@mailwoman/corpus 9.0.0 → 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 +3 -3
- package/data/PROVENANCE.md +227 -0
- package/data/reviewed-ve-postcode-tuples.json +74 -0
- package/data/sub-venue-lexicon.json +18269 -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 +5 -4
- 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 +3 -3
- 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 +2 -2
- 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 +3 -3
- 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 +2 -2
- package/out/src/adapters/gnaf/adapter.js.map +1 -1
- package/out/src/adapters/gnaf/assemble.js +1 -1
- package/out/src/adapters/gnaf/assemble.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 +3 -3
- 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 +2 -2
- 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 +7 -6
- 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 +12 -7
- 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 +12 -18
- 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 +12 -7
- package/out/src/adapters/state-tx-notaries/adapter.js.map +1 -1
- package/out/src/adapters/synth-po-box/adapter.d.ts +3 -3
- package/out/src/adapters/synth-po-box/adapter.d.ts.map +1 -1
- package/out/src/adapters/synth-po-box/adapter.js +3 -3
- 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 +2 -2
- 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 +7 -6
- 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 +11 -7
- 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 +6 -5
- 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 +8 -8
- 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 +10 -10
- 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 +7 -6
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -1
- package/out/src/{adapter.d.ts → adapters/utils/index.d.ts} +8 -2
- package/out/src/adapters/utils/index.d.ts.map +1 -0
- package/out/src/{adapter.js → adapters/utils/index.js} +11 -3
- package/out/src/adapters/utils/index.js.map +1 -0
- 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 -4
- package/out/src/build.d.ts.map +1 -1
- package/out/src/build.js +7 -7
- package/out/src/build.js.map +1 -1
- package/out/src/index.d.ts +3 -17
- package/out/src/index.d.ts.map +1 -1
- package/out/src/index.js +3 -17
- package/out/src/index.js.map +1 -1
- package/out/src/name-prone-us-suffixes.d.ts +12 -0
- package/out/src/name-prone-us-suffixes.d.ts.map +1 -0
- package/out/src/name-prone-us-suffixes.js +12 -0
- package/out/src/name-prone-us-suffixes.js.map +1 -0
- 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 +14 -21
- 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 +11 -20
- 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 +8 -14
- package/out/src/shard-recipes/german.js.map +1 -1
- package/out/src/shard-recipes/house-venue.d.ts.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 +8 -1
- 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 +7 -13
- package/out/src/shard-recipes/intersection.js.map +1 -1
- package/out/src/shard-recipes/locale.d.ts +5 -5
- package/out/src/shard-recipes/locale.d.ts.map +1 -1
- package/out/src/shard-recipes/locale.js +13 -20
- package/out/src/shard-recipes/locale.js.map +1 -1
- package/out/src/shard-recipes/no-street.d.ts.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 +60 -43
- 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 +51 -23
- package/out/src/shard-recipes/scaffold.d.ts.map +1 -1
- package/out/src/shard-recipes/scaffold.js +59 -23
- package/out/src/shard-recipes/scaffold.js.map +1 -1
- package/out/src/shard-recipes/street-affix.d.ts +54 -0
- package/out/src/shard-recipes/street-affix.d.ts.map +1 -1
- package/out/src/shard-recipes/street-affix.js +203 -35
- package/out/src/shard-recipes/street-affix.js.map +1 -1
- package/out/src/shard-recipes/street-bare.d.ts.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.d.ts.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 +3 -6
- package/out/src/shard-recipes/sub-venue-sources.d.ts.map +1 -1
- package/out/src/shard-recipes/sub-venue-sources.js +4 -9
- package/out/src/shard-recipes/sub-venue-sources.js.map +1 -1
- package/out/src/shard-recipes/sub-venue.d.ts +2 -2
- package/out/src/shard-recipes/sub-venue.d.ts.map +1 -1
- package/out/src/shard-recipes/sub-venue.js +7 -6
- 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 +6 -12
- package/out/src/shard-recipes/unit.js.map +1 -1
- package/out/src/{synthesize-anchor-absorption.d.ts → synthesizers/anchor-absorption.d.ts} +1 -1
- package/out/src/synthesizers/anchor-absorption.d.ts.map +1 -0
- package/out/src/{synthesize-anchor-absorption.js → synthesizers/anchor-absorption.js} +1 -1
- package/out/src/synthesizers/anchor-absorption.js.map +1 -0
- package/out/src/{synthesize-boundary-stress.d.ts → synthesizers/boundary-stress.d.ts} +3 -3
- package/out/src/synthesizers/boundary-stress.d.ts.map +1 -0
- package/out/src/{synthesize-boundary-stress.js → synthesizers/boundary-stress.js} +2 -2
- package/out/src/synthesizers/boundary-stress.js.map +1 -0
- package/out/src/{synthesize-german.d.ts → synthesizers/german.d.ts} +2 -2
- package/out/src/synthesizers/german.d.ts.map +1 -0
- package/out/src/{synthesize-german.js → synthesizers/german.js} +2 -2
- package/out/src/synthesizers/german.js.map +1 -0
- package/out/src/{synthesize-house-venue.d.ts → synthesizers/house-venue.d.ts} +4 -4
- package/out/src/synthesizers/house-venue.d.ts.map +1 -0
- package/out/src/{synthesize-house-venue.js → synthesizers/house-venue.js} +20 -6
- package/out/src/synthesizers/house-venue.js.map +1 -0
- package/out/src/{synthesize-intersection.d.ts → synthesizers/intersection.d.ts} +2 -2
- package/out/src/synthesizers/intersection.d.ts.map +1 -0
- package/out/src/{synthesize-intersection.js → synthesizers/intersection.js} +1 -1
- package/out/src/synthesizers/intersection.js.map +1 -0
- package/out/src/{synthesize-no-street.d.ts → synthesizers/no-street.d.ts} +3 -3
- package/out/src/synthesizers/no-street.d.ts.map +1 -0
- package/out/src/{synthesize-no-street.js → synthesizers/no-street.js} +2 -2
- package/out/src/synthesizers/no-street.js.map +1 -0
- package/out/src/{synthesize-po-box.d.ts → synthesizers/po-box.d.ts} +2 -2
- package/out/src/synthesizers/po-box.d.ts.map +1 -0
- package/out/src/{synthesize-po-box.js → synthesizers/po-box.js} +1 -1
- package/out/src/synthesizers/po-box.js.map +1 -0
- package/out/src/{synthesize-street.d.ts → synthesizers/street.d.ts} +2 -2
- package/out/src/synthesizers/street.d.ts.map +1 -0
- package/out/src/{synthesize-street.js → synthesizers/street.js} +4 -3
- package/out/src/synthesizers/street.js.map +1 -0
- package/out/src/{synthesize.d.ts → synthesizers/utils.d.ts} +3 -3
- package/out/src/synthesizers/utils.d.ts.map +1 -0
- package/out/src/{synthesize.js → synthesizers/utils.js} +5 -4
- package/out/src/synthesizers/utils.js.map +1 -0
- 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 +5 -17
- 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 +17 -22
- 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.d.ts.map +1 -1
- package/out/src/tools/golden-relabel-street.js +4 -77
- 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 -3
- 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 -27
- 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/{align.d.ts → utils/align.d.ts} +1 -1
- package/out/src/utils/align.d.ts.map +1 -0
- package/out/src/utils/align.js.map +1 -0
- package/out/src/utils/golden.d.ts.map +1 -0
- package/out/src/{golden.js → utils/golden.js} +2 -2
- package/out/src/utils/golden.js.map +1 -0
- package/out/src/utils/index.d.ts +14 -0
- package/out/src/utils/index.d.ts.map +1 -0
- package/out/src/utils/index.js +14 -0
- package/out/src/utils/index.js.map +1 -0
- package/out/src/utils/license.d.ts.map +1 -0
- package/out/src/{license.js → utils/license.js} +1 -1
- package/out/src/utils/license.js.map +1 -0
- package/out/src/{parquet.d.ts → utils/parquet.d.ts} +24 -5
- package/out/src/utils/parquet.d.ts.map +1 -0
- package/out/src/{parquet.js → utils/parquet.js} +6 -3
- package/out/src/utils/parquet.js.map +1 -0
- package/out/src/{split.d.ts → utils/split.d.ts} +1 -1
- package/out/src/utils/split.d.ts.map +1 -0
- package/out/src/{split.js → utils/split.js} +2 -2
- package/out/src/utils/split.js.map +1 -0
- package/out/src/utils/tokenize.d.ts.map +1 -0
- package/out/src/utils/tokenize.js.map +1 -0
- package/out/src/utils/wof-json.d.ts.map +1 -0
- package/out/src/utils/wof-json.js.map +1 -0
- package/package.json +287 -21
- package/src/adapters/ban/adapter.ts +7 -5
- package/src/adapters/fcc-bdc/adapter.ts +5 -4
- package/src/adapters/geonames/adapter.ts +3 -3
- package/src/adapters/geonames-postal/adapter.ts +4 -4
- package/src/adapters/gnaf/adapter.ts +3 -3
- package/src/adapters/gnaf/assemble.ts +1 -1
