@mailwoman/corpus 9.2.0 → 9.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +22 -22
- package/data/PROVENANCE.md +7 -7
- package/lib/adapters/ban/adapter.ts +190 -0
- package/lib/adapters/ban/street-decompose.ts +66 -0
- package/lib/adapters/fcc-bdc/adapter.ts +174 -0
- package/lib/adapters/geonames/adapter.ts +199 -0
- package/lib/adapters/geonames-postal/adapter.ts +122 -0
- package/lib/adapters/gnaf/adapter.ts +149 -0
- package/lib/adapters/gnaf/assemble.ts +225 -0
- package/lib/adapters/index.ts +153 -0
- package/lib/adapters/openaddresses/adapter.ts +251 -0
- package/lib/adapters/overture/adapter.ts +162 -0
- package/lib/adapters/state-hi-schools/adapter.ts +170 -0
- package/lib/adapters/state-hi-schools/workbook.ts +35 -0
- package/lib/adapters/synth-po-box/adapter.ts +204 -0
- package/lib/adapters/tiger/adapter.ts +252 -0
- package/lib/adapters/tiger/street-decompose.ts +83 -0
- package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +167 -0
- package/lib/adapters/usgov-imls-pls/adapter.ts +143 -0
- package/lib/adapters/usgov-irs-bmf/adapter.ts +151 -0
- package/lib/adapters/usgov-nad/adapter.ts +334 -0
- package/lib/adapters/usgov-nppes/adapter.ts +151 -0
- package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +193 -0
- package/lib/adapters/utils/index.ts +307 -0
- package/lib/adapters/wof-admin-jp/adapter.ts +214 -0
- package/lib/adapters/wof-admin-json/adapter.ts +231 -0
- package/lib/adapters/wof-json-rows.ts +129 -0
- package/lib/adapters/wof-postalcode-json/adapter.ts +176 -0
- package/lib/build.ts +378 -0
- package/lib/env.ts +50 -0
- package/lib/index.ts +13 -0
- package/lib/name-prone-us-suffixes.ts +12 -0
- package/lib/recipes/anchor-absorption.ts +101 -0
- package/lib/recipes/bare-country.ts +95 -0
- package/lib/recipes/boundary-stress.ts +100 -0
- package/lib/recipes/cn-organizational-units.ts +199 -0
- package/lib/recipes/country-balanced.ts +509 -0
- package/lib/recipes/cz-pcfirst-preposition.ts +111 -0
- package/lib/recipes/fr-admin-split.ts +242 -0
- package/lib/recipes/fr-bare-street.ts +170 -0
- package/lib/recipes/fr-fragment.ts +333 -0
- package/lib/recipes/fr-lieudit.ts +301 -0
- package/lib/recipes/fr-order.ts +245 -0
- package/lib/recipes/german.ts +359 -0
- package/lib/recipes/house-venue.ts +92 -0
- package/lib/recipes/index.ts +97 -0
- package/lib/recipes/intersection.ts +618 -0
- package/lib/recipes/locale.ts +599 -0
- package/lib/recipes/nl-postcode.ts +115 -0
- package/lib/recipes/no-fragment.ts +219 -0
- package/lib/recipes/no-street-led.ts +141 -0
- package/lib/recipes/no-street.ts +90 -0
- package/lib/recipes/po-box-cedex.ts +976 -0
- package/lib/recipes/po-box.ts +123 -0
- package/lib/recipes/reviewed-postcode-tail.ts +190 -0
- package/lib/recipes/scaffold.ts +469 -0
- package/lib/recipes/si-bare-village.ts +97 -0
- package/lib/recipes/street-affix.ts +804 -0
- package/lib/recipes/street-bare.ts +100 -0
- package/lib/recipes/street.ts +81 -0
- package/lib/recipes/sub-venue-sources.ts +877 -0
- package/lib/recipes/sub-venue.ts +997 -0
- package/lib/recipes/trailing-region.ts +183 -0
- package/lib/recipes/unit.ts +304 -0
- package/lib/runner.ts +312 -0
- package/lib/synthesizers/anchor-absorption.ts +288 -0
- package/lib/synthesizers/boundary-stress.ts +532 -0
- package/lib/synthesizers/german.ts +260 -0
- package/lib/synthesizers/house-venue.ts +308 -0
- package/lib/synthesizers/intersection.ts +233 -0
- package/lib/synthesizers/no-street.ts +327 -0
- package/lib/synthesizers/po-box.ts +323 -0
- package/lib/synthesizers/street.ts +269 -0
- package/lib/synthesizers/utils.ts +993 -0
- package/lib/test-kit/corpus-recipe.ts +86 -0
- package/lib/test-kit/index.ts +100 -0
- package/lib/tools/align-slice.ts +68 -0
- package/lib/tools/audit.ts +403 -0
- package/lib/tools/corpus-stats.ts +136 -0
- package/lib/tools/fetch/ban.ts +289 -0
- package/lib/tools/fetch/download.ts +262 -0
- package/lib/tools/fetch/geonames-dump.ts +257 -0
- package/lib/tools/fetch/geonames-postal.ts +180 -0
- package/lib/tools/fetch/hrsa.ts +59 -0
- package/lib/tools/fetch/imls-pls.ts +149 -0
- package/lib/tools/fetch/index.ts +147 -0
- package/lib/tools/fetch/nad.ts +341 -0
- package/lib/tools/fetch/nppes.ts +165 -0
- package/lib/tools/fetch/openaddresses.ts +347 -0
- package/lib/tools/fetch/ourairports.ts +170 -0
- package/lib/tools/fetch/ppd.ts +121 -0
- package/lib/tools/fetch/state-hi-schools.ts +161 -0
- package/lib/tools/fetch/state-sources.ts +146 -0
- package/lib/tools/fetch/tiger-full.ts +308 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +384 -0
- package/lib/tools/golden-expand.ts +574 -0
- package/lib/tools/golden-promote.ts +337 -0
- package/lib/tools/golden-relabel-street.ts +683 -0
- package/lib/tools/index.ts +28 -0
- package/lib/tools/ingest-csv.ts +378 -0
- package/lib/tools/jsonl-to-parquet.ts +207 -0
- package/lib/tools/lint-slice-vocab.ts +388 -0
- package/lib/tools/lint-slice.ts +496 -0
- package/lib/tools/overlay-manifest.ts +148 -0
- package/lib/tools/overture-subvenue.ts +209 -0
- package/lib/tools/postcode-triples.ts +363 -0
- package/lib/tools/slice-kryptonite.ts +137 -0
- package/lib/tools/slice-translit.ts +218 -0
- package/lib/tools/sub-venue/harvest.ts +234 -0
- package/lib/tools/sub-venue/head-nouns.ts +245 -0
- package/lib/tools/sub-venue/surfaces.ts +95 -0
- package/lib/tools/sub-venue/table.ts +281 -0
- package/lib/tools/sub-venue/wikidata.ts +85 -0
- package/lib/tools/sub-venue-lexicon.ts +429 -0
- package/lib/tools/sub-venue-promotions.ts +330 -0
- package/lib/types.ts +247 -0
- package/lib/utils/align.ts +330 -0
- package/lib/utils/golden.ts +189 -0
- package/lib/utils/index.ts +14 -0
- package/lib/utils/parquet.ts +582 -0
- package/lib/utils/slice-stats.ts +95 -0
- package/lib/utils/split.ts +279 -0
- package/lib/utils/tokenize.ts +120 -0
- package/lib/utils/wof-json.ts +247 -0
- package/out/adapters/ban/adapter.d.ts.map +1 -0
- package/out/adapters/ban/adapter.js +149 -0
- package/out/adapters/ban/adapter.js.map +1 -0
- package/out/adapters/ban/street-decompose.d.ts.map +1 -0
- package/out/adapters/ban/street-decompose.js +51 -0
- package/out/adapters/ban/street-decompose.js.map +1 -0
- package/out/adapters/fcc-bdc/adapter.d.ts.map +1 -0
- package/out/adapters/fcc-bdc/adapter.js +144 -0
- package/out/adapters/fcc-bdc/adapter.js.map +1 -0
- package/out/adapters/geonames/adapter.d.ts.map +1 -0
- package/out/adapters/geonames/adapter.js +176 -0
- package/out/adapters/geonames/adapter.js.map +1 -0
- package/out/adapters/geonames-postal/adapter.d.ts +54 -0
- package/out/adapters/geonames-postal/adapter.d.ts.map +1 -0
- package/out/adapters/geonames-postal/adapter.js +107 -0
- package/out/adapters/geonames-postal/adapter.js.map +1 -0
- package/out/adapters/gnaf/adapter.d.ts +49 -0
- package/out/adapters/gnaf/adapter.d.ts.map +1 -0
- package/out/adapters/gnaf/adapter.js +124 -0
- package/out/adapters/gnaf/adapter.js.map +1 -0
- package/out/adapters/gnaf/assemble.d.ts +65 -0
- package/out/adapters/gnaf/assemble.d.ts.map +1 -0
- package/out/adapters/gnaf/assemble.js +154 -0
- package/out/adapters/gnaf/assemble.js.map +1 -0
- package/out/adapters/index.d.ts +51 -0
- package/out/adapters/index.d.ts.map +1 -0
- package/out/adapters/index.js +95 -0
- package/out/adapters/index.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -0
- package/out/adapters/openaddresses/adapter.js +186 -0
- package/out/adapters/openaddresses/adapter.js.map +1 -0
- package/out/adapters/overture/adapter.d.ts +48 -0
- package/out/adapters/overture/adapter.d.ts.map +1 -0
- package/out/adapters/overture/adapter.js +125 -0
- package/out/adapters/overture/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/adapter.d.ts +46 -0
- package/out/adapters/state-hi-schools/adapter.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/adapter.js +145 -0
- package/out/adapters/state-hi-schools/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/workbook.d.ts +29 -0
- package/out/adapters/state-hi-schools/workbook.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/workbook.js +20 -0
- package/out/adapters/state-hi-schools/workbook.js.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
- package/out/adapters/synth-po-box/adapter.d.ts.map +1 -0
- package/out/adapters/synth-po-box/adapter.js +140 -0
- package/out/adapters/synth-po-box/adapter.js.map +1 -0
- package/out/adapters/tiger/adapter.d.ts +55 -0
- package/out/adapters/tiger/adapter.d.ts.map +1 -0
- package/out/adapters/tiger/adapter.js +201 -0
- package/out/adapters/tiger/adapter.js.map +1 -0
- package/out/adapters/tiger/street-decompose.d.ts.map +1 -0
- package/out/adapters/tiger/street-decompose.js +68 -0
- package/out/adapters/tiger/street-decompose.js.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +56 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js +132 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts +36 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.js +114 -0
- package/out/adapters/usgov-imls-pls/adapter.js.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts +37 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.js +120 -0
- package/out/adapters/usgov-irs-bmf/adapter.js.map +1 -0
- package/out/adapters/usgov-nad/adapter.d.ts +48 -0
- package/out/adapters/usgov-nad/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nad/adapter.js +249 -0
- package/out/adapters/usgov-nad/adapter.js.map +1 -0
- package/out/adapters/usgov-nppes/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nppes/adapter.js +118 -0
- package/out/adapters/usgov-nppes/adapter.js.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +154 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -0
- package/out/adapters/utils/index.d.ts +191 -0
- package/out/adapters/utils/index.d.ts.map +1 -0
- package/out/adapters/utils/index.js +206 -0
- package/out/adapters/utils/index.js.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.js +161 -0
- package/out/adapters/wof-admin-jp/adapter.js.map +1 -0
- package/out/adapters/wof-admin-json/adapter.d.ts +79 -0
- package/out/adapters/wof-admin-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-json/adapter.js +197 -0
- package/out/adapters/wof-admin-json/adapter.js.map +1 -0
- package/out/adapters/wof-json-rows.d.ts +62 -0
- package/out/adapters/wof-json-rows.d.ts.map +1 -0
- package/out/adapters/wof-json-rows.js +83 -0
- package/out/adapters/wof-json-rows.js.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts +65 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.js +151 -0
- package/out/adapters/wof-postalcode-json/adapter.js.map +1 -0
- package/out/build.d.ts +132 -0
- package/out/build.d.ts.map +1 -0
- package/out/build.js +245 -0
- package/out/build.js.map +1 -0
- package/out/codex/us-fips-state.d.ts.map +1 -0
- package/out/codex/us-fips-state.js.map +1 -0
- package/out/env.d.ts +46 -0
- package/out/env.d.ts.map +1 -0
- package/out/env.js +46 -0
- package/out/env.js.map +1 -0
- package/out/index.d.ts +13 -0
- package/out/index.d.ts.map +1 -0
- package/out/index.js +13 -0
- package/out/index.js.map +1 -0
- package/out/name-prone-us-suffixes.d.ts +12 -0
- package/out/name-prone-us-suffixes.d.ts.map +1 -0
- package/out/name-prone-us-suffixes.js +12 -0
- package/out/name-prone-us-suffixes.js.map +1 -0
- package/out/recipes/anchor-absorption.d.ts +20 -0
- package/out/recipes/anchor-absorption.d.ts.map +1 -0
- package/out/recipes/anchor-absorption.js +81 -0
- package/out/recipes/anchor-absorption.js.map +1 -0
- package/out/recipes/bare-country.d.ts +25 -0
- package/out/recipes/bare-country.d.ts.map +1 -0
- package/out/recipes/bare-country.js +87 -0
- package/out/recipes/bare-country.js.map +1 -0
- package/out/recipes/boundary-stress.d.ts +20 -0
- package/out/recipes/boundary-stress.d.ts.map +1 -0
- package/out/recipes/boundary-stress.js +83 -0
- package/out/recipes/boundary-stress.js.map +1 -0
- package/out/recipes/cn-organizational-units.d.ts +36 -0
- package/out/recipes/cn-organizational-units.d.ts.map +1 -0
- package/out/recipes/cn-organizational-units.js +159 -0
- package/out/recipes/cn-organizational-units.js.map +1 -0
- package/out/recipes/country-balanced.d.ts +32 -0
- package/out/recipes/country-balanced.d.ts.map +1 -0
- package/out/recipes/country-balanced.js +393 -0
- package/out/recipes/country-balanced.js.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts +22 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.js +100 -0
- package/out/recipes/cz-pcfirst-preposition.js.map +1 -0
- package/out/recipes/fr-admin-split.d.ts +38 -0
- package/out/recipes/fr-admin-split.d.ts.map +1 -0
- package/out/recipes/fr-admin-split.js +192 -0
- package/out/recipes/fr-admin-split.js.map +1 -0
- package/out/recipes/fr-bare-street.d.ts +28 -0
- package/out/recipes/fr-bare-street.d.ts.map +1 -0
- package/out/recipes/fr-bare-street.js +143 -0
- package/out/recipes/fr-bare-street.js.map +1 -0
- package/out/recipes/fr-fragment.d.ts +77 -0
- package/out/recipes/fr-fragment.d.ts.map +1 -0
- package/out/recipes/fr-fragment.js +276 -0
- package/out/recipes/fr-fragment.js.map +1 -0
- package/out/recipes/fr-lieudit.d.ts +32 -0
- package/out/recipes/fr-lieudit.d.ts.map +1 -0
- package/out/recipes/fr-lieudit.js +227 -0
- package/out/recipes/fr-lieudit.js.map +1 -0
- package/out/recipes/fr-order.d.ts +38 -0
- package/out/recipes/fr-order.d.ts.map +1 -0
- package/out/recipes/fr-order.js +197 -0
- package/out/recipes/fr-order.js.map +1 -0
- package/out/recipes/german.d.ts +44 -0
- package/out/recipes/german.d.ts.map +1 -0
- package/out/recipes/german.js +288 -0
- package/out/recipes/german.js.map +1 -0
- package/out/recipes/house-venue.d.ts +18 -0
- package/out/recipes/house-venue.d.ts.map +1 -0
- package/out/recipes/house-venue.js +73 -0
- package/out/recipes/house-venue.js.map +1 -0
- package/out/recipes/index.d.ts +24 -0
- package/out/recipes/index.d.ts.map +1 -0
- package/out/recipes/index.js +91 -0
- package/out/recipes/index.js.map +1 -0
- package/out/recipes/intersection.d.ts +42 -0
- package/out/recipes/intersection.d.ts.map +1 -0
- package/out/recipes/intersection.js +452 -0
- package/out/recipes/intersection.js.map +1 -0
- package/out/recipes/locale.d.ts +136 -0
- package/out/recipes/locale.d.ts.map +1 -0
- package/out/recipes/locale.js +460 -0
- package/out/recipes/locale.js.map +1 -0
- package/out/recipes/nl-postcode.d.ts +26 -0
- package/out/recipes/nl-postcode.d.ts.map +1 -0
- package/out/recipes/nl-postcode.js +102 -0
- package/out/recipes/nl-postcode.js.map +1 -0
- package/out/recipes/no-fragment.d.ts +43 -0
- package/out/recipes/no-fragment.d.ts.map +1 -0
- package/out/recipes/no-fragment.js +182 -0
- package/out/recipes/no-fragment.js.map +1 -0
- package/out/recipes/no-street-led.d.ts +24 -0
- package/out/recipes/no-street-led.d.ts.map +1 -0
- package/out/recipes/no-street-led.js +113 -0
- package/out/recipes/no-street-led.js.map +1 -0
- package/out/recipes/no-street.d.ts +18 -0
- package/out/recipes/no-street.d.ts.map +1 -0
- package/out/recipes/no-street.js +71 -0
- package/out/recipes/no-street.js.map +1 -0
- package/out/recipes/po-box-cedex.d.ts +38 -0
- package/out/recipes/po-box-cedex.d.ts.map +1 -0
- package/out/recipes/po-box-cedex.js +767 -0
