@mailwoman/corpus 9.3.0 → 10.0.0
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 +16 -0
- package/lib/adapters/geonames/adapter.ts +3 -3
- package/lib/adapters/geonames/postal/adapter.ts +122 -0
- package/lib/adapters/index.ts +39 -32
- package/lib/adapters/openaddresses/adapter.ts +4 -7
- package/lib/adapters/osm/adapter.ts +278 -0
- package/lib/adapters/overture/adapter.ts +22 -7
- package/lib/adapters/utils/index.ts +1 -1
- package/lib/adapters/wof/admin/json/adapter.ts +239 -0
- package/lib/adapters/wof/json-rows.ts +181 -0
- package/lib/adapters/wof/postalcode-json/adapter.ts +196 -0
- package/lib/au/adapters/gnaf/adapter.ts +152 -0
- package/lib/au/adapters/gnaf/assemble.ts +225 -0
- package/lib/cz/recipes/pcfirst-preposition.ts +112 -0
- package/lib/de/recipes/locale.ts +360 -0
- package/lib/fr/adapters/ban/adapter.ts +159 -0
- package/lib/fr/recipes/admin-split.ts +243 -0
- package/lib/fr/recipes/bare-street.ts +171 -0
- package/lib/fr/recipes/fragment.ts +334 -0
- package/lib/fr/recipes/lieudit.ts +274 -0
- package/lib/fr/recipes/order.ts +246 -0
- package/lib/fr/tools/fetch/ban.ts +289 -0
- package/lib/index.ts +1 -1
- package/lib/international/recipes/locale.ts +598 -0
- package/lib/jp/tools/fetch/houjin.ts +141 -0
- package/lib/kr/adapters/juso/label-rows.ts +259 -0
- package/lib/kr/adapters/localdata/align.ts +299 -0
- package/lib/kr/adapters/localdata/key-index.ts +185 -0
- package/lib/kr/adapters/localdata/permit-rows.ts +186 -0
- package/lib/kr/tools/fetch/juso.ts +172 -0
- package/lib/kr/tools/fetch/localdata.ts +206 -0
- package/lib/nl/recipes/postcode.ts +117 -0
- package/lib/no/recipes/fragment.ts +213 -0
- package/lib/no/recipes/street/index.ts +91 -0
- package/lib/no/recipes/street/led.ts +135 -0
- package/lib/recipes/anchor-absorption.ts +2 -2
- package/lib/recipes/bare/country.ts +95 -0
- package/lib/recipes/bare/postcode/eval.ts +99 -0
- package/lib/recipes/bare/postcode/index.ts +327 -0
- package/lib/recipes/boundary-stress.ts +3 -1
- package/lib/recipes/country-balanced.ts +3 -2
- package/lib/recipes/house-venue.ts +2 -1
- package/lib/recipes/index.ts +28 -21
- package/lib/recipes/intersection.ts +3 -2
- package/lib/recipes/po/box/cedex/au-nz.ts +82 -0
- package/lib/recipes/po/box/cedex/ca.ts +58 -0
- package/lib/recipes/po/box/cedex/fr.ts +76 -0
- package/lib/recipes/po/box/cedex/phrases.ts +108 -0
- package/lib/recipes/po/box/cedex/recipe.ts +203 -0
- package/lib/recipes/po/box/cedex/sources.ts +189 -0
- package/lib/recipes/po/box/cedex/types.ts +35 -0
- package/lib/recipes/po/box/cedex/us.ts +69 -0
- package/lib/recipes/po/box/cedex/vocabulary.ts +106 -0
- package/lib/recipes/po/box/cedex.ts +9 -0
- package/lib/recipes/po/box/index.ts +128 -0
- package/lib/recipes/scaffold.ts +18 -42
- package/lib/recipes/street/affix.ts +807 -0
- package/lib/recipes/street/bare.ts +102 -0
- package/lib/recipes/street.ts +3 -1
- package/lib/recipes/sub/venue/context.ts +149 -0
- package/lib/recipes/sub/venue/index.ts +997 -0
- package/lib/recipes/sub/venue/sources.ts +739 -0
- package/lib/recipes/trailing-region.ts +9 -9
- package/lib/recipes/unit.ts +3 -3
- package/lib/sg/recipes/register.ts +270 -0
- package/lib/sg/tools/fetch/acra.ts +179 -0
- package/lib/si/recipes/bare-village.ts +99 -0
- package/lib/south-asia/recipes/register.ts +214 -0
- package/lib/synthesizers/anchor-absorption.ts +1 -1
- package/lib/synthesizers/locale.ts +261 -0
- package/lib/synthesizers/street.ts +1 -1
- package/lib/synthesizers/utils.ts +2 -2
- package/lib/tools/audit.ts +3 -2
- package/lib/tools/corpus-stats.ts +3 -3
- package/lib/tools/fetch/download/index.ts +10 -0
- package/lib/tools/fetch/download/manifest.ts +102 -0
- package/lib/tools/fetch/download/network.ts +226 -0
- package/lib/tools/fetch/download/retry.ts +173 -0
- package/lib/tools/fetch/geonames/dump.ts +257 -0
- package/lib/tools/fetch/geonames/postal.ts +180 -0
- package/lib/tools/fetch/index.ts +47 -20
- package/lib/tools/fetch/openaddresses.ts +2 -2
- package/lib/tools/fetch/ourairports.ts +2 -2
- package/lib/tools/fetch/ppd.ts +1 -3
- package/lib/tools/fetch/wikidata-subvenue.ts +2 -2
- package/lib/tools/golden/promote.ts +340 -0
- package/lib/tools/golden/relabel-street/directory.ts +340 -0
- package/lib/tools/golden/relabel-street/index.ts +9 -0
- package/lib/tools/golden/relabel-street/row.ts +361 -0
- package/lib/tools/index.ts +10 -10
- package/lib/tools/ingest-csv.ts +5 -7
- package/lib/tools/lint/slice/vocab.ts +376 -0
- package/lib/tools/overlay-manifest.ts +92 -25
- package/lib/tools/overture-subvenue.ts +1 -1
- package/lib/tools/postcode-triples.ts +138 -14
- package/lib/tools/sub/venue/harvest.ts +234 -0
- package/lib/tools/sub/venue/head-nouns.ts +245 -0
- package/lib/tools/sub/venue/lexicon.ts +429 -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/tw/tools/fetch/gcis.ts +180 -0
- package/lib/types.ts +1 -1
- package/lib/us/adapters/fcc-bdc/adapter.ts +173 -0
- package/lib/us/adapters/state/hi-schools/adapter.ts +160 -0
- package/lib/us/adapters/state/ia-contractors/adapter.ts +136 -0
- package/lib/us/adapters/state/ny-notaries/adapter.ts +133 -0
- package/lib/us/adapters/state/tx-notaries/adapter.ts +149 -0
- package/lib/us/adapters/tiger/adapter.ts +250 -0
- package/lib/us/adapters/usgov/hrsa-fqhc/adapter.ts +156 -0
- package/lib/us/adapters/usgov/imls-pls/adapter.ts +134 -0
- package/lib/us/adapters/usgov/irs-bmf/adapter.ts +145 -0
- package/lib/us/adapters/usgov/nad/adapter.ts +324 -0
- package/lib/us/adapters/usgov/nppes/adapter.ts +143 -0
- package/lib/us/adapters/usgov/samhsa-treatment-locator/adapter.ts +182 -0
- package/lib/us/tools/fetch/hrsa.ts +59 -0
- package/lib/us/tools/fetch/imls-pls.ts +149 -0
- package/lib/us/tools/fetch/nad.ts +341 -0
- package/lib/us/tools/fetch/nppes.ts +165 -0
- package/lib/us/tools/fetch/state/hi-schools.ts +161 -0
- package/lib/us/tools/fetch/state/sources.ts +146 -0
- package/lib/us/tools/fetch/tiger-full.ts +308 -0
- package/lib/utils/align.ts +1 -1
- package/lib/utils/golden.ts +12 -8
- package/lib/utils/wof-json.ts +7 -13
- package/out/adapters/geonames/adapter.d.ts +1 -1
- package/out/adapters/geonames/adapter.js +3 -3
- package/out/adapters/geonames/adapter.js.map +1 -1
- 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/index.d.ts +16 -16
- package/out/adapters/index.d.ts.map +1 -1
- package/out/adapters/index.js +34 -32
- package/out/adapters/index.js.map +1 -1
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -1
- package/out/adapters/openaddresses/adapter.js +4 -6
- package/out/adapters/openaddresses/adapter.js.map +1 -1
- package/out/adapters/osm/adapter.d.ts +95 -0
- package/out/adapters/osm/adapter.d.ts.map +1 -0
- package/out/adapters/osm/adapter.js +211 -0
- package/out/adapters/osm/adapter.js.map +1 -0
- package/out/adapters/overture/adapter.d.ts +10 -0
- package/out/adapters/overture/adapter.d.ts.map +1 -1
- package/out/adapters/overture/adapter.js +20 -7
- package/out/adapters/overture/adapter.js.map +1 -1
- package/out/adapters/synth-po-box/adapter.js.map +1 -1
- package/out/adapters/utils/index.d.ts +1 -1
- package/out/adapters/utils/index.d.ts.map +1 -1
- package/out/adapters/utils/index.js.map +1 -1
- 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 +204 -0
- package/out/adapters/wof/admin/json/adapter.js.map +1 -0
- package/out/adapters/wof/json-rows.d.ts +73 -0
- package/out/adapters/wof/json-rows.d.ts.map +1 -0
- package/out/adapters/wof/json-rows.js +115 -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 +167 -0
- package/out/adapters/wof/postalcode-json/adapter.js.map +1 -0
- package/out/au/adapters/gnaf/adapter.d.ts.map +1 -0
- package/out/au/adapters/gnaf/adapter.js +127 -0
- package/out/au/adapters/gnaf/adapter.js.map +1 -0
- package/out/au/adapters/gnaf/assemble.d.ts +65 -0
- package/out/au/adapters/gnaf/assemble.d.ts.map +1 -0
- package/out/au/adapters/gnaf/assemble.js +154 -0
- package/out/au/adapters/gnaf/assemble.js.map +1 -0
- package/out/cn/recipes/organizational-units.d.ts +36 -0
- package/out/cn/recipes/organizational-units.d.ts.map +1 -0
- package/out/cn/recipes/organizational-units.js +159 -0
- package/out/cn/recipes/organizational-units.js.map +1 -0
- package/out/cz/recipes/pcfirst-preposition.d.ts +22 -0
- package/out/cz/recipes/pcfirst-preposition.d.ts.map +1 -0
- package/out/cz/recipes/pcfirst-preposition.js +101 -0
- package/out/cz/recipes/pcfirst-preposition.js.map +1 -0
- package/out/de/recipes/locale.d.ts +44 -0
- package/out/de/recipes/locale.d.ts.map +1 -0
- package/out/de/recipes/locale.js +289 -0
- package/out/de/recipes/locale.js.map +1 -0
- package/out/env.d.ts +1 -1
- package/out/fr/adapters/ban/adapter.d.ts.map +1 -0
- package/out/fr/adapters/ban/adapter.js +123 -0
- package/out/fr/adapters/ban/adapter.js.map +1 -0
- package/out/fr/adapters/ban/street-decompose.d.ts.map +1 -0
- package/out/fr/adapters/ban/street-decompose.js.map +1 -0
- package/out/fr/recipes/admin-split.d.ts +38 -0
- package/out/fr/recipes/admin-split.d.ts.map +1 -0
- package/out/fr/recipes/admin-split.js +192 -0
- package/out/fr/recipes/admin-split.js.map +1 -0
- package/out/fr/recipes/bare-street.d.ts +28 -0
- package/out/fr/recipes/bare-street.d.ts.map +1 -0
- package/out/fr/recipes/bare-street.js +144 -0
- package/out/fr/recipes/bare-street.js.map +1 -0
- package/out/fr/recipes/fragment.d.ts +77 -0
- package/out/fr/recipes/fragment.d.ts.map +1 -0
- package/out/fr/recipes/fragment.js +277 -0
- package/out/fr/recipes/fragment.js.map +1 -0
- package/out/fr/recipes/lieudit.d.ts +32 -0
- package/out/fr/recipes/lieudit.d.ts.map +1 -0
- package/out/fr/recipes/lieudit.js +211 -0
- package/out/fr/recipes/lieudit.js.map +1 -0
- package/out/fr/recipes/order.d.ts +38 -0
- package/out/fr/recipes/order.d.ts.map +1 -0
- package/out/fr/recipes/order.js +198 -0
- package/out/fr/recipes/order.js.map +1 -0
- package/out/fr/tools/fetch/ban.d.ts +31 -0
- package/out/fr/tools/fetch/ban.d.ts.map +1 -0
- package/out/fr/tools/fetch/ban.js +239 -0
- package/out/fr/tools/fetch/ban.js.map +1 -0
- package/out/index.d.ts +1 -1
- package/out/index.d.ts.map +1 -1
- package/out/index.js +1 -1
- package/out/index.js.map +1 -1
- package/out/international/recipes/locale.d.ts +136 -0
- package/out/international/recipes/locale.d.ts.map +1 -0
- package/out/international/recipes/locale.js +458 -0
- package/out/international/recipes/locale.js.map +1 -0
- package/out/jp/adapters/wof-admin/adapter.d.ts.map +1 -0
- package/out/jp/adapters/wof-admin/adapter.js.map +1 -0
- package/out/jp/tools/fetch/houjin.d.ts +24 -0
- package/out/jp/tools/fetch/houjin.d.ts.map +1 -0
- package/out/jp/tools/fetch/houjin.js +102 -0
- package/out/jp/tools/fetch/houjin.js.map +1 -0
- package/out/kr/adapters/juso/label-rows.d.ts +76 -0
- package/out/kr/adapters/juso/label-rows.d.ts.map +1 -0
- package/out/kr/adapters/juso/label-rows.js +194 -0
- package/out/kr/adapters/juso/label-rows.js.map +1 -0
- package/out/kr/adapters/localdata/align.d.ts +43 -0
- package/out/kr/adapters/localdata/align.d.ts.map +1 -0
- package/out/kr/adapters/localdata/align.js +223 -0
- package/out/kr/adapters/localdata/align.js.map +1 -0
- package/out/kr/adapters/localdata/key-index.d.ts +71 -0
- package/out/kr/adapters/localdata/key-index.d.ts.map +1 -0
- package/out/kr/adapters/localdata/key-index.js +133 -0
- package/out/kr/adapters/localdata/key-index.js.map +1 -0
- package/out/kr/adapters/localdata/permit-rows.d.ts +66 -0
- package/out/kr/adapters/localdata/permit-rows.d.ts.map +1 -0
- package/out/kr/adapters/localdata/permit-rows.js +131 -0
- package/out/kr/adapters/localdata/permit-rows.js.map +1 -0
- package/out/kr/tools/fetch/juso.d.ts +30 -0
- package/out/kr/tools/fetch/juso.d.ts.map +1 -0
- package/out/kr/tools/fetch/juso.js +120 -0
- package/out/kr/tools/fetch/juso.js.map +1 -0
- package/out/kr/tools/fetch/localdata.d.ts +30 -0
- package/out/kr/tools/fetch/localdata.d.ts.map +1 -0
- package/out/kr/tools/fetch/localdata.js +139 -0
- package/out/kr/tools/fetch/localdata.js.map +1 -0
- package/out/nl/recipes/postcode.d.ts +26 -0
- package/out/nl/recipes/postcode.d.ts.map +1 -0
- package/out/nl/recipes/postcode.js +103 -0
- package/out/nl/recipes/postcode.js.map +1 -0
- package/out/no/recipes/fragment.d.ts +43 -0
- package/out/no/recipes/fragment.d.ts.map +1 -0
- package/out/no/recipes/fragment.js +183 -0
- package/out/no/recipes/fragment.js.map +1 -0
- package/out/no/recipes/street/index.d.ts +18 -0
- package/out/no/recipes/street/index.d.ts.map +1 -0
- package/out/no/recipes/street/index.js +72 -0
- package/out/no/recipes/street/index.js.map +1 -0
- package/out/no/recipes/street/led.d.ts +24 -0
- package/out/no/recipes/street/led.d.ts.map +1 -0
- package/out/no/recipes/street/led.js +114 -0
- package/out/no/recipes/street/led.js.map +1 -0
- package/out/recipes/anchor-absorption.d.ts.map +1 -1
