@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
|
@@ -0,0 +1,105 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* `po-box` slice recipe — synthetic PO box rows: tuples → {@link synthesizePoBoxRow} → aligned
|
|
7
|
+
* LabeledRow, plus optional self-contained US military/diplomatic rows (#517) at
|
|
8
|
+
* `--military-ratio`. Region is required EXCEPT region-less locales (NZ). Ported from
|
|
9
|
+
* scripts/build-po-box-slice.mjs.
|
|
10
|
+
*/
|
|
11
|
+
import { makeLcg } from "@mailwoman/core/utils";
|
|
12
|
+
import { alignAndWrite, readTuples, sliceSourceID, SYNTHETIC_TUPLE_LICENSE as LICENSE, } from "#recipes/scaffold";
|
|
13
|
+
import { synthesizeMilitaryPoBoxRow, synthesizePoBoxRow } from "#synthesizers/po-box";
|
|
14
|
+
/**
|
|
15
|
+
* Slice recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
16
|
+
* and `description` below for the surface form it generates.
|
|
17
|
+
*/
|
|
18
|
+
export const poBoxRecipe = {
|
|
19
|
+
name: "po-box",
|
|
20
|
+
description: "PO box rows: tuples → synthesizePoBoxRow (+ optional US military/diplomatic rows)",
|
|
21
|
+
mode: "tuples",
|
|
22
|
+
options: [
|
|
23
|
+
{ flag: "--pmb-ratio <p>", description: "P(private-mailbox layout). Default 0.15" },
|
|
24
|
+
{ flag: "--military-ratio <p>", description: "P(emit one US military/diplomatic row per input, #517). Default 0" },
|
|
25
|
+
],
|
|
26
|
+
async run(opts, write) {
|
|
27
|
+
if (!opts.input)
|
|
28
|
+
throw new Error("po-box recipe requires --input <tuples.jsonl>");
|
|
29
|
+
const random = makeLcg(opts.seed);
|
|
30
|
+
const pmbRatio = opts.pmbRatio ?? 0.15;
|
|
31
|
+
const militaryRatio = opts.militaryRatio ?? 0;
|
|
32
|
+
// `--source-name` so a slice built for one class carries its own source label and its own dose. A
|
|
33
|
+
// military-only slice (`--variants 0 --military-ratio 1`) is otherwise indistinguishable from the
|
|
34
|
+
// leader-template rows in the mixture, and the two are dosed for different reasons (#517).
|
|
35
|
+
const source = opts.sourceName ?? "synth-po-box";
|
|
36
|
+
let read = 0;
|
|
37
|
+
let emitted = 0;
|
|
38
|
+
let skipped = 0;
|
|
39
|
+
for await (const tuple of readTuples(opts.input)) {
|
|
40
|
+
read++;
|
|
41
|
+
// Region required EXCEPT region-less locales (NZ: "Private Bag 12, Auckland 1010", #517).
|
|
42
|
+
const regionOptional = ["NZ", "NZL", "NEW ZEALAND"].includes(String(tuple.country || "").toUpperCase());
|
|
43
|
+
if (!tuple.locality || !tuple.postcode || !tuple.country || (!tuple.region && !regionOptional)) {
|
|
44
|
+
skipped++;
|
|
45
|
+
continue;
|
|
46
|
+
}
|
|
47
|
+
for (let v = 0; v < opts.variants; v++) {
|
|
48
|
+
const synth = synthesizePoBoxRow(tuple, { random, pmbRatio });
|
|
49
|
+
if (!synth)
|
|
50
|
+
continue;
|
|
51
|
+
const ok = alignAndWrite(write, {
|
|
52
|
+
raw: synth.raw,
|
|
53
|
+
components: synth.components,
|
|
54
|
+
country: tuple.country,
|
|
55
|
+
locale: synth.locale,
|
|
56
|
+
source,
|
|
57
|
+
source_id: sliceSourceID(source, {
|
|
58
|
+
locality: tuple.locality,
|
|
59
|
+
region: tuple.region,
|
|
60
|
+
postcode: tuple.postcode,
|
|
61
|
+
country: tuple.country,
|
|
62
|
+
v: String(v),
|
|
63
|
+
}),
|
|
64
|
+
corpus_version: "0.4.0",
|
|
65
|
+
license: LICENSE,
|
|
66
|
+
}, synth.template);
|
|
67
|
+
if (ok) {
|
|
68
|
+
emitted++;
|
|
69
|
+
}
|
|
70
|
+
else {
|
|
71
|
+
skipped++;
|
|
72
|
+
}
|
|
73
|
+
}
|
|
74
|
+
// US military/diplomatic rows (#517): self-contained, one per input line at --military-ratio.
|
|
75
|
+
// Default 0 → byte-stable (random() not called when off). US-only.