- package/out/recipes/po-box-cedex.js.map +1 -0
- package/out/recipes/po-box.d.ts +17 -0
- package/out/recipes/po-box.d.ts.map +1 -0
- package/out/recipes/po-box.js +100 -0
- package/out/recipes/po-box.js.map +1 -0
- package/out/recipes/reviewed-postcode-tail.d.ts +47 -0
- package/out/recipes/reviewed-postcode-tail.d.ts.map +1 -0
- package/out/recipes/reviewed-postcode-tail.js +125 -0
- package/out/recipes/reviewed-postcode-tail.js.map +1 -0
- package/out/recipes/scaffold.d.ts +324 -0
- package/out/recipes/scaffold.d.ts.map +1 -0
- package/out/recipes/scaffold.js +186 -0
- package/out/recipes/scaffold.js.map +1 -0
- package/out/recipes/si-bare-village.d.ts +32 -0
- package/out/recipes/si-bare-village.d.ts.map +1 -0
- package/out/recipes/si-bare-village.js +88 -0
- package/out/recipes/si-bare-village.js.map +1 -0
- package/out/recipes/street-affix.d.ts +89 -0
- package/out/recipes/street-affix.d.ts.map +1 -0
- package/out/recipes/street-affix.js +563 -0
- package/out/recipes/street-affix.js.map +1 -0
- package/out/recipes/street-bare.d.ts +25 -0
- package/out/recipes/street-bare.d.ts.map +1 -0
- package/out/recipes/street-bare.js +86 -0
- package/out/recipes/street-bare.js.map +1 -0
- package/out/recipes/street.d.ts +15 -0
- package/out/recipes/street.d.ts.map +1 -0
- package/out/recipes/street.js +69 -0
- package/out/recipes/street.js.map +1 -0
- package/out/recipes/sub-venue-sources.d.ts +229 -0
- package/out/recipes/sub-venue-sources.d.ts.map +1 -0
- package/out/recipes/sub-venue-sources.js +653 -0
- package/out/recipes/sub-venue-sources.js.map +1 -0
- package/out/recipes/sub-venue.d.ts +269 -0
- package/out/recipes/sub-venue.d.ts.map +1 -0
- package/out/recipes/sub-venue.js +725 -0
- package/out/recipes/sub-venue.js.map +1 -0
- package/out/recipes/trailing-region.d.ts +74 -0
- package/out/recipes/trailing-region.d.ts.map +1 -0
- package/out/recipes/trailing-region.js +157 -0
- package/out/recipes/trailing-region.js.map +1 -0
- package/out/recipes/unit.d.ts +29 -0
- package/out/recipes/unit.d.ts.map +1 -0
- package/out/recipes/unit.js +230 -0
- package/out/recipes/unit.js.map +1 -0
- package/out/runner.d.ts +130 -0
- package/out/runner.d.ts.map +1 -0
- package/out/runner.js +185 -0
- package/out/runner.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +63 -0
- package/out/synthesizers/anchor-absorption.d.ts.map +1 -0
- package/out/synthesizers/anchor-absorption.js +221 -0
- package/out/synthesizers/anchor-absorption.js.map +1 -0
- package/out/synthesizers/boundary-stress.d.ts +78 -0
- package/out/synthesizers/boundary-stress.d.ts.map +1 -0
- package/out/synthesizers/boundary-stress.js +455 -0
- package/out/synthesizers/boundary-stress.js.map +1 -0
- package/out/synthesizers/german.d.ts +115 -0
- package/out/synthesizers/german.d.ts.map +1 -0
- package/out/synthesizers/german.js +149 -0
- package/out/synthesizers/german.js.map +1 -0
- package/out/synthesizers/house-venue.d.ts +56 -0
- package/out/synthesizers/house-venue.d.ts.map +1 -0
- package/out/synthesizers/house-venue.js +247 -0
- package/out/synthesizers/house-venue.js.map +1 -0
- package/out/synthesizers/intersection.d.ts +52 -0
- package/out/synthesizers/intersection.d.ts.map +1 -0
- package/out/synthesizers/intersection.js +175 -0
- package/out/synthesizers/intersection.js.map +1 -0
- package/out/synthesizers/no-street.d.ts +72 -0
- package/out/synthesizers/no-street.d.ts.map +1 -0
- package/out/synthesizers/no-street.js +262 -0
- package/out/synthesizers/no-street.js.map +1 -0
- package/out/synthesizers/po-box.d.ts +108 -0
- package/out/synthesizers/po-box.d.ts.map +1 -0
- package/out/synthesizers/po-box.js +250 -0
- package/out/synthesizers/po-box.js.map +1 -0
- package/out/synthesizers/street.d.ts +54 -0
- package/out/synthesizers/street.d.ts.map +1 -0
- package/out/synthesizers/street.js +218 -0
- package/out/synthesizers/street.js.map +1 -0
- package/out/synthesizers/utils.d.ts +241 -0
- package/out/synthesizers/utils.d.ts.map +1 -0
- package/out/synthesizers/utils.js +776 -0
- package/out/synthesizers/utils.js.map +1 -0
- package/out/test-kit/corpus-recipe.d.ts +59 -0
- package/out/test-kit/corpus-recipe.d.ts.map +1 -0
- package/out/test-kit/corpus-recipe.js +39 -0
- package/out/test-kit/corpus-recipe.js.map +1 -0
- package/out/test-kit/index.d.ts +48 -0
- package/out/test-kit/index.d.ts.map +1 -0
- package/out/test-kit/index.js +78 -0
- package/out/test-kit/index.js.map +1 -0
- package/out/tools/align-slice.d.ts +7 -0
- package/out/tools/align-slice.d.ts.map +1 -0
- package/out/tools/align-slice.js +55 -0
- package/out/tools/align-slice.js.map +1 -0
- package/out/tools/audit.d.ts +29 -0
- package/out/tools/audit.d.ts.map +1 -0
- package/out/tools/audit.js +282 -0
- package/out/tools/audit.js.map +1 -0
- package/out/tools/corpus-stats.d.ts +44 -0
- package/out/tools/corpus-stats.d.ts.map +1 -0
- package/out/tools/corpus-stats.js +102 -0
- package/out/tools/corpus-stats.js.map +1 -0
- package/out/tools/fetch/ban.d.ts +31 -0
- package/out/tools/fetch/ban.d.ts.map +1 -0
- package/out/tools/fetch/ban.js +239 -0
- package/out/tools/fetch/ban.js.map +1 -0
- package/out/tools/fetch/download.d.ts +117 -0
- package/out/tools/fetch/download.d.ts.map +1 -0
- package/out/tools/fetch/download.js +160 -0
- package/out/tools/fetch/download.js.map +1 -0
- package/out/tools/fetch/geonames-dump.d.ts +91 -0
- package/out/tools/fetch/geonames-dump.d.ts.map +1 -0
- package/out/tools/fetch/geonames-dump.js +171 -0
- package/out/tools/fetch/geonames-dump.js.map +1 -0
- package/out/tools/fetch/geonames-postal.d.ts +76 -0
- package/out/tools/fetch/geonames-postal.d.ts.map +1 -0
- package/out/tools/fetch/geonames-postal.js +126 -0
- package/out/tools/fetch/geonames-postal.js.map +1 -0
- package/out/tools/fetch/hrsa.d.ts +18 -0
- package/out/tools/fetch/hrsa.d.ts.map +1 -0
- package/out/tools/fetch/hrsa.js +46 -0
- package/out/tools/fetch/hrsa.js.map +1 -0
- package/out/tools/fetch/imls-pls.d.ts +25 -0
- package/out/tools/fetch/imls-pls.d.ts.map +1 -0
- package/out/tools/fetch/imls-pls.js +108 -0
- package/out/tools/fetch/imls-pls.js.map +1 -0
- package/out/tools/fetch/index.d.ts +144 -0
- package/out/tools/fetch/index.d.ts.map +1 -0
- package/out/tools/fetch/index.js +143 -0
- package/out/tools/fetch/index.js.map +1 -0
- package/out/tools/fetch/nad.d.ts +70 -0
- package/out/tools/fetch/nad.d.ts.map +1 -0
- package/out/tools/fetch/nad.js +234 -0
- package/out/tools/fetch/nad.js.map +1 -0
- package/out/tools/fetch/nppes.d.ts +26 -0
- package/out/tools/fetch/nppes.d.ts.map +1 -0
- package/out/tools/fetch/nppes.js +126 -0
- package/out/tools/fetch/nppes.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +9 -0
- package/out/tools/fetch/openaddresses.d.ts.map +1 -0
- package/out/tools/fetch/openaddresses.js +279 -0
- package/out/tools/fetch/openaddresses.js.map +1 -0
- package/out/tools/fetch/ourairports.d.ts +45 -0
- package/out/tools/fetch/ourairports.d.ts.map +1 -0
- package/out/tools/fetch/ourairports.js +128 -0
- package/out/tools/fetch/ourairports.js.map +1 -0
- package/out/tools/fetch/ppd.d.ts.map +1 -0
- package/out/tools/fetch/ppd.js +85 -0
- package/out/tools/fetch/ppd.js.map +1 -0
- package/out/tools/fetch/state-hi-schools.d.ts +26 -0
- package/out/tools/fetch/state-hi-schools.d.ts.map +1 -0
- package/out/tools/fetch/state-hi-schools.js +112 -0
- package/out/tools/fetch/state-hi-schools.js.map +1 -0
- package/out/tools/fetch/state-sources.d.ts +26 -0
- package/out/tools/fetch/state-sources.d.ts.map +1 -0
- package/out/tools/fetch/state-sources.js +111 -0
- package/out/tools/fetch/state-sources.js.map +1 -0
- package/out/tools/fetch/tiger-full.d.ts +22 -0
- package/out/tools/fetch/tiger-full.d.ts.map +1 -0
- package/out/tools/fetch/tiger-full.js +217 -0
- package/out/tools/fetch/tiger-full.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +171 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.js +274 -0
- package/out/tools/fetch/wikidata-subvenue.js.map +1 -0
- package/out/tools/gb-title-case.d.ts.map +1 -0
- package/out/tools/gb-title-case.js.map +1 -0
- package/out/tools/golden-expand.d.ts +90 -0
- package/out/tools/golden-expand.d.ts.map +1 -0
- package/out/tools/golden-expand.js +406 -0
- package/out/tools/golden-expand.js.map +1 -0
- package/out/tools/golden-promote.d.ts.map +1 -0
- package/out/tools/golden-promote.js +240 -0
- package/out/tools/golden-promote.js.map +1 -0
- package/out/tools/golden-relabel-street.d.ts +196 -0
- package/out/tools/golden-relabel-street.d.ts.map +1 -0
- package/out/tools/golden-relabel-street.js +440 -0
- package/out/tools/golden-relabel-street.js.map +1 -0
- package/out/tools/index.d.ts +28 -0
- package/out/tools/index.d.ts.map +1 -0
- package/out/tools/index.js +28 -0
- package/out/tools/index.js.map +1 -0
- package/out/tools/ingest-csv.d.ts.map +1 -0
- package/out/tools/ingest-csv.js +265 -0
- package/out/tools/ingest-csv.js.map +1 -0
- package/out/tools/jsonl-to-parquet.d.ts +61 -0
- package/out/tools/jsonl-to-parquet.d.ts.map +1 -0
- package/out/tools/jsonl-to-parquet.js +150 -0
- package/out/tools/jsonl-to-parquet.js.map +1 -0
- package/out/tools/lint-slice-vocab.d.ts +90 -0
- package/out/tools/lint-slice-vocab.d.ts.map +1 -0
- package/out/tools/lint-slice-vocab.js +267 -0
- package/out/tools/lint-slice-vocab.js.map +1 -0
- package/out/tools/lint-slice.d.ts +93 -0
- package/out/tools/lint-slice.d.ts.map +1 -0
- package/out/tools/lint-slice.js +322 -0
- package/out/tools/lint-slice.js.map +1 -0
- package/out/tools/overlay-manifest.d.ts +39 -0
- package/out/tools/overlay-manifest.d.ts.map +1 -0
- package/out/tools/overlay-manifest.js +90 -0
- package/out/tools/overlay-manifest.js.map +1 -0
- package/out/tools/overture-subvenue.d.ts +112 -0
- package/out/tools/overture-subvenue.d.ts.map +1 -0
- package/out/tools/overture-subvenue.js +139 -0
- package/out/tools/overture-subvenue.js.map +1 -0
- package/out/tools/postcode-triples.d.ts +174 -0
- package/out/tools/postcode-triples.d.ts.map +1 -0
- package/out/tools/postcode-triples.js +292 -0
- package/out/tools/postcode-triples.js.map +1 -0
- package/out/tools/slice-kryptonite.d.ts +32 -0
- package/out/tools/slice-kryptonite.d.ts.map +1 -0
- package/out/tools/slice-kryptonite.js +99 -0
- package/out/tools/slice-kryptonite.js.map +1 -0
- package/out/tools/slice-translit.d.ts +51 -0
- package/out/tools/slice-translit.d.ts.map +1 -0
- package/out/tools/slice-translit.js +166 -0
- package/out/tools/slice-translit.js.map +1 -0
- package/out/tools/sub-venue/harvest.d.ts +100 -0
- package/out/tools/sub-venue/harvest.d.ts.map +1 -0
- package/out/tools/sub-venue/harvest.js +168 -0
- package/out/tools/sub-venue/harvest.js.map +1 -0
- package/out/tools/sub-venue/head-nouns.d.ts +50 -0
- package/out/tools/sub-venue/head-nouns.d.ts.map +1 -0
- package/out/tools/sub-venue/head-nouns.js +213 -0
- package/out/tools/sub-venue/head-nouns.js.map +1 -0
- package/out/tools/sub-venue/surfaces.d.ts +45 -0
- package/out/tools/sub-venue/surfaces.d.ts.map +1 -0
- package/out/tools/sub-venue/surfaces.js +77 -0
- package/out/tools/sub-venue/surfaces.js.map +1 -0
- package/out/tools/sub-venue/table.d.ts +229 -0
- package/out/tools/sub-venue/table.d.ts.map +1 -0
- package/out/tools/sub-venue/table.js +108 -0
- package/out/tools/sub-venue/table.js.map +1 -0
- package/out/tools/sub-venue/wikidata.d.ts +26 -0
- package/out/tools/sub-venue/wikidata.d.ts.map +1 -0
- package/out/tools/sub-venue/wikidata.js +62 -0
- package/out/tools/sub-venue/wikidata.js.map +1 -0
- package/out/tools/sub-venue-lexicon.d.ts +156 -0
- package/out/tools/sub-venue-lexicon.d.ts.map +1 -0
- package/out/tools/sub-venue-lexicon.js +283 -0
- package/out/tools/sub-venue-lexicon.js.map +1 -0
- package/out/tools/sub-venue-promotions.d.ts +94 -0
- package/out/tools/sub-venue-promotions.d.ts.map +1 -0
- package/out/tools/sub-venue-promotions.js +266 -0
- package/out/tools/sub-venue-promotions.js.map +1 -0
- package/out/types.d.ts +221 -0
- package/out/types.d.ts.map +1 -0
- package/out/types.js.map +1 -0
- package/out/utils/align.d.ts +93 -0
- package/out/utils/align.d.ts.map +1 -0
- package/out/utils/align.js +234 -0
- package/out/utils/align.js.map +1 -0
- package/out/utils/golden.d.ts +85 -0
- package/out/utils/golden.d.ts.map +1 -0
- package/out/utils/golden.js +127 -0
- package/out/utils/golden.js.map +1 -0
- package/out/utils/index.d.ts +14 -0
- package/out/utils/index.d.ts.map +1 -0
- package/out/utils/index.js +14 -0
- package/out/utils/index.js.map +1 -0
- package/out/utils/license.d.ts.map +1 -0
- package/out/utils/license.js.map +1 -0
- package/out/utils/parquet.d.ts +178 -0
- package/out/utils/parquet.d.ts.map +1 -0
- package/out/utils/parquet.js +371 -0
- package/out/utils/parquet.js.map +1 -0
- package/out/utils/slice-stats.d.ts +52 -0
- package/out/utils/slice-stats.d.ts.map +1 -0
- package/out/utils/slice-stats.js +58 -0
- package/out/utils/slice-stats.js.map +1 -0
- package/out/utils/split.d.ts +128 -0
- package/out/utils/split.d.ts.map +1 -0
- package/out/utils/split.js +204 -0
- package/out/utils/split.js.map +1 -0
- package/out/utils/tokenize.d.ts +64 -0
- package/out/utils/tokenize.d.ts.map +1 -0
- package/out/utils/tokenize.js +82 -0
- package/out/utils/tokenize.js.map +1 -0
- package/out/utils/wof-json.d.ts +113 -0
- package/out/utils/wof-json.d.ts.map +1 -0
- package/out/utils/wof-json.js +173 -0
- package/out/utils/wof-json.js.map +1 -0
- package/package.json +259 -194
- package/out/src/adapters/ban/adapter.d.ts.map +0 -1
- package/out/src/adapters/ban/adapter.js +0 -149
- package/out/src/adapters/ban/adapter.js.map +0 -1
- package/out/src/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/ban/street-decompose.js +0 -75
- package/out/src/adapters/ban/street-decompose.js.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.d.ts.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.js +0 -144
- package/out/src/adapters/fcc-bdc/adapter.js.map +0 -1
- package/out/src/adapters/geonames/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames/adapter.js +0 -176
- package/out/src/adapters/geonames/adapter.js.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.d.ts +0 -41
- package/out/src/adapters/geonames-postal/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.js +0 -104
- package/out/src/adapters/geonames-postal/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/adapter.d.ts +0 -49
- package/out/src/adapters/gnaf/adapter.d.ts.map +0 -1
- package/out/src/adapters/gnaf/adapter.js +0 -124
- package/out/src/adapters/gnaf/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/assemble.d.ts +0 -65
- package/out/src/adapters/gnaf/assemble.d.ts.map +0 -1
- package/out/src/adapters/gnaf/assemble.js +0 -154
- package/out/src/adapters/gnaf/assemble.js.map +0 -1
- package/out/src/adapters/index.d.ts +0 -51
- package/out/src/adapters/index.d.ts.map +0 -1
- package/out/src/adapters/index.js +0 -95
- package/out/src/adapters/index.js.map +0 -1
- package/out/src/adapters/openaddresses/adapter.d.ts.map +0 -1
- package/out/src/adapters/openaddresses/adapter.js +0 -186
- package/out/src/adapters/openaddresses/adapter.js.map +0 -1
- package/out/src/adapters/overture/adapter.d.ts +0 -48
- package/out/src/adapters/overture/adapter.d.ts.map +0 -1