- package/out/recipes/anchor-absorption.js +2 -1
- package/out/recipes/anchor-absorption.js.map +1 -1
- 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/bare/postcode/eval.d.ts +29 -0
- package/out/recipes/bare/postcode/eval.d.ts.map +1 -0
- package/out/recipes/bare/postcode/eval.js +85 -0
- package/out/recipes/bare/postcode/eval.js.map +1 -0
- package/out/recipes/bare/postcode/index.d.ts +62 -0
- package/out/recipes/bare/postcode/index.d.ts.map +1 -0
- package/out/recipes/bare/postcode/index.js +267 -0
- package/out/recipes/bare/postcode/index.js.map +1 -0
- package/out/recipes/boundary-stress.d.ts.map +1 -1
- package/out/recipes/boundary-stress.js +2 -1
- package/out/recipes/boundary-stress.js.map +1 -1
- package/out/recipes/country-balanced.d.ts.map +1 -1
- package/out/recipes/country-balanced.js +2 -1
- package/out/recipes/country-balanced.js.map +1 -1
- package/out/recipes/house-venue.d.ts.map +1 -1
- package/out/recipes/house-venue.js +2 -1
- package/out/recipes/house-venue.js.map +1 -1
- package/out/recipes/index.d.ts.map +1 -1
- package/out/recipes/index.js +28 -21
- package/out/recipes/index.js.map +1 -1
- package/out/recipes/intersection.d.ts.map +1 -1
- package/out/recipes/intersection.js +2 -1
- package/out/recipes/intersection.js.map +1 -1
- package/out/recipes/po/box/cedex/au-nz.d.ts +7 -0
- package/out/recipes/po/box/cedex/au-nz.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/au-nz.js +56 -0
- package/out/recipes/po/box/cedex/au-nz.js.map +1 -0
- package/out/recipes/po/box/cedex/ca.d.ts +7 -0
- package/out/recipes/po/box/cedex/ca.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/ca.js +38 -0
- package/out/recipes/po/box/cedex/ca.js.map +1 -0
- package/out/recipes/po/box/cedex/fr.d.ts +7 -0
- package/out/recipes/po/box/cedex/fr.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/fr.js +57 -0
- package/out/recipes/po/box/cedex/fr.js.map +1 -0
- package/out/recipes/po/box/cedex/phrases.d.ts +8 -0
- package/out/recipes/po/box/cedex/phrases.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/phrases.js +76 -0
- package/out/recipes/po/box/cedex/phrases.js.map +1 -0
- package/out/recipes/po/box/cedex/recipe.d.ts +9 -0
- package/out/recipes/po/box/cedex/recipe.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/recipe.js +153 -0
- package/out/recipes/po/box/cedex/recipe.js.map +1 -0
- package/out/recipes/po/box/cedex/sources.d.ts +86 -0
- package/out/recipes/po/box/cedex/sources.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/sources.js +143 -0
- package/out/recipes/po/box/cedex/sources.js.map +1 -0
- package/out/recipes/po/box/cedex/types.d.ts +31 -0
- package/out/recipes/po/box/cedex/types.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/types.js +5 -0
- package/out/recipes/po/box/cedex/types.js.map +1 -0
- package/out/recipes/po/box/cedex/us.d.ts +7 -0
- package/out/recipes/po/box/cedex/us.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/us.js +51 -0
- package/out/recipes/po/box/cedex/us.js.map +1 -0
- package/out/recipes/po/box/cedex/vocabulary.d.ts +68 -0
- package/out/recipes/po/box/cedex/vocabulary.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/vocabulary.js +90 -0
- package/out/recipes/po/box/cedex/vocabulary.js.map +1 -0
- package/out/recipes/po/box/cedex.d.ts +9 -0
- package/out/recipes/po/box/cedex.d.ts.map +1 -0
- package/out/recipes/po/box/cedex.js +9 -0
- package/out/recipes/po/box/cedex.js.map +1 -0
- package/out/recipes/po/box/index.d.ts +17 -0
- package/out/recipes/po/box/index.d.ts.map +1 -0
- package/out/recipes/po/box/index.js +105 -0
- package/out/recipes/po/box/index.js.map +1 -0
- package/out/recipes/scaffold.d.ts +20 -1
- package/out/recipes/scaffold.d.ts.map +1 -1
- package/out/recipes/scaffold.js +18 -49
- package/out/recipes/scaffold.js.map +1 -1
- 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 +565 -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.map +1 -1
- package/out/recipes/street.js +2 -1
- package/out/recipes/street.js.map +1 -1
- package/out/recipes/sub/venue/context.d.ts +29 -0
- package/out/recipes/sub/venue/context.d.ts.map +1 -0
- package/out/recipes/sub/venue/context.js +106 -0
- package/out/recipes/sub/venue/context.js.map +1 -0
- package/out/recipes/sub/venue/index.d.ts +270 -0
- package/out/recipes/sub/venue/index.d.ts.map +1 -0
- package/out/recipes/sub/venue/index.js +728 -0
- package/out/recipes/sub/venue/index.js.map +1 -0
- package/out/recipes/sub/venue/sources.d.ts +209 -0
- package/out/recipes/sub/venue/sources.d.ts.map +1 -0
- package/out/recipes/sub/venue/sources.js +555 -0
- package/out/recipes/sub/venue/sources.js.map +1 -0
- package/out/recipes/trailing-region.d.ts.map +1 -1
- package/out/recipes/trailing-region.js +8 -2
- package/out/recipes/trailing-region.js.map +1 -1
- package/out/recipes/unit.d.ts.map +1 -1
- package/out/recipes/unit.js +2 -1
- package/out/recipes/unit.js.map +1 -1
- package/out/sg/recipes/register.d.ts +69 -0
- package/out/sg/recipes/register.d.ts.map +1 -0
- package/out/sg/recipes/register.js +211 -0
- package/out/sg/recipes/register.js.map +1 -0
- package/out/sg/tools/fetch/acra.d.ts +23 -0
- package/out/sg/tools/fetch/acra.d.ts.map +1 -0
- package/out/sg/tools/fetch/acra.js +126 -0
- package/out/sg/tools/fetch/acra.js.map +1 -0
- package/out/si/recipes/bare-village.d.ts +32 -0
- package/out/si/recipes/bare-village.d.ts.map +1 -0
- package/out/si/recipes/bare-village.js +89 -0
- package/out/si/recipes/bare-village.js.map +1 -0
- package/out/south-asia/recipes/register.d.ts +51 -0
- package/out/south-asia/recipes/register.d.ts.map +1 -0
- package/out/south-asia/recipes/register.js +154 -0
- package/out/south-asia/recipes/register.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +1 -1
- package/out/synthesizers/anchor-absorption.d.ts.map +1 -1
- package/out/synthesizers/anchor-absorption.js.map +1 -1
- package/out/synthesizers/boundary-stress.js.map +1 -1
- package/out/synthesizers/house-venue.js.map +1 -1
- package/out/synthesizers/intersection.js.map +1 -1
- package/out/synthesizers/locale.d.ts +116 -0
- package/out/synthesizers/locale.d.ts.map +1 -0
- package/out/synthesizers/locale.js +150 -0
- package/out/synthesizers/locale.js.map +1 -0
- package/out/synthesizers/no-street.d.ts.map +1 -1
- package/out/synthesizers/no-street.js.map +1 -1
- package/out/synthesizers/po-box.js.map +1 -1
- package/out/synthesizers/street.d.ts.map +1 -1
- package/out/synthesizers/street.js +1 -1
- package/out/synthesizers/street.js.map +1 -1
- package/out/synthesizers/utils.js +1 -1
- package/out/synthesizers/utils.js.map +1 -1
- package/out/test-kit/corpus-recipe.d.ts.map +1 -1
- package/out/test-kit/corpus-recipe.js.map +1 -1
- package/out/tools/audit.d.ts.map +1 -1
- package/out/tools/audit.js +3 -2
- package/out/tools/audit.js.map +1 -1
- package/out/tools/corpus-stats.js +3 -3
- package/out/tools/corpus-stats.js.map +1 -1
- package/out/tools/fetch/download/index.d.ts +10 -0
- package/out/tools/fetch/download/index.d.ts.map +1 -0
- package/out/tools/fetch/download/index.js +10 -0
- package/out/tools/fetch/download/index.js.map +1 -0
- package/out/tools/fetch/download/manifest.d.ts +47 -0
- package/out/tools/fetch/download/manifest.d.ts.map +1 -0
- package/out/tools/fetch/download/manifest.js +74 -0
- package/out/tools/fetch/download/manifest.js.map +1 -0
- package/out/tools/fetch/download/network.d.ts +105 -0
- package/out/tools/fetch/download/network.d.ts.map +1 -0
- package/out/tools/fetch/download/network.js +130 -0
- package/out/tools/fetch/download/network.js.map +1 -0
- package/out/tools/fetch/download/retry.d.ts +45 -0
- package/out/tools/fetch/download/retry.d.ts.map +1 -0
- package/out/tools/fetch/download/retry.js +136 -0
- package/out/tools/fetch/download/retry.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/index.d.ts +47 -20
- package/out/tools/fetch/index.d.ts.map +1 -1
- package/out/tools/fetch/index.js +47 -20
- package/out/tools/fetch/index.js.map +1 -1
- package/out/tools/fetch/openaddresses.d.ts +1 -1
- package/out/tools/fetch/openaddresses.d.ts.map +1 -1
- package/out/tools/fetch/openaddresses.js +1 -1
- package/out/tools/fetch/openaddresses.js.map +1 -1
- package/out/tools/fetch/ourairports.d.ts +1 -1
- package/out/tools/fetch/ourairports.d.ts.map +1 -1
- package/out/tools/fetch/ourairports.js +1 -1
- package/out/tools/fetch/ourairports.js.map +1 -1
- package/out/tools/fetch/ppd.js +1 -3
- package/out/tools/fetch/ppd.js.map +1 -1
- package/out/tools/fetch/wikidata-subvenue.d.ts +1 -1
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -1
- package/out/tools/fetch/wikidata-subvenue.js +1 -1
- package/out/tools/fetch/wikidata-subvenue.js.map +1 -1
- 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 +72 -0
- package/out/tools/golden/promote.d.ts.map +1 -0
- package/out/tools/golden/promote.js +243 -0
- package/out/tools/golden/promote.js.map +1 -0
- package/out/tools/golden/relabel-street/directory.d.ts +83 -0
- package/out/tools/golden/relabel-street/directory.d.ts.map +1 -0
- package/out/tools/golden/relabel-street/directory.js +216 -0
- package/out/tools/golden/relabel-street/directory.js.map +1 -0
- package/out/tools/golden/relabel-street/index.d.ts +9 -0
- package/out/tools/golden/relabel-street/index.d.ts.map +1 -0
- package/out/tools/golden/relabel-street/index.js +9 -0
- package/out/tools/golden/relabel-street/index.js.map +1 -0
- package/out/tools/golden/relabel-street/row.d.ts +121 -0
- package/out/tools/golden/relabel-street/row.d.ts.map +1 -0
- package/out/tools/golden/relabel-street/row.js +232 -0
- package/out/tools/golden/relabel-street/row.js.map +1 -0
- package/out/tools/index.d.ts +10 -10
- package/out/tools/index.d.ts.map +1 -1
- package/out/tools/index.js +10 -10
- package/out/tools/index.js.map +1 -1
- package/out/tools/ingest-csv.d.ts.map +1 -1
- package/out/tools/ingest-csv.js +5 -7
- package/out/tools/ingest-csv.js.map +1 -1
- package/out/tools/lint/slice/index.d.ts +93 -0
- package/out/tools/lint/slice/index.d.ts.map +1 -0
- package/out/tools/lint/slice/index.js +322 -0
- package/out/tools/lint/slice/index.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 +254 -0
- package/out/tools/lint/slice/vocab.js.map +1 -0
- package/out/tools/overlay-manifest.d.ts +56 -6
- package/out/tools/overlay-manifest.d.ts.map +1 -1
- package/out/tools/overlay-manifest.js +56 -15
- package/out/tools/overlay-manifest.js.map +1 -1
- package/out/tools/overture-subvenue.d.ts +1 -1
- package/out/tools/postcode-triples.d.ts +36 -0
- package/out/tools/postcode-triples.d.ts.map +1 -1
- package/out/tools/postcode-triples.js +91 -12
- package/out/tools/postcode-triples.js.map +1 -1
- 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.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/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.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.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/tw/tools/fetch/gcis.d.ts +23 -0
- package/out/tw/tools/fetch/gcis.d.ts.map +1 -0
- package/out/tw/tools/fetch/gcis.js +135 -0
- package/out/tw/tools/fetch/gcis.js.map +1 -0
- package/out/types.d.ts +1 -1
- package/out/types.d.ts.map +1 -1
- package/out/us/adapters/fcc-bdc/adapter.d.ts.map +1 -0
- package/out/us/adapters/fcc-bdc/adapter.js +142 -0
- package/out/us/adapters/fcc-bdc/adapter.js.map +1 -0
- package/out/us/adapters/state/hi-schools/adapter.d.ts.map +1 -0
- package/out/us/adapters/state/hi-schools/adapter.js +136 -0
- package/out/us/adapters/state/hi-schools/adapter.js.map +1 -0
- package/out/us/adapters/state/hi-schools/workbook.d.ts.map +1 -0
- package/out/us/adapters/state/hi-schools/workbook.js.map +1 -0
- package/out/us/adapters/state/ia-contractors/adapter.d.ts.map +1 -0
- package/out/us/adapters/state/ia-contractors/adapter.js +104 -0
- package/out/us/adapters/state/ia-contractors/adapter.js.map +1 -0
- package/out/us/adapters/state/ny-notaries/adapter.d.ts.map +1 -0
- package/out/us/adapters/state/ny-notaries/adapter.js +112 -0
- package/out/us/adapters/state/ny-notaries/adapter.js.map +1 -0
- package/out/us/adapters/state/tx-notaries/adapter.d.ts.map +1 -0
- package/out/us/adapters/state/tx-notaries/adapter.js +118 -0
- package/out/us/adapters/state/tx-notaries/adapter.js.map +1 -0
- package/out/us/adapters/tiger/adapter.d.ts +55 -0
- package/out/us/adapters/tiger/adapter.d.ts.map +1 -0
- package/out/us/adapters/tiger/adapter.js +197 -0
- package/out/us/adapters/tiger/adapter.js.map +1 -0
- package/out/us/adapters/tiger/street-decompose.d.ts.map +1 -0
- package/out/us/adapters/tiger/street-decompose.js.map +1 -0
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.js +121 -0
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.js.map +1 -0
- package/out/us/adapters/usgov/imls-pls/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/imls-pls/adapter.js +106 -0