|
|
76
|
+
if (militaryRatio > 0 && random() < militaryRatio) {
|
|
77
|
+
const mil = synthesizeMilitaryPoBoxRow({ random });
|
|
78
|
+
const ok = alignAndWrite(write, {
|
|
79
|
+
raw: mil.raw,
|
|
80
|
+
components: mil.components,
|
|
81
|
+
country: "US",
|
|
82
|
+
locale: mil.locale,
|
|
83
|
+
source,
|
|
84
|
+
source_id: sliceSourceID(source, {
|
|
85
|
+
po_box: mil.components.po_box,
|
|
86
|
+
locality: mil.components.locality,
|
|
87
|
+
region: mil.components.region,
|
|
88
|
+
postcode: mil.components.postcode,
|
|
89
|
+
v: `mil${emitted}`,
|
|
90
|
+
}),
|
|
91
|
+
corpus_version: "0.4.0",
|
|
92
|
+
license: LICENSE,
|
|
93
|
+
}, mil.template);
|
|
94
|
+
if (ok) {
|
|
95
|
+
emitted++;
|
|
96
|
+
}
|
|
97
|
+
else {
|
|
98
|
+
skipped++;
|
|
99
|
+
}
|
|
100
|
+
}
|
|
101
|
+
}
|
|
102
|
+
return { read, emitted, skipped };
|
|
103
|
+
},
|
|
104
|
+
};
|
|
105
|
+
//# sourceMappingURL=index.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../../lib/recipes/po/box/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAEH,OAAO,EAAE,OAAO,EAAE,MAAM,uBAAuB,CAAA;AAE/C,OAAO,EACN,aAAa,EACb,UAAU,EACV,aAAa,EACb,uBAAuB,IAAI,OAAO,GAElC,MAAM,mBAAmB,CAAA;AAC1B,OAAO,EAAE,0BAA0B,EAAE,kBAAkB,EAAuB,MAAM,sBAAsB,CAAA;AAE1G;;;GAGG;AACH,MAAM,CAAC,MAAM,WAAW,GAAiB;IACxC,IAAI,EAAE,QAAQ;IACd,WAAW,EAAE,mFAAmF;IAChG,IAAI,EAAE,QAAQ;IACd,OAAO,EAAE;QACR,EAAE,IAAI,EAAE,iBAAiB,EAAE,WAAW,EAAE,yCAAyC,EAAE;QACnF,EAAE,IAAI,EAAE,sBAAsB,EAAE,WAAW,EAAE,mEAAmE,EAAE;KAClH;IACD,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,IAAI,CAAC,IAAI,CAAC,KAAK;YAAE,MAAM,IAAI,KAAK,CAAC,+CAA+C,CAAC,CAAA;QACjF,MAAM,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACjC,MAAM,QAAQ,GAAG,IAAI,CAAC,QAAQ,IAAI,IAAI,CAAA;QACtC,MAAM,aAAa,GAAG,IAAI,CAAC,aAAa,IAAI,CAAC,CAAA;QAC7C,kGAAkG;QAClG,kGAAkG;QAClG,2FAA2F;QAC3F,MAAM,MAAM,GAAG,IAAI,CAAC,UAAU,IAAI,cAAc,CAAA;QAChD,IAAI,IAAI,GAAG,CAAC,CAAA;QACZ,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QAEf,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,UAAU,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;YAClD,IAAI,EAAE,CAAA;YACN,0FAA0F;YAC1F,MAAM,cAAc,GAAG,CAAC,IAAI,EAAE,KAAK,EAAE,aAAa,CAAC,CAAC,QAAQ,CAAC,MAAM,CAAC,KAAK,CAAC,OAAO,IAAI,EAAE,CAAC,CAAC,WAAW,EAAE,CAAC,CAAA;YAEvG,IAAI,CAAC,KAAK,CAAC,QAAQ,IAAI,CAAC,KAAK,CAAC,QAAQ,IAAI,CAAC,KAAK,CAAC,OAAO,IAAI,CAAC,CAAC,KAAK,CAAC,MAAM,IAAI,CAAC,cAAc,CAAC,EAAE,CAAC;gBAChG,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,QAAQ,EAAE,CAAC,EAAE,EAAE,CAAC;gBACxC,MAAM,KAAK,GAAG,kBAAkB,CAAC,KAAuB,EAAE,EAAE,MAAM,EAAE,QAAQ,EAAE,CAAC,CAAA;gBAE/E,IAAI,CAAC,KAAK;oBAAE,SAAQ;gBAEpB,MAAM,EAAE,GAAG,aAAa,CACvB,KAAK,EACL;oBACC,GAAG,EAAE,KAAK,CAAC,GAAG;oBACd,UAAU,EAAE,KAAK,CAAC,UAAU;oBAC5B,OAAO,EAAE,KAAK,CAAC,OAAO;oBACtB,MAAM,EAAE,KAAK,CAAC,MAAM;oBACpB,MAAM;oBACN,SAAS,EAAE,aAAa,CAAC,MAAM,EAAE;wBAChC,QAAQ,EAAE,KAAK,CAAC,QAAQ;wBACxB,MAAM,EAAE,KAAK,CAAC,MAAM;wBACpB,QAAQ,EAAE,KAAK,CAAC,QAAQ;wBACxB,OAAO,EAAE,KAAK,CAAC,OAAO;wBACtB,CAAC,EAAE,MAAM,CAAC,CAAC,CAAC;qBACZ,CAAC;oBACF,cAAc,EAAE,OAAO;oBACvB,OAAO,EAAE,OAAO;iBAChB,EACD,KAAK,CAAC,QAAQ,CACd,CAAA;gBAED,IAAI,EAAE,EAAE,CAAC;oBACR,OAAO,EAAE,CAAA;gBACV,CAAC;qBAAM,CAAC;oBACP,OAAO,EAAE,CAAA;gBACV,CAAC;YACF,CAAC;YAED,8FAA8F;YAC9F,mEAAmE;YACnE,IAAI,aAAa,GAAG,CAAC,IAAI,MAAM,EAAE,GAAG,aAAa,EAAE,CAAC;gBACnD,MAAM,GAAG,GAAG,0BAA0B,CAAC,EAAE,MAAM,EAAE,CAAC,CAAA;gBAElD,MAAM,EAAE,GAAG,aAAa,CACvB,KAAK,EACL;oBACC,GAAG,EAAE,GAAG,CAAC,GAAG;oBACZ,UAAU,EAAE,GAAG,CAAC,UAAU;oBAC1B,OAAO,EAAE,IAAI;oBACb,MAAM,EAAE,GAAG,CAAC,MAAM;oBAClB,MAAM;oBACN,SAAS,EAAE,aAAa,CAAC,MAAM,EAAE;wBAChC,MAAM,EAAE,GAAG,CAAC,UAAU,CAAC,MAAM;wBAC7B,QAAQ,EAAE,GAAG,CAAC,UAAU,CAAC,QAAQ;wBACjC,MAAM,EAAE,GAAG,CAAC,UAAU,CAAC,MAAM;wBAC7B,QAAQ,EAAE,GAAG,CAAC,UAAU,CAAC,QAAQ;wBACjC,CAAC,EAAE,MAAM,OAAO,EAAE;qBAClB,CAAC;oBACF,cAAc,EAAE,OAAO;oBACvB,OAAO,EAAE,OAAO;iBAChB,EACD,GAAG,CAAC,QAAQ,CACZ,CAAA;gBAED,IAAI,EAAE,EAAE,CAAC;oBACR,OAAO,EAAE,CAAA;gBACV,CAAC;qBAAM,CAAC;oBACP,OAAO,EAAE,CAAA;gBACV,CAAC;YACF,CAAC;QACF,CAAC;QAED,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;IAClC,CAAC;CACD,CAAA"}
|
|
@@ -66,12 +66,31 @@ export interface SliceTuple {
|
|
|
66
66
|
* A recipe must seed the same one its `.mjs` did, the same way it did (usually `seed`, but some derive a per-stream
|
|
67
67
|
* seed), or `--seed N` stops being byte-reproducible.
