@mailwoman/corpus 9.2.0 → 9.4.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +22 -22
- package/data/PROVENANCE.md +7 -7
- package/lib/adapters/ban/adapter.ts +190 -0
- package/lib/adapters/ban/street-decompose.ts +66 -0
- package/lib/adapters/fcc-bdc/adapter.ts +174 -0
- package/lib/adapters/geonames/adapter.ts +199 -0
- package/lib/adapters/geonames-postal/adapter.ts +122 -0
- package/lib/adapters/gnaf/adapter.ts +149 -0
- package/lib/adapters/gnaf/assemble.ts +225 -0
- package/lib/adapters/index.ts +153 -0
- package/lib/adapters/openaddresses/adapter.ts +251 -0
- package/lib/adapters/overture/adapter.ts +162 -0
- package/lib/adapters/state-hi-schools/adapter.ts +170 -0
- package/lib/adapters/state-hi-schools/workbook.ts +35 -0
- package/lib/adapters/synth-po-box/adapter.ts +204 -0
- package/lib/adapters/tiger/adapter.ts +252 -0
- package/lib/adapters/tiger/street-decompose.ts +83 -0
- package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +167 -0
- package/lib/adapters/usgov-imls-pls/adapter.ts +143 -0
- package/lib/adapters/usgov-irs-bmf/adapter.ts +151 -0
- package/lib/adapters/usgov-nad/adapter.ts +334 -0
- package/lib/adapters/usgov-nppes/adapter.ts +151 -0
- package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +193 -0
- package/lib/adapters/utils/index.ts +307 -0
- package/lib/adapters/wof-admin-jp/adapter.ts +214 -0
- package/lib/adapters/wof-admin-json/adapter.ts +231 -0
- package/lib/adapters/wof-json-rows.ts +129 -0
- package/lib/adapters/wof-postalcode-json/adapter.ts +176 -0
- package/lib/build.ts +378 -0
- package/lib/env.ts +50 -0
- package/lib/index.ts +13 -0
- package/lib/recipes/anchor-absorption.ts +101 -0
- package/lib/recipes/bare-country.ts +95 -0
- package/lib/recipes/boundary-stress.ts +102 -0
- package/lib/recipes/cn-organizational-units.ts +199 -0
- package/lib/recipes/country-balanced.ts +510 -0
- package/lib/recipes/cz-pcfirst-preposition.ts +112 -0
- package/lib/recipes/fr-admin-split.ts +243 -0
- package/lib/recipes/fr-bare-street.ts +171 -0
- package/lib/recipes/fr-fragment.ts +334 -0
- package/lib/recipes/fr-lieudit.ts +301 -0
- package/lib/recipes/fr-order.ts +246 -0
- package/lib/recipes/german.ts +360 -0
- package/lib/recipes/house-venue.ts +93 -0
- package/lib/recipes/index.ts +97 -0
- package/lib/recipes/intersection.ts +619 -0
- package/lib/recipes/locale.ts +600 -0
- package/lib/recipes/nl-postcode.ts +117 -0
- package/lib/recipes/no-fragment.ts +213 -0
- package/lib/recipes/no-street-led.ts +135 -0
- package/lib/recipes/no-street.ts +91 -0
- package/lib/recipes/po-box-cedex.ts +976 -0
- package/lib/recipes/po-box.ts +124 -0
- package/lib/recipes/reviewed-postcode-tail.ts +190 -0
- package/lib/recipes/scaffold.ts +468 -0
- package/lib/recipes/si-bare-village.ts +99 -0
- package/lib/recipes/street-affix.ts +805 -0
- package/lib/recipes/street-bare.ts +102 -0
- package/lib/recipes/street.ts +83 -0
- package/lib/recipes/sub-venue-sources.ts +878 -0
- package/lib/recipes/sub-venue.ts +998 -0
- package/lib/recipes/trailing-region.ts +178 -0
- package/lib/recipes/unit.ts +304 -0
- package/lib/runner.ts +312 -0
- package/lib/synthesizers/anchor-absorption.ts +288 -0
- package/lib/synthesizers/boundary-stress.ts +532 -0
- package/lib/synthesizers/german.ts +260 -0
- package/lib/synthesizers/house-venue.ts +308 -0
- package/lib/synthesizers/intersection.ts +233 -0
- package/lib/synthesizers/no-street.ts +327 -0
- package/lib/synthesizers/po-box.ts +323 -0
- package/lib/synthesizers/street.ts +269 -0
- package/lib/synthesizers/utils.ts +993 -0
- package/lib/test-kit/corpus-recipe.ts +86 -0
- package/lib/test-kit/index.ts +100 -0
- package/lib/tools/align-slice.ts +68 -0
- package/lib/tools/audit.ts +403 -0
- package/lib/tools/corpus-stats.ts +136 -0
- package/lib/tools/fetch/acra-sg.ts +174 -0
- package/lib/tools/fetch/ban.ts +289 -0
- package/lib/tools/fetch/download.ts +477 -0
- package/lib/tools/fetch/gcis-tw.ts +175 -0
- package/lib/tools/fetch/geonames-dump.ts +257 -0
- package/lib/tools/fetch/geonames-postal.ts +180 -0
- package/lib/tools/fetch/houjin-jp.ts +135 -0
- package/lib/tools/fetch/hrsa.ts +59 -0
- package/lib/tools/fetch/imls-pls.ts +149 -0
- package/lib/tools/fetch/index.ts +174 -0
- package/lib/tools/fetch/juso-kr.ts +165 -0
- package/lib/tools/fetch/localdata-kr.ts +194 -0
- package/lib/tools/fetch/nad.ts +341 -0
- package/lib/tools/fetch/nppes.ts +165 -0
- package/lib/tools/fetch/openaddresses.ts +347 -0
- package/lib/tools/fetch/ourairports.ts +170 -0
- package/lib/tools/fetch/ppd.ts +121 -0
- package/lib/tools/fetch/state-hi-schools.ts +161 -0
- package/lib/tools/fetch/state-sources.ts +146 -0
- package/lib/tools/fetch/tiger-full.ts +308 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +384 -0
- package/lib/tools/golden-expand.ts +574 -0
- package/lib/tools/golden-promote.ts +337 -0
- package/lib/tools/golden-relabel-street.ts +686 -0
- package/lib/tools/index.ts +28 -0
- package/lib/tools/ingest-csv.ts +378 -0
- package/lib/tools/jsonl-to-parquet.ts +207 -0
- package/lib/tools/lint-slice-vocab.ts +388 -0
- package/lib/tools/lint-slice.ts +496 -0
- package/lib/tools/overlay-manifest.ts +148 -0
- package/lib/tools/overture-subvenue.ts +209 -0
- package/lib/tools/postcode-triples.ts +363 -0
- package/lib/tools/slice-kryptonite.ts +137 -0
- package/lib/tools/slice-translit.ts +218 -0
- package/lib/tools/sub-venue/harvest.ts +234 -0
- package/lib/tools/sub-venue/head-nouns.ts +245 -0
- package/lib/tools/sub-venue/surfaces.ts +95 -0
- package/lib/tools/sub-venue/table.ts +281 -0
- package/lib/tools/sub-venue/wikidata.ts +85 -0
- package/lib/tools/sub-venue-lexicon.ts +429 -0
- package/lib/tools/sub-venue-promotions.ts +330 -0
- package/lib/types.ts +247 -0
- package/lib/utils/align.ts +330 -0
- package/lib/utils/golden.ts +189 -0
- package/lib/utils/index.ts +14 -0
- package/lib/utils/parquet.ts +582 -0
- package/lib/utils/slice-stats.ts +95 -0
- package/lib/utils/split.ts +279 -0
- package/lib/utils/tokenize.ts +120 -0
- package/lib/utils/wof-json.ts +247 -0
- package/out/adapters/ban/adapter.d.ts.map +1 -0
- package/out/adapters/ban/adapter.js +149 -0
- package/out/adapters/ban/adapter.js.map +1 -0
- package/out/adapters/ban/street-decompose.d.ts.map +1 -0
- package/out/adapters/ban/street-decompose.js +51 -0
- package/out/adapters/ban/street-decompose.js.map +1 -0
- package/out/adapters/fcc-bdc/adapter.d.ts.map +1 -0
- package/out/adapters/fcc-bdc/adapter.js +144 -0
- package/out/adapters/fcc-bdc/adapter.js.map +1 -0
- package/out/adapters/geonames/adapter.d.ts.map +1 -0
- package/out/adapters/geonames/adapter.js +176 -0
- package/out/adapters/geonames/adapter.js.map +1 -0
- package/out/adapters/geonames-postal/adapter.d.ts +54 -0
- package/out/adapters/geonames-postal/adapter.d.ts.map +1 -0
- package/out/adapters/geonames-postal/adapter.js +107 -0
- package/out/adapters/geonames-postal/adapter.js.map +1 -0
- package/out/adapters/gnaf/adapter.d.ts +49 -0
- package/out/adapters/gnaf/adapter.d.ts.map +1 -0
- package/out/adapters/gnaf/adapter.js +124 -0
- package/out/adapters/gnaf/adapter.js.map +1 -0
- package/out/adapters/gnaf/assemble.d.ts +65 -0
- package/out/adapters/gnaf/assemble.d.ts.map +1 -0
- package/out/adapters/gnaf/assemble.js +154 -0
- package/out/adapters/gnaf/assemble.js.map +1 -0
- package/out/adapters/index.d.ts +51 -0
- package/out/adapters/index.d.ts.map +1 -0
- package/out/adapters/index.js +95 -0
- package/out/adapters/index.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -0
- package/out/adapters/openaddresses/adapter.js +186 -0
- package/out/adapters/openaddresses/adapter.js.map +1 -0
- package/out/adapters/overture/adapter.d.ts +48 -0
- package/out/adapters/overture/adapter.d.ts.map +1 -0
- package/out/adapters/overture/adapter.js +125 -0
- package/out/adapters/overture/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/adapter.d.ts +46 -0
- package/out/adapters/state-hi-schools/adapter.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/adapter.js +145 -0
- package/out/adapters/state-hi-schools/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/workbook.d.ts +29 -0
- package/out/adapters/state-hi-schools/workbook.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/workbook.js +20 -0
- package/out/adapters/state-hi-schools/workbook.js.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
- package/out/adapters/synth-po-box/adapter.d.ts.map +1 -0
- package/out/adapters/synth-po-box/adapter.js +140 -0
- package/out/adapters/synth-po-box/adapter.js.map +1 -0
- package/out/adapters/tiger/adapter.d.ts +55 -0
- package/out/adapters/tiger/adapter.d.ts.map +1 -0
- package/out/adapters/tiger/adapter.js +201 -0
- package/out/adapters/tiger/adapter.js.map +1 -0
- package/out/adapters/tiger/street-decompose.d.ts.map +1 -0
- package/out/adapters/tiger/street-decompose.js +68 -0
- package/out/adapters/tiger/street-decompose.js.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +56 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js +132 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts +36 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.js +114 -0
- package/out/adapters/usgov-imls-pls/adapter.js.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts +37 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.js +120 -0
- package/out/adapters/usgov-irs-bmf/adapter.js.map +1 -0
- package/out/adapters/usgov-nad/adapter.d.ts +48 -0
- package/out/adapters/usgov-nad/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nad/adapter.js +249 -0
- package/out/adapters/usgov-nad/adapter.js.map +1 -0
- package/out/adapters/usgov-nppes/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nppes/adapter.js +118 -0
- package/out/adapters/usgov-nppes/adapter.js.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +154 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -0
- package/out/adapters/utils/index.d.ts +191 -0
- package/out/adapters/utils/index.d.ts.map +1 -0
- package/out/adapters/utils/index.js +206 -0
- package/out/adapters/utils/index.js.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.js +161 -0
- package/out/adapters/wof-admin-jp/adapter.js.map +1 -0
- package/out/adapters/wof-admin-json/adapter.d.ts +79 -0
- package/out/adapters/wof-admin-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-json/adapter.js +197 -0
- package/out/adapters/wof-admin-json/adapter.js.map +1 -0
- package/out/adapters/wof-json-rows.d.ts +62 -0
- package/out/adapters/wof-json-rows.d.ts.map +1 -0
- package/out/adapters/wof-json-rows.js +83 -0
- package/out/adapters/wof-json-rows.js.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts +65 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.js +151 -0
- package/out/adapters/wof-postalcode-json/adapter.js.map +1 -0
- package/out/build.d.ts +132 -0
- package/out/build.d.ts.map +1 -0
- package/out/build.js +245 -0
- package/out/build.js.map +1 -0
- package/out/codex/us-fips-state.d.ts.map +1 -0
- package/out/codex/us-fips-state.js.map +1 -0
- package/out/env.d.ts +46 -0
- package/out/env.d.ts.map +1 -0
- package/out/env.js +46 -0
- package/out/env.js.map +1 -0
- package/out/index.d.ts +13 -0
- package/out/index.d.ts.map +1 -0
- package/out/index.js +13 -0
- package/out/index.js.map +1 -0
- package/out/recipes/anchor-absorption.d.ts +20 -0
- package/out/recipes/anchor-absorption.d.ts.map +1 -0
- package/out/recipes/anchor-absorption.js +82 -0
- package/out/recipes/anchor-absorption.js.map +1 -0
- package/out/recipes/bare-country.d.ts +25 -0
- package/out/recipes/bare-country.d.ts.map +1 -0
- package/out/recipes/bare-country.js +88 -0
- package/out/recipes/bare-country.js.map +1 -0
- package/out/recipes/boundary-stress.d.ts +20 -0
- package/out/recipes/boundary-stress.d.ts.map +1 -0
- package/out/recipes/boundary-stress.js +84 -0
- package/out/recipes/boundary-stress.js.map +1 -0
- package/out/recipes/cn-organizational-units.d.ts +36 -0
- package/out/recipes/cn-organizational-units.d.ts.map +1 -0
- package/out/recipes/cn-organizational-units.js +159 -0
- package/out/recipes/cn-organizational-units.js.map +1 -0
- package/out/recipes/country-balanced.d.ts +32 -0
- package/out/recipes/country-balanced.d.ts.map +1 -0
- package/out/recipes/country-balanced.js +394 -0
- package/out/recipes/country-balanced.js.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts +22 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.js +101 -0
- package/out/recipes/cz-pcfirst-preposition.js.map +1 -0
- package/out/recipes/fr-admin-split.d.ts +38 -0
- package/out/recipes/fr-admin-split.d.ts.map +1 -0
- package/out/recipes/fr-admin-split.js +192 -0
- package/out/recipes/fr-admin-split.js.map +1 -0
- package/out/recipes/fr-bare-street.d.ts +28 -0
- package/out/recipes/fr-bare-street.d.ts.map +1 -0
- package/out/recipes/fr-bare-street.js +144 -0
- package/out/recipes/fr-bare-street.js.map +1 -0
- package/out/recipes/fr-fragment.d.ts +77 -0
- package/out/recipes/fr-fragment.d.ts.map +1 -0
- package/out/recipes/fr-fragment.js +277 -0
- package/out/recipes/fr-fragment.js.map +1 -0
- package/out/recipes/fr-lieudit.d.ts +32 -0
- package/out/recipes/fr-lieudit.d.ts.map +1 -0
- package/out/recipes/fr-lieudit.js +227 -0
- package/out/recipes/fr-lieudit.js.map +1 -0
- package/out/recipes/fr-order.d.ts +38 -0
- package/out/recipes/fr-order.d.ts.map +1 -0
- package/out/recipes/fr-order.js +198 -0
- package/out/recipes/fr-order.js.map +1 -0
- package/out/recipes/german.d.ts +44 -0
- package/out/recipes/german.d.ts.map +1 -0
- package/out/recipes/german.js +289 -0
- package/out/recipes/german.js.map +1 -0
- package/out/recipes/house-venue.d.ts +18 -0
- package/out/recipes/house-venue.d.ts.map +1 -0
- package/out/recipes/house-venue.js +74 -0
- package/out/recipes/house-venue.js.map +1 -0
- package/out/recipes/index.d.ts +24 -0
- package/out/recipes/index.d.ts.map +1 -0
- package/out/recipes/index.js +91 -0
- package/out/recipes/index.js.map +1 -0
- package/out/recipes/intersection.d.ts +42 -0
- package/out/recipes/intersection.d.ts.map +1 -0
- package/out/recipes/intersection.js +453 -0
- package/out/recipes/intersection.js.map +1 -0
- package/out/recipes/locale.d.ts +136 -0
- package/out/recipes/locale.d.ts.map +1 -0
- package/out/recipes/locale.js +460 -0
- package/out/recipes/locale.js.map +1 -0
- package/out/recipes/nl-postcode.d.ts +26 -0
- package/out/recipes/nl-postcode.d.ts.map +1 -0
- package/out/recipes/nl-postcode.js +103 -0
- package/out/recipes/nl-postcode.js.map +1 -0
- package/out/recipes/no-fragment.d.ts +43 -0
- package/out/recipes/no-fragment.d.ts.map +1 -0
- package/out/recipes/no-fragment.js +183 -0
- package/out/recipes/no-fragment.js.map +1 -0
- package/out/recipes/no-street-led.d.ts +24 -0
- package/out/recipes/no-street-led.d.ts.map +1 -0
- package/out/recipes/no-street-led.js +114 -0
- package/out/recipes/no-street-led.js.map +1 -0
- package/out/recipes/no-street.d.ts +18 -0
- package/out/recipes/no-street.d.ts.map +1 -0
- package/out/recipes/no-street.js +72 -0
- package/out/recipes/no-street.js.map +1 -0
- package/out/recipes/po-box-cedex.d.ts +38 -0
- package/out/recipes/po-box-cedex.d.ts.map +1 -0
- package/out/recipes/po-box-cedex.js +768 -0
- package/out/recipes/po-box-cedex.js.map +1 -0
- package/out/recipes/po-box.d.ts +17 -0
- package/out/recipes/po-box.d.ts.map +1 -0
- package/out/recipes/po-box.js +101 -0
