@mailwoman/corpus 9.1.0 → 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 +24 -24
- package/data/PROVENANCE.md +20 -7
- package/data/reviewed-ve-postcode-tuples.json +74 -0
- 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/state-ia-contractors/adapter.ts +144 -0
- package/lib/adapters/state-ny-notaries/adapter.ts +141 -0
- package/lib/adapters/state-tx-notaries/adapter.ts +157 -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/license.ts +50 -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 +44 -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 +68 -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 +46 -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 +72 -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 +34 -0
- package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.js +111 -0
- package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.d.ts +32 -0
- package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.js +119 -0
- package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.d.ts +33 -0
- package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.js +125 -0
- package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
- package/out/adapters/synth-po-box/adapter.d.ts +67 -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 +39 -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 +46 -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 +65 -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 +14 -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 +47 -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 +350 -65
- package/out/src/adapters/ban/adapter.d.ts +0 -44
- package/out/src/adapters/ban/adapter.d.ts.map +0 -1
- package/out/src/adapters/ban/adapter.js +0 -148
- 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 +0 -68
- 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 +0 -46
- 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 +0 -72
- 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 -132
- package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.d.ts +0 -34
- package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.js +0 -106
- package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.d.ts +0 -32
- package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.js +0 -125
- package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.d.ts +0 -33
- package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.js +0 -120
- package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.d.ts +0 -67
- 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 -138
- 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 -110
- 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 -123
- 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 +0 -39
- 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 +0 -46
- 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 -155
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
- package/out/src/adapters/utils/index.d.ts +0 -144
- package/out/src/adapters/utils/index.d.ts.map +0 -1
- package/out/src/adapters/utils/index.js +0 -151
- package/out/src/adapters/utils/index.js.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.d.ts +0 -65
- 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 -93
- package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.js +0 -248
- package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -70
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.js +0 -185
- package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
- package/out/src/build.d.ts +0 -131
- package/out/src/build.d.ts.map +0 -1
- package/out/src/build.js +0 -248
- 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 -64
- 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 -83
- package/out/src/shard-recipes/anchor-absorption.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 -405
- 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 -82
- 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 -187
- 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 -82
- 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 -225
- 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 -207
- 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 -83
- 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 -458
- 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/scaffold.d.ts +0 -217
- package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
- package/out/src/shard-recipes/scaffold.js +0 -138
- 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 -709
- package/out/src/shard-recipes/sub-venue.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 -253
- 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 -220
- 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 -707
- 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 -255
- package/out/src/tools/fetch/ban.js.map +0 -1
- package/out/src/tools/fetch/download.d.ts +0 -69
- package/out/src/tools/fetch/download.d.ts.map +0 -1
- package/out/src/tools/fetch/download.js +0 -100
- package/out/src/tools/fetch/download.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 -133
- package/out/src/tools/fetch/index.d.ts.map +0 -1
- package/out/src/tools/fetch/index.js +0 -132
- 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 -225
- 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 -124
- 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 -316
- 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 -123
- package/out/src/tools/fetch/ourairports.js.map +0 -1
- package/out/src/tools/fetch/ppd.d.ts +0 -18
- 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 -178
- package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
- package/out/src/tools/fetch/state-sources.d.ts +0 -22
- package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
- package/out/src/tools/fetch/state-sources.js +0 -115
- 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 -254
- 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 -404
- 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 -307
- 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 -35
- package/out/src/tools/overlay-manifest.d.ts.map +0 -1
- package/out/src/tools/overlay-manifest.js +0 -88
- 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/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 -101
- 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 -197
- package/out/src/tools/shard-translit.js.map +0 -1
- package/out/src/tools/sub-venue-lexicon.d.ts +0 -507
- package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
- package/out/src/tools/sub-venue-lexicon.js +0 -817
- 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 +0 -47
- package/out/src/utils/license.js.map +0 -1
- package/out/src/utils/parquet.d.ts +0 -143
- package/out/src/utils/parquet.d.ts.map +0 -1
- package/out/src/utils/parquet.js +0 -258
- 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 -189
- package/src/adapters/ban/street-decompose.ts +0 -96
- package/src/adapters/fcc-bdc/adapter.ts +0 -173
- package/src/adapters/geonames/adapter.ts +0 -199
- package/src/adapters/geonames-postal/adapter.ts +0 -118
- package/src/adapters/gnaf/adapter.ts +0 -148
- package/src/adapters/gnaf/assemble.ts +0 -226
- package/src/adapters/index.ts +0 -149
- package/src/adapters/openaddresses/adapter.ts +0 -250
- package/src/adapters/overture/adapter.ts +0 -161
- package/src/adapters/state-hi-schools/adapter.ts +0 -162
- package/src/adapters/state-ia-contractors/adapter.ts +0 -138
- package/src/adapters/state-ny-notaries/adapter.ts +0 -159
- package/src/adapters/state-tx-notaries/adapter.ts +0 -151
- package/src/adapters/synth-po-box/adapter.ts +0 -203
- package/src/adapters/tiger/adapter.ts +0 -252
- package/src/adapters/tiger/street-decompose.ts +0 -111
- package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -181
- package/src/adapters/usgov-imls-pls/adapter.ts +0 -138
- package/src/adapters/usgov-irs-bmf/adapter.ts +0 -161
- package/src/adapters/usgov-nad/adapter.ts +0 -347
- package/src/adapters/usgov-nppes/adapter.ts +0 -157
- package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -202
- package/src/adapters/utils/index.ts +0 -220
- package/src/adapters/wof-admin-jp/adapter.ts +0 -219
- package/src/adapters/wof-admin-json/adapter.ts +0 -294
- package/src/adapters/wof-postalcode-json/adapter.ts +0 -216
- 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 -88
- package/src/parquet-wrapper/schema.ts +0 -88
- package/src/parquet-wrapper/writer.ts +0 -110
- package/src/runner.ts +0 -322
- package/src/shard-recipes/anchor-absorption.ts +0 -103
- package/src/shard-recipes/boundary-stress.ts +0 -104
- package/src/shard-recipes/country-balanced.ts +0 -522
- package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -92
- package/src/shard-recipes/fr-admin-split.ts +0 -237
- package/src/shard-recipes/fr-bare-street.ts +0 -95
- package/src/shard-recipes/fr-fragment.ts +0 -332
- package/src/shard-recipes/fr-lieudit.ts +0 -300
- package/src/shard-recipes/fr-order.ts +0 -256
- package/src/shard-recipes/german.ts +0 -169
- package/src/shard-recipes/house-venue.ts +0 -88
- package/src/shard-recipes/index.ts +0 -89
- package/src/shard-recipes/intersection.ts +0 -629
- package/src/shard-recipes/locale.ts +0 -601
- 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 -919
- package/src/shard-recipes/po-box.ts +0 -123
- package/src/shard-recipes/scaffold.ts +0 -329
- package/src/shard-recipes/si-bare-village.ts +0 -97
- package/src/shard-recipes/street-affix.ts +0 -825
- 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 -895
- package/src/shard-recipes/sub-venue.ts +0 -982
- package/src/shard-recipes/unit.ts +0 -320
- package/src/synthesizers/anchor-absorption.ts +0 -290
- package/src/synthesizers/boundary-stress.ts +0 -531
- package/src/synthesizers/german.ts +0 -250
- package/src/synthesizers/house-venue.ts +0 -316
- 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 -272
- package/src/synthesizers/utils.ts +0 -901
- package/src/tools/align-shard.ts +0 -69
- package/src/tools/audit.ts +0 -399
- package/src/tools/corpus-stats.ts +0 -184
- package/src/tools/fetch/ban.ts +0 -310
- package/src/tools/fetch/download.ts +0 -158
- package/src/tools/fetch/hrsa.ts +0 -68
- package/src/tools/fetch/imls-pls.ts +0 -158
- package/src/tools/fetch/index.ts +0 -136
- package/src/tools/fetch/nad.ts +0 -331
- package/src/tools/fetch/nppes.ts +0 -172
- package/src/tools/fetch/openaddresses.ts +0 -408
- package/src/tools/fetch/ourairports.ts +0 -166
- package/src/tools/fetch/ppd.ts +0 -137
- package/src/tools/fetch/state-hi-schools.ts +0 -228
- package/src/tools/fetch/state-sources.ts +0 -155
- package/src/tools/fetch/tiger-full.ts +0 -361
- package/src/tools/fetch/wikidata-subvenue.ts +0 -386
- package/src/tools/golden-expand.ts +0 -573
- 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 -435
- 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 -145
- package/src/tools/overture-subvenue.ts +0 -215
- package/src/tools/shard-kryptonite.ts +0 -138
- package/src/tools/shard-translit.ts +0 -270
- package/src/tools/sub-venue-lexicon.ts +0 -1250
- package/src/tools/sub-venue-promotions.ts +0 -330
- package/src/types.ts +0 -247
- package/src/utils/align.ts +0 -330
- package/src/utils/golden.ts +0 -176
- package/src/utils/index.ts +0 -14
- package/src/utils/license.ts +0 -50
- package/src/utils/parquet.ts +0 -377
- package/src/utils/split.ts +0 -278
- package/src/utils/tokenize.ts +0 -78
- package/src/utils/wof-json.ts +0 -244
- /package/{src → lib}/codex/us-fips-state.ts +0 -0
- /package/{src → lib}/tools/gb-title-case.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/tiger/street-decompose.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}/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
|
@@ -0,0 +1,239 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Fetch the full French BAN (Base Adresse Nationale) — all metropolitan départements (01-95, 2A,
|
|
7
|
+
* 2B) plus 5 overseas DOM/TOM (971-976 excl. 975).
