nad.ts +341 -0
- package/lib/tools/fetch/nppes.ts +165 -0
- package/lib/tools/fetch/openaddresses.ts +347 -0
- package/lib/tools/fetch/ourairports.ts +170 -0
- package/lib/tools/fetch/ppd.ts +121 -0
- package/lib/tools/fetch/state-hi-schools.ts +161 -0
- package/lib/tools/fetch/state-sources.ts +146 -0
- package/lib/tools/fetch/tiger-full.ts +308 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +384 -0
- package/lib/tools/golden-expand.ts +574 -0
- package/lib/tools/golden-promote.ts +337 -0
- package/lib/tools/golden-relabel-street.ts +683 -0
- package/lib/tools/index.ts +28 -0
- package/lib/tools/ingest-csv.ts +378 -0
- package/lib/tools/jsonl-to-parquet.ts +207 -0
- package/lib/tools/lint-slice-vocab.ts +388 -0
- package/lib/tools/lint-slice.ts +496 -0
- package/lib/tools/overlay-manifest.ts +148 -0
- package/lib/tools/overture-subvenue.ts +209 -0
- package/lib/tools/postcode-triples.ts +363 -0
- package/lib/tools/slice-kryptonite.ts +137 -0
- package/lib/tools/slice-translit.ts +218 -0
- package/lib/tools/sub-venue/harvest.ts +234 -0
- package/lib/tools/sub-venue/head-nouns.ts +245 -0
- package/lib/tools/sub-venue/surfaces.ts +95 -0
- package/lib/tools/sub-venue/table.ts +281 -0
- package/lib/tools/sub-venue/wikidata.ts +85 -0
- package/lib/tools/sub-venue-lexicon.ts +429 -0
- package/lib/tools/sub-venue-promotions.ts +330 -0
- package/lib/types.ts +247 -0
- package/lib/utils/align.ts +330 -0
- package/lib/utils/golden.ts +189 -0
- package/lib/utils/index.ts +14 -0
- package/lib/utils/parquet.ts +582 -0
- package/lib/utils/slice-stats.ts +95 -0
- package/lib/utils/split.ts +279 -0
- package/lib/utils/tokenize.ts +120 -0
- package/lib/utils/wof-json.ts +247 -0
- package/out/adapters/ban/adapter.d.ts.map +1 -0
- package/out/adapters/ban/adapter.js +149 -0
- package/out/adapters/ban/adapter.js.map +1 -0
- package/out/adapters/ban/street-decompose.d.ts.map +1 -0
- package/out/adapters/ban/street-decompose.js +51 -0
- package/out/adapters/ban/street-decompose.js.map +1 -0
- package/out/adapters/fcc-bdc/adapter.d.ts.map +1 -0
- package/out/adapters/fcc-bdc/adapter.js +144 -0
- package/out/adapters/fcc-bdc/adapter.js.map +1 -0
- package/out/adapters/geonames/adapter.d.ts.map +1 -0
- package/out/adapters/geonames/adapter.js +176 -0
- package/out/adapters/geonames/adapter.js.map +1 -0
- package/out/adapters/geonames-postal/adapter.d.ts +54 -0
- package/out/adapters/geonames-postal/adapter.d.ts.map +1 -0
- package/out/adapters/geonames-postal/adapter.js +107 -0
- package/out/adapters/geonames-postal/adapter.js.map +1 -0
- package/out/adapters/gnaf/adapter.d.ts +49 -0
- package/out/adapters/gnaf/adapter.d.ts.map +1 -0
- package/out/adapters/gnaf/adapter.js +124 -0
- package/out/adapters/gnaf/adapter.js.map +1 -0
- package/out/adapters/gnaf/assemble.d.ts +65 -0
- package/out/adapters/gnaf/assemble.d.ts.map +1 -0
- package/out/adapters/gnaf/assemble.js +154 -0
- package/out/adapters/gnaf/assemble.js.map +1 -0
- package/out/adapters/index.d.ts +51 -0
- package/out/adapters/index.d.ts.map +1 -0
- package/out/adapters/index.js +95 -0
- package/out/adapters/index.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -0
- package/out/adapters/openaddresses/adapter.js +186 -0
- package/out/adapters/openaddresses/adapter.js.map +1 -0
- package/out/adapters/overture/adapter.d.ts +48 -0
- package/out/adapters/overture/adapter.d.ts.map +1 -0
- package/out/adapters/overture/adapter.js +125 -0
- package/out/adapters/overture/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/adapter.d.ts +46 -0
- package/out/adapters/state-hi-schools/adapter.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/adapter.js +145 -0
- package/out/adapters/state-hi-schools/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/workbook.d.ts +29 -0
- package/out/adapters/state-hi-schools/workbook.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/workbook.js +20 -0
- package/out/adapters/state-hi-schools/workbook.js.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
- package/out/adapters/synth-po-box/adapter.d.ts.map +1 -0
- package/out/adapters/synth-po-box/adapter.js +140 -0
- package/out/adapters/synth-po-box/adapter.js.map +1 -0
- package/out/adapters/tiger/adapter.d.ts +55 -0
- package/out/adapters/tiger/adapter.d.ts.map +1 -0
- package/out/adapters/tiger/adapter.js +201 -0
- package/out/adapters/tiger/adapter.js.map +1 -0
- package/out/adapters/tiger/street-decompose.d.ts.map +1 -0
- package/out/adapters/tiger/street-decompose.js +68 -0
- package/out/adapters/tiger/street-decompose.js.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +56 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js +132 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts +36 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.js +114 -0
- package/out/adapters/usgov-imls-pls/adapter.js.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts +37 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.js +120 -0
- package/out/adapters/usgov-irs-bmf/adapter.js.map +1 -0
- package/out/adapters/usgov-nad/adapter.d.ts +48 -0
- package/out/adapters/usgov-nad/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nad/adapter.js +249 -0
- package/out/adapters/usgov-nad/adapter.js.map +1 -0
- package/out/adapters/usgov-nppes/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nppes/adapter.js +118 -0
- package/out/adapters/usgov-nppes/adapter.js.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +154 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -0
- package/out/adapters/utils/index.d.ts +191 -0
- package/out/adapters/utils/index.d.ts.map +1 -0
- package/out/adapters/utils/index.js +206 -0
- package/out/adapters/utils/index.js.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.js +161 -0
- package/out/adapters/wof-admin-jp/adapter.js.map +1 -0
- package/out/adapters/wof-admin-json/adapter.d.ts +79 -0
- package/out/adapters/wof-admin-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-json/adapter.js +197 -0
- package/out/adapters/wof-admin-json/adapter.js.map +1 -0
- package/out/adapters/wof-json-rows.d.ts +62 -0
- package/out/adapters/wof-json-rows.d.ts.map +1 -0
- package/out/adapters/wof-json-rows.js +83 -0
- package/out/adapters/wof-json-rows.js.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts +65 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.js +151 -0
- package/out/adapters/wof-postalcode-json/adapter.js.map +1 -0
- package/out/build.d.ts +132 -0
- package/out/build.d.ts.map +1 -0
- package/out/build.js +245 -0
- package/out/build.js.map +1 -0
- package/out/codex/us-fips-state.d.ts.map +1 -0
- package/out/codex/us-fips-state.js.map +1 -0
- package/out/env.d.ts +46 -0
- package/out/env.d.ts.map +1 -0
- package/out/env.js +46 -0
- package/out/env.js.map +1 -0
- package/out/index.d.ts +13 -0
- package/out/index.d.ts.map +1 -0
- package/out/index.js +13 -0
- package/out/index.js.map +1 -0
- package/out/name-prone-us-suffixes.d.ts +12 -0
- package/out/name-prone-us-suffixes.d.ts.map +1 -0
- package/out/name-prone-us-suffixes.js +12 -0
- package/out/name-prone-us-suffixes.js.map +1 -0
- package/out/recipes/anchor-absorption.d.ts +20 -0
- package/out/recipes/anchor-absorption.d.ts.map +1 -0
- package/out/recipes/anchor-absorption.js +81 -0
- package/out/recipes/anchor-absorption.js.map +1 -0
- package/out/recipes/bare-country.d.ts +25 -0
- package/out/recipes/bare-country.d.ts.map +1 -0
- package/out/recipes/bare-country.js +87 -0
- package/out/recipes/bare-country.js.map +1 -0
- package/out/recipes/boundary-stress.d.ts +20 -0
- package/out/recipes/boundary-stress.d.ts.map +1 -0
- package/out/recipes/boundary-stress.js +83 -0
- package/out/recipes/boundary-stress.js.map +1 -0
- package/out/recipes/cn-organizational-units.d.ts +36 -0
- package/out/recipes/cn-organizational-units.d.ts.map +1 -0
- package/out/recipes/cn-organizational-units.js +159 -0
- package/out/recipes/cn-organizational-units.js.map +1 -0
- package/out/recipes/country-balanced.d.ts +32 -0
- package/out/recipes/country-balanced.d.ts.map +1 -0
- package/out/recipes/country-balanced.js +393 -0
- package/out/recipes/country-balanced.js.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts +22 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.js +100 -0
- package/out/recipes/cz-pcfirst-preposition.js.map +1 -0
- package/out/recipes/fr-admin-split.d.ts +38 -0
- package/out/recipes/fr-admin-split.d.ts.map +1 -0
- package/out/recipes/fr-admin-split.js +192 -0
- package/out/recipes/fr-admin-split.js.map +1 -0
- package/out/recipes/fr-bare-street.d.ts +28 -0
- package/out/recipes/fr-bare-street.d.ts.map +1 -0
- package/out/recipes/fr-bare-street.js +143 -0
- package/out/recipes/fr-bare-street.js.map +1 -0
- package/out/recipes/fr-fragment.d.ts +77 -0
- package/out/recipes/fr-fragment.d.ts.map +1 -0
- package/out/recipes/fr-fragment.js +276 -0
- package/out/recipes/fr-fragment.js.map +1 -0
- package/out/recipes/fr-lieudit.d.ts +32 -0
- package/out/recipes/fr-lieudit.d.ts.map +1 -0
- package/out/recipes/fr-lieudit.js +227 -0
- package/out/recipes/fr-lieudit.js.map +1 -0
- package/out/recipes/fr-order.d.ts +38 -0
- package/out/recipes/fr-order.d.ts.map +1 -0
- package/out/recipes/fr-order.js +197 -0
- package/out/recipes/fr-order.js.map +1 -0
- package/out/recipes/german.d.ts +44 -0
- package/out/recipes/german.d.ts.map +1 -0
- package/out/recipes/german.js +288 -0
- package/out/recipes/german.js.map +1 -0
- package/out/recipes/house-venue.d.ts +18 -0
- package/out/recipes/house-venue.d.ts.map +1 -0
- package/out/recipes/house-venue.js +73 -0
- package/out/recipes/house-venue.js.map +1 -0
- package/out/recipes/index.d.ts +24 -0
- package/out/recipes/index.d.ts.map +1 -0
- package/out/recipes/index.js +91 -0
- package/out/recipes/index.js.map +1 -0
- package/out/recipes/intersection.d.ts +42 -0
- package/out/recipes/intersection.d.ts.map +1 -0
- package/out/recipes/intersection.js +452 -0
- package/out/recipes/intersection.js.map +1 -0
- package/out/recipes/locale.d.ts +136 -0
- package/out/recipes/locale.d.ts.map +1 -0
- package/out/recipes/locale.js +460 -0
- package/out/recipes/locale.js.map +1 -0
- package/out/recipes/nl-postcode.d.ts +26 -0
- package/out/recipes/nl-postcode.d.ts.map +1 -0
- package/out/recipes/nl-postcode.js +102 -0
- package/out/recipes/nl-postcode.js.map +1 -0
- package/out/recipes/no-fragment.d.ts +43 -0
- package/out/recipes/no-fragment.d.ts.map +1 -0
- package/out/recipes/no-fragment.js +182 -0
- package/out/recipes/no-fragment.js.map +1 -0
- package/out/recipes/no-street-led.d.ts +24 -0
- package/out/recipes/no-street-led.d.ts.map +1 -0
- package/out/recipes/no-street-led.js +113 -0
- package/out/recipes/no-street-led.js.map +1 -0
- package/out/recipes/no-street.d.ts +18 -0
- package/out/recipes/no-street.d.ts.map +1 -0
- package/out/recipes/no-street.js +71 -0
- package/out/recipes/no-street.js.map +1 -0
- package/out/recipes/po-box-cedex.d.ts +38 -0
- package/out/recipes/po-box-cedex.d.ts.map +1 -0
- package/out/recipes/po-box-cedex.js +767 -0
- package/out/recipes/po-box-cedex.js.map +1 -0
- package/out/recipes/po-box.d.ts +17 -0
- package/out/recipes/po-box.d.ts.map +1 -0
- package/out/recipes/po-box.js +100 -0
- package/out/recipes/po-box.js.map +1 -0
- package/out/recipes/reviewed-postcode-tail.d.ts +47 -0
- package/out/recipes/reviewed-postcode-tail.d.ts.map +1 -0
- package/out/recipes/reviewed-postcode-tail.js +125 -0
- package/out/recipes/reviewed-postcode-tail.js.map +1 -0
- package/out/recipes/scaffold.d.ts +324 -0
- package/out/recipes/scaffold.d.ts.map +1 -0
- package/out/recipes/scaffold.js +186 -0
- package/out/recipes/scaffold.js.map +1 -0
- package/out/recipes/si-bare-village.d.ts +32 -0
- package/out/recipes/si-bare-village.d.ts.map +1 -0
- package/out/recipes/si-bare-village.js +88 -0
- package/out/recipes/si-bare-village.js.map +1 -0
- package/out/recipes/street-affix.d.ts +89 -0
- package/out/recipes/street-affix.d.ts.map +1 -0
- package/out/recipes/street-affix.js +563 -0
- package/out/recipes/street-affix.js.map +1 -0
- package/out/recipes/street-bare.d.ts +25 -0
- package/out/recipes/street-bare.d.ts.map +1 -0
- package/out/recipes/street-bare.js +86 -0
- package/out/recipes/street-bare.js.map +1 -0
- package/out/recipes/street.d.ts +15 -0
- package/out/recipes/street.d.ts.map +1 -0
- package/out/recipes/street.js +69 -0
- package/out/recipes/street.js.map +1 -0
- package/out/recipes/sub-venue-sources.d.ts +229 -0
- package/out/recipes/sub-venue-sources.d.ts.map +1 -0
- package/out/recipes/sub-venue-sources.js +653 -0
- package/out/recipes/sub-venue-sources.js.map +1 -0
- package/out/recipes/sub-venue.d.ts +269 -0
- package/out/recipes/sub-venue.d.ts.map +1 -0
- package/out/recipes/sub-venue.js +725 -0
- package/out/recipes/sub-venue.js.map +1 -0
- package/out/recipes/trailing-region.d.ts +74 -0
- package/out/recipes/trailing-region.d.ts.map +1 -0
- package/out/recipes/trailing-region.js +157 -0
- package/out/recipes/trailing-region.js.map +1 -0
- package/out/recipes/unit.d.ts +29 -0
- package/out/recipes/unit.d.ts.map +1 -0
- package/out/recipes/unit.js +230 -0
- package/out/recipes/unit.js.map +1 -0
- package/out/runner.d.ts +130 -0
- package/out/runner.d.ts.map +1 -0