|
|
68
68
|
*/
|
|
69
|
-
export { makeLcg, mulberry32 as makeMulberry32, makeLcg as makeRandom } from "@mailwoman/core/utils";
|
|
70
69
|
/**
|
|
71
70
|
* One CSV record, keyed by its lower-cased header name, every value trimmed. A column the header does not declare reads
|
|
72
71
|
* as `undefined`; a column the header declares but this record does not reach reads as `""`.
|
|
73
72
|
*/
|
|
74
73
|
export type CSVRecord = Record<string, string | undefined>;
|
|
74
|
+
/**
|
|
75
|
+
* Line breaks inside a value become single spaces, and every value is trimmed.
|
|
76
|
+
*
|
|
77
|
+
* A quote-aware parse is the first thing able to return a value CONTAINING a line break — `us/ia/statewide.csv` has 12,
|
|
78
|
+
* all unit designators like `"#2\n#2"` — and every consumer synthesizes one-line address text from these cells with no
|
|
79
|
+
* guard, because until that parse landed no value could carry one. Collapsing keeps the record (the address is fine;
|
|
80
|
+
* the source's line break is not part of it) without emitting a training row with a newline inside it.
|
|
81
|
+
*
|
|
82
|
+
* Only `\r` and `\n`, deliberately — NOT `\s`. Runs of spaces and tabs pass through exactly as the source wrote them
|
|
83
|
+
* (OA's IA extract writes `NORTH`, three spaces, `MAIN STREET`), because those could always appear and every slice
|
|
84
|
+
* built to date contains them. Widening this to `\s+` silently rewrites values on rows with no line break at all.
|
|
85
|
+
* `scaffold.test.ts` pins both halves.
|
|
86
|
+
*
|
|
87
|
+
* This is what a CSV reader here still owns. Quote handling, object rows, and lower-case keys are `CSVSpliterator`'s
|
|
88
|
+
* defaults, so a recipe reads a source with `CSVSpliterator.fromAsync(source).map(withoutLineBreaks)` and needs nothing
|
|
89
|
+
* else.
|
|
90
|
+
*
|
|
91
|
+
* @category CSV
|
|
92
|
+
*/
|
|
93
|
+
export declare function withoutLineBreaks(record: CSVRecord): CSVRecord;
|
|
75
94
|
/**
|
|
76
95
|
* Read a CSV as header-keyed records.
|
|
77
96
|
*
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"scaffold.d.ts","sourceRoot":"","sources":["../../lib/recipes/scaffold.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAKH,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,SAAS,CAAA;AAC9C,OAAO,KAAK,EAAE,kBAAkB,EAAE,iBAAiB,EAAE,MAAM,aAAa,CAAA;AACxE,OAAO,EAAE,aAAa,EAAmC,MAAM,aAAa,CAAA;AAK5E;;;GAGG;AACH,wBAAgB,aAAa,CAAC,SAAS,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,SAAS,CAAC,GAAG,MAAM,CAElG;AAED;;;;;;;;;;;;;;;;GAgBG;AACH,MAAM,MAAM,iBAAiB,GAAG,SAAS,GAAG,gBAAgB,GAAG,cAAc,CAAA;AAE7E;;GAEG;AACH,MAAM,WAAW,UAAU;IAC1B,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB;;;;OAIG;IACH,iBAAiB,CAAC,EAAE,MAAM,CAAA;IAC1B,MAAM,CAAC,EAAE,MAAM,CAAA;IACf,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB,OAAO,CAAC,EAAE,MAAM,CAAA;IAChB;;;OAGG;IACH,iBAAiB,CAAC,EAAE,iBAAiB,CAAA;IACrC,CAAC,CAAC,EAAE,MAAM,GAAG,OAAO,CAAA;CACpB;AAED;;;;;;;;;;GAUG;AACH,
|
|
1
|
+
{"version":3,"file":"scaffold.d.ts","sourceRoot":"","sources":["../../lib/recipes/scaffold.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAKH,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,SAAS,CAAA;AAC9C,OAAO,KAAK,EAAE,kBAAkB,EAAE,iBAAiB,EAAE,MAAM,aAAa,CAAA;AACxE,OAAO,EAAE,aAAa,EAAmC,MAAM,aAAa,CAAA;AAK5E;;;GAGG;AACH,wBAAgB,aAAa,CAAC,SAAS,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,SAAS,CAAC,GAAG,MAAM,CAElG;AAED;;;;;;;;;;;;;;;;GAgBG;AACH,MAAM,MAAM,iBAAiB,GAAG,SAAS,GAAG,gBAAgB,GAAG,cAAc,CAAA;AAE7E;;GAEG;AACH,MAAM,WAAW,UAAU;IAC1B,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB;;;;OAIG;IACH,iBAAiB,CAAC,EAAE,MAAM,CAAA;IAC1B,MAAM,CAAC,EAAE,MAAM,CAAA;IACf,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB,OAAO,CAAC,EAAE,MAAM,CAAA;IAChB;;;OAGG;IACH,iBAAiB,CAAC,EAAE,iBAAiB,CAAA;IACrC,CAAC,CAAC,EAAE,MAAM,GAAG,OAAO,CAAA;CACpB;AAED;;;;;;;;;;GAUG;AAEH;;;GAGG;AACH,MAAM,MAAM,SAAS,GAAG,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,SAAS,CAAC,CAAA;AAE1D;;;;;;;;;;;;;;;;;;GAkBG;AACH,wBAAgB,iBAAiB,CAAC,MAAM,EAAE,SAAS,GAAG,SAAS,CAQ9D;AAED;;;;;;;;;;;GAWG;AACH,wBAAgB,cAAc,CAAC,MAAM,EAAE,iBAAiB,GAAG,kBAAkB,GAAG,aAAa,CAAC,SAAS,CAAC,CAEvG;AAED;;;;;;;;;GASG;AACH,wBAAgB,oBAAoB,CAAC,WAAW,EAAE,eAAe,EAAE,SAAS,EAAE,MAAM,GAAG,aAAa,CAAC,SAAS,CAAC,CAU9G;AAED;;;GAGG;AACH,eAAO,MAAM,uBAAuB,qEAAgE,CAAA;AAEpG;;;;;;;;GAQG;AACH,eAAO,MAAM,aAAa,UAAW,MAAM,KAAG,MACsB,CAAA;AAEpE;;GAEG;AACH,MAAM,WAAW,aAAa;IAC7B,GAAG,EAAE,eAAe,CAAA;IACpB,GAAG,EAAE,MAAM,CAAA;CACX;AAED;;;GAGG;AACH,MAAM,WAAW,aAAa;IAC7B,YAAY,EAAE,MAAM,CAAA;IACpB,MAAM,EAAE,MAAM,CAAA;IACd,QAAQ,EAAE,MAAM,CAAA;IAChB,QAAQ,EAAE,MAAM,CAAA;CAChB;AAED,MAAM,WAAW,mBAAmB,CAAC,CAAC;IACrC;;;OAGG;IACH,KAAK,CAAC,EAAE,MAAM,CAAA;IACd;;OAEG;IACH,eAAe,CAAC,EAAE,OAAO,CAAA;IACzB;;;OAGG;IACH,qBAAqB,CAAC,EAAE,OAAO,CAAA;IAC/B;;OAEG;IACH,KAAK,EAAE,CAAC,MAAM,EAAE,aAAa,EAAE,GAAG,EAAE,SAAS,EAAE,GAAG,EAAE,MAAM,KAAK,CAAC,CAAA;CAChE;AAED;;;;;;GAMG;AACH,wBAAsB,YAAY,CAAC,CAAC,EAAE,MAAM,EAAE,aAAa,EAAE,OAAO,EAAE,mBAAmB,CAAC,CAAC,CAAC,GAAG,OAAO,CAAC,CAAC,EAAE,CAAC,CA6B1G;AAED;;GAEG;AACH,wBAAgB,UAAU,CAAC,KAAK,EAAE,eAAe,GAAG,aAAa,CAAC,UAAU,CAAC,CAU5E;AAED;;GAEG;AACH,MAAM,WAAW,iBAAiB;IACjC,GAAG,EAAE,MAAM,CAAA;IACX,UAAU,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IAClC,OAAO,EAAE,MAAM,CAAA;IACf,MAAM,CAAC,EAAE,MAAM,CAAA;IACf,MAAM,EAAE,MAAM,CAAA;IACd,SAAS,EAAE,MAAM,CAAA;IACjB,cAAc,CAAC,EAAE,MAAM,CAAA;IACvB,OAAO,CAAC,EAAE,MAAM,CAAA;CAChB;AAED;;;GAGG;AACH,wBAAgB,aAAa,CAC5B,KAAK,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,EAC7B,SAAS,EAAE,iBAAiB,EAC5B,WAAW,EAAE,MAAM,EACnB,WAAW,GAAE,MAAM,GAAG,IAAW,GAC/B,OAAO,CAOT;AAED;;GAEG;AACH,MAAM,WAAW,eAAe;IAC/B,MAAM,EAAE,MAAM,CAAA;IACd,IAAI,EAAE,MAAM,CAAA;IACZ,QAAQ,EAAE,MAAM,CAAA;IAChB,KAAK,CAAC,EAAE,MAAM,CAAA;IACd,KAAK,CAAC,EAAE,MAAM,CAAA;IACd,MAAM,CAAC,EAAE,OAAO,CAAA;IAChB,UAAU,CAAC,EAAE,MAAM,CAAA;IAEnB,eAAe,CAAC,EAAE,MAAM,CAAA;IACxB,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB,aAAa,CAAC,EAAE,MAAM,CAAA;IACtB,gBAAgB,CAAC,EAAE,MAAM,CAAA;IACzB,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB,OAAO,CAAC,EAAE,MAAM,CAAA;IAChB,YAAY,CAAC,EAAE,MAAM,CAAA;IACrB;;;OAGG;IACH,iBAAiB,CAAC,EAAE,MAAM,CAAA;IAC1B;;;OAGG;IACH,gBAAgB,CAAC,EAAE,MAAM,CAAA;IACzB;;;OAGG;IACH,OAAO,CAAC,EAAE,MAAM,CAAA;IAChB;;OAEG;IACH,eAAe,CAAC,EAAE,MAAM,CAAA;IACxB;;;;;;OAMG;IACH,kBAAkB,CAAC,EAAE,OAAO,CAAA;IAC5B,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB,MAAM,CAAC,EAAE,MAAM,CAAA;IACf,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,CAAA;IACf,gBAAgB,CAAC,EAAE,MAAM,CAAA;IACzB;;;OAGG;IACH,eAAe,CAAC,EAAE,MAAM,CAAA;IACxB;;OAEG;IACH,WAAW,CAAC,EAAE,MAAM,CAAA;IACpB;;;OAGG;IACH,eAAe,CAAC,EAAE,MAAM,CAAA;IACxB;;OAEG;IACH,mBAAmB,CAAC,EAAE,MAAM,CAAA;IAC5B;;;OAGG;IACH,OAAO,CAAC,EAAE,MAAM,CAAA;IAChB;;;OAGG;IACH,WAAW,CAAC,EAAE,MAAM,CAAA;IACpB;;;OAGG;IACH,KAAK,CAAC,EAAE,MAAM,CAAA;IACd;;;OAGG;IACH,cAAc,CAAC,EAAE,MAAM,CAAA;IACvB;;OAEG;IACH,gBAAgB,CAAC,EAAE,MAAM,CAAA;CACzB;AAED;;GAEG;AACH,MAAM,WAAW,UAAU;IAC1B,IAAI,CAAC,EAAE,MAAM,CAAA;IACb,OAAO,EAAE,MAAM,CAAA;IACf,OAAO,EAAE,MAAM,CAAA;IACf;;;;OAIG;IACH,YAAY,CAAC,EAAE,MAAM,CAAA;CACrB;AAED;;GAEG;AACH,MAAM,WAAW,iBAAiB;IACjC,IAAI,EAAE,MAAM,CAAA;IACZ,WAAW,EAAE,MAAM,CAAA;CACnB;AAED;;GAEG;AACH,MAAM,WAAW,YAAY;IAC5B;;OAEG;IACH,IAAI,EAAE,MAAM,CAAA;IACZ;;OAEG;IACH,WAAW,EAAE,MAAM,CAAA;IACnB;;OAEG;IACH,IAAI,EAAE,QAAQ,GAAG,UAAU,CAAA;IAC3B;;OAEG;IACH,OAAO,CAAC,EAAE,iBAAiB,EAAE,CAAA;IAC7B;;;OAGG;IACH,GAAG,CAAC,IAAI,EAAE,eAAe,EAAE,KAAK,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAAG,OAAO,CAAC,UAAU,CAAC,CAAA;CAC9E"}
|
package/out/recipes/scaffold.js
CHANGED
|
@@ -22,53 +22,30 @@ export function sliceSourceID(adapterID, parts) {