- package/out/us/adapters/usgov/imls-pls/adapter.js.map +1 -0
- package/out/us/adapters/usgov/irs-bmf/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/irs-bmf/adapter.js +116 -0
- package/out/us/adapters/usgov/irs-bmf/adapter.js.map +1 -0
- package/out/us/adapters/usgov/nad/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/nad/adapter.js +239 -0
- package/out/us/adapters/usgov/nad/adapter.js.map +1 -0
- package/out/us/adapters/usgov/nppes/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/nppes/adapter.js +110 -0
- package/out/us/adapters/usgov/nppes/adapter.js.map +1 -0
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js +143 -0
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js.map +1 -0
- package/out/us/fips-state.d.ts +41 -0
- package/out/us/fips-state.d.ts.map +1 -0
- package/out/us/fips-state.js +100 -0
- package/out/us/fips-state.js.map +1 -0
- package/out/us/tools/fetch/hrsa.d.ts +18 -0
- package/out/us/tools/fetch/hrsa.d.ts.map +1 -0
- package/out/us/tools/fetch/hrsa.js +46 -0
- package/out/us/tools/fetch/hrsa.js.map +1 -0
- package/out/us/tools/fetch/imls-pls.d.ts +25 -0
- package/out/us/tools/fetch/imls-pls.d.ts.map +1 -0
- package/out/us/tools/fetch/imls-pls.js +108 -0
- package/out/us/tools/fetch/imls-pls.js.map +1 -0
- package/out/us/tools/fetch/nad.d.ts +70 -0
- package/out/us/tools/fetch/nad.d.ts.map +1 -0
- package/out/us/tools/fetch/nad.js +234 -0
- package/out/us/tools/fetch/nad.js.map +1 -0
- package/out/us/tools/fetch/nppes.d.ts +26 -0
- package/out/us/tools/fetch/nppes.d.ts.map +1 -0
- package/out/us/tools/fetch/nppes.js +126 -0
- package/out/us/tools/fetch/nppes.js.map +1 -0
- package/out/us/tools/fetch/state/hi-schools.d.ts +26 -0
- package/out/us/tools/fetch/state/hi-schools.d.ts.map +1 -0
- package/out/us/tools/fetch/state/hi-schools.js +112 -0
- package/out/us/tools/fetch/state/hi-schools.js.map +1 -0
- package/out/us/tools/fetch/state/sources.d.ts +26 -0
- package/out/us/tools/fetch/state/sources.d.ts.map +1 -0
- package/out/us/tools/fetch/state/sources.js +111 -0
- package/out/us/tools/fetch/state/sources.js.map +1 -0
- package/out/us/tools/fetch/tiger-full.d.ts +22 -0
- package/out/us/tools/fetch/tiger-full.d.ts.map +1 -0
- package/out/us/tools/fetch/tiger-full.js +217 -0
- package/out/us/tools/fetch/tiger-full.js.map +1 -0
- package/out/utils/align.d.ts +1 -1
- package/out/utils/align.d.ts.map +1 -1
- package/out/utils/align.js.map +1 -1
- package/out/utils/golden.d.ts +7 -3
- package/out/utils/golden.d.ts.map +1 -1
- package/out/utils/golden.js +12 -8
- package/out/utils/golden.js.map +1 -1
- package/out/utils/parquet.d.ts.map +1 -1
- package/out/utils/split.js.map +1 -1
- package/out/utils/wof-json.d.ts.map +1 -1
- package/out/utils/wof-json.js +7 -12
- package/out/utils/wof-json.js.map +1 -1
- package/out/ve/recipes/reviewed-postcode-tail.d.ts.map +1 -0
- package/out/ve/recipes/reviewed-postcode-tail.js.map +1 -0
- package/package.json +196 -46
- package/lib/adapters/ban/adapter.ts +0 -190
- package/lib/adapters/fcc-bdc/adapter.ts +0 -174
- package/lib/adapters/geonames-postal/adapter.ts +0 -122
- package/lib/adapters/gnaf/adapter.ts +0 -149
- package/lib/adapters/gnaf/assemble.ts +0 -225
- package/lib/adapters/state-hi-schools/adapter.ts +0 -170
- package/lib/adapters/state-ia-contractors/adapter.ts +0 -144
- package/lib/adapters/state-ny-notaries/adapter.ts +0 -141
- package/lib/adapters/state-tx-notaries/adapter.ts +0 -157
- package/lib/adapters/tiger/adapter.ts +0 -252
- package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +0 -167
- package/lib/adapters/usgov-imls-pls/adapter.ts +0 -143
- package/lib/adapters/usgov-irs-bmf/adapter.ts +0 -151
- package/lib/adapters/usgov-nad/adapter.ts +0 -334
- package/lib/adapters/usgov-nppes/adapter.ts +0 -151
- package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -193
- package/lib/adapters/wof-admin-json/adapter.ts +0 -231
- package/lib/adapters/wof-json-rows.ts +0 -129
- package/lib/adapters/wof-postalcode-json/adapter.ts +0 -176
- package/lib/name-prone-us-suffixes.ts +0 -12
- package/lib/recipes/bare-country.ts +0 -95
- package/lib/recipes/cz-pcfirst-preposition.ts +0 -111
- package/lib/recipes/fr-admin-split.ts +0 -242
- package/lib/recipes/fr-bare-street.ts +0 -170
- package/lib/recipes/fr-fragment.ts +0 -333
- package/lib/recipes/fr-lieudit.ts +0 -301
- package/lib/recipes/fr-order.ts +0 -245
- package/lib/recipes/german.ts +0 -359
- package/lib/recipes/locale.ts +0 -599
- package/lib/recipes/nl-postcode.ts +0 -115
- package/lib/recipes/no-fragment.ts +0 -219
- package/lib/recipes/no-street-led.ts +0 -141
- package/lib/recipes/no-street.ts +0 -90
- package/lib/recipes/po-box-cedex.ts +0 -976
- package/lib/recipes/po-box.ts +0 -123
- package/lib/recipes/si-bare-village.ts +0 -97
- package/lib/recipes/street-affix.ts +0 -804
- package/lib/recipes/street-bare.ts +0 -100
- package/lib/recipes/sub-venue-sources.ts +0 -877
- package/lib/recipes/sub-venue.ts +0 -997
- package/lib/synthesizers/german.ts +0 -260
- package/lib/tools/fetch/ban.ts +0 -289
- package/lib/tools/fetch/download.ts +0 -262
- package/lib/tools/fetch/geonames-dump.ts +0 -257
- package/lib/tools/fetch/geonames-postal.ts +0 -180
- package/lib/tools/fetch/hrsa.ts +0 -59
- package/lib/tools/fetch/imls-pls.ts +0 -149
- package/lib/tools/fetch/nad.ts +0 -341
- package/lib/tools/fetch/nppes.ts +0 -165
- package/lib/tools/fetch/state-hi-schools.ts +0 -161
- package/lib/tools/fetch/state-sources.ts +0 -146
- package/lib/tools/fetch/tiger-full.ts +0 -308
- package/lib/tools/golden-promote.ts +0 -337
- package/lib/tools/golden-relabel-street.ts +0 -683
- package/lib/tools/lint-slice-vocab.ts +0 -388
- package/lib/tools/sub-venue/harvest.ts +0 -234
- package/lib/tools/sub-venue/head-nouns.ts +0 -245
- package/lib/tools/sub-venue/surfaces.ts +0 -95
- package/lib/tools/sub-venue/table.ts +0 -281
- package/lib/tools/sub-venue/wikidata.ts +0 -85
- package/lib/tools/sub-venue-lexicon.ts +0 -429
- package/out/adapters/ban/adapter.d.ts.map +0 -1
- package/out/adapters/ban/adapter.js +0 -149
- package/out/adapters/ban/adapter.js.map +0 -1
- package/out/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/adapters/ban/street-decompose.js.map +0 -1
- package/out/adapters/fcc-bdc/adapter.d.ts.map +0 -1
- package/out/adapters/fcc-bdc/adapter.js +0 -144
- package/out/adapters/fcc-bdc/adapter.js.map +0 -1
- package/out/adapters/geonames-postal/adapter.d.ts.map +0 -1
- package/out/adapters/geonames-postal/adapter.js +0 -107
- package/out/adapters/geonames-postal/adapter.js.map +0 -1
- package/out/adapters/gnaf/adapter.d.ts.map +0 -1
- package/out/adapters/gnaf/adapter.js +0 -124
- package/out/adapters/gnaf/adapter.js.map +0 -1
- package/out/adapters/gnaf/assemble.d.ts +0 -65
- package/out/adapters/gnaf/assemble.d.ts.map +0 -1
- package/out/adapters/gnaf/assemble.js +0 -154
- package/out/adapters/gnaf/assemble.js.map +0 -1
- package/out/adapters/state-hi-schools/adapter.d.ts.map +0 -1
- package/out/adapters/state-hi-schools/adapter.js +0 -145
- package/out/adapters/state-hi-schools/adapter.js.map +0 -1
- package/out/adapters/state-hi-schools/workbook.d.ts.map +0 -1
- package/out/adapters/state-hi-schools/workbook.js.map +0 -1
- package/out/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
- package/out/adapters/state-ia-contractors/adapter.js +0 -111
- package/out/adapters/state-ia-contractors/adapter.js.map +0 -1
- package/out/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
- package/out/adapters/state-ny-notaries/adapter.js +0 -119
- package/out/adapters/state-ny-notaries/adapter.js.map +0 -1
- package/out/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
- package/out/adapters/state-tx-notaries/adapter.js +0 -125
- package/out/adapters/state-tx-notaries/adapter.js.map +0 -1
- package/out/adapters/tiger/adapter.d.ts +0 -55
- package/out/adapters/tiger/adapter.d.ts.map +0 -1
- package/out/adapters/tiger/adapter.js +0 -201
- package/out/adapters/tiger/adapter.js.map +0 -1
- package/out/adapters/tiger/street-decompose.d.ts.map +0 -1
- package/out/adapters/tiger/street-decompose.js.map +0 -1
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-hrsa-fqhc/adapter.js +0 -132
- package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
- package/out/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-imls-pls/adapter.js +0 -114
- package/out/adapters/usgov-imls-pls/adapter.js.map +0 -1
- package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-irs-bmf/adapter.js +0 -120
- package/out/adapters/usgov-irs-bmf/adapter.js.map +0 -1
- package/out/adapters/usgov-nad/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-nad/adapter.js +0 -249
- package/out/adapters/usgov-nad/adapter.js.map +0 -1
- package/out/adapters/usgov-nppes/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-nppes/adapter.js +0 -118
- package/out/adapters/usgov-nppes/adapter.js.map +0 -1
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -154
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
- package/out/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
- package/out/adapters/wof-admin-jp/adapter.js.map +0 -1
- package/out/adapters/wof-admin-json/adapter.d.ts +0 -79
- package/out/adapters/wof-admin-json/adapter.d.ts.map +0 -1
- package/out/adapters/wof-admin-json/adapter.js +0 -197
- package/out/adapters/wof-admin-json/adapter.js.map +0 -1
- package/out/adapters/wof-json-rows.d.ts +0 -62
- package/out/adapters/wof-json-rows.d.ts.map +0 -1
- package/out/adapters/wof-json-rows.js +0 -83
- package/out/adapters/wof-json-rows.js.map +0 -1
- package/out/adapters/wof-postalcode-json/adapter.d.ts +0 -65
- package/out/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
- package/out/adapters/wof-postalcode-json/adapter.js +0 -151
- package/out/adapters/wof-postalcode-json/adapter.js.map +0 -1
- package/out/codex/us-fips-state.d.ts +0 -41
- package/out/codex/us-fips-state.d.ts.map +0 -1
- package/out/codex/us-fips-state.js +0 -100
- package/out/codex/us-fips-state.js.map +0 -1
- package/out/name-prone-us-suffixes.d.ts +0 -12
- package/out/name-prone-us-suffixes.d.ts.map +0 -1
- package/out/name-prone-us-suffixes.js +0 -12
- package/out/name-prone-us-suffixes.js.map +0 -1
- package/out/recipes/bare-country.d.ts +0 -25
- package/out/recipes/bare-country.d.ts.map +0 -1
- package/out/recipes/bare-country.js +0 -87
- package/out/recipes/bare-country.js.map +0 -1
- package/out/recipes/cn-organizational-units.d.ts +0 -36
- package/out/recipes/cn-organizational-units.d.ts.map +0 -1
- package/out/recipes/cn-organizational-units.js +0 -159
- package/out/recipes/cn-organizational-units.js.map +0 -1
- package/out/recipes/cz-pcfirst-preposition.d.ts +0 -22
- package/out/recipes/cz-pcfirst-preposition.d.ts.map +0 -1
- package/out/recipes/cz-pcfirst-preposition.js +0 -100
- package/out/recipes/cz-pcfirst-preposition.js.map +0 -1
- package/out/recipes/fr-admin-split.d.ts +0 -38
- package/out/recipes/fr-admin-split.d.ts.map +0 -1
- package/out/recipes/fr-admin-split.js +0 -192
- package/out/recipes/fr-admin-split.js.map +0 -1
- package/out/recipes/fr-bare-street.d.ts +0 -28
- package/out/recipes/fr-bare-street.d.ts.map +0 -1
- package/out/recipes/fr-bare-street.js +0 -143
- package/out/recipes/fr-bare-street.js.map +0 -1
- package/out/recipes/fr-fragment.d.ts +0 -77
- package/out/recipes/fr-fragment.d.ts.map +0 -1
- package/out/recipes/fr-fragment.js +0 -276
- package/out/recipes/fr-fragment.js.map +0 -1
- package/out/recipes/fr-lieudit.d.ts +0 -32
- package/out/recipes/fr-lieudit.d.ts.map +0 -1
- package/out/recipes/fr-lieudit.js +0 -227
- package/out/recipes/fr-lieudit.js.map +0 -1
- package/out/recipes/fr-order.d.ts +0 -38
- package/out/recipes/fr-order.d.ts.map +0 -1
- package/out/recipes/fr-order.js +0 -197
- package/out/recipes/fr-order.js.map +0 -1
- package/out/recipes/german.d.ts +0 -44
- package/out/recipes/german.d.ts.map +0 -1
- package/out/recipes/german.js +0 -288
- package/out/recipes/german.js.map +0 -1
- package/out/recipes/locale.d.ts +0 -136
- package/out/recipes/locale.d.ts.map +0 -1
- package/out/recipes/locale.js +0 -460
- package/out/recipes/locale.js.map +0 -1
- package/out/recipes/nl-postcode.d.ts +0 -26
- package/out/recipes/nl-postcode.d.ts.map +0 -1
- package/out/recipes/nl-postcode.js +0 -102
- package/out/recipes/nl-postcode.js.map +0 -1
- package/out/recipes/no-fragment.d.ts +0 -43
- package/out/recipes/no-fragment.d.ts.map +0 -1
- package/out/recipes/no-fragment.js +0 -182
- package/out/recipes/no-fragment.js.map +0 -1
- package/out/recipes/no-street-led.d.ts +0 -24
- package/out/recipes/no-street-led.d.ts.map +0 -1
- package/out/recipes/no-street-led.js +0 -113
- package/out/recipes/no-street-led.js.map +0 -1
- package/out/recipes/no-street.d.ts +0 -18
- package/out/recipes/no-street.d.ts.map +0 -1
