@mailwoman/corpus 9.2.0 → 9.4.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +22 -22
- package/data/PROVENANCE.md +7 -7
- package/lib/adapters/ban/adapter.ts +190 -0
- package/lib/adapters/ban/street-decompose.ts +66 -0
- package/lib/adapters/fcc-bdc/adapter.ts +174 -0
- package/lib/adapters/geonames/adapter.ts +199 -0
- package/lib/adapters/geonames-postal/adapter.ts +122 -0
- package/lib/adapters/gnaf/adapter.ts +149 -0
- package/lib/adapters/gnaf/assemble.ts +225 -0
- package/lib/adapters/index.ts +153 -0
- package/lib/adapters/openaddresses/adapter.ts +251 -0
- package/lib/adapters/overture/adapter.ts +162 -0
- package/lib/adapters/state-hi-schools/adapter.ts +170 -0
- package/lib/adapters/state-hi-schools/workbook.ts +35 -0
- package/lib/adapters/synth-po-box/adapter.ts +204 -0
- package/lib/adapters/tiger/adapter.ts +252 -0
- package/lib/adapters/tiger/street-decompose.ts +83 -0
- package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +167 -0
- package/lib/adapters/usgov-imls-pls/adapter.ts +143 -0
- package/lib/adapters/usgov-irs-bmf/adapter.ts +151 -0
- package/lib/adapters/usgov-nad/adapter.ts +334 -0
- package/lib/adapters/usgov-nppes/adapter.ts +151 -0
- package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +193 -0
- package/lib/adapters/utils/index.ts +307 -0
- package/lib/adapters/wof-admin-jp/adapter.ts +214 -0
- package/lib/adapters/wof-admin-json/adapter.ts +231 -0
- package/lib/adapters/wof-json-rows.ts +129 -0
- package/lib/adapters/wof-postalcode-json/adapter.ts +176 -0
- package/lib/build.ts +378 -0
- package/lib/env.ts +50 -0
- package/lib/index.ts +13 -0
- package/lib/recipes/anchor-absorption.ts +101 -0
- package/lib/recipes/bare-country.ts +95 -0
- package/lib/recipes/boundary-stress.ts +102 -0
- package/lib/recipes/cn-organizational-units.ts +199 -0
- package/lib/recipes/country-balanced.ts +510 -0
- package/lib/recipes/cz-pcfirst-preposition.ts +112 -0
- package/lib/recipes/fr-admin-split.ts +243 -0
- package/lib/recipes/fr-bare-street.ts +171 -0
- package/lib/recipes/fr-fragment.ts +334 -0
- package/lib/recipes/fr-lieudit.ts +301 -0
- package/lib/recipes/fr-order.ts +246 -0
- package/lib/recipes/german.ts +360 -0
- package/lib/recipes/house-venue.ts +93 -0
- package/lib/recipes/index.ts +97 -0
- package/lib/recipes/intersection.ts +619 -0
- package/lib/recipes/locale.ts +600 -0
- package/lib/recipes/nl-postcode.ts +117 -0
- package/lib/recipes/no-fragment.ts +213 -0
- package/lib/recipes/no-street-led.ts +135 -0
- package/lib/recipes/no-street.ts +91 -0
- package/lib/recipes/po-box-cedex.ts +976 -0
- package/lib/recipes/po-box.ts +124 -0
- package/lib/recipes/reviewed-postcode-tail.ts +190 -0
- package/lib/recipes/scaffold.ts +468 -0
- package/lib/recipes/si-bare-village.ts +99 -0
- package/lib/recipes/street-affix.ts +805 -0
- package/lib/recipes/street-bare.ts +102 -0
- package/lib/recipes/street.ts +83 -0
- package/lib/recipes/sub-venue-sources.ts +878 -0
- package/lib/recipes/sub-venue.ts +998 -0
- package/lib/recipes/trailing-region.ts +178 -0
- package/lib/recipes/unit.ts +304 -0
- package/lib/runner.ts +312 -0
- package/lib/synthesizers/anchor-absorption.ts +288 -0
- package/lib/synthesizers/boundary-stress.ts +532 -0
- package/lib/synthesizers/german.ts +260 -0
- package/lib/synthesizers/house-venue.ts +308 -0
- package/lib/synthesizers/intersection.ts +233 -0
- package/lib/synthesizers/no-street.ts +327 -0
- package/lib/synthesizers/po-box.ts +323 -0
- package/lib/synthesizers/street.ts +269 -0
- package/lib/synthesizers/utils.ts +993 -0
- package/lib/test-kit/corpus-recipe.ts +86 -0
- package/lib/test-kit/index.ts +100 -0
- package/lib/tools/align-slice.ts +68 -0
- package/lib/tools/audit.ts +403 -0
- package/lib/tools/corpus-stats.ts +136 -0
- package/lib/tools/fetch/acra-sg.ts +174 -0
- package/lib/tools/fetch/ban.ts +289 -0
- package/lib/tools/fetch/download.ts +477 -0
- package/lib/tools/fetch/gcis-tw.ts +175 -0
- package/lib/tools/fetch/geonames-dump.ts +257 -0
- package/lib/tools/fetch/geonames-postal.ts +180 -0
- package/lib/tools/fetch/houjin-jp.ts +135 -0
- package/lib/tools/fetch/hrsa.ts +59 -0
- package/lib/tools/fetch/imls-pls.ts +149 -0
- package/lib/tools/fetch/index.ts +174 -0
- package/lib/tools/fetch/juso-kr.ts +165 -0
- package/lib/tools/fetch/localdata-kr.ts +194 -0
- package/lib/tools/fetch/nad.ts +341 -0
- package/lib/tools/fetch/nppes.ts +165 -0
- package/lib/tools/fetch/openaddresses.ts +347 -0
- package/lib/tools/fetch/ourairports.ts +170 -0
- package/lib/tools/fetch/ppd.ts +121 -0
- package/lib/tools/fetch/state-hi-schools.ts +161 -0
- package/lib/tools/fetch/state-sources.ts +146 -0
- package/lib/tools/fetch/tiger-full.ts +308 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +384 -0
- package/lib/tools/golden-expand.ts +574 -0
- package/lib/tools/golden-promote.ts +337 -0
- package/lib/tools/golden-relabel-street.ts +686 -0
- package/lib/tools/index.ts +28 -0
- package/lib/tools/ingest-csv.ts +378 -0
- package/lib/tools/jsonl-to-parquet.ts +207 -0
- package/lib/tools/lint-slice-vocab.ts +388 -0
- package/lib/tools/lint-slice.ts +496 -0
- package/lib/tools/overlay-manifest.ts +148 -0
- package/lib/tools/overture-subvenue.ts +209 -0
- package/lib/tools/postcode-triples.ts +363 -0
- package/lib/tools/slice-kryptonite.ts +137 -0
- package/lib/tools/slice-translit.ts +218 -0
- package/lib/tools/sub-venue/harvest.ts +234 -0
- package/lib/tools/sub-venue/head-nouns.ts +245 -0
- package/lib/tools/sub-venue/surfaces.ts +95 -0
- package/lib/tools/sub-venue/table.ts +281 -0
- package/lib/tools/sub-venue/wikidata.ts +85 -0
- package/lib/tools/sub-venue-lexicon.ts +429 -0
- package/lib/tools/sub-venue-promotions.ts +330 -0
- package/lib/types.ts +247 -0
- package/lib/utils/align.ts +330 -0
- package/lib/utils/golden.ts +189 -0
- package/lib/utils/index.ts +14 -0
- package/lib/utils/parquet.ts +582 -0
- package/lib/utils/slice-stats.ts +95 -0
- package/lib/utils/split.ts +279 -0
- package/lib/utils/tokenize.ts +120 -0
- package/lib/utils/wof-json.ts +247 -0
- package/out/adapters/ban/adapter.d.ts.map +1 -0
- package/out/adapters/ban/adapter.js +149 -0
- package/out/adapters/ban/adapter.js.map +1 -0
- package/out/adapters/ban/street-decompose.d.ts.map +1 -0
- package/out/adapters/ban/street-decompose.js +51 -0
- package/out/adapters/ban/street-decompose.js.map +1 -0
- package/out/adapters/fcc-bdc/adapter.d.ts.map +1 -0
- package/out/adapters/fcc-bdc/adapter.js +144 -0
- package/out/adapters/fcc-bdc/adapter.js.map +1 -0
- package/out/adapters/geonames/adapter.d.ts.map +1 -0
- package/out/adapters/geonames/adapter.js +176 -0
- package/out/adapters/geonames/adapter.js.map +1 -0
- package/out/adapters/geonames-postal/adapter.d.ts +54 -0
- package/out/adapters/geonames-postal/adapter.d.ts.map +1 -0
- package/out/adapters/geonames-postal/adapter.js +107 -0
- package/out/adapters/geonames-postal/adapter.js.map +1 -0
- package/out/adapters/gnaf/adapter.d.ts +49 -0
- package/out/adapters/gnaf/adapter.d.ts.map +1 -0
- package/out/adapters/gnaf/adapter.js +124 -0
- package/out/adapters/gnaf/adapter.js.map +1 -0
- package/out/adapters/gnaf/assemble.d.ts +65 -0
- package/out/adapters/gnaf/assemble.d.ts.map +1 -0
- package/out/adapters/gnaf/assemble.js +154 -0
- package/out/adapters/gnaf/assemble.js.map +1 -0
- package/out/adapters/index.d.ts +51 -0
- package/out/adapters/index.d.ts.map +1 -0
- package/out/adapters/index.js +95 -0
- package/out/adapters/index.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -0
- package/out/adapters/openaddresses/adapter.js +186 -0
- package/out/adapters/openaddresses/adapter.js.map +1 -0
- package/out/adapters/overture/adapter.d.ts +48 -0
- package/out/adapters/overture/adapter.d.ts.map +1 -0
- package/out/adapters/overture/adapter.js +125 -0
- package/out/adapters/overture/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/adapter.d.ts +46 -0
- package/out/adapters/state-hi-schools/adapter.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/adapter.js +145 -0
- package/out/adapters/state-hi-schools/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/workbook.d.ts +29 -0
- package/out/adapters/state-hi-schools/workbook.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/workbook.js +20 -0
- package/out/adapters/state-hi-schools/workbook.js.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
- package/out/adapters/synth-po-box/adapter.d.ts.map +1 -0
- package/out/adapters/synth-po-box/adapter.js +140 -0
- package/out/adapters/synth-po-box/adapter.js.map +1 -0
- package/out/adapters/tiger/adapter.d.ts +55 -0
- package/out/adapters/tiger/adapter.d.ts.map +1 -0
- package/out/adapters/tiger/adapter.js +201 -0
- package/out/adapters/tiger/adapter.js.map +1 -0
- package/out/adapters/tiger/street-decompose.d.ts.map +1 -0
- package/out/adapters/tiger/street-decompose.js +68 -0
- package/out/adapters/tiger/street-decompose.js.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +56 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js +132 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts +36 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.js +114 -0
- package/out/adapters/usgov-imls-pls/adapter.js.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts +37 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.js +120 -0
- package/out/adapters/usgov-irs-bmf/adapter.js.map +1 -0
- package/out/adapters/usgov-nad/adapter.d.ts +48 -0
- package/out/adapters/usgov-nad/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nad/adapter.js +249 -0
- package/out/adapters/usgov-nad/adapter.js.map +1 -0
- package/out/adapters/usgov-nppes/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nppes/adapter.js +118 -0
- package/out/adapters/usgov-nppes/adapter.js.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +154 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -0
- package/out/adapters/utils/index.d.ts +191 -0
- package/out/adapters/utils/index.d.ts.map +1 -0
- package/out/adapters/utils/index.js +206 -0
- package/out/adapters/utils/index.js.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.js +161 -0
- package/out/adapters/wof-admin-jp/adapter.js.map +1 -0
- package/out/adapters/wof-admin-json/adapter.d.ts +79 -0
- package/out/adapters/wof-admin-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-json/adapter.js +197 -0
- package/out/adapters/wof-admin-json/adapter.js.map +1 -0
- package/out/adapters/wof-json-rows.d.ts +62 -0
- package/out/adapters/wof-json-rows.d.ts.map +1 -0
- package/out/adapters/wof-json-rows.js +83 -0
- package/out/adapters/wof-json-rows.js.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts +65 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.js +151 -0
- package/out/adapters/wof-postalcode-json/adapter.js.map +1 -0
- package/out/build.d.ts +132 -0
- package/out/build.d.ts.map +1 -0
- package/out/build.js +245 -0
- package/out/build.js.map +1 -0
- package/out/codex/us-fips-state.d.ts.map +1 -0
- package/out/codex/us-fips-state.js.map +1 -0
- package/out/env.d.ts +46 -0
- package/out/env.d.ts.map +1 -0
- package/out/env.js +46 -0
- package/out/env.js.map +1 -0
- package/out/index.d.ts +13 -0
- package/out/index.d.ts.map +1 -0
- package/out/index.js +13 -0
- package/out/index.js.map +1 -0
- package/out/recipes/anchor-absorption.d.ts +20 -0
- package/out/recipes/anchor-absorption.d.ts.map +1 -0
- package/out/recipes/anchor-absorption.js +82 -0
- package/out/recipes/anchor-absorption.js.map +1 -0
- package/out/recipes/bare-country.d.ts +25 -0
- package/out/recipes/bare-country.d.ts.map +1 -0
- package/out/recipes/bare-country.js +88 -0
- package/out/recipes/bare-country.js.map +1 -0
- package/out/recipes/boundary-stress.d.ts +20 -0
- package/out/recipes/boundary-stress.d.ts.map +1 -0
- package/out/recipes/boundary-stress.js +84 -0
- package/out/recipes/boundary-stress.js.map +1 -0
- package/out/recipes/cn-organizational-units.d.ts +36 -0
- package/out/recipes/cn-organizational-units.d.ts.map +1 -0
- package/out/recipes/cn-organizational-units.js +159 -0
- package/out/recipes/cn-organizational-units.js.map +1 -0
- package/out/recipes/country-balanced.d.ts +32 -0
- package/out/recipes/country-balanced.d.ts.map +1 -0
- package/out/recipes/country-balanced.js +394 -0
- package/out/recipes/country-balanced.js.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts +22 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.js +101 -0
- package/out/recipes/cz-pcfirst-preposition.js.map +1 -0
- package/out/recipes/fr-admin-split.d.ts +38 -0
- package/out/recipes/fr-admin-split.d.ts.map +1 -0
- package/out/recipes/fr-admin-split.js +192 -0
- package/out/recipes/fr-admin-split.js.map +1 -0
- package/out/recipes/fr-bare-street.d.ts +28 -0
- package/out/recipes/fr-bare-street.d.ts.map +1 -0
- package/out/recipes/fr-bare-street.js +144 -0
- package/out/recipes/fr-bare-street.js.map +1 -0
- package/out/recipes/fr-fragment.d.ts +77 -0
- package/out/recipes/fr-fragment.d.ts.map +1 -0
- package/out/recipes/fr-fragment.js +277 -0
- package/out/recipes/fr-fragment.js.map +1 -0
- package/out/recipes/fr-lieudit.d.ts +32 -0
- package/out/recipes/fr-lieudit.d.ts.map +1 -0
- package/out/recipes/fr-lieudit.js +227 -0
- package/out/recipes/fr-lieudit.js.map +1 -0
- package/out/recipes/fr-order.d.ts +38 -0
- package/out/recipes/fr-order.d.ts.map +1 -0
- package/out/recipes/fr-order.js +198 -0
- package/out/recipes/fr-order.js.map +1 -0
- package/out/recipes/german.d.ts +44 -0
- package/out/recipes/german.d.ts.map +1 -0
- package/out/recipes/german.js +289 -0
- package/out/recipes/german.js.map +1 -0
- package/out/recipes/house-venue.d.ts +18 -0
- package/out/recipes/house-venue.d.ts.map +1 -0
- package/out/recipes/house-venue.js +74 -0
- package/out/recipes/house-venue.js.map +1 -0
- package/out/recipes/index.d.ts +24 -0
- package/out/recipes/index.d.ts.map +1 -0
- package/out/recipes/index.js +91 -0
- package/out/recipes/index.js.map +1 -0
- package/out/recipes/intersection.d.ts +42 -0
- package/out/recipes/intersection.d.ts.map +1 -0
- package/out/recipes/intersection.js +453 -0
- package/out/recipes/intersection.js.map +1 -0
- package/out/recipes/locale.d.ts +136 -0
- package/out/recipes/locale.d.ts.map +1 -0
- package/out/recipes/locale.js +460 -0
- package/out/recipes/locale.js.map +1 -0
- package/out/recipes/nl-postcode.d.ts +26 -0
- package/out/recipes/nl-postcode.d.ts.map +1 -0
- package/out/recipes/nl-postcode.js +103 -0
- package/out/recipes/nl-postcode.js.map +1 -0
- package/out/recipes/no-fragment.d.ts +43 -0
- package/out/recipes/no-fragment.d.ts.map +1 -0
- package/out/recipes/no-fragment.js +183 -0
- package/out/recipes/no-fragment.js.map +1 -0
- package/out/recipes/no-street-led.d.ts +24 -0
- package/out/recipes/no-street-led.d.ts.map +1 -0
- package/out/recipes/no-street-led.js +114 -0
- package/out/recipes/no-street-led.js.map +1 -0
- package/out/recipes/no-street.d.ts +18 -0
- package/out/recipes/no-street.d.ts.map +1 -0
- package/out/recipes/no-street.js +72 -0
- package/out/recipes/no-street.js.map +1 -0
- package/out/recipes/po-box-cedex.d.ts +38 -0
- package/out/recipes/po-box-cedex.d.ts.map +1 -0
- package/out/recipes/po-box-cedex.js +768 -0
- package/out/recipes/po-box-cedex.js.map +1 -0
- package/out/recipes/po-box.d.ts +17 -0
- package/out/recipes/po-box.d.ts.map +1 -0
