@mailwoman/corpus 9.2.0 → 9.4.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +22 -22
- package/data/PROVENANCE.md +7 -7
- package/lib/adapters/ban/adapter.ts +190 -0
- package/lib/adapters/ban/street-decompose.ts +66 -0
- package/lib/adapters/fcc-bdc/adapter.ts +174 -0
- package/lib/adapters/geonames/adapter.ts +199 -0
- package/lib/adapters/geonames-postal/adapter.ts +122 -0
- package/lib/adapters/gnaf/adapter.ts +149 -0
- package/lib/adapters/gnaf/assemble.ts +225 -0
- package/lib/adapters/index.ts +153 -0
- package/lib/adapters/openaddresses/adapter.ts +251 -0
- package/lib/adapters/overture/adapter.ts +162 -0
- package/lib/adapters/state-hi-schools/adapter.ts +170 -0
- package/lib/adapters/state-hi-schools/workbook.ts +35 -0
- package/lib/adapters/synth-po-box/adapter.ts +204 -0
- package/lib/adapters/tiger/adapter.ts +252 -0
- package/lib/adapters/tiger/street-decompose.ts +83 -0
- package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +167 -0
- package/lib/adapters/usgov-imls-pls/adapter.ts +143 -0
- package/lib/adapters/usgov-irs-bmf/adapter.ts +151 -0
- package/lib/adapters/usgov-nad/adapter.ts +334 -0
- package/lib/adapters/usgov-nppes/adapter.ts +151 -0
- package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +193 -0
- package/lib/adapters/utils/index.ts +307 -0
- package/lib/adapters/wof-admin-jp/adapter.ts +214 -0
- package/lib/adapters/wof-admin-json/adapter.ts +231 -0
- package/lib/adapters/wof-json-rows.ts +129 -0
- package/lib/adapters/wof-postalcode-json/adapter.ts +176 -0
- package/lib/build.ts +378 -0
- package/lib/env.ts +50 -0
- package/lib/index.ts +13 -0
- package/lib/recipes/anchor-absorption.ts +101 -0
- package/lib/recipes/bare-country.ts +95 -0
- package/lib/recipes/boundary-stress.ts +102 -0
- package/lib/recipes/cn-organizational-units.ts +199 -0
- package/lib/recipes/country-balanced.ts +510 -0
- package/lib/recipes/cz-pcfirst-preposition.ts +112 -0
- package/lib/recipes/fr-admin-split.ts +243 -0
- package/lib/recipes/fr-bare-street.ts +171 -0
- package/lib/recipes/fr-fragment.ts +334 -0
- package/lib/recipes/fr-lieudit.ts +301 -0
- package/lib/recipes/fr-order.ts +246 -0
- package/lib/recipes/german.ts +360 -0
- package/lib/recipes/house-venue.ts +93 -0
- package/lib/recipes/index.ts +97 -0
- package/lib/recipes/intersection.ts +619 -0
- package/lib/recipes/locale.ts +600 -0
- package/lib/recipes/nl-postcode.ts +117 -0
- package/lib/recipes/no-fragment.ts +213 -0
- package/lib/recipes/no-street-led.ts +135 -0
- package/lib/recipes/no-street.ts +91 -0
- package/lib/recipes/po-box-cedex.ts +976 -0
- package/lib/recipes/po-box.ts +124 -0
- package/lib/recipes/reviewed-postcode-tail.ts +190 -0
- package/lib/recipes/scaffold.ts +468 -0
- package/lib/recipes/si-bare-village.ts +99 -0
- package/lib/recipes/street-affix.ts +805 -0
- package/lib/recipes/street-bare.ts +102 -0
- package/lib/recipes/street.ts +83 -0
- package/lib/recipes/sub-venue-sources.ts +878 -0
- package/lib/recipes/sub-venue.ts +998 -0
- package/lib/recipes/trailing-region.ts +178 -0
- package/lib/recipes/unit.ts +304 -0
- package/lib/runner.ts +312 -0
- package/lib/synthesizers/anchor-absorption.ts +288 -0
- package/lib/synthesizers/boundary-stress.ts +532 -0
- package/lib/synthesizers/german.ts +260 -0
- package/lib/synthesizers/house-venue.ts +308 -0
- package/lib/synthesizers/intersection.ts +233 -0
- package/lib/synthesizers/no-street.ts +327 -0
- package/lib/synthesizers/po-box.ts +323 -0
- package/lib/synthesizers/street.ts +269 -0
- package/lib/synthesizers/utils.ts +993 -0
- package/lib/test-kit/corpus-recipe.ts +86 -0
- package/lib/test-kit/index.ts +100 -0
- package/lib/tools/align-slice.ts +68 -0
- package/lib/tools/audit.ts +403 -0
- package/lib/tools/corpus-stats.ts +136 -0
- package/lib/tools/fetch/acra-sg.ts +174 -0
- package/lib/tools/fetch/ban.ts +289 -0
- package/lib/tools/fetch/download.ts +477 -0
- package/lib/tools/fetch/gcis-tw.ts +175 -0
- package/lib/tools/fetch/geonames-dump.ts +257 -0
- package/lib/tools/fetch/geonames-postal.ts +180 -0
- package/lib/tools/fetch/houjin-jp.ts +135 -0
- package/lib/tools/fetch/hrsa.ts +59 -0
- package/lib/tools/fetch/imls-pls.ts +149 -0
- package/lib/tools/fetch/index.ts +174 -0
- package/lib/tools/fetch/juso-kr.ts +165 -0
- package/lib/tools/fetch/localdata-kr.ts +194 -0
- package/lib/tools/fetch/nad.ts +341 -0
- package/lib/tools/fetch/nppes.ts +165 -0
- package/lib/tools/fetch/openaddresses.ts +347 -0
- package/lib/tools/fetch/ourairports.ts +170 -0
- package/lib/tools/fetch/ppd.ts +121 -0
- package/lib/tools/fetch/state-hi-schools.ts +161 -0
- package/lib/tools/fetch/state-sources.ts +146 -0
- package/lib/tools/fetch/tiger-full.ts +308 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +384 -0
- package/lib/tools/golden-expand.ts +574 -0
- package/lib/tools/golden-promote.ts +337 -0
- package/lib/tools/golden-relabel-street.ts +686 -0
- package/lib/tools/index.ts +28 -0
- package/lib/tools/ingest-csv.ts +378 -0
- package/lib/tools/jsonl-to-parquet.ts +207 -0
- package/lib/tools/lint-slice-vocab.ts +388 -0
- package/lib/tools/lint-slice.ts +496 -0
- package/lib/tools/overlay-manifest.ts +148 -0
- package/lib/tools/overture-subvenue.ts +209 -0
- package/lib/tools/postcode-triples.ts +363 -0
- package/lib/tools/slice-kryptonite.ts +137 -0
- package/lib/tools/slice-translit.ts +218 -0
- package/lib/tools/sub-venue/harvest.ts +234 -0
- package/lib/tools/sub-venue/head-nouns.ts +245 -0
- package/lib/tools/sub-venue/surfaces.ts +95 -0
- package/lib/tools/sub-venue/table.ts +281 -0
- package/lib/tools/sub-venue/wikidata.ts +85 -0
- package/lib/tools/sub-venue-lexicon.ts +429 -0
- package/lib/tools/sub-venue-promotions.ts +330 -0
- package/lib/types.ts +247 -0
- package/lib/utils/align.ts +330 -0
- package/lib/utils/golden.ts +189 -0
- package/lib/utils/index.ts +14 -0
- package/lib/utils/parquet.ts +582 -0
- package/lib/utils/slice-stats.ts +95 -0
- package/lib/utils/split.ts +279 -0
- package/lib/utils/tokenize.ts +120 -0
- package/lib/utils/wof-json.ts +247 -0
- package/out/adapters/ban/adapter.d.ts.map +1 -0
- package/out/adapters/ban/adapter.js +149 -0
- package/out/adapters/ban/adapter.js.map +1 -0
- package/out/adapters/ban/street-decompose.d.ts.map +1 -0
- package/out/adapters/ban/street-decompose.js +51 -0
- package/out/adapters/ban/street-decompose.js.map +1 -0
- package/out/adapters/fcc-bdc/adapter.d.ts.map +1 -0
- package/out/adapters/fcc-bdc/adapter.js +144 -0
- package/out/adapters/fcc-bdc/adapter.js.map +1 -0
- package/out/adapters/geonames/adapter.d.ts.map +1 -0
- package/out/adapters/geonames/adapter.js +176 -0
- package/out/adapters/geonames/adapter.js.map +1 -0
- package/out/adapters/geonames-postal/adapter.d.ts +54 -0
- package/out/adapters/geonames-postal/adapter.d.ts.map +1 -0
- package/out/adapters/geonames-postal/adapter.js +107 -0
- package/out/adapters/geonames-postal/adapter.js.map +1 -0
- package/out/adapters/gnaf/adapter.d.ts +49 -0
- package/out/adapters/gnaf/adapter.d.ts.map +1 -0
- package/out/adapters/gnaf/adapter.js +124 -0
- package/out/adapters/gnaf/adapter.js.map +1 -0
- package/out/adapters/gnaf/assemble.d.ts +65 -0
- package/out/adapters/gnaf/assemble.d.ts.map +1 -0
- package/out/adapters/gnaf/assemble.js +154 -0
- package/out/adapters/gnaf/assemble.js.map +1 -0
- package/out/adapters/index.d.ts +51 -0
- package/out/adapters/index.d.ts.map +1 -0
- package/out/adapters/index.js +95 -0
- package/out/adapters/index.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -0
- package/out/adapters/openaddresses/adapter.js +186 -0
- package/out/adapters/openaddresses/adapter.js.map +1 -0
- package/out/adapters/overture/adapter.d.ts +48 -0
- package/out/adapters/overture/adapter.d.ts.map +1 -0
- package/out/adapters/overture/adapter.js +125 -0
- package/out/adapters/overture/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/adapter.d.ts +46 -0
- package/out/adapters/state-hi-schools/adapter.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/adapter.js +145 -0
- package/out/adapters/state-hi-schools/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/workbook.d.ts +29 -0
- package/out/adapters/state-hi-schools/workbook.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/workbook.js +20 -0
- package/out/adapters/state-hi-schools/workbook.js.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
- package/out/adapters/synth-po-box/adapter.d.ts.map +1 -0
- package/out/adapters/synth-po-box/adapter.js +140 -0
- package/out/adapters/synth-po-box/adapter.js.map +1 -0
- package/out/adapters/tiger/adapter.d.ts +55 -0
- package/out/adapters/tiger/adapter.d.ts.map +1 -0
- package/out/adapters/tiger/adapter.js +201 -0
- package/out/adapters/tiger/adapter.js.map +1 -0
- package/out/adapters/tiger/street-decompose.d.ts.map +1 -0
- package/out/adapters/tiger/street-decompose.js +68 -0
- package/out/adapters/tiger/street-decompose.js.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +56 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js +132 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts +36 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.js +114 -0
- package/out/adapters/usgov-imls-pls/adapter.js.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts +37 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.js +120 -0
- package/out/adapters/usgov-irs-bmf/adapter.js.map +1 -0
- package/out/adapters/usgov-nad/adapter.d.ts +48 -0
- package/out/adapters/usgov-nad/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nad/adapter.js +249 -0
- package/out/adapters/usgov-nad/adapter.js.map +1 -0
- package/out/adapters/usgov-nppes/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nppes/adapter.js +118 -0
- package/out/adapters/usgov-nppes/adapter.js.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +154 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -0
- package/out/adapters/utils/index.d.ts +191 -0
- package/out/adapters/utils/index.d.ts.map +1 -0
- package/out/adapters/utils/index.js +206 -0
- package/out/adapters/utils/index.js.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.js +161 -0
- package/out/adapters/wof-admin-jp/adapter.js.map +1 -0
- package/out/adapters/wof-admin-json/adapter.d.ts +79 -0
- package/out/adapters/wof-admin-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-json/adapter.js +197 -0
- package/out/adapters/wof-admin-json/adapter.js.map +1 -0
- package/out/adapters/wof-json-rows.d.ts +62 -0
- package/out/adapters/wof-json-rows.d.ts.map +1 -0
- package/out/adapters/wof-json-rows.js +83 -0
- package/out/adapters/wof-json-rows.js.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts +65 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.js +151 -0
- package/out/adapters/wof-postalcode-json/adapter.js.map +1 -0
- package/out/build.d.ts +132 -0
- package/out/build.d.ts.map +1 -0
- package/out/build.js +245 -0
- package/out/build.js.map +1 -0
- package/out/codex/us-fips-state.d.ts.map +1 -0
- package/out/codex/us-fips-state.js.map +1 -0
- package/out/env.d.ts +46 -0
- package/out/env.d.ts.map +1 -0
- package/out/env.js +46 -0
- package/out/env.js.map +1 -0
- package/out/index.d.ts +13 -0
- package/out/index.d.ts.map +1 -0
- package/out/index.js +13 -0
- package/out/index.js.map +1 -0
- package/out/recipes/anchor-absorption.d.ts +20 -0
- package/out/recipes/anchor-absorption.d.ts.map +1 -0
- package/out/recipes/anchor-absorption.js +82 -0
- package/out/recipes/anchor-absorption.js.map +1 -0
- package/out/recipes/bare-country.d.ts +25 -0
- package/out/recipes/bare-country.d.ts.map +1 -0
- package/out/recipes/bare-country.js +88 -0
- package/out/recipes/bare-country.js.map +1 -0
- package/out/recipes/boundary-stress.d.ts +20 -0
- package/out/recipes/boundary-stress.d.ts.map +1 -0
- package/out/recipes/boundary-stress.js +84 -0
- package/out/recipes/boundary-stress.js.map +1 -0
- package/out/recipes/cn-organizational-units.d.ts +36 -0
- package/out/recipes/cn-organizational-units.d.ts.map +1 -0
- package/out/recipes/cn-organizational-units.js +159 -0
- package/out/recipes/cn-organizational-units.js.map +1 -0
- package/out/recipes/country-balanced.d.ts +32 -0
- package/out/recipes/country-balanced.d.ts.map +1 -0
- package/out/recipes/country-balanced.js +394 -0
- package/out/recipes/country-balanced.js.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts +22 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.js +101 -0
- package/out/recipes/cz-pcfirst-preposition.js.map +1 -0
- package/out/recipes/fr-admin-split.d.ts +38 -0
- package/out/recipes/fr-admin-split.d.ts.map +1 -0
- package/out/recipes/fr-admin-split.js +192 -0
- package/out/recipes/fr-admin-split.js.map +1 -0
- package/out/recipes/fr-bare-street.d.ts +28 -0
- package/out/recipes/fr-bare-street.d.ts.map +1 -0
- package/out/recipes/fr-bare-street.js +144 -0
- package/out/recipes/fr-bare-street.js.map +1 -0
- package/out/recipes/fr-fragment.d.ts +77 -0
- package/out/recipes/fr-fragment.d.ts.map +1 -0
- package/out/recipes/fr-fragment.js +277 -0
- package/out/recipes/fr-fragment.js.map +1 -0
- package/out/recipes/fr-lieudit.d.ts +32 -0
- package/out/recipes/fr-lieudit.d.ts.map +1 -0
- package/out/recipes/fr-lieudit.js +227 -0
- package/out/recipes/fr-lieudit.js.map +1 -0
- package/out/recipes/fr-order.d.ts +38 -0
- package/out/recipes/fr-order.d.ts.map +1 -0
- package/out/recipes/fr-order.js +198 -0
- package/out/recipes/fr-order.js.map +1 -0
- package/out/recipes/german.d.ts +44 -0
- package/out/recipes/german.d.ts.map +1 -0
- package/out/recipes/german.js +289 -0
- package/out/recipes/german.js.map +1 -0
