@mailwoman/corpus 9.2.0 → 9.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +22 -22
- package/data/PROVENANCE.md +7 -7
- package/lib/adapters/ban/adapter.ts +190 -0
- package/lib/adapters/ban/street-decompose.ts +66 -0
- package/lib/adapters/fcc-bdc/adapter.ts +174 -0
- package/lib/adapters/geonames/adapter.ts +199 -0
- package/lib/adapters/geonames-postal/adapter.ts +122 -0
- package/lib/adapters/gnaf/adapter.ts +149 -0
- package/lib/adapters/gnaf/assemble.ts +225 -0
- package/lib/adapters/index.ts +153 -0
- package/lib/adapters/openaddresses/adapter.ts +251 -0
- package/lib/adapters/overture/adapter.ts +162 -0
- package/lib/adapters/state-hi-schools/adapter.ts +170 -0
- package/lib/adapters/state-hi-schools/workbook.ts +35 -0
- package/lib/adapters/synth-po-box/adapter.ts +204 -0
- package/lib/adapters/tiger/adapter.ts +252 -0
- package/lib/adapters/tiger/street-decompose.ts +83 -0
- package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +167 -0
- package/lib/adapters/usgov-imls-pls/adapter.ts +143 -0
- package/lib/adapters/usgov-irs-bmf/adapter.ts +151 -0
- package/lib/adapters/usgov-nad/adapter.ts +334 -0
- package/lib/adapters/usgov-nppes/adapter.ts +151 -0
- package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +193 -0
- package/lib/adapters/utils/index.ts +307 -0
- package/lib/adapters/wof-admin-jp/adapter.ts +214 -0
- package/lib/adapters/wof-admin-json/adapter.ts +231 -0
- package/lib/adapters/wof-json-rows.ts +129 -0
- package/lib/adapters/wof-postalcode-json/adapter.ts +176 -0
- package/lib/build.ts +378 -0
- package/lib/env.ts +50 -0
- package/lib/index.ts +13 -0
- package/lib/name-prone-us-suffixes.ts +12 -0
- package/lib/recipes/anchor-absorption.ts +101 -0
- package/lib/recipes/bare-country.ts +95 -0
- package/lib/recipes/boundary-stress.ts +100 -0
- package/lib/recipes/cn-organizational-units.ts +199 -0
- package/lib/recipes/country-balanced.ts +509 -0
- package/lib/recipes/cz-pcfirst-preposition.ts +111 -0
- package/lib/recipes/fr-admin-split.ts +242 -0
- package/lib/recipes/fr-bare-street.ts +170 -0
- package/lib/recipes/fr-fragment.ts +333 -0
- package/lib/recipes/fr-lieudit.ts +301 -0
- package/lib/recipes/fr-order.ts +245 -0
- package/lib/recipes/german.ts +359 -0
- package/lib/recipes/house-venue.ts +92 -0
- package/lib/recipes/index.ts +97 -0
- package/lib/recipes/intersection.ts +618 -0
- package/lib/recipes/locale.ts +599 -0
- package/lib/recipes/nl-postcode.ts +115 -0
- package/lib/recipes/no-fragment.ts +219 -0
- package/lib/recipes/no-street-led.ts +141 -0
- package/lib/recipes/no-street.ts +90 -0
- package/lib/recipes/po-box-cedex.ts +976 -0
- package/lib/recipes/po-box.ts +123 -0
- package/lib/recipes/reviewed-postcode-tail.ts +190 -0
- package/lib/recipes/scaffold.ts +469 -0
- package/lib/recipes/si-bare-village.ts +97 -0
- package/lib/recipes/street-affix.ts +804 -0
- package/lib/recipes/street-bare.ts +100 -0
- package/lib/recipes/street.ts +81 -0
- package/lib/recipes/sub-venue-sources.ts +877 -0
- package/lib/recipes/sub-venue.ts +997 -0
- package/lib/recipes/trailing-region.ts +183 -0
- package/lib/recipes/unit.ts +304 -0
- package/lib/runner.ts +312 -0
- package/lib/synthesizers/anchor-absorption.ts +288 -0
- package/lib/synthesizers/boundary-stress.ts +532 -0
- package/lib/synthesizers/german.ts +260 -0
- package/lib/synthesizers/house-venue.ts +308 -0
- package/lib/synthesizers/intersection.ts +233 -0
- package/lib/synthesizers/no-street.ts +327 -0
- package/lib/synthesizers/po-box.ts +323 -0
- package/lib/synthesizers/street.ts +269 -0
- package/lib/synthesizers/utils.ts +993 -0
- package/lib/test-kit/corpus-recipe.ts +86 -0
- package/lib/test-kit/index.ts +100 -0
- package/lib/tools/align-slice.ts +68 -0
- package/lib/tools/audit.ts +403 -0
- package/lib/tools/corpus-stats.ts +136 -0
- package/lib/tools/fetch/ban.ts +289 -0
- package/lib/tools/fetch/download.ts +262 -0
- package/lib/tools/fetch/geonames-dump.ts +257 -0
- package/lib/tools/fetch/geonames-postal.ts +180 -0
- package/lib/tools/fetch/hrsa.ts +59 -0
- package/lib/tools/fetch/imls-pls.ts +149 -0
- package/lib/tools/fetch/index.ts +147 -0
- package/lib/tools/fetch/nad.ts +341 -0
- package/lib/tools/fetch/nppes.ts +165 -0
- package/lib/tools/fetch/openaddresses.ts +347 -0
- package/lib/tools/fetch/ourairports.ts +170 -0
- package/lib/tools/fetch/ppd.ts +121 -0
- package/lib/tools/fetch/state-hi-schools.ts +161 -0
- package/lib/tools/fetch/state-sources.ts +146 -0
- package/lib/tools/fetch/tiger-full.ts +308 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +384 -0
- package/lib/tools/golden-expand.ts +574 -0
- package/lib/tools/golden-promote.ts +337 -0
- package/lib/tools/golden-relabel-street.ts +683 -0
- package/lib/tools/index.ts +28 -0
- package/lib/tools/ingest-csv.ts +378 -0
- package/lib/tools/jsonl-to-parquet.ts +207 -0
- package/lib/tools/lint-slice-vocab.ts +388 -0
- package/lib/tools/lint-slice.ts +496 -0
- package/lib/tools/overlay-manifest.ts +148 -0
- package/lib/tools/overture-subvenue.ts +209 -0
- package/lib/tools/postcode-triples.ts +363 -0
- package/lib/tools/slice-kryptonite.ts +137 -0
- package/lib/tools/slice-translit.ts +218 -0
- package/lib/tools/sub-venue/harvest.ts +234 -0
- package/lib/tools/sub-venue/head-nouns.ts +245 -0
- package/lib/tools/sub-venue/surfaces.ts +95 -0
- package/lib/tools/sub-venue/table.ts +281 -0
- package/lib/tools/sub-venue/wikidata.ts +85 -0
- package/lib/tools/sub-venue-lexicon.ts +429 -0
- package/lib/tools/sub-venue-promotions.ts +330 -0
- package/lib/types.ts +247 -0
- package/lib/utils/align.ts +330 -0
- package/lib/utils/golden.ts +189 -0
- package/lib/utils/index.ts +14 -0
- package/lib/utils/parquet.ts +582 -0
- package/lib/utils/slice-stats.ts +95 -0
- package/lib/utils/split.ts +279 -0
- package/lib/utils/tokenize.ts +120 -0
- package/lib/utils/wof-json.ts +247 -0
- package/out/adapters/ban/adapter.d.ts.map +1 -0
- package/out/adapters/ban/adapter.js +149 -0
- package/out/adapters/ban/adapter.js.map +1 -0
- package/out/adapters/ban/street-decompose.d.ts.map +1 -0
- package/out/adapters/ban/street-decompose.js +51 -0
- package/out/adapters/ban/street-decompose.js.map +1 -0
- package/out/adapters/fcc-bdc/adapter.d.ts.map +1 -0
- package/out/adapters/fcc-bdc/adapter.js +144 -0
- package/out/adapters/fcc-bdc/adapter.js.map +1 -0
- package/out/adapters/geonames/adapter.d.ts.map +1 -0
- package/out/adapters/geonames/adapter.js +176 -0
- package/out/adapters/geonames/adapter.js.map +1 -0
- package/out/adapters/geonames-postal/adapter.d.ts +54 -0
- package/out/adapters/geonames-postal/adapter.d.ts.map +1 -0
- package/out/adapters/geonames-postal/adapter.js +107 -0
- package/out/adapters/geonames-postal/adapter.js.map +1 -0
- package/out/adapters/gnaf/adapter.d.ts +49 -0
- package/out/adapters/gnaf/adapter.d.ts.map +1 -0
- package/out/adapters/gnaf/adapter.js +124 -0
- package/out/adapters/gnaf/adapter.js.map +1 -0
- package/out/adapters/gnaf/assemble.d.ts +65 -0
- package/out/adapters/gnaf/assemble.d.ts.map +1 -0
- package/out/adapters/gnaf/assemble.js +154 -0
- package/out/adapters/gnaf/assemble.js.map +1 -0
- package/out/adapters/index.d.ts +51 -0
- package/out/adapters/index.d.ts.map +1 -0
- package/out/adapters/index.js +95 -0
- package/out/adapters/index.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -0
- package/out/adapters/openaddresses/adapter.js +186 -0
- package/out/adapters/openaddresses/adapter.js.map +1 -0
- package/out/adapters/overture/adapter.d.ts +48 -0
- package/out/adapters/overture/adapter.d.ts.map +1 -0
- package/out/adapters/overture/adapter.js +125 -0
- package/out/adapters/overture/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/adapter.d.ts +46 -0
- package/out/adapters/state-hi-schools/adapter.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/adapter.js +145 -0
- package/out/adapters/state-hi-schools/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/workbook.d.ts +29 -0
- package/out/adapters/state-hi-schools/workbook.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/workbook.js +20 -0
- package/out/adapters/state-hi-schools/workbook.js.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
- package/out/adapters/synth-po-box/adapter.d.ts.map +1 -0
- package/out/adapters/synth-po-box/adapter.js +140 -0
- package/out/adapters/synth-po-box/adapter.js.map +1 -0
- package/out/adapters/tiger/adapter.d.ts +55 -0
- package/out/adapters/tiger/adapter.d.ts.map +1 -0
- package/out/adapters/tiger/adapter.js +201 -0
- package/out/adapters/tiger/adapter.js.map +1 -0
- package/out/adapters/tiger/street-decompose.d.ts.map +1 -0
- package/out/adapters/tiger/street-decompose.js +68 -0
- package/out/adapters/tiger/street-decompose.js.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +56 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js +132 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts +36 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.js +114 -0
- package/out/adapters/usgov-imls-pls/adapter.js.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts +37 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.js +120 -0
- package/out/adapters/usgov-irs-bmf/adapter.js.map +1 -0
- package/out/adapters/usgov-nad/adapter.d.ts +48 -0
- package/out/adapters/usgov-nad/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nad/adapter.js +249 -0
- package/out/adapters/usgov-nad/adapter.js.map +1 -0
- package/out/adapters/usgov-nppes/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nppes/adapter.js +118 -0
- package/out/adapters/usgov-nppes/adapter.js.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +154 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -0
- package/out/adapters/utils/index.d.ts +191 -0
- package/out/adapters/utils/index.d.ts.map +1 -0
- package/out/adapters/utils/index.js +206 -0
- package/out/adapters/utils/index.js.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.js +161 -0
- package/out/adapters/wof-admin-jp/adapter.js.map +1 -0
- package/out/adapters/wof-admin-json/adapter.d.ts +79 -0
- package/out/adapters/wof-admin-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-json/adapter.js +197 -0
- package/out/adapters/wof-admin-json/adapter.js.map +1 -0
- package/out/adapters/wof-json-rows.d.ts +62 -0
- package/out/adapters/wof-json-rows.d.ts.map +1 -0
- package/out/adapters/wof-json-rows.js +83 -0
- package/out/adapters/wof-json-rows.js.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts +65 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.js +151 -0
- package/out/adapters/wof-postalcode-json/adapter.js.map +1 -0
- package/out/build.d.ts +132 -0
- package/out/build.d.ts.map +1 -0
- package/out/build.js +245 -0
- package/out/build.js.map +1 -0
- package/out/codex/us-fips-state.d.ts.map +1 -0
- package/out/codex/us-fips-state.js.map +1 -0
- package/out/env.d.ts +46 -0
- package/out/env.d.ts.map +1 -0
- package/out/env.js +46 -0
- package/out/env.js.map +1 -0
- package/out/index.d.ts +13 -0
- package/out/index.d.ts.map +1 -0
- package/out/index.js +13 -0
- package/out/index.js.map +1 -0
- package/out/name-prone-us-suffixes.d.ts +12 -0
- package/out/name-prone-us-suffixes.d.ts.map +1 -0
- package/out/name-prone-us-suffixes.js +12 -0
- package/out/name-prone-us-suffixes.js.map +1 -0
- package/out/recipes/anchor-absorption.d.ts +20 -0
- package/out/recipes/anchor-absorption.d.ts.map +1 -0
- package/out/recipes/anchor-absorption.js +81 -0
- package/out/recipes/anchor-absorption.js.map +1 -0
- package/out/recipes/bare-country.d.ts +25 -0
- package/out/recipes/bare-country.d.ts.map +1 -0
- package/out/recipes/bare-country.js +87 -0
- package/out/recipes/bare-country.js.map +1 -0
- package/out/recipes/boundary-stress.d.ts +20 -0
- package/out/recipes/boundary-stress.d.ts.map +1 -0
- package/out/recipes/boundary-stress.js +83 -0
- package/out/recipes/boundary-stress.js.map +1 -0
- package/out/recipes/cn-organizational-units.d.ts +36 -0
- package/out/recipes/cn-organizational-units.d.ts.map +1 -0
- package/out/recipes/cn-organizational-units.js +159 -0
- package/out/recipes/cn-organizational-units.js.map +1 -0
- package/out/recipes/country-balanced.d.ts +32 -0
- package/out/recipes/country-balanced.d.ts.map +1 -0
- package/out/recipes/country-balanced.js +393 -0
- package/out/recipes/country-balanced.js.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts +22 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.js +100 -0
- package/out/recipes/cz-pcfirst-preposition.js.map +1 -0
- package/out/recipes/fr-admin-split.d.ts +38 -0
- package/out/recipes/fr-admin-split.d.ts.map +1 -0
- package/out/recipes/fr-admin-split.js +192 -0
- package/out/recipes/fr-admin-split.js.map +1 -0
- package/out/recipes/fr-bare-street.d.ts +28 -0
- package/out/recipes/fr-bare-street.d.ts.map +1 -0
- package/out/recipes/fr-bare-street.js +143 -0
- package/out/recipes/fr-bare-street.js.map +1 -0
- package/out/recipes/fr-fragment.d.ts +77 -0
- package/out/recipes/fr-fragment.d.ts.map +1 -0
- package/out/recipes/fr-fragment.js +276 -0
- package/out/recipes/fr-fragment.js.map +1 -0
- package/out/recipes/fr-lieudit.d.ts +32 -0
- package/out/recipes/fr-lieudit.d.ts.map +1 -0
- package/out/recipes/fr-lieudit.js +227 -0
- package/out/recipes/fr-lieudit.js.map +1 -0
- package/out/recipes/fr-order.d.ts +38 -0
- package/out/recipes/fr-order.d.ts.map +1 -0
- package/out/recipes/fr-order.js +197 -0
- package/out/recipes/fr-order.js.map +1 -0
- package/out/recipes/german.d.ts +44 -0
- package/out/recipes/german.d.ts.map +1 -0
- package/out/recipes/german.js +288 -0
- package/out/recipes/german.js.map +1 -0
- package/out/recipes/house-venue.d.ts +18 -0
- package/out/recipes/house-venue.d.ts.map +1 -0
- package/out/recipes/house-venue.js +73 -0
- package/out/recipes/house-venue.js.map +1 -0
- package/out/recipes/index.d.ts +24 -0
- package/out/recipes/index.d.ts.map +1 -0
- package/out/recipes/index.js +91 -0
- package/out/recipes/index.js.map +1 -0
- package/out/recipes/intersection.d.ts +42 -0
- package/out/recipes/intersection.d.ts.map +1 -0
- package/out/recipes/intersection.js +452 -0
- package/out/recipes/intersection.js.map +1 -0
- package/out/recipes/locale.d.ts +136 -0
- package/out/recipes/locale.d.ts.map +1 -0
- package/out/recipes/locale.js +460 -0
- package/out/recipes/locale.js.map +1 -0
- package/out/recipes/nl-postcode.d.ts +26 -0
- package/out/recipes/nl-postcode.d.ts.map +1 -0
- package/out/recipes/nl-postcode.js +102 -0
- package/out/recipes/nl-postcode.js.map +1 -0
- package/out/recipes/no-fragment.d.ts +43 -0
- package/out/recipes/no-fragment.d.ts.map +1 -0
- package/out/recipes/no-fragment.js +182 -0
- package/out/recipes/no-fragment.js.map +1 -0
- package/out/recipes/no-street-led.d.ts +24 -0
- package/out/recipes/no-street-led.d.ts.map +1 -0
- package/out/recipes/no-street-led.js +113 -0
- package/out/recipes/no-street-led.js.map +1 -0
- package/out/recipes/no-street.d.ts +18 -0
- package/out/recipes/no-street.d.ts.map +1 -0
- package/out/recipes/no-street.js +71 -0
- package/out/recipes/no-street.js.map +1 -0
- package/out/recipes/po-box-cedex.d.ts +38 -0
- package/out/recipes/po-box-cedex.d.ts.map +1 -0
- package/out/recipes/po-box-cedex.js +767 -0
- package/out/recipes/po-box-cedex.js.map +1 -0
- package/out/recipes/po-box.d.ts +17 -0
- package/out/recipes/po-box.d.ts.map +1 -0
- package/out/recipes/po-box.js +100 -0
- package/out/recipes/po-box.js.map +1 -0
- package/out/recipes/reviewed-postcode-tail.d.ts +47 -0
- package/out/recipes/reviewed-postcode-tail.d.ts.map +1 -0
- package/out/recipes/reviewed-postcode-tail.js +125 -0
- package/out/recipes/reviewed-postcode-tail.js.map +1 -0
- package/out/recipes/scaffold.d.ts +324 -0
- package/out/recipes/scaffold.d.ts.map +1 -0