- package/out/recipes/po-box.js +101 -0
- package/out/recipes/po-box.js.map +1 -0
- package/out/recipes/reviewed-postcode-tail.d.ts +47 -0
- package/out/recipes/reviewed-postcode-tail.d.ts.map +1 -0
- package/out/recipes/reviewed-postcode-tail.js +125 -0
- package/out/recipes/reviewed-postcode-tail.js.map +1 -0
- package/out/recipes/scaffold.d.ts +323 -0
- package/out/recipes/scaffold.d.ts.map +1 -0
- package/out/recipes/scaffold.js +174 -0
- package/out/recipes/scaffold.js.map +1 -0
- package/out/recipes/si-bare-village.d.ts +32 -0
- package/out/recipes/si-bare-village.d.ts.map +1 -0
- package/out/recipes/si-bare-village.js +89 -0
- package/out/recipes/si-bare-village.js.map +1 -0
- package/out/recipes/street-affix.d.ts +89 -0
- package/out/recipes/street-affix.d.ts.map +1 -0
- package/out/recipes/street-affix.js +563 -0
- package/out/recipes/street-affix.js.map +1 -0
- package/out/recipes/street-bare.d.ts +25 -0
- package/out/recipes/street-bare.d.ts.map +1 -0
- package/out/recipes/street-bare.js +87 -0
- package/out/recipes/street-bare.js.map +1 -0
- package/out/recipes/street.d.ts +15 -0
- package/out/recipes/street.d.ts.map +1 -0
- package/out/recipes/street.js +70 -0
- package/out/recipes/street.js.map +1 -0
- package/out/recipes/sub-venue-sources.d.ts +229 -0
- package/out/recipes/sub-venue-sources.d.ts.map +1 -0
- package/out/recipes/sub-venue-sources.js +654 -0
- package/out/recipes/sub-venue-sources.js.map +1 -0
- package/out/recipes/sub-venue.d.ts +269 -0
- package/out/recipes/sub-venue.d.ts.map +1 -0
- package/out/recipes/sub-venue.js +726 -0
- package/out/recipes/sub-venue.js.map +1 -0
- package/out/recipes/trailing-region.d.ts +74 -0
- package/out/recipes/trailing-region.d.ts.map +1 -0
- package/out/recipes/trailing-region.js +158 -0
- package/out/recipes/trailing-region.js.map +1 -0
- package/out/recipes/unit.d.ts +29 -0
- package/out/recipes/unit.d.ts.map +1 -0
- package/out/recipes/unit.js +231 -0
- package/out/recipes/unit.js.map +1 -0
- package/out/runner.d.ts +130 -0
- package/out/runner.d.ts.map +1 -0
- package/out/runner.js +185 -0
- package/out/runner.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +63 -0
- package/out/synthesizers/anchor-absorption.d.ts.map +1 -0
- package/out/synthesizers/anchor-absorption.js +221 -0
- package/out/synthesizers/anchor-absorption.js.map +1 -0
- package/out/synthesizers/boundary-stress.d.ts +78 -0
- package/out/synthesizers/boundary-stress.d.ts.map +1 -0
- package/out/synthesizers/boundary-stress.js +455 -0
- package/out/synthesizers/boundary-stress.js.map +1 -0
- package/out/synthesizers/german.d.ts +115 -0
- package/out/synthesizers/german.d.ts.map +1 -0
- package/out/synthesizers/german.js +149 -0
- package/out/synthesizers/german.js.map +1 -0
- package/out/synthesizers/house-venue.d.ts +56 -0
- package/out/synthesizers/house-venue.d.ts.map +1 -0
- package/out/synthesizers/house-venue.js +247 -0
- package/out/synthesizers/house-venue.js.map +1 -0
- package/out/synthesizers/intersection.d.ts +52 -0
- package/out/synthesizers/intersection.d.ts.map +1 -0
- package/out/synthesizers/intersection.js +175 -0
- package/out/synthesizers/intersection.js.map +1 -0
- package/out/synthesizers/no-street.d.ts +72 -0
- package/out/synthesizers/no-street.d.ts.map +1 -0
- package/out/synthesizers/no-street.js +262 -0
- package/out/synthesizers/no-street.js.map +1 -0
- package/out/synthesizers/po-box.d.ts +108 -0
- package/out/synthesizers/po-box.d.ts.map +1 -0
- package/out/synthesizers/po-box.js +250 -0
- package/out/synthesizers/po-box.js.map +1 -0
- package/out/synthesizers/street.d.ts +54 -0
- package/out/synthesizers/street.d.ts.map +1 -0
- package/out/synthesizers/street.js +218 -0
- package/out/synthesizers/street.js.map +1 -0
- package/out/synthesizers/utils.d.ts +241 -0
- package/out/synthesizers/utils.d.ts.map +1 -0
- package/out/synthesizers/utils.js +776 -0
- package/out/synthesizers/utils.js.map +1 -0
- package/out/test-kit/corpus-recipe.d.ts +59 -0
- package/out/test-kit/corpus-recipe.d.ts.map +1 -0
- package/out/test-kit/corpus-recipe.js +39 -0
- package/out/test-kit/corpus-recipe.js.map +1 -0
- package/out/test-kit/index.d.ts +48 -0
- package/out/test-kit/index.d.ts.map +1 -0
- package/out/test-kit/index.js +78 -0
- package/out/test-kit/index.js.map +1 -0
- package/out/tools/align-slice.d.ts +7 -0
- package/out/tools/align-slice.d.ts.map +1 -0
- package/out/tools/align-slice.js +55 -0
- package/out/tools/align-slice.js.map +1 -0
- package/out/tools/audit.d.ts +29 -0
- package/out/tools/audit.d.ts.map +1 -0
- package/out/tools/audit.js +282 -0
- package/out/tools/audit.js.map +1 -0
- package/out/tools/corpus-stats.d.ts +44 -0
- package/out/tools/corpus-stats.d.ts.map +1 -0
- package/out/tools/corpus-stats.js +102 -0
- package/out/tools/corpus-stats.js.map +1 -0
- package/out/tools/fetch/acra-sg.d.ts +23 -0
- package/out/tools/fetch/acra-sg.d.ts.map +1 -0
- package/out/tools/fetch/acra-sg.js +126 -0
- package/out/tools/fetch/acra-sg.js.map +1 -0
- package/out/tools/fetch/ban.d.ts +31 -0
- package/out/tools/fetch/ban.d.ts.map +1 -0
- package/out/tools/fetch/ban.js +239 -0
- package/out/tools/fetch/ban.js.map +1 -0
- package/out/tools/fetch/download.d.ts +182 -0
- package/out/tools/fetch/download.d.ts.map +1 -0
- package/out/tools/fetch/download.js +318 -0
- package/out/tools/fetch/download.js.map +1 -0
- package/out/tools/fetch/gcis-tw.d.ts +23 -0
- package/out/tools/fetch/gcis-tw.d.ts.map +1 -0
- package/out/tools/fetch/gcis-tw.js +135 -0
- package/out/tools/fetch/gcis-tw.js.map +1 -0
- package/out/tools/fetch/geonames-dump.d.ts +91 -0
- package/out/tools/fetch/geonames-dump.d.ts.map +1 -0
- package/out/tools/fetch/geonames-dump.js +171 -0
- package/out/tools/fetch/geonames-dump.js.map +1 -0
- package/out/tools/fetch/geonames-postal.d.ts +76 -0
- package/out/tools/fetch/geonames-postal.d.ts.map +1 -0
- package/out/tools/fetch/geonames-postal.js +126 -0
- package/out/tools/fetch/geonames-postal.js.map +1 -0
- package/out/tools/fetch/houjin-jp.d.ts +24 -0
- package/out/tools/fetch/houjin-jp.d.ts.map +1 -0
- package/out/tools/fetch/houjin-jp.js +102 -0
- package/out/tools/fetch/houjin-jp.js.map +1 -0
- package/out/tools/fetch/hrsa.d.ts +18 -0
- package/out/tools/fetch/hrsa.d.ts.map +1 -0
- package/out/tools/fetch/hrsa.js +46 -0
- package/out/tools/fetch/hrsa.js.map +1 -0
- package/out/tools/fetch/imls-pls.d.ts +25 -0
- package/out/tools/fetch/imls-pls.d.ts.map +1 -0
- package/out/tools/fetch/imls-pls.js +108 -0
- package/out/tools/fetch/imls-pls.js.map +1 -0
- package/out/tools/fetch/index.d.ts +171 -0
- package/out/tools/fetch/index.d.ts.map +1 -0
- package/out/tools/fetch/index.js +170 -0
- package/out/tools/fetch/index.js.map +1 -0
- package/out/tools/fetch/juso-kr.d.ts +30 -0
- package/out/tools/fetch/juso-kr.d.ts.map +1 -0
- package/out/tools/fetch/juso-kr.js +120 -0
- package/out/tools/fetch/juso-kr.js.map +1 -0
- package/out/tools/fetch/localdata-kr.d.ts +30 -0
- package/out/tools/fetch/localdata-kr.d.ts.map +1 -0
- package/out/tools/fetch/localdata-kr.js +139 -0
- package/out/tools/fetch/localdata-kr.js.map +1 -0
- package/out/tools/fetch/nad.d.ts +70 -0
- package/out/tools/fetch/nad.d.ts.map +1 -0
- package/out/tools/fetch/nad.js +234 -0
- package/out/tools/fetch/nad.js.map +1 -0
- package/out/tools/fetch/nppes.d.ts +26 -0
- package/out/tools/fetch/nppes.d.ts.map +1 -0
- package/out/tools/fetch/nppes.js +126 -0
- package/out/tools/fetch/nppes.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +9 -0
- package/out/tools/fetch/openaddresses.d.ts.map +1 -0
- package/out/tools/fetch/openaddresses.js +279 -0
- package/out/tools/fetch/openaddresses.js.map +1 -0
- package/out/tools/fetch/ourairports.d.ts +45 -0
- package/out/tools/fetch/ourairports.d.ts.map +1 -0
- package/out/tools/fetch/ourairports.js +128 -0
- package/out/tools/fetch/ourairports.js.map +1 -0
- package/out/tools/fetch/ppd.d.ts.map +1 -0
- package/out/tools/fetch/ppd.js +85 -0
- package/out/tools/fetch/ppd.js.map +1 -0
- package/out/tools/fetch/state-hi-schools.d.ts +26 -0
- package/out/tools/fetch/state-hi-schools.d.ts.map +1 -0
- package/out/tools/fetch/state-hi-schools.js +112 -0
- package/out/tools/fetch/state-hi-schools.js.map +1 -0
- package/out/tools/fetch/state-sources.d.ts +26 -0
- package/out/tools/fetch/state-sources.d.ts.map +1 -0
- package/out/tools/fetch/state-sources.js +111 -0
- package/out/tools/fetch/state-sources.js.map +1 -0
- package/out/tools/fetch/tiger-full.d.ts +22 -0
- package/out/tools/fetch/tiger-full.d.ts.map +1 -0
- package/out/tools/fetch/tiger-full.js +217 -0
- package/out/tools/fetch/tiger-full.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +171 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.js +274 -0
- package/out/tools/fetch/wikidata-subvenue.js.map +1 -0
- package/out/tools/gb-title-case.d.ts.map +1 -0
- package/out/tools/gb-title-case.js.map +1 -0
- package/out/tools/golden-expand.d.ts +90 -0
- package/out/tools/golden-expand.d.ts.map +1 -0
- package/out/tools/golden-expand.js +406 -0
- package/out/tools/golden-expand.js.map +1 -0
- package/out/tools/golden-promote.d.ts.map +1 -0
- package/out/tools/golden-promote.js +240 -0
- package/out/tools/golden-promote.js.map +1 -0
- package/out/tools/golden-relabel-street.d.ts +196 -0
- package/out/tools/golden-relabel-street.d.ts.map +1 -0
- package/out/tools/golden-relabel-street.js +439 -0
- package/out/tools/golden-relabel-street.js.map +1 -0
- package/out/tools/index.d.ts +28 -0
- package/out/tools/index.d.ts.map +1 -0
- package/out/tools/index.js +28 -0
- package/out/tools/index.js.map +1 -0
- package/out/tools/ingest-csv.d.ts.map +1 -0
- package/out/tools/ingest-csv.js +265 -0
- package/out/tools/ingest-csv.js.map +1 -0
- package/out/tools/jsonl-to-parquet.d.ts +61 -0
- package/out/tools/jsonl-to-parquet.d.ts.map +1 -0
- package/out/tools/jsonl-to-parquet.js +150 -0
- package/out/tools/jsonl-to-parquet.js.map +1 -0
- package/out/tools/lint-slice-vocab.d.ts +90 -0
- package/out/tools/lint-slice-vocab.d.ts.map +1 -0
- package/out/tools/lint-slice-vocab.js +267 -0
- package/out/tools/lint-slice-vocab.js.map +1 -0
- package/out/tools/lint-slice.d.ts +93 -0
- package/out/tools/lint-slice.d.ts.map +1 -0
- package/out/tools/lint-slice.js +322 -0
- package/out/tools/lint-slice.js.map +1 -0
- package/out/tools/overlay-manifest.d.ts +39 -0
- package/out/tools/overlay-manifest.d.ts.map +1 -0
- package/out/tools/overlay-manifest.js +90 -0
- package/out/tools/overlay-manifest.js.map +1 -0
- package/out/tools/overture-subvenue.d.ts +112 -0
- package/out/tools/overture-subvenue.d.ts.map +1 -0
- package/out/tools/overture-subvenue.js +139 -0
- package/out/tools/overture-subvenue.js.map +1 -0
- package/out/tools/postcode-triples.d.ts +174 -0
- package/out/tools/postcode-triples.d.ts.map +1 -0
- package/out/tools/postcode-triples.js +292 -0
- package/out/tools/postcode-triples.js.map +1 -0
- package/out/tools/slice-kryptonite.d.ts +32 -0
- package/out/tools/slice-kryptonite.d.ts.map +1 -0
- package/out/tools/slice-kryptonite.js +99 -0
- package/out/tools/slice-kryptonite.js.map +1 -0
- package/out/tools/slice-translit.d.ts +51 -0
- package/out/tools/slice-translit.d.ts.map +1 -0
- package/out/tools/slice-translit.js +166 -0
- package/out/tools/slice-translit.js.map +1 -0
- package/out/tools/sub-venue/harvest.d.ts +100 -0
- package/out/tools/sub-venue/harvest.d.ts.map +1 -0
- package/out/tools/sub-venue/harvest.js +168 -0
- package/out/tools/sub-venue/harvest.js.map +1 -0
- package/out/tools/sub-venue/head-nouns.d.ts +50 -0
- package/out/tools/sub-venue/head-nouns.d.ts.map +1 -0
- package/out/tools/sub-venue/head-nouns.js +213 -0
- package/out/tools/sub-venue/head-nouns.js.map +1 -0
- package/out/tools/sub-venue/surfaces.d.ts +45 -0
- package/out/tools/sub-venue/surfaces.d.ts.map +1 -0
- package/out/tools/sub-venue/surfaces.js +77 -0
- package/out/tools/sub-venue/surfaces.js.map +1 -0
- package/out/tools/sub-venue/table.d.ts +229 -0
- package/out/tools/sub-venue/table.d.ts.map +1 -0
- package/out/tools/sub-venue/table.js +108 -0
- package/out/tools/sub-venue/table.js.map +1 -0
- package/out/tools/sub-venue/wikidata.d.ts +26 -0
- package/out/tools/sub-venue/wikidata.d.ts.map +1 -0
- package/out/tools/sub-venue/wikidata.js +62 -0
- package/out/tools/sub-venue/wikidata.js.map +1 -0
- package/out/tools/sub-venue-lexicon.d.ts +156 -0
- package/out/tools/sub-venue-lexicon.d.ts.map +1 -0
- package/out/tools/sub-venue-lexicon.js +283 -0
- package/out/tools/sub-venue-lexicon.js.map +1 -0
- package/out/tools/sub-venue-promotions.d.ts +94 -0
- package/out/tools/sub-venue-promotions.d.ts.map +1 -0
- package/out/tools/sub-venue-promotions.js +266 -0
- package/out/tools/sub-venue-promotions.js.map +1 -0
- package/out/types.d.ts +221 -0
- package/out/types.d.ts.map +1 -0
- package/out/types.js.map +1 -0
- package/out/utils/align.d.ts +93 -0
- package/out/utils/align.d.ts.map +1 -0
- package/out/utils/align.js +234 -0
- package/out/utils/align.js.map +1 -0
- package/out/utils/golden.d.ts +85 -0
- package/out/utils/golden.d.ts.map +1 -0
- package/out/utils/golden.js +127 -0
- package/out/utils/golden.js.map +1 -0
- package/out/utils/index.d.ts +14 -0
- package/out/utils/index.d.ts.map +1 -0
- package/out/utils/index.js +14 -0
- package/out/utils/index.js.map +1 -0
- package/out/utils/license.d.ts.map +1 -0
- package/out/utils/license.js.map +1 -0
- package/out/utils/parquet.d.ts +178 -0
- package/out/utils/parquet.d.ts.map +1 -0
- package/out/utils/parquet.js +371 -0
- package/out/utils/parquet.js.map +1 -0
- package/out/utils/slice-stats.d.ts +52 -0
- package/out/utils/slice-stats.d.ts.map +1 -0
- package/out/utils/slice-stats.js +58 -0
- package/out/utils/slice-stats.js.map +1 -0
- package/out/utils/split.d.ts +128 -0
- package/out/utils/split.d.ts.map +1 -0
- package/out/utils/split.js +204 -0
- package/out/utils/split.js.map +1 -0
- package/out/utils/tokenize.d.ts +64 -0
- package/out/utils/tokenize.d.ts.map +1 -0
- package/out/utils/tokenize.js +82 -0
- package/out/utils/tokenize.js.map +1 -0
- package/out/utils/wof-json.d.ts +113 -0
- package/out/utils/wof-json.d.ts.map +1 -0
- package/out/utils/wof-json.js +173 -0
- package/out/utils/wof-json.js.map +1 -0
- package/package.json +259 -194
- package/out/src/adapters/ban/adapter.d.ts.map +0 -1
- package/out/src/adapters/ban/adapter.js +0 -149
- package/out/src/adapters/ban/adapter.js.map +0 -1
- package/out/src/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/ban/street-decompose.js +0 -75
- package/out/src/adapters/ban/street-decompose.js.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.d.ts.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.js +0 -144
- package/out/src/adapters/fcc-bdc/adapter.js.map +0 -1
- package/out/src/adapters/geonames/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames/adapter.js +0 -176
- package/out/src/adapters/geonames/adapter.js.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.d.ts +0 -41
- package/out/src/adapters/geonames-postal/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.js +0 -104
- package/out/src/adapters/geonames-postal/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/adapter.d.ts +0 -49
- package/out/src/adapters/gnaf/adapter.d.ts.map +0 -1
- package/out/src/adapters/gnaf/adapter.js +0 -124