- package/out/runner.js +185 -0
- package/out/runner.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +63 -0
- package/out/synthesizers/anchor-absorption.d.ts.map +1 -0
- package/out/synthesizers/anchor-absorption.js +221 -0
- package/out/synthesizers/anchor-absorption.js.map +1 -0
- package/out/synthesizers/boundary-stress.d.ts +78 -0
- package/out/synthesizers/boundary-stress.d.ts.map +1 -0
- package/out/synthesizers/boundary-stress.js +455 -0
- package/out/synthesizers/boundary-stress.js.map +1 -0
- package/out/synthesizers/german.d.ts +115 -0
- package/out/synthesizers/german.d.ts.map +1 -0
- package/out/synthesizers/german.js +149 -0
- package/out/synthesizers/german.js.map +1 -0
- package/out/synthesizers/house-venue.d.ts +56 -0
- package/out/synthesizers/house-venue.d.ts.map +1 -0
- package/out/synthesizers/house-venue.js +247 -0
- package/out/synthesizers/house-venue.js.map +1 -0
- package/out/synthesizers/intersection.d.ts +52 -0
- package/out/synthesizers/intersection.d.ts.map +1 -0
- package/out/synthesizers/intersection.js +175 -0
- package/out/synthesizers/intersection.js.map +1 -0
- package/out/synthesizers/no-street.d.ts +72 -0
- package/out/synthesizers/no-street.d.ts.map +1 -0
- package/out/synthesizers/no-street.js +262 -0
- package/out/synthesizers/no-street.js.map +1 -0
- package/out/synthesizers/po-box.d.ts +108 -0
- package/out/synthesizers/po-box.d.ts.map +1 -0
- package/out/synthesizers/po-box.js +250 -0
- package/out/synthesizers/po-box.js.map +1 -0
- package/out/synthesizers/street.d.ts +54 -0
- package/out/synthesizers/street.d.ts.map +1 -0
- package/out/synthesizers/street.js +218 -0
- package/out/synthesizers/street.js.map +1 -0
- package/out/synthesizers/utils.d.ts +241 -0
- package/out/synthesizers/utils.d.ts.map +1 -0
- package/out/synthesizers/utils.js +776 -0
- package/out/synthesizers/utils.js.map +1 -0
- package/out/test-kit/corpus-recipe.d.ts +59 -0
- package/out/test-kit/corpus-recipe.d.ts.map +1 -0
- package/out/test-kit/corpus-recipe.js +39 -0
- package/out/test-kit/corpus-recipe.js.map +1 -0
- package/out/test-kit/index.d.ts +48 -0
- package/out/test-kit/index.d.ts.map +1 -0
- package/out/test-kit/index.js +78 -0
- package/out/test-kit/index.js.map +1 -0
- package/out/tools/align-slice.d.ts +7 -0
- package/out/tools/align-slice.d.ts.map +1 -0
- package/out/tools/align-slice.js +55 -0
- package/out/tools/align-slice.js.map +1 -0
- package/out/tools/audit.d.ts +29 -0
- package/out/tools/audit.d.ts.map +1 -0
- package/out/tools/audit.js +282 -0
- package/out/tools/audit.js.map +1 -0
- package/out/tools/corpus-stats.d.ts +44 -0
- package/out/tools/corpus-stats.d.ts.map +1 -0
- package/out/tools/corpus-stats.js +102 -0
- package/out/tools/corpus-stats.js.map +1 -0
- package/out/tools/fetch/ban.d.ts +31 -0
- package/out/tools/fetch/ban.d.ts.map +1 -0
- package/out/tools/fetch/ban.js +239 -0
- package/out/tools/fetch/ban.js.map +1 -0
- package/out/tools/fetch/download.d.ts +117 -0
- package/out/tools/fetch/download.d.ts.map +1 -0
- package/out/tools/fetch/download.js +160 -0
- package/out/tools/fetch/download.js.map +1 -0
- package/out/tools/fetch/geonames-dump.d.ts +91 -0
- package/out/tools/fetch/geonames-dump.d.ts.map +1 -0
- package/out/tools/fetch/geonames-dump.js +171 -0
- package/out/tools/fetch/geonames-dump.js.map +1 -0
- package/out/tools/fetch/geonames-postal.d.ts +76 -0
- package/out/tools/fetch/geonames-postal.d.ts.map +1 -0
- package/out/tools/fetch/geonames-postal.js +126 -0
- package/out/tools/fetch/geonames-postal.js.map +1 -0
- package/out/tools/fetch/hrsa.d.ts +18 -0
- package/out/tools/fetch/hrsa.d.ts.map +1 -0
- package/out/tools/fetch/hrsa.js +46 -0
- package/out/tools/fetch/hrsa.js.map +1 -0
- package/out/tools/fetch/imls-pls.d.ts +25 -0
- package/out/tools/fetch/imls-pls.d.ts.map +1 -0
- package/out/tools/fetch/imls-pls.js +108 -0
- package/out/tools/fetch/imls-pls.js.map +1 -0
- package/out/tools/fetch/index.d.ts +144 -0
- package/out/tools/fetch/index.d.ts.map +1 -0
- package/out/tools/fetch/index.js +143 -0
- package/out/tools/fetch/index.js.map +1 -0
- package/out/tools/fetch/nad.d.ts +70 -0
- package/out/tools/fetch/nad.d.ts.map +1 -0
- package/out/tools/fetch/nad.js +234 -0
- package/out/tools/fetch/nad.js.map +1 -0
- package/out/tools/fetch/nppes.d.ts +26 -0
- package/out/tools/fetch/nppes.d.ts.map +1 -0
- package/out/tools/fetch/nppes.js +126 -0
- package/out/tools/fetch/nppes.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +9 -0
- package/out/tools/fetch/openaddresses.d.ts.map +1 -0
- package/out/tools/fetch/openaddresses.js +279 -0
- package/out/tools/fetch/openaddresses.js.map +1 -0
- package/out/tools/fetch/ourairports.d.ts +45 -0
- package/out/tools/fetch/ourairports.d.ts.map +1 -0
- package/out/tools/fetch/ourairports.js +128 -0
- package/out/tools/fetch/ourairports.js.map +1 -0
- package/out/tools/fetch/ppd.d.ts.map +1 -0
- package/out/tools/fetch/ppd.js +85 -0
- package/out/tools/fetch/ppd.js.map +1 -0
- package/out/tools/fetch/state-hi-schools.d.ts +26 -0
- package/out/tools/fetch/state-hi-schools.d.ts.map +1 -0
- package/out/tools/fetch/state-hi-schools.js +112 -0
- package/out/tools/fetch/state-hi-schools.js.map +1 -0
- package/out/tools/fetch/state-sources.d.ts +26 -0
- package/out/tools/fetch/state-sources.d.ts.map +1 -0
- package/out/tools/fetch/state-sources.js +111 -0
- package/out/tools/fetch/state-sources.js.map +1 -0
- package/out/tools/fetch/tiger-full.d.ts +22 -0
- package/out/tools/fetch/tiger-full.d.ts.map +1 -0
- package/out/tools/fetch/tiger-full.js +217 -0
- package/out/tools/fetch/tiger-full.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +171 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.js +274 -0
- package/out/tools/fetch/wikidata-subvenue.js.map +1 -0
- package/out/tools/gb-title-case.d.ts.map +1 -0
- package/out/tools/gb-title-case.js.map +1 -0
- package/out/tools/golden-expand.d.ts +90 -0
- package/out/tools/golden-expand.d.ts.map +1 -0
- package/out/tools/golden-expand.js +406 -0
- package/out/tools/golden-expand.js.map +1 -0
- package/out/tools/golden-promote.d.ts.map +1 -0
- package/out/tools/golden-promote.js +240 -0
- package/out/tools/golden-promote.js.map +1 -0
- package/out/tools/golden-relabel-street.d.ts +196 -0
- package/out/tools/golden-relabel-street.d.ts.map +1 -0
- package/out/tools/golden-relabel-street.js +440 -0
- package/out/tools/golden-relabel-street.js.map +1 -0
- package/out/tools/index.d.ts +28 -0
- package/out/tools/index.d.ts.map +1 -0
- package/out/tools/index.js +28 -0
- package/out/tools/index.js.map +1 -0
- package/out/tools/ingest-csv.d.ts.map +1 -0
- package/out/tools/ingest-csv.js +265 -0
- package/out/tools/ingest-csv.js.map +1 -0
- package/out/tools/jsonl-to-parquet.d.ts +61 -0
- package/out/tools/jsonl-to-parquet.d.ts.map +1 -0
- package/out/tools/jsonl-to-parquet.js +150 -0
- package/out/tools/jsonl-to-parquet.js.map +1 -0
- package/out/tools/lint-slice-vocab.d.ts +90 -0
- package/out/tools/lint-slice-vocab.d.ts.map +1 -0
- package/out/tools/lint-slice-vocab.js +267 -0
- package/out/tools/lint-slice-vocab.js.map +1 -0
- package/out/tools/lint-slice.d.ts +93 -0
- package/out/tools/lint-slice.d.ts.map +1 -0
- package/out/tools/lint-slice.js +322 -0
- package/out/tools/lint-slice.js.map +1 -0
- package/out/tools/overlay-manifest.d.ts +39 -0
- package/out/tools/overlay-manifest.d.ts.map +1 -0
- package/out/tools/overlay-manifest.js +90 -0
- package/out/tools/overlay-manifest.js.map +1 -0
- package/out/tools/overture-subvenue.d.ts +112 -0
- package/out/tools/overture-subvenue.d.ts.map +1 -0
- package/out/tools/overture-subvenue.js +139 -0
- package/out/tools/overture-subvenue.js.map +1 -0
- package/out/tools/postcode-triples.d.ts +174 -0
- package/out/tools/postcode-triples.d.ts.map +1 -0
- package/out/tools/postcode-triples.js +292 -0
- package/out/tools/postcode-triples.js.map +1 -0
- package/out/tools/slice-kryptonite.d.ts +32 -0
- package/out/tools/slice-kryptonite.d.ts.map +1 -0
- package/out/tools/slice-kryptonite.js +99 -0
- package/out/tools/slice-kryptonite.js.map +1 -0
- package/out/tools/slice-translit.d.ts +51 -0
- package/out/tools/slice-translit.d.ts.map +1 -0
- package/out/tools/slice-translit.js +166 -0
- package/out/tools/slice-translit.js.map +1 -0
- package/out/tools/sub-venue/harvest.d.ts +100 -0
- package/out/tools/sub-venue/harvest.d.ts.map +1 -0
- package/out/tools/sub-venue/harvest.js +168 -0
- package/out/tools/sub-venue/harvest.js.map +1 -0
- package/out/tools/sub-venue/head-nouns.d.ts +50 -0
- package/out/tools/sub-venue/head-nouns.d.ts.map +1 -0
- package/out/tools/sub-venue/head-nouns.js +213 -0
- package/out/tools/sub-venue/head-nouns.js.map +1 -0
- package/out/tools/sub-venue/surfaces.d.ts +45 -0
- package/out/tools/sub-venue/surfaces.d.ts.map +1 -0
- package/out/tools/sub-venue/surfaces.js +77 -0
- package/out/tools/sub-venue/surfaces.js.map +1 -0
- package/out/tools/sub-venue/table.d.ts +229 -0
- package/out/tools/sub-venue/table.d.ts.map +1 -0
- package/out/tools/sub-venue/table.js +108 -0
- package/out/tools/sub-venue/table.js.map +1 -0
- package/out/tools/sub-venue/wikidata.d.ts +26 -0
- package/out/tools/sub-venue/wikidata.d.ts.map +1 -0
- package/out/tools/sub-venue/wikidata.js +62 -0
- package/out/tools/sub-venue/wikidata.js.map +1 -0
- package/out/tools/sub-venue-lexicon.d.ts +156 -0
- package/out/tools/sub-venue-lexicon.d.ts.map +1 -0
- package/out/tools/sub-venue-lexicon.js +283 -0
- package/out/tools/sub-venue-lexicon.js.map +1 -0
- package/out/tools/sub-venue-promotions.d.ts +94 -0
- package/out/tools/sub-venue-promotions.d.ts.map +1 -0
- package/out/tools/sub-venue-promotions.js +266 -0
- package/out/tools/sub-venue-promotions.js.map +1 -0
- package/out/types.d.ts +221 -0
- package/out/types.d.ts.map +1 -0
- package/out/types.js.map +1 -0
- package/out/utils/align.d.ts +93 -0
- package/out/utils/align.d.ts.map +1 -0
- package/out/utils/align.js +234 -0
- package/out/utils/align.js.map +1 -0
- package/out/utils/golden.d.ts +85 -0
- package/out/utils/golden.d.ts.map +1 -0
- package/out/utils/golden.js +127 -0
- package/out/utils/golden.js.map +1 -0
- package/out/utils/index.d.ts +14 -0
- package/out/utils/index.d.ts.map +1 -0
- package/out/utils/index.js +14 -0
- package/out/utils/index.js.map +1 -0
- package/out/utils/license.d.ts.map +1 -0
- package/out/utils/license.js.map +1 -0
- package/out/utils/parquet.d.ts +178 -0
- package/out/utils/parquet.d.ts.map +1 -0
- package/out/utils/parquet.js +371 -0
- package/out/utils/parquet.js.map +1 -0
- package/out/utils/slice-stats.d.ts +52 -0
- package/out/utils/slice-stats.d.ts.map +1 -0
- package/out/utils/slice-stats.js +58 -0
- package/out/utils/slice-stats.js.map +1 -0
- package/out/utils/split.d.ts +128 -0
- package/out/utils/split.d.ts.map +1 -0
- package/out/utils/split.js +204 -0
- package/out/utils/split.js.map +1 -0
- package/out/utils/tokenize.d.ts +64 -0
- package/out/utils/tokenize.d.ts.map +1 -0
- package/out/utils/tokenize.js +82 -0
- package/out/utils/tokenize.js.map +1 -0
- package/out/utils/wof-json.d.ts +113 -0
- package/out/utils/wof-json.d.ts.map +1 -0
- package/out/utils/wof-json.js +173 -0
- package/out/utils/wof-json.js.map +1 -0
- package/package.json +259 -194
- package/out/src/adapters/ban/adapter.d.ts.map +0 -1
- package/out/src/adapters/ban/adapter.js +0 -149
- package/out/src/adapters/ban/adapter.js.map +0 -1
- package/out/src/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/ban/street-decompose.js +0 -75
- package/out/src/adapters/ban/street-decompose.js.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.d.ts.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.js +0 -144
- package/out/src/adapters/fcc-bdc/adapter.js.map +0 -1
- package/out/src/adapters/geonames/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames/adapter.js +0 -176
- package/out/src/adapters/geonames/adapter.js.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.d.ts +0 -41
- package/out/src/adapters/geonames-postal/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.js +0 -104
- package/out/src/adapters/geonames-postal/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/adapter.d.ts +0 -49
- package/out/src/adapters/gnaf/adapter.d.ts.map +0 -1
- package/out/src/adapters/gnaf/adapter.js +0 -124
- package/out/src/adapters/gnaf/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/assemble.d.ts +0 -65
- package/out/src/adapters/gnaf/assemble.d.ts.map +0 -1
- package/out/src/adapters/gnaf/assemble.js +0 -154
- package/out/src/adapters/gnaf/assemble.js.map +0 -1
- package/out/src/adapters/index.d.ts +0 -51
- package/out/src/adapters/index.d.ts.map +0 -1
- package/out/src/adapters/index.js +0 -95
- package/out/src/adapters/index.js.map +0 -1
- package/out/src/adapters/openaddresses/adapter.d.ts.map +0 -1
- package/out/src/adapters/openaddresses/adapter.js +0 -186
- package/out/src/adapters/openaddresses/adapter.js.map +0 -1
- package/out/src/adapters/overture/adapter.d.ts +0 -48
- package/out/src/adapters/overture/adapter.d.ts.map +0 -1
- package/out/src/adapters/overture/adapter.js +0 -125
- package/out/src/adapters/overture/adapter.js.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.d.ts +0 -47