|
|
8
|
+
*
|
|
9
|
+
* Source: https://adresse.data.gouv.fr/data/ban/adresses/latest/csv/
|
|
10
|
+
* Licence: Licence Ouverte 2.0 (attribution required — Tier B).
|
|
11
|
+
*
|
|
12
|
+
* Files already present with matching sha256 are skipped (re-runnable). Downloads `.csv.gz`,
|
|
13
|
+
* decompresses to `.csv`, deletes the `.gz` artifact. One shared `MANIFEST.json` at
|
|
14
|
+
* `<outRoot>/ban/MANIFEST.json` covers all codes.
|
|
15
|
+
*
|
|
16
|
+
* Invoke via `mailwoman corpus fetch ban --out-root <path>`. Built-in `fetch` with gzip/brotli
|
|
17
|
+
* decompression replaces curl; native `node:zlib` gunzip replaces the `gunzip` subprocess; no
|
|
18
|
+
* Python.
|
|
19
|
+
*/
|
|
20
|
+
import { gunzip } from "@mailwoman/core/fs/compression";
|
|
21
|
+
import { BYTES_PER_KIB, ByteFormatter } from "@mailwoman/core/fs/formatters";
|
|
22
|
+
import { isFile, readLocalBuffer, tryStat } from "@mailwoman/core/fs/readers";
|
|
23
|
+
import { makeDirectories, removePath, writeLocalFile } from "@mailwoman/core/fs/writers";
|
|
24
|
+
import { sha256File } from "@mailwoman/core/hash";
|
|
25
|
+
import { sleep } from "@mailwoman/core/utils/sleep";
|
|
26
|
+
import { join } from "path-ts";
|
|
27
|
+
import { downloadToFile, loadManifestEntries, writeManifest } from "#tools/fetch/download";
|
|
28
|
+
/**
|
|
29
|
+
* Bytes per KiB — the divisor for human-readable sizes, and the floor below which a "download" is an error page rather
|
|
30
|
+
* than data.
|
|
31
|
+
*/
|
|
32
|
+
const BASE_URL = "https://adresse.data.gouv.fr/data/ban/adresses/latest/csv";
|
|
33
|
+
/**
|
|
34
|
+
* All département codes — metropolitan 01-95 (with 2A/2B for Corsica instead of 20) plus overseas DOM/TOM. Codes do not
|
|
35
|
+
* change.
|
|
36
|
+
*/
|
|
37
|
+
const DEPT_CODES = [
|
|
38
|
+
"01",
|
|
39
|
+
"02",
|
|
40
|
+
"03",
|
|
41
|
+
"04",
|
|
42
|
+
"05",
|
|
43
|
+
"06",
|
|
44
|
+
"07",
|
|
45
|
+
"08",
|
|
46
|
+
"09",
|
|
47
|
+
"10",
|
|
48
|
+
"11",
|
|
49
|
+
"12",
|
|
50
|
+
"13",
|
|
51
|
+
"14",
|
|
52
|
+
"15",
|
|
53
|
+
"16",
|
|
54
|
+
"17",
|
|
55
|
+
"18",
|
|
56
|
+
"19",
|
|
57
|
+
"21",
|
|
58
|
+
"22",
|
|
59
|
+
"23",
|
|
60
|
+
"24",
|
|
61
|
+
"25",
|
|
62
|
+
"26",
|
|
63
|
+
"27",
|
|
64
|
+
"28",
|
|
65
|
+
"29",
|
|
66
|
+
"2A",
|
|
67
|
+
"2B",
|
|
68
|
+
"30",
|
|
69
|
+
"31",
|
|
70
|
+
"32",
|
|
71
|
+
"33",
|
|
72
|
+
"34",
|
|
73
|
+
"35",
|
|
74
|
+
"36",
|
|
75
|
+
"37",
|
|
76
|
+
"38",
|
|
77
|
+
"39",
|
|
78
|
+
"40",
|
|
79
|
+
"41",
|
|
80
|
+
"42",
|
|
81
|
+
"43",
|
|
82
|
+
"44",
|
|
83
|
+
"45",
|
|
84
|
+
"46",
|
|
85
|
+
"47",
|
|
86
|
+
"48",
|
|
87
|
+
"49",
|
|
88
|
+
"50",
|
|
89
|
+
"51",
|
|
90
|
+
"52",
|
|
91
|
+
"53",
|
|
92
|
+
"54",
|
|
93
|
+
"55",
|
|
94
|
+
"56",
|
|
95
|
+
"57",
|
|
96
|
+
"58",
|
|
97
|
+
"59",
|
|
98
|
+
"60",
|
|
99
|
+
"61",
|
|
100
|
+
"62",
|
|
101
|
+
"63",
|
|
102
|
+
"64",
|
|
103
|
+
"65",
|
|
104
|
+
"66",
|
|
105
|
+
"67",
|
|
106
|
+
"68",
|
|
107
|
+
"69",
|
|
108
|
+
"70",
|
|
109
|
+
"71",
|
|
110
|
+
"72",
|
|
111
|
+
"73",
|
|
112
|
+
"74",
|
|
113
|
+
"75",
|
|
114
|
+
"76",
|
|
115
|
+
"77",
|
|
116
|
+
"78",
|
|
117
|
+
"79",
|
|
118
|
+
"80",
|
|
119
|
+
"81",
|
|
120
|
+
"82",
|
|
121
|
+
"83",
|
|
122
|
+
"84",
|
|
123
|
+
"85",
|
|
124
|
+
"86",
|
|
125
|
+
"87",
|
|
126
|
+
"88",
|
|
127
|
+
"89",
|
|
128
|
+
"90",
|
|
129
|
+
"91",
|
|
130
|
+
"92",
|
|
131
|
+
"93",
|
|
132
|
+
"94",
|
|
133
|
+
"95",
|
|
134
|
+
"971",
|
|
135
|
+
"972",
|
|
136
|
+
"973",
|
|
137
|
+
"974",
|
|
138
|
+
"976",
|
|
139
|
+
];
|
|
140
|
+
export async function fetchBan(options, report) {
|
|
141
|
+
const banDir = join(options.outRoot, "ban");
|
|
142
|
+
const manifestPath = join(banDir, "MANIFEST.json");
|
|
143
|
+
await makeDirectories(banDir);
|
|
144
|
+
// Load existing entries (code -> entry): skip detection + preservation of untouched codes.
|
|
145
|
+
const entries = await loadManifestEntries(manifestPath, (entry) => entry.dept_code);
|
|
146
|
+
let fetched = 0;
|
|
147
|
+
let skipped = 0;
|
|
148
|
+
let failed = 0;
|
|
149
|
+
const failedCodes = [];
|
|
150
|
+
for (const code of DEPT_CODES) {
|
|
151
|
+
const filename = `adresses-${code}.csv`;
|
|
152
|
+
const gzFile = join(banDir, `${filename}.gz`);
|
|
153
|
+
const csvFile = join(banDir, filename);
|
|
154
|
+
const url = `${BASE_URL}/adresses-${code}.csv.gz`;
|
|
155
|
+
report?.(`=== dept ${code}`);
|
|
156
|
+
// If the CSV already exists, compare its sha256 against the manifest.