- package/src/adapters/index.ts +3 -2
- package/src/adapters/openaddresses/adapter.ts +4 -4
- package/src/adapters/overture/adapter.ts +3 -3
- package/src/adapters/state-hi-schools/adapter.ts +8 -7
- package/src/adapters/state-ia-contractors/adapter.ts +13 -8
- package/src/adapters/state-ny-notaries/adapter.ts +13 -32
- package/src/adapters/state-tx-notaries/adapter.ts +13 -8
- package/src/adapters/synth-po-box/adapter.ts +4 -4
- package/src/adapters/tiger/adapter.ts +5 -3
- package/src/adapters/usgov-hrsa-fqhc/adapter.ts +8 -7
- package/src/adapters/usgov-imls-pls/adapter.ts +12 -8
- package/src/adapters/usgov-irs-bmf/adapter.ts +7 -6
- package/src/adapters/usgov-nad/adapter.ts +9 -9
- package/src/adapters/usgov-nppes/adapter.ts +13 -12
- package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +8 -7
- package/src/{adapter.ts → adapters/utils/index.ts} +15 -3
- package/src/adapters/wof-admin-jp/adapter.ts +9 -12
- package/src/adapters/wof-admin-json/adapter.ts +15 -54
- package/src/adapters/wof-json-rows.ts +79 -0
- package/src/adapters/wof-postalcode-json/adapter.ts +16 -50
- package/src/build.ts +8 -8
- package/src/index.ts +3 -17
- package/src/name-prone-us-suffixes.ts +12 -0
- package/src/parquet-wrapper/reader.ts +9 -0
- package/src/runner.ts +2 -2
- 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 +3 -2
- package/src/shard-recipes/country-balanced.ts +16 -27
- 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 +13 -26
- package/src/shard-recipes/german.ts +9 -18
- package/src/shard-recipes/house-venue.ts +2 -1
- package/src/shard-recipes/index.ts +8 -1
- package/src/shard-recipes/intersection.ts +9 -17
- package/src/shard-recipes/locale.ts +16 -24
- package/src/shard-recipes/no-street.ts +2 -1
- package/src/shard-recipes/po-box-cedex.ts +76 -58
- package/src/shard-recipes/po-box.ts +2 -1
- package/src/shard-recipes/reviewed-postcode-tail.ts +189 -0
- package/src/shard-recipes/scaffold.ts +99 -24
- package/src/shard-recipes/street-affix.ts +284 -45
- package/src/shard-recipes/street-bare.ts +4 -3
- package/src/shard-recipes/street.ts +3 -2
- package/src/shard-recipes/sub-venue-sources.ts +13 -23
- package/src/shard-recipes/sub-venue.ts +11 -9
- package/src/shard-recipes/trailing-region.ts +183 -0
- package/src/shard-recipes/unit.ts +8 -17
- package/src/{synthesize-boundary-stress.ts → synthesizers/boundary-stress.ts} +2 -2
- package/src/{synthesize-german.ts → synthesizers/german.ts} +3 -2
- package/src/{synthesize-house-venue.ts → synthesizers/house-venue.ts} +20 -6
- package/src/{synthesize-intersection.ts → synthesizers/intersection.ts} +1 -1
- package/src/{synthesize-no-street.ts → synthesizers/no-street.ts} +2 -2
- package/src/{synthesize-po-box.ts → synthesizers/po-box.ts} +1 -1
- package/src/{synthesize-street.ts → synthesizers/street.ts} +5 -3
- package/src/{synthesize.ts → synthesizers/utils.ts} +6 -4
- 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 +6 -20
- package/src/tools/fetch/index.ts +11 -0
- package/src/tools/fetch/nad.ts +21 -10
- package/src/tools/fetch/nppes.ts +17 -23
- 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 +5 -68
- 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 +4 -5
- package/src/tools/shard-translit.ts +16 -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/{align.ts → utils/align.ts} +2 -1
- package/src/{golden.ts → utils/golden.ts} +2 -3
- package/src/utils/index.ts +14 -0
- package/src/{license.ts → utils/license.ts} +1 -1
- package/src/{parquet.ts → utils/parquet.ts} +22 -9
- package/src/{split.ts → utils/split.ts} +3 -3
- package/out/src/adapter.d.ts.map +0 -1
- package/out/src/adapter.js.map +0 -1
- package/out/src/align.d.ts.map +0 -1
- package/out/src/align.js.map +0 -1
- package/out/src/format.d.ts +0 -14
- package/out/src/format.d.ts.map +0 -1
- package/out/src/format.js +0 -14
- package/out/src/format.js.map +0 -1
- package/out/src/golden.d.ts.map +0 -1
- package/out/src/golden.js.map +0 -1
- package/out/src/license.d.ts.map +0 -1
- package/out/src/license.js.map +0 -1
- package/out/src/parquet.d.ts.map +0 -1
- package/out/src/parquet.js.map +0 -1
- package/out/src/split.d.ts.map +0 -1
- package/out/src/split.js.map +0 -1
- package/out/src/synthesize-anchor-absorption.d.ts.map +0 -1
- package/out/src/synthesize-anchor-absorption.js.map +0 -1
- package/out/src/synthesize-boundary-stress.d.ts.map +0 -1
- package/out/src/synthesize-boundary-stress.js.map +0 -1
- package/out/src/synthesize-german.d.ts.map +0 -1
- package/out/src/synthesize-german.js.map +0 -1
- package/out/src/synthesize-house-venue.d.ts.map +0 -1
- package/out/src/synthesize-house-venue.js.map +0 -1
- package/out/src/synthesize-intersection.d.ts.map +0 -1
- package/out/src/synthesize-intersection.js.map +0 -1
- package/out/src/synthesize-no-street.d.ts.map +0 -1
- package/out/src/synthesize-no-street.js.map +0 -1
- package/out/src/synthesize-po-box.d.ts.map +0 -1
- package/out/src/synthesize-po-box.js.map +0 -1
- package/out/src/synthesize-street.d.ts.map +0 -1
- package/out/src/synthesize-street.js.map +0 -1
- package/out/src/synthesize.d.ts.map +0 -1
- package/out/src/synthesize.js.map +0 -1
- package/out/src/tokenize.d.ts.map +0 -1
- package/out/src/tokenize.js.map +0 -1
- package/out/src/wof-json.d.ts.map +0 -1
- package/out/src/wof-json.js.map +0 -1
- package/src/format.ts +0 -14
- /package/out/src/{align.js → utils/align.js} +0 -0
- /package/out/src/{golden.d.ts → utils/golden.d.ts} +0 -0
- /package/out/src/{license.d.ts → utils/license.d.ts} +0 -0
- /package/out/src/{tokenize.d.ts → utils/tokenize.d.ts} +0 -0
- /package/out/src/{tokenize.js → utils/tokenize.js} +0 -0
- /package/out/src/{wof-json.d.ts → utils/wof-json.d.ts} +0 -0
- /package/out/src/{wof-json.js → utils/wof-json.js} +0 -0
- /package/src/{synthesize-anchor-absorption.ts → synthesizers/anchor-absorption.ts} +0 -0
- /package/src/{tokenize.ts → utils/tokenize.ts} +0 -0
- /package/src/{wof-json.ts → utils/wof-json.ts} +0 -0
|
@@ -0,0 +1,125 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Fetch the GeoNames per-country postal-code exports — the only source in this family that carries a
|
|
7
|
+
* `(postcode, locality, region)` triple with the NAMES inline.
|
|
8
|
+
*
|
|
9
|
+
* Source : https://download.geonames.org/export/zip/<CC>.zip
|
|
10
|
+
* License: CC-BY-4.0, attribute "GeoNames". Tier B.
|
|
11
|
+
*
|
|
12
|
+
* ## Why this source and not a join
|
|
13
|
+
*
|
|
14
|
+
* A postcode shard is only useful to the corpus if a postcode reaches a locality and a region. Two routes exist and
|
|
15
|
+
* only one of them works everywhere:
|
|
16
|
+
*
|
|
17
|
+
* - **`parent_id`** — `postalcode-intl.db` carries a real parent that resolves in the admin gazetteer (measured: NL
|
|
18
|
+
* 97.5% of rows linked, FR 90.7%, DE 66.1%, ES 34.9%, IT 27.4%, and 93.8–100% of those resolve to a
|
|
19
|
+
* `locality`/`localadmin`). It is also the ONLY shard that does: `postalcode-geonames-intl.db` and every
|
|
20
|
+
* `postalcode-<cc>-overture.db` carry `parent_id = 0` on every row, so five countries have this route and the rest
|
|
21
|
+
* have none.
|
|
22
|
+
* - **Nearest locality centroid** — the obvious fallback, and it does not work. Scored against the `parent_id` truth
|
|
23
|
+
* on 1,000–1,500 postcodes per country: NL 81.1%, DE 44.7%, ES 35.1%, FR 29.0%, IT 13.5%. A locality's centroid
|
|
24
|
+
* sits at its middle, so a postcode near the edge is routinely closer to a neighbouring town's centroid than to its
|
|
25
|
+
* own. Under 50% for four of the five, which is not a join.
|
|
26
|
+
*
|
|
27
|
+
* The GeoNames export sidesteps both: columns 3 and 4 ARE the place and admin1 names, so there is nothing to join and
|
|
28
|
+
* nothing to approximate. `@mailwoman/corpus`'s `geonames-postal` adapter consumes it directly.
|
|
29
|
+
*
|
|
30
|
+
* ## Coverage is not universal, and the gap is the point
|
|
31
|
+
*
|
|
32
|
+
* GeoNames publishes ~80 countries, NOT all of them. Venezuela returns 404 — so a VE postcode shard cannot be built
|
|
33
|
+
* from this source at any effort, and that is an acquisition question rather than a build one. Ask for a country
|
|
34
|
+
* before assuming it is there; an absent country fails as one entry, never as the whole run.
|
|
35
|
+
*
|
|
36
|
+
* ## Row counts from this source overstate, for some countries by exactly 2×
|
|
37
|
+
*
|
|
38
|
+
* Countries whose postcode format contains a hyphen are published TWICE — once `3750-000`, once `3750000`. Measured
|
|
39
|
+
* on the shard built from this source: PT 395,544 rows over 197,772 distinct codes and PL 40,598 over 20,299, both
|
|
40
|
+
* exactly 2.00×, while AU, CZ and AT (no hyphen in the format) are 1.00×. A consumer sizing a shard from the row
|
|
41
|
+
* count doubles its estimate for those countries.