- package/out/src/adapters/state-hi-schools/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.js +0 -133
- package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.d.ts.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.js +0 -140
- package/out/src/adapters/synth-po-box/adapter.js.map +0 -1
- package/out/src/adapters/tiger/adapter.d.ts +0 -55
- package/out/src/adapters/tiger/adapter.d.ts.map +0 -1
- package/out/src/adapters/tiger/adapter.js +0 -201
- package/out/src/adapters/tiger/adapter.js.map +0 -1
- package/out/src/adapters/tiger/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/tiger/street-decompose.js +0 -90
- package/out/src/adapters/tiger/street-decompose.js.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -47
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +0 -139
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts +0 -36
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.js +0 -114
- package/out/src/adapters/usgov-imls-pls/adapter.js.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.js +0 -124
- package/out/src/adapters/usgov-irs-bmf/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.d.ts +0 -48
- package/out/src/adapters/usgov-nad/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.js +0 -252
- package/out/src/adapters/usgov-nad/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.js +0 -116
- package/out/src/adapters/usgov-nppes/adapter.js.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -156
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
- package/out/src/adapters/utils/index.d.ts +0 -150
- package/out/src/adapters/utils/index.d.ts.map +0 -1
- package/out/src/adapters/utils/index.js +0 -159
- package/out/src/adapters/utils/index.js.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.js +0 -164
- package/out/src/adapters/wof-admin-jp/adapter.js.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.d.ts +0 -82
- package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.js +0 -224
- package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
- package/out/src/adapters/wof-json-rows.d.ts +0 -32
- package/out/src/adapters/wof-json-rows.d.ts.map +0 -1
- package/out/src/adapters/wof-json-rows.js +0 -45
- package/out/src/adapters/wof-json-rows.js.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -65
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.js +0 -160
- package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
- package/out/src/build.d.ts +0 -132
- package/out/src/build.d.ts.map +0 -1
- package/out/src/build.js +0 -251
- package/out/src/build.js.map +0 -1
- package/out/src/codex/us-fips-state.d.ts.map +0 -1
- package/out/src/codex/us-fips-state.js.map +0 -1
- package/out/src/index.d.ts +0 -14
- package/out/src/index.d.ts.map +0 -1
- package/out/src/index.js +0 -14
- package/out/src/index.js.map +0 -1
- package/out/src/name-prone-us-suffixes.d.ts +0 -12
- package/out/src/name-prone-us-suffixes.d.ts.map +0 -1
- package/out/src/name-prone-us-suffixes.js +0 -12
- package/out/src/name-prone-us-suffixes.js.map +0 -1
- package/out/src/parquet-wrapper/index.d.ts +0 -9
- package/out/src/parquet-wrapper/index.d.ts.map +0 -1
- package/out/src/parquet-wrapper/index.js +0 -9
- package/out/src/parquet-wrapper/index.js.map +0 -1
- package/out/src/parquet-wrapper/reader.d.ts +0 -34
- package/out/src/parquet-wrapper/reader.d.ts.map +0 -1
- package/out/src/parquet-wrapper/reader.js +0 -69
- package/out/src/parquet-wrapper/reader.js.map +0 -1
- package/out/src/parquet-wrapper/schema.d.ts +0 -49
- package/out/src/parquet-wrapper/schema.d.ts.map +0 -1
- package/out/src/parquet-wrapper/schema.js +0 -55
- package/out/src/parquet-wrapper/schema.js.map +0 -1
- package/out/src/parquet-wrapper/writer.d.ts +0 -46
- package/out/src/parquet-wrapper/writer.d.ts.map +0 -1
- package/out/src/parquet-wrapper/writer.js +0 -76
- package/out/src/parquet-wrapper/writer.js.map +0 -1
- package/out/src/runner.d.ts +0 -126
- package/out/src/runner.d.ts.map +0 -1
- package/out/src/runner.js +0 -189
- package/out/src/runner.js.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.d.ts +0 -20
- package/out/src/shard-recipes/anchor-absorption.d.ts.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.js +0 -82
- package/out/src/shard-recipes/anchor-absorption.js.map +0 -1
- package/out/src/shard-recipes/bare-country.d.ts +0 -25
- package/out/src/shard-recipes/bare-country.d.ts.map +0 -1
- package/out/src/shard-recipes/bare-country.js +0 -87
- package/out/src/shard-recipes/bare-country.js.map +0 -1
- package/out/src/shard-recipes/boundary-stress.d.ts +0 -20
- package/out/src/shard-recipes/boundary-stress.d.ts.map +0 -1
- package/out/src/shard-recipes/boundary-stress.js +0 -83
- package/out/src/shard-recipes/boundary-stress.js.map +0 -1
- package/out/src/shard-recipes/country-balanced.d.ts +0 -32
- package/out/src/shard-recipes/country-balanced.d.ts.map +0 -1
- package/out/src/shard-recipes/country-balanced.js +0 -406
- package/out/src/shard-recipes/country-balanced.js.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts +0 -22
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.js +0 -100
- package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.d.ts +0 -38
- package/out/src/shard-recipes/fr-admin-split.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.js +0 -188
- package/out/src/shard-recipes/fr-admin-split.js.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.d.ts +0 -28
- package/out/src/shard-recipes/fr-bare-street.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.js +0 -143
- package/out/src/shard-recipes/fr-bare-street.js.map +0 -1
- package/out/src/shard-recipes/fr-fragment.d.ts +0 -77
- package/out/src/shard-recipes/fr-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-fragment.js +0 -276
- package/out/src/shard-recipes/fr-fragment.js.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.d.ts +0 -32
- package/out/src/shard-recipes/fr-lieudit.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.js +0 -226
- package/out/src/shard-recipes/fr-lieudit.js.map +0 -1
- package/out/src/shard-recipes/fr-order.d.ts +0 -38
- package/out/src/shard-recipes/fr-order.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-order.js +0 -208
- package/out/src/shard-recipes/fr-order.js.map +0 -1
- package/out/src/shard-recipes/german.d.ts +0 -23
- package/out/src/shard-recipes/german.d.ts.map +0 -1
- package/out/src/shard-recipes/german.js +0 -132
- package/out/src/shard-recipes/german.js.map +0 -1
- package/out/src/shard-recipes/house-venue.d.ts +0 -18
- package/out/src/shard-recipes/house-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/house-venue.js +0 -74
- package/out/src/shard-recipes/house-venue.js.map +0 -1
- package/out/src/shard-recipes/index.d.ts +0 -24
- package/out/src/shard-recipes/index.d.ts.map +0 -1
- package/out/src/shard-recipes/index.js +0 -89
- package/out/src/shard-recipes/index.js.map +0 -1
- package/out/src/shard-recipes/intersection.d.ts +0 -42
- package/out/src/shard-recipes/intersection.d.ts.map +0 -1
- package/out/src/shard-recipes/intersection.js +0 -460
- package/out/src/shard-recipes/intersection.js.map +0 -1
- package/out/src/shard-recipes/locale.d.ts +0 -135
- package/out/src/shard-recipes/locale.d.ts.map +0 -1
- package/out/src/shard-recipes/locale.js +0 -459
- package/out/src/shard-recipes/locale.js.map +0 -1
- package/out/src/shard-recipes/nl-postcode.d.ts +0 -26
- package/out/src/shard-recipes/nl-postcode.d.ts.map +0 -1
- package/out/src/shard-recipes/nl-postcode.js +0 -102
- package/out/src/shard-recipes/nl-postcode.js.map +0 -1
- package/out/src/shard-recipes/no-fragment.d.ts +0 -43
- package/out/src/shard-recipes/no-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/no-fragment.js +0 -188
- package/out/src/shard-recipes/no-fragment.js.map +0 -1
- package/out/src/shard-recipes/no-street-led.d.ts +0 -24
- package/out/src/shard-recipes/no-street-led.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street-led.js +0 -121
- package/out/src/shard-recipes/no-street-led.js.map +0 -1
- package/out/src/shard-recipes/no-street.d.ts +0 -18
- package/out/src/shard-recipes/no-street.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street.js +0 -72
- package/out/src/shard-recipes/no-street.js.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.d.ts +0 -38
- package/out/src/shard-recipes/po-box-cedex.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.js +0 -726
- package/out/src/shard-recipes/po-box-cedex.js.map +0 -1
- package/out/src/shard-recipes/po-box.d.ts +0 -17
- package/out/src/shard-recipes/po-box.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box.js +0 -101
- package/out/src/shard-recipes/po-box.js.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts +0 -47
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.js +0 -125
- package/out/src/shard-recipes/reviewed-postcode-tail.js.map +0 -1
- package/out/src/shard-recipes/scaffold.d.ts +0 -246
- package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
- package/out/src/shard-recipes/scaffold.js +0 -137
- package/out/src/shard-recipes/scaffold.js.map +0 -1
- package/out/src/shard-recipes/si-bare-village.d.ts +0 -32
- package/out/src/shard-recipes/si-bare-village.d.ts.map +0 -1
- package/out/src/shard-recipes/si-bare-village.js +0 -88
- package/out/src/shard-recipes/si-bare-village.js.map +0 -1
- package/out/src/shard-recipes/street-affix.d.ts +0 -89
- package/out/src/shard-recipes/street-affix.d.ts.map +0 -1
- package/out/src/shard-recipes/street-affix.js +0 -578
- package/out/src/shard-recipes/street-affix.js.map +0 -1
- package/out/src/shard-recipes/street-bare.d.ts +0 -25
- package/out/src/shard-recipes/street-bare.d.ts.map +0 -1
- package/out/src/shard-recipes/street-bare.js +0 -86
- package/out/src/shard-recipes/street-bare.js.map +0 -1
- package/out/src/shard-recipes/street.d.ts +0 -15
- package/out/src/shard-recipes/street.d.ts.map +0 -1
- package/out/src/shard-recipes/street.js +0 -69
- package/out/src/shard-recipes/street.js.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.d.ts +0 -228
- package/out/src/shard-recipes/sub-venue-sources.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.js +0 -664
- package/out/src/shard-recipes/sub-venue-sources.js.map +0 -1
- package/out/src/shard-recipes/sub-venue.d.ts +0 -269
- package/out/src/shard-recipes/sub-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue.js +0 -710
- package/out/src/shard-recipes/sub-venue.js.map +0 -1
- package/out/src/shard-recipes/trailing-region.d.ts +0 -74
- package/out/src/shard-recipes/trailing-region.d.ts.map +0 -1
- package/out/src/shard-recipes/trailing-region.js +0 -157
- package/out/src/shard-recipes/trailing-region.js.map +0 -1
- package/out/src/shard-recipes/unit.d.ts +0 -29
- package/out/src/shard-recipes/unit.d.ts.map +0 -1
- package/out/src/shard-recipes/unit.js +0 -243
- package/out/src/shard-recipes/unit.js.map +0 -1
- package/out/src/synthesizers/anchor-absorption.d.ts +0 -63
- package/out/src/synthesizers/anchor-absorption.d.ts.map +0 -1
- package/out/src/synthesizers/anchor-absorption.js +0 -223
- package/out/src/synthesizers/anchor-absorption.js.map +0 -1
- package/out/src/synthesizers/boundary-stress.d.ts +0 -78
- package/out/src/synthesizers/boundary-stress.d.ts.map +0 -1
- package/out/src/synthesizers/boundary-stress.js +0 -455
- package/out/src/synthesizers/boundary-stress.js.map +0 -1
- package/out/src/synthesizers/german.d.ts +0 -107
- package/out/src/synthesizers/german.d.ts.map +0 -1
- package/out/src/synthesizers/german.js +0 -148
- package/out/src/synthesizers/german.js.map +0 -1
- package/out/src/synthesizers/house-venue.d.ts +0 -56
- package/out/src/synthesizers/house-venue.d.ts.map +0 -1
- package/out/src/synthesizers/house-venue.js +0 -267
- package/out/src/synthesizers/house-venue.js.map +0 -1
- package/out/src/synthesizers/intersection.d.ts +0 -52
- package/out/src/synthesizers/intersection.d.ts.map +0 -1
- package/out/src/synthesizers/intersection.js +0 -175
- package/out/src/synthesizers/intersection.js.map +0 -1
- package/out/src/synthesizers/no-street.d.ts +0 -72
- package/out/src/synthesizers/no-street.d.ts.map +0 -1
- package/out/src/synthesizers/no-street.js +0 -282
- package/out/src/synthesizers/no-street.js.map +0 -1
- package/out/src/synthesizers/po-box.d.ts +0 -104
- package/out/src/synthesizers/po-box.d.ts.map +0 -1
- package/out/src/synthesizers/po-box.js +0 -266
- package/out/src/synthesizers/po-box.js.map +0 -1
- package/out/src/synthesizers/street.d.ts +0 -54
- package/out/src/synthesizers/street.d.ts.map +0 -1
- package/out/src/synthesizers/street.js +0 -221
- package/out/src/synthesizers/street.js.map +0 -1
- package/out/src/synthesizers/utils.d.ts +0 -203
- package/out/src/synthesizers/utils.d.ts.map +0 -1
- package/out/src/synthesizers/utils.js +0 -708
- package/out/src/synthesizers/utils.js.map +0 -1
- package/out/src/tools/align-shard.d.ts +0 -8
- package/out/src/tools/align-shard.d.ts.map +0 -1
- package/out/src/tools/align-shard.js +0 -56
- package/out/src/tools/align-shard.js.map +0 -1
- package/out/src/tools/audit.d.ts +0 -28
- package/out/src/tools/audit.d.ts.map +0 -1
- package/out/src/tools/audit.js +0 -285
- package/out/src/tools/audit.js.map +0 -1
- package/out/src/tools/corpus-stats.d.ts +0 -44