- package/out/recipes/house-venue.d.ts +18 -0
- package/out/recipes/house-venue.d.ts.map +1 -0
- package/out/recipes/house-venue.js +74 -0
- package/out/recipes/house-venue.js.map +1 -0
- package/out/recipes/index.d.ts +24 -0
- package/out/recipes/index.d.ts.map +1 -0
- package/out/recipes/index.js +91 -0
- package/out/recipes/index.js.map +1 -0
- package/out/recipes/intersection.d.ts +42 -0
- package/out/recipes/intersection.d.ts.map +1 -0
- package/out/recipes/intersection.js +453 -0
- package/out/recipes/intersection.js.map +1 -0
- package/out/recipes/locale.d.ts +136 -0
- package/out/recipes/locale.d.ts.map +1 -0
- package/out/recipes/locale.js +460 -0
- package/out/recipes/locale.js.map +1 -0
- package/out/recipes/nl-postcode.d.ts +26 -0
- package/out/recipes/nl-postcode.d.ts.map +1 -0
- package/out/recipes/nl-postcode.js +103 -0
- package/out/recipes/nl-postcode.js.map +1 -0
- package/out/recipes/no-fragment.d.ts +43 -0
- package/out/recipes/no-fragment.d.ts.map +1 -0
- package/out/recipes/no-fragment.js +183 -0
- package/out/recipes/no-fragment.js.map +1 -0
- package/out/recipes/no-street-led.d.ts +24 -0
- package/out/recipes/no-street-led.d.ts.map +1 -0
- package/out/recipes/no-street-led.js +114 -0
- package/out/recipes/no-street-led.js.map +1 -0
- package/out/recipes/no-street.d.ts +18 -0
- package/out/recipes/no-street.d.ts.map +1 -0
- package/out/recipes/no-street.js +72 -0
- package/out/recipes/no-street.js.map +1 -0
- package/out/recipes/po-box-cedex.d.ts +38 -0
- package/out/recipes/po-box-cedex.d.ts.map +1 -0
- package/out/recipes/po-box-cedex.js +768 -0
- package/out/recipes/po-box-cedex.js.map +1 -0
- package/out/recipes/po-box.d.ts +17 -0
- package/out/recipes/po-box.d.ts.map +1 -0
- package/out/recipes/po-box.js +101 -0
- package/out/recipes/po-box.js.map +1 -0
- package/out/recipes/reviewed-postcode-tail.d.ts +47 -0
- package/out/recipes/reviewed-postcode-tail.d.ts.map +1 -0
- package/out/recipes/reviewed-postcode-tail.js +125 -0
- package/out/recipes/reviewed-postcode-tail.js.map +1 -0
- package/out/recipes/scaffold.d.ts +323 -0
- package/out/recipes/scaffold.d.ts.map +1 -0
- package/out/recipes/scaffold.js +174 -0
- package/out/recipes/scaffold.js.map +1 -0
- package/out/recipes/si-bare-village.d.ts +32 -0
- package/out/recipes/si-bare-village.d.ts.map +1 -0
- package/out/recipes/si-bare-village.js +89 -0
- package/out/recipes/si-bare-village.js.map +1 -0
- package/out/recipes/street-affix.d.ts +89 -0
- package/out/recipes/street-affix.d.ts.map +1 -0
- package/out/recipes/street-affix.js +563 -0
- package/out/recipes/street-affix.js.map +1 -0
- package/out/recipes/street-bare.d.ts +25 -0
- package/out/recipes/street-bare.d.ts.map +1 -0
- package/out/recipes/street-bare.js +87 -0
- package/out/recipes/street-bare.js.map +1 -0
- package/out/recipes/street.d.ts +15 -0
- package/out/recipes/street.d.ts.map +1 -0
- package/out/recipes/street.js +70 -0
- package/out/recipes/street.js.map +1 -0
- package/out/recipes/sub-venue-sources.d.ts +229 -0
- package/out/recipes/sub-venue-sources.d.ts.map +1 -0
- package/out/recipes/sub-venue-sources.js +654 -0
- package/out/recipes/sub-venue-sources.js.map +1 -0
- package/out/recipes/sub-venue.d.ts +269 -0
- package/out/recipes/sub-venue.d.ts.map +1 -0
- package/out/recipes/sub-venue.js +726 -0
- package/out/recipes/sub-venue.js.map +1 -0
- package/out/recipes/trailing-region.d.ts +74 -0
- package/out/recipes/trailing-region.d.ts.map +1 -0
- package/out/recipes/trailing-region.js +158 -0
- package/out/recipes/trailing-region.js.map +1 -0
- package/out/recipes/unit.d.ts +29 -0
- package/out/recipes/unit.d.ts.map +1 -0
- package/out/recipes/unit.js +231 -0
- package/out/recipes/unit.js.map +1 -0
- package/out/runner.d.ts +130 -0
- package/out/runner.d.ts.map +1 -0
- package/out/runner.js +185 -0
- package/out/runner.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +63 -0
- package/out/synthesizers/anchor-absorption.d.ts.map +1 -0
- package/out/synthesizers/anchor-absorption.js +221 -0
- package/out/synthesizers/anchor-absorption.js.map +1 -0
- package/out/synthesizers/boundary-stress.d.ts +78 -0
- package/out/synthesizers/boundary-stress.d.ts.map +1 -0
- package/out/synthesizers/boundary-stress.js +455 -0
- package/out/synthesizers/boundary-stress.js.map +1 -0
- package/out/synthesizers/german.d.ts +115 -0
- package/out/synthesizers/german.d.ts.map +1 -0
- package/out/synthesizers/german.js +149 -0
- package/out/synthesizers/german.js.map +1 -0
- package/out/synthesizers/house-venue.d.ts +56 -0
- package/out/synthesizers/house-venue.d.ts.map +1 -0
- package/out/synthesizers/house-venue.js +247 -0
- package/out/synthesizers/house-venue.js.map +1 -0
- package/out/synthesizers/intersection.d.ts +52 -0
- package/out/synthesizers/intersection.d.ts.map +1 -0
- package/out/synthesizers/intersection.js +175 -0
- package/out/synthesizers/intersection.js.map +1 -0
- package/out/synthesizers/no-street.d.ts +72 -0
- package/out/synthesizers/no-street.d.ts.map +1 -0
- package/out/synthesizers/no-street.js +262 -0
- package/out/synthesizers/no-street.js.map +1 -0
- package/out/synthesizers/po-box.d.ts +108 -0
- package/out/synthesizers/po-box.d.ts.map +1 -0
- package/out/synthesizers/po-box.js +250 -0
- package/out/synthesizers/po-box.js.map +1 -0
- package/out/synthesizers/street.d.ts +54 -0
- package/out/synthesizers/street.d.ts.map +1 -0
- package/out/synthesizers/street.js +218 -0
- package/out/synthesizers/street.js.map +1 -0
- package/out/synthesizers/utils.d.ts +241 -0
- package/out/synthesizers/utils.d.ts.map +1 -0
- package/out/synthesizers/utils.js +776 -0
- package/out/synthesizers/utils.js.map +1 -0
- package/out/test-kit/corpus-recipe.d.ts +59 -0
- package/out/test-kit/corpus-recipe.d.ts.map +1 -0
- package/out/test-kit/corpus-recipe.js +39 -0
- package/out/test-kit/corpus-recipe.js.map +1 -0
- package/out/test-kit/index.d.ts +48 -0
- package/out/test-kit/index.d.ts.map +1 -0
- package/out/test-kit/index.js +78 -0
- package/out/test-kit/index.js.map +1 -0
- package/out/tools/align-slice.d.ts +7 -0
- package/out/tools/align-slice.d.ts.map +1 -0
- package/out/tools/align-slice.js +55 -0
- package/out/tools/align-slice.js.map +1 -0
- package/out/tools/audit.d.ts +29 -0
- package/out/tools/audit.d.ts.map +1 -0
- package/out/tools/audit.js +282 -0
- package/out/tools/audit.js.map +1 -0
- package/out/tools/corpus-stats.d.ts +44 -0
- package/out/tools/corpus-stats.d.ts.map +1 -0
- package/out/tools/corpus-stats.js +102 -0
- package/out/tools/corpus-stats.js.map +1 -0
- package/out/tools/fetch/acra-sg.d.ts +23 -0
- package/out/tools/fetch/acra-sg.d.ts.map +1 -0
- package/out/tools/fetch/acra-sg.js +126 -0
- package/out/tools/fetch/acra-sg.js.map +1 -0
- package/out/tools/fetch/ban.d.ts +31 -0
- package/out/tools/fetch/ban.d.ts.map +1 -0
- package/out/tools/fetch/ban.js +239 -0
- package/out/tools/fetch/ban.js.map +1 -0
- package/out/tools/fetch/download.d.ts +182 -0
- package/out/tools/fetch/download.d.ts.map +1 -0
- package/out/tools/fetch/download.js +318 -0
- package/out/tools/fetch/download.js.map +1 -0
- package/out/tools/fetch/gcis-tw.d.ts +23 -0
- package/out/tools/fetch/gcis-tw.d.ts.map +1 -0
- package/out/tools/fetch/gcis-tw.js +135 -0
- package/out/tools/fetch/gcis-tw.js.map +1 -0
- package/out/tools/fetch/geonames-dump.d.ts +91 -0
- package/out/tools/fetch/geonames-dump.d.ts.map +1 -0
- package/out/tools/fetch/geonames-dump.js +171 -0
- package/out/tools/fetch/geonames-dump.js.map +1 -0
- package/out/tools/fetch/geonames-postal.d.ts +76 -0
- package/out/tools/fetch/geonames-postal.d.ts.map +1 -0
- package/out/tools/fetch/geonames-postal.js +126 -0
- package/out/tools/fetch/geonames-postal.js.map +1 -0
- package/out/tools/fetch/houjin-jp.d.ts +24 -0
- package/out/tools/fetch/houjin-jp.d.ts.map +1 -0
- package/out/tools/fetch/houjin-jp.js +102 -0
- package/out/tools/fetch/houjin-jp.js.map +1 -0
- package/out/tools/fetch/hrsa.d.ts +18 -0
- package/out/tools/fetch/hrsa.d.ts.map +1 -0
- package/out/tools/fetch/hrsa.js +46 -0
- package/out/tools/fetch/hrsa.js.map +1 -0
- package/out/tools/fetch/imls-pls.d.ts +25 -0
- package/out/tools/fetch/imls-pls.d.ts.map +1 -0
- package/out/tools/fetch/imls-pls.js +108 -0
- package/out/tools/fetch/imls-pls.js.map +1 -0
- package/out/tools/fetch/index.d.ts +171 -0
- package/out/tools/fetch/index.d.ts.map +1 -0
- package/out/tools/fetch/index.js +170 -0
- package/out/tools/fetch/index.js.map +1 -0
- package/out/tools/fetch/juso-kr.d.ts +30 -0
- package/out/tools/fetch/juso-kr.d.ts.map +1 -0
- package/out/tools/fetch/juso-kr.js +120 -0
- package/out/tools/fetch/juso-kr.js.map +1 -0
- package/out/tools/fetch/localdata-kr.d.ts +30 -0
- package/out/tools/fetch/localdata-kr.d.ts.map +1 -0
- package/out/tools/fetch/localdata-kr.js +139 -0
- package/out/tools/fetch/localdata-kr.js.map +1 -0
- package/out/tools/fetch/nad.d.ts +70 -0
- package/out/tools/fetch/nad.d.ts.map +1 -0
- package/out/tools/fetch/nad.js +234 -0
- package/out/tools/fetch/nad.js.map +1 -0
- package/out/tools/fetch/nppes.d.ts +26 -0
- package/out/tools/fetch/nppes.d.ts.map +1 -0
- package/out/tools/fetch/nppes.js +126 -0
- package/out/tools/fetch/nppes.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +9 -0
- package/out/tools/fetch/openaddresses.d.ts.map +1 -0
- package/out/tools/fetch/openaddresses.js +279 -0
- package/out/tools/fetch/openaddresses.js.map +1 -0
- package/out/tools/fetch/ourairports.d.ts +45 -0
- package/out/tools/fetch/ourairports.d.ts.map +1 -0
- package/out/tools/fetch/ourairports.js +128 -0
- package/out/tools/fetch/ourairports.js.map +1 -0
- package/out/tools/fetch/ppd.d.ts.map +1 -0
- package/out/tools/fetch/ppd.js +85 -0
- package/out/tools/fetch/ppd.js.map +1 -0
- package/out/tools/fetch/state-hi-schools.d.ts +26 -0
- package/out/tools/fetch/state-hi-schools.d.ts.map +1 -0
- package/out/tools/fetch/state-hi-schools.js +112 -0
- package/out/tools/fetch/state-hi-schools.js.map +1 -0
- package/out/tools/fetch/state-sources.d.ts +26 -0
- package/out/tools/fetch/state-sources.d.ts.map +1 -0
- package/out/tools/fetch/state-sources.js +111 -0
- package/out/tools/fetch/state-sources.js.map +1 -0
- package/out/tools/fetch/tiger-full.d.ts +22 -0
- package/out/tools/fetch/tiger-full.d.ts.map +1 -0
- package/out/tools/fetch/tiger-full.js +217 -0
- package/out/tools/fetch/tiger-full.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +171 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.js +274 -0
- package/out/tools/fetch/wikidata-subvenue.js.map +1 -0
- package/out/tools/gb-title-case.d.ts.map +1 -0
- package/out/tools/gb-title-case.js.map +1 -0
- package/out/tools/golden-expand.d.ts +90 -0
- package/out/tools/golden-expand.d.ts.map +1 -0
- package/out/tools/golden-expand.js +406 -0
- package/out/tools/golden-expand.js.map +1 -0
- package/out/tools/golden-promote.d.ts.map +1 -0
- package/out/tools/golden-promote.js +240 -0
- package/out/tools/golden-promote.js.map +1 -0
- package/out/tools/golden-relabel-street.d.ts +196 -0
- package/out/tools/golden-relabel-street.d.ts.map +1 -0
- package/out/tools/golden-relabel-street.js +439 -0
- package/out/tools/golden-relabel-street.js.map +1 -0
- package/out/tools/index.d.ts +28 -0
- package/out/tools/index.d.ts.map +1 -0
- package/out/tools/index.js +28 -0
- package/out/tools/index.js.map +1 -0
- package/out/tools/ingest-csv.d.ts.map +1 -0
- package/out/tools/ingest-csv.js +265 -0
- package/out/tools/ingest-csv.js.map +1 -0
- package/out/tools/jsonl-to-parquet.d.ts +61 -0
- package/out/tools/jsonl-to-parquet.d.ts.map +1 -0
- package/out/tools/jsonl-to-parquet.js +150 -0
- package/out/tools/jsonl-to-parquet.js.map +1 -0
- package/out/tools/lint-slice-vocab.d.ts +90 -0
- package/out/tools/lint-slice-vocab.d.ts.map +1 -0
- package/out/tools/lint-slice-vocab.js +267 -0
- package/out/tools/lint-slice-vocab.js.map +1 -0
- package/out/tools/lint-slice.d.ts +93 -0
- package/out/tools/lint-slice.d.ts.map +1 -0
- package/out/tools/lint-slice.js +322 -0
- package/out/tools/lint-slice.js.map +1 -0
- package/out/tools/overlay-manifest.d.ts +39 -0
- package/out/tools/overlay-manifest.d.ts.map +1 -0
- package/out/tools/overlay-manifest.js +90 -0
- package/out/tools/overlay-manifest.js.map +1 -0
- package/out/tools/overture-subvenue.d.ts +112 -0
- package/out/tools/overture-subvenue.d.ts.map +1 -0
- package/out/tools/overture-subvenue.js +139 -0
- package/out/tools/overture-subvenue.js.map +1 -0
- package/out/tools/postcode-triples.d.ts +174 -0
- package/out/tools/postcode-triples.d.ts.map +1 -0
- package/out/tools/postcode-triples.js +292 -0
- package/out/tools/postcode-triples.js.map +1 -0
- package/out/tools/slice-kryptonite.d.ts +32 -0
- package/out/tools/slice-kryptonite.d.ts.map +1 -0
- package/out/tools/slice-kryptonite.js +99 -0
- package/out/tools/slice-kryptonite.js.map +1 -0
- package/out/tools/slice-translit.d.ts +51 -0
- package/out/tools/slice-translit.d.ts.map +1 -0
- package/out/tools/slice-translit.js +166 -0
- package/out/tools/slice-translit.js.map +1 -0
- package/out/tools/sub-venue/harvest.d.ts +100 -0
- package/out/tools/sub-venue/harvest.d.ts.map +1 -0
- package/out/tools/sub-venue/harvest.js +168 -0
- package/out/tools/sub-venue/harvest.js.map +1 -0
- package/out/tools/sub-venue/head-nouns.d.ts +50 -0
- package/out/tools/sub-venue/head-nouns.d.ts.map +1 -0
- package/out/tools/sub-venue/head-nouns.js +213 -0
- package/out/tools/sub-venue/head-nouns.js.map +1 -0
- package/out/tools/sub-venue/surfaces.d.ts +45 -0
- package/out/tools/sub-venue/surfaces.d.ts.map +1 -0
