@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
|
@@ -1,440 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Golden-set street-suffix relabel — v0.1.2 → v0.1.3.
|
|
7
|
-
*
|
|
8
|
-
* ## Why this exists
|
|
9
|
-
*
|
|
10
|
-
* The golden answer key and the training corpus disagreed about ONE thing, and the v9.0.0
|
|
11
|
-
* promotion gate read the disagreement as a model regression (`us.street` 87.4 vs a floor of
|
|
12
|
-
* 87.8). The corpus SPLITS a US street into `street` + `street_suffix` — TIGER's adapter
|
|
13
|
-
* decomposes at `corpus/src/adapters/tiger/street-decompose.ts`, the `street-affix` shard recipe
|
|
14
|
-
* teaches it from USPS Pub-28, and `ComponentTag` carries `street_suffix` as a first-class tag.
|
|
15
|
-
* The golden set FOLDED it: 2,216 US rows carry a `street`, and exactly 2 of them label a
|
|
16
|
-
* `street_suffix`. Operator ruling, 2026-08-06: **the split is canonical**; the golden is the
|
|
17
|
-
* stale side. This tool moves the answer key onto the corpus convention.
|
|
18
|
-
*
|
|
19
|
-
* ## The instrument
|
|
20
|
-
*
|
|
21
|
-
* `matchTrailingSuffix` from `@mailwoman/codex/us` — the USPS Pub-28 Appendix C table, which is
|
|
22
|
-
* also what the corpus shard recipe splits on. The table is NOT re-implemented here, and the
|
|
23
|
-
* libpostal dictionary TIGER reads is deliberately not used: measured on this golden set the two
|
|
24
|
-
* disagree on 51 US rows, and the disagreements run in the codex table's favour (libpostal's
|
|
25
|
-
* `directionals.txt` lists `center|c`, so TIGER reads the `C` of "C STREET" as a directional
|
|
26
|
-
* prefix and then emits no suffix at all).
|
|
27
|
-
*
|
|
28
|
-
* ## What it changes, and what it refuses to
|
|
29
|
-
*
|
|
30
|
-
* Applied only to rows whose `country` is `US`. Three branches, mirroring the SHAPE of TIGER's
|
|
31
|
-
* `decomposeStreet` on codex tables:
|
|
32
|
-
*
|
|
33
|
-
* - **street type** — the last whitespace-separated word is a Pub-28 suffix, and something is left
|
|
34
|
-
* over: "Main St" → `street: "Main"`, `street_suffix: "St"` (1,559 rows).
|
|
35
|
-
* - **street type + post-directional** — the last word is a directional AND the one before it is a
|
|
36
|
-
* Pub-28 suffix: "Pennsylvania Avenue NW" → `street: "Pennsylvania"`,
|
|
37
|
-
* `street_suffix: "Avenue NW"` (347 rows). The post-directional joins the suffix rather than
|
|
38
|
-
* becoming a tag of its own, because that is what the corpus adapter emits; there is no
|
|
39
|
-
* `street_postfix` tag to move it to.
|
|
40
|
-
* - **everything else is left folded** and reported. In particular a BARE post-directional tail
|
|
41
|
-
* ("Seymour East", "BROADWAY N" — 16 rows) is NOT split: a directional is not a Pub-28 suffix,
|
|
42
|
-
* and the observed rows in that class are unit-contaminated ("1ST AVE SW BOX E", where the
|
|
43
|
-
* trailing "E" is a box letter).
|
|
44
|
-
*
|
|
45
|
-
* FR rows are untouched, deliberately and permanently as far as this tool is concerned. French
|
|
46
|
-
* street typology puts the type FIRST ("Rue de la Paix") and the golden labels only 7 of 665 FR
|
|
47
|
-
* street rows with a `street_prefix`; whether FR should split at all is a different question with
|
|
48
|
-
* a different table behind it, and nothing here should be read as having answered it.
|
|
49
|
-
*
|
|
50
|
-
* ## Surface bytes
|
|
51
|
-
*
|
|
52
|
-
* The split is a cut at a whitespace run in the ORIGINAL string — no trimming, no case
|
|
53
|
-
* normalization, no re-joining of tokens. `street + gap + street_suffix` reconstructs the input
|
|
54
|
-
* byte-for-byte, so the whitespace between them belongs to neither span (the same shape the corpus
|
|
55
|
-
* adapter's spans have). The tool asserts this per row and refuses to write a file if it ever
|
|
56
|
-
* fails.
|
|
57
|
-
*/
|
|
58
|
-
import { existsSync, mkdirSync, readdirSync, readFileSync, writeFileSync } from "node:fs";
|
|
59
|
-
import { basename, join } from "node:path";
|
|
60
|
-
import { isStreetDirectionalToken, matchTrailingSuffix } from "@mailwoman/codex/us";
|
|
61
|
-
import { isPresent, parseJSONStrict, tryParsingJSON } from "@mailwoman/core/objects";
|
|
62
|
-
import { sha256File } from "@mailwoman/core/utils";
|
|
63
|
-
import { TextSpliterator } from "spliterator";
|
|
64
|
-
import { NAME_PRONE_US_SUFFIXES } from "../name-prone-us-suffixes.js";
|
|
65
|
-
/**
|
|
66
|
-
* Cut `s` at its LAST whitespace run, returning the three pieces verbatim. Null when there is no interior whitespace,
|
|
67
|
-
* when the head would be empty, or when `s` carries leading/trailing whitespace (a golden row is stored trimmed; an
|
|
68
|
-
* untrimmed one is reported rather than silently normalized).
|
|
69
|
-
*/
|
|
70
|
-
function splitLastWord(s) {
|
|
71
|
-
if (s !== s.trim() || !s)
|
|
72
|
-
return null;
|
|
73
|
-
const match = /^(.*\S)(\s+)(\S+)$/.exec(s);
|
|
74
|
-
if (!match)
|
|
75
|
-
return null;
|
|
76
|
-
return { head: match[1], gap: match[2], tail: match[3] };
|
|
77
|
-
}
|
|
78
|
-
/**
|
|
79
|
-
* Cut `s` at its FIRST whitespace run — the leading-directional counterpart of {@link splitLastWord}. `head` is the
|
|
80
|
-
* first word, `tail` the rest, both verbatim.
|
|
81
|
-
*/
|
|
82
|
-
function splitFirstWord(s) {
|
|
83
|
-
if (s !== s.trim() || !s)
|
|
84
|
-
return null;
|
|
85
|
-
const match = /^(\S+)(\s+)(\S.*)$/.exec(s);
|
|
86
|
-
if (!match)
|
|
87
|
-
return null;
|
|
88
|
-
return { head: match[1], gap: match[2], tail: match[3] };
|
|
89
|
-
}
|
|
90
|
-
// ── Row-level relabel ──────────────────────────────────────────────────────
|
|
91
|
-
/**
|
|
92
|
-
* Rebuild `components` with `street_suffix` inserted immediately after `street`, so the written row reads in address
|
|
93
|
-
* order rather than with the new tag appended at the end.
|
|
94
|
-
*/
|
|
95
|
-
function withStreetSpans(components, spans) {
|
|
96
|
-
const out = {};
|
|
97
|
-
for (const [key, value] of Object.entries(components)) {
|
|
98
|
-
if (key === "street") {
|
|
99
|
-
if (spans.prefix) {
|
|
100
|
-
out.street_prefix = spans.prefix;
|
|
101
|
-
}
|
|
102
|
-
out.street = spans.street;
|
|
103
|
-
if (spans.suffix) {
|
|
104
|
-
out.street_suffix = spans.suffix;
|
|
105
|
-
}
|
|
106
|
-
continue;
|
|
107
|
-
}
|
|
108
|
-
if (key === "street_prefix" || key === "street_suffix")
|
|
109
|
-
continue;
|
|
110
|
-
out[key] = value;
|
|
111
|
-
}
|
|
112
|
-
return out;
|
|
113
|
-
}
|
|
114
|
-
/**
|
|
115
|
-
* Decide, and apply, the US street-span split for ONE golden row. Pure: never mutates its argument, and returns the
|
|
116
|
-
* same object reference when the row is left alone.