- package/out/src/tools/corpus-stats.d.ts.map +0 -1
- package/out/src/tools/corpus-stats.js +0 -138
- package/out/src/tools/corpus-stats.js.map +0 -1
- package/out/src/tools/fetch/ban.d.ts +0 -31
- package/out/src/tools/fetch/ban.d.ts.map +0 -1
- package/out/src/tools/fetch/ban.js +0 -239
- package/out/src/tools/fetch/ban.js.map +0 -1
- package/out/src/tools/fetch/download.d.ts +0 -78
- package/out/src/tools/fetch/download.d.ts.map +0 -1
- package/out/src/tools/fetch/download.js +0 -116
- package/out/src/tools/fetch/download.js.map +0 -1
- package/out/src/tools/fetch/geonames-dump.d.ts +0 -87
- package/out/src/tools/fetch/geonames-dump.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-dump.js +0 -178
- package/out/src/tools/fetch/geonames-dump.js.map +0 -1
- package/out/src/tools/fetch/geonames-postal.d.ts +0 -76
- package/out/src/tools/fetch/geonames-postal.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-postal.js +0 -125
- package/out/src/tools/fetch/geonames-postal.js.map +0 -1
- package/out/src/tools/fetch/hrsa.d.ts +0 -18
- package/out/src/tools/fetch/hrsa.d.ts.map +0 -1
- package/out/src/tools/fetch/hrsa.js +0 -46
- package/out/src/tools/fetch/hrsa.js.map +0 -1
- package/out/src/tools/fetch/imls-pls.d.ts +0 -25
- package/out/src/tools/fetch/imls-pls.d.ts.map +0 -1
- package/out/src/tools/fetch/imls-pls.js +0 -108
- package/out/src/tools/fetch/imls-pls.js.map +0 -1
- package/out/src/tools/fetch/index.d.ts +0 -144
- package/out/src/tools/fetch/index.d.ts.map +0 -1
- package/out/src/tools/fetch/index.js +0 -143
- package/out/src/tools/fetch/index.js.map +0 -1
- package/out/src/tools/fetch/nad.d.ts +0 -70
- package/out/src/tools/fetch/nad.d.ts.map +0 -1
- package/out/src/tools/fetch/nad.js +0 -234
- package/out/src/tools/fetch/nad.js.map +0 -1
- package/out/src/tools/fetch/nppes.d.ts +0 -26
- package/out/src/tools/fetch/nppes.d.ts.map +0 -1
- package/out/src/tools/fetch/nppes.js +0 -126
- package/out/src/tools/fetch/nppes.js.map +0 -1
- package/out/src/tools/fetch/openaddresses.d.ts +0 -61
- package/out/src/tools/fetch/openaddresses.d.ts.map +0 -1
- package/out/src/tools/fetch/openaddresses.js +0 -317
- package/out/src/tools/fetch/openaddresses.js.map +0 -1
- package/out/src/tools/fetch/ourairports.d.ts +0 -45
- package/out/src/tools/fetch/ourairports.d.ts.map +0 -1
- package/out/src/tools/fetch/ourairports.js +0 -128
- package/out/src/tools/fetch/ourairports.js.map +0 -1
- package/out/src/tools/fetch/ppd.d.ts.map +0 -1
- package/out/src/tools/fetch/ppd.js +0 -100
- package/out/src/tools/fetch/ppd.js.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.d.ts +0 -25
- package/out/src/tools/fetch/state-hi-schools.d.ts.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.js +0 -162
- package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
- package/out/src/tools/fetch/state-sources.d.ts +0 -26
- package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
- package/out/src/tools/fetch/state-sources.js +0 -111
- package/out/src/tools/fetch/state-sources.js.map +0 -1
- package/out/src/tools/fetch/tiger-full.d.ts +0 -42
- package/out/src/tools/fetch/tiger-full.d.ts.map +0 -1
- package/out/src/tools/fetch/tiger-full.js +0 -248
- package/out/src/tools/fetch/tiger-full.js.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.d.ts +0 -171
- package/out/src/tools/fetch/wikidata-subvenue.d.ts.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.js +0 -275
- package/out/src/tools/fetch/wikidata-subvenue.js.map +0 -1
- package/out/src/tools/gb-title-case.d.ts.map +0 -1
- package/out/src/tools/gb-title-case.js.map +0 -1
- package/out/src/tools/golden-expand.d.ts +0 -90
- package/out/src/tools/golden-expand.d.ts.map +0 -1
- package/out/src/tools/golden-expand.js +0 -413
- package/out/src/tools/golden-expand.js.map +0 -1
- package/out/src/tools/golden-promote.d.ts.map +0 -1
- package/out/src/tools/golden-promote.js +0 -244
- package/out/src/tools/golden-promote.js.map +0 -1
- package/out/src/tools/golden-relabel-street.d.ts +0 -196
- package/out/src/tools/golden-relabel-street.d.ts.map +0 -1
- package/out/src/tools/golden-relabel-street.js +0 -440
- package/out/src/tools/golden-relabel-street.js.map +0 -1
- package/out/src/tools/index.d.ts +0 -28
- package/out/src/tools/index.d.ts.map +0 -1
- package/out/src/tools/index.js +0 -28
- package/out/src/tools/index.js.map +0 -1
- package/out/src/tools/ingest-csv.d.ts.map +0 -1
- package/out/src/tools/ingest-csv.js +0 -296
- package/out/src/tools/ingest-csv.js.map +0 -1
- package/out/src/tools/jsonl-to-parquet.d.ts +0 -61
- package/out/src/tools/jsonl-to-parquet.d.ts.map +0 -1
- package/out/src/tools/jsonl-to-parquet.js +0 -164
- package/out/src/tools/jsonl-to-parquet.js.map +0 -1
- package/out/src/tools/lint-shard-vocab.d.ts +0 -90
- package/out/src/tools/lint-shard-vocab.d.ts.map +0 -1
- package/out/src/tools/lint-shard-vocab.js +0 -281
- package/out/src/tools/lint-shard-vocab.js.map +0 -1
- package/out/src/tools/lint-shard.d.ts +0 -93
- package/out/src/tools/lint-shard.d.ts.map +0 -1
- package/out/src/tools/lint-shard.js +0 -354
- package/out/src/tools/lint-shard.js.map +0 -1
- package/out/src/tools/overlay-manifest.d.ts +0 -39
- package/out/src/tools/overlay-manifest.d.ts.map +0 -1
- package/out/src/tools/overlay-manifest.js +0 -98
- package/out/src/tools/overlay-manifest.js.map +0 -1
- package/out/src/tools/overture-subvenue.d.ts +0 -112
- package/out/src/tools/overture-subvenue.d.ts.map +0 -1
- package/out/src/tools/overture-subvenue.js +0 -144
- package/out/src/tools/overture-subvenue.js.map +0 -1
- package/out/src/tools/postcode-triples.d.ts +0 -175
- package/out/src/tools/postcode-triples.d.ts.map +0 -1
- package/out/src/tools/postcode-triples.js +0 -304
- package/out/src/tools/postcode-triples.js.map +0 -1
- package/out/src/tools/shard-kryptonite.d.ts +0 -32
- package/out/src/tools/shard-kryptonite.d.ts.map +0 -1
- package/out/src/tools/shard-kryptonite.js +0 -100
- package/out/src/tools/shard-kryptonite.js.map +0 -1
- package/out/src/tools/shard-translit.d.ts +0 -51
- package/out/src/tools/shard-translit.d.ts.map +0 -1
- package/out/src/tools/shard-translit.js +0 -175
- package/out/src/tools/shard-translit.js.map +0 -1
- package/out/src/tools/sub-venue/harvest.d.ts +0 -100
- package/out/src/tools/sub-venue/harvest.d.ts.map +0 -1
- package/out/src/tools/sub-venue/harvest.js +0 -168
- package/out/src/tools/sub-venue/harvest.js.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.d.ts +0 -50
- package/out/src/tools/sub-venue/head-nouns.d.ts.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.js +0 -210
- package/out/src/tools/sub-venue/head-nouns.js.map +0 -1
- package/out/src/tools/sub-venue/surfaces.d.ts +0 -45
- package/out/src/tools/sub-venue/surfaces.d.ts.map +0 -1
- package/out/src/tools/sub-venue/surfaces.js +0 -77
- package/out/src/tools/sub-venue/surfaces.js.map +0 -1
- package/out/src/tools/sub-venue/table.d.ts +0 -229
- package/out/src/tools/sub-venue/table.d.ts.map +0 -1
- package/out/src/tools/sub-venue/table.js +0 -108
- package/out/src/tools/sub-venue/table.js.map +0 -1
- package/out/src/tools/sub-venue/wikidata.d.ts +0 -26
- package/out/src/tools/sub-venue/wikidata.d.ts.map +0 -1
- package/out/src/tools/sub-venue/wikidata.js +0 -62
- package/out/src/tools/sub-venue/wikidata.js.map +0 -1
- package/out/src/tools/sub-venue-lexicon.d.ts +0 -156
- package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
- package/out/src/tools/sub-venue-lexicon.js +0 -282
- package/out/src/tools/sub-venue-lexicon.js.map +0 -1
- package/out/src/tools/sub-venue-promotions.d.ts +0 -94
- package/out/src/tools/sub-venue-promotions.d.ts.map +0 -1
- package/out/src/tools/sub-venue-promotions.js +0 -266
- package/out/src/tools/sub-venue-promotions.js.map +0 -1
- package/out/src/types.d.ts +0 -221
- package/out/src/types.d.ts.map +0 -1
- package/out/src/types.js.map +0 -1
- package/out/src/utils/align.d.ts +0 -93
- package/out/src/utils/align.d.ts.map +0 -1
- package/out/src/utils/align.js +0 -234
- package/out/src/utils/align.js.map +0 -1
- package/out/src/utils/golden.d.ts +0 -69
- package/out/src/utils/golden.d.ts.map +0 -1
- package/out/src/utils/golden.js +0 -127
- package/out/src/utils/golden.js.map +0 -1
- package/out/src/utils/index.d.ts +0 -14
- package/out/src/utils/index.d.ts.map +0 -1
- package/out/src/utils/index.js +0 -14
- package/out/src/utils/index.js.map +0 -1
- package/out/src/utils/license.d.ts.map +0 -1
- package/out/src/utils/license.js.map +0 -1
- package/out/src/utils/parquet.d.ts +0 -162
- package/out/src/utils/parquet.d.ts.map +0 -1
- package/out/src/utils/parquet.js +0 -262
- package/out/src/utils/parquet.js.map +0 -1
- package/out/src/utils/split.d.ts +0 -127
- package/out/src/utils/split.d.ts.map +0 -1
- package/out/src/utils/split.js +0 -204
- package/out/src/utils/split.js.map +0 -1
- package/out/src/utils/tokenize.d.ts +0 -56
- package/out/src/utils/tokenize.d.ts.map +0 -1
- package/out/src/utils/tokenize.js +0 -48
- package/out/src/utils/tokenize.js.map +0 -1
- package/out/src/utils/wof-json.d.ts +0 -109
- package/out/src/utils/wof-json.d.ts.map +0 -1
- package/out/src/utils/wof-json.js +0 -173
- package/out/src/utils/wof-json.js.map +0 -1
- package/src/adapters/ban/adapter.ts +0 -191
- package/src/adapters/ban/street-decompose.ts +0 -96
- package/src/adapters/fcc-bdc/adapter.ts +0 -174
- package/src/adapters/geonames/adapter.ts +0 -200
- package/src/adapters/geonames-postal/adapter.ts +0 -119
- package/src/adapters/gnaf/adapter.ts +0 -149
- package/src/adapters/gnaf/assemble.ts +0 -226
- package/src/adapters/index.ts +0 -149
- package/src/adapters/openaddresses/adapter.ts +0 -251
- package/src/adapters/overture/adapter.ts +0 -162
- package/src/adapters/state-hi-schools/adapter.ts +0 -164
- package/src/adapters/synth-po-box/adapter.ts +0 -204
- package/src/adapters/tiger/adapter.ts +0 -253
- package/src/adapters/tiger/street-decompose.ts +0 -111
- package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -183
- package/src/adapters/usgov-imls-pls/adapter.ts +0 -143
- package/src/adapters/usgov-irs-bmf/adapter.ts +0 -163
- package/src/adapters/usgov-nad/adapter.ts +0 -348
- package/src/adapters/usgov-nppes/adapter.ts +0 -159
- package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -204
- package/src/adapters/utils/index.ts +0 -233
- package/src/adapters/wof-admin-jp/adapter.ts +0 -216
- package/src/adapters/wof-admin-json/adapter.ts +0 -256
- package/src/adapters/wof-json-rows.ts +0 -79
- package/src/adapters/wof-postalcode-json/adapter.ts +0 -183
- package/src/build.ts +0 -386
- package/src/index.ts +0 -14
- package/src/name-prone-us-suffixes.ts +0 -12
- package/src/parquet-wrapper/index.ts +0 -9
- package/src/parquet-wrapper/reader.ts +0 -97
- package/src/parquet-wrapper/schema.ts +0 -88
- package/src/parquet-wrapper/writer.ts +0 -110
- package/src/runner.ts +0 -317
- package/src/shard-recipes/anchor-absorption.ts +0 -103
- package/src/shard-recipes/bare-country.ts +0 -95
- package/src/shard-recipes/boundary-stress.ts +0 -101
- package/src/shard-recipes/country-balanced.ts +0 -524
- package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -111
- package/src/shard-recipes/fr-admin-split.ts +0 -239
- package/src/shard-recipes/fr-bare-street.ts +0 -170
- package/src/shard-recipes/fr-fragment.ts +0 -332
- package/src/shard-recipes/fr-lieudit.ts +0 -302
- package/src/shard-recipes/fr-order.ts +0 -258
- package/src/shard-recipes/german.ts +0 -170
- package/src/shard-recipes/house-venue.ts +0 -88
- package/src/shard-recipes/index.ts +0 -95
- package/src/shard-recipes/intersection.ts +0 -630
- package/src/shard-recipes/locale.ts +0 -599
- package/src/shard-recipes/nl-postcode.ts +0 -115
- package/src/shard-recipes/no-fragment.ts +0 -219
- package/src/shard-recipes/no-street-led.ts +0 -143
- package/src/shard-recipes/no-street.ts +0 -86
- package/src/shard-recipes/po-box-cedex.ts +0 -920
- package/src/shard-recipes/po-box.ts +0 -119
- package/src/shard-recipes/reviewed-postcode-tail.ts +0 -189
- package/src/shard-recipes/scaffold.ts +0 -360
- package/src/shard-recipes/si-bare-village.ts +0 -97
- package/src/shard-recipes/street-affix.ts +0 -826
- package/src/shard-recipes/street-bare.ts +0 -101
- package/src/shard-recipes/street.ts +0 -82
- package/src/shard-recipes/sub-venue-sources.ts +0 -885
- package/src/shard-recipes/sub-venue.ts +0 -984
- package/src/shard-recipes/trailing-region.ts +0 -183
- package/src/shard-recipes/unit.ts +0 -321
- package/src/synthesizers/anchor-absorption.ts +0 -290
- package/src/synthesizers/boundary-stress.ts +0 -531
- package/src/synthesizers/german.ts +0 -251
- package/src/synthesizers/house-venue.ts +0 -330
- package/src/synthesizers/intersection.ts +0 -232
- package/src/synthesizers/no-street.ts +0 -349
- package/src/synthesizers/po-box.ts +0 -339
- package/src/synthesizers/street.ts +0 -274
- package/src/synthesizers/utils.ts +0 -903
- package/src/tools/align-shard.ts +0 -70
- package/src/tools/audit.ts +0 -399
- package/src/tools/corpus-stats.ts +0 -184
- package/src/tools/fetch/ban.ts +0 -290
- package/src/tools/fetch/download.ts +0 -176
- package/src/tools/fetch/geonames-dump.ts +0 -267
- package/src/tools/fetch/geonames-postal.ts +0 -180