- package/out/tools/sub-venue/surfaces.js +77 -0
- package/out/tools/sub-venue/surfaces.js.map +1 -0
- package/out/tools/sub-venue/table.d.ts +229 -0
- package/out/tools/sub-venue/table.d.ts.map +1 -0
- package/out/tools/sub-venue/table.js +108 -0
- package/out/tools/sub-venue/table.js.map +1 -0
- package/out/tools/sub-venue/wikidata.d.ts +26 -0
- package/out/tools/sub-venue/wikidata.d.ts.map +1 -0
- package/out/tools/sub-venue/wikidata.js +62 -0
- package/out/tools/sub-venue/wikidata.js.map +1 -0
- package/out/tools/sub-venue-lexicon.d.ts +156 -0
- package/out/tools/sub-venue-lexicon.d.ts.map +1 -0
- package/out/tools/sub-venue-lexicon.js +283 -0
- package/out/tools/sub-venue-lexicon.js.map +1 -0
- package/out/tools/sub-venue-promotions.d.ts +94 -0
- package/out/tools/sub-venue-promotions.d.ts.map +1 -0
- package/out/tools/sub-venue-promotions.js +266 -0
- package/out/tools/sub-venue-promotions.js.map +1 -0
- package/out/types.d.ts +221 -0
- package/out/types.d.ts.map +1 -0
- package/out/types.js.map +1 -0
- package/out/utils/align.d.ts +93 -0
- package/out/utils/align.d.ts.map +1 -0
- package/out/utils/align.js +234 -0
- package/out/utils/align.js.map +1 -0
- package/out/utils/golden.d.ts +85 -0
- package/out/utils/golden.d.ts.map +1 -0
- package/out/utils/golden.js +127 -0
- package/out/utils/golden.js.map +1 -0
- package/out/utils/index.d.ts +14 -0
- package/out/utils/index.d.ts.map +1 -0
- package/out/utils/index.js +14 -0
- package/out/utils/index.js.map +1 -0
- package/out/utils/license.d.ts.map +1 -0
- package/out/utils/license.js.map +1 -0
- package/out/utils/parquet.d.ts +178 -0
- package/out/utils/parquet.d.ts.map +1 -0
- package/out/utils/parquet.js +371 -0
- package/out/utils/parquet.js.map +1 -0
- package/out/utils/slice-stats.d.ts +52 -0
- package/out/utils/slice-stats.d.ts.map +1 -0
- package/out/utils/slice-stats.js +58 -0
- package/out/utils/slice-stats.js.map +1 -0
- package/out/utils/split.d.ts +128 -0
- package/out/utils/split.d.ts.map +1 -0
- package/out/utils/split.js +204 -0
- package/out/utils/split.js.map +1 -0
- package/out/utils/tokenize.d.ts +64 -0
- package/out/utils/tokenize.d.ts.map +1 -0
- package/out/utils/tokenize.js +82 -0
- package/out/utils/tokenize.js.map +1 -0
- package/out/utils/wof-json.d.ts +113 -0
- package/out/utils/wof-json.d.ts.map +1 -0
- package/out/utils/wof-json.js +173 -0
- package/out/utils/wof-json.js.map +1 -0
- package/package.json +259 -194
- package/out/src/adapters/ban/adapter.d.ts.map +0 -1
- package/out/src/adapters/ban/adapter.js +0 -149
- package/out/src/adapters/ban/adapter.js.map +0 -1
- package/out/src/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/ban/street-decompose.js +0 -75
- package/out/src/adapters/ban/street-decompose.js.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.d.ts.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.js +0 -144
- package/out/src/adapters/fcc-bdc/adapter.js.map +0 -1
- package/out/src/adapters/geonames/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames/adapter.js +0 -176
- package/out/src/adapters/geonames/adapter.js.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.d.ts +0 -41
- package/out/src/adapters/geonames-postal/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.js +0 -104
- package/out/src/adapters/geonames-postal/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/adapter.d.ts +0 -49
- package/out/src/adapters/gnaf/adapter.d.ts.map +0 -1
- package/out/src/adapters/gnaf/adapter.js +0 -124
- package/out/src/adapters/gnaf/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/assemble.d.ts +0 -65
- package/out/src/adapters/gnaf/assemble.d.ts.map +0 -1
- package/out/src/adapters/gnaf/assemble.js +0 -154
- package/out/src/adapters/gnaf/assemble.js.map +0 -1
- package/out/src/adapters/index.d.ts +0 -51
- package/out/src/adapters/index.d.ts.map +0 -1
- package/out/src/adapters/index.js +0 -95
- package/out/src/adapters/index.js.map +0 -1
- package/out/src/adapters/openaddresses/adapter.d.ts.map +0 -1
- package/out/src/adapters/openaddresses/adapter.js +0 -186
- package/out/src/adapters/openaddresses/adapter.js.map +0 -1
- package/out/src/adapters/overture/adapter.d.ts +0 -48
- package/out/src/adapters/overture/adapter.d.ts.map +0 -1
- package/out/src/adapters/overture/adapter.js +0 -125
- package/out/src/adapters/overture/adapter.js.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.d.ts +0 -47
- package/out/src/adapters/state-hi-schools/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.js +0 -133
- package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.d.ts.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.js +0 -140
- package/out/src/adapters/synth-po-box/adapter.js.map +0 -1
- package/out/src/adapters/tiger/adapter.d.ts +0 -55
- package/out/src/adapters/tiger/adapter.d.ts.map +0 -1
- package/out/src/adapters/tiger/adapter.js +0 -201
- package/out/src/adapters/tiger/adapter.js.map +0 -1
- package/out/src/adapters/tiger/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/tiger/street-decompose.js +0 -90
- package/out/src/adapters/tiger/street-decompose.js.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -47
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +0 -139
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts +0 -36
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.js +0 -114
- package/out/src/adapters/usgov-imls-pls/adapter.js.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.js +0 -124
- package/out/src/adapters/usgov-irs-bmf/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.d.ts +0 -48
- package/out/src/adapters/usgov-nad/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.js +0 -252
- package/out/src/adapters/usgov-nad/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.js +0 -116
- package/out/src/adapters/usgov-nppes/adapter.js.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -156
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
- package/out/src/adapters/utils/index.d.ts +0 -150
- package/out/src/adapters/utils/index.d.ts.map +0 -1
- package/out/src/adapters/utils/index.js +0 -159
- package/out/src/adapters/utils/index.js.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.js +0 -164
- package/out/src/adapters/wof-admin-jp/adapter.js.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.d.ts +0 -82
- package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.js +0 -224
- package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
- package/out/src/adapters/wof-json-rows.d.ts +0 -32
- package/out/src/adapters/wof-json-rows.d.ts.map +0 -1
- package/out/src/adapters/wof-json-rows.js +0 -45
- package/out/src/adapters/wof-json-rows.js.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -65
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.js +0 -160
- package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
- package/out/src/build.d.ts +0 -132
- package/out/src/build.d.ts.map +0 -1
- package/out/src/build.js +0 -251
- package/out/src/build.js.map +0 -1
- package/out/src/codex/us-fips-state.d.ts.map +0 -1
- package/out/src/codex/us-fips-state.js.map +0 -1
- package/out/src/index.d.ts +0 -14
- package/out/src/index.d.ts.map +0 -1
- package/out/src/index.js +0 -14
- package/out/src/index.js.map +0 -1
- package/out/src/name-prone-us-suffixes.d.ts +0 -12
- package/out/src/name-prone-us-suffixes.d.ts.map +0 -1
- package/out/src/name-prone-us-suffixes.js +0 -12
- package/out/src/name-prone-us-suffixes.js.map +0 -1
- package/out/src/parquet-wrapper/index.d.ts +0 -9
- package/out/src/parquet-wrapper/index.d.ts.map +0 -1
- package/out/src/parquet-wrapper/index.js +0 -9
- package/out/src/parquet-wrapper/index.js.map +0 -1
- package/out/src/parquet-wrapper/reader.d.ts +0 -34
- package/out/src/parquet-wrapper/reader.d.ts.map +0 -1
- package/out/src/parquet-wrapper/reader.js +0 -69
- package/out/src/parquet-wrapper/reader.js.map +0 -1
- package/out/src/parquet-wrapper/schema.d.ts +0 -49
- package/out/src/parquet-wrapper/schema.d.ts.map +0 -1
- package/out/src/parquet-wrapper/schema.js +0 -55
- package/out/src/parquet-wrapper/schema.js.map +0 -1
- package/out/src/parquet-wrapper/writer.d.ts +0 -46
- package/out/src/parquet-wrapper/writer.d.ts.map +0 -1
- package/out/src/parquet-wrapper/writer.js +0 -76
- package/out/src/parquet-wrapper/writer.js.map +0 -1
- package/out/src/runner.d.ts +0 -126
- package/out/src/runner.d.ts.map +0 -1
- package/out/src/runner.js +0 -189
- package/out/src/runner.js.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.d.ts +0 -20
- package/out/src/shard-recipes/anchor-absorption.d.ts.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.js +0 -82
- package/out/src/shard-recipes/anchor-absorption.js.map +0 -1
- package/out/src/shard-recipes/bare-country.d.ts +0 -25
- package/out/src/shard-recipes/bare-country.d.ts.map +0 -1
- package/out/src/shard-recipes/bare-country.js +0 -87
- package/out/src/shard-recipes/bare-country.js.map +0 -1
- package/out/src/shard-recipes/boundary-stress.d.ts +0 -20
- package/out/src/shard-recipes/boundary-stress.d.ts.map +0 -1
- package/out/src/shard-recipes/boundary-stress.js +0 -83
- package/out/src/shard-recipes/boundary-stress.js.map +0 -1
- package/out/src/shard-recipes/country-balanced.d.ts +0 -32
- package/out/src/shard-recipes/country-balanced.d.ts.map +0 -1
- package/out/src/shard-recipes/country-balanced.js +0 -406
- package/out/src/shard-recipes/country-balanced.js.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts +0 -22
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.js +0 -100
- package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.d.ts +0 -38
- package/out/src/shard-recipes/fr-admin-split.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.js +0 -188
- package/out/src/shard-recipes/fr-admin-split.js.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.d.ts +0 -28
- package/out/src/shard-recipes/fr-bare-street.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.js +0 -143
- package/out/src/shard-recipes/fr-bare-street.js.map +0 -1
- package/out/src/shard-recipes/fr-fragment.d.ts +0 -77
- package/out/src/shard-recipes/fr-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-fragment.js +0 -276
- package/out/src/shard-recipes/fr-fragment.js.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.d.ts +0 -32
- package/out/src/shard-recipes/fr-lieudit.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.js +0 -226
- package/out/src/shard-recipes/fr-lieudit.js.map +0 -1
- package/out/src/shard-recipes/fr-order.d.ts +0 -38
- package/out/src/shard-recipes/fr-order.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-order.js +0 -208
- package/out/src/shard-recipes/fr-order.js.map +0 -1
- package/out/src/shard-recipes/german.d.ts +0 -23
- package/out/src/shard-recipes/german.d.ts.map +0 -1
- package/out/src/shard-recipes/german.js +0 -132
- package/out/src/shard-recipes/german.js.map +0 -1
- package/out/src/shard-recipes/house-venue.d.ts +0 -18
- package/out/src/shard-recipes/house-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/house-venue.js +0 -74
- package/out/src/shard-recipes/house-venue.js.map +0 -1
- package/out/src/shard-recipes/index.d.ts +0 -24
- package/out/src/shard-recipes/index.d.ts.map +0 -1
- package/out/src/shard-recipes/index.js +0 -89
- package/out/src/shard-recipes/index.js.map +0 -1
- package/out/src/shard-recipes/intersection.d.ts +0 -42
- package/out/src/shard-recipes/intersection.d.ts.map +0 -1
- package/out/src/shard-recipes/intersection.js +0 -460
- package/out/src/shard-recipes/intersection.js.map +0 -1
- package/out/src/shard-recipes/locale.d.ts +0 -135
- package/out/src/shard-recipes/locale.d.ts.map +0 -1
- package/out/src/shard-recipes/locale.js +0 -459
- package/out/src/shard-recipes/locale.js.map +0 -1
- package/out/src/shard-recipes/nl-postcode.d.ts +0 -26
- package/out/src/shard-recipes/nl-postcode.d.ts.map +0 -1
- package/out/src/shard-recipes/nl-postcode.js +0 -102
- package/out/src/shard-recipes/nl-postcode.js.map +0 -1
- package/out/src/shard-recipes/no-fragment.d.ts +0 -43
- package/out/src/shard-recipes/no-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/no-fragment.js +0 -188
- package/out/src/shard-recipes/no-fragment.js.map +0 -1
- package/out/src/shard-recipes/no-street-led.d.ts +0 -24
- package/out/src/shard-recipes/no-street-led.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street-led.js +0 -121
- package/out/src/shard-recipes/no-street-led.js.map +0 -1
- package/out/src/shard-recipes/no-street.d.ts +0 -18
- package/out/src/shard-recipes/no-street.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street.js +0 -72
- package/out/src/shard-recipes/no-street.js.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.d.ts +0 -38
- package/out/src/shard-recipes/po-box-cedex.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.js +0 -726
- package/out/src/shard-recipes/po-box-cedex.js.map +0 -1
- package/out/src/shard-recipes/po-box.d.ts +0 -17
- package/out/src/shard-recipes/po-box.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box.js +0 -101
- package/out/src/shard-recipes/po-box.js.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts +0 -47
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.js +0 -125
- package/out/src/shard-recipes/reviewed-postcode-tail.js.map +0 -1
- package/out/src/shard-recipes/scaffold.d.ts +0 -246
- package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
- package/out/src/shard-recipes/scaffold.js +0 -137
- package/out/src/shard-recipes/scaffold.js.map +0 -1
- package/out/src/shard-recipes/si-bare-village.d.ts +0 -32