|
|
117
|
-
*/
|
|
118
|
-
export function relabelGoldenStreetRow(row, options = {}) {
|
|
119
|
-
const splitPrefix = options.splitPrefix ?? true;
|
|
120
|
-
const keep = (rowClass) => ({
|
|
121
|
-
row,
|
|
122
|
-
changed: false,
|
|
123
|
-
rowClass,
|
|
124
|
-
flags: [],
|
|
125
|
-
prefixSplit: false,
|
|
126
|
-
});
|
|
127
|
-
if ((row.country ?? "").toUpperCase() !== "US")
|
|
128
|
-
return keep("not-us");
|
|
129
|
-
const street = row.components.street;
|
|
130
|
-
if (!street)
|
|
131
|
-
return keep("no-street");
|
|
132
|
-
if (row.components.street_suffix)
|
|
133
|
-
return keep("already-split");
|
|
134
|
-
if (street !== street.trim())
|
|
135
|
-
return keep("untrimmed-street");
|
|
136
|
-
const flags = [];
|
|
137
|
-
let rowClass;
|
|
138
|
-
let name = street;
|
|
139
|
-
let suffix;
|
|
140
|
-
let suffixGap = "";
|
|
141
|
-
let canonical;
|
|
142
|
-
const cut = splitLastWord(street);
|
|
143
|
-
if (!cut) {
|
|
144
|
-
rowClass = matchTrailingSuffix(street) ? "suffix-only-street" : "single-token";
|
|
145
|
-
}
|
|
146
|
-
else if (isStreetDirectionalToken(cut.tail)) {
|
|
147
|
-
// Street type + post-directional ("Pennsylvania Avenue NW"). The corpus adapter emits the pair as
|
|
148
|
-
// ONE suffix span, and there is no post-directional tag to move it to.
|
|
149
|
-
const inner = splitLastWord(cut.head);
|
|
150
|
-
const typeMatch = inner ? matchTrailingSuffix(inner.tail) : null;
|
|
151
|
-
if (!inner || !typeMatch) {
|
|
152
|
-
rowClass = "postdirectional-tail-only";
|
|
153
|
-
}
|
|
154
|
-
else {
|
|
155
|
-
rowClass = "split-suffix-postdirectional";
|
|
156
|
-
name = inner.head;
|
|
157
|
-
suffix = `${inner.tail}${cut.gap}${cut.tail}`;
|
|
158
|
-
suffixGap = inner.gap;
|
|
159
|
-
canonical = typeMatch.canonical;
|
|
160
|
-
}
|
|
161
|
-
}
|
|
162
|
-
else {
|
|
163
|
-
const typeMatch = matchTrailingSuffix(street);
|
|
164
|
-
if (!typeMatch) {
|
|
165
|
-
rowClass = "no-suffix-match";
|
|
166
|
-
}
|
|
167
|
-
else {
|
|
168
|
-
rowClass = "split-suffix";
|
|
169
|
-
name = cut.head;
|
|
170
|
-
suffix = cut.tail;
|
|
171
|
-
suffixGap = cut.gap;
|
|
172
|
-
canonical = typeMatch.canonical;
|
|
173
|
-
}
|
|
174
|
-
}
|
|
175
|
-
// Leading directional → street_prefix, on whatever name survived the suffix move. Independent of the
|
|
176
|
-
// suffix branch, because "N Main" is as folded as "N Main St" is.
|
|
177
|
-
let prefix;
|
|
178
|
-
let prefixGap = "";
|
|
179
|
-
if (splitPrefix && !row.components.street_prefix) {
|
|
180
|
-
const lead = splitFirstWord(name);
|
|
181
|
-
if (lead && isStreetDirectionalToken(lead.head)) {
|
|
182
|
-
prefix = lead.head;
|
|
183
|
-
prefixGap = lead.gap;
|
|
184
|
-
name = lead.tail;
|
|
185
|
-
}
|
|
186
|
-
}
|
|
187
|
-
if (!suffix && !prefix)
|
|
188
|
-
return keep(rowClass);
|
|
189
|
-
if (!suffix) {
|
|
190
|
-
rowClass = "split-prefix-only";
|
|
191
|
-
}
|
|
192
|
-
// The invariant this tool exists to keep: the spans plus the whitespace between them ARE the original
|
|
193
|
-
// span, byte for byte. Anything else means a token was rewritten.
|
|
194
|
-
const rebuilt = `${prefix ? prefix + prefixGap : ""}${name}${suffix ? suffixGap + suffix : ""}`;
|
|
195
|
-
if (rebuilt !== street) {
|
|
196
|
-
throw new Error(`golden-relabel: span reconstruction failed for ${JSON.stringify(street)}`);
|
|
197
|
-
}
|
|
198
|
-
if (canonical && NAME_PRONE_US_SUFFIXES.has(canonical)) {
|
|
199
|
-
flags.push({
|
|
200
|
-
kind: "name-prone-suffix",
|
|
201
|
-
detail: `${canonical} heads proper names as often as street types`,
|
|
202
|
-
});
|
|
203
|
-
}
|
|
204
|
-
const venue = row.components.venue;
|
|
205
|
-
if (suffix && venue && new RegExp(`(^|\\W)${escapeRegExp(suffix)}(\\W|$)`, "i").test(venue)) {
|
|
206
|
-
flags.push({
|
|
207
|
-
kind: "venue-context",
|
|
208
|
-
detail: `venue ${JSON.stringify(venue)} also carries ${JSON.stringify(suffix)}`,
|
|
209
|
-
});
|
|
210
|
-
}
|
|
211
|
-
// Narrow on purpose: a name that happens to be a Pub-28 canonical is NOT interesting ("Mountain Rd",
|
|
212
|
-
// "Valley Dr", "Mills Ln" are ordinary streets, and flagging them buried the deck — 108 rows of noise
|
|
213
|
-
// on the first run). A name that is a bare DIRECTIONAL is: "East Rd" leaves `street: "East"`, which is
|
|
214
|
-
// a direction, not a name.
|
|
215
|
-
if (isStreetDirectionalToken(name)) {
|
|
216
|
-
flags.push({
|
|
217
|
-
kind: "remainder-is-affix",
|
|
218
|
-
detail: `street would become the bare directional ${JSON.stringify(name)}`,
|
|
219
|
-
});
|
|
220
|
-
}
|
|
221
|
-
return {
|
|
222
|
-
row: {
|
|
223
|
-
...row,
|
|
224
|
-
components: withStreetSpans(row.components, {
|
|
225
|
-
...(prefix ? { prefix } : row.components.street_prefix ? { prefix: row.components.street_prefix } : {}),
|
|
226
|
-
street: name,
|
|
227
|
-
...(suffix ? { suffix } : {}),
|
|
228
|
-
}),
|
|
229
|
-
},
|
|
230
|
-
changed: true,
|
|
231
|
-
rowClass,
|
|
232
|
-
flags,
|
|
233
|
-
prefixSplit: Boolean(prefix),
|
|
234
|
-
beforeStreet: street,
|
|
235
|
-
};
|
|
236
|
-
}
|
|
237
|
-
function escapeRegExp(s) {
|
|
238
|
-
return s.replaceAll(/[.*+?^${}()|[\]\\]/g, "\\$&");
|
|
239
|
-
}
|
|
240
|
-
const EMPTY_COUNTS = () => ({
|
|
241
|
-
"split-suffix": 0,
|
|
242
|
-
"split-suffix-postdirectional": 0,
|
|
243
|
-
"split-prefix-only": 0,
|
|
244
|
-
"already-split": 0,
|
|
245
|
-
"single-token": 0,
|
|
246
|
-
"suffix-only-street": 0,
|
|
247
|
-
"postdirectional-tail-only": 0,
|
|
248
|
-
"no-suffix-match": 0,
|
|
249
|
-
"no-street": 0,
|
|
250
|
-
"not-us": 0,
|
|
251
|
-
"untrimmed-street": 0,
|
|
252
|
-
});
|
|
253
|
-
/**
|
|
254
|
-
* Classes that are LEFT FOLDED but still belong in the deck, because the operator asked to see them by name: a street
|
|
255
|
-
* that is entirely one suffix word, and a bare post-directional tail.