- package/out/src/adapters/gnaf/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/assemble.d.ts +0 -65
- package/out/src/adapters/gnaf/assemble.d.ts.map +0 -1
- package/out/src/adapters/gnaf/assemble.js +0 -154
- package/out/src/adapters/gnaf/assemble.js.map +0 -1
- package/out/src/adapters/index.d.ts +0 -51
- package/out/src/adapters/index.d.ts.map +0 -1
- package/out/src/adapters/index.js +0 -95
- package/out/src/adapters/index.js.map +0 -1
- package/out/src/adapters/openaddresses/adapter.d.ts.map +0 -1
- package/out/src/adapters/openaddresses/adapter.js +0 -186
- package/out/src/adapters/openaddresses/adapter.js.map +0 -1
- package/out/src/adapters/overture/adapter.d.ts +0 -48
- package/out/src/adapters/overture/adapter.d.ts.map +0 -1
- package/out/src/adapters/overture/adapter.js +0 -125
- package/out/src/adapters/overture/adapter.js.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.d.ts +0 -47
- package/out/src/adapters/state-hi-schools/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.js +0 -133
- package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.d.ts.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.js +0 -140
- package/out/src/adapters/synth-po-box/adapter.js.map +0 -1
- package/out/src/adapters/tiger/adapter.d.ts +0 -55
- package/out/src/adapters/tiger/adapter.d.ts.map +0 -1
- package/out/src/adapters/tiger/adapter.js +0 -201
- package/out/src/adapters/tiger/adapter.js.map +0 -1
- package/out/src/adapters/tiger/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/tiger/street-decompose.js +0 -90
- package/out/src/adapters/tiger/street-decompose.js.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -47
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +0 -139
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts +0 -36
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.js +0 -114
- package/out/src/adapters/usgov-imls-pls/adapter.js.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.js +0 -124
- package/out/src/adapters/usgov-irs-bmf/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.d.ts +0 -48
- package/out/src/adapters/usgov-nad/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.js +0 -252
- package/out/src/adapters/usgov-nad/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.js +0 -116
- package/out/src/adapters/usgov-nppes/adapter.js.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -156
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
- package/out/src/adapters/utils/index.d.ts +0 -150
- package/out/src/adapters/utils/index.d.ts.map +0 -1
- package/out/src/adapters/utils/index.js +0 -159
- package/out/src/adapters/utils/index.js.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.js +0 -164
- package/out/src/adapters/wof-admin-jp/adapter.js.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.d.ts +0 -82
- package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.js +0 -224
- package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
- package/out/src/adapters/wof-json-rows.d.ts +0 -32
- package/out/src/adapters/wof-json-rows.d.ts.map +0 -1
- package/out/src/adapters/wof-json-rows.js +0 -45
- package/out/src/adapters/wof-json-rows.js.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -65
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.js +0 -160
- package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
- package/out/src/build.d.ts +0 -132
- package/out/src/build.d.ts.map +0 -1
- package/out/src/build.js +0 -251
- package/out/src/build.js.map +0 -1
- package/out/src/codex/us-fips-state.d.ts.map +0 -1
- package/out/src/codex/us-fips-state.js.map +0 -1
- package/out/src/index.d.ts +0 -14
- package/out/src/index.d.ts.map +0 -1
- package/out/src/index.js +0 -14
- package/out/src/index.js.map +0 -1
- package/out/src/name-prone-us-suffixes.d.ts +0 -12
- package/out/src/name-prone-us-suffixes.d.ts.map +0 -1
- package/out/src/name-prone-us-suffixes.js +0 -12
- package/out/src/name-prone-us-suffixes.js.map +0 -1
- package/out/src/parquet-wrapper/index.d.ts +0 -9
- package/out/src/parquet-wrapper/index.d.ts.map +0 -1
- package/out/src/parquet-wrapper/index.js +0 -9
- package/out/src/parquet-wrapper/index.js.map +0 -1
- package/out/src/parquet-wrapper/reader.d.ts +0 -34
- package/out/src/parquet-wrapper/reader.d.ts.map +0 -1
- package/out/src/parquet-wrapper/reader.js +0 -69
- package/out/src/parquet-wrapper/reader.js.map +0 -1
- package/out/src/parquet-wrapper/schema.d.ts +0 -49
- package/out/src/parquet-wrapper/schema.d.ts.map +0 -1
- package/out/src/parquet-wrapper/schema.js +0 -55
- package/out/src/parquet-wrapper/schema.js.map +0 -1
- package/out/src/parquet-wrapper/writer.d.ts +0 -46
- package/out/src/parquet-wrapper/writer.d.ts.map +0 -1
- package/out/src/parquet-wrapper/writer.js +0 -76
- package/out/src/parquet-wrapper/writer.js.map +0 -1
- package/out/src/runner.d.ts +0 -126
- package/out/src/runner.d.ts.map +0 -1
- package/out/src/runner.js +0 -189
- package/out/src/runner.js.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.d.ts +0 -20
- package/out/src/shard-recipes/anchor-absorption.d.ts.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.js +0 -82
- package/out/src/shard-recipes/anchor-absorption.js.map +0 -1
- package/out/src/shard-recipes/bare-country.d.ts +0 -25
- package/out/src/shard-recipes/bare-country.d.ts.map +0 -1
- package/out/src/shard-recipes/bare-country.js +0 -87
- package/out/src/shard-recipes/bare-country.js.map +0 -1
- package/out/src/shard-recipes/boundary-stress.d.ts +0 -20
- package/out/src/shard-recipes/boundary-stress.d.ts.map +0 -1
- package/out/src/shard-recipes/boundary-stress.js +0 -83
- package/out/src/shard-recipes/boundary-stress.js.map +0 -1
- package/out/src/shard-recipes/country-balanced.d.ts +0 -32
- package/out/src/shard-recipes/country-balanced.d.ts.map +0 -1
- package/out/src/shard-recipes/country-balanced.js +0 -406
- package/out/src/shard-recipes/country-balanced.js.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts +0 -22
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.js +0 -100
- package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.d.ts +0 -38
- package/out/src/shard-recipes/fr-admin-split.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.js +0 -188
- package/out/src/shard-recipes/fr-admin-split.js.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.d.ts +0 -28
- package/out/src/shard-recipes/fr-bare-street.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.js +0 -143
- package/out/src/shard-recipes/fr-bare-street.js.map +0 -1
- package/out/src/shard-recipes/fr-fragment.d.ts +0 -77
- package/out/src/shard-recipes/fr-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-fragment.js +0 -276
- package/out/src/shard-recipes/fr-fragment.js.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.d.ts +0 -32
- package/out/src/shard-recipes/fr-lieudit.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.js +0 -226
- package/out/src/shard-recipes/fr-lieudit.js.map +0 -1
- package/out/src/shard-recipes/fr-order.d.ts +0 -38
- package/out/src/shard-recipes/fr-order.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-order.js +0 -208
- package/out/src/shard-recipes/fr-order.js.map +0 -1
- package/out/src/shard-recipes/german.d.ts +0 -23
- package/out/src/shard-recipes/german.d.ts.map +0 -1
- package/out/src/shard-recipes/german.js +0 -132
- package/out/src/shard-recipes/german.js.map +0 -1
- package/out/src/shard-recipes/house-venue.d.ts +0 -18
- package/out/src/shard-recipes/house-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/house-venue.js +0 -74
- package/out/src/shard-recipes/house-venue.js.map +0 -1
- package/out/src/shard-recipes/index.d.ts +0 -24
- package/out/src/shard-recipes/index.d.ts.map +0 -1
- package/out/src/shard-recipes/index.js +0 -89
- package/out/src/shard-recipes/index.js.map +0 -1
- package/out/src/shard-recipes/intersection.d.ts +0 -42
- package/out/src/shard-recipes/intersection.d.ts.map +0 -1
- package/out/src/shard-recipes/intersection.js +0 -460
- package/out/src/shard-recipes/intersection.js.map +0 -1
- package/out/src/shard-recipes/locale.d.ts +0 -135
- package/out/src/shard-recipes/locale.d.ts.map +0 -1
- package/out/src/shard-recipes/locale.js +0 -459
- package/out/src/shard-recipes/locale.js.map +0 -1
- package/out/src/shard-recipes/nl-postcode.d.ts +0 -26
- package/out/src/shard-recipes/nl-postcode.d.ts.map +0 -1
- package/out/src/shard-recipes/nl-postcode.js +0 -102
- package/out/src/shard-recipes/nl-postcode.js.map +0 -1
- package/out/src/shard-recipes/no-fragment.d.ts +0 -43
- package/out/src/shard-recipes/no-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/no-fragment.js +0 -188
- package/out/src/shard-recipes/no-fragment.js.map +0 -1
- package/out/src/shard-recipes/no-street-led.d.ts +0 -24
- package/out/src/shard-recipes/no-street-led.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street-led.js +0 -121
- package/out/src/shard-recipes/no-street-led.js.map +0 -1
- package/out/src/shard-recipes/no-street.d.ts +0 -18
- package/out/src/shard-recipes/no-street.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street.js +0 -72
- package/out/src/shard-recipes/no-street.js.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.d.ts +0 -38
- package/out/src/shard-recipes/po-box-cedex.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.js +0 -726
- package/out/src/shard-recipes/po-box-cedex.js.map +0 -1
- package/out/src/shard-recipes/po-box.d.ts +0 -17
- package/out/src/shard-recipes/po-box.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box.js +0 -101
- package/out/src/shard-recipes/po-box.js.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts +0 -47
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.js +0 -125
- package/out/src/shard-recipes/reviewed-postcode-tail.js.map +0 -1
- package/out/src/shard-recipes/scaffold.d.ts +0 -246
- package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
- package/out/src/shard-recipes/scaffold.js +0 -137
- package/out/src/shard-recipes/scaffold.js.map +0 -1
- package/out/src/shard-recipes/si-bare-village.d.ts +0 -32
- package/out/src/shard-recipes/si-bare-village.d.ts.map +0 -1
- package/out/src/shard-recipes/si-bare-village.js +0 -88
- package/out/src/shard-recipes/si-bare-village.js.map +0 -1
- package/out/src/shard-recipes/street-affix.d.ts +0 -89
- package/out/src/shard-recipes/street-affix.d.ts.map +0 -1
- package/out/src/shard-recipes/street-affix.js +0 -578
- package/out/src/shard-recipes/street-affix.js.map +0 -1
- package/out/src/shard-recipes/street-bare.d.ts +0 -25
- package/out/src/shard-recipes/street-bare.d.ts.map +0 -1
- package/out/src/shard-recipes/street-bare.js +0 -86
- package/out/src/shard-recipes/street-bare.js.map +0 -1
- package/out/src/shard-recipes/street.d.ts +0 -15
- package/out/src/shard-recipes/street.d.ts.map +0 -1
- package/out/src/shard-recipes/street.js +0 -69
- package/out/src/shard-recipes/street.js.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.d.ts +0 -228
- package/out/src/shard-recipes/sub-venue-sources.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.js +0 -664
- package/out/src/shard-recipes/sub-venue-sources.js.map +0 -1
- package/out/src/shard-recipes/sub-venue.d.ts +0 -269
- package/out/src/shard-recipes/sub-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue.js +0 -710
- package/out/src/shard-recipes/sub-venue.js.map +0 -1
- package/out/src/shard-recipes/trailing-region.d.ts +0 -74
- package/out/src/shard-recipes/trailing-region.d.ts.map +0 -1
- package/out/src/shard-recipes/trailing-region.js +0 -157
- package/out/src/shard-recipes/trailing-region.js.map +0 -1
- package/out/src/shard-recipes/unit.d.ts +0 -29
- package/out/src/shard-recipes/unit.d.ts.map +0 -1
- package/out/src/shard-recipes/unit.js +0 -243
- package/out/src/shard-recipes/unit.js.map +0 -1
- package/out/src/synthesizers/anchor-absorption.d.ts +0 -63
- package/out/src/synthesizers/anchor-absorption.d.ts.map +0 -1
- package/out/src/synthesizers/anchor-absorption.js +0 -223
- package/out/src/synthesizers/anchor-absorption.js.map +0 -1
- package/out/src/synthesizers/boundary-stress.d.ts +0 -78
- package/out/src/synthesizers/boundary-stress.d.ts.map +0 -1
- package/out/src/synthesizers/boundary-stress.js +0 -455
- package/out/src/synthesizers/boundary-stress.js.map +0 -1
- package/out/src/synthesizers/german.d.ts +0 -107
- package/out/src/synthesizers/german.d.ts.map +0 -1
- package/out/src/synthesizers/german.js +0 -148
- package/out/src/synthesizers/german.js.map +0 -1
- package/out/src/synthesizers/house-venue.d.ts +0 -56
- package/out/src/synthesizers/house-venue.d.ts.map +0 -1
- package/out/src/synthesizers/house-venue.js +0 -267
- package/out/src/synthesizers/house-venue.js.map +0 -1
- package/out/src/synthesizers/intersection.d.ts +0 -52
- package/out/src/synthesizers/intersection.d.ts.map +0 -1
- package/out/src/synthesizers/intersection.js +0 -175
- package/out/src/synthesizers/intersection.js.map +0 -1
- package/out/src/synthesizers/no-street.d.ts +0 -72
- package/out/src/synthesizers/no-street.d.ts.map +0 -1
- package/out/src/synthesizers/no-street.js +0 -282
- package/out/src/synthesizers/no-street.js.map +0 -1
- package/out/src/synthesizers/po-box.d.ts +0 -104
- package/out/src/synthesizers/po-box.d.ts.map +0 -1
- package/out/src/synthesizers/po-box.js +0 -266
- package/out/src/synthesizers/po-box.js.map +0 -1
- package/out/src/synthesizers/street.d.ts +0 -54
- package/out/src/synthesizers/street.d.ts.map +0 -1
- package/out/src/synthesizers/street.js +0 -221
- package/out/src/synthesizers/street.js.map +0 -1
- package/out/src/synthesizers/utils.d.ts +0 -203
- package/out/src/synthesizers/utils.d.ts.map +0 -1
- package/out/src/synthesizers/utils.js +0 -708
- package/out/src/synthesizers/utils.js.map +0 -1
- package/out/src/tools/align-shard.d.ts +0 -8
- package/out/src/tools/align-shard.d.ts.map +0 -1
- package/out/src/tools/align-shard.js +0 -56
- package/out/src/tools/align-shard.js.map +0 -1
- package/out/src/tools/audit.d.ts +0 -28
- package/out/src/tools/audit.d.ts.map +0 -1
- package/out/src/tools/audit.js +0 -285
- package/out/src/tools/audit.js.map +0 -1
- package/out/src/tools/corpus-stats.d.ts +0 -44
- package/out/src/tools/corpus-stats.d.ts.map +0 -1
- package/out/src/tools/corpus-stats.js +0 -138
- package/out/src/tools/corpus-stats.js.map +0 -1
- package/out/src/tools/fetch/ban.d.ts +0 -31
- package/out/src/tools/fetch/ban.d.ts.map +0 -1
- package/out/src/tools/fetch/ban.js +0 -239
- package/out/src/tools/fetch/ban.js.map +0 -1
- package/out/src/tools/fetch/download.d.ts +0 -78
- package/out/src/tools/fetch/download.d.ts.map +0 -1
- package/out/src/tools/fetch/download.js +0 -116
- package/out/src/tools/fetch/download.js.map +0 -1
- package/out/src/tools/fetch/geonames-dump.d.ts +0 -87
- package/out/src/tools/fetch/geonames-dump.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-dump.js +0 -178
- package/out/src/tools/fetch/geonames-dump.js.map +0 -1
- package/out/src/tools/fetch/geonames-postal.d.ts +0 -76
- package/out/src/tools/fetch/geonames-postal.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-postal.js +0 -125
- package/out/src/tools/fetch/geonames-postal.js.map +0 -1
- package/out/src/tools/fetch/hrsa.d.ts +0 -18
- package/out/src/tools/fetch/hrsa.d.ts.map +0 -1
- package/out/src/tools/fetch/hrsa.js +0 -46