- package/out/src/shard-recipes/si-bare-village.d.ts.map +0 -1
- package/out/src/shard-recipes/si-bare-village.js +0 -88
- package/out/src/shard-recipes/si-bare-village.js.map +0 -1
- package/out/src/shard-recipes/street-affix.d.ts +0 -89
- package/out/src/shard-recipes/street-affix.d.ts.map +0 -1
- package/out/src/shard-recipes/street-affix.js +0 -578
- package/out/src/shard-recipes/street-affix.js.map +0 -1
- package/out/src/shard-recipes/street-bare.d.ts +0 -25
- package/out/src/shard-recipes/street-bare.d.ts.map +0 -1
- package/out/src/shard-recipes/street-bare.js +0 -86
- package/out/src/shard-recipes/street-bare.js.map +0 -1
- package/out/src/shard-recipes/street.d.ts +0 -15
- package/out/src/shard-recipes/street.d.ts.map +0 -1
- package/out/src/shard-recipes/street.js +0 -69
- package/out/src/shard-recipes/street.js.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.d.ts +0 -228
- package/out/src/shard-recipes/sub-venue-sources.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.js +0 -664
- package/out/src/shard-recipes/sub-venue-sources.js.map +0 -1
- package/out/src/shard-recipes/sub-venue.d.ts +0 -269
- package/out/src/shard-recipes/sub-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue.js +0 -710
- package/out/src/shard-recipes/sub-venue.js.map +0 -1
- package/out/src/shard-recipes/trailing-region.d.ts +0 -74
- package/out/src/shard-recipes/trailing-region.d.ts.map +0 -1
- package/out/src/shard-recipes/trailing-region.js +0 -157
- package/out/src/shard-recipes/trailing-region.js.map +0 -1
- package/out/src/shard-recipes/unit.d.ts +0 -29
- package/out/src/shard-recipes/unit.d.ts.map +0 -1
- package/out/src/shard-recipes/unit.js +0 -243
- package/out/src/shard-recipes/unit.js.map +0 -1
- package/out/src/synthesizers/anchor-absorption.d.ts +0 -63
- package/out/src/synthesizers/anchor-absorption.d.ts.map +0 -1
- package/out/src/synthesizers/anchor-absorption.js +0 -223
- package/out/src/synthesizers/anchor-absorption.js.map +0 -1
- package/out/src/synthesizers/boundary-stress.d.ts +0 -78
- package/out/src/synthesizers/boundary-stress.d.ts.map +0 -1
- package/out/src/synthesizers/boundary-stress.js +0 -455
- package/out/src/synthesizers/boundary-stress.js.map +0 -1
- package/out/src/synthesizers/german.d.ts +0 -107
- package/out/src/synthesizers/german.d.ts.map +0 -1
- package/out/src/synthesizers/german.js +0 -148
- package/out/src/synthesizers/german.js.map +0 -1
- package/out/src/synthesizers/house-venue.d.ts +0 -56
- package/out/src/synthesizers/house-venue.d.ts.map +0 -1
- package/out/src/synthesizers/house-venue.js +0 -267
- package/out/src/synthesizers/house-venue.js.map +0 -1
- package/out/src/synthesizers/intersection.d.ts +0 -52
- package/out/src/synthesizers/intersection.d.ts.map +0 -1
- package/out/src/synthesizers/intersection.js +0 -175
- package/out/src/synthesizers/intersection.js.map +0 -1
- package/out/src/synthesizers/no-street.d.ts +0 -72
- package/out/src/synthesizers/no-street.d.ts.map +0 -1
- package/out/src/synthesizers/no-street.js +0 -282
- package/out/src/synthesizers/no-street.js.map +0 -1
- package/out/src/synthesizers/po-box.d.ts +0 -104
- package/out/src/synthesizers/po-box.d.ts.map +0 -1
- package/out/src/synthesizers/po-box.js +0 -266
- package/out/src/synthesizers/po-box.js.map +0 -1
- package/out/src/synthesizers/street.d.ts +0 -54
- package/out/src/synthesizers/street.d.ts.map +0 -1
- package/out/src/synthesizers/street.js +0 -221
- package/out/src/synthesizers/street.js.map +0 -1
- package/out/src/synthesizers/utils.d.ts +0 -203
- package/out/src/synthesizers/utils.d.ts.map +0 -1
- package/out/src/synthesizers/utils.js +0 -708
- package/out/src/synthesizers/utils.js.map +0 -1
- package/out/src/tools/align-shard.d.ts +0 -8
- package/out/src/tools/align-shard.d.ts.map +0 -1
- package/out/src/tools/align-shard.js +0 -56
- package/out/src/tools/align-shard.js.map +0 -1
- package/out/src/tools/audit.d.ts +0 -28
- package/out/src/tools/audit.d.ts.map +0 -1
- package/out/src/tools/audit.js +0 -285
- package/out/src/tools/audit.js.map +0 -1
- package/out/src/tools/corpus-stats.d.ts +0 -44
- package/out/src/tools/corpus-stats.d.ts.map +0 -1
- package/out/src/tools/corpus-stats.js +0 -138
- package/out/src/tools/corpus-stats.js.map +0 -1
- package/out/src/tools/fetch/ban.d.ts +0 -31
- package/out/src/tools/fetch/ban.d.ts.map +0 -1
- package/out/src/tools/fetch/ban.js +0 -239
- package/out/src/tools/fetch/ban.js.map +0 -1
- package/out/src/tools/fetch/download.d.ts +0 -78
- package/out/src/tools/fetch/download.d.ts.map +0 -1
- package/out/src/tools/fetch/download.js +0 -116
- package/out/src/tools/fetch/download.js.map +0 -1
- package/out/src/tools/fetch/geonames-dump.d.ts +0 -87
- package/out/src/tools/fetch/geonames-dump.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-dump.js +0 -178
- package/out/src/tools/fetch/geonames-dump.js.map +0 -1
- package/out/src/tools/fetch/geonames-postal.d.ts +0 -76
- package/out/src/tools/fetch/geonames-postal.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-postal.js +0 -125
- package/out/src/tools/fetch/geonames-postal.js.map +0 -1
- package/out/src/tools/fetch/hrsa.d.ts +0 -18
- package/out/src/tools/fetch/hrsa.d.ts.map +0 -1
- package/out/src/tools/fetch/hrsa.js +0 -46
- package/out/src/tools/fetch/hrsa.js.map +0 -1
- package/out/src/tools/fetch/imls-pls.d.ts +0 -25
- package/out/src/tools/fetch/imls-pls.d.ts.map +0 -1
- package/out/src/tools/fetch/imls-pls.js +0 -108
- package/out/src/tools/fetch/imls-pls.js.map +0 -1
- package/out/src/tools/fetch/index.d.ts +0 -144
- package/out/src/tools/fetch/index.d.ts.map +0 -1
- package/out/src/tools/fetch/index.js +0 -143
- package/out/src/tools/fetch/index.js.map +0 -1
- package/out/src/tools/fetch/nad.d.ts +0 -70
- package/out/src/tools/fetch/nad.d.ts.map +0 -1
- package/out/src/tools/fetch/nad.js +0 -234
- package/out/src/tools/fetch/nad.js.map +0 -1
- package/out/src/tools/fetch/nppes.d.ts +0 -26
- package/out/src/tools/fetch/nppes.d.ts.map +0 -1
- package/out/src/tools/fetch/nppes.js +0 -126
- package/out/src/tools/fetch/nppes.js.map +0 -1
- package/out/src/tools/fetch/openaddresses.d.ts +0 -61
- package/out/src/tools/fetch/openaddresses.d.ts.map +0 -1
- package/out/src/tools/fetch/openaddresses.js +0 -317
- package/out/src/tools/fetch/openaddresses.js.map +0 -1
- package/out/src/tools/fetch/ourairports.d.ts +0 -45
- package/out/src/tools/fetch/ourairports.d.ts.map +0 -1
- package/out/src/tools/fetch/ourairports.js +0 -128
- package/out/src/tools/fetch/ourairports.js.map +0 -1
- package/out/src/tools/fetch/ppd.d.ts.map +0 -1
- package/out/src/tools/fetch/ppd.js +0 -100
- package/out/src/tools/fetch/ppd.js.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.d.ts +0 -25
- package/out/src/tools/fetch/state-hi-schools.d.ts.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.js +0 -162
- package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
- package/out/src/tools/fetch/state-sources.d.ts +0 -26
- package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
- package/out/src/tools/fetch/state-sources.js +0 -111
- package/out/src/tools/fetch/state-sources.js.map +0 -1
- package/out/src/tools/fetch/tiger-full.d.ts +0 -42
- package/out/src/tools/fetch/tiger-full.d.ts.map +0 -1
- package/out/src/tools/fetch/tiger-full.js +0 -248
- package/out/src/tools/fetch/tiger-full.js.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.d.ts +0 -171
- package/out/src/tools/fetch/wikidata-subvenue.d.ts.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.js +0 -275
- package/out/src/tools/fetch/wikidata-subvenue.js.map +0 -1
- package/out/src/tools/gb-title-case.d.ts.map +0 -1
- package/out/src/tools/gb-title-case.js.map +0 -1
- package/out/src/tools/golden-expand.d.ts +0 -90
- package/out/src/tools/golden-expand.d.ts.map +0 -1
- package/out/src/tools/golden-expand.js +0 -413
- package/out/src/tools/golden-expand.js.map +0 -1
- package/out/src/tools/golden-promote.d.ts.map +0 -1
- package/out/src/tools/golden-promote.js +0 -244
- package/out/src/tools/golden-promote.js.map +0 -1
- package/out/src/tools/golden-relabel-street.d.ts +0 -196
- package/out/src/tools/golden-relabel-street.d.ts.map +0 -1
- package/out/src/tools/golden-relabel-street.js +0 -440
- package/out/src/tools/golden-relabel-street.js.map +0 -1
- package/out/src/tools/index.d.ts +0 -28
- package/out/src/tools/index.d.ts.map +0 -1
- package/out/src/tools/index.js +0 -28
- package/out/src/tools/index.js.map +0 -1
- package/out/src/tools/ingest-csv.d.ts.map +0 -1
- package/out/src/tools/ingest-csv.js +0 -296
- package/out/src/tools/ingest-csv.js.map +0 -1
- package/out/src/tools/jsonl-to-parquet.d.ts +0 -61
- package/out/src/tools/jsonl-to-parquet.d.ts.map +0 -1
- package/out/src/tools/jsonl-to-parquet.js +0 -164
- package/out/src/tools/jsonl-to-parquet.js.map +0 -1
- package/out/src/tools/lint-shard-vocab.d.ts +0 -90
- package/out/src/tools/lint-shard-vocab.d.ts.map +0 -1
- package/out/src/tools/lint-shard-vocab.js +0 -281
- package/out/src/tools/lint-shard-vocab.js.map +0 -1
- package/out/src/tools/lint-shard.d.ts +0 -93
- package/out/src/tools/lint-shard.d.ts.map +0 -1
- package/out/src/tools/lint-shard.js +0 -354
- package/out/src/tools/lint-shard.js.map +0 -1
- package/out/src/tools/overlay-manifest.d.ts +0 -39
- package/out/src/tools/overlay-manifest.d.ts.map +0 -1
- package/out/src/tools/overlay-manifest.js +0 -98
- package/out/src/tools/overlay-manifest.js.map +0 -1
- package/out/src/tools/overture-subvenue.d.ts +0 -112
- package/out/src/tools/overture-subvenue.d.ts.map +0 -1
- package/out/src/tools/overture-subvenue.js +0 -144
- package/out/src/tools/overture-subvenue.js.map +0 -1
- package/out/src/tools/postcode-triples.d.ts +0 -175
- package/out/src/tools/postcode-triples.d.ts.map +0 -1
- package/out/src/tools/postcode-triples.js +0 -304
- package/out/src/tools/postcode-triples.js.map +0 -1
- package/out/src/tools/shard-kryptonite.d.ts +0 -32
- package/out/src/tools/shard-kryptonite.d.ts.map +0 -1
- package/out/src/tools/shard-kryptonite.js +0 -100
- package/out/src/tools/shard-kryptonite.js.map +0 -1
- package/out/src/tools/shard-translit.d.ts +0 -51
- package/out/src/tools/shard-translit.d.ts.map +0 -1
- package/out/src/tools/shard-translit.js +0 -175
- package/out/src/tools/shard-translit.js.map +0 -1
- package/out/src/tools/sub-venue/harvest.d.ts +0 -100
- package/out/src/tools/sub-venue/harvest.d.ts.map +0 -1
- package/out/src/tools/sub-venue/harvest.js +0 -168
- package/out/src/tools/sub-venue/harvest.js.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.d.ts +0 -50
- package/out/src/tools/sub-venue/head-nouns.d.ts.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.js +0 -210
- package/out/src/tools/sub-venue/head-nouns.js.map +0 -1
- package/out/src/tools/sub-venue/surfaces.d.ts +0 -45
- package/out/src/tools/sub-venue/surfaces.d.ts.map +0 -1
- package/out/src/tools/sub-venue/surfaces.js +0 -77
- package/out/src/tools/sub-venue/surfaces.js.map +0 -1
- package/out/src/tools/sub-venue/table.d.ts +0 -229
- package/out/src/tools/sub-venue/table.d.ts.map +0 -1
- package/out/src/tools/sub-venue/table.js +0 -108
- package/out/src/tools/sub-venue/table.js.map +0 -1
- package/out/src/tools/sub-venue/wikidata.d.ts +0 -26
- package/out/src/tools/sub-venue/wikidata.d.ts.map +0 -1
- package/out/src/tools/sub-venue/wikidata.js +0 -62
- package/out/src/tools/sub-venue/wikidata.js.map +0 -1
- package/out/src/tools/sub-venue-lexicon.d.ts +0 -156
- package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
- package/out/src/tools/sub-venue-lexicon.js +0 -282
- package/out/src/tools/sub-venue-lexicon.js.map +0 -1
- package/out/src/tools/sub-venue-promotions.d.ts +0 -94
- package/out/src/tools/sub-venue-promotions.d.ts.map +0 -1
- package/out/src/tools/sub-venue-promotions.js +0 -266
- package/out/src/tools/sub-venue-promotions.js.map +0 -1
- package/out/src/types.d.ts +0 -221
- package/out/src/types.d.ts.map +0 -1
- package/out/src/types.js.map +0 -1
- package/out/src/utils/align.d.ts +0 -93
- package/out/src/utils/align.d.ts.map +0 -1
- package/out/src/utils/align.js +0 -234
- package/out/src/utils/align.js.map +0 -1
- package/out/src/utils/golden.d.ts +0 -69
- package/out/src/utils/golden.d.ts.map +0 -1
- package/out/src/utils/golden.js +0 -127
- package/out/src/utils/golden.js.map +0 -1
- package/out/src/utils/index.d.ts +0 -14
- package/out/src/utils/index.d.ts.map +0 -1
- package/out/src/utils/index.js +0 -14
- package/out/src/utils/index.js.map +0 -1
- package/out/src/utils/license.d.ts.map +0 -1
- package/out/src/utils/license.js.map +0 -1
- package/out/src/utils/parquet.d.ts +0 -162
- package/out/src/utils/parquet.d.ts.map +0 -1
- package/out/src/utils/parquet.js +0 -262
- package/out/src/utils/parquet.js.map +0 -1
- package/out/src/utils/split.d.ts +0 -127
- package/out/src/utils/split.d.ts.map +0 -1
- package/out/src/utils/split.js +0 -204
- package/out/src/utils/split.js.map +0 -1
- package/out/src/utils/tokenize.d.ts +0 -56
- package/out/src/utils/tokenize.d.ts.map +0 -1
- package/out/src/utils/tokenize.js +0 -48
- package/out/src/utils/tokenize.js.map +0 -1
- package/out/src/utils/wof-json.d.ts +0 -109
- package/out/src/utils/wof-json.d.ts.map +0 -1
- package/out/src/utils/wof-json.js +0 -173
- package/out/src/utils/wof-json.js.map +0 -1
- package/src/adapters/ban/adapter.ts +0 -191
- package/src/adapters/ban/street-decompose.ts +0 -96
- package/src/adapters/fcc-bdc/adapter.ts +0 -174
- package/src/adapters/geonames/adapter.ts +0 -200
- package/src/adapters/geonames-postal/adapter.ts +0 -119