|
|
|
22
22
|
return stableSourceIDFromParts(adapterID, parts);
|
|
23
23
|
}
|
|
24
24
|
/**
|
|
25
|
-
*
|
|
26
|
-
* `@mailwoman/core/utils` so a recipe keeps importing everything it needs from this one scaffold module.
|
|
25
|
+
* Line breaks inside a value become single spaces, and every value is trimmed.
|
|
27
26
|
*
|
|
28
|
-
* -
|
|
29
|
-
*
|
|
30
|
-
*
|
|
31
|
-
*
|
|
32
|
-
* A recipe must seed the same one its `.mjs` did, the same way it did (usually `seed`, but some derive a per-stream
|
|
33
|
-
* seed), or `--seed N` stops being byte-reproducible.
|
|
34
|
-
*/
|
|
35
|
-
export { makeLcg, mulberry32 as makeMulberry32, makeLcg as makeRandom } from "@mailwoman/core/utils";
|
|
36
|
-
/**
|
|
37
|
-
* Quote handling spans the ROW split, not only the column split: a newline inside a quoted field belongs to a single
|
|
38
|
-
* record, so the record boundaries can only be found by a scanner that already knows where the quotes are. Find the
|
|
39
|
-
* lines first and unquote afterwards and such a record splits in two — the first half short by however many columns
|
|
40
|
-
* followed the newline, which is how a `street` value comes to be read as `city`.
|
|
41
|
-
*
|
|
42
|
-
* `header: false` keeps the first record in the stream, so this module owns the lower-casing rather than
|
|
43
|
-
* `normalizeKeys` — see {@link toHeader}.
|
|
44
|
-
*/
|
|
45
|
-
const CSV_INIT = { header: false, enableQuoteHandling: true };
|
|
46
|
-
/**
|
|
47
|
-
* Header names are lower-cased on the way in. `normalizeKeys` will not do it: it leaves an ALL CAPS header alone, and
|
|
48
|
-
* OpenAddresses ships `LON,LAT,NUMBER,STREET` while other extracts ship the same names lower-case. A recipe names its
|
|
49
|
-
* columns in lower case either way.
|
|
50
|
-
*/
|
|
51
|
-
function toHeader(cells) {
|
|
52
|
-
return cells.map((name) => name.trim().toLowerCase());
|
|
53
|
-
}
|
|
54
|
-
/**
|
|
55
|
-
* Line breaks inside a value become single spaces. A quote-aware parse is the first thing here able to return a value
|
|
56
|
-
* CONTAINING one — `us/ia/statewide.csv` has 12, all unit designators like `"#2\n#2"` — and every consumer synthesizes
|
|
57
|
-
* one-line address text from these cells with no guard, because until that parse landed no value could carry one.
|
|
58
|
-
* Collapsing keeps the record (the address is fine; the source's line break is not part of it) without emitting a
|
|
59
|
-
* training row with a newline inside it.
|
|
27
|
+
* A quote-aware parse is the first thing able to return a value CONTAINING a line break — `us/ia/statewide.csv` has 12,
|
|
28
|
+
* all unit designators like `"#2\n#2"` — and every consumer synthesizes one-line address text from these cells with no
|
|
29
|
+
* guard, because until that parse landed no value could carry one. Collapsing keeps the record (the address is fine;
|
|
30
|
+
* the source's line break is not part of it) without emitting a training row with a newline inside it.
|
|
60
31
|
*
|
|
61
32
|
* Only `\r` and `\n`, deliberately — NOT `\s`. Runs of spaces and tabs pass through exactly as the source wrote them
|
|
62
33
|
* (OA's IA extract writes `NORTH`, three spaces, `MAIN STREET`), because those could always appear and every slice
|
|
63
34
|
* built to date contains them. Widening this to `\s+` silently rewrites values on rows with no line break at all.
|
|
64
|
-
* `scaffold.test.ts` pins both halves
|
|
35
|
+
* `scaffold.test.ts` pins both halves.
|
|
36
|
+
*
|
|
37
|
+
* This is what a CSV reader here still owns. Quote handling, object rows, and lower-case keys are `CSVSpliterator`'s
|
|
38
|
+
* defaults, so a recipe reads a source with `CSVSpliterator.fromAsync(source).map(withoutLineBreaks)` and needs nothing
|
|
39
|
+
* else.