- package/out/src/tools/fetch/hrsa.js.map +0 -1
- package/out/src/tools/fetch/imls-pls.d.ts +0 -25
- package/out/src/tools/fetch/imls-pls.d.ts.map +0 -1
- package/out/src/tools/fetch/imls-pls.js +0 -108
- package/out/src/tools/fetch/imls-pls.js.map +0 -1
- package/out/src/tools/fetch/index.d.ts +0 -144
- package/out/src/tools/fetch/index.d.ts.map +0 -1
- package/out/src/tools/fetch/index.js +0 -143
- package/out/src/tools/fetch/index.js.map +0 -1
- package/out/src/tools/fetch/nad.d.ts +0 -70
- package/out/src/tools/fetch/nad.d.ts.map +0 -1
- package/out/src/tools/fetch/nad.js +0 -234
- package/out/src/tools/fetch/nad.js.map +0 -1
- package/out/src/tools/fetch/nppes.d.ts +0 -26
- package/out/src/tools/fetch/nppes.d.ts.map +0 -1
- package/out/src/tools/fetch/nppes.js +0 -126
- package/out/src/tools/fetch/nppes.js.map +0 -1
- package/out/src/tools/fetch/openaddresses.d.ts +0 -61
- package/out/src/tools/fetch/openaddresses.d.ts.map +0 -1
- package/out/src/tools/fetch/openaddresses.js +0 -317
- package/out/src/tools/fetch/openaddresses.js.map +0 -1
- package/out/src/tools/fetch/ourairports.d.ts +0 -45
- package/out/src/tools/fetch/ourairports.d.ts.map +0 -1
- package/out/src/tools/fetch/ourairports.js +0 -128
- package/out/src/tools/fetch/ourairports.js.map +0 -1
- package/out/src/tools/fetch/ppd.d.ts.map +0 -1
- package/out/src/tools/fetch/ppd.js +0 -100
- package/out/src/tools/fetch/ppd.js.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.d.ts +0 -25
- package/out/src/tools/fetch/state-hi-schools.d.ts.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.js +0 -162
- package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
- package/out/src/tools/fetch/state-sources.d.ts +0 -26
- package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
- package/out/src/tools/fetch/state-sources.js +0 -111
- package/out/src/tools/fetch/state-sources.js.map +0 -1
- package/out/src/tools/fetch/tiger-full.d.ts +0 -42
- package/out/src/tools/fetch/tiger-full.d.ts.map +0 -1
- package/out/src/tools/fetch/tiger-full.js +0 -248
- package/out/src/tools/fetch/tiger-full.js.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.d.ts +0 -171
- package/out/src/tools/fetch/wikidata-subvenue.d.ts.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.js +0 -275
- package/out/src/tools/fetch/wikidata-subvenue.js.map +0 -1
- package/out/src/tools/gb-title-case.d.ts.map +0 -1
- package/out/src/tools/gb-title-case.js.map +0 -1
- package/out/src/tools/golden-expand.d.ts +0 -90
- package/out/src/tools/golden-expand.d.ts.map +0 -1
- package/out/src/tools/golden-expand.js +0 -413
- package/out/src/tools/golden-expand.js.map +0 -1
- package/out/src/tools/golden-promote.d.ts.map +0 -1
- package/out/src/tools/golden-promote.js +0 -244
- package/out/src/tools/golden-promote.js.map +0 -1
- package/out/src/tools/golden-relabel-street.d.ts +0 -196
- package/out/src/tools/golden-relabel-street.d.ts.map +0 -1
- package/out/src/tools/golden-relabel-street.js +0 -440
- package/out/src/tools/golden-relabel-street.js.map +0 -1
- package/out/src/tools/index.d.ts +0 -28
- package/out/src/tools/index.d.ts.map +0 -1
- package/out/src/tools/index.js +0 -28
- package/out/src/tools/index.js.map +0 -1
- package/out/src/tools/ingest-csv.d.ts.map +0 -1
- package/out/src/tools/ingest-csv.js +0 -296
- package/out/src/tools/ingest-csv.js.map +0 -1
- package/out/src/tools/jsonl-to-parquet.d.ts +0 -61
- package/out/src/tools/jsonl-to-parquet.d.ts.map +0 -1
- package/out/src/tools/jsonl-to-parquet.js +0 -164
- package/out/src/tools/jsonl-to-parquet.js.map +0 -1
- package/out/src/tools/lint-shard-vocab.d.ts +0 -90
- package/out/src/tools/lint-shard-vocab.d.ts.map +0 -1
- package/out/src/tools/lint-shard-vocab.js +0 -281
- package/out/src/tools/lint-shard-vocab.js.map +0 -1
- package/out/src/tools/lint-shard.d.ts +0 -93
- package/out/src/tools/lint-shard.d.ts.map +0 -1
- package/out/src/tools/lint-shard.js +0 -354
- package/out/src/tools/lint-shard.js.map +0 -1
- package/out/src/tools/overlay-manifest.d.ts +0 -39
- package/out/src/tools/overlay-manifest.d.ts.map +0 -1
- package/out/src/tools/overlay-manifest.js +0 -98
- package/out/src/tools/overlay-manifest.js.map +0 -1
- package/out/src/tools/overture-subvenue.d.ts +0 -112
- package/out/src/tools/overture-subvenue.d.ts.map +0 -1
- package/out/src/tools/overture-subvenue.js +0 -144
- package/out/src/tools/overture-subvenue.js.map +0 -1
- package/out/src/tools/postcode-triples.d.ts +0 -175
- package/out/src/tools/postcode-triples.d.ts.map +0 -1
- package/out/src/tools/postcode-triples.js +0 -304
- package/out/src/tools/postcode-triples.js.map +0 -1
- package/out/src/tools/shard-kryptonite.d.ts +0 -32
- package/out/src/tools/shard-kryptonite.d.ts.map +0 -1
- package/out/src/tools/shard-kryptonite.js +0 -100
- package/out/src/tools/shard-kryptonite.js.map +0 -1
- package/out/src/tools/shard-translit.d.ts +0 -51
- package/out/src/tools/shard-translit.d.ts.map +0 -1
- package/out/src/tools/shard-translit.js +0 -175
- package/out/src/tools/shard-translit.js.map +0 -1
- package/out/src/tools/sub-venue/harvest.d.ts +0 -100
- package/out/src/tools/sub-venue/harvest.d.ts.map +0 -1
- package/out/src/tools/sub-venue/harvest.js +0 -168
- package/out/src/tools/sub-venue/harvest.js.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.d.ts +0 -50
- package/out/src/tools/sub-venue/head-nouns.d.ts.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.js +0 -210
- package/out/src/tools/sub-venue/head-nouns.js.map +0 -1
- package/out/src/tools/sub-venue/surfaces.d.ts +0 -45
- package/out/src/tools/sub-venue/surfaces.d.ts.map +0 -1
- package/out/src/tools/sub-venue/surfaces.js +0 -77
- package/out/src/tools/sub-venue/surfaces.js.map +0 -1
- package/out/src/tools/sub-venue/table.d.ts +0 -229
- package/out/src/tools/sub-venue/table.d.ts.map +0 -1
- package/out/src/tools/sub-venue/table.js +0 -108
- package/out/src/tools/sub-venue/table.js.map +0 -1
- package/out/src/tools/sub-venue/wikidata.d.ts +0 -26
- package/out/src/tools/sub-venue/wikidata.d.ts.map +0 -1
- package/out/src/tools/sub-venue/wikidata.js +0 -62
- package/out/src/tools/sub-venue/wikidata.js.map +0 -1
- package/out/src/tools/sub-venue-lexicon.d.ts +0 -156
- package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
- package/out/src/tools/sub-venue-lexicon.js +0 -282
- package/out/src/tools/sub-venue-lexicon.js.map +0 -1
- package/out/src/tools/sub-venue-promotions.d.ts +0 -94
- package/out/src/tools/sub-venue-promotions.d.ts.map +0 -1
- package/out/src/tools/sub-venue-promotions.js +0 -266
- package/out/src/tools/sub-venue-promotions.js.map +0 -1
- package/out/src/types.d.ts +0 -221
- package/out/src/types.d.ts.map +0 -1
- package/out/src/types.js.map +0 -1
- package/out/src/utils/align.d.ts +0 -93
- package/out/src/utils/align.d.ts.map +0 -1
- package/out/src/utils/align.js +0 -234
- package/out/src/utils/align.js.map +0 -1
- package/out/src/utils/golden.d.ts +0 -69
- package/out/src/utils/golden.d.ts.map +0 -1
- package/out/src/utils/golden.js +0 -127
- package/out/src/utils/golden.js.map +0 -1
- package/out/src/utils/index.d.ts +0 -14
- package/out/src/utils/index.d.ts.map +0 -1
- package/out/src/utils/index.js +0 -14
- package/out/src/utils/index.js.map +0 -1
- package/out/src/utils/license.d.ts.map +0 -1
- package/out/src/utils/license.js.map +0 -1
- package/out/src/utils/parquet.d.ts +0 -162
- package/out/src/utils/parquet.d.ts.map +0 -1
- package/out/src/utils/parquet.js +0 -262
- package/out/src/utils/parquet.js.map +0 -1
- package/out/src/utils/split.d.ts +0 -127
- package/out/src/utils/split.d.ts.map +0 -1
- package/out/src/utils/split.js +0 -204
- package/out/src/utils/split.js.map +0 -1
- package/out/src/utils/tokenize.d.ts +0 -56
- package/out/src/utils/tokenize.d.ts.map +0 -1
- package/out/src/utils/tokenize.js +0 -48
- package/out/src/utils/tokenize.js.map +0 -1
- package/out/src/utils/wof-json.d.ts +0 -109
- package/out/src/utils/wof-json.d.ts.map +0 -1
- package/out/src/utils/wof-json.js +0 -173
- package/out/src/utils/wof-json.js.map +0 -1
- package/src/adapters/ban/adapter.ts +0 -191
- package/src/adapters/ban/street-decompose.ts +0 -96
- package/src/adapters/fcc-bdc/adapter.ts +0 -174
- package/src/adapters/geonames/adapter.ts +0 -200
- package/src/adapters/geonames-postal/adapter.ts +0 -119
- package/src/adapters/gnaf/adapter.ts +0 -149
- package/src/adapters/gnaf/assemble.ts +0 -226
- package/src/adapters/index.ts +0 -149
- package/src/adapters/openaddresses/adapter.ts +0 -251
- package/src/adapters/overture/adapter.ts +0 -162
- package/src/adapters/state-hi-schools/adapter.ts +0 -164
- package/src/adapters/synth-po-box/adapter.ts +0 -204
- package/src/adapters/tiger/adapter.ts +0 -253
- package/src/adapters/tiger/street-decompose.ts +0 -111
- package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -183
- package/src/adapters/usgov-imls-pls/adapter.ts +0 -143
- package/src/adapters/usgov-irs-bmf/adapter.ts +0 -163
- package/src/adapters/usgov-nad/adapter.ts +0 -348
- package/src/adapters/usgov-nppes/adapter.ts +0 -159
- package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -204
- package/src/adapters/utils/index.ts +0 -233
- package/src/adapters/wof-admin-jp/adapter.ts +0 -216
- package/src/adapters/wof-admin-json/adapter.ts +0 -256
- package/src/adapters/wof-json-rows.ts +0 -79
- package/src/adapters/wof-postalcode-json/adapter.ts +0 -183
- package/src/build.ts +0 -386
- package/src/index.ts +0 -14
- package/src/name-prone-us-suffixes.ts +0 -12
- package/src/parquet-wrapper/index.ts +0 -9
- package/src/parquet-wrapper/reader.ts +0 -97
- package/src/parquet-wrapper/schema.ts +0 -88
- package/src/parquet-wrapper/writer.ts +0 -110
- package/src/runner.ts +0 -317
- package/src/shard-recipes/anchor-absorption.ts +0 -103
- package/src/shard-recipes/bare-country.ts +0 -95
- package/src/shard-recipes/boundary-stress.ts +0 -101
- package/src/shard-recipes/country-balanced.ts +0 -524
- package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -111
- package/src/shard-recipes/fr-admin-split.ts +0 -239
- package/src/shard-recipes/fr-bare-street.ts +0 -170
- package/src/shard-recipes/fr-fragment.ts +0 -332
- package/src/shard-recipes/fr-lieudit.ts +0 -302
- package/src/shard-recipes/fr-order.ts +0 -258
- package/src/shard-recipes/german.ts +0 -170
- package/src/shard-recipes/house-venue.ts +0 -88
- package/src/shard-recipes/index.ts +0 -95
- package/src/shard-recipes/intersection.ts +0 -630
- package/src/shard-recipes/locale.ts +0 -599
- package/src/shard-recipes/nl-postcode.ts +0 -115
- package/src/shard-recipes/no-fragment.ts +0 -219
- package/src/shard-recipes/no-street-led.ts +0 -143
- package/src/shard-recipes/no-street.ts +0 -86
- package/src/shard-recipes/po-box-cedex.ts +0 -920
- package/src/shard-recipes/po-box.ts +0 -119
- package/src/shard-recipes/reviewed-postcode-tail.ts +0 -189
- package/src/shard-recipes/scaffold.ts +0 -360
- package/src/shard-recipes/si-bare-village.ts +0 -97
- package/src/shard-recipes/street-affix.ts +0 -826
- package/src/shard-recipes/street-bare.ts +0 -101
- package/src/shard-recipes/street.ts +0 -82
- package/src/shard-recipes/sub-venue-sources.ts +0 -885
- package/src/shard-recipes/sub-venue.ts +0 -984
- package/src/shard-recipes/trailing-region.ts +0 -183
- package/src/shard-recipes/unit.ts +0 -321
- package/src/synthesizers/anchor-absorption.ts +0 -290
- package/src/synthesizers/boundary-stress.ts +0 -531
- package/src/synthesizers/german.ts +0 -251
- package/src/synthesizers/house-venue.ts +0 -330
- package/src/synthesizers/intersection.ts +0 -232
- package/src/synthesizers/no-street.ts +0 -349
- package/src/synthesizers/po-box.ts +0 -339
- package/src/synthesizers/street.ts +0 -274
- package/src/synthesizers/utils.ts +0 -903
- package/src/tools/align-shard.ts +0 -70
- package/src/tools/audit.ts +0 -399
- package/src/tools/corpus-stats.ts +0 -184
- package/src/tools/fetch/ban.ts +0 -290
- package/src/tools/fetch/download.ts +0 -176
- package/src/tools/fetch/geonames-dump.ts +0 -267
- package/src/tools/fetch/geonames-postal.ts +0 -180
- package/src/tools/fetch/hrsa.ts +0 -68
- package/src/tools/fetch/imls-pls.ts +0 -158
- package/src/tools/fetch/index.ts +0 -147
- package/src/tools/fetch/nad.ts +0 -342
- package/src/tools/fetch/nppes.ts +0 -174
- package/src/tools/fetch/openaddresses.ts +0 -404
- package/src/tools/fetch/ourairports.ts +0 -171
- package/src/tools/fetch/ppd.ts +0 -137
- package/src/tools/fetch/state-hi-schools.ts +0 -208
- package/src/tools/fetch/state-sources.ts +0 -155
- package/src/tools/fetch/tiger-full.ts +0 -354
- package/src/tools/fetch/wikidata-subvenue.ts +0 -386
- package/src/tools/golden-expand.ts +0 -584
- package/src/tools/golden-promote.ts +0 -353
- package/src/tools/golden-relabel-street.ts +0 -685
- package/src/tools/index.ts +0 -28
- package/src/tools/ingest-csv.ts +0 -422
- package/src/tools/jsonl-to-parquet.ts +0 -221
- package/src/tools/lint-shard-vocab.ts +0 -409
- package/src/tools/lint-shard.ts +0 -543
- package/src/tools/overlay-manifest.ts +0 -157
- package/src/tools/overture-subvenue.ts +0 -215
- package/src/tools/postcode-triples.ts +0 -375
- package/src/tools/shard-kryptonite.ts +0 -139
- package/src/tools/shard-translit.ts +0 -245
- package/src/tools/sub-venue/harvest.ts +0 -235
- package/src/tools/sub-venue/head-nouns.ts +0 -242
- package/src/tools/sub-venue/surfaces.ts +0 -95
- package/src/tools/sub-venue/table.ts +0 -281
- package/src/tools/sub-venue/wikidata.ts +0 -85
- package/src/tools/sub-venue-lexicon.ts +0 -431
- package/src/tools/sub-venue-promotions.ts +0 -330
- package/src/types.ts +0 -247
- package/src/utils/align.ts +0 -331
- package/src/utils/golden.ts +0 -176
- package/src/utils/index.ts +0 -14
- package/src/utils/parquet.ts +0 -391
- package/src/utils/split.ts +0 -279
- package/src/utils/tokenize.ts +0 -78
- package/src/utils/wof-json.ts +0 -244
- /package/{src → lib}/adapters/state-ia-contractors/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-ny-notaries/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-tx-notaries/adapter.ts +0 -0
- /package/{src → lib}/codex/us-fips-state.ts +0 -0
- /package/{src → lib}/tools/gb-title-case.ts +0 -0
- /package/{src → lib}/utils/license.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/fcc-bdc/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/geonames/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/openaddresses/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/synth-po-box/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/tiger/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-nppes/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-samhsa-treatment-locator/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/wof-admin-jp/adapter.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.js +0 -0
- /package/out/{src/tools → tools}/fetch/ppd.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.js +0 -0
- /package/out/{src/tools → tools}/golden-promote.d.ts +0 -0
- /package/out/{src/tools → tools}/ingest-csv.d.ts +0 -0
- /package/out/{src/types.js → types.js} +0 -0
- /package/out/{src/utils → utils}/license.d.ts +0 -0
- /package/out/{src/utils → utils}/license.js +0 -0
|
@@ -0,0 +1,318 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Download and manifest utilities for `mailwoman corpus fetch <source>`.