- package/src/tools/fetch/hrsa.ts +0 -68
- package/src/tools/fetch/imls-pls.ts +0 -158
- package/src/tools/fetch/index.ts +0 -147
- package/src/tools/fetch/nad.ts +0 -342
- package/src/tools/fetch/nppes.ts +0 -174
- package/src/tools/fetch/openaddresses.ts +0 -404
- package/src/tools/fetch/ourairports.ts +0 -171
- package/src/tools/fetch/ppd.ts +0 -137
- package/src/tools/fetch/state-hi-schools.ts +0 -208
- package/src/tools/fetch/state-sources.ts +0 -155
- package/src/tools/fetch/tiger-full.ts +0 -354
- package/src/tools/fetch/wikidata-subvenue.ts +0 -386
- package/src/tools/golden-expand.ts +0 -584
- package/src/tools/golden-promote.ts +0 -353
- package/src/tools/golden-relabel-street.ts +0 -685
- package/src/tools/index.ts +0 -28
- package/src/tools/ingest-csv.ts +0 -422
- package/src/tools/jsonl-to-parquet.ts +0 -221
- package/src/tools/lint-shard-vocab.ts +0 -409
- package/src/tools/lint-shard.ts +0 -543
- package/src/tools/overlay-manifest.ts +0 -157
- package/src/tools/overture-subvenue.ts +0 -215
- package/src/tools/postcode-triples.ts +0 -375
- package/src/tools/shard-kryptonite.ts +0 -139
- package/src/tools/shard-translit.ts +0 -245
- package/src/tools/sub-venue/harvest.ts +0 -235
- package/src/tools/sub-venue/head-nouns.ts +0 -242
- package/src/tools/sub-venue/surfaces.ts +0 -95
- package/src/tools/sub-venue/table.ts +0 -281
- package/src/tools/sub-venue/wikidata.ts +0 -85
- package/src/tools/sub-venue-lexicon.ts +0 -431
- package/src/tools/sub-venue-promotions.ts +0 -330
- package/src/types.ts +0 -247
- package/src/utils/align.ts +0 -331
- package/src/utils/golden.ts +0 -176
- package/src/utils/index.ts +0 -14
- package/src/utils/parquet.ts +0 -391
- package/src/utils/split.ts +0 -279
- package/src/utils/tokenize.ts +0 -78
- package/src/utils/wof-json.ts +0 -244
- /package/{src → lib}/adapters/state-ia-contractors/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-ny-notaries/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-tx-notaries/adapter.ts +0 -0
- /package/{src → lib}/codex/us-fips-state.ts +0 -0
- /package/{src → lib}/tools/gb-title-case.ts +0 -0
- /package/{src → lib}/utils/license.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/fcc-bdc/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/geonames/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/openaddresses/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/synth-po-box/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/tiger/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-nppes/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-samhsa-treatment-locator/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/wof-admin-jp/adapter.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.js +0 -0
- /package/out/{src/tools → tools}/fetch/ppd.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.js +0 -0
- /package/out/{src/tools → tools}/golden-promote.d.ts +0 -0
- /package/out/{src/tools → tools}/ingest-csv.d.ts +0 -0
- /package/out/{src/types.js → types.js} +0 -0
- /package/out/{src/utils → utils}/license.d.ts +0 -0
- /package/out/{src/utils → utils}/license.js +0 -0
|
@@ -1,266 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* The sub-venue curation ledger (#35 wave 2) — every decision taken about whether a designator
|
|
7
|
-
* surface may be used for parsing IN A GIVEN LOCALE, with the census that backs it.
|
|
8
|
-
*
|
|
9
|
-
* This file is HAND-AUTHORED. `sub-venue-lexicon.ts` is a pure function of its sources; nothing in it
|
|
10
|
-
* can decide that Spanish `terminal` is safe and British `hall` is not, because that judgement is
|
|
11
|
-
* about the confounds a token has in a language, and a confound is a fact about the world rather than
|
|
12
|
-
* about the data. What the builder does is APPLY these decisions — {@link SUBVENUE_PROMOTIONS} is the
|
|
13
|
-
* only thing that ever sets `curated: true` on a machine-derived surface.
|
|
14
|
-
*
|
|
15
|
-
* ── Why every decision is per-LOCALE ─────────────────────────────────────────────────────────────
|
|
16
|
-
* Wave 1 measured `hall` at 3,274 hits in the Great Britain extract and stopped there, which reads as
|
|
17
|
-
* a verdict on the word. It is not. Re-censused per region 2026-08-05, the same token is a British
|
|
18
|
-
* disaster and a German designator, and no single global flag can express that. The rule this file
|
|
19
|
-
* enforces: a promotion names a designator, a phrase, AND a locale, and it is earned by a count taken
|
|
20
|
-
* in that locale's own data.
|
|
21
|
-
*
|
|
22
|
-
* ── What "real" and "confound" mean in the numbers below ─────────────────────────────────────────
|
|
23
|
-
* Each census counts the surface's occurrences in one region's extract and splits them two ways:
|
|
24
|
-
*
|
|
25
|
-
* - **real** — the phrase sits in a name that is genuinely venue-interior structure, judged by the
|
|
26
|
-
* rule designator of the feature carrying it (`terminal`, `gate`, `campus`) and by the name taking a
|
|
27
|
-
* `<designator> <identifier>` or `<modifier> <designator>` shape.
|
|
28
|
-
* - **confound** — everything else, and the `confoundNote` says WHAT it is. A count with no note is
|
|
29
|
-
* not a census; "3,274 hits" told nobody that 3,205 of them were bus stops named after a village
|
|
30
|
-
* hall.
|
|
31
|
-
*
|
|
32
|
-
* The instrument is `context` on {@link SubVenueSurface} plus the name-shape split; both are
|
|
33
|
-
* reproducible from the committed extracts, and `PROVENANCE.md` records the commands.
|
|
34
|
-
*
|
|
35
|
-
* ── A rejection is a deliverable ─────────────────────────────────────────────────────────────────
|
|
36
|
-
* Rejections stay in this table forever. They are what stops the next contributor re-proposing
|
|
37
|
-
* `hall` for en-GB from the same Wikidata concept that proposed it the first time.
|
|
38
|
-
*/
|
|
39
|
-
/**
|
|
40
|
-
* The ledger. Sorted by designator, then locale, then phrase in the emitted artifact; source order here is grouped by
|
|
41
|
-
* designator for reading.
|
|
42
|
-
*
|
|
43
|
-
* ── A rejection of a SHIPPED designator is ADVISORY ──────────────────────────────────────────────
|
|
44
|
-
* `neural/venue-structure.ts` ships `wing`, `terminal`, `concourse` and six more as a FLAT English vocabulary with no
|
|
45
|
-
* locale gate. Nothing in this table can un-ship them: the `wing` / en-US rejection below tells a shard author which
|
|
46
|
-
* locale to exclude from a generated line, and does not stop the span proposer from firing on "Red Wing". Giving the
|
|
47
|
-
* shipped vocabulary a per-locale gate is the largest thing the shard will want that does not exist yet.
|
|
48
|
-
*/
|
|
49
|
-
export const SUBVENUE_PROMOTIONS = [
|
|
50
|
-
// ── wing ────────────────────────────────────────────────────────────────────────────────────────
|
|
51
|
-
// The designator the corpus task's board rests on (`West Wing` is the one modifier case that
|
|
52
|
-
// already parses), and the cleanest per-locale split in the whole exercise.
|
|
53
|
-
{
|
|
54
|
-
designatorID: "wing",
|
|
55
|
-
phrase: "wing",
|
|
56
|
-
locale: "en-GB",
|
|
57
|
-
decision: "promote",
|
|
58
|
-
real: 23,
|
|
59
|
-
confound: 6,
|
|
60
|
-
confoundNote: "Wing Close, Wing Road and Wing Tollgate House — the Buckinghamshire village of Wing — plus Cambian Wing " +
|
|
61
|
-
"College. All six are the <wing> <word> shape; every real hit is a hospital wing (Bexley Wing, Sorby Wing, " +
|
|
62
|
-
"Maternity Wing, West Wing, Bedford Hospital North Wing). CAVEAT, and it limits how far this generalizes: " +
|
|
63
|
-
"24 of the 29 hits sit on a public_transport=platform, because British bus stops are named after the " +
|
|
64
|
-
"hospital wing they serve. The extractor maps no building wings at all — `aile` in France is 0 hits, `ala` " +
|
|
65
|
-
"in Spain 0, `flügel` in Germany 0 — so this evidence is a property of British stop naming, not of a source " +
|
|
66
|
-
"that has wings in it.",
|
|
67
|
-
census: "great-britain.jsonl 2026-08-05, 29 name hits across name + name:<lang>",
|
|
68
|
-
},
|
|
69
|
-
{
|
|
70
|
-
designatorID: "wing",
|
|
71
|
-
phrase: "wing",
|
|
72
|
-
locale: "en-US",
|
|
73
|
-
decision: "reject",
|
|
74
|
-
real: 4,
|
|
75
|
-
confound: 3354,
|
|
76
|
-
confoundNote: "Red Wing, the boot brand, is 676 shoe_store rows; chicken wings are another 759 " +
|
|
77
|
-
"(chicken_wings_restaurant 394, chicken_restaurant 365) plus 166 general restaurants. The four real hits are " +
|
|
78
|
-
"campus_building rows. This is the same word as en-GB's clean 23 and it is unusable here.",
|
|
79
|
-
census: "poi.db 2026-05-20.0, full 13,681,698-row scan 2026-08-05",
|
|
80
|
-
},
|
|
81
|
-
{
|
|
82
|
-
designatorID: "wing",
|
|
83
|
-
phrase: "wing",
|
|
84
|
-
locale: "fr-FR",
|
|
85
|
-
decision: "reject",
|
|
86
|
-
real: 0,
|
|
87
|
-
confound: 26,
|
|
88
|
-
confoundNote: "Wing Chun and Wing Tsun martial-arts clubs, 15 of 26. Nothing in the French slice of the layer is a " +
|
|
89
|
-
"building wing.",
|
|
90
|
-
census: "poi.db 2026-05-20.0, full scan 2026-08-05 (FR partition, 721,352 rows)",
|
|
91
|
-
},
|
|
92
|
-
// ── hall ────────────────────────────────────────────────────────────────────────────────────────
|
|
93
|
-
// Wave 1 flagged `hall` as per-locale poison on a GB number alone. Two locales measured; both
|
|
94
|
-
// reject, and for DIFFERENT reasons, which is the part worth keeping.
|
|
95
|
-
{
|
|
96
|
-
designatorID: "hall",
|
|
97
|
-
phrase: "hall",
|
|
98
|
-
locale: "en-GB",
|
|
99
|
-
decision: "reject",
|
|
100
|
-
real: 0,
|
|
101
|
-
confound: 3273,
|
|
102
|
-
confoundNote: "3,204 of 3,273 hits sit on a public_transport=platform: a British bus stop named after the village hall it " +
|
|
103
|
-
"stands outside. The distribution is Village Hall, Town Hall, British Legion Hall, and then Hall Lane / Hall " +
|
|
104
|
-
"Road / SPEKE HALL ROAD — streets. The 52 that take a <hall> <identifier> shape are bus-stop position codes " +
|
|
105
|
-
"(Village Hall (o/s), Town Hall (3)), and all 16 <modifier> <hall> hits are streets (East Hall Lane, North " +
|
|
106
|
-
"Hall Road).",
|
|
107
|
-
census: "great-britain.jsonl 2026-08-05, 3,273 name hits",
|
|
108
|
-
},
|
|
109
|
-
{
|
|
110
|
-
designatorID: "hall",
|
|
111
|
-
phrase: "hall",
|
|
112
|
-
locale: "en-US",
|
|
113
|
-
decision: "reject",
|
|
114
|
-
real: 2095,
|
|
115
|
-
confound: 27_081,
|
|
116
|
-
confoundNote: "City Hall (5,066 town_hall rows), Kingdom Hall of Jehovah's Witnesses (2,312), event halls (2,622) and " +
|
|
117
|
-
"dormitory halls (1,989). Every one names a whole VENUE, not interior structure, so promoting the surface " +
|
|
118
|
-
"would tag them `unit`. The 2,095 real hits are US campus buildings (UAA Cuddy Hall) and they are outnumbered " +
|
|
119
|
-
"13 to 1.",
|
|
120
|
-
census: "poi.db 2026-05-20.0, full 13,681,698-row scan 2026-08-05",
|
|
121
|
-
},
|
|
122
|
-
{
|
|
123
|
-
designatorID: "hall",
|
|
124
|
-
phrase: "halle",
|
|
125
|
-
locale: "de-DE",
|
|
126
|
-
decision: "promote",
|
|
127
|
-
shape: "identifier-required",
|
|
128
|
-
real: 32,
|
|
129
|
-
confound: 168,
|
|
130
|
-
confoundNote: "The confound is 97 hits of the CITY Halle — Halle (Saale), population 240,000, plus Halle (Westf) — and 68 " +
|
|
131
|
-
"village and event halls (PHOENIX Halle, Urexweiler Halle), which are whole venues. That is a worse " +
|
|
132
|
-
"confound than wave 1 assumed when it called `Halle 2` the German counter-example to en-GB: the word is " +
|
|
133
|
-
"also a locality. It is promoted anyway because the confound is SEPARABLE BY SHAPE, and that was checked " +
|
|
134
|
-
"rather than assumed — dumping all 32 <halle> <identifier> hits returns numbered factory, trade-fair and " +
|
|
135
|
-
"airport halls (VW Halle 42, Audi GVZ Halle G, Messe West Halle 8, Flughafen Halle 7, Speyer Halle 101) and " +
|
|
136
|
-
"not one instance of the city. Never modifier-eligible and never proposed bare.",
|
|
137
|
-
census: "germany.jsonl 2026-08-05 (403,863 rows), 200 hits; all 32 shape hits enumerated",
|
|
138
|
-
},
|
|
139
|
-
{
|
|
140
|
-
designatorID: "hall",
|
|
141
|
-
phrase: "hall",
|
|
142
|
-
locale: "fr-FR",
|
|
143
|
-
decision: "promote",
|
|
144
|
-
real: 35,
|
|
145
|
-
confound: 5,
|
|
146
|
-
confoundNote: "Five: an English `Town Hall` and `Multipurpose hall` on French name:en tags, plus `Manning Hall`. French " +
|
|
147
|
-
"uses `hall` as the airport designator directly — 19 hits are Charles de Gaulle (Terminal 2E - Hall K/L/M, " +
|
|
148
|
-
"Terminal 1 - Hall A/B, Hall D) and 16 more are building halls (Hall des Sources, Hall du Marché, Hôpital " +
|
|
149
|
-
"Hall Sud). The word that is poison in en-GB is the ordinary designator one country away.",
|
|
150
|
-
census: "france.jsonl 2026-08-05 (251,260 rows), 40 hits; all 19 shape hits enumerated",
|
|
151
|
-
},
|
|
152
|
-
// ── gate ────────────────────────────────────────────────────────────────────────────────────────
|
|
153
|
-
// The English surface ships and is deliberately NOT modifier-eligible. These decide its localized
|
|
154
|
-
// forms, and the two land on opposite sides for a reason worth keeping.