|
|
42
|
+
*
|
|
43
|
+
* ## Why `downloadToFile` and not `APIClient`
|
|
44
|
+
*
|
|
45
|
+
* Same split `AGENTS.md` draws and the `ourairports` sibling explains: these are static file transfers from a plain
|
|
46
|
+
* file host, run once per refresh. The pacing, retry and caching `APIClient` exists for have nothing to act on here.
|
|
47
|
+
*
|
|
48
|
+
* Invoke via `mailwoman corpus fetch geonames-postal --countries pt,au,nz`.
|
|
49
|
+
*/
|
|
50
|
+
import { mkdirSync } from "node:fs";
|
|
51
|
+
import { join } from "node:path";
|
|
52
|
+
import { sha256File } from "@mailwoman/core/utils";
|
|
53
|
+
import { downloadToFile, HTTPStatusError, writeManifest } from "./download.js";
|
|
54
|
+
/**
|
|
55
|
+
* The one status that means "the source does not publish this country" rather than "the transfer failed".
|
|
56
|
+
*/
|
|
57
|
+
const HTTP_NOT_FOUND = 404;
|
|
58
|
+
const SLUG = "geonames-postal";
|
|
59
|
+
/**
|
|
60
|
+
* GeoNames' own export directory. One zip per ISO alpha-2 code, each holding `<CC>.txt` plus the shared `readme.txt`.
|
|
61
|
+
*/
|
|
62
|
+
const BASE_URL = "https://download.geonames.org/export/zip";
|
|
63
|
+
/**
|
|
64
|
+
* Countries fetched when the caller names none.
|
|
65
|
+
*
|
|
66
|
+
* These are the ones the corpus wants and cannot get from `postalcode-intl.db`'s `parent_id` route — see the header for
|
|
67
|
+
* why that route covers exactly five countries. Venezuela is deliberately absent because GeoNames does not publish it.
|
|
68
|
+
*/
|
|
69
|
+
export const GEONAMES_POSTAL_DEFAULT_COUNTRIES = ["PT", "AU", "NZ", "IE", "BR", "ZA", "MX"];
|
|
70
|
+
/**
|
|
71
|
+
* Download the requested GeoNames postal zips into `<outRoot>/geonames-postal/`, with a sibling `MANIFEST.json`
|
|
72
|
+
* carrying each file's origin URL, sha256 and byte count, plus the countries the source does not publish.
|
|
73
|
+
*
|
|
74
|
+
* A country the source does not carry is counted as failed and named in `failedCodes` — it does not stop the rest.
|
|
75
|
+
*/
|
|
76
|
+
export async function fetchGeonamesPostal(options, report) {
|
|
77
|
+
const destDir = join(options.outRoot, SLUG);
|
|
78
|
+
mkdirSync(destDir, { recursive: true });
|
|
79
|
+
const countries = (options.countries ?? GEONAMES_POSTAL_DEFAULT_COUNTRIES).map((code) => code.trim().toUpperCase());
|
|
80
|
+
const baseURL = options.baseURL ?? BASE_URL;
|
|
81
|
+
const entries = [];
|
|
82
|
+
const failedCodes = [];
|
|
83
|
+
const unavailable = [];
|
|
84
|
+
let fetched = 0;
|
|
85
|
+
let failed = 0;
|
|
86
|
+
for (const country of countries) {
|
|
87
|
+
const filename = `${country}.zip`;
|
|
88
|
+
const url = `${baseURL}/${filename}`;
|
|
89
|
+
const dest = join(destDir, filename);
|
|
90
|
+
report?.(`=== ${SLUG} / ${country}`);
|
|
91
|
+
try {
|
|
92
|
+
const { bytes } = await downloadToFile({ url, dest, timeoutMs: 300_000, retries: 2, report });
|
|
93
|
+
entries.push({ country, filename, source_url: url, sha256: await sha256File(dest), bytes });
|
|
94
|
+
fetched++;
|
|
95
|
+
}
|
|
96
|
+
catch (error) {
|
|
97
|
+
const message = error instanceof Error ? error.message : String(error);
|
|
98
|
+
// A 404 here means GeoNames does not publish the country at all, which is a different finding from a failed
|
|
99
|
+
// transfer and the one a caller planning a shard needs to see. Branch on the TYPED status: matching message
|
|
100
|
+
// prose classified a 500 as "unpublished" whenever the URL happened to contain the substring 404 — an
|
|
101
|
+
// ephemeral test-server port did exactly that in CI.
|
|
102
|
+
if (error instanceof HTTPStatusError && error.status === HTTP_NOT_FOUND) {
|
|
103
|
+
report?.(`✗ ${country}: GeoNames does not publish a postal export for this country`);
|
|
104
|
+
unavailable.push(country);
|
|
105
|
+
}
|
|
106
|
+
else {
|
|
107
|
+
report?.(`✗ ${country}: ${message}`);
|
|
108
|
+
}
|
|
109
|
+
failedCodes.push(country);
|
|
110
|
+
failed++;
|
|
111
|
+
}
|
|
112
|
+
}
|
|
113
|
+
const manifest = {
|
|
114
|
+
source: "GeoNames postal codes",
|
|
115
|
+
base_url: baseURL,
|
|
116
|
+
license: "CC-BY-4.0",
|
|
117
|
+
attribution: "GeoNames",
|
|
118
|
+
downloaded_at: new Date().toISOString(),
|
|
119
|
+
files: entries,
|
|
120
|
+
unavailable,
|
|
121
|
+
};
|
|
122
|
+
await writeManifest(join(destDir, "MANIFEST.json"), manifest);
|
|
123
|
+
return { fetched, skipped: 0, failed, failedCodes };
|
|
124
|
+
}
|
|
125
|
+
//# sourceMappingURL=geonames-postal.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"geonames-postal.js","sourceRoot":"","sources":["../../../../src/tools/fetch/geonames-postal.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAgDG;AAEH,OAAO,EAAE,SAAS,EAAE,MAAM,SAAS,CAAA;AACnC,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAEhC,OAAO,EAAE,UAAU,EAAE,MAAM,uBAAuB,CAAA;AAGlD,OAAO,EAAE,cAAc,EAAE,eAAe,EAAE,aAAa,EAAE,MAAM,eAAe,CAAA;AAE9E;;GAEG;AACH,MAAM,cAAc,GAAG,GAAG,CAAA;AAE1B,MAAM,IAAI,GAAG,iBAAiB,CAAA;AAE9B;;GAEG;AACH,MAAM,QAAQ,GAAG,0CAA0C,CAAA;AAE3D;;;;;GAKG;AACH,MAAM,CAAC,MAAM,iCAAiC,GAAG,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,CAAU,CAAA;AAoCpG;;;;;GAKG;AACH,MAAM,CAAC,KAAK,UAAU,mBAAmB,CACxC,OAAmC,EACnC,MAA+B;IAE/B,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,IAAI,CAAC,CAAA;IAC3C,SAAS,CAAC,OAAO,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;IAEvC,MAAM,SAAS,GAAG,CAAC,OAAO,CAAC,SAAS,IAAI,iCAAiC,CAAC,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAC,CAAA;IACnH,MAAM,OAAO,GAAG,OAAO,CAAC,OAAO,IAAI,QAAQ,CAAA;IAC3C,MAAM,OAAO,GAA8B,EAAE,CAAA;IAC7C,MAAM,WAAW,GAAa,EAAE,CAAA;IAChC,MAAM,WAAW,GAAa,EAAE,CAAA;IAChC,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,MAAM,GAAG,CAAC,CAAA;IAEd,KAAK,MAAM,OAAO,IAAI,SAAS,EAAE,CAAC;QACjC,MAAM,QAAQ,GAAG,GAAG,OAAO,MAAM,CAAA;QACjC,MAAM,GAAG,GAAG,GAAG,OAAO,IAAI,QAAQ,EAAE,CAAA;QACpC,MAAM,IAAI,GAAG,IAAI,CAAC,OAAO,EAAE,QAAQ,CAAC,CAAA;QAEpC,MAAM,EAAE,CAAC,OAAO,IAAI,MAAM,OAAO,EAAE,CAAC,CAAA;QAEpC,IAAI,CAAC;YACJ,MAAM,EAAE,KAAK,EAAE,GAAG,MAAM,cAAc,CAAC,EAAE,GAAG,EAAE,IAAI,EAAE,SAAS,EAAE,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,CAAA;YAE7F,OAAO,CAAC,IAAI,CAAC,EAAE,OAAO,EAAE,QAAQ,EAAE,UAAU,EAAE,GAAG,EAAE,MAAM,EAAE,MAAM,UAAU,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,CAAC,CAAA;YAE3F,OAAO,EAAE,CAAA;QACV,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,MAAM,OAAO,GAAG,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAA;YAEtE,4GAA4G;YAC5G,4GAA4G;YAC5G,sGAAsG;YACtG,qDAAqD;YACrD,IAAI,KAAK,YAAY,eAAe,IAAI,KAAK,CAAC,MAAM,KAAK,cAAc,EAAE,CAAC;gBACzE,MAAM,EAAE,CAAC,KAAK,OAAO,8DAA8D,CAAC,CAAA;gBACpF,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;YAC1B,CAAC;iBAAM,CAAC;gBACP,MAAM,EAAE,CAAC,KAAK,OAAO,KAAK,OAAO,EAAE,CAAC,CAAA;YACrC,CAAC;YAED,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;YAEzB,MAAM,EAAE,CAAA;QACT,CAAC;IACF,CAAC;IAED,MAAM,QAAQ,GAA2B;QACxC,MAAM,EAAE,uBAAuB;QAC/B,QAAQ,EAAE,OAAO;QACjB,OAAO,EAAE,WAAW;QACpB,WAAW,EAAE,UAAU;QACvB,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;QACvC,KAAK,EAAE,OAAO;QACd,WAAW;KACX,CAAA;IAED,MAAM,aAAa,CAAC,IAAI,CAAC,OAAO,EAAE,eAAe,CAAC,EAAE,QAAQ,CAAC,CAAA;IAE7D,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,WAAW,EAAE,CAAA;AACpD,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"imls-pls.d.ts","sourceRoot":"","sources":["../../../../src/tools/fetch/imls-pls.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;GAoBG;
|
|
1
|
+
{"version":3,"file":"imls-pls.d.ts","sourceRoot":"","sources":["../../../../src/tools/fetch/imls-pls.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;GAoBG;AAaH,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAAE,MAAM,eAAe,CAAA;AAcnE,MAAM,MAAM,mBAAmB,GAAG,gBAAgB,CAAA;AAUlD,wBAAsB,YAAY,CACjC,OAAO,EAAE,mBAAmB,EAC5B,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,YAAY,CAAC,CAiGvB"}
|
|
@@ -21,34 +21,22 @@
|
|
|
21
21
|
*/
|
|
22
22
|
/* oxlint-disable sister-software/prefer-region-over-marks -- these markers label steps inside one
|
|
23
23
|
procedure, not sections of declarations. A region there folds nothing a reader wants folded. */
|
|
24
|
-
import { execFile } from "node:child_process";
|
|
25
24
|
import { existsSync, mkdirSync, statSync } from "node:fs";
|
|
26
25
|
import { rm } from "node:fs/promises";
|
|
27
26
|
import { basename, join } from "node:path";
|
|
28
|
-
import {
|
|
27
|
+
import { BYTES_PER_KIB, ByteFormatter } from "@mailwoman/core/fs/utils";
|
|
28
|
+
import { extractZipEntry, listZipEntries } from "@mailwoman/core/fs/zip";
|
|
29
29
|
import { sha256File } from "@mailwoman/core/utils";
|
|
30
|
-
import { TextSpliterator } from "spliterator";
|
|
31
30
|
import { downloadToFile, readManifest, writeManifest } from "./download.js";
|
|
32
31
|
/**
|
|
33
32
|
* Bytes per KiB — the divisor for human-readable sizes, and the floor below which a "download" is an error page rather
|
|
34
33
|
* than data.