|
|
7
|
+
*/
|
|
8
|
+
import { pathExists, readLocalTextFile, tryStat } from "@mailwoman/core/fs/readers";
|
|
9
|
+
import { openWriteStream, pipeline, Readable } from "@mailwoman/core/fs/streams";
|
|
10
|
+
import { movePath, writeLocalFile, writeLocalTextFile } from "@mailwoman/core/fs/writers";
|
|
11
|
+
import { tryParsingJSON } from "@mailwoman/core/json";
|
|
12
|
+
import { sleep } from "@mailwoman/core/utils/sleep";
|
|
13
|
+
/**
|
|
14
|
+
* Rate limited — retryable, the server is asking us to back off.
|
|
15
|
+
*/
|
|
16
|
+
const HTTP_TOO_MANY_REQUESTS = 429;
|
|
17
|
+
/**
|
|
18
|
+
* The answer to a satisfiable `Range` request; anything else means the host ignored the range and would send the whole
|
|
19
|
+
* body again.
|
|
20
|
+
*/
|
|
21
|
+
const HTTP_PARTIAL_CONTENT = 206;
|
|
22
|
+
/**
|
|
23
|
+
* The answer to a range that starts at or past the end of the body: the resume point is already the whole file.
|
|
24
|
+
*/
|
|
25
|
+
const HTTP_RANGE_NOT_SATISFIABLE = 416;
|
|
26
|
+
/**
|
|
27
|
+
* Lowest 5xx status. Server-side failures are retryable; 4xx are not.
|
|
28
|
+
*/
|
|
29
|
+
const HTTP_SERVER_ERROR_MIN = 500;
|
|
30
|
+
/**
|
|
31
|
+
* Highest 5xx status.
|
|
32
|
+
*/
|
|
33
|
+
const HTTP_SERVER_ERROR_MAX = 599;
|
|
34
|
+
/**
|
|
35
|
+
* The option base every `mailwoman corpus fetch <source>` module extends.
|
|
36
|
+
*/
|
|
37
|
+
/**
|
|
38
|
+
* How long a failed transfer waits before the next attempt.
|
|
39
|
+
*/
|
|
40
|
+
export const DEFAULT_RETRY_DELAY_MS = 5000;
|
|
41
|
+
/**
|
|
42
|
+
* A status worth retrying: rate limiting or a server-side failure.
|
|
43
|
+
*/
|
|
44
|
+
/**
|
|
45
|
+
* An HTTP failure that CARRIES its status, so callers branch on `error.status` rather than on message prose. The prose
|
|
46
|
+
* route shipped a real flake: a caller classified "not published upstream" with `message.includes("404")`, and the
|
|
47
|
+
* message contains the URL — an ephemeral test-server port such as `:40453` satisfies it while the actual status is 500.
|
|
48
|
+
* Roughly 1–2% of ephemeral ports contain the substring, which is exactly the kind of sometimes-failure that burns a CI
|
|
49
|
+
* run and vanishes locally.
|
|
50
|
+
*/
|
|
51
|
+
export class HTTPStatusError extends Error {
|
|
52
|
+
status;
|
|
53
|
+
constructor(status, message) {
|
|
54
|
+
super(message);
|
|
55
|
+
this.name = "HTTPStatusError";
|
|
56
|
+
this.status = status;
|
|
57
|
+
}
|
|
58
|
+
}
|
|
59
|
+
export function isTransientStatus(status) {
|
|
60
|
+
return status === HTTP_TOO_MANY_REQUESTS || (status >= HTTP_SERVER_ERROR_MIN && status <= HTTP_SERVER_ERROR_MAX);
|
|
61
|
+
}
|
|
62
|
+
/**
|
|
63
|
+
* Download `url` to `dest` with per-attempt timeout and transient-status retry. Throws on a non-transient HTTP status
|
|
64
|
+
* or once retries are exhausted. Returns the byte count written.
|
|
65
|
+
*/
|
|
66
|
+
export async function downloadToFile(options) {
|
|
67
|
+
const { url, dest, timeoutMs = 600_000, retries = 0, retryDelayMs = DEFAULT_RETRY_DELAY_MS, headers, report, } = options;
|
|
68
|
+
let lastError;
|
|
69
|
+
for (let attempt = 0; attempt <= retries; attempt++) {
|
|
70
|
+
if (attempt > 0) {
|
|
71
|
+
report?.(`retry ${attempt}/${retries} after ${retryDelayMs}ms — ${url}`);
|
|
72
|
+
await sleep(retryDelayMs);
|
|
73
|
+
}
|
|
74
|
+
let res;
|
|
75
|
+
try {
|
|
76
|
+
// Raw `fetch`, deliberately: this is the shared FILE downloader and the body is piped to disk below.
|
|
77
|
+
// `APIClient` is the repo default for API requests — small bodies, repeated calls — and buffers a
|
|
78
|
+
// non-stream response in memory, which is the one thing a multi-gigabyte transfer must not do.
|
|
79
|
+
res = await fetch(url, { headers, signal: AbortSignal.timeout(timeoutMs) });
|
|
80
|
+
}
|
|
81
|
+
catch (error) {
|
|
82
|
+
// AbortSignal timeouts and network-level failures are retryable.
|
|
83
|
+
lastError = error;
|
|
84
|
+
continue;
|
|
85
|
+
}
|
|
86
|
+
if (!res.ok) {
|
|
87
|
+
const error = new HTTPStatusError(res.status, `HTTP ${res.status} ${res.statusText} — ${url}`);
|
|
88
|
+
if (!isTransientStatus(res.status))
|
|
89
|
+
throw error;
|
|
90
|
+
lastError = error;
|
|
91
|
+
continue;
|
|
92
|
+
}
|
|
93
|
+
try {
|
|
94
|
+
const buffer = Buffer.from(await res.arrayBuffer());
|
|
95
|
+
await writeLocalFile(buffer, dest);
|
|
96
|
+
return { bytes: buffer.byteLength };
|
|
97
|
+
}
|
|
98
|
+
catch (error) {
|
|
99
|
+
// A mid-stream abort while reading the body is retryable too.
|
|
100
|
+
lastError = error;
|
|
101
|
+
}
|
|
102
|
+
}
|
|
103
|
+
throw lastError instanceof Error ? lastError : new Error(String(lastError));
|
|
104
|
+
}
|
|
105
|
+
/**
|
|
106
|
+
* Stream an HTTP download to disk, returning the final HTTP status (0 on network error after retries). Follows
|
|
107
|
+
* redirects (the Census and OpenAddresses endpoints both 302 to their real hosts).
|
|
108
|
+
*
|
|
109
|
+
* Kept separate from {@link downloadToFile} on purpose: this one streams a multi-GB body to disk (the buffered helper
|
|
110
|
+
* reads via `arrayBuffer()`) and returns the HTTP status instead of throwing, which the per-file result collectors and
|
|
111
|
+
* two-URL fallback ladders consume.
|
|
112
|
+
*/
|
|
113
|
+
export async function streamDownload(url, dest, opts) {
|
|
114
|
+
for (let attempt = 0; attempt <= opts.retries; attempt++) {
|
|
115
|
+
try {
|
|
116
|
+
const res = await fetch(url, {
|
|
117
|
+
headers: opts.headers ?? {},
|
|
118
|
+
redirect: "follow",
|
|
119
|
+
signal: AbortSignal.timeout(opts.timeoutMs),
|
|
120
|
+
});
|
|
121
|
+
if (res.ok && res.body) {
|
|
122
|
+
await pipeline(Readable.fromWeb(res.body), openWriteStream(dest));
|
|
123
|
+
return res.status;
|
|
124
|
+
}
|
|
125
|
+
if (attempt < opts.retries && isTransientStatus(res.status)) {
|
|
126
|
+
await sleep(opts.retryDelayMs);
|
|
127
|
+
continue;
|
|
128
|
+
}
|
|
129
|
+
return res.status;
|
|
130
|
+
}
|
|
131
|
+
catch {
|
|
132
|
+
if (attempt < opts.retries) {
|
|
133
|
+
await sleep(opts.retryDelayMs);
|
|
134
|
+
continue;
|
|
135
|
+
}
|
|
136
|
+
return 0;
|
|
137
|
+
}
|
|
138
|
+
}
|
|
139
|
+
return 0;
|
|
140
|
+
}
|
|
141
|
+
/**
|
|
142
|
+
* Read a MANIFEST.json; `null` when missing or corrupt (callers re-fetch from scratch).
|
|
143
|
+
*/
|
|
144
|
+
export async function readManifest(path) {
|
|
145
|
+
if (!(await pathExists(path)))
|
|
146
|
+
return null;
|
|
147
|
+
// A read failure (e.g. the file vanished after the existsSync probe) maps to null like corrupt
|
|
148
|
+
// JSON does; tryParsingJSON returns null for the non-string sentinel.
|
|
149
|
+
const text = await readLocalTextFile(path).catch(() => null);
|
|
150
|
+
return tryParsingJSON(text);
|
|
151
|
+
}
|
|
152
|
+
/**
|
|
153
|
+
* Load manifest entries into a map so untouched keys survive a partial re-fetch.
|
|
154
|
+
*/
|
|
155
|
+
export async function loadManifestEntries(path, key) {
|
|
156
|
+
const entries = new Map();
|
|
157
|
+
const parsed = await readManifest(path);
|
|
158
|
+
for (const entry of parsed ?? []) {
|
|
159
|
+
entries.set(key(entry), entry);
|
|
160
|
+
}
|
|
161
|
+
return entries;
|
|
162
|
+
}
|
|
163
|
+
/**
|
|
164
|
+
* Write a MANIFEST.json in the house shape: pretty-printed, trailing newline.
|
|
165
|
+
*/
|
|
166
|
+
export async function writeManifest(path, manifest) {
|
|
167
|
+
await writeLocalTextFile(JSON.stringify(manifest, null, 2) + "\n", path);
|
|
168
|
+
}
|
|
169
|
+
/**
|
|
170
|
+
* Pipe a response body to `dest` and answer the byte count. The one primitive the portal fetchers share when the
|
|
171
|
+
* request is not a bare GET — a session cookie, a CSRF header, or a form POST stands between the listing and the file,
|
|
172
|
+
* so {@link streamDownload}'s URL-only contract does not fit and each module builds its own `Response` first. Writes a
|
|
173
|
+
* `.tmp` sibling and renames, so an interrupted transfer never lands at the final path looking complete.
|
|
174
|
+
*/
|
|
175
|
+
export async function streamBodyToFile(res, dest) {
|
|
176
|
+
if (!res.body)
|
|
177
|
+
throw new HTTPStatusError(res.status, `HTTP ${res.status} with no body — ${res.url}`);
|
|
178
|
+
let bytes = 0;
|
|
179
|
+
const counter = new TransformStream({
|
|
180
|
+
transform(chunk, controller) {
|
|
181
|
+
bytes += chunk.byteLength;
|
|
182
|
+
controller.enqueue(chunk);
|
|
183
|
+
},
|
|
184
|
+
});
|
|
185
|
+
const tmp = dest + ".tmp";
|
|
186
|
+
await pipeline(Readable.fromWeb(res.body.pipeThrough(counter)), openWriteStream(tmp));
|
|
187
|
+
await movePath(tmp, dest);
|
|
188
|
+
return bytes;
|
|
189
|
+
}
|
|
190
|
+
/**
|
|
191
|
+
* The per-file entries of a {@link SourceCollectionManifest} keyed by file name, or an empty map when the manifest is
|
|
192
|
+
* missing or not in the collection shape, so a re-run after an interruption fetches only what is missing. The
|
|
193
|
+
* single-file modules' `loadManifestEntries` reads a bare array and is not this.
|
|
194
|
+
*/
|
|
195
|
+
export async function loadCollectionFiles(path) {
|
|
196
|
+
const parsed = await readManifest(path);
|
|
197
|
+
const entries = new Map();
|
|
198
|
+
for (const entry of Array.isArray(parsed?.files) ? parsed.files : []) {
|
|
199
|
+
entries.set(entry.filename, entry);
|
|
200
|
+
}
|
|
201
|
+
return entries;
|
|
202
|
+
}
|
|
203
|
+
/**
|
|
204
|
+
* Run one transfer up to `1 + retries` times, pausing `retryDelayMs` between attempts. A government portal drops a
|
|
205
|
+
* multi-hundred-megabyte connection often enough that a collection fetch which lets the first `TypeError: terminated`
|
|
206
|
+
* propagate loses the whole run to one file; the per-file loop calls the transfer through this and records the failure
|
|
207
|
+
* only once the attempts are spent. The last error is rethrown so the caller can name the file it lost.
|
|
208
|
+
*/
|
|
209
|
+
export async function withRetries(transfer, options = {}) {
|
|
210
|
+
const { retries = 3, retryDelayMs = DEFAULT_RETRY_DELAY_MS, report, label = "transfer" } = options;
|
|
211
|
+
let lastError;
|
|
212
|
+
for (let attempt = 0; attempt <= retries; attempt++) {
|
|
213
|
+
if (attempt > 0) {
|
|
214
|
+
report?.(` retry ${attempt}/${retries} after ${retryDelayMs}ms — ${label}`);
|
|
215
|
+
await sleep(retryDelayMs);
|
|
216
|
+
}
|
|
217
|
+
try {
|
|
218
|
+
return await transfer();
|
|
219
|
+
}
|
|
220
|
+
catch (error) {
|
|
221
|
+
lastError = error;
|
|
222
|
+
}
|
|
223
|
+
}
|
|
224
|
+
throw lastError instanceof Error ? lastError : new Error(String(lastError));
|
|
225
|
+
}
|
|
226
|
+
/**
|
|
227
|
+
* The byte count already at `path`, or 0 when nothing is there — the resume point of an interrupted range download.
|
|
228
|
+
*/
|
|
229
|
+
async function bytesOnDisk(path) {
|
|
230
|
+
const stat = await tryStat(path);
|
|
231
|
+
return stat?.size ?? 0;
|
|
232
|
+
}
|
|
233
|
+
/**
|
|
234
|
+
* Download `url` to `dest` in ranges, resuming from whatever the `.tmp` sibling already holds. For a host that drops a
|
|
235
|
+
* long connection every few megabytes but answers `Range` with 206 (the Korean address portal does both, measured at
|
|
236
|
+
* 0.9–12 MB per connection against a 181 MB file), a whole-body transfer never finishes and a plain retry starts over;
|
|
237
|
+
* this one asks for the remainder each time and keeps what landed. The total comes from the first `Content-Range`, and
|
|
238
|
+
* the loop gives up after `maxConnections` connections so a host that keeps answering 206 with no bytes cannot spin.
|
|
239
|
+
* Answers the byte count written; throws when the host answers anything but 206 for a range.
|
|
240
|
+
*/
|
|
241
|
+
export async function resumableDownload(options) {
|
|
242
|
+
const { url, dest, headers = {}, maxConnections = 400, retryDelayMs = DEFAULT_RETRY_DELAY_MS, report } = options;
|
|
243
|
+
const tmp = dest + ".tmp";
|
|
244
|
+
let have = await bytesOnDisk(tmp);
|
|
245
|
+
let total;
|
|
246
|
+
for (let connection = 0; connection < maxConnections; connection++) {
|
|
247
|
+
if (total !== undefined && have >= total)
|
|
248
|
+
break;
|
|
249
|
+
let res;
|
|
250
|
+
try {
|
|
251
|
+
res = await fetch(url, { headers: { ...headers, range: `bytes=${have}-` }, signal: AbortSignal.timeout(600_000) });
|
|
252
|
+
}
|
|
253
|
+
catch {
|
|
254
|
+
await sleep(retryDelayMs);
|
|
255
|
+
continue;
|
|
256
|
+
}
|
|
257
|
+
if (res.status === HTTP_RANGE_NOT_SATISFIABLE && have > 0) {
|
|
258
|
+
// Nothing past `have`: the file on disk is already the whole body (a parallel filler or an earlier run
|
|
259
|
+
// landed it), and `Content-Range: bytes */<total>` says how long it is.