- package/out/src/adapters/overture/adapter.js +0 -125
- package/out/src/adapters/overture/adapter.js.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.d.ts +0 -47
- package/out/src/adapters/state-hi-schools/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.js +0 -133
- package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.d.ts.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.js +0 -140
- package/out/src/adapters/synth-po-box/adapter.js.map +0 -1
- package/out/src/adapters/tiger/adapter.d.ts +0 -55
- package/out/src/adapters/tiger/adapter.d.ts.map +0 -1
- package/out/src/adapters/tiger/adapter.js +0 -201
- package/out/src/adapters/tiger/adapter.js.map +0 -1
- package/out/src/adapters/tiger/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/tiger/street-decompose.js +0 -90
- package/out/src/adapters/tiger/street-decompose.js.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -47
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +0 -139
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts +0 -36
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.js +0 -114
- package/out/src/adapters/usgov-imls-pls/adapter.js.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.js +0 -124
- package/out/src/adapters/usgov-irs-bmf/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.d.ts +0 -48
- package/out/src/adapters/usgov-nad/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.js +0 -252
- package/out/src/adapters/usgov-nad/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.js +0 -116
- package/out/src/adapters/usgov-nppes/adapter.js.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -156
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
- package/out/src/adapters/utils/index.d.ts +0 -150
- package/out/src/adapters/utils/index.d.ts.map +0 -1
- package/out/src/adapters/utils/index.js +0 -159
- package/out/src/adapters/utils/index.js.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.js +0 -164
- package/out/src/adapters/wof-admin-jp/adapter.js.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.d.ts +0 -82
- package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.js +0 -224
- package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
- package/out/src/adapters/wof-json-rows.d.ts +0 -32
- package/out/src/adapters/wof-json-rows.d.ts.map +0 -1
- package/out/src/adapters/wof-json-rows.js +0 -45
- package/out/src/adapters/wof-json-rows.js.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -65
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.js +0 -160
- package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
- package/out/src/build.d.ts +0 -132
- package/out/src/build.d.ts.map +0 -1
- package/out/src/build.js +0 -251
- package/out/src/build.js.map +0 -1
- package/out/src/codex/us-fips-state.d.ts.map +0 -1
- package/out/src/codex/us-fips-state.js.map +0 -1
- package/out/src/index.d.ts +0 -14
- package/out/src/index.d.ts.map +0 -1
- package/out/src/index.js +0 -14
- package/out/src/index.js.map +0 -1
- package/out/src/name-prone-us-suffixes.d.ts +0 -12
- package/out/src/name-prone-us-suffixes.d.ts.map +0 -1
- package/out/src/name-prone-us-suffixes.js +0 -12
- package/out/src/name-prone-us-suffixes.js.map +0 -1
- package/out/src/parquet-wrapper/index.d.ts +0 -9
- package/out/src/parquet-wrapper/index.d.ts.map +0 -1
- package/out/src/parquet-wrapper/index.js +0 -9
- package/out/src/parquet-wrapper/index.js.map +0 -1
- package/out/src/parquet-wrapper/reader.d.ts +0 -34
- package/out/src/parquet-wrapper/reader.d.ts.map +0 -1
- package/out/src/parquet-wrapper/reader.js +0 -69
- package/out/src/parquet-wrapper/reader.js.map +0 -1
- package/out/src/parquet-wrapper/schema.d.ts +0 -49
- package/out/src/parquet-wrapper/schema.d.ts.map +0 -1
- package/out/src/parquet-wrapper/schema.js +0 -55
- package/out/src/parquet-wrapper/schema.js.map +0 -1
- package/out/src/parquet-wrapper/writer.d.ts +0 -46
- package/out/src/parquet-wrapper/writer.d.ts.map +0 -1
- package/out/src/parquet-wrapper/writer.js +0 -76
- package/out/src/parquet-wrapper/writer.js.map +0 -1
- package/out/src/runner.d.ts +0 -126
- package/out/src/runner.d.ts.map +0 -1
- package/out/src/runner.js +0 -189
- package/out/src/runner.js.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.d.ts +0 -20
- package/out/src/shard-recipes/anchor-absorption.d.ts.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.js +0 -82
- package/out/src/shard-recipes/anchor-absorption.js.map +0 -1
- package/out/src/shard-recipes/bare-country.d.ts +0 -25
- package/out/src/shard-recipes/bare-country.d.ts.map +0 -1
- package/out/src/shard-recipes/bare-country.js +0 -87
- package/out/src/shard-recipes/bare-country.js.map +0 -1
- package/out/src/shard-recipes/boundary-stress.d.ts +0 -20
- package/out/src/shard-recipes/boundary-stress.d.ts.map +0 -1
- package/out/src/shard-recipes/boundary-stress.js +0 -83
- package/out/src/shard-recipes/boundary-stress.js.map +0 -1
- package/out/src/shard-recipes/country-balanced.d.ts +0 -32
- package/out/src/shard-recipes/country-balanced.d.ts.map +0 -1
- package/out/src/shard-recipes/country-balanced.js +0 -406
- package/out/src/shard-recipes/country-balanced.js.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts +0 -22
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.js +0 -100
- package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.d.ts +0 -38
- package/out/src/shard-recipes/fr-admin-split.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.js +0 -188
- package/out/src/shard-recipes/fr-admin-split.js.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.d.ts +0 -28
- package/out/src/shard-recipes/fr-bare-street.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.js +0 -143
- package/out/src/shard-recipes/fr-bare-street.js.map +0 -1
- package/out/src/shard-recipes/fr-fragment.d.ts +0 -77
- package/out/src/shard-recipes/fr-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-fragment.js +0 -276
- package/out/src/shard-recipes/fr-fragment.js.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.d.ts +0 -32
- package/out/src/shard-recipes/fr-lieudit.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.js +0 -226
- package/out/src/shard-recipes/fr-lieudit.js.map +0 -1
- package/out/src/shard-recipes/fr-order.d.ts +0 -38
- package/out/src/shard-recipes/fr-order.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-order.js +0 -208
- package/out/src/shard-recipes/fr-order.js.map +0 -1
- package/out/src/shard-recipes/german.d.ts +0 -23
- package/out/src/shard-recipes/german.d.ts.map +0 -1
- package/out/src/shard-recipes/german.js +0 -132
- package/out/src/shard-recipes/german.js.map +0 -1
- package/out/src/shard-recipes/house-venue.d.ts +0 -18
- package/out/src/shard-recipes/house-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/house-venue.js +0 -74
- package/out/src/shard-recipes/house-venue.js.map +0 -1
- package/out/src/shard-recipes/index.d.ts +0 -24
- package/out/src/shard-recipes/index.d.ts.map +0 -1
- package/out/src/shard-recipes/index.js +0 -89
- package/out/src/shard-recipes/index.js.map +0 -1
- package/out/src/shard-recipes/intersection.d.ts +0 -42
- package/out/src/shard-recipes/intersection.d.ts.map +0 -1
- package/out/src/shard-recipes/intersection.js +0 -460
- package/out/src/shard-recipes/intersection.js.map +0 -1
- package/out/src/shard-recipes/locale.d.ts +0 -135
- package/out/src/shard-recipes/locale.d.ts.map +0 -1
- package/out/src/shard-recipes/locale.js +0 -459
- package/out/src/shard-recipes/locale.js.map +0 -1
- package/out/src/shard-recipes/nl-postcode.d.ts +0 -26
- package/out/src/shard-recipes/nl-postcode.d.ts.map +0 -1
- package/out/src/shard-recipes/nl-postcode.js +0 -102
- package/out/src/shard-recipes/nl-postcode.js.map +0 -1
- package/out/src/shard-recipes/no-fragment.d.ts +0 -43
- package/out/src/shard-recipes/no-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/no-fragment.js +0 -188
- package/out/src/shard-recipes/no-fragment.js.map +0 -1
- package/out/src/shard-recipes/no-street-led.d.ts +0 -24
- package/out/src/shard-recipes/no-street-led.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street-led.js +0 -121
- package/out/src/shard-recipes/no-street-led.js.map +0 -1
- package/out/src/shard-recipes/no-street.d.ts +0 -18
- package/out/src/shard-recipes/no-street.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street.js +0 -72
- package/out/src/shard-recipes/no-street.js.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.d.ts +0 -38
- package/out/src/shard-recipes/po-box-cedex.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.js +0 -726
- package/out/src/shard-recipes/po-box-cedex.js.map +0 -1
- package/out/src/shard-recipes/po-box.d.ts +0 -17
- package/out/src/shard-recipes/po-box.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box.js +0 -101
- package/out/src/shard-recipes/po-box.js.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts +0 -47
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.js +0 -125
- package/out/src/shard-recipes/reviewed-postcode-tail.js.map +0 -1
- package/out/src/shard-recipes/scaffold.d.ts +0 -246
- package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
- package/out/src/shard-recipes/scaffold.js +0 -137
- package/out/src/shard-recipes/scaffold.js.map +0 -1
- package/out/src/shard-recipes/si-bare-village.d.ts +0 -32
- package/out/src/shard-recipes/si-bare-village.d.ts.map +0 -1
- package/out/src/shard-recipes/si-bare-village.js +0 -88
- package/out/src/shard-recipes/si-bare-village.js.map +0 -1
- package/out/src/shard-recipes/street-affix.d.ts +0 -89
- package/out/src/shard-recipes/street-affix.d.ts.map +0 -1
- package/out/src/shard-recipes/street-affix.js +0 -578
- package/out/src/shard-recipes/street-affix.js.map +0 -1
- package/out/src/shard-recipes/street-bare.d.ts +0 -25
- package/out/src/shard-recipes/street-bare.d.ts.map +0 -1
- package/out/src/shard-recipes/street-bare.js +0 -86
- package/out/src/shard-recipes/street-bare.js.map +0 -1
- package/out/src/shard-recipes/street.d.ts +0 -15
- package/out/src/shard-recipes/street.d.ts.map +0 -1
- package/out/src/shard-recipes/street.js +0 -69
- package/out/src/shard-recipes/street.js.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.d.ts +0 -228
- package/out/src/shard-recipes/sub-venue-sources.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.js +0 -664
- package/out/src/shard-recipes/sub-venue-sources.js.map +0 -1
- package/out/src/shard-recipes/sub-venue.d.ts +0 -269
- package/out/src/shard-recipes/sub-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue.js +0 -710
- package/out/src/shard-recipes/sub-venue.js.map +0 -1
- package/out/src/shard-recipes/trailing-region.d.ts +0 -74
- package/out/src/shard-recipes/trailing-region.d.ts.map +0 -1
- package/out/src/shard-recipes/trailing-region.js +0 -157
- package/out/src/shard-recipes/trailing-region.js.map +0 -1
- package/out/src/shard-recipes/unit.d.ts +0 -29
- package/out/src/shard-recipes/unit.d.ts.map +0 -1
- package/out/src/shard-recipes/unit.js +0 -243
- package/out/src/shard-recipes/unit.js.map +0 -1
- package/out/src/synthesizers/anchor-absorption.d.ts +0 -63
- package/out/src/synthesizers/anchor-absorption.d.ts.map +0 -1
- package/out/src/synthesizers/anchor-absorption.js +0 -223
- package/out/src/synthesizers/anchor-absorption.js.map +0 -1
- package/out/src/synthesizers/boundary-stress.d.ts +0 -78
- package/out/src/synthesizers/boundary-stress.d.ts.map +0 -1
- package/out/src/synthesizers/boundary-stress.js +0 -455
- package/out/src/synthesizers/boundary-stress.js.map +0 -1
- package/out/src/synthesizers/german.d.ts +0 -107
- package/out/src/synthesizers/german.d.ts.map +0 -1
- package/out/src/synthesizers/german.js +0 -148
- package/out/src/synthesizers/german.js.map +0 -1
- package/out/src/synthesizers/house-venue.d.ts +0 -56
- package/out/src/synthesizers/house-venue.d.ts.map +0 -1
- package/out/src/synthesizers/house-venue.js +0 -267
- package/out/src/synthesizers/house-venue.js.map +0 -1
- package/out/src/synthesizers/intersection.d.ts +0 -52
- package/out/src/synthesizers/intersection.d.ts.map +0 -1
- package/out/src/synthesizers/intersection.js +0 -175
- package/out/src/synthesizers/intersection.js.map +0 -1
- package/out/src/synthesizers/no-street.d.ts +0 -72
- package/out/src/synthesizers/no-street.d.ts.map +0 -1
- package/out/src/synthesizers/no-street.js +0 -282
- package/out/src/synthesizers/no-street.js.map +0 -1
- package/out/src/synthesizers/po-box.d.ts +0 -104
- package/out/src/synthesizers/po-box.d.ts.map +0 -1
- package/out/src/synthesizers/po-box.js +0 -266
- package/out/src/synthesizers/po-box.js.map +0 -1
- package/out/src/synthesizers/street.d.ts +0 -54
- package/out/src/synthesizers/street.d.ts.map +0 -1
- package/out/src/synthesizers/street.js +0 -221
- package/out/src/synthesizers/street.js.map +0 -1
- package/out/src/synthesizers/utils.d.ts +0 -203
- package/out/src/synthesizers/utils.d.ts.map +0 -1
- package/out/src/synthesizers/utils.js +0 -708
- package/out/src/synthesizers/utils.js.map +0 -1
- package/out/src/tools/align-shard.d.ts +0 -8
- package/out/src/tools/align-shard.d.ts.map +0 -1
- package/out/src/tools/align-shard.js +0 -56
- package/out/src/tools/align-shard.js.map +0 -1
- package/out/src/tools/audit.d.ts +0 -28
- package/out/src/tools/audit.d.ts.map +0 -1
- package/out/src/tools/audit.js +0 -285
- package/out/src/tools/audit.js.map +0 -1
- package/out/src/tools/corpus-stats.d.ts +0 -44
- package/out/src/tools/corpus-stats.d.ts.map +0 -1
- package/out/src/tools/corpus-stats.js +0 -138
- package/out/src/tools/corpus-stats.js.map +0 -1
- package/out/src/tools/fetch/ban.d.ts +0 -31
- package/out/src/tools/fetch/ban.d.ts.map +0 -1
- package/out/src/tools/fetch/ban.js +0 -239
- package/out/src/tools/fetch/ban.js.map +0 -1
- package/out/src/tools/fetch/download.d.ts +0 -78
- package/out/src/tools/fetch/download.d.ts.map +0 -1
- package/out/src/tools/fetch/download.js +0 -116
- package/out/src/tools/fetch/download.js.map +0 -1
- package/out/src/tools/fetch/geonames-dump.d.ts +0 -87
- package/out/src/tools/fetch/geonames-dump.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-dump.js +0 -178
- package/out/src/tools/fetch/geonames-dump.js.map +0 -1
- package/out/src/tools/fetch/geonames-postal.d.ts +0 -76
- package/out/src/tools/fetch/geonames-postal.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-postal.js +0 -125
- package/out/src/tools/fetch/geonames-postal.js.map +0 -1
- package/out/src/tools/fetch/hrsa.d.ts +0 -18
- package/out/src/tools/fetch/hrsa.d.ts.map +0 -1
- package/out/src/tools/fetch/hrsa.js +0 -46
- package/out/src/tools/fetch/hrsa.js.map +0 -1
- package/out/src/tools/fetch/imls-pls.d.ts +0 -25
- package/out/src/tools/fetch/imls-pls.d.ts.map +0 -1
- package/out/src/tools/fetch/imls-pls.js +0 -108
- package/out/src/tools/fetch/imls-pls.js.map +0 -1
- package/out/src/tools/fetch/index.d.ts +0 -144
- package/out/src/tools/fetch/index.d.ts.map +0 -1
- package/out/src/tools/fetch/index.js +0 -143
- package/out/src/tools/fetch/index.js.map +0 -1
- package/out/src/tools/fetch/nad.d.ts +0 -70
- package/out/src/tools/fetch/nad.d.ts.map +0 -1
- package/out/src/tools/fetch/nad.js +0 -234