|
|
35
34
|
*/
|
|
36
|
-
const BYTES_PER_KIB = 1024;
|
|
37
|
-
const execFileAsync = promisify(execFile);
|
|
38
35
|
/**
|
|
39
36
|
* The PLS FY 2023 bulk CSV ZIP (most recent as of 2026-05). If IMLS publishes a newer year, update this URL.
|
|
40
37
|
*/
|
|
41
38
|
const ZIP_URL = "https://www.imls.gov/sites/default/files/2025-08/pls_fy2023_csv.zip";
|
|
42
39
|
const SLUG = "usgov-imls-pls";
|
|
43
|
-
/**
|
|
44
|
-
* Return the filenames listed inside a ZIP (the trailing column of each `unzip -l` row).
|
|
45
|
-
*/
|
|
46
|
-
async function listZipEntries(zipPath) {
|
|
47
|
-
const listing = await execFileAsync("unzip", ["-l", zipPath]);
|
|
48
|
-
return [...TextSpliterator.from(listing.stdout)]
|
|
49
|
-
.map((line) => line.trim().split(/\s+/).pop() ?? "")
|
|
50
|
-
.filter((name) => name.length > 0);
|
|
51
|
-
}
|
|
52
40
|
export async function fetchIMLSPLS(options, report) {
|
|
53
41
|
const destDir = join(options.outRoot, SLUG);
|
|
54
42
|
mkdirSync(destDir, { recursive: true });
|
|
@@ -73,7 +61,7 @@ export async function fetchIMLSPLS(options, report) {
|
|
|
73
61
|
headers: { "Accept-Encoding": "gzip, br" },
|
|
74
62
|
report,
|
|
75
63
|
});
|
|
76
|
-
report?.(` Downloaded: ${(zipSize
|
|
64
|
+
report?.(` Downloaded: ${ByteFormatter.formatIEC(zipSize)}`);
|
|
77
65
|
if (zipSize < BYTES_PER_KIB) {
|
|
78
66
|
report?.(` ✗ Response too small (${zipSize} bytes) — probable error page`);
|
|
79
67
|
return { fetched: 0, skipped: 0, failed: 1, failedCodes: [SLUG] };
|
|
@@ -82,7 +70,7 @@ export async function fetchIMLSPLS(options, report) {
|
|
|
82
70
|
// Outlet files match: pls_fy*outlet*.csv (case-insensitive)
|
|
83
71
|
// Administrative-entity files match: pls_fy*ae*.csv — we skip those.
|
|
84
72
|
report?.(" Inspecting ZIP contents ...");
|
|
85
|
-
const entries = await listZipEntries(zipDest);
|
|
73
|
+
const entries = (await listZipEntries(zipDest)).map((entry) => entry.name);
|
|
86
74
|
let csvName = entries.find((name) => /pls_fy.*outlet.*\.csv/i.test(name));
|
|
87
75
|
// Fallback: if IMLS renames the file, grab any CSV that is NOT the ae file.
|
|
88
76
|
if (!csvName) {
|
|
@@ -97,8 +85,8 @@ export async function fetchIMLSPLS(options, report) {
|
|
|
97
85
|
return { fetched: 0, skipped: 0, failed: 1, failedCodes: [SLUG] };
|
|
98
86
|
}
|
|
99
87
|
report?.(` Extracting outlet CSV: ${csvName}`);
|
|
100
|
-
await execFileAsync("unzip", ["-o", "-j", zipDest, csvName, "-d", destDir]);
|
|
101
88
|
const csvDest = join(destDir, basename(csvName));
|
|
89
|
+
await extractZipEntry(zipDest, csvName, csvDest);
|
|
102
90
|
const csvSize = statSync(csvDest).size;
|
|
103
91
|
const csvSha = await sha256File(csvDest);
|
|
104
92
|
// MARK: Remove ZIP (small, but keep destDir clean)
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"imls-pls.js","sourceRoot":"","sources":["../../../../src/tools/fetch/imls-pls.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;GAoBG;AAEH;kGACkG;AAElG,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"imls-pls.js","sourceRoot":"","sources":["../../../../src/tools/fetch/imls-pls.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;GAoBG;AAEH;kGACkG;AAElG,OAAO,EAAE,UAAU,EAAE,SAAS,EAAE,QAAQ,EAAE,MAAM,SAAS,CAAA;AACzD,OAAO,EAAE,EAAE,EAAE,MAAM,kBAAkB,CAAA;AACrC,OAAO,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAE1C,OAAO,EAAE,aAAa,EAAE,aAAa,EAAE,MAAM,0BAA0B,CAAA;AACvE,OAAO,EAAE,eAAe,EAAE,cAAc,EAAE,MAAM,wBAAwB,CAAA;AACxE,OAAO,EAAE,UAAU,EAAE,MAAM,uBAAuB,CAAA;AAGlD,OAAO,EAAE,cAAc,EAAE,YAAY,EAAE,aAAa,EAAE,MAAM,eAAe,CAAA;AAE3E;;;GAGG;AAEH;;GAEG;AACH,MAAM,OAAO,GAAG,qEAAqE,CAAA;AACrF,MAAM,IAAI,GAAG,gBAAgB,CAAA;AAY7B,MAAM,CAAC,KAAK,UAAU,YAAY,CACjC,OAA4B,EAC5B,MAA+B;IAE/B,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,IAAI,CAAC,CAAA;IAC3C,SAAS,CAAC,OAAO,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;IAEvC,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,EAAE,QAAQ,CAAC,OAAO,CAAC,CAAC,CAAA;IAChD,MAAM,YAAY,GAAG,IAAI,CAAC,OAAO,EAAE,eAAe,CAAC,CAAA;IAEnD,MAAM,EAAE,CAAC,OAAO,IAAI,EAAE,CAAC,CAAA;IAEvB,0BAA0B;IAE1B,MAAM,QAAQ,GAAG,MAAM,YAAY,CAA0B,YAAY,CAAC,CAAA;IAE1E,IAAI,QAAQ,EAAE,MAAM,IAAI,QAAQ,CAAC,QAAQ,EAAE,CAAC;QAC3C,MAAM,YAAY,GAAG,IAAI,CAAC,OAAO,EAAE,QAAQ,CAAC,QAAQ,CAAC,CAAA;QAErD,IAAI,UAAU,CAAC,YAAY,CAAC,IAAI,CAAC,MAAM,UAAU,CAAC,YAAY,CAAC,CAAC,KAAK,QAAQ,CAAC,MAAM,EAAE,CAAC;YACtF,MAAM,EAAE,CAAC,oEAAoE,CAAC,CAAA;YAE9E,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,WAAW,EAAE,EAAE,EAAE,CAAA;QAC9D,CAAC;IACF,CAAC;IAED,qBAAqB;IAErB,MAAM,EAAE,CAAC,iBAAiB,OAAO,MAAM,CAAC,CAAA;IAExC,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,GAAG,MAAM,cAAc,CAAC;QAC/C,GAAG,EAAE,OAAO;QACZ,IAAI,EAAE,OAAO;QACb,SAAS,EAAE,OAAO;QAClB,OAAO,EAAE,EAAE,iBAAiB,EAAE,UAAU,EAAE;QAC1C,MAAM;KACN,CAAC,CAAA;IAEF,MAAM,EAAE,CAAC,iBAAiB,aAAa,CAAC,SAAS,CAAC,OAAO,CAAC,EAAE,CAAC,CAAA;IAE7D,IAAI,OAAO,GAAG,aAAa,EAAE,CAAC;QAC7B,MAAM,EAAE,CAAC,2BAA2B,OAAO,+BAA+B,CAAC,CAAA;QAE3E,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,WAAW,EAAE,CAAC,IAAI,CAAC,EAAE,CAAA;IAClE,CAAC;IAED,gDAAgD;IAChD,4DAA4D;IAC5D,qEAAqE;IACrE,MAAM,EAAE,CAAC,+BAA+B,CAAC,CAAA;IACzC,MAAM,OAAO,GAAG,CAAC,MAAM,cAAc,CAAC,OAAO,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,IAAI,CAAC,CAAA;IAE1E,IAAI,OAAO,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,wBAAwB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAA;IAEzE,4EAA4E;IAC5E,IAAI,CAAC,OAAO,EAAE,CAAC;QACd,OAAO,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,2BAA2B,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAA;IAClG,CAAC;IAED,IAAI,CAAC,OAAO,EAAE,CAAC;QACd,MAAM,EAAE,CAAC,2BAA2B,CAAC,CAAA;QAErC,KAAK,MAAM,IAAI,IAAI,OAAO,EAAE,CAAC;YAC5B,MAAM,EAAE,CAAC,OAAO,IAAI,EAAE,CAAC,CAAA;QACxB,CAAC;QAED,MAAM,EAAE,CAAC,kFAAkF,CAAC,CAAA;QAE5F