|
|
260
|
+
const whole = /\*\/(\d+)/.exec(res.headers.get("content-range") ?? "")?.[1];
|
|
261
|
+
total = whole ? Number(whole) : have;
|
|
262
|
+
await res.body?.cancel();
|
|
263
|
+
break;
|
|
264
|
+
}
|
|
265
|
+
if (res.status !== HTTP_PARTIAL_CONTENT) {
|
|
266
|
+
throw new HTTPStatusError(res.status, `HTTP ${res.status} for a range request — ${url}`);
|
|
267
|
+
}
|
|
268
|
+
const range = /bytes \d+-\d+\/(\d+)/.exec(res.headers.get("content-range") ?? "")?.[1];
|
|
269
|
+
if (range) {
|
|
270
|
+
total = Number(range);
|
|
271
|
+
}
|
|
272
|
+
const before = have;
|
|
273
|
+
try {
|
|
274
|
+
// Append: the stream opens the file for appending so a partial body extends what earlier connections left.
|
|
275
|
+
await pipeline(Readable.fromWeb(res.body), openWriteStream(tmp, { flags: "a" }));
|
|
276
|
+
}
|
|
277
|
+
catch {
|
|
278
|
+
// The connection dropped mid-body; the bytes that landed are on disk, and the next range starts after them.
|
|
279
|
+
}
|
|
280
|
+
have = await bytesOnDisk(tmp);
|
|
281
|
+
if (have === before) {
|
|
282
|
+
await sleep(retryDelayMs);
|
|
283
|
+
}
|
|
284
|
+
else {
|
|
285
|
+
report?.(` ${(have / 1024 / 1024).toFixed(1)} MB${total ? ` of ${(total / 1024 / 1024).toFixed(1)} MB` : ""}`);
|
|
286
|
+
}
|
|
287
|
+
}
|
|
288
|
+
if (total === undefined || have < total) {
|
|
289
|
+
throw new Error(`resumable download stalled at ${have} of ${total ?? "?"} bytes — ${url}`);
|
|
290
|
+
}
|
|
291
|
+
await movePath(tmp, dest);
|
|
292
|
+
return have;
|
|
293
|
+
}
|
|
294
|
+
/**
|
|
295
|
+
* The `Set-Cookie` values of a response folded into one `Cookie` header value, so a second request to the same portal
|
|
296
|
+
* carries the session the first one opened.
|
|
297
|
+
*/
|
|
298
|
+
export function cookieHeader(res) {
|
|
299
|
+
return res.headers
|
|
300
|
+
.getSetCookie()
|
|
301
|
+
.map((cookie) => cookie.split(";")[0])
|
|
302
|
+
.join("; ");
|
|
303
|
+
}
|
|
304
|
+
/**
|
|
305
|
+
* The file name a `Content-Disposition: attachment` header names, RFC 5987 form (`filename*=utf-8''…`) first, plain
|
|
306
|
+
* `filename="…"` second, or `fallback` when the header carries neither.
|
|
307
|
+
*/
|
|
308
|
+
export function attachmentFilename(res, fallback) {
|
|
309
|
+
const disposition = res.headers.get("content-disposition") ?? "";
|
|
310
|
+
const extended = /filename\*=(?:utf-8|UTF-8)'[^']*'([^;]+)/.exec(disposition)?.[1];
|
|
311
|
+
if (extended)
|
|
312
|
+
return decodeURIComponent(extended.trim());
|
|
313
|
+
const plain = /filename="?([^";]+)"?/.exec(disposition)?.[1];
|
|
314
|
+
if (plain)
|
|
315
|
+
return decodeURIComponent(plain.trim());
|
|
316
|
+
return fallback;
|
|
317
|
+
}
|
|
318
|
+
//# sourceMappingURL=download.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"download.js","sourceRoot":"","sources":["../../../lib/tools/fetch/download.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH,OAAO,EAAE,UAAU,EAAE,iBAAiB,EAAE,OAAO,EAAE,MAAM,4BAA4B,CAAA;AACnF,OAAO,EAAE,eAAe,EAAE,QAAQ,EAAE,QAAQ,EAAE,MAAM,4BAA4B,CAAA;AAChF,OAAO,EAAE,QAAQ,EAAE,cAAc,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAA;AACzF,OAAO,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAA;AACrD,OAAO,EAAE,KAAK,EAAE,MAAM,6BAA6B,CAAA;AAGnD;;GAEG;AACH,MAAM,sBAAsB,GAAG,GAAG,CAAA;AAElC;;;GAGG;AACH,MAAM,oBAAoB,GAAG,GAAG,CAAA;AAEhC;;GAEG;AACH,MAAM,0BAA0B,GAAG,GAAG,CAAA;AAEtC;;GAEG;AACH,MAAM,qBAAqB,GAAG,GAAG,CAAA;AAEjC;;GAEG;AACH,MAAM,qBAAqB,GAAG,GAAG,CAAA;AAEjC;;GAEG;AACH;;GAEG;AACH,MAAM,CAAC,MAAM,sBAAsB,GAAG,IAAI,CAAA;AAuC1C;;GAEG;AACH;;;;;;GAMG;AACH,MAAM,OAAO,eAAgB,SAAQ,KAAK;IAChC,MAAM,CAAQ;IAEvB,YAAY,MAAc,EAAE,OAAe;QAC1C,KAAK,CAAC,OAAO,CAAC,CAAA;QACd,IAAI,CAAC,IAAI,GAAG,iBAAiB,CAAA;QAC7B,IAAI,CAAC,MAAM,GAAG,MAAM,CAAA;IACrB,CAAC;CACD;AAED,MAAM,UAAU,iBAAiB,CAAC,MAAc;IAC/C,OAAO,MAAM,KAAK,sBAAsB,IAAI,CAAC,MAAM,IAAI,qBAAqB,IAAI,MAAM,IAAI,qBAAqB,CAAC,CAAA;AACjH,CAAC;AAqBD;;;GAGG;AACH,MAAM,CAAC,KAAK,UAAU,cAAc,CAAC,OAAwB;IAC5D,MAAM,EACL,GAAG,EACH,IAAI,EACJ,SAAS,GAAG,OAAO,EACnB,OAAO,GAAG,CAAC,EACX,YAAY,GAAG,sBAAsB,EACrC,OAAO,EACP,MAAM,GACN,GAAG,OAAO,CAAA;IAEX,IAAI,SAAkB,CAAA;IAEtB,KAAK,IAAI,OAAO,GAAG,CAAC,EAAE,OAAO,IAAI,OAAO,EAAE,OAAO,EAAE,EAAE,CAAC;QACrD,IAAI,OAAO,GAAG,CAAC,EAAE,CAAC;YACjB,MAAM,EAAE,CAAC,SAAS,OAAO,IAAI,OAAO,UAAU,YAAY,QAAQ,GAAG,EAAE,CAAC,CAAA;YACxE,MAAM,KAAK,CAAC,YAAY,CAAC,CAAA;QAC1B,CAAC;QAED,IAAI,GAAa,CAAA;QAEjB,IAAI,CAAC;YACJ,qGAAqG;YACrG,kGAAkG;YAClG,+FAA+F;YAC/F,GAAG,GAAG,MAAM,KAAK,CAAC,GAAG,EAAE,EAAE,OAAO,EAAE,MAAM,EAAE,WAAW,CAAC,OAAO,CAAC,SAAS,CAAC,EAAE,CAAC,CAAA;QAC5E,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,iEAAiE;YACjE,SAAS,GAAG,KAAK,CAAA;YAEjB,SAAQ;QACT,CAAC;QAED,IAAI,CAAC,GAAG,CAAC,EAAE,EAAE,CAAC;YACb,MAAM,KAAK,GAAG,IAAI,eAAe,CAAC,GAAG,CAAC,MAAM,EAAE,QAAQ,GAAG,CAAC,MAAM,IAAI,GAAG,CAAC,UAAU,MAAM,GAAG,EAAE,CAAC,CAAA;YAE9F,IAAI,CAAC,iBAAiB,CAAC,GAAG,CAAC,MAAM,CAAC;gBAAE,MAAM,KAAK,CAAA;YAC/C,SAAS,GAAG,KAAK,CAAA;YAEjB,SAAQ;QACT,CAAC;QAED,IAAI,CAAC;YACJ,MAAM,MAAM,GAAG,MAAM,CAAC,IAAI,CAAC,MAAM,GAAG,CAAC,WAAW,EAAE,CAAC,CAAA;YACnD,MAAM,cAAc,CAAC,MAAM,EAAE,IAAI,CAAC,CAAA;YAElC,OAAO,EAAE,KAAK,EAAE,MAAM,CAAC,UAAU,EAAE,CAAA;QACpC,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,8DAA8D;YAC9D,SAAS,GAAG,KAAK,CAAA;QAClB,CAAC;IACF,CAAC;IAED,MAAM,SAAS,YAAY,KAAK,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,IAAI,KAAK,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,CAAA;AAC5E,CAAC;AASD;;;;;;;GAOG;AACH,MAAM,CAAC,KAAK,UAAU,cAAc,CAAC,GAAW,EAAE,IAAY,EAAE,IAA2B;IAC1F,KAAK,IAAI,OAAO,GAAG,CAAC,EAAE,OAAO,IAAI,IAAI,CAAC,OAAO,EAAE,OAAO,EAAE,EAAE,CAAC;QAC1D,IAAI,CAAC;YACJ,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,GAAG,EAAE;gBAC5B,OAAO,EAAE,IAAI,CAAC,OAAO,IAAI,EAAE;gBAC3B,QAAQ,EAAE,QAAQ;gBAClB,MAAM,EAAE,WAAW,CAAC,OAAO,CAAC,IAAI,CAAC,SAAS,CAAC;aAC3C,CAAC,CAAA;YAEF,IAAI,GAAG,CAAC,EAAE,IAAI,GAAG,CAAC,IAAI,EAAE,CAAC;gBACxB,MAAM,QAAQ,CAAC,QAAQ,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,eAAe,CAAC,IAAI,CAAC,CAAC,CAAA;gBAEjE,OAAO,GAAG,CAAC,MAAM,CAAA;YAClB,CAAC;YAED,IAAI,OAAO,GAAG,IAAI,CAAC,OAAO,IAAI,iBAAiB,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC;gBAC7D,MAAM,KAAK,CAAC,IAAI,CAAC,YAAY,CAAC,CAAA;gBAE9B,SAAQ;YACT,CAAC;YAED,OAAO,GAAG,CAAC,MAAM,CAAA;QAClB,CAAC;QAAC,MAAM,CAAC;YACR,IAAI,OAAO,GAAG,IAAI,CAAC,OAAO,EAAE,CAAC;gBAC5B,MAAM,KAAK,CAAC,IAAI,CAAC,YAAY,CAAC,CAAA;gBAE9B,SAAQ;YACT,CAAC;YAED,OAAO,CAAC,CAAA;QACT,CAAC;IACF,CAAC;IAED,OAAO,CAAC,CAAA;AACT,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,YAAY,CAAI,IAAY;IACjD,IAAI,CAAC,CAAC,MAAM,UAAU,CAAC,IAAI,CAAC,CAAC;QAAE,OAAO,IAAI,CAAA;IAE1C,+FAA+F;IAC/F,sEAAsE;IACtE,MAAM,IAAI,GAAG,MAAM,iBAAiB,CAAC,IAAI,CAAC,CAAC,KAAK,CAAC,GAAG,EAAE,CAAC,IAAI,CAAC,CAAA;IAE5D,OAAO,cAAc,CAAI,IAAI,CAAC,CAAA;AAC/B,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,mBAAmB,CAAI,IAAY,EAAE,GAAyB;IACnF,MAAM,OAAO,GAAG,IAAI,GAAG,EAAa,CAAA;IACpC,MAAM,MAAM,GAAG,MAAM,YAAY,CAAM,IAAI,CAAC,CAAA;IAE5C,KAAK,MAAM,KAAK,IAAI,MAAM,IAAI,EAAE,EAAE,CAAC;QAClC,OAAO,CAAC,GAAG,CAAC,GAAG,CAAC,KAAK,CAAC,EAAE,KAAK,CAAC,CAAA;IAC/B,CAAC;IAED,OAAO,OAAO,CAAA;AACf,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,aAAa,CAAC,IAAY,EAAE,QAAiB;IAClE,MAAM,kBAAkB,CAAC,IAAI,CAAC,SAAS,CAAC,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAC,GAAG,IAAI,EAAE,IAAI,CAAC,CAAA;AACzE,CAAC;AAiBD;;;;;GAKG;AACH,MAAM,CAAC,KAAK,UAAU,gBAAgB,CAAC,GAAa,EAAE,IAAY;IACjE,IAAI,CAAC,GAAG,CAAC,IAAI;QAAE,MAAM,IAAI,eAAe,CAAC,GAAG,CAAC,MAAM,EAAE,QAAQ,GAAG,CAAC,MAAM,mBAAmB,GAAG,CAAC,GAAG,EAAE,CAAC,CAAA;IACpG,IAAI,KAAK,GAAG,CAAC,CAAA;IAEb,MAAM,OAAO,GAAG,IAAI,eAAe,CAAyB;QAC3D,SAAS,CAAC,KAAK,EAAE,UAAU;YAC1B,KAAK,IAAI,KAAK,CAAC,UAAU,CAAA;YACzB,UAAU,CAAC,OAAO,CAAC,KAAK,CAAC,CAAA;QAC1B,CAAC;KACD,CAAC,CAAA;IAEF,MAAM,GAAG,GAAG,IAAI,GAAG,MAAM,CAAA;IACzB,MAAM,QAAQ,CAAC,QAAQ,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,WAAW,CAAC,OAAO,CAAC,CAAC,EAAE,eAAe,CAAC,GAAG,CAAC,CAAC,CAAA;IACrF,MAAM,QAAQ,CAAC,GAAG,EAAE,IAAI,CAAC,CAAA;IAEzB,OAAO,KAAK,CAAA;AACb,CAAC;AAED;;;;GAIG;AACH,MAAM,CAAC,KAAK,UAAU,mBAAmB,CAAC,IAAY;IACrD,MAAM,MAAM,GAAG,MAAM,YAAY,CAA2B,IAAI,CAAC,CAAA;IACjE,MAAM,OAAO,GAAG,IAAI,GAAG,EAA0B,CAAA;IAEjD,KAAK,MAAM,KAAK,IAAI,KAAK,CAAC,OAAO,CAAC,MAAM,EAAE,KAAK,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC;QACtE,OAAO,CAAC,GAAG,CAAC,KAAK,CAAC,QAAQ,EAAE,KAAK,CAAC,CAAA;IACnC,CAAC;IAED,OAAO,OAAO,CAAA;AACf,CAAC;AAED;;;;;GAKG;AACH,MAAM,CAAC,KAAK,UAAU,WAAW,CAChC,QAA0B,EAC1B,UAAwG,EAAE;IAE1G,MAAM,EAAE,OAAO,GAAG,CAAC,EAAE,YAAY,GAAG,sBAAsB,EAAE,MAAM,EAAE,KAAK,GAAG,UAAU,EAAE,GAAG,OAAO,CAAA;IAClG,IAAI,SAAkB,CAAA;IAEtB,KAAK,IAAI,OAAO,GAAG,CAAC,EAAE,OAAO,IAAI,OAAO,EAAE,OAAO,EAAE,EAAE,CAAC;QACrD,IAAI,OAAO,GAAG,CAAC,EAAE,CAAC;YACjB,MAAM,EAAE,CAAC,WAAW,OAAO,IAAI,OAAO,UAAU,YAAY,QAAQ,KAAK,EAAE,CAAC,CAAA;YAC5E,MAAM,KAAK,CAAC,YAAY,CAAC,CAAA;QAC1B,CAAC;QAED,IAAI,CAAC;YACJ,OAAO,MAAM,QAAQ,EAAE,CAAA;QACxB,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,SAAS,GAAG,KAAK,CAAA;QAClB,CAAC;IACF,CAAC;IAED,MAAM,SAAS,YAAY,KAAK,