- package/out/src/tools/fetch/nad.js.map +0 -1
- package/out/src/tools/fetch/nppes.d.ts +0 -26
- package/out/src/tools/fetch/nppes.d.ts.map +0 -1
- package/out/src/tools/fetch/nppes.js +0 -126
- package/out/src/tools/fetch/nppes.js.map +0 -1
- package/out/src/tools/fetch/openaddresses.d.ts +0 -61
- package/out/src/tools/fetch/openaddresses.d.ts.map +0 -1
- package/out/src/tools/fetch/openaddresses.js +0 -317
- package/out/src/tools/fetch/openaddresses.js.map +0 -1
- package/out/src/tools/fetch/ourairports.d.ts +0 -45
- package/out/src/tools/fetch/ourairports.d.ts.map +0 -1
- package/out/src/tools/fetch/ourairports.js +0 -128
- package/out/src/tools/fetch/ourairports.js.map +0 -1
- package/out/src/tools/fetch/ppd.d.ts.map +0 -1
- package/out/src/tools/fetch/ppd.js +0 -100
- package/out/src/tools/fetch/ppd.js.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.d.ts +0 -25
- package/out/src/tools/fetch/state-hi-schools.d.ts.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.js +0 -162
- package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
- package/out/src/tools/fetch/state-sources.d.ts +0 -26
- package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
- package/out/src/tools/fetch/state-sources.js +0 -111
- package/out/src/tools/fetch/state-sources.js.map +0 -1
- package/out/src/tools/fetch/tiger-full.d.ts +0 -42
- package/out/src/tools/fetch/tiger-full.d.ts.map +0 -1
- package/out/src/tools/fetch/tiger-full.js +0 -248
- package/out/src/tools/fetch/tiger-full.js.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.d.ts +0 -171
- package/out/src/tools/fetch/wikidata-subvenue.d.ts.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.js +0 -275
- package/out/src/tools/fetch/wikidata-subvenue.js.map +0 -1
- package/out/src/tools/gb-title-case.d.ts.map +0 -1
- package/out/src/tools/gb-title-case.js.map +0 -1
- package/out/src/tools/golden-expand.d.ts +0 -90
- package/out/src/tools/golden-expand.d.ts.map +0 -1
- package/out/src/tools/golden-expand.js +0 -413
- package/out/src/tools/golden-expand.js.map +0 -1
- package/out/src/tools/golden-promote.d.ts.map +0 -1
- package/out/src/tools/golden-promote.js +0 -244
- package/out/src/tools/golden-promote.js.map +0 -1
- package/out/src/tools/golden-relabel-street.d.ts +0 -196
- package/out/src/tools/golden-relabel-street.d.ts.map +0 -1
- package/out/src/tools/golden-relabel-street.js +0 -440
- package/out/src/tools/golden-relabel-street.js.map +0 -1
- package/out/src/tools/index.d.ts +0 -28
- package/out/src/tools/index.d.ts.map +0 -1
- package/out/src/tools/index.js +0 -28
- package/out/src/tools/index.js.map +0 -1
- package/out/src/tools/ingest-csv.d.ts.map +0 -1
- package/out/src/tools/ingest-csv.js +0 -296
- package/out/src/tools/ingest-csv.js.map +0 -1
- package/out/src/tools/jsonl-to-parquet.d.ts +0 -61
- package/out/src/tools/jsonl-to-parquet.d.ts.map +0 -1
- package/out/src/tools/jsonl-to-parquet.js +0 -164
- package/out/src/tools/jsonl-to-parquet.js.map +0 -1
- package/out/src/tools/lint-shard-vocab.d.ts +0 -90
- package/out/src/tools/lint-shard-vocab.d.ts.map +0 -1
- package/out/src/tools/lint-shard-vocab.js +0 -281
- package/out/src/tools/lint-shard-vocab.js.map +0 -1
- package/out/src/tools/lint-shard.d.ts +0 -93
- package/out/src/tools/lint-shard.d.ts.map +0 -1
- package/out/src/tools/lint-shard.js +0 -354
- package/out/src/tools/lint-shard.js.map +0 -1
- package/out/src/tools/overlay-manifest.d.ts +0 -39
- package/out/src/tools/overlay-manifest.d.ts.map +0 -1
- package/out/src/tools/overlay-manifest.js +0 -98
- package/out/src/tools/overlay-manifest.js.map +0 -1
- package/out/src/tools/overture-subvenue.d.ts +0 -112
- package/out/src/tools/overture-subvenue.d.ts.map +0 -1
- package/out/src/tools/overture-subvenue.js +0 -144
- package/out/src/tools/overture-subvenue.js.map +0 -1
- package/out/src/tools/postcode-triples.d.ts +0 -175
- package/out/src/tools/postcode-triples.d.ts.map +0 -1
- package/out/src/tools/postcode-triples.js +0 -304
- package/out/src/tools/postcode-triples.js.map +0 -1
- package/out/src/tools/shard-kryptonite.d.ts +0 -32
- package/out/src/tools/shard-kryptonite.d.ts.map +0 -1
- package/out/src/tools/shard-kryptonite.js +0 -100
- package/out/src/tools/shard-kryptonite.js.map +0 -1
- package/out/src/tools/shard-translit.d.ts +0 -51
- package/out/src/tools/shard-translit.d.ts.map +0 -1
- package/out/src/tools/shard-translit.js +0 -175
- package/out/src/tools/shard-translit.js.map +0 -1
- package/out/src/tools/sub-venue/harvest.d.ts +0 -100
- package/out/src/tools/sub-venue/harvest.d.ts.map +0 -1
- package/out/src/tools/sub-venue/harvest.js +0 -168
- package/out/src/tools/sub-venue/harvest.js.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.d.ts +0 -50
- package/out/src/tools/sub-venue/head-nouns.d.ts.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.js +0 -210
- package/out/src/tools/sub-venue/head-nouns.js.map +0 -1
- package/out/src/tools/sub-venue/surfaces.d.ts +0 -45
- package/out/src/tools/sub-venue/surfaces.d.ts.map +0 -1
- package/out/src/tools/sub-venue/surfaces.js +0 -77
- package/out/src/tools/sub-venue/surfaces.js.map +0 -1
- package/out/src/tools/sub-venue/table.d.ts +0 -229
- package/out/src/tools/sub-venue/table.d.ts.map +0 -1
- package/out/src/tools/sub-venue/table.js +0 -108
- package/out/src/tools/sub-venue/table.js.map +0 -1
- package/out/src/tools/sub-venue/wikidata.d.ts +0 -26
- package/out/src/tools/sub-venue/wikidata.d.ts.map +0 -1
- package/out/src/tools/sub-venue/wikidata.js +0 -62
- package/out/src/tools/sub-venue/wikidata.js.map +0 -1
- package/out/src/tools/sub-venue-lexicon.d.ts +0 -156
- package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
- package/out/src/tools/sub-venue-lexicon.js +0 -282
- package/out/src/tools/sub-venue-lexicon.js.map +0 -1
- package/out/src/tools/sub-venue-promotions.d.ts +0 -94
- package/out/src/tools/sub-venue-promotions.d.ts.map +0 -1
- package/out/src/tools/sub-venue-promotions.js +0 -266
- package/out/src/tools/sub-venue-promotions.js.map +0 -1
- package/out/src/types.d.ts +0 -221
- package/out/src/types.d.ts.map +0 -1
- package/out/src/types.js.map +0 -1
- package/out/src/utils/align.d.ts +0 -93
- package/out/src/utils/align.d.ts.map +0 -1
- package/out/src/utils/align.js +0 -234
- package/out/src/utils/align.js.map +0 -1
- package/out/src/utils/golden.d.ts +0 -69
- package/out/src/utils/golden.d.ts.map +0 -1
- package/out/src/utils/golden.js +0 -127
- package/out/src/utils/golden.js.map +0 -1
- package/out/src/utils/index.d.ts +0 -14
- package/out/src/utils/index.d.ts.map +0 -1
- package/out/src/utils/index.js +0 -14
- package/out/src/utils/index.js.map +0 -1
- package/out/src/utils/license.d.ts.map +0 -1
- package/out/src/utils/license.js.map +0 -1
- package/out/src/utils/parquet.d.ts +0 -162
- package/out/src/utils/parquet.d.ts.map +0 -1
- package/out/src/utils/parquet.js +0 -262
- package/out/src/utils/parquet.js.map +0 -1
- package/out/src/utils/split.d.ts +0 -127
- package/out/src/utils/split.d.ts.map +0 -1
- package/out/src/utils/split.js +0 -204
- package/out/src/utils/split.js.map +0 -1
- package/out/src/utils/tokenize.d.ts +0 -56
- package/out/src/utils/tokenize.d.ts.map +0 -1
- package/out/src/utils/tokenize.js +0 -48
- package/out/src/utils/tokenize.js.map +0 -1
- package/out/src/utils/wof-json.d.ts +0 -109
- package/out/src/utils/wof-json.d.ts.map +0 -1
- package/out/src/utils/wof-json.js +0 -173
- package/out/src/utils/wof-json.js.map +0 -1
- package/src/adapters/ban/adapter.ts +0 -191
- package/src/adapters/ban/street-decompose.ts +0 -96
- package/src/adapters/fcc-bdc/adapter.ts +0 -174
- package/src/adapters/geonames/adapter.ts +0 -200
- package/src/adapters/geonames-postal/adapter.ts +0 -119
- package/src/adapters/gnaf/adapter.ts +0 -149
- package/src/adapters/gnaf/assemble.ts +0 -226
- package/src/adapters/index.ts +0 -149
- package/src/adapters/openaddresses/adapter.ts +0 -251
- package/src/adapters/overture/adapter.ts +0 -162
- package/src/adapters/state-hi-schools/adapter.ts +0 -164
- package/src/adapters/synth-po-box/adapter.ts +0 -204
- package/src/adapters/tiger/adapter.ts +0 -253
- package/src/adapters/tiger/street-decompose.ts +0 -111
- package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -183
- package/src/adapters/usgov-imls-pls/adapter.ts +0 -143
- package/src/adapters/usgov-irs-bmf/adapter.ts +0 -163
- package/src/adapters/usgov-nad/adapter.ts +0 -348
- package/src/adapters/usgov-nppes/adapter.ts +0 -159
- package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -204
- package/src/adapters/utils/index.ts +0 -233
- package/src/adapters/wof-admin-jp/adapter.ts +0 -216
- package/src/adapters/wof-admin-json/adapter.ts +0 -256
- package/src/adapters/wof-json-rows.ts +0 -79
- package/src/adapters/wof-postalcode-json/adapter.ts +0 -183
- package/src/build.ts +0 -386
- package/src/index.ts +0 -14
- package/src/name-prone-us-suffixes.ts +0 -12
- package/src/parquet-wrapper/index.ts +0 -9
- package/src/parquet-wrapper/reader.ts +0 -97
- package/src/parquet-wrapper/schema.ts +0 -88
- package/src/parquet-wrapper/writer.ts +0 -110
- package/src/runner.ts +0 -317
- package/src/shard-recipes/anchor-absorption.ts +0 -103
- package/src/shard-recipes/bare-country.ts +0 -95
- package/src/shard-recipes/boundary-stress.ts +0 -101
- package/src/shard-recipes/country-balanced.ts +0 -524
- package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -111
- package/src/shard-recipes/fr-admin-split.ts +0 -239
- package/src/shard-recipes/fr-bare-street.ts +0 -170
- package/src/shard-recipes/fr-fragment.ts +0 -332
- package/src/shard-recipes/fr-lieudit.ts +0 -302
- package/src/shard-recipes/fr-order.ts +0 -258
- package/src/shard-recipes/german.ts +0 -170
- package/src/shard-recipes/house-venue.ts +0 -88
- package/src/shard-recipes/index.ts +0 -95
- package/src/shard-recipes/intersection.ts +0 -630
- package/src/shard-recipes/locale.ts +0 -599
- package/src/shard-recipes/nl-postcode.ts +0 -115
- package/src/shard-recipes/no-fragment.ts +0 -219
- package/src/shard-recipes/no-street-led.ts +0 -143
- package/src/shard-recipes/no-street.ts +0 -86
- package/src/shard-recipes/po-box-cedex.ts +0 -920
- package/src/shard-recipes/po-box.ts +0 -119
- package/src/shard-recipes/reviewed-postcode-tail.ts +0 -189
- package/src/shard-recipes/scaffold.ts +0 -360
- package/src/shard-recipes/si-bare-village.ts +0 -97
- package/src/shard-recipes/street-affix.ts +0 -826
- package/src/shard-recipes/street-bare.ts +0 -101
- package/src/shard-recipes/street.ts +0 -82
- package/src/shard-recipes/sub-venue-sources.ts +0 -885
- package/src/shard-recipes/sub-venue.ts +0 -984
- package/src/shard-recipes/trailing-region.ts +0 -183
- package/src/shard-recipes/unit.ts +0 -321
- package/src/synthesizers/anchor-absorption.ts +0 -290
- package/src/synthesizers/boundary-stress.ts +0 -531
- package/src/synthesizers/german.ts +0 -251
- package/src/synthesizers/house-venue.ts +0 -330
- package/src/synthesizers/intersection.ts +0 -232
- package/src/synthesizers/no-street.ts +0 -349
- package/src/synthesizers/po-box.ts +0 -339
- package/src/synthesizers/street.ts +0 -274
- package/src/synthesizers/utils.ts +0 -903
- package/src/tools/align-shard.ts +0 -70
- package/src/tools/audit.ts +0 -399
- package/src/tools/corpus-stats.ts +0 -184
- package/src/tools/fetch/ban.ts +0 -290
- package/src/tools/fetch/download.ts +0 -176
- package/src/tools/fetch/geonames-dump.ts +0 -267
- package/src/tools/fetch/geonames-postal.ts +0 -180
- package/src/tools/fetch/hrsa.ts +0 -68
- package/src/tools/fetch/imls-pls.ts +0 -158
- package/src/tools/fetch/index.ts +0 -147
- package/src/tools/fetch/nad.ts +0 -342
- package/src/tools/fetch/nppes.ts +0 -174
- package/src/tools/fetch/openaddresses.ts +0 -404
- package/src/tools/fetch/ourairports.ts +0 -171
- package/src/tools/fetch/ppd.ts +0 -137
- package/src/tools/fetch/state-hi-schools.ts +0 -208
- package/src/tools/fetch/state-sources.ts +0 -155
- package/src/tools/fetch/tiger-full.ts +0 -354
- package/src/tools/fetch/wikidata-subvenue.ts +0 -386
- package/src/tools/golden-expand.ts +0 -584
- package/src/tools/golden-promote.ts +0 -353
- package/src/tools/golden-relabel-street.ts +0 -685
- package/src/tools/index.ts +0 -28
- package/src/tools/ingest-csv.ts +0 -422
- package/src/tools/jsonl-to-parquet.ts +0 -221
- package/src/tools/lint-shard-vocab.ts +0 -409
- package/src/tools/lint-shard.ts +0 -543
- package/src/tools/overlay-manifest.ts +0 -157
- package/src/tools/overture-subvenue.ts +0 -215
- package/src/tools/postcode-triples.ts +0 -375
- package/src/tools/shard-kryptonite.ts +0 -139
- package/src/tools/shard-translit.ts +0 -245
- package/src/tools/sub-venue/harvest.ts +0 -235
- package/src/tools/sub-venue/head-nouns.ts +0 -242
- package/src/tools/sub-venue/surfaces.ts +0 -95
- package/src/tools/sub-venue/table.ts +0 -281
- package/src/tools/sub-venue/wikidata.ts +0 -85
- package/src/tools/sub-venue-lexicon.ts +0 -431
- package/src/tools/sub-venue-promotions.ts +0 -330
- package/src/types.ts +0 -247
- package/src/utils/align.ts +0 -331
- package/src/utils/golden.ts +0 -176
- package/src/utils/index.ts +0 -14
- package/src/utils/parquet.ts +0 -391
- package/src/utils/split.ts +0 -279
- package/src/utils/tokenize.ts +0 -78
- package/src/utils/wof-json.ts +0 -244
- /package/{src → lib}/adapters/state-ia-contractors/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-ny-notaries/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-tx-notaries/adapter.ts +0 -0
- /package/{src → lib}/codex/us-fips-state.ts +0 -0
- /package/{src → lib}/tools/gb-title-case.ts +0 -0
- /package/{src → lib}/utils/license.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/fcc-bdc/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/geonames/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/openaddresses/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/synth-po-box/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/tiger/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-nppes/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-samhsa-treatment-locator/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/wof-admin-jp/adapter.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.js +0 -0
- /package/out/{src/tools → tools}/fetch/ppd.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.js +0 -0
- /package/out/{src/tools → tools}/golden-promote.d.ts +0 -0
- /package/out/{src/tools → tools}/ingest-csv.d.ts +0 -0
- /package/out/{src/types.js → types.js} +0 -0
- /package/out/{src/utils → utils}/license.d.ts +0 -0
- /package/out/{src/utils → utils}/license.js +0 -0
|
@@ -1,128 +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 { mkdirSync } from "node:fs";
|
|
39
|
-
import { join } from "node:path";
|
|
40
|
-
import { APIClient } from "@mailwoman/core/api";
|
|
41
|
-
import { sha256File } from "@mailwoman/core/utils";
|
|
42
|
-
import { downloadToFile, writeManifest } from "./download.js";
|
|
43
|
-
const SLUG = "ourairports";
|
|
44
|
-
/**
|
|
45
|
-
* The GitHub Pages mirror the project itself publishes. `ourairports.com/data/*.csv` 302s here, so pointing at the
|
|
46
|
-
* mirror directly saves a redirect and is the URL the project's own README gives.