,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,WAAW,EAAE,CAAC,IAAI,CAAC,EAAE,CAAA;IAClE,CAAC;IAED,MAAM,EAAE,CAAC,4BAA4B,OAAO,EAAE,CAAC,CAAA;IAE/C,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,EAAE,QAAQ,CAAC,OAAO,CAAC,CAAC,CAAA;IAEhD,MAAM,eAAe,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC,CAAA;IAChD,MAAM,OAAO,GAAG,QAAQ,CAAC,OAAO,CAAC,CAAC,IAAI,CAAA;IACtC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,OAAO,CAAC,CAAA;IAExC,mDAAmD;IAEnD,MAAM,EAAE,CAAC,OAAO,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC,CAAA;IAClC,MAAM,EAAE,CAAC,0BAA0B,CAAC,CAAA;IAEpC,uBAAuB;IAEvB,MAAM,QAAQ,GAAmB;QAChC,UAAU,EAAE,OAAO;QACnB,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;QACvC,QAAQ,EAAE,QAAQ,CAAC,OAAO,CAAC;QAC3B,MAAM,EAAE,MAAM;QACd,KAAK,EAAE,OAAO;KACd,CAAA;IAED,MAAM,aAAa,CAAC,YAAY,EAAE,QAAQ,CAAC,CAAA;IAE3C,MAAM,EAAE,CAAC,OAAO,CAAC,OAAO,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe,MAAM,EAAE,CAAC,CAAA;IAC1E,MAAM,EAAE,CAAC,yBAAyB,YAAY,EAAE,CAAC,CAAA;IAEjD,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,WAAW,EAAE,EAAE,EAAE,CAAA;AAC9D,CAAC"}
|
|
@@ -33,6 +33,11 @@
|
|
|
33
33
|
* Ouverte 2.0).
|
|
34
34
|
* - `nad` — US DOT National Address Database (~97M address points, ArcGIS FeatureServer). Tier A
|
|
35
35
|
* (US PD).
|
|
36
|
+
* - `geonames-postal` — GeoNames per-country postal exports (~80 countries). Tier B (CC-BY-4.0,
|
|
37
|
+
* attribute "GeoNames"). The only source in this family carrying `(postcode, locality, region)`
|
|
38
|
+
* with the names INLINE, which is why it exists: the `parent_id` join route covers exactly five
|
|
39
|
+
* countries and the nearest-centroid fallback measured under 50% agreement on four of those five.
|
|
40
|
+
* GeoNames does not publish every country — Venezuela 404s.
|
|
36
41
|
* - `hrsa` — HRSA Health Center Service Delivery Sites (federal). Tier A (US PD).
|
|
37
42
|
* - `imls-pls` — IMLS Public Libraries Survey, outlet-level (~17K library branches, FY 2023).
|
|
38
43
|
* Tier A (US PD).
|
|
@@ -92,6 +97,8 @@
|
|
|
92
97
|
* 5. Add the source's adapter (or extend an existing one) under `corpus/src/adapters/`.
|
|
93
98
|
*/
|
|
94
99
|
import { fetchBan } from "./ban.ts";
|
|
100
|
+
import { fetchGeonamesDumps } from "./geonames-dump.ts";
|
|
101
|
+
import { fetchGeonamesPostal } from "./geonames-postal.ts";
|
|
95
102
|
import { fetchHRSA } from "./hrsa.ts";
|
|
96
103
|
import { fetchIMLSPLS } from "./imls-pls.ts";
|
|
97
104
|
import { fetchNAD } from "./nad.ts";
|
|
@@ -103,6 +110,8 @@ import { fetchStateSources } from "./state-sources.ts";
|
|
|
103
110
|
import { fetchTigerFull } from "./tiger-full.ts";
|
|
104
111
|
import { fetchWikidataSubVenue } from "./wikidata-subvenue.ts";
|
|
105
112
|
export * from "./ban.ts";
|
|
113
|
+
export * from "./geonames-dump.ts";
|
|
114
|
+
export * from "./geonames-postal.ts";
|
|
106
115
|
export * from "./hrsa.ts";
|
|
107
116
|
export * from "./imls-pls.ts";
|
|
108
117
|
export * from "./nad.ts";
|
|
@@ -119,6 +128,8 @@ export * from "./wikidata-subvenue.ts";
|
|
|
119
128
|
export declare const FETCH_SOURCES: {
|
|
120
129
|
readonly ban: typeof fetchBan;
|
|
121
130
|
readonly nad: typeof fetchNAD;
|
|
131
|
+
readonly "geonames-dump": typeof fetchGeonamesDumps;
|
|
132
|
+
readonly "geonames-postal": typeof fetchGeonamesPostal;
|
|
122
133
|
readonly hrsa: typeof fetchHRSA;
|
|
123
134
|
readonly "imls-pls": typeof fetchIMLSPLS;
|
|
124
135
|
readonly nppes: typeof fetchNPPES;
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../../src/tools/fetch/index.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../../src/tools/fetch/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAiGG;AAEH,OAAO,EAAE,QAAQ,EAAE,MAAM,UAAU,CAAA;AACnC,OAAO,EAAE,kBAAkB,EAAE,MAAM,oBAAoB,CAAA;AACvD,OAAO,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AAC1D,OAAO,EAAE,SAAS,EAAE,MAAM,WAAW,CAAA;AACrC,OAAO,EAAE,YAAY,EAAE,MAAM,eAAe,CAAA;AAC5C,OAAO,EAAE,QAAQ,EAAE,MAAM,UAAU,CAAA;AACnC,OAAO,EAAE,UAAU,EAAE,MAAM,YAAY,CAAA;AACvC,OAAO,EAAE,kBAAkB,EAAE,MAAM,oBAAoB,CAAA;AACvD,OAAO,EAAE,gBAAgB,EAAE,MAAM,kBAAkB,CAAA;AACnD,OAAO,EAAE,mBAAmB,EAAE,MAAM,uBAAuB,CAAA;AAC3D,OAAO,EAAE,iBAAiB,EAAE,MAAM,oBAAoB,CAAA;AACtD,OAAO,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAA;AAChD,OAAO,EAAE,qBAAqB,EAAE,MAAM,wBAAwB,CAAA;AAE9D,cAAc,UAAU,CAAA;AACxB,cAAc,oBAAoB,CAAA;AAClC,cAAc,sBAAsB,CAAA;AACpC,cAAc,WAAW,CAAA;AACzB,cAAc,eAAe,CAAA;AAC7B,cAAc,UAAU,CAAA;AACxB,cAAc,YAAY,CAAA;AAC1B,cAAc,oBAAoB,CAAA;AAClC,cAAc,kBAAkB,CAAA;AAChC,cAAc,uBAAuB,CAAA;AACrC,cAAc,oBAAoB,CAAA;AAClC,cAAc,iBAAiB,CAAA;AAC/B,cAAc,wBAAwB,CAAA;AAEtC;;GAEG;AACH,eAAO,MAAM,aAAa;;;;;;;;;;;;;;CAchB,CAAA;AAEV,MAAM,MAAM,aAAa,GAAG,MAAM,OAAO,aAAa,CAAA"}
|
|
@@ -33,6 +33,11 @@
|
|
|
33
33
|
* Ouverte 2.0).
|
|
34
34
|
* - `nad` — US DOT National Address Database (~97M address points, ArcGIS FeatureServer). Tier A
|
|
35
35
|
* (US PD).
|
|
36
|
+
* - `geonames-postal` — GeoNames per-country postal exports (~80 countries). Tier B (CC-BY-4.0,
|
|
37
|
+
* attribute "GeoNames"). The only source in this family carrying `(postcode, locality, region)`
|
|
38
|
+
* with the names INLINE, which is why it exists: the `parent_id` join route covers exactly five
|
|
39
|
+
* countries and the nearest-centroid fallback measured under 50% agreement on four of those five.
|
|
40
|
+
* GeoNames does not publish every country — Venezuela 404s.
|
|
36
41
|
* - `hrsa` — HRSA Health Center Service Delivery Sites (federal). Tier A (US PD).
|
|
37
42
|
* - `imls-pls` — IMLS Public Libraries Survey, outlet-level (~17K library branches, FY 2023).
|
|
38
43
|
* Tier A (US PD).
|
|
@@ -92,6 +97,8 @@
|
|
|
92
97
|
* 5. Add the source's adapter (or extend an existing one) under `corpus/src/adapters/`.