|
|
40
|
+
*
|
|
41
|
+
* @category CSV
|
|
65
42
|
*/
|
|
66
|
-
function
|
|
67
|
-
const
|
|
68
|
-
for (
|
|
69
|
-
|
|
43
|
+
export function withoutLineBreaks(record) {
|
|
44
|
+
const out = {};
|
|
45
|
+
for (const [key, value] of Object.entries(record)) {
|
|
46
|
+
out[key] = (value ?? "").replaceAll(/[\r\n]+/g, " ").trim();
|
|
70
47
|
}
|
|
71
|
-
return
|
|
48
|
+
return out;
|
|
72
49
|
}
|
|
73
50
|
/**
|
|
74
51
|
* Read a CSV as header-keyed records.
|
|
@@ -83,15 +60,7 @@ function toRecord(header, cells) {
|
|
|
83
60
|
* @category CSV
|
|
84
61
|
*/
|
|
85
62
|
export function readCSVRecords(source) {
|
|
86
|
-
|
|
87
|
-
return CSVSpliterator.fromAsync(source, CSV_INIT)
|
|
88
|
-
.filter((cells) => {
|
|
89
|
-
if (header)
|
|
90
|
-
return true;
|
|
91
|
-
header = toHeader(cells);
|
|
92
|
-
return false;
|
|
93
|
-
})
|
|
94
|
-
.map((cells) => toRecord(header, cells));
|
|
63
|
+
return CSVSpliterator.fromAsync(source).map(withoutLineBreaks);
|
|
95
64
|
}
|
|
96
65
|
/**
|
|
97
66
|
* {@link readCSVRecords} over one member of a zip archive — what every recipe reading a cached OA source wants.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"scaffold.js","sourceRoot":"","sources":["../../lib/recipes/scaffold.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAEH,OAAO,EAAE,UAAU,EAAE,MAAM,4BAA4B,CAAA;AACvD,OAAO,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAA;AACrD,OAAO,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAA;AAGrD,OAAO,EAAE,aAAa,EAAE,cAAc,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE5E,OAAO,EAAE,uBAAuB,EAAE,MAAM,iBAAiB,CAAA;AACzD,OAAO,EAAE,QAAQ,EAAE,MAAM,QAAQ,CAAA;AAEjC;;;GAGG;AACH,MAAM,UAAU,aAAa,CAAC,SAAiB,EAAE,KAAyC;IACzF,OAAO,uBAAuB,CAAC,SAAS,EAAE,KAAK,CAAC,CAAA;AACjD,CAAC;
|
|
1
|
+
{"version":3,"file":"scaffold.js","sourceRoot":"","sources":["../../lib/recipes/scaffold.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAEH,OAAO,EAAE,UAAU,EAAE,MAAM,4BAA4B,CAAA;AACvD,OAAO,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAA;AACrD,OAAO,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAA;AAGrD,OAAO,EAAE,aAAa,EAAE,cAAc,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE5E,OAAO,EAAE,uBAAuB,EAAE,MAAM,iBAAiB,CAAA;AACzD,OAAO,EAAE,QAAQ,EAAE,MAAM,QAAQ,CAAA;AAEjC;;;GAGG;AACH,MAAM,UAAU,aAAa,CAAC,SAAiB,EAAE,KAAyC;IACzF,OAAO,uBAAuB,CAAC,SAAS,EAAE,KAAK,CAAC,CAAA;AACjD,CAAC;AA6DD;;;;;;;;;;;;;;;;;;GAkBG;AACH,MAAM,UAAU,iBAAiB,CAAC,MAAiB;IAClD,MAAM,GAAG,GAAc,EAAE,CAAA;IAEzB,KAAK,MAAM,CAAC,GAAG,EAAE,KAAK,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,MAAM,CAAC,EAAE,CAAC;QACnD,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,KAAK,IAAI,EAAE,CAAC,CAAC,UAAU,CAAC,UAAU,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;IAC5D,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC;AAED;;;;;;;;;;;GAWG;AACH,MAAM,UAAU,cAAc,CAAC,MAA8C;IAC5E,OAAO,cAAc,CAAC,SAAS,CAAY,MAAM,CAAC,CAAC,GAAG,CAAC,iBAAiB,CAAC,CAAA;AAC1E,CAAC;AAED;;;;;;;;;GASG;AACH,MAAM,UAAU,oBAAoB,CAAC,WAA4B,EAAE,SAAiB;IACnF,OAAO,aAAa,CAAC,IAAI,CAAY,KAAK,IAAI,EAAE;QAC/C,IAAI,CAAC,CAAC,MAAM,UAAU,CAAC,MAAM,CAAC,WAAW,CAAC,CAAC,CAAC,EAAE,CAAC;YAC9C,OAAO,CAAC,KAAK,CAAC,WAAW,WAAW,6BAA6B,SAAS,EAAE,CAAC,CAAA;YAE7E,OAAO,EAAE,CAAA;QACV,CAAC;QAED,OAAO,cAAc,CAAC,YAAY,CAAC,WAAW,EAAE,SAAS,CAAC,CAAC,CAAA;IAC5D,CAAC,CAAC,CAAA;AACH,CAAC;AAED;;;GAGG;AACH,MAAM,CAAC,MAAM,uBAAuB,GAAG,6DAA6D,CAAA;AAEpG;;;;;;;;GAQG;AACH,MAAM,CAAC,MAAM,aAAa,GAAG,CAAC,KAAa,EAAU,EAAE,CACtD,KAAK,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,WAAW,EAAE,CAAC,UAAU,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;AA0CpE;;;;;;GAMG;AACH,MAAM,CAAC,KAAK,UAAU,YAAY,CAAI,MAAqB,EAAE,OAA+B;IAC3F,MAAM,MAAM,GAAQ,EAAE,CAAA;IACtB,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAA;IAE9B,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,oBAAoB,CAAC,MAAM,CAAC,GAAG,EAAE,MAAM,CAAC,GAAG,CAAC,EAAE,CAAC;QACtE,IAAI,OAAO,CAAC,KAAK,KAAK,SAAS,IAAI,MAAM,CAAC,MAAM,IAAI,OAAO,CAAC,KAAK;YAAE,MAAK;QAExE,MAAM,MAAM,GAAG,GAAG,CAAC,MAAM,IAAI,EAAE,CAAA;QAC/B,MAAM,QAAQ,GAAG,GAAG,CAAC,IAAI,IAAI,EAAE,CAAA;QAC/B,MAAM,YAAY,GAAG,GAAG,CAAC,MAAM,IAAI,EAAE,CAAA;QACrC,MAAM,QAAQ,GAAG,GAAG,CAAC,QAAQ,IAAI,EAAE,CAAA;QAEnC,IAAI,CAAC,MAAM,IAAI,CAAC,QAAQ,IAAI,CAAC,YAAY;YAAE,SAAQ;QAEnD,IAAI,OAAO,CAAC,eAAe,IAAI,CAAC,QAAQ;YAAE,SAAQ;QAElD,MAAM,GAAG