|
|
155
|
-
{
|
|
156
|
-
designatorID: "gate",
|
|
157
|
-
phrase: "flugsteig",
|
|
158
|
-
locale: "de-DE",
|
|
159
|
-
decision: "promote",
|
|
160
|
-
real: 19,
|
|
161
|
-
confound: 0,
|
|
162
|
-
confoundNote: "None, at full-country scale. 18 of 19 hits are <flugsteig> <identifier> (Flugsteig 10, Flugsteig 9/9A, " +
|
|
163
|
-
"Terminal 1 Flugsteig B) and the last is bare; context is 12 terminal features and 7 gates. The word is a " +
|
|
164
|
-
"pure aviation term with no street, locality or business collision in German. Frankfurt's own name:en " +
|
|
165
|
-
"renders Flugsteig J as `Pier J`, which is a second attestation of the same feature under a second " +
|
|
166
|
-
"designator. A 11-of-11 read on the Hessen extract was the hypothesis; this is the count that earned it.",
|
|
167
|
-
census: "germany.jsonl 2026-08-05 (403,863 rows), 19 hits across name + name:<lang>",
|
|
168
|
-
},
|
|
169
|
-
{
|
|
170
|
-
designatorID: "gate",
|
|
171
|
-
phrase: "porte",
|
|
172
|
-
locale: "fr-FR",
|
|
173
|
-
decision: "reject",
|
|
174
|
-
real: 19,
|
|
175
|
-
confound: 927,
|
|
176
|
-
confoundNote: "946 hits, of which 894 are Paris city gates and the Métro stations named after them — Porte d'Orléans, " +
|
|
177
|
-
"Porte Dauphine, Porte de Champerret, Porte de Saint-Cloud. Unlike `halle`, the confound REACHES the " +
|
|
178
|
-
"designator+identifier shape: 17 of the 36 hits in that bucket are Porte Saint-Martin, Porte Saint-Denis, " +
|
|
179
|
-
"Porte Notre-Dame. Shape cannot separate it, which is the same test that killed `pier` for en-US. The 19 " +
|
|
180
|
-
"real hits are ferry and cruise gates (Porte 4 : Ferrys, Berliet Porte C).",
|
|
181
|
-
census: "france.jsonl 2026-08-05 (251,260 rows), 946 hits; all 36 shape hits enumerated",
|
|
182
|
-
},
|
|
183
|
-
// ── pier ────────────────────────────────────────────────────────────────────────────────────────
|
|
184
|
-
// New in wave 2, and the second clean per-locale split: promotable in en-GB, killed in en-US by a
|
|
185
|
-
// furniture chain whose name is exactly the designator+identifier shape.
|
|
186
|
-
{
|
|
187
|
-
designatorID: "pier",
|
|
188
|
-
phrase: "pier",
|
|
189
|
-
locale: "en-GB",
|
|
190
|
-
decision: "promote",
|
|
191
|
-
real: 120,
|
|
192
|
-
confound: 44,
|
|
193
|
-
confoundNote: "Pier Road, Pier Street, Pier Avenue, Pier Terrace — 44 street names, all of them the <pier> <street-type> " +
|
|
194
|
-
"shape, which the designator+identifier rule cannot reach. The real side is 98 named piers (Eastbourne Pier, " +
|
|
195
|
-
"Cadogan Pier), 10 in <pier> <identifier> shape (Pier 1, Pier 2, `Terminal 3, Pier 6`), 10 bare and 2 with a " +
|
|
196
|
-
"modifier. Promoted as a SURFACE only; not modifier-eligible, on the same reasoning that excludes `gate`.",
|
|
197
|
-
census: "great-britain.jsonl 2026-08-05, 164 name hits",
|
|
198
|
-
},
|
|
199
|
-
{
|
|
200
|
-
designatorID: "pier",
|
|
201
|
-
phrase: "pier",
|
|
202
|
-
locale: "en-US",
|
|
203
|
-
decision: "reject",
|
|
204
|
-
real: 278,
|
|
205
|
-
confound: 2330,
|
|
206
|
-
confoundNote: "Pier 1 Imports and its franchises are 341 home_decor_store plus 217 furniture_store rows, and they carry the " +
|
|
207
|
-
"<pier> <identifier> shape EXACTLY — so unlike en-GB the confound is not separable by shape. Another 159 are " +
|
|
208
|
-
"seafood restaurants and 144 are parks.",
|
|
209
|
-
census: "poi.db 2026-05-20.0, full 13,681,698-row scan 2026-08-05",
|
|
210
|
-
},
|
|
211
|
-
// ── terminal ────────────────────────────────────────────────────────────────────────────────────
|
|
212
|
-
// The English surface already ships. These promote the LOCALIZED forms, which is what a non-English
|
|
213
|
-
// shard line needs and what wave 1 had none of.
|
|
214
|
-
{
|
|
215
|
-
designatorID: "terminal",
|
|
216
|
-
phrase: "terminal",
|
|
217
|
-
locale: "es-ES",
|
|
218
|
-
decision: "promote",
|
|
219
|
-
real: 190,
|
|
220
|
-
confound: 0,
|
|
221
|
-
confoundNote: "None. Spanish borrows the English word unchanged and uses it in every shape the task targets: Terminal A, " +
|
|
222
|
-
"Terminal T1, Terminal 4S, plus named terminals (Terminal Marítima de Santander). No Spanish street type " +
|
|
223
|
-
"collides with it. The Wikidata label `terminal aeroportuaria` is the encyclopaedic form and stays uncurated; " +
|
|
224
|
-
"this promotes the derived head noun.",
|
|
225
|
-
census: "spain.jsonl 2026-08-05, 190 hits across name + name:<lang>",
|
|
226
|
-
},
|
|
227
|
-
{
|
|
228
|
-
designatorID: "terminal",
|
|
229
|
-
phrase: "terminal",
|
|
230
|
-
locale: "ca-ES",
|
|
231
|
-
decision: "promote",
|
|
232
|
-
real: 15,
|
|
233
|
-
confound: 0,
|
|
234
|
-
confoundNote: "None. Catalan is the same borrowing (Terminal 1, Terminal Sortides, Terminal Arribades) and needs its own " +
|
|
235
|
-
"entry because a surface's language subtag is `ca`, which an es-ES decision does not reach.",
|
|
236
|
-
census: "spain.jsonl 2026-08-05, 15 name:ca hits",
|
|
237
|
-
},
|
|
238
|
-
{
|
|
239
|
-
designatorID: "terminal",
|
|
240
|
-
phrase: "terminal",
|
|
241
|
-
locale: "fr-FR",
|
|
242
|
-
decision: "promote",
|
|
243
|
-
real: 169,
|
|
244
|
-
confound: 0,
|
|
245
|
-
confoundNote: "None. 99 hits are <terminal> <identifier> (Aéroport CDG Terminal 2F, Terminal 2G, Lyon Saint-Exupéry " +
|
|
246
|
-
"Terminal 1), 51 are named terminals (Terminal de Grande-Bretagne, Terminal Croisières) and 13 trail a " +
|
|
247
|
-
"venue name. French borrows the word unchanged and no French street type collides with it.",
|
|
248
|
-
census: "france.jsonl 2026-08-05 (251,260 rows), 169 hits across name + name:<lang>",
|
|
249
|
-
},
|
|
250
|
-
{
|
|
251
|
-
designatorID: "terminal",
|
|
252
|
-
phrase: "ターミナル",
|
|
253
|
-
locale: "ja-JP",
|
|
254
|
-
decision: "promote",
|
|
255
|
-
real: 1213,
|
|
256
|
-
confound: 2,
|
|
257
|
-
confoundNote: "Two hits are `ターミナル前` — a bus stop named 'in front of the terminal', which is arguably still real. " +
|
|
258
|
-
"Japanese has no street-name class containing the word. 246 hits take the Japanese target shape " +
|
|
259
|
-
"<identifier><designator> (第2ターミナル, 羽田空港第1ターミナル); 957 are compounds naming a terminal " +
|
|
260
|
-
"(バスターミナル, フェリーターミナル, 成田空港第一ターミナル); 10 are <designator> <identifier>. This is the " +
|
|
261
|
-
"surface the corpus task named as missing, and it exists only because the head-noun derivation produced it " +
|
|
262
|
-
"from five compound Wikidata labels first.",
|
|
263
|
-
census: "japan.jsonl 2026-08-05, 1,215 hits across name + name:<lang>",
|
|
264
|
-
},
|
|
265
|
-
];
|
|
266
|
-
//# sourceMappingURL=sub-venue-promotions.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"sub-venue-promotions.js","sourceRoot":"","sources":["../../../src/tools/sub-venue-promotions.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAqCG;AA+CH;;;;;;;;;GASG;AACH,MAAM,CAAC,MAAM,mBAAmB,GAAiC;IAChE,mGAAmG;IACnG,6FAA6F;IAC7F,4EAA4E;IAC5E;QACC,YAAY,EAAE,MAAM;QACpB,MAAM,EAAE,MAAM;QACd,MAAM,EAAE,OAAO;QACf,QAAQ,EAAE,SAAS;QACnB,IAAI,EAAE,EAAE;QACR,QAAQ,EAAE,CAAC;QACX,YAAY,EACX,0GAA0G;YAC1G,4GAA4G;YAC5G,2GAA2G;YAC3G,sGAAsG;YACtG,4GAA4G;YAC5G,6GAA6G;YAC7G,uBAAuB;QACxB,MAAM,EAAE,wEAAwE;KAChF;IACD;QACC,YAAY,EAAE,MAAM;QACpB,MAAM,EAAE,MAAM;QACd,MAAM,EAAE,OAAO;QACf,QAAQ,EAAE,QAAQ;QAClB,IAAI,EAAE,CAAC;QACP,QAAQ,EAAE,IAAI;QACd,YAAY,EACX,kFAAkF;YAClF,8GAA8G;YAC9G,0FAA0F;QAC3F,MAAM,EAAE,0DAA0D;KAClE;IACD;QACC,YAAY,EAAE,MAAM;QACpB,MAAM,EAAE,MAAM;QACd,MAAM,EAAE,OAAO;QACf,QAAQ,EAAE,QAAQ;QAClB,IAAI,EAAE,CAAC;QACP,QAAQ,EAAE,EAAE;QACZ,YAAY,EACX,sGAAsG;YACtG,gBAAgB;QACjB,MAAM,EAAE,wEAAwE;KAChF;IAED,mGAAmG;IACnG,8FAA8F;IAC9F,sEAAsE;IACtE;QACC,YAAY,EAAE,MAAM;QACpB,MAAM,EAAE,MAAM;QACd,MAAM,EAAE,OAAO;QACf,QAAQ,EAAE,QAAQ;QAClB,IAAI,EAAE,CAAC;QACP,QAAQ,EAAE,IAAI;QACd,YAAY,EACX,6GAA6G;YAC7G,8GAA8G;YAC9G,6GAA6G;YAC7G,4GAA4G;YAC5G,aAAa;QACd,MAAM,EAAE,iDAAiD;KACzD;IACD;QACC,YAAY,EAAE,MAAM;QACpB,MAAM,EAAE,MAAM;QACd,MAAM,EAAE,OAAO;QACf,QAAQ,EAAE,QAAQ;QAClB,IAAI,EAAE,IAAI;QACV,QAAQ,EAAE,MAAM;QAChB,YAAY,EACX,yGAAyG;YACzG,2GAA2G;YAC3G,+GAA+G;YAC/G,UAAU;QACX,MAAM,EAAE,0DAA0D;KAClE;IACD;QACC,YAAY,EAAE,MAAM;QACpB,MAAM,EAAE,OAAO;QACf,MAAM,EAAE,OAAO;QACf,QAAQ,EAAE,SAAS;QACnB,KAAK,EAAE,qBAAqB;QAC5B,IAAI,EAAE,EAAE;QACR,QAAQ,EAAE,GAAG;QACb,YAAY,EACX,6GAA6G;YAC7G,qGAAqG;YACrG,yGAAyG;YACzG,0GAA0G;YAC1G,0GAA0G;YAC1G,6GAA6G;YAC7G,gFAAgF;QACjF,MAAM,EAAE,iFAAiF;KACzF;IACD;QACC,YAAY,EAAE,MAAM;QACpB,MAAM,EAAE,MAAM;QACd,MAAM,EAAE,OAAO;QACf,QAAQ,EAAE,SAAS;QACnB,IAAI,EAAE,EAAE;QACR,QAAQ,EAAE,CAAC;QACX,YAAY,EACX,2GAA2G;YAC3G,4GAA4G;YAC5G,2GAA2G;YAC3G,0FAA0F;QAC3F,MAAM,EAAE,+EAA+E;KACvF;IAED,mGAAmG;IACnG,kGAAkG;IAClG,wEAAwE;IACxE;QACC,YAAY,EAAE,MAAM;QACpB,MAAM,EAAE,WAAW;QACnB,MAAM,EAAE,OAAO;QACf,QAAQ,EAAE,SAAS;QACnB,IAAI,EAAE,EAAE;QACR,QAAQ,EAAE,CAAC;QACX,YAAY,EACX,yGAAyG;YACzG,2GAA2G;YAC3G,uGAAuG;YACvG,oGAAoG;YACpG,yGAAyG;QAC1G,MAAM,EAAE,4EAA4E;KACpF;IACD;QACC,YAAY,EAAE,MAAM;QACpB,MAAM,EAAE,OAAO;QACf,MAAM,EAAE,OAAO;QACf,QAAQ,EAAE,QAAQ;QAClB,IAAI,EAAE,EAAE;QACR,QAAQ,EAAE,GAAG;QACb,YAAY,EACX,yGAAyG;YACzG,sGAAsG;YACtG,2GAA2G;YAC3G,0GAA0G;YAC1G,2EAA2E;QAC5E,MAAM,EAAE,gFAAgF;KACxF;IAED,mGAAmG;IACnG,kGAAkG;IAClG,yEAAyE;IACzE;QACC,YAAY,EAAE,MAAM;QACpB,MAAM,EAAE,MAAM;QACd,MAAM,EAAE,OAAO;QACf,QAAQ,EAAE,SAAS;QACnB,IAAI,EAAE,GAAG;QACT,QAAQ,EAAE,EAAE;QACZ,YAAY,EACX,4GAA4G;YAC5G,8GAA8G;YAC9G,8GAA8G;YAC9G,0GAA0G;QAC3G,MAAM,EAAE,+CAA+C;KACvD;IACD;QACC,YAAY,EAAE,MAAM;QACpB,MAAM,EAAE,MAAM;QACd,MAAM,EAAE,OAAO;QACf,QAAQ,EAAE,QAAQ;QAClB,IAAI,EAAE,GAAG;QACT,QAAQ,EAAE,IAAI;QACd,YAAY,EACX,+GAA+G;YAC/G,8GAA8G;YAC9G,wCAAwC;QACzC,MAAM,EAAE,0DAA0D;KAClE;IAED,mGAAmG;IACnG,oGAAoG;IACpG,gDAAgD;IAChD;QACC,YAAY,EAAE,UAAU;QACxB,MAAM,EAAE,UAAU;QAClB,MAAM,EAAE,OAAO;QACf,QAAQ,EAAE,SAAS;QACnB,IAAI,EAAE,GAAG;QACT,QAAQ,EAAE,CAAC;QACX,YAAY,EACX,4GAA4G;YAC5G,0GAA0G;YAC1G,+GAA+G;YAC/G,sCAAsC;QACvC,MAAM,EAAE,4DAA4D;KACpE;IACD;QACC,YAAY,EAAE,UAAU;QACxB,MAAM,EAAE,UAAU;QAClB,MAAM,EAAE,OAAO;QACf,QAAQ,EAAE,SAAS;QACnB,IAAI,EAAE,EAAE;QACR,QAAQ,EAAE,CAAC;QACX,YAAY,EACX,4GAA4G;YAC5G,4FAA4F;QAC7F,MAAM,EAAE,yCAAyC;KACjD;IACD;QACC,YAAY,EAAE,UAAU;QACxB,MAAM,EAAE,UAAU;QAClB,MAAM,EAAE,OAAO;QACf,QAAQ,EAAE,SAAS;QACnB,IAAI,EAAE,GAAG;QACT,QAAQ,EAAE,CAAC;QACX,YAAY,EACX,uGAAuG;YACvG,wGAAwG;YACxG,2FAA2F;QAC5F,MAAM,EAAE,4EAA4E;KACpF;IACD;QACC,YAAY,EAAE,UAAU;QACxB,MAAM,EAAE,OAAO;QACf,MAAM,EAAE,OAAO;QACf,QAAQ,EAAE,SAAS;QACnB,IAAI,EAAE,IAAI;QACV,QAAQ,EAAE,CAAC;QACX,YAAY,EACX,qGAAqG;YACrG,iGAAiG;YACjG,uFAAuF;YACvF,mFAAmF;YACnF,4GAA4G;YAC5G,2CAA2C;QAC5C,MAAM,EAAE,8DAA8D;KACtE;CACD,CAAA"}
|
package/out/src/types.d.ts
DELETED
|
@@ -1,221 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Canonical row schemas for the corpus pipeline (per #6 / Phase 1 plan).