- package/src/adapters/gnaf/adapter.ts +0 -149
- package/src/adapters/gnaf/assemble.ts +0 -226
- package/src/adapters/index.ts +0 -149
- package/src/adapters/openaddresses/adapter.ts +0 -251
- package/src/adapters/overture/adapter.ts +0 -162
- package/src/adapters/state-hi-schools/adapter.ts +0 -164
- package/src/adapters/synth-po-box/adapter.ts +0 -204
- package/src/adapters/tiger/adapter.ts +0 -253
- package/src/adapters/tiger/street-decompose.ts +0 -111
- package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -183
- package/src/adapters/usgov-imls-pls/adapter.ts +0 -143
- package/src/adapters/usgov-irs-bmf/adapter.ts +0 -163
- package/src/adapters/usgov-nad/adapter.ts +0 -348
- package/src/adapters/usgov-nppes/adapter.ts +0 -159
- package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -204
- package/src/adapters/utils/index.ts +0 -233
- package/src/adapters/wof-admin-jp/adapter.ts +0 -216
- package/src/adapters/wof-admin-json/adapter.ts +0 -256
- package/src/adapters/wof-json-rows.ts +0 -79
- package/src/adapters/wof-postalcode-json/adapter.ts +0 -183
- package/src/build.ts +0 -386
- package/src/index.ts +0 -14
- package/src/name-prone-us-suffixes.ts +0 -12
- package/src/parquet-wrapper/index.ts +0 -9
- package/src/parquet-wrapper/reader.ts +0 -97
- package/src/parquet-wrapper/schema.ts +0 -88
- package/src/parquet-wrapper/writer.ts +0 -110
- package/src/runner.ts +0 -317
- package/src/shard-recipes/anchor-absorption.ts +0 -103
- package/src/shard-recipes/bare-country.ts +0 -95
- package/src/shard-recipes/boundary-stress.ts +0 -101
- package/src/shard-recipes/country-balanced.ts +0 -524
- package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -111
- package/src/shard-recipes/fr-admin-split.ts +0 -239
- package/src/shard-recipes/fr-bare-street.ts +0 -170
- package/src/shard-recipes/fr-fragment.ts +0 -332
- package/src/shard-recipes/fr-lieudit.ts +0 -302
- package/src/shard-recipes/fr-order.ts +0 -258
- package/src/shard-recipes/german.ts +0 -170
- package/src/shard-recipes/house-venue.ts +0 -88
- package/src/shard-recipes/index.ts +0 -95
- package/src/shard-recipes/intersection.ts +0 -630
- package/src/shard-recipes/locale.ts +0 -599
- package/src/shard-recipes/nl-postcode.ts +0 -115
- package/src/shard-recipes/no-fragment.ts +0 -219
- package/src/shard-recipes/no-street-led.ts +0 -143
- package/src/shard-recipes/no-street.ts +0 -86
- package/src/shard-recipes/po-box-cedex.ts +0 -920
- package/src/shard-recipes/po-box.ts +0 -119
- package/src/shard-recipes/reviewed-postcode-tail.ts +0 -189
- package/src/shard-recipes/scaffold.ts +0 -360
- package/src/shard-recipes/si-bare-village.ts +0 -97
- package/src/shard-recipes/street-affix.ts +0 -826
- package/src/shard-recipes/street-bare.ts +0 -101
- package/src/shard-recipes/street.ts +0 -82
- package/src/shard-recipes/sub-venue-sources.ts +0 -885
- package/src/shard-recipes/sub-venue.ts +0 -984
- package/src/shard-recipes/trailing-region.ts +0 -183
- package/src/shard-recipes/unit.ts +0 -321
- package/src/synthesizers/anchor-absorption.ts +0 -290
- package/src/synthesizers/boundary-stress.ts +0 -531
- package/src/synthesizers/german.ts +0 -251
- package/src/synthesizers/house-venue.ts +0 -330
- package/src/synthesizers/intersection.ts +0 -232
- package/src/synthesizers/no-street.ts +0 -349
- package/src/synthesizers/po-box.ts +0 -339
- package/src/synthesizers/street.ts +0 -274
- package/src/synthesizers/utils.ts +0 -903
- package/src/tools/align-shard.ts +0 -70
- package/src/tools/audit.ts +0 -399
- package/src/tools/corpus-stats.ts +0 -184
- package/src/tools/fetch/ban.ts +0 -290
- package/src/tools/fetch/download.ts +0 -176
- package/src/tools/fetch/geonames-dump.ts +0 -267
- package/src/tools/fetch/geonames-postal.ts +0 -180
- package/src/tools/fetch/hrsa.ts +0 -68
- package/src/tools/fetch/imls-pls.ts +0 -158
- package/src/tools/fetch/index.ts +0 -147
- package/src/tools/fetch/nad.ts +0 -342
- package/src/tools/fetch/nppes.ts +0 -174
- package/src/tools/fetch/openaddresses.ts +0 -404
- package/src/tools/fetch/ourairports.ts +0 -171
- package/src/tools/fetch/ppd.ts +0 -137
- package/src/tools/fetch/state-hi-schools.ts +0 -208
- package/src/tools/fetch/state-sources.ts +0 -155
- package/src/tools/fetch/tiger-full.ts +0 -354
- package/src/tools/fetch/wikidata-subvenue.ts +0 -386
- package/src/tools/golden-expand.ts +0 -584
- package/src/tools/golden-promote.ts +0 -353
- package/src/tools/golden-relabel-street.ts +0 -685
- package/src/tools/index.ts +0 -28
- package/src/tools/ingest-csv.ts +0 -422
- package/src/tools/jsonl-to-parquet.ts +0 -221
- package/src/tools/lint-shard-vocab.ts +0 -409
- package/src/tools/lint-shard.ts +0 -543
- package/src/tools/overlay-manifest.ts +0 -157
- package/src/tools/overture-subvenue.ts +0 -215
- package/src/tools/postcode-triples.ts +0 -375
- package/src/tools/shard-kryptonite.ts +0 -139
- package/src/tools/shard-translit.ts +0 -245
- package/src/tools/sub-venue/harvest.ts +0 -235
- package/src/tools/sub-venue/head-nouns.ts +0 -242
- package/src/tools/sub-venue/surfaces.ts +0 -95
- package/src/tools/sub-venue/table.ts +0 -281
- package/src/tools/sub-venue/wikidata.ts +0 -85
- package/src/tools/sub-venue-lexicon.ts +0 -431
- package/src/tools/sub-venue-promotions.ts +0 -330
- package/src/types.ts +0 -247
- package/src/utils/align.ts +0 -331
- package/src/utils/golden.ts +0 -176
- package/src/utils/index.ts +0 -14
- package/src/utils/parquet.ts +0 -391
- package/src/utils/split.ts +0 -279
- package/src/utils/tokenize.ts +0 -78
- package/src/utils/wof-json.ts +0 -244
- /package/{src → lib}/adapters/state-ia-contractors/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-ny-notaries/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-tx-notaries/adapter.ts +0 -0
- /package/{src → lib}/codex/us-fips-state.ts +0 -0
- /package/{src → lib}/tools/gb-title-case.ts +0 -0
- /package/{src → lib}/utils/license.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/fcc-bdc/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/geonames/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/openaddresses/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/synth-po-box/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/tiger/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-nppes/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-samhsa-treatment-locator/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/wof-admin-jp/adapter.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.js +0 -0
- /package/out/{src/tools → tools}/fetch/ppd.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.js +0 -0
- /package/out/{src/tools → tools}/golden-promote.d.ts +0 -0
- /package/out/{src/tools → tools}/ingest-csv.d.ts +0 -0
- /package/out/{src/types.js → types.js} +0 -0
- /package/out/{src/utils → utils}/license.d.ts +0 -0
- /package/out/{src/utils → utils}/license.js +0 -0
|
@@ -1,126 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Re-fetch the NPPES (National Plan and Provider Enumeration System) full monthly data
|
|
7
|
-
* dissemination file. ~7M provider rows with venue+address data. Source for the `usgov-nppes`
|
|
8
|
-
* adapter. US Public Domain.
|
|
9
|
-
*
|
|
10
|
-
* The file is published monthly by CMS. This module discovers the current filename by scraping the
|
|
11
|
-
* NPI_Files.html index, then downloads the ZIP and extracts only the main registry CSV
|
|
12
|
-
* (npidata_pfile_*.csv). The smaller endpoint/othername/pl files stay zipped — we don't need them.
|
|
13
|
-
*
|
|
14
|
-
* Uses Node's built-in fetch (gzip/brotli) to parse the HTML index and download the ZIP, and
|
|
15
|
-
* streaming sha256 instead of sha256sum. The ZIP is unpacked with the `unzip` binary via
|
|
16
|
-
* `node:child_process` (no clean Node equivalent for member listing + selective extraction). NOTE:
|
|
17
|
-
* the old bash fetcher used `curl --continue-at -` to resume a partial download; native fetch has
|
|
18
|
-
* no resume, so a partial run re-downloads from the start.
|
|
19
|
-
*
|
|
20
|
-
* Invoke via `mailwoman corpus fetch nppes --out-root <path>`. Idempotent: if dest CSV exists and
|
|
21
|
-
* sha256 matches MANIFEST, skips download.
|
|
22
|
-
*/
|
|
23
|
-
/* oxlint-disable sister-software/prefer-region-over-marks -- these markers label steps inside one
|
|
24
|
-
procedure, not sections of declarations. A region there folds nothing a reader wants folded. */
|
|
25
|
-
import { existsSync, mkdirSync, statSync } from "node:fs";
|
|
26
|
-
import { rm } from "node:fs/promises";
|
|
27
|
-
import { basename, join } from "node:path";
|
|
28
|
-
import { APIClient, pluckResponseData } from "@mailwoman/core/api";
|
|
29
|
-
import { extractZipEntry, listZipEntries } from "@mailwoman/core/fs/zip";
|
|
30
|
-
import { sha256File } from "@mailwoman/core/utils";
|
|
31
|
-
import { downloadToFile, readManifest, writeManifest } from "./download.js";
|
|
32
|
-
const INDEX_URL = "https://download.cms.gov/nppes/NPI_Files.html";
|
|
33
|
-
const BASE_URL = "https://download.cms.gov/nppes";
|
|
34
|
-
const SLUG = "usgov-nppes";
|
|
35
|
-
/**
|
|
36
|
-
* Scrape the NPI_Files.html index for the latest full monthly ZIP. Full-replacement files match
|
|
37
|
-
* `NPPES_Data_Dissemination_<Month>_<Year>*.zip`; weekly files carry a `MMDDYY_MMDDYY` date range, which we exclude.
|
|
38
|
-
*/
|
|
39
|
-
async function discoverLatestZip() {
|
|
40
|
-
// `responseType: "text"` — the index is HTML, scraped by regex below.
|
|
41
|
-
const html = await new APIClient({
|
|
42
|
-
displayName: "nppes-index",
|
|
43
|
-
retry: true,
|
|
44
|
-
axios: { headers: { "Accept-Encoding": "gzip, br" } },
|
|
45
|
-
})
|
|
46
|
-
.fetch({ url: INDEX_URL, responseType: "text", timeout: 60_000 })
|
|
47
|
-
.then(pluckResponseData);
|
|
48
|
-
for (const match of html.matchAll(/NPPES_Data_Dissemination_[A-Za-z]+_\d{4}[^"]*\.zip/g)) {
|
|
49
|
-
const name = match[0];
|
|
50
|
-
if (name && !/\d{6}_\d{6}/.test(name))
|
|
51
|
-
return name;
|
|
52
|
-
}
|
|
53
|
-
return undefined;
|
|
54
|
-
}
|
|
55
|
-
/**
|
|
56
|
-
* The main registry CSV (npidata_pfile_*.csv), which the archive also carries alongside a header file and a per-month
|
|
57
|
-
* change file.
|
|
58
|
-
*/
|
|
59
|
-
async function findNpidataCSV(zipPath) {
|
|
60
|
-
const entries = await listZipEntries(zipPath);
|
|
61
|
-
return entries.find((entry) => /npidata_pfile\S+\.csv/i.test(entry.name))?.name;
|
|
62
|
-
}
|
|
63
|
-
export async function fetchNPPES(options, report) {
|
|
64
|
-
const destDir = join(options.outRoot, SLUG);
|
|
65
|
-
mkdirSync(destDir, { recursive: true });
|
|
66
|
-
const manifestPath = join(destDir, "MANIFEST.json");
|
|
67
|
-
report?.(`=== ${SLUG}`);
|
|
68
|
-
report?.(` Discovering latest full-replacement ZIP from ${INDEX_URL} ...`);
|
|
69
|
-
const zipFilename = await discoverLatestZip();
|
|
70
|
-
if (!zipFilename) {
|
|
71
|
-
report?.(` ✗ Could not discover ZIP filename from ${INDEX_URL}`);
|
|
72
|
-
return { fetched: 0, skipped: 0, failed: 1, failedCodes: [SLUG] };
|
|
73
|
-
}
|
|
74
|
-
const zipURL = `${BASE_URL}/${zipFilename}`;
|
|
75
|
-
const zipDest = join(destDir, zipFilename);
|
|
76
|
-
report?.(` Latest full file: ${zipFilename}`);
|
|
77
|
-
// Idempotency check: if the main CSV already exists and sha matches,
|
|
78
|
-
// skip re-download.
|
|
79
|
-
const recorded = await readManifest(manifestPath);
|
|
80
|
-
if (recorded?.sha256 && recorded.filename) {
|
|
81
|
-
const recordedPath = join(destDir, recorded.filename);
|
|
82
|
-
if (existsSync(recordedPath) && (await sha256File(recordedPath)) === recorded.sha256) {
|
|
83
|
-
report?.(" ✓ Already current (sha256 matches MANIFEST) — skipping download.");
|
|
84
|
-
return { fetched: 0, skipped: 1, failed: 0, failedCodes: [] };
|
|
85
|
-
}
|
|
86
|
-
}
|
|
87
|
-
// MARK: Download ZIP (large; 60-minute timeout)
|
|
88
|
-
report?.(` Downloading ${zipURL} ...`);
|
|
89
|
-
const { bytes: zipSize } = await downloadToFile({
|
|
90
|
-
url: zipURL,
|
|
91
|
-
dest: zipDest,
|
|
92
|
-
timeoutMs: 3_600_000,
|
|
93
|
-
headers: { "Accept-Encoding": "gzip, br" },
|
|
94
|
-
report,
|
|
95
|
-
});
|
|
96
|
-
report?.(` Downloaded: ${(zipSize / 1024 / 1024).toFixed(1)} MB`);
|
|
97
|
-
// MARK: Extract only the main registry CSV (npidata_pfile_*.csv)
|
|
98
|
-
report?.(" Extracting npidata_pfile CSV from ZIP ...");
|
|
99
|
-
const csvName = await findNpidataCSV(zipDest);
|
|
100
|
-
if (!csvName) {
|
|
101
|
-
report?.(" ✗ Could not find npidata_pfile CSV inside ZIP");
|
|
102
|
-
return { fetched: 0, skipped: 0, failed: 1, failedCodes: [SLUG] };
|
|
103
|
-
}
|
|
104
|
-
report?.(` Extracting: ${csvName}`);
|
|
105
|
-
const csvDest = join(destDir, basename(csvName));
|
|
106
|
-
await extractZipEntry(zipDest, csvName, csvDest);
|
|
107
|
-
const csvSize = statSync(csvDest).size;
|
|
108
|
-
const csvSha = await sha256File(csvDest);
|
|
109
|
-
report?.(` CSV size: ${(csvSize / 1024 / 1024).toFixed(1)} MB`);
|
|
110
|
-
// MARK: Remove the ZIP to reclaim ~1 GB
|
|
111
|
-
await rm(zipDest, { force: true });
|
|
112
|
-
report?.(" Removed ZIP (CSV kept)");
|
|
113
|
-
// MARK: Write MANIFEST (records the extracted CSV, not the ZIP)
|
|
114
|
-
const manifest = {
|
|
115
|
-
source_url: zipURL,
|
|
116
|
-
downloaded_at: new Date().toISOString(),
|
|
117
|
-
filename: csvName,
|
|
118
|
-
sha256: csvSha,
|
|
119
|
-
bytes: csvSize,
|
|
120
|
-
};
|
|
121
|
-
await writeManifest(manifestPath, manifest);
|
|
122
|
-
report?.(` ✓ ${(csvSize / 1024 / 1024).toFixed(1)} MB sha256=${csvSha}`);
|