- package/out/recipes/scaffold.js +186 -0
- package/out/recipes/scaffold.js.map +1 -0
- package/out/recipes/si-bare-village.d.ts +32 -0
- package/out/recipes/si-bare-village.d.ts.map +1 -0
- package/out/recipes/si-bare-village.js +88 -0
- package/out/recipes/si-bare-village.js.map +1 -0
- package/out/recipes/street-affix.d.ts +89 -0
- package/out/recipes/street-affix.d.ts.map +1 -0
- package/out/recipes/street-affix.js +563 -0
- package/out/recipes/street-affix.js.map +1 -0
- package/out/recipes/street-bare.d.ts +25 -0
- package/out/recipes/street-bare.d.ts.map +1 -0
- package/out/recipes/street-bare.js +86 -0
- package/out/recipes/street-bare.js.map +1 -0
- package/out/recipes/street.d.ts +15 -0
- package/out/recipes/street.d.ts.map +1 -0
- package/out/recipes/street.js +69 -0
- package/out/recipes/street.js.map +1 -0
- package/out/recipes/sub-venue-sources.d.ts +229 -0
- package/out/recipes/sub-venue-sources.d.ts.map +1 -0
- package/out/recipes/sub-venue-sources.js +653 -0
- package/out/recipes/sub-venue-sources.js.map +1 -0
- package/out/recipes/sub-venue.d.ts +269 -0
- package/out/recipes/sub-venue.d.ts.map +1 -0
- package/out/recipes/sub-venue.js +725 -0
- package/out/recipes/sub-venue.js.map +1 -0
- package/out/recipes/trailing-region.d.ts +74 -0
- package/out/recipes/trailing-region.d.ts.map +1 -0
- package/out/recipes/trailing-region.js +157 -0
- package/out/recipes/trailing-region.js.map +1 -0
- package/out/recipes/unit.d.ts +29 -0
- package/out/recipes/unit.d.ts.map +1 -0
- package/out/recipes/unit.js +230 -0
- package/out/recipes/unit.js.map +1 -0
- package/out/runner.d.ts +130 -0
- package/out/runner.d.ts.map +1 -0
- package/out/runner.js +185 -0
- package/out/runner.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +63 -0
- package/out/synthesizers/anchor-absorption.d.ts.map +1 -0
- package/out/synthesizers/anchor-absorption.js +221 -0
- package/out/synthesizers/anchor-absorption.js.map +1 -0
- package/out/synthesizers/boundary-stress.d.ts +78 -0
- package/out/synthesizers/boundary-stress.d.ts.map +1 -0
- package/out/synthesizers/boundary-stress.js +455 -0
- package/out/synthesizers/boundary-stress.js.map +1 -0
- package/out/synthesizers/german.d.ts +115 -0
- package/out/synthesizers/german.d.ts.map +1 -0
- package/out/synthesizers/german.js +149 -0
- package/out/synthesizers/german.js.map +1 -0
- package/out/synthesizers/house-venue.d.ts +56 -0
- package/out/synthesizers/house-venue.d.ts.map +1 -0
- package/out/synthesizers/house-venue.js +247 -0
- package/out/synthesizers/house-venue.js.map +1 -0
- package/out/synthesizers/intersection.d.ts +52 -0
- package/out/synthesizers/intersection.d.ts.map +1 -0
- package/out/synthesizers/intersection.js +175 -0
- package/out/synthesizers/intersection.js.map +1 -0
- package/out/synthesizers/no-street.d.ts +72 -0
- package/out/synthesizers/no-street.d.ts.map +1 -0
- package/out/synthesizers/no-street.js +262 -0
- package/out/synthesizers/no-street.js.map +1 -0
- package/out/synthesizers/po-box.d.ts +108 -0
- package/out/synthesizers/po-box.d.ts.map +1 -0
- package/out/synthesizers/po-box.js +250 -0
- package/out/synthesizers/po-box.js.map +1 -0
- package/out/synthesizers/street.d.ts +54 -0
- package/out/synthesizers/street.d.ts.map +1 -0
- package/out/synthesizers/street.js +218 -0
- package/out/synthesizers/street.js.map +1 -0
- package/out/synthesizers/utils.d.ts +241 -0
- package/out/synthesizers/utils.d.ts.map +1 -0
- package/out/synthesizers/utils.js +776 -0
- package/out/synthesizers/utils.js.map +1 -0
- package/out/test-kit/corpus-recipe.d.ts +59 -0
- package/out/test-kit/corpus-recipe.d.ts.map +1 -0
- package/out/test-kit/corpus-recipe.js +39 -0
- package/out/test-kit/corpus-recipe.js.map +1 -0
- package/out/test-kit/index.d.ts +48 -0
- package/out/test-kit/index.d.ts.map +1 -0
- package/out/test-kit/index.js +78 -0
- package/out/test-kit/index.js.map +1 -0
- package/out/tools/align-slice.d.ts +7 -0
- package/out/tools/align-slice.d.ts.map +1 -0
- package/out/tools/align-slice.js +55 -0
- package/out/tools/align-slice.js.map +1 -0
- package/out/tools/audit.d.ts +29 -0
- package/out/tools/audit.d.ts.map +1 -0
- package/out/tools/audit.js +282 -0
- package/out/tools/audit.js.map +1 -0
- package/out/tools/corpus-stats.d.ts +44 -0
- package/out/tools/corpus-stats.d.ts.map +1 -0
- package/out/tools/corpus-stats.js +102 -0
- package/out/tools/corpus-stats.js.map +1 -0
- package/out/tools/fetch/ban.d.ts +31 -0
- package/out/tools/fetch/ban.d.ts.map +1 -0
- package/out/tools/fetch/ban.js +239 -0
- package/out/tools/fetch/ban.js.map +1 -0
- package/out/tools/fetch/download.d.ts +117 -0
- package/out/tools/fetch/download.d.ts.map +1 -0
- package/out/tools/fetch/download.js +160 -0
- package/out/tools/fetch/download.js.map +1 -0
- package/out/tools/fetch/geonames-dump.d.ts +91 -0
- package/out/tools/fetch/geonames-dump.d.ts.map +1 -0
- package/out/tools/fetch/geonames-dump.js +171 -0
- package/out/tools/fetch/geonames-dump.js.map +1 -0
- package/out/tools/fetch/geonames-postal.d.ts +76 -0
- package/out/tools/fetch/geonames-postal.d.ts.map +1 -0
- package/out/tools/fetch/geonames-postal.js +126 -0
- package/out/tools/fetch/geonames-postal.js.map +1 -0
- package/out/tools/fetch/hrsa.d.ts +18 -0
- package/out/tools/fetch/hrsa.d.ts.map +1 -0
- package/out/tools/fetch/hrsa.js +46 -0
- package/out/tools/fetch/hrsa.js.map +1 -0
- package/out/tools/fetch/imls-pls.d.ts +25 -0
- package/out/tools/fetch/imls-pls.d.ts.map +1 -0
- package/out/tools/fetch/imls-pls.js +108 -0
- package/out/tools/fetch/imls-pls.js.map +1 -0
- package/out/tools/fetch/index.d.ts +144 -0
- package/out/tools/fetch/index.d.ts.map +1 -0
- package/out/tools/fetch/index.js +143 -0
- package/out/tools/fetch/index.js.map +1 -0
- package/out/tools/fetch/nad.d.ts +70 -0
- package/out/tools/fetch/nad.d.ts.map +1 -0
- package/out/tools/fetch/nad.js +234 -0
- package/out/tools/fetch/nad.js.map +1 -0
- package/out/tools/fetch/nppes.d.ts +26 -0
- package/out/tools/fetch/nppes.d.ts.map +1 -0
- package/out/tools/fetch/nppes.js +126 -0
- package/out/tools/fetch/nppes.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +9 -0
- package/out/tools/fetch/openaddresses.d.ts.map +1 -0
- package/out/tools/fetch/openaddresses.js +279 -0
- package/out/tools/fetch/openaddresses.js.map +1 -0
- package/out/tools/fetch/ourairports.d.ts +45 -0
- package/out/tools/fetch/ourairports.d.ts.map +1 -0
- package/out/tools/fetch/ourairports.js +128 -0
- package/out/tools/fetch/ourairports.js.map +1 -0
- package/out/tools/fetch/ppd.d.ts.map +1 -0
- package/out/tools/fetch/ppd.js +85 -0
- package/out/tools/fetch/ppd.js.map +1 -0
- package/out/tools/fetch/state-hi-schools.d.ts +26 -0
- package/out/tools/fetch/state-hi-schools.d.ts.map +1 -0
- package/out/tools/fetch/state-hi-schools.js +112 -0
- package/out/tools/fetch/state-hi-schools.js.map +1 -0
- package/out/tools/fetch/state-sources.d.ts +26 -0
- package/out/tools/fetch/state-sources.d.ts.map +1 -0
- package/out/tools/fetch/state-sources.js +111 -0
- package/out/tools/fetch/state-sources.js.map +1 -0
- package/out/tools/fetch/tiger-full.d.ts +22 -0
- package/out/tools/fetch/tiger-full.d.ts.map +1 -0
- package/out/tools/fetch/tiger-full.js +217 -0
- package/out/tools/fetch/tiger-full.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +171 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.js +274 -0
- package/out/tools/fetch/wikidata-subvenue.js.map +1 -0
- package/out/tools/gb-title-case.d.ts.map +1 -0
- package/out/tools/gb-title-case.js.map +1 -0
- package/out/tools/golden-expand.d.ts +90 -0
- package/out/tools/golden-expand.d.ts.map +1 -0
- package/out/tools/golden-expand.js +406 -0
- package/out/tools/golden-expand.js.map +1 -0
- package/out/tools/golden-promote.d.ts.map +1 -0
- package/out/tools/golden-promote.js +240 -0
- package/out/tools/golden-promote.js.map +1 -0
- package/out/tools/golden-relabel-street.d.ts +196 -0
- package/out/tools/golden-relabel-street.d.ts.map +1 -0
- package/out/tools/golden-relabel-street.js +440 -0
- package/out/tools/golden-relabel-street.js.map +1 -0
- package/out/tools/index.d.ts +28 -0
- package/out/tools/index.d.ts.map +1 -0
- package/out/tools/index.js +28 -0
- package/out/tools/index.js.map +1 -0
- package/out/tools/ingest-csv.d.ts.map +1 -0
- package/out/tools/ingest-csv.js +265 -0
- package/out/tools/ingest-csv.js.map +1 -0
- package/out/tools/jsonl-to-parquet.d.ts +61 -0
- package/out/tools/jsonl-to-parquet.d.ts.map +1 -0
- package/out/tools/jsonl-to-parquet.js +150 -0
- package/out/tools/jsonl-to-parquet.js.map +1 -0
- package/out/tools/lint-slice-vocab.d.ts +90 -0
- package/out/tools/lint-slice-vocab.d.ts.map +1 -0
- package/out/tools/lint-slice-vocab.js +267 -0
- package/out/tools/lint-slice-vocab.js.map +1 -0
- package/out/tools/lint-slice.d.ts +93 -0
- package/out/tools/lint-slice.d.ts.map +1 -0
- package/out/tools/lint-slice.js +322 -0
- package/out/tools/lint-slice.js.map +1 -0
- package/out/tools/overlay-manifest.d.ts +39 -0
- package/out/tools/overlay-manifest.d.ts.map +1 -0
- package/out/tools/overlay-manifest.js +90 -0
- package/out/tools/overlay-manifest.js.map +1 -0
- package/out/tools/overture-subvenue.d.ts +112 -0
- package/out/tools/overture-subvenue.d.ts.map +1 -0
- package/out/tools/overture-subvenue.js +139 -0
- package/out/tools/overture-subvenue.js.map +1 -0
- package/out/tools/postcode-triples.d.ts +174 -0
- package/out/tools/postcode-triples.d.ts.map +1 -0
- package/out/tools/postcode-triples.js +292 -0
- package/out/tools/postcode-triples.js.map +1 -0
- package/out/tools/slice-kryptonite.d.ts +32 -0
- package/out/tools/slice-kryptonite.d.ts.map +1 -0
- package/out/tools/slice-kryptonite.js +99 -0
- package/out/tools/slice-kryptonite.js.map +1 -0
- package/out/tools/slice-translit.d.ts +51 -0
- package/out/tools/slice-translit.d.ts.map +1 -0
- package/out/tools/slice-translit.js +166 -0
- package/out/tools/slice-translit.js.map +1 -0
- package/out/tools/sub-venue/harvest.d.ts +100 -0
- package/out/tools/sub-venue/harvest.d.ts.map +1 -0
- package/out/tools/sub-venue/harvest.js +168 -0
- package/out/tools/sub-venue/harvest.js.map +1 -0
- package/out/tools/sub-venue/head-nouns.d.ts +50 -0
- package/out/tools/sub-venue/head-nouns.d.ts.map +1 -0
- package/out/tools/sub-venue/head-nouns.js +213 -0
- package/out/tools/sub-venue/head-nouns.js.map +1 -0
- package/out/tools/sub-venue/surfaces.d.ts +45 -0
- package/out/tools/sub-venue/surfaces.d.ts.map +1 -0
- package/out/tools/sub-venue/surfaces.js +77 -0
- package/out/tools/sub-venue/surfaces.js.map +1 -0
- package/out/tools/sub-venue/table.d.ts +229 -0
- package/out/tools/sub-venue/table.d.ts.map +1 -0
- package/out/tools/sub-venue/table.js +108 -0
- package/out/tools/sub-venue/table.js.map +1 -0
- package/out/tools/sub-venue/wikidata.d.ts +26 -0
- package/out/tools/sub-venue/wikidata.d.ts.map +1 -0
- package/out/tools/sub-venue/wikidata.js +62 -0
- package/out/tools/sub-venue/wikidata.js.map +1 -0
- package/out/tools/sub-venue-lexicon.d.ts +156 -0
- package/out/tools/sub-venue-lexicon.d.ts.map +1 -0
- package/out/tools/sub-venue-lexicon.js +283 -0
- package/out/tools/sub-venue-lexicon.js.map +1 -0
- package/out/tools/sub-venue-promotions.d.ts +94 -0
- package/out/tools/sub-venue-promotions.d.ts.map +1 -0
- package/out/tools/sub-venue-promotions.js +266 -0
- package/out/tools/sub-venue-promotions.js.map +1 -0
- package/out/types.d.ts +221 -0
- package/out/types.d.ts.map +1 -0
- package/out/types.js.map +1 -0
- package/out/utils/align.d.ts +93 -0
- package/out/utils/align.d.ts.map +1 -0
- package/out/utils/align.js +234 -0
- package/out/utils/align.js.map +1 -0
- package/out/utils/golden.d.ts +85 -0
- package/out/utils/golden.d.ts.map +1 -0
- package/out/utils/golden.js +127 -0
- package/out/utils/golden.js.map +1 -0
- package/out/utils/index.d.ts +14 -0
- package/out/utils/index.d.ts.map +1 -0
- package/out/utils/index.js +14 -0
- package/out/utils/index.js.map +1 -0
- package/out/utils/license.d.ts.map +1 -0
- package/out/utils/license.js.map +1 -0
- package/out/utils/parquet.d.ts +178 -0
- package/out/utils/parquet.d.ts.map +1 -0
- package/out/utils/parquet.js +371 -0
- package/out/utils/parquet.js.map +1 -0
- package/out/utils/slice-stats.d.ts +52 -0
- package/out/utils/slice-stats.d.ts.map +1 -0
- package/out/utils/slice-stats.js +58 -0
- package/out/utils/slice-stats.js.map +1 -0
- package/out/utils/split.d.ts +128 -0
- package/out/utils/split.d.ts.map +1 -0
- package/out/utils/split.js +204 -0
- package/out/utils/split.js.map +1 -0
- package/out/utils/tokenize.d.ts +64 -0
- package/out/utils/tokenize.d.ts.map +1 -0
- package/out/utils/tokenize.js +82 -0
- package/out/utils/tokenize.js.map +1 -0
- package/out/utils/wof-json.d.ts +113 -0
- package/out/utils/wof-json.d.ts.map +1 -0
- package/out/utils/wof-json.js +173 -0
- package/out/utils/wof-json.js.map +1 -0
- package/package.json +259 -194
- package/out/src/adapters/ban/adapter.d.ts.map +0 -1
- package/out/src/adapters/ban/adapter.js +0 -149
- package/out/src/adapters/ban/adapter.js.map +0 -1
- package/out/src/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/ban/street-decompose.js +0 -75
- package/out/src/adapters/ban/street-decompose.js.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.d.ts.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.js +0 -144
- package/out/src/adapters/fcc-bdc/adapter.js.map +0 -1
- package/out/src/adapters/geonames/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames/adapter.js +0 -176
- package/out/src/adapters/geonames/adapter.js.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.d.ts +0 -41
- package/out/src/adapters/geonames-postal/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.js +0 -104
- package/out/src/adapters/geonames-postal/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/adapter.d.ts +0 -49
- package/out/src/adapters/gnaf/adapter.d.ts.map +0 -1
- package/out/src/adapters/gnaf/adapter.js +0 -124
- package/out/src/adapters/gnaf/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/assemble.d.ts +0 -65
- package/out/src/adapters/gnaf/assemble.d.ts.map +0 -1
- package/out/src/adapters/gnaf/assemble.js +0 -154
- package/out/src/adapters/gnaf/assemble.js.map +0 -1
- package/out/src/adapters/index.d.ts +0 -51
- package/out/src/adapters/index.d.ts.map +0 -1
- package/out/src/adapters/index.js +0 -95
- package/out/src/adapters/index.js.map +0 -1
- package/out/src/adapters/openaddresses/adapter.d.ts.map +0 -1
- package/out/src/adapters/openaddresses/adapter.js +0 -186
- package/out/src/adapters/openaddresses/adapter.js.map +0 -1
- package/out/src/adapters/overture/adapter.d.ts +0 -48
- package/out/src/adapters/overture/adapter.d.ts.map +0 -1
- package/out/src/adapters/overture/adapter.js +0 -125
- package/out/src/adapters/overture/adapter.js.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.d.ts +0 -47
- package/out/src/adapters/state-hi-schools/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.js +0 -133
- package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.d.ts.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.js +0 -140
- package/out/src/adapters/synth-po-box/adapter.js.map +0 -1
- package/out/src/adapters/tiger/adapter.d.ts +0 -55
- package/out/src/adapters/tiger/adapter.d.ts.map +0 -1
- package/out/src/adapters/tiger/adapter.js +0 -201
- package/out/src/adapters/tiger/adapter.js.map +0 -1
- package/out/src/adapters/tiger/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/tiger/street-decompose.js +0 -90
- package/out/src/adapters/tiger/street-decompose.js.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -47
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +0 -139