|
|
47
|
-
*/
|
|
48
|
-
const BASE_URL = "https://davidmegginson.github.io/ourairports-data";
|
|
49
|
-
/**
|
|
50
|
-
* The files worth having, and why each one.
|
|
51
|
-
*
|
|
52
|
-
* `airports.csv` is the payload. The other three are small joins that turn its codes into text: `countries.csv` and
|
|
53
|
-
* `regions.csv` expand `iso_country`/`iso_region` into names (a corpus line needs "Germany", not "DE"), and
|
|
54
|
-
* `runways.csv` is the only file carrying per-airport sub-structure of any kind — runway designators, which are NOT
|
|
55
|
-
* sub-venue designators (nobody addresses mail to a runway) but are worth having on disk as the negative class if the
|
|
56
|
-
* shard ever needs one.
|
|
57
|
-
*/
|
|
58
|
-
const FILES = ["airports.csv", "countries.csv", "regions.csv", "runways.csv"];
|
|
59
|
-
/**
|
|
60
|
-
* Read the upstream `Last-Modified` with a HEAD. Returns `null` on any failure — provenance metadata is nice to have
|
|
61
|
-
* and must never fail a download that otherwise succeeded.
|
|
62
|
-
*/
|
|
63
|
-
async function readLastModified(url) {
|
|
64
|
-
try {
|
|
65
|
-
const res = await new APIClient({ displayName: "ourairports", retry: true }).fetch({
|
|
66
|
-
url,
|
|
67
|
-
method: "head",
|
|
68
|
-
timeout: 30_000,
|
|
69
|
-
});
|
|
70
|
-
return res.headers["last-modified"] ?? null;
|
|
71
|
-
}
|
|
72
|
-
catch {
|
|
73
|
-
return null;
|
|
74
|
-
}
|
|
75
|
-
}
|
|
76
|
-
/**
|
|
77
|
-
* Download the OurAirports CSVs into `<outRoot>/ourairports/`, with a sibling `MANIFEST.json` carrying each file's
|
|
78
|
-
* origin URL, sha256, byte count and upstream `Last-Modified`.
|
|
79
|
-
*/
|
|
80
|
-
export async function fetchOurAirports(options, report) {
|
|
81
|
-
const destDir = join(options.outRoot, SLUG);
|
|
82
|
-
mkdirSync(destDir, { recursive: true });
|
|
83
|
-
const entries = [];
|
|
84
|
-
const failedCodes = [];
|
|
85
|
-
let fetched = 0;
|
|
86
|
-
let failed = 0;
|
|
87
|
-
for (const filename of FILES) {
|
|
88
|
-
const url = `${BASE_URL}/${filename}`;
|
|
89
|
-
const dest = join(destDir, filename);
|
|
90
|
-
report?.(`=== ${SLUG} / ${filename}`);
|
|
91
|
-
try {
|
|
92
|
-
const [{ bytes }, lastModified] = await Promise.all([
|
|
93
|
-
downloadToFile({
|
|
94
|
-
url,
|
|
95
|
-
dest,
|
|
96
|
-
timeoutMs: 600_000,
|
|
97
|
-
retries: 2,
|
|
98
|
-
headers: { "Accept-Encoding": "gzip, br" },
|
|
99
|
-
report,
|
|
100
|
-
}),
|
|
101
|
-
readLastModified(url),
|
|
102
|
-
]);
|
|
103
|
-
entries.push({
|
|
104
|
-
filename,
|
|
105
|
-
source_url: url,
|
|
106
|
-
sha256: await sha256File(dest),
|
|
107
|
-
bytes,
|
|
108
|
-
last_modified: lastModified,
|
|
109
|
-
});
|
|
110
|
-
fetched++;
|
|
111
|
-
}
|
|
112
|
-
catch (error) {
|
|
113
|
-
report?.(`✗ ${filename}: ${error instanceof Error ? error.message : String(error)}`);
|
|
114
|
-
failedCodes.push(filename);
|
|
115
|
-
failed++;
|
|
116
|
-
}
|
|
117
|
-
}
|
|
118
|
-
const manifest = {
|
|
119
|
-
source: "OurAirports",
|
|
120
|
-
base_url: BASE_URL,
|
|
121
|
-
license: "public domain (courtesy credit requested)",
|
|
122
|
-
downloaded_at: new Date().toISOString(),
|
|
123
|
-
files: entries,
|
|
124
|
-
};
|
|
125
|
-
await writeManifest(join(destDir, "MANIFEST.json"), manifest);
|
|
126
|
-
return { fetched, skipped: 0, failed, failedCodes };
|
|
127
|
-
}
|
|
128
|
-
//# sourceMappingURL=ourairports.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"ourairports.js","sourceRoot":"","sources":["../../../../src/tools/fetch/ourairports.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAoCG;AAEH,OAAO,EAAE,SAAS,EAAE,MAAM,SAAS,CAAA;AACnC,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAEhC,OAAO,EAAE,SAAS,EAAE,MAAM,qBAAqB,CAAA;AAC/C,OAAO,EAAE,UAAU,EAAE,MAAM,uBAAuB,CAAA;AAGlD,OAAO,EAAE,cAAc,EAAE,aAAa,EAAE,MAAM,eAAe,CAAA;AAE7D,MAAM,IAAI,GAAG,aAAa,CAAA;AAE1B;;;GAGG;AACH,MAAM,QAAQ,GAAG,mDAAmD,CAAA;AAEpE;;;;;;;;GAQG;AACH,MAAM,KAAK,GAAG,CAAC,cAAc,EAAE,eAAe,EAAE,aAAa,EAAE,aAAa,CAAU,CAAA;AAyBtF;;;GAGG;AACH,KAAK,UAAU,gBAAgB,CAAC,GAAW;IAC1C,IAAI,CAAC;QACJ,MAAM,GAAG,GAAG,MAAM,IAAI,SAAS,CAAC,EAAE,WAAW,EAAE,aAAa,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC,CAAC,KAAK,CAAC;YAClF,GAAG;YACH,MAAM,EAAE,MAAM;YACd,OAAO,EAAE,MAAM;SACf,CAAC,CAAA;QAEF,OAAQ,GAAG,CAAC,OAAO,CAAC,eAAe,CAAwB,IAAI,IAAI,CAAA;IACpE,CAAC;IAAC,MAAM,CAAC;QACR,OAAO,IAAI,CAAA;IACZ,CAAC;AACF,CAAC;AAED;;;GAGG;AACH,MAAM,CAAC,KAAK,UAAU,gBAAgB,CACrC,OAAgC,EAChC,MAA+B;IAE/B,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,IAAI,CAAC,CAAA;IAC3C,SAAS,CAAC,OAAO,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;IAEvC,MAAM,OAAO,GAA2B,EAAE,CAAA;IAC1C,MAAM,WAAW,GAAa,EAAE,CAAA;IAChC,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,MAAM,GAAG,CAAC,CAAA;IAEd,KAAK,MAAM,QAAQ,IAAI,KAAK,EAAE,CAAC;QAC9B,MAAM,GAAG,GAAG,GAAG,QAAQ,IAAI,QAAQ,EAAE,CAAA;QACrC,MAAM,IAAI,GAAG,IAAI,CAAC,OAAO,EAAE,QAAQ,CAAC,CAAA;QAEpC,MAAM,EAAE,CAAC,OAAO,IAAI,MAAM,QAAQ,EAAE,CAAC,CAAA;QAErC,IAAI,CAAC;YACJ,MAAM,CAAC,EAAE,KAAK,EAAE,EAAE,YAAY,CAAC,GAAG,MAAM,OAAO,CAAC,GAAG,CAAC;gBACnD,cAAc,CAAC;oBACd,GAAG;oBACH,IAAI;oBACJ,SAAS,EAAE,OAAO;oBAClB,OAAO,EAAE,CAAC;oBACV,OAAO,EAAE,EAAE,iBAAiB,EAAE,UAAU,EAAE;oBAC1C,MAAM;iBACN,CAAC;gBACF,gBAAgB,CAAC,GAAG,CAAC;aACrB,CAAC,CAAA;YAEF,OAAO,CAAC,IAAI,CAAC;gBACZ,QAAQ;gBACR,UAAU,EAAE,GAAG;gBACf,MAAM,EAAE,MAAM,UAAU,CAAC,IAAI,CAAC;gBAC9B,KAAK;gBACL,aAAa,EAAE,YAAY;aAC3B,CAAC,CAAA;YAEF,OAAO,EAAE,CAAA;QACV,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,MAAM,EAAE,CAAC,KAAK,QAAQ,KAAK,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE,CAAC,CAAA;YACpF,WAAW,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAA;YAE1B,MAAM,EAAE,CAAA;QACT,CAAC;IACF,CAAC;IAED,MAAM,QAAQ,GAAwB;QACrC,MAAM,EAAE,aAAa;QACrB,QAAQ,EAAE,QAAQ;QAClB,OAAO,EAAE,2CAA2C;QACpD,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;QACvC,KAAK,EAAE,OAAO;KACd,CAAA;IAED,MAAM,aAAa,CAAC,IAAI,CAAC,OAAO,EAAE,eAAe,CAAC,EAAE,QAAQ,CAAC,CAAA;IAE7D,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,WAAW,EAAE,CAAA;AACpD,CAAC"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"ppd.d.ts","sourceRoot":"","sources":["../../../../src/tools/fetch/ppd.ts"],"names":[],"mappings":"AA2BA,MAAM,WAAW,eAAe;IAC/B,IAAI,EAAE,MAAM,CAAA;IACZ,WAAW,EAAE,MAAM,CAAA;IACnB,WAAW,EAAE,MAAM,CAAA;IACnB,eAAe,EAAE,MAAM,CAAA;IACvB,iBAAiB,EAAE,MAAM,CAAA;CACzB;AAID;;;;GAIG;AACH,wBAAsB,gBAAgB,CACrC,KAAK,EAAE,aAAa,CAAC,MAAM,EAAE,CAAC,GAAG,QAAQ,CAAC,MAAM,EAAE,CAAC,EACnD,KAAK,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC3B,OAAO,CAAC,eAAe,CAAC,CAwD1B"}
|
|
@@ -1,100 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* HM Land Registry Price Paid Data → OA-shaped GB tuples CSV for the `locale` shard recipe.
|
|
7
|
-
*
|
|
8
|
-
* PPD is E&W-only, ALL-CAPS, and column-structured (no header row). We emit the exact OA header
|
|
9
|
-
* `readTuples` (`shard-recipes/locale.ts`) indexes by name, mapped for `districtAsLocality: true`:
|
|
10
|
-
* CITY = PPD locality (dependent locality; blank when it merely repeats the town — 1995-era rows
|
|
11
|
-
* pad locality=town), DISTRICT = PPD post town, REGION = county. SAON (flat/unit) rows and
|
|
12
|
-
* building-name PAONs are skipped in v1 and counted — `LocaleBaseTuple` has no unit field yet.
|
|
13
|
-
*
|
|
14
|
-
* Snapshot provenance: `$MAILWOMAN_DATA_ROOT/ppd/<date>/pp-complete.csv` (md5 sibling).
|
|
15
|
-
* License: OGL v3 (attribution: HM Land Registry).