- package/out/recipes/po-box.js.map +1 -0
- package/out/recipes/reviewed-postcode-tail.d.ts +47 -0
- package/out/recipes/reviewed-postcode-tail.d.ts.map +1 -0
- package/out/recipes/reviewed-postcode-tail.js +125 -0
- package/out/recipes/reviewed-postcode-tail.js.map +1 -0
- package/out/recipes/scaffold.d.ts +323 -0
- package/out/recipes/scaffold.d.ts.map +1 -0
- package/out/recipes/scaffold.js +174 -0
- package/out/recipes/scaffold.js.map +1 -0
- package/out/recipes/si-bare-village.d.ts +32 -0
- package/out/recipes/si-bare-village.d.ts.map +1 -0
- package/out/recipes/si-bare-village.js +89 -0
- package/out/recipes/si-bare-village.js.map +1 -0
- package/out/recipes/street-affix.d.ts +89 -0
- package/out/recipes/street-affix.d.ts.map +1 -0
- package/out/recipes/street-affix.js +563 -0
- package/out/recipes/street-affix.js.map +1 -0
- package/out/recipes/street-bare.d.ts +25 -0
- package/out/recipes/street-bare.d.ts.map +1 -0
- package/out/recipes/street-bare.js +87 -0
- package/out/recipes/street-bare.js.map +1 -0
- package/out/recipes/street.d.ts +15 -0
- package/out/recipes/street.d.ts.map +1 -0
- package/out/recipes/street.js +70 -0
- package/out/recipes/street.js.map +1 -0
- package/out/recipes/sub-venue-sources.d.ts +229 -0
- package/out/recipes/sub-venue-sources.d.ts.map +1 -0
- package/out/recipes/sub-venue-sources.js +654 -0
- package/out/recipes/sub-venue-sources.js.map +1 -0
- package/out/recipes/sub-venue.d.ts +269 -0
- package/out/recipes/sub-venue.d.ts.map +1 -0
- package/out/recipes/sub-venue.js +726 -0
- package/out/recipes/sub-venue.js.map +1 -0
- package/out/recipes/trailing-region.d.ts +74 -0
- package/out/recipes/trailing-region.d.ts.map +1 -0
- package/out/recipes/trailing-region.js +158 -0
- package/out/recipes/trailing-region.js.map +1 -0
- package/out/recipes/unit.d.ts +29 -0
- package/out/recipes/unit.d.ts.map +1 -0
- package/out/recipes/unit.js +231 -0
- package/out/recipes/unit.js.map +1 -0
- package/out/runner.d.ts +130 -0
- package/out/runner.d.ts.map +1 -0
- package/out/runner.js +185 -0
- package/out/runner.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +63 -0
- package/out/synthesizers/anchor-absorption.d.ts.map +1 -0
- package/out/synthesizers/anchor-absorption.js +221 -0
- package/out/synthesizers/anchor-absorption.js.map +1 -0
- package/out/synthesizers/boundary-stress.d.ts +78 -0
- package/out/synthesizers/boundary-stress.d.ts.map +1 -0
- package/out/synthesizers/boundary-stress.js +455 -0
- package/out/synthesizers/boundary-stress.js.map +1 -0
- package/out/synthesizers/german.d.ts +115 -0
- package/out/synthesizers/german.d.ts.map +1 -0
- package/out/synthesizers/german.js +149 -0
- package/out/synthesizers/german.js.map +1 -0
- package/out/synthesizers/house-venue.d.ts +56 -0
- package/out/synthesizers/house-venue.d.ts.map +1 -0
- package/out/synthesizers/house-venue.js +247 -0
- package/out/synthesizers/house-venue.js.map +1 -0
- package/out/synthesizers/intersection.d.ts +52 -0
- package/out/synthesizers/intersection.d.ts.map +1 -0
- package/out/synthesizers/intersection.js +175 -0
- package/out/synthesizers/intersection.js.map +1 -0
- package/out/synthesizers/no-street.d.ts +72 -0
- package/out/synthesizers/no-street.d.ts.map +1 -0
- package/out/synthesizers/no-street.js +262 -0
- package/out/synthesizers/no-street.js.map +1 -0
- package/out/synthesizers/po-box.d.ts +108 -0
- package/out/synthesizers/po-box.d.ts.map +1 -0
- package/out/synthesizers/po-box.js +250 -0
- package/out/synthesizers/po-box.js.map +1 -0
- package/out/synthesizers/street.d.ts +54 -0
- package/out/synthesizers/street.d.ts.map +1 -0
- package/out/synthesizers/street.js +218 -0
- package/out/synthesizers/street.js.map +1 -0
- package/out/synthesizers/utils.d.ts +241 -0
- package/out/synthesizers/utils.d.ts.map +1 -0
- package/out/synthesizers/utils.js +776 -0
- package/out/synthesizers/utils.js.map +1 -0
- package/out/test-kit/corpus-recipe.d.ts +59 -0
- package/out/test-kit/corpus-recipe.d.ts.map +1 -0
- package/out/test-kit/corpus-recipe.js +39 -0
- package/out/test-kit/corpus-recipe.js.map +1 -0
- package/out/test-kit/index.d.ts +48 -0
- package/out/test-kit/index.d.ts.map +1 -0
- package/out/test-kit/index.js +78 -0
- package/out/test-kit/index.js.map +1 -0
- package/out/tools/align-slice.d.ts +7 -0
- package/out/tools/align-slice.d.ts.map +1 -0
- package/out/tools/align-slice.js +55 -0
- package/out/tools/align-slice.js.map +1 -0
- package/out/tools/audit.d.ts +29 -0
- package/out/tools/audit.d.ts.map +1 -0
- package/out/tools/audit.js +282 -0
- package/out/tools/audit.js.map +1 -0
- package/out/tools/corpus-stats.d.ts +44 -0
- package/out/tools/corpus-stats.d.ts.map +1 -0
- package/out/tools/corpus-stats.js +102 -0
- package/out/tools/corpus-stats.js.map +1 -0
- package/out/tools/fetch/acra-sg.d.ts +23 -0
- package/out/tools/fetch/acra-sg.d.ts.map +1 -0
- package/out/tools/fetch/acra-sg.js +126 -0
- package/out/tools/fetch/acra-sg.js.map +1 -0
- package/out/tools/fetch/ban.d.ts +31 -0
- package/out/tools/fetch/ban.d.ts.map +1 -0
- package/out/tools/fetch/ban.js +239 -0
- package/out/tools/fetch/ban.js.map +1 -0
- package/out/tools/fetch/download.d.ts +182 -0
- package/out/tools/fetch/download.d.ts.map +1 -0
- package/out/tools/fetch/download.js +318 -0
- package/out/tools/fetch/download.js.map +1 -0
- package/out/tools/fetch/gcis-tw.d.ts +23 -0
- package/out/tools/fetch/gcis-tw.d.ts.map +1 -0
- package/out/tools/fetch/gcis-tw.js +135 -0
- package/out/tools/fetch/gcis-tw.js.map +1 -0
- package/out/tools/fetch/geonames-dump.d.ts +91 -0
- package/out/tools/fetch/geonames-dump.d.ts.map +1 -0
- package/out/tools/fetch/geonames-dump.js +171 -0
- package/out/tools/fetch/geonames-dump.js.map +1 -0
- package/out/tools/fetch/geonames-postal.d.ts +76 -0
- package/out/tools/fetch/geonames-postal.d.ts.map +1 -0
- package/out/tools/fetch/geonames-postal.js +126 -0
- package/out/tools/fetch/geonames-postal.js.map +1 -0
- package/out/tools/fetch/houjin-jp.d.ts +24 -0
- package/out/tools/fetch/houjin-jp.d.ts.map +1 -0
- package/out/tools/fetch/houjin-jp.js +102 -0
- package/out/tools/fetch/houjin-jp.js.map +1 -0
- package/out/tools/fetch/hrsa.d.ts +18 -0
- package/out/tools/fetch/hrsa.d.ts.map +1 -0
- package/out/tools/fetch/hrsa.js +46 -0
- package/out/tools/fetch/hrsa.js.map +1 -0
- package/out/tools/fetch/imls-pls.d.ts +25 -0
- package/out/tools/fetch/imls-pls.d.ts.map +1 -0
- package/out/tools/fetch/imls-pls.js +108 -0
- package/out/tools/fetch/imls-pls.js.map +1 -0
- package/out/tools/fetch/index.d.ts +171 -0
- package/out/tools/fetch/index.d.ts.map +1 -0
- package/out/tools/fetch/index.js +170 -0
- package/out/tools/fetch/index.js.map +1 -0
- package/out/tools/fetch/juso-kr.d.ts +30 -0
- package/out/tools/fetch/juso-kr.d.ts.map +1 -0
- package/out/tools/fetch/juso-kr.js +120 -0
- package/out/tools/fetch/juso-kr.js.map +1 -0
- package/out/tools/fetch/localdata-kr.d.ts +30 -0
- package/out/tools/fetch/localdata-kr.d.ts.map +1 -0
- package/out/tools/fetch/localdata-kr.js +139 -0
- package/out/tools/fetch/localdata-kr.js.map +1 -0
- package/out/tools/fetch/nad.d.ts +70 -0
- package/out/tools/fetch/nad.d.ts.map +1 -0
- package/out/tools/fetch/nad.js +234 -0
- package/out/tools/fetch/nad.js.map +1 -0
- package/out/tools/fetch/nppes.d.ts +26 -0
- package/out/tools/fetch/nppes.d.ts.map +1 -0
- package/out/tools/fetch/nppes.js +126 -0
- package/out/tools/fetch/nppes.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +9 -0
- package/out/tools/fetch/openaddresses.d.ts.map +1 -0
- package/out/tools/fetch/openaddresses.js +279 -0
- package/out/tools/fetch/openaddresses.js.map +1 -0
- package/out/tools/fetch/ourairports.d.ts +45 -0
- package/out/tools/fetch/ourairports.d.ts.map +1 -0
- package/out/tools/fetch/ourairports.js +128 -0
- package/out/tools/fetch/ourairports.js.map +1 -0
- package/out/tools/fetch/ppd.d.ts.map +1 -0
- package/out/tools/fetch/ppd.js +85 -0
- package/out/tools/fetch/ppd.js.map +1 -0
- package/out/tools/fetch/state-hi-schools.d.ts +26 -0
- package/out/tools/fetch/state-hi-schools.d.ts.map +1 -0
- package/out/tools/fetch/state-hi-schools.js +112 -0
- package/out/tools/fetch/state-hi-schools.js.map +1 -0
- package/out/tools/fetch/state-sources.d.ts +26 -0
- package/out/tools/fetch/state-sources.d.ts.map +1 -0
- package/out/tools/fetch/state-sources.js +111 -0
- package/out/tools/fetch/state-sources.js.map +1 -0
- package/out/tools/fetch/tiger-full.d.ts +22 -0
- package/out/tools/fetch/tiger-full.d.ts.map +1 -0
- package/out/tools/fetch/tiger-full.js +217 -0
- package/out/tools/fetch/tiger-full.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +171 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.js +274 -0
- package/out/tools/fetch/wikidata-subvenue.js.map +1 -0
- package/out/tools/gb-title-case.d.ts.map +1 -0
- package/out/tools/gb-title-case.js.map +1 -0
- package/out/tools/golden-expand.d.ts +90 -0
- package/out/tools/golden-expand.d.ts.map +1 -0
- package/out/tools/golden-expand.js +406 -0
- package/out/tools/golden-expand.js.map +1 -0
- package/out/tools/golden-promote.d.ts.map +1 -0
- package/out/tools/golden-promote.js +240 -0
- package/out/tools/golden-promote.js.map +1 -0
- package/out/tools/golden-relabel-street.d.ts +196 -0
- package/out/tools/golden-relabel-street.d.ts.map +1 -0
- package/out/tools/golden-relabel-street.js +439 -0
- package/out/tools/golden-relabel-street.js.map +1 -0
- package/out/tools/index.d.ts +28 -0
- package/out/tools/index.d.ts.map +1 -0
- package/out/tools/index.js +28 -0
- package/out/tools/index.js.map +1 -0
- package/out/tools/ingest-csv.d.ts.map +1 -0
- package/out/tools/ingest-csv.js +265 -0
- package/out/tools/ingest-csv.js.map +1 -0
- package/out/tools/jsonl-to-parquet.d.ts +61 -0
- package/out/tools/jsonl-to-parquet.d.ts.map +1 -0
- package/out/tools/jsonl-to-parquet.js +150 -0
- package/out/tools/jsonl-to-parquet.js.map +1 -0
- package/out/tools/lint-slice-vocab.d.ts +90 -0
- package/out/tools/lint-slice-vocab.d.ts.map +1 -0
- package/out/tools/lint-slice-vocab.js +267 -0
- package/out/tools/lint-slice-vocab.js.map +1 -0
- package/out/tools/lint-slice.d.ts +93 -0
- package/out/tools/lint-slice.d.ts.map +1 -0
- package/out/tools/lint-slice.js +322 -0
- package/out/tools/lint-slice.js.map +1 -0
- package/out/tools/overlay-manifest.d.ts +39 -0
- package/out/tools/overlay-manifest.d.ts.map +1 -0
- package/out/tools/overlay-manifest.js +90 -0
- package/out/tools/overlay-manifest.js.map +1 -0
- package/out/tools/overture-subvenue.d.ts +112 -0
- package/out/tools/overture-subvenue.d.ts.map +1 -0
- package/out/tools/overture-subvenue.js +139 -0
- package/out/tools/overture-subvenue.js.map +1 -0
- package/out/tools/postcode-triples.d.ts +174 -0
- package/out/tools/postcode-triples.d.ts.map +1 -0
- package/out/tools/postcode-triples.js +292 -0
- package/out/tools/postcode-triples.js.map +1 -0
- package/out/tools/slice-kryptonite.d.ts +32 -0
- package/out/tools/slice-kryptonite.d.ts.map +1 -0
- package/out/tools/slice-kryptonite.js +99 -0
- package/out/tools/slice-kryptonite.js.map +1 -0
- package/out/tools/slice-translit.d.ts +51 -0
- package/out/tools/slice-translit.d.ts.map +1 -0
- package/out/tools/slice-translit.js +166 -0
- package/out/tools/slice-translit.js.map +1 -0
- package/out/tools/sub-venue/harvest.d.ts +100 -0
- package/out/tools/sub-venue/harvest.d.ts.map +1 -0
- package/out/tools/sub-venue/harvest.js +168 -0
- package/out/tools/sub-venue/harvest.js.map +1 -0
- package/out/tools/sub-venue/head-nouns.d.ts +50 -0
- package/out/tools/sub-venue/head-nouns.d.ts.map +1 -0
- package/out/tools/sub-venue/head-nouns.js +213 -0
- package/out/tools/sub-venue/head-nouns.js.map +1 -0
- package/out/tools/sub-venue/surfaces.d.ts +45 -0
- package/out/tools/sub-venue/surfaces.d.ts.map +1 -0
- package/out/tools/sub-venue/surfaces.js +77 -0
- package/out/tools/sub-venue/surfaces.js.map +1 -0
- package/out/tools/sub-venue/table.d.ts +229 -0
- package/out/tools/sub-venue/table.d.ts.map +1 -0
- package/out/tools/sub-venue/table.js +108 -0
- package/out/tools/sub-venue/table.js.map +1 -0
- package/out/tools/sub-venue/wikidata.d.ts +26 -0
- package/out/tools/sub-venue/wikidata.d.ts.map +1 -0
- package/out/tools/sub-venue/wikidata.js +62 -0
- package/out/tools/sub-venue/wikidata.js.map +1 -0
- package/out/tools/sub-venue-lexicon.d.ts +156 -0
- package/out/tools/sub-venue-lexicon.d.ts.map +1 -0
- package/out/tools/sub-venue-lexicon.js +283 -0
- package/out/tools/sub-venue-lexicon.js.map +1 -0
- package/out/tools/sub-venue-promotions.d.ts +94 -0
- package/out/tools/sub-venue-promotions.d.ts.map +1 -0
- package/out/tools/sub-venue-promotions.js +266 -0
- package/out/tools/sub-venue-promotions.js.map +1 -0
- package/out/types.d.ts +221 -0
- package/out/types.d.ts.map +1 -0
- package/out/types.js.map +1 -0
- package/out/utils/align.d.ts +93 -0
- package/out/utils/align.d.ts.map +1 -0
- package/out/utils/align.js +234 -0
- package/out/utils/align.js.map +1 -0
- package/out/utils/golden.d.ts +85 -0
- package/out/utils/golden.d.ts.map +1 -0
- package/out/utils/golden.js +127 -0
- package/out/utils/golden.js.map +1 -0
- package/out/utils/index.d.ts +14 -0
- package/out/utils/index.d.ts.map +1 -0
- package/out/utils/index.js +14 -0
- package/out/utils/index.js.map +1 -0
- package/out/utils/license.d.ts.map +1 -0
- package/out/utils/license.js.map +1 -0
- package/out/utils/parquet.d.ts +178 -0
- package/out/utils/parquet.d.ts.map +1 -0
- package/out/utils/parquet.js +371 -0
- package/out/utils/parquet.js.map +1 -0
- package/out/utils/slice-stats.d.ts +52 -0
- package/out/utils/slice-stats.d.ts.map +1 -0
- package/out/utils/slice-stats.js +58 -0
- package/out/utils/slice-stats.js.map +1 -0
- package/out/utils/split.d.ts +128 -0
- package/out/utils/split.d.ts.map +1 -0
- package/out/utils/split.js +204 -0
- package/out/utils/split.js.map +1 -0
- package/out/utils/tokenize.d.ts +64 -0
- package/out/utils/tokenize.d.ts.map +1 -0
- package/out/utils/tokenize.js +82 -0
- package/out/utils/tokenize.js.map +1 -0
- package/out/utils/wof-json.d.ts +113 -0
- package/out/utils/wof-json.d.ts.map +1 -0
- package/out/utils/wof-json.js +173 -0
- package/out/utils/wof-json.js.map +1 -0
- package/package.json +259 -194
- package/out/src/adapters/ban/adapter.d.ts.map +0 -1
- package/out/src/adapters/ban/adapter.js +0 -149
- package/out/src/adapters/ban/adapter.js.map +0 -1
- package/out/src/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/ban/street-decompose.js +0 -75
- package/out/src/adapters/ban/street-decompose.js.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.d.ts.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.js +0 -144
- package/out/src/adapters/fcc-bdc/adapter.js.map +0 -1
- package/out/src/adapters/geonames/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames/adapter.js +0 -176
- package/out/src/adapters/geonames/adapter.js.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.d.ts +0 -41
- package/out/src/adapters/geonames-postal/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.js +0 -104
- package/out/src/adapters/geonames-postal/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/adapter.d.ts +0 -49
- package/out/src/adapters/gnaf/adapter.d.ts.map +0 -1
- package/out/src/adapters/gnaf/adapter.js +0 -124