|
|
93
98
|
*/
|
|
94
99
|
import { fetchBan } from "./ban.js";
|
|
100
|
+
import { fetchGeonamesDumps } from "./geonames-dump.js";
|
|
101
|
+
import { fetchGeonamesPostal } from "./geonames-postal.js";
|
|
95
102
|
import { fetchHRSA } from "./hrsa.js";
|
|
96
103
|
import { fetchIMLSPLS } from "./imls-pls.js";
|
|
97
104
|
import { fetchNAD } from "./nad.js";
|
|
@@ -103,6 +110,8 @@ import { fetchStateSources } from "./state-sources.js";
|
|
|
103
110
|
import { fetchTigerFull } from "./tiger-full.js";
|
|
104
111
|
import { fetchWikidataSubVenue } from "./wikidata-subvenue.js";
|
|
105
112
|
export * from "./ban.js";
|
|
113
|
+
export * from "./geonames-dump.js";
|
|
114
|
+
export * from "./geonames-postal.js";
|
|
106
115
|
export * from "./hrsa.js";
|
|
107
116
|
export * from "./imls-pls.js";
|
|
108
117
|
export * from "./nad.js";
|
|
@@ -119,6 +128,8 @@ export * from "./wikidata-subvenue.js";
|
|
|
119
128
|
export const FETCH_SOURCES = {
|
|
120
129
|
ban: fetchBan,
|
|
121
130
|
nad: fetchNAD,
|
|
131
|
+
"geonames-dump": fetchGeonamesDumps,
|
|
132
|
+
"geonames-postal": fetchGeonamesPostal,
|
|
122
133
|
hrsa: fetchHRSA,
|
|
123
134
|
"imls-pls": fetchIMLSPLS,
|
|
124
135
|
nppes: fetchNPPES,
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../../src/tools/fetch/index.ts"],"names":[],"mappings":"AAAA
|
|
1
|
+
{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../../src/tools/fetch/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAiGG;AAEH,OAAO,EAAE,QAAQ,EAAE,MAAM,UAAU,CAAA;AACnC,OAAO,EAAE,kBAAkB,EAAE,MAAM,oBAAoB,CAAA;AACvD,OAAO,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AAC1D,OAAO,EAAE,SAAS,EAAE,MAAM,WAAW,CAAA;AACrC,OAAO,EAAE,YAAY,EAAE,MAAM,eAAe,CAAA;AAC5C,OAAO,EAAE,QAAQ,EAAE,MAAM,UAAU,CAAA;AACnC,OAAO,EAAE,UAAU,EAAE,MAAM,YAAY,CAAA;AACvC,OAAO,EAAE,kBAAkB,EAAE,MAAM,oBAAoB,CAAA;AACvD,OAAO,EAAE,gBAAgB,EAAE,MAAM,kBAAkB,CAAA;AACnD,OAAO,EAAE,mBAAmB,EAAE,MAAM,uBAAuB,CAAA;AAC3D,OAAO,EAAE,iBAAiB,EAAE,MAAM,oBAAoB,CAAA;AACtD,OAAO,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAA;AAChD,OAAO,EAAE,qBAAqB,EAAE,MAAM,wBAAwB,CAAA;AAE9D,cAAc,UAAU,CAAA;AACxB,cAAc,oBAAoB,CAAA;AAClC,cAAc,sBAAsB,CAAA;AACpC,cAAc,WAAW,CAAA;AACzB,cAAc,eAAe,CAAA;AAC7B,cAAc,UAAU,CAAA;AACxB,cAAc,YAAY,CAAA;AAC1B,cAAc,oBAAoB,CAAA;AAClC,cAAc,kBAAkB,CAAA;AAChC,cAAc,uBAAuB,CAAA;AACrC,cAAc,oBAAoB,CAAA;AAClC,cAAc,iBAAiB,CAAA;AAC/B,cAAc,wBAAwB,CAAA;AAEtC;;GAEG;AACH,MAAM,CAAC,MAAM,aAAa,GAAG;IAC5B,GAAG,EAAE,QAAQ;IACb,GAAG,EAAE,QAAQ;IACb,eAAe,EAAE,kBAAkB;IACnC,iBAAiB,EAAE,mBAAmB;IACtC,IAAI,EAAE,SAAS;IACf,UAAU,EAAE,YAAY;IACxB,KAAK,EAAE,UAAU;IACjB,aAAa,EAAE,kBAAkB;IACjC,WAAW,EAAE,gBAAgB;IAC7B,eAAe,EAAE,iBAAiB;IAClC,kBAAkB,EAAE,mBAAmB;IACvC,YAAY,EAAE,cAAc;IAC5B,mBAAmB,EAAE,qBAAqB;CACjC,CAAA"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"nad.d.ts","sourceRoot":"","sources":["../../../../src/tools/fetch/nad.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAoCG;
|
|
1
|
+
{"version":3,"file":"nad.d.ts","sourceRoot":"","sources":["../../../../src/tools/fetch/nad.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAoCG;AASH,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAAE,MAAM,eAAe,CAAA;AAQnE,MAAM,WAAW,eAAgB,SAAQ,gBAAgB;IACxD;;OAEG;IACH,IAAI,CAAC,EAAE,eAAe,GAAG,MAAM,CAAA;IAC/B;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,CAAA;IACf;;OAEG;IACH,SAAS,CAAC,EAAE,MAAM,CAAA;IAClB;;OAEG;IACH,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB;;OAEG;IACH,WAAW,CAAC,EAAE,MAAM,CAAA;IACpB;;OAEG;IACH,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,CAAA;CACf;AAuPD,wBAAsB,QAAQ,CAAC,OAAO,EAAE,eAAe,EAAE,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAAG,OAAO,CAAC,YAAY,CAAC,CAY/G"}
|
|
@@ -38,23 +38,33 @@
|
|
|
38
38
|
import { existsSync, mkdirSync, statSync } from "node:fs";
|
|
39
39
|
import { writeFile } from "node:fs/promises";
|
|
40
40
|
import { join } from "node:path";
|
|
41
|
+
import { APIClient, pluckResponseData } from "@mailwoman/core/api";
|
|
41
42
|
import { sha256File } from "@mailwoman/core/utils";
|
|
42
43
|
import { downloadToFile, readManifest, writeManifest } from "./download.js";
|
|
43
44
|
const SLUG = "usgov-nad";
|
|
44
45
|
const FEATURE_SERVICE_URL = "https://services.arcgis.com/xOi1kZaI0eWDREZv/ArcGIS/rest/services/Address_Points_from_National_Address_Database_view/FeatureServer/0";
|
|
46
|
+
/**
|
|
47
|
+
* ArcGIS paged reads. Retry is ON: the loop walks OBJECTID ranges to completion, so one throttled page previously ended
|
|
48
|
+
* a multi-hour national download. No rate budget — pages are requested one at a time and each assembles thousands of
|
|
49
|
+
* records server-side.
|
|
50
|
+
*/
|
|
51
|
+
const nadClient = new APIClient({
|
|
52
|
+
displayName: "nad",
|
|
53
|
+
retry: true,
|
|
54
|
+
axios: { headers: { "Accept-Encoding": "gzip, br" } },
|
|
55
|
+
});
|
|
45
56
|
async function fetchPage(startOID, endOID, pageSize) {
|
|
46
57
|
const url = new URL(`${FEATURE_SERVICE_URL}/query`);
|
|
47
58
|
url.searchParams.set("where", `OBJECTID BETWEEN ${startOID} AND ${endOID}`);
|
|
48
59
|
url.searchParams.set("outFields", "*");
|
|
49
60
|
url.searchParams.set("f", "json");
|
|
50
61
|
url.searchParams.set("resultRecordCount", String(pageSize));
|
|
51
|
-
const
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
|
|
56
|
-
|
|
57
|
-
const data = (await res.json());
|
|
62
|
+
const data = await nadClient
|
|
63
|
+
.fetch({
|
|
64
|
+
url: url.toString(),
|
|
65
|
+
timeout: 120_000,
|
|
66
|
+
})
|
|
67
|
+
.then(pluckResponseData);
|
|
58
68
|
if (data.error)
|
|
59
69
|
throw new Error(`ArcGIS error on OID ${startOID}-${endOID}: ${data.error.message}`);
|
|
60
70
|
return (data.features ?? []).map((f) => f.attributes);
|
|
@@ -64,10 +74,9 @@ async function discoverTotalCount() {