|
123
|
-
report?.(` MANIFEST written to ${manifestPath}`);
|
|
124
|
-
return { fetched: 1, skipped: 0, failed: 0, failedCodes: [] };
|
|
125
|
-
}
|
|
126
|
-
//# sourceMappingURL=nppes.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"nppes.js","sourceRoot":"","sources":["../../../../src/tools/fetch/nppes.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;GAqBG;AAEH;kGACkG;AAElG,OAAO,EAAE,UAAU,EAAE,SAAS,EAAE,QAAQ,EAAE,MAAM,SAAS,CAAA;AACzD,OAAO,EAAE,EAAE,EAAE,MAAM,kBAAkB,CAAA;AACrC,OAAO,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAE1C,OAAO,EAAE,SAAS,EAAE,iBAAiB,EAAE,MAAM,qBAAqB,CAAA;AAClE,OAAO,EAAE,eAAe,EAAE,cAAc,EAAE,MAAM,wBAAwB,CAAA;AACxE,OAAO,EAAE,UAAU,EAAE,MAAM,uBAAuB,CAAA;AAGlD,OAAO,EAAE,cAAc,EAAE,YAAY,EAAE,aAAa,EAAE,MAAM,eAAe,CAAA;AAE3E,MAAM,SAAS,GAAG,+CAA+C,CAAA;AACjE,MAAM,QAAQ,GAAG,gCAAgC,CAAA;AACjD,MAAM,IAAI,GAAG,aAAa,CAAA;AAY1B;;;GAGG;AACH,KAAK,UAAU,iBAAiB;IAC/B,sEAAsE;IACtE,MAAM,IAAI,GAAG,MAAM,IAAI,SAAS,CAAC;QAChC,WAAW,EAAE,aAAa;QAC1B,KAAK,EAAE,IAAI;QACX,KAAK,EAAE,EAAE,OAAO,EAAE,EAAE,iBAAiB,EAAE,UAAU,EAAE,EAAE;KACrD,CAAC;SACA,KAAK,CAAS,EAAE,GAAG,EAAE,SAAS,EAAE,YAAY,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC;SACxE,IAAI,CAAC,iBAAiB,CAAC,CAAA;IAEzB,KAAK,MAAM,KAAK,IAAI,IAAI,CAAC,QAAQ,CAAC,qDAAqD,CAAC,EAAE,CAAC;QAC1F,MAAM,IAAI,GAAG,KAAK,CAAC,CAAC,CAAC,CAAA;QAErB,IAAI,IAAI,IAAI,CAAC,aAAa,CAAC,IAAI,CAAC,IAAI,CAAC;YAAE,OAAO,IAAI,CAAA;IACnD,CAAC;IAED,OAAO,SAAS,CAAA;AACjB,CAAC;AAED;;;GAGG;AACH,KAAK,UAAU,cAAc,CAAC,OAAe;IAC5C,MAAM,OAAO,GAAG,MAAM,cAAc,CAAC,OAAO,CAAC,CAAA;IAE7C,OAAO,OAAO,CAAC,IAAI,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,wBAAwB,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,EAAE,IAAI,CAAA;AAChF,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,UAAU,CAAC,OAA0B,EAAE,MAA+B;IAC3F,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,IAAI,CAAC,CAAA;IAC3C,SAAS,CAAC,OAAO,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;IACvC,MAAM,YAAY,GAAG,IAAI,CAAC,OAAO,EAAE,eAAe,CAAC,CAAA;IAEnD,MAAM,EAAE,CAAC,OAAO,IAAI,EAAE,CAAC,CAAA;IACvB,MAAM,EAAE,CAAC,kDAAkD,SAAS,MAAM,CAAC,CAAA;IAE3E,MAAM,WAAW,GAAG,MAAM,iBAAiB,EAAE,CAAA;IAE7C,IAAI,CAAC,WAAW,EAAE,CAAC;QAClB,MAAM,EAAE,CAAC,4CAA4C,SAAS,EAAE,CAAC,CAAA;QAEjE,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,WAAW,EAAE,CAAC,IAAI,CAAC,EAAE,CAAA;IAClE,CAAC;IAED,MAAM,MAAM,GAAG,GAAG,QAAQ,IAAI,WAAW,EAAE,CAAA;IAC3C,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,EAAE,WAAW,CAAC,CAAA;IAC1C,MAAM,EAAE,CAAC,uBAAuB,WAAW,EAAE,CAAC,CAAA;IAE9C,qEAAqE;IACrE,oBAAoB;IACpB,MAAM,QAAQ,GAAG,MAAM,YAAY,CAA0B,YAAY,CAAC,CAAA;IAE1E,IAAI,QAAQ,EAAE,MAAM,IAAI,QAAQ,CAAC,QAAQ,EAAE,CAAC;QAC3C,MAAM,YAAY,GAAG,IAAI,CAAC,OAAO,EAAE,QAAQ,CAAC,QAAQ,CAAC,CAAA;QAErD,IAAI,UAAU,CAAC,YAAY,CAAC,IAAI,CAAC,MAAM,UAAU,CAAC,YAAY,CAAC,CAAC,KAAK,QAAQ,CAAC,MAAM,EAAE,CAAC;YACtF,MAAM,EAAE,CAAC,oEAAoE,CAAC,CAAA;YAE9E,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,WAAW,EAAE,EAAE,EAAE,CAAA;QAC9D,CAAC;IACF,CAAC;IAED,gDAAgD;IAEhD,MAAM,EAAE,CAAC,iBAAiB,MAAM,MAAM,CAAC,CAAA;IAEvC,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,GAAG,MAAM,cAAc,CAAC;QAC/C,GAAG,EAAE,MAAM;QACX,IAAI,EAAE,OAAO;QACb,SAAS,EAAE,SAAS;QACpB,OAAO,EAAE,EAAE,iBAAiB,EAAE,UAAU,EAAE;QAC1C,MAAM;KACN,CAAC,CAAA;IAEF,MAAM,EAAE,CAAC,iBAAiB,CAAC,OAAO,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,KAAK,CAAC,CAAA;IAElE,iEAAiE;IAEjE,MAAM,EAAE,CAAC,6CAA6C,CAAC,CAAA;IACvD,MAAM,OAAO,GAAG,MAAM,cAAc,CAAC,OAAO,CAAC,CAAA;IAE7C,IAAI,CAAC,OAAO,EAAE,CAAC;QACd,MAAM,EAAE,CAAC,iDAAiD,CAAC,CAAA;QAE3D,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,WAAW,EAAE,CAAC,IAAI,CAAC,EAAE,CAAA;IAClE,CAAC;IAED,MAAM,EAAE,CAAC,iBAAiB,OAAO,EAAE,CAAC,CAAA;IAEpC,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,EAAE,QAAQ,CAAC,OAAO,CAAC,CAAC,CAAA;IAEhD,MAAM,eAAe,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC,CAAA;IAChD,MAAM,OAAO,GAAG,QAAQ,CAAC,OAAO,CAAC,CAAC,IAAI,CAAA;IACtC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,OAAO,CAAC,CAAA;IACxC,MAAM,EAAE,CAAC,eAAe,CAAC,OAAO,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,KAAK,CAAC,CAAA;IAEhE,wCAAwC;IAExC,MAAM,EAAE,CAAC,OAAO,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC,CAAA;IAClC,MAAM,EAAE,CAAC,0BAA0B,CAAC,CAAA;IAEpC,gEAAgE;IAEhE,MAAM,QAAQ,GAAmB;QAChC,UAAU,EAAE,MAAM;QAClB,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;QACvC,QAAQ,EAAE,OAAO;QACjB,MAAM,EAAE,MAAM;QACd,KAAK,EAAE,OAAO;KACd,CAAA;IAED,MAAM,aAAa,CAAC,YAAY,EAAE,QAAQ,CAAC,CAAA;IAE3C,MAAM,EAAE,CAAC,OAAO,CAAC,OAAO,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe,MAAM,EAAE,CAAC,CAAA;IAC1E,MAAM,EAAE,CAAC,yBAAyB,YAAY,EAAE,CAAC,CAAA;IAEjD,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,WAAW,EAAE,EAAE,EAAE,CAAA;AAC9D,CAAC"}
|
|
@@ -1,61 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Fetch an OpenAddresses country collection from batch.openaddresses.io.
|
|
7
|
-
*
|
|
8
|
-
* Source: https://batch.openaddresses.io
|
|
9
|
-
* License: MIXED — OpenAddresses aggregates hundreds of upstream sources with per-source licenses
|
|
10
|
-
* (CC-BY, CC0, PDDL, ODbL, CC-BY-SA, and proprietary attribution-only). The per-row LICENSE filter
|
|
11
|
-
* in the openaddresses adapter is essential for proprietary-weights training: Tier-C rows (ODbL,
|
|
12
|
-
* CC-BY-SA, CC-SA) are dropped at ingest by default. This module downloads the raw collection; the
|
|
13
|
-
* adapter does the license gating.
|
|
14
|
-
*
|
|
15
|
-
* Native `fetch` streams the download to disk (no curl + Python subprocess tax);
|
|
16
|
-
* `node:child_process` keeps the genuine shell ops it still needs (`file` magic detection +
|
|
17
|
-
* `gunzip` decompression, both nice/ionice-deprioritized).
|
|
18
|
-
*
|
|
19
|
-
* ## Authentication note (2026-05-18)
|
|
20
|
-
*
|
|
21
|
-
* The batch.openaddresses.io download endpoint now requires a registered account. Downloads are
|
|
22
|
-
* still free at the "basic" tier (GeoJSON+LD output).
|
|
23
|
-
*
|
|
24
|
-
* 1. Register at https://batch.openaddresses.io/register
|
|
25
|
-
* 2. Log in and go to Profile → "Create Token"
|
|
26
|
-
* 3. Export the token: `export OA_BATCH_TOKEN=<your-token>`
|
|
27
|
-
* 4. Re-run the command.
|
|
28
|
-
*
|
|
29
|
-
* The collection URL pattern (verified 2026-05-18):
|
|
30
|
-
*
|
|
31
|
-
* - `POST /api/login {username, password}` → `{token}`
|
|
32
|
-
* - `GET /api/job/{job_id}/output/source.geojson.gz?token={token}`
|
|
33
|
-
*
|
|
34
|
-
* Collections are downloaded as a combined GeoJSON.gz via:
|
|
35
|
-
*
|
|
36
|
-
* - `GET /api/collections/{collection_id}/download` (returns a redirect to S3)
|
|
37
|
-
*
|
|
38
|
-
* Collection IDs discovered from `/api/collections`:
|
|
39
|
-
*
|
|
40
|
-
* - `id=6 name="ca" size=2044467556` (~1.9 GiB uncompressed, verified 2026-05-18)
|
|
41
|
-
*
|
|
42
|
-
* ## Usage
|
|
43
|
-
*
|
|
44
|
-
* ```sh
|
|
45
|
-
* # With token (preferred). Default country: ca. Supports any OA country code (us-west, fr, …)
|
|
46
|
-
* OA_BATCH_TOKEN=<token> mailwoman corpus fetch openaddresses --country ca \
|
|
47
|
-
* --out-root $MAILWOMAN_DATA_ROOT/corpus/sources
|
|
48
|
-
*
|
|
49
|
-
* # Without token (will detect + print instructions, then report the failure):
|
|
50
|
-
* mailwoman corpus fetch openaddresses --country ca
|
|
51
|
-
* ```
|
|
52
|
-
*/
|
|
53
|
-
import type { BaseFetchOptions, FetchSummary } from "./download.ts";
|
|
54
|
-
export interface FetchOpenAddressesOptions extends BaseFetchOptions {
|
|
55
|
-
/**
|
|
56
|
-
* OA country collection code. Default `ca`.
|
|
57
|
-
*/
|
|
58
|
-
country?: string;
|
|
59
|
-
}
|
|
60
|
-
export declare function fetchOpenAddresses(options: FetchOpenAddressesOptions, report?: (line: string) => void): Promise<FetchSummary>;
|
|
61
|
-
//# sourceMappingURL=openaddresses.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"openaddresses.d.ts","sourceRoot":"","sources":["../../../../src/tools/fetch/openaddresses.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAmDG;AAkBH,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAAE,MAAM,eAAe,CAAA;AAkCnE,MAAM,WAAW,yBAA0B,SAAQ,gBAAgB;IAClE;;OAEG;IACH,OAAO,CAAC,EAAE,MAAM,CAAA;CAChB;AA6FD,wBAAsB,kBAAkB,CACvC,OAAO,EAAE,yBAAyB,EAClC,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,YAAY,CAAC,CAuMvB"}
|
|
@@ -1,317 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Fetch an OpenAddresses country collection from batch.openaddresses.io.
|
|
7
|
-
*
|
|
8
|
-
* Source: https://batch.openaddresses.io
|
|
9
|
-
* License: MIXED — OpenAddresses aggregates hundreds of upstream sources with per-source licenses
|
|
10
|
-
* (CC-BY, CC0, PDDL, ODbL, CC-BY-SA, and proprietary attribution-only). The per-row LICENSE filter
|
|
11
|
-
* in the openaddresses adapter is essential for proprietary-weights training: Tier-C rows (ODbL,
|
|
12
|
-
* CC-BY-SA, CC-SA) are dropped at ingest by default. This module downloads the raw collection; the
|
|
13
|
-
* adapter does the license gating.
|
|
14
|
-
*
|
|
15
|
-
* Native `fetch` streams the download to disk (no curl + Python subprocess tax);
|
|
16
|
-
* `node:child_process` keeps the genuine shell ops it still needs (`file` magic detection +
|
|
17
|
-
* `gunzip` decompression, both nice/ionice-deprioritized).
|
|
18
|
-
*
|
|
19
|
-
* ## Authentication note (2026-05-18)
|
|
20
|
-
*
|
|
21
|
-
* The batch.openaddresses.io download endpoint now requires a registered account. Downloads are
|
|
22
|
-
* still free at the "basic" tier (GeoJSON+LD output).
|
|
23
|
-
*
|
|
24
|
-
* 1. Register at https://batch.openaddresses.io/register
|
|
25
|
-
* 2. Log in and go to Profile → "Create Token"
|
|
26
|
-
* 3. Export the token: `export OA_BATCH_TOKEN=<your-token>`
|
|
27
|
-
* 4. Re-run the command.
|
|
28
|
-
*
|
|
29
|
-
* The collection URL pattern (verified 2026-05-18):
|
|
30
|
-
*
|
|
31
|
-
* - `POST /api/login {username, password}` → `{token}`
|
|
32
|
-
* - `GET /api/job/{job_id}/output/source.geojson.gz?token={token}`
|
|
33
|
-
*
|
|
34
|
-
* Collections are downloaded as a combined GeoJSON.gz via:
|
|
35
|
-
*
|
|
36
|
-
* - `GET /api/collections/{collection_id}/download` (returns a redirect to S3)
|
|
37
|
-
*
|
|
38
|
-
* Collection IDs discovered from `/api/collections`:
|
|
39
|
-
*
|
|
40
|
-
* - `id=6 name="ca" size=2044467556` (~1.9 GiB uncompressed, verified 2026-05-18)
|
|
41
|
-
*
|
|
42
|
-
* ## Usage
|
|
43
|
-
*
|
|
44
|
-
* ```sh
|
|
45
|
-
* # With token (preferred). Default country: ca. Supports any OA country code (us-west, fr, …)
|
|
46
|
-
* OA_BATCH_TOKEN=<token> mailwoman corpus fetch openaddresses --country ca \
|
|
47
|
-
* --out-root $MAILWOMAN_DATA_ROOT/corpus/sources
|
|
48
|
-
*
|
|
49
|
-
* # Without token (will detect + print instructions, then report the failure):
|
|
50
|
-
* mailwoman corpus fetch openaddresses --country ca
|
|
51
|
-
* ```
|
|
52
|
-
*/
|
|
53
|
-
/* oxlint-disable sister-software/prefer-region-over-marks -- these markers label steps inside one
|
|
54
|
-
procedure, not sections of declarations. A region there folds nothing a reader wants folded. */
|
|
55
|
-
import { execFile, spawn } from "node:child_process";
|
|
56
|
-
import { createReadStream, createWriteStream, existsSync, mkdirSync, renameSync, rmSync, statSync } from "node:fs";
|
|
57
|
-
import { join } from "node:path";
|
|
58
|
-
import { Readable } from "node:stream";
|
|
59
|
-
import { pipeline } from "node:stream/promises";
|
|
60
|
-
import { setTimeout as sleep } from "node:timers/promises";
|
|
61
|
-
import { promisify } from "node:util";
|
|
62
|
-
import { APIClient, isSuccessStatus } from "@mailwoman/core/api";
|
|
63
|
-
import { $private } from "@mailwoman/core/env";
|
|
64
|
-
import { ByteFormatter } from "@mailwoman/core/fs/utils";
|
|
65
|
-
import { sha256File } from "@mailwoman/core/utils";
|
|
66
|
-
import { isTransientStatus, writeManifest } from "./download.js";
|
|
67
|
-
/**
|
|
68
|
-
* Bytes per KiB — the divisor for human-readable sizes, and the floor below which a "download" is an error page rather
|
|
69
|
-
* than data.
|
|
70
|
-
*/
|
|
71
|
-
/**
|
|
72
|
-
* A successful fetch; anything else is an error page or a redirect we did not follow.
|
|
73
|
-
*/
|
|
74
|
-
const HTTP_OK = 200;
|
|
75
|
-
/**
|
|
76
|
-
* Smallest plausible OpenAddresses shard. Below 10 KiB the file is a stub or an error body.
|
|
77
|
-
*/
|
|
78
|
-
const MIN_PLAUSIBLE_SHARD_BYTES = 10_240;
|
|
79
|
-
const execFileAsync = promisify(execFile);
|
|
80
|
-
const OA_BASE = "https://batch.openaddresses.io";
|
|
81
|
-
/**
|
|
82
|
-
* Collection IDs known as of 2026-05-18 (discovered via `GET /api/collections`). OA assigns stable integer IDs to each
|
|
83
|
-
* country collection; re-check `GET /api/collections` if a new country is needed and the ID is unknown.
|
|
84
|
-
*/
|
|
85
|
-
const OA_COLLECTION_IDS = {
|
|
86
|
-
ca: 6,
|
|
87
|
-
"us-west": 4,
|
|
88
|
-
"us-south": 3,
|
|
89
|
-
"us-northeast": 2,
|
|
90
|
-
"us-midwest": 5,
|
|
91
|
-
global: 1,
|
|
92
|
-
};
|
|
93
|
-
/**
|
|
94
|
-
* Stream-count newlines, matching `wc -l` (memory-safe for the multi-GB collection).
|
|
95
|
-
*/
|
|
96
|
-
async function countLines(path) {
|
|
97
|
-
let count = 0;
|
|
98
|
-
for await (const chunk of createReadStream(path)) {
|
|
99
|
-
for (const byte of chunk) {
|
|
100
|
-
if (byte === 0x0a) {
|
|
101
|
-
count++;
|
|
102
|
-
}
|
|
103
|
-
}
|
|
104
|
-
}
|
|
105
|
-
return count;
|
|
106
|
-
}
|
|
107
|
-
/**
|
|
108
|
-
* Stream an HTTP download to disk, returning the final HTTP status (0 on network error after retries). Follows
|
|
109
|
-
* redirects (the OA download endpoint 302s to a pre-signed S3 URL).