- package/out/src/adapters/gnaf/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/assemble.d.ts +0 -65
- package/out/src/adapters/gnaf/assemble.d.ts.map +0 -1
- package/out/src/adapters/gnaf/assemble.js +0 -154
- package/out/src/adapters/gnaf/assemble.js.map +0 -1
- package/out/src/adapters/index.d.ts +0 -51
- package/out/src/adapters/index.d.ts.map +0 -1
- package/out/src/adapters/index.js +0 -95
- package/out/src/adapters/index.js.map +0 -1
- package/out/src/adapters/openaddresses/adapter.d.ts.map +0 -1
- package/out/src/adapters/openaddresses/adapter.js +0 -186
- package/out/src/adapters/openaddresses/adapter.js.map +0 -1
- package/out/src/adapters/overture/adapter.d.ts +0 -48
- package/out/src/adapters/overture/adapter.d.ts.map +0 -1
- package/out/src/adapters/overture/adapter.js +0 -125
- package/out/src/adapters/overture/adapter.js.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.d.ts +0 -47
- package/out/src/adapters/state-hi-schools/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.js +0 -133
- package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.d.ts.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.js +0 -140
- package/out/src/adapters/synth-po-box/adapter.js.map +0 -1
- package/out/src/adapters/tiger/adapter.d.ts +0 -55
- package/out/src/adapters/tiger/adapter.d.ts.map +0 -1
- package/out/src/adapters/tiger/adapter.js +0 -201
- package/out/src/adapters/tiger/adapter.js.map +0 -1
- package/out/src/adapters/tiger/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/tiger/street-decompose.js +0 -90
- package/out/src/adapters/tiger/street-decompose.js.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -47
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +0 -139
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts +0 -36
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.js +0 -114
- package/out/src/adapters/usgov-imls-pls/adapter.js.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.js +0 -124
- package/out/src/adapters/usgov-irs-bmf/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.d.ts +0 -48
- package/out/src/adapters/usgov-nad/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.js +0 -252
- package/out/src/adapters/usgov-nad/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.js +0 -116
- package/out/src/adapters/usgov-nppes/adapter.js.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -156
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
- package/out/src/adapters/utils/index.d.ts +0 -150
- package/out/src/adapters/utils/index.d.ts.map +0 -1
- package/out/src/adapters/utils/index.js +0 -159
- package/out/src/adapters/utils/index.js.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.js +0 -164
- package/out/src/adapters/wof-admin-jp/adapter.js.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.d.ts +0 -82
- package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.js +0 -224
- package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
- package/out/src/adapters/wof-json-rows.d.ts +0 -32
- package/out/src/adapters/wof-json-rows.d.ts.map +0 -1
- package/out/src/adapters/wof-json-rows.js +0 -45
- package/out/src/adapters/wof-json-rows.js.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -65
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.js +0 -160
- package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
- package/out/src/build.d.ts +0 -132
- package/out/src/build.d.ts.map +0 -1
- package/out/src/build.js +0 -251
- package/out/src/build.js.map +0 -1
- package/out/src/codex/us-fips-state.d.ts.map +0 -1
- package/out/src/codex/us-fips-state.js.map +0 -1
- package/out/src/index.d.ts +0 -14
- package/out/src/index.d.ts.map +0 -1
- package/out/src/index.js +0 -14
- package/out/src/index.js.map +0 -1
- package/out/src/name-prone-us-suffixes.d.ts +0 -12
- package/out/src/name-prone-us-suffixes.d.ts.map +0 -1
- package/out/src/name-prone-us-suffixes.js +0 -12
- package/out/src/name-prone-us-suffixes.js.map +0 -1
- package/out/src/parquet-wrapper/index.d.ts +0 -9
- package/out/src/parquet-wrapper/index.d.ts.map +0 -1
- package/out/src/parquet-wrapper/index.js +0 -9
- package/out/src/parquet-wrapper/index.js.map +0 -1
- package/out/src/parquet-wrapper/reader.d.ts +0 -34
- package/out/src/parquet-wrapper/reader.d.ts.map +0 -1
- package/out/src/parquet-wrapper/reader.js +0 -69
- package/out/src/parquet-wrapper/reader.js.map +0 -1
- package/out/src/parquet-wrapper/schema.d.ts +0 -49
- package/out/src/parquet-wrapper/schema.d.ts.map +0 -1
- package/out/src/parquet-wrapper/schema.js +0 -55
- package/out/src/parquet-wrapper/schema.js.map +0 -1
- package/out/src/parquet-wrapper/writer.d.ts +0 -46
- package/out/src/parquet-wrapper/writer.d.ts.map +0 -1
- package/out/src/parquet-wrapper/writer.js +0 -76
- package/out/src/parquet-wrapper/writer.js.map +0 -1
- package/out/src/runner.d.ts +0 -126
- package/out/src/runner.d.ts.map +0 -1
- package/out/src/runner.js +0 -189
- package/out/src/runner.js.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.d.ts +0 -20
- package/out/src/shard-recipes/anchor-absorption.d.ts.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.js +0 -82
- package/out/src/shard-recipes/anchor-absorption.js.map +0 -1
- package/out/src/shard-recipes/bare-country.d.ts +0 -25
- package/out/src/shard-recipes/bare-country.d.ts.map +0 -1
- package/out/src/shard-recipes/bare-country.js +0 -87
- package/out/src/shard-recipes/bare-country.js.map +0 -1
- package/out/src/shard-recipes/boundary-stress.d.ts +0 -20
- package/out/src/shard-recipes/boundary-stress.d.ts.map +0 -1
- package/out/src/shard-recipes/boundary-stress.js +0 -83
- package/out/src/shard-recipes/boundary-stress.js.map +0 -1
- package/out/src/shard-recipes/country-balanced.d.ts +0 -32
- package/out/src/shard-recipes/country-balanced.d.ts.map +0 -1
- package/out/src/shard-recipes/country-balanced.js +0 -406
- package/out/src/shard-recipes/country-balanced.js.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts +0 -22
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.js +0 -100
- package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.d.ts +0 -38
- package/out/src/shard-recipes/fr-admin-split.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.js +0 -188
- package/out/src/shard-recipes/fr-admin-split.js.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.d.ts +0 -28
- package/out/src/shard-recipes/fr-bare-street.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.js +0 -143
- package/out/src/shard-recipes/fr-bare-street.js.map +0 -1
- package/out/src/shard-recipes/fr-fragment.d.ts +0 -77
- package/out/src/shard-recipes/fr-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-fragment.js +0 -276
- package/out/src/shard-recipes/fr-fragment.js.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.d.ts +0 -32
- package/out/src/shard-recipes/fr-lieudit.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.js +0 -226
- package/out/src/shard-recipes/fr-lieudit.js.map +0 -1
- package/out/src/shard-recipes/fr-order.d.ts +0 -38
- package/out/src/shard-recipes/fr-order.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-order.js +0 -208
- package/out/src/shard-recipes/fr-order.js.map +0 -1
- package/out/src/shard-recipes/german.d.ts +0 -23
- package/out/src/shard-recipes/german.d.ts.map +0 -1
- package/out/src/shard-recipes/german.js +0 -132
- package/out/src/shard-recipes/german.js.map +0 -1
- package/out/src/shard-recipes/house-venue.d.ts +0 -18
- package/out/src/shard-recipes/house-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/house-venue.js +0 -74
- package/out/src/shard-recipes/house-venue.js.map +0 -1
- package/out/src/shard-recipes/index.d.ts +0 -24
- package/out/src/shard-recipes/index.d.ts.map +0 -1
- package/out/src/shard-recipes/index.js +0 -89
- package/out/src/shard-recipes/index.js.map +0 -1
- package/out/src/shard-recipes/intersection.d.ts +0 -42
- package/out/src/shard-recipes/intersection.d.ts.map +0 -1
- package/out/src/shard-recipes/intersection.js +0 -460
- package/out/src/shard-recipes/intersection.js.map +0 -1
- package/out/src/shard-recipes/locale.d.ts +0 -135
- package/out/src/shard-recipes/locale.d.ts.map +0 -1
- package/out/src/shard-recipes/locale.js +0 -459
- package/out/src/shard-recipes/locale.js.map +0 -1
- package/out/src/shard-recipes/nl-postcode.d.ts +0 -26
- package/out/src/shard-recipes/nl-postcode.d.ts.map +0 -1
- package/out/src/shard-recipes/nl-postcode.js +0 -102
- package/out/src/shard-recipes/nl-postcode.js.map +0 -1
- package/out/src/shard-recipes/no-fragment.d.ts +0 -43
- package/out/src/shard-recipes/no-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/no-fragment.js +0 -188
- package/out/src/shard-recipes/no-fragment.js.map +0 -1
- package/out/src/shard-recipes/no-street-led.d.ts +0 -24
- package/out/src/shard-recipes/no-street-led.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street-led.js +0 -121
- package/out/src/shard-recipes/no-street-led.js.map +0 -1
- package/out/src/shard-recipes/no-street.d.ts +0 -18
- package/out/src/shard-recipes/no-street.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street.js +0 -72
- package/out/src/shard-recipes/no-street.js.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.d.ts +0 -38
- package/out/src/shard-recipes/po-box-cedex.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.js +0 -726
- package/out/src/shard-recipes/po-box-cedex.js.map +0 -1
- package/out/src/shard-recipes/po-box.d.ts +0 -17
- package/out/src/shard-recipes/po-box.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box.js +0 -101
- package/out/src/shard-recipes/po-box.js.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts +0 -47
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.js +0 -125
- package/out/src/shard-recipes/reviewed-postcode-tail.js.map +0 -1
- package/out/src/shard-recipes/scaffold.d.ts +0 -246
- package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
- package/out/src/shard-recipes/scaffold.js +0 -137
- package/out/src/shard-recipes/scaffold.js.map +0 -1
- package/out/src/shard-recipes/si-bare-village.d.ts +0 -32
- package/out/src/shard-recipes/si-bare-village.d.ts.map +0 -1
- package/out/src/shard-recipes/si-bare-village.js +0 -88
- package/out/src/shard-recipes/si-bare-village.js.map +0 -1
- package/out/src/shard-recipes/street-affix.d.ts +0 -89
- package/out/src/shard-recipes/street-affix.d.ts.map +0 -1
- package/out/src/shard-recipes/street-affix.js +0 -578
- package/out/src/shard-recipes/street-affix.js.map +0 -1
- package/out/src/shard-recipes/street-bare.d.ts +0 -25
- package/out/src/shard-recipes/street-bare.d.ts.map +0 -1
- package/out/src/shard-recipes/street-bare.js +0 -86
- package/out/src/shard-recipes/street-bare.js.map +0 -1
- package/out/src/shard-recipes/street.d.ts +0 -15
- package/out/src/shard-recipes/street.d.ts.map +0 -1
- package/out/src/shard-recipes/street.js +0 -69
- package/out/src/shard-recipes/street.js.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.d.ts +0 -228
- package/out/src/shard-recipes/sub-venue-sources.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.js +0 -664
- package/out/src/shard-recipes/sub-venue-sources.js.map +0 -1
- package/out/src/shard-recipes/sub-venue.d.ts +0 -269
- package/out/src/shard-recipes/sub-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue.js +0 -710
- package/out/src/shard-recipes/sub-venue.js.map +0 -1
- package/out/src/shard-recipes/trailing-region.d.ts +0 -74
- package/out/src/shard-recipes/trailing-region.d.ts.map +0 -1
- package/out/src/shard-recipes/trailing-region.js +0 -157
- package/out/src/shard-recipes/trailing-region.js.map +0 -1
- package/out/src/shard-recipes/unit.d.ts +0 -29
- package/out/src/shard-recipes/unit.d.ts.map +0 -1
- package/out/src/shard-recipes/unit.js +0 -243
- package/out/src/shard-recipes/unit.js.map +0 -1
- package/out/src/synthesizers/anchor-absorption.d.ts +0 -63
- package/out/src/synthesizers/anchor-absorption.d.ts.map +0 -1
- package/out/src/synthesizers/anchor-absorption.js +0 -223
- package/out/src/synthesizers/anchor-absorption.js.map +0 -1
- package/out/src/synthesizers/boundary-stress.d.ts +0 -78
- package/out/src/synthesizers/boundary-stress.d.ts.map +0 -1
- package/out/src/synthesizers/boundary-stress.js +0 -455
- package/out/src/synthesizers/boundary-stress.js.map +0 -1
- package/out/src/synthesizers/german.d.ts +0 -107
- package/out/src/synthesizers/german.d.ts.map +0 -1
- package/out/src/synthesizers/german.js +0 -148
- package/out/src/synthesizers/german.js.map +0 -1
- package/out/src/synthesizers/house-venue.d.ts +0 -56
- package/out/src/synthesizers/house-venue.d.ts.map +0 -1
- package/out/src/synthesizers/house-venue.js +0 -267
- package/out/src/synthesizers/house-venue.js.map +0 -1
- package/out/src/synthesizers/intersection.d.ts +0 -52
- package/out/src/synthesizers/intersection.d.ts.map +0 -1
- package/out/src/synthesizers/intersection.js +0 -175
- package/out/src/synthesizers/intersection.js.map +0 -1
- package/out/src/synthesizers/no-street.d.ts +0 -72
- package/out/src/synthesizers/no-street.d.ts.map +0 -1
- package/out/src/synthesizers/no-street.js +0 -282
- package/out/src/synthesizers/no-street.js.map +0 -1
- package/out/src/synthesizers/po-box.d.ts +0 -104
- package/out/src/synthesizers/po-box.d.ts.map +0 -1
- package/out/src/synthesizers/po-box.js +0 -266
- package/out/src/synthesizers/po-box.js.map +0 -1
- package/out/src/synthesizers/street.d.ts +0 -54
- package/out/src/synthesizers/street.d.ts.map +0 -1
- package/out/src/synthesizers/street.js +0 -221
- package/out/src/synthesizers/street.js.map +0 -1
- package/out/src/synthesizers/utils.d.ts +0 -203
- package/out/src/synthesizers/utils.d.ts.map +0 -1
- package/out/src/synthesizers/utils.js +0 -708
- package/out/src/synthesizers/utils.js.map +0 -1
- package/out/src/tools/align-shard.d.ts +0 -8
- package/out/src/tools/align-shard.d.ts.map +0 -1
- package/out/src/tools/align-shard.js +0 -56
- package/out/src/tools/align-shard.js.map +0 -1
- package/out/src/tools/audit.d.ts +0 -28
- package/out/src/tools/audit.d.ts.map +0 -1
- package/out/src/tools/audit.js +0 -285
- package/out/src/tools/audit.js.map +0 -1
- package/out/src/tools/corpus-stats.d.ts +0 -44
- package/out/src/tools/corpus-stats.d.ts.map +0 -1
- package/out/src/tools/corpus-stats.js +0 -138
- package/out/src/tools/corpus-stats.js.map +0 -1
- package/out/src/tools/fetch/ban.d.ts +0 -31
- package/out/src/tools/fetch/ban.d.ts.map +0 -1
- package/out/src/tools/fetch/ban.js +0 -239
- package/out/src/tools/fetch/ban.js.map +0 -1
- package/out/src/tools/fetch/download.d.ts +0 -78
- package/out/src/tools/fetch/download.d.ts.map +0 -1
- package/out/src/tools/fetch/download.js +0 -116
- package/out/src/tools/fetch/download.js.map +0 -1
- package/out/src/tools/fetch/geonames-dump.d.ts +0 -87
- package/out/src/tools/fetch/geonames-dump.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-dump.js +0 -178
- package/out/src/tools/fetch/geonames-dump.js.map +0 -1
- package/out/src/tools/fetch/geonames-postal.d.ts +0 -76
- package/out/src/tools/fetch/geonames-postal.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-postal.js +0 -125
- package/out/src/tools/fetch/geonames-postal.js.map +0 -1
- package/out/src/tools/fetch/hrsa.d.ts +0 -18
- package/out/src/tools/fetch/hrsa.d.ts.map +0 -1
- package/out/src/tools/fetch/hrsa.js +0 -46
- package/out/src/tools/fetch/hrsa.js.map +0 -1
