@mailwoman/corpus 9.1.0 → 9.2.0
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 +2 -2
- package/data/PROVENANCE.md +13 -0
- package/data/reviewed-ve-postcode-tuples.json +74 -0
- package/out/src/adapters/ban/adapter.d.ts +1 -1
- package/out/src/adapters/ban/adapter.d.ts.map +1 -1
- package/out/src/adapters/ban/adapter.js +4 -3
- package/out/src/adapters/ban/adapter.js.map +1 -1
- package/out/src/adapters/fcc-bdc/adapter.d.ts +1 -1
- package/out/src/adapters/fcc-bdc/adapter.d.ts.map +1 -1
- package/out/src/adapters/fcc-bdc/adapter.js +2 -2
- package/out/src/adapters/fcc-bdc/adapter.js.map +1 -1
- package/out/src/adapters/geonames/adapter.d.ts +1 -1
- package/out/src/adapters/geonames/adapter.d.ts.map +1 -1
- package/out/src/adapters/geonames/adapter.js +1 -1
- package/out/src/adapters/geonames/adapter.js.map +1 -1
- package/out/src/adapters/geonames-postal/adapter.d.ts +1 -1
- package/out/src/adapters/geonames-postal/adapter.d.ts.map +1 -1
- package/out/src/adapters/geonames-postal/adapter.js +2 -2
- package/out/src/adapters/geonames-postal/adapter.js.map +1 -1
- package/out/src/adapters/gnaf/adapter.d.ts +1 -1
- package/out/src/adapters/gnaf/adapter.d.ts.map +1 -1
- package/out/src/adapters/gnaf/adapter.js +1 -1
- package/out/src/adapters/gnaf/adapter.js.map +1 -1
- package/out/src/adapters/index.d.ts +1 -1
- package/out/src/adapters/index.d.ts.map +1 -1
- package/out/src/adapters/index.js +1 -1
- package/out/src/adapters/index.js.map +1 -1
- package/out/src/adapters/openaddresses/adapter.d.ts +1 -1
- package/out/src/adapters/openaddresses/adapter.d.ts.map +1 -1
- package/out/src/adapters/openaddresses/adapter.js +2 -2
- package/out/src/adapters/openaddresses/adapter.js.map +1 -1
- package/out/src/adapters/overture/adapter.d.ts +1 -1
- package/out/src/adapters/overture/adapter.d.ts.map +1 -1
- package/out/src/adapters/overture/adapter.js +1 -1
- package/out/src/adapters/overture/adapter.js.map +1 -1
- package/out/src/adapters/state-hi-schools/adapter.d.ts +1 -1
- package/out/src/adapters/state-hi-schools/adapter.d.ts.map +1 -1
- package/out/src/adapters/state-hi-schools/adapter.js +6 -5
- package/out/src/adapters/state-hi-schools/adapter.js.map +1 -1
- package/out/src/adapters/state-ia-contractors/adapter.d.ts +1 -1
- package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +1 -1
- package/out/src/adapters/state-ia-contractors/adapter.js +11 -6
- package/out/src/adapters/state-ia-contractors/adapter.js.map +1 -1
- package/out/src/adapters/state-ny-notaries/adapter.d.ts +1 -1
- package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +1 -1
- package/out/src/adapters/state-ny-notaries/adapter.js +11 -17
- package/out/src/adapters/state-ny-notaries/adapter.js.map +1 -1
- package/out/src/adapters/state-tx-notaries/adapter.d.ts +1 -1
- package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +1 -1
- package/out/src/adapters/state-tx-notaries/adapter.js +11 -6
- package/out/src/adapters/state-tx-notaries/adapter.js.map +1 -1
- package/out/src/adapters/synth-po-box/adapter.d.ts +2 -2
- package/out/src/adapters/synth-po-box/adapter.d.ts.map +1 -1
- package/out/src/adapters/synth-po-box/adapter.js +2 -2
- package/out/src/adapters/synth-po-box/adapter.js.map +1 -1
- package/out/src/adapters/tiger/adapter.d.ts +1 -1
- package/out/src/adapters/tiger/adapter.d.ts.map +1 -1
- package/out/src/adapters/tiger/adapter.js +1 -1
- package/out/src/adapters/tiger/adapter.js.map +1 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +1 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +6 -5
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -1
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts +1 -1
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +1 -1
- package/out/src/adapters/usgov-imls-pls/adapter.js +10 -6
- package/out/src/adapters/usgov-imls-pls/adapter.js.map +1 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +1 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.js +5 -4
- package/out/src/adapters/usgov-irs-bmf/adapter.js.map +1 -1
- package/out/src/adapters/usgov-nad/adapter.d.ts +1 -1
- package/out/src/adapters/usgov-nad/adapter.d.ts.map +1 -1
- package/out/src/adapters/usgov-nad/adapter.js +7 -7
- package/out/src/adapters/usgov-nad/adapter.js.map +1 -1
- package/out/src/adapters/usgov-nppes/adapter.d.ts +1 -1
- package/out/src/adapters/usgov-nppes/adapter.d.ts.map +1 -1
- package/out/src/adapters/usgov-nppes/adapter.js +9 -9
- package/out/src/adapters/usgov-nppes/adapter.js.map +1 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts +1 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +6 -5
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -1
- package/out/src/adapters/utils/index.d.ts +7 -1
- package/out/src/adapters/utils/index.d.ts.map +1 -1
- package/out/src/adapters/utils/index.js +10 -2
- package/out/src/adapters/utils/index.js.map +1 -1
- package/out/src/adapters/wof-admin-jp/adapter.d.ts +1 -1
- package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +1 -1
- package/out/src/adapters/wof-admin-jp/adapter.js +5 -5
- package/out/src/adapters/wof-admin-jp/adapter.js.map +1 -1
- package/out/src/adapters/wof-admin-json/adapter.d.ts +4 -15
- package/out/src/adapters/wof-admin-json/adapter.d.ts.map +1 -1
- package/out/src/adapters/wof-admin-json/adapter.js +11 -35
- package/out/src/adapters/wof-admin-json/adapter.js.map +1 -1
- package/out/src/adapters/wof-json-rows.d.ts +32 -0
- package/out/src/adapters/wof-json-rows.d.ts.map +1 -0
- package/out/src/adapters/wof-json-rows.js +45 -0
- package/out/src/adapters/wof-json-rows.js.map +1 -0
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts +4 -9
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +1 -1
- package/out/src/adapters/wof-postalcode-json/adapter.js +12 -37
- package/out/src/adapters/wof-postalcode-json/adapter.js.map +1 -1
- package/out/src/build.d.ts +4 -3
- package/out/src/build.d.ts.map +1 -1
- package/out/src/build.js +7 -4
- package/out/src/build.js.map +1 -1
- package/out/src/index.d.ts +1 -1
- package/out/src/index.d.ts.map +1 -1
- package/out/src/index.js +1 -1
- package/out/src/index.js.map +1 -1
- package/out/src/parquet-wrapper/reader.d.ts.map +1 -1
- package/out/src/parquet-wrapper/reader.js +5 -0
- package/out/src/parquet-wrapper/reader.js.map +1 -1
- package/out/src/runner.d.ts +2 -2
- package/out/src/runner.d.ts.map +1 -1
- package/out/src/runner.js +1 -1
- package/out/src/runner.js.map +1 -1
- package/out/src/shard-recipes/anchor-absorption.d.ts.map +1 -1
- package/out/src/shard-recipes/anchor-absorption.js +4 -5
- package/out/src/shard-recipes/anchor-absorption.js.map +1 -1
- package/out/src/shard-recipes/bare-country.d.ts +25 -0
- package/out/src/shard-recipes/bare-country.d.ts.map +1 -0
- package/out/src/shard-recipes/bare-country.js +87 -0
- package/out/src/shard-recipes/bare-country.js.map +1 -0
- package/out/src/shard-recipes/boundary-stress.d.ts.map +1 -1
- package/out/src/shard-recipes/boundary-stress.js +2 -2
- package/out/src/shard-recipes/boundary-stress.js.map +1 -1
- package/out/src/shard-recipes/country-balanced.d.ts.map +1 -1
- package/out/src/shard-recipes/country-balanced.js +6 -5
- package/out/src/shard-recipes/country-balanced.js.map +1 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +1 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.js +28 -10
- package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +1 -1
- package/out/src/shard-recipes/fr-admin-split.d.ts.map +1 -1
- package/out/src/shard-recipes/fr-admin-split.js +4 -3
- package/out/src/shard-recipes/fr-admin-split.js.map +1 -1
- package/out/src/shard-recipes/fr-bare-street.d.ts.map +1 -1
- package/out/src/shard-recipes/fr-bare-street.js +72 -11
- package/out/src/shard-recipes/fr-bare-street.js.map +1 -1
- package/out/src/shard-recipes/fr-lieudit.d.ts.map +1 -1
- package/out/src/shard-recipes/fr-lieudit.js +4 -3
- package/out/src/shard-recipes/fr-lieudit.js.map +1 -1
- package/out/src/shard-recipes/fr-order.d.ts.map +1 -1
- package/out/src/shard-recipes/fr-order.js +4 -3
- package/out/src/shard-recipes/fr-order.js.map +1 -1
- package/out/src/shard-recipes/german.d.ts.map +1 -1
- package/out/src/shard-recipes/german.js +3 -3
- package/out/src/shard-recipes/german.js.map +1 -1
- package/out/src/shard-recipes/house-venue.js +1 -1
- package/out/src/shard-recipes/house-venue.js.map +1 -1
- package/out/src/shard-recipes/index.d.ts.map +1 -1
- package/out/src/shard-recipes/index.js +6 -0
- package/out/src/shard-recipes/index.js.map +1 -1
- package/out/src/shard-recipes/intersection.d.ts.map +1 -1
- package/out/src/shard-recipes/intersection.js +3 -3
- package/out/src/shard-recipes/intersection.js.map +1 -1
- package/out/src/shard-recipes/locale.d.ts +1 -1
- package/out/src/shard-recipes/locale.d.ts.map +1 -1
- package/out/src/shard-recipes/locale.js +5 -4
- package/out/src/shard-recipes/locale.js.map +1 -1
- package/out/src/shard-recipes/no-street.js +1 -1
- package/out/src/shard-recipes/no-street.js.map +1 -1
- package/out/src/shard-recipes/po-box-cedex.d.ts.map +1 -1
- package/out/src/shard-recipes/po-box-cedex.js +2 -2
- package/out/src/shard-recipes/po-box-cedex.js.map +1 -1
- package/out/src/shard-recipes/po-box.d.ts.map +1 -1
- package/out/src/shard-recipes/po-box.js +1 -1
- package/out/src/shard-recipes/po-box.js.map +1 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts +47 -0
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts.map +1 -0
- package/out/src/shard-recipes/reviewed-postcode-tail.js +125 -0
- package/out/src/shard-recipes/reviewed-postcode-tail.js.map +1 -0
- package/out/src/shard-recipes/scaffold.d.ts +33 -4
- package/out/src/shard-recipes/scaffold.d.ts.map +1 -1
- package/out/src/shard-recipes/scaffold.js +5 -6
- package/out/src/shard-recipes/scaffold.js.map +1 -1
- package/out/src/shard-recipes/street-affix.d.ts.map +1 -1
- package/out/src/shard-recipes/street-affix.js +2 -2
- package/out/src/shard-recipes/street-affix.js.map +1 -1
- package/out/src/shard-recipes/street-bare.js +3 -3
- package/out/src/shard-recipes/street-bare.js.map +1 -1
- package/out/src/shard-recipes/street.js +2 -2
- package/out/src/shard-recipes/street.js.map +1 -1
- package/out/src/shard-recipes/sub-venue-sources.d.ts +2 -2
- package/out/src/shard-recipes/sub-venue-sources.d.ts.map +1 -1
- package/out/src/shard-recipes/sub-venue-sources.js +1 -1
- package/out/src/shard-recipes/sub-venue-sources.js.map +1 -1
- package/out/src/shard-recipes/sub-venue.d.ts +1 -1
- package/out/src/shard-recipes/sub-venue.d.ts.map +1 -1
- package/out/src/shard-recipes/sub-venue.js +6 -5
- package/out/src/shard-recipes/sub-venue.js.map +1 -1
- package/out/src/shard-recipes/trailing-region.d.ts +74 -0
- package/out/src/shard-recipes/trailing-region.d.ts.map +1 -0
- package/out/src/shard-recipes/trailing-region.js +157 -0
- package/out/src/shard-recipes/trailing-region.js.map +1 -0
- package/out/src/shard-recipes/unit.d.ts.map +1 -1
- package/out/src/shard-recipes/unit.js +2 -2
- package/out/src/shard-recipes/unit.js.map +1 -1
- package/out/src/synthesizers/boundary-stress.d.ts +1 -1
- package/out/src/synthesizers/boundary-stress.d.ts.map +1 -1
- package/out/src/synthesizers/german.d.ts +1 -1
- package/out/src/synthesizers/german.d.ts.map +1 -1
- package/out/src/synthesizers/german.js.map +1 -1
- package/out/src/synthesizers/house-venue.d.ts +1 -1
- package/out/src/synthesizers/house-venue.d.ts.map +1 -1
- package/out/src/synthesizers/house-venue.js +16 -2
- package/out/src/synthesizers/house-venue.js.map +1 -1
- package/out/src/synthesizers/intersection.d.ts +1 -1
- package/out/src/synthesizers/intersection.d.ts.map +1 -1