- package/out/recipes/no-street.js +0 -71
- package/out/recipes/no-street.js.map +0 -1
- package/out/recipes/po-box-cedex.d.ts +0 -38
- package/out/recipes/po-box-cedex.d.ts.map +0 -1
- package/out/recipes/po-box-cedex.js +0 -767
- package/out/recipes/po-box-cedex.js.map +0 -1
- package/out/recipes/po-box.d.ts +0 -17
- package/out/recipes/po-box.d.ts.map +0 -1
- package/out/recipes/po-box.js +0 -100
- package/out/recipes/po-box.js.map +0 -1
- package/out/recipes/reviewed-postcode-tail.d.ts.map +0 -1
- package/out/recipes/reviewed-postcode-tail.js.map +0 -1
- package/out/recipes/si-bare-village.d.ts +0 -32
- package/out/recipes/si-bare-village.d.ts.map +0 -1
- package/out/recipes/si-bare-village.js +0 -88
- package/out/recipes/si-bare-village.js.map +0 -1
- package/out/recipes/street-affix.d.ts +0 -89
- package/out/recipes/street-affix.d.ts.map +0 -1
- package/out/recipes/street-affix.js +0 -563
- package/out/recipes/street-affix.js.map +0 -1
- package/out/recipes/street-bare.d.ts +0 -25
- package/out/recipes/street-bare.d.ts.map +0 -1
- package/out/recipes/street-bare.js +0 -86
- package/out/recipes/street-bare.js.map +0 -1
- package/out/recipes/sub-venue-sources.d.ts +0 -229
- package/out/recipes/sub-venue-sources.d.ts.map +0 -1
- package/out/recipes/sub-venue-sources.js +0 -653
- package/out/recipes/sub-venue-sources.js.map +0 -1
- package/out/recipes/sub-venue.d.ts +0 -269
- package/out/recipes/sub-venue.d.ts.map +0 -1
- package/out/recipes/sub-venue.js +0 -725
- package/out/recipes/sub-venue.js.map +0 -1
- package/out/synthesizers/german.d.ts +0 -115
- package/out/synthesizers/german.d.ts.map +0 -1
- package/out/synthesizers/german.js +0 -149
- package/out/synthesizers/german.js.map +0 -1
- package/out/tools/fetch/ban.d.ts +0 -31
- package/out/tools/fetch/ban.d.ts.map +0 -1
- package/out/tools/fetch/ban.js +0 -239
- package/out/tools/fetch/ban.js.map +0 -1
- package/out/tools/fetch/download.d.ts +0 -117
- package/out/tools/fetch/download.d.ts.map +0 -1
- package/out/tools/fetch/download.js +0 -160
- package/out/tools/fetch/download.js.map +0 -1
- package/out/tools/fetch/geonames-dump.d.ts +0 -91
- package/out/tools/fetch/geonames-dump.d.ts.map +0 -1
- package/out/tools/fetch/geonames-dump.js +0 -171
- package/out/tools/fetch/geonames-dump.js.map +0 -1
- package/out/tools/fetch/geonames-postal.d.ts +0 -76
- package/out/tools/fetch/geonames-postal.d.ts.map +0 -1
- package/out/tools/fetch/geonames-postal.js +0 -126
- package/out/tools/fetch/geonames-postal.js.map +0 -1
- package/out/tools/fetch/hrsa.d.ts +0 -18
- package/out/tools/fetch/hrsa.d.ts.map +0 -1
- package/out/tools/fetch/hrsa.js +0 -46
- package/out/tools/fetch/hrsa.js.map +0 -1
- package/out/tools/fetch/imls-pls.d.ts +0 -25
- package/out/tools/fetch/imls-pls.d.ts.map +0 -1
- package/out/tools/fetch/imls-pls.js +0 -108
- package/out/tools/fetch/imls-pls.js.map +0 -1
- package/out/tools/fetch/nad.d.ts +0 -70
- package/out/tools/fetch/nad.d.ts.map +0 -1
- package/out/tools/fetch/nad.js +0 -234
- package/out/tools/fetch/nad.js.map +0 -1
- package/out/tools/fetch/nppes.d.ts +0 -26
- package/out/tools/fetch/nppes.d.ts.map +0 -1
- package/out/tools/fetch/nppes.js +0 -126
- package/out/tools/fetch/nppes.js.map +0 -1
- package/out/tools/fetch/state-hi-schools.d.ts +0 -26
- package/out/tools/fetch/state-hi-schools.d.ts.map +0 -1
- package/out/tools/fetch/state-hi-schools.js +0 -112
- package/out/tools/fetch/state-hi-schools.js.map +0 -1
- package/out/tools/fetch/state-sources.d.ts +0 -26
- package/out/tools/fetch/state-sources.d.ts.map +0 -1
- package/out/tools/fetch/state-sources.js +0 -111
- package/out/tools/fetch/state-sources.js.map +0 -1
- package/out/tools/fetch/tiger-full.d.ts +0 -22
- package/out/tools/fetch/tiger-full.d.ts.map +0 -1
- package/out/tools/fetch/tiger-full.js +0 -217
- package/out/tools/fetch/tiger-full.js.map +0 -1
- package/out/tools/golden-expand.d.ts +0 -90
- package/out/tools/golden-expand.d.ts.map +0 -1
- package/out/tools/golden-expand.js +0 -406
- package/out/tools/golden-expand.js.map +0 -1
- package/out/tools/golden-promote.d.ts +0 -72
- package/out/tools/golden-promote.d.ts.map +0 -1
- package/out/tools/golden-promote.js +0 -240
- package/out/tools/golden-promote.js.map +0 -1
- package/out/tools/golden-relabel-street.d.ts +0 -196
- package/out/tools/golden-relabel-street.d.ts.map +0 -1
- package/out/tools/golden-relabel-street.js +0 -440
- package/out/tools/golden-relabel-street.js.map +0 -1
- package/out/tools/lint-slice-vocab.d.ts +0 -90
- package/out/tools/lint-slice-vocab.d.ts.map +0 -1
- package/out/tools/lint-slice-vocab.js +0 -267
- package/out/tools/lint-slice-vocab.js.map +0 -1
- package/out/tools/lint-slice.d.ts +0 -93
- package/out/tools/lint-slice.d.ts.map +0 -1
- package/out/tools/lint-slice.js +0 -322
- package/out/tools/lint-slice.js.map +0 -1
- package/out/tools/slice-kryptonite.d.ts +0 -32
- package/out/tools/slice-kryptonite.d.ts.map +0 -1
- package/out/tools/slice-kryptonite.js +0 -99
- package/out/tools/slice-kryptonite.js.map +0 -1
- package/out/tools/slice-translit.d.ts +0 -51
- package/out/tools/slice-translit.d.ts.map +0 -1
- package/out/tools/slice-translit.js +0 -166
- package/out/tools/slice-translit.js.map +0 -1
- package/out/tools/sub-venue/harvest.d.ts +0 -100
- package/out/tools/sub-venue/harvest.d.ts.map +0 -1
- package/out/tools/sub-venue/harvest.js +0 -168
- package/out/tools/sub-venue/harvest.js.map +0 -1
- package/out/tools/sub-venue/head-nouns.d.ts +0 -50
- package/out/tools/sub-venue/head-nouns.d.ts.map +0 -1
- package/out/tools/sub-venue/head-nouns.js.map +0 -1
- package/out/tools/sub-venue/surfaces.d.ts +0 -45
- package/out/tools/sub-venue/surfaces.d.ts.map +0 -1
- package/out/tools/sub-venue/surfaces.js.map +0 -1
- package/out/tools/sub-venue/table.d.ts +0 -229
- package/out/tools/sub-venue/table.d.ts.map +0 -1
- package/out/tools/sub-venue/table.js.map +0 -1
- package/out/tools/sub-venue/wikidata.d.ts +0 -26
- package/out/tools/sub-venue/wikidata.d.ts.map +0 -1
- package/out/tools/sub-venue/wikidata.js +0 -62
- package/out/tools/sub-venue/wikidata.js.map +0 -1
- package/out/tools/sub-venue-lexicon.d.ts +0 -156
- package/out/tools/sub-venue-lexicon.d.ts.map +0 -1
- package/out/tools/sub-venue-lexicon.js +0 -283
- package/out/tools/sub-venue-lexicon.js.map +0 -1
- package/out/tools/sub-venue-promotions.d.ts +0 -94
- package/out/tools/sub-venue-promotions.d.ts.map +0 -1
- package/out/tools/sub-venue-promotions.js +0 -266
- package/out/tools/sub-venue-promotions.js.map +0 -1
- /package/lib/{recipes/cn-organizational-units.ts → cn/recipes/organizational-units.ts} +0 -0
- /package/lib/{adapters → fr/adapters}/ban/street-decompose.ts +0 -0
- /package/lib/{adapters/wof-admin-jp → jp/adapters/wof-admin}/adapter.ts +0 -0
- /package/lib/tools/{golden-expand.ts → golden/expand.ts} +0 -0
- /package/lib/tools/{lint-slice.ts → lint/slice/index.ts} +0 -0
- /package/lib/tools/{slice-kryptonite.ts → slice/kryptonite.ts} +0 -0
- /package/lib/tools/{slice-translit.ts → slice/translit.ts} +0 -0
- /package/lib/tools/{sub-venue-promotions.ts → sub/venue/promotions.ts} +0 -0
- /package/lib/{adapters/state-hi-schools → us/adapters/state/hi-schools}/workbook.ts +0 -0
- /package/lib/{adapters → us/adapters}/tiger/street-decompose.ts +0 -0
- /package/lib/{codex/us-fips-state.ts → us/fips-state.ts} +0 -0
- /package/lib/{recipes → ve/recipes}/reviewed-postcode-tail.ts +0 -0
- /package/out/adapters/{geonames-postal → geonames/postal}/adapter.d.ts +0 -0
- /package/out/{adapters → au/adapters}/gnaf/adapter.d.ts +0 -0
- /package/out/{adapters → fr/adapters}/ban/adapter.d.ts +0 -0
- /package/out/{adapters → fr/adapters}/ban/street-decompose.d.ts +0 -0
- /package/out/{adapters → fr/adapters}/ban/street-decompose.js +0 -0
- /package/out/{adapters/wof-admin-jp → jp/adapters/wof-admin}/adapter.d.ts +0 -0
- /package/out/{adapters/wof-admin-jp → jp/adapters/wof-admin}/adapter.js +0 -0
- /package/out/tools/{sub-venue → sub/venue}/head-nouns.js +0 -0
- /package/out/tools/{sub-venue → sub/venue}/surfaces.js +0 -0
- /package/out/tools/{sub-venue → sub/venue}/table.js +0 -0
- /package/out/{adapters → us/adapters}/fcc-bdc/adapter.d.ts +0 -0
- /package/out/{adapters/state-hi-schools → us/adapters/state/hi-schools}/adapter.d.ts +0 -0
- /package/out/{adapters/state-hi-schools → us/adapters/state/hi-schools}/workbook.d.ts +0 -0
- /package/out/{adapters/state-hi-schools → us/adapters/state/hi-schools}/workbook.js +0 -0
- /package/out/{adapters/state-ia-contractors → us/adapters/state/ia-contractors}/adapter.d.ts +0 -0
- /package/out/{adapters/state-ny-notaries → us/adapters/state/ny-notaries}/adapter.d.ts +0 -0
- /package/out/{adapters/state-tx-notaries → us/adapters/state/tx-notaries}/adapter.d.ts +0 -0
- /package/out/{adapters → us/adapters}/tiger/street-decompose.d.ts +0 -0
- /package/out/{adapters → us/adapters}/tiger/street-decompose.js +0 -0
- /package/out/{adapters/usgov-hrsa-fqhc → us/adapters/usgov/hrsa-fqhc}/adapter.d.ts +0 -0
- /package/out/{adapters/usgov-imls-pls → us/adapters/usgov/imls-pls}/adapter.d.ts +0 -0
- /package/out/{adapters/usgov-irs-bmf → us/adapters/usgov/irs-bmf}/adapter.d.ts +0 -0
- /package/out/{adapters/usgov-nad → us/adapters/usgov/nad}/adapter.d.ts +0 -0
- /package/out/{adapters/usgov-nppes → us/adapters/usgov/nppes}/adapter.d.ts +0 -0
- /package/out/{adapters/usgov-samhsa-treatment-locator → us/adapters/usgov/samhsa-treatment-locator}/adapter.d.ts +0 -0
- /package/out/{recipes → ve/recipes}/reviewed-postcode-tail.d.ts +0 -0
- /package/out/{recipes → ve/recipes}/reviewed-postcode-tail.js +0 -0
|
@@ -1,201 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `tiger`: US Census TIGER/Line consumer adapter.
|
|
7
|
-
*
|
|
8
|
-
* TIGER/Line is the canonical US street + locality dataset published by the Census Bureau as a
|
|
9
|
-
* **public-domain** product (no ODbL share-alike concerns for US-only corpora). Coverage extends
|
|
10
|
-
* to every named street segment + every incorporated place + CDP across the 50 states + DC + the
|
|
11
|
-
* five primary territories — substantially better US street-name coverage than OSM, especially in
|
|
12
|
-
* rural areas.
|
|
13
|
-
*
|
|
14
|
-
* Following the `wof-admin` / `wof-postalcode` pattern, this adapter consumes a SQLite database the
|
|
15
|
-
* operator pre-builds from the raw TIGER shapefiles (see the README for the schema and a
|
|
16
|
-
* suggested `ogr2ogr` pipeline). The mailwoman side does not parse Shapefile binary directly —
|
|
17
|
-
* keeping the adapter narrow lets the operator pick their own ingestion tool (ogr2ogr / shp2pgsql
|
|
18
|
-
* / a custom Python script / etc.) without forcing a heavy native dep into `@mailwoman/corpus`.
|
|
19
|
-
*
|
|
20
|
-
* Two row classes are emitted:
|
|
21
|
-
*
|
|
22
|
-
* - **Street-level** (`tiger_streets`): one row per segment, optionally with up to two postcode
|
|
23
|
-
* variants if `zipl` / `zipr` differ. Components: `{ street, region, postcode? }`. Streets
|
|
24
|
-
* without a recognized state FIPS are dropped — there's no useful row without `region`.
|
|
25
|
-
* - **Locality-level** (`tiger_places`): up to three variants per place: locality-only,
|
|
26
|
-
* locality-with-region, locality-with-region-country (mirrors `wof-admin`'s fan-out for
|
|
27
|
-
* consistency).
|
|
28
|
-
* - `packages/corpus/lib/codex/us-fips-state.ts` — the FIPS → `{abbreviation, name}` lookup table
|
|
29
|
-
* (originally `tiger/state.ts`, AGPL-3.0 → AGPL-3.0). The full isp-nexus TIGER module ships a
|
|
30
|
-
* TypeORM-backed service layer; mailwoman only needs the lookup data so we don't carry the
|
|
31
|
-
* service layer over.
|
|
32
|
-
*
|
|
33
|
-
* License: stamped `"Public Domain"` per Census Bureau guidance on TIGER/Line. No per-row override
|
|
34
|
-
* needed — every row in TIGER is the same license.
|
|
35
|
-
*/
|
|
36
|
-
import { formatAddress, reconcileComponents } from "@mailwoman/formatter";
|
|
37
|
-
import { DatabaseClient } from "@mailwoman/sqlite/client";
|
|
38
|
-
import { decomposeStreet } from "#adapters/tiger/street-decompose";
|
|
39
|
-
import { lookupFipsState } from "#codex/us-fips-state";
|
|
40
|
-
/**
|
|
41
|
-
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
42
|
-
* it came from.
|
|
43
|
-
*/
|
|
44
|
-
export const TIGER_ADAPTER_ID = "tiger";
|
|
45
|
-
/**
|
|
46
|
-
* License carried by this source (Public Domain), attached to each row so downstream consumers inherit the terms rather
|
|
47
|
-
* than having to look them up.
|
|
48
|
-
*/
|
|
49
|
-
export const TIGER_DEFAULT_LICENSE = "Public Domain";
|
|
50
|
-
/**
|
|
51
|
-
* The country surface form used in `formatAddress` for US. Matches the canonical OpenCage US template output so
|
|
52
|
-
* reconciliation doesn't strip it when the row carries `country` explicitly.