|
|
157
|
+
if (await isFile(csvFile)) {
|
|
158
|
+
const existingSha = await sha256File(csvFile);
|
|
159
|
+
const recordedSha = entries.get(code)?.sha256;
|
|
160
|
+
if (recordedSha && existingSha === recordedSha) {
|
|
161
|
+
report?.(` → already present + sha matches — skipping`);
|
|
162
|
+
skipped++;
|
|
163
|
+
continue;
|
|
164
|
+
}
|
|
165
|
+
report?.(` → present but sha mismatch or no manifest entry — re-fetching`);
|
|
166
|
+
await removePath(csvFile);
|
|
167
|
+
}
|
|
168
|
+
// Download the gzipped CSV.
|
|
169
|
+
try {
|
|
170
|
+
await downloadToFile({
|
|
171
|
+
url,
|
|
172
|
+
dest: gzFile,
|
|
173
|
+
timeoutMs: 600_000,
|
|
174
|
+
headers: { "Accept-Encoding": "gzip, br" },
|
|
175
|
+
report,
|
|
176
|
+
});
|
|
177
|
+
}
|
|
178
|
+
catch (error) {
|
|
179
|
+
report?.(` ✗ download failed: ${url} (${error.message})`);
|
|
180
|
+
failed++;
|
|
181
|
+
failedCodes.push(code);
|
|
182
|
+
continue;
|
|
183
|
+
}
|
|
184
|
+
// Guard against truncated 404/error pages.
|
|
185
|
+
const gzSize = (await tryStat(gzFile))?.size ?? 0;
|
|
186
|
+
if (gzSize < BYTES_PER_KIB) {
|
|
187
|
+
report?.(` ✗ response too small (${gzSize} bytes) — probable 404 / error page`);
|
|
188
|
+
await removePath(gzFile);
|
|
189
|
+
failed++;
|
|
190
|
+
failedCodes.push(code);
|
|
191
|
+
continue;
|
|
192
|
+
}
|
|
193
|
+
// Decompress in-place; delete the .gz.
|
|
194
|
+
try {
|
|
195
|
+
await writeLocalFile(await gunzip(await readLocalBuffer(gzFile)), csvFile);
|
|
196
|
+
}
|
|
197
|
+
catch (error) {
|
|
198
|
+
report?.(` ✗ decompress failed: ${error.message}`);
|
|
199
|
+
await removePath(gzFile);
|
|
200
|
+
failed++;
|
|
201
|
+
failedCodes.push(code);
|
|
202
|
+
continue;
|
|
203
|
+
}
|
|
204
|
+
await removePath(gzFile);
|
|
205
|
+
if (!(await isFile(csvFile))) {
|
|
206
|
+
report?.(` ✗ decompressed file not found at ${csvFile}`);
|
|
207
|
+
failed++;
|
|
208
|
+
failedCodes.push(code);
|
|
209
|
+
continue;
|
|
210
|
+
}
|
|
211
|
+
const bytes = (await tryStat(csvFile))?.size ?? 0;
|
|
212
|
+
const sha = await sha256File(csvFile);
|
|
213
|
+
entries.set(code, {
|
|
214
|
+
dept_code: code,
|
|
215
|
+
filename,
|
|
216
|
+
source_url: url,
|
|
217
|
+
downloaded_at: new Date().toISOString(),
|
|
218
|
+
sha256: sha,
|
|
219
|
+
bytes,
|
|
220
|
+
});
|
|
221
|
+
report?.(` ✓ ${ByteFormatter.formatIEC(bytes)} sha256=${sha}`);
|
|
222
|
+
fetched++;
|
|
223
|
+
// Be a polite citizen — short pause between requests.
|
|
224
|
+
await sleep(200);
|
|
225
|
+
}
|
|
226
|
+
// Write the consolidated MANIFEST.json (entries sorted by dept_code, codepoint order).
|
|
227
|
+
const sorted = [...entries.values()].toSorted((a, b) => a.dept_code < b.dept_code ? -1 : a.dept_code > b.dept_code ? 1 : 0);
|
|
228
|
+
await writeManifest(manifestPath, sorted);
|
|
229
|
+
report?.(`Wrote ${manifestPath} with ${sorted.length} entries.`);
|
|
230
|
+
report?.(`=== summary ===`);
|
|
231
|
+
report?.(`fetched: ${fetched}`);
|
|
232
|
+
report?.(`skipped: ${skipped} (already present + sha matched)`);
|
|
233
|
+
report?.(`failed: ${failed}`);
|
|
234
|
+
if (failedCodes.length) {
|
|
235
|
+
report?.(`failed codes: ${failedCodes.join(" ")}`);
|
|
236
|
+
}
|
|
237
|
+
return { fetched, skipped, failed, failedCodes };
|
|
238
|
+
}
|
|
239
|
+
//# sourceMappingURL=ban.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"ban.js","sourceRoot":"","sources":["../../../lib/tools/fetch/ban.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;GAkBG;AAEH,OAAO,EAAE,MAAM,EAAE,MAAM,gCAAgC,CAAA;AACvD,OAAO,EAAE,aAAa,EAAE,aAAa,EAAE,MAAM,+BAA+B,CAAA;AAC5E,OAAO,EAAE,MAAM,EAAE,eAAe,EAAE,OAAO,EAAE,MAAM,4BAA4B,CAAA;AAC7E,OAAO,EAAE,eAAe,EAAE,UAAU,EAAE,cAAc,EAAE,MAAM,4BAA4B,CAAA;AACxF,OAAO,EAAE,UAAU,EAAE,MAAM,sBAAsB,CAAA;AACjD,OAAO,EAAE,KAAK,EAAE,MAAM,6BAA6B,CAAA;AACnD,OAAO,EAAE,IAAI,EAAE,MAAM,SAAS,CAAA;AAG9B,OAAO,EAAE,cAAc,EAAE,mBAAmB,EAAE,aAAa,EAAE,MAAM,uBAAuB,CAAA;AAE1F;;;GAGG;AAEH,MAAM,QAAQ,GAAG,2DAA2D,CAAA;AAE5E;;;GAGG;AACH,MAAM,UAAU,GAAG;IAClB,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,IAAI;IACJ,KAAK;IACL,KAAK;IACL,KAAK;IACL,KAAK;IACL,KAAK;CACL,CAAA;AAaD,MAAM,CAAC,KAAK,UAAU,QAAQ,CAAC,OAAwB,EAAE,MAA+B;IACvF,MAAM,MAAM,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,KAAK,CAAC,CAAA;IAC3C,MAAM,YAAY,GAAG,IAAI,CAAC,MAAM,EAAE,eAAe,CAAC,CAAA;IAClD,MAAM,eAAe,CAAC,MAAM,CAAC,CAAA;IAE7B,2FAA2F;IAC3F,MAAM,OAAO,GAAG,MAAM,mBAAmB,CAAmB,YAAY,EAAE,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,SAAS,CAAC,CAAA;IAErG,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,MAAM,GAAG,CAAC,CAAA;IACd,MAAM,WAAW,GAAa,EAAE,CAAA;IAEhC,KAAK,MAAM,IAAI,IAAI,UAAU,EAAE,CAAC;QAC/B,MAAM,QAAQ,GAAG,YAAY,IAAI,MAAM,CAAA;QACvC,MAAM,MAAM,GAAG,IAAI,CAAC,MAAM,EAAE,GAAG,QAAQ,KAAK,CAAC,CAAA;QAC7C,MAAM,OAAO,GAAG,IAAI,CAAC,MAAM,EAAE,QAAQ,CAAC,CAAA;QACtC,MAAM,GAAG,GAAG,GAAG,QAAQ,aAAa,IAAI,SAAS,CAAA;QAEjD,MAAM,EAAE,CAAC,YAAY,IAAI,EAAE,CAAC,CAAA;QAE5B,sEAAsE;QACtE,IAAI,MAAM,MAAM,CAAC,OAAO,CAAC,EAAE,CAAC;YAC3B,MAAM,WAAW,GAAG,MAAM,UAAU,CAAC,OAAO,CAAC,CAAA;YAC7C,MAAM,WAAW,GAAG,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,MAAM,CAAA;YAE7C,IAAI,WAAW,IAAI,WAAW,KAAK,WAAW,EAAE,CAAC;gBAChD,MAAM,EAAE,CAAC,8CAA8C,CAAC,CAAA;gBAExD,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,MAAM,EAAE,CAAC,iEAAiE,CAAC,CAAA;YAC3E,MAAM,UAAU,CAAC