- package/out/src/synthesizers/no-street.d.ts +1 -1
- package/out/src/synthesizers/no-street.d.ts.map +1 -1
- package/out/src/synthesizers/po-box.d.ts +1 -1
- package/out/src/synthesizers/po-box.d.ts.map +1 -1
- package/out/src/synthesizers/street.d.ts +1 -1
- package/out/src/synthesizers/street.d.ts.map +1 -1
- package/out/src/synthesizers/street.js +3 -2
- package/out/src/synthesizers/street.js.map +1 -1
- package/out/src/synthesizers/utils.d.ts +1 -1
- package/out/src/synthesizers/utils.d.ts.map +1 -1
- package/out/src/synthesizers/utils.js +3 -2
- package/out/src/synthesizers/utils.js.map +1 -1
- package/out/src/tools/align-shard.d.ts.map +1 -1
- package/out/src/tools/align-shard.js +2 -2
- package/out/src/tools/align-shard.js.map +1 -1
- package/out/src/tools/fetch/ban.d.ts.map +1 -1
- package/out/src/tools/fetch/ban.js +2 -18
- package/out/src/tools/fetch/ban.js.map +1 -1
- package/out/src/tools/fetch/download.d.ts +12 -3
- package/out/src/tools/fetch/download.d.ts.map +1 -1
- package/out/src/tools/fetch/download.js +20 -4
- package/out/src/tools/fetch/download.js.map +1 -1
- package/out/src/tools/fetch/geonames-dump.d.ts +87 -0
- package/out/src/tools/fetch/geonames-dump.d.ts.map +1 -0
- package/out/src/tools/fetch/geonames-dump.js +178 -0
- package/out/src/tools/fetch/geonames-dump.js.map +1 -0
- package/out/src/tools/fetch/geonames-postal.d.ts +76 -0
- package/out/src/tools/fetch/geonames-postal.d.ts.map +1 -0
- package/out/src/tools/fetch/geonames-postal.js +125 -0
- package/out/src/tools/fetch/geonames-postal.js.map +1 -0
- package/out/src/tools/fetch/imls-pls.d.ts.map +1 -1
- package/out/src/tools/fetch/imls-pls.js +2 -2
- package/out/src/tools/fetch/imls-pls.js.map +1 -1
- package/out/src/tools/fetch/index.d.ts +11 -0
- package/out/src/tools/fetch/index.d.ts.map +1 -1
- package/out/src/tools/fetch/index.js +11 -0
- package/out/src/tools/fetch/index.js.map +1 -1
- package/out/src/tools/fetch/nad.d.ts.map +1 -1
- package/out/src/tools/fetch/nad.js +20 -11
- package/out/src/tools/fetch/nad.js.map +1 -1
- package/out/src/tools/fetch/nppes.d.ts.map +1 -1
- package/out/src/tools/fetch/nppes.js +9 -7
- package/out/src/tools/fetch/nppes.js.map +1 -1
- package/out/src/tools/fetch/openaddresses.d.ts.map +1 -1
- package/out/src/tools/fetch/openaddresses.js +18 -17
- package/out/src/tools/fetch/openaddresses.js.map +1 -1
- package/out/src/tools/fetch/ourairports.d.ts.map +1 -1
- package/out/src/tools/fetch/ourairports.js +7 -2
- package/out/src/tools/fetch/ourairports.js.map +1 -1
- package/out/src/tools/fetch/ppd.d.ts +0 -4
- package/out/src/tools/fetch/ppd.d.ts.map +1 -1
- package/out/src/tools/fetch/ppd.js +1 -1
- package/out/src/tools/fetch/ppd.js.map +1 -1
- package/out/src/tools/fetch/state-hi-schools.d.ts.map +1 -1
- package/out/src/tools/fetch/state-hi-schools.js +3 -19
- package/out/src/tools/fetch/state-hi-schools.js.map +1 -1
- package/out/src/tools/fetch/state-sources.d.ts +4 -0
- package/out/src/tools/fetch/state-sources.d.ts.map +1 -1
- package/out/src/tools/fetch/state-sources.js +1 -5
- package/out/src/tools/fetch/state-sources.js.map +1 -1
- package/out/src/tools/fetch/tiger-full.d.ts.map +1 -1
- package/out/src/tools/fetch/tiger-full.js +15 -21
- package/out/src/tools/fetch/tiger-full.js.map +1 -1
- package/out/src/tools/golden-expand.d.ts.map +1 -1
- package/out/src/tools/golden-expand.js +34 -25
- package/out/src/tools/golden-expand.js.map +1 -1
- package/out/src/tools/golden-relabel-street.js +2 -2
- package/out/src/tools/golden-relabel-street.js.map +1 -1
- package/out/src/tools/index.d.ts +2 -2
- package/out/src/tools/index.d.ts.map +1 -1
- package/out/src/tools/index.js +2 -2
- package/out/src/tools/index.js.map +1 -1
- package/out/src/tools/ingest-csv.d.ts.map +1 -1
- package/out/src/tools/ingest-csv.js +0 -11
- package/out/src/tools/ingest-csv.js.map +1 -1
- package/out/src/tools/overlay-manifest.d.ts +4 -0
- package/out/src/tools/overlay-manifest.d.ts.map +1 -1
- package/out/src/tools/overlay-manifest.js +16 -6
- package/out/src/tools/overlay-manifest.js.map +1 -1
- package/out/src/tools/postcode-triples.d.ts +175 -0
- package/out/src/tools/postcode-triples.d.ts.map +1 -0
- package/out/src/tools/postcode-triples.js +304 -0
- package/out/src/tools/postcode-triples.js.map +1 -0
- package/out/src/tools/shard-kryptonite.d.ts.map +1 -1
- package/out/src/tools/shard-kryptonite.js +1 -2
- package/out/src/tools/shard-kryptonite.js.map +1 -1
- package/out/src/tools/shard-translit.d.ts.map +1 -1
- package/out/src/tools/shard-translit.js +4 -26
- package/out/src/tools/shard-translit.js.map +1 -1
- package/out/src/tools/sub-venue/harvest.d.ts +100 -0
- package/out/src/tools/sub-venue/harvest.d.ts.map +1 -0
- package/out/src/tools/sub-venue/harvest.js +168 -0
- package/out/src/tools/sub-venue/harvest.js.map +1 -0
- package/out/src/tools/sub-venue/head-nouns.d.ts +50 -0
- package/out/src/tools/sub-venue/head-nouns.d.ts.map +1 -0
- package/out/src/tools/sub-venue/head-nouns.js +210 -0
- package/out/src/tools/sub-venue/head-nouns.js.map +1 -0
- package/out/src/tools/sub-venue/surfaces.d.ts +45 -0
- package/out/src/tools/sub-venue/surfaces.d.ts.map +1 -0
- package/out/src/tools/sub-venue/surfaces.js +77 -0
- package/out/src/tools/sub-venue/surfaces.js.map +1 -0
- package/out/src/tools/sub-venue/table.d.ts +229 -0
- package/out/src/tools/sub-venue/table.d.ts.map +1 -0
- package/out/src/tools/sub-venue/table.js +108 -0
- package/out/src/tools/sub-venue/table.js.map +1 -0
- package/out/src/tools/sub-venue/wikidata.d.ts +26 -0
- package/out/src/tools/sub-venue/wikidata.d.ts.map +1 -0
- package/out/src/tools/sub-venue/wikidata.js +62 -0
- package/out/src/tools/sub-venue/wikidata.js.map +1 -0
- package/out/src/tools/sub-venue-lexicon.d.ts +27 -378
- package/out/src/tools/sub-venue-lexicon.d.ts.map +1 -1
- package/out/src/tools/sub-venue-lexicon.js +30 -565
- package/out/src/tools/sub-venue-lexicon.js.map +1 -1
- package/out/src/utils/align.d.ts +1 -1
- package/out/src/utils/align.d.ts.map +1 -1
- package/out/src/utils/align.js.map +1 -1
- package/out/src/utils/golden.js +1 -1
- package/out/src/utils/golden.js.map +1 -1
- package/out/src/utils/license.js +1 -1
- package/out/src/utils/license.js.map +1 -1
- package/out/src/utils/parquet.d.ts +24 -5
- package/out/src/utils/parquet.d.ts.map +1 -1
- package/out/src/utils/parquet.js +6 -2
- package/out/src/utils/parquet.js.map +1 -1
- package/out/src/utils/split.d.ts +1 -1
- package/out/src/utils/split.d.ts.map +1 -1
- package/out/src/utils/split.js +2 -2
- package/out/src/utils/split.js.map +1 -1
- package/package.json +230 -10
- package/src/adapters/ban/adapter.ts +6 -4
- package/src/adapters/fcc-bdc/adapter.ts +4 -3
- package/src/adapters/geonames/adapter.ts +3 -2
- package/src/adapters/geonames-postal/adapter.ts +4 -3
- package/src/adapters/gnaf/adapter.ts +3 -2
- package/src/adapters/index.ts +2 -2
- package/src/adapters/openaddresses/adapter.ts +4 -3
- package/src/adapters/overture/adapter.ts +3 -2
- package/src/adapters/state-hi-schools/adapter.ts +8 -6
- package/src/adapters/state-ia-contractors/adapter.ts +13 -7
- package/src/adapters/state-ny-notaries/adapter.ts +13 -31
- package/src/adapters/state-tx-notaries/adapter.ts +13 -7
- package/src/adapters/synth-po-box/adapter.ts +5 -4
- package/src/adapters/tiger/adapter.ts +3 -2
- package/src/adapters/usgov-hrsa-fqhc/adapter.ts +8 -6
- package/src/adapters/usgov-imls-pls/adapter.ts +12 -7
- package/src/adapters/usgov-irs-bmf/adapter.ts +7 -5
- package/src/adapters/usgov-nad/adapter.ts +9 -8
- package/src/adapters/usgov-nppes/adapter.ts +13 -11
- package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +8 -6
- package/src/adapters/utils/index.ts +16 -3
- package/src/adapters/wof-admin-jp/adapter.ts +9 -12
- package/src/adapters/wof-admin-json/adapter.ts +16 -54
- package/src/adapters/wof-json-rows.ts +79 -0
- package/src/adapters/wof-postalcode-json/adapter.ts +17 -50
- package/src/build.ts +10 -10
- package/src/index.ts +1 -1
- package/src/parquet-wrapper/reader.ts +9 -0
- package/src/runner.ts +2 -7
- package/src/shard-recipes/anchor-absorption.ts +5 -5
- package/src/shard-recipes/bare-country.ts +95 -0
- package/src/shard-recipes/boundary-stress.ts +2 -5
- package/src/shard-recipes/country-balanced.ts +8 -6
- package/src/shard-recipes/cz-pcfirst-preposition.ts +29 -10
- package/src/shard-recipes/fr-admin-split.ts +6 -4
- package/src/shard-recipes/fr-bare-street.ts +85 -10
- package/src/shard-recipes/fr-lieudit.ts +6 -4
- package/src/shard-recipes/fr-order.ts +6 -4
- package/src/shard-recipes/german.ts +4 -3
- package/src/shard-recipes/house-venue.ts +1 -1
- package/src/shard-recipes/index.ts +6 -0
- package/src/shard-recipes/intersection.ts +5 -4
- package/src/shard-recipes/locale.ts +6 -8
- package/src/shard-recipes/no-street.ts +1 -1
- package/src/shard-recipes/po-box-cedex.ts +4 -3
- package/src/shard-recipes/po-box.ts +1 -5
- package/src/shard-recipes/reviewed-postcode-tail.ts +189 -0
- package/src/shard-recipes/scaffold.ts +38 -7
- package/src/shard-recipes/street-affix.ts +4 -3
- package/src/shard-recipes/street-bare.ts +3 -3
- package/src/shard-recipes/street.ts +2 -2
- package/src/shard-recipes/sub-venue-sources.ts +4 -14
- package/src/shard-recipes/sub-venue.ts +10 -8
- package/src/shard-recipes/trailing-region.ts +183 -0
- package/src/shard-recipes/unit.ts +4 -3
- package/src/synthesizers/boundary-stress.ts +1 -1
- package/src/synthesizers/german.ts +2 -1
- package/src/synthesizers/house-venue.ts +17 -3
- package/src/synthesizers/intersection.ts +1 -1
- package/src/synthesizers/no-street.ts +1 -1
- package/src/synthesizers/po-box.ts +1 -1
- package/src/synthesizers/street.ts +5 -3
- package/src/synthesizers/utils.ts +5 -3
- package/src/tools/align-shard.ts +3 -2
- package/src/tools/fetch/ban.ts +2 -22
- package/src/tools/fetch/download.ts +22 -4
- package/src/tools/fetch/geonames-dump.ts +267 -0
- package/src/tools/fetch/geonames-postal.ts +180 -0
- package/src/tools/fetch/imls-pls.ts +2 -2
- package/src/tools/fetch/index.ts +11 -0
- package/src/tools/fetch/nad.ts +21 -10
- package/src/tools/fetch/nppes.ts +8 -6
- package/src/tools/fetch/openaddresses.ts +18 -22
- package/src/tools/fetch/ourairports.ts +7 -2
- package/src/tools/fetch/ppd.ts +1 -1
- package/src/tools/fetch/state-hi-schools.ts +3 -23
- package/src/tools/fetch/state-sources.ts +1 -1
- package/src/tools/fetch/tiger-full.ts +17 -24
- package/src/tools/golden-expand.ts +44 -33
- package/src/tools/golden-relabel-street.ts +2 -2
- package/src/tools/index.ts +2 -2
- package/src/tools/ingest-csv.ts +0 -13
- package/src/tools/overlay-manifest.ts +20 -8
- package/src/tools/postcode-triples.ts +375 -0
- package/src/tools/shard-kryptonite.ts +5 -4
- package/src/tools/shard-translit.ts +10 -35
- package/src/tools/sub-venue/harvest.ts +235 -0
- package/src/tools/sub-venue/head-nouns.ts +242 -0
- package/src/tools/sub-venue/surfaces.ts +95 -0
- package/src/tools/sub-venue/table.ts +281 -0
- package/src/tools/sub-venue/wikidata.ts +85 -0
- package/src/tools/sub-venue-lexicon.ts +67 -886
- package/src/utils/align.ts +2 -1
- package/src/utils/golden.ts +1 -1
- package/src/utils/license.ts +1 -1
- package/src/utils/parquet.ts +22 -8
- package/src/utils/split.ts +4 -3
package/README.md
CHANGED
|
@@ -70,8 +70,8 @@ node scripts/corpus-stats.mjs
|
|
|
70
70
|
|
|
71
71
|
- [`@mailwoman/neural`](../neural) — the runtime that loads and runs the trained model
|
|
72
72
|
- [`@mailwoman/neural-weights-en-us`](../neural-weights-en-us) — the trained model itself
|
|
73
|
-
- [Corpus Construction concepts](https://mailwoman.