|
|
53
|
-
*/
|
|
54
|
-
const US_COUNTRY_DISPLAY = "United States of America";
|
|
55
|
-
/**
|
|
56
|
-
* Yield one or more `CanonicalRow`s per street segment. Postcode variants:
|
|
57
|
-
*
|
|
58
|
-
* - No ZIP set → one row, street + region.
|
|
59
|
-
* - `zipl === zipr` → one row, street + region + postcode.
|
|
60
|
-
* - `zipl !== zipr` → two rows (one per side's ZIP).
|
|
61
|
-
*/
|
|
62
|
-
function* streetVariants(row) {
|
|
63
|
-
const fullname = row.fullname.trim();
|
|
64
|
-
if (!fullname)
|
|
65
|
-
return;
|
|
66
|
-
const state = lookupFipsState(row.statefp);
|
|
67
|
-
if (!state)
|
|
68
|
-
return;
|
|
69
|
-
const zipl = row.zipl?.trim() ?? "";
|
|
70
|
-
const zipr = row.zipr?.trim() ?? "";
|
|
71
|
-
const decomposed = decomposeStreet(fullname);
|
|
72
|
-
const baseComponents = {
|
|
73
|
-
region: state.abbreviation,
|
|
74
|
-
street: decomposed.street,
|
|
75
|
-
};
|
|
76
|
-
if (decomposed.prefix) {
|
|
77
|
-
baseComponents.street_prefix = decomposed.prefix;
|
|
78
|
-
}
|
|
79
|
-
if (decomposed.suffix) {
|
|
80
|
-
baseComponents.street_suffix = decomposed.suffix;
|
|
81
|
-
}
|
|
82
|
-
if (!zipl && !zipr) {
|
|
83
|
-
yield { components: baseComponents, variantKey: "no-zip" };
|
|
84
|
-
return;
|
|
85
|
-
}
|
|
86
|
-
if (zipl && zipr && zipl === zipr) {
|
|
87
|
-
yield {
|
|
88
|
-
components: { ...baseComponents, postcode: zipl },
|
|
89
|
-
variantKey: `zip-${zipl}`,
|
|
90
|
-
};
|
|
91
|
-
return;
|
|
92
|
-
}
|
|
93
|
-
if (zipl) {
|
|
94
|
-
yield { components: { ...baseComponents, postcode: zipl }, variantKey: `zipl-${zipl}` };
|
|
95
|
-
}
|
|
96
|
-
if (zipr && zipr !== zipl) {
|
|
97
|
-
yield { components: { ...baseComponents, postcode: zipr }, variantKey: `zipr-${zipr}` };
|
|
98
|
-
}
|
|
99
|
-
}
|
|
100
|
-
/**
|
|
101
|
-
* Three locality-level variants, mirroring `wof-admin`'s fan-out.
|
|
102
|
-
*/
|
|
103
|
-
function* placeVariants(row) {
|
|
104
|
-
const name = row.name.trim();
|
|
105
|
-
if (!name)
|
|
106
|
-
return;
|
|
107
|
-
const state = lookupFipsState(row.statefp);
|
|
108
|
-
if (!state)
|
|
109
|
-
return;
|
|
110
|
-
yield {
|
|
111
|
-
components: { locality: name },
|
|
112
|
-
variantKey: "locality-only",
|
|
113
|
-
};
|
|
114
|
-
yield {
|
|
115
|
-
components: { locality: name, region: state.abbreviation },
|
|
116
|
-
variantKey: "with-region",
|
|
117
|
-
};
|
|
118
|
-
yield {
|
|
119
|
-
components: { locality: name, region: state.abbreviation, country: US_COUNTRY_DISPLAY },
|
|
120
|
-
variantKey: "with-region-country",
|
|
121
|
-
};
|
|
122
|
-
}
|
|
123
|
-
/**
|
|
124
|
-
* Build a TIGER adapter. Pure factory so multiple instances can be created in tests.
|
|
125
|
-
*/
|
|
126
|
-
export function createTigerAdapter() {
|
|
127
|
-
return {
|
|
128
|
-
id: TIGER_ADAPTER_ID,
|
|
129
|
-
defaultLicense: TIGER_DEFAULT_LICENSE,
|
|
130
|
-
description: "US Census TIGER/Line streets + places consumer (public-domain); SQLite DB built via `mailwoman tiger fetch`.",
|
|
131
|
-
async *rows(opts) {
|
|
132
|
-
if (opts.country && opts.country !== "US") {
|
|
133
|
-
throw new Error(`tiger adapter: only US supported, got country=${opts.country}`);
|
|
134
|
-
}
|
|
135
|
-
const db = new DatabaseClient(opts.inputPath, { readOnly: true });
|
|
136
|
-
let emitted = 0;
|
|
137
|
-
try {
|
|
138
|
-
const streetStmt = db.prepare(`SELECT linearid, fullname, zipl, zipr, statefp FROM tiger_streets`);
|
|
139
|
-
const placeStmt = db.prepare(`SELECT geoid, name, statefp, lsad FROM tiger_places`);
|
|
140
|
-
for (const row of streetStmt.iterate()) {
|
|
141
|
-
if (opts.signal?.aborted)
|
|
142
|
-
return;
|
|
143
|
-
for (const variant of streetVariants(row)) {
|
|
144
|
-
if (opts.limit !== undefined && emitted >= opts.limit)
|
|
145
|
-
return;
|
|
146
|
-
const raw = formatAddress(variant.components, "US", { separator: ", " });
|
|
147
|
-
if (!raw)
|
|
148
|
-
continue;
|
|
149
|
-
const aligned = reconcileComponents(variant.components, raw);
|
|
150
|
-
if (!Object.keys(aligned).length)
|
|
151
|
-
continue;
|
|
152
|
-
yield {
|
|
153
|
-
raw,
|
|
154
|
-
components: aligned,
|
|
155
|
-
country: "US",
|
|
156
|
-
locale: "en-US",
|
|
157
|
-
source: TIGER_ADAPTER_ID,
|
|
158
|
-
source_id: `${TIGER_ADAPTER_ID}-st-${row.linearid}-${variant.variantKey}`,
|
|
159
|
-
corpus_version: "",
|
|
160
|
-
license: TIGER_DEFAULT_LICENSE,
|
|
161
|
-
};
|
|
162
|
-
emitted++;
|
|
163
|
-
}
|
|
164
|
-
}
|
|
165
|
-
for (const row of placeStmt.iterate()) {
|
|
166
|
-
if (opts.signal?.aborted)
|
|
167
|
-
return;
|
|
168
|
-
for (const variant of placeVariants(row)) {
|
|
169
|
-
if (opts.limit !== undefined && emitted >= opts.limit)
|
|
170
|
-
return;
|
|
171
|
-
const raw = formatAddress(variant.components, "US", { separator: ", " });
|
|
172
|
-
if (!raw)
|
|
173
|
-
continue;
|
|
174
|
-
const aligned = reconcileComponents(variant.components, raw);
|
|
175
|
-
if (!Object.keys(aligned).length)
|
|
176
|
-
continue;
|
|
177
|
-
yield {
|
|
178
|
-
raw,
|
|
179
|
-
components: aligned,
|
|
180
|
-
country: "US",
|
|
181
|
-
locale: "en-US",
|
|
182
|
-
source: TIGER_ADAPTER_ID,
|
|
183
|
-
source_id: `${TIGER_ADAPTER_ID}-pl-${row.geoid}-${variant.variantKey}`,
|
|
184
|
-
corpus_version: "",
|
|
185
|
-
license: TIGER_DEFAULT_LICENSE,
|
|
186
|
-
};
|
|
187
|
-
emitted++;
|
|
188
|
-
}
|
|
189
|
-
}
|
|
190
|
-
}
|
|
191
|
-
finally {
|
|
192
|
-
await db.destroy();
|
|
193
|
-
}
|
|
194
|
-
},
|
|
195
|
-
};
|
|
196
|
-
}
|
|
197
|
-
/**
|
|
198
|
-
* The configured adapter instance registered with the corpus builder.
|
|
199
|
-
*/
|
|
200
|
-
export const tigerAdapter = createTigerAdapter();
|
|
201
|
-
//# sourceMappingURL=adapter.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../lib/adapters/tiger/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAkCG;AAEH,OAAO,EAAE,aAAa,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AACzE,OAAO,EAAE,cAAc,EAAE,MAAM,0BAA0B,CAAA;AAGzD,OAAO,EAAE,eAAe,EAAE,MAAM,kCAAkC,CAAA;AAClE,OAAO,EAAE,eAAe,EAAE,MAAM,sBAAsB,CAAA;AAGtD;;;GAGG;AACH,MAAM,CAAC,MAAM,gBAAgB,GAAG,OAAO,CAAA;AACvC;;;GAGG;AACH,MAAM,CAAC,MAAM,qBAAqB,GAAG,eAAe,CAAA;AAEpD;;;GAGG;AACH,MAAM,kBAAkB,GAAG,0BAA0B,CAAA;AAiBrD;;;;;;GAMG;AACH,QAAQ,CAAC,CAAC,cAAc,CAAC,GAAmB;IAI3C,MAAM,QAAQ,GAAG,GAAG,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAA;IAEpC,IAAI,CAAC,QAAQ;QAAE,OAAM;IACrB,MAAM,KAAK,GAAG,eAAe,CAAC,GAAG,CAAC,OAAO,CAAC,CAAA;IAE1C,IAAI,CAAC,KAAK;QAAE,OAAM;IAElB,MAAM,IAAI,GAAG,GAAG,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;IACnC,MAAM,IAAI,GAAG,GAAG,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;IAEnC,MAAM,UAAU,GAAG,eAAe,CAAC,QAAQ,CAAC,CAAA;IAE5C,MAAM,cAAc,GAA+B;QAClD,MAAM,EAAE,KAAK,CAAC,YAAY;QAC1B,MAAM,EAAE,UAAU,CAAC,MAAM;KACzB,CAAA;IAED,IAAI,UAAU,CAAC,MAAM,EAAE,CAAC;QACvB,cAAc,CAAC,aAAa,GAAG,UAAU,CAAC,MAAM,CAAA;IACjD,CAAC;IAED,IAAI,UAAU,CAAC,MAAM,EAAE,CAAC;QACvB,cAAc,CAAC,aAAa,GAAG,UAAU,CAAC,MAAM,CAAA;IACjD,CAAC;IAED,IAAI,CAAC,IAAI,IAAI,CAAC,IAAI,EAAE,CAAC;QACpB,MAAM,EAAE,UAAU,EAAE,cAAc,EAAE,UAAU,EAAE,QAAQ,EAAE,CAAA;QAE1D,OAAM;IACP,CAAC;IAED,IAAI,IAAI,IAAI,IAAI,IAAI,IAAI,KAAK,IAAI,EAAE,CAAC;QACnC,MAAM;YACL,UAAU,EAAE,EAAE,GAAG,cAAc,EAAE,QAAQ,EAAE,IAAI,EAAE;YACjD,UAAU,EAAE,OAAO,IAAI,EAAE;SACzB,CAAA;QAED,OAAM;IACP,CAAC;IAED,IAAI,IAAI,EAAE,CAAC;QACV,MAAM,EAAE,UAAU,EAAE,EAAE,GAAG,cAAc,EAAE,QAAQ,EAAE,IAAI,EAAE,EAAE,UAAU,EAAE,QAAQ,IAAI,EAAE,EAAE,CAAA;IACxF,CAAC;IAED,IAAI,IAAI,IAAI,IAAI,KAAK,IAAI,EAAE,CAAC;QAC3B,MAAM,EAAE,UAAU,EAAE,EAAE,GAAG,cAAc,EAAE,QAAQ,EAAE,IAAI,EAAE,EAAE,UAAU,EAAE,QAAQ,IAAI,EAAE,EAAE,CAAA;IACxF,CAAC;AACF,CAAC;AAED;;GAEG;AACH,QAAQ,CAAC,CAAC,aAAa,CAAC,GAAkB;IAIzC,MAAM,IAAI,GAAG,GAAG,CAAC,IAAI,CAAC,IAAI,EAAE,CAAA;IAE5B,IAAI,CAAC,IAAI;QAAE,OAAM;IACjB,MAAM,KAAK,GAAG,eAAe,CAAC,GAAG,CAAC,OAAO,CAAC,CAAA;IAE1C,IAAI,CAAC,KAAK;QAAE,OAAM;IAElB,MAAM;QACL,UAAU,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE;QAC9B,UAAU,EAAE,eAAe;KAC3B,CAAA;IAED,MAAM;QACL,UAAU,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,CAAC,YAAY,EAAE;QAC1D,UAAU,EAAE,aAAa;KACzB,CAAA;IAED,MAAM;QACL,UAAU,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,CAAC,YAAY,EAAE,OAAO,EAAE,kBAAkB,EAAE;QACvF,UAAU,EAAE,qBAAqB;KACjC,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,kBAAkB;IACjC,OAAO;QACN,EAAE,EAAE,gBAAgB;QACpB,cAAc,EAAE,qBAAqB;QACrC,WAAW,EACV,8GAA8G;QAE/G,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,IAAI,IAAI,CAAC,OAAO,IAAI,IAAI,CAAC,OAAO,KAAK,IAAI,EAAE,CAAC;gBAC3C,MAAM,IAAI,KAAK,CAAC,iDAAiD,IAAI,CAAC,OAAO,EAAE,CAAC,CAAA;YACjF,CAAC;YAED,MAAM,EAAE,GAAG,IAAI,cAAc,CAAgB,IAAI,CAAC,SAAS,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAA;YAChF,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,CAAC;gBACJ,MAAM,UAAU,GAAG,EAAE,CAAC,OAAO,CAAC,mEAAmE,CAAC,CAAA;gBAClG,MAAM,SAAS,GAAG,EAAE,CAAC,OAAO,CAAC,qDAAqD,CAAC,CAAA;gBAEnF,KAAK,MAAM,GAAG,IAAI,UAAU,CAAC,OAAO,EAAsC,EAAE,CAAC;oBAC5E,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;wBAAE,OAAM;oBAEhC,KAAK,MAAM,OAAO,IAAI,cAAc,CAAC,GAAG,CAAC,EAAE,CAAC;wBAC3C,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;4BAAE,OAAM;wBAC7D,MAAM,GAAG,GAAG,aAAa,CAAC,OAAO,CAAC,UAAU,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;wBAExE,IAAI,CAAC,GAAG;4BAAE,SAAQ;wBAClB,MAAM,OAAO,GAAG,mBAAmB,CAAC,OAAO,CAAC,UAAU,EAAE,GAAG,CAAC,CAAA;wBAE5D,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM;4BAAE,SAAQ;wBAE1C,MAAM;4BACL,GAAG;4BACH,UAAU,EAAE,OAAO;4BACnB,OAAO,EAAE,IAAI;4BACb,MAAM,EAAE,OAAO;4BACf,MAAM,EAAE,gBAAgB;4BACxB,SAAS,EAAE,GAAG,gBAAgB,OAAO,GAAG,CAAC,QAAQ,IAAI,OAAO,CAAC,UAAU,EAAE;4BACzE,cAAc,EAAE,EAAE;4BAClB,OAAO,EAAE,qBAAqB;yBAC9B,CAAA;wBAED,OAAO,EAAE,CAAA;oBACV,CAAC;gBACF,CAAC;gBAED,KAAK,MAAM,GAAG,IAAI,SAAS,CAAC,OAAO,EAAqC,EAAE,CAAC;oBAC1E,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;wBAAE,OAAM;oBAEhC,KAAK,MAAM,OAAO,IAAI,aAAa,CAAC,GAAG,CAAC,EAAE,CAAC;wBAC1C,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;4BAAE,OAAM;wBAC7D,MAAM,GAAG,GAAG,aAAa,CAAC,OAAO,CAAC,UAAU,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;wBAExE,IAAI,CAAC,GAAG;4BAAE,SAAQ;wBAClB,MAAM,OAAO,GAAG,mBAAmB,CAAC,OAAO,CAAC,UAAU,EAAE,GAAG,CAAC,CAAA;wBAE5D,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM;4BAAE,SAAQ;wBAE1C,MAAM;4BACL,GAAG;4BACH,UAAU,EAAE,OAAO;4BACnB,OAAO,EAAE,IAAI;4BACb,MAAM,EAAE,OAAO;4BACf,MAAM,EAAE,gBAAgB;4BACxB,SAAS,EAAE,GAAG,gBAAgB,OAAO,GAAG,CAAC,KAAK,IAAI,OAAO,CAAC,UAAU,EAAE;4BACtE,cAAc,EAAE,EAAE;4BAClB,OAAO,EAAE,qBAAqB;yBAC9B,CAAA;wBAED,OAAO,EAAE,CAAA;oBACV,CAAC;gBACF,CAAC;YACF,CAAC;oBAAS,CAAC;gBACV,MAAM,EAAE,CAAC,OAAO,EAAE,CAAA;YACnB,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,YAAY,GAAG,kBAAkB,EAAE,CAAA"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"street-decompose.d.ts","sourceRoot":"","sources":["../../../lib/adapters/tiger/street-decompose.