,OAAO,CAAC,CAAA;QAC1B,CAAC;QAED,4BAA4B;QAC5B,IAAI,CAAC;YACJ,MAAM,cAAc,CAAC;gBACpB,GAAG;gBACH,IAAI,EAAE,MAAM;gBACZ,SAAS,EAAE,OAAO;gBAClB,OAAO,EAAE,EAAE,iBAAiB,EAAE,UAAU,EAAE;gBAC1C,MAAM;aACN,CAAC,CAAA;QACH,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,MAAM,EAAE,CAAC,wBAAwB,GAAG,KAAM,KAAe,CAAC,OAAO,GAAG,CAAC,CAAA;YAErE,MAAM,EAAE,CAAA;YACR,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;YAEtB,SAAQ;QACT,CAAC;QAED,2CAA2C;QAC3C,MAAM,MAAM,GAAG,CAAC,MAAM,OAAO,CAAC,MAAM,CAAC,CAAC,EAAE,IAAI,IAAI,CAAC,CAAA;QAEjD,IAAI,MAAM,GAAG,aAAa,EAAE,CAAC;YAC5B,MAAM,EAAE,CAAC,2BAA2B,MAAM,qCAAqC,CAAC,CAAA;YAChF,MAAM,UAAU,CAAC,MAAM,CAAC,CAAA;YAExB,MAAM,EAAE,CAAA;YACR,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;YAEtB,SAAQ;QACT,CAAC;QAED,uCAAuC;QACvC,IAAI,CAAC;YACJ,MAAM,cAAc,CAAC,MAAM,MAAM,CAAC,MAAM,eAAe,CAAC,MAAM,CAAC,CAAC,EAAE,OAAO,CAAC,CAAA;QAC3E,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,MAAM,EAAE,CAAC,0BAA2B,KAAe,CAAC,OAAO,EAAE,CAAC,CAAA;YAC9D,MAAM,UAAU,CAAC,MAAM,CAAC,CAAA;YAExB,MAAM,EAAE,CAAA;YACR,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;YAEtB,SAAQ;QACT,CAAC;QAED,MAAM,UAAU,CAAC,MAAM,CAAC,CAAA;QAExB,IAAI,CAAC,CAAC,MAAM,MAAM,CAAC,OAAO,CAAC,CAAC,EAAE,CAAC;YAC9B,MAAM,EAAE,CAAC,sCAAsC,OAAO,EAAE,CAAC,CAAA;YAEzD,MAAM,EAAE,CAAA;YACR,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;YAEtB,SAAQ;QACT,CAAC;QAED,MAAM,KAAK,GAAG,CAAC,MAAM,OAAO,CAAC,OAAO,CAAC,CAAC,EAAE,IAAI,IAAI,CAAC,CAAA;QACjD,MAAM,GAAG,GAAG,MAAM,UAAU,CAAC,OAAO,CAAC,CAAA;QAErC,OAAO,CAAC,GAAG,CAAC,IAAI,EAAE;YACjB,SAAS,EAAE,IAAI;YACf,QAAQ;YACR,UAAU,EAAE,GAAG;YACf,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;YACvC,MAAM,EAAE,GAAG;YACX,KAAK;SACL,CAAC,CAAA;QAEF,MAAM,EAAE,CAAC,OAAO,aAAa,CAAC,SAAS,CAAC,KAAK,CAAC,YAAY,GAAG,EAAE,CAAC,CAAA;QAEhE,OAAO,EAAE,CAAA;QAET,sDAAsD;QACtD,MAAM,KAAK,CAAC,GAAG,CAAC,CAAA;IACjB,CAAC;IAED,uFAAuF;IACvF,MAAM,MAAM,GAAG,CAAC,GAAG,OAAO,CAAC,MAAM,EAAE,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CACtD,CAAC,CAAC,SAAS,GAAG,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,SAAS,GAAG,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAClE,CAAA;IAED,MAAM,aAAa,CAAC,YAAY,EAAE,MAAM,CAAC,CAAA;IACzC,MAAM,EAAE,CAAC,SAAS,YAAY,SAAS,MAAM,CAAC,MAAM,WAAW,CAAC,CAAA;IAEhE,MAAM,EAAE,CAAC,iBAAiB,CAAC,CAAA;IAC3B,MAAM,EAAE,CAAC,aAAa,OAAO,EAAE,CAAC,CAAA;IAChC,MAAM,EAAE,CAAC,aAAa,OAAO,kCAAkC,CAAC,CAAA;IAChE,MAAM,EAAE,CAAC,aAAa,MAAM,EAAE,CAAC,CAAA;IAE/B,IAAI,WAAW,CAAC,MAAM,EAAE,CAAC;QACxB,MAAM,EAAE,CAAC,iBAAiB,WAAW,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,CAAA;IACnD,CAAC;IAED,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,EAAE,WAAW,EAAE,CAAA;AACjD,CAAC"}
|
|
@@ -0,0 +1,117 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Download and manifest utilities for `mailwoman corpus fetch <source>`.
|
|
7
|
+
*/
|
|
8
|
+
import type { PathBuilderLike } from "path-ts";
|
|
9
|
+
/**
|
|
10
|
+
* The option base every `mailwoman corpus fetch <source>` module extends.
|
|
11
|
+
*/
|
|
12
|
+
/**
|
|
13
|
+
* How long a failed transfer waits before the next attempt.
|
|
14
|
+
*/
|
|
15
|
+
export declare const DEFAULT_RETRY_DELAY_MS = 5000;
|
|
16
|
+
export interface BaseFetchOptions {
|
|
17
|
+
/**
|
|
18
|
+
* Destination root for downloaded source data. Each source writes its own subdirectory.
|
|
19
|
+
*/
|
|
20
|
+
outRoot: PathBuilderLike;
|
|
21
|
+
/**
|
|
22
|
+
* Pause between transfer retries, in milliseconds. Defaults to {@linkcode DEFAULT_RETRY_DELAY_MS}.
|
|
23
|
+
*
|
|
24
|
+
* A test that exercises the failure path pays this delay once per retry in real time — measured at 20.1 s for the two
|
|
25
|
+
* failing-transfer cases in `geonames-postal.test.ts`, which is the whole cost of that file. The retry COUNT is the
|
|
26
|
+
* behaviour under test there; the pause between attempts is not, so it is a caller's to shorten.
|
|
27
|
+
*/
|
|
28
|
+
retryDelayMs?: number;
|
|
29
|
+
}
|
|
30
|
+
/**
|
|
31
|
+
* The per-run result every fetch module returns; the command maps `failed > 0` to exit code 1.
|
|
32
|
+
*/
|
|
33
|
+
export interface FetchSummary {
|
|
34
|
+
fetched: number;
|
|
35
|
+
skipped: number;
|
|
36
|
+
failed: number;
|
|
37
|
+
failedCodes: string[];
|
|
38
|
+
}
|
|
39
|
+
/**
|
|
40
|
+
* The sibling `MANIFEST.json` shape the single-file fetch modules write: origin URL + fetch timestamp + byte count +
|
|
41
|
+
* sha256, so downstream adapters can verify provenance.
|
|
42
|
+
*/
|
|
43
|
+
export interface SourceManifest {
|
|
44
|
+
source_url: string;
|
|
45
|
+
downloaded_at: string;
|
|
46
|
+
filename: string;
|
|
47
|
+
sha256: string;
|
|
48
|
+
bytes: number;
|
|
49
|
+
}
|
|
50
|
+
/**
|
|
51
|
+
* A status worth retrying: rate limiting or a server-side failure.
|
|
52
|
+
*/
|
|
53
|
+
/**
|
|
54
|
+
* An HTTP failure that CARRIES its status, so callers branch on `error.status` rather than on message prose. The prose
|
|
55
|
+
* route shipped a real flake: a caller classified "not published upstream" with `message.includes("404")`, and the
|
|
56
|
+
* message contains the URL — an ephemeral test-server port such as `:40453` satisfies it while the actual status is 500.
|
|
57
|
+
* Roughly 1–2% of ephemeral ports contain the substring, which is exactly the kind of sometimes-failure that burns a CI
|
|
58
|
+
* run and vanishes locally.