- package/out/src/tools/fetch/imls-pls.d.ts +0 -25
- package/out/src/tools/fetch/imls-pls.d.ts.map +0 -1
- package/out/src/tools/fetch/imls-pls.js +0 -108
- package/out/src/tools/fetch/imls-pls.js.map +0 -1
- package/out/src/tools/fetch/index.d.ts +0 -144
- package/out/src/tools/fetch/index.d.ts.map +0 -1
- package/out/src/tools/fetch/index.js +0 -143
- package/out/src/tools/fetch/index.js.map +0 -1
- package/out/src/tools/fetch/nad.d.ts +0 -70
- package/out/src/tools/fetch/nad.d.ts.map +0 -1
- package/out/src/tools/fetch/nad.js +0 -234
- package/out/src/tools/fetch/nad.js.map +0 -1
- package/out/src/tools/fetch/nppes.d.ts +0 -26
- package/out/src/tools/fetch/nppes.d.ts.map +0 -1
- package/out/src/tools/fetch/nppes.js +0 -126
- package/out/src/tools/fetch/nppes.js.map +0 -1
- package/out/src/tools/fetch/openaddresses.d.ts +0 -61
- package/out/src/tools/fetch/openaddresses.d.ts.map +0 -1
- package/out/src/tools/fetch/openaddresses.js +0 -317
- package/out/src/tools/fetch/openaddresses.js.map +0 -1
- package/out/src/tools/fetch/ourairports.d.ts +0 -45
- package/out/src/tools/fetch/ourairports.d.ts.map +0 -1
- package/out/src/tools/fetch/ourairports.js +0 -128
- package/out/src/tools/fetch/ourairports.js.map +0 -1
- package/out/src/tools/fetch/ppd.d.ts.map +0 -1
- package/out/src/tools/fetch/ppd.js +0 -100
- package/out/src/tools/fetch/ppd.js.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.d.ts +0 -25
- package/out/src/tools/fetch/state-hi-schools.d.ts.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.js +0 -162
- package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
- package/out/src/tools/fetch/state-sources.d.ts +0 -26
- package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
- package/out/src/tools/fetch/state-sources.js +0 -111
- package/out/src/tools/fetch/state-sources.js.map +0 -1
- package/out/src/tools/fetch/tiger-full.d.ts +0 -42
- package/out/src/tools/fetch/tiger-full.d.ts.map +0 -1
- package/out/src/tools/fetch/tiger-full.js +0 -248
- package/out/src/tools/fetch/tiger-full.js.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.d.ts +0 -171
- package/out/src/tools/fetch/wikidata-subvenue.d.ts.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.js +0 -275
- package/out/src/tools/fetch/wikidata-subvenue.js.map +0 -1
- package/out/src/tools/gb-title-case.d.ts.map +0 -1
- package/out/src/tools/gb-title-case.js.map +0 -1
- package/out/src/tools/golden-expand.d.ts +0 -90
- package/out/src/tools/golden-expand.d.ts.map +0 -1
- package/out/src/tools/golden-expand.js +0 -413
- package/out/src/tools/golden-expand.js.map +0 -1
- package/out/src/tools/golden-promote.d.ts.map +0 -1
- package/out/src/tools/golden-promote.js +0 -244
- package/out/src/tools/golden-promote.js.map +0 -1
- package/out/src/tools/golden-relabel-street.d.ts +0 -196
- package/out/src/tools/golden-relabel-street.d.ts.map +0 -1
- package/out/src/tools/golden-relabel-street.js +0 -440
- package/out/src/tools/golden-relabel-street.js.map +0 -1
- package/out/src/tools/index.d.ts +0 -28
- package/out/src/tools/index.d.ts.map +0 -1
- package/out/src/tools/index.js +0 -28
- package/out/src/tools/index.js.map +0 -1
- package/out/src/tools/ingest-csv.d.ts.map +0 -1
- package/out/src/tools/ingest-csv.js +0 -296
- package/out/src/tools/ingest-csv.js.map +0 -1
- package/out/src/tools/jsonl-to-parquet.d.ts +0 -61
- package/out/src/tools/jsonl-to-parquet.d.ts.map +0 -1
- package/out/src/tools/jsonl-to-parquet.js +0 -164
- package/out/src/tools/jsonl-to-parquet.js.map +0 -1
- package/out/src/tools/lint-shard-vocab.d.ts +0 -90
- package/out/src/tools/lint-shard-vocab.d.ts.map +0 -1
- package/out/src/tools/lint-shard-vocab.js +0 -281
- package/out/src/tools/lint-shard-vocab.js.map +0 -1
- package/out/src/tools/lint-shard.d.ts +0 -93
- package/out/src/tools/lint-shard.d.ts.map +0 -1
- package/out/src/tools/lint-shard.js +0 -354
- package/out/src/tools/lint-shard.js.map +0 -1
- package/out/src/tools/overlay-manifest.d.ts +0 -39
- package/out/src/tools/overlay-manifest.d.ts.map +0 -1
- package/out/src/tools/overlay-manifest.js +0 -98
- package/out/src/tools/overlay-manifest.js.map +0 -1
- package/out/src/tools/overture-subvenue.d.ts +0 -112
- package/out/src/tools/overture-subvenue.d.ts.map +0 -1
- package/out/src/tools/overture-subvenue.js +0 -144
- package/out/src/tools/overture-subvenue.js.map +0 -1
- package/out/src/tools/postcode-triples.d.ts +0 -175
- package/out/src/tools/postcode-triples.d.ts.map +0 -1
- package/out/src/tools/postcode-triples.js +0 -304
- package/out/src/tools/postcode-triples.js.map +0 -1
- package/out/src/tools/shard-kryptonite.d.ts +0 -32
- package/out/src/tools/shard-kryptonite.d.ts.map +0 -1
- package/out/src/tools/shard-kryptonite.js +0 -100
- package/out/src/tools/shard-kryptonite.js.map +0 -1
- package/out/src/tools/shard-translit.d.ts +0 -51
- package/out/src/tools/shard-translit.d.ts.map +0 -1
- package/out/src/tools/shard-translit.js +0 -175
- package/out/src/tools/shard-translit.js.map +0 -1
- package/out/src/tools/sub-venue/harvest.d.ts +0 -100
- package/out/src/tools/sub-venue/harvest.d.ts.map +0 -1
- package/out/src/tools/sub-venue/harvest.js +0 -168
- package/out/src/tools/sub-venue/harvest.js.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.d.ts +0 -50
- package/out/src/tools/sub-venue/head-nouns.d.ts.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.js +0 -210
- package/out/src/tools/sub-venue/head-nouns.js.map +0 -1
- package/out/src/tools/sub-venue/surfaces.d.ts +0 -45
- package/out/src/tools/sub-venue/surfaces.d.ts.map +0 -1
- package/out/src/tools/sub-venue/surfaces.js +0 -77
- package/out/src/tools/sub-venue/surfaces.js.map +0 -1
- package/out/src/tools/sub-venue/table.d.ts +0 -229
- package/out/src/tools/sub-venue/table.d.ts.map +0 -1
- package/out/src/tools/sub-venue/table.js +0 -108
- package/out/src/tools/sub-venue/table.js.map +0 -1
- package/out/src/tools/sub-venue/wikidata.d.ts +0 -26
- package/out/src/tools/sub-venue/wikidata.d.ts.map +0 -1
- package/out/src/tools/sub-venue/wikidata.js +0 -62
- package/out/src/tools/sub-venue/wikidata.js.map +0 -1
- package/out/src/tools/sub-venue-lexicon.d.ts +0 -156
- package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
- package/out/src/tools/sub-venue-lexicon.js +0 -282
- package/out/src/tools/sub-venue-lexicon.js.map +0 -1
- package/out/src/tools/sub-venue-promotions.d.ts +0 -94
- package/out/src/tools/sub-venue-promotions.d.ts.map +0 -1
- package/out/src/tools/sub-venue-promotions.js +0 -266
- package/out/src/tools/sub-venue-promotions.js.map +0 -1
- package/out/src/types.d.ts +0 -221
- package/out/src/types.d.ts.map +0 -1
- package/out/src/types.js.map +0 -1
- package/out/src/utils/align.d.ts +0 -93
- package/out/src/utils/align.d.ts.map +0 -1
- package/out/src/utils/align.js +0 -234
- package/out/src/utils/align.js.map +0 -1
- package/out/src/utils/golden.d.ts +0 -69
- package/out/src/utils/golden.d.ts.map +0 -1
- package/out/src/utils/golden.js +0 -127
- package/out/src/utils/golden.js.map +0 -1
- package/out/src/utils/index.d.ts +0 -14
- package/out/src/utils/index.d.ts.map +0 -1
- package/out/src/utils/index.js +0 -14
- package/out/src/utils/index.js.map +0 -1
- package/out/src/utils/license.d.ts.map +0 -1
- package/out/src/utils/license.js.map +0 -1
- package/out/src/utils/parquet.d.ts +0 -162
- package/out/src/utils/parquet.d.ts.map +0 -1
- package/out/src/utils/parquet.js +0 -262
- package/out/src/utils/parquet.js.map +0 -1
- package/out/src/utils/split.d.ts +0 -127
- package/out/src/utils/split.d.ts.map +0 -1
- package/out/src/utils/split.js +0 -204
- package/out/src/utils/split.js.map +0 -1
- package/out/src/utils/tokenize.d.ts +0 -56
- package/out/src/utils/tokenize.d.ts.map +0 -1
- package/out/src/utils/tokenize.js +0 -48
- package/out/src/utils/tokenize.js.map +0 -1
- package/out/src/utils/wof-json.d.ts +0 -109
- package/out/src/utils/wof-json.d.ts.map +0 -1
- package/out/src/utils/wof-json.js +0 -173
- package/out/src/utils/wof-json.js.map +0 -1
- package/src/adapters/ban/adapter.ts +0 -191
- package/src/adapters/ban/street-decompose.ts +0 -96
- package/src/adapters/fcc-bdc/adapter.ts +0 -174
- package/src/adapters/geonames/adapter.ts +0 -200
- package/src/adapters/geonames-postal/adapter.ts +0 -119
- package/src/adapters/gnaf/adapter.ts +0 -149
- package/src/adapters/gnaf/assemble.ts +0 -226
- package/src/adapters/index.ts +0 -149
- package/src/adapters/openaddresses/adapter.ts +0 -251
- package/src/adapters/overture/adapter.ts +0 -162
- package/src/adapters/state-hi-schools/adapter.ts +0 -164
- package/src/adapters/synth-po-box/adapter.ts +0 -204
- package/src/adapters/tiger/adapter.ts +0 -253
- package/src/adapters/tiger/street-decompose.ts +0 -111
- package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -183
- package/src/adapters/usgov-imls-pls/adapter.ts +0 -143
- package/src/adapters/usgov-irs-bmf/adapter.ts +0 -163
- package/src/adapters/usgov-nad/adapter.ts +0 -348
- package/src/adapters/usgov-nppes/adapter.ts +0 -159
- package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -204
- package/src/adapters/utils/index.ts +0 -233
- package/src/adapters/wof-admin-jp/adapter.ts +0 -216
- package/src/adapters/wof-admin-json/adapter.ts +0 -256
- package/src/adapters/wof-json-rows.ts +0 -79
- package/src/adapters/wof-postalcode-json/adapter.ts +0 -183
- package/src/build.ts +0 -386
- package/src/index.ts +0 -14
- package/src/name-prone-us-suffixes.ts +0 -12
- package/src/parquet-wrapper/index.ts +0 -9
- package/src/parquet-wrapper/reader.ts +0 -97
- package/src/parquet-wrapper/schema.ts +0 -88
- package/src/parquet-wrapper/writer.ts +0 -110
- package/src/runner.ts +0 -317
- package/src/shard-recipes/anchor-absorption.ts +0 -103
- package/src/shard-recipes/bare-country.ts +0 -95
- package/src/shard-recipes/boundary-stress.ts +0 -101
- package/src/shard-recipes/country-balanced.ts +0 -524
- package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -111
- package/src/shard-recipes/fr-admin-split.ts +0 -239
- package/src/shard-recipes/fr-bare-street.ts +0 -170
- package/src/shard-recipes/fr-fragment.ts +0 -332
- package/src/shard-recipes/fr-lieudit.ts +0 -302
- package/src/shard-recipes/fr-order.ts +0 -258
- package/src/shard-recipes/german.ts +0 -170
- package/src/shard-recipes/house-venue.ts +0 -88
- package/src/shard-recipes/index.ts +0 -95
- package/src/shard-recipes/intersection.ts +0 -630
- package/src/shard-recipes/locale.ts +0 -599
- package/src/shard-recipes/nl-postcode.ts +0 -115
- package/src/shard-recipes/no-fragment.ts +0 -219
- package/src/shard-recipes/no-street-led.ts +0 -143
- package/src/shard-recipes/no-street.ts +0 -86
- package/src/shard-recipes/po-box-cedex.ts +0 -920
- package/src/shard-recipes/po-box.ts +0 -119
- package/src/shard-recipes/reviewed-postcode-tail.ts +0 -189
- package/src/shard-recipes/scaffold.ts +0 -360
- package/src/shard-recipes/si-bare-village.ts +0 -97
- package/src/shard-recipes/street-affix.ts +0 -826
- package/src/shard-recipes/street-bare.ts +0 -101
- package/src/shard-recipes/street.ts +0 -82
- package/src/shard-recipes/sub-venue-sources.ts +0 -885
- package/src/shard-recipes/sub-venue.ts +0 -984
- package/src/shard-recipes/trailing-region.ts +0 -183
- package/src/shard-recipes/unit.ts +0 -321
- package/src/synthesizers/anchor-absorption.ts +0 -290
- package/src/synthesizers/boundary-stress.ts +0 -531
- package/src/synthesizers/german.ts +0 -251
- package/src/synthesizers/house-venue.ts +0 -330
- package/src/synthesizers/intersection.ts +0 -232
- package/src/synthesizers/no-street.ts +0 -349
- package/src/synthesizers/po-box.ts +0 -339
- package/src/synthesizers/street.ts +0 -274
- package/src/synthesizers/utils.ts +0 -903
- package/src/tools/align-shard.ts +0 -70
- package/src/tools/audit.ts +0 -399
- package/src/tools/corpus-stats.ts +0 -184
- package/src/tools/fetch/ban.ts +0 -290
- package/src/tools/fetch/download.ts +0 -176
- package/src/tools/fetch/geonames-dump.ts +0 -267
- package/src/tools/fetch/geonames-postal.ts +0 -180
- package/src/tools/fetch/hrsa.ts +0 -68
- package/src/tools/fetch/imls-pls.ts +0 -158
- package/src/tools/fetch/index.ts +0 -147
- package/src/tools/fetch/nad.ts +0 -342
- package/src/tools/fetch/nppes.ts +0 -174
- package/src/tools/fetch/openaddresses.ts +0 -404
- package/src/tools/fetch/ourairports.ts +0 -171
- package/src/tools/fetch/ppd.ts +0 -137
- package/src/tools/fetch/state-hi-schools.ts +0 -208
- package/src/tools/fetch/state-sources.ts +0 -155
- package/src/tools/fetch/tiger-full.ts +0 -354
- package/src/tools/fetch/wikidata-subvenue.ts +0 -386
- package/src/tools/golden-expand.ts +0 -584
- package/src/tools/golden-promote.ts +0 -353
- package/src/tools/golden-relabel-street.ts +0 -685
- package/src/tools/index.ts +0 -28
- package/src/tools/ingest-csv.ts +0 -422
- package/src/tools/jsonl-to-parquet.ts +0 -221
- package/src/tools/lint-shard-vocab.ts +0 -409
- package/src/tools/lint-shard.ts +0 -543
- package/src/tools/overlay-manifest.ts +0 -157
- package/src/tools/overture-subvenue.ts +0 -215
- package/src/tools/postcode-triples.ts +0 -375
- package/src/tools/shard-kryptonite.ts +0 -139
- package/src/tools/shard-translit.ts +0 -245
- package/src/tools/sub-venue/harvest.ts +0 -235
- package/src/tools/sub-venue/head-nouns.ts +0 -242
- package/src/tools/sub-venue/surfaces.ts +0 -95
- package/src/tools/sub-venue/table.ts +0 -281
- package/src/tools/sub-venue/wikidata.ts +0 -85
- package/src/tools/sub-venue-lexicon.ts +0 -431
- package/src/tools/sub-venue-promotions.ts +0 -330
- package/src/types.ts +0 -247
- package/src/utils/align.ts +0 -331
- package/src/utils/golden.ts +0 -176
- package/src/utils/index.ts +0 -14
- package/src/utils/parquet.ts +0 -391
- package/src/utils/split.ts +0 -279
- package/src/utils/tokenize.ts +0 -78
- package/src/utils/wof-json.ts +0 -244
- /package/{src → lib}/adapters/state-ia-contractors/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-ny-notaries/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-tx-notaries/adapter.ts +0 -0
- /package/{src → lib}/codex/us-fips-state.ts +0 -0
- /package/{src → lib}/tools/gb-title-case.ts +0 -0
- /package/{src → lib}/utils/license.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/fcc-bdc/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/geonames/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/openaddresses/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/synth-po-box/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/tiger/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-nppes/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-samhsa-treatment-locator/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/wof-admin-jp/adapter.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.js +0 -0
- /package/out/{src/tools → tools}/fetch/ppd.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.js +0 -0
- /package/out/{src/tools → tools}/golden-promote.d.ts +0 -0
- /package/out/{src/tools → tools}/ingest-csv.d.ts +0 -0
- /package/out/{src/types.js → types.js} +0 -0
- /package/out/{src/utils → utils}/license.d.ts +0 -0
- /package/out/{src/utils → utils}/license.js +0 -0
package/out/src/build.d.ts
DELETED
|
@@ -1,132 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* End-to-end corpus build (Phase 1 task #10 in the plan).