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts +0 -36
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.js +0 -114
- package/out/src/adapters/usgov-imls-pls/adapter.js.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.js +0 -124
- package/out/src/adapters/usgov-irs-bmf/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.d.ts +0 -48
- package/out/src/adapters/usgov-nad/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.js +0 -252
- package/out/src/adapters/usgov-nad/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.js +0 -116
- package/out/src/adapters/usgov-nppes/adapter.js.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -156
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
- package/out/src/adapters/utils/index.d.ts +0 -150
- package/out/src/adapters/utils/index.d.ts.map +0 -1
- package/out/src/adapters/utils/index.js +0 -159
- package/out/src/adapters/utils/index.js.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.js +0 -164
- package/out/src/adapters/wof-admin-jp/adapter.js.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.d.ts +0 -82
- package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.js +0 -224
- package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
- package/out/src/adapters/wof-json-rows.d.ts +0 -32
- package/out/src/adapters/wof-json-rows.d.ts.map +0 -1
- package/out/src/adapters/wof-json-rows.js +0 -45
- package/out/src/adapters/wof-json-rows.js.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -65
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.js +0 -160
- package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
- package/out/src/build.d.ts +0 -132
- package/out/src/build.d.ts.map +0 -1
- package/out/src/build.js +0 -251
- package/out/src/build.js.map +0 -1
- package/out/src/codex/us-fips-state.d.ts.map +0 -1
- package/out/src/codex/us-fips-state.js.map +0 -1
- package/out/src/index.d.ts +0 -14
- package/out/src/index.d.ts.map +0 -1
- package/out/src/index.js +0 -14
- package/out/src/index.js.map +0 -1
- package/out/src/name-prone-us-suffixes.d.ts +0 -12
- package/out/src/name-prone-us-suffixes.d.ts.map +0 -1
- package/out/src/name-prone-us-suffixes.js +0 -12
- package/out/src/name-prone-us-suffixes.js.map +0 -1
- package/out/src/parquet-wrapper/index.d.ts +0 -9
- package/out/src/parquet-wrapper/index.d.ts.map +0 -1
- package/out/src/parquet-wrapper/index.js +0 -9
- package/out/src/parquet-wrapper/index.js.map +0 -1
- package/out/src/parquet-wrapper/reader.d.ts +0 -34
- package/out/src/parquet-wrapper/reader.d.ts.map +0 -1
- package/out/src/parquet-wrapper/reader.js +0 -69
- package/out/src/parquet-wrapper/reader.js.map +0 -1
- package/out/src/parquet-wrapper/schema.d.ts +0 -49
- package/out/src/parquet-wrapper/schema.d.ts.map +0 -1
- package/out/src/parquet-wrapper/schema.js +0 -55
- package/out/src/parquet-wrapper/schema.js.map +0 -1
- package/out/src/parquet-wrapper/writer.d.ts +0 -46
- package/out/src/parquet-wrapper/writer.d.ts.map +0 -1
- package/out/src/parquet-wrapper/writer.js +0 -76
- package/out/src/parquet-wrapper/writer.js.map +0 -1
- package/out/src/runner.d.ts +0 -126
- package/out/src/runner.d.ts.map +0 -1
- package/out/src/runner.js +0 -189
- package/out/src/runner.js.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.d.ts +0 -20
- package/out/src/shard-recipes/anchor-absorption.d.ts.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.js +0 -82
- package/out/src/shard-recipes/anchor-absorption.js.map +0 -1
- package/out/src/shard-recipes/bare-country.d.ts +0 -25
- package/out/src/shard-recipes/bare-country.d.ts.map +0 -1
- package/out/src/shard-recipes/bare-country.js +0 -87
- package/out/src/shard-recipes/bare-country.js.map +0 -1
- package/out/src/shard-recipes/boundary-stress.d.ts +0 -20
- package/out/src/shard-recipes/boundary-stress.d.ts.map +0 -1
- package/out/src/shard-recipes/boundary-stress.js +0 -83
- package/out/src/shard-recipes/boundary-stress.js.map +0 -1
- package/out/src/shard-recipes/country-balanced.d.ts +0 -32
- package/out/src/shard-recipes/country-balanced.d.ts.map +0 -1
- package/out/src/shard-recipes/country-balanced.js +0 -406
- package/out/src/shard-recipes/country-balanced.js.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts +0 -22
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.js +0 -100
- package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.d.ts +0 -38
- package/out/src/shard-recipes/fr-admin-split.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.js +0 -188
- package/out/src/shard-recipes/fr-admin-split.js.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.d.ts +0 -28
- package/out/src/shard-recipes/fr-bare-street.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.js +0 -143
- package/out/src/shard-recipes/fr-bare-street.js.map +0 -1
- package/out/src/shard-recipes/fr-fragment.d.ts +0 -77
- package/out/src/shard-recipes/fr-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-fragment.js +0 -276
- package/out/src/shard-recipes/fr-fragment.js.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.d.ts +0 -32
- package/out/src/shard-recipes/fr-lieudit.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.js +0 -226
- package/out/src/shard-recipes/fr-lieudit.js.map +0 -1
- package/out/src/shard-recipes/fr-order.d.ts +0 -38
- package/out/src/shard-recipes/fr-order.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-order.js +0 -208
- package/out/src/shard-recipes/fr-order.js.map +0 -1
- package/out/src/shard-recipes/german.d.ts +0 -23
- package/out/src/shard-recipes/german.d.ts.map +0 -1
- package/out/src/shard-recipes/german.js +0 -132
- package/out/src/shard-recipes/german.js.map +0 -1
- package/out/src/shard-recipes/house-venue.d.ts +0 -18
- package/out/src/shard-recipes/house-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/house-venue.js +0 -74
- package/out/src/shard-recipes/house-venue.js.map +0 -1
- package/out/src/shard-recipes/index.d.ts +0 -24
- package/out/src/shard-recipes/index.d.ts.map +0 -1
- package/out/src/shard-recipes/index.js +0 -89
- package/out/src/shard-recipes/index.js.map +0 -1
- package/out/src/shard-recipes/intersection.d.ts +0 -42
- package/out/src/shard-recipes/intersection.d.ts.map +0 -1
- package/out/src/shard-recipes/intersection.js +0 -460
- package/out/src/shard-recipes/intersection.js.map +0 -1
- package/out/src/shard-recipes/locale.d.ts +0 -135
- package/out/src/shard-recipes/locale.d.ts.map +0 -1
- package/out/src/shard-recipes/locale.js +0 -459
- package/out/src/shard-recipes/locale.js.map +0 -1
- package/out/src/shard-recipes/nl-postcode.d.ts +0 -26
- package/out/src/shard-recipes/nl-postcode.d.ts.map +0 -1
- package/out/src/shard-recipes/nl-postcode.js +0 -102
- package/out/src/shard-recipes/nl-postcode.js.map +0 -1
- package/out/src/shard-recipes/no-fragment.d.ts +0 -43
- package/out/src/shard-recipes/no-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/no-fragment.js +0 -188
- package/out/src/shard-recipes/no-fragment.js.map +0 -1
- package/out/src/shard-recipes/no-street-led.d.ts +0 -24
- package/out/src/shard-recipes/no-street-led.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street-led.js +0 -121
- package/out/src/shard-recipes/no-street-led.js.map +0 -1
- package/out/src/shard-recipes/no-street.d.ts +0 -18
- package/out/src/shard-recipes/no-street.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street.js +0 -72
- package/out/src/shard-recipes/no-street.js.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.d.ts +0 -38
- package/out/src/shard-recipes/po-box-cedex.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.js +0 -726
- package/out/src/shard-recipes/po-box-cedex.js.map +0 -1
- package/out/src/shard-recipes/po-box.d.ts +0 -17
- package/out/src/shard-recipes/po-box.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box.js +0 -101
- package/out/src/shard-recipes/po-box.js.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts +0 -47
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.js +0 -125
- package/out/src/shard-recipes/reviewed-postcode-tail.js.map +0 -1
- package/out/src/shard-recipes/scaffold.d.ts +0 -246
- package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
- package/out/src/shard-recipes/scaffold.js +0 -137
- package/out/src/shard-recipes/scaffold.js.map +0 -1
- package/out/src/shard-recipes/si-bare-village.d.ts +0 -32
- package/out/src/shard-recipes/si-bare-village.d.ts.map +0 -1
- package/out/src/shard-recipes/si-bare-village.js +0 -88
- package/out/src/shard-recipes/si-bare-village.js.map +0 -1
- package/out/src/shard-recipes/street-affix.d.ts +0 -89
- package/out/src/shard-recipes/street-affix.d.ts.map +0 -1
- package/out/src/shard-recipes/street-affix.js +0 -578
- package/out/src/shard-recipes/street-affix.js.map +0 -1
- package/out/src/shard-recipes/street-bare.d.ts +0 -25
- package/out/src/shard-recipes/street-bare.d.ts.map +0 -1
- package/out/src/shard-recipes/street-bare.js +0 -86
- package/out/src/shard-recipes/street-bare.js.map +0 -1
- package/out/src/shard-recipes/street.d.ts +0 -15
- package/out/src/shard-recipes/street.d.ts.map +0 -1
- package/out/src/shard-recipes/street.js +0 -69
- package/out/src/shard-recipes/street.js.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.d.ts +0 -228
- package/out/src/shard-recipes/sub-venue-sources.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.js +0 -664
- package/out/src/shard-recipes/sub-venue-sources.js.map +0 -1
- package/out/src/shard-recipes/sub-venue.d.ts +0 -269
- package/out/src/shard-recipes/sub-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue.js +0 -710
- package/out/src/shard-recipes/sub-venue.js.map +0 -1
- package/out/src/shard-recipes/trailing-region.d.ts +0 -74
- package/out/src/shard-recipes/trailing-region.d.ts.map +0 -1
- package/out/src/shard-recipes/trailing-region.js +0 -157
- package/out/src/shard-recipes/trailing-region.js.map +0 -1
- package/out/src/shard-recipes/unit.d.ts +0 -29
- package/out/src/shard-recipes/unit.d.ts.map +0 -1
- package/out/src/shard-recipes/unit.js +0 -243
- package/out/src/shard-recipes/unit.js.map +0 -1
- package/out/src/synthesizers/anchor-absorption.d.ts +0 -63
- package/out/src/synthesizers/anchor-absorption.d.ts.map +0 -1
- package/out/src/synthesizers/anchor-absorption.js +0 -223
- package/out/src/synthesizers/anchor-absorption.js.map +0 -1
- package/out/src/synthesizers/boundary-stress.d.ts +0 -78
- package/out/src/synthesizers/boundary-stress.d.ts.map +0 -1
- package/out/src/synthesizers/boundary-stress.js +0 -455
- package/out/src/synthesizers/boundary-stress.js.map +0 -1
- package/out/src/synthesizers/german.d.ts +0 -107
- package/out/src/synthesizers/german.d.ts.map +0 -1
- package/out/src/synthesizers/german.js +0 -148
- package/out/src/synthesizers/german.js.map +0 -1
- package/out/src/synthesizers/house-venue.d.ts +0 -56
- package/out/src/synthesizers/house-venue.d.ts.map +0 -1
- package/out/src/synthesizers/house-venue.js +0 -267
- package/out/src/synthesizers/house-venue.js.map +0 -1
- package/out/src/synthesizers/intersection.d.ts +0 -52
- package/out/src/synthesizers/intersection.d.ts.map +0 -1
- package/out/src/synthesizers/intersection.js +0 -175
- package/out/src/synthesizers/intersection.js.map +0 -1
- package/out/src/synthesizers/no-street.d.ts +0 -72
- package/out/src/synthesizers/no-street.d.ts.map +0 -1
- package/out/src/synthesizers/no-street.js +0 -282
- package/out/src/synthesizers/no-street.js.map +0 -1
- package/out/src/synthesizers/po-box.d.ts +0 -104
- package/out/src/synthesizers/po-box.d.ts.map +0 -1
- package/out/src/synthesizers/po-box.js +0 -266
- package/out/src/synthesizers/po-box.js.map +0 -1
- package/out/src/synthesizers/street.d.ts +0 -54
- package/out/src/synthesizers/street.d.ts.map +0 -1
- package/out/src/synthesizers/street.js +0 -221
- package/out/src/synthesizers/street.js.map +0 -1
- package/out/src/synthesizers/utils.d.ts +0 -203
- package/out/src/synthesizers/utils.d.ts.map +0 -1
- package/out/src/synthesizers/utils.js +0 -708
- package/out/src/synthesizers/utils.js.map +0 -1
- package/out/src/tools/align-shard.d.ts +0 -8
- package/out/src/tools/align-shard.d.ts.map +0 -1
- package/out/src/tools/align-shard.js +0 -56
- package/out/src/tools/align-shard.js.map +0 -1
- package/out/src/tools/audit.d.ts +0 -28
- package/out/src/tools/audit.d.ts.map +0 -1
- package/out/src/tools/audit.js +0 -285
- package/out/src/tools/audit.js.map +0 -1
- package/out/src/tools/corpus-stats.d.ts +0 -44
- package/out/src/tools/corpus-stats.d.ts.map +0 -1
- package/out/src/tools/corpus-stats.js +0 -138
- package/out/src/tools/corpus-stats.js.map +0 -1
- package/out/src/tools/fetch/ban.d.ts +0 -31
- package/out/src/tools/fetch/ban.d.ts.map +0 -1
- package/out/src/tools/fetch/ban.js +0 -239
- package/out/src/tools/fetch/ban.js.map +0 -1
- package/out/src/tools/fetch/download.d.ts +0 -78
- package/out/src/tools/fetch/download.d.ts.map +0 -1
- package/out/src/tools/fetch/download.js +0 -116
- package/out/src/tools/fetch/download.js.map +0 -1
- package/out/src/tools/fetch/geonames-dump.d.ts +0 -87
- package/out/src/tools/fetch/geonames-dump.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-dump.js +0 -178
- package/out/src/tools/fetch/geonames-dump.js.map +0 -1
- package/out/src/tools/fetch/geonames-postal.d.ts +0 -76
- package/out/src/tools/fetch/geonames-postal.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-postal.js +0 -125
- package/out/src/tools/fetch/geonames-postal.js.map +0 -1
- package/out/src/tools/fetch/hrsa.d.ts +0 -18
- package/out/src/tools/fetch/hrsa.d.ts.map +0 -1
- package/out/src/tools/fetch/hrsa.js +0 -46
- package/out/src/tools/fetch/hrsa.js.map +0 -1
- package/out/src/tools/fetch/imls-pls.d.ts +0 -25
- package/out/src/tools/fetch/imls-pls.d.ts.map +0 -1
- package/out/src/tools/fetch/imls-pls.js +0 -108
- package/out/src/tools/fetch/imls-pls.js.map +0 -1
- package/out/src/tools/fetch/index.d.ts +0 -144
- package/out/src/tools/fetch/index.d.ts.map +0 -1
- package/out/src/tools/fetch/index.js +0 -143
- package/out/src/tools/fetch/index.js.map +0 -1
- package/out/src/tools/fetch/nad.d.ts +0 -70
- package/out/src/tools/fetch/nad.d.ts.map +0 -1
- package/out/src/tools/fetch/nad.js +0 -234
- package/out/src/tools/fetch/nad.js.map +0 -1
- package/out/src/tools/fetch/nppes.d.ts +0 -26
- package/out/src/tools/fetch/nppes.d.ts.map +0 -1
- package/out/src/tools/fetch/nppes.js +0 -126
- package/out/src/tools/fetch/nppes.js.map +0 -1
- package/out/src/tools/fetch/openaddresses.d.ts +0 -61
- package/out/src/tools/fetch/openaddresses.d.ts.map +0 -1
- package/out/src/tools/fetch/openaddresses.js +0 -317
- package/out/src/tools/fetch/openaddresses.js.map +0 -1
- package/out/src/tools/fetch/ourairports.d.ts +0 -45
- package/out/src/tools/fetch/ourairports.d.ts.map +0 -1
- package/out/src/tools/fetch/ourairports.js +0 -128
- package/out/src/tools/fetch/ourairports.js.map +0 -1
- package/out/src/tools/fetch/ppd.d.ts.map +0 -1
- package/out/src/tools/fetch/ppd.js +0 -100
- package/out/src/tools/fetch/ppd.js.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.d.ts +0 -25
- package/out/src/tools/fetch/state-hi-schools.d.ts.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.js +0 -162
- package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
- package/out/src/tools/fetch/state-sources.d.ts +0 -26
- package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
- package/out/src/tools/fetch/state-sources.js +0 -111
- package/out/src/tools/fetch/state-sources.js.map +0 -1
- package/out/src/tools/fetch/tiger-full.d.ts +0 -42
- package/out/src/tools/fetch/tiger-full.d.ts.map +0 -1
- package/out/src/tools/fetch/tiger-full.js +0 -248