|
|
59
|
+
*/
|
|
60
|
+
export declare class HTTPStatusError extends Error {
|
|
61
|
+
readonly status: number;
|
|
62
|
+
constructor(status: number, message: string);
|
|
63
|
+
}
|
|
64
|
+
export declare function isTransientStatus(status: number): boolean;
|
|
65
|
+
export interface DownloadOptions {
|
|
66
|
+
url: string;
|
|
67
|
+
dest: string;
|
|
68
|
+
/**
|
|
69
|
+
* Per-attempt timeout. Default 10 minutes — these are multi-GB government dumps.
|
|
70
|
+
*/
|
|
71
|
+
timeoutMs?: number;
|
|
72
|
+
/**
|
|
73
|
+
* Extra attempts after the first, taken only on transient statuses or network errors. Default 0.
|
|
74
|
+
*/
|
|
75
|
+
retries?: number;
|
|
76
|
+
/**
|
|
77
|
+
* Delay between attempts. Default 5s.
|
|
78
|
+
*/
|
|
79
|
+
retryDelayMs?: number;
|
|
80
|
+
headers?: Record<string, string>;
|
|
81
|
+
report?: (line: string) => void;
|
|
82
|
+
}
|
|
83
|
+
/**
|
|
84
|
+
* Download `url` to `dest` with per-attempt timeout and transient-status retry. Throws on a non-transient HTTP status
|
|
85
|
+
* or once retries are exhausted. Returns the byte count written.
|
|
86
|
+
*/
|
|
87
|
+
export declare function downloadToFile(options: DownloadOptions): Promise<{
|
|
88
|
+
bytes: number;
|
|
89
|
+
}>;
|
|
90
|
+
export interface StreamDownloadOptions {
|
|
91
|
+
headers?: Record<string, string>;
|
|
92
|
+
timeoutMs: number;
|
|
93
|
+
retries: number;
|
|
94
|
+
retryDelayMs: number;
|
|
95
|
+
}
|
|
96
|
+
/**
|
|
97
|
+
* Stream an HTTP download to disk, returning the final HTTP status (0 on network error after retries). Follows
|
|
98
|
+
* redirects (the Census and OpenAddresses endpoints both 302 to their real hosts).
|
|
99
|
+
*
|
|
100
|
+
* Kept separate from {@link downloadToFile} on purpose: this one streams a multi-GB body to disk (the buffered helper
|
|
101
|
+
* reads via `arrayBuffer()`) and returns the HTTP status instead of throwing, which the per-file result collectors and
|
|
102
|
+
* two-URL fallback ladders consume.
|
|
103
|
+
*/
|
|
104
|
+
export declare function streamDownload(url: string, dest: string, opts: StreamDownloadOptions): Promise<number>;
|
|
105
|
+
/**
|
|
106
|
+
* Read a MANIFEST.json; `null` when missing or corrupt (callers re-fetch from scratch).
|
|
107
|
+
*/
|
|
108
|
+
export declare function readManifest<T>(path: string): Promise<T | null>;
|
|
109
|
+
/**
|
|
110
|
+
* Load manifest entries into a map so untouched keys survive a partial re-fetch.
|
|
111
|
+
*/
|
|
112
|
+
export declare function loadManifestEntries<T>(path: string, key: (entry: T) => string): Promise<Map<string, T>>;
|
|
113
|
+
/**
|
|
114
|
+
* Write a MANIFEST.json in the house shape: pretty-printed, trailing newline.
|
|
115
|
+
*/
|
|
116
|
+
export declare function writeManifest(path: string, manifest: unknown): Promise<void>;
|
|
117
|
+
//# sourceMappingURL=download.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"download.d.ts","sourceRoot":"","sources":["../../../lib/tools/fetch/download.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAOH,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,SAAS,CAAA;AAiB9C;;GAEG;AACH;;GAEG;AACH,eAAO,MAAM,sBAAsB,OAAO,CAAA;AAE1C,MAAM,WAAW,gBAAgB;IAChC;;OAEG;IACH,OAAO,EAAE,eAAe,CAAA;IACxB;;;;;;OAMG;IACH,YAAY,CAAC,EAAE,MAAM,CAAA;CACrB;AAED;;GAEG;AACH,MAAM,WAAW,YAAY;IAC5B,OAAO,EAAE,MAAM,CAAA;IACf,OAAO,EAAE,MAAM,CAAA;IACf,MAAM,EAAE,MAAM,CAAA;IACd,WAAW,EAAE,MAAM,EAAE,CAAA;CACrB;AAED;;;GAGG;AACH,MAAM,WAAW,cAAc;IAC9B,UAAU,EAAE,MAAM,CAAA;IAClB,aAAa,EAAE,MAAM,CAAA;IACrB,QAAQ,EAAE,MAAM,CAAA;IAChB,MAAM,EAAE,MAAM,CAAA;IACd,KAAK,EAAE,MAAM,CAAA;CACb;AAED;;GAEG;AACH;;;;;;GAMG;AACH,qBAAa,eAAgB,SAAQ,KAAK;IACzC,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAA;gBAEX,MAAM,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM;CAK3C;AAED,wBAAgB,iBAAiB,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAEzD;AAED,MAAM,WAAW,eAAe;IAC/B,GAAG,EAAE,MAAM,CAAA;IACX,IAAI,EAAE,MAAM,CAAA;IACZ;;OAEG;IACH,SAAS,CAAC,EAAE,MAAM,CAAA;IAClB;;OAEG;IACH,OAAO,CAAC,EAAE,MAAM,CAAA;IAChB;;OAEG;IACH,YAAY,CAAC,EAAE,MAAM,CAAA;IACrB,OAAO,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IAChC,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,CAAA;CAC/B;AAED;;;GAGG;AACH,wBAAsB,cAAc,CAAC,OAAO,EAAE,eAAe,GAAG,OAAO,CAAC;IAAE,KAAK,EAAE,MAAM,CAAA;CAAE,CAAC,CAsDzF;AAED,MAAM,WAAW,qBAAqB;IACrC,OAAO,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IAChC,SAAS,EAAE,MAAM,CAAA;IACjB,OAAO,EAAE,MAAM,CAAA;IACf,YAAY,EAAE,MAAM,CAAA;CACpB;AAED;;;;;;;GAOG;AACH,wBAAsB,cAAc,CAAC,GAAG,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,qBAAqB,GAAG,OAAO,CAAC,MAAM,CAAC,CAkC5G;AAED;;GAEG;AACH,wBAAsB,YAAY,CAAC,CAAC,EAAE,IAAI,EAAE,MAAM,GAAG,OAAO,CAAC,CAAC,GAAG,IAAI,CAAC,CAQrE;AAED;;GAEG;AACH,wBAAsB,mBAAmB,CAAC,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,GAAG,EAAE,CAAC,KAAK,EAAE,CAAC,KAAK,MAAM,GAAG,OAAO,CAAC,GAAG,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,CAS7G;AAED;;GAEG;AACH,wBAAsB,aAAa,CAAC,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,OAAO,GAAG,OAAO,CAAC,IAAI,CAAC,CAElF"}
|
|
@@ -0,0 +1,160 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Download and manifest utilities for `mailwoman corpus fetch <source>`.
|
|
7
|
+
*/
|
|
8
|
+
import { pathExists, readLocalTextFile } from "@mailwoman/core/fs/readers";
|
|
9
|
+
import { openWriteStream, pipeline, Readable } from "@mailwoman/core/fs/streams";
|
|
10
|
+
import { writeLocalFile, writeLocalTextFile } from "@mailwoman/core/fs/writers";
|
|
11
|
+
import { tryParsingJSON } from "@mailwoman/core/json";
|
|
12
|
+
import { sleep } from "@mailwoman/core/utils/sleep";
|
|
13
|
+
/**
|
|
14
|
+
* Rate limited — retryable, the server is asking us to back off.
|
|
15
|
+
*/
|
|
16
|
+
const HTTP_TOO_MANY_REQUESTS = 429;
|
|
17
|
+
/**
|
|
18
|
+
* Lowest 5xx status. Server-side failures are retryable; 4xx are not.
|
|
19
|
+
*/
|
|
20
|
+
const HTTP_SERVER_ERROR_MIN = 500;
|
|
21
|
+
/**
|
|
22
|
+
* Highest 5xx status.
|
|
23
|
+
*/
|
|
24
|
+
const HTTP_SERVER_ERROR_MAX = 599;
|
|
25
|
+
/**
|
|
26
|
+
* The option base every `mailwoman corpus fetch <source>` module extends.