|
|
256
|
-
*/
|
|
257
|
-
const DECK_WORTHY_UNCHANGED = new Set([
|
|
258
|
-
"suffix-only-street",
|
|
259
|
-
"postdirectional-tail-only",
|
|
260
|
-
"untrimmed-street",
|
|
261
|
-
]);
|
|
262
|
-
/**
|
|
263
|
-
* Relabel every `.jsonl` in a golden version dir, writing a new version dir plus a review deck and a MANIFEST that
|
|
264
|
-
* records the convention, the parent, and the counts. Non-JSONL siblings (README, split manifests) are copied forward
|
|
265
|
-
* so the new version is self-contained; nested split dirs (`dev/`, `test/`) are relabelled recursively.
|
|
266
|
-
*/
|
|
267
|
-
export async function relabelGoldenDirectory(options, report = console.log) {
|
|
268
|
-
const { input, output } = options;
|
|
269
|
-
const deckPath = options.deck ?? join(output, "REVIEW-DECK.jsonl");
|
|
270
|
-
mkdirSync(output, { recursive: true });
|
|
271
|
-
const deck = [];
|
|
272
|
-
const files = {};
|
|
273
|
-
const walk = (dirIn, dirOut, prefix) => {
|
|
274
|
-
mkdirSync(dirOut, { recursive: true });
|
|
275
|
-
for (const name of readdirSync(dirIn, { withFileTypes: true })) {
|
|
276
|
-
const from = join(dirIn, name.name);
|
|
277
|
-
const to = join(dirOut, name.name);
|
|
278
|
-
if (name.isDirectory()) {
|
|
279
|
-
walk(from, to, `${prefix}${name.name}/`);
|
|
280
|
-
continue;
|
|
281
|
-
}
|
|
282
|
-
if (!name.name.endsWith(".jsonl")) {
|
|
283
|
-
// MANIFEST is rewritten below; everything else (README, SPLIT-MANIFEST) rides forward.
|
|
284
|
-
if (name.name !== "MANIFEST.json") {
|
|
285
|
-
writeFileSync(to, readFileSync(from));
|
|
286
|
-
}
|
|
287
|
-
continue;
|
|
288
|
-
}
|
|
289
|
-
const counts = EMPTY_COUNTS();
|
|
290
|
-
let changed = 0;
|
|
291
|
-
let flagged = 0;
|
|
292
|
-
let prefixSplit = 0;
|
|
293
|
-
const out = [];
|
|
294
|
-
let lineNumber = 0;
|
|
295
|
-
for (const line of TextSpliterator.from(readFileSync(from, "utf8"))) {
|
|
296
|
-
if (!line.trim())
|
|
297
|
-
continue;
|
|
298
|
-
lineNumber++;
|
|
299
|
-
// A corrupt answer-key line must STOP the relabel, not silently drop a row — a golden file
|
|
300
|
-
// short by one row is a floor cut against a different denominator.
|
|
301
|
-
const row = parseJSONStrict(line);
|
|
302
|
-
const result = relabelGoldenStreetRow(row, { splitPrefix: options.splitPrefix ?? true });
|
|
303
|
-
counts[result.rowClass]++;
|
|
304
|
-
if (result.changed) {
|
|
305
|
-
changed++;
|
|
306
|
-
}
|
|
307
|
-
if (result.prefixSplit) {
|
|
308
|
-
prefixSplit++;
|
|
309
|
-
}
|
|
310
|
-
if (result.flags.length) {
|
|
311
|
-
flagged++;
|
|
312
|
-
}
|
|
313
|
-
if (result.changed || DECK_WORTHY_UNCHANGED.has(result.rowClass)) {
|
|
314
|
-
deck.push({
|
|
315
|
-
file: `${prefix}${name.name}`,
|
|
316
|
-
line: lineNumber,
|
|
317
|
-
raw: row.raw,
|
|
318
|
-
rowClass: result.rowClass,
|
|
319
|
-
before: row.components,
|
|
320
|
-
after: result.row.components,
|
|
321
|
-
flags: result.flags,
|
|
322
|
-
});
|
|
323
|
-
}
|
|
324
|
-
out.push(JSON.stringify(result.row));
|
|
325
|
-
}
|
|
326
|
-
writeFileSync(to, out.join("\n") + "\n");
|
|
327
|
-
files[`${prefix}${name.name}`] = { entries: lineNumber, changed, flagged, prefixSplit, counts };
|
|
328
|
-
report(` ${prefix}${name.name}: ${lineNumber} rows, ${changed} changed (${prefixSplit} with a prefix lift), ${flagged} flagged`);
|
|
329
|
-
}
|
|
330
|
-
};
|
|
331
|
-
report(`relabel ${input} → ${output}`);
|
|
332
|
-
walk(input, output, "");
|
|
333
|
-
writeFileSync(deckPath, deck.map((entry) => JSON.stringify(entry)).join("\n") + "\n");
|
|
334
|
-
writeFileSync(deckPath.replace(/\.jsonl$/, ".md"), renderDeckMarkdown(deck, basename(input), basename(output)));
|
|
335
|
-
const manifestFiles = {};
|
|
336
|
-
for (const [name, stats] of Object.entries(files)) {
|
|
337
|
-
manifestFiles[name] = {
|
|
338
|
-
entries: stats.entries,
|
|
339
|
-
sha256: await sha256File(join(output, name)),
|
|
340
|
-
changed: stats.changed,
|
|
341
|
-
flagged: stats.flagged,
|
|
342
|
-
prefix_split: stats.prefixSplit,
|
|
343
|
-
};
|
|
344
|
-
}
|
|
345
|
-
const totalChanged = Object.values(files).reduce((n, f) => n + f.changed, 0);
|
|
346
|
-
const totalFlagged = Object.values(files).reduce((n, f) => n + f.flagged, 0);
|
|
347
|
-
const manifest = {
|
|
348
|
-
version: basename(output),
|
|
349
|
-
parent: options.parentLabel ?? basename(input),
|
|
350
|
-
generated_at: new Date().toISOString(),
|
|
351
|
-
tool: "corpus/src/tools/golden-relabel-street.ts (mailwoman corpus golden-relabel)",
|
|
352
|
-
...(options.commit ? { commit: options.commit } : {}),
|
|
353
|
-
convention: {
|
|
354
|
-
street_convention: { US: "split", "*": "folded" },
|
|
355
|
-
declared: "US street spans are labeled SPLIT: a leading directional is its own `street_prefix` span, the Pub-28 " +
|
|
356
|
-
"street type (plus a post-directional, when one trails it) is its own `street_suffix` span, and `street` " +
|
|
357
|
-
"carries only the name. Non-US rows keep the folded convention of the parent version. A scorer that " +
|
|
358
|
-
"folds `street_prefix`/`street`/`street_suffix` back together before comparing is NOT grading this " +
|
|
359
|
-
"answer key.",
|
|
360
|
-
instrument: "@mailwoman/codex/us — matchTrailingSuffix (USPS Pub-28 Appendix C) for the type, " +
|
|
361
|
-
"isStreetDirectionalToken for the directionals",
|
|
362
|
-
left_folded: "single-token streets, streets that are entirely one suffix word, bare post-directional tails, and any " +
|
|
363
|
-
"street whose trailing word is not in the Pub-28 table",
|
|
364
|
-
prefix_split: options.splitPrefix ?? true,
|
|
365
|
-
},
|
|
366
|
-
counts: {
|
|
367
|
-
changed: totalChanged,
|
|
368
|
-
flagged: totalFlagged,
|
|
369
|
-
prefix_split: Object.values(files).reduce((n, f) => n + f.prefixSplit, 0),
|
|
370
|
-
per_file: Object.fromEntries(Object.entries(files).map(([name, stats]) => [name, stats.counts])),
|
|
371
|
-
},
|
|
372
|
-
files: manifestFiles,
|
|
373
|
-
review_deck: basename(deckPath),
|
|
374
|
-
};
|
|
375
|
-
writeFileSync(join(output, "MANIFEST.json"), JSON.stringify(manifest, null, "\t") + "\n");
|
|
376
|
-
report(`✓ ${totalChanged} rows split, ${totalFlagged} flagged — deck at ${deckPath}`);
|
|
377
|
-
return { files, deckPath, outputDir: output, totalChanged, totalFlagged };
|
|
378
|
-
}
|
|
379
|
-
/**
|
|
380
|
-
* Render the operator-facing half of the review deck: the flagged rows first (those are the ones asking for a ruling),
|
|
381
|
-
* then the classes the tool LEFT FOLDED by name, then a sample of the ordinary corrections. The JSONL sibling carries
|
|
382
|
-
* every row; this file is the one a human reads.