- package/out/src/tools/fetch/tiger-full.js.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.d.ts +0 -171
- package/out/src/tools/fetch/wikidata-subvenue.d.ts.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.js +0 -275
- package/out/src/tools/fetch/wikidata-subvenue.js.map +0 -1
- package/out/src/tools/gb-title-case.d.ts.map +0 -1
- package/out/src/tools/gb-title-case.js.map +0 -1
- package/out/src/tools/golden-expand.d.ts +0 -90
- package/out/src/tools/golden-expand.d.ts.map +0 -1
- package/out/src/tools/golden-expand.js +0 -413
- package/out/src/tools/golden-expand.js.map +0 -1
- package/out/src/tools/golden-promote.d.ts.map +0 -1
- package/out/src/tools/golden-promote.js +0 -244
- package/out/src/tools/golden-promote.js.map +0 -1
- package/out/src/tools/golden-relabel-street.d.ts +0 -196
- package/out/src/tools/golden-relabel-street.d.ts.map +0 -1
- package/out/src/tools/golden-relabel-street.js +0 -440
- package/out/src/tools/golden-relabel-street.js.map +0 -1
- package/out/src/tools/index.d.ts +0 -28
- package/out/src/tools/index.d.ts.map +0 -1
- package/out/src/tools/index.js +0 -28
- package/out/src/tools/index.js.map +0 -1
- package/out/src/tools/ingest-csv.d.ts.map +0 -1
- package/out/src/tools/ingest-csv.js +0 -296
- package/out/src/tools/ingest-csv.js.map +0 -1
- package/out/src/tools/jsonl-to-parquet.d.ts +0 -61
- package/out/src/tools/jsonl-to-parquet.d.ts.map +0 -1
- package/out/src/tools/jsonl-to-parquet.js +0 -164
- package/out/src/tools/jsonl-to-parquet.js.map +0 -1
- package/out/src/tools/lint-shard-vocab.d.ts +0 -90
- package/out/src/tools/lint-shard-vocab.d.ts.map +0 -1
- package/out/src/tools/lint-shard-vocab.js +0 -281
- package/out/src/tools/lint-shard-vocab.js.map +0 -1
- package/out/src/tools/lint-shard.d.ts +0 -93
- package/out/src/tools/lint-shard.d.ts.map +0 -1
- package/out/src/tools/lint-shard.js +0 -354
- package/out/src/tools/lint-shard.js.map +0 -1
- package/out/src/tools/overlay-manifest.d.ts +0 -39
- package/out/src/tools/overlay-manifest.d.ts.map +0 -1
- package/out/src/tools/overlay-manifest.js +0 -98
- package/out/src/tools/overlay-manifest.js.map +0 -1
- package/out/src/tools/overture-subvenue.d.ts +0 -112
- package/out/src/tools/overture-subvenue.d.ts.map +0 -1
- package/out/src/tools/overture-subvenue.js +0 -144
- package/out/src/tools/overture-subvenue.js.map +0 -1
- package/out/src/tools/postcode-triples.d.ts +0 -175
- package/out/src/tools/postcode-triples.d.ts.map +0 -1
- package/out/src/tools/postcode-triples.js +0 -304
- package/out/src/tools/postcode-triples.js.map +0 -1
- package/out/src/tools/shard-kryptonite.d.ts +0 -32
- package/out/src/tools/shard-kryptonite.d.ts.map +0 -1
- package/out/src/tools/shard-kryptonite.js +0 -100
- package/out/src/tools/shard-kryptonite.js.map +0 -1
- package/out/src/tools/shard-translit.d.ts +0 -51
- package/out/src/tools/shard-translit.d.ts.map +0 -1
- package/out/src/tools/shard-translit.js +0 -175
- package/out/src/tools/shard-translit.js.map +0 -1
- package/out/src/tools/sub-venue/harvest.d.ts +0 -100
- package/out/src/tools/sub-venue/harvest.d.ts.map +0 -1
- package/out/src/tools/sub-venue/harvest.js +0 -168
- package/out/src/tools/sub-venue/harvest.js.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.d.ts +0 -50
- package/out/src/tools/sub-venue/head-nouns.d.ts.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.js +0 -210
- package/out/src/tools/sub-venue/head-nouns.js.map +0 -1
- package/out/src/tools/sub-venue/surfaces.d.ts +0 -45
- package/out/src/tools/sub-venue/surfaces.d.ts.map +0 -1
- package/out/src/tools/sub-venue/surfaces.js +0 -77
- package/out/src/tools/sub-venue/surfaces.js.map +0 -1
- package/out/src/tools/sub-venue/table.d.ts +0 -229
- package/out/src/tools/sub-venue/table.d.ts.map +0 -1
- package/out/src/tools/sub-venue/table.js +0 -108
- package/out/src/tools/sub-venue/table.js.map +0 -1
- package/out/src/tools/sub-venue/wikidata.d.ts +0 -26
- package/out/src/tools/sub-venue/wikidata.d.ts.map +0 -1
- package/out/src/tools/sub-venue/wikidata.js +0 -62
- package/out/src/tools/sub-venue/wikidata.js.map +0 -1
- package/out/src/tools/sub-venue-lexicon.d.ts +0 -156
- package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
- package/out/src/tools/sub-venue-lexicon.js +0 -282
- package/out/src/tools/sub-venue-lexicon.js.map +0 -1
- package/out/src/tools/sub-venue-promotions.d.ts +0 -94
- package/out/src/tools/sub-venue-promotions.d.ts.map +0 -1
- package/out/src/tools/sub-venue-promotions.js +0 -266
- package/out/src/tools/sub-venue-promotions.js.map +0 -1
- package/out/src/types.d.ts +0 -221
- package/out/src/types.d.ts.map +0 -1
- package/out/src/types.js.map +0 -1
- package/out/src/utils/align.d.ts +0 -93
- package/out/src/utils/align.d.ts.map +0 -1
- package/out/src/utils/align.js +0 -234
- package/out/src/utils/align.js.map +0 -1
- package/out/src/utils/golden.d.ts +0 -69
- package/out/src/utils/golden.d.ts.map +0 -1
- package/out/src/utils/golden.js +0 -127
- package/out/src/utils/golden.js.map +0 -1
- package/out/src/utils/index.d.ts +0 -14
- package/out/src/utils/index.d.ts.map +0 -1
- package/out/src/utils/index.js +0 -14
- package/out/src/utils/index.js.map +0 -1
- package/out/src/utils/license.d.ts.map +0 -1
- package/out/src/utils/license.js.map +0 -1
- package/out/src/utils/parquet.d.ts +0 -162
- package/out/src/utils/parquet.d.ts.map +0 -1
- package/out/src/utils/parquet.js +0 -262
- package/out/src/utils/parquet.js.map +0 -1
- package/out/src/utils/split.d.ts +0 -127
- package/out/src/utils/split.d.ts.map +0 -1
- package/out/src/utils/split.js +0 -204
- package/out/src/utils/split.js.map +0 -1
- package/out/src/utils/tokenize.d.ts +0 -56
- package/out/src/utils/tokenize.d.ts.map +0 -1
- package/out/src/utils/tokenize.js +0 -48
- package/out/src/utils/tokenize.js.map +0 -1
- package/out/src/utils/wof-json.d.ts +0 -109
- package/out/src/utils/wof-json.d.ts.map +0 -1
- package/out/src/utils/wof-json.js +0 -173
- package/out/src/utils/wof-json.js.map +0 -1
- package/src/adapters/ban/adapter.ts +0 -191
- package/src/adapters/ban/street-decompose.ts +0 -96
- package/src/adapters/fcc-bdc/adapter.ts +0 -174
- package/src/adapters/geonames/adapter.ts +0 -200
- package/src/adapters/geonames-postal/adapter.ts +0 -119
- package/src/adapters/gnaf/adapter.ts +0 -149
- package/src/adapters/gnaf/assemble.ts +0 -226
- package/src/adapters/index.ts +0 -149
- package/src/adapters/openaddresses/adapter.ts +0 -251
- package/src/adapters/overture/adapter.ts +0 -162
- package/src/adapters/state-hi-schools/adapter.ts +0 -164
- package/src/adapters/synth-po-box/adapter.ts +0 -204
- package/src/adapters/tiger/adapter.ts +0 -253
- package/src/adapters/tiger/street-decompose.ts +0 -111
- package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -183
- package/src/adapters/usgov-imls-pls/adapter.ts +0 -143
- package/src/adapters/usgov-irs-bmf/adapter.ts +0 -163
- package/src/adapters/usgov-nad/adapter.ts +0 -348
- package/src/adapters/usgov-nppes/adapter.ts +0 -159
- package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -204
- package/src/adapters/utils/index.ts +0 -233
- package/src/adapters/wof-admin-jp/adapter.ts +0 -216
- package/src/adapters/wof-admin-json/adapter.ts +0 -256
- package/src/adapters/wof-json-rows.ts +0 -79
- package/src/adapters/wof-postalcode-json/adapter.ts +0 -183
- package/src/build.ts +0 -386
- package/src/index.ts +0 -14
- package/src/name-prone-us-suffixes.ts +0 -12
- package/src/parquet-wrapper/index.ts +0 -9
- package/src/parquet-wrapper/reader.ts +0 -97
- package/src/parquet-wrapper/schema.ts +0 -88
- package/src/parquet-wrapper/writer.ts +0 -110
- package/src/runner.ts +0 -317
- package/src/shard-recipes/anchor-absorption.ts +0 -103
- package/src/shard-recipes/bare-country.ts +0 -95
- package/src/shard-recipes/boundary-stress.ts +0 -101
- package/src/shard-recipes/country-balanced.ts +0 -524
- package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -111
- package/src/shard-recipes/fr-admin-split.ts +0 -239
- package/src/shard-recipes/fr-bare-street.ts +0 -170
- package/src/shard-recipes/fr-fragment.ts +0 -332
- package/src/shard-recipes/fr-lieudit.ts +0 -302
- package/src/shard-recipes/fr-order.ts +0 -258
- package/src/shard-recipes/german.ts +0 -170
- package/src/shard-recipes/house-venue.ts +0 -88
- package/src/shard-recipes/index.ts +0 -95
- package/src/shard-recipes/intersection.ts +0 -630
- package/src/shard-recipes/locale.ts +0 -599
- package/src/shard-recipes/nl-postcode.ts +0 -115
- package/src/shard-recipes/no-fragment.ts +0 -219
- package/src/shard-recipes/no-street-led.ts +0 -143
- package/src/shard-recipes/no-street.ts +0 -86
- package/src/shard-recipes/po-box-cedex.ts +0 -920
- package/src/shard-recipes/po-box.ts +0 -119
- package/src/shard-recipes/reviewed-postcode-tail.ts +0 -189
- package/src/shard-recipes/scaffold.ts +0 -360
- package/src/shard-recipes/si-bare-village.ts +0 -97
- package/src/shard-recipes/street-affix.ts +0 -826
- package/src/shard-recipes/street-bare.ts +0 -101
- package/src/shard-recipes/street.ts +0 -82
- package/src/shard-recipes/sub-venue-sources.ts +0 -885
- package/src/shard-recipes/sub-venue.ts +0 -984
- package/src/shard-recipes/trailing-region.ts +0 -183
- package/src/shard-recipes/unit.ts +0 -321
- package/src/synthesizers/anchor-absorption.ts +0 -290
- package/src/synthesizers/boundary-stress.ts +0 -531
- package/src/synthesizers/german.ts +0 -251
- package/src/synthesizers/house-venue.ts +0 -330
- package/src/synthesizers/intersection.ts +0 -232
- package/src/synthesizers/no-street.ts +0 -349
- package/src/synthesizers/po-box.ts +0 -339
- package/src/synthesizers/street.ts +0 -274
- package/src/synthesizers/utils.ts +0 -903
- package/src/tools/align-shard.ts +0 -70
- package/src/tools/audit.ts +0 -399
- package/src/tools/corpus-stats.ts +0 -184
- package/src/tools/fetch/ban.ts +0 -290
- package/src/tools/fetch/download.ts +0 -176
- package/src/tools/fetch/geonames-dump.ts +0 -267
- package/src/tools/fetch/geonames-postal.ts +0 -180
- package/src/tools/fetch/hrsa.ts +0 -68
- package/src/tools/fetch/imls-pls.ts +0 -158
- package/src/tools/fetch/index.ts +0 -147
- package/src/tools/fetch/nad.ts +0 -342
- package/src/tools/fetch/nppes.ts +0 -174
- package/src/tools/fetch/openaddresses.ts +0 -404
- package/src/tools/fetch/ourairports.ts +0 -171
- package/src/tools/fetch/ppd.ts +0 -137
- package/src/tools/fetch/state-hi-schools.ts +0 -208
- package/src/tools/fetch/state-sources.ts +0 -155
- package/src/tools/fetch/tiger-full.ts +0 -354
- package/src/tools/fetch/wikidata-subvenue.ts +0 -386
- package/src/tools/golden-expand.ts +0 -584
- package/src/tools/golden-promote.ts +0 -353
- package/src/tools/golden-relabel-street.ts +0 -685
- package/src/tools/index.ts +0 -28
- package/src/tools/ingest-csv.ts +0 -422
- package/src/tools/jsonl-to-parquet.ts +0 -221
- package/src/tools/lint-shard-vocab.ts +0 -409
- package/src/tools/lint-shard.ts +0 -543
- package/src/tools/overlay-manifest.ts +0 -157
- package/src/tools/overture-subvenue.ts +0 -215
- package/src/tools/postcode-triples.ts +0 -375
- package/src/tools/shard-kryptonite.ts +0 -139
- package/src/tools/shard-translit.ts +0 -245
- package/src/tools/sub-venue/harvest.ts +0 -235
- package/src/tools/sub-venue/head-nouns.ts +0 -242
- package/src/tools/sub-venue/surfaces.ts +0 -95
- package/src/tools/sub-venue/table.ts +0 -281
- package/src/tools/sub-venue/wikidata.ts +0 -85
- package/src/tools/sub-venue-lexicon.ts +0 -431
- package/src/tools/sub-venue-promotions.ts +0 -330
- package/src/types.ts +0 -247
- package/src/utils/align.ts +0 -331
- package/src/utils/golden.ts +0 -176
- package/src/utils/index.ts +0 -14
- package/src/utils/parquet.ts +0 -391
- package/src/utils/split.ts +0 -279
- package/src/utils/tokenize.ts +0 -78
- package/src/utils/wof-json.ts +0 -244
- /package/{src → lib}/adapters/state-ia-contractors/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-ny-notaries/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-tx-notaries/adapter.ts +0 -0
- /package/{src → lib}/codex/us-fips-state.ts +0 -0
- /package/{src → lib}/tools/gb-title-case.ts +0 -0
- /package/{src → lib}/utils/license.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/fcc-bdc/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/geonames/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/openaddresses/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/synth-po-box/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/tiger/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-nppes/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-samhsa-treatment-locator/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/wof-admin-jp/adapter.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.js +0 -0
- /package/out/{src/tools → tools}/fetch/ppd.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.js +0 -0
- /package/out/{src/tools → tools}/golden-promote.d.ts +0 -0
- /package/out/{src/tools → tools}/ingest-csv.d.ts +0 -0
- /package/out/{src/types.js → types.js} +0 -0
- /package/out/{src/utils → utils}/license.d.ts +0 -0
- /package/out/{src/utils → utils}/license.js +0 -0
|
@@ -1,354 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Corpus linter. Compares a new shard against pre-computed corpus statistics and flags patterns
|
|
7
|
-
* that would cause the class of failure we hit with v0.6.2's "5th Avenue Theatre" adversarial
|
|
8
|
-
* venue templates.
|
|
9
|
-
*
|
|
10
|
-
* Per DeepSeek turn 9 design (2026-05-29). v1 checks:
|
|
11
|
-
*
|
|
12
|
-
* 1. **Token-label distribution outliers.** For each token in the new shard, compare the shard's
|
|
13
|
-
* majority label to the corpus's majority label. Flag when the corpus has a
|
|
14
|
-
* confidently-established majority (>66%) AND the shard's majority differs AND both have
|
|
15
|
-
* non-trivial counts (shard ≥ 50, corpus ≥ 200).
|
|
16
|
-
* 2. **Label-vacuum tokens.** Token labeled with a tag that has ZERO instances in the corpus for that
|
|
17
|
-
* token, despite the token being well-represented in the corpus. Stronger signal than #1 —
|
|
18
|
-
* we're introducing a novel association, not shifting a distribution.
|
|
19
|
-
* 3. **Bigram-label collisions.** Identical (token_bigram, label_bigram) appears in shard while the
|
|
20
|
-
* same token_bigram has a DIFFERENT majority label_bigram in the corpus. The "5th Avenue"
|
|
21
|
-
* with [B-venue, I-venue] vs corpus's [B-house_number, I-street] case.
|
|
22
|
-
* 4. **Common-form anti-pattern rules.** Applies `lint-rules.json` — token-regex → forbidden-labels
|
|
23
|
-
* mappings — flagging matches.
|
|
24
|
-
* 5. **Basic sanity.** Truncated rows (tokens.length !== labels.length), all-O rows >90% of shard.
|
|
25
|
-
*
|
|
26
|
-
* Output: markdown report on stdout, optional JSON sidecar via `outJSON`. The command exits 0 if
|
|
27
|
-
* no errors, 1 if any errors (warnings don't gate). Per the design, the MANIFEST entry for a
|
|
28
|
-
* flagged shard should require `lint_acknowledged: true` before training consumes it.
|
|
29
|
-
*
|
|
30
|
-
* Usage: mailwoman dev lint corpus-shard\
|
|
31
|
-
* --shard <new-shard.parquet>\
|
|
32
|
-
* --stats <corpus-stats.json>\
|
|
33
|
-
* [--rules <rules.json>]\
|
|
34
|
-
* [--out-md /tmp/lint-report.md]\
|
|
35
|
-
* [--out-json /tmp/lint-report.json]
|
|
36
|
-
*/
|
|
37
|
-
import { existsSync, readFileSync, writeFileSync } from "node:fs";
|
|
38
|
-
import { fileURLToPath } from "node:url";
|
|
39
|
-
import { parseJSONStrict } from "@mailwoman/core/objects";
|
|
40
|
-
import { ParquetReader } from "../parquet-wrapper/index.js";
|
|
41
|
-
/**
|
|
42
|
-
* Occurrences of a forbidden label before it is reported — one or two are noise, five is a pattern.