|
|
16
|
-
*/
|
|
17
|
-
import { createReadStream, createWriteStream } from "node:fs";
|
|
18
|
-
import { parseArgs } from "node:util";
|
|
19
|
-
import { runIfScript } from "@mailwoman/core/scripting";
|
|
20
|
-
import { dataRootPath } from "@mailwoman/core/utils";
|
|
21
|
-
import { CSVSpliterator } from "spliterator";
|
|
22
|
-
import { titleCaseGB } from "../gb-title-case.js";
|
|
23
|
-
const HOUSE_NUMBER_PATTERN = /^\d+[A-Za-z]?(\s*-\s*\d+[A-Za-z]?)?$/;
|
|
24
|
-
const quote = (value) => (value ? `"${value.replaceAll('"', '""')}"` : "");
|
|
25
|
-
/**
|
|
26
|
-
* Convert PPD rows (`id,price,date,postcode,type,new,tenure,PAON,SAON,street,locality,town,district,county,cat,status`
|
|
27
|
-
* — headerless) into OA-shaped tuple lines via `write`, applying the skip rules + title-casing. Accepts a plain array
|
|
28
|
-
* of rows (tests) or a streamed async source (the real 31M-row extraction).
|
|
29
|
-
*/
|
|
30
|
-
export async function extractPPDTuples(input, write) {
|
|
31
|
-
const stats = { kept: 0, skippedSAON: 0, skippedPAON: 0, skippedNoStreet: 0, skippedNoPostcode: 0 };
|
|
32
|
-
write("NUMBER,STREET,CITY,DISTRICT,REGION,POSTCODE");
|
|
33
|
-
for await (const cells of input) {
|
|
34
|
-
// HM Land Registry Price Paid Data column order (see the PPD FAQ for the full field list).
|
|
35
|
-
const postcode = cells[3];
|
|
36
|
-
const paon = cells[7];
|
|
37
|
-
const saon = cells[8];
|
|
38
|
-
const street = cells[9];
|
|
39
|
-
const locality = cells[10];
|
|
40
|
-
const town = cells[11];
|
|
41
|
-
const county = cells[13];
|
|
42
|
-
if (saon) {
|
|
43
|
-
stats.skippedSAON++;
|
|
44
|
-
continue;
|
|
45
|
-
}
|
|
46
|
-
if (!paon || !HOUSE_NUMBER_PATTERN.test(paon)) {
|
|
47
|
-
stats.skippedPAON++;
|
|
48
|
-
continue;
|
|
49
|
-
}
|
|
50
|
-
if (!street) {
|
|
51
|
-
stats.skippedNoStreet++;
|
|
52
|
-
continue;
|
|
53
|
-
}
|
|
54
|
-
if (!postcode) {
|
|
55
|
-
stats.skippedNoPostcode++;
|
|
56
|
-
continue;
|
|
57
|
-
}
|
|
58
|
-
const number = paon.replace(/\s*-\s*/, "-");
|
|
59
|
-
const city = locality && locality !== town ? titleCaseGB(locality) : "";
|
|
60
|
-
write([
|
|
61
|
-
number,
|
|
62
|
-
quote(titleCaseGB(street)),
|
|
63
|
-
quote(city),
|
|
64
|
-
quote(titleCaseGB(town ?? "")),
|
|
65
|
-
quote(titleCaseGB(county ?? "")),
|
|
66
|
-
postcode,
|
|
67
|
-
].join(","));
|
|
68
|
-
stats.kept++;
|
|
69
|
-
}
|
|
70
|
-
return stats;
|
|
71
|
-
}
|
|
72
|
-
/**
|
|
73
|
-
* Stream `inputPath` (PPD CSV) → `outputPath` (OA-shaped tuples CSV), returning the row-count stats.
|
|
74
|
-
*/
|
|
75
|
-
async function runPPDExtract(inputPath, outputPath) {
|
|
76
|
-
// No `encoding` — CSVSpliterator delimits raw bytes and decodes utf-8 itself (see readTuples in
|
|
77
|
-
// shard-recipes/locale.ts). `header: false` yields every row as data — PPD ships no header row.
|
|
78
|
-
const rows = CSVSpliterator.fromAsync(createReadStream(inputPath), {
|
|
79
|
-
mode: "array",
|
|
80
|
-
header: false,
|
|
81
|
-
enableQuoteHandling: true,
|
|
82
|
-
});
|
|
83
|
-
const out = createWriteStream(outputPath, { encoding: "utf8" });
|
|
84
|
-
const stats = await extractPPDTuples(rows, (line) => out.write(line + "\n"));
|
|
85
|
-
await new Promise((res) => {
|
|
86
|
-
out.end(res);
|
|
87
|
-
});
|
|
88
|
-
return stats;
|
|
89
|
-
}
|
|
90
|
-
runIfScript(import.meta, async () => {
|
|
91
|
-
const { values } = parseArgs({
|
|
92
|
-
options: {
|
|
93
|
-
input: { type: "string", default: dataRootPath("ppd", "2026-07-22", "pp-complete.csv") },
|
|
94
|
-
output: { type: "string", default: dataRootPath("ppd", "2026-07-22", "gb-tuples.csv") },
|
|
95
|
-
},
|
|
96
|
-
});
|
|
97
|
-
const stats = await runPPDExtract(values.input, values.output);
|
|
98
|
-
console.log(`[ppd] ${JSON.stringify(stats)}`);
|
|
99
|
-
});
|
|
100
|
-
//# sourceMappingURL=ppd.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"ppd.js","sourceRoot":"","sources":["../../../../src/tools/fetch/ppd.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;GAeG;AACH,OAAO,EAAE,gBAAgB,EAAE,iBAAiB,EAAE,MAAM,SAAS,CAAA;AAC7D,OAAO,EAAE,SAAS,EAAE,MAAM,WAAW,CAAA;AAErC,OAAO,EAAE,WAAW,EAAE,MAAM,2BAA2B,CAAA;AACvD,OAAO,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAA;AACpD,OAAO,EAAE,cAAc,EAAE,MAAM,aAAa,CAAA;AAE5C,OAAO,EAAE,WAAW,EAAE,MAAM,qBAAqB,CAAA;AAEjD,MAAM,oBAAoB,GAAG,sCAAsC,CAAA;AAUnE,MAAM,KAAK,GAAG,CAAC,KAAa,EAAU,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,IAAI,KAAK,CAAC,UAAU,CAAC,GAAG,EAAE,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,CAAA;AAE1F;;;;GAIG;AACH,MAAM,CAAC,KAAK,UAAU,gBAAgB,CACrC,KAAmD,EACnD,KAA6B;IAE7B,MAAM,KAAK,GAAoB,EAAE,IAAI,EAAE,CAAC,EAAE,WAAW,EAAE,CAAC,EAAE,WAAW,EAAE,CAAC,EAAE,eAAe,EAAE,CAAC,EAAE,iBAAiB,EAAE,CAAC,EAAE,CAAA;IACpH,KAAK,CAAC,6CAA6C,CAAC,CAAA;IAEpD,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,KAAK,EAAE,CAAC;QACjC,2FAA2F;QAC3F,MAAM,QAAQ,GAAG,KAAK,CAAC,CAAC,CAAC,CAAA;QACzB,MAAM,IAAI,GAAG,KAAK,CAAC,CAAC,CAAC,CAAA;QACrB,MAAM,IAAI,GAAG,KAAK,CAAC,CAAC,CAAC,CAAA;QACrB,MAAM,MAAM,GAAG,KAAK,CAAC,CAAC,CAAC,CAAA;QACvB,MAAM,QAAQ,GAAG,KAAK,CAAC,EAAE,CAAC,CAAA;QAC1B,MAAM,IAAI,GAAG,KAAK,CAAC,EAAE,CAAC,CAAA;QACtB,MAAM,MAAM,GAAG,KAAK,CAAC,EAAE,CAAC,CAAA;QAExB,IAAI,IAAI,EAAE,CAAC;YACV,KAAK,CAAC,WAAW,EAAE,CAAA;YAEnB,SAAQ;QACT,CAAC;QAED,IAAI,CAAC,IAAI,IAAI,CAAC,oBAAoB,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;YAC/C,KAAK,CAAC,WAAW,EAAE,CAAA;YAEnB,SAAQ;QACT,CAAC;QAED,IAAI,CAAC,MAAM,EAAE,CAAC;YACb,KAAK,CAAC,eAAe,EAAE,CAAA;YAEvB,SAAQ;QACT,CAAC;QAED,IAAI,CAAC,QAAQ,EAAE,CAAC;YACf,KAAK,CAAC,iBAAiB,EAAE,CAAA;YAEzB,SAAQ;QACT,CAAC;QAED,MAAM,MAAM,GAAG,IAAI,CAAC,OAAO,CAAC,SAAS,EAAE,GAAG,CAAC,CAAA;QAC3C,MAAM,IAAI,GAAG,QAAQ,IAAI,QAAQ,KAAK,IAAI,CAAC,CAAC,CAAC,WAAW,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,EAAE,CAAA;QAEvE,KAAK,CACJ;YACC,MAAM;YACN,KAAK,CAAC,WAAW,CAAC,MAAM,CAAC,CAAC;YAC1B,KAAK,CAAC,IAAI,CAAC;YACX,KAAK,CAAC,WAAW,CAAC,IAAI,IAAI,EAAE,CAAC,CAAC;YAC9B,KAAK,CAAC,WAAW,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC;YAChC,QAAQ;SACR,CAAC,IAAI,CAAC,GAAG,CAAC,CACX,CAAA;QAED,KAAK,CAAC,IAAI,EAAE,CAAA;IACb,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC;AAED;;GAEG;AACH,KAAK,UAAU,aAAa,CAAC,SAAiB,EAAE,UAAkB;IACjE,gGAAgG;IAChG,gGAAgG;IAChG,MAAM,IAAI,GAAG,cAAc,CAAC,SAAS,CAAW,gBAAgB,CAAC,SAAS,CAAC,EAAE;QAC5E,IAAI,EAAE,OAAO;QACb,MAAM,EAAE,KAAK;QACb,mBAAmB,EAAE,IAAI;KACzB,CAAC,CAAA;IAEF,MAAM,GAAG,GAAG,iBAAiB,CAAC,UAAU,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,CAAC,CAAA;IAC/D,MAAM,KAAK,GAAG,MAAM,gBAAgB,CAAC,IAAI,EAAE,CAAC,IAAI,EAAE,EAAE,CAAC,GAAG,CAAC,KAAK,CAAC,IAAI,GAAG,IAAI,CAAC,CAAC,CAAA;IAE5E,MAAM,IAAI,OAAO,CAAO,CAAC,GAAG,EAAE,EAAE;QAC/B,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;IACb,CAAC,CAAC,CAAA;IAEF,OAAO,KAAK,CAAA;AACb,CAAC;AAED,WAAW,CAAC,MAAM,CAAC,IAAI,EAAE,KAAK,IAAI,EAAE;IACnC,MAAM,EAAE,MAAM,EAAE,GAAG,SAAS,CAAC;QAC5B,OAAO,EAAE;YACR,KAAK,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,OAAO,EAAE,YAAY,CAAC,KAAK,EAAE,YAAY,EAAE,iBAAiB,CAAC,EAAE;YACxF,MAAM,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,OAAO,EAAE,YAAY,CAAC,KAAK,EAAE,YAAY,EAAE,eAAe,CAAC,EAAE;SACvF;KACD,CAAC,CAAA;IAEF,MAAM,KAAK,GAAG,MAAM,aAAa,CAAC,MAAM,CAAC,KAAM,EAAE,MAAM,CAAC,MAAO,CAAC,CAAA;IAEhE,OAAO,CAAC,GAAG,CAAC,SAAS,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,EAAE,CAAC,CAAA;AAC9C,CAAC,CAAC,CAAA"}
|
|
@@ -1,25 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Re-fetch the Hawaii State DOE school directory and convert the XLSX workbook to a flat CSV the
|
|
7
|
-
* `state-hi-schools` adapter can consume.
|
|
8
|
-
*
|
|
9
|
-
* Upstream is a single XLSX (~64 KB) with two sheets — `HIDOE` (~258 district schools) and `PCS`
|
|
10
|
-
* (~38 public charter schools). Both sheets share the same header. This module concatenates them
|
|
11
|
-
* under one shared header so the adapter can stream a single CSV.
|
|
12
|
-
*
|
|
13
|
-
* License: Hawaii state government open data (Tier A — state PD-equivalent).
|
|
14
|
-
*
|
|
15
|
-
* Built-in `fetch` (gzip/brotli) replaces curl for the download; the XLSX → CSV step still rides
|
|
16
|
-
* `python3` + `openpyxl` via `node:child_process` — there is no clean node equivalent without
|
|
17
|
-
* adding a workbook-parsing dependency.
|
|
18
|
-
*
|
|
19
|
-
* Invoke via `mailwoman corpus fetch state-hi-schools --out-root <path>`. Idempotent: if the dest
|
|
20
|
-
* CSV exists and sha matches MANIFEST, skips download.
|
|
21
|
-
*/
|
|
22
|
-
import type { BaseFetchOptions, FetchSummary } from "./download.ts";
|
|
23
|
-
export type FetchStateHISchoolsOptions = BaseFetchOptions;
|
|
24
|
-
export declare function fetchStateHISchools(options: FetchStateHISchoolsOptions, report?: (line: string) => void): Promise<FetchSummary>;
|
|
25
|
-
//# sourceMappingURL=state-hi-schools.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"state-hi-schools.d.ts","sourceRoot":"","sources":["../../../../src/tools/fetch/state-hi-schools.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;GAoBG;AAUH,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAAE,MAAM,eAAe,CAAA;AAanE,MAAM,MAAM,0BAA0B,GAAG,gBAAgB,CAAA;AAsEzD,wBAAsB,mBAAmB,CACxC,OAAO,EAAE,0BAA0B,EACnC,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,YAAY,CAAC,CA2FvB"}
|
|
@@ -1,162 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Re-fetch the Hawaii State DOE school directory and convert the XLSX workbook to a flat CSV the
|
|
7
|
-
* `state-hi-schools` adapter can consume.
|
|
8
|
-
*
|
|
9
|
-
* Upstream is a single XLSX (~64 KB) with two sheets — `HIDOE` (~258 district schools) and `PCS`
|
|
10
|
-
* (~38 public charter schools). Both sheets share the same header. This module concatenates them
|
|
11
|
-
* under one shared header so the adapter can stream a single CSV.
|
|
12
|
-
*
|
|
13
|
-
* License: Hawaii state government open data (Tier A — state PD-equivalent).
|
|
14
|
-
*
|
|
15
|
-
* Built-in `fetch` (gzip/brotli) replaces curl for the download; the XLSX → CSV step still rides
|
|
16
|
-
* `python3` + `openpyxl` via `node:child_process` — there is no clean node equivalent without
|
|
17
|
-
* adding a workbook-parsing dependency.
|
|
18
|
-
*
|
|
19
|
-
* Invoke via `mailwoman corpus fetch state-hi-schools --out-root <path>`. Idempotent: if the dest
|
|
20
|
-
* CSV exists and sha matches MANIFEST, skips download.
|
|
21
|
-
*/
|
|
22
|
-
import { spawn, spawnSync } from "node:child_process";
|
|
23
|
-
import { existsSync, mkdirSync, statSync } from "node:fs";
|
|
24
|
-
import { unlink } from "node:fs/promises";
|
|
25
|
-
import { join } from "node:path";
|
|
26
|
-
import { BYTES_PER_KIB, ByteFormatter } from "@mailwoman/core/fs/utils";
|
|
27
|
-
import { sha256File } from "@mailwoman/core/utils";
|
|
28
|
-
import { downloadToFile, readManifest, writeManifest } from "./download.js";
|
|
29
|
-
/**
|
|
30
|
-
* Bytes per KiB — the divisor for human-readable sizes, and the floor below which a "download" is an error page rather
|
|
31
|
-
* than data.
|
|
32
|
-
*/
|
|
33
|
-
const SOURCE_URL = "https://www.hawaiipublicschools.org/DOE%20Forms/SchoolList.xlsx";
|
|
34
|
-
const SLUG = "state-hi-schools";
|
|
35
|
-
const CSV_FILENAME = "HI_Public_Schools_List.csv";
|
|
36
|
-
const XLSX_FILENAME = "HI_Public_Schools_List.xlsx";
|
|
37
|
-
/**
|
|
38
|
-
* The XLSX → CSV converter: concatenate every sheet under one shared header (the first sheet's). Runs as `python3 -c
|
|
39
|
-
* <script> <xlsx-path> <csv-path>`, so `sys.argv[1]`/`sys.argv[2]` are the I/O paths. TODO: Get rid of this.