|
|
383
|
-
*/
|
|
384
|
-
function renderDeckMarkdown(deck, parent, version) {
|
|
385
|
-
const span = (components) => [components.street_prefix, components.street, components.street_suffix]
|
|
386
|
-
.filter(isPresent)
|
|
387
|
-
.map((s) => JSON.stringify(s))
|
|
388
|
-
.join(" + ");
|
|
389
|
-
// The split dirs are copies of the same rows — dedupe the deck to the top-level files for reading.
|
|
390
|
-
const top = deck.filter((entry) => !entry.file.includes("/"));
|
|
391
|
-
const flagged = top.filter((entry) => entry.flags.length);
|
|
392
|
-
const folded = top.filter((entry) => isLeftFolded(entry.rowClass));
|
|
393
|
-
const plain = top.filter((entry) => !entry.flags.length && !isLeftFolded(entry.rowClass));
|
|
394
|
-
const rows = (entries) => entries
|
|
395
|
-
.map((entry) => `| ${entry.file}:${entry.line} | ${span(entry.before)} | ${span(entry.after)} | ${entry.flags.map((f) => f.kind).join(", ") || "—"} | ${JSON.stringify(entry.raw)} |`)
|
|
396
|
-
.join("\n");
|
|
397
|
-
const header = "| row | before | after | flags | raw |\n|---|---|---|---|---|";
|
|
398
|
-
return [
|
|
399
|
-
`# Golden street-suffix relabel review deck — ${parent} → ${version}`,
|
|
400
|
-
"",
|
|
401
|
-
"Rows are deduped to the top-level files (`dev/` and `test/` carry the same rows).",
|
|
402
|
-
"A flag is a REVIEW TRIGGER, not an adjudication: the split below is already applied.",
|
|
403
|
-
"",
|
|
404
|
-
`## Flagged (${flagged.length}) — needs a ruling`,
|
|
405
|
-
"",
|
|
406
|
-
header,
|
|
407
|
-
rows(flagged),
|
|
408
|
-
"",
|
|
409
|
-
`## Left folded (${folded.length}) — the tool declined to split these`,
|
|
410
|
-
"",
|
|
411
|
-
header,
|
|
412
|
-
rows(folded),
|
|
413
|
-
"",
|
|
414
|
-
`## Ordinary corrections (${plain.length}) — first 100 shown; the JSONL deck has all`,
|
|
415
|
-
"",
|
|
416
|
-
header,
|
|
417
|
-
rows(plain.slice(0, 100)),
|
|
418
|
-
"",
|
|
419
|
-
].join("\n");
|
|
420
|
-
}
|
|
421
|
-
/**
|
|
422
|
-
* Every relabel class that means the row was left folded, for callers that want to report the residue.
|
|
423
|
-
*/
|
|
424
|
-
export function isLeftFolded(rowClass) {
|
|
425
|
-
return rowClass !== "split-suffix" && rowClass !== "split-suffix-postdirectional" && rowClass !== "split-prefix-only";
|
|
426
|
-
}
|
|
427
|
-
/**
|
|
428
|
-
* True when a golden dir declares the US-split convention — i.e. it is safe to grade it with an UNFOLDED scorer.
|
|
429
|
-
*/
|
|
430
|
-
export function goldenDeclaresSplitStreets(dir) {
|
|
431
|
-
for (const candidate of [join(dir, "MANIFEST.json"), join(dir, "..", "MANIFEST.json")]) {
|
|
432
|
-
if (!existsSync(candidate))
|
|
433
|
-
continue;
|
|
434
|
-
const manifest = tryParsingJSON(readFileSync(candidate, "utf8"));
|
|
435
|
-
if (manifest?.convention?.street_convention?.US === "split")
|
|
436
|
-
return true;
|
|
437
|
-
}
|
|
438
|
-
return false;
|
|
439
|
-
}
|
|
440
|
-
//# sourceMappingURL=golden-relabel-street.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"golden-relabel-street.js","sourceRoot":"","sources":["../../../src/tools/golden-relabel-street.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAwDG;AAEH,OAAO,EAAE,UAAU,EAAE,SAAS,EAAE,WAAW,EAAE,YAAY,EAAE,aAAa,EAAE,MAAM,SAAS,CAAA;AACzF,OAAO,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAE1C,OAAO,EAAE,wBAAwB,EAAE,mBAAmB,EAAuB,MAAM,qBAAqB,CAAA;AACxG,OAAO,EAAE,SAAS,EAAE,eAAe,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAA;AACpF,OAAO,EAAE,UAAU,EAAE,MAAM,uBAAuB,CAAA;AAClD,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C,OAAO,EAAE,sBAAsB,EAAE,MAAM,8BAA8B,CAAA;AAkFrE;;;;GAIG;AACH,SAAS,aAAa,CAAC,CAAS;IAC/B,IAAI,CAAC,KAAK,CAAC,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;QAAE,OAAO,IAAI,CAAA;IACrC,MAAM,KAAK,GAAG,oBAAoB,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IAE1C,IAAI,CAAC,KAAK;QAAE,OAAO,IAAI,CAAA;IAEvB,OAAO,EAAE,IAAI,EAAE,KAAK,CAAC,CAAC,CAAE,EAAE,GAAG,EAAE,KAAK,CAAC,CAAC,CAAE,EAAE,IAAI,EAAE,KAAK,CAAC,CAAC,CAAE,EAAE,CAAA;AAC5D,CAAC;AAED;;;GAGG;AACH,SAAS,cAAc,CAAC,CAAS;IAChC,IAAI,CAAC,KAAK,CAAC,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;QAAE,OAAO,IAAI,CAAA;IACrC,MAAM,KAAK,GAAG,oBAAoB,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IAE1C,IAAI,CAAC,KAAK;QAAE,OAAO,IAAI,CAAA;IAEvB,OAAO,EAAE,IAAI,EAAE,KAAK,CAAC,CAAC,CAAE,EAAE,GAAG,EAAE,KAAK,CAAC,CAAC,CAAE,EAAE,IAAI,EAAE,KAAK,CAAC,CAAC,CAAE,EAAE,CAAA;AAC5D,CAAC;AAED,8EAA8E;AAE9E;;;GAGG;AACH,SAAS,eAAe,CACvB,UAAkC,EAClC,KAA2D;IAE3D,MAAM,GAAG,GAA2B,EAAE,CAAA;IAEtC,KAAK,MAAM,CAAC,GAAG,EAAE,KAAK,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,UAAU,CAAC,EAAE,CAAC;QACvD,IAAI,GAAG,KAAK,QAAQ,EAAE,CAAC;YACtB,IAAI,KAAK,CAAC,MAAM,EAAE,CAAC;gBAClB,GAAG,CAAC,aAAa,GAAG,KAAK,CAAC,MAAM,CAAA;YACjC,CAAC;YAED,GAAG,CAAC,MAAM,GAAG,KAAK,CAAC,MAAM,CAAA;YAEzB,IAAI,KAAK,CAAC,MAAM,EAAE,CAAC;gBAClB,GAAG,CAAC,aAAa,GAAG,KAAK,CAAC,MAAM,CAAA;YACjC,CAAC;YAED,SAAQ;QACT,CAAC;QAED,IAAI,GAAG,KAAK,eAAe,IAAI,GAAG,KAAK,eAAe;YAAE,SAAQ;QAChE,GAAG,CAAC,GAAG,CAAC,GAAG,KAAK,CAAA;IACjB,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC;AAiBD;;;GAGG;AACH,MAAM,UAAU,sBAAsB,CACrC,GAAoB,EACpB,UAAmC,EAAE;IAErC,MAAM,WAAW,GAAG,OAAO,CAAC,WAAW,IAAI,IAAI,CAAA;IAE/C,MAAM,IAAI,GAAG,CAAC,QAA4B,EAAuB,EAAE,CAAC,CAAC;QACpE,GAAG;QACH,OAAO,EAAE,KAAK;QACd,QAAQ;QACR,KAAK,EAAE,EAAE;QACT,WAAW,EAAE,KAAK;KAClB,CAAC,CAAA;IAEF,IAAI,CAAC,GAAG,CAAC,OAAO,IAAI,EAAE,CAAC,CAAC,WAAW,EAAE,KAAK,IAAI;QAAE,OAAO,IAAI,CAAC,QAAQ,CAAC,CAAA;IACrE,MAAM,MAAM,GAAG,GAAG,CAAC,UAAU,CAAC,MAAM,CAAA;IAEpC,IAAI,CAAC,MAAM;QAAE,OAAO,IAAI,CAAC,WAAW,CAAC,CAAA;IAErC,IAAI,GAAG,CAAC,UAAU,CAAC,aAAa;QAAE,OAAO,IAAI,CAAC,eAAe,CAAC,CAAA;IAE9D,IAAI,MAAM,KAAK,MAAM,CAAC,IAAI,EAAE;QAAE,OAAO,IAAI,CAAC,kBAAkB,CAAC,CAAA;IAE7D,MAAM,KAAK,GAAwB,EAAE,CAAA;IACrC,IAAI,QAA4B,CAAA;IAChC,IAAI,IAAI,GAAG,MAAM,CAAA;IACjB,IAAI,MAA0B,CAAA;IAC9B,IAAI,SAAS,GAAG,EAAE,CAAA;IAClB,IAAI,SAAqC,CAAA;IAEzC,MAAM,GAAG,GAAG,aAAa,CAAC,MAAM,CAAC,CAAA;IAEjC,IAAI,CAAC,GAAG,EAAE,CAAC;QACV,QAAQ,GAAG,mBAAmB,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,oBAAoB,CAAC,CAAC,CAAC,cAAc,CAAA;IAC/E,CAAC;SAAM,IAAI,wBAAwB,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC;QAC/C,kGAAkG;QAClG,uEAAuE;QACvE,MAAM,KAAK,GAAG,aAAa,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;QACrC,MAAM,SAAS,GAAG,KAAK,CAAC,CAAC,CAAC,mBAAmB,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAA;QAEhE,IAAI,CAAC,KAAK,IAAI,CAAC,SAAS,EAAE,CAAC;YAC1B,QAAQ,GAAG,2BAA2B,CAAA;QACvC,CAAC;aAAM,CAAC;YACP,QAAQ,GAAG,8BAA8B,CAAA;YACzC,IAAI,GAAG,KAAK,CAAC,IAAI,CAAA;YACjB,MAAM,GAAG,GAAG,KAAK,CAAC,IAAI,GAAG,GAAG,CAAC,GAAG,GAAG,GAAG,CAAC,IAAI,EAAE,CAAA;YAC7C,SAAS,GAAG,KAAK,CAAC,GAAG,CAAA;YACrB,SAAS,GAAG,SAAS,CAAC,SAAS,CAAA;QAChC,CAAC;IACF,CAAC;SAAM,CAAC;QACP,MAAM,SAAS,GAAG,mBAAmB,CAAC,MAAM,CAAC,CAAA;QAE7C,IAAI,CAAC,SAAS,EAAE,CAAC;YAChB,QAAQ,GAAG,iBAAiB,CAAA;QAC7B,CAAC;aAAM,CAAC;YACP,QAAQ,GAAG,cAAc,CAAA;YACzB,IAAI,GAAG,GAAG,CAAC,IAAI,CAAA;YACf,MAAM,GAAG,GAAG,CAAC,IAAI,CAAA;YACjB,SAAS,GAAG,GAAG,CAAC,GAAG,CAAA;YACnB,SAAS,GAAG,SAAS,CAAC,SAAS,CAAA;QAChC,CAAC;IACF,CAAC;IAED,qGAAqG;IACrG,kEAAkE;IAClE,IAAI,MAA0B,CAAA;IAC9B,IAAI,SAAS,GAAG,EAAE,CAAA;IAElB,IAAI,WAAW,IAAI,CAAC,GAAG,CAAC,UAAU,CAAC,aAAa,EAAE,CAAC;QAClD,MAAM,IAAI,GAAG,cAAc,CAAC,IAAI,CAAC,CAAA;QAEjC,IAAI,IAAI,IAAI,wBAAwB,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;YACjD,MAAM,GAAG,IAAI,CAAC,IAAI,CAAA;YAClB,SAAS,GAAG,IAAI,CAAC,GAAG,CAAA;YACpB,IAAI,GAAG,IAAI,CAAC,IAAI,CAAA;QACjB,CAAC;IACF,CAAC;IAED,IAAI,CAAC,MAAM,IAAI,CAAC,MAAM;QAAE,OAAO,IAAI,CAAC,QAAQ,CAAC,CAAA;IAE7C,IAAI,CAAC,MAAM,EAAE,CAAC;QACb,QAAQ,GAAG,mBAAmB,CAAA;IAC/B,CAAC;IAED,sGAAsG;IACtG,kEAAkE;IAClE,MAAM,OAAO,GAAG,GAAG,MAAM,CAAC,CAAC,CAAC,MAAM,GAAG,SAAS,CAAC,CAAC,CAAC,EAAE,GAAG,IAAI,GAAG,MAAM,CAAC,CAAC,CAAC,SAAS,GAAG,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAA;IAE/F,IAAI,OAAO,KAAK,MAAM,EAAE,CAAC;QACxB,MAAM,IAAI,KAAK,CAAC,kDAAkD,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,EAAE,CAAC,CAAA;IAC5F,CAAC;IAED,IAAI,SAAS,IAAI,sBAAsB,CAAC,GAAG,CAAC,SAAS,CAAC,EAAE,CAAC;QACxD,KAAK,CAAC,IAAI,CAAC;YACV,IAAI,EAAE,mBAAmB;YACzB,MAAM,EAAE,GAAG,SAAS,8CAA8C;SAClE,CAAC,CAAA;IACH,CAAC;IAED,MAAM,KAAK,GAAG,GAAG,CAAC,UAAU,CAAC,KAAK,CAAA;IAElC,IAAI,MAAM,IAAI,KAAK,IAAI,IAAI,MAAM,CAAC,UAAU,YAAY,CAAC,MAAM,CAAC,SAAS,EAAE,GAAG,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;QAC7F,KAAK,CAAC,IAAI,CAAC;YACV,IAAI,EAAE,eAAe;YACrB,MAAM,EAAE,SAAS,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,iBAAiB,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,EAAE;SAC/E,CAAC,CAAA;IACH,CAAC;IAED,qGAAqG;IACrG,sGAAsG;IACtG,uGAAuG;IACvG,2BAA2B;IAC3B,IAAI,wBAAwB,CAAC,IAAI,CAAC,EAAE,CAAC;QACpC,KAAK,CAAC,IAAI,CAAC;YACV,IAAI,EAAE,oBAAoB;