|
|
43
|
-
*/
|
|
44
|
-
const FORBIDDEN_LABEL_REPORT_THRESHOLD = 5;
|
|
45
|
-
/**
|
|
46
|
-
* Examples printed per finding before the list is truncated.
|
|
47
|
-
*/
|
|
48
|
-
const MAX_LISTED_EXAMPLES = 20;
|
|
49
|
-
const SEP = "";
|
|
50
|
-
/**
|
|
51
|
-
* Calibrated thresholds (DeepSeek turn 9). These can be tuned over time if new failure modes surface that the current
|
|
52
|
-
* numbers miss.
|
|
53
|
-
*/
|
|
54
|
-
const CORPUS_CONFIDENCE_FLOOR = 0.66;
|
|
55
|
-
const SHARD_MIN_COUNT = 50;
|
|
56
|
-
const CORPUS_MIN_COUNT = 200;
|
|
57
|
-
const VACUUM_SHARD_MIN_COUNT = 20;
|
|
58
|
-
const VACUUM_CORPUS_MIN_COUNT = 100;
|
|
59
|
-
const BIGRAM_MIN_COUNT = 10;
|
|
60
|
-
const ALL_O_RATIO_CEILING = 0.9;
|
|
61
|
-
/**
|
|
62
|
-
* Default `lint-rules.json` path — the rules ship beside this module in the source tree. tsc does not emit
|
|
63
|
-
* readFileSync'd JSON into `out/`, so the compiled tree falls back to the source-tree copy (corpus/out/src/tools/ →
|
|
64
|
-
* corpus/src/tools/). In-repo the `node` exports condition loads this module from source anyway, so the sibling URL is
|
|
65
|
-
* the common path.
|
|
66
|
-
*/
|
|
67
|
-
function defaultRulesPath() {
|
|
68
|
-
const sibling = new URL("./lint-rules.json", import.meta.url);
|
|
69
|
-
if (existsSync(sibling))
|
|
70
|
-
return fileURLToPath(sibling);
|
|
71
|
-
return fileURLToPath(new URL("../../../src/tools/lint-rules.json", import.meta.url));
|
|
72
|
-
}
|
|
73
|
-
/**
|
|
74
|
-
* Stream a shard's `tokens`/`labels` columns.
|
|
75
|
-
*
|
|
76
|
-
* Projected rather than read whole: parquet is columnar, so the twelve unused columns are never touched. The rows feed
|
|
77
|
-
* straight into {@link statsFromShard} and are never all resident.
|
|
78
|
-
*/
|
|
79
|
-
async function* streamShard(shardPath) {
|
|
80
|
-
await using reader = await ParquetReader.openFile(shardPath);
|
|
81
|
-
yield* reader.project("tokens", "labels");
|
|
82
|
-
}
|
|
83
|
-
async function statsFromShard(rows) {
|
|
84
|
-
const out = {
|
|
85
|
-
rowCount: 0,
|
|
86
|
-
tokens: new Map(),
|
|
87
|
-
bigrams: new Map(),
|
|
88
|
-
truncatedRows: 0,
|
|
89
|
-
allORows: 0,
|
|
90
|
-
};
|
|
91
|
-
for await (const row of rows) {
|
|
92
|
-
out.rowCount++;
|
|
93
|
-
if (row.tokens.length !== row.labels.length) {
|
|
94
|
-
out.truncatedRows++;
|
|
95
|
-
continue;
|
|
96
|
-
}
|
|
97
|
-
if (row.labels.every((l) => l === "O")) {
|
|
98
|
-
out.allORows++;
|
|
99
|
-
}
|
|
100
|
-
for (let i = 0; i < row.tokens.length; i++) {
|
|
101
|
-
const tk = row.tokens[i];
|
|
102
|
-
const lb = row.labels[i];
|
|
103
|
-
let labelMap = out.tokens.get(tk);
|
|
104
|
-
if (!labelMap) {
|
|
105
|
-
labelMap = new Map();
|
|
106
|
-
out.tokens.set(tk, labelMap);
|
|
107
|
-
}
|
|
108
|
-
labelMap.set(lb, (labelMap.get(lb) ?? 0) + 1);
|
|
109
|
-
if (i + 1 < row.tokens.length) {
|
|
110
|
-
const bigramKey = tk + SEP + row.tokens[i + 1];
|
|
111
|
-
const bigramLabel = lb + SEP + row.labels[i + 1];
|
|
112
|
-
let bMap = out.bigrams.get(bigramKey);
|
|
113
|
-
if (!bMap) {
|
|
114
|
-
bMap = new Map();
|
|
115
|
-
out.bigrams.set(bigramKey, bMap);
|
|
116
|
-
}
|
|
117
|
-
bMap.set(bigramLabel, (bMap.get(bigramLabel) ?? 0) + 1);
|
|
118
|
-
}
|
|
119
|
-
}
|
|
120
|
-
}
|
|
121
|
-
return out;
|
|
122
|
-
}
|
|
123
|
-
function majorityLabel(distribution) {
|
|
124
|
-
const entries = distribution instanceof Map ? [...distribution.entries()] : Object.entries(distribution);
|
|
125
|
-
let bestLabel = "";
|
|
126
|
-
let bestCount = 0;
|
|
127
|
-
let total = 0;
|
|
128
|
-
for (const [label, count] of entries) {
|
|
129
|
-
total += count;
|
|
130
|
-
if (count > bestCount) {
|
|
131
|
-
bestCount = count;
|
|
132
|
-
bestLabel = label;
|
|
133
|
-
}
|
|
134
|
-
}
|
|
135
|
-
return { label: bestLabel, count: bestCount, total, confidence: total === 0 ? 0 : bestCount / total };
|
|
136
|
-
}
|
|
137
|
-
function checkDistributionOutliers(shard, corpus) {
|
|
138
|
-
const flags = [];
|
|
139
|
-
for (const [token, shardLabelMap] of shard.tokens) {
|
|
140
|
-
const corpusLabelMap = corpus.tokens[token];
|
|
141
|
-
if (!corpusLabelMap)
|
|
142
|
-
continue;
|
|
143
|
-
const shardMaj = majorityLabel(shardLabelMap);
|
|
144
|
-
const corpusMaj = majorityLabel(corpusLabelMap);
|
|
145
|
-
if (corpusMaj.confidence >= CORPUS_CONFIDENCE_FLOOR &&
|
|
146
|
-
shardMaj.label !== corpusMaj.label &&
|
|
147
|
-
shardMaj.count >= SHARD_MIN_COUNT &&
|
|
148
|
-
corpusMaj.total >= CORPUS_MIN_COUNT) {
|
|
149
|
-
flags.push({
|
|
150
|
-
check: "distribution-outlier",
|
|
151
|
-
severity: "error",
|
|
152
|
-
token,
|
|
153
|
-
shardLabel: shardMaj.label,
|
|
154
|
-
corpusLabel: corpusMaj.label,
|
|
155
|
-
shardCount: shardMaj.count,
|
|
156
|
-
corpusCount: corpusMaj.count,
|
|
157
|
-
detail: `Token "${token}": shard majority is ${shardMaj.label} (${shardMaj.count}/${shardMaj.total}, ${(shardMaj.confidence * 100).toFixed(0)}%), corpus majority is ${corpusMaj.label} (${corpusMaj.count}/${corpusMaj.total}, ${(corpusMaj.confidence * 100).toFixed(0)}%).`,
|
|
158
|
-
});
|
|
159
|
-
}
|
|
160
|
-
}
|
|
161
|
-
return flags;
|
|
162
|
-
}
|
|
163
|
-
function checkLabelVacuum(shard, corpus) {
|
|
164
|
-
const flags = [];
|
|
165
|
-
for (const [token, shardLabelMap] of shard.tokens) {
|
|
166
|
-
const corpusLabelMap = corpus.tokens[token];
|
|
167
|
-
if (!corpusLabelMap)
|
|
168
|
-
continue;
|
|
169
|
-
const corpusTotal = Object.values(corpusLabelMap).reduce((a, b) => a + b, 0);
|
|
170
|
-
if (corpusTotal < VACUUM_CORPUS_MIN_COUNT)
|
|
171
|
-
continue;
|
|
172
|
-
for (const [label, shardCount] of shardLabelMap) {
|
|
173
|
-
if (shardCount < VACUUM_SHARD_MIN_COUNT)
|
|
174
|
-
continue;
|
|
175
|
-
if (corpusLabelMap[label] === undefined || corpusLabelMap[label] === 0) {
|
|
176
|
-
flags.push({
|
|
177
|
-
check: "label-vacuum",
|
|
178
|
-
severity: "error",
|
|
179
|
-
token,
|
|
180
|
-
shardLabel: label,
|
|
181
|
-
shardCount,
|
|
182
|
-
corpusCount: corpusTotal,
|
|
183
|
-
detail: `Token "${token}": shard labels it ${label} ${shardCount} times, but the corpus (${corpusTotal} instances of this token) has ZERO instances of this label.`,
|
|
184
|
-
});
|
|
185
|
-
}
|
|
186
|
-
}
|
|
187
|
-
}
|
|
188
|
-
return flags;
|
|
189
|
-
}
|
|
190
|
-
function checkBigramCollisions(shard, corpus) {
|
|
191
|
-
const flags = [];
|
|
192
|
-
for (const [bigram, shardLabelMap] of shard.bigrams) {
|
|
193
|
-
const corpusLabelMap = corpus.bigrams[bigram];
|
|
194
|
-
if (!corpusLabelMap)
|
|
195
|
-
continue;
|
|
196
|
-
const shardMaj = majorityLabel(shardLabelMap);
|
|
197
|
-
const corpusMaj = majorityLabel(corpusLabelMap);
|
|
198
|
-
if (shardMaj.label !== corpusMaj.label &&
|
|
199
|
-
shardMaj.count >= BIGRAM_MIN_COUNT &&
|
|
200
|
-
corpusMaj.count >= BIGRAM_MIN_COUNT) {
|
|
201
|
-
const renderBigram = bigram.split(SEP).join(" ");
|
|
202
|
-
const renderShardLabel = shardMaj.label.split(SEP).join(" → ");
|
|
203
|
-
const renderCorpusLabel = corpusMaj.label.split(SEP).join(" → ");
|
|
204
|
-
flags.push({
|
|
205
|
-
check: "bigram-collision",
|
|
206
|
-
severity: "error",
|
|
207
|
-
bigram: renderBigram,
|
|
208
|
-
shardLabel: renderShardLabel,
|
|
209
|
-
corpusLabel: renderCorpusLabel,
|
|
210
|
-
shardCount: shardMaj.count,
|
|
211
|
-
corpusCount: corpusMaj.count,
|
|
212
|
-
detail: `Bigram "${renderBigram}": shard label-bigram is [${renderShardLabel}] (${shardMaj.count}×), corpus label-bigram is [${renderCorpusLabel}] (${corpusMaj.count}×). Same surface text, different structural reading.`,
|
|
213
|
-
});
|
|
214
|
-
}
|
|
215
|
-
}
|
|
216
|
-
return flags;
|
|
217
|
-
}
|
|
218
|
-
function checkRules(shard, rulesFile) {
|
|
219
|
-
const flags = [];
|
|
220
|
-
const compiled = rulesFile.rules.map((r) => ({
|
|
221
|
-
rule: r,
|
|
222
|
-
regex: new RegExp(r.pattern, r.pattern_case_sensitive ? "" : "i"),
|
|
223
|
-
}));
|
|
224
|
-
for (const [token, labelMap] of shard.tokens) {
|
|
225
|
-
for (const { rule, regex } of compiled) {
|
|
226
|
-
if (!regex.test(token))
|
|
227
|
-
continue;
|
|
228
|
-
for (const [label, count] of labelMap) {
|
|
229
|
-
if (rule.forbidden_labels.includes(label) && count >= FORBIDDEN_LABEL_REPORT_THRESHOLD) {
|
|
230
|
-
flags.push({
|
|
231
|
-
check: "anti-pattern-rule",
|
|
232
|
-
severity: rule.severity,
|
|
233
|
-
ruleID: rule.id,
|
|
234
|
-
token,
|
|
235
|
-
shardLabel: label,
|
|
236
|
-
shardCount: count,
|
|
237
|
-
detail: `Token "${token}" matched rule ${rule.id} and is labeled ${label} ${count} time(s). Rule message: ${rule.message}`,
|
|
238
|
-
});
|
|
239
|
-
}
|
|
240
|
-
}
|
|
241
|
-
}
|
|
242
|
-
}
|
|
243
|
-
return flags;
|
|
244
|
-
}
|
|
245
|
-
function checkSanity(shard) {
|
|
246
|
-
const flags = [];
|
|
247
|
-
if (shard.truncatedRows > 0) {
|
|
248
|
-
flags.push({
|
|
249
|
-
check: "truncated-rows",
|
|
250
|
-
severity: "error",
|
|
251
|
-
detail: `${shard.truncatedRows} row(s) have tokens.length !== labels.length. Pipeline alignment bug.`,
|
|
252
|
-
});
|
|
253
|
-
}
|
|
254
|
-
const allORatio = shard.allORows / Math.max(1, shard.rowCount);
|
|
255
|
-
if (allORatio >= ALL_O_RATIO_CEILING) {
|
|
256
|
-
flags.push({
|
|
257
|
-
check: "all-O-shard",
|
|
258
|
-
severity: "warn",
|
|
259
|
-
detail: `${shard.allORows}/${shard.rowCount} rows (${(allORatio * 100).toFixed(0)}%) are entirely O-labeled. Shard contributes no signal.`,
|
|
260
|
-
});
|
|
261
|
-
}
|
|
262
|
-
return flags;
|
|
263
|
-
}
|
|
264
|
-
function renderReport(opts, shard, flags) {
|
|
265
|
-
const errors = flags.filter((f) => f.severity === "error");
|
|
266
|
-
const warns = flags.filter((f) => f.severity === "warn");
|
|
267
|
-
const verdict = !errors.length ? "**PASS** ✓" : "**FLAGGED** ⚠";
|
|
268
|
-
const lines = [
|
|
269
|
-
`# Corpus Lint: ${verdict}`,
|
|
270
|
-
"",
|
|
271
|
-
`- **Shard:** \`${opts.shardPath}\``,
|
|
272
|
-
`- **Corpus stats:** \`${opts.statsPath}\``,
|
|
273
|
-
`- **Rules:** \`${opts.rulesPath}\``,
|
|
274
|
-
`- **Shard rows:** ${shard.rowCount}`,
|
|
275
|
-
`- **Unique tokens:** ${shard.tokens.size}`,
|
|
276
|
-
`- **Unique bigrams:** ${shard.bigrams.size}`,
|
|
277
|
-
"",
|
|
278
|
-
`**Errors:** ${errors.length} (gates the shard's inclusion unless MANIFEST sets \`lint_acknowledged: true\`)`,
|
|
279
|
-
`**Warnings:** ${warns.length} (advisory)`,
|
|
280
|
-
"",
|
|
281
|
-
];
|
|
282
|
-
if (!flags.length) {
|
|
283
|
-
lines.push("No anomalies detected.");
|
|
284
|
-
return lines.join("\n");
|
|
285
|
-
}
|
|
286
|
-
const byCheck = new Map();
|
|
287
|
-
for (const f of flags) {
|
|
288
|
-
const arr = byCheck.get(f.check) ?? [];
|
|
289
|
-
arr.push(f);
|
|
290
|
-
byCheck.set(f.check, arr);
|
|
291
|
-
}
|
|
292
|
-
for (const [check, list] of byCheck) {
|
|
293
|
-
lines.push(`## ${check} (${list.length})`);
|
|
294
|
-
lines.push("");
|
|
295
|
-
// Sort by shardCount desc — highest-volume issues first
|
|
296
|
-
list.sort((a, b) => (b.shardCount ?? 0) - (a.shardCount ?? 0));
|
|
297
|
-
for (const f of list.slice(0, 20)) {
|
|
298
|
-
lines.push(`- **[${f.severity.toUpperCase()}]** ${f.detail}`);
|
|
299
|
-
}
|
|
300
|
-
if (list.length > MAX_LISTED_EXAMPLES) {
|
|
301
|
-
lines.push(`- ... and ${list.length - 20} more`);
|
|
302
|
-
}
|
|
303
|
-
lines.push("");
|
|
304
|
-
}
|
|
305
|
-
return lines.join("\n");
|
|
306
|
-
}
|
|
307
|
-
/**
|
|
308
|
-
* Lint a shard against corpus stats + the anti-pattern rules; print the markdown report to stdout.