|
|
27
|
+
*/
|
|
28
|
+
/**
|
|
29
|
+
* How long a failed transfer waits before the next attempt.
|
|
30
|
+
*/
|
|
31
|
+
export const DEFAULT_RETRY_DELAY_MS = 5000;
|
|
32
|
+
/**
|
|
33
|
+
* A status worth retrying: rate limiting or a server-side failure.
|
|
34
|
+
*/
|
|
35
|
+
/**
|
|
36
|
+
* An HTTP failure that CARRIES its status, so callers branch on `error.status` rather than on message prose. The prose
|
|
37
|
+
* route shipped a real flake: a caller classified "not published upstream" with `message.includes("404")`, and the
|
|
38
|
+
* message contains the URL — an ephemeral test-server port such as `:40453` satisfies it while the actual status is 500.
|
|
39
|
+
* Roughly 1–2% of ephemeral ports contain the substring, which is exactly the kind of sometimes-failure that burns a CI
|
|
40
|
+
* run and vanishes locally.
|
|
41
|
+
*/
|
|
42
|
+
export class HTTPStatusError extends Error {
|
|
43
|
+
status;
|
|
44
|
+
constructor(status, message) {
|
|
45
|
+
super(message);
|
|
46
|
+
this.name = "HTTPStatusError";
|
|
47
|
+
this.status = status;
|
|
48
|
+
}
|
|
49
|
+
}
|
|
50
|
+
export function isTransientStatus(status) {
|
|
51
|
+
return status === HTTP_TOO_MANY_REQUESTS || (status >= HTTP_SERVER_ERROR_MIN && status <= HTTP_SERVER_ERROR_MAX);
|
|
52
|
+
}
|
|
53
|
+
/**
|
|
54
|
+
* Download `url` to `dest` with per-attempt timeout and transient-status retry. Throws on a non-transient HTTP status
|
|
55
|
+
* or once retries are exhausted. Returns the byte count written.
|
|
56
|
+
*/
|
|
57
|
+
export async function downloadToFile(options) {
|
|
58
|
+
const { url, dest, timeoutMs = 600_000, retries = 0, retryDelayMs = DEFAULT_RETRY_DELAY_MS, headers, report, } = options;
|
|
59
|
+
let lastError;
|
|
60
|
+
for (let attempt = 0; attempt <= retries; attempt++) {
|
|
61
|
+
if (attempt > 0) {
|
|
62
|
+
report?.(`retry ${attempt}/${retries} after ${retryDelayMs}ms — ${url}`);
|
|
63
|
+
await sleep(retryDelayMs);
|
|
64
|
+
}
|
|
65
|
+
let res;
|
|
66
|
+
try {
|
|
67
|
+
// Raw `fetch`, deliberately: this is the shared FILE downloader and the body is piped to disk below.
|
|
68
|
+
// `APIClient` is the repo default for API requests — small bodies, repeated calls — and buffers a
|
|
69
|
+
// non-stream response in memory, which is the one thing a multi-gigabyte transfer must not do.
|
|
70
|
+
res = await fetch(url, { headers, signal: AbortSignal.timeout(timeoutMs) });
|
|
71
|
+
}
|
|
72
|
+
catch (error) {
|
|
73
|
+
// AbortSignal timeouts and network-level failures are retryable.
|
|
74
|
+
lastError = error;
|
|
75
|
+
continue;
|
|
76
|
+
}
|
|
77
|
+
if (!res.ok) {
|
|
78
|
+
const error = new HTTPStatusError(res.status, `HTTP ${res.status} ${res.statusText} — ${url}`);
|
|
79
|
+
if (!isTransientStatus(res.status))
|
|
80
|
+
throw error;
|
|
81
|
+
lastError = error;
|
|
82
|
+
continue;
|
|
83
|
+
}
|
|
84
|
+
try {
|
|
85
|
+
const buffer = Buffer.from(await res.arrayBuffer());
|
|
86
|
+
await writeLocalFile(buffer, dest);
|
|
87
|
+
return { bytes: buffer.byteLength };
|
|
88
|
+
}
|
|
89
|
+
catch (error) {
|
|
90
|
+
// A mid-stream abort while reading the body is retryable too.
|
|
91
|
+
lastError = error;
|
|
92
|
+
}
|
|
93
|
+
}
|
|
94
|
+
throw lastError instanceof Error ? lastError : new Error(String(lastError));
|
|
95
|
+
}
|
|
96
|
+
/**
|
|
97
|
+
* Stream an HTTP download to disk, returning the final HTTP status (0 on network error after retries). Follows
|
|
98
|
+
* redirects (the Census and OpenAddresses endpoints both 302 to their real hosts).
|
|
99
|
+
*
|
|
100
|
+
* Kept separate from {@link downloadToFile} on purpose: this one streams a multi-GB body to disk (the buffered helper
|
|
101
|
+
* reads via `arrayBuffer()`) and returns the HTTP status instead of throwing, which the per-file result collectors and
|
|
102
|
+
* two-URL fallback ladders consume.
|
|
103
|
+
*/
|
|
104
|
+
export async function streamDownload(url, dest, opts) {
|
|
105
|
+
for (let attempt = 0; attempt <= opts.retries; attempt++) {
|
|
106
|
+
try {
|
|
107
|
+
const res = await fetch(url, {
|
|
108
|
+
headers: opts.headers ?? {},
|
|
109
|
+
redirect: "follow",
|
|
110
|
+
signal: AbortSignal.timeout(opts.timeoutMs),
|
|
111
|
+
});
|
|
112
|
+
if (res.ok && res.body) {
|
|
113
|
+
await pipeline(Readable.fromWeb(res.body), openWriteStream(dest));
|
|
114
|
+
return res.status;
|
|
115
|
+
}
|
|
116
|
+
if (attempt < opts.retries && isTransientStatus(res.status)) {
|
|
117
|
+
await sleep(opts.retryDelayMs);
|
|
118
|
+
continue;
|
|
119
|
+
}
|
|
120
|
+
return res.status;
|
|
121
|
+
}
|
|
122
|
+
catch {
|
|
123
|
+
if (attempt < opts.retries) {
|
|
124
|
+
await sleep(opts.retryDelayMs);
|
|
125
|
+
continue;
|
|
126
|
+
}
|
|
127
|
+
return 0;
|
|
128
|
+
}
|
|
129
|
+
}
|
|
130
|
+
return 0;
|
|
131
|
+
}
|
|
132
|
+
/**
|
|
133
|
+
* Read a MANIFEST.json; `null` when missing or corrupt (callers re-fetch from scratch).
|
|
134
|
+
*/
|
|
135
|
+
export async function readManifest(path) {
|
|
136
|
+
if (!(await pathExists(path)))
|
|
137
|
+
return null;
|
|
138
|
+
// A read failure (e.g. the file vanished after the existsSync probe) maps to null like corrupt
|
|
139
|
+
// JSON does; tryParsingJSON returns null for the non-string sentinel.
|
|
140
|
+
const text = await readLocalTextFile(path).catch(() => null);
|
|
141
|
+
return tryParsingJSON(text);
|
|
142
|
+
}
|
|
143
|
+
/**
|
|
144
|
+
* Load manifest entries into a map so untouched keys survive a partial re-fetch.
|
|
145
|
+
*/
|
|
146
|
+
export async function loadManifestEntries(path, key) {
|
|
147
|
+
const entries = new Map();
|
|
148
|
+
const parsed = await readManifest(path);
|
|
149
|
+
for (const entry of parsed ?? []) {
|
|
150
|
+
entries.set(key(entry), entry);
|
|
151
|
+
}
|
|
152
|
+
return entries;
|
|
153
|
+
}
|
|
154
|
+
/**
|
|
155
|
+
* Write a MANIFEST.json in the house shape: pretty-printed, trailing newline.