|
|
74
|
-
- [Training Pipeline concepts](https://mailwoman.
|
|
73
|
+
- [Corpus Construction concepts](https://mailwoman.ai/articles/concepts/corpus-construction/)
|
|
74
|
+
- [Training Pipeline concepts](https://mailwoman.ai/articles/concepts/training-pipeline/)
|
|
75
75
|
- [CONTRIBUTING_MODEL_WORK](https://github.com/sister-software/mailwoman/blob/main/docs/engineering/CONTRIBUTING_MODEL_WORK.mdx)
|
|
76
76
|
|
|
77
77
|
## License
|
package/data/PROVENANCE.md
CHANGED
|
@@ -1,5 +1,18 @@
|
|
|
1
1
|
# `corpus/data/` provenance
|
|
2
2
|
|
|
3
|
+
## `reviewed-ve-postcode-tuples.json` — reviewed Venezuelan postcode placement (#1821)
|
|
4
|
+
|
|
5
|
+
Four geographic facts support the Venezuelan `locality postcode, region` convention. The Barcelona
|
|
6
|
+
tuple comes from the Anzoátegui state government's contact address. The Caracas, Sanare, and Santa
|
|
7
|
+
Elena de Guairén tuples come from the Universal Postal Union's Venezuela addressing guide. The file
|
|
8
|
+
records the publisher, full source address, retrieval date, review status, and source-license note for
|
|
9
|
+
each tuple.
|
|
10
|
+
|
|
11
|
+
Only factual fields are stored. No source prose is copied, and the corpus rows do not claim that either
|
|
12
|
+
source published the facts under CC0 or another open-data license. The recipe creates bounded synthetic
|
|
13
|
+
case, punctuation, accent, country-tail, and left-context forms while keeping each reviewed
|
|
14
|
+
postcode-to-place join unchanged.
|
|
15
|
+
|
|
3
16
|
## `sub-venue-lexicon.json` — the sub-venue designator lexicon (#35, waves 1–2)
|
|
4
17
|
|
|
5
18
|
The vocabulary a corpus shard (and eventually the span proposer) reads to recognize `Terminal 5`,
|
|
@@ -0,0 +1,74 @@
|
|
|
1
|
+
{
|
|
2
|
+
"version": "1.0.0",
|
|
3
|
+
"reviewedAt": "2026-08-24",
|
|
4
|
+
"tuples": [
|
|
5
|
+
{
|
|
6
|
+
"id": "ve-barcelona-6001-anzoategui",
|
|
7
|
+
"locality": "Barcelona",
|
|
8
|
+
"postcode": "6001",
|
|
9
|
+
"region": "Anzoátegui",
|
|
10
|
+
"country": "Venezuela",
|
|
11
|
+
"cc": "VE",
|
|
12
|
+
"locale": "es-VE",
|
|
13
|
+
"postcodePlacement": "after_locality",
|
|
14
|
+
"provenance": {
|
|
15
|
+
"publisher": "Gobierno del Estado Anzoátegui",
|
|
16
|
+
"url": "https://anzoategui.gob.ve/contacto/",
|
|
17
|
+
"retrievedAt": "2026-08-24",
|
|
18
|
+
"reviewStatus": "reviewed",
|
|
19
|
+
"sourceLicenseNote": "Factual address fields only; the source page does not state a reusable data license."
|
|
20
|
+
}
|
|
21
|
+
},
|
|
22
|
+
{
|
|
23
|
+
"id": "ve-caracas-1010-distrito-capital",
|
|
24
|
+
"locality": "Caracas",
|
|
25
|
+
"postcode": "1010",
|
|
26
|
+
"region": "Distrito Capital",
|
|
27
|
+
"country": "Venezuela",
|
|
28
|
+
"cc": "VE",
|
|
29
|
+
"locale": "es-VE",
|
|
30
|
+
"postcodePlacement": "after_locality",
|
|
31
|
+
"provenance": {
|
|
32
|
+
"publisher": "Universal Postal Union",
|
|
33
|
+
"url": "https://www.upu.int/UPU/media/upu/PostalEntitiesFiles/addressingUnit/venEn.pdf",
|
|
34
|
+
"retrievedAt": "2026-08-24",
|
|
35
|
+
"reviewStatus": "reviewed",
|
|
36
|
+
"sourceLicenseNote": "Factual postal fields only; no source prose is reproduced."
|
|
37
|
+
}
|
|
38
|
+
},
|
|
39
|
+
{
|
|
40
|
+
"id": "ve-sanare-3028-lara",
|
|
41
|
+
"locality": "Sanare",
|
|
42
|
+
"postcode": "3028",
|
|
43
|
+
"region": "Lara",
|
|
44
|
+
"country": "Venezuela",
|
|
45
|
+
"cc": "VE",
|
|
46
|
+
"locale": "es-VE",
|
|
47
|
+
"postcodePlacement": "after_locality",
|
|
48
|
+
"provenance": {
|
|
49
|
+
"publisher": "Universal Postal Union",
|
|
50
|
+
"url": "https://www.upu.int/UPU/media/upu/PostalEntitiesFiles/addressingUnit/venEn.pdf",
|
|
51
|
+
"retrievedAt": "2026-08-24",
|
|
52
|
+
"reviewStatus": "reviewed",
|
|
53
|
+
"sourceLicenseNote": "Factual postal fields only; no source prose is reproduced."
|
|
54
|
+
}
|
|
55
|
+
},
|
|
56
|
+
{
|
|
57
|
+
"id": "ve-santa-elena-8011-bolivar",
|
|
58
|
+
"locality": "Santa Elena de Guairén",
|
|
59
|
+
"postcode": "8011",
|
|
60
|
+
"region": "Bolívar",
|
|
61
|
+
"country": "Venezuela",
|
|
62
|
+
"cc": "VE",
|
|
63
|
+
"locale": "es-VE",
|
|
64
|
+
"postcodePlacement": "after_locality",
|
|
65
|
+
"provenance": {
|
|
66
|
+
"publisher": "Universal Postal Union",
|
|
67
|
+
"url": "https://www.upu.int/UPU/media/upu/PostalEntitiesFiles/addressingUnit/venEn.pdf",
|
|
68
|
+
"retrievedAt": "2026-08-24",
|
|
69
|
+
"reviewStatus": "reviewed",
|
|
70
|
+
"sourceLicenseNote": "Factual postal fields only; no source prose is reproduced."
|
|
71
|
+
}
|
|
72
|
+
}
|
|
73
|
+
]
|
|
74
|
+
}
|
|
@@ -30,7 +30,7 @@
|
|
|
30
30
|
* `opts.signal` for cancellation, and `opts.country` for a self-consistency check (errors if
|
|
31
31
|
* country !== FR).
|
|
32
32
|
*/
|
|
33
|
-
import type { CorpusAdapter } from "
|
|
33
|
+
import type { CorpusAdapter } from "#types";
|
|
34
34
|
/**
|
|
35
35
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
36
36
|
* it came from.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/ban/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA+BG;
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/ban/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA+BG;AAOH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,QAAQ,CAAA;AAIzE;;;GAGG;AACH,eAAO,MAAM,cAAc,QAAQ,CAAA;AAsDnC,wBAAgB,gBAAgB,IAAI,aAAa,CAqFhD;AAED;;GAEG;AACH,eAAO,MAAM,UAAU,eAAqB,CAAA"}
|
|
@@ -30,9 +30,10 @@
|
|
|
30
30
|
* `opts.signal` for cancellation, and `opts.country` for a self-consistency check (errors if
|
|
31
31
|
* country !== FR).
|
|
32
32
|
*/
|
|
33
|
-
import {
|
|
33
|
+
import { isPresent } from "@mailwoman/core/objects";
|
|
34
34
|
import { reconcileComponents } from "@mailwoman/formatter";
|
|
35
35
|
import { CSVSpliterator } from "spliterator";
|
|
36
|
+
import { stableSourceID } from "#adapters/utils";
|
|
36
37
|
import { decomposeFrStreet } from "./street-decompose.js";
|
|
37
38
|
/**
|
|
38
39
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
@@ -61,11 +62,11 @@ function composeHouseNumber(numero, rep) {
|
|
|
61
62
|
*/
|
|
62
63
|
function composeRaw(house, street, postcode, locality) {
|
|
63
64
|
const parts = [];
|
|
64
|
-
const streetPart = [house, street].filter(
|
|
65
|
+
const streetPart = [house, street].filter(isPresent).join(" ").trim();
|
|
65
66
|
if (streetPart) {
|
|
66
67
|
parts.push(streetPart);
|
|
67
68
|
}
|
|
68
|
-
const cityPart = [postcode, locality].filter(
|
|
69
|
+
const cityPart = [postcode, locality].filter(isPresent).join(" ").trim();
|
|
69
70
|
if (cityPart) {
|
|
70
71
|
parts.push(cityPart);
|
|
71
72
|
}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/ban/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA+BG;AAEH,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/ban/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA+BG;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,cAAc,EAAE,MAAM,iBAAiB,CAAA;AAGhD,OAAO,EAAE,iBAAiB,EAAE,MAAM,uBAAuB,CAAA;AAEzD;;;GAGG;AACH,MAAM,CAAC,MAAM,cAAc,GAAG,KAAK,CAAA;AAenC;;;GAGG;AACH,SAAS,kBAAkB,CAAC,MAAc,EAAE,GAAW;IACtD,MAAM,CAAC,GAAG,MAAM,CAAC,IAAI,EAAE,CAAA;IACvB,MAAM,CAAC,GAAG,GAAG,CAAC,IAAI,EAAE,CAAA;IAEpB,IAAI,CAAC,CAAC;QAAE,OAAO,EAAE,CAAA;IAEjB,OAAO,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,CAAA;AAC3B,CAAC;AAED;;;;;;;;GAQG;AACH,SAAS,UAAU,CAAC,KAAa,EAAE,MAAc,EAAE,QAAgB,EAAE,QAAgB;IACpF,MAAM,KAAK,GAAa,EAAE,CAAA;IAC1B,MAAM,UAAU,GAAG,CAAC,KAAK,EAAE,MAAM,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;IAErE,IAAI,UAAU,EAAE,CAAC;QAChB,KAAK,CAAC,IAAI,CAAC,UAAU,CAAC,CAAA;IACvB,CAAC;IAED,MAAM,QAAQ,GAAG,CAAC,QAAQ,EAAE,QAAQ,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;IAExE,IAAI,QAAQ,EAAE,CAAC;QACd,KAAK,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAA;IACrB,CAAC;IAED,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,UAAU,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;AACvD,CAAC;AAED,MAAM,UAAU,gBAAgB;IAC/B,OAAO;QACN,EAAE,EAAE,cAAc;QAClB,cAAc,EAAE,qBAAqB;QACrC,WAAW,EAAE,+EAA+E;QAE5F,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,+CAA+C,IAAI,CAAC,OAAO,EAAE,CAAC,CAAA;YAC/E,CAAC;YAED,MAAM,IAAI,GAAG,cAAc,CAAC,SAAS,CAAC,IAAI,CAAC,SAAS,EAAE;gBACrD,IAAI,EAAE,QAAQ;gBACd,aAAa,EAAE,KAAK;gBACpB,eAAe,EAAE,GAAG;gBACpB,mBAAmB,EAAE,IAAI;aACzB,CAAC,CAAA;YAEF,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,KAAK,EAAE,MAAM,MAAM,IAAI,IAA6B,EAAE,CAAC;gBAC1D,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,kBAAkB,CAAC,MAAM,CAAC,MAAM,IAAI,EAAE,EAAE,MAAM,CAAC,GAAG,IAAI,EAAE,CAAC,CAAA;gBACvE,MAAM,MAAM,GAAG,CAAC,MAAM,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAC7C,MAAM,QAAQ,GAAG,CAAC,MAAM,CAAC,WAAW,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAClD,MAAM,QAAQ,GAAG,CAAC,MAAM,CAAC,WAAW,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAElD,IAAI,CAAC,MAAM,IAAI,CAAC,QAAQ;oBAAE,SAAQ;gBAElC,IAAI,CAAC,KAAK,IAAI,CAAC,QAAQ;oBAAE,SAAQ;gBAEjC,MAAM,UAAU,GAAG,iBAAiB,CAAC,MAAM,CAAC,CAAA;gBAE5C,MAAM,UAAU,GAA+B,EAAE,CAAA;gBAEjD,IAAI,KAAK,EAAE,CAAC;oBACX,UAAU,CAAC,YAAY,GAAG,KAAK,CAAA;gBAChC,CAAC;gBAED,IAAI,UAAU,CAAC,MAAM,EAAE,CAAC;oBACvB,UAAU,CAAC,aAAa,GAAG,UAAU,CAAC,MAAM,CAAA;gBAC7C,CAAC;gBAED,IAAI,UAAU,CAAC,MAAM,EAAE,CAAC;oBACvB,UAAU,CAAC,MAAM,GAAG,UAAU,CAAC,MAAM,CAAA;gBACtC,CAAC;gBAED,IAAI,QAAQ,EAAE,CAAC;oBACd,UAAU,CAAC,QAAQ,GAAG,QAAQ,CAAA;gBAC/B,CAAC;gBAED,IAAI,QAAQ,EAAE,CAAC;oBACd,UAAU,CAAC,QAAQ,GAAG,QAAQ,CAAA;gBAC/B,CAAC;gBAED,MAAM,GAAG,GAAG,UAAU,CAAC,KAAK,EAAE,MAAM,EAAE,QAAQ,EAAE,QAAQ,CAAC,CAAA;gBAEzD,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,QAAQ,GAAG,MAAM,CAAC,EAAE,EAAE,IAAI,EAAE;oBACjC,CAAC,CAAC,GAAG,cAAc,IAAI,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,EAAE;oBACzC,CAAC,CAAC,cAAc,CAAC,cAAc,EAAE,OAAO,CAAC,CAAA;gBAE1C,MAAM;oBACL,GAAG;oBACH,UAAU,EAAE,OAAO;oBACnB,OAAO,EAAE,IAAI;oBACb,MAAM,EAAE,OAAO;oBACf,MAAM,EAAE,cAAc;oBACtB,SAAS,EAAE,QAAQ;oBACnB,cAAc,EAAE,EAAE;oBAClB,OAAO,EAAE,qBAAqB;iBAC9B,CAAA;gBAED,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,UAAU,GAAG,gBAAgB,EAAE,CAAA"}
|
|
@@ -33,7 +33,7 @@
|
|
|
33
33
|
* The CostQuest Fabric source data has its own license; consumers who substitute that path should
|
|
34
34
|
* re-stamp accordingly.