YAC1B,MAAM,EAAE,4CAA4C,IAAI,CAAC,SAAS,CAAC,IAAI,CAAC,EAAE;SAC1E,CAAC,CAAA;IACH,CAAC;IAED,OAAO;QACN,GAAG,EAAE;YACJ,GAAG,GAAG;YACN,UAAU,EAAE,eAAe,CAAC,GAAG,CAAC,UAAU,EAAE;gBAC3C,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC,UAAU,CAAC,aAAa,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,GAAG,CAAC,UAAU,CAAC,aAAa,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;gBACvG,MAAM,EAAE,IAAI;gBACZ,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;aAC7B,CAAC;SACF;QACD,OAAO,EAAE,IAAI;QACb,QAAQ;QACR,KAAK;QACL,WAAW,EAAE,OAAO,CAAC,MAAM,CAAC;QAC5B,YAAY,EAAE,MAAM;KACpB,CAAA;AACF,CAAC;AAED,SAAS,YAAY,CAAC,CAAS;IAC9B,OAAO,CAAC,CAAC,UAAU,CAAC,qBAAqB,EAAE,MAAM,CAAC,CAAA;AACnD,CAAC;AAkED,MAAM,YAAY,GAAG,GAAwB,EAAE,CAAC,CAAC;IAChD,cAAc,EAAE,CAAC;IACjB,8BAA8B,EAAE,CAAC;IACjC,mBAAmB,EAAE,CAAC;IACtB,eAAe,EAAE,CAAC;IAClB,cAAc,EAAE,CAAC;IACjB,oBAAoB,EAAE,CAAC;IACvB,2BAA2B,EAAE,CAAC;IAC9B,iBAAiB,EAAE,CAAC;IACpB,WAAW,EAAE,CAAC;IACd,QAAQ,EAAE,CAAC;IACX,kBAAkB,EAAE,CAAC;CACrB,CAAC,CAAA;AAEF;;;GAGG;AACH,MAAM,qBAAqB,GAAoC,IAAI,GAAG,CAAC;IACtE,oBAAoB;IACpB,2BAA2B;IAC3B,kBAAkB;CAClB,CAAC,CAAA;AAEF;;;;GAIG;AACH,MAAM,CAAC,KAAK,UAAU,sBAAsB,CAC3C,OAA6B,EAC7B,SAAiC,OAAO,CAAC,GAAG;IAE5C,MAAM,EAAE,KAAK,EAAE,MAAM,EAAE,GAAG,OAAO,CAAA;IACjC,MAAM,QAAQ,GAAG,OAAO,CAAC,IAAI,IAAI,IAAI,CAAC,MAAM,EAAE,mBAAmB,CAAC,CAAA;IAClE,SAAS,CAAC,MAAM,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;IAEtC,MAAM,IAAI,GAA6B,EAAE,CAAA;IACzC,MAAM,KAAK,GAAiC,EAAE,CAAA;IAE9C,MAAM,IAAI,GAAG,CAAC,KAAa,EAAE,MAAc,EAAE,MAAc,EAAQ,EAAE;QACpE,SAAS,CAAC,MAAM,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;QAEtC,KAAK,MAAM,IAAI,IAAI,WAAW,CAAC,KAAK,EAAE,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,EAAE,CAAC;YAChE,MAAM,IAAI,GAAG,IAAI,CAAC,KAAK,EAAE,IAAI,CAAC,IAAI,CAAC,CAAA;YACnC,MAAM,EAAE,GAAG,IAAI,CAAC,MAAM,EAAE,IAAI,CAAC,IAAI,CAAC,CAAA;YAElC,IAAI,IAAI,CAAC,WAAW,EAAE,EAAE,CAAC;gBACxB,IAAI,CAAC,IAAI,EAAE,EAAE,EAAE,GAAG,MAAM,GAAG,IAAI,CAAC,IAAI,GAAG,CAAC,CAAA;gBAExC,SAAQ;YACT,CAAC;YAED,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,QAAQ,CAAC,QAAQ,CAAC,EAAE,CAAC;gBACnC,uFAAuF;gBACvF,IAAI,IAAI,CAAC,IAAI,KAAK,eAAe,EAAE,CAAC;oBACnC,aAAa,CAAC,EAAE,EAAE,YAAY,CAAC,IAAI,CAAC,CAAC,CAAA;gBACtC,CAAC;gBAED,SAAQ;YACT,CAAC;YAED,MAAM,MAAM,GAAG,YAAY,EAAE,CAAA;YAC7B,IAAI,OAAO,GAAG,CAAC,CAAA;YACf,IAAI,OAAO,GAAG,CAAC,CAAA;YACf,IAAI,WAAW,GAAG,CAAC,CAAA;YACnB,MAAM,GAAG,GAAa,EAAE,CAAA;YACxB,IAAI,UAAU,GAAG,CAAC,CAAA;YAElB,KAAK,MAAM,IAAI,IAAI,eAAe,CAAC,IAAI,CAAC,YAAY,CAAC,IAAI,EAAE,MAAM,CAAC,CAAC,EAAE,CAAC;gBACrE,IAAI,CAAC,IAAI,CAAC,IAAI,EAAE;oBAAE,SAAQ;gBAE1B,UAAU,EAAE,CAAA;gBACZ,2FAA2F;gBAC3F,mEAAmE;gBACnE,MAAM,GAAG,GAAG,eAAe,CAAkB,IAAI,CAAC,CAAA;gBAClD,MAAM,MAAM,GAAG,sBAAsB,CAAC,GAAG,EAAE,EAAE,WAAW,EAAE,OAAO,CAAC,WAAW,IAAI,IAAI,EAAE,CAAC,CAAA;gBAExF,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,EAAE,CAAA;gBAEzB,IAAI,MAAM,CAAC,OAAO,EAAE,CAAC;oBACpB,OAAO,EAAE,CAAA;gBACV,CAAC;gBAED,IAAI,MAAM,CAAC,WAAW,EAAE,CAAC;oBACxB,WAAW,EAAE,CAAA;gBACd,CAAC;gBAED,IAAI,MAAM,CAAC,KAAK,CAAC,MAAM,EAAE,CAAC;oBACzB,OAAO,EAAE,CAAA;gBACV,CAAC;gBAED,IAAI,MAAM,CAAC,OAAO,IAAI,qBAAqB,CAAC,GAAG,CAAC,MAAM,CAAC,QAAQ,CAAC,EAAE,CAAC;oBAClE,IAAI,CAAC,IAAI,CAAC;wBACT,IAAI,EAAE,GAAG,MAAM,GAAG,IAAI,CAAC,IAAI,EAAE;wBAC7B,IAAI,EAAE,UAAU;wBAChB,GAAG,EAAE,GAAG,CAAC,GAAG;wBACZ,QAAQ,EAAE,MAAM,CAAC,QAAQ;wBACzB,MAAM,EAAE,GAAG,CAAC,UAAU;wBACtB,KAAK,EAAE,MAAM,CAAC,GAAG,CAAC,UAAU;wBAC5B,KAAK,EAAE,MAAM,CAAC,KAAK;qBACnB,CAAC,CAAA;gBACH,CAAC;gBAED,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAA;YACrC,CAAC;YAED,aAAa,CAAC,EAAE,EAAE,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,IAAI,CAAC,CAAA;YACxC,KAAK,CAAC,GAAG,MAAM,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC,GAAG,EAAE,OAAO,EAAE,UAAU,EAAE,OAAO,EAAE,OAAO,EAAE,WAAW,EAAE,MAAM,EAAE,CAAA;YAE/F,MAAM,CACL,KAAK,MAAM,GAAG,IAAI,CAAC,IAAI,KAAK,UAAU,UAAU,OAAO,aAAa,WAAW,yBAAyB,OAAO,UAAU,CACzH,CAAA;QACF,CAAC;IACF,CAAC,CAAA;IAED,MAAM,CAAC,WAAW,KAAK,MAAM,MAAM,EAAE,CAAC,CAAA;IACtC,IAAI,CAAC,KAAK,EAAE,MAAM,EAAE,EAAE,CAAC,CAAA;IAEvB,aAAa,CAAC,QAAQ,EAAE,IAAI,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,IAAI,CAAC,CAAA;IACrF,aAAa,CAAC,QAAQ,CAAC,OAAO,CAAC,UAAU,EAAE,KAAK,CAAC,EAAE,kBAAkB,CAAC,IAAI,EAAE,QAAQ,CAAC,KAAK,CAAC,EAAE,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,CAAA;IAE/G,MAAM,aAAa,GAGf,EAAE,CAAA;IAEN,KAAK,MAAM,CAAC,IAAI,EAAE,KAAK,