|
|
156
|
+
*/
|
|
157
|
+
export async function writeManifest(path, manifest) {
|
|
158
|
+
await writeLocalTextFile(JSON.stringify(manifest, null, 2) + "\n", path);
|
|
159
|
+
}
|
|
160
|
+
//# sourceMappingURL=download.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"download.js","sourceRoot":"","sources":["../../../lib/tools/fetch/download.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH,OAAO,EAAE,UAAU,EAAE,iBAAiB,EAAE,MAAM,4BAA4B,CAAA;AAC1E,OAAO,EAAE,eAAe,EAAE,QAAQ,EAAE,QAAQ,EAAE,MAAM,4BAA4B,CAAA;AAChF,OAAO,EAAE,cAAc,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAA;AAC/E,OAAO,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAA;AACrD,OAAO,EAAE,KAAK,EAAE,MAAM,6BAA6B,CAAA;AAGnD;;GAEG;AACH,MAAM,sBAAsB,GAAG,GAAG,CAAA;AAElC;;GAEG;AACH,MAAM,qBAAqB,GAAG,GAAG,CAAA;AAEjC;;GAEG;AACH,MAAM,qBAAqB,GAAG,GAAG,CAAA;AAEjC;;GAEG;AACH;;GAEG;AACH,MAAM,CAAC,MAAM,sBAAsB,GAAG,IAAI,CAAA;AAuC1C;;GAEG;AACH;;;;;;GAMG;AACH,MAAM,OAAO,eAAgB,SAAQ,KAAK;IAChC,MAAM,CAAQ;IAEvB,YAAY,MAAc,EAAE,OAAe;QAC1C,KAAK,CAAC,OAAO,CAAC,CAAA;QACd,IAAI,CAAC,IAAI,GAAG,iBAAiB,CAAA;QAC7B,IAAI,CAAC,MAAM,GAAG,MAAM,CAAA;IACrB,CAAC;CACD;AAED,MAAM,UAAU,iBAAiB,CAAC,MAAc;IAC/C,OAAO,MAAM,KAAK,sBAAsB,IAAI,CAAC,MAAM,IAAI,qBAAqB,IAAI,MAAM,IAAI,qBAAqB,CAAC,CAAA;AACjH,CAAC;AAqBD;;;GAGG;AACH,MAAM,CAAC,KAAK,UAAU,cAAc,CAAC,OAAwB;IAC5D,MAAM,EACL,GAAG,EACH,IAAI,EACJ,SAAS,GAAG,OAAO,EACnB,OAAO,GAAG,CAAC,EACX,YAAY,GAAG,sBAAsB,EACrC,OAAO,EACP,MAAM,GACN,GAAG,OAAO,CAAA;IAEX,IAAI,SAAkB,CAAA;IAEtB,KAAK,IAAI,OAAO,GAAG,CAAC,EAAE,OAAO,IAAI,OAAO,EAAE,OAAO,EAAE,EAAE,CAAC;QACrD,IAAI,OAAO,GAAG,CAAC,EAAE,CAAC;YACjB,MAAM,EAAE,CAAC,SAAS,OAAO,IAAI,OAAO,UAAU,YAAY,QAAQ,GAAG,EAAE,CAAC,CAAA;YACxE,MAAM,KAAK,CAAC,YAAY,CAAC,CAAA;QAC1B,CAAC;QAED,IAAI,GAAa,CAAA;QAEjB,IAAI,CAAC;YACJ,qGAAqG;YACrG,kGAAkG;YAClG,+FAA+F;YAC/F,GAAG,GAAG,MAAM,KAAK,CAAC,GAAG,EAAE,EAAE,OAAO,EAAE,MAAM,EAAE,WAAW,CAAC,OAAO,CAAC,SAAS,CAAC,EAAE,CAAC,CAAA;QAC5E,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,iEAAiE;YACjE,SAAS,GAAG,KAAK,CAAA;YAEjB,SAAQ;QACT,CAAC;QAED,IAAI,CAAC,GAAG,CAAC,EAAE,EAAE,CAAC;YACb,MAAM,KAAK,GAAG,IAAI,eAAe,CAAC,GAAG,CAAC,MAAM,EAAE,QAAQ,GAAG,CAAC,MAAM,IAAI,GAAG,CAAC,UAAU,MAAM,GAAG,EAAE,CAAC,CAAA;YAE9F,IAAI,CAAC,iBAAiB,CAAC,GAAG,CAAC,MAAM,CAAC;gBAAE,MAAM,KAAK,CAAA;YAC/C,SAAS,GAAG,KAAK,CAAA;YAEjB,SAAQ;QACT,CAAC;QAED,IAAI,CAAC;YACJ,MAAM,MAAM,GAAG,MAAM,CAAC,IAAI,CAAC,MAAM,GAAG,CAAC,WAAW,EAAE,CAAC,CAAA;YACnD,MAAM,cAAc,CAAC,MAAM,EAAE,IAAI,CAAC,CAAA;YAElC,OAAO,EAAE,KAAK,EAAE,MAAM,CAAC,UAAU,EAAE,CAAA;QACpC,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,8DAA8D;YAC9D,SAAS,GAAG,KAAK,CAAA;QAClB,CAAC;IACF,CAAC;IAED,MAAM,SAAS,YAAY,KAAK,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,IAAI,KAAK,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,CAAA;AAC5E,CAAC;AASD;;;;;;;GAOG;AACH,MAAM,CAAC,KAAK,UAAU,cAAc,CAAC,GAAW,EAAE,IAAY,EAAE,IAA2B;IAC1F,KAAK,IAAI,OAAO,GAAG,CAAC,EAAE,OAAO,IAAI,IAAI,CAAC,OAAO,EAAE,OAAO,EAAE,EAAE,CAAC;QAC1D,IAAI,CAAC;YACJ,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,GAAG,EAAE;gBAC5B,OAAO,EAAE,IAAI,CAAC,OAAO,IAAI,EAAE;gBAC3B,QAAQ,EAAE,QAAQ;gBAClB,MAAM,EAAE,WAAW,CAAC,OAAO,CAAC,IAAI,CAAC,SAAS,CAAC;aAC3C,CAAC,CAAA;YAEF,IAAI,GAAG,CAAC,EAAE,IAAI,GAAG,CAAC,IAAI,EAAE,CAAC;gBACxB,MAAM,QAAQ,CAAC,QAAQ,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,eAAe,CAAC,IAAI,CAAC,CAAC,CAAA;gBAEjE,OAAO,GAAG,CAAC,MAAM,CAAA;YAClB,CAAC;YAED,IAAI,OAAO,GAAG,IAAI,CAAC,OAAO,IAAI,iBAAiB,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC;gBAC7D,MAAM,KAAK,CAAC,IAAI,CAAC,YAAY,CAAC,CAAA;gBAE9B,SAAQ;YACT,CAAC;YAED,OAAO,GAAG,CAAC,MAAM,CAAA;QAClB,CAAC;QAAC,MAAM,CAAC;YACR,IAAI,OAAO,GAAG,IAAI,CAAC,OAAO,EAAE,CAAC;gBAC5B,MAAM,KAAK,CAAC,IAAI,CAAC,YAAY,CAAC,CAAA;gBAE9B,SAAQ;YACT,CAAC;YAED,OAAO,CAAC,CAAA;QACT,CAAC;IACF,CAAC;IAED,OAAO,CAAC,CAAA;AACT,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,YAAY,CAAI,IAAY;IACjD,IAAI,CAAC,CAAC,MAAM,UAAU,CAAC,IAAI,CAAC,CAAC;QAAE,OAAO,IAAI,CAAA;IAE1C,+FAA+F;IAC/F,sEAAsE;IACtE,MAAM,IAAI,GAAG,MAAM,iBAAiB,CAAC,IAAI,CAAC,CAAC,KAAK,CAAC,GAAG,EAAE,CAAC,IAAI,CAAC,CAAA;IAE5D,OAAO,cAAc,CAAI,IAAI,CAAC,CAAA;AAC/B,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,mBAAmB,CAAI,IAAY,EAAE,GAAyB;IACnF,MAAM,OAAO,GAAG,IAAI,GAAG,EAAa,CAAA;IACpC,MAAM,MAAM,GAAG,MAAM,YAAY,CAAM,IAAI,CAAC,CAAA;IAE5C,KAAK,MAAM,KAAK,IAAI,MAAM,IAAI,EAAE,EAAE,CAAC;QAClC,OAAO,CAAC,GAAG,CAAC,GAAG,CAAC,KAAK,CAAC,EAAE,KAAK,CAAC,CAAA;IAC/B,CAAC;IAED,OAAO,OAAO,CAAA;AACf,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,aAAa,CAAC,IAAY,EAAE,QAAiB;IAClE,MAAM,kBAAkB,CAAC,IAAI,CAAC,SAAS,CAAC,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC,GAAG,IAAI,EAAE,IAAI,CAAC,CAAA;AACzE,CAAC"}
|
|
@@ -0,0 +1,91 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Fetch GeoNames per-country GAZETTEER dumps — the 19-column `<CC>.txt` files under
|
|
7
|
+
* `https://download.geonames.org/export/dump/` (NOT the postal exports; those are `export/zip/` and
|
|
8
|
+
* `geonames-postal.ts`'s job). The dumps carry feature classes and codes (column 8: `PPLC` national capital,
|
|
9
|
+
* `PPLA` first-order administrative seat), which is what the capitals reference build consumes (#1880).