|
|
35
35
|
*/
|
|
36
|
-
import type { CorpusAdapter } from "
|
|
36
|
+
import type { CorpusAdapter } from "#types";
|
|
37
37
|
/**
|
|
38
38
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
39
39
|
* it came from.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/fcc-bdc/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAkCG;
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/fcc-bdc/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAkCG;AAQH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,QAAQ,CAAA;AAEzE;;;GAGG;AACH,eAAO,MAAM,kBAAkB,YAAY,CAAA;AAC3C;;;GAGG;AACH,eAAO,MAAM,uBAAuB,kBAAkB,CAAA;AActD;;;;;;;;;;;GAWG;AACH,wBAAgB,aAAa,CAAC,GAAG,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,GAAG,IAAI,GAAG,MAAM,CAWxE;AAED;;GAEG;AACH,wBAAgB,mBAAmB,IAAI,aAAa,CAyEnD;AAED;;GAEG;AACH,eAAO,MAAM,aAAa,eAAwB,CAAA"}
|
|
@@ -34,9 +34,9 @@
|
|
|
34
34
|
* re-stamp accordingly.
|
|
35
35
|
*/
|
|
36
36
|
import { DatabaseSync } from "node:sqlite";
|
|
37
|
-
import { splitStreetLine } from "@mailwoman/corpus/adapters/utils";
|
|
38
|
-
import { lookupStateAbbreviation } from "@mailwoman/corpus/codex/us-fips-state";
|
|
39
37
|
import { formatAddress, reconcileComponents } from "@mailwoman/formatter";
|
|
38
|
+
import { splitStreetLine } from "#adapters/utils";
|
|
39
|
+
import { lookupStateAbbreviation } from "#codex/us-fips-state";
|
|
40
40
|
/**
|
|
41
41
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
42
42
|
* it came from.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/fcc-bdc/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAkCG;AAEH,OAAO,EAAE,YAAY,EAAE,MAAM,aAAa,CAAA;AAE1C,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/fcc-bdc/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAkCG;AAEH,OAAO,EAAE,YAAY,EAAE,MAAM,aAAa,CAAA;AAE1C,OAAO,EAAE,aAAa,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AAEzE,OAAO,EAAE,eAAe,EAAE,MAAM,iBAAiB,CAAA;AACjD,OAAO,EAAE,uBAAuB,EAAE,MAAM,sBAAsB,CAAA;AAG9D;;;GAGG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAAG,SAAS,CAAA;AAC3C;;;GAGG;AACH,MAAM,CAAC,MAAM,uBAAuB,GAAG,eAAe,CAAA;AActD;;;;;;;;;;;GAWG;AACH,MAAM,UAAU,aAAa,CAAC,GAAW,EAAE,MAAqB;IAC/D,MAAM,CAAC,GAAG,GAAG,CAAC,IAAI,EAAE,CAAA;IAEpB,IAAI,CAAC,CAAC;QAAE,OAAO,EAAE,CAAA;IACjB,MAAM,CAAC,GAAG,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;IAE9B,IAAI,CAAC,CAAC;QAAE,OAAO,CAAC,CAAA;IAEhB,IAAI,CAAC,CAAC,QAAQ,CAAC,GAAG,CAAC;QAAE,OAAO,CAAC,CAAA;IAE7B,OAAO,GAAG,CAAC,IAAI,CAAC,EAAE,CAAA;AACnB,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,mBAAmB;IAClC,OAAO;QACN,EAAE,EAAE,kBAAkB;QACtB,cAAc,EAAE,uBAAuB;QACvC,WAAW,EACV,wIAAwI;QAEzI,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,mDAAmD,IAAI,CAAC,OAAO,EAAE,CAAC,CAAA;YACnF,CAAC;YAED,MAAM,EAAE,GAAG,IAAI,YAAY,CAAC,IAAI,CAAC,SAAS,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,CAAA;YAC/D,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,CAAC;gBACJ,MAAM,IAAI,GAAG,EAAE,CAAC,OAAO,CACtB;;2BAEsB,CACtB,CAAA;gBAED,KAAK,MAAM,GAAG,IAAI,IAAI,CAAC,OAAO,EAAsC,EAAE,CAAC;oBACtE,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;wBAAE,OAAM;oBAEhC,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;wBAAE,OAAM;oBAE7D,MAAM,KAAK,GAAG,eAAe,CAAC,GAAG,CAAC,eAAe,IAAI,EAAE,CAAC,CAAA;oBAExD,IAAI,CAAC,KAAK;wBAAE,SAAQ;oBACpB,MAAM,KAAK,GAAG,uBAAuB,CAAC,GAAG,CAAC,KAAK,CAAC,CAAA;oBAEhD,IAAI,CAAC,KAAK;wBAAE,SAAQ;oBACpB,MAAM,QAAQ,GAAG,GAAG,CAAC,IAAI,EAAE,IAAI,EAAE,CAAA;oBAEjC,IAAI,CAAC,QAAQ;wBAAE,SAAQ;oBACvB,MAAM,QAAQ,GAAG,aAAa,CAAC,GAAG,CAAC,GAAG,IAAI,EAAE,EAAE,GAAG,CAAC,UAAU,IAAI,IAAI,CAAC,CAAA;oBAErE,IAAI,CAAC,QAAQ;wBAAE,SAAQ;oBAEvB,MAAM,UAAU,GAA+B;wBAC9C,GAAG,CAAC,KAAK,CAAC,YAAY,CAAC,CAAC,CAAC,EAAE,YAAY,EAAE,KAAK,CAAC,YAAY,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;wBACnE,MAAM,EAAE,KAAK,CAAC,MAAM;wBACpB,QAAQ;wBACR,MAAM,EAAE,KAAK,CAAC,YAAY;wBAC1B,QAAQ;qBACR,CAAA;oBAED,MAAM,GAAG,GAAG,aAAa,CAAC,UAAU,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;oBAEhE,IAAI,CAAC,GAAG;wBAAE,SAAQ;oBAClB,MAAM,OAAO,GAAG,mBAAmB,CAAC,UAAU,EAAE,GAAG,CAAC,CAAA;oBAEpD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM;wBAAE,SAAQ;oBAE1C,MAAM;wBACL,GAAG;wBACH,UAAU,EAAE,OAAO;wBACnB,OAAO,EAAE,IAAI;wBACb,MAAM,EAAE,OAAO;wBACf,MAAM,EAAE,kBAAkB;wBAC1B,SAAS,EAAE,GAAG,kBAAkB,IAAI,GAAG,CAAC,WAAW,EAAE;wBACrD,cAAc,EAAE,EAAE;wBAClB,OAAO,EAAE,uBAAuB;qBAChC,CAAA;oBAED,OAAO,EAAE,CAAA;gBACV,CAAC;YACF,CAAC;oBAAS,CAAC;gBACV,EAAE,CAAC,KAAK,EAAE,CAAA;YACX,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,aAAa,GAAG,mBAAmB,EAAE,CAAA"}
|
|
@@ -27,7 +27,7 @@
|
|
|
27
27
|
*
|
|
28
28
|
* License: stamped `"CC-BY-4.0"` per row (GeoNames' terms); provenance is the `geonames-<id>` key.
|
|
29
29
|
*/
|
|
30
|
-
import type { CorpusAdapter } from "
|
|
30
|
+
import type { CorpusAdapter } from "#types";
|
|
31
31
|
/**
|
|
32
32
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
33
33
|
* it came from.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/geonames/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/geonames/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AASH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,QAAQ,CAAA;AAEzE;;;GAGG;AACH,eAAO,MAAM,mBAAmB,aAAa,CAAA;AAC7C;;;GAGG;AACH,eAAO,MAAM,wBAAwB,cAAc,CAAA;AA8DnD,wBAAgB,qBAAqB,IAAI,aAAa,CAoFrD;AAED;;GAEG;AACH,eAAO,MAAM,eAAe,eAA0B,CAAA"}
|
|
@@ -28,10 +28,10 @@
|
|
|
28
28
|
* License: stamped `"CC-BY-4.0"` per row (GeoNames' terms); provenance is the `geonames-<id>` key.