|
|
110
|
-
*
|
|
111
|
-
* NOTE(phase1): kept local instead of the shared `downloadToFile` — this one streams a multi-GB body to disk (the
|
|
112
|
-
* shared util buffers via `arrayBuffer()`) and returns the HTTP status instead of throwing, which the caller needs for
|
|
113
|
-
* its two-URL fallback ladder.
|
|
114
|
-
*/
|
|
115
|
-
async function streamDownload(url, dest, opts) {
|
|
116
|
-
for (let attempt = 0; attempt <= opts.retries; attempt++) {
|
|
117
|
-
try {
|
|
118
|
-
const res = await fetch(url, {
|
|
119
|
-
headers: opts.headers ?? {},
|
|
120
|
-
redirect: "follow",
|
|
121
|
-
signal: AbortSignal.timeout(opts.timeoutMs),
|
|
122
|
-
});
|
|
123
|
-
if (res.ok && res.body) {
|
|
124
|
-
await pipeline(Readable.fromWeb(res.body), createWriteStream(dest));
|
|
125
|
-
return res.status;
|
|
126
|
-
}
|
|
127
|
-
if (attempt < opts.retries && isTransientStatus(res.status)) {
|
|
128
|
-
await sleep(opts.retryDelayMs);
|
|
129
|
-
continue;
|
|
130
|
-
}
|
|
131
|
-
return res.status;
|
|
132
|
-
}
|
|
133
|
-
catch {
|
|
134
|
-
if (attempt < opts.retries) {
|
|
135
|
-
await sleep(opts.retryDelayMs);
|
|
136
|
-
continue;
|
|
137
|
-
}
|
|
138
|
-
return 0;
|
|
139
|
-
}
|
|
140
|
-
}
|
|
141
|
-
return 0;
|
|
142
|
-
}
|
|
143
|
-
/**
|
|
144
|
-
* Decompress `src` → `dest` with the same deprioritized subprocess the old fetcher used.
|
|
145
|
-
*/
|
|
146
|
-
async function gunzipToFile(src, dest) {
|
|
147
|
-
const child = spawn("nice", ["-n", "15", "ionice", "-c", "3", "gunzip", "-c", src], {
|
|
148
|
-
stdio: ["ignore", "pipe", "inherit"],
|
|
149
|
-
});
|
|
150
|
-
await pipeline(child.stdout, createWriteStream(dest));
|
|
151
|
-
await new Promise((resolve, reject) => {
|
|
152
|
-
child.on("close", (code) => (code === 0 ? resolve() : reject(new Error(`gunzip exited with code ${code}`))));
|
|
153
|
-
child.on("error", reject);
|
|
154
|
-
});
|
|
155
|
-
}
|
|
156
|
-
export async function fetchOpenAddresses(options, report) {
|
|
157
|
-
const country = options.country ?? "ca";
|
|
158
|
-
const token = $private.OA_BATCH_TOKEN;
|
|
159
|
-
const destDir = join(options.outRoot, "openaddresses", country);
|
|
160
|
-
const manifestPath = join(destDir, "MANIFEST.json");
|
|
161
|
-
const outputFile = join(destDir, "collection.geojsonl");
|
|
162
|
-
const fail = (code) => ({ fetched: 0, skipped: 0, failed: 1, failedCodes: [code] });
|
|
163
|
-
report?.(`=== fetch openaddresses: country=${country}`);
|
|
164
|
-
report?.(` dest: ${destDir}`);
|
|
165
|
-
mkdirSync(destDir, { recursive: true });
|
|
166
|
-
// MARK: Authentication check
|
|
167
|
-
if (!token) {
|
|
168
|
-
report?.(`
|
|
169
|
-
ERROR: OA_BATCH_TOKEN is not set.
|
|
170
|
-
|
|
171
|
-
As of 2026-05-18, batch.openaddresses.io requires a registered (free) account
|
|
172
|
-
to download collection files. Data remains openly licensed — the auth gate
|
|
173
|
-
is there to prevent CDN abuse, not to restrict access.
|
|
174
|
-
|
|
175
|
-
Steps to get a token:
|
|
176
|
-
1. Register at: https://batch.openaddresses.io/register
|
|
177
|
-
2. Verify your email and log in.
|
|
178
|
-
3. Go to Profile → "Create Token" → copy the token.
|
|
179
|
-
4. Export it in this shell:
|
|
180
|
-
export OA_BATCH_TOKEN=<your-token>
|
|
181
|
-
5. Re-run this command.
|
|
182
|
-
|
|
183
|
-
The Canada collection (ca) is ~2 GiB compressed / ~7 GiB uncompressed
|
|
184
|
-
(estimated), so budget ~20–45 minutes at typical cloud-to-host bandwidth.
|
|
185
|
-
`);
|
|
186
|
-
return fail("OA_BATCH_TOKEN");
|
|
187
|
-
}
|
|
188
|
-
// MARK: Determine collection ID
|
|
189
|
-
let collectionID = OA_COLLECTION_IDS[country];
|
|
190
|
-
if (collectionID === undefined) {
|
|
191
|
-
report?.(`Unknown country code '${country}'. Fetching collection list to find ID...`);
|
|
192
|
-
// The collections API only. The COLLECTION ARCHIVES stay on raw `fetch` — they stream multi-gigabyte
|
|
193
|
-
// bodies straight to disk, where response caching is nonsense and axios would buffer them in memory.
|
|
194
|
-
const res = await new APIClient({
|
|
195
|
-
displayName: "openaddresses-api",
|
|
196
|
-
retry: true,
|
|
197
|
-
axios: { headers: { Authorization: `Bearer ${token}`, "Accept-Encoding": "gzip, br" } },
|
|
198
|
-
})
|
|
199
|
-
// `validateStatus` keeps a non-2xx as a RESPONSE rather than a throw: the caller reports the status and
|
|
200
|
-
// returns `fail(country)`, a graceful path this must not turn into an exception.
|
|
201
|
-
.fetch({
|
|
202
|
-
url: `${OA_BASE}/api/collections`,
|
|
203
|
-
timeout: 30_000,
|
|
204
|
-
validateStatus: () => true,
|
|
205
|
-
});
|
|
206
|
-
if (!isSuccessStatus(res.status)) {
|
|
207
|
-
report?.(`ERROR: GET /api/collections returned HTTP ${res.status}.`);
|
|
208
|
-
return fail(country);
|
|
209
|
-
}
|
|
210
|
-
const collections = res.data;
|
|
211
|
-
const match = collections.find((item) => item.name === country);
|
|
212
|
-
if (match?.id === undefined) {
|
|
213
|
-
report?.(`ERROR: Could not find a collection named '${country}' in GET /api/collections.`);
|
|
214
|
-
report?.(`Available collections:`);
|
|
215
|
-
for (const item of collections) {
|
|
216
|
-
const size = (item.size ?? 0).toLocaleString();
|
|
217
|
-
report?.(` ${(item.name ?? "").padEnd(20)} id=${item.id} ${item.human ?? ""} size=${size} bytes`);
|
|
218
|
-
}
|
|
219
|
-
return fail(country);
|
|
220
|
-
}
|
|
221
|
-
collectionID = match.id;
|
|
222
|
-
report?.(` Found collection id=${collectionID} for '${country}'`);
|
|
223
|
-
}
|
|
224
|
-
// MARK: Download via the collections download endpoint (302s to S3)
|
|
225
|
-
report?.(` Resolving download URL for collection id=${collectionID}...`);
|
|
226
|
-
report?.(` Attempting authenticated download...`);
|
|
227
|
-
const tmpGz = join(destDir, "collection.geojsonl.gz.tmp");
|
|
228
|
-
const tmpRaw = join(destDir, "collection.geojsonl.tmp");
|
|
229
|
-
const sourceURL = `${OA_BASE}/api/collections/${collectionID}/download`;
|
|
230
|
-
let httpStatus = await streamDownload(sourceURL, tmpGz, {
|
|
231
|
-
headers: { Authorization: `Bearer ${token}` },
|
|
232
|
-
timeoutMs: 7_200_000,
|
|
233
|
-
retries: 3,
|
|
234
|
-
retryDelayMs: 30_000,
|
|
235
|
-
});
|
|
236
|
-
if (httpStatus !== HTTP_OK) {
|
|
237
|
-
// Try the geojsonl.gz directly with token as query param (alternate URL shape).
|
|
238
|
-
httpStatus = await streamDownload(`${OA_BASE}/api/collections/${collectionID}/geojsonl.gz?token=${token}`, tmpGz, {
|
|
239
|
-
timeoutMs: 7_200_000,
|
|
240
|
-
retries: 3,
|
|
241
|
-
retryDelayMs: 30_000,
|
|
242
|
-
});
|
|
243
|
-
}
|
|
244
|
-
if (httpStatus !== HTTP_OK) {
|
|
245
|
-
rmSync(tmpGz, { force: true });
|
|
246
|
-
report?.(`
|
|
247
|
-
ERROR: Download returned HTTP ${httpStatus}.
|
|
248
|
-
|
|
249
|
-
Likely causes:
|
|
250
|
-
1. OA_BATCH_TOKEN is invalid or expired — re-create it at Profile → Tokens.
|
|
251
|
-
2. The collection download endpoint URL has changed (this module was written
|
|
252
|
-
against the 2026-05-18 batch.openaddresses.io API; it may need updating).
|
|
253
|
-
3. Network error or CDN outage.
|
|
254
|
-
|
|
255
|
-
Manual download (after logging in to batch.openaddresses.io):
|
|
256
|
-
- Navigate to https://batch.openaddresses.io/collection/${collectionID}
|
|
257
|
-
- Click "GeoJSON+LD" to download the collection.
|
|
258
|
-
- Save as: ${outputFile}
|
|
259
|
-
|
|
260
|
-
URL tried: ${OA_BASE}/api/collections/${collectionID}/download
|
|
261
|
-
`);
|
|
262
|
-
return fail(country);
|
|
263
|
-
}
|
|
264
|
-
// MARK: Decompress if the downloaded file is gzipped
|
|
265
|
-
const fileMagic = (await execFileAsync("file", ["--brief", tmpGz]).catch(() => ({ stdout: "" }))).stdout;
|
|
266
|
-
if (/gzip|compressed/i.test(fileMagic)) {
|
|
267
|
-
report?.(` Decompressing gzip archive...`);
|
|
268
|
-
await gunzipToFile(tmpGz, tmpRaw);
|
|
269
|
-
rmSync(tmpGz, { force: true });
|
|
270
|
-
renameSync(tmpRaw, outputFile);
|
|
271
|
-
}
|
|
272
|
-
else if (/JSON|ASCII|UTF-8/i.test(fileMagic)) {
|
|
273
|
-
// Already line-delimited GeoJSON.
|
|
274
|
-
renameSync(tmpGz, outputFile);
|
|
275
|
-
rmSync(tmpRaw, { force: true });
|
|
276
|
-
}
|
|
277
|
-
else {
|
|
278
|
-
// Unknown type — keep as-is and let the operator inspect.
|
|
279
|
-
renameSync(tmpGz, outputFile);
|
|
280
|
-
report?.(` WARNING: Downloaded file type is '${fileMagic.trim()}' — may need manual decompression.`);
|
|
281
|
-
}
|
|
282
|
-
// MARK: Verify + write MANIFEST
|
|
283
|
-
if (!existsSync(outputFile)) {
|
|
284
|
-
report?.(`ERROR: Output file not found at ${outputFile} after download.`);
|
|
285
|
-
return fail(country);
|
|
286
|
-
}
|
|
287
|
-
const size = statSync(outputFile).size;
|
|
288
|
-
if (size < MIN_PLAUSIBLE_SHARD_BYTES) {
|
|
289
|
-
report?.(`ERROR: File is suspiciously small (${size} bytes) — likely an error response.`);
|
|
290
|
-
return fail(country);
|
|
291
|
-
}
|
|
292
|
-
const sha = await sha256File(outputFile);
|
|
293
|
-
const rowCount = await countLines(outputFile);
|
|
294
|
-
const downloadedAt = new Date().toISOString().replace(/\.\d{3}Z$/, "Z");
|
|
295
|
-
const manifest = {
|
|
296
|
-
source_url: sourceURL,
|
|
297
|
-
collection_id: collectionID,
|
|
298
|
-
country,
|
|
299
|
-
filename: "collection.geojsonl",
|
|
300
|
-
downloaded_at: downloadedAt,
|
|
301
|
-
sha256: sha,
|
|
302
|
-
bytes: size,
|
|
303
|
-
row_count: rowCount,
|
|
304
|
-
notes: "batch.openaddresses.io requires a free registered account for downloads. License is mixed per-row; use the openaddresses adapter with allowShareAlike=false (default) to filter Tier-C rows.",
|
|
305
|
-
};
|
|
306
|
-
await writeManifest(manifestPath, manifest);
|
|
307
|
-
report?.(` ✓ ${ByteFormatter.formatIEC(size)} rows=${rowCount} sha256=${sha}`);
|
|
308
|
-
report?.(` MANIFEST written to ${manifestPath}`);
|
|
309
|
-
report?.(`=== done`);
|
|
310
|
-
report?.(`Feed to the adapter:`);
|
|
311
|
-
report?.(` mailwoman corpus run openaddresses \\`);
|
|
312
|
-
report?.(` --input ${outputFile} \\`);
|
|
313
|
-
report?.(` --country ${country.toUpperCase()} \\`);
|
|
314
|
-
report?.(` --output ${options.outRoot}`);
|
|
315
|
-
return { fetched: 1, skipped: 0, failed: 0, failedCodes: [] };
|
|
316
|
-
}
|
|
317
|
-