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AASH,MAAM,WAAW,gBAAgB;IAChC,MAAM,EAAE,MAAM,GAAG,IAAI,CAAA;IACrB,MAAM,EAAE,MAAM,CAAA;IACd,MAAM,EAAE,MAAM,GAAG,IAAI,CAAA;CACrB;AAED;;;;;GAKG;AACH,wBAAgB,eAAe,CAAC,QAAQ,EAAE,MAAM,GAAG,gBAAgB,CA6ClE"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"street-decompose.js","sourceRoot":"","sources":["../../../lib/adapters/tiger/street-decompose.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAEH,OAAO,EAAE,uBAAuB,EAAE,MAAM,iBAAiB,CAAA;AAEzD,MAAM,CAAC,YAAY,EAAE,YAAY,CAAC,GAAG,MAAM,OAAO,CAAC,GAAG,CAAC;IACtD,uBAAuB,CAAC,IAAI,EAAE,kBAAkB,CAAC;IACjD,uBAAuB,CAAC,IAAI,EAAE,kBAAkB,CAAC;CACjD,CAAC,CAAA;AAQF;;;;;GAKG;AACH,MAAM,UAAU,eAAe,CAAC,QAAgB;IAC/C,MAAM,OAAO,GAAG,QAAQ,CAAC,IAAI,EAAE,CAAA;IAE/B,IAAI,CAAC,OAAO;QAAE,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,EAAE,EAAE,EAAE,MAAM,EAAE,IAAI,EAAE,CAAA;IAE/D,MAAM,MAAM,GAAG,OAAO,CAAC,KAAK,CAAC,KAAK,CAAC,CAAA;IAEnC,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,CAAA;IAE/E,MAAM,IAAI,GAAG,CAAC,CAAS,EAAE,EAAE,CAAC,CAAC,CAAC,WAAW,EAAE,CAAC,OAAO,CAAC,KAAK,EAAE,EAAE,CAAC,CAAA;IAE9D,IAAI,MAAM,GAAkB,IAAI,CAAA;IAChC,IAAI,MAAM,GAAkB,IAAI,CAAA;IAChC,IAAI,QAAQ,GAAG,CAAC,CAAA;IAChB,IAAI,MAAM,GAAG,MAAM,CAAC,MAAM,CAAA;IAE1B,6BAA6B;IAC7B,IAAI,YAAY,CAAC,GAAG,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,CAAE,CAAC,CAAC,IAAI,MAAM,CAAC,MAAM,IAAI,CAAC,EAAE,CAAC;QAC9D,MAAM,GAAG,MAAM,CAAC,CAAC,CAAE,CAAA;QACnB,QAAQ,GAAG,CAAC,CAAA;IACb,CAAC;IAED,mFAAmF;IACnF,MAAM,IAAI,GAAG,IAAI,CAAC,MAAM,CAAC,MAAM,GAAG,CAAC,CAAE,CAAC,CAAA;IACtC,MAAM,UAAU,GAAG,MAAM,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,MAAM,GAAG,CAAC,CAAE,CAAC,CAAC,CAAC,CAAC,EAAE,CAAA;IAE/D,IAAI,YAAY,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,YAAY,CAAC,GAAG,CAAC,UAAU,CAAC,EAAE,CAAC;QAC5D,MAAM,GAAG,MAAM,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,MAAM,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;QACnD,MAAM,IAAI,CAAC,CAAA;IACZ,CAAC;SAAM,IAAI,YAAY,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,MAAM,GAAG,QAAQ,IAAI,CAAC,EAAE,CAAC;QAC7D,MAAM,GAAG,MAAM,CAAC,MAAM,GAAG,CAAC,CAAE,CAAA;QAC5B,MAAM,IAAI,CAAC,CAAA;IACZ,CAAC;SAAM,IAAI,YAAY,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,MAAM,GAAG,QAAQ,IAAI,CAAC,EAAE,CAAC;QAC7D,gCAAgC;QAChC,MAAM,GAAG,MAAM,CAAC,MAAM,GAAG,CAAC,CAAE,CAAA;QAC5B,MAAM,IAAI,CAAC,CAAA;IACZ,CAAC;IAED,MAAM,MAAM,GAAG,MAAM,CAAC,KAAK,CAAC,QAAQ,EAAE,MAAM,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;IAE9D,IAAI,CAAC,MAAM,EAAE,CAAC;QACb,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,CAAA;IACvD,CAAC;IAED,OAAO,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,CAAA;AAClC,CAAC"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../lib/adapters/usgov-hrsa-fqhc/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA6BG;AAOH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,QAAQ,CAAA;AAEzE;;;GAGG;AACH,eAAO,MAAM,0BAA0B,oBAAoB,CAAA;AAC3D;;;GAGG;AACH,eAAO,MAAM,+BAA+B,kBAAkB,CAAA;AAmB9D;;;;;;;;GAQG;AAEH,wBAAgB,0BAA0B,IAAI,aAAa,CAqF1D;AAED;;GAEG;AACH,eAAO,MAAM,oBAAoB,eAA+B,CAAA"}
|
|
@@ -1,132 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `usgov-hrsa-fqhc`: HRSA "Health Center Service Delivery Site Locations" CSV consumer.
|
|
7
|
-
*
|
|
8
|
-
* Federally Qualified Health Centers (FQHCs) are HRSA-funded community health programs that
|
|
9
|
-
* self-report site addresses to the HRSA Data Warehouse. The published CSV (`data.hrsa.gov`)
|
|
10
|
-
* carries the site name, the postal-formatted street address, and the locality/region/postcode
|
|
11
|
-
* quad. The source earns its place on adversarial-value-per-row (#22): every facility name is a
|
|
12
|
-
* human-typed venue string and the addresses pass through enough hands to accumulate the
|
|
13
|
-
* abbreviation drift + suite designator chaos that pure gazetteer data does not.
|
|
14
|
-
*
|
|
15
|
-
* The adapter consumes a CSV file the operator pre-downloads. The HRSA data is published as a
|
|
16
|
-
* single national CSV (~10K rows), small enough that the operator can re-fetch on every corpus
|
|
17
|
-
* rebuild without an intermediate SQLite step. Column names below match the HRSA Data Warehouse's
|
|
18
|
-
* "Health Center Service Delivery Site" public dataset. Operators substituting the
|
|
19
|
-
* closely-related "Site Address" or "Health Center" public extracts may need to remap columns;
|
|
20
|
-
* the README documents the expected set.
|
|
21
|
-
*
|
|
22
|
-
* Output: one row per CSV record, with `venue` component carrying the site name and the address
|
|
23
|
-
* quad on `(house_number, street, locality, region, postcode)`. Component order is critical:
|
|
24
|
-
* `venue` is inserted FIRST so alignment claims its surface span before `locality` searches for
|
|
25
|
-
* its own (the kryptonite case "Buffalo Health Clinic, …, Buffalo, NY" relies on `venue`
|
|
26
|
-
* consuming the first "Buffalo" so locality lands on the second).
|
|
27
|
-
*
|
|
28
|
-
* License: stamped `"Public Domain"` per the HRSA Data Warehouse's federal government distribution
|
|
29
|
-
* terms.
|
|
30
|
-
*/
|
|
31
|
-
import { reconcileComponents } from "@mailwoman/formatter";
|
|
32
|
-
import { CSVSpliterator } from "spliterator";
|
|
33
|
-
import { composeRaw, splitStreetLine, stableSourceID } from "#adapters/utils";
|
|
34
|
-
import { lookupStateAbbreviation } from "#codex/us-fips-state";
|
|
35
|
-
/**
|
|
36
|
-
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
37
|
-
* it came from.
|
|
38
|
-
*/
|
|
39
|
-
export const USGOV_HRSA_FQHC_ADAPTER_ID = "usgov-hrsa-fqhc";
|
|
40
|
-
/**
|
|
41
|
-
* License carried by this source (Public Domain), attached to each row so downstream consumers inherit the terms rather
|
|
42
|
-
* than having to look them up.
|
|
43
|
-
*/
|
|
44
|
-
export const USGOV_HRSA_FQHC_DEFAULT_LICENSE = "Public Domain";
|
|
45
|
-
/**
|
|
46
|
-
* Split a "123 Main St Suite 4" surface form into `(house_number, street)`. The regex tolerates one trailing letter on
|
|
47
|
-
* the number (`"123A Main St"`) and a hyphenated form (`"40-12 Bell Blvd"`); anything else falls back to street-only.
|
|
48
|
-
*
|
|
49
|
-
* Suite / Apt / Unit designators stay on `street` — Mailwoman's `unit` component exists but the address-formatter does
|
|
50
|
-
* not have a clean slot for it, and HRSA addresses do not separate the suite into its own column. Leaving the surface
|
|
51
|
-
* form intact in `street` preserves the adversarial training signal (the model learns that a trailing "Suite 4" is part
|
|
52
|
-
* of the road line in this distribution).
|
|
53
|
-
*/
|
|
54
|
-
export function createUSGovHRSAFQHCAdapter() {
|
|
55
|
-
return {
|
|
56
|
-
id: USGOV_HRSA_FQHC_ADAPTER_ID,
|
|
57
|
-
defaultLicense: USGOV_HRSA_FQHC_DEFAULT_LICENSE,
|
|
58
|
-
description: "HRSA Federally Qualified Health Center site locations (public-domain). Adversarial source: venue + address co-occurrence, hand-entered.",
|
|
59
|
-
async *rows(opts) {
|
|
60
|
-
if (opts.country && opts.country !== "US") {
|
|
61
|
-
throw new Error(`usgov-hrsa-fqhc adapter: only US supported, got country=${opts.country}`);
|
|
62
|
-
}
|
|
63
|
-
const rows = CSVSpliterator.fromAsync(opts.inputPath, {
|
|
64
|
-
mode: "object",
|
|
65
|
-
normalizeKeys: false,
|
|
66
|
-
enableQuoteHandling: true,
|
|
67
|
-
});
|
|
68
|
-
let emitted = 0;
|
|
69
|
-
for await (const record of rows) {
|
|
70
|
-
if (opts.signal?.aborted)
|
|
71
|
-
break;
|
|
72
|
-
if (opts.limit !== undefined && emitted >= opts.limit)
|
|
73
|
-
break;
|
|
74
|
-
const venue = (record["Site Name"] ?? "").trim();
|
|
75
|
-
const split = splitStreetLine(record["Site Address"] ?? "");
|
|
76
|
-
const city = (record["Site City"] ?? "").trim();
|
|
77
|
-
const stateAbbr = (record["Site State Abbreviation"] ?? "").trim();
|
|
78
|
-
const postcode = (record["Site Postal Code"] ?? "").trim();
|
|
79
|
-
if (!venue || !split || !city || !postcode)
|
|
80
|
-
continue;
|
|
81
|
-
const state = lookupStateAbbreviation(stateAbbr);
|
|
82
|
-
if (!state)
|
|
83
|
-
continue;
|
|
84
|
-
// Insertion order matters here. `venue` first so alignment claims its span
|
|
85
|
-
// (which may contain a token like "Buffalo") before `locality` runs its
|
|
86
|
-
// search — the kryptonite case `Buffalo Health Clinic, Buffalo NY`
|
|
87
|
-
// otherwise mis-labels the venue's "Buffalo" as locality.
|
|
88
|
-
const components = {
|
|
89
|
-
venue,
|
|
90
|
-
...(split.house_number ? { house_number: split.house_number } : {}),
|
|
91
|
-
street: split.street,
|
|
92
|
-
locality: city,
|
|
93
|
-
region: state.abbreviation,
|
|
94
|
-
postcode,
|
|
95
|
-
};
|
|
96
|
-
const raw = composeRaw({
|
|
97
|
-
venue,
|
|
98
|
-
houseNumber: split.house_number,
|
|
99
|
-
street: split.street,
|
|
100
|
-
locality: city,
|
|
101
|
-
region: state.abbreviation,
|
|
102
|
-
postcode,
|
|
103
|
-
});
|
|
104
|
-
if (!raw)
|
|
105
|
-
continue;
|
|
106
|
-
const aligned = reconcileComponents(components, raw);
|
|
107
|
-
if (!Object.keys(aligned).length)
|
|
108
|
-
continue;
|
|
109
|
-
const siteID = (record["Site ID"] ?? "").trim();
|
|
110
|
-
const sourceID = siteID
|
|
111
|
-
? `${USGOV_HRSA_FQHC_ADAPTER_ID}-${siteID}`
|
|
112
|
-
: stableSourceID(USGOV_HRSA_FQHC_ADAPTER_ID, aligned);
|
|
113
|
-
yield {
|
|
114
|
-
raw,
|
|
115
|
-
components: aligned,
|
|
116
|
-
country: "US",
|
|
117
|
-
locale: "en-US",
|
|
118
|
-
source: USGOV_HRSA_FQHC_ADAPTER_ID,
|
|
119
|
-
source_id: sourceID,
|
|
120
|
-
corpus_version: "",
|
|
121
|
-
license: USGOV_HRSA_FQHC_DEFAULT_LICENSE,
|
|
122
|
-
};
|
|
123
|
-
emitted++;
|
|
124
|
-
}
|
|
125
|
-
},
|
|
126
|
-
};
|
|
127
|
-
}
|
|
128
|
-
/**
|
|
129
|
-
* The configured adapter instance registered with the corpus builder.