|
|
29
29
|
*/
|
|
30
30
|
import { existsSync } from "node:fs";
|
|
31
|
-
import { stableSourceID } from "@mailwoman/corpus/adapters/utils";
|
|
32
31
|
import { reconcileComponents } from "@mailwoman/formatter";
|
|
33
32
|
import { dirname, join } from "path-ts";
|
|
34
33
|
import { TSVSpliterator } from "spliterator";
|
|
34
|
+
import { stableSourceID } from "#adapters/utils";
|
|
35
35
|
/**
|
|
36
36
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
37
37
|
* it came from.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/geonames/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AAEH,OAAO,EAAE,UAAU,EAAE,MAAM,SAAS,CAAA;AAEpC,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/geonames/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AAEH,OAAO,EAAE,UAAU,EAAE,MAAM,SAAS,CAAA;AAEpC,OAAO,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AAC1D,OAAO,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,SAAS,CAAA;AACvC,OAAO,EAAE,cAAc,EAAE,MAAM,aAAa,CAAA;AAE5C,OAAO,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAA;AAGhD;;;GAGG;AACH,MAAM,CAAC,MAAM,mBAAmB,GAAG,UAAU,CAAA;AAC7C;;;GAGG;AACH,MAAM,CAAC,MAAM,wBAAwB,GAAG,WAAW,CAAA;AAEnD;;GAEG;AACH,MAAM,GAAG,GAAG;IACX,SAAS,EAAE,CAAC;IACZ,IAAI,EAAE,CAAC;IACP,cAAc,EAAE,CAAC;IACjB,YAAY,EAAE,CAAC;IACf,WAAW,EAAE,CAAC;IACd,OAAO,EAAE,CAAC;IACV,MAAM,EAAE,EAAE;CACD,CAAA;AAEV;;GAEG;AACH,MAAM,eAAe,GAAG,IAAI,GAAG,CAAC,CAAC,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,OAAO,CAAC,CAAC,CAAA;AAElE;;GAEG;AACH,KAAK,UAAU,UAAU,CAAC,GAAW;IACpC,MAAM,GAAG,GAAG,IAAI,GAAG,EAAkB,CAAA;IACrC,MAAM,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,sBAAsB,CAAC,CAAA;IAE5C,IAAI,CAAC,UAAU,CAAC,EAAE,CAAC;QAAE,OAAO,GAAG,CAAA;IAE/B,kGAAkG;IAClG,IAAI,KAAK,EAAE,MAAM,IAAI,IAAI,cAAc,CAAC,SAAS,CAAC,EAAE,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC;QAC1E,IAAI,IAAI,CAAC,CAAC,CAAC,IAAI,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC;YACxB,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,CAAC,CAAC,CAAA;QAC1B,CAAC;IACF,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC;AAED;;GAEG;AACH,KAAK,UAAU,aAAa,CAAC,GAAW;IACvC,MAAM,GAAG,GAAG,IAAI,GAAG,EAAkB,CAAA;IACrC,MAAM,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,iBAAiB,CAAC,CAAA;IAEvC,IAAI,CAAC,UAAU,CAAC,EAAE,CAAC;QAAE,OAAO,GAAG,CAAA;IAE/B,gGAAgG;IAChG,8CAA8C;IAC9C,IAAI,KAAK,EAAE,MAAM,IAAI,IAAI,cAAc,CAAC,SAAS,CAAC,EAAE,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,EAAE,CAAC;QAC1E,IAAI,IAAI,CAAC,CAAC,CAAC,EAAE,UAAU,CAAC,GAAG,CAAC;YAAE,SAAQ;QAEtC,4DAA4D;QAC5D,IAAI,IAAI,CAAC,CAAC,CAAC,IAAI,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC;YACxB,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,CAAC,CAAC,CAAA;QAC1B,CAAC;IACF,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC;AAED,MAAM,UAAU,qBAAqB;IACpC,OAAO;QACN,EAAE,EAAE,mBAAmB;QACvB,cAAc,EAAE,wBAAwB;QACxC,WAAW,EACV,0JAA0J;QAE3J,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,MAAM,GAAG,GAAG,OAAO,CAAC,IAAI,CAAC,SAAS,CAAC,CAAA;YACnC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,GAAG,CAAC,CAAA;YACpC,MAAM,SAAS,GAAG,MAAM,aAAa,CAAC,GAAG,CAAC,CAAA;YAE1C,wDAAwD;YACxD,MAAM,IAAI,GAAG,cAAc,CAAC,SAAS,CAAC,IAAI,CAAC,SAAS,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,CAAA;YAExE,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;gBAC9B,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,IAAI,GAAG,CAAC,GAAG,CAAC,YAAY,CAAC,KAAK,GAAG;oBAAE,SAAQ;gBAE3C,IAAI,eAAe,CAAC,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,WAAW,CAAC,IAAI,EAAE,CAAC;oBAAE,SAAQ;gBAE7D,MAAM,EAAE,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAE1C,IAAI,CAAC,EAAE;oBAAE,SAAQ;gBAEjB,IAAI,IAAI,CAAC,OAAO,IAAI,EAAE,KAAK,IAAI,CAAC,OAAO;oBAAE,SAAQ;gBAEjD,MAAM,QAAQ,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAE7C,IAAI,CAAC,QAAQ;oBAAE,SAAQ;gBACvB,MAAM,SAAS,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,SAAS,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBACnD,MAAM,MAAM,GAAG,MAAM,CAAC,GAAG,CAAC,GAAG,EAAE,IAAI,CAAC,GAAG,CAAC,GAAG,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAA;gBACpE,MAAM,OAAO,GAAG,SAAS,CAAC,GAAG,CAAC,EAAE,CAAC,CAAA;gBAEjC,8EAA8E;gBAC9E,6CAA6C;gBAC7C,MAAM,QAAQ,GAA2E,EAAE,CAAA;gBAE3F,IAAI,MAAM,EAAE,CAAC;oBACZ,QAAQ,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,EAAE,GAAG,EAAE,GAAG,QAAQ,KAAK,MAAM,EAAE,EAAE,CAAC,CAAA;oBAExF,IAAI,OAAO,EAAE,CAAC;wBACb,QAAQ,CAAC,IAAI,CAAC;4BACb,IAAI,EAAE,KAAK;4BACX,IAAI,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,OAAO,EAAE;4BACnC,GAAG,EAAE,GAAG,QAAQ,KAAK,MAAM,KAAK,OAAO,EAAE;yBACzC,CAAC,CAAA;oBACH,CAAC;gBACF,CAAC;qBAAM,IAAI,OAAO,EAAE,CAAC;oBACpB,QAAQ,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,EAAE,QAAQ,EAAE,OAAO,EAAE,EAAE,GAAG,EAAE,GAAG,QAAQ,KAAK,OAAO,EAAE,EAAE,CAAC,CAAA;gBAC3F,CAAC;qBAAM,CAAC;oBACP,QAAQ,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,GAAG,EAAE,IAAI,EAAE,EAAE,QAAQ,EAAE,EAAE,GAAG,EAAE,QAAQ,EAAE,CAAC,CAAA;gBAChE,CAAC;gBAED,KAAK,MAAM,CAAC,IAAI,QAAQ,EAAE,CAAC;oBAC1B,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;wBAAE,MAAK;oBAC5D,MAAM,OAAO,GAAG,mBAAmB,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,GAAG,CAAC,CAAA;oBAElD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM;wBAAE,SAAQ;oBAE1C,MAAM,QAAQ,GAAG,SAAS;wBACzB,CAAC,CAAC,GAAG,mBAAmB,IAAI,SAAS,IAAI,CAAC,CAAC,IAAI,EAAE;wBACjD,CAAC,CAAC,cAAc,CAAC,mBAAmB,EAAE,OAAO,CAAC,CAAA;oBAE/C,MAAM;wBACL,GAAG,EAAE,CAAC,CAAC,GAAG;wBACV,UAAU,EAAE,OAAO;wBACnB,OAAO,EAAE,EAAE;wBACX,MAAM,EAAE,mBAAmB;wBAC3B,SAAS,EAAE,QAAQ;wBACnB,cAAc,EAAE,EAAE;wBAClB,OAAO,EAAE,wBAAwB;qBACjC,CAAA;oBAED,OAAO,EAAE,CAAA;gBACV,CAAC;YACF,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,eAAe,GAAG,qBAAqB,EAAE,CAAA"}
|
|
@@ -22,7 +22,7 @@
|
|
|
22
22
|
* non-US countries; for US, the postcode-last sources are the right order. License:
|
|
23
23
|
* `"CC-BY-4.0"` per row (attribute "GeoNames").
|
|
24
24
|
*/
|
|
25
|
-
import type { CorpusAdapter } from "
|
|
25
|
+
import type { CorpusAdapter } from "#types";
|
|
26
26
|
/**
|
|
27
27
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
28
28
|
* it came from.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/geonames-postal/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/geonames-postal/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAMH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,QAAQ,CAAA;AAEzE;;;GAGG;AACH,eAAO,MAAM,0BAA0B,oBAAoB,CAAA;AAC3D;;;GAGG;AACH,eAAO,MAAM,+BAA+B,cAAc,CAAA;AAO1D,wBAAgB,2BAA2B,IAAI,aAAa,CAkE3D;AAED;;GAEG;AACH,eAAO,MAAM,qBAAqB,eAAgC,CAAA"}
|
|
@@ -22,9 +22,9 @@
|
|
|
22
22
|
* non-US countries; for US, the postcode-last sources are the right order. License:
|
|
23
23
|
* `"CC-BY-4.0"` per row (attribute "GeoNames").
|
|
24
24
|
*/
|
|
25
|
-
import { stableSourceID } from "@mailwoman/corpus/adapters/utils";
|
|
26
25
|
import { reconcileComponents } from "@mailwoman/formatter";
|
|
27
26
|
import { TSVSpliterator } from "spliterator";
|
|
27
|
+
import { stableSourceID } from "#adapters/utils";
|
|
28
28
|
/**
|
|
29
29
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
30
30
|
* it came from.
|
|
@@ -43,7 +43,7 @@ export function createGeonamesPostalAdapter() {
|
|
|
43
43
|
return {
|
|
44
44
|
id: GEONAMES_POSTAL_ADAPTER_ID,
|
|
45
45
|
defaultLicense: GEONAMES_POSTAL_DEFAULT_LICENSE,
|
|
46
|
-
description: "GeoNames
|
|
46
|
+
description: "GeoNames postcodes (CC-BY-4.0) — multi-locale postcode→locality→region, names inline; international postcode-first order.",
|
|
47
47
|
async *rows(opts) {
|
|
48
48
|
// `header: false` — the GeoNames postal dump is headerless, and the spliterator would
|
|
49
49
|
// otherwise consume row 1 as column names and lose its first postcode.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/geonames-postal/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAEH,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/geonames-postal/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAEH,OAAO,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AAC1D,OAAO,EAAE,cAAc,EAAE,MAAM,aAAa,CAAA;AAE5C,OAAO,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAA;AAGhD;;;GAGG;AACH,MAAM,CAAC,MAAM,0BAA0B,GAAG,iBAAiB,CAAA;AAC3D;;;GAGG;AACH,MAAM,CAAC,MAAM,+BAA+B,GAAG,WAAW,CAAA;AAE1D;;GAEG;AACH,MAAM,GAAG,GAAG,EAAE,OAAO,EAAE,CAAC,EAAE,QAAQ,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,UAAU,EAAE,CAAC,EAAW,CAAA;AAEzE,MAAM,UAAU,2BAA2B;IAC1C,OAAO;QACN,EAAE,EAAE,0BAA0B;QAC9B,cAAc,EAAE,+BAA+B;QAC/C,WAAW,EACV,2HAA2H;QAE5H,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,sFAAsF;YACtF,uEAAuE;YACvE,MAAM,IAAI,GAAG,cAAc,CAAC,SAAS,CAAC,IAAI,CAAC,SAAS,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,CAAA;YAExE,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,IAA+B,EAAE,CAAC;gBACzD,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,EAAE,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAE1C,IAAI,CAAC,EAAE;oBAAE,SAAQ;gBAEjB,IAAI,IAAI,CAAC,OAAO,IAAI,EAAE,KAAK,IAAI,CAAC,OAAO;oBAAE,SAAQ;gBAEjD,MAAM,QAAQ,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBACjD,MAAM,QAAQ,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAE9C,IAAI,CAAC,QAAQ,IAAI,CAAC,QAAQ;oBAAE,SAAQ;gBACpC,MAAM,MAAM,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,UAAU,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAEjD,oFAAoF;gBACpF,iFAAiF;gBACjF,MAAM,QAAQ,GAA2E;oBACxF,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,EAAE,QAAQ,EAAE,QAAQ,EAAE,EAAE,GAAG,EAAE,GAAG,QAAQ,IAAI,QAAQ,EAAE,EAAE;iBAC5E,CAAA;gBAED,IAAI,MAAM,IAAI,MAAM,CAAC,WAAW,EAAE,KAAK,QAAQ,CAAC,WAAW,EAAE,EAAE,CAAC;oBAC/D,QAAQ,CAAC,IAAI,CAAC;wBACb,IAAI,EAAE,KAAK;wBACX,IAAI,EAAE,EAAE,QAAQ,EAAE,QAAQ,EAAE,MAAM,EAAE;wBACpC,GAAG,EAAE,GAAG,QAAQ,IAAI,QAAQ,KAAK,MAAM,EAAE;qBACzC,CAAC,CAAA;gBACH,CAAC;gBAED,KAAK,MAAM,CAAC,IAAI,QAAQ,EAAE,CAAC;oBAC1B,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;wBAAE,MAAK;oBAC5D,MAAM,OAAO,GAAG,mBAAmB,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,GAAG,CAAC,CAAA;oBAElD,IAAI,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM,GAAG,CAAC;wBAAE,SAAQ;oBAE7C,MAAM;wBACL,GAAG,EAAE,CAAC,CAAC,GAAG;wBACV,UAAU,EAAE,OAAO;wBACnB,OAAO,EAAE,EAAE;wBACX,MAAM,EAAE,0BAA0B;wBAClC,SAAS,EAAE,GAAG,cAAc,CAAC,0BAA0B,EAAE,OAAO,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE;wBAC7E,cAAc,EAAE,EAAE;wBAClB,OAAO,EAAE,+BAA+B;qBACxC,CAAA;oBAED,OAAO,EAAE,CAAA;gBACV,CAAC;YACF,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,qBAAqB,GAAG,2BAA2B,EAAE,CAAA"}
|
|
@@ -27,7 +27,7 @@
|
|
|
27
27
|
* Input: the assembled component JSONL (one `{house_number,street,locality,region,postcode}` per
|
|
28
28
|
* line). Open G-NAF licence — attribute "Geoscape Australia".