|
|
7
|
-
*
|
|
8
|
-
* The corpus pipeline produces two row shapes:
|
|
9
|
-
*
|
|
10
|
-
* 1. `CanonicalRow`: an adapter's raw output. Carries a free-form `raw` string, a per-component
|
|
11
|
-
* ground-truth dict, provenance, and an optional augmentation marker. Adapters emit these.
|
|
12
|
-
* 2. `LabeledRow`: alignment's output. Adds a SentencePiece token list and a parallel BIO label list,
|
|
13
|
-
* suitable for direct ingestion by the neural training loop.
|
|
14
|
-
*
|
|
15
|
-
* `CorpusAdapter` is the contract every data source implements; `AdapterOptions` is the
|
|
16
|
-
* per-invocation knob set (input path, optional country filter, row cap, abort signal).
|
|
17
|
-
*/
|
|
18
|
-
import type { BIOLabel, ComponentTag } from "@mailwoman/core/types";
|
|
19
|
-
/**
|
|
20
|
-
* Provenance + augmentation metadata that travels with every corpus row.
|
|
21
|
-
*
|
|
22
|
-
* `synth` is `undefined` for natural (un-augmented) rows; present only when a row was produced by the synthesis
|
|
23
|
-
* pipeline (see `synthesize.ts`).
|
|
24
|
-
*/
|
|
25
|
-
export interface SourceProvenance {
|
|
26
|
-
/**
|
|
27
|
-
* Adapter id that emitted this row, e.g. `"wof-admin"`, `"ban"`, `"openaddresses"`.
|
|
28
|
-
*/
|
|
29
|
-
source: string;
|
|
30
|
-
/**
|
|
31
|
-
* Stable id within the adapter's source. For SQLite-backed adapters this is the row's primary key; for CSV/GeoJSON, a
|
|
32
|
-
* hash of the canonical components. Must be stable across reruns so that dedup and holdout manifests are
|
|
33
|
-
* reproducible.
|
|
34
|
-
*/
|
|
35
|
-
source_id: string;
|
|
36
|
-
/**
|
|
37
|
-
* Corpus version string. Stamped by the runner, not the adapter. Locked together with the tokenizer version:
|
|
38
|
-
* `corpus-v0.1.0` ships with `tokenizer-v0.1.0`.
|
|
39
|
-
*/
|
|
40
|
-
corpus_version: string;
|
|
41
|
-
/**
|
|
42
|
-
* Short license label or SPDX id for _this_ row. Defaults to the adapter's `defaultLicense`, but per-row sources
|
|
43
|
-
* (OpenAddresses) override.
|
|
44
|
-
*/
|
|
45
|
-
license: string;
|
|
46
|
-
}
|
|
47
|
-
/**
|
|
48
|
-
* Marker placed on rows produced by `synthesize.ts`. Allows downstream code to weight, stratify, or exclude
|
|
49
|
-
* augmentations.
|
|
50
|
-
*/
|
|
51
|
-
export interface SynthMarker {
|
|
52
|
-
/**
|
|
53
|
-
* Pipeline id describing what augmentation produced this row. Free-form but stable — e.g. `"case-perturb"`,
|
|
54
|
-
* `"accent-strip"`, `"abbrev-swap"`, `"compose:case-perturb+typo"`.
|
|
55
|
-
*/
|
|
56
|
-
method: string;
|
|
57
|
-
/**
|
|
58
|
-
* `source_id` of the un-augmented row this was derived from. Allows tracing every synthetic row back to its natural
|
|
59
|
-
* ancestor.
|
|
60
|
-
*/
|
|
61
|
-
base_source_id: string;
|
|
62
|
-
}
|
|
63
|
-
/**
|
|
64
|
-
* One address row, before tokenization + BIO labeling.
|
|
65
|
-
*
|
|
66
|
-
* `raw` is what a parser would see in the wild — possibly multi-line, with arbitrary whitespace. `components` is the
|
|
67
|
-
* ground-truth tagging: every `ComponentTag` present in the source data, mapped to its surface form _as it appears in
|
|
68
|
-
* `raw`_. Alignment uses this to assign BIO labels.
|
|
69
|
-
*
|
|
70
|
-
* Country is ISO 3166-1 alpha-2 (`"US"`, `"FR"`). Locale is BCP-47 (`"en-US"`, `"fr-FR"`) and is optional; adapters
|
|
71
|
-
* that can't be sure leave it empty and let the runner default by country.
|
|
72
|
-
*/
|
|
73
|
-
export interface CanonicalRow extends SourceProvenance {
|
|
74
|
-
/**
|
|
75
|
-
* Address string as it might appear in source data.
|
|
76
|
-
*/
|
|
77
|
-
raw: string;
|
|
78
|
-
/**
|
|
79
|
-
* Component-by-tag ground truth. Surface forms must occur in `raw` (within the alignment edit distance threshold) or
|
|
80
|
-
* the row will land in the quarantine pile.
|
|
81
|
-
*/
|
|
82
|
-
components: Partial<Record<ComponentTag, string>>;
|
|
83
|
-
/**
|
|
84
|
-
* ISO 3166-1 alpha-2 country code.
|
|
85
|
-
*/
|
|
86
|
-
country: string;
|
|
87
|
-
/**
|
|
88
|
-
* Optional BCP-47 locale. Defaulted by country if absent.
|
|
89
|
-
*/
|
|
90
|
-
locale?: string;
|
|
91
|
-
/**
|
|
92
|
-
* Present only on synthetic rows.
|
|
93
|
-
*/
|
|
94
|
-
synth?: SynthMarker;
|
|
95
|
-
}
|
|
96
|
-
/**
|
|
97
|
-
* Output of `align.ts`. Carries everything `CanonicalRow` does, plus parallel `tokens` and `labels` arrays of identical
|
|
98
|
-
* length (`labels[i]` is the BIO tag for `tokens[i]`) and — as of the v0.5.0 char-offset migration (#519) — parallel
|
|
99
|
-
* char-span arrays addressing `raw` directly.
|
|
100
|
-
*
|
|
101
|
-
* The span triple is the v0.5.0 source of truth; `tokens`/`labels` remain emitted during the transition (and stay
|
|
102
|
-
* derivable afterwards: whitespace split + span lookup). The reverse derivation — today's token labels — is the lossy
|
|
103
|
-
* direction (punctuation-mute).
|
|
104
|
-
*/
|
|
105
|
-
export interface LabeledRow extends CanonicalRow {
|
|
106
|
-
/**
|
|
107
|
-
* SentencePiece subword tokens for `raw`.
|
|
108
|
-
*/
|
|
109
|
-
tokens: readonly string[];
|
|
110
|
-
/**
|
|
111
|
-
* BIO labels, one per token. Same length as `tokens`.
|
|
112
|
-
*/
|
|
113
|
-
labels: readonly BIOLabel[];
|
|
114
|
-
/**
|
|
115
|
-
* Char-offset label spans over `raw` (parallel arrays, per the #519 ruling): `span_starts[i]` is the inclusive start
|
|
116
|
-
* offset (UTF-16 code units) of span `i`, `span_ends[i]` its exclusive end, `span_tags[i]` its component tag.
|
|
117
|
-
* Invariants — enforced loudly by `alignRow`, documented for every other producer: sorted ascending by start,
|
|
118
|
-
* non-overlapping. `raw` must be NFC-normalized or the offsets are ambiguous (also enforced by `alignRow`).
|
|
119
|
-
*
|
|
120
|
-
* Optional during the v0.4.x → v0.5.0 transition only: alignment always emits the triple; frozen historical corpora
|
|
121
|
-
* and not-yet-migrated synthesis paths may lack it. Required once v0.5.0 lands and the token path is deleted.
|
|
122
|
-
*/
|
|
123
|
-
span_starts?: readonly number[];
|
|
124
|
-
/**
|
|
125
|
-
* Exclusive end offsets, parallel to `span_starts`.
|
|
126
|
-
*/
|
|
127
|
-
span_ends?: readonly number[];
|
|
128
|
-
/**
|
|
129
|
-
* Component tags, parallel to `span_starts`.
|
|
130
|
-
*/
|
|
131
|
-
span_tags?: readonly ComponentTag[];
|
|
132
|
-
}
|
|
133
|
-
/**
|
|
134
|
-
* A row that alignment refused to label. Lands in `/data/corpus/quarantine/` for human review.
|
|
135
|
-
*
|
|
136
|
-
* The `reason` is human-readable; common values are `"component-not-found:<tag>"`, `"edit-distance-exceeded:<tag>"`,
|
|
137
|
-
* `"raw-empty"`. Re-running alignment after a fix should re-emit the quarantined rows; the runner keys them by
|
|
138
|
-
* `source_id`.
|
|
139
|
-
*/
|
|
140
|
-
export interface QuarantinedRow {
|
|
141
|
-
row: CanonicalRow;
|
|
142
|
-
reason: string;
|
|
143
|
-
}
|
|
144
|
-
/**
|
|
145
|
-
* Per-invocation knobs handed to an adapter by the runner.
|
|
146
|
-
*
|
|
147
|
-
* `inputPath` is interpreted by the adapter — it might be a single file path, a directory of shards, or even an HTTPS
|
|
148
|
-
* URL. Each adapter documents its own expected shape in its README.
|
|
149
|
-
*
|
|
150
|
-
* `country` filters to a single ISO 3166-1 alpha-2 country _at the adapter level_. Adapters that hold multi-country
|
|
151
|
-
* data (OSM PBF, OpenAddresses) MUST honor this; single-country adapters (BAN) may ignore it but should reject
|
|
152
|
-
* mismatches.
|
|
153
|
-
*
|
|
154
|
-
* `limit` is a soft cap on rows emitted; useful for fixture-driven tests and smoke runs.
|
|
155
|
-
*
|
|
156
|
-
* `signal` allows the runner to cancel a long-running scan cleanly.
|
|
157
|
-
*/
|
|
158
|
-
export interface AdapterOptions {
|
|
159
|
-
/**
|
|
160
|
-
* Path to the adapter's input data (file, directory, or URL — adapter-specific).
|
|
161
|
-
*/
|
|
162
|
-
inputPath: string;
|
|
163
|
-
/**
|
|
164
|
-
* Optional output directory, available to adapters that maintain side state (rare).
|
|
165
|
-
*/
|
|
166
|
-
outputDir?: string;
|
|
167
|
-
/**
|
|
168
|
-
* ISO 3166-1 alpha-2 country filter.
|
|
169
|
-
*/
|
|
170
|
-
country?: string;
|
|
171
|
-
/**
|
|
172
|
-
* Soft row cap. Adapters should stop iterating once this is reached.