|
|
130
|
-
*/
|
|
131
|
-
export const usgovHrsaFqhcAdapter = createUSGovHRSAFQHCAdapter();
|
|
132
|
-
//# sourceMappingURL=adapter.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../lib/adapters/usgov-hrsa-fqhc/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA6BG;AAEH,OAAO,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AAC1D,OAAO,EAAE,cAAc,EAAE,MAAM,aAAa,CAAA;AAE5C,OAAO,EAAE,UAAU,EAAE,eAAe,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAA;AAC7E,OAAO,EAAE,uBAAuB,EAAE,MAAM,sBAAsB,CAAA;AAG9D;;;GAGG;AACH,MAAM,CAAC,MAAM,0BAA0B,GAAG,iBAAiB,CAAA;AAC3D;;;GAGG;AACH,MAAM,CAAC,MAAM,+BAA+B,GAAG,eAAe,CAAA;AAmB9D;;;;;;;;GAQG;AAEH,MAAM,UAAU,0BAA0B;IACzC,OAAO;QACN,EAAE,EAAE,0BAA0B;QAC9B,cAAc,EAAE,+BAA+B;QAC/C,WAAW,EACV,yIAAyI;QAE1I,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,IAAI,IAAI,CAAC,OAAO,IAAI,IAAI,CAAC,OAAO,KAAK,IAAI,EAAE,CAAC;gBAC3C,MAAM,IAAI,KAAK,CAAC,2DAA2D,IAAI,CAAC,OAAO,EAAE,CAAC,CAAA;YAC3F,CAAC;YAED,MAAM,IAAI,GAAG,cAAc,CAAC,SAAS,CAAC,IAAI,CAAC,SAAS,EAAE;gBACrD,IAAI,EAAE,QAAQ;gBACd,aAAa,EAAE,KAAK;gBACpB,mBAAmB,EAAE,IAAI;aACzB,CAAC,CAAA;YAEF,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,KAAK,EAAE,MAAM,MAAM,IAAI,IAAkC,EAAE,CAAC;gBAC/D,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;oBAAE,MAAK;gBAE/B,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;oBAAE,MAAK;gBAE5D,MAAM,KAAK,GAAG,CAAC,MAAM,CAAC,WAAW,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAChD,MAAM,KAAK,GAAG,eAAe,CAAC,MAAM,CAAC,cAAc,CAAC,IAAI,EAAE,CAAC,CAAA;gBAC3D,MAAM,IAAI,GAAG,CAAC,MAAM,CAAC,WAAW,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAC/C,MAAM,SAAS,GAAG,CAAC,MAAM,CAAC,yBAAyB,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAClE,MAAM,QAAQ,GAAG,CAAC,MAAM,CAAC,kBAAkB,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAE1D,IAAI,CAAC,KAAK,IAAI,CAAC,KAAK,IAAI,CAAC,IAAI,IAAI,CAAC,QAAQ;oBAAE,SAAQ;gBACpD,MAAM,KAAK,GAAG,uBAAuB,CAAC,SAAS,CAAC,CAAA;gBAEhD,IAAI,CAAC,KAAK;oBAAE,SAAQ;gBAEpB,2EAA2E;gBAC3E,wEAAwE;gBACxE,mEAAmE;gBACnE,0DAA0D;gBAC1D,MAAM,UAAU,GAA+B;oBAC9C,KAAK;oBACL,GAAG,CAAC,KAAK,CAAC,YAAY,CAAC,CAAC,CAAC,EAAE,YAAY,EAAE,KAAK,CAAC,YAAY,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;oBACnE,MAAM,EAAE,KAAK,CAAC,MAAM;oBACpB,QAAQ,EAAE,IAAI;oBACd,MAAM,EAAE,KAAK,CAAC,YAAY;oBAC1B,QAAQ;iBACR,CAAA;gBAED,MAAM,GAAG,GAAG,UAAU,CAAC;oBACtB,KAAK;oBACL,WAAW,EAAE,KAAK,CAAC,YAAY;oBAC/B,MAAM,EAAE,KAAK,CAAC,MAAM;oBACpB,QAAQ,EAAE,IAAI;oBACd,MAAM,EAAE,KAAK,CAAC,YAAY;oBAC1B,QAAQ;iBACR,CAAC,CAAA;gBAEF,IAAI,CAAC,GAAG;oBAAE,SAAQ;gBAElB,MAAM,OAAO,GAAG,mBAAmB,CAAC,UAAU,EAAE,GAAG,CAAC,CAAA;gBAEpD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM;oBAAE,SAAQ;gBAE1C,MAAM,MAAM,GAAG,CAAC,MAAM,CAAC,SAAS,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAE/C,MAAM,QAAQ,GAAG,MAAM;oBACtB,CAAC,CAAC,GAAG,0BAA0B,IAAI,MAAM,EAAE;oBAC3C,CAAC,CAAC,cAAc,CAAC,0BAA0B,EAAE,OAAO,CAAC,CAAA;gBAEtD,MAAM;oBACL,GAAG;oBACH,UAAU,EAAE,OAAO;oBACnB,OAAO,EAAE,IAAI;oBACb,MAAM,EAAE,OAAO;oBACf,MAAM,EAAE,0BAA0B;oBAClC,SAAS,EAAE,QAAQ;oBACnB,cAAc,EAAE,EAAE;oBAClB,OAAO,EAAE,+BAA+B;iBACxC,CAAA;gBAED,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,oBAAoB,GAAG,0BAA0B,EAAE,CAAA"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../lib/adapters/usgov-imls-pls/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;GAkBG;AAQH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,QAAQ,CAAA;AAEzE;;;GAGG;AACH,eAAO,MAAM,yBAAyB,mBAAmB,CAAA;AACzD;;;GAGG;AACH,eAAO,MAAM,8BAA8B,kBAAkB,CAAA;AAY7D,wBAAgB,yBAAyB,IAAI,aAAa,CAwFzD;AAED;;GAEG;AACH,eAAO,MAAM,mBAAmB,eAA8B,CAAA"}
|
|
@@ -1,114 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `usgov-imls-pls`: IMLS Public Libraries Survey outlet CSV consumer.
|
|
7
|
-
*
|
|
8
|
-
* The Institute of Museum and Library Services publishes an annual Public Libraries Survey with one
|
|
9
|
-
* row per library outlet (~17K rows). Each row carries the library name, street address, city,
|
|
10
|
-
* ZIP, county, and geocoordinates.
|
|
11
|
-
*
|
|
12
|
-
* The adapter consumes the outlet CSV the operator pre-downloads via `fetch-imls-pls.ts`. Column
|
|
13
|
-
* names match the IMLS PLS outlet file header.
|
|
14
|
-
*
|
|
15
|
-
* Output: one row per outlet with `venue` (library name), `(house_number, street, locality,
|
|
16
|
-
* subregion, postcode)`, and lat/lon preserved in `source_id` stability.
|
|
17
|
-
*
|
|
18
|
-
* License: stamped `"Public Domain"` per IMLS federal government distribution terms.
|
|
19
|
-
*/
|
|
20
|
-
import { isPresent } from "@mailwoman/core/objects";
|
|
21
|
-
import { reconcileComponents } from "@mailwoman/formatter";
|
|
22
|
-
import { CSVSpliterator } from "spliterator";
|
|
23
|
-
import { splitStreetLine, stableSourceID } from "#adapters/utils";
|
|
24
|
-
import { lookupStateAbbreviation } from "#codex/us-fips-state";
|
|
25
|
-
/**
|
|
26
|
-
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
27
|
-
* it came from.
|
|
28
|
-
*/
|
|
29
|
-
export const USGOV_IMLS_PLS_ADAPTER_ID = "usgov-imls-pls";
|
|
30
|
-
/**
|
|
31
|
-
* License carried by this source (Public Domain), attached to each row so downstream consumers inherit the terms rather
|
|
32
|
-
* than having to look them up.
|
|
33
|
-
*/
|
|
34
|
-
export const USGOV_IMLS_PLS_DEFAULT_LICENSE = "Public Domain";
|
|
35
|
-
export function createUSGovIMLSPLSAdapter() {
|
|
36
|
-
return {
|
|
37
|
-
id: USGOV_IMLS_PLS_ADAPTER_ID,
|
|
38
|
-
defaultLicense: USGOV_IMLS_PLS_DEFAULT_LICENSE,
|
|
39
|
-
description: "IMLS Public Libraries Survey — ~17K library outlets with venue+address (public-domain).",
|
|
40
|
-
async *rows(opts) {
|
|
41
|
-
if (opts.country && opts.country !== "US") {
|
|
42
|
-
throw new Error(`usgov-imls-pls adapter: only US supported, got country=${opts.country}`);
|
|
43
|
-
}
|
|
44
|
-
const rows = CSVSpliterator.fromAsync(opts.inputPath, {
|
|
45
|
-
mode: "object",
|
|
46
|
-
normalizeKeys: false,
|
|
47
|
-
enableQuoteHandling: true,
|
|
48
|
-
});
|
|
49
|
-
let emitted = 0;
|
|
50
|
-
for await (const record of rows) {
|
|
51
|
-
if (opts.signal?.aborted)
|
|
52
|
-
break;
|
|
53
|
-
if (opts.limit !== undefined && emitted >= opts.limit)
|
|
54
|
-
break;
|
|
55
|
-
const libName = (record.LIBNAME ?? "").trim();
|
|
56
|
-
const address = (record.ADDRESS ?? "").trim();
|
|
57
|
-
const city = (record.CITY ?? "").trim();
|
|
58
|
-
const zip = (record.ZIP ?? "").trim();
|
|
59
|
-
const stateAbbr = (record.STABR ?? "").trim();
|
|
60
|
-
if (!libName || !city || !zip)
|
|
61
|
-
continue;
|
|
62
|
-
const state = lookupStateAbbreviation(stateAbbr);
|
|
63
|
-
if (!state)
|
|
64
|
-
continue;
|
|
65
|
-
const split = splitStreetLine(address);
|
|
66
|
-
if (!split)
|
|
67
|
-
continue;
|
|
68
|
-
const components = {
|
|
69
|
-
venue: libName,
|
|
70
|
-
...(split.house_number ? { house_number: split.house_number } : {}),
|
|
71
|
-
street: split.street,
|
|
72
|
-
locality: city,
|
|
73
|
-
region: state.abbreviation,
|
|
74
|
-
postcode: zip,
|
|
75
|
-
// #552: no subregion — US postal addresses don't surface the county, so emitting
|
|
76
|
-
// subregion creates a phantom component with no raw-span to align to, quarantining
|
|
77
|
-
// ~21% of rows. The county is still available in the source CSV; it just isn't
|
|
78
|
-
// a postal-surface component here.
|
|
79
|
-
};
|
|
80
|
-
const streetPart = [split.house_number, split.street].filter(isPresent).join(" ").trim();
|
|
81
|
-
const raw = [
|
|
82
|
-
libName,
|
|
83
|
-
streetPart,
|
|
84
|
-
[city, [stateAbbr, zip].filter(isPresent).join(" ")].filter(isPresent).join(", "),
|
|
85
|
-
]
|
|
86
|
-
.filter(isPresent)
|
|
87
|
-
.join(", ");
|
|
88
|
-
const aligned = reconcileComponents(components, raw);
|
|
89
|
-
if (Object.keys(aligned).length <= 2)
|
|
90
|
-
continue;
|
|
91
|
-
const fscsKey = (record.FSCSKEY ?? "").trim();
|
|
92
|
-
const sourceID = fscsKey
|
|
93
|
-
? `${USGOV_IMLS_PLS_ADAPTER_ID}-${fscsKey}`
|
|
94
|
-
: stableSourceID(USGOV_IMLS_PLS_ADAPTER_ID, aligned);
|
|
95
|
-
yield {
|
|
96
|
-
raw,
|
|
97
|
-
components: aligned,
|
|
98
|
-
country: "US",
|
|
99
|
-
locale: "en-US",
|
|
100
|
-
source: USGOV_IMLS_PLS_ADAPTER_ID,
|
|
101
|
-
source_id: sourceID,
|
|
102
|
-
corpus_version: "",
|
|
103
|
-
license: USGOV_IMLS_PLS_DEFAULT_LICENSE,
|
|
104
|
-
};
|
|
105
|
-
emitted++;
|
|
106
|
-
}
|
|
107
|
-
},
|
|
108
|
-
};
|
|
109
|
-
}
|
|
110
|
-
/**
|
|
111
|
-
* The configured adapter instance registered with the corpus builder.
|
|
112
|
-
*/
|
|
113
|
-
export const usgovImlsPlsAdapter = createUSGovIMLSPLSAdapter();
|
|
114
|
-
//# sourceMappingURL=adapter.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../lib/adapters/usgov-imls-pls/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;GAkBG;AAEH,OAAO,EAAE,SAAS,EAAE,MAAM,yBAAyB,CAAA;AACnD,OAAO,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AAC1D,OAAO,EAAE,cAAc,EAAE,MAAM,aAAa,CAAA;AAE5C,OAAO,EAAE,eAAe,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAA;AACjE,OAAO,EAAE,uBAAuB,EAAE,MAAM,sBAAsB,CAAA;AAG9D;;;GAGG;AACH,MAAM,CAAC,MAAM,yBAAyB,GAAG,gBAAgB,CAAA;AACzD;;;GAGG;AACH,MAAM,CAAC,MAAM,8BAA8B,GAAG,eAAe,CAAA;AAY7D,MAAM,UAAU,yBAAyB;IACxC,OAAO;QACN,EAAE,EAAE,yBAAyB;QAC7B,cAAc,EAAE,8BAA8B;QAC9C,WAAW,EAAE,yFAAyF;QAEtG,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,IAAI,IAAI,CAAC,OAAO,IAAI,IAAI,CAAC,OAAO,KAAK,IAAI,EAAE,CAAC;gBAC3C,MAAM,IAAI,KAAK,CAAC,0DAA0D,IAAI,CAAC,OAAO,EAAE,CAAC,CAAA;YAC1F,CAAC;YAED,MAAM,IAAI,GAAG,cAAc,CAAC,SAAS,CAAC,IAAI,CAAC,SAAS,EAAE;gBACrD,IAAI,EAAE,QAAQ;gBACd,aAAa,EAAE,KAAK;gBACpB,mBAAmB,EAAE,IAAI;aACzB,CAAC,CAAA;YAEF,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,KAAK,EAAE,MAAM,MAAM,IAAI,IAAoC,EAAE,CAAC;gBACjE,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;oBAAE,MAAK;gBAE/B,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;oBAAE,MAAK;gBAE5D,MAAM,OAAO,GAAG,CAAC,MAAM,CAAC,OAAO,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAC7C,MAAM,OAAO,GAAG,CAAC,MAAM,CAAC,OAAO,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAC7C,MAAM,IAAI,GAAG,CAAC,MAAM,CAAC,IAAI,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBACvC,MAAM,GAAG,GAAG,CAAC,MAAM,CAAC,GAAG,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBACrC,MAAM,SAAS,GAAG,CAAC,MAAM,CAAC,KAAK,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAE7C,IAAI,CAAC,OAAO,IAAI,CAAC,IAAI,IAAI,CAAC,GAAG;oBAAE,SAAQ;gBAEvC,MAAM,KAAK,GAAG,uBAAuB,CAAC,SAAS,CAAC,CAAA;gBAEhD,IAAI,CAAC,KAAK;oBAAE,SAAQ;gBAEpB,MAAM,KAAK,GAAG,eAAe,CAAC,OAAO,CAAC,CAAA;gBAEtC,IAAI,CAAC,KAAK;oBAAE,SAAQ;gBAEpB,MAAM,UAAU,GAA+B;oBAC9C,KAAK,EAAE,OAAO;oBACd,GAAG,CAAC,KAAK,CAAC,YAAY,CAAC,CAAC,CAAC,EAAE,YAAY,EAAE,KAAK,CAAC,YAAY,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;oBACnE,MAAM,EAAE,KAAK,CAAC,MAAM;oBACpB,QAAQ,EAAE,IAAI;oBACd,MAAM,EAAE,KAAK,CAAC,YAAY;oBAC1B,QAAQ,EAAE,GAAG;oBACb,iFAAiF;oBACjF,mFAAmF;oBACnF,+EAA+E;oBAC/E,mCAAmC;iBACnC,CAAA;gBAED,MAAM,UAAU,GAAG,CAAC,KAAK,CAAC,YAAY,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;gBAExF,MAAM,GAAG,GAAG;oBACX,OAAO;oBACP,UAAU;oBACV,CAAC,IAAI,EAAE,CAAC,SAAS,EAAE,GAAG,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC;iBACjF;qBACC,MAAM,CAAC,SAAS,CAAC;qBACjB,IAAI,CAAC,IAAI,CAAC,CAAA;gBAEZ,MAAM,OAAO,GAAG,mBAAmB,CAAC,UAAU,EAAE,GAAG,CAAC,CAAA;gBAEpD,IAAI,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM,IAAI,CAAC;oBAAE,SAAQ;gBAE9C,MAAM,OAAO,GAAG,CAAC,MAAM,CAAC,OAAO,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAE7C,MAAM,QAAQ,GAAG,OAAO;oBACvB,CAAC,CAAC,GAAG,yBAAyB,IAAI,OAAO,EAAE;oBAC3C,CAAC,CAAC,cAAc,CAAC,yBAAyB,EAAE,OAAO,CAAC,CAAA;gBAErD,MAAM;oBACL,GAAG;oBACH,UAAU,EAAE,OAAO;oBACnB,OAAO,EAAE,IAAI;oBACb,MAAM,EAAE,OAAO;oBACf,MAAM,EAAE,yBAAyB;oBACjC,SAAS,EAAE,QAAQ;oBACnB,cAAc,EAAE,EAAE;oBAClB,OAAO,EAAE,8BAA8B;iBACvC,CAAA;gBAED,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,mBAAmB,GAAG,yBAAyB,EAAE,CAAA"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../lib/adapters/usgov-irs-bmf/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;GAmBG;AAOH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,QAAQ,CAAA;AAEzE;;;GAGG;AACH,eAAO,MAAM,wBAAwB,kBAAkB,CAAA;AACvD;;;GAGG;AACH,eAAO,MAAM,6BAA6B,kBAAkB,CAAA;AA+B5D,wBAAgB,wBAAwB,IAAI,aAAa,CA6ExD;AAED;;GAEG;AACH,eAAO,MAAM,kBAAkB,eAA6B,CAAA"}
|
|
@@ -1,120 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `usgov-irs-bmf`: IRS Exempt Organizations Business Master File (EO BMF) CSV consumer.