,GAAG,CACX,OAAO,CAAC,qBAAqB;YAC5B,CAAC,CAAC,GAAG,YAAY,IAAI,MAAM,IAAI,QAAQ,IAAI,QAAQ,EAAE;YACrD,CAAC,CAAC,GAAG,YAAY,IAAI,MAAM,IAAI,QAAQ,EAAE,CAC1C,CAAC,WAAW,EAAE,CAAA;QAEf,IAAI,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC;YAAE,SAAQ;QAC3B,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;QAEb,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,KAAK,CAAC,EAAE,YAAY,EAAE,MAAM,EAAE,QAAQ,EAAE,QAAQ,EAAE,EAAE,GAAG,EAAE,GAAG,CAAC,CAAC,CAAA;IACnF,CAAC;IAED,OAAO,MAAM,CAAA;AACd,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,UAAU,CAAC,KAAsB;IAChD,qHAAqH;IACrH,qHAAqH;IACrH,mBAAmB;IACnB,OAAO,eAAe,CAAC,SAAS,CAAC,KAAK,CAAC;SACrC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC;SAC1B,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,OAAO,CAAC,IAAI,CAAC,CAAC;SAC/B,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,cAAc,CAAa,IAAI,CAAC,CAAC;SAC/C,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,KAAK,IAAI,CAAC;SACjC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAM,CAAC,CAAA;AACzB,CAAC;AAgBD;;;GAGG;AACH,MAAM,UAAU,aAAa,CAC5B,KAA6B,EAC7B,SAA4B,EAC5B,WAAmB,EACnB,WAAW,GAAkB,IAAI;IAEjC,MAAM,OAAO,GAAG,QAAQ,CAAC,SAA2C,CAAC,CAAA;IAErE,IAAI,CAAC,OAAO,CAAC,GAAG;QAAE,OAAO,KAAK,CAAA;IAC9B,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,GAAG,OAAO,CAAC,GAAG,EAAE,YAAY,EAAE,WAAW,EAAE,aAAa,EAAE,WAAW,EAAE,CAAC,GAAG,IAAI,CAAC,CAAA;IAEvG,OAAO,IAAI,CAAA;AACZ,CAAC"}
|
|
@@ -0,0 +1,89 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* `street-affix` slice recipe — the US street-affix coverage slice (the v0-parity `street_prefix` /
|
|
7
|
+
* `street_suffix` gap — both ~0% F1 in the #15 assessment, collapsed into `street`). Raises
|
|
8
|
+
* PREVALENCE of affix-split streets with format diversity so the model learns to split "N Main
|
|
9
|
+
* St" → street_prefix="N" + street="Main" + street_suffix="St", and (negative space) sharpens
|
|
10
|
+
* `street` itself. Ported from scripts/build-street-affix-slice.mjs.
|
|
11
|
+
*
|
|
12
|
+
* Reads REAL US OpenAddresses tuples and SPLITS the OA `street` field via the codex:
|
|
13
|
+
* `matchLeadingDirectional` (USPS Pub-28 C1) for the prefix, `matchTrailingSuffix` (Pub-28 C2
|
|
14
|
+
* street suffixes) for the suffix. OA streets nearly all carry a suffix; only ~10-20% carry a
|
|
15
|
+
* directional, so we INJECT a directional prefix onto a fraction of prefix-less streets to give
|
|
16
|
+
* `street_prefix` real signal. Each row varies surface form per affix — abbreviated ("N", "St")
|
|
17
|
+
* vs expanded ("North", "Street") — and varies the layout (full address / bare / street-only /
|
|
18
|
+
* venue-prefixed).
|
|
19
|
+
*
|
|
20
|
+
* LEAKAGE-SAFE EVAL (`--golden`): held-out eval uses the VERMONT source only (the corpus
|
|
21
|
+
* defaultHoldout), a different seed, and emits {raw, components} for per-locale-f1. Train uses
|
|
22
|
+
* every NON-Vermont US source.
|
|
23
|
+
*
|
|
24
|
+
* Multi-locale BALANCE (`--multilocale-count`, opts.multilocaleCount > 0): appends NO-affix
|
|
25
|
+
* native-order rows (FR/DE/IT/NL) AFTER the US affix rows, riding the same source weight, purely
|
|
26
|
+
* to keep the postcode-ORDER distribution multi-locale so a US-heavy affix slice doesn't dilute
|
|
27
|
+
* FR/DE postcode (the v0.9.8 blemish).
|
|
28
|
+
*/
|
|
29
|
+
import type { ComponentTag } from "@mailwoman/codex/component";
|
|
30
|
+
import { type CorpusRecipe } from "#recipes/scaffold";
|
|
31
|
+
/**
|
|
32
|
+
* A real US skeleton tuple read from a cached OA zip.
|
|
33
|
+
*/
|
|
34
|
+
interface USTuple {
|
|
35
|
+
house_number: string;
|
|
36
|
+
street: string;
|
|
37
|
+
locality: string;
|
|
38
|
+
region: string;
|
|
39
|
+
postcode: string;
|
|
40
|
+
base_source_id: string;
|
|
41
|
+
}
|
|
42
|
+
export type SuffixBoundaryClass = "terminal-only" | "terminal-contrast";
|
|
43
|
+
/**
|
|
44
|
+
* Classify a real street surface for #1569. `terminal-only` has an ambiguous suffix-eligible name word immediately
|
|
45
|
+
* before a different terminal type (`Blue Hill Rd`); `terminal-contrast` ends at the ambiguous word itself (`Sutton
|
|
46
|
+
* Hollow`). The contrast check intentionally wins when both final words are name-prone: only the LAST token is the
|
|
47
|
+
* suffix under the canonical rule.