|
|
173
|
-
*/
|
|
174
|
-
limit?: number;
|
|
175
|
-
/**
|
|
176
|
-
* Cancellation hook. Adapters should respect this on every iteration boundary.
|
|
177
|
-
*/
|
|
178
|
-
signal?: AbortSignal;
|
|
179
|
-
}
|
|
180
|
-
/**
|
|
181
|
-
* The contract every data source implements.
|
|
182
|
-
*
|
|
183
|
-
* Adapters are async generators: they yield `CanonicalRow`s one at a time, the runner consumes them (writing JSONL +
|
|
184
|
-
* maintaining checksums + driving alignment). Streaming is mandatory — many sources are tens of millions of rows and
|
|
185
|
-
* cannot be buffered.
|
|
186
|
-
*
|
|
187
|
-
* `defaultLicense` is stamped onto every emitted row's `license` field unless the adapter sets `license` explicitly
|
|
188
|
-
* (e.g. OpenAddresses, which carries per-source licenses).
|
|
189
|
-
*/
|
|
190
|
-
export interface CorpusAdapter {
|
|
191
|
-
/**
|
|
192
|
-
* Stable, machine-friendly id used in paths and CLI args. E.g. `"wof-admin"`.
|
|
193
|
-
*/
|
|
194
|
-
readonly id: string;
|
|
195
|
-
/**
|
|
196
|
-
* Default SPDX-ish license label for rows from this adapter. Per-row overrides allowed.
|
|
197
|
-
*/
|
|
198
|
-
readonly defaultLicense: string;
|
|
199
|
-
/**
|
|
200
|
-
* One-sentence description shown by `npx mailwoman corpus list`.
|
|
201
|
-
*/
|
|
202
|
-
readonly description: string;
|
|
203
|
-
/**
|
|
204
|
-
* Async iterable of canonical rows.
|
|
205
|
-
*
|
|
206
|
-
* Implementations MUST:
|
|
207
|
-
*
|
|
208
|
-
* - Honor `opts.country` (filter or reject mismatches).
|
|
209
|
-
* - Honor `opts.limit` (stop after N rows).
|
|
210
|
-
* - Respect `opts.signal` on every iteration.
|
|
211
|
-
* - Set `source` to `this.id` on every emitted row.
|
|
212
|
-
* - Set `license` to `this.defaultLicense` unless overriding per-row.
|
|
213
|
-
*
|
|
214
|
-
* Implementations MUST NOT:
|
|
215
|
-
*
|
|
216
|
-
* - Set `corpus_version` (the runner stamps it).
|
|
217
|
-
* - Mutate previously-yielded rows.
|
|
218
|
-
*/
|
|
219
|
-
rows(opts: AdapterOptions): AsyncIterable<CanonicalRow>;
|
|
220
|
-
}
|
|
221
|
-
//# sourceMappingURL=types.d.ts.map
|
package/out/src/types.d.ts.map
DELETED
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../../src/types.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAEH,OAAO,KAAK,EAAE,QAAQ,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAA;AAEnE;;;;;GAKG;AACH,MAAM,WAAW,gBAAgB;IAChC;;OAEG;IACH,MAAM,EAAE,MAAM,CAAA;IAEd;;;;OAIG;IACH,SAAS,EAAE,MAAM,CAAA;IAEjB;;;OAGG;IACH,cAAc,EAAE,MAAM,CAAA;IAEtB;;;OAGG;IACH,OAAO,EAAE,MAAM,CAAA;CACf;AAED;;;GAGG;AACH,MAAM,WAAW,WAAW;IAC3B;;;OAGG;IACH,MAAM,EAAE,MAAM,CAAA;IAEd;;;OAGG;IACH,cAAc,EAAE,MAAM,CAAA;CACtB;AAED;;;;;;;;;GASG;AACH,MAAM,WAAW,YAAa,SAAQ,gBAAgB;IACrD;;OAEG;IACH,GAAG,EAAE,MAAM,CAAA;IAEX;;;OAGG;IACH,UAAU,EAAE,OAAO,CAAC,MAAM,CAAC,YAAY,EAAE,MAAM,CAAC,CAAC,CAAA;IAEjD;;OAEG;IACH,OAAO,EAAE,MAAM,CAAA;IAEf;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,CAAA;IAEf;;OAEG;IACH,KAAK,CAAC,EAAE,WAAW,CAAA;CACnB;AAED;;;;;;;;GAQG;AACH,MAAM,WAAW,UAAW,SAAQ,YAAY;IAC/C;;OAEG;IACH,MAAM,EAAE,SAAS,MAAM,EAAE,CAAA;IAEzB;;OAEG;IACH,MAAM,EAAE,SAAS,QAAQ,EAAE,CAAA;IAE3B;;;;;;;;OAQG;IACH,WAAW,CAAC,EAAE,SAAS,MAAM,EAAE,CAAA;IAE/B;;OAEG;IACH,SAAS,CAAC,EAAE,SAAS,MAAM,EAAE,CAAA;IAE7B;;OAEG;IACH,SAAS,CAAC,EAAE,SAAS,YAAY,EAAE,CAAA;CACnC;AAED;;;;;;GAMG;AACH,MAAM,WAAW,cAAc;IAC9B,GAAG,EAAE,YAAY,CAAA;IACjB,MAAM,EAAE,MAAM,CAAA;CACd;AAED;;;;;;;;;;;;;GAaG;AACH,MAAM,WAAW,cAAc;IAC9B;;OAEG;IACH,SAAS,EAAE,MAAM,CAAA;IAEjB;;OAEG;IACH,SAAS,CAAC,EAAE,MAAM,CAAA;IAElB;;OAEG;IACH,OAAO,CAAC,EAAE,MAAM,CAAA;IAEhB;;OAEG;IACH,KAAK,CAAC,EAAE,MAAM,CAAA;IAEd;;OAEG;IACH,MAAM,CAAC,EAAE,WAAW,CAAA;CACpB;AAED;;;;;;;;;GASG;AACH,MAAM,WAAW,aAAa;IAC7B;;OAEG;IACH,QAAQ,CAAC,EAAE,EAAE,MAAM,CAAA;IAEnB;;OAEG;IACH,QAAQ,CAAC,cAAc,EAAE,MAAM,CAAA;IAE/B;;OAEG;IACH,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAA;IAE5B;;;;;;;;;;;;;;;OAeG;IACH,IAAI,CAAC,IAAI,EAAE,cAAc,GAAG,aAAa,CAAC,YAAY,CAAC,CAAA;CACvD"}
|
package/out/src/types.js.map
DELETED
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"types.js","sourceRoot":"","sources":["../../src/types.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG"}
|
package/out/src/utils/align.d.ts
DELETED
|
@@ -1,93 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Alignment: turn a `CanonicalRow` (raw + components) into a `LabeledRow` (raw + tokens + BIO
|
|
7
|
-
* labels) or a `QuarantinedRow` (raw + reason) per the Phase 1 plan.
|
|
8
|
-
*
|
|
9
|
-
* Pipeline:
|
|
10
|
-
*
|
|
11
|
-
* 1. For each `(tag, value)` in `components`, find the value's character span in `raw`. First try a
|
|
12
|
-
* verbatim substring match (case-insensitive, whitespace-collapsed). If that fails, fall
|
|
13
|
-
* back to fuzzy match via `fastest-levenshtein`, with a tunable edit distance threshold.
|
|
14
|
-
* 2. If any component cannot be located, reject the row with a human-readable reason and send it to
|
|
15
|
-
* the quarantine pile (`reason: "component-not-found:<tag>"` or
|
|
16
|
-
* `"edit-distance-exceeded:<tag>:<dist>"`).
|
|
17
|
-
* 3. Tokenize `raw` with the supplied `Tokenizer` (defaults to the whitespace tokenizer).
|
|
18
|
-
* 4. For each token: walk the list of component spans, pick the one whose span contains the token's
|
|
19
|
-
* character range. First token in a component span → `B-<tag>`; subsequent tokens →
|
|
20
|
-
* `I-<tag>`; no overlap → `O`.
|
|
21
|
-
* 5. Emit the located char spans verbatim as `span_starts[]` / `span_ends[]` / `span_tags[]` (the
|
|
22
|
-
* v0.5.0 char-offset format, #519). The token quantization in step 4 is the part the v0.5.0
|
|
23
|
-
* rebuild deletes; during the transition both representations ride on every labeled row.
|
|
24
|
-
*
|
|
25
|
-
* Structural invariants the function preserves (the span ones loudly — a violation throws rather
|
|
26
|
-
* than quarantines, because it indicates a bug here, not bad source data):
|
|
27
|
-
*
|
|
28
|
-
* - `tokens.length === labels.length` always.
|
|
29
|
-
* - Each component contributes at most one contiguous BIO run (no `B-tag … O … I-tag` gaps). This is
|
|
30
|
-
* enforced by greedy first-match span assignment + ordered token iteration.
|
|
31
|
-
* - The span triple is sorted ascending by start and non-overlapping.
|
|
32
|
-
* - `raw` is NFC-normalized (asserted per row; a non-NFC raw makes char offsets ambiguous downstream
|
|
33
|
-
* — NFD `é` occupies two code units where NFC `é` occupies one — and silently so).
|
|
34
|
-
*/
|
|
35
|
-
import type { ComponentTag } from "@mailwoman/core/types";
|
|
36
|
-
import type { CanonicalRow, LabeledRow, QuarantinedRow } from "#types";
|
|
37
|
-
import { type Tokenizer } from "./tokenize.ts";
|
|
38
|
-
/**
|
|
39
|
-
* Options for `alignRow`.
|
|
40
|
-
*/
|
|
41
|
-
export interface AlignOptions {
|
|
42
|
-
/**
|
|
43
|
-
* Tokenizer to use. Defaults to `whitespaceTokenizer()`.
|
|
44
|
-
*/
|
|
45
|
-
tokenizer?: Tokenizer;
|
|
46
|
-
/**
|
|
47
|
-
* Max Levenshtein edit distance to accept when a verbatim substring match fails. Set `0` to require verbatim matches
|
|
48
|
-
* only. Default `2`.
|
|
49
|
-
*
|
|
50
|
-
* Distance is computed against same-length windows in `raw`, so the threshold scales naturally with the component
|
|
51
|
-
* value length.
|
|
52
|
-
*/
|
|
53
|
-
maxEditDistance?: number;
|
|
54
|
-
/**
|
|
55
|
-
* Case-insensitive comparison for substring search. Default `true`. The retained span in `raw` is the original case;
|
|
56
|
-
* only matching is case-insensitive.
|
|
57
|
-
*/
|
|
58
|
-
caseInsensitive?: boolean;
|
|
59
|
-
}
|
|
60
|
-
/**
|
|
61
|
-
* Either a successful labeled row or a quarantined one.
|
|
62
|
-
*/
|
|
63
|
-
export type AlignmentResult = {
|
|
64
|
-
kind: "labeled";
|
|
65
|
-
row: LabeledRow;
|
|
66
|
-
} | {
|
|
67
|
-
kind: "quarantined";
|
|
68
|
-
row: QuarantinedRow;
|
|
69
|
-
};
|
|
70
|
-
/**
|
|
71
|
-
* One located char-offset label span over a row's `raw` ([start, end) in UTF-16 code units). The element type behind
|
|
72
|
-
* the parallel `span_starts[]`/`span_ends[]`/`span_tags[]` triple on `LabeledRow` (#519).
|
|
73
|
-
*/
|
|
74
|
-
export interface ComponentSpan {
|
|
75
|
-
tag: ComponentTag;
|
|
76
|
-
start: number;
|
|
77
|
-
end: number;
|
|
78
|
-
}
|
|
79
|
-
/**
|
|
80
|
-
* Align a single row.
|
|
81
|
-
*/
|
|
82
|
-
export declare function alignRow(row: CanonicalRow, opts?: AlignOptions): AlignmentResult;
|
|
83
|
-
/**
|
|
84
|
-
* Enforce the #519 span-triple invariants — in-bounds, sorted ascending by start, non-overlapping — loudly.
|
|
85
|
-
*
|
|
86
|
-
* For `alignRow`: `claimed`-span bookkeeping in `locateSpan` already makes overlap impossible and the caller sorts, so
|
|
87
|
-
* a violation here is a bug in this file, not bad source data: throw (naming the row) rather than quarantine, so the
|
|
88
|
-
* corruption can't ride into a corpus. Exported for every OTHER span producer (`composeAdversarialRow`'s offset
|
|
89
|
-
* arithmetic, future synthesis paths) — any code that emits the triple without going through `alignRow` must pass its
|
|
90
|
-
* output through this.
|
|
91
|
-
*/
|
|
92
|
-
export declare function assertSpanInvariants(spans: readonly ComponentSpan[], row: Pick<CanonicalRow, "raw" | "source" | "source_id">): void;
|
|
93
|
-
//# sourceMappingURL=align.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"align.d.ts","sourceRoot":"","sources":["../../../src/utils/align.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAiCG;AAEH,OAAO,KAAK,EAAY,YAAY,EAAE,MAAM,uBAAuB,CAAA;AAGnE,OAAO,KAAK,EAAE,YAAY,EAAE,UAAU,EAAE,cAAc,EAAE,MAAM,QAAQ,CAAA;AAEtE,OAAO,EAAuC,KAAK,SAAS,EAAE,MAAM,eAAe,CAAA;AAEnF;;GAEG;AACH,MAAM,WAAW,YAAY;IAC5B;;OAEG;IACH,SAAS,CAAC,EAAE,SAAS,CAAA;IAErB;;;;;;OAMG;IACH,eAAe,CAAC,EAAE,MAAM,CAAA;IAExB;;;OAGG;IACH,eAAe,CAAC,EAAE,OAAO,CAAA;CACzB;AAED;;GAEG;AACH,MAAM,MAAM,eAAe,GAAG;IAAE,IAAI,EAAE,SAAS,CAAC;IAAC,GAAG,EAAE,UAAU,CAAA;CAAE,GAAG;IAAE,IAAI,EAAE,aAAa,CAAC;IAAC,GAAG,EAAE,cAAc,CAAA;CAAE,CAAA;AAEjH;;;GAGG;AACH,MAAM,WAAW,aAAa;IAC7B,GAAG,EAAE,YAAY,CAAA;IACjB,KAAK,EAAE,MAAM,CAAA;IACb,GAAG,EAAE,MAAM,CAAA;CACX;AAED;;GAEG;AACH,wBAAgB,QAAQ,CAAC,GAAG,EAAE,YAAY,EAAE,IAAI,GAAE,YAAiB,GAAG,eAAe,CAsFpF;AAED;;;;;;;;GAQG;AACH,wBAAgB,oBAAoB,CACnC,KAAK,EAAE,SAAS,aAAa,EAAE,EAC/B,GAAG,EAAE,IAAI,CAAC,YAAY,EAAE,KAAK,GAAG,QAAQ,GAAG,WAAW,CAAC,GACrD,IAAI,CA4BN"}
|