//# sourceMappingURL=openaddresses.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"openaddresses.js","sourceRoot":"","sources":["../../../../src/tools/fetch/openaddresses.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAmDG;AAEH;kGACkG;AAElG,OAAO,EAAE,QAAQ,EAAE,KAAK,EAAE,MAAM,oBAAoB,CAAA;AACpD,OAAO,EAAE,gBAAgB,EAAE,iBAAiB,EAAE,UAAU,EAAE,SAAS,EAAE,UAAU,EAAE,MAAM,EAAE,QAAQ,EAAE,MAAM,SAAS,CAAA;AAClH,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAChC,OAAO,EAAE,QAAQ,EAAE,MAAM,aAAa,CAAA;AACtC,OAAO,EAAE,QAAQ,EAAE,MAAM,sBAAsB,CAAA;AAC/C,OAAO,EAAE,UAAU,IAAI,KAAK,EAAE,MAAM,sBAAsB,CAAA;AAC1D,OAAO,EAAE,SAAS,EAAE,MAAM,WAAW,CAAA;AAErC,OAAO,EAAE,SAAS,EAAE,eAAe,EAAE,MAAM,qBAAqB,CAAA;AAChE,OAAO,EAAE,QAAQ,EAAE,MAAM,qBAAqB,CAAA;AAC9C,OAAO,EAAE,aAAa,EAAE,MAAM,0BAA0B,CAAA;AACxD,OAAO,EAAE,UAAU,EAAE,MAAM,uBAAuB,CAAA;AAGlD,OAAO,EAAE,iBAAiB,EAAE,aAAa,EAAE,MAAM,eAAe,CAAA;AAEhE;;;GAGG;AACH;;GAEG;AACH,MAAM,OAAO,GAAG,GAAG,CAAA;AAEnB;;GAEG;AACH,MAAM,yBAAyB,GAAG,MAAM,CAAA;AAExC,MAAM,aAAa,GAAG,SAAS,CAAC,QAAQ,CAAC,CAAA;AAEzC,MAAM,OAAO,GAAG,gCAAgC,CAAA;AAEhD;;;GAGG;AACH,MAAM,iBAAiB,GAA2B;IACjD,EAAE,EAAE,CAAC;IACL,SAAS,EAAE,CAAC;IACZ,UAAU,EAAE,CAAC;IACb,cAAc,EAAE,CAAC;IACjB,YAAY,EAAE,CAAC;IACf,MAAM,EAAE,CAAC;CACT,CAAA;AAgBD;;GAEG;AACH,KAAK,UAAU,UAAU,CAAC,IAAY;IACrC,IAAI,KAAK,GAAG,CAAC,CAAA;IAEb,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,gBAAgB,CAAC,IAAI,CAA0B,EAAE,CAAC;QAC3E,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;YAC1B,IAAI,IAAI,KAAK,IAAI,EAAE,CAAC;gBACnB,KAAK,EAAE,CAAA;YACR,CAAC;QACF,CAAC;IACF,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC;AASD;;;;;;;GAOG;AACH,KAAK,UAAU,cAAc,CAAC,GAAW,EAAE,IAAY,EAAE,IAAwB;IAChF,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,iBAAiB,CAAC,IAAI,CAAC,CAAC,CAAA;gBAEnE,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,KAAK,UAAU,YAAY,CAAC,GAAW,EAAE,IAAY;IACpD,MAAM,KAAK,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,IAAI,EAAE,GAAG,EAAE,QAAQ,EAAE,IAAI,EAAE,GAAG,CAAC,EAAE;QACnF,KAAK,EAAE,CAAC,QAAQ,EAAE,MAAM,EAAE,SAAS,CAAC;KACpC,CAAC,CAAA;IAEF,MAAM,QAAQ,CAAC,KAAK,CAAC,MAAO,EAAE,iBAAiB,CAAC,IAAI,CAAC,CAAC,CAAA;IAEtD,MAAM,IAAI,OAAO,CAAO,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE;QAC3C,KAAK,CAAC,EAAE,CAAC,OAAO,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,IAAI,KAAK,CAAC,CAAC,CAAC,CAAC,OAAO,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,IAAI,KAAK,CAAC,2BAA2B,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC,CAAA;QAC5G,KAAK,CAAC,EAAE,CAAC,OAAO,EAAE,MAAM,CAAC,CAAA;IAC1B,CAAC,CAAC,CAAA;AACH,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,kBAAkB,CACvC,OAAkC,EAClC,MAA+B;IAE/B,MAAM,OAAO,GAAG,OAAO,CAAC,OAAO,IAAI,IAAI,CAAA;IACvC,MAAM,KAAK,GAAG,QAAQ,CAAC,cAAc,CAAA;IAErC,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,eAAe,EAAE,OAAO,CAAC,CAAA;IAC/D,MAAM,YAAY,GAAG,IAAI,CAAC,OAAO,EAAE,eAAe,CAAC,CAAA;IACnD,MAAM,UAAU,GAAG,IAAI,CAAC,OAAO,EAAE,qBAAqB,CAAC,CAAA;IAEvD,MAAM,IAAI,GAAG,CAAC,IAAY,EAAgB,EAAE,CAAC,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,WAAW,EAAE,CAAC,IAAI,CAAC,EAAE,CAAC,CAAA;IAEzG,MAAM,EAAE,CAAC,oCAAoC,OAAO,EAAE,CAAC,CAAA;IACvD,MAAM,EAAE,CAAC,aAAa,OAAO,EAAE,CAAC,CAAA;IAEhC,SAAS,CAAC,OAAO,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;IAEvC,6BAA6B;IAE7B,IAAI,CAAC,KAAK,EAAE,CAAC;QACZ,MAAM,EAAE,CAAC;;;;;;;;;;;;;;;;;CAiBV,CAAC,CAAA;QAEA,OAAO,IAAI,CAAC,gBAAgB,CAAC,CAAA;IAC9B,CAAC;IAED,gCAAgC;IAEhC,IAAI,YAAY,GAAG,iBAAiB,CAAC,OAAO,CAAC,CAAA;IAE7C,IAAI,YAAY,KAAK,SAAS,EAAE,CAAC;QAChC,MAAM,EAAE,CAAC,yBAAyB,OAAO,2CAA2C,CAAC,CAAA;QAErF,qGAAqG;QACrG,qGAAqG;QACrG,MAAM,GAAG,GAAG,MAAM,IAAI,SAAS,CAAC;YAC/B,WAAW,EAAE,mBAAmB;YAChC,KAAK,EAAE,IAAI;YACX,KAAK,EAAE,EAAE,OAAO,EAAE,EAAE,aAAa,EAAE,UAAU,KAAK,EAAE,EAAE,iBAAiB,EAAE,UAAU,EAAE,EAAE;SACvF,CAAC;YACD,wGAAwG;YACxG,iFAAiF;aAChF,KAAK,CAAiB;YACtB,GAAG,EAAE,GAAG,OAAO,kBAAkB;YACjC,OAAO,EAAE,MAAM;YACf,cAAc,EAAE,GAAG,EAAE,CAAC,IAAI;SAC1B,CAAC,CAAA;QAEH,IAAI,CAAC,eAAe,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC;YAClC,MAAM,EAAE,CAAC,6CAA6C,GAAG,CAAC,MAAM,GAAG,CAAC,CAAA;YAEpE,OAAO,IAAI,CAAC,OAAO,CAAC,CAAA;QACrB,CAAC;QAED,MAAM,WAAW,GAAG,GAAG,CAAC,IAAI,CAAA;QAC5B,MAAM,KAAK,GAAG,WAAW,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,IAAI,KAAK,OAAO,CAAC,CAAA;QAE/D,IAAI,KAAK,EAAE,EAAE,KAAK,SAAS,EAAE,CAAC;YAC7B,MAAM,EAAE,CAAC,6CAA6C,OAAO,4BAA4B,CAAC,CAAA;YAC1F,MAAM,EAAE,CAAC,wBAAwB,CAAC,CAAA;YAElC,KAAK,MAAM,IAAI,IAAI,WAAW,EAAE,CAAC;gBAChC,MAAM,IAAI,GAAG,CAAC,IAAI,CAAC,IAAI,IAAI,CAAC,CAAC,CAAC,cAAc,EAAE,CAAA;gBAC9C,MAAM,EAAE,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,IAAI,EAAE,CAAC,CAAC,MAAM,CAAC,EAAE,CAAC,QAAQ,IAAI,CAAC,EAAE,KAAK,IAAI,CAAC,KAAK,IAAI,EAAE,UAAU,IAAI,QAAQ,CAAC,CAAA;YACtG,CAAC;YAED,OAAO,IAAI,CAAC,OAAO,CAAC,CAAA;QACrB,CAAC;QAED,YAAY,GAAG,KAAK,CAAC,EAAE,CAAA;QACvB,MAAM,EAAE,CAAC,yBAAyB,YAAY,SAAS,OAAO,GAAG,CAAC,CAAA;IACnE,CAAC;IAED,oEAAoE;IAEpE,MAAM,EAAE,CAAC,8CAA8C,YAAY,KAAK,CAAC,CAAA;IACzE,MAAM,EAAE,CAAC,wCAAwC,CAAC,CAAA;IAElD,MAAM,KAAK,GAAG,IAAI,CAAC,OAAO,EAAE,4BAA4B,CAAC,CAAA;IACzD,MAAM,MAAM,GAAG,IAAI,CAAC,OAAO,EAAE,yBAAyB,CAAC,CAAA;IACvD,MAAM,SAAS,GAAG,GAAG,OAAO,oBAAoB,YAAY,WAAW,CAAA;IAEvE,IAAI,UAAU,GAAG,MAAM,cAAc,CAAC,SAAS,EAAE,KAAK,EAAE;QACvD,OAAO,EAAE,EAAE,aAAa,EAAE,UAAU,KAAK,EAAE,EAAE;QAC7C,SAAS,EAAE,SAAS;QACpB,OAAO,EAAE,CAAC;QACV,YAAY,EAAE,MAAM;KACpB,CAAC,CAAA;IAEF,IAAI,UAAU,KAAK,OAAO,EAAE,CAAC;QAC5B,gFAAgF;QAChF,UAAU,GAAG,MAAM,cAAc,CAAC,GAAG,OAAO,oBAAoB,YAAY,sBAAsB,KAAK,EAAE,EAAE,KAAK,EAAE;YACjH,SAAS,EAAE,SAAS;YACpB,OAAO,EAAE,CAAC;YACV,YAAY,EAAE,MAAM;SACpB,CAAC,CAAA;IACH,CAAC;IAED,IAAI,UAAU,KAAK,OAAO,EAAE,CAAC;QAC5B,MAAM,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC,CAAA;QAE9B,MAAM,EAAE,CAAC;gCACqB,UAAU;;;;;;;;;4DASkB,YAAY;;eAEzD,UAAU;;aAEZ,OAAO,oBAAoB,YAAY;CACnD,CAAC,CAAA;QAEA,OAAO,IAAI,CAAC,OAAO,CAAC,CAAA;IACrB,CAAC;IAED,qDAAqD;IAErD,MAAM,SAAS,GAAG,CAAC,MAAM,aAAa,CAAC,MAAM,EAAE,CAAC,SAAS,EAAE,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,GAAG,EAAE,CAAC,CAAC,EAAE,MAAM,EAAE,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,MAAM,CAAA;IAExG,IAAI,kBAAkB,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,CAAC;QACxC,MAAM,EAAE,CAAC,iCAAiC,CAAC,CAAA;QAC3C,MAAM,YAAY,CAAC,KAAK,EAAE,MAAM,CAAC,CAAA;QACjC,MAAM,CAAC,KAAK,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC,CAAA;QAC9B,UAAU,CAAC,MAAM,EAAE,UAAU,CAAC,CAAA;IAC/B,CAAC;SAAM,IAAI,mBAAmB,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,CAAC;QAChD,kCAAkC;QAClC,UAAU,CAAC,KAAK,EAAE,UAAU,CAAC,CAAA;QAC7B,MAAM,CAAC,MAAM,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC,CAAA;IAChC,CAAC;SAAM,CAAC;QACP,0DAA0D;QAC1D,UAAU,CAAC,KAAK,EAAE,UAAU,CAAC,CAAA;QAC7B,MAAM,EAAE,CAAC,uCAAuC,SAAS,CAAC,IAAI,EAAE,oCAAoC,CAAC,CAAA;IACtG,CAAC;IAED,gCAAgC;IAEhC,IAAI,CAAC,UAAU,CAAC,UAAU,CAAC,EAAE,CAAC;QAC7B,MAAM,EAAE,CAAC,mCAAmC,UAAU,kBAAkB,CAAC,CAAA;QAEzE,OAAO,IAAI,CAAC,OAAO,CAAC,CAAA;IACrB,CAAC;IAED,MAAM,IAAI,GAAG,QAAQ,CAAC,UAAU,CAAC,CAAC,IAAI,CAAA;IAEtC,IAAI,IAAI,GAAG,yBAAyB,EAAE,CAAC;QACtC,MAAM,EAAE,CAAC,sCAAsC,IAAI,qCAAqC,CAAC,CAAA;QAEzF,OAAO,IAAI,CAAC,OAAO,CAAC,CAAA;IACrB,CAAC;IAED,MAAM,GAAG,GAAG,MAAM,UAAU,CAAC,UAAU,CAAC,CAAA;IACxC,MAAM,QAAQ,GAAG,MAAM,UAAU,CAAC,UAAU,CAAC,CAAA;IAC7C,MAAM,YAAY,GAAG,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE,CAAC,OAAO,CAAC,WAAW,EAAE,GAAG,CAAC,CAAA;IAEvE,MAAM,QAAQ,GAAG;QAChB,UAAU,EAAE,SAAS;QACrB,aAAa,EAAE,YAAY;QAC3B,OAAO;QACP,QAAQ,EAAE,qBAAqB;QAC/B,aAAa,EAAE,YAAY;QAC3B,MAAM,EAAE,GAAG;QACX,KAAK,EAAE,IAAI;QACX,SAAS,EAAE,QAAQ;QACnB,KAAK,EACJ,8LAA8L;KAC/L,CAAA;IAED,MAAM,aAAa,CAAC,YAAY,EAAE,QAAQ,CAAC,CAAA;IAE3C,MAAM,EAAE,CAAC,OAAO,aAAa,CAAC,SAAS,CAAC,IAAI,CAAC,UAAU,QAAQ,YAAY,GAAG,EAAE,CAAC,CAAA;IACjF,MAAM,EAAE,CAAC,yBAAyB,YAAY,EAAE,CAAC,CAAA;IACjD,MAAM,EAAE,CAAC,UAAU,CAAC,CAAA;IACpB,MAAM,EAAE,CAAC,sBAAsB,CAAC,CAAA;IAChC,MAAM,EAAE,CAAC,yCAAyC,CAAC,CAAA;IACnD,MAAM,EAAE,CAAC,eAAe,UAAU,KAAK,CAAC,CAAA;IACxC,MAAM,EAAE,CAAC,iBAAiB,OAAO,CAAC,WAAW,EAAE,KAAK,CAAC,CAAA;IACrD,MAAM,EAAE,CAAC,gBAAgB,OAAO,CAAC,OAAO,EAAE,CAAC,CAAA;IAE3C,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,WAAW,EAAE,EAAE,EAAE,CAAA;AAC9D,CAAC"}
|
|
@@ -1,45 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Fetch the OurAirports CSV dumps — the VENUE side of the sub-venue corpus arc (#35).
|
|
7
|
-
*
|
|
8
|
-
* Source : https://davidmegginson.github.io/ourairports-data/ (the project's own GitHub Pages
|
|
9
|
-
* mirror of the nightly export; `ourairports.com/data/` redirects here).
|
|
10
|
-
* License: PUBLIC DOMAIN. OurAirports places its data in the public domain and asks only for a
|
|
11
|
-
* courtesy credit — no attribution obligation rides on a derived shard, which makes this
|
|
12
|
-
* the one transport source in the arc with no licensing question at all. Tier A.
|
|
13
|
-
*
|
|
14
|
-
* ## What it is good for, and what it is not
|
|
15
|
-
*
|
|
16
|
-
* `airports.csv` is every airport on earth with ICAO/IATA codes, coordinates, `municipality`, and
|
|
17
|
-
* `iso_country` — 12.7 MB, ~83,000 rows as of 2026-08-04. That is the CONTAINING VENUE for a
|
|
18
|
-
* `<sub-venue>, <venue>, <street>, <locality>, <postcode>` corpus line, and it is better at that job
|
|
19
|
-
* than OSM: every row is named, the name is canonical, and `municipality` gives the locality without
|
|
20
|
-
* a spatial join.
|
|
21
|
-
*
|
|
22
|
-
* It carries NO interior structure. There is no terminal, concourse, gate or pier table — the
|
|
23
|
-
* corpus task says as much ("Good for the venue side of each pair, weaker on interior structure")
|
|
24
|
-
* and a row-level read confirms it. Pair it with the OSM `aeroway` extractor
|
|
25
|
-
* (`@mailwoman/osm/sdk`'s `extractOSMSubVenues`), which is where the sub-venue half comes from.
|
|
26
|
-
*
|
|
27
|
-
* ## Why `downloadToFile` and not `APIClient`
|
|
28
|
-
*
|
|
29
|
-
* `AGENTS.md` routes HTTP through `APIClient`, and that rule is about API REQUESTS — small bodies,
|
|
30
|
-
* repeated calls, rate-limited hosts. This is four static file transfers against a GitHub Pages CDN
|
|
31
|
-
* with no rate limit and nothing to pace, run once per refresh. It uses the same `downloadToFile`
|
|
32
|
-
* every other module in this `fetch/` family uses, which is where the retry and timeout live.
|
|
33
|
-
* The Wikidata sibling (`wikidata-subvenue.ts`) IS an API client and is built on `APIClient`
|
|
34
|
-
* accordingly; the split between the two is the one `AGENTS.md` draws.
|
|
35
|
-
*
|
|
36
|
-
* Invoke via `mailwoman corpus fetch ourairports --out-root <path>`.
|
|
37
|
-
*/
|
|
38
|
-
import type { BaseFetchOptions, FetchSummary } from "./download.ts";
|
|
39
|
-
export type FetchOurAirportsOptions = BaseFetchOptions;
|
|
40
|
-
/**
|
|
41
|
-
* Download the OurAirports CSVs into `<outRoot>/ourairports/`, with a sibling `MANIFEST.json` carrying each file's
|
|
42
|
-
* origin URL, sha256, byte count and upstream `Last-Modified`.
|
|
43
|
-
*/
|
|
44
|
-
export declare function fetchOurAirports(options: FetchOurAirportsOptions, report?: (line: string) => void): Promise<FetchSummary>;
|
|
45
|
-
//# sourceMappingURL=ourairports.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"ourairports.d.ts","sourceRoot":"","sources":["../../../../src/tools/fetch/ourairports.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAoCG;AAQH,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAAE,MAAM,eAAe,CAAA;AAsBnE,MAAM,MAAM,uBAAuB,GAAG,gBAAgB,CAAA;AAyCtD;;;GAGG;AACH,wBAAsB,gBAAgB,CACrC,OAAO,EAAE,uBAAuB,EAChC,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,YAAY,CAAC,CAwDvB"}
|