|
|
309
|
-
*/
|
|
310
|
-
export async function lintCorpusShard(options, report) {
|
|
311
|
-
const rulesPath = options.rulesPath ?? defaultRulesPath();
|
|
312
|
-
report?.(`Reading corpus stats from ${options.statsPath}...`);
|
|
313
|
-
const corpus = parseJSONStrict(readFileSync(options.statsPath, "utf8"));
|
|
314
|
-
report?.(` ${corpus.row_count} rows from ${corpus.shard_paths.length} shard(s); ${Object.keys(corpus.tokens).length} tokens, ${Object.keys(corpus.bigrams).length} bigrams`);
|
|
315
|
-
report?.(`Reading shard from ${options.shardPath}...`);
|
|
316
|
-
const shard = await statsFromShard(streamShard(options.shardPath));
|
|
317
|
-
report?.(` ${shard.rowCount} rows`);
|
|
318
|
-
report?.(`Loading rules from ${rulesPath}...`);
|
|
319
|
-
const rulesFile = parseJSONStrict(readFileSync(rulesPath, "utf8"));
|
|
320
|
-
report?.(`Running checks...`);
|
|
321
|
-
const flags = [
|
|
322
|
-
...checkDistributionOutliers(shard, corpus),
|
|
323
|
-
...checkLabelVacuum(shard, corpus),
|
|
324
|
-
...checkBigramCollisions(shard, corpus),
|
|
325
|
-
...checkRules(shard, rulesFile),
|
|
326
|
-
...checkSanity(shard),
|
|
327
|
-
];
|
|
328
|
-
const rendered = renderReport({ shardPath: options.shardPath, statsPath: options.statsPath, rulesPath }, shard, flags);
|
|
329
|
-
console.log(rendered);
|
|
330
|
-
if (options.outMd) {
|
|
331
|
-
writeFileSync(options.outMd, rendered);
|
|
332
|
-
}
|
|
333
|
-
if (options.outJSON) {
|
|
334
|
-
writeFileSync(options.outJSON, JSON.stringify({
|
|
335
|
-
shard: options.shardPath,
|
|
336
|
-
stats: options.statsPath,
|
|
337
|
-
flags,
|
|
338
|
-
summary: {
|
|
339
|
-
errors: flags.filter((f) => f.severity === "error").length,
|
|
340
|
-
warnings: flags.filter((f) => f.severity === "warn").length,
|
|
341
|
-
},
|
|
342
|
-
}, null, 2));
|
|
343
|
-
}
|
|
344
|
-
const errorCount = flags.filter((f) => f.severity === "error").length;
|
|
345
|
-
const warningCount = flags.filter((f) => f.severity === "warn").length;
|
|
346
|
-
if (errorCount > 0) {
|
|
347
|
-
report?.(`LINT FAILED: ${errorCount} error(s).`);
|
|
348
|
-
}
|
|
349
|
-
else {
|
|
350
|
-
report?.("LINT PASSED.");
|
|
351
|
-
}
|
|
352
|
-
return { errors: errorCount, warnings: warningCount, findings: flags, report: rendered };
|
|
353
|
-
}
|
|
354
|
-
//# sourceMappingURL=lint-shard.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"lint-shard.js","sourceRoot":"","sources":["../../../src/tools/lint-shard.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAmCG;AAEH,OAAO,EAAE,UAAU,EAAE,YAAY,EAAE,aAAa,EAAE,MAAM,SAAS,CAAA;AACjE,OAAO,EAAE,aAAa,EAAE,MAAM,UAAU,CAAA;AAExC,OAAO,EAAE,eAAe,EAAE,MAAM,yBAAyB,CAAA;AAEzD,OAAO,EAAE,aAAa,EAAE,MAAM,6BAA6B,CAAA;AAE3D;;GAEG;AACH,MAAM,gCAAgC,GAAG,CAAC,CAAA;AAE1C;;GAEG;AACH,MAAM,mBAAmB,GAAG,EAAE,CAAA;AAE9B,MAAM,GAAG,GAAG,EAAE,CAAA;AAEd;;;GAGG;AACH,MAAM,uBAAuB,GAAG,IAAI,CAAA;AACpC,MAAM,eAAe,GAAG,EAAE,CAAA;AAC1B,MAAM,gBAAgB,GAAG,GAAG,CAAA;AAC5B,MAAM,sBAAsB,GAAG,EAAE,CAAA;AACjC,MAAM,uBAAuB,GAAG,GAAG,CAAA;AACnC,MAAM,gBAAgB,GAAG,EAAE,CAAA;AAC3B,MAAM,mBAAmB,GAAG,GAAG,CAAA;AAE/B;;;;;GAKG;AACH,SAAS,gBAAgB;IACxB,MAAM,OAAO,GAAG,IAAI,GAAG,CAAC,mBAAmB,EAAE,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;IAE7D,IAAI,UAAU,CAAC,OAAO,CAAC;QAAE,OAAO,aAAa,CAAC,OAAO,CAAC,CAAA;IAEtD,OAAO,aAAa,CAAC,IAAI,GAAG,CAAC,oCAAoC,EAAE,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAA;AACrF,CAAC;AAwDD;;;;;GAKG;AACH,KAAK,SAAS,CAAC,CAAC,WAAW,CAAC,SAAiB;IAC5C,YAAY,MAAM,GAAG,MAAM,aAAa,CAAC,QAAQ,CAAW,SAAS,CAAC,CAAA;IAEtE,KAAK,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,QAAQ,EAAE,QAAQ,CAAC,CAAA;AAC1C,CAAC;AAUD,KAAK,UAAU,cAAc,CAAC,IAA6B;IAC1D,MAAM,GAAG,GAAe;QACvB,QAAQ,EAAE,CAAC;QACX,MAAM,EAAE,IAAI,GAAG,EAAE;QACjB,OAAO,EAAE,IAAI,GAAG,EAAE;QAClB,aAAa,EAAE,CAAC;QAChB,QAAQ,EAAE,CAAC;KACX,CAAA;IAED,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;QAC9B,GAAG,CAAC,QAAQ,EAAE,CAAA;QAEd,IAAI,GAAG,CAAC,MAAM,CAAC,MAAM,KAAK,GAAG,CAAC,MAAM,CAAC,MAAM,EAAE,CAAC;YAC7C,GAAG,CAAC,aAAa,EAAE,CAAA;YAEnB,SAAQ;QACT,CAAC;QAED,IAAI,GAAG,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,GAAG,CAAC,EAAE,CAAC;YACxC,GAAG,CAAC,QAAQ,EAAE,CAAA;QACf,CAAC;QAED,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,GAAG,CAAC,MAAM,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;YAC5C,MAAM,EAAE,GAAG,GAAG,CAAC,MAAM,CAAC,CAAC,CAAE,CAAA;YACzB,MAAM,EAAE,GAAG,GAAG,CAAC,MAAM,CAAC,CAAC,CAAE,CAAA;YACzB,IAAI,QAAQ,GAAG,GAAG,CAAC,MAAM,CAAC,GAAG,CAAC,EAAE,CAAC,CAAA;YAEjC,IAAI,CAAC,QAAQ,EAAE,CAAC;gBACf,QAAQ,GAAG,IAAI,GAAG,EAAE,CAAA;gBACpB,GAAG,CAAC,MAAM,CAAC,GAAG,CAAC,EAAE,EAAE,QAAQ,CAAC,CAAA;YAC7B,CAAC;YAED,QAAQ,CAAC,GAAG,CAAC,EAAE,EAAE,CAAC,QAAQ,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAA;YAE7C,IAAI,CAAC,GAAG,CAAC,GAAG,GAAG,CAAC,MAAM,CAAC,MAAM,EAAE,CAAC;gBAC/B,MAAM,SAAS,GAAG,EAAE,GAAG,GAAG,GAAG,GAAG,CAAC,MAAM,CAAC,CAAC,GAAG,CAAC,CAAE,CAAA;gBAC/C,MAAM,WAAW,GAAG,EAAE,GAAG,GAAG,GAAG,GAAG,CAAC,MAAM,CAAC,CAAC,GAAG,CAAC,CAAE,CAAA;gBACjD,IAAI,IAAI,GAAG,GAAG,CAAC,OAAO,CAAC,GAAG,CAAC,SAAS,CAAC,CAAA;gBAErC,IAAI,CAAC,IAAI,EAAE,CAAC;oBACX,IAAI,GAAG,IAAI,GAAG,EAAE,CAAA;oBAChB,GAAG,CAAC,OAAO,CAAC,GAAG,CAAC,SAAS,EAAE,IAAI,CAAC,CAAA;gBACjC,CAAC;gBAED,IAAI,CAAC,GAAG,CAAC,WAAW,EAAE,CAAC,IAAI,CAAC,GAAG,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAA;YACxD,CAAC;QACF,CAAC;IACF,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC;AAED,SAAS,aAAa,CAAC,YAA0D;IAMhF,MAAM,OAAO,GAAG,YAAY,YAAY,GAAG,CAAC,CAAC,CAAC,CAAC,GAAG,YAAY,CAAC,OAAO,EAAE,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,YAAY,CAAC,CAAA;IACxG,IAAI,SAAS,GAAG,EAAE,CAAA;IAClB,IAAI,SAAS,GAAG,CAAC,CAAA;IACjB,IAAI,KAAK,GAAG,CAAC,CAAA;IAEb,KAAK,MAAM,CAAC,KAAK,EAAE,KAAK,CAAC,IAAI,OAAO,EAAE,CAAC;QACtC,KAAK,IAAI,KAAK,CAAA;QAEd,IAAI,KAAK,GAAG,SAAS,EAAE,CAAC;YACvB,SAAS,GAAG,KAAK,CAAA;YACjB,SAAS,GAAG,KAAK,CAAA;QAClB,CAAC;IACF,CAAC;IAED,OAAO,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,SAAS,EAAE,KAAK,EAAE,UAAU,EAAE,KAAK,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,SAAS,GAAG,KAAK,EAAE,CAAA;AACtG,CAAC;AA+BD,SAAS,yBAAyB,CAAC,KAAiB,EAAE,MAAmB;IACxE,MAAM,KAAK,GAAoB,EAAE,CAAA;IAEjC,KAAK,MAAM,CAAC,KAAK,EAAE,aAAa,CAAC,IAAI,KAAK,CAAC,MAAM,EAAE,CAAC;QACnD,MAAM,cAAc,GAAG,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAA;QAE3C,IAAI,CAAC,cAAc;YAAE,SAAQ;QAC7B,MAAM,QAAQ,GAAG,aAAa,CAAC,aAAa,CAAC,CAAA;QAC7C,MAAM,SAAS,GAAG,aAAa,CAAC,cAAc,CAAC,CAAA;QAE/C,IACC,SAAS,CAAC,UAAU,IAAI,uBAAuB;YAC/C,QAAQ,CAAC,KAAK,KAAK,SAAS,CAAC,KAAK;YAClC,QAAQ,CAAC,KAAK,IAAI,eAAe;YACjC,SAAS,CAAC,KAAK,IAAI,gBAAgB,EAClC,CAAC;YACF,KAAK,CAAC,IAAI,CAAC;gBACV,KAAK,EAAE,sBAAsB;gBAC7B,QAAQ,EAAE,OAAO;gBACjB,KAAK;gBACL,UAAU,EAAE,QAAQ,CAAC,KAAK;gBAC1B,WAAW,EAAE,SAAS,CAAC,KAAK;gBAC5B,UAAU,EAAE,QAAQ,CAAC,KAAK;gBAC1B,WAAW,EAAE,SAAS,CAAC,KAAK;gBAC5B,MAAM,EAAE,UAAU,KAAK,wBAAwB,QAAQ,CAAC,KAAK,KAAK,QAAQ,CAAC,KAAK,IAAI,QAAQ,CAAC,KAAK,KAAK,CAAC,QAAQ,CAAC,UAAU,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,0BAA0B,SAAS,CAAC,KAAK,KAAK,SAAS,CAAC,KAAK,IAAI,SAAS,CAAC,KAAK,KAAK,CAAC,SAAS,CAAC,UAAU,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,KAAK;aAC9Q,CAAC,CAAA;QACH,CAAC;IACF,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC;AAED,SAAS,gBAAgB,CAAC,KAAiB,EAAE,MAAmB;IAC/D,MAAM,KAAK,GAAoB,EAAE,CAAA;IAEjC,KAAK,MAAM,CAAC,KAAK,EAAE,aAAa,CAAC,IAAI,KAAK,CAAC,MAAM,EAAE,CAAC;QACnD,MAAM,cAAc,GAAG,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAA;QAE3C,IAAI,CAAC,cAAc;YAAE,SAAQ;QAC7B,MAAM,WAAW,GAAG,MAAM,CAAC,MAAM,CAAC,cAAc,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC,CAAA;QAE5E,IAAI,WAAW,GAAG,uBAAuB;YAAE,SAAQ;QAEnD,KAAK,MAAM,CAAC,KAAK,EAAE,UAAU,CAAC,IAAI,aAAa,EAAE,CAAC;YACjD,IAAI,UAAU,GAAG,sBAAsB;gBAAE,SAAQ;YAEjD,IAAI,cAAc,CAAC,KAAK,CAAC,KAAK,SAAS,IAAI,cAAc,CAAC,KAAK,CAAC,KAAK,CAAC,EAAE,CAAC;gBACxE,KAAK,CAAC,IAAI,CAAC;oBACV,KAAK,EAAE,cAAc;oBACrB,QAAQ,EAAE,OAAO;oBACjB,KAAK;oBACL,UAAU,EAAE,KAAK;oBACjB,UAAU;oBACV,WAAW,EAAE,WAAW;oBACxB,MAAM,EAAE,UAAU,KAAK,sBAAsB,KAAK,IAAI,UAAU,2BAA2B,WAAW,6DAA6D;iBACnK,CAAC,CAAA;YACH,CAAC;QACF,CAAC;IACF,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC;AAED,SAAS,qBAAqB,CAAC,KAAiB,EAAE,MAAmB;IACpE,MAAM,KAAK,GAAoB,EAAE,CAAA;IAEjC,KAAK,MAAM,CAAC,MAAM,EAAE,aAAa,CAAC,IAAI,KAAK,CAAC,OAAO,EAAE,CAAC;QACrD,MAAM,cAAc,GAAG,MAAM,CAAC,OAAO,CAAC,MAAM,CAAC,CAAA;QAE7C,IAAI,CAAC,cAAc;YAAE,SAAQ;QAC7B,MAAM,QAAQ,GAAG,aAAa,CAAC,aAAa,CAAC,CAAA;QAC7C,MAAM,SAAS,GAAG,aAAa,CAAC,cAAc,CAAC,CAAA;QAE/C,IACC,QAAQ,CAAC,KAAK,KAAK,SAAS,CAAC,KAAK;YAClC,QAAQ,CAAC,KAAK,IAAI,gBAAgB;YAClC,SAAS,CAAC,KAAK,IAAI,gBAAgB,EAClC,CAAC;YACF,MAAM,YAAY,GAAG,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;YAChD,MAAM,gBAAgB,GAAG,QAAQ,CAAC,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;YAC9D,MAAM,iBAAiB,GAAG,SAAS,CAAC,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;YAEhE,KAAK,CAAC,IAAI,CAAC;gBACV,KAAK,EAAE,kBAAkB;gBACzB,QAAQ,EAAE,OAAO;gBACjB,MAAM,EAAE,YAAY;gBACpB,UAAU,EAAE,gBAAgB;gBAC5B,WAAW,EAAE,iBAAiB;gBAC9B,UAAU,EAAE,QAAQ,CAAC,KAAK;gBAC1B,WAAW,EAAE,SAAS,CAAC,KAAK;gBAC5B,MAAM,EAAE,WAAW,YAAY,6BAA6B,gBAAgB,MAAM,QAAQ,CAAC,KAAK,+BAA+B,iBAAiB,MAAM,SAAS,CAAC,KAAK,sDAAsD;aAC3N,CAAC,CAAA;QACH,CAAC;IACF,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC;AAED,SAAS,UAAU,CAAC,KAAiB,EAAE,SAAwB;IAC9D,MAAM,KAAK,GAAoB,EAAE,CAAA;IAEjC,MAAM,QAAQ,GAAG,SAAS,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC;QAC5C,IAAI,EAAE,CAAC;QACP,KAAK,EAAE,IAAI,MAAM,CAAC,CAAC,CAAC,OAAO,EAAE,CAAC,CAAC,sBAAsB,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC;KACjE,CAAC,CAAC,CAAA;IAEH,KAAK,MAAM,CAAC,KAAK,EAAE,QAAQ,CAAC,IAAI,KAAK,CAAC,MAAM,EAAE,CAAC;QAC9C,KAAK,MAAM,EAAE,IAAI,EAAE,KAAK,EAAE,IAAI,QAAQ,EAAE,CAAC;YACxC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC;gBAAE,SAAQ;YAEhC,KAAK,MAAM,CAAC,KAAK,EAAE,KAAK,CAAC,IAAI,QAAQ,EAAE,CAAC;gBACvC,IAAI,IAAI,CAAC,gBAAgB,CAAC,QAAQ,CAAC,KAAK,CAAC,IAAI,KAAK,IAAI,gCAAgC,EAAE,CAAC;oBACxF,KAAK,CAAC,IAAI,CAAC;wBACV,KAAK,EAAE,mBAAmB;wBAC1B,QAAQ,EAAE,IAAI,CAAC,QAAQ;wBACvB,MAAM,EAAE,IAAI,CAAC,EAAE;wBACf,KAAK;wBACL,UAAU,EAAE,KAAK;wBACjB,UAAU,EAAE,KAAK;wBACjB,MAAM,EAAE,UAAU,KAAK,kBAAkB,IAAI,CAAC,EAAE,mBAAmB,KAAK,IAAI,KAAK,2BAA2B,IAAI,CAAC,OAAO,EAAE;qBAC1H,CAAC,CAAA;gBACH,CAAC;YACF,CAAC;QACF,CAAC;IACF,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC;AAED,SAAS,WAAW,CAAC,KAAiB;IACrC,MAAM,KAAK,GAAoB,EAAE,CAAA;IAEjC,IAAI,KAAK,CAAC,aAAa,GAAG,CAAC,EAAE,CAAC;QAC7B,KAAK,CAAC,IAAI,CAAC;YACV,KAAK,EAAE,gBAAgB;YACvB,QAAQ,EAAE,OAAO;YACjB,MAAM,EAAE,GAAG,KAAK,CAAC,aAAa,uEAAuE;SACrG,CAAC,CAAA;IACH,CAAC;IAED,MAAM,SAAS,GAAG,KAAK,CAAC,QAAQ,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,KAAK,CAAC,QAAQ,CAAC,CAAA;IAE9D,IAAI,SAAS,IAAI,mBAAmB,EAAE,CAAC;QACtC,KAAK,CAAC,IAAI,CAAC;YACV,KAAK,EAAE,aAAa;YACpB,QAAQ,EAAE,MAAM;YAChB,MAAM,EAAE,GAAG,KAAK,CAAC,QAAQ,IAAI,KAAK,CAAC,QAAQ,UAAU,CAAC,SAAS,GAAG,GAAG,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,yDAAyD;SAC1I,CAAC,CAAA;IACH,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC;AAED,SAAS,YAAY,CACpB,IAAiE,EACjE,KAAiB,EACjB,KAAsB;IAEtB,MAAM,MAAM,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,OAAO,CAAC,CAAA;IAC1D,MAAM,KAAK,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,MAAM,CAAC,CAAA;IACxD,MAAM,OAAO,GAAG,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,eAAe,CAAA;IAE/D,MAAM,KAAK,GAAa;QACvB,kBAAkB,OAAO,EAAE;QAC3B,EAAE;QACF,kBAAkB,IAAI,CAAC,SAAS,IAAI;QACpC,yBAAyB,IAAI,CAAC,SAAS,IAAI;QAC3C,kBAAkB,IAAI,CAAC,SAAS,IAAI;QACpC,qBAAqB,KAAK,CAAC,QAAQ,EAAE;QACrC,wBAAwB,KAAK,CAAC,MAAM,CAAC,IAAI,EAAE;QAC3C,yBAAyB,KAAK,CAAC,OAAO,CAAC,IAAI,EAAE;QAC7C,EAAE;QACF,eAAe,MAAM,CAAC,MAAM,iFAAiF;QAC7G,iBAAiB,KAAK,CAAC,MAAM,aAAa;QAC1C,EAAE;KACF,CAAA;IAED,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,CAAC;QACnB,KAAK,CAAC,IAAI,CAAC,wBAAwB,CAAC,CAAA;QAEpC,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;IACxB,CAAC;IAED,MAAM,OAAO,GAAG,IAAI,GAAG,EAA2B,CAAA;IAElD,KAAK,MAAM,CAAC,IAAI,KAAK,EAAE,CAAC;QACvB,MAAM,GAAG,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,KAAK,CAAC,IAAI,EAAE,CAAA;QACtC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;QACX,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,KAAK,EAAE,GAAG,CAAC,CAAA;IAC1B,CAAC;IAED,KAAK,MAAM,CAAC,KAAK,EAAE,IAAI,CAAC,IAAI,OAAO,EAAE,CAAC;QACrC,KAAK,CAAC,IAAI,CAAC,MAAM,KAAK,KAAK,IAAI,CAAC,MAAM,GAAG,CAAC,CAAA;QAC1C,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAA;QACd,wDAAwD;QACxD,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,UAAU,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,UAAU,IAAI,CAAC,CAAC,CAAC,CAAA;QAE9D,KAAK,MAAM,CAAC,IAAI,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,EAAE,CAAC,EAAE,CAAC;YACnC,KAAK,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,QAAQ,CAAC,WAAW,EAAE,OAAO,CAAC,CAAC,MAAM,EAAE,CAAC,CAAA;QAC9D,CAAC;QAED,IAAI,IAAI,CAAC,MAAM,GAAG,mBAAmB,EAAE,CAAC;YACvC,KAAK,CAAC,IAAI,CAAC,aAAa,IAAI,CAAC,MAAM,GAAG,EAAE,OAAO,CAAC,CAAA;QACjD,CAAC;QAED,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC,CAAA;IACf,CAAC;IAED,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;AACxB,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,eAAe,CACpC,OAA+B,EAC/B,MAA+B;IAE/B,MAAM,SAAS,GAAG,OAAO,CAAC,SAAS,IAAI,gBAAgB,EAAE,CAAA;IACzD,MAAM,EAAE,CAAC,6BAA6B,OAAO,CAAC,SAAS,KAAK,CAAC,CAAA;IAC7D,MAAM,MAAM,GAAG,eAAe,CAAc,YAAY,CAAC,OAAO,CAAC,SAAS,EAAE,MAAM,CAAC,CAAC,CAAA;IAEpF,MAAM,EAAE,CACP,KAAK,MAAM,CAAC,SAAS,cAAc,MAAM,CAAC,WAAW,CAAC,MAAM,cAAc,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,MAAM,YAAY,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,MAAM,UAAU,CACnK,CAAA;IAED,MAAM,EAAE,CAAC,sBAAsB,OAAO,CAAC,SAAS,KAAK,CAAC,CAAA;IAEtD,MAAM,KAAK,GAAG,MAAM,cAAc,CAAC,WAAW,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC,CAAA;IAElE,MAAM,EAAE,CAAC,KAAK,KAAK,CAAC,QAAQ,OAAO,CAAC,CAAA;IAEpC,MAAM,EAAE,CAAC,sBAAsB,SAAS,KAAK,CAAC,CAAA;IAC9C,MAAM,SAAS,GAAG,eAAe,CAAgB,YAAY,CAAC,SAAS,EAAE,MAAM,CAAC,CAAC,CAAA;IAEjF,MAAM,EAAE,CAAC,mBAAmB,CAAC,CAAA;IAE7B,MAAM,KAAK,GAAoB;QAC9B,GAAG,yBAAyB,CAAC,KAAK,EAAE,MAAM,CAAC;QAC3C,GAAG,gBAAgB,CAAC,KAAK,EAAE,MAAM,CAAC;QAClC,GAAG,qBAAqB,CAAC,KAAK,EAAE,MAAM,CAAC;QACvC,GAAG,UAAU,CAAC,KAAK,EAAE,SAAS,CAAC;QAC/B,GAAG,WAAW,CAAC,KAAK,CAAC;KACrB,CAAA;IAED,MAAM,QAAQ,GAAG,YAAY,CAAC,EAAE,SAAS,EAAE,OAAO,CAAC,SAAS,EAAE,SAAS,EAAE,OAAO,CAAC,SAAS,EAAE,SAAS,EAAE,EAAE,KAAK,EAAE,KAAK,CAAC,CAAA;IAEtH,OAAO,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAA;IAErB,IAAI,OAAO,CAAC,KAAK,EAAE,CAAC;QACnB,aAAa,CAAC,OAAO,CAAC,KAAK,EAAE,QAAQ,CAAC,CAAA;IACvC,CAAC;IAED,IAAI,OAAO,CAAC,OAAO,EAAE,CAAC;QACrB,aAAa,CACZ,OAAO,CAAC,OAAO,EACf,IAAI,CAAC,SAAS,CACb;YACC,KAAK,EAAE,OAAO,CAAC,SAAS;YACxB,KAAK,EAAE,OAAO,CAAC,SAAS;YACxB,KAAK;YACL,OAAO,EAAE;gBACR,MAAM,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,OAAO,CAAC,CAAC,MAAM;gBAC1D,QAAQ,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,MAAM,CAAC,CAAC,MAAM;aAC3D;SACD,EACD,IAAI,EACJ,CAAC,CACD,CACD,CAAA;IACF,CAAC;IAED,MAAM,UAAU,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,OAAO,CAAC,CAAC,MAAM,CAAA;IACrE,MAAM,YAAY,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,KAAK,MAAM,CAAC,CAAC,MAAM,CAAA;IAEtE,IAAI,UAAU,GAAG,CAAC,EAAE,CAAC;QACpB,MAAM,EAAE,CAAC,gBAAgB,UAAU,YAAY,CAAC,CAAA;IACjD,CAAC;SAAM,CAAC;QACP,MAAM,EAAE,CAAC,cAAc,CAAC,CAAA;IACzB,CAAC;IAED,OAAO,EAAE,MAAM,EAAE,UAAU,EAAE,QAAQ,EAAE,YAAY,EAAE,QAAQ,EAAE,KAAK,EAAE,MAAM,EAAE,QAAQ,EAAE,CAAA;AACzF,CAAC"}
|
|
@@ -1,39 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Assemble a corpus OVERLAY MANIFEST — generalized from assemble-fr-admin-split-overlay-manifest.
|
|
7
|
-
* ADDS one shard parquet to a base corpus, keeping every base shard VERBATIM (pure overlay ADD),
|
|
8
|
-
* and re-roots base paths to /data (the Modal volume). Parameterized by --shard-parquet +
|
|
9
|
-
* --source so it works for any overlay shard (the fr-admin-split one is the original; #148's
|
|
10
|
-
* overture-multilocale is the second user).
|
|
11
|
-
*
|
|
12
|
-
* Ported faithfully from scripts/assemble-overlay-manifest.py. The new shard's source_id column is
|
|
13
|
-
* read through DuckDB (`@duckdb/node-api`) instead of PyArrow; everything else is pure JSON.
|
|
14
|
-
*
|
|
15
|
-
* Pipeline (the recipe rides the result): node scripts/build-overture-multilocale-canonical.mjs
|
|
16
|
-
* --cap 150000 --out /tmp/ovl/overture-ml.canonical.jsonl node scripts/align-canonical-shard.ts
|
|
17
|
-
* --input <canonical> --output <labeled> --corpus-version 0.5.0 mailwoman dev jsonl-to-parquet
|
|
18
|
-
* --input <labeled> --output <NEW>/train/<shard-parquet> node
|
|
19
|
-
* scripts/assemble-overlay-manifest.ts --base <BASE>/MANIFEST.json --new-dir <NEW>\
|
|
20
|
-
* --modal-root /data/corpus/versioned/<ver>/<dir> --version <ver>\
|
|
21
|
-
* --shard-parquet <shard-parquet> --source <source> --note "..."
|
|
22
|
-
*
|
|
23
|
-
* # then push the overlay to R2 + sync + `modal run -d ... --config <recipe>.yaml --resume none`.
|
|
24
|
-
*/
|
|
25
|
-
export interface OverlayManifestOptions {
|
|
26
|
-
base: string;
|
|
27
|
-
newDir: string;
|
|
28
|
-
modalRoot: string;
|
|
29
|
-
version: string;
|
|
30
|
-
shardParquet: string;
|
|
31
|
-
source: string;
|
|
32
|
-
note: string;
|
|
33
|
-
}
|
|
34
|
-
/**
|
|
35
|
-
* Resolve a base manifest's shard path to the mounted corpus tree used by Modal.
|
|
36
|
-
*/
|
|
37
|
-
export declare function rerootBaseShardPath(path: string, baseManifestPath: string): string;
|
|
38
|
-
export declare function assembleOverlayManifest(args: OverlayManifestOptions): Promise<void>;
|
|
39
|
-
//# sourceMappingURL=overlay-manifest.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"overlay-manifest.d.ts","sourceRoot":"","sources":["../../../src/tools/overlay-manifest.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAiEH,MAAM,WAAW,sBAAsB;IACtC,IAAI,EAAE,MAAM,CAAA;IACZ,MAAM,EAAE,MAAM,CAAA;IACd,SAAS,EAAE,MAAM,CAAA;IACjB,OAAO,EAAE,MAAM,CAAA;IACf,YAAY,EAAE,MAAM,CAAA;IACpB,MAAM,EAAE,MAAM,CAAA;IACd,IAAI,EAAE,MAAM,CAAA;CACZ;AAED;;GAEG;AACH,wBAAgB,mBAAmB,CAAC,IAAI,EAAE,MAAM,EAAE,gBAAgB,EAAE,MAAM,GAAG,MAAM,CAalF;AAED,wBAAsB,uBAAuB,CAAC,IAAI,EAAE,sBAAsB,GAAG,OAAO,CAAC,IAAI,CAAC,CAwCzF"}
|
|
@@ -1,98 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Assemble a corpus OVERLAY MANIFEST — generalized from assemble-fr-admin-split-overlay-manifest.
|
|
7
|
-
* ADDS one shard parquet to a base corpus, keeping every base shard VERBATIM (pure overlay ADD),
|
|
8
|
-
* and re-roots base paths to /data (the Modal volume). Parameterized by --shard-parquet +
|
|
9
|
-
* --source so it works for any overlay shard (the fr-admin-split one is the original; #148's
|
|
10
|
-
* overture-multilocale is the second user).
|
|
11
|
-
*
|
|
12
|
-
* Ported faithfully from scripts/assemble-overlay-manifest.py. The new shard's source_id column is
|
|
13
|
-
* read through DuckDB (`@duckdb/node-api`) instead of PyArrow; everything else is pure JSON.
|
|
14
|
-
*
|
|
15
|
-
* Pipeline (the recipe rides the result): node scripts/build-overture-multilocale-canonical.mjs
|
|
16
|
-
* --cap 150000 --out /tmp/ovl/overture-ml.canonical.jsonl node scripts/align-canonical-shard.ts
|
|
17
|
-
* --input <canonical> --output <labeled> --corpus-version 0.5.0 mailwoman dev jsonl-to-parquet
|
|
18
|
-
* --input <labeled> --output <NEW>/train/<shard-parquet> node
|
|
19
|
-
* scripts/assemble-overlay-manifest.ts --base <BASE>/MANIFEST.json --new-dir <NEW>\
|
|
20
|
-
* --modal-root /data/corpus/versioned/<ver>/<dir> --version <ver>\
|
|
21
|
-
* --shard-parquet <shard-parquet> --source <source> --note "..."
|
|
22
|
-
*
|
|
23
|
-
* # then push the overlay to R2 + sync + `modal run -d ... --config <recipe>.yaml --resume none`.
|
|
24
|
-
*/
|
|
25
|
-
import { readFileSync, statSync, writeFileSync } from "node:fs";
|
|
26
|
-
import { basename, dirname, join } from "node:path";
|
|
27
|
-
import { parseJSONStrict } from "@mailwoman/core/objects";
|
|
28
|
-
import { sha256Hex } from "@mailwoman/core/utils";
|
|
29
|
-
/**
|
|
30
|
-
* Escape a path for single-quoted SQL string literals.
|
|
31
|
-
*/
|
|
32
|
-
function sqlString(value) {
|
|
33
|
-
return value.replaceAll("'", "''");
|
|
34
|
-
}
|
|
35
|
-
async function descriptor(localPath, modalPath, split, source) {
|
|
36
|
-
// @duckdb/node-api is an optional peer — lazy import (the pipeline convention).
|
|
37
|
-
const { DuckDBInstance } = await import("@duckdb/node-api");
|
|
38
|
-
const instance = await DuckDBInstance.create();
|
|
39
|
-
const db = await instance.connect();
|
|
40
|
-
const result = await db.runAndReadAll(`SELECT source_id FROM read_parquet('${sqlString(localPath)}')`);
|
|
41
|
-
const sids = result.getRowObjects().map((r) => r.source_id);
|
|
42
|
-
return {
|
|
43
|
-
split,
|
|
44
|
-
path: modalPath,
|
|
45
|
-
format: "parquet",
|
|
46
|
-
compression: "SNAPPY",
|
|
47
|
-
rows: sids.length,
|
|
48
|
-
bytes: statSync(localPath).size,
|
|
49
|
-
sha256: sha256Hex(readFileSync(localPath)),
|
|
50
|
-
first_source_id: sids[0],
|
|
51
|
-
last_source_id: sids.at(-1),
|
|
52
|
-
source,
|
|
53
|
-
};
|
|
54
|
-
}
|
|
55
|
-
/**
|
|
56
|
-
* Resolve a base manifest's shard path to the mounted corpus tree used by Modal.