|
|
29
29
|
*/
|
|
30
|
-
import type { CorpusAdapter } from "
|
|
30
|
+
import type { CorpusAdapter } from "#types";
|
|
31
31
|
/**
|
|
32
32
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
33
33
|
* it came from.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/gnaf/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/gnaf/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AAOH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,QAAQ,CAAA;AAEzE;;;GAGG;AACH,eAAO,MAAM,eAAe,SAAS,CAAA;AACrC;;GAEG;AACH,eAAO,MAAM,oBAAoB,cAAc,CAAA;AA4B/C;;;GAGG;AACH,wBAAgB,iBAAiB,IAAI,aAAa,CAkEjD;AAED;;GAEG;AACH,eAAO,MAAM,WAAW,eAAsB,CAAA"}
|
|
@@ -28,9 +28,9 @@
|
|
|
28
28
|
* line). Open G-NAF licence — attribute "Geoscape Australia".
|
|
29
29
|
*/
|
|
30
30
|
import { tryParsingJSON } from "@mailwoman/core/objects";
|
|
31
|
-
import { stableSourceID } from "@mailwoman/corpus/adapters/utils";
|
|
32
31
|
import { reconcileComponents } from "@mailwoman/formatter";
|
|
33
32
|
import { TextSpliterator } from "spliterator";
|
|
33
|
+
import { stableSourceID } from "#adapters/utils";
|
|
34
34
|
/**
|
|
35
35
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
36
36
|
* it came from.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/gnaf/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AAEH,OAAO,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAA;AACxD,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/gnaf/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AAEH,OAAO,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAA;AACxD,OAAO,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AAC1D,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C,OAAO,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAA;AAGhD;;;GAGG;AACH,MAAM,CAAC,MAAM,eAAe,GAAG,MAAM,CAAA;AACrC;;GAEG;AACH,MAAM,CAAC,MAAM,oBAAoB,GAAG,WAAW,CAAA;AAU/C;;;;GAIG;AACH,SAAS,YAAY,CAAC,CAAY;IACjC,MAAM,MAAM,GAAG,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;IAE7C,OAAO;QACN,yGAAyG;QACzG,GAAG,CAAC,CAAC,YAAY,IAAI,CAAC,CAAC,MAAM,KAAK,CAAC,CAAC,QAAQ,GAAG,MAAM,IAAI,CAAC,CAAC,QAAQ,EAAE;QACrE,yEAAyE;QACzE,GAAG,CAAC,CAAC,QAAQ,IAAI,CAAC,CAAC,QAAQ,KAAK,CAAC,CAAC,MAAM,IAAI,CAAC,CAAC,YAAY,EAAE;QAC5D,mDAAmD;QACnD,GAAG,CAAC,CAAC,QAAQ,KAAK,CAAC,CAAC,QAAQ,KAAK,CAAC,CAAC,MAAM,IAAI,CAAC,CAAC,YAAY,EAAE;KAC7D,CAAA;AACF,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,iBAAiB;IAChC,OAAO;QACN,EAAE,EAAE,eAAe;QACnB,cAAc,EAAE,oBAAoB;QACpC,WAAW,EACV,4KAA4K;QAE7K,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,IAAI,OAAO,GAAG,CAAC,CAAA;YACf,IAAI,GAAG,GAAG,CAAC,CAAA;YAEX,gGAAgG;YAChG,kGAAkG;YAClG,qGAAqG;YACrG,gEAAgE;YAChE,IAAI,KAAK,EAAE,MAAM,IAAI,IAAI,eAAe,CAAC,SAAS,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,CAAC;gBACpE,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,IAAI,CAAC,IAAI,CAAC,IAAI,EAAE;oBAAE,SAAQ;gBAE1B,MAAM,CAAC,GAAG,cAAc,CAAY,IAAI,CAAC,CAAA;gBAEzC,IAAI,CAAC,KAAK,IAAI;oBAAE,SAAQ;gBAExB,IAAI,CAAC,CAAC,CAAC,YAAY,IAAI,CAAC,CAAC,CAAC,MAAM,IAAI,CAAC,CAAC,CAAC,QAAQ,IAAI,CAAC,CAAC,CAAC,QAAQ;oBAAE,SAAQ;gBAExE,MAAM,MAAM,GAAG,YAAY,CAAC,CAAC,CAAC,CAAA;gBAC9B,MAAM,KAAK,GAAG,GAAG,GAAG,MAAM,CAAC,MAAM,CAAA;gBAEjC,GAAG,EAAE,CAAA;gBACL,MAAM,GAAG,GAAG,MAAM,CAAC,KAAK,CAAE,CAAA;gBAE1B,MAAM,UAAU,GAA+B;oBAC9C,YAAY,EAAE,CAAC,CAAC,YAAY;oBAC5B,MAAM,EAAE,CAAC,CAAC,MAAM;oBAChB,QAAQ,EAAE,CAAC,CAAC,QAAQ;oBACpB,QAAQ,EAAE,CAAC,CAAC,QAAQ;iBACpB,CAAA;gBAED,yFAAyF;gBACzF,qFAAqF;gBACrF,IAAI,KAAK,KAAK,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,CAAC;oBAC7B,UAAU,CAAC,MAAM,GAAG,CAAC,CAAC,MAAM,CAAA;gBAC7B,CAAC;gBAED,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;oBACL,GAAG;oBACH,UAAU,EAAE,OAAO;oBACnB,OAAO,EAAE,IAAI;oBACb,MAAM,EAAE,OAAO;oBACf,MAAM,EAAE,eAAe;oBACvB,SAAS,EAAE,GAAG,cAAc,CAAC,eAAe,EAAE,OAAO,CAAC,KAAK,KAAK,EAAE;oBAClE,cAAc,EAAE,EAAE;oBAClB,OAAO,EAAE,oBAAoB;iBAC7B,CAAA;gBAED,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,WAAW,GAAG,iBAAiB,EAAE,CAAA"}
|
|
@@ -18,7 +18,7 @@
|
|
|
18
18
|
* JSON-bundle pivot (`./wof-admin-json/` and `./wof-postalcode-json/` directories hold the
|
|
19
19
|
* implementations; the registered ids are unchanged).
|
|
20
20
|
*/
|
|
21
|
-
import type { CorpusAdapter } from "
|
|
21
|
+
import type { CorpusAdapter } from "#types";
|
|
22
22
|
/**
|
|
23
23
|
* Built-in adapters. Order is significant: `corpus build` iterates this list to drive every adapter in turn.
|
|
24
24
|
* Coarse-first (admin → postcode), then street-level (BAN FR, TIGER US, OpenAddresses global), then adversarial-source
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/adapters/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;GAmBG;AAGH,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,
|
|
1
|
+
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/adapters/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;GAmBG;AAGH,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,QAAQ,CAAA;AAsB3C;;;;;;;;;GASG;AACH,eAAO,MAAM,gBAAgB,EAAE,SAAS,aAAa,EAoBpD,CAAA;AAQD,OAAO,EAAE,cAAc,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAA;AAC7D,OAAO,EAAE,kBAAkB,EAAE,uBAAuB,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAA;AAEjG,OAAO,EACN,0BAA0B,EAC1B,+BAA+B,EAC/B,qBAAqB,GACrB,MAAM,8BAA8B,CAAA;AAErC,OAAO,EAAE,mBAAmB,EAAE,wBAAwB,EAAE,eAAe,EAAE,MAAM,uBAAuB,CAAA;AAEtG,OAAO,EACN,wBAAwB,EACxB,6BAA6B,EAC7B,oBAAoB,GACpB,MAAM,4BAA4B,CAAA;AAEnC,OAAO,EACN,2BAA2B,EAC3B,gCAAgC,EAChC,qBAAqB,GACrB,MAAM,+BAA+B,CAAA;AAEtC,OAAO,EACN,+BAA+B,EAC/B,oCAAoC,EACpC,yBAAyB,GACzB,MAAM,mCAAmC,CAAA;AAE1C,OAAO,EACN,4BAA4B,EAC5B,iCAAiC,EACjC,sBAAsB,GACtB,MAAM,gCAAgC,CAAA;AAEvC,OAAO,EACN,4BAA4B,EAC5B,iCAAiC,EACjC,sBAAsB,GACtB,MAAM,gCAAgC,CAAA;AAEvC,OAAO,EAAE,gBAAgB,EAAE,qBAAqB,EAAE,YAAY,EAAE,MAAM,oBAAoB,CAAA;AAE1F,OAAO,EACN,0BAA0B,EAC1B,+BAA+B,EAC/B,oBAAoB,GACpB,MAAM,8BAA8B,CAAA;AAErC,OAAO,EACN,yBAAyB,EACzB,8BAA8B,EAC9B,mBAAmB,GACnB,MAAM,6BAA6B,CAAA;AAEpC,OAAO,EAAE,wBAAwB,EAAE,6BAA6B,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAA;AACxH,OAAO,EAAE,oBAAoB,EAAE,yBAAyB,EAAE,eAAe,EAAE,MAAM,wBAAwB,CAAA;AACzG,OAAO,EAAE,sBAAsB,EAAE,2BAA2B,EAAE,iBAAiB,EAAE,MAAM,0BAA0B,CAAA;AAEjH,OAAO,EACN,uBAAuB,EACvB,4BAA4B,EAC5B,kCAAkC,GAClC,MAAM,6CAA6C,CAAA;AAEpD,OAAO,EAAE,oBAAoB,EAAE,eAAe,EAAE,MAAM,6BAA6B,CAAA;AACnF,OAAO,EAAE,yBAAyB,EAAE,oBAAoB,EAAE,MAAM,kCAAkC,CAAA"}
|
|
@@ -18,7 +18,7 @@
|
|
|
18
18
|
* JSON-bundle pivot (`./wof-admin-json/` and `./wof-postalcode-json/` directories hold the
|
|
19
19
|
* implementations; the registered ids are unchanged).
|
|
20
20
|
*/
|
|
21
|
-
import { defaultAdapterRegistry } from "
|
|
21
|
+
import { defaultAdapterRegistry } from "#adapters/utils";
|
|
22
22
|
import { banAdapter } from "./ban/adapter.js";
|
|
23
23
|
import { fccBdcAdapter } from "./fcc-bdc/adapter.js";
|
|
24
24
|
import { geonamesPostalAdapter } from "./geonames-postal/adapter.js";
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/adapters/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;GAmBG;AAEH,OAAO,EAAE,sBAAsB,EAAE,MAAM,
|
|
1
|
+
{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/adapters/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;GAmBG;AAEH,OAAO,EAAE,sBAAsB,EAAE,MAAM,iBAAiB,CAAA;AAGxD,OAAO,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAA;AAC7C,OAAO,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAA;AACpD,OAAO,EAAE,qBAAqB,EAAE,MAAM,8BAA8B,CAAA;AACpE,OAAO,EAAE,eAAe,EAAE,MAAM,uBAAuB,CAAA;AACvD,OAAO,EAAE,WAAW,EAAE,MAAM,mBAAmB,CAAA;AAC/C,OAAO,EAAE,oBAAoB,EAAE,MAAM,4BAA4B,CAAA;AACjE,OAAO,EAAE,eAAe,EAAE,MAAM,uBAAuB,CAAA;AACvD,OAAO,EAAE,qBAAqB,EAAE,MAAM,+BAA+B,CAAA;AACrE,OAAO,EAAE,yBAAyB,EAAE,MAAM,mCAAmC,CAAA;AAC7E,OAAO,EAAE,sBAAsB,EAAE,MAAM,gCAAgC,CAAA;AACvE,OAAO,EAAE,sBAAsB,EAAE,MAAM,gCAAgC,CAAA;AACvE,OAAO,EAAE,YAAY,EAAE,MAAM,oBAAoB,CAAA;AACjD,OAAO,EAAE,oBAAoB,EAAE,MAAM,8BAA8B,CAAA;AACnE,OAAO,EAAE,mBAAmB,EAAE,MAAM,6BAA6B,CAAA;AACjE,OAAO,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAA;AAC/D,OAAO,EAAE,eAAe,EAAE,MAAM,wBAAwB,CAAA;AACxD,OAAO,EAAE,iBAAiB,EAAE,MAAM,0BAA0B,CAAA;AAC5D,OAAO,EAAE,eAAe,EAAE,MAAM,6BAA6B,CAAA;AAC7D,OAAO,EAAE,oBAAoB,EAAE,MAAM,kCAAkC,CAAA;AAEvE;;;;;;;;;GASG;AACH,MAAM,CAAC,MAAM,gBAAgB,GAA6B;IACzD,eAAe;IACf,oBAAoB;IACpB,eAAe;IACf,qBAAqB;IACrB,UAAU;IACV,YAAY;IACZ,oBAAoB;IACpB,eAAe;IACf,WAAW;IACX,aAAa;IACb,oBAAoB;IACpB,iBAAiB;IACjB,eAAe;IACf,mBAAmB;IACnB,kBAAkB;IAClB,yBAAyB;IACzB,sBAAsB;IACtB,sBAAsB;IACtB,qBAAqB;CACrB,CAAA;AAED,KAAK,MAAM,OAAO,IAAI,gBAAgB,EAAE,CAAC;IACxC,IAAI,CAAC,sBAAsB,CAAC,GAAG,CAAC,OAAO,CAAC,EAAE,CAAC,EAAE,CAAC;QAC7C,sBAAsB,CAAC,QAAQ,CAAC,OAAO,CAAC,CAAA;IACzC,CAAC;AACF,CAAC;AAED,OAAO,EAAE,cAAc,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAA;AAC7D,OAAO,EAAE,kBAAkB,EAAE,uBAAuB,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAA;AAEjG,OAAO,EACN,0BAA0B,EAC1B,+BAA+B,EAC/B,qBAAqB,GACrB,MAAM,8BAA8B,CAAA;AAErC,OAAO,EAAE,mBAAmB,EAAE,wBAAwB,EAAE,eAAe,EAAE,MAAM,uBAAuB,CAAA;AAEtG,OAAO,EACN,wBAAwB,EACxB,6BAA6B,EAC7B,oBAAoB,GACpB,MAAM,4BAA4B,CAAA;AAEnC,OAAO,EACN,2BAA2B,EAC3B,gCAAgC,EAChC,qBAAqB,GACrB,MAAM,+BAA+B,CAAA;AAEtC,OAAO,EACN,+BAA+B,EAC/B,oCAAoC,EACpC,yBAAyB,GACzB,MAAM,mCAAmC,CAAA;AAE1C,OAAO,EACN,4BAA4B,EAC5B,iCAAiC,EACjC,sBAAsB,GACtB,MAAM,gCAAgC,CAAA;AAEvC,OAAO,EACN,4BAA4B,EAC5B,iCAAiC,EACjC,sBAAsB,GACtB,MAAM,gCAAgC,CAAA;AAEvC,OAAO,EAAE,gBAAgB,EAAE,qBAAqB,EAAE,YAAY,EAAE,MAAM,oBAAoB,CAAA;AAE1F,OAAO,EACN,0BAA0B,EAC1B,+BAA+B,EAC/B,oBAAoB,GACpB,MAAM,8BAA8B,CAAA;AAErC,OAAO,EACN,yBAAyB,EACzB,8BAA8B,EAC9B,mBAAmB,GACnB,MAAM,6BAA6B,CAAA;AAEpC,OAAO,EAAE,wBAAwB,EAAE,6BAA6B,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAA;AACxH,OAAO,EAAE,oBAAoB,EAAE,yBAAyB,EAAE,eAAe,EAAE,MAAM,wBAAwB,CAAA;AACzG,OAAO,EAAE,sBAAsB,EAAE,2BAA2B,EAAE,iBAAiB,EAAE,MAAM,0BAA0B,CAAA;AAEjH,OAAO,EACN,uBAAuB,EACvB,4BAA4B,EAC5B,kCAAkC,GAClC,MAAM,6CAA6C,CAAA;AAEpD,OAAO,EAAE,oBAAoB,EAAE,eAAe,EAAE,MAAM,6BAA6B,CAAA;AACnF,OAAO,EAAE,yBAAyB,EAAE,oBAAoB,EAAE,MAAM,kCAAkC,CAAA"}
|
|
@@ -35,7 +35,7 @@
|
|
|
35
35
|
* inflate alignment quarantine because postal addresses don't include it. Phase 6+ may revisit
|
|
36
36
|
* for non-US locales where district names DO appear on the envelope.