|
|
48
|
+
*/
|
|
49
|
+
export declare function classifySuffixBoundaryStreet(street: string): SuffixBoundaryClass | null;
|
|
50
|
+
/**
|
|
51
|
+
* Layout-shell options for {@link renderRow}. `cutoffs` are the cumulative random() boundaries for [full, bare,
|
|
52
|
+
* street-only] — the remainder is the venue shell. Defaults reproduce the original street-affix distribution
|
|
53
|
+
* (40/25/20/15) with the six template venues.
|
|
54
|
+
*/
|
|
55
|
+
interface RenderRowOpts {
|
|
56
|
+
venues?: readonly string[];
|
|
57
|
+
cutoffs?: readonly [number, number, number];
|
|
58
|
+
}
|
|
59
|
+
/**
|
|
60
|
+
* Embed the rendered street in a RANDOM layout so the model recognizes affixes wherever the street sits: full address,
|
|
61
|
+
* bare house+street, street-only (pure affix parse), or venue-prefixed.
|
|
62
|
+
*/
|
|
63
|
+
export declare function renderRow(random: () => number, base: USTuple, street: string, streetComponents: Partial<Record<ComponentTag, string>>, opts?: RenderRowOpts): {
|
|
64
|
+
fmt: string;
|
|
65
|
+
raw: string;
|
|
66
|
+
components: Partial<Record<ComponentTag, string>>;
|
|
67
|
+
};
|
|
68
|
+
/**
|
|
69
|
+
* Slice recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
70
|
+
* and `description` below for the surface form it generates.
|
|
71
|
+
*/
|
|
72
|
+
export declare const streetAffixRecipe: CorpusRecipe;
|
|
73
|
+
/**
|
|
74
|
+
* #1569 root-fix slice. Both classes come from real non-Vermont OA streets and use the affix recipe's existing layout
|
|
75
|
+
* diversity. v4.3.1 makes terminal-only 80% of the mix: the first 40/60 run moved a 100-row TRAIN sample only 4→11
|
|
76
|
+
* while contrast was already 95/100 before training (93/100 after). Post-run audit found that the global affix relabel
|
|
77
|
+
* pass corrupts many already-decomposed target rows into double suffixes; do not retrain this recipe until relabel is
|
|
78
|
+
* idempotent over a decomposed street family. The 20% contrast leg remains explicit, additive to the already-strong
|
|
79
|
+
* base distribution, and B2 still checks it unchanged.
|
|
80
|
+
*
|
|
81
|
+
* V2 (corpus 0.19.0, 2026-08-10 recipe review): the v4.3.3 board split (rich venue-led rows 5/43 vs bare 53/65) showed
|
|
82
|
+
* the model separating template rows from real ones, and the venue shell was the giveaway — six fixed venue strings. v2
|
|
83
|
+
* draws the venue shell from thousands of REAL HRSA facility names and raises its share (venue 30%, full 35%, bare 20%,
|
|
84
|
+
* street-only 15%). Dose policy moved to the recipe's config side: weight ≤4 effective passes per run (Muennighoff
|
|
85
|
+
* 2023's repetition knee) and the source is excluded from the augmentation pool — see the v4.4.0 config.
|
|
86
|
+
*/
|
|
87
|
+
export declare const suffixBoundaryRecipe: CorpusRecipe;
|
|
88
|
+
export {};
|
|
89
|
+
//# sourceMappingURL=affix.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"affix.d.ts","sourceRoot":"","sources":["../../../lib/recipes/street/affix.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;GA2BG;AAEH,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,4BAA4B,CAAA;AAgB9D,OAAO,EAA+C,KAAK,YAAY,EAAE,MAAM,mBAAmB,CAAA;AAqFlG;;GAEG;AACH,UAAU,OAAO;IAChB,YAAY,EAAE,MAAM,CAAA;IACpB,MAAM,EAAE,MAAM,CAAA;IACd,QAAQ,EAAE,MAAM,CAAA;IAChB,MAAM,EAAE,MAAM,CAAA;IACd,QAAQ,EAAE,MAAM,CAAA;IAChB,cAAc,EAAE,MAAM,CAAA;CACtB;AAiFD,MAAM,MAAM,mBAAmB,GAAG,eAAe,GAAG,mBAAmB,CAAA;AAKvE;;;;;GAKG;AACH,wBAAgB,4BAA4B,CAAC,MAAM,EAAE,MAAM,GAAG,mBAAmB,GAAG,IAAI,CAevF;AAmGD;;;;GAIG;AACH,UAAU,aAAa;IACtB,MAAM,CAAC,EAAE,SAAS,MAAM,EAAE,CAAA;IAC1B,OAAO,CAAC,EAAE,SAAS,CAAC,MAAM,EAAE,MAAM,EAAE,MAAM,CAAC,CAAA;CAC3C;AAED;;;GAGG;AACH,wBAAgB,SAAS,CACxB,MAAM,EAAE,MAAM,MAAM,EACpB,IAAI,EAAE,OAAO,EACb,MAAM,EAAE,MAAM,EACd,gBAAgB,EAAE,OAAO,CAAC,MAAM,CAAC,YAAY,EAAE,MAAM,CAAC,CAAC,EACvD,IAAI,GAAE,aAAkB,GACtB;IAAE,GAAG,EAAE,MAAM,CAAC;IAAC,GAAG,EAAE,MAAM,CAAC;IAAC,UAAU,EAAE,OAAO,CAAC,MAAM,CAAC,YAAY,EAAE,MAAM,CAAC,CAAC,CAAA;CAAE,CA8BjF;AAsCD;;;GAGG;AACH,eAAO,MAAM,iBAAiB,EAAE,YAiM/B,CAAA;AAOD;;;;;;;;;;;;;GAaG;AACH,eAAO,MAAM,oBAAoB,EAAE,YA0JlC,CAAA"}
|