|
|
7
|
-
*
|
|
8
|
-
* `buildCorpus(opts)` orchestrates every stage of the pipeline:
|
|
9
|
-
*
|
|
10
|
-
* 1. **Adapter runs** — drives every adapter in turn (via `runAdapter`), writing
|
|
11
|
-
* `<intermediate>/<adapter.id>/canonical.jsonl` shards.
|
|
12
|
-
* 2. **Synthesis** — optional. For each canonical row, every applicable augmentation in the row's
|
|
13
|
-
* country-default policy emits an augmented row alongside the original.
|
|
14
|
-
* 3. **Alignment** — every row (original + augmented) is aligned via `alignRow`. Successes go to
|
|
15
|
-
* `labeled.jsonl`; quarantines are appended to `quarantine.jsonl` with reasons.
|
|
16
|
-
* 4. **Splits** — `splitRows` partitions labeled `source_id`s into train/val/test by locality holdout.
|
|
17
|
-
* Manifest written to `splits/SPLIT_MANIFEST.json` + per-split `train.txt` / `val.txt` /
|
|
18
|
-
* `test.txt`.
|
|
19
|
-
* 5. **Parquet shards** — `writeShards` streams labeled rows into 1M-row `.parquet` shards per split
|
|
20
|
-
* under `corpus-v<version>/{train,val,test}/part-NNNN.parquet` (SNAPPY-compressed, 50k-row
|
|
21
|
-
* row groups), with per-shard checksums + per-stage manifest in
|
|
22
|
-
* `corpus-v<version>/MANIFEST.json`.
|
|
23
|
-
* 6. **Top-level manifest** — `<outputDir>/MANIFEST.json` ties every per-stage manifest together with
|
|
24
|
-
* a top-level corpus_version, built_at, and aggregate counts.
|
|
25
|
-
*
|
|
26
|
-
* Output layout:
|
|
27
|
-
*
|
|
28
|
-
* ```
|
|
29
|
-
* <outputDir>/
|
|
30
|
-
* MANIFEST.json
|
|
31
|
-
* intermediate/
|
|
32
|
-
* <adapter.id>/canonical.jsonl # one per adapter
|
|
33
|
-
* labeled.jsonl # post-alignment, pre-shard
|
|
34
|
-
* quarantine.jsonl # rows that failed alignment
|
|
35
|
-
* splits/
|
|
36
|
-
* SPLIT_MANIFEST.json
|
|
37
|
-
* train.txt / val.txt / test.txt
|
|
38
|
-
* corpus-v<version>/
|
|
39
|
-
* MANIFEST.json
|
|
40
|
-
* train/part-NNNN.parquet
|
|
41
|
-
* val/part-NNNN.parquet
|
|
42
|
-
* test/part-NNNN.parquet
|
|
43
|
-
* ```
|
|
44
|
-
*
|
|
45
|
-
* The intermediate files live alongside the final shards for reproducibility + debugging. Operators
|
|
46
|
-
* can `rm -rf intermediate/` after the build if disk is tight; the final `corpus-v<version>/` is
|
|
47
|
-
* self-contained.
|
|
48
|
-
*/
|
|
49
|
-
import { type AdapterRunManifest } from "#runner";
|
|
50
|
-
import type { AdapterOptions, CorpusAdapter } from "#types";
|
|
51
|
-
import { type ShardManifest } from "#utils/parquet";
|
|
52
|
-
import { type SplitManifest } from "#utils/split";
|
|
53
|
-
/**
|
|
54
|
-
* Stage tags surfaced to `onProgress`.
|
|
55
|
-
*/
|
|
56
|
-
export type BuildStage = "adapter-run" | "align" | "split" | "shard" | "manifest";
|
|
57
|
-
/**
|
|
58
|
-
* Per-invocation options for `buildCorpus`.
|
|
59
|
-
*/
|
|
60
|
-
export interface BuildCorpusOptions {
|
|
61
|
-
/**
|
|
62
|
-
* Root output directory. All build artifacts land beneath it.
|
|
63
|
-
*/
|
|
64
|
-
outputDir: string;
|
|
65
|
-
/**
|
|
66
|
-
* Corpus version (e.g. `"0.1.0"`). Stamped onto every row + into the output dir name.
|
|
67
|
-
*/
|
|
68
|
-
corpusVersion: string;
|
|
69
|
-
/**
|
|
70
|
-
* Adapters to drive, in order. Defaults to `defaultAdapterRegistry.list()`. Pass an explicit list to filter (e.g.
|
|
71
|
-
* `[wofAdminAdapter]` for a smoke run).
|
|
72
|
-
*/
|
|
73
|
-
adapters?: readonly CorpusAdapter[];
|
|
74
|
-
/**
|
|
75
|
-
* Per-adapter `AdapterOptions` — looked up by adapter id. Adapters whose id is missing from this map are skipped (and
|
|
76
|
-
* noted in the manifest).
|
|
77
|
-
*/
|
|
78
|
-
adapterInputs: Record<string, AdapterOptions>;
|
|
79
|
-
/**
|
|
80
|
-
* Enable synthesis pass. Default `true`. Set `false` for fixture-driven smoke tests.
|
|
81
|
-
*/
|
|
82
|
-
synthesize?: boolean;
|
|
83
|
-
/**
|
|
84
|
-
* Forwarded to `writeShards`. Default 1_000_000.
|
|
85
|
-
*/
|
|
86
|
-
rowsPerShard?: number;
|
|
87
|
-
/**
|
|
88
|
-
* Progress hook. Errors thrown abort the build.
|
|
89
|
-
*/
|
|
90
|
-
onProgress?: (stage: BuildStage, message: string) => void;
|
|
91
|
-
/**
|
|
92
|
-
* License kinds to PURPOSELY exclude from this build (#26). Compiled patterns (see `compileLicenseExcludes` /
|
|
93
|
-
* `SHARE_ALIKE_PATTERN` in `license.ts`); a row whose `license` matches any is dropped at ingest. Default (omitted)
|
|
94
|
-
* includes EVERYTHING — exclusion is a deliberate act, not a silent default. A proprietary-weights build passes the
|
|
95
|
-
* share-alike set (`--exclude-share-alike`).
|
|
96
|
-
*/
|
|
97
|
-
excludeLicenses?: readonly RegExp[];
|
|
98
|
-
}
|
|
99
|
-
/**
|
|
100
|
-
* Top-level manifest tying every stage together.
|
|
101
|
-
*/
|
|
102
|
-
export interface BuildCorpusManifest {
|
|
103
|
-
corpus_version: string;
|
|
104
|
-
built_at: string;
|
|
105
|
-
adapters: AdapterRunManifest[];
|
|
106
|
-
skipped_adapters: string[];
|
|
107
|
-
splits: {
|
|
108
|
-
counts: SplitManifest["counts"];
|
|
109
|
-
holdouts: SplitManifest["holdouts"];
|
|
110
|
-
};
|
|
111
|
-
shards: {
|
|
112
|
-
counts: ShardManifest["counts"];
|
|
113
|
-
total_rows: number;
|
|
114
|
-
};
|
|
115
|
-
quarantine_count: number;
|
|
116
|
-
total_aligned_rows: number;
|
|
117
|
-
/**
|
|
118
|
-
* Resolved license set across all INCLUDED rows (license string → row count), + the count dropped by
|
|
119
|
-
* `excludeLicenses` (#26). The model card derives its data-attribution table from `licenses`.
|
|
120
|
-
*/
|
|
121
|
-
licenses: Record<string, number>;
|
|
122
|
-
excluded_by_license: number;
|
|
123
|
-
}
|
|
124
|
-
/**
|
|
125
|
-
* Drive the full corpus build to completion.
|
|
126
|
-
*
|
|
127
|
-
* Memory profile: the function maintains an in-memory `Map<source_id, SplitName>` to bridge the align → shard hand-off.
|
|
128
|
-
* For Phase 1 fixture-scale runs (≤ 10⁴ rows) this is trivial. For real 5M+ runs, the map fits comfortably in a few
|
|
129
|
-
* hundred MB; the canonical.jsonl and labeled.jsonl payloads stream and never sit in memory.
|
|
130
|
-
*/
|
|
131
|
-
export declare function buildCorpus(opts: BuildCorpusOptions): Promise<BuildCorpusManifest>;
|
|
132
|
-
//# sourceMappingURL=build.d.ts.map
|
package/out/src/build.d.ts.map
DELETED
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"build.d.ts","sourceRoot":"","sources":["../../src/build.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA+CG;AAWH,OAAO,EAAc,KAAK,kBAAkB,EAAE,MAAM,SAAS,CAAA;AAE7D,OAAO,KAAK,EAAE,cAAc,EAAgB,aAAa,EAAc,MAAM,QAAQ,CAAA;AAGrF,OAAO,EAAe,KAAK,aAAa,EAAE,MAAM,gBAAgB,CAAA;AAChE,OAAO,EAIN,KAAK,aAAa,EAElB,MAAM,cAAc,CAAA;AAErB;;GAEG;AACH,MAAM,MAAM,UAAU,GAAG,aAAa,GAAG,OAAO,GAAG,OAAO,GAAG,OAAO,GAAG,UAAU,CAAA;AAEjF;;GAEG;AACH,MAAM,WAAW,kBAAkB;IAClC;;OAEG;IACH,SAAS,EAAE,MAAM,CAAA;IAEjB;;OAEG;IACH,aAAa,EAAE,MAAM,CAAA;IAErB;;;OAGG;IACH,QAAQ,CAAC,EAAE,SAAS,aAAa,EAAE,CAAA;IAEnC;;;OAGG;IACH,aAAa,EAAE,MAAM,CAAC,MAAM,EAAE,cAAc,CAAC,CAAA;IAE7C;;OAEG;IACH,UAAU,CAAC,EAAE,OAAO,CAAA;IAEpB;;OAEG;IACH,YAAY,CAAC,EAAE,MAAM,CAAA;IAErB;;OAEG;IACH,UAAU,CAAC,EAAE,CAAC,KAAK,EAAE,UAAU,EAAE,OAAO,EAAE,MAAM,KAAK,IAAI,CAAA;IAEzD;;;;;OAKG;IACH,eAAe,CAAC,EAAE,SAAS,MAAM,EAAE,CAAA;CACnC;AAED;;GAEG;AACH,MAAM,WAAW,mBAAmB;IACnC,cAAc,EAAE,MAAM,CAAA;IACtB,QAAQ,EAAE,MAAM,CAAA;IAChB,QAAQ,EAAE,kBAAkB,EAAE,CAAA;IAC9B,gBAAgB,EAAE,MAAM,EAAE,CAAA;IAC1B,MAAM,EAAE;QAAE,MAAM,EAAE,aAAa,CAAC,QAAQ,CAAC,CAAC;QAAC,QAAQ,EAAE,aAAa,CAAC,UAAU,CAAC,CAAA;KAAE,CAAA;IAChF,MAAM,EAAE;QAAE,MAAM,EAAE,aAAa,CAAC,QAAQ,CAAC,CAAC;QAAC,UAAU,EAAE,MAAM,CAAA;KAAE,CAAA;IAC/D,gBAAgB,EAAE,MAAM,CAAA;IACxB,kBAAkB,EAAE,MAAM,CAAA;IAC1B;;;OAGG;IACH,QAAQ,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IAChC,mBAAmB,EAAE,MAAM,CAAA;CAC3B;AAED;;;;;;GAMG;AACH,wBAAsB,WAAW,CAAC,IAAI,EAAE,kBAAkB,GAAG,OAAO,CAAC,mBAAmB,CAAC,CAyNxF"}
|
package/out/src/build.js
DELETED
|
@@ -1,251 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* End-to-end corpus build (Phase 1 task #10 in the plan).
|
|
7
|
-
*
|
|
8
|
-
* `buildCorpus(opts)` orchestrates every stage of the pipeline:
|
|
9
|
-
*
|
|
10
|
-
* 1. **Adapter runs** — drives every adapter in turn (via `runAdapter`), writing
|
|
11
|
-
* `<intermediate>/<adapter.id>/canonical.jsonl` shards.
|
|
12
|
-
* 2. **Synthesis** — optional. For each canonical row, every applicable augmentation in the row's
|
|
13
|
-
* country-default policy emits an augmented row alongside the original.
|
|
14
|
-
* 3. **Alignment** — every row (original + augmented) is aligned via `alignRow`. Successes go to
|
|
15
|
-
* `labeled.jsonl`; quarantines are appended to `quarantine.jsonl` with reasons.
|
|
16
|
-
* 4. **Splits** — `splitRows` partitions labeled `source_id`s into train/val/test by locality holdout.
|
|
17
|
-
* Manifest written to `splits/SPLIT_MANIFEST.json` + per-split `train.txt` / `val.txt` /
|
|
18
|
-
* `test.txt`.
|
|
19
|
-
* 5. **Parquet shards** — `writeShards` streams labeled rows into 1M-row `.parquet` shards per split
|
|
20
|
-
* under `corpus-v<version>/{train,val,test}/part-NNNN.parquet` (SNAPPY-compressed, 50k-row
|
|
21
|
-
* row groups), with per-shard checksums + per-stage manifest in
|
|
22
|
-
* `corpus-v<version>/MANIFEST.json`.
|
|
23
|
-
* 6. **Top-level manifest** — `<outputDir>/MANIFEST.json` ties every per-stage manifest together with
|
|
24
|
-
* a top-level corpus_version, built_at, and aggregate counts.
|
|
25
|
-
*
|
|
26
|
-
* Output layout:
|
|
27
|
-
*
|
|
28
|
-
* ```
|
|
29
|
-
* <outputDir>/
|
|
30
|
-
* MANIFEST.json
|
|
31
|
-
* intermediate/
|
|
32
|
-
* <adapter.id>/canonical.jsonl # one per adapter
|
|
33
|
-
* labeled.jsonl # post-alignment, pre-shard
|
|
34
|
-
* quarantine.jsonl # rows that failed alignment
|
|
35
|
-
* splits/
|
|
36
|
-
* SPLIT_MANIFEST.json
|
|
37
|
-
* train.txt / val.txt / test.txt
|
|
38
|
-
* corpus-v<version>/
|
|
39
|
-
* MANIFEST.json
|
|
40
|
-
* train/part-NNNN.parquet
|
|
41
|
-
* val/part-NNNN.parquet
|
|
42
|
-
* test/part-NNNN.parquet
|
|
43
|
-
* ```
|
|
44
|
-
*
|
|
45
|
-
* The intermediate files live alongside the final shards for reproducibility + debugging. Operators
|
|
46
|
-
* can `rm -rf intermediate/` after the build if disk is tight; the final `corpus-v<version>/` is
|
|
47
|
-
* self-contained.