|
|
37
37
|
*/
|
|
38
|
-
import type { CorpusAdapter } from "
|
|
38
|
+
import type { CorpusAdapter } from "#types";
|
|
39
39
|
/**
|
|
40
40
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
41
41
|
* it came from.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/openaddresses/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAoCG;
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/openaddresses/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAoCG;AAOH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,QAAQ,CAAA;AAGzE;;;GAGG;AACH,eAAO,MAAM,wBAAwB,kBAAkB,CAAA;AACvD;;;GAGG;AACH,eAAO,MAAM,6BAA6B,cAAc,CAAA;AAsDxD,MAAM,WAAW,2BAA2B;IAC3C;;;OAGG;IACH,cAAc,CAAC,EAAE,MAAM,CAAA;IAEvB;;;;;OAKG;IACH,eAAe,CAAC,EAAE,OAAO,CAAA;CACzB;AAED;;;GAGG;AACH,wBAAgB,0BAA0B,CAAC,IAAI,GAAE,2BAAgC,GAAG,aAAa,CAoHhG;AAED;;GAEG;AACH,eAAO,MAAM,oBAAoB,eAA+B,CAAA"}
|
|
@@ -36,10 +36,10 @@
|
|
|
36
36
|
* for non-US locales where district names DO appear on the envelope.
|
|
37
37
|
*/
|
|
38
38
|
import { tryParsingJSON } from "@mailwoman/core/objects";
|
|
39
|
-
import { stableSourceID } from "@mailwoman/corpus/adapters/utils";
|
|
40
|
-
import { SHARE_ALIKE_PATTERN } from "@mailwoman/corpus/utils";
|
|
41
39
|
import { formatAddress, reconcileComponents } from "@mailwoman/formatter";
|
|
42
40
|
import { TextSpliterator } from "spliterator";
|
|
41
|
+
import { stableSourceID } from "#adapters/utils";
|
|
42
|
+
import { SHARE_ALIKE_PATTERN } from "#utils";
|
|
43
43
|
/**
|
|
44
44
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
45
45
|
* it came from.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/openaddresses/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAoCG;AAEH,OAAO,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAA;AACxD,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/openaddresses/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAoCG;AAEH,OAAO,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAA;AACxD,OAAO,EAAE,aAAa,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AACzE,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C,OAAO,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAA;AAEhD,OAAO,EAAE,mBAAmB,EAAE,MAAM,QAAQ,CAAA;AAE5C;;;GAGG;AACH,MAAM,CAAC,MAAM,wBAAwB,GAAG,eAAe,CAAA;AACvD;;;GAGG;AACH,MAAM,CAAC,MAAM,6BAA6B,GAAG,WAAW,CAAA;AAmBxD;;GAEG;AACH,SAAS,mBAAmB,CAAC,GAAY;IACxC,IAAI,CAAC,GAAG,IAAI,OAAO,GAAG,KAAK,QAAQ;QAAE,OAAO,EAAE,CAAA;IAC9C,MAAM,GAAG,GAA2B,EAAE,CAAA;IAEtC,KAAK,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,GAA8B,CAAC,EAAE,CAAC;QACrE,IAAI,OAAO,CAAC,KAAK,QAAQ,EAAE,CAAC;YAC3B,GAAG,CAAC,CAAC,CAAC,WAAW,EAAE,CAAC,GAAG,CAAC,CAAA;QACzB,CAAC;aAAM,IAAI,OAAO,CAAC,KAAK,QAAQ,EAAE,CAAC;YAClC,GAAG,CAAC,CAAC,CAAC,WAAW,EAAE,CAAC,GAAG,MAAM,CAAC,CAAC,CAAC,CAAA;QACjC,CAAC;IACF,CAAC;IAED,OAAO,GAAmB,CAAA;AAC3B,CAAC;AAED;;GAEG;AACH,SAAS,gBAAgB,CAAC,IAAY;IACrC,MAAM,OAAO,GAAG,IAAI,CAAC,IAAI,EAAE,CAAA;IAE3B,IAAI,CAAC,OAAO,IAAI,OAAO,CAAC,UAAU,CAAC,GAAG,CAAC;QAAE,OAAO,IAAI,CAAA;IACpD,MAAM,MAAM,GAAG,cAAc,CAAC,OAAO,CAAC,CAAA;IAEtC,IAAI,CAAC,MAAM,IAAI,OAAO,MAAM,KAAK,QAAQ;QAAE,OAAO,IAAI,CAAA;IACtD,MAAM,GAAG,GAAG,MAAiD,CAAA;IAE7D,IAAI,GAAG,CAAC,IAAI,KAAK,SAAS;QAAE,OAAO,IAAI,CAAA;IAEvC,OAAO,mBAAmB,CAAC,GAAG,CAAC,UAAU,CAAC,CAAA;AAC3C,CAAC;AAkBD;;;GAGG;AACH,MAAM,UAAU,0BAA0B,CAAC,OAAoC,EAAE;IAChF,MAAM,cAAc,GAAG,IAAI,CAAC,cAAc,IAAI,6BAA6B,CAAA;IAC3E,MAAM,eAAe,GAAG,IAAI,CAAC,eAAe,IAAI,IAAI,CAAA;IAEpD,OAAO;QACN,EAAE,EAAE,wBAAwB;QAC5B,cAAc;QACd,WAAW,EAAE,6EAA6E;QAE1F,KAAK,CAAC,CAAC,IAAI,CAAC,WAA2B;YACtC,IAAI,CAAC,WAAW,CAAC,OAAO,EAAE,CAAC;gBAC1B,MAAM,IAAI,KAAK,CACd,0HAA0H,CAC1H,CAAA;YACF,CAAC;YAED,MAAM,OAAO,GAAG,WAAW,CAAC,OAAO,CAAA;YAEnC,qFAAqF;YACrF,yFAAyF;YACzF,kDAAkD;YAClD,MAAM,KAAK,GAAG,eAAe,CAAC,SAAS,CAAC,WAAW,CAAC,SAAS,CAAC,CAAA;YAE9D,IAAI,OAAO,GAAG,CAAC,CAAA;YACf,IAAI,iBAAiB,GAAG,CAAC,CAAA;YAEzB,IAAI,CAAC;gBACJ,IAAI,KAAK,EAAE,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;oBAChC,IAAI,WAAW,CAAC,MAAM,EAAE,OAAO;wBAAE,MAAK;oBAEtC,IAAI,WAAW,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,WAAW,CAAC,KAAK;wBAAE,MAAK;oBAE1E,MAAM,KAAK,GAAG,gBAAgB,CAAC,IAAI,CAAC,CAAA;oBAEpC,IAAI,CAAC,KAAK;wBAAE,SAAQ;oBAEpB,MAAM,WAAW,GAAG,KAAK,CAAC,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;oBAC9C,MAAM,MAAM,GAAG,KAAK,CAAC,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;oBACzC,MAAM,IAAI,GAAG,KAAK,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;oBACrC,MAAM,IAAI,GAAG,KAAK,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;oBACrC,MAAM,MAAM,GAAG,KAAK,CAAC,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;oBACzC,MAAM,QAAQ,GAAG,KAAK,CAAC,QAAQ,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;oBAE7C,iFAAiF;oBACjF,wDAAwD;oBACxD,IAAI,CAAC,MAAM;wBAAE,SAAQ;oBAErB,IAAI,CAAC,IAAI,IAAI,CAAC,QAAQ;wBAAE,SAAQ;oBAEhC,MAAM,OAAO,GAAG,CAAC,KAAK,CAAC,OAAO,EAAE,IAAI,EAAE,IAAI,cAAc,CAAC,CAAC,IAAI,EAAE,CAAA;oBAEhE,IAAI,CAAC,eAAe,IAAI,mBAAmB,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE,CAAC;wBAC3D,iBAAiB,EAAE,CAAA;wBAEnB,SAAQ;oBACT,CAAC;oBAED,MAAM,UAAU,GAA+B,EAAE,CAAA;oBAEjD,IAAI,WAAW,EAAE,CAAC;wBACjB,UAAU,CAAC,YAAY,GAAG,WAAW,CAAA;oBACtC,CAAC;oBAED,IAAI,MAAM,EAAE,CAAC;wBACZ,UAAU,CAAC,MAAM,GAAG,MAAM,CAAA;oBAC3B,CAAC;oBAED,IAAI,IAAI,EAAE,CAAC;wBACV,UAAU,CAAC,IAAI,GAAG,IAAI,CAAA;oBACvB,CAAC;oBAED,IAAI,IAAI,EAAE,CAAC;wBACV,UAAU,CAAC,QAAQ,GAAG,IAAI,CAAA;oBAC3B,CAAC;oBAED,IAAI,MAAM,EAAE,CAAC;wBACZ,UAAU,CAAC,MAAM,GAAG,MAAM,CAAA;oBAC3B,CAAC;oBAED,IAAI,QAAQ,EAAE,CAAC;wBACd,UAAU,CAAC,QAAQ,GAAG,QAAQ,CAAA;oBAC/B,CAAC;oBAED,MAAM,GAAG,GAAG,aAAa,CAAC,UAAU,EAAE,OAAO,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;oBAEnE,IAAI,CAAC,GAAG;wBAAE,SAAQ;oBAElB,MAAM,OAAO,GAAG,mBAAmB,CAAC,UAAU,EAAE,GAAG,CAAC,CAAA;oBAEpD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM;wBAAE,SAAQ;oBAE1C,MAAM,YAAY,GAAG,KAAK,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,KAAK,CAAC,EAAE,EAAE,IAAI,EAAE,CAAA;oBAE3D,MAAM,QAAQ,GAAG,YAAY;wBAC5B,CAAC,CAAC,GAAG,wBAAwB,IAAI,YAAY,EAAE;wBAC/C,CAAC,CAAC,cAAc,CAAC,wBAAwB,EAAE,OAAO,CAAC,CAAA;oBAEpD,MAAM;wBACL,GAAG;wBACH,UAAU,EAAE,OAAO;wBACnB,OAAO;wBACP,MAAM,EAAE,wBAAwB;wBAChC,SAAS,EAAE,QAAQ;wBACnB,cAAc,EAAE,EAAE;wBAClB,OAAO;qBACP,CAAA;oBAED,OAAO,EAAE,CAAA;gBACV,CAAC;YACF,CAAC;oBAAS,CAAC;gBACV,IAAI,iBAAiB,GAAG,CAAC,EAAE,CAAC;oBAC3B,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,oBAAoB,iBAAiB,8BAA8B,OAAO,SAAS,CAAC,CAAA;gBAC1G,CAAC;YACF,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,oBAAoB,GAAG,0BAA0B,EAAE,CAAA"}
|
|
@@ -29,7 +29,7 @@
|
|
|
29
29
|
* (skipped when "S-N"/"S/N" = sin número) | | `unit` | `unit` (if non-empty) | | `postcode`|
|
|
30
30
|
* `postcode` | | `locality`| `locality` (Overture address_levels municipality, or postal_city) |
|
|
31
31
|
*/
|
|
32
|
-
import type { CorpusAdapter } from "
|
|
32
|
+
import type { CorpusAdapter } from "#types";
|
|
33
33
|
/**
|
|
34
34
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
35
35
|
* it came from.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/overture/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8BG;
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/overture/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8BG;AAOH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,QAAQ,CAAA;AAEzE;;;GAGG;AACH,eAAO,MAAM,mBAAmB,aAAa,CAAA;AAC7C;;;GAGG;AACH,eAAO,MAAM,wBAAwB,wBAAwB,CAAA;AAuB7D,wBAAgB,qBAAqB,IAAI,aAAa,CAqFrD;AAED;;GAEG;AACH,eAAO,MAAM,eAAe,eAA0B,CAAA"}
|
|
@@ -30,9 +30,9 @@
|
|
|
30
30
|
* `postcode` | | `locality`| `locality` (Overture address_levels municipality, or postal_city) |
|
|
31
31
|
*/
|
|
32
32
|
import { tryParsingJSON } from "@mailwoman/core/objects";
|
|
33
|
-
import { stableSourceID } from "@mailwoman/corpus/adapters/utils";
|
|
34
33
|
import { formatAddress, reconcileComponents } from "@mailwoman/formatter";
|
|
35
34
|
import { TextSpliterator } from "spliterator";
|
|
35
|
+
import { stableSourceID } from "#adapters/utils";
|
|
36
36
|
/**
|
|
37
37
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
38
38
|