|
|
57
|
-
*/
|
|
58
|
-
export function rerootBaseShardPath(path, baseManifestPath) {
|
|
59
|
-
const versionedIndex = path.indexOf("/corpus/versioned/");
|
|
60
|
-
if (versionedIndex !== -1)
|
|
61
|
-
return "/data" + path.slice(versionedIndex);
|
|
62
|
-
if (/^\/data\/(?:train|val|test)\//u.test(path)) {
|
|
63
|
-
const localBaseDir = dirname(baseManifestPath);
|
|
64
|
-
const baseModalRoot = `/data/corpus/versioned/${basename(dirname(localBaseDir))}/${basename(localBaseDir)}`;
|
|
65
|
-
return baseModalRoot + path.slice("/data".length);
|
|
66
|
-
}
|
|
67
|
-
return path;
|
|
68
|
-
}
|
|
69
|
-
export async function assembleOverlayManifest(args) {
|
|
70
|
-
const base = parseJSONStrict(readFileSync(args.base, "utf8"));
|
|
71
|
-
if (base.shards.some((s) => s.source === args.source)) {
|
|
72
|
-
console.log(`WARN: base already contains source '${args.source}' — is this the right base?`);
|
|
73
|
-
}
|
|
74
|
-
const kept = base.shards.map((s) => ({ ...s, path: rerootBaseShardPath(s.path, args.base) }));
|
|
75
|
-
const newTrain = await descriptor(join(args.newDir, "train", args.shardParquet), `${args.modalRoot}/train/${args.shardParquet}`, "train", args.source);
|
|
76
|
-
const manifest = {
|
|
77
|
-
corpus_version: args.version,
|
|
78
|
-
overlay_base: base.corpus_version ?? null,
|
|
79
|
-
note: args.note || `${base.corpus_version} shards (all kept verbatim) + the ${args.source} shard. Pure overlay add.`,
|
|
80
|
-
schema: base.schema,
|
|
81
|
-
rows_per_shard: base.rows_per_shard,
|
|
82
|
-
row_group_size: base.row_group_size,
|
|
83
|
-
shards: [...kept, newTrain],
|
|
84
|
-
counts: {
|
|
85
|
-
train: base.counts.train + newTrain.rows,
|
|
86
|
-
val: base.counts.val,
|
|
87
|
-
test: base.counts.test,
|
|
88
|
-
},
|
|
89
|
-
total_rows: base.total_rows + newTrain.rows,
|
|
90
|
-
};
|
|
91
|
-
const out = join(args.newDir, "MANIFEST.json");
|
|
92
|
-
writeFileSync(out, JSON.stringify(manifest, null, 1) + "\n");
|
|
93
|
-
console.log(`wrote ${out}`);
|
|
94
|
-
console.log(` shards: ${manifest.shards.length} (${kept.length} base kept, +1 ${args.source})`);
|
|
95
|
-
console.log(` counts: ${JSON.stringify(manifest.counts)} total: ${manifest.total_rows}`);
|
|
96
|
-
console.log(` ${args.source} train: ${newTrain.rows} rows (${newTrain.bytes} bytes)`);
|
|
97
|
-
}
|
|
98
|
-
//# sourceMappingURL=overlay-manifest.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"overlay-manifest.js","sourceRoot":"","sources":["../../../src/tools/overlay-manifest.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAEH,OAAO,EAAE,YAAY,EAAE,QAAQ,EAAE,aAAa,EAAE,MAAM,SAAS,CAAA;AAC/D,OAAO,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAEnD,OAAO,EAAE,eAAe,EAAE,MAAM,yBAAyB,CAAA;AACzD,OAAO,EAAE,SAAS,EAAE,MAAM,uBAAuB,CAAA;AAyBjD;;GAEG;AACH,SAAS,SAAS,CAAC,KAAa;IAC/B,OAAO,KAAK,CAAC,UAAU,CAAC,GAAG,EAAE,IAAI,CAAC,CAAA;AACnC,CAAC;AAED,KAAK,UAAU,UAAU,CACxB,SAAiB,EACjB,SAAiB,EACjB,KAAa,EACb,MAAc;IAEd,gFAAgF;IAChF,MAAM,EAAE,cAAc,EAAE,GAAG,MAAM,MAAM,CAAC,kBAAkB,CAAC,CAAA;IAC3D,MAAM,QAAQ,GAAG,MAAM,cAAc,CAAC,MAAM,EAAE,CAAA;IAC9C,MAAM,EAAE,GAAG,MAAM,QAAQ,CAAC,OAAO,EAAE,CAAA;IACnC,MAAM,MAAM,GAAG,MAAM,EAAE,CAAC,aAAa,CAAC,uCAAuC,SAAS,CAAC,SAAS,CAAC,IAAI,CAAC,CAAA;IACtG,MAAM,IAAI,GAAG,MAAM,CAAC,aAAa,EAAE,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,SAAmB,CAAC,CAAA;IAErE,OAAO;QACN,KAAK;QACL,IAAI,EAAE,SAAS;QACf,MAAM,EAAE,SAAS;QACjB,WAAW,EAAE,QAAQ;QACrB,IAAI,EAAE,IAAI,CAAC,MAAM;QACjB,KAAK,EAAE,QAAQ,CAAC,SAAS,CAAC,CAAC,IAAI;QAC/B,MAAM,EAAE,SAAS,CAAC,YAAY,CAAC,SAAS,CAAC,CAAC;QAC1C,eAAe,EAAE,IAAI,CAAC,CAAC,CAAE;QACzB,cAAc,EAAE,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC,CAAE;QAC5B,MAAM;KACN,CAAA;AACF,CAAC;AAYD;;GAEG;AACH,MAAM,UAAU,mBAAmB,CAAC,IAAY,EAAE,gBAAwB;IACzE,MAAM,cAAc,GAAG,IAAI,CAAC,OAAO,CAAC,oBAAoB,CAAC,CAAA;IAEzD,IAAI,cAAc,KAAK,CAAC,CAAC;QAAE,OAAO,OAAO,GAAG,IAAI,CAAC,KAAK,CAAC,cAAc,CAAC,CAAA;IAEtE,IAAI,gCAAgC,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;QACjD,MAAM,YAAY,GAAG,OAAO,CAAC,gBAAgB,CAAC,CAAA;QAC9C,MAAM,aAAa,GAAG,0BAA0B,QAAQ,CAAC,OAAO,CAAC,YAAY,CAAC,CAAC,IAAI,QAAQ,CAAC,YAAY,CAAC,EAAE,CAAA;QAE3G,OAAO,aAAa,GAAG,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,MAAM,CAAC,CAAA;IAClD,CAAC;IAED,OAAO,IAAI,CAAA;AACZ,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,uBAAuB,CAAC,IAA4B;IACzE,MAAM,IAAI,GAAG,eAAe,CAAe,YAAY,CAAC,IAAI,CAAC,IAAI,EAAE,MAAM,CAAC,CAAC,CAAA;IAE3E,IAAI,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,KAAK,IAAI,CAAC,MAAM,CAAC,EAAE,CAAC;QACvD,OAAO,CAAC,GAAG,CAAC,uCAAuC,IAAI,CAAC,MAAM,6BAA6B,CAAC,CAAA;IAC7F,CAAC;IAED,MAAM,IAAI,GAAG,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,EAAE,GAAG,CAAC,EAAE,IAAI,EAAE,mBAAmB,CAAC,CAAC,CAAC,IAAI,EAAE,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAA;IAE7F,MAAM,QAAQ,GAAG,MAAM,UAAU,CAChC,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,OAAO,EAAE,IAAI,CAAC,YAAY,CAAC,EAC7C,GAAG,IAAI,CAAC,SAAS,UAAU,IAAI,CAAC,YAAY,EAAE,EAC9C,OAAO,EACP,IAAI,CAAC,MAAM,CACX,CAAA;IAED,MAAM,QAAQ,GAAG;QAChB,cAAc,EAAE,IAAI,CAAC,OAAO;QAC5B,YAAY,EAAE,IAAI,CAAC,cAAc,IAAI,IAAI;QACzC,IAAI,EACH,IAAI,CAAC,IAAI,IAAI,GAAG,IAAI,CAAC,cAAc,qCAAqC,IAAI,CAAC,MAAM,2BAA2B;QAC/G,MAAM,EAAE,IAAI,CAAC,MAAM;QACnB,cAAc,EAAE,IAAI,CAAC,cAAc;QACnC,cAAc,EAAE,IAAI,CAAC,cAAc;QACnC,MAAM,EAAE,CAAC,GAAG,IAAI,EAAE,QAAQ,CAAC;QAC3B,MAAM,EAAE;YACP,KAAK,EAAE,IAAI,CAAC,MAAM,CAAC,KAAK,GAAG,QAAQ,CAAC,IAAI;YACxC,GAAG,EAAE,IAAI,CAAC,MAAM,CAAC,GAAG;YACpB,IAAI,EAAE,IAAI,CAAC,MAAM,CAAC,IAAI;SACtB;QACD,UAAU,EAAE,IAAI,CAAC,UAAU,GAAG,QAAQ,CAAC,IAAI;KAC3C,CAAA;IAED,MAAM,GAAG,GAAG,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,eAAe,CAAC,CAAA;IAC9C,aAAa,CAAC,GAAG,EAAE,IAAI,CAAC,SAAS,CAAC,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC,GAAG,IAAI,CAAC,CAAA;IAE5D,OAAO,CAAC,GAAG,CAAC,SAAS,GAAG,EAAE,CAAC,CAAA;IAC3B,OAAO,CAAC,GAAG,CAAC,aAAa,QAAQ,CAAC,MAAM,CAAC,MAAM,KAAK,IAAI,CAAC,MAAM,kBAAkB,IAAI,CAAC,MAAM,GAAG,CAAC,CAAA;IAChG,OAAO,CAAC,GAAG,CAAC,aAAa,IAAI,CAAC,SAAS,CAAC,QAAQ,CAAC,MAAM,CAAC,YAAY,QAAQ,CAAC,UAAU,EAAE,CAAC,CAAA;IAC1F,OAAO,CAAC,GAAG,CAAC,KAAK,IAAI,CAAC,MAAM,WAAW,QAAQ,CAAC,IAAI,UAAU,QAAQ,CAAC,KAAK,SAAS,CAAC,CAAA;AACvF,CAAC"}
|
|
@@ -1,112 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Overture Places source for the sub-venue lexicon (#35 wave 2) — read the sub-venue-bearing
|
|
7
|
-
* category slices of `poi.db` (spatial layer #1, `$MAILWOMAN_DATA_ROOT/poi/poi.db`) and yield
|
|
8
|
-
* {@link SubVenueHarvestRow}s the lexicon builder consumes exactly like an OSM extract.
|
|
9
|
-
*
|
|
10
|
-
* ── WHY OVERTURE AT ALL, when the OSM extractor already exists ────────────────────────────────────
|
|
11
|
-
* Wave 1 measured `concourse` at 21 real Overture rows against 4 in the whole Great Britain OSM
|
|
12
|
-
* extract, 3 of which are a street called CONCOURSE WAY. Overture's `airport_terminal` category is
|
|
13
|
-
* curated venue-interior naming; OSM's `aeroway=terminal` is a building footprint that usually
|
|
14
|
-
* carries the AIRPORT's name. The two sources fail differently, so both are read.
|
|
15
|
-
*
|
|
16
|
-
* ── THE CATEGORY SET IS MEASURED, NOT GUESSED ────────────────────────────────────────────────────
|
|
17
|
-
* A full scan of all 13,681,698 rows (2026-08-05, poi.db vintage 2026-05-20.0) counted, per
|
|
18
|
-
* category, how many named rows carry a designator token. The ranking is NOT what a category name
|
|
19
|
-
* predicts — `gas_station` leads the whole table with 12,996 hits, every one of them the token
|
|
20
|
-
* `station` inside "Holiday Station" / "Chevron Station Seward", and `shoe_store` contributes 708
|
|
21
|
-
* hits of `wing` because Red Wing sells boots. {@link OVERTURE_SUBVENUE_CATEGORIES} is the four
|
|
22
|
-
* categories whose hits survived reading the distribution; the rejects are listed below it so nobody
|
|
23
|
-
* re-proposes them.
|
|
24
|
-
*
|
|
25
|
-
* ── poi.db IS FOUR COUNTRIES ─────────────────────────────────────────────────────────────────────
|
|
26
|
-
* Measured the same day: US 11,521,612 / CA 794,418 / FR 721,352 / MX 644,316, and nothing else. The
|
|
27
|
-
* shipped layer is not a world gazetteer, so Overture can attest en-US, en-CA, fr-FR and es-MX
|
|
28
|
-
* surfaces and NOTHING ELSE. Every non-Latin designator the corpus task asks for — `ターミナル`,
|
|
29
|
-
* `Halle`, `Flügel` — has to come from the OSM leg. Do not read a zero count here as evidence of
|
|
30
|
-
* absence in the world; it is evidence of absence in four countries.
|
|
31
|
-
*
|
|
32
|
-
* ── The row shape fits; the PROVENANCE STAMP did not ─────────────────────────────────────────────
|
|
33
|
-
* Wave 1's `OSMSubVenueRow` was written to accept a non-OSM row, and it does: an Overture row is
|
|
34
|
-
* `{ designatorID, name }` with no `ref` and no `localizedNames`. What did NOT fit is
|
|
35
|
-
* `extractAttestedPhrases`, which hardcoded `osm:name` as the surface's `source`. Feeding Overture
|
|
36
|
-
* rows through it unchanged would have labelled every Overture surface as OSM-attested — a
|
|
37
|
-
* provenance lie, and under ODbL a consequential one. Hence the `source`/`region` options on that
|
|
38
|
-
* function and the source-neutral {@link SubVenueHarvestRow} name.
|
|
39
|
-
*/
|
|
40
|
-
import type { SubVenueHarvestRow } from "./sub-venue-lexicon.ts";
|
|
41
|
-
/**
|
|
42
|
-
* Overture Places category → the designator its rows attest.
|
|
43
|
-
*
|
|
44
|
-
* Each entry carries the 2026-08-05 full-scan measurement in a comment: `rows` is the category's total, `hits` is how
|
|
45
|
-
* many of its named rows contain any designator token, and the token list is the top of that distribution.
|
|
46
|
-
*
|
|
47
|
-
* REJECTED, with the number that rejected them — do not re-add without a fresh census:
|
|
48
|
-
*
|
|
49
|
-
* - `gas_station` (12,996 hits) — all `station` inside a brand name (Holiday Station, Chevron Station Seward).
|
|
50
|
-
* - `fire_station` (10,377) — same, plus 330 `hall` from fire halls, which are venues rather than sub-venues.
|
|
51
|
-
* - `town_hall` (5,528) — `City Hall` is a whole building, the `venue` tier, not interior structure.
|
|
52
|
-
* - `building_supply_store` (4,030) — `building` inside "Allied Building Products".
|
|
53
|
-
* - `jehovahs_witness_place_of_worship` (2,334) — every hit is "Kingdom Hall of Jehovah's Witnesses".
|
|
54
|
-
* - `shoe_store` (909, of which 708 `wing`) — Red Wing. This one is a CONFOUND BOARD entry, not a source.
|
|
55
|
-
* - `college_university` (3,697) — 2,082 `campus`, but the row names the whole institution; `campus_building` is the
|
|
56
|
-
* interior slice and is kept instead.
|
|
57
|
-
* - `airport` (6,000 rows, 4,302 hits) — 4,071 of them are the token `airport` in the aerodrome's own name. Venue tier,
|
|
58
|
-
* already covered by OurAirports, and it drowns the interior signal.
|
|
59
|
-
* - `transport_interchange` (1 row), `rail_facility_or_service` (81 rows, 2 hits) — too small to matter.
|
|
60
|
-
* - `public_transit_facility_or_service` (2,274 rows, 185 hits) — 161 are `station` naming the station itself.
|
|
61
|
-
*/
|
|
62
|
-
export declare const OVERTURE_SUBVENUE_CATEGORIES: Readonly<Record<string, string>>;
|
|
63
|
-
/**
|
|
64
|
-
* The layer's `source_vintage` — the Overture release the rows came from (`2026-05-20.0`), for the lexicon's
|
|
65
|
-
* `sources[]`.
|
|
66
|
-
*
|
|
67
|
-
* Read off the database rather than passed in, because a vintage a caller types is a vintage that goes stale silently.
|
|
68
|
-
* The layer-contract tables are part of every layer database by construction — see `docs/engineering/reference/
|
|
69
|
-
* layer-contract.mdx` — so there is no version of poi.db where this is absent.
|
|
70
|
-
*/
|
|
71
|
-
export declare function readOvertureLayerVintage(databasePath: string): Promise<string>;
|
|
72
|
-
export interface ReadOvertureSubVenuesOptions {
|
|
73
|
-
/**
|
|
74
|
-
* Path to `poi.db`. Typically `dataRootPath("poi", "poi.db")`.
|
|
75
|
-
*/
|
|
76
|
-
databasePath: string;
|
|
77
|
-
/**
|
|
78
|
-
* Category → designator map. Defaults to {@link OVERTURE_SUBVENUE_CATEGORIES}.
|
|
79
|
-
*/
|
|
80
|
-
categories?: Readonly<Record<string, string>>;
|
|
81
|
-
/**
|
|
82
|
-
* Restrict to these ISO 3166-1 alpha-2 countries. Omit for all four the layer carries.
|
|
83
|
-
*/
|
|
84
|
-
countries?: readonly string[];
|
|
85
|
-
}
|
|
86
|
-
/**
|
|
87
|
-
* One Overture row plus the country it came from — {@link SubVenueHarvestRow} widened by the field the layer has and an
|
|
88
|
-
* OSM extract does not (a Geofabrik extract's country is a property of the invocation, so OSM rows carry `country:
|
|
89
|
-
* ""`).
|
|
90
|
-
*/
|
|
91
|
-
export interface OvertureSubVenueRow extends SubVenueHarvestRow {
|
|
92
|
-
/**
|
|
93
|
-
* ISO 3166-1 alpha-2, straight off the Overture partition.
|
|
94
|
-
*/
|
|
95
|
-
country: string;
|
|
96
|
-
/**
|
|
97
|
-
* The Overture category the row was read from, so a surface's provenance survives past the designator.
|
|
98
|
-
*/
|
|
99
|
-
category: string;
|
|
100
|
-
}
|
|
101
|
-
/**
|
|
102
|
-
* Read the sub-venue-bearing category slices of `poi.db`.
|
|
103
|
-
*
|
|
104
|
-
* Cold path, already async, no interface constraint — so Kysely, per the repo's inline-SQL rule.
|
|
105
|
-
*
|
|
106
|
-
* `category_id` is the SECOND component of poi.db's clustered `(h3_cell, category_id, …)` primary key, which reads like
|
|
107
|
-
* a full 13.7M-row scan and is not one: SQLite skip-scans the leading `h3_cell` and the whole four-category read
|
|
108
|
-
* returned 9,219 rows in **1.4 s** on the shipped layer (2026-08-05). A JS-side scan of every row to survey the same
|
|
109
|
-
* question took 52 s, which is the number to remember if you are tempted to filter in JS instead.
|
|
110
|
-
*/
|
|
111
|
-
export declare function readOvertureSubVenues(options: ReadOvertureSubVenuesOptions): Promise<OvertureSubVenueRow[]>;
|
|
112
|
-
//# sourceMappingURL=overture-subvenue.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"overture-subvenue.d.ts","sourceRoot":"","sources":["../../../src/tools/overture-subvenue.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAsCG;AAMH,OAAO,KAAK,EAAE,kBAAkB,EAAE,MAAM,wBAAwB,CAAA;AAEhE;;;;;;;;;;;;;;;;;;;;GAoBG;AACH,eAAO,MAAM,4BAA4B,EAAE,QAAQ,CAAC,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAczE,CAAA;AA0BD;;;;;;;GAOG;AACH,wBAAsB,wBAAwB,CAAC,YAAY,EAAE,MAAM,GAAG,OAAO,CAAC,MAAM,CAAC,CAYpF;AAED,MAAM,WAAW,4BAA4B;IAC5C;;OAEG;IACH,YAAY,EAAE,MAAM,CAAA;IACpB;;OAEG;IACH,UAAU,CAAC,EAAE,QAAQ,CAAC,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC,CAAA;IAC7C;;OAEG;IACH,SAAS,CAAC,EAAE,SAAS,MAAM,EAAE,CAAA;CAC7B;AAED;;;;GAIG;AACH,MAAM,WAAW,mBAAoB,SAAQ,kBAAkB;IAC9D;;OAEG;IACH,OAAO,EAAE,MAAM,CAAA;IACf;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAA;CAChB;AAED;;;;;;;;;GASG;AACH,wBAAsB,qBAAqB,CAAC,OAAO,EAAE,4BAA4B,GAAG,OAAO,CAAC,mBAAmB,EAAE,CAAC,CA4CjH"}
|