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,IAAI,KAAK,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,CAAA;AAC5E,CAAC;AAED;;GAEG;AACH,KAAK,UAAU,WAAW,CAAC,IAAY;IACtC,MAAM,IAAI,GAAG,MAAM,OAAO,CAAC,IAAI,CAAC,CAAA;IAEhC,OAAO,IAAI,EAAE,IAAI,IAAI,CAAC,CAAA;AACvB,CAAC;AAED;;;;;;;GAOG;AACH,MAAM,CAAC,KAAK,UAAU,iBAAiB,CAAC,OAOvC;IACA,MAAM,EAAE,GAAG,EAAE,IAAI,EAAE,OAAO,GAAG,EAAE,EAAE,cAAc,GAAG,GAAG,EAAE,YAAY,GAAG,sBAAsB,EAAE,MAAM,EAAE,GAAG,OAAO,CAAA;IAChH,MAAM,GAAG,GAAG,IAAI,GAAG,MAAM,CAAA;IACzB,IAAI,IAAI,GAAG,MAAM,WAAW,CAAC,GAAG,CAAC,CAAA;IACjC,IAAI,KAAyB,CAAA;IAE7B,KAAK,IAAI,UAAU,GAAG,CAAC,EAAE,UAAU,GAAG,cAAc,EAAE,UAAU,EAAE,EAAE,CAAC;QACpE,IAAI,KAAK,KAAK,SAAS,IAAI,IAAI,IAAI,KAAK;YAAE,MAAK;QAE/C,IAAI,GAAa,CAAA;QAEjB,IAAI,CAAC;YACJ,GAAG,GAAG,MAAM,KAAK,CAAC,GAAG,EAAE,EAAE,OAAO,EAAE,EAAE,GAAG,OAAO,EAAE,KAAK,EAAE,SAAS,IAAI,GAAG,EAAE,EAAE,MAAM,EAAE,WAAW,CAAC,OAAO,CAAC,OAAO,CAAC,EAAE,CAAC,CAAA;QACnH,CAAC;QAAC,MAAM,CAAC;YACR,MAAM,KAAK,CAAC,YAAY,CAAC,CAAA;YAEzB,SAAQ;QACT,CAAC;QAED,IAAI,GAAG,CAAC,MAAM,KAAK,0BAA0B,IAAI,IAAI,GAAG,CAAC,EAAE,CAAC;YAC3D,uGAAuG;YACvG,wEAAwE;YACxE,MAAM,KAAK,GAAG,WAAW,CAAC,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,GAAG,CAAC,eAAe,CAAC,IAAI,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;YAC3E,KAAK,GAAG,KAAK,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,IAAI,CAAA;YACpC,MAAM,GAAG,CAAC,IAAI,EAAE,MAAM,EAAE,CAAA;YAExB,MAAK;QACN,CAAC;QAED,IAAI,GAAG,CAAC,MAAM,KAAK,oBAAoB,EAAE,CAAC;YACzC,MAAM,IAAI,eAAe,CAAC,GAAG,CAAC,MAAM,EAAE,QAAQ,GAAG,CAAC,MAAM,0BAA0B,GAAG,EAAE,CAAC,CAAA;QACzF,CAAC;QAED,MAAM,KAAK,GAAG,sBAAsB,CAAC,IAAI,CAAC,GAAG,CAAC,OAAO,CAAC,GAAG,CAAC,eAAe,CAAC,IAAI,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;QAEtF,IAAI,KAAK,EAAE,CAAC;YACX,KAAK,GAAG,MAAM,CAAC,KAAK,CAAC,CAAA;QACtB,CAAC;QAED,MAAM,MAAM,GAAG,IAAI,CAAA;QAEnB,IAAI,CAAC;YACJ,2GAA2G;YAC3G,MAAM,QAAQ,CACb,QAAQ,CAAC,OAAO,CAAC,GAAG,CAAC,IAA8C,CAAC,EACpE,eAAe,CAAC,GAAG,EAAE,EAAE,KAAK,EAAE,GAAG,EAAE,CAAC,CACpC,CAAA;QACF,CAAC;QAAC,MAAM,CAAC;YACR,4GAA4G;QAC7G,CAAC;QAED,IAAI,GAAG,MAAM,WAAW,CAAC,GAAG,CAAC,CAAA;QAE7B,IAAI,IAAI,KAAK,MAAM,EAAE,CAAC;YACrB,MAAM,KAAK,CAAC,YAAY,CAAC,CAAA;QAC1B,CAAC;aAAM,CAAC;YACP,MAAM,EAAE,CAAC,KAAK,CAAC,IAAI,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,KAAK,CAAC,CAAC,CAAC,OAAO,CAAC,KAAK,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAA;QAChH,CAAC;IACF,CAAC;IAED,IAAI,KAAK,KAAK,SAAS,IAAI,IAAI,GAAG,KAAK,EAAE,CAAC;QACzC,MAAM,IAAI,KAAK,CAAC,iCAAiC,IAAI,OAAO,KAAK,IAAI,GAAG,YAAY,GAAG,EAAE,CAAC,CAAA;IAC3F,CAAC;IAED,MAAM,QAAQ,CAAC,GAAG,EAAE,IAAI,CAAC,CAAA;IAEzB,OAAO,IAAI,CAAA;AACZ,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,YAAY,CAAC,GAAa;IACzC,OAAO,GAAG,CAAC,OAAO;SAChB,YAAY,EAAE;SACd,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC;SACrC,IAAI,CAAC,IAAI,CAAC,CAAA;AACb,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,kBAAkB,CAAC,GAAa,EAAE,QAAgB;IACjE,MAAM,WAAW,GAAG,GAAG,CAAC,OAAO,CAAC,GAAG,CAAC,qBAAqB,CAAC,IAAI,EAAE,CAAA;IAChE,MAAM,QAAQ,GAAG,0CAA0C,CAAC,IAAI,CAAC,WAAW,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;IAElF,IAAI,QAAQ;QAAE,OAAO,kBAAkB,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAC,CAAA;IACxD,MAAM,KAAK,GAAG,uBAAuB,CAAC,IAAI,CAAC,WAAW,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;IAE5D,IAAI,KAAK;QAAE,OAAO,kBAAkB,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,CAAA;IAElD,OAAO,QAAQ,CAAA;AAChB,CAAC"}
|
|
@@ -0,0 +1,23 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Fetch Taiwan's company and business registers (公司登記資料, 商業登記資料) from the Ministry of
|
|
7
|
+
* Economic Affairs' commerce open-data platform, data.gcis.nat.gov.tw. The platform publishes the
|
|
8
|
+
* full registers as CSV files split by region (the six special municipalities each on their own,
|
|
9
|
+
* the rest of the island in four bands) and by industry letter, 148 files in all, each row carrying
|
|
10
|
+
* the registered address (公司地址) and, for companies, the tax office's business address
|
|
11
|
+
* (營業地址) as free text. This is the NOISY source for Taiwanese addresses: a person typed these.
|
|
12
|
+
*
|
|
13
|
+
* License: 政府資料開放授權條款-第1版 (Open Government Data License, Taiwan, v1.0). The platform's
|
|
14
|
+
* own dialog states the condition that binds: attribution in the form it prescribes, or the grant is
|
|
15
|
+
* void from the start ("未盡顯名標示義務者,視為自始未取得開放資料之授權"). The manifest records the
|
|
16
|
+
* prescribed wording per file so the corpus build and the model card can carry it.
|
|
17
|
+
*
|
|
18
|
+
* Invoke via `mailwoman corpus fetch gcis-tw --out-root <path>`.
|
|
19
|
+
*/
|
|
20
|
+
import type { BaseFetchOptions, FetchSummary } from "#tools/fetch/download";
|
|
21
|
+
export type FetchGCISTWOptions = BaseFetchOptions;
|
|
22
|
+
export declare function fetchGCISTW(options: FetchGCISTWOptions, report?: (line: string) => void): Promise<FetchSummary>;
|
|
23
|
+
//# sourceMappingURL=gcis-tw.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"gcis-tw.d.ts","sourceRoot":"","sources":["../../../lib/tools/fetch/gcis-tw.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;GAkBG;AASH,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAA4C,MAAM,uBAAuB,CAAA;AAgBrH,MAAM,MAAM,kBAAkB,GAAG,gBAAgB,CAAA;AA+CjD,wBAAsB,WAAW,CAAC,OAAO,EAAE,kBAAkB,EAAE,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAAG,OAAO,CAAC,YAAY,CAAC,CAoFrH"}
|
|
@@ -0,0 +1,135 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Fetch Taiwan's company and business registers (公司登記資料, 商業登記資料) from the Ministry of
|
|
7
|
+
* Economic Affairs' commerce open-data platform, data.gcis.nat.gov.tw. The platform publishes the
|
|
8
|
+
* full registers as CSV files split by region (the six special municipalities each on their own,
|
|
9
|
+
* the rest of the island in four bands) and by industry letter, 148 files in all, each row carrying
|
|
10
|
+
* the registered address (公司地址) and, for companies, the tax office's business address
|
|
11
|
+
* (營業地址) as free text. This is the NOISY source for Taiwanese addresses: a person typed these.
|
|
12
|
+
*
|
|
13
|
+
* License: 政府資料開放授權條款-第1版 (Open Government Data License, Taiwan, v1.0). The platform's
|
|
14
|
+
* own dialog states the condition that binds: attribution in the form it prescribes, or the grant is
|
|
15
|
+
* void from the start ("未盡顯名標示義務者,視為自始未取得開放資料之授權"). The manifest records the
|
|
16
|
+
* prescribed wording per file so the corpus build and the model card can carry it.
|
|
17
|
+
*
|
|
18
|
+
* Invoke via `mailwoman corpus fetch gcis-tw --out-root <path>`.
|
|
19
|
+
*/
|
|
20
|
+
import { BYTES_PER_KIB } from "@mailwoman/core/fs/formatters";
|
|
21
|
+
import { pathExists } from "@mailwoman/core/fs/readers";
|
|
22
|
+
import { makeDirectories } from "@mailwoman/core/fs/writers";
|
|
23
|
+
import { sha256File } from "@mailwoman/core/hash";
|
|
24
|
+
import { sleep } from "@mailwoman/core/utils/sleep";
|
|
25
|
+
import { join } from "path-ts";
|
|
26
|
+
import { loadCollectionFiles, streamBodyToFile, withRetries, writeManifest } from "#tools/fetch/download";
|
|
27
|
+
const SLUG = "gcis-tw";
|
|
28
|
+
const PORTAL = "https://data.gcis.nat.gov.tw";
|
|
29
|
+
const CATALOG_URL = `${PORTAL}/od/datacategory`;
|
|
30
|
+
const LICENSE = "政府資料開放授權條款-第1版 (Open Government Data License, Taiwan, v1.0) — http://data.gov.tw/license";
|
|
31
|
+
const ATTRIBUTION = "提供機關/經濟部商業發展署 [<dataset title>] — the 顯名聲明 each file's dialog prescribes";
|
|
32
|
+
const PACE_MS = 300;
|
|
33
|
+
/**
|
|
34
|
+
* The bulk register files: `<region><register>資料-<industry letter><industry>`. The per-industry API datasets and the
|
|
35
|
+
* monthly new-registration lists share the catalog and are not these.
|
|
36
|
+
*/
|
|
37
|
+
const BULK_TITLE = /(公司登記資料|商業登記資料)-[A-Z]/;
|
|
38
|
+
/**
|
|
39
|
+
* A file name a shell and a manifest can carry: the title with its punctuation folded to underscores.
|
|
40
|
+
*/
|
|
41
|
+
function filenameFor(title) {
|
|
42
|
+
return `${title
|
|
43
|
+
.replaceAll(/[()()、,/\\\s]+/g, "_")
|
|
44
|
+
.replaceAll(/_+/g, "_")
|
|
45
|
+
.replaceAll(/^_|_$/g, "")}.csv`;
|
|
46
|
+
}
|
|
47
|
+
async function listBulkDatasets() {
|
|
48
|
+
const res = await fetch(CATALOG_URL, { headers: { accept: "text/html" } });
|
|
49
|
+
if (!res.ok)
|
|
50
|
+
throw new Error(`gcis-tw: the catalog answered HTTP ${res.status}`);
|
|
51
|
+
const html = await res.text();
|
|
52
|
+
const datasets = [];
|
|
53
|
+
for (const [, path, rawTitle] of html.matchAll(/<a[^>]*href="(\/od\/detail[^"]*)"[^>]*>([^<]+)<\/a>/g)) {
|
|
54
|
+
const title = rawTitle?.trim();
|
|
55
|
+
if (!path || !title || !BULK_TITLE.test(title))
|
|
56
|
+
continue;
|
|
57
|
+
datasets.push({ title, detailPath: path.replace(/;jsessionid=[^?]*/, "") });
|
|
58
|
+
}
|
|
59
|
+
return datasets;
|
|
60
|
+
}
|
|
61
|
+
/**
|
|
62
|
+
* The `/od/file?oid=…` link a dataset's detail page hands its download dialog.