* it came from.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/overture/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8BG;AAEH,OAAO,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAA;AACxD,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/overture/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8BG;AAEH,OAAO,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAA;AACxD,OAAO,EAAE,aAAa,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AACzE,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C,OAAO,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAA;AAGhD;;;GAGG;AACH,MAAM,CAAC,MAAM,mBAAmB,GAAG,UAAU,CAAA;AAC7C;;;GAGG;AACH,MAAM,CAAC,MAAM,wBAAwB,GAAG,qBAAqB,CAAA;AAa7D,SAAS,SAAS,CAAC,IAAY;IAC9B,MAAM,CAAC,GAAG,IAAI,CAAC,IAAI,EAAE,CAAA;IAErB,IAAI,CAAC,CAAC,IAAI,CAAC,CAAC,UAAU,CAAC,GAAG,CAAC;QAAE,OAAO,IAAI,CAAA;IAExC,MAAM,CAAC,GAAG,cAAc,CAAC,CAAC,CAAC,CAAA;IAE3B,OAAO,CAAC,IAAI,OAAO,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAE,CAAuB,CAAC,CAAC,CAAC,IAAI,CAAA;AACpE,CAAC;AAED,MAAM,UAAU,qBAAqB;IACpC,OAAO;QACN,EAAE,EAAE,mBAAmB;QACvB,cAAc,EAAE,wBAAwB;QACxC,WAAW,EAAE,yFAAyF;QAEtG,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,IAAI,CAAC,IAAI,CAAC,OAAO,EAAE,CAAC;gBACnB,MAAM,IAAI,KAAK,CACd,2GAA2G,CAC3G,CAAA;YACF,CAAC;YAED,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,CAAA;YAE5B,uFAAuF;YACvF,wFAAwF;YACxF,iCAAiC;YACjC,MAAM,KAAK,GAAG,eAAe,CAAC,SAAS,CAAC,IAAI,CAAC,SAAS,CAAC,CAAA;YAEvD,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,KAAK,EAAE,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;gBAChC,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,CAAC,GAAG,SAAS,CAAC,IAAI,CAAC,CAAA;gBAEzB,IAAI,CAAC,CAAC;oBAAE,SAAQ;gBAEhB,MAAM,MAAM,GAAG,CAAC,CAAC,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;gBACrC,MAAM,MAAM,GAAG,CAAC,CAAC,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;gBACrC,MAAM,IAAI,GAAG,CAAC,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;gBACjC,MAAM,QAAQ,GAAG,CAAC,CAAC,QAAQ,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;gBACzC,MAAM,QAAQ,GAAG,CAAC,CAAC,QAAQ,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;gBAEzC,yFAAyF;gBACzF,IAAI,CAAC,MAAM;oBAAE,SAAQ;gBAErB,IAAI,CAAC,QAAQ,IAAI,CAAC,QAAQ;oBAAE,SAAQ;gBAEpC,MAAM,UAAU,GAA+B,EAAE,CAAA;gBAEjD,8EAA8E;gBAC9E,IAAI,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,EAAE,CAAC;oBACxB,UAAU,CAAC,YAAY,GAAG,MAAM,CAAA;gBACjC,CAAC;gBAED,UAAU,CAAC,MAAM,GAAG,MAAM,CAAA;gBAE1B,IAAI,IAAI,EAAE,CAAC;oBACV,UAAU,CAAC,IAAI,GAAG,IAAI,CAAA;gBACvB,CAAC;gBAED,IAAI,QAAQ,EAAE,CAAC;oBACd,UAAU,CAAC,QAAQ,GAAG,QAAQ,CAAA;gBAC/B,CAAC;gBAED,IAAI,QAAQ,EAAE,CAAC;oBACd,UAAU,CAAC,QAAQ,GAAG,QAAQ,CAAA;gBAC/B,CAAC;gBAED,MAAM,GAAG,GAAG,aAAa,CAAC,UAAU,EAAE,OAAO,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;gBAEnE,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;oBACL,GAAG;oBACH,UAAU,EAAE,OAAO;oBACnB,OAAO;oBACP,MAAM,EAAE,mBAAmB;oBAC3B,SAAS,EAAE,cAAc,CAAC,mBAAmB,EAAE,OAAO,CAAC;oBACvD,cAAc,EAAE,EAAE;oBAClB,OAAO,EAAE,wBAAwB;iBACjC,CAAA;gBAED,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,eAAe,GAAG,qBAAqB,EAAE,CAAA"}
|
|
@@ -28,7 +28,7 @@
|
|
|
28
28
|
*
|
|
29
29
|
* License: stamped `"Public Domain"` per Hawaii state government open-data terms.
|
|
30
30
|
*/
|
|
31
|
-
import type { CorpusAdapter } from "
|
|
31
|
+
import type { CorpusAdapter } from "#types";
|
|
32
32
|
/**
|
|
33
33
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
34
34
|
* it came from.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/state-hi-schools/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA6BG;
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/state-hi-schools/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA6BG;AAQH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,QAAQ,CAAA;AAEzE;;;GAGG;AACH,eAAO,MAAM,2BAA2B,qBAAqB,CAAA;AAC7D;;;GAGG;AACH,eAAO,MAAM,gCAAgC,kBAAkB,CAAA;AAyB/D,wBAAgB,2BAA2B,IAAI,aAAa,CAqF3D;AAED;;GAEG;AACH,eAAO,MAAM,qBAAqB,eAAgC,CAAA"}
|
|
@@ -28,10 +28,11 @@
|
|
|
28
28
|
*
|
|
29
29
|
* License: stamped `"Public Domain"` per Hawaii state government open-data terms.
|
|
30
30
|
*/
|
|
31
|
-
import {
|
|
32
|
-
import { lookupStateAbbreviation } from "@mailwoman/corpus/codex/us-fips-state";
|
|
31
|
+
import { isPresent } from "@mailwoman/core/objects";
|
|
33
32
|
import { reconcileComponents } from "@mailwoman/formatter";
|
|
34
33
|
import { CSVSpliterator } from "spliterator";
|
|
34
|
+
import { splitStreetLine, stableSourceID } from "#adapters/utils";
|
|
35
|
+
import { lookupStateAbbreviation } from "#codex/us-fips-state";
|
|
35
36
|
/**
|
|
36
37
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
37
38
|
* it came from.
|
|
@@ -95,13 +96,13 @@ export function createStateHiSchoolsAdapter() {
|
|
|
95
96
|
region: state.abbreviation,
|
|
96
97
|
postcode: zip,
|
|
97
98
|
};
|
|
98
|
-
const streetPart = [split.house_number, split.street].filter(
|
|
99
|
+
const streetPart = [split.house_number, split.street].filter(isPresent).join(" ").trim();
|
|
99
100
|
const raw = [
|
|
100
101
|
name,
|
|
101
102
|
streetPart,
|
|
102
|
-
[city, [HI_STATE_ABBR, zip].filter(
|
|
103
|
+
[city, [HI_STATE_ABBR, zip].filter(isPresent).join(" ")].filter(isPresent).join(", "),
|
|
103
104
|
]
|
|
104
|
-
.filter(
|
|
105
|
+
.filter(isPresent)
|
|
105
106
|
.join(", ");
|
|
106
107
|
const aligned = reconcileComponents(components, raw);
|
|
107
108
|
if (Object.keys(aligned).length <= 2)
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/state-hi-schools/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA6BG;AAEH,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/state-hi-schools/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA6BG;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,2BAA2B,GAAG,kBAAkB,CAAA;AAC7D;;;GAGG;AACH,MAAM,CAAC,MAAM,gCAAgC,GAAG,eAAe,CAAA;AAE/D,MAAM,aAAa,GAAG,IAAI,CAAA;AAU1B,SAAS,YAAY,CAAC,GAAW;IAChC,MAAM,OAAO,GAAG,GAAG,CAAC,IAAI,EAAE,CAAA;IAE1B,IAAI,CAAC,OAAO;QAAE,OAAO,EAAE,CAAA;IAEvB,uFAAuF;IACvF,wFAAwF;IACxF,2EAA2E;IAC3E,IAAI,SAAS,CAAC,IAAI,CAAC,OAAO,CAAC;QAAE,OAAO,IAAI,OAAO,EAAE,CAAA;IAEjD,OAAO,OAAO,CAAA;AACf,CAAC;AAED,MAAM,UAAU,2BAA2B;IAC1C,OAAO;QACN,EAAE,EAAE,2BAA2B;QAC/B,cAAc,EAAE,gCAAgC;QAChD,WAAW,EAAE,sGAAsG;QAEnH,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,4DAA4D,IAAI,CAAC,OAAO,EAAE,CAAC,CAAA;YAC5F,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,MAAM,KAAK,GAAG,uBAAuB,CAAC,aAAa,CAAC,CAAA;YAEpD,IAAI,CAAC,KAAK,EAAE,CAAC;gBACZ,MAAM,IAAI,KAAK,CAAC,oEAAoE,CAAC,CAAA;YACtF,CAAC;YAED,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,IAAI,GAAG,CAAC,MAAM,CAAC,IAAI,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBACvC,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,YAAY,CAAC,MAAM,CAAC,GAAG,IAAI,EAAE,CAAC,CAAA;gBAE1C,IAAI,CAAC,IAAI,IAAI,CAAC,OAAO,IAAI,CAAC,IAAI,IAAI,CAAC,GAAG;oBAAE,SAAQ;gBAEhD,MAAM,KAAK,GAAG,eAAe,CAAC,OAAO,CAAC,CAAA;gBAEtC,IAAI,CAAC,KAAK;oBAAE,SAAQ;gBAEpB,MAAM,UAAU,GAA+B;oBAC9C,KAAK,EAAE,IAAI;oBACX,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;iBACb,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,IAAI;oBACJ,UAAU;oBACV,CAAC,IAAI,EAAE,CAAC,aAAa,EAAE,GAAG,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC;iBACrF;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,IAAI,GAAG,CAAC,MAAM,CAAC,IAAI,IAAI,EAAE,CAAC,CAAC,QAAQ,EAAE,CAAC,IAAI,EAAE,CAAA;gBAElD,MAAM,QAAQ,GAAG,IAAI;oBACpB,CAAC,CAAC,GAAG,2BAA2B,IAAI,IAAI,EAAE;oBAC1C,CAAC,CAAC,cAAc,CAAC,2BAA2B,EAAE,OAAO,CAAC,CAAA;gBAEvD,MAAM;oBACL,GAAG;oBACH,UAAU,EAAE,OAAO;oBACnB,OAAO,EAAE,IAAI;oBACb,MAAM,EAAE,OAAO;oBACf,MAAM,EAAE,2BAA2B;oBACnC,SAAS,EAAE,QAAQ;oBACnB,cAAc,EAAE,EAAE;oBAClB,OAAO,EAAE,gCAAgC;iBACzC,CAAA;gBAED,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,qBAAqB,GAAG,2BAA2B,EAAE,CAAA"}
|
|
@@ -15,7 +15,7 @@
|
|
|
15
15
|
*
|
|
16
16
|
* License: stamped `"Public Domain"` per Iowa state government open-data terms.
|
|
17
17
|
*/
|
|
18
|
-
import type { CorpusAdapter } from "
|
|
18
|
+
import type { CorpusAdapter } from "#types";
|
|
19
19
|
/**
|
|
20
20
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
21
21
|
* it came from.
|