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,KAAK,CAAC,EAAE,CAAC;QACnD,aAAa,CAAC,IAAI,CAAC,GAAG;YACrB,OAAO,EAAE,KAAK,CAAC,OAAO;YACtB,MAAM,EAAE,MAAM,UAAU,CAAC,IAAI,CAAC,MAAM,EAAE,IAAI,CAAC,CAAC;YAC5C,OAAO,EAAE,KAAK,CAAC,OAAO;YACtB,OAAO,EAAE,KAAK,CAAC,OAAO;YACtB,YAAY,EAAE,KAAK,CAAC,WAAW;SAC/B,CAAA;IACF,CAAC;IAED,MAAM,YAAY,GAAG,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,CAAC,CAAC,CAAA;IAC5E,MAAM,YAAY,GAAG,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,CAAC,CAAC,CAAA;IAE5E,MAAM,QAAQ,GAAG;QAChB,OAAO,EAAE,QAAQ,CAAC,MAAM,CAAC;QACzB,MAAM,EAAE,OAAO,CAAC,WAAW,IAAI,QAAQ,CAAC,KAAK,CAAC;QAC9C,YAAY,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;QACtC,IAAI,EAAE,6EAA6E;QACnF,GAAG,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,OAAO,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;QACrD,UAAU,EAAE;YACX,iBAAiB,EAAE,EAAE,EAAE,EAAE,OAAO,EAAE,GAAG,EAAE,QAAQ,EAAE;YACjD,QAAQ,EACP,uGAAuG;gBACvG,0GAA0G;gBAC1G,qGAAqG;gBACrG,oGAAoG;gBACpG,aAAa;YACd,UAAU,EACT,mFAAmF;gBACnF,+CAA+C;YAChD,WAAW,EACV,wGAAwG;gBACxG,uDAAuD;YACxD,YAAY,EAAE,OAAO,CAAC,WAAW,IAAI,IAAI;SACzC;QACD,MAAM,EAAE;YACP,OAAO,EAAE,YAAY;YACrB,OAAO,EAAE,YAAY;YACrB,YAAY,EAAE,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,WAAW,EAAE,CAAC,CAAC;YACzE,QAAQ,EAAE,MAAM,CAAC,WAAW,CAAC,MAAM,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,EAAE,KAAK,CAAC,EAAE,EAAE,CAAC,CAAC,IAAI,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC;SAChG;QACD,KAAK,EAAE,aAAa;QACpB,WAAW,EAAE,QAAQ,CAAC,QAAQ,CAAC;KAC/B,CAAA;IAED,aAAa,CAAC,IAAI,CAAC,MAAM,EAAE,eAAe,CAAC,EAAE,IAAI,CAAC,SAAS,CAAC,QAAQ,EAAE,IAAI,EAAE,IAAI,CAAC,GAAG,IAAI,CAAC,CAAA;IACzF,MAAM,CAAC,KAAK,YAAY,gBAAgB,YAAY,sBAAsB,QAAQ,EAAE,CAAC,CAAA;IAErF,OAAO,EAAE,KAAK,EAAE,QAAQ,EAAE,SAAS,EAAE,MAAM,EAAE,YAAY,EAAE,YAAY,EAAE,CAAA;AAC1E,CAAC;AAED;;;;GAIG;AACH,SAAS,kBAAkB,CAAC,IAA8B,EAAE,MAAc,EAAE,OAAe;IAC1F,MAAM,IAAI,GAAG,CAAC,UAAkC,EAAU,EAAE,CAC3D,CAAC,UAAU,CAAC,aAAa,EAAE,UAAU,CAAC,MAAM,EAAE,UAAU,CAAC,aAAa,CAAC;SACrE,MAAM,CAAC,SAAS,CAAC;SACjB,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC;SAC7B,IAAI,CAAC,KAAK,CAAC,CAAA;IAEd,mGAAmG;IACnG,MAAM,GAAG,GAAG,IAAI,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,CAAA;IAC7D,MAAM,OAAO,GAAG,GAAG,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,CAAA;IACzD,MAAM,MAAM,GAAG,GAAG,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,YAAY,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC,CAAA;IAClE,MAAM,KAAK,GAAG,GAAG,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,MAAM,IAAI,CAAC,YAAY,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC,CAAA;IAEzF,MAAM,IAAI,GAAG,CAAC,OAAiC,EAAU,EAAE,CAC1D,OAAO;SACL,GAAG,CACH,CAAC,KAAK,EAAE,EAAE,CACT,KAAK,KAAK,CAAC,IAAI,IAAI,KAAK,CAAC,IAAI,MAAM,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,MAAM,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,GAAG,MAAM,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,GAAG,CAAC,IAAI,CACtK;SACA,IAAI,CAAC,IAAI,CAAC,CAAA;IAEb,MAAM,MAAM,GAAG,+DAA+D,CAAA;IAE9E,OAAO;QACN,gDAAgD,MAAM,MAAM,OAAO,EAAE;QACrE,EAAE;QACF,mFAAmF;QACnF,sFAAsF;QACtF,EAAE;QACF,eAAe,OAAO,CAAC,MAAM,oBAAoB;QACjD,EAAE;QACF,MAAM;QACN,IAAI,CAAC,OAAO,CAAC;QACb,EAAE;QACF,mBAAmB,MAAM,CAAC,MAAM,sCAAsC;QACtE,EAAE;QACF,MAAM;QACN,IAAI,CAAC,MAAM,CAAC;QACZ,EAAE;QACF,4BAA4B,KAAK,CAAC,MAAM,6CAA6C;QACrF,EAAE;QACF,MAAM;QACN,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC;QACzB,EAAE;KACF,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;AACb,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,YAAY,CAAC,QAA4B;IACxD,OAAO,QAAQ,KAAK,cAAc,IAAI,QAAQ,KAAK,8BAA8B,IAAI,QAAQ,KAAK,mBAAmB,CAAA;AACtH,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,0BAA0B,CAAC,GAAW;IACrD,KAAK,MAAM,SAAS,IAAI,CAAC,IAAI,CAAC,GAAG,EAAE,eAAe,CAAC,EAAE,IAAI,CAAC,GAAG,EAAE,IAAI,EAAE,eAAe,CAAC,CAAC,EAAE,CAAC;QACxF,IAAI,CAAC,UAAU,CAAC,SAAS,CAAC;YAAE,SAAQ;QAEpC,MAAM,QAAQ,GAAG,cAAc,CAC9B,YAAY,CAAC,SAAS,EAAE,MAAM,CAAC,CAC/B,CAAA;QAED,IAAI,QAAQ,EAAE,UAAU,EAAE,iBAAiB,EAAE,EAAE,KAAK,OAAO;YAAE,OAAO,IAAI,CAAA;IACzE,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC"}
|
package/out/src/tools/index.d.ts
DELETED
|
@@ -1,28 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Corpus operator tools — the `run()`-style modules behind `mailwoman corpus …` commands. No argv,
|
|
7
|
-
* no `process.exit`: commands own parsing, rendering, and exit codes.