|
|
63
|
+
*/
|
|
64
|
+
async function fileURLFor(dataset) {
|
|
65
|
+
const res = await fetch(`${PORTAL}${dataset.detailPath}`, { headers: { accept: "text/html" } });
|
|
66
|
+
if (!res.ok)
|
|
67
|
+
return undefined;
|
|
68
|
+
const html = await res.text();
|
|
69
|
+
const path = /showDialog\('(\/od\/file\?oid=[^']+)'\)/.exec(html)?.[1];
|
|
70
|
+
return path ? `${PORTAL}${path}` : undefined;
|
|
71
|
+
}
|
|
72
|
+
export async function fetchGCISTW(options, report) {
|
|
73
|
+
const destDir = join(options.outRoot, SLUG);
|
|
74
|
+
await makeDirectories(destDir);
|
|
75
|
+
const manifestPath = join(destDir, "MANIFEST.json");
|
|
76
|
+
const datasets = await listBulkDatasets();
|
|
77
|
+
report?.(`=== ${SLUG}: ${datasets.length} bulk register files in the catalog`);
|
|
78
|
+
const previous = await loadCollectionFiles(manifestPath);
|
|
79
|
+
const files = new Map();
|
|
80
|
+
let fetched = 0;
|
|
81
|
+
let skipped = 0;
|
|
82
|
+
const failedCodes = [];
|
|
83
|
+
for (const dataset of datasets) {
|
|
84
|
+
const filename = filenameFor(dataset.title);
|
|
85
|
+
const dest = join(destDir, filename);
|
|
86
|
+
const before = previous.get(filename);
|
|
87
|
+
if (before && (await pathExists(dest))) {
|
|
88
|
+
files.set(filename, before);
|
|
89
|
+
skipped++;
|
|
90
|
+
continue;
|
|
91
|
+
}
|
|
92
|
+
await sleep(PACE_MS);
|
|
93
|
+
const url = await fileURLFor(dataset);
|
|
94
|
+
if (!url) {
|
|
95
|
+
report?.(` ✗ no file link on the detail page for ${dataset.title}`);
|
|
96
|
+
failedCodes.push(dataset.title);
|
|
97
|
+
continue;
|
|
98
|
+
}
|
|
99
|
+
report?.(`--- ${dataset.title}`);
|
|
100
|
+
let bytes;
|
|
101
|
+
try {
|
|
102
|
+
bytes = await withRetries(async () => {
|
|
103
|
+
const res = await fetch(url, { headers: { accept: "*/*" }, signal: AbortSignal.timeout(1_800_000) });
|
|
104
|
+
if (!res.ok)
|
|
105
|
+
throw new Error(`HTTP ${res.status} for ${dataset.title}`);
|
|
106
|
+
return streamBodyToFile(res, dest);
|
|
107
|
+
}, { report, label: dataset.title });
|
|
108
|
+
}
|
|
109
|
+
catch (error) {
|
|
110
|
+
report?.(` ✗ ${error.message}`);
|
|
111
|
+
failedCodes.push(dataset.title);
|
|
112
|
+
continue;
|
|
113
|
+
}
|
|
114
|
+
if (bytes < BYTES_PER_KIB) {
|
|
115
|
+
report?.(` ✗ ${bytes} bytes — an error page, not the register`);
|
|
116
|
+
failedCodes.push(dataset.title);
|
|
117
|
+
continue;
|
|
118
|
+
}
|
|
119
|
+
const sha = await sha256File(dest);
|
|
120
|
+
files.set(filename, { source_url: url, downloaded_at: new Date().toISOString(), filename, sha256: sha, bytes });
|
|
121
|
+
fetched++;
|
|
122
|
+
report?.(` ✓ ${(bytes / 1024 / 1024).toFixed(1)} MB sha256=${sha}`);
|
|
123
|
+
const manifest = {
|
|
124
|
+
source: SLUG,
|
|
125
|
+
source_url: CATALOG_URL,
|
|
126
|
+
license: LICENSE,
|
|
127
|
+
attribution: ATTRIBUTION,
|
|
128
|
+
downloaded_at: new Date().toISOString(),
|
|
129
|
+
files: [...files.values()],
|
|
130
|
+
};
|
|
131
|
+
await writeManifest(manifestPath, manifest);
|
|
132
|
+
}
|
|
133
|
+
return { fetched, skipped, failed: failedCodes.length, failedCodes };
|
|
134
|
+
}
|
|
135
|
+
//# sourceMappingURL=gcis-tw.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"gcis-tw.js","sourceRoot":"","sources":["../../../lib/tools/fetch/gcis-tw.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;GAkBG;AAEH,OAAO,EAAE,aAAa,EAAE,MAAM,+BAA+B,CAAA;AAC7D,OAAO,EAAE,UAAU,EAAE,MAAM,4BAA4B,CAAA;AACvD,OAAO,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAA;AAC5D,OAAO,EAAE,UAAU,EAAE,MAAM,sBAAsB,CAAA;AACjD,OAAO,EAAE,KAAK,EAAE,MAAM,6BAA6B,CAAA;AACnD,OAAO,EAAE,IAAI,EAAE,MAAM,SAAS,CAAA;AAG9B,OAAO,EAAE,mBAAmB,EAAE,gBAAgB,EAAE,WAAW,EAAE,aAAa,EAAE,MAAM,uBAAuB,CAAA;AAEzG,MAAM,IAAI,GAAG,SAAS,CAAA;AACtB,MAAM,MAAM,GAAG,8BAA8B,CAAA;AAC7C,MAAM,WAAW,GAAG,GAAG,MAAM,kBAAkB,CAAA;AAC/C,MAAM,OAAO,GAAG,0FAA0F,CAAA;AAC1G,MAAM,WAAW,GAAG,0EAA0E,CAAA;AAC9F,MAAM,OAAO,GAAG,GAAG,CAAA;AAEnB;;;GAGG;AACH,MAAM,UAAU,GAAG,uBAAuB,CAAA;AAS1C;;GAEG;AACH,SAAS,WAAW,CAAC,KAAa;IACjC,OAAO,GAAG,KAAK;SACb,UAAU,CAAC,iBAAiB,EAAE,GAAG,CAAC;SAClC,UAAU,CAAC,KAAK,EAAE,GAAG,CAAC;SACtB,UAAU,CAAC,QAAQ,EAAE,EAAE,CAAC,MAAM,CAAA;AACjC,CAAC;AAED,KAAK,UAAU,gBAAgB;IAC9B,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,WAAW,EAAE,EAAE,OAAO,EAAE,EAAE,MAAM,EAAE,WAAW,EAAE,EAAE,CAAC,CAAA;IAE1E,IAAI,CAAC,GAAG,CAAC,EAAE;QAAE,MAAM,IAAI,KAAK,CAAC,sCAAsC,GAAG,CAAC,MAAM,EAAE,CAAC,CAAA;IAChF,MAAM,IAAI,GAAG,MAAM,GAAG,CAAC,IAAI,EAAE,CAAA;IAC7B,MAAM,QAAQ,GAAc,EAAE,CAAA;IAE9B,KAAK,MAAM,CAAC,EAAE,IAAI,EAAE,QAAQ,CAAC,IAAI,IAAI,CAAC,QAAQ,CAAC,sDAAsD,CAAC,EAAE,CAAC;QACxG,MAAM,KAAK,GAAG,QAAQ,EAAE,IAAI,EAAE,CAAA;QAE9B,IAAI,CAAC,IAAI,IAAI,CAAC,KAAK,IAAI,CAAC,UAAU,CAAC,IAAI,CAAC,KAAK,CAAC;YAAE,SAAQ;QACxD,QAAQ,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,UAAU,EAAE,IAAI,CAAC,OAAO,CAAC,mBAAmB,EAAE,EAAE,CAAC,EAAE,CAAC,CAAA;IAC5E,CAAC;IAED,OAAO,QAAQ,CAAA;AAChB,CAAC;AAED;;GAEG;AACH,KAAK,UAAU,UAAU,CAAC,OAAgB;IACzC,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,GAAG,MAAM,GAAG,OAAO,CAAC,UAAU,EAAE,EAAE,EAAE,OAAO,EAAE,EAAE,MAAM,EAAE,WAAW,EAAE,EAAE,CAAC,CAAA;IAE/F,IAAI,CAAC,GAAG,CAAC,EAAE;QAAE,OAAO,SAAS,CAAA;IAC7B,MAAM,IAAI,GAAG,MAAM,GAAG,CAAC,IAAI,EAAE,CAAA;IAC7B,MAAM,IAAI,GAAG,yCAAyC,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC,CAAA;IAEtE,OAAO,IAAI,CAAC,CAAC,CAAC,GAAG,MAAM,GAAG,IAAI,EAAE,CAAC,CAAC,CAAC,SAAS,CAAA;AAC7C,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,WAAW,CAAC,OAA2B,EAAE,MAA+B;IAC7F,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,IAAI,CAAC,CAAA;IAC3C,MAAM,eAAe,CAAC,OAAO,CAAC,CAAA;IAC9B,MAAM,YAAY,GAAG,IAAI,CAAC,OAAO,EAAE,eAAe,CAAC,CAAA;IAEnD,MAAM,QAAQ,GAAG,MAAM,gBAAgB,EAAE,CAAA;IACzC,MAAM,EAAE,CAAC,OAAO,IAAI,KAAK,QAAQ,CAAC,MAAM,qCAAqC,CAAC,CAAA;IAE9E,MAAM,QAAQ,GAAG,MAAM,mBAAmB,CAAC,YAAY,CAAC,CAAA;IACxD,MAAM,KAAK,GAAG,IAAI,GAAG,EAA0B,CAAA;IAC/C,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,MAAM,WAAW,GAAa,EAAE,CAAA;IAEhC,KAAK,MAAM,OAAO,IAAI,QAAQ,EAAE,CAAC;QAChC,MAAM,QAAQ,GAAG,WAAW,CAAC,OAAO,CAAC,KAAK,CAAC,CAAA;QAC3C,MAAM,IAAI,GAAG,IAAI,CAAC,OAAO,EAAE,QAAQ,CAAC,CAAA;QACpC,MAAM,MAAM,GAAG,QAAQ,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAA;QAErC,IAAI,MAAM,IAAI,CAAC,MAAM,UAAU,CAAC,IAAI,CAAC,CAAC,EAAE,CAAC;YACxC,KAAK,CAAC,GAAG,CAAC,QAAQ,EAAE,MAAM,CAAC,CAAA;YAE3B,OAAO,EAAE,CAAA;YAET,SAAQ;QACT,CAAC;QAED,MAAM,KAAK,CAAC,OAAO,CAAC,CAAA;QACpB,MAAM,GAAG,GAAG,MAAM,UAAU,CAAC,OAAO,CAAC,CAAA;QAErC,IAAI,CAAC,GAAG,EAAE,CAAC;YACV,MAAM,EAAE,CAAC,2CAA2C,OAAO,CAAC,KAAK,EAAE,CAAC,CAAA;YACpE,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,KAAK,CAAC,CAAA;YAE/B,SAAQ;QACT,CAAC;QAED,MAAM,EAAE,CAAC,OAAO,OAAO,CAAC,KAAK,EAAE,CAAC,CAAA;QAChC,IAAI,KAAa,CAAA;QAEjB,IAAI,CAAC;YACJ,KAAK,GAAG,MAAM,WAAW,CACxB,KAAK,IAAI,EAAE;gBACV,MAAM,GAAG,GAAG,MAAM,KAAK,CAAC,GAAG,EAAE,EAAE,OAAO,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,EAAE,MAAM,EAAE,WAAW,CAAC,OAAO,CAAC,SAAS,CAAC,EAAE,CAAC,CAAA;gBAEpG,IAAI,CAAC,GAAG,CAAC,EAAE;oBAAE,MAAM,IAAI,KAAK,CAAC,QAAQ,GAAG,CAAC,MAAM,QAAQ,OAAO,CAAC,KAAK,EAAE,CAAC,CAAA;gBAEvE,OAAO,gBAAgB,CAAC,GAAG,EAAE,IAAI,CAAC,CAAA;YACnC,CAAC,EACD,EAAE,MAAM,EAAE,KAAK,EAAE,OAAO,CAAC,KAAK,EAAE,CAChC,CAAA;QACF,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,MAAM,EAAE,CAAC,OAAQ,KAAe,CAAC,OAAO,EAAE,CAAC,CAAA;YAC3C,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,KAAK,CAAC,CAAA;YAE/B,SAAQ;QACT,CAAC;QAED,IAAI,KAAK,GAAG,aAAa,EAAE,CAAC;YAC3B,MAAM,EAAE,CAAC,OAAO,KAAK,0CAA0C,CAAC,CAAA;YAChE,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,KAAK,CAAC,CAAA;YAE/B,SAAQ;QACT,CAAC;QAED,MAAM,GAAG,GAAG,MAAM,UAAU,CAAC,IAAI,CAAC,CAAA;QAClC,KAAK,CAAC,GAAG,CAAC,QAAQ,EAAE,EAAE,UAAU,EAAE,GAAG,EAAE,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,GAAG,EAAE,KAAK,EAAE,CAAC,CAAA;QAE/G,OAAO,EAAE,CAAA;QACT,MAAM,EAAE,CAAC,OAAO,CAAC,KAAK,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe,GAAG,EAAE,CAAC,CAAA;QAErE,MAAM,QAAQ,GAA6B;YAC1C,MAAM,EAAE,IAAI;YACZ,UAAU,EAAE,WAAW;YACvB,OAAO,EAAE,OAAO;YAChB,WAAW,EAAE,WAAW;YACxB,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;YACvC,KAAK,EAAE,CAAC,GAAG,KAAK,CAAC,MAAM,EAAE,CAAC;SAC1B,CAAA;QAED,MAAM,aAAa,CAAC,YAAY,EAAE,QAAQ,CAAC,CAAA;IAC5C,CAAC;IAED,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,EAAE,WAAW,CAAC,MAAM,EAAE,WAAW,EAAE,CAAA;AACrE,CAAC"}
|
|
@@ -0,0 +1,91 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Fetch GeoNames per-country GAZETTEER dumps — the 19-column `<CC>.txt` files under
|
|
7
|
+
* `https://download.geonames.org/export/dump/` (NOT the postal exports; those are `export/zip/` and
|
|
8
|
+
* `geonames-postal.ts`'s job). The dumps carry feature classes and codes (column 8: `PPLC` national capital,
|
|
9
|
+
* `PPLA` first-order administrative seat), which is what the capitals reference build consumes (#1880).
|
|
10
|
+
*
|
|
11
|
+
* The catalog question is answered by the SOURCE, not by an ISO list: `countryInfo.txt` in the same directory
|
|
12
|
+
* enumerates every country GeoNames publishes, one row per ISO alpha-2 code, and also names each country's
|
|
13
|
+
* capital — the cross-check the capitals build grades its `PPLC` extraction against. Fetch that first; derive
|
|
14
|
+
* the country set from it; then a dump absent from disk is a measured gap against the source's own catalog
|
|
15
|
+
* rather than a silent hole. The dump directory may hold files this tool did not fetch: present files are never
|
|
16
|
+
* overwritten, and a present `<CC>.txt` that is NOT a 19-column gazetteer dump (GeoNames' postal exports share
|
|
17
|
+
* the basename) is reported as `wrong_format_present`, never counted as coverage.
|
|
18
|
+
*/
|
|
19
|
+
import type { BaseFetchOptions, FetchSummary } from "#tools/fetch/download";
|
|
20
|
+
export interface FetchGeonamesDumpOptions extends BaseFetchOptions {
|
|
21
|
+
/**
|
|
22
|
+
* ISO alpha-2 codes, any casing. Absent → every country `countryInfo.txt` enumerates.
|
|
23
|
+
*/
|
|
24
|
+
countries?: readonly string[];
|
|
25
|
+
/**
|
|
26
|
+
* Dump directory to read from. Defaults to GeoNames' own; exists so the 404 and coverage behaviour can be exercised
|
|
27
|
+
* against a local server.
|
|
28
|
+
*/
|
|
29
|
+
baseURL?: string;
|
|
30
|
+
/**
|
|
31
|
+
* Refetch a dump whose `<CC>.txt` already exists. Default false — the tool fills gaps.
|
|
32
|
+
*/
|
|
33
|
+
force?: boolean;
|
|
34
|
+
}
|
|
35
|
+
interface GeonamesDumpFileEntry {
|
|
36
|
+
country: string;
|
|
37
|
+
filename: string;
|
|
38
|
+
source_url: string;
|
|
39
|
+
sha256: string;
|
|
40
|
+
bytes: number;
|
|
41
|
+
}
|
|
42
|
+
export interface GeonamesDumpManifest {
|
|
43
|
+
source: string;
|
|
44
|
+
base_url: string;
|
|
45
|
+
license: string;
|
|
46
|
+
attribution: string;
|
|
47
|
+
downloaded_at: string;
|
|
48
|
+
files: GeonamesDumpFileEntry[];
|
|
49
|
+
/**
|
|
50
|
+
* `<CC>.txt` files already on disk and left alone — the hand-fetched population this tool extends.
|
|
51
|
+
*/
|
|
52
|
+
skipped_present: string[];
|
|
53
|
+
/**
|
|
54
|
+
* Countries in the source catalog that the source's dump directory nonetheless 404s — a fact about the source,
|
|
55
|
+
* recorded so a later reader does not spend the fetch to rediscover it.
|
|
56
|
+
*/
|
|
57
|
+
unavailable: string[];
|
|
58
|
+
/**
|
|
59
|
+
* Present `<CC>.txt` files that are NOT 19-column gazetteer dumps — GeoNames' postal exports share the same basename,
|
|
60
|
+
* and seven tier-1 postal files sat at these paths reading as "present" until the capitals build found them
|
|
61
|
+
* capital-less. Left in place (this tool never overwrites data it did not fetch); the fix is to move the file to its
|
|
62
|
+
* own home and rerun.
|
|
63
|
+
*/
|
|
64
|
+
wrong_format_present: string[];
|
|
65
|
+
}
|
|
66
|
+
/**
|
|
67
|
+
* True when the first non-empty line carries the gazetteer dump's 19 tab-separated columns. Accepts a partial head read
|
|
68
|
+
* — the first line is the whole question, so callers need not hand it a resident 350 MB dump.
|
|
69
|
+
*
|
|
70
|
+
* Walk the string directly rather than constructing a spliterator: the capitals builder already holds whole country
|
|
71
|
+
* dumps as strings, and a byte-oriented spliterator would UTF-8 encode that input — allocating up to another 350 MB —
|
|
72
|
+
* merely to inspect its first non-empty line.
|
|
73
|
+
*/
|
|
74
|
+
export declare function looksLikeGazetteerDump(text: string): boolean;
|
|
75
|
+
/**
|
|
76
|
+
* Parse the ISO codes (column 1) and capital names (column 6) out of `countryInfo.txt` — `#`-prefixed lines are the
|
|
77
|
+
* file's own commentary.
|
|
78
|
+
*/
|
|
79
|
+
export declare function parseCountryInfo(text: string): Array<{
|
|
80
|
+
country: string;
|
|
81
|
+
capital: string;
|
|
82
|
+
}>;
|
|
83
|
+
/**
|
|
84
|
+
* Download `countryInfo.txt` plus every missing `<CC>.zip`, extracting each to `<outRoot>/<CC>.txt` beside the
|
|
85
|
+
* hand-fetched dumps, with a `MANIFEST.json` naming fetched, skipped-present, and source-unavailable countries.
|
|
86
|
+
*/
|
|
87
|
+
export declare function fetchGeonamesDumps(options: FetchGeonamesDumpOptions, report?: (line: string) => void): Promise<FetchSummary & {
|
|
88
|
+
skippedPresent: string[];
|
|
89
|
+
}>;
|
|
90
|
+
export {};
|
|
91
|
+
//# sourceMappingURL=geonames-dump.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"geonames-dump.d.ts","sourceRoot":"","sources":["../../../lib/tools/fetch/geonames-dump.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;GAiBG;AAQH,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAA;AAgB3E,MAAM,WAAW,wBAAyB,SAAQ,gBAAgB;IACjE;;OAEG;IACH,SAAS,CAAC,EAAE,SAAS,MAAM,EAAE,CAAA;IAC7B;;;OAGG;IACH,OAAO,CAAC,EAAE,MAAM,CAAA;IAChB;;OAEG;IACH,KAAK,CAAC,EAAE,OAAO,CAAA;CACf;AAED,UAAU,qBAAqB;IAC9B,OAAO,EAAE,MAAM,CAAA;IACf,QAAQ,EAAE,MAAM,CAAA;IAChB,UAAU,EAAE,MAAM,CAAA;IAClB,MAAM,EAAE,MAAM,CAAA;IACd,KAAK,EAAE,MAAM,CAAA;CACb;AAED,MAAM,WAAW,oBAAoB;IACpC,MAAM,EAAE,MAAM,CAAA;IACd,QAAQ,EAAE,MAAM,CAAA;IAChB,OAAO,EAAE,MAAM,CAAA;IACf,WAAW,EAAE,MAAM,CAAA;IACnB,aAAa,EAAE,MAAM,CAAA;IACrB,KAAK,EAAE,qBAAqB,EAAE,CAAA;IAC9B;;OAEG;IACH,eAAe,EAAE,MAAM,EAAE,CAAA;IACzB;;;OAGG;IACH,WAAW,EAAE,MAAM,EAAE,CAAA;IACrB;;;;;OAKG;IACH,oBAAoB,EAAE,MAAM,EAAE,CAAA;CAC9B;AAQD;;;;;;;GAOG;AACH,wBAAgB,sBAAsB,CAAC,IAAI,EAAE,MAAM,GAAG,OAAO,CAuB5D;AAED;;;GAGG;AACH,wBAAgB,gBAAgB,CAAC,IAAI,EAAE,MAAM,GAAG,KAAK,CAAC;IAAE,OAAO,EAAE,MAAM,CAAC;IAAC,OAAO,EAAE,MAAM,CAAA;CAAE,CAAC,CAiB1F;AAQD;;;GAGG;AACH,wBAAsB,kBAAkB,CACvC,OAAO,EAAE,wBAAwB,EACjC,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,YAAY,GAAG;IAAE,cAAc,EAAE,MAAM,EAAE,CAAA;CAAE,CAAC,CA2FtD"}
|