|
|
40
|
-
*/
|
|
41
|
-
const PY_CONVERT = `
|
|
42
|
-
import csv
|
|
43
|
-
import sys
|
|
44
|
-
from openpyxl import load_workbook
|
|
45
|
-
|
|
46
|
-
xlsx_path, csv_path = sys.argv[1], sys.argv[2]
|
|
47
|
-
wb = load_workbook(xlsx_path, data_only=True, read_only=True)
|
|
48
|
-
|
|
49
|
-
with open(csv_path, "w", newline="", encoding="utf-8") as out:
|
|
50
|
-
writer = csv.writer(out)
|
|
51
|
-
shared_header = None
|
|
52
|
-
total_data_rows = 0
|
|
53
|
-
for sheet_name in wb.sheetnames:
|
|
54
|
-
ws = wb[sheet_name]
|
|
55
|
-
rows = ws.iter_rows(values_only=True)
|
|
56
|
-
try:
|
|
57
|
-
header = next(rows)
|
|
58
|
-
except StopIteration:
|
|
59
|
-
continue
|
|
60
|
-
norm_header = ["" if v is None else str(v).strip() for v in header]
|
|
61
|
-
if shared_header is None:
|
|
62
|
-
shared_header = norm_header
|
|
63
|
-
writer.writerow(shared_header)
|
|
64
|
-
elif norm_header != shared_header:
|
|
65
|
-
print(
|
|
66
|
-
f" ! sheet '{sheet_name}' header diverges from shared header; concatenating anyway",
|
|
67
|
-
file=sys.stderr,
|
|
68
|
-
)
|
|
69
|
-
for row in rows:
|
|
70
|
-
if row is None:
|
|
71
|
-
continue
|
|
72
|
-
# Skip fully-empty rows (XLSX iter_rows can yield phantom trailing rows).
|
|
73
|
-
if all(v is None or (isinstance(v, str) and not v.strip()) for v in row):
|
|
74
|
-
continue
|
|
75
|
-
writer.writerow(["" if v is None else str(v).strip() for v in row])
|
|
76
|
-
total_data_rows += 1
|
|
77
|
-
|
|
78
|
-
print(f" converted {total_data_rows} data rows from {len(wb.sheetnames)} sheets", file=sys.stderr)
|
|
79
|
-
`;
|
|
80
|
-
/**
|
|
81
|
-
* Run the openpyxl converter. Its stderr narration streams straight through to the process stderr (matching the old
|
|
82
|
-
* `stdio: inherit` behavior) rather than routing through `report` — the python child owns those lines.
|
|
83
|
-
*/
|
|
84
|
-
async function convertXLSXToCSV(xlsxPath, csvPath) {
|
|
85
|
-
const child = spawn("python3", ["-c", PY_CONVERT, xlsxPath, csvPath], {
|
|
86
|
-
stdio: ["ignore", "inherit", "inherit"],
|
|
87
|
-
});
|
|
88
|
-
await new Promise((resolve, reject) => {
|
|
89
|
-
child.on("close", (code) => (code === 0 ? resolve() : reject(new Error(`python3 converter exited with ${code}`))));
|
|
90
|
-
child.on("error", reject);
|
|
91
|
-
});
|
|
92
|
-
}
|
|
93
|
-
export async function fetchStateHISchools(options, report) {
|
|
94
|
-
const destDir = join(options.outRoot, SLUG);
|
|
95
|
-
mkdirSync(destDir, { recursive: true });
|
|
96
|
-
const xlsxDest = join(destDir, XLSX_FILENAME);
|
|
97
|
-
const csvDest = join(destDir, CSV_FILENAME);
|
|
98
|
-
const manifestPath = join(destDir, "MANIFEST.json");
|
|
99
|
-
report?.(`=== ${SLUG}`);
|
|
100
|
-
// Idempotency: skip if CSV exists and sha matches recorded MANIFEST.
|
|
101
|
-
if (existsSync(csvDest)) {
|
|
102
|
-
const recorded = await readManifest(manifestPath);
|
|
103
|
-
if (recorded?.sha256 && recorded.filename === CSV_FILENAME) {
|
|
104
|
-
const actualSha = await sha256File(csvDest);
|
|
105
|
-
if (actualSha === recorded.sha256) {
|
|
106
|
-
report?.(` ✓ Already current (sha256 matches MANIFEST) — skipping download.`);
|
|
107
|
-
return { fetched: 0, skipped: 1, failed: 0, failedCodes: [] };
|
|
108
|
-
}
|
|
109
|
-
}
|
|
110
|
-
}
|
|
111
|
-
// Preflight: openpyxl must be importable.
|
|
112
|
-
const preflight = spawnSync("python3", ["-c", "import openpyxl"], { stdio: "ignore" });
|
|
113
|
-
if (preflight.status !== 0) {
|
|
114
|
-
report?.(` ✗ python3 with the \`openpyxl\` package is required to convert the HIDOE XLSX.\n` +
|
|
115
|
-
` Debian/Ubuntu: sudo apt-get install -y python3-openpyxl\n` +
|
|
116
|
-
` macOS Homebrew: brew install python && pip3 install openpyxl`);
|
|
117
|
-
return { fetched: 0, skipped: 0, failed: 1, failedCodes: [SLUG] };
|
|
118
|
-
}
|
|
119
|
-
// Download XLSX.
|
|
120
|
-
report?.(` Downloading ${SOURCE_URL} ...`);
|
|
121
|
-
try {
|
|
122
|
-
await downloadToFile({
|
|
123
|
-
url: SOURCE_URL,
|
|
124
|
-
dest: xlsxDest,
|
|
125
|
-
timeoutMs: 600_000,
|
|
126
|
-
headers: { "Accept-Encoding": "gzip, br" },
|
|
127
|
-
report,
|
|
128
|
-
});
|
|
129
|
-
}
|
|
130
|
-
catch (error) {
|
|
131
|
-
report?.(` ✗ Download failed (${error.message})`);
|
|
132
|
-
return { fetched: 0, skipped: 0, failed: 1, failedCodes: [SLUG] };
|
|
133
|
-
}
|
|
134
|
-
const xlsxSize = statSync(xlsxDest).size;
|
|
135
|
-
report?.(` Downloaded XLSX: ${ByteFormatter.formatIEC(xlsxSize)}`);
|
|
136
|
-
if (xlsxSize < BYTES_PER_KIB) {
|
|
137
|
-
report?.(` ✗ Response too small (${xlsxSize} bytes) — probable error page`);
|
|
138
|
-
return { fetched: 0, skipped: 0, failed: 1, failedCodes: [SLUG] };
|
|
139
|
-
}
|
|
140
|
-
// Convert XLSX → CSV (concatenate both sheets under one shared header).
|
|
141
|
-
report?.(` Converting XLSX → CSV (concatenating sheets) ...`);
|
|
142
|
-
await convertXLSXToCSV(xlsxDest, csvDest);
|
|
143
|
-
const csvSize = statSync(csvDest).size;
|
|
144
|
-
const csvSha = await sha256File(csvDest);
|
|
145
|
-
// Remove XLSX (CSV is the canonical artifact the adapter consumes).
|
|
146
|
-
await unlink(xlsxDest);
|
|
147
|
-
report?.(` Removed XLSX (CSV kept)`);
|
|
148
|
-
// Write MANIFEST.
|
|
149
|
-
const manifest = {
|
|
150
|
-
source_url: SOURCE_URL,
|
|
151
|
-
downloaded_at: new Date().toISOString(),
|
|
152
|
-
filename: CSV_FILENAME,
|
|
153
|
-
sha256: csvSha,
|
|
154
|
-
bytes: csvSize,
|
|
155
|
-
notes: "Converted from XLSX (sheets HIDOE + PCS concatenated under shared header).",
|
|
156
|
-
};
|
|
157
|
-
await writeManifest(manifestPath, manifest);
|
|
158
|
-
report?.(` ✓ ${ByteFormatter.formatIEC(csvSize)} sha256=${csvSha}`);
|
|
159
|
-
report?.(` MANIFEST written to ${manifestPath}`);
|
|
160
|
-
return { fetched: 1, skipped: 0, failed: 0, failedCodes: [] };
|
|
161
|
-
}
|
|
162
|
-
//# sourceMappingURL=state-hi-schools.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"state-hi-schools.js","sourceRoot":"","sources":["../../../../src/tools/fetch/state-hi-schools.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;GAoBG;AAEH,OAAO,EAAE,KAAK,EAAE,SAAS,EAAE,MAAM,oBAAoB,CAAA;AACrD,OAAO,EAAE,UAAU,EAAE,SAAS,EAAE,QAAQ,EAAE,MAAM,SAAS,CAAA;AACzD,OAAO,EAAE,MAAM,EAAE,MAAM,kBAAkB,CAAA;AACzC,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAEhC,OAAO,EAAE,aAAa,EAAE,aAAa,EAAE,MAAM,0BAA0B,CAAA;AACvE,OAAO,EAAE,UAAU,EAAE,MAAM,uBAAuB,CAAA;AAGlD,OAAO,EAAE,cAAc,EAAE,YAAY,EAAE,aAAa,EAAE,MAAM,eAAe,CAAA;AAE3E;;;GAGG;AAEH,MAAM,UAAU,GAAG,iEAAiE,CAAA;AACpF,MAAM,IAAI,GAAG,kBAAkB,CAAA;AAC/B,MAAM,YAAY,GAAG,4BAA4B,CAAA;AACjD,MAAM,aAAa,GAAG,6BAA6B,CAAA;AAInD;;;GAGG;AACH,MAAM,UAAU,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAsClB,CAAA;AAWD;;;GAGG;AACH,KAAK,UAAU,gBAAgB,CAAC,QAAgB,EAAE,OAAe;IAChE,MAAM,KAAK,GAAG,KAAK,CAAC,SAAS,EAAE,CAAC,IAAI,EAAE,UAAU,EAAE,QAAQ,EAAE,OAAO,CAAC,EAAE;QACrE,KAAK,EAAE,CAAC,QAAQ,EAAE,SAAS,EAAE,SAAS,CAAC;KACvC,CAAC,CAAA;IAEF,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,iCAAiC,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC,CAAA;QAClH,KAAK,CAAC,EAAE,CAAC,OAAO,EAAE,MAAM,CAAC,CAAA;IAC1B,CAAC,CAAC,CAAA;AACH,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,mBAAmB,CACxC,OAAmC,EACnC,MAA+B;IAE/B,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,IAAI,CAAC,CAAA;IAC3C,SAAS,CAAC,OAAO,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;IAEvC,MAAM,QAAQ,GAAG,IAAI,CAAC,OAAO,EAAE,aAAa,CAAC,CAAA;IAC7C,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,EAAE,YAAY,CAAC,CAAA;IAC3C,MAAM,YAAY,GAAG,IAAI,CAAC,OAAO,EAAE,eAAe,CAAC,CAAA;IAEnD,MAAM,EAAE,CAAC,OAAO,IAAI,EAAE,CAAC,CAAA;IAEvB,qEAAqE;IACrE,IAAI,UAAU,CAAC,OAAO,CAAC,EAAE,CAAC;QACzB,MAAM,QAAQ,GAAG,MAAM,YAAY,CAAoB,YAAY,CAAC,CAAA;QAEpE,IAAI,QAAQ,EAAE,MAAM,IAAI,QAAQ,CAAC,QAAQ,KAAK,YAAY,EAAE,CAAC;YAC5D,MAAM,SAAS,GAAG,MAAM,UAAU,CAAC,OAAO,CAAC,CAAA;YAE3C,IAAI,SAAS,KAAK,QAAQ,CAAC,MAAM,EAAE,CAAC;gBACnC,MAAM,EAAE,CAAC,oEAAoE,CAAC,CAAA;gBAE9E,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,WAAW,EAAE,EAAE,EAAE,CAAA;YAC9D,CAAC;QACF,CAAC;IACF,CAAC;IAED,0CAA0C;IAC1C,MAAM,SAAS,GAAG,SAAS,CAAC,SAAS,EAAE,CAAC,IAAI,EAAE,iBAAiB,CAAC,EAAE,EAAE,KAAK,EAAE,QAAQ,EAAE,CAAC,CAAA;IAEtF,IAAI,SAAS,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAC5B,MAAM,EAAE,CACP,oFAAoF;YACnF,gEAAgE;YAChE,kEAAkE,CACnE,CAAA;QAED,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,WAAW,EAAE,CAAC,IAAI,CAAC,EAAE,CAAA;IAClE,CAAC;IAED,iBAAiB;IACjB,MAAM,EAAE,CAAC,iBAAiB,UAAU,MAAM,CAAC,CAAA;IAE3C,IAAI,CAAC;QACJ,MAAM,cAAc,CAAC;YACpB,GAAG,EAAE,UAAU;YACf,IAAI,EAAE,QAAQ;YACd,SAAS,EAAE,OAAO;YAClB,OAAO,EAAE,EAAE,iBAAiB,EAAE,UAAU,EAAE;YAC1C,MAAM;SACN,CAAC,CAAA;IACH,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QAChB,MAAM,EAAE,CAAC,wBAAyB,KAAe,CAAC,OAAO,GAAG,CAAC,CAAA;QAE7D,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,QAAQ,GAAG,QAAQ,CAAC,QAAQ,CAAC,CAAC,IAAI,CAAA;IACxC,MAAM,EAAE,CAAC,sBAAsB,aAAa,CAAC,SAAS,CAAC,QAAQ,CAAC,EAAE,CAAC,CAAA;IAEnE,IAAI,QAAQ,GAAG,aAAa,EAAE,CAAC;QAC9B,MAAM,EAAE,CAAC,2BAA2B,QAAQ,+BAA+B,CAAC,CAAA;QAE5E,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,WAAW,EAAE,CAAC,IAAI,CAAC,EAAE,CAAA;IAClE,CAAC;IAED,wEAAwE;IACxE,MAAM,EAAE,CAAC,oDAAoD,CAAC,CAAA;IAC9D,MAAM,gBAAgB,CAAC,QAAQ,EAAE,OAAO,CAAC,CAAA;IAEzC,MAAM,OAAO,GAAG,QAAQ,CAAC,OAAO,CAAC,CAAC,IAAI,CAAA;IACtC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,OAAO,CAAC,CAAA;IAExC,oEAAoE;IACpE,MAAM,MAAM,CAAC,QAAQ,CAAC,CAAA;IACtB,MAAM,EAAE,CAAC,2BAA2B,CAAC,CAAA;IAErC,kBAAkB;IAClB,MAAM,QAAQ,GAAa;QAC1B,UAAU,EAAE,UAAU;QACtB,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;QACvC,QAAQ,EAAE,YAAY;QACtB,MAAM,EAAE,MAAM;QACd,KAAK,EAAE,OAAO;QACd,KAAK,EAAE,4EAA4E;KACnF,CAAA;IAED,MAAM,aAAa,CAAC,YAAY,EAAE,QAAQ,CAAC,CAAA;IAE3C,MAAM,EAAE,CAAC,OAAO,aAAa,CAAC,SAAS,CAAC,OAAO,CAAC,YAAY,MAAM,EAAE,CAAC,CAAA;IACrE,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"}
|
|
@@ -1,26 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Re-fetch the state-level open-data sources (NY/TX/DE/OR notaries, IA contractors, WA health
|
|
7
|
-
* providers, HI lobbyists). Reproducible recovery if `$MAILWOMAN_DATA_ROOT` is lost.
|
|
8
|
-
*
|
|
9
|
-
* HI public schools is fetched separately by `mailwoman corpus fetch state-hi-schools` — its
|
|
10
|
-
* upstream is an XLSX workbook that requires an openpyxl-driven sheet-concatenation pre-step
|
|
11
|
-
* before the adapter can consume it.
|
|
12
|
-
*
|
|
13
|
-
* Each source lands in its own subdirectory of `<outRoot>/<slug>/` along with a `MANIFEST.json`
|
|
14
|
-
* recording origin URL + download timestamp + sha256 so downstream adapters can verify provenance.
|
|
15
|
-
*
|
|
16
|
-
* Invoke via `mailwoman corpus fetch state-sources --out-root <path>`. Uses Node's built-in fetch
|
|
17
|
-
* (gzip/brotli) and streaming sha256 instead of curl + sha256sum.