|
|
48
|
-
*/
|
|
49
|
-
import { createWriteStream, existsSync, readFileSync } from "node:fs";
|
|
50
|
-
import { mkdir, writeFile } from "node:fs/promises";
|
|
51
|
-
import { join } from "node:path";
|
|
52
|
-
import { $public } from "@mailwoman/core/env";
|
|
53
|
-
import { parseJSONStrict } from "@mailwoman/core/objects";
|
|
54
|
-
import { JSONSpliterator } from "spliterator";
|
|
55
|
-
import { defaultAdapterRegistry } from "#adapters/utils";
|
|
56
|
-
import { runAdapter } from "#runner";
|
|
57
|
-
import { defaultAugmentationsForCountry, synthesizeRow } from "#synthesizers/utils";
|
|
58
|
-
import { alignRow } from "#utils/align";
|
|
59
|
-
import { licenseExcluded } from "#utils/license";
|
|
60
|
-
import { writeShards } from "#utils/parquet";
|
|
61
|
-
import { defaultHoldouts, splitForRow, writeSplitManifestsFromLabeledFiles, } from "#utils/split";
|
|
62
|
-
/**
|
|
63
|
-
* Drive the full corpus build to completion.
|
|
64
|
-
*
|
|
65
|
-
* Memory profile: the function maintains an in-memory `Map<source_id, SplitName>` to bridge the align → shard hand-off.
|
|
66
|
-
* For Phase 1 fixture-scale runs (≤ 10⁴ rows) this is trivial. For real 5M+ runs, the map fits comfortably in a few
|
|
67
|
-
* hundred MB; the canonical.jsonl and labeled.jsonl payloads stream and never sit in memory.
|
|
68
|
-
*/
|
|
69
|
-
export async function buildCorpus(opts) {
|
|
70
|
-
const adapters = opts.adapters ?? defaultAdapterRegistry.list();
|
|
71
|
-
const synthesize = opts.synthesize ?? true;
|
|
72
|
-
const rowsPerShard = opts.rowsPerShard ?? 1_000_000;
|
|
73
|
-
const built_at = new Date().toISOString();
|
|
74
|
-
await mkdir(opts.outputDir, { recursive: true });
|
|
75
|
-
const intermediateDir = join(opts.outputDir, "intermediate");
|
|
76
|
-
await mkdir(intermediateDir, { recursive: true });
|
|
77
|
-
// 1. Adapter runs.
|
|
78
|
-
const adapterRuns = [];
|
|
79
|
-
const skipped = [];
|
|
80
|
-
for (const adapter of adapters) {
|
|
81
|
-
const adapterOptions = opts.adapterInputs[adapter.id];
|
|
82
|
-
if (!adapterOptions) {
|
|
83
|
-
skipped.push(adapter.id);
|
|
84
|
-
opts.onProgress?.("adapter-run", `skipped ${adapter.id} (no input configured)`);
|
|
85
|
-
continue;
|
|
86
|
-
}
|
|
87
|
-
// Opt-in resume (MAILWOMAN_RESUME=1): if a complete per-adapter canonical.jsonl + MANIFEST.json
|
|
88
|
-
// already exist, reuse them instead of re-emitting. The MANIFEST is written only after the
|
|
89
|
-
// canonical is fully flushed, so its presence guarantees completeness; row order is identical,
|
|
90
|
-
// so downstream holdout-split determinism is preserved. Recovers an align-phase crash without
|
|
91
|
-
// redoing the (expensive) emit phase. Default (unset) re-emits, preserving correctness. (2026-06-12.)
|
|
92
|
-
const adapterDir = join(intermediateDir, adapter.id);
|
|
93
|
-
const cachedManifest = join(adapterDir, "MANIFEST.json");
|
|
94
|
-
if ($public.MAILWOMAN_RESUME === "1" &&
|
|
95
|
-
existsSync(cachedManifest) &&
|
|
96
|
-
existsSync(join(adapterDir, "canonical.jsonl"))) {
|
|
97
|
-
const cached = parseJSONStrict(readFileSync(cachedManifest, "utf8"));
|
|
98
|
-
opts.onProgress?.("adapter-run", `resumed ${adapter.id} (reused ${cached.yielded} canonical rows)`);
|
|
99
|
-
adapterRuns.push(cached);
|
|
100
|
-
continue;
|
|
101
|
-
}
|
|
102
|
-
opts.onProgress?.("adapter-run", `running ${adapter.id}`);
|
|
103
|
-
const m = await runAdapter({
|
|
104
|
-
adapter,
|
|
105
|
-
adapterOptions,
|
|
106
|
-
outputDir: intermediateDir,
|
|
107
|
-
corpusVersion: opts.corpusVersion,
|
|
108
|
-
});
|
|
109
|
-
adapterRuns.push(m);
|
|
110
|
-
}
|
|
111
|
-
// 2 + 3. Synthesis + alignment: stream every canonical.jsonl, optionally augment, align,
|
|
112
|
-
// and route each labeled row directly to its split-specific JSONL (`labeled-{train,val,test}.
|
|
113
|
-
// jsonl`). Memory cost is O(1) — the prior in-memory `splitInputs` array + `splitByIDMap`
|
|
114
|
-
// + `SplitManifest.{train,val,test}` arrays are gone; per-row split is decided inline via
|
|
115
|
-
// `splitForRow` (a pure function of source_id + region + holdout policy).
|
|
116
|
-
const labeledPaths = {
|
|
117
|
-
train: join(intermediateDir, "labeled-train.jsonl"),
|
|
118
|
-
val: join(intermediateDir, "labeled-val.jsonl"),
|
|
119
|
-
test: join(intermediateDir, "labeled-test.jsonl"),
|
|
120
|
-
};
|
|
121
|
-
const labeledStreams = {
|
|
122
|
-
train: createWriteStream(labeledPaths.train, { encoding: "utf8" }),
|
|
123
|
-
val: createWriteStream(labeledPaths.val, { encoding: "utf8" }),
|
|
124
|
-
test: createWriteStream(labeledPaths.test, { encoding: "utf8" }),
|
|
125
|
-
};
|
|
126
|
-
const quarantinePath = join(intermediateDir, "quarantine.jsonl");
|
|
127
|
-
const quarantineStream = createWriteStream(quarantinePath, { encoding: "utf8" });
|
|
128
|
-
let aligned = 0;
|
|
129
|
-
let quarantined = 0;
|
|
130
|
-
const counts = { train: 0, val: 0, test: 0 };
|
|
131
|
-
const holdouts = defaultHoldouts();
|
|
132
|
-
// License accounting + the deliberate exclusion filter (#26). `licenseCounts` is the resolved
|
|
133
|
-
// license set (→ manifest + model-card attribution); `excludeLicenses` (empty by default → include
|
|
134
|
-
// everything) is the operator's PURPOSEFUL exclusion, never a silent drop.
|
|
135
|
-
const excludeLicenses = opts.excludeLicenses ?? [];
|
|
136
|
-
const licenseCounts = new Map();
|
|
137
|
-
let excludedByLicense = 0;
|
|
138
|
-
const writeQuarantine = (row, reason) => {
|
|
139
|
-
quarantineStream.write(`${JSON.stringify({ row, reason })}\n`);
|
|
140
|
-
};
|
|
141
|
-
for (const adapterRun of adapterRuns) {
|
|
142
|
-
opts.onProgress?.("align", `aligning ${adapterRun.adapter_id}`);
|
|
143
|
-
for await (const row of streamJSONL(adapterRun.jsonl_path)) {
|
|
144
|
-
licenseCounts.set(row.license, (licenseCounts.get(row.license) ?? 0) + 1);
|
|
145
|
-
// Deliberate license exclusion (#26): drop a row ONLY when the operator named its license
|
|
146
|
-
// kind via `excludeLicenses`. Default (no patterns) keeps everything — exclusion is a
|
|
147
|
-
// purposeful act, not a silent default. Counted BEFORE the drop so the manifest's license
|
|
148
|
-
// set reflects what the corpus actually CONTAINED, and `excluded_by_license` what was cut.
|
|
149
|
-
if (licenseExcluded(row.license, excludeLicenses)) {
|
|
150
|
-
excludedByLicense++;
|
|
151
|
-
continue;
|
|
152
|
-
}
|
|
153
|
-
const fanned = [row];
|
|
154
|
-
if (synthesize) {
|
|
155
|
-
for (const aug of synthesizeRow(row, defaultAugmentationsForCountry(row.country))) {
|
|
156
|
-
fanned.push(aug);
|
|
157
|
-
}
|
|
158
|
-
}
|
|
159
|
-
for (const r of fanned) {
|
|
160
|
-
let result;
|
|
161
|
-
try {
|
|
162
|
-
result = alignRow(r);
|
|
163
|
-
}
|
|
164
|
-
catch (error) {
|
|
165
|
-
// Last-resort robustness (2026-06-12): no single row may crash a multi-hour build.
|
|
166
|
-
// alignRow's targeted paths normalize/quarantine known issues with specific reasons;
|
|
167
|
-
// this catches any UNKNOWN throw (e.g. assertSpanInvariants on an unforeseen span
|
|
168
|
-
// shape) → quarantine + continue. A spike in `align-threw` reasons is a finding.
|
|
169
|
-
writeQuarantine(r, `align-threw:${error.message.slice(0, 160)}`);
|
|
170
|
-
quarantined++;
|
|
171
|
-
continue;
|
|
172
|
-
}
|
|
173
|
-
if (result.kind === "labeled") {
|
|
174
|
-
const split = splitForRow(result.row, holdouts);
|
|
175
|
-
labeledStreams[split].write(`${JSON.stringify(result.row)}\n`);
|
|
176
|
-
counts[split]++;
|
|
177
|
-
aligned++;
|
|
178
|
-
}
|
|
179
|
-
else {
|
|
180
|
-
writeQuarantine(r, result.row.reason);
|
|
181
|
-
quarantined++;
|
|
182
|
-
}
|
|
183
|
-
}
|
|
184
|
-
}
|
|
185
|
-
}
|
|
186
|
-
for (const s of Object.values(labeledStreams)) {
|
|
187
|
-
s.end();
|
|
188
|
-
}
|
|
189
|
-
quarantineStream.end();
|
|
190
|
-
await Promise.all([...Object.values(labeledStreams).map(streamEnd), streamEnd(quarantineStream)]);
|
|
191
|
-
// 4. Splits — manifest derived by streaming the per-split labeled files; no in-memory
|
|
192
|
-
// source-id arrays. `sort(1)` from coreutils produces the deterministic per-split .txt
|
|
193
|
-
// manifests with disk spill for splits that exceed in-memory thresholds.
|
|
194
|
-
opts.onProgress?.("split", `splitting ${aligned} aligned rows`);
|
|
195
|
-
const splitsDir = join(opts.outputDir, "splits");
|
|
196
|
-
const splitCounts = await writeSplitManifestsFromLabeledFiles({
|
|
197
|
-
labeledPaths,
|
|
198
|
-
outputDir: splitsDir,
|
|
199
|
-
corpusVersion: opts.corpusVersion,
|
|
200
|
-
counts,
|
|
201
|
-
holdouts,
|
|
202
|
-
});
|
|
203
|
-
// 5. Parquet shards — per-split labeled JSONL streams in, sharded `.parquet` out. The prior
|
|
204
|
-
// `splitFor(source_id)` callback (and the `Map<source_id, SplitName>` behind it) is gone.
|
|
205
|
-
opts.onProgress?.("shard", "writing parquet shards");
|
|
206
|
-
const shardManifest = await writeShards({
|
|
207
|
-
train: streamJSONL(labeledPaths.train),
|
|
208
|
-
val: streamJSONL(labeledPaths.val),
|
|
209
|
-
test: streamJSONL(labeledPaths.test),
|
|
210
|
-
}, {
|
|
211
|
-
outputDir: opts.outputDir,
|
|
212
|
-
corpusVersion: opts.corpusVersion,
|
|
213
|
-
rowsPerShard,
|
|
214
|
-
});
|
|
215
|
-
// License-set visibility (#26): loudly report the resolved license set so a build is an obvious
|
|
216
|
-
// deliberate act — especially a proprietary-weights build (did you pass --exclude-share-alike?).
|
|
217
|
-
const licenseSummary = [...licenseCounts.entries()].toSorted((a, b) => b[1] - a[1]);
|
|
218
|
-
opts.onProgress?.("manifest", `license set: ${licenseSummary.map(([l, c]) => `${l}=${c}`).join(", ")}` +
|
|
219
|
-
(excludedByLicense > 0
|
|
220
|
-
? ` | EXCLUDED ${excludedByLicense} rows by --exclude-licenses`
|
|
221
|
-
: " | NO license exclusion applied (all rows kept)"));
|
|
222
|
-
// 6. Top-level manifest.
|
|
223
|
-
opts.onProgress?.("manifest", "writing top-level MANIFEST.json");
|
|
224
|
-
const manifest = {
|
|
225
|
-
corpus_version: opts.corpusVersion,
|
|
226
|
-
built_at,
|
|
227
|
-
adapters: adapterRuns,
|
|
228
|
-
skipped_adapters: skipped,
|
|
229
|
-
splits: { counts: splitCounts, holdouts },
|
|
230
|
-
shards: { counts: shardManifest.counts, total_rows: shardManifest.total_rows },
|
|
231
|
-
quarantine_count: quarantined,
|
|
232
|
-
total_aligned_rows: aligned,
|
|
233
|
-
licenses: Object.fromEntries(licenseSummary),
|
|
234
|
-
excluded_by_license: excludedByLicense,
|
|
235
|
-
};
|
|
236
|
-
await writeFile(join(opts.outputDir, "MANIFEST.json"), `${JSON.stringify(manifest, null, 2)}\n`, "utf8");
|
|
237
|
-
return manifest;
|
|
238
|
-
}
|
|
239
|
-
async function* streamJSONL(path) {
|
|
240
|
-
// JSONSpliterator yields already-parsed rows (skipEmpty is on by default, so blank
|
|
241
|
-
// lines are dropped at the row level) and throws SyntaxError on a malformed row —
|
|
242
|
-
// same fail-loud behavior as the prior readline + bare `JSON.parse`.