|
|
7
|
-
*
|
|
8
|
-
* The EO BMF is the IRS's authoritative registry of US tax-exempt organizations (charities,
|
|
9
|
-
* churches, foundations, ...), published as per-region CSVs at
|
|
10
|
-
* `https://www.irs.gov/charities-non-profits/exempt-organizations-business-master-file-extract-eo-bmf`
|
|
11
|
-
* (`eo1.csv`..`eo4.csv`, `eo_pr.csv`, `eo_xx.csv`). Each row carries an organization NAME plus
|
|
12
|
-
* its mailing address. It complements `usgov-nppes` with a DIFFERENT venue population
|
|
13
|
-
* (non-profits vs healthcare providers) and, notably, a high share of PO-box addresses — useful
|
|
14
|
-
* `po_box`-tag signal (a tag with historically low recall).
|
|
15
|
-
*
|
|
16
|
-
* Output: one row per record with a usable city + postcode. NAME → `venue`; the street line becomes
|
|
17
|
-
* `po_box` when it's a PO-box, else `house_number` + `street`; CITY/STATE/ZIP fill the locality
|
|
18
|
-
* line. STATE is already a USPS abbreviation in the source. License: `"Public Domain"` (US
|
|
19
|
-
* federal).
|
|
20
|
-
*/
|
|
21
|
-
import { isPresent } from "@mailwoman/core/objects";
|
|
22
|
-
import { reconcileComponents } from "@mailwoman/formatter";
|
|
23
|
-
import { CSVSpliterator } from "spliterator";
|
|
24
|
-
import { composeRaw, splitStreetLine, stableSourceID } from "#adapters/utils";
|
|
25
|
-
/**
|
|
26
|
-
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
27
|
-
* it came from.
|
|
28
|
-
*/
|
|
29
|
-
export const USGOV_IRS_BMF_ADAPTER_ID = "usgov-irs-bmf";
|
|
30
|
-
/**
|
|
31
|
-
* License carried by this source (Public Domain), attached to each row so downstream consumers inherit the terms rather
|
|
32
|
-
* than having to look them up.
|
|
33
|
-
*/
|
|
34
|
-
export const USGOV_IRS_BMF_DEFAULT_LICENSE = "Public Domain";
|
|
35
|
-
/**
|
|
36
|
-
* PO box in its many written forms: "PO BOX 12", "P.O. BOX 12", "P O BOX 12", "POB 12", "BOX 12".
|
|
37
|
-
*/
|
|
38
|
-
const PO_BOX = /^\s*(?:P\.?\s?O\.?\s*BOX|POB|BOX)\s+\w/i;
|
|
39
|
-
/**
|
|
40
|
-
* Classify the street line into a `po_box` or a `{house_number?, street}` split.
|
|
41
|
-
*
|
|
42
|
-
* BMF mixes street addresses and PO boxes in one `STREET` column, so the PO-box shapes have to be claimed BEFORE the
|
|
43
|
-
* shared house-number split runs — otherwise `splitStreetLine` would hand back `"PO Box 1234"` as a plain street, which
|
|
44
|
-
* is correct for every other US adapter and wrong here.
|
|
45
|
-
*/
|
|
46
|
-
function splitStreetLineOrPOBox(street) {
|
|
47
|
-
const trimmed = street.trim();
|
|
48
|
-
if (PO_BOX.test(trimmed))
|
|
49
|
-
return { po_box: trimmed };
|
|
50
|
-
return splitStreetLine(trimmed);
|
|
51
|
-
}
|
|
52
|
-
export function createUSGovIRSBMFAdapter() {
|
|
53
|
-
return {
|
|
54
|
-
id: USGOV_IRS_BMF_ADAPTER_ID,
|
|
55
|
-
defaultLicense: USGOV_IRS_BMF_DEFAULT_LICENSE,
|
|
56
|
-
description: "IRS Exempt Organizations Business Master File — US non-profit venue+address (public-domain), with strong PO-box coverage.",
|
|
57
|
-
async *rows(opts) {
|
|
58
|
-
if (opts.country && opts.country !== "US") {
|
|
59
|
-
throw new Error(`usgov-irs-bmf adapter: only US supported, got country=${opts.country}`);
|
|
60
|
-
}
|
|
61
|
-
const rows = CSVSpliterator.fromAsync(opts.inputPath, {
|
|
62
|
-
mode: "object",
|
|
63
|
-
normalizeKeys: false,
|
|
64
|
-
enableQuoteHandling: true,
|
|
65
|
-
});
|
|
66
|
-
let emitted = 0;
|
|
67
|
-
for await (const record of rows) {
|
|
68
|
-
if (opts.signal?.aborted)
|
|
69
|
-
break;
|
|
70
|
-
if (opts.limit !== undefined && emitted >= opts.limit)
|
|
71
|
-
break;
|
|
72
|
-
const ein = (record.EIN ?? "").trim();
|
|
73
|
-
const venue = (record.NAME ?? "").trim() || undefined;
|
|
74
|
-
const street = (record.STREET ?? "").trim();
|
|
75
|
-
const city = (record.CITY ?? "").trim();
|
|
76
|
-
const state = (record.STATE ?? "").trim();
|
|
77
|
-
const zipRaw = (record.ZIP ?? "").trim();
|
|
78
|
-
if (!city || !zipRaw)
|
|
79
|
-
continue;
|
|
80
|
-
const postcode = zipRaw.split("-")[0].trim(); // 5-digit; drop the optional +4
|
|
81
|
-
const split = splitStreetLineOrPOBox(street);
|
|
82
|
-
if (!split)
|
|
83
|
-
continue;
|
|
84
|
-
const streetPart = "po_box" in split ? split.po_box : [split.house_number, split.street].filter(isPresent).join(" ");
|
|
85
|
-
const components = {
|
|
86
|
-
...(venue ? { venue } : {}),
|
|
87
|
-
...("po_box" in split
|
|
88
|
-
? { po_box: split.po_box }
|
|
89
|
-
: { ...(split.house_number ? { house_number: split.house_number } : {}), street: split.street }),
|
|
90
|
-
locality: city,
|
|
91
|
-
...(state ? { region: state } : {}),
|
|
92
|
-
postcode,
|
|
93
|
-
};
|
|
94
|
-
const raw = composeRaw({ venue, streetLine: streetPart, locality: city, region: state, postcode });
|
|
95
|
-
if (!raw)
|
|
96
|
-
continue;
|
|
97
|
-
const aligned = reconcileComponents(components, raw);
|
|
98
|
-
if (Object.keys(aligned).length <= 2)
|
|
99
|
-
continue;
|
|
100
|
-
const sourceID = ein ? `${USGOV_IRS_BMF_ADAPTER_ID}-${ein}` : stableSourceID(USGOV_IRS_BMF_ADAPTER_ID, aligned);
|
|
101
|
-
yield {
|
|
102
|
-
raw,
|
|
103
|
-
components: aligned,
|
|
104
|
-
country: "US",
|
|
105
|
-
locale: "en-US",
|
|
106
|
-
source: USGOV_IRS_BMF_ADAPTER_ID,
|
|
107
|
-
source_id: sourceID,
|
|
108
|
-
corpus_version: "",
|
|
109
|
-
license: USGOV_IRS_BMF_DEFAULT_LICENSE,
|
|
110
|
-
};
|
|
111
|
-
emitted++;
|
|
112
|
-
}
|
|
113
|
-
},
|
|
114
|
-
};
|
|
115
|
-
}
|
|
116
|
-
/**
|
|
117
|
-
* The configured adapter instance registered with the corpus builder.
|
|
118
|
-
*/
|
|
119
|
-
export const USGovIRSBMFAdapter = createUSGovIRSBMFAdapter();
|
|
120
|
-
//# sourceMappingURL=adapter.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../lib/adapters/usgov-irs-bmf/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;GAmBG;AAEH,OAAO,EAAE,SAAS,EAAE,MAAM,yBAAyB,CAAA;AACnD,OAAO,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AAC1D,OAAO,EAAE,cAAc,EAAE,MAAM,aAAa,CAAA;AAE5C,OAAO,EAAE,UAAU,EAAE,eAAe,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAA;AAG7E;;;GAGG;AACH,MAAM,CAAC,MAAM,wBAAwB,GAAG,eAAe,CAAA;AACvD;;;GAGG;AACH,MAAM,CAAC,MAAM,6BAA6B,GAAG,eAAe,CAAA;AAE5D;;GAEG;AACH,MAAM,MAAM,GAAG,yCAAyC,CAAA;AAWxD;;;;;;GAMG;AACH,SAAS,sBAAsB,CAAC,MAAc;IAC7C,MAAM,OAAO,GAAG,MAAM,CAAC,IAAI,EAAE,CAAA;IAE7B,IAAI,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC;QAAE,OAAO,EAAE,MAAM,EAAE,OAAO,EAAE,CAAA;IAEpD,OAAO,eAAe,CAAC,OAAO,CAAC,CAAA;AAChC,CAAC;AAED,MAAM,UAAU,wBAAwB;IACvC,OAAO;QACN,EAAE,EAAE,wBAAwB;QAC5B,cAAc,EAAE,6BAA6B;QAC7C,WAAW,EACV,2HAA2H;QAE5H,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,IAAI,IAAI,CAAC,OAAO,IAAI,IAAI,CAAC,OAAO,KAAK,IAAI,EAAE,CAAC;gBAC3C,MAAM,IAAI,KAAK,CAAC,yDAAyD,IAAI,CAAC,OAAO,EAAE,CAAC,CAAA;YACzF,CAAC;YAED,MAAM,IAAI,GAAG,cAAc,CAAC,SAAS,CAAC,IAAI,CAAC,SAAS,EAAE;gBACrD,IAAI,EAAE,QAAQ;gBACd,aAAa,EAAE,KAAK;gBACpB,mBAAmB,EAAE,IAAI;aACzB,CAAC,CAAA;YAEF,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,KAAK,EAAE,MAAM,MAAM,IAAI,IAAgC,EAAE,CAAC;gBAC7D,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;oBAAE,MAAK;gBAE/B,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;oBAAE,MAAK;gBAE5D,MAAM,GAAG,GAAG,CAAC,MAAM,CAAC,GAAG,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBACrC,MAAM,KAAK,GAAG,CAAC,MAAM,CAAC,IAAI,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,IAAI,SAAS,CAAA;gBACrD,MAAM,MAAM,GAAG,CAAC,MAAM,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAC3C,MAAM,IAAI,GAAG,CAAC,MAAM,CAAC,IAAI,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBACvC,MAAM,KAAK,GAAG,CAAC,MAAM,CAAC,KAAK,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBACzC,MAAM,MAAM,GAAG,CAAC,MAAM,CAAC,GAAG,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAExC,IAAI,CAAC,IAAI,IAAI,CAAC,MAAM;oBAAE,SAAQ;gBAC9B,MAAM,QAAQ,GAAG,MAAM,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,CAAE,CAAC,IAAI,EAAE,CAAA,CAAC,gCAAgC;gBAE9E,MAAM,KAAK,GAAG,sBAAsB,CAAC,MAAM,CAAC,CAAA;gBAE5C,IAAI,CAAC,KAAK;oBAAE,SAAQ;gBAEpB,MAAM,UAAU,GACf,QAAQ,IAAI,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,YAAY,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;gBAElG,MAAM,UAAU,GAA+B;oBAC9C,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;oBAC3B,GAAG,CAAC,QAAQ,IAAI,KAAK;wBACpB,CAAC,CAAC,EAAE,MAAM,EAAE,KAAK,CAAC,MAAM,EAAE;wBAC1B,CAAC,CAAC,EAAE,GAAG,CAAC,KAAK,CAAC,YAAY,CAAC,CAAC,CAAC,EAAE,YAAY,EAAE,KAAK,CAAC,YAAY,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,MAAM,EAAE,KAAK,CAAC,MAAM,EAAE,CAAC;oBACjG,QAAQ,EAAE,IAAI;oBACd,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;oBACnC,QAAQ;iBACR,CAAA;gBAED,MAAM,GAAG,GAAG,UAAU,CAAC,EAAE,KAAK,EAAE,UAAU,EAAE,UAAU,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,QAAQ,EAAE,CAAC,CAAA;gBAElG,IAAI,CAAC,GAAG;oBAAE,SAAQ;gBAElB,MAAM,OAAO,GAAG,mBAAmB,CAAC,UAAU,EAAE,GAAG,CAAC,CAAA;gBAEpD,IAAI,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM,IAAI,CAAC;oBAAE,SAAQ;gBAE9C,MAAM,QAAQ,GAAG,GAAG,CAAC,CAAC,CAAC,GAAG,wBAAwB,IAAI,GAAG,EAAE,CAAC,CAAC,CAAC,cAAc,CAAC,wBAAwB,EAAE,OAAO,CAAC,CAAA;gBAE/G,MAAM;oBACL,GAAG;oBACH,UAAU,EAAE,OAAO;oBACnB,OAAO,EAAE,IAAI;oBACb,MAAM,EAAE,OAAO;oBACf,MAAM,EAAE,wBAAwB;oBAChC,SAAS,EAAE,QAAQ;oBACnB,cAAc,EAAE,EAAE;oBAClB,OAAO,EAAE,6BAA6B;iBACtC,CAAA;gBAED,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAAG,wBAAwB,EAAE,CAAA"}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../lib/adapters/usgov-nad/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8BG;AAUH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,QAAQ,CAAA;AAEzE;;;GAGG;AACH,eAAO,MAAM,oBAAoB,cAAc,CAAA;AAC/C;;;GAGG;AACH,eAAO,MAAM,yBAAyB,kBAAkB,CAAA;AA8KxD,wBAAgB,qBAAqB,IAAI,aAAa,CAuGrD;AAED;;GAEG;AACH,eAAO,MAAM,eAAe,eAA0B,CAAA"}
|