|
|
8
|
-
*/
|
|
9
|
-
export * from "./align-shard.ts";
|
|
10
|
-
export * from "./audit.ts";
|
|
11
|
-
export * from "./corpus-stats.ts";
|
|
12
|
-
export * from "./ingest-csv.ts";
|
|
13
|
-
export * from "./overlay-manifest.ts";
|
|
14
|
-
export * from "./fetch/download.ts";
|
|
15
|
-
export * from "./fetch/index.ts";
|
|
16
|
-
export * from "./golden-expand.ts";
|
|
17
|
-
export * from "./golden-promote.ts";
|
|
18
|
-
export * from "./golden-relabel-street.ts";
|
|
19
|
-
export * from "./jsonl-to-parquet.ts";
|
|
20
|
-
export * from "./lint-shard.ts";
|
|
21
|
-
export * from "./lint-shard-vocab.ts";
|
|
22
|
-
export * from "./shard-kryptonite.ts";
|
|
23
|
-
export * from "./overture-subvenue.ts";
|
|
24
|
-
export * from "./postcode-triples.ts";
|
|
25
|
-
export * from "./sub-venue-lexicon.ts";
|
|
26
|
-
export * from "./sub-venue-promotions.ts";
|
|
27
|
-
export * from "./shard-translit.ts";
|
|
28
|
-
//# sourceMappingURL=index.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/tools/index.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAEH,cAAc,kBAAkB,CAAA;AAChC,cAAc,YAAY,CAAA;AAC1B,cAAc,mBAAmB,CAAA;AACjC,cAAc,iBAAiB,CAAA;AAC/B,cAAc,uBAAuB,CAAA;AACrC,cAAc,qBAAqB,CAAA;AACnC,cAAc,kBAAkB,CAAA;AAChC,cAAc,oBAAoB,CAAA;AAClC,cAAc,qBAAqB,CAAA;AACnC,cAAc,4BAA4B,CAAA;AAC1C,cAAc,uBAAuB,CAAA;AACrC,cAAc,iBAAiB,CAAA;AAC/B,cAAc,uBAAuB,CAAA;AACrC,cAAc,uBAAuB,CAAA;AACrC,cAAc,wBAAwB,CAAA;AACtC,cAAc,uBAAuB,CAAA;AACrC,cAAc,wBAAwB,CAAA;AACtC,cAAc,2BAA2B,CAAA;AACzC,cAAc,qBAAqB,CAAA"}
|
package/out/src/tools/index.js
DELETED
|
@@ -1,28 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Corpus operator tools — the `run()`-style modules behind `mailwoman corpus …` commands. No argv,
|
|
7
|
-
* no `process.exit`: commands own parsing, rendering, and exit codes.
|
|
8
|
-
*/
|
|
9
|
-
export * from "./align-shard.js";
|
|
10
|
-
export * from "./audit.js";
|
|
11
|
-
export * from "./corpus-stats.js";
|
|
12
|
-
export * from "./ingest-csv.js";
|
|
13
|
-
export * from "./overlay-manifest.js";
|
|
14
|
-
export * from "./fetch/download.js";
|
|
15
|
-
export * from "./fetch/index.js";
|
|
16
|
-
export * from "./golden-expand.js";
|
|
17
|
-
export * from "./golden-promote.js";
|
|
18
|
-
export * from "./golden-relabel-street.js";
|
|
19
|
-
export * from "./jsonl-to-parquet.js";
|
|
20
|
-
export * from "./lint-shard.js";
|
|
21
|
-
export * from "./lint-shard-vocab.js";
|
|
22
|
-
export * from "./shard-kryptonite.js";
|
|
23
|
-
export * from "./overture-subvenue.js";
|
|
24
|
-
export * from "./postcode-triples.js";
|
|
25
|
-
export * from "./sub-venue-lexicon.js";
|
|
26
|
-
export * from "./sub-venue-promotions.js";
|
|
27
|
-
export * from "./shard-translit.js";
|
|
28
|
-
//# sourceMappingURL=index.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/tools/index.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAEH,cAAc,kBAAkB,CAAA;AAChC,cAAc,YAAY,CAAA;AAC1B,cAAc,mBAAmB,CAAA;AACjC,cAAc,iBAAiB,CAAA;AAC/B,cAAc,uBAAuB,CAAA;AACrC,cAAc,qBAAqB,CAAA;AACnC,cAAc,kBAAkB,CAAA;AAChC,cAAc,oBAAoB,CAAA;AAClC,cAAc,qBAAqB,CAAA;AACnC,cAAc,4BAA4B,CAAA;AAC1C,cAAc,uBAAuB,CAAA;AACrC,cAAc,iBAAiB,CAAA;AAC/B,cAAc,uBAAuB,CAAA;AACrC,cAAc,uBAAuB,CAAA;AACrC,cAAc,wBAAwB,CAAA;AACtC,cAAc,uBAAuB,CAAA;AACrC,cAAc,wBAAwB,CAAA;AACtC,cAAc,2BAA2B,CAAA;AACzC,cAAc,qBAAqB,CAAA"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"ingest-csv.d.ts","sourceRoot":"","sources":["../../../src/tools/ingest-csv.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;GAyBG;AAqWH;;GAEG;AACH,MAAM,WAAW,gBAAgB;IAChC,KAAK,EAAE,MAAM,CAAA;IACb,KAAK,CAAC,EAAE,MAAM,CAAA;IACd,MAAM,CAAC,EAAE,MAAM,CAAA;IACf,MAAM,CAAC,EAAE,MAAM,CAAA;IACf,SAAS,CAAC,EAAE,MAAM,CAAA;IAClB,IAAI,CAAC,EAAE,MAAM,CAAA;IACb,QAAQ,CAAC,EAAE,OAAO,CAAA;IAClB,MAAM,CAAC,EAAE,OAAO,CAAA;CAChB;AAED;;;;;GAKG;AACH,wBAAsB,SAAS,CAAC,OAAO,EAAE,gBAAgB,GAAG,OAAO,CAAC,IAAI,CAAC,CAiBxE"}
|