|
|
18
|
-
*/
|
|
19
|
-
import type { BaseFetchOptions, FetchSummary } from "./download.ts";
|
|
20
|
-
/**
|
|
21
|
-
* Bytes per KiB — the divisor for human-readable sizes, and the floor below which a "download" is an error page rather
|
|
22
|
-
* than data.
|
|
23
|
-
*/
|
|
24
|
-
export type FetchStateSourcesOptions = BaseFetchOptions;
|
|
25
|
-
export declare function fetchStateSources(options: FetchStateSourcesOptions, report?: (line: string) => void): Promise<FetchSummary>;
|
|
26
|
-
//# sourceMappingURL=state-sources.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"state-sources.d.ts","sourceRoot":"","sources":["../../../../src/tools/fetch/state-sources.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;GAiBG;AAQH,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAAE,MAAM,eAAe,CAAA;AAGnE;;;GAGG;AAEH,MAAM,MAAM,wBAAwB,GAAG,gBAAgB,CAAA;AAsDvD,wBAAsB,iBAAiB,CACtC,OAAO,EAAE,wBAAwB,EACjC,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,YAAY,CAAC,CAgEvB"}
|
|
@@ -1,111 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Re-fetch the state-level open-data sources (NY/TX/DE/OR notaries, IA contractors, WA health
|
|
7
|
-
* providers, HI lobbyists). Reproducible recovery if `$MAILWOMAN_DATA_ROOT` is lost.
|
|
8
|
-
*
|
|
9
|
-
* HI public schools is fetched separately by `mailwoman corpus fetch state-hi-schools` — its
|
|
10
|
-
* upstream is an XLSX workbook that requires an openpyxl-driven sheet-concatenation pre-step
|
|
11
|
-
* before the adapter can consume it.
|
|
12
|
-
*
|
|
13
|
-
* Each source lands in its own subdirectory of `<outRoot>/<slug>/` along with a `MANIFEST.json`
|
|
14
|
-
* recording origin URL + download timestamp + sha256 so downstream adapters can verify provenance.
|
|
15
|
-
*
|
|
16
|
-
* Invoke via `mailwoman corpus fetch state-sources --out-root <path>`. Uses Node's built-in fetch
|
|
17
|
-
* (gzip/brotli) and streaming sha256 instead of curl + sha256sum.
|
|
18
|
-
*/
|
|
19
|
-
import { mkdirSync } from "node:fs";
|
|
20
|
-
import { join } from "node:path";
|
|
21
|
-
import { BYTES_PER_KIB } from "@mailwoman/core/fs/utils";
|
|
22
|
-
import { sha256File } from "@mailwoman/core/utils";
|
|
23
|
-
import { downloadToFile, writeManifest } from "./download.js";
|
|
24
|
-
const SOURCES = [
|
|
25
|
-
{
|
|
26
|
-
slug: "state-ny-notaries",
|
|
27
|
-
filename: "NY_Commissioned_Notaries.csv",
|
|
28
|
-
url: "https://data.ny.gov/api/views/rwbv-mz6z/rows.csv?accessType=DOWNLOAD",
|
|
29
|
-
},
|
|
30
|
-
{
|
|
31
|
-
slug: "state-tx-notaries",
|
|
32
|
-
filename: "TX_Notary_Public_Commissions.csv",
|
|
33
|
-
url: "https://data.texas.gov/api/views/gmd3-bnrd/rows.csv?accessType=DOWNLOAD",
|
|
34
|
-
},
|
|
35
|
-
{
|
|
36
|
-
slug: "state-de-notaries",
|
|
37
|
-
filename: "DE_Notaries_Commissioned.csv",
|
|
38
|
-
url: "https://data.delaware.gov/api/views/q8dr-mj6p/rows.csv?accessType=DOWNLOAD",
|
|
39
|
-
},
|
|
40
|
-
{
|
|
41
|
-
slug: "state-or-notaries",
|
|
42
|
-
filename: "OR_Active_Notaries.csv",
|
|
43
|
-
url: "https://data.oregon.gov/api/views/j2pk-zk6z/rows.csv?accessType=DOWNLOAD",
|
|
44
|
-
},
|
|
45
|
-
{
|
|
46
|
-
slug: "state-ia-contractors",
|
|
47
|
-
filename: "IA_Active_Construction_Contractor_Registrations.csv",
|
|
48
|
-
url: "https://data.iowa.gov/api/views/dpf3-iz94/rows.csv?accessType=DOWNLOAD",
|
|
49
|
-
},
|
|
50
|
-
{
|
|
51
|
-
slug: "state-wa-health-providers",
|
|
52
|
-
filename: "WA_Health_Care_Provider_Credential_Data.csv",
|
|
53
|
-
url: "https://data.wa.gov/api/views/qxh8-f4bd/rows.csv?accessType=DOWNLOAD",
|
|
54
|
-
},
|
|
55
|
-
{
|
|
56
|
-
slug: "state-hi-lobbyists",
|
|
57
|
-
filename: "HI_Lobbyist_Registration_Statements.csv",
|
|
58
|
-
url: "https://data.hawaii.gov/api/views/cm7c-skav/rows.csv?accessType=DOWNLOAD",
|
|
59
|
-
},
|
|
60
|
-
];
|
|
61
|
-
export async function fetchStateSources(options, report) {
|
|
62
|
-
mkdirSync(options.outRoot, { recursive: true });
|
|
63
|
-
let fetched = 0;
|
|
64
|
-
let failed = 0;
|
|
65
|
-
const failedCodes = [];
|
|
66
|
-
for (const { slug, filename, url } of SOURCES) {
|
|
67
|
-
const destDir = join(options.outRoot, slug);
|
|
68
|
-
mkdirSync(destDir, { recursive: true });
|
|
69
|
-
const dest = join(destDir, filename);
|
|
70
|
-
report?.(`=== ${slug} / ${filename}`);
|
|
71
|
-
let bytes;
|
|
72
|
-
try {
|
|
73
|
-
;
|
|
74
|
-
({ bytes } = await downloadToFile({
|
|
75
|
-
url,
|
|
76
|
-
dest,
|
|
77
|
-
timeoutMs: 600_000,
|
|
78
|
-
headers: { "Accept-Encoding": "gzip, br" },
|
|
79
|
-
report,
|
|
80
|
-
}));
|
|
81
|
-
}
|
|
82
|
-
catch (error) {
|
|
83
|
-
report?.(` ✗ download failed for ${url}: ${error.message}`);
|
|
84
|
-
failed++;
|
|
85
|
-
failedCodes.push(slug);
|
|
86
|
-
continue;
|
|
87
|
-
}
|
|
88
|
-
if (bytes < BYTES_PER_KIB) {
|
|
89
|
-
report?.(` ✗ response too small (${bytes} bytes) — probable 404 / error page`);
|
|
90
|
-
failed++;
|
|
91
|
-
failedCodes.push(slug);
|
|
92
|
-
continue;
|
|
93
|
-
}
|
|
94
|
-
const sha = await sha256File(dest);
|
|
95
|
-
const manifest = {
|
|
96
|
-
source_url: url,
|
|
97
|
-
downloaded_at: new Date().toISOString(),
|
|
98
|
-
filename,
|
|
99
|
-
sha256: sha,
|
|
100
|
-
bytes,
|
|
101
|
-
};
|
|
102
|
-
await writeManifest(join(destDir, "MANIFEST.json"), manifest);
|
|
103
|
-
report?.(` ✓ ${(bytes / 1024 / 1024).toFixed(1)} MB sha256=${sha}`);
|
|
104
|
-
fetched++;
|
|
105
|
-
}
|
|
106
|
-
report?.(`=== summary ===`);
|
|
107
|
-
report?.(`fetched: ${fetched}`);
|
|
108
|
-
report?.(`failed: ${failed}`);
|
|
109
|
-
return { fetched, skipped: 0, failed, failedCodes };
|
|
110
|
-
}
|
|
111
|
-
//# sourceMappingURL=state-sources.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"state-sources.js","sourceRoot":"","sources":["../../../../src/tools/fetch/state-sources.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;GAiBG;AAEH,OAAO,EAAE,SAAS,EAAE,MAAM,SAAS,CAAA;AACnC,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAEhC,OAAO,EAAE,aAAa,EAAE,MAAM,0BAA0B,CAAA;AACxD,OAAO,EAAE,UAAU,EAAE,MAAM,uBAAuB,CAAA;AAGlD,OAAO,EAAE,cAAc,EAAE,aAAa,EAAE,MAAM,eAAe,CAAA;AAe7D,MAAM,OAAO,GAAsB;IAClC;QACC,IAAI,EAAE,mBAAmB;QACzB,QAAQ,EAAE,8BAA8B;QACxC,GAAG,EAAE,sEAAsE;KAC3E;IACD;QACC,IAAI,EAAE,mBAAmB;QACzB,QAAQ,EAAE,kCAAkC;QAC5C,GAAG,EAAE,yEAAyE;KAC9E;IACD;QACC,IAAI,EAAE,mBAAmB;QACzB,QAAQ,EAAE,8BAA8B;QACxC,GAAG,EAAE,4EAA4E;KACjF;IACD;QACC,IAAI,EAAE,mBAAmB;QACzB,QAAQ,EAAE,wBAAwB;QAClC,GAAG,EAAE,0EAA0E;KAC/E;IACD;QACC,IAAI,EAAE,sBAAsB;QAC5B,QAAQ,EAAE,qDAAqD;QAC/D,GAAG,EAAE,wEAAwE;KAC7E;IACD;QACC,IAAI,EAAE,2BAA2B;QACjC,QAAQ,EAAE,6CAA6C;QACvD,GAAG,EAAE,sEAAsE;KAC3E;IACD;QACC,IAAI,EAAE,oBAAoB;QAC1B,QAAQ,EAAE,yCAAyC;QACnD,GAAG,EAAE,0EAA0E;KAC/E;CACD,CAAA;AAUD,MAAM,CAAC,KAAK,UAAU,iBAAiB,CACtC,OAAiC,EACjC,MAA+B;IAE/B,SAAS,CAAC,OAAO,CAAC,OAAO,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;IAE/C,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,MAAM,GAAG,CAAC,CAAA;IACd,MAAM,WAAW,GAAa,EAAE,CAAA;IAEhC,KAAK,MAAM,EAAE,IAAI,EAAE,QAAQ,EAAE,GAAG,EAAE,IAAI,OAAO,EAAE,CAAC;QAC/C,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,IAAI,CAAC,CAAA;QAC3C,SAAS,CAAC,OAAO,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;QACvC,MAAM,IAAI,GAAG,IAAI,CAAC,OAAO,EAAE,QAAQ,CAAC,CAAA;QAEpC,MAAM,EAAE,CAAC,OAAO,IAAI,MAAM,QAAQ,EAAE,CAAC,CAAA;QAErC,IAAI,KAAa,CAAA;QAEjB,IAAI,CAAC;YACJ,CAAC;YAAA,CAAC,EAAE,KAAK,EAAE,GAAG,MAAM,cAAc,CAAC;gBAClC,GAAG;gBACH,IAAI;gBACJ,SAAS,EAAE,OAAO;gBAClB,OAAO,EAAE,EAAE,iBAAiB,EAAE,UAAU,EAAE;gBAC1C,MAAM;aACN,CAAC,CAAC,CAAA;QACJ,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,MAAM,EAAE,CAAC,2BAA2B,GAAG,KAAM,KAAe,CAAC,OAAO,EAAE,CAAC,CAAA;YAEvE,MAAM,EAAE,CAAA;YACR,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;YAEtB,SAAQ;QACT,CAAC;QAED,IAAI,KAAK,GAAG,aAAa,EAAE,CAAC;YAC3B,MAAM,EAAE,CAAC,2BAA2B,KAAK,qCAAqC,CAAC,CAAA;YAE/E,MAAM,EAAE,CAAA;YACR,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;YAEtB,SAAQ;QACT,CAAC;QAED,MAAM,GAAG,GAAG,MAAM,UAAU,CAAC,IAAI,CAAC,CAAA;QAElC,MAAM,QAAQ,GAAmB;YAChC,UAAU,EAAE,GAAG;YACf,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;YACvC,QAAQ;YACR,MAAM,EAAE,GAAG;YACX,KAAK;SACL,CAAA;QAED,MAAM,aAAa,CAAC,IAAI,CAAC,OAAO,EAAE,eAAe,CAAC,EAAE,QAAQ,CAAC,CAAA;QAE7D,MAAM,EAAE,CAAC,OAAO,CAAC,KAAK,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe,GAAG,EAAE,CAAC,CAAA;QAErE,OAAO,EAAE,CAAA;IACV,CAAC;IAED,MAAM,EAAE,CAAC,iBAAiB,CAAC,CAAA;IAC3B,MAAM,EAAE,CAAC,YAAY,OAAO,EAAE,CAAC,CAAA;IAC/B,MAAM,EAAE,CAAC,YAAY,MAAM,EAAE,CAAC,CAAA;IAE9B,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,WAAW,EAAE,CAAA;AACpD,CAAC"}
|
|
@@ -1,42 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* Fetch the full TIGER 2024 ADDRFEAT dataset — all US counties.
|
|
7
|
-
*
|
|
8
|
-
* TIGER ADDRFEAT 2024 source:
|
|
9
|
-
*
|
|
10
|
-
* - https://www2.census.gov/geo/tiger/TIGER2024/ADDRFEAT/
|
|
11
|
-
* - Files: `tl_2024_<statefips><countyfips>_addrfeat.zip`
|
|
12
|
-
*
|
|
13
|
-
* Each state's ZIPs land in `<outRoot>/tiger/addrfeat/state-<statefips>/` with a per-state
|
|
14
|
-
* `MANIFEST.json` recording filename, sha256, and bytes for every county ZIP so re-runs can skip
|
|
15
|
-
* already-verified files. (Extraction + ogr2ogr ingestion happen later, in the `tiger` adapter;
|
|
16
|
-
* this module is download + provenance only.)
|
|
17
|
-
*
|
|
18
|
-
* Invoke via `mailwoman corpus fetch tiger-full --out-root <path>`. Native `fetch` streams each
|
|
19
|
-
* county ZIP to disk (no curl subprocess).
|
|
20
|
-
*/
|
|
21
|
-
import type { BaseFetchOptions, FetchSummary } from "./download.ts";
|
|
22
|
-
export interface FetchTigerFullOptions extends BaseFetchOptions {
|
|
23
|
-
/**
|
|
24
|
-
* Space-separated list of 2-digit state FIPS codes to skip entirely. Default `"50"` — Vermont, already fetched in
|
|
25
|
-
* v0.1.1.
|
|
26
|
-
*/
|
|
27
|
-
skipStateFips?: string;
|
|
28
|
-
/**
|
|
29
|
-
* Seconds to sleep between downloads. Default `0.2`.
|
|
30
|
-
*/
|
|
31
|
-
rateSleep?: number;
|
|
32
|
-
/**
|
|
33
|
-
* Max concurrent download workers per state. Default `4`.
|
|
34
|
-
*/
|
|
35
|
-
maxParallel?: number;
|
|
36
|
-
/**
|
|
37
|
-
* Print planned downloads without fetching. Default `false`.
|
|
38
|
-
*/
|
|
39
|
-
dryRun?: boolean;
|
|
40
|
-
}
|
|
41
|
-
export declare function fetchTigerFull(options: FetchTigerFullOptions, report?: (line: string) => void): Promise<FetchSummary>;
|
|
42
|
-
//# sourceMappingURL=tiger-full.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"tiger-full.d.ts","sourceRoot":"","sources":["../../../../src/tools/fetch/tiger-full.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;GAmBG;AAeH,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAAE,MAAM,eAAe,CAAA;AAmBnE,MAAM,WAAW,qBAAsB,SAAQ,gBAAgB;IAC9D;;;OAGG;IACH,aAAa,CAAC,EAAE,MAAM,CAAA;IACtB;;OAEG;IACH,SAAS,CAAC,EAAE,MAAM,CAAA;IAClB;;OAEG;IACH,WAAW,CAAC,EAAE,MAAM,CAAA;IACpB;;OAEG;IACH,MAAM,CAAC,EAAE,OAAO,CAAA;CAChB;AA0GD,wBAAsB,cAAc,CACnC,OAAO,EAAE,qBAAqB,EAC9B,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,YAAY,CAAC,CA6KvB"}
|