|
|
243
|
-
yield* JSONSpliterator.fromAsync(path);
|
|
244
|
-
}
|
|
245
|
-
function streamEnd(s) {
|
|
246
|
-
return new Promise((resolve, reject) => {
|
|
247
|
-
s.once("close", resolve);
|
|
248
|
-
s.once("error", reject);
|
|
249
|
-
});
|
|
250
|
-
}
|
|
251
|
-
//# sourceMappingURL=build.js.map
|
package/out/src/build.js.map
DELETED
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"build.js","sourceRoot":"","sources":["../../src/build.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA+CG;AAEH,OAAO,EAAE,iBAAiB,EAAE,UAAU,EAAE,YAAY,EAAoB,MAAM,SAAS,CAAA;AACvF,OAAO,EAAE,KAAK,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAA;AACnD,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAEhC,OAAO,EAAE,OAAO,EAAE,MAAM,qBAAqB,CAAA;AAC7C,OAAO,EAAE,eAAe,EAAE,MAAM,yBAAyB,CAAA;AACzD,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C,OAAO,EAAE,sBAAsB,EAAE,MAAM,iBAAiB,CAAA;AACxD,OAAO,EAAE,UAAU,EAA2B,MAAM,SAAS,CAAA;AAC7D,OAAO,EAAE,8BAA8B,EAAE,aAAa,EAAE,MAAM,qBAAqB,CAAA;AAEnF,OAAO,EAAE,QAAQ,EAAE,MAAM,cAAc,CAAA;AACvC,OAAO,EAAE,eAAe,EAAE,MAAM,gBAAgB,CAAA;AAChD,OAAO,EAAE,WAAW,EAAsB,MAAM,gBAAgB,CAAA;AAChE,OAAO,EACN,eAAe,EACf,WAAW,EACX,mCAAmC,GAGnC,MAAM,cAAc,CAAA;AA6ErB;;;;;;GAMG;AACH,MAAM,CAAC,KAAK,UAAU,WAAW,CAAC,IAAwB;IACzD,MAAM,QAAQ,GAAG,IAAI,CAAC,QAAQ,IAAI,sBAAsB,CAAC,IAAI,EAAE,CAAA;IAC/D,MAAM,UAAU,GAAG,IAAI,CAAC,UAAU,IAAI,IAAI,CAAA;IAC1C,MAAM,YAAY,GAAG,IAAI,CAAC,YAAY,IAAI,SAAS,CAAA;IACnD,MAAM,QAAQ,GAAG,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE,CAAA;IAEzC,MAAM,KAAK,CAAC,IAAI,CAAC,SAAS,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;IAChD,MAAM,eAAe,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,cAAc,CAAC,CAAA;IAC5D,MAAM,KAAK,CAAC,eAAe,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;IAEjD,mBAAmB;IACnB,MAAM,WAAW,GAAyB,EAAE,CAAA;IAC5C,MAAM,OAAO,GAAa,EAAE,CAAA;IAE5B,KAAK,MAAM,OAAO,IAAI,QAAQ,EAAE,CAAC;QAChC,MAAM,cAAc,GAAG,IAAI,CAAC,aAAa,CAAC,OAAO,CAAC,EAAE,CAAC,CAAA;QAErD,IAAI,CAAC,cAAc,EAAE,CAAC;YACrB,OAAO,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE,CAAC,CAAA;YACxB,IAAI,CAAC,UAAU,EAAE,CAAC,aAAa,EAAE,WAAW,OAAO,CAAC,EAAE,wBAAwB,CAAC,CAAA;YAE/E,SAAQ;QACT,CAAC;QAED,gGAAgG;QAChG,2FAA2F;QAC3F,+FAA+F;QAC/F,8FAA8F;QAC9F,sGAAsG;QACtG,MAAM,UAAU,GAAG,IAAI,CAAC,eAAe,EAAE,OAAO,CAAC,EAAE,CAAC,CAAA;QACpD,MAAM,cAAc,GAAG,IAAI,CAAC,UAAU,EAAE,eAAe,CAAC,CAAA;QAExD,IACC,OAAO,CAAC,gBAAgB,KAAK,GAAG;YAChC,UAAU,CAAC,cAAc,CAAC;YAC1B,UAAU,CAAC,IAAI,CAAC,UAAU,EAAE,iBAAiB,CAAC,CAAC,EAC9C,CAAC;YACF,MAAM,MAAM,GAAG,eAAe,CAAqB,YAAY,CAAC,cAAc,EAAE,MAAM,CAAC,CAAC,CAAA;YACxF,IAAI,CAAC,UAAU,EAAE,CAAC,aAAa,EAAE,WAAW,OAAO,CAAC,EAAE,YAAY,MAAM,CAAC,OAAO,kBAAkB,CAAC,CAAA;YACnG,WAAW,CAAC,IAAI,CAAC,MAAM,CAAC,CAAA;YAExB,SAAQ;QACT,CAAC;QAED,IAAI,CAAC,UAAU,EAAE,CAAC,aAAa,EAAE,WAAW,OAAO,CAAC,EAAE,EAAE,CAAC,CAAA;QAEzD,MAAM,CAAC,GAAG,MAAM,UAAU,CAAC;YAC1B,OAAO;YACP,cAAc;YACd,SAAS,EAAE,eAAe;YAC1B,aAAa,EAAE,IAAI,CAAC,aAAa;SACjC,CAAC,CAAA;QAEF,WAAW,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IACpB,CAAC;IAED,yFAAyF;IACzF,8FAA8F;IAC9F,0FAA0F;IAC1F,0FAA0F;IAC1F,0EAA0E;IAC1E,MAAM,YAAY,GAA8B;QAC/C,KAAK,EAAE,IAAI,CAAC,eAAe,EAAE,qBAAqB,CAAC;QACnD,GAAG,EAAE,IAAI,CAAC,eAAe,EAAE,mBAAmB,CAAC;QAC/C,IAAI,EAAE,IAAI,CAAC,eAAe,EAAE,oBAAoB,CAAC;KACjD,CAAA;IAED,MAAM,cAAc,GAAmC;QACtD,KAAK,EAAE,iBAAiB,CAAC,YAAY,CAAC,KAAK,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,CAAC;QAClE,GAAG,EAAE,iBAAiB,CAAC,YAAY,CAAC,GAAG,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,CAAC;QAC9D,IAAI,EAAE,iBAAiB,CAAC,YAAY,CAAC,IAAI,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,CAAC;KAChE,CAAA;IAED,MAAM,cAAc,GAAG,IAAI,CAAC,eAAe,EAAE,kBAAkB,CAAC,CAAA;IAChE,MAAM,gBAAgB,GAAG,iBAAiB,CAAC,cAAc,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,CAAC,CAAA;IAEhF,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,WAAW,GAAG,CAAC,CAAA;IACnB,MAAM,MAAM,GAA8B,EAAE,KAAK,EAAE,CAAC,EAAE,GAAG,EAAE,CAAC,EAAE,IAAI,EAAE,CAAC,EAAE,CAAA;IACvE,MAAM,QAAQ,GAAG,eAAe,EAAE,CAAA;IAClC,8FAA8F;IAC9F,mGAAmG;IACnG,2EAA2E;IAC3E,MAAM,eAAe,GAAG,IAAI,CAAC,eAAe,IAAI,EAAE,CAAA;IAClD,MAAM,aAAa,GAAG,IAAI,GAAG,EAAkB,CAAA;IAC/C,IAAI,iBAAiB,GAAG,CAAC,CAAA;IAEzB,MAAM,eAAe,GAAG,CAAC,GAAiB,EAAE,MAAc,EAAQ,EAAE;QACnE,gBAAgB,CAAC,KAAK,CAAC,GAAG,IAAI,CAAC,SAAS,CAAC,EAAE,GAAG,EAAE,MAAM,EAAE,CAAC,IAAI,CAAC,CAAA;IAC/D,CAAC,CAAA;IAED,KAAK,MAAM,UAAU,IAAI,WAAW,EAAE,CAAC;QACtC,IAAI,CAAC,UAAU,EAAE,CAAC,OAAO,EAAE,YAAY,UAAU,CAAC,UAAU,EAAE,CAAC,CAAA;QAE/D,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,WAAW,CAAe,UAAU,CAAC,UAAU,CAAC,EAAE,CAAC;YAC1E,aAAa,CAAC,GAAG,CAAC,GAAG,CAAC,OAAO,EAAE,CAAC,aAAa,CAAC,GAAG,CAAC,GAAG,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAA;YAEzE,0FAA0F;YAC1F,sFAAsF;YACtF,0FAA0F;YAC1F,2FAA2F;YAC3F,IAAI,eAAe,CAAC,GAAG,CAAC,OAAO,EAAE,eAAe,CAAC,EAAE,CAAC;gBACnD,iBAAiB,EAAE,CAAA;gBAEnB,SAAQ;YACT,CAAC;YAED,MAAM,MAAM,GAAmB,CAAC,GAAG,CAAC,CAAA;YAEpC,IAAI,UAAU,EAAE,CAAC;gBAChB,KAAK,MAAM,GAAG,IAAI,aAAa,CAAC,GAAG,EAAE,8BAA8B,CAAC,GAAG,CAAC,OAAO,CAAC,CAAC,EAAE,CAAC;oBACnF,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;gBACjB,CAAC;YACF,CAAC;YAED,KAAK,MAAM,CAAC,IAAI,MAAM,EAAE,CAAC;gBACxB,IAAI,MAAmC,CAAA;gBAEvC,IAAI,CAAC;oBACJ,MAAM,GAAG,QAAQ,CAAC,CAAC,CAAC,CAAA;gBACrB,CAAC;gBAAC,OAAO,KAAK,EAAE,CAAC;oBAChB,mFAAmF;oBACnF,qFAAqF;oBACrF,kFAAkF;oBAClF,iFAAiF;oBACjF,eAAe,CAAC,CAAC,EAAE,eAAgB,KAAe,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,EAAE,CAAC,CAAA;oBAE3E,WAAW,EAAE,CAAA;oBAEb,SAAQ;gBACT,CAAC;gBAED,IAAI,MAAM,CAAC,IAAI,KAAK,SAAS,EAAE,CAAC;oBAC/B,MAAM,KAAK,GAAG,WAAW,CAAC,MAAM,CAAC,GAAG,EAAE,QAAQ,CAAC,CAAA;oBAC/C,cAAc,CAAC,KAAK,CAAC,CAAC,KAAK,CAAC,GAAG,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;oBAE9D,MAAM,CAAC,KAAK,CAAC,EAAE,CAAA;oBAEf,OAAO,EAAE,CAAA;gBACV,CAAC;qBAAM,CAAC;oBACP,eAAe,CAAC,CAAC,EAAE,MAAM,CAAC,GAAG,CAAC,MAAM,CAAC,CAAA;oBAErC,WAAW,EAAE,CAAA;gBACd,CAAC;YACF,CAAC;QACF,CAAC;IACF,CAAC;IAED,KAAK,MAAM,CAAC,IAAI,MAAM,CAAC,MAAM,CAAC,cAAc,CAAC,EAAE,CAAC;QAC/C,CAAC,CAAC,GAAG,EAAE,CAAA;IACR,CAAC;IAED,gBAAgB,CAAC,GAAG,EAAE,CAAA;IACtB,MAAM,OAAO,CAAC,GAAG,CAAC,CAAC,GAAG,MAAM,CAAC,MAAM,CAAC,cAAc,CAAC,CAAC,GAAG,CAAC,SAAS,CAAC,EAAE,SAAS,CAAC,gBAAgB,CAAC,CAAC,CAAC,CAAA;IAEjG,sFAAsF;IACtF,uFAAuF;IACvF,yEAAyE;IACzE,IAAI,CAAC,UAAU,EAAE,CAAC,OAAO,EAAE,aAAa,OAAO,eAAe,CAAC,CAAA;IAC/D,MAAM,SAAS,GAAG,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,QAAQ,CAAC,CAAA;IAEhD,MAAM,WAAW,GAAG,MAAM,mCAAmC,CAAC;QAC7D,YAAY;QACZ,SAAS,EAAE,SAAS;QACpB,aAAa,EAAE,IAAI,CAAC,aAAa;QACjC,MAAM;QACN,QAAQ;KACR,CAAC,CAAA;IAEF,4FAA4F;IAC5F,0FAA0F;IAC1F,IAAI,CAAC,UAAU,EAAE,CAAC,OAAO,EAAE,wBAAwB,CAAC,CAAA;IAEpD,MAAM,aAAa,GAAG,MAAM,WAAW,CACtC;QACC,KAAK,EAAE,WAAW,CAAa,YAAY,CAAC,KAAK,CAAC;QAClD,GAAG,EAAE,WAAW,CAAa,YAAY,CAAC,GAAG,CAAC;QAC9C,IAAI,EAAE,WAAW,CAAa,YAAY,CAAC,IAAI,CAAC;KAChD,EACD;QACC,SAAS,EAAE,IAAI,CAAC,SAAS;QACzB,aAAa,EAAE,IAAI,CAAC,aAAa;QACjC,YAAY;KACZ,CACD,CAAA;IAED,gGAAgG;IAChG,iGAAiG;IACjG,MAAM,cAAc,GAAG,CAAC,GAAG,aAAa,CAAC,OAAO,EAAE,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAA;IAEnF,IAAI,CAAC,UAAU,EAAE,CAChB,UAAU,EACV,gBAAgB,cAAc,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE;QACvE,CAAC,iBAAiB,GAAG,CAAC;YACrB,CAAC,CAAC,eAAe,iBAAiB,6BAA6B;YAC/D,CAAC,CAAC,iDAAiD,CAAC,CACtD,CAAA;IAED,yBAAyB;IACzB,IAAI,CAAC,UAAU,EAAE,CAAC,UAAU,EAAE,iCAAiC,CAAC,CAAA;IAEhE,MAAM,QAAQ,GAAwB;QACrC,cAAc,EAAE,IAAI,CAAC,aAAa;QAClC,QAAQ;QACR,QAAQ,EAAE,WAAW;QACrB,gBAAgB,EAAE,OAAO;QACzB,MAAM,EAAE,EAAE,MAAM,EAAE,WAAW,EAAE,QAAQ,EAAE;QACzC,MAAM,EAAE,EAAE,MAAM,EAAE,aAAa,CAAC,MAAM,EAAE,UAAU,EAAE,aAAa,CAAC,UAAU,EAAE;QAC9E,gBAAgB,EAAE,WAAW;QAC7B,kBAAkB,EAAE,OAAO;QAC3B,QAAQ,EAAE,MAAM,CAAC,WAAW,CAAC,cAAc,CAAC;QAC5C,mBAAmB,EAAE,iBAAiB;KACtC,CAAA;IAED,MAAM,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,EAAE,eAAe,CAAC,EAAE,GAAG,IAAI,CAAC,SAAS,CAAC,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,MAAM,CAAC,CAAA;IAExG,OAAO,QAAQ,CAAA;AAChB,CAAC;AAED,KAAK,SAAS,CAAC,CAAC,WAAW,CAAI,IAAY;IAC1C,mFAAmF;IACnF,kFAAkF;IAClF,qEAAqE;IACrE,KAAK,CAAC,CAAC,eAAe,CAAC,SAAS,CAAI,IAAI,CAAC,CAAA;AAC1C,CAAC;AAED,SAAS,SAAS,CAAC,CAAc;IAChC,OAAO,IAAI,OAAO,CAAC,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE;QACtC,CAAC,CAAC,IAAI,CAAC,OAAO,EAAE,OAAO,CAAC,CAAA;QACxB,CAAC,CAAC,IAAI,CAAC,OAAO,EAAE,MAAM,CAAC,CAAA;IACxB,CAAC,CAAC,CAAA;AACH,CAAC"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"us-fips-state.d.ts","sourceRoot":"","sources":["../../../src/codex/us-fips-state.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;GAaG;AAEH;;GAEG;AACH,MAAM,WAAW,WAAW;IAC3B,YAAY,EAAE,MAAM,CAAA;IACpB,IAAI,EAAE,MAAM,CAAA;CACZ;AAED;;;GAGG;AACH,eAAO,MAAM,aAAa,EAAE,QAAQ,CAAC,MAAM,CAAC,MAAM,EAAE,WAAW,CAAC,CA0D9D,CAAA;AAEF;;GAEG;AACH,wBAAgB,eAAe,CAAC,OAAO,EAAE,MAAM,GAAG,IAAI,GAAG,SAAS,GAAG,WAAW,GAAG,IAAI,CAItF;AAED;;;GAGG;AACH,eAAO,MAAM,wBAAwB,EAAE,QAAQ,CAAC,MAAM,CAAC,MAAM,EAAE,WAAW,CAAC,CAE1E,CAAA;AAED;;;GAGG;AACH,wBAAgB,uBAAuB,CAAC,YAAY,EAAE,MAAM,GAAG,IAAI,GAAG,SAAS,GAAG,WAAW,GAAG,IAAI,CAInG"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"us-fips-state.js","sourceRoot":"","sources":["../../../src/codex/us-fips-state.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;GAaG;AAUH;;;GAGG;AACH,MAAM,CAAC,MAAM,aAAa,GAA0C,MAAM,CAAC,MAAM,CAAC;IACjF,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,SAAS,EAAE;IAC7C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE;IAC5C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,SAAS,EAAE;IAC7C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE;IAC9C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,YAAY,EAAE;IAChD,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE;IAC9C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,aAAa,EAAE;IACjD,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE;IAC9C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,sBAAsB,EAAE;IAC1D,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,SAAS,EAAE;IAC7C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,SAAS,EAAE;IAC7C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE;IAC5C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,OAAO,EAAE;IAC3C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE;IAC9C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,SAAS,EAAE;IAC7C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE;IAC1C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE;IAC5C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE;IAC9C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,WAAW,EAAE;IAC/C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,OAAO,EAAE;IAC3C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE;IAC9C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,eAAe,EAAE;IACnD,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE;IAC9C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,WAAW,EAAE;IAC/C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,aAAa,EAAE;IACjD,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE;IAC9C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,SAAS,EAAE;IAC7C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE;IAC9C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE;IAC5C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,eAAe,EAAE;IACnD,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,YAAY,EAAE;IAChD,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,YAAY,EAAE;IAChD,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE;IAC9C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,gBAAgB,EAAE;IACpD,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,cAAc,EAAE;IAClD,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE;IAC1C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE;IAC9C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE;IAC5C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,cAAc,EAAE;IAClD,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,cAAc,EAAE;IAClD,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,gBAAgB,EAAE;IACpD,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,cAAc,EAAE;IAClD,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,WAAW,EAAE;IAC/C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,OAAO,EAAE;IAC3C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE;IAC1C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,SAAS,EAAE;IAC7C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,UAAU,EAAE;IAC9C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,YAAY,EAAE;IAChD,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,eAAe,EAAE;IACnD,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,WAAW,EAAE;IAC/C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,SAAS,EAAE;IAC7C,cAAc;IACd,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,gBAAgB,EAAE;IACpD,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE;IAC1C,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,0BAA0B,EAAE;IAC9D,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,aAAa,EAAE;IACjD,IAAI,EAAE,EAAE,YAAY,EAAE,IAAI,EAAE,IAAI,EAAE,gBAAgB,EAAE;CACpD,CAAC,CAAA;AAEF;;GAEG;AACH,MAAM,UAAU,eAAe,CAAC,OAAkC;IACjE,IAAI,CAAC,OAAO;QAAE,OAAO,IAAI,CAAA;IAEzB,OAAO,aAAa,CAAC,OAAO,CAAC,IAAI,IAAI,CAAA;AACtC,CAAC;AAED;;;GAGG;AACH,MAAM,CAAC,MAAM,wBAAwB,GAA0C,MAAM,CAAC,MAAM,CAC3F,MAAM,CAAC,WAAW,CAAC,MAAM,CAAC,MAAM,CAAC,aAAa,CAAC,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,IAAI,CAAC,YAAY,EAAE,IAAI,CAAC,CAAC,CAAC,CACzF,CAAA;AAED;;;GAGG;AACH,MAAM,UAAU,uBAAuB,CAAC,YAAuC;IAC9E,IAAI,CAAC,YAAY;QAAE,OAAO,IAAI,CAAA;IAE9B,OAAO,wBAAwB,CAAC,YAAY,CAAC,WAAW,EAAE,CAAC,IAAI,IAAI,CAAA;AACpE,CAAC"}
|
package/out/src/index.d.ts
DELETED
|
@@ -1,14 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*/
|
|
6
|
-
export * from "./adapters/utils/index.ts";
|
|
7
|
-
export * from "./adapters/gnaf/assemble.ts";
|
|
8
|
-
export * from "./adapters/index.ts";
|
|
9
|
-
export * from "./build.ts";
|
|
10
|
-
export * from "./runner.ts";
|
|
11
|
-
export * from "./parquet-wrapper/index.ts";
|
|
12
|
-
export * from "./shard-recipes/index.ts";
|
|
13
|
-
export * from "#types";
|
|
14
|
-
//# sourceMappingURL=index.d.ts.map
|
package/out/src/index.d.ts.map
DELETED
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../src/index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,cAAc,2BAA2B,CAAA;AACzC,cAAc,6BAA6B,CAAA;AAC3C,cAAc,qBAAqB,CAAA;AACnC,cAAc,YAAY,CAAA;AAC1B,cAAc,aAAa,CAAA;AAC3B,cAAc,4BAA4B,CAAA;AAC1C,cAAc,0BAA0B,CAAA;AACxC,cAAc,QAAQ,CAAA"}
|
package/out/src/index.js
DELETED
|
@@ -1,14 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*/
|
|
6
|
-
export * from "./adapters/utils/index.js";
|
|
7
|
-
export * from "./adapters/gnaf/assemble.js";
|
|
8
|
-
export * from "./adapters/index.js";
|
|
9
|
-
export * from "./build.js";
|
|
10
|
-
export * from "./runner.js";
|
|
11
|
-
export * from "./parquet-wrapper/index.js";
|
|
12
|
-
export * from "./shard-recipes/index.js";
|
|
13
|
-
export * from "#types";
|
|
14
|
-
//# sourceMappingURL=index.js.map
|
package/out/src/index.js.map
DELETED
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,cAAc,2BAA2B,CAAA;AACzC,cAAc,6BAA6B,CAAA;AAC3C,cAAc,qBAAqB,CAAA;AACnC,cAAc,YAAY,CAAA;AAC1B,cAAc,aAAa,CAAA;AAC3B,cAAc,4BAA4B,CAAA;AAC1C,cAAc,0BAA0B,CAAA;AACxC,cAAc,QAAQ,CAAA"}
|
|
@@ -1,12 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Re-export shim: the name-prone set moved to `@mailwoman/codex/us` (data in
|
|
7
|
-
* `codex/us/street-suffix.json`, 2026-08-10) so the golden relabel flags, the #1569 shard
|
|
8
|
-
* recipe, AND the Python relabel pass (via the `gazetteer affix-relabel` v2 lexicon) all read
|
|
9
|
-
* one record. Import from `@mailwoman/codex/us` in new code.