|
|
10
|
+
*
|
|
11
|
+
* The catalog question is answered by the SOURCE, not by an ISO list: `countryInfo.txt` in the same directory
|
|
12
|
+
* enumerates every country GeoNames publishes, one row per ISO alpha-2 code, and also names each country's
|
|
13
|
+
* capital — the cross-check the capitals build grades its `PPLC` extraction against. Fetch that first; derive
|
|
14
|
+
* the country set from it; then a dump absent from disk is a measured gap against the source's own catalog
|
|
15
|
+
* rather than a silent hole. The dump directory may hold files this tool did not fetch: present files are never
|
|
16
|
+
* overwritten, and a present `<CC>.txt` that is NOT a 19-column gazetteer dump (GeoNames' postal exports share
|
|
17
|
+
* the basename) is reported as `wrong_format_present`, never counted as coverage.
|
|
18
|
+
*/
|
|
19
|
+
import type { BaseFetchOptions, FetchSummary } from "#tools/fetch/download";
|
|
20
|
+
export interface FetchGeonamesDumpOptions extends BaseFetchOptions {
|
|
21
|
+
/**
|
|
22
|
+
* ISO alpha-2 codes, any casing. Absent → every country `countryInfo.txt` enumerates.
|
|
23
|
+
*/
|
|
24
|
+
countries?: readonly string[];
|
|
25
|
+
/**
|
|
26
|
+
* Dump directory to read from. Defaults to GeoNames' own; exists so the 404 and coverage behaviour can be exercised
|
|
27
|
+
* against a local server.
|
|
28
|
+
*/
|
|
29
|
+
baseURL?: string;
|
|
30
|
+
/**
|
|
31
|
+
* Refetch a dump whose `<CC>.txt` already exists. Default false — the tool fills gaps.
|
|
32
|
+
*/
|
|
33
|
+
force?: boolean;
|
|
34
|
+
}
|
|
35
|
+
interface GeonamesDumpFileEntry {
|
|
36
|
+
country: string;
|
|
37
|
+
filename: string;
|
|
38
|
+
source_url: string;
|
|
39
|
+
sha256: string;
|
|
40
|
+
bytes: number;
|
|
41
|
+
}
|
|
42
|
+
export interface GeonamesDumpManifest {
|
|
43
|
+
source: string;
|
|
44
|
+
base_url: string;
|
|
45
|
+
license: string;
|
|
46
|
+
attribution: string;
|
|
47
|
+
downloaded_at: string;
|
|
48
|
+
files: GeonamesDumpFileEntry[];
|
|
49
|
+
/**
|
|
50
|
+
* `<CC>.txt` files already on disk and left alone — the hand-fetched population this tool extends.
|
|
51
|
+
*/
|
|
52
|
+
skipped_present: string[];
|
|
53
|
+
/**
|
|
54
|
+
* Countries in the source catalog that the source's dump directory nonetheless 404s — a fact about the source,
|
|
55
|
+
* recorded so a later reader does not spend the fetch to rediscover it.
|
|
56
|
+
*/
|
|
57
|
+
unavailable: string[];
|
|
58
|
+
/**
|
|
59
|
+
* Present `<CC>.txt` files that are NOT 19-column gazetteer dumps — GeoNames' postal exports share the same basename,
|
|
60
|
+
* and seven tier-1 postal files sat at these paths reading as "present" until the capitals build found them
|
|
61
|
+
* capital-less. Left in place (this tool never overwrites data it did not fetch); the fix is to move the file to its
|
|
62
|
+
* own home and rerun.
|
|
63
|
+
*/
|
|
64
|
+
wrong_format_present: string[];
|
|
65
|
+
}
|
|
66
|
+
/**
|
|
67
|
+
* True when the first non-empty line carries the gazetteer dump's 19 tab-separated columns. Accepts a partial head read
|
|
68
|
+
* — the first line is the whole question, so callers need not hand it a resident 350 MB dump.
|
|
69
|
+
*
|
|
70
|
+
* Walk the string directly rather than constructing a spliterator: the capitals builder already holds whole country
|
|
71
|
+
* dumps as strings, and a byte-oriented spliterator would UTF-8 encode that input — allocating up to another 350 MB —
|
|
72
|
+
* merely to inspect its first non-empty line.
|
|
73
|
+
*/
|
|
74
|
+
export declare function looksLikeGazetteerDump(text: string): boolean;
|
|
75
|
+
/**
|
|
76
|
+
* Parse the ISO codes (column 1) and capital names (column 6) out of `countryInfo.txt` — `#`-prefixed lines are the
|
|
77
|
+
* file's own commentary.
|
|
78
|
+
*/
|
|
79
|
+
export declare function parseCountryInfo(text: string): Array<{
|
|
80
|
+
country: string;
|
|
81
|
+
capital: string;
|
|
82
|
+
}>;
|
|
83
|
+
/**
|
|
84
|
+
* Download `countryInfo.txt` plus every missing `<CC>.zip`, extracting each to `<outRoot>/<CC>.txt` beside the
|
|
85
|
+
* hand-fetched dumps, with a `MANIFEST.json` naming fetched, skipped-present, and source-unavailable countries.
|
|
86
|
+
*/
|
|
87
|
+
export declare function fetchGeonamesDumps(options: FetchGeonamesDumpOptions, report?: (line: string) => void): Promise<FetchSummary & {
|
|
88
|
+
skippedPresent: string[];
|
|
89
|
+
}>;
|
|
90
|
+
export {};
|
|
91
|
+
//# sourceMappingURL=geonames-dump.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"geonames-dump.d.ts","sourceRoot":"","sources":["../../../lib/tools/fetch/geonames-dump.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;GAiBG;AAQH,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAA;AAgB3E,MAAM,WAAW,wBAAyB,SAAQ,gBAAgB;IACjE;;OAEG;IACH,SAAS,CAAC,EAAE,SAAS,MAAM,EAAE,CAAA;IAC7B;;;OAGG;IACH,OAAO,CAAC,EAAE,MAAM,CAAA;IAChB;;OAEG;IACH,KAAK,CAAC,EAAE,OAAO,CAAA;CACf;AAED,UAAU,qBAAqB;IAC9B,OAAO,EAAE,MAAM,CAAA;IACf,QAAQ,EAAE,MAAM,CAAA;IAChB,UAAU,EAAE,MAAM,CAAA;IAClB,MAAM,EAAE,MAAM,CAAA;IACd,KAAK,EAAE,MAAM,CAAA;CACb;AAED,MAAM,WAAW,oBAAoB;IACpC,MAAM,EAAE,MAAM,CAAA;IACd,QAAQ,EAAE,MAAM,CAAA;IAChB,OAAO,EAAE,MAAM,CAAA;IACf,WAAW,EAAE,MAAM,CAAA;IACnB,aAAa,EAAE,MAAM,CAAA;IACrB,KAAK,EAAE,qBAAqB,EAAE,CAAA;IAC9B;;OAEG;IACH,eAAe,EAAE,MAAM,EAAE,CAAA;IACzB;;;OAGG;IACH,WAAW,EAAE,MAAM,EAAE,CAAA;IACrB;;;;;OAKG;IACH,oBAAoB,EAAE,MAAM,EAAE,CAAA;CAC9B;AAQD;;;;;;;GAOG;AACH,wBAAgB,sBAAsB,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAuB5D;AAED;;;GAGG;AACH,wBAAgB,gBAAgB,CAAC,IAAI,EAAE,MAAM,GAAG,KAAK,CAAC;IAAE,OAAO,EAAE,MAAM,CAAC;IAAC,OAAO,EAAE,MAAM,CAAA;CAAE,CAAC,CAiB1F;AAQD;;;GAGG;AACH,wBAAsB,kBAAkB,CACvC,OAAO,EAAE,wBAAwB,EACjC,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,YAAY,GAAG;IAAE,cAAc,EAAE,MAAM,EAAE,CAAA;CAAE,CAAC,CA2FtD"}
|