|
|
10
|
-
*/
|
|
11
|
-
export { NAME_PRONE_US_SUFFIXES } from "@mailwoman/codex/us";
|
|
12
|
-
//# sourceMappingURL=name-prone-us-suffixes.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"name-prone-us-suffixes.d.ts","sourceRoot":"","sources":["../../src/name-prone-us-suffixes.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAEH,OAAO,EAAE,sBAAsB,EAAE,MAAM,qBAAqB,CAAA"}
|
|
@@ -1,12 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Re-export shim: the name-prone set moved to `@mailwoman/codex/us` (data in
|
|
7
|
-
* `codex/us/street-suffix.json`, 2026-08-10) so the golden relabel flags, the #1569 shard
|
|
8
|
-
* recipe, AND the Python relabel pass (via the `gazetteer affix-relabel` v2 lexicon) all read
|
|
9
|
-
* one record. Import from `@mailwoman/codex/us` in new code.
|
|
10
|
-
*/
|
|
11
|
-
export { NAME_PRONE_US_SUFFIXES } from "@mailwoman/codex/us";
|
|
12
|
-
//# sourceMappingURL=name-prone-us-suffixes.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"name-prone-us-suffixes.js","sourceRoot":"","sources":["../../src/name-prone-us-suffixes.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAEH,OAAO,EAAE,sBAAsB,EAAE,MAAM,qBAAqB,CAAA"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/parquet-wrapper/index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,cAAc,aAAa,CAAA;AAC3B,cAAc,aAAa,CAAA;AAC3B,cAAc,aAAa,CAAA"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/parquet-wrapper/index.ts"],"names":[],"mappings":"AAAA;;;;GAIG;AAEH,cAAc,aAAa,CAAA;AAC3B,cAAc,aAAa,CAAA;AAC3B,cAAc,aAAa,CAAA"}
|
|
@@ -1,34 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Typed wrapper around `@dsnp/parquetjs`'s `ParquetReader` that narrows the row-iterator generic to
|
|
7
|
-
* a user-supplied record type and adds `AsyncDisposable` support so `await using` cleans up the
|
|
8
|
-
* envelope reader without an explicit `close()`.
|
|
9
|
-
*/
|
|
10
|
-
import { ParquetReader as BaseParquetReader } from "@dsnp/parquetjs";
|
|
11
|
-
import type { BufferReaderOptions } from "@dsnp/parquetjs/dist/lib/bufferReader.js";
|
|
12
|
-
import { ParquetEnvelopeReader } from "@dsnp/parquetjs/dist/lib/reader.js";
|
|
13
|
-
import type { ParquetSchema, ParquetRecordLike } from "./schema.ts";
|
|
14
|
-
/**
|
|
15
|
-
* A typed Parquet reader, wrapping the base Parquet reader.
|
|
16
|
-
*/
|
|
17
|
-
export declare class ParquetReader<T extends ParquetRecordLike> extends BaseParquetReader implements AsyncDisposable {
|
|
18
|
-
schema: ParquetSchema<T>;
|
|
19
|
-
static openFile<T extends ParquetRecordLike>(filePath: string | URL, options?: BufferReaderOptions): Promise<ParquetReader<T>>;
|
|
20
|
-
static openBuffer<T extends ParquetRecordLike>(buffer: Buffer, options?: BufferReaderOptions): Promise<ParquetReader<T>>;
|
|
21
|
-
static openEnvelopeReader<T extends ParquetRecordLike>(envelopeReader: ParquetEnvelopeReader, opts?: BufferReaderOptions): Promise<ParquetReader<T>>;
|
|
22
|
-
[Symbol.asyncIterator](): AsyncGenerator<T, void, unknown>;
|
|
23
|
-
/**
|
|
24
|
-
* Iterate a subset of the columns, narrowed to the keys asked for.
|
|
25
|
-
*
|
|
26
|
-
* Parquet is columnar, so a projection is read avoided rather than read-then-discarded: on a 14-column corpus shard,
|
|
27
|
-
* two columns cost 93 ms against 253 ms for the whole row. The default iterator reads every column, which is what a
|
|
28
|
-
* caller wanting the whole record should use.
|
|
29
|
-
*/
|
|
30
|
-
project<K extends keyof T>(...columns: K[]): AsyncGenerator<Pick<T, K>, void, unknown>;
|
|
31
|
-
[Symbol.asyncDispose](): Promise<void>;
|
|
32
|
-
dispose(): Promise<void>;
|
|
33
|
-
}
|
|
34
|
-
//# sourceMappingURL=reader.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"reader.d.ts","sourceRoot":"","sources":["../../../src/parquet-wrapper/reader.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAEH,OAAO,EAAE,aAAa,IAAI,iBAAiB,EAAE,MAAM,iBAAiB,CAAA;AACpE,OAAO,KAAK,EAAE,mBAAmB,EAAE,MAAM,0CAA0C,CAAA;AACnF,OAAO,EAAE,qBAAqB,EAAE,MAAM,oCAAoC,CAAA;AAE1E,OAAO,KAAK,EAAE,aAAa,EAAE,iBAAiB,EAAE,MAAM,aAAa,CAAA;AAEnE;;GAEG;AACH,qBAAa,aAAa,CAAC,CAAC,SAAS,iBAAiB,CAAE,SAAQ,iBAAkB,YAAW,eAAe;IACnG,MAAM,EAAE,aAAa,CAAC,CAAC,CAAC,CAAA;WAEV,QAAQ,CAAC,CAAC,SAAS,iBAAiB,EACzD,QAAQ,EAAE,MAAM,GAAG,GAAG,EACtB,OAAO,CAAC,EAAE,mBAAmB,GAC3B,OAAO,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC;WAMN,UAAU,CAAC,CAAC,SAAS,iBAAiB,EAAE,MAAM,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,mBAAmB;WAMrF,kBAAkB,CAAC,CAAC,SAAS,iBAAiB,EACnE,cAAc,EAAE,qBAAqB,EACrC,IAAI,CAAC,EAAE,mBAAmB;IAkBX,CAAC,MAAM,CAAC,aAAa,CAAC,IAAI,cAAc,CAAC,CAAC,EAAE,IAAI,EAAE,OAAO,CAAC;IAI1E;;;;;;OAMG;IACW,OAAO,CAAC,CAAC,SAAS,MAAM,CAAC,EAAE,GAAG,OAAO,EAAE,CAAC,EAAE,GAAG,cAAc,CAAC,IAAI,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,IAAI,EAAE,OAAO,CAAC;IAqBvF,CAAC,MAAM,CAAC,YAAY,CAAC;IAIrB,OAAO;CAGpB"}
|
|
@@ -1,69 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Typed wrapper around `@dsnp/parquetjs`'s `ParquetReader` that narrows the row-iterator generic to
|
|
7
|
-
* a user-supplied record type and adds `AsyncDisposable` support so `await using` cleans up the
|
|
8
|
-
* envelope reader without an explicit `close()`.
|
|
9
|
-
*/
|
|
10
|
-
import { ParquetReader as BaseParquetReader } from "@dsnp/parquetjs";
|
|
11
|
-
import { ParquetEnvelopeReader } from "@dsnp/parquetjs/dist/lib/reader.js";
|
|
12
|
-
/**
|
|
13
|
-
* A typed Parquet reader, wrapping the base Parquet reader.
|
|
14
|
-
*/
|
|
15
|
-
export class ParquetReader extends BaseParquetReader {
|
|
16
|
-
static async openFile(filePath, options) {
|
|
17
|
-
const envelopeReader = await ParquetEnvelopeReader.openFile(filePath.toString(), options);
|
|
18
|
-
return ParquetReader.openEnvelopeReader(envelopeReader, options);
|
|
19
|
-
}
|
|
20
|
-
static async openBuffer(buffer, options) {
|
|
21
|
-
const envelopeReader = await ParquetEnvelopeReader.openBuffer(buffer, options);
|
|
22
|
-
return this.openEnvelopeReader(envelopeReader, options);
|
|
23
|
-
}
|
|
24
|
-
static async openEnvelopeReader(envelopeReader, opts) {
|
|
25
|
-
if (opts?.metadata) {
|
|
26
|
-
return new ParquetReader(opts.metadata, envelopeReader, opts);
|
|
27
|
-
}
|
|
28
|
-
try {
|
|
29
|
-
await envelopeReader.readHeader();
|
|
30
|
-
const metadata = await envelopeReader.readFooter();
|
|
31
|
-
return new ParquetReader(metadata, envelopeReader, opts);
|
|
32
|
-
}
|
|
33
|
-
catch (error) {
|
|
34
|
-
await envelopeReader.close();
|
|
35
|
-
throw error;
|
|
36
|
-
}
|
|
37
|
-
}
|
|
38
|
-
[Symbol.asyncIterator]() {
|
|
39
|
-
return super[Symbol.asyncIterator]();
|
|
40
|
-
}
|
|
41
|
-
/**
|
|
42
|
-
* Iterate a subset of the columns, narrowed to the keys asked for.
|
|
43
|
-
*
|
|
44
|
-
* Parquet is columnar, so a projection is read avoided rather than read-then-discarded: on a 14-column corpus shard,
|
|
45
|
-
* two columns cost 93 ms against 253 ms for the whole row. The default iterator reads every column, which is what a
|
|
46
|
-
* caller wanting the whole record should use.
|
|
47
|
-
*/
|
|
48
|
-
async *project(...columns) {
|
|
49
|
-
const missing = columns.filter((column) => !Object.hasOwn(this.schema.schema, column));
|
|
50
|
-
if (missing.length) {
|
|
51
|
-
throw new Error(`Parquet projection requested column${missing.length === 1 ? "" : "s"} absent from the file schema: ` +
|
|
52
|
-
missing.map(String).join(", "));
|
|
53
|
-
}
|
|
54
|
-
const cursor = this.getCursor(columns.map((column) => [column]));
|
|
55
|
-
for (;;) {
|
|
56
|
-
const row = (await cursor.next());
|
|
57
|
-
if (!row)
|
|
58
|
-
return;
|
|
59
|
-
yield row;
|
|
60
|
-
}
|
|
61
|
-
}
|
|
62
|
-
async [Symbol.asyncDispose]() {
|
|
63
|
-
return this.close();
|
|
64
|
-
}
|
|
65
|
-
async dispose() {
|
|
66
|
-
return this[Symbol.asyncDispose]();
|
|
67
|
-
}
|
|
68
|
-
}
|
|
69
|
-
//# sourceMappingURL=reader.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"reader.js","sourceRoot":"","sources":["../../../src/parquet-wrapper/reader.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAEH,OAAO,EAAE,aAAa,IAAI,iBAAiB,EAAE,MAAM,iBAAiB,CAAA;AAEpE,OAAO,EAAE,qBAAqB,EAAE,MAAM,oCAAoC,CAAA;AAI1E;;GAEG;AACH,MAAM,OAAO,aAA2C,SAAQ,iBAAiB;IAGhF,MAAM,CAAU,KAAK,CAAC,QAAQ,CAC7B,QAAsB,EACtB,OAA6B;QAE7B,MAAM,cAAc,GAAG,MAAM,qBAAqB,CAAC,QAAQ,CAAC,QAAQ,CAAC,QAAQ,EAAE,EAAE,OAAO,CAAC,CAAA;QAEzF,OAAO,aAAa,CAAC,kBAAkB,CAAI,cAAc,EAAE,OAAO,CAAC,CAAA;IACpE,CAAC;IAED,MAAM,CAAU,KAAK,CAAC,UAAU,CAA8B,MAAc,EAAE,OAA6B;QAC1G,MAAM,cAAc,GAAG,MAAM,qBAAqB,CAAC,UAAU,CAAC,MAAM,EAAE,OAAO,CAAC,CAAA;QAE9E,OAAO,IAAI,CAAC,kBAAkB,CAAI,cAAc,EAAE,OAAO,CAAC,CAAA;IAC3D,CAAC;IAED,MAAM,CAAU,KAAK,CAAC,kBAAkB,CACvC,cAAqC,EACrC,IAA0B;QAE1B,IAAI,IAAI,EAAE,QAAQ,EAAE,CAAC;YACpB,OAAO,IAAI,aAAa,CAAI,IAAI,CAAC,QAAQ,EAAE,cAAc,EAAE,IAAI,CAAC,CAAA;QACjE,CAAC;QAED,IAAI,CAAC;YACJ,MAAM,cAAc,CAAC,UAAU,EAAE,CAAA;YAEjC,MAAM,QAAQ,GAAG,MAAM,cAAc,CAAC,UAAU,EAAE,CAAA;YAElD,OAAO,IAAI,aAAa,CAAI,QAAQ,EAAE,cAAc,EAAE,IAAI,CAAC,CAAA;QAC5D,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,MAAM,cAAc,CAAC,KAAK,EAAE,CAAA;YAC5B,MAAM,KAAK,CAAA;QACZ,CAAC;IACF,CAAC;IAEe,CAAC,MAAM,CAAC,aAAa,CAAC;QACrC,OAAO,KAAK,CAAC,MAAM,CAAC,aAAa,CAAC,EAAsC,CAAA;IACzE,CAAC;IAED;;;;;;OAMG;IACI,KAAK,CAAC,CAAC,OAAO,CAAoB,GAAG,OAAY;QACvD,MAAM,OAAO,GAAG,OAAO,CAAC,MAAM,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC,MAAM,CAAC,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC,CAAA;QAEtF,IAAI,OAAO,CAAC,MAAM,EAAE,CAAC;YACpB,MAAM,IAAI,KAAK,CACd,sCAAsC,OAAO,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,gCAAgC;gBACpG,OAAO,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAC/B,CAAA;QACF,CAAC;QAED,MAAM,MAAM,GAAG,IAAI,CAAC,SAAS,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC,MAAgB,CAAC,CAAC,CAAC,CAAA;QAE1E,SAAS,CAAC;YACT,MAAM,GAAG,GAAG,CAAC,MAAM,MAAM,CAAC,IAAI,EAAE,CAAsB,CAAA;YAEtD,IAAI,CAAC,GAAG;gBAAE,OAAM;YAEhB,MAAM,GAAG,CAAA;QACV,CAAC;IACF,CAAC;IAEM,KAAK,CAAC,CAAC,MAAM,CAAC,YAAY,CAAC;QACjC,OAAO,IAAI,CAAC,KAAK,EAAE,CAAA;IACpB,CAAC;IAEM,KAAK,CAAC,OAAO;QACnB,OAAO,IAAI,CAAC,MAAM,CAAC,YAAY,CAAC,EAAE,CAAA;IACnC,CAAC;CACD"}
|