|
|
|
64
74
|
url.searchParams.set("where", "1=1");
|
|
65
75
|
url.searchParams.set("returnCountOnly", "true");
|
|
66
76
|
url.searchParams.set("f", "json");
|
|
67
|
-
const
|
|
68
|
-
|
|
69
|
-
|
|
70
|
-
const data = (await res.json());
|
|
77
|
+
const data = await nadClient
|
|
78
|
+
.fetch({ url: url.toString(), timeout: 30_000 })
|
|
79
|
+
.then(pluckResponseData);
|
|
71
80
|
if (typeof data.count !== "number")
|
|
72
81
|
throw new Error("NAD count query returned no count field");
|
|
73
82
|
return data.count;
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"nad.js","sourceRoot":"","sources":["../../../../src/tools/fetch/nad.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAoCG;AAEH,OAAO,EAAE,UAAU,EAAE,SAAS,EAAE,QAAQ,EAAE,MAAM,SAAS,CAAA;AACzD,OAAO,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAA;AAC5C,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAEhC,OAAO,EAAE,UAAU,EAAE,MAAM,uBAAuB,CAAA;AAGlD,OAAO,EAAE,cAAc,EAAE,YAAY,EAAE,aAAa,EAAE,MAAM,eAAe,CAAA;AAE3E,MAAM,IAAI,GAAG,WAAW,CAAA;AAExB,MAAM,mBAAmB,GACxB,sIAAsI,CAAA;AA6CvI,KAAK,UAAU,SAAS,CAAC,QAAgB,EAAE,MAAc,EAAE,QAAgB;IAC1E,MAAM,GAAG,GAAG,IAAI,GAAG,CAAC,GAAG,mBAAmB,QAAQ,CAAC,CAAA;IACnD,GAAG,CAAC,YAAY,CAAC,GAAG,CAAC,OAAO,EAAE,oBAAoB,QAAQ,QAAQ,MAAM,EAAE,CAAC,CAAA;IAC3E,GAAG,CAAC,YAAY,CAAC,GAAG,CAAC,WAAW,EAAE,GAAG,CAAC,CAAA;IACtC,GAAG,CAAC,YAAY,CAAC,GAAG,CAAC,GAAG,EAAE,MAAM,CAAC,CAAA;IACjC,GAAG,CAAC,YAAY,CAAC,GAAG,CAAC,mBAAmB,EAAE,MAAM,CAAC,QAAQ,CAAC,CAAC,CAAA;IAE3D,MAAM,
|
|
1
|
+
{"version":3,"file":"nad.js","sourceRoot":"","sources":["../../../../src/tools/fetch/nad.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAoCG;AAEH,OAAO,EAAE,UAAU,EAAE,SAAS,EAAE,QAAQ,EAAE,MAAM,SAAS,CAAA;AACzD,OAAO,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAA;AAC5C,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAEhC,OAAO,EAAE,SAAS,EAAE,iBAAiB,EAAE,MAAM,qBAAqB,CAAA;AAClE,OAAO,EAAE,UAAU,EAAE,MAAM,uBAAuB,CAAA;AAGlD,OAAO,EAAE,cAAc,EAAE,YAAY,EAAE,aAAa,EAAE,MAAM,eAAe,CAAA;AAE3E,MAAM,IAAI,GAAG,WAAW,CAAA;AAExB,MAAM,mBAAmB,GACxB,sIAAsI,CAAA;AA6CvI;;;;GAIG;AACH,MAAM,SAAS,GAAG,IAAI,SAAS,CAAC;IAC/B,WAAW,EAAE,KAAK;IAClB,KAAK,EAAE,IAAI;IACX,KAAK,EAAE,EAAE,OAAO,EAAE,EAAE,iBAAiB,EAAE,UAAU,EAAE,EAAE;CACrD,CAAC,CAAA;AAEF,KAAK,UAAU,SAAS,CAAC,QAAgB,EAAE,MAAc,EAAE,QAAgB;IAC1E,MAAM,GAAG,GAAG,IAAI,GAAG,CAAC,GAAG,mBAAmB,QAAQ,CAAC,CAAA;IACnD,GAAG,CAAC,YAAY,CAAC,GAAG,CAAC,OAAO,EAAE,oBAAoB,QAAQ,QAAQ,MAAM,EAAE,CAAC,CAAA;IAC3E,GAAG,CAAC,YAAY,CAAC,GAAG,CAAC,WAAW,EAAE,GAAG,CAAC,CAAA;IACtC,GAAG,CAAC,YAAY,CAAC,GAAG,CAAC,GAAG,EAAE,MAAM,CAAC,CAAA;IACjC,GAAG,CAAC,YAAY,CAAC,GAAG,CAAC,mBAAmB,EAAE,MAAM,CAAC,QAAQ,CAAC,CAAC,CAAA;IAE3D,MAAM,IAAI,GAAG,MAAM,SAAS;SAC1B,KAAK,CAA6E;QAClF,GAAG,EAAE,GAAG,CAAC,QAAQ,EAAE;QACnB,OAAO,EAAE,OAAO;KAChB,CAAC;SACD,IAAI,CAAC,iBAAiB,CAAC,CAAA;IAEzB,IAAI,IAAI,CAAC,KAAK;QAAE,MAAM,IAAI,KAAK,CAAC,uBAAuB,QAAQ,IAAI,MAAM,KAAK,IAAI,CAAC,KAAK,CAAC,OAAO,EAAE,CAAC,CAAA;IAEnG,OAAO,CAAC,IAAI,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,UAAU,CAAC,CAAA;AACtD,CAAC;AAED,KAAK,UAAU,kBAAkB;IAChC,MAAM,GAAG,GAAG,IAAI,GAAG,CAAC,GAAG,mBAAmB,QAAQ,CAAC,CAAA;IACnD,GAAG,CAAC,YAAY,CAAC,GAAG,CAAC,OAAO,EAAE,KAAK,CAAC,CAAA;IACpC,GAAG,CAAC,YAAY,CAAC,GAAG,CAAC,iBAAiB,EAAE,MAAM,CAAC,CAAA;IAC/C,GAAG,CAAC,YAAY,CAAC,GAAG,CAAC,GAAG,EAAE,MAAM,CAAC,CAAA;IAEjC,MAAM,IAAI,GAAG,MAAM,SAAS;SAC1B,KAAK,CAAqB,EAAE,GAAG,EAAE,GAAG,CAAC,QAAQ,EAAE,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC;SACnE,IAAI,CAAC,iBAAiB,CAAC,CAAA;IAEzB,IAAI,OAAO,IAAI,CAAC,KAAK,KAAK,QAAQ;QAAE,MAAM,IAAI,KAAK,CAAC,yCAAyC,CAAC,CAAA;IAE9F,OAAO,IAAI,CAAC,KAAK,CAAA;AAClB,CAAC;AAED;;;;;GAKG;AACH,KAAK,UAAU,UAAU,CACxB,SAAiB,EACjB,UAAkB,EAClB,QAAgB,EAChB,QAAgB,EAChB,WAAmB,EACnB,MAA+B;IAE/B,MAAM,UAAU,GAA4B,EAAE,CAAA;IAE9C,KAAK,IAAI,MAAM,GAAG,UAAU,EAAE,MAAM,IAAI,QAAQ,EAAE,MAAM,IAAI,QAAQ,EAAE,CAAC;QACtE,UAAU,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,IAAI,CAAC,GAAG,CAAC,MAAM,GAAG,QAAQ,GAAG,CAAC,EAAE,QAAQ,CAAC,CAAC,CAAC,CAAA;IACrE,CAAC;IAED,yFAAyF;IACzF,MAAM,WAAW,GAAoD,UAAU,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,CAAC;QAC1F,IAAI,EAAE,EAAE;QACR,KAAK,EAAE,IAAI;KACX,CAAC,CAAC,CAAA;IAEH,IAAI,QAAQ,GAAG,CAAC,CAAA;IAEhB,MAAM,OAAO,GAAG,KAAK,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,IAAI,CAAC,GAAG,CAAC,WAAW,EAAE,UAAU,CAAC,MAAM,CAAC,EAAE,EAAE,KAAK,IAAI,EAAE;QAC3F,OAAO,IAAI,EAAE,CAAC;YACb,MAAM,IAAI,GAAG,QAAQ,EAAE,CAAA;YAEvB,IAAI,IAAI,IAAI,UAAU,CAAC,MAAM;gBAAE,OAAM;YACrC,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,GAAG,UAAU,CAAC,IAAI,CAAE,CAAA;YAEhC,IAAI,CAAC;gBACJ,WAAW,CAAC,IAAI,CAAE,CAAC,IAAI,GAAG,MAAM,SAAS,CAAC,CAAC,EAAE,CAAC,EAAE,QAAQ,CAAC,CAAA;YAC1D,CAAC;YAAC,OAAO,KAAK,EAAE,CAAC;gBAChB,WAAW,CAAC,IAAI,CAAE,CAAC,KAAK,GAAG,KAAc,CAAA;gBACzC,MAAM,EAAE,CAAC,cAAc,CAAC,IAAI,CAAC,KAAM,KAAe,CAAC,OAAO,EAAE,CAAC,CAAA;YAC9D,CAAC;QACF,CAAC;IACF,CAAC,CAAC,CAAA;IAEF,MAAM,OAAO,CAAC,GAAG,CAAC,OAAO,CAAC,CAAA;IAE1B,mFAAmF;IACnF,MAAM,KAAK,GAAa,EAAE,CAAA;IAC1B,IAAI,MAAM,GAAG,CAAC,CAAA;IAEd,KAAK,MAAM,EAAE,IAAI,EAAE,KAAK,EAAE,IAAI,WAAW,EAAE,CAAC;QAC3C,IAAI,KAAK,EAAE,CAAC;YACX,MAAM,EAAE,CAAA;YAER,SAAQ;QACT,CAAC;QAED,KAAK,MAAM,GAAG,IAAI,IAAI,EAAE,CAAC;YACxB,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,CAAA;QAChC,CAAC;IACF,CAAC;IAED,MAAM,SAAS,CAAC,SAAS,EAAE,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,IAAI,CAAC,CAAA;IAExE,OAAO,EAAE,WAAW,EAAE,KAAK,CAAC,MAAM,EAAE,MAAM,EAAE,CAAA;AAC7C,CAAC;AAED,KAAK,UAAU,iBAAiB,CAAC,OAAwB,EAAE,MAA+B;IACzF,MAAM,SAAS,GAAG,OAAO,CAAC,SAAS,IAAI,OAAO,CAAA;IAC9C,MAAM,QAAQ,GAAG,OAAO,CAAC,QAAQ,IAAI,IAAI,CAAA;IACzC,MAAM,WAAW,GAAG,OAAO,CAAC,WAAW,IAAI,CAAC,CAAA;IAC5C,MAAM,QAAQ,GAAG,OAAO,CAAC,QAAQ,IAAI,CAAC,CAAA;IAEtC,MAAM,QAAQ,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,IAAI,EAAE,eAAe,CAAC,CAAA;IAC7D,SAAS,CAAC,QAAQ,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;IAExC,MAAM,EAAE,CAAC,OAAO,IAAI,kBAAkB,CAAC,CAAA;IACvC,MAAM,EAAE,CAAC,gCAAgC,CAAC,CAAA;IAC1C,MAAM,UAAU,GAAG,MAAM,kBAAkB,EAAE,CAAA;IAC7C,MAAM,MAAM,GAAG,OAAO,CAAC,MAAM,IAAI,UAAU,CAAA;IAC3C,MAAM,EAAE,CAAC,oBAAoB,UAAU,CAAC,cAAc,EAAE,EAAE,CAAC,CAAA;IAC3D,MAAM,EAAE,CAAC,gBAAgB,QAAQ,CAAC,cAAc,EAAE,OAAO,MAAM,CAAC,cAAc,EAAE,EAAE,CAAC,CAAA;IACnF,MAAM,EAAE,CAAC,iBAAiB,SAAS,gBAAgB,QAAQ,kBAAkB,WAAW,EAAE,CAAC,CAAA;IAE3F,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,OAAO,GAAG,CAAC,CAAA;IACf,IAAI,YAAY,GAAG,CAAC,CAAA;IACpB,IAAI,WAAW,GAAG,CAAC,CAAA;IACnB,MAAM,WAAW,GAAa,EAAE,CAAA;IAEhC,KAAK,IAAI,MAAM,GAAG,QAAQ,EAAE,MAAM,IAAI,MAAM,EAAE,MAAM,IAAI,SAAS,EAAE,CAAC;QACnE,MAAM,QAAQ,GAAG,IAAI,CAAC,GAAG,CAAC,MAAM,GAAG,SAAS,GAAG,CAAC,EAAE,MAAM,CAAC,CAAA;QACzD,MAAM,SAAS,GAAG,QAAQ,MAAM,IAAI,QAAQ,EAAE,CAAA;QAC9C,MAAM,SAAS,GAAG,IAAI,CAAC,QAAQ,EAAE,GAAG,SAAS,SAAS,CAAC,CAAA;QACvD,MAAM,YAAY,GAAG,IAAI,CAAC,QAAQ,EAAE,GAAG,SAAS,gBAAgB,CAAC,CAAA;QAEjE,qFAAqF;QACrF,2FAA2F;QAC3F,IAAI,UAAU,CAAC,SAAS,CAAC,EAAE,CAAC;YAC3B,MAAM,QAAQ,GAAG,MAAM,YAAY,CAAgB,YAAY,CAAC,CAAA;YAEhE,IAAI,QAAQ,EAAE,QAAQ,EAAE,CAAC;gBACxB,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;QACF,CAAC;QAED,MAAM,EAAE,CAAC,cAAc,SAAS,MAAM,CAAC,CAAA;QACvC,MAAM,EAAE,GAAG,IAAI,CAAC,GAAG,EAAE,CAAA;QACrB,MAAM,EAAE,WAAW,EAAE,MAAM,EAAE,GAAG,MAAM,UAAU,CAAC,SAAS,EAAE,MAAM,EAAE,QAAQ,EAAE,QAAQ,EAAE,WAAW,EAAE,MAAM,CAAC,CAAA;QAC5G,MAAM,OAAO,GAAG,CAAC,CAAC,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE,CAAC,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,CAAA;QACrD,MAAM,KAAK,GAAG,QAAQ,CAAC,SAAS,CAAC,CAAC,IAAI,CAAA;QACtC,MAAM,GAAG,GAAG,MAAM,UAAU,CAAC,SAAS,CAAC,CAAA;QAEvC,MAAM,QAAQ,GAAkB;YAC/B,UAAU,EAAE,mBAAmB;YAC/B,SAAS,EAAE,CAAC,MAAM,EAAE,QAAQ,CAAC;YAC7B,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;YACvC,QAAQ,EAAE,GAAG,SAAS,SAAS;YAC/B,MAAM,EAAE,GAAG;YACX,KAAK;YACL,YAAY,EAAE,WAAW;YACzB,WAAW,EAAE,MAAM;YACnB,QAAQ,EAAE,MAAM,KAAK,CAAC;SACtB,CAAA;QAED,MAAM,aAAa,CAAC,YAAY,EAAE,QAAQ,CAAC,CAAA;QAE3C,MAAM,MAAM,GAAG,MAAM,KAAK,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,KAAK,MAAM,cAAc,CAAA;QAE7D,MAAM,EAAE,CACP,OAAO,MAAM,KAAK,WAAW,CAAC,cAAc,EAAE,eAAe,OAAO,OAAO,CAAC,KAAK,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CACjH,CAAA;QAED,OAAO,EAAE,CAAA;QACT,YAAY,IAAI,WAAW,CAAA;QAC3B,WAAW,IAAI,MAAM,CAAA;QAErB,IAAI,MAAM,GAAG,CAAC,EAAE,CAAC;YAChB,WAAW,CAAC,IAAI,CAAC,SAAS,CAAC,CAAA;QAC5B,CAAC;IACF,CAAC;IAED,MAAM,EAAE,CAAC,+BAA+B,CAAC,CAAA;IACzC,MAAM,EAAE,CAAC,mBAAmB,OAAO,cAAc,OAAO,EAAE,CAAC,CAAA;IAC3D,MAAM,EAAE,CAAC,kBAAkB,YAAY,CAAC,cAAc,EAAE,EAAE,CAAC,CAAA;IAC3D,MAAM,EAAE,CAAC,kBAAkB,WAAW,EAAE,CAAC,CAAA;IACzC,MAAM,EAAE,CAAC,kBAAkB,QAAQ,EAAE,CAAC,CAAA;IAEtC,gGAAgG;IAChG,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,MAAM,EAAE,WAAW,EAAE,WAAW,EAAE,CAAA;AAC9D,CAAC;AAED,KAAK,UAAU,QAAQ,CAAC,OAAwB,EAAE,MAA+B;IAChF,IAAI,CAAC,OAAO,CAAC,MAAM,EAAE,CAAC;QACrB,MAAM,IAAI,KAAK,CACd,8DAA8D;YAC7D,mFAAmF;YACnF,+DAA+D,CAChE,CAAA;IACF,CAAC;IAED,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,IAAI,CAAC,CAAA;IAC3C,SAAS,CAAC,OAAO,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;IACvC,MAAM,QAAQ,GAAG,IAAI,GAAG,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC,QAAQ,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,IAAI,SAAS,CAAA;IAC/E,MAAM,QAAQ,GAAG,IAAI,CAAC,OAAO,EAAE,QAAQ,CAAC,CAAA;IAExC,MAAM,EAAE,CAAC,OAAO,IAAI,MAAM,QAAQ,EAAE,CAAC,CAAA;IACrC,MAAM,EAAE,CAAC,UAAU,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,GAAG,OAAO,CAAC,MAAM,CAAC,MAAM,GAAG,GAAG,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAA;IAE3F,MAAM,EAAE,KAAK,EAAE,GAAG,MAAM,cAAc,CAAC,EAAE,GAAG,EAAE,OAAO,CAAC,MAAM,EAAE,IAAI,EAAE,QAAQ,EAAE,SAAS,EAAE,CAAC,GAAG,IAAI,GAAG,IAAI,EAAE,MAAM,EAAE,CAAC,CAAA;IAEnH,MAAM,GAAG,GAAG,MAAM,UAAU,CAAC,QAAQ,CAAC,CAAA;IAEtC,MAAM,aAAa,CAAC,IAAI,CAAC,OAAO,EAAE,eAAe,CAAC,EAAE;QACnD,UAAU,EAAE,OAAO,CAAC,MAAM;QAC1B,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;QACvC,QAAQ;QACR,MAAM,EAAE,GAAG;QACX,KAAK;KACL,CAAC,CAAA;IAEF,MAAM,EAAE,CAAC,OAAO,CAAC,KAAK,GAAG,IAAI,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe,GAAG,EAAE,CAAC,CAAA;IAE5E,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,WAAW,EAAE,EAAE,EAAE,CAAA;AAC9D,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,QAAQ,CAAC,OAAwB,EAAE,MAA+B;IACvF,MAAM,IAAI,GAAG,OAAO,CAAC,IAAI,IAAI,eAAe,CAAA;IAE5C,IAAI,IAAI,KAAK,eAAe,EAAE,CAAC;QAC9B,OAAO,iBAAiB,CAAC,OAAO,EAAE,MAAM,CAAC,CAAA;IAC1C,CAAC;IAED,IAAI,IAAI,KAAK,MAAM,EAAE,CAAC;QACrB,OAAO,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC,CAAA;IACjC,CAAC;IAED,MAAM,IAAI,KAAK,CAAC,iBAAiB,MAAM,CAAC,IAAI,CAAC,iCAAiC,CAAC,CAAA;AAChF,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"nppes.d.ts","sourceRoot":"","sources":["../../../../src/tools/fetch/nppes.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;GAqBG;
|
|
1
|
+
{"version":3,"file":"nppes.d.ts","sourceRoot":"","sources":["../../../../src/tools/fetch/nppes.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;GAqBG;AAaH,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAAE,MAAM,eAAe,CAAA;AAOnE,MAAM,MAAM,iBAAiB,GAAG,gBAAgB,CAAA;AA2ChD,wBAAsB,UAAU,CAAC,OAAO,EAAE,iBAAiB,EAAE,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAAG,OAAO,CAAC,YAAY,CAAC,CAyFnH"}
|
|
@@ -22,15 +22,13 @@
|
|
|
22
22
|
*/
|
|
23
23
|
/* oxlint-disable sister-software/prefer-region-over-marks -- these markers label steps inside one
|
|
24
24
|
procedure, not sections of declarations. A region there folds nothing a reader wants folded. */
|
|
25
|
-
import { execFile } from "node:child_process";
|
|
26
25
|
import { existsSync, mkdirSync, statSync } from "node:fs";
|
|
27
26
|
import { rm } from "node:fs/promises";
|
|
28
|
-
import { join } from "node:path";
|
|
29
|
-
import {
|
|
27
|
+
import { basename, join } from "node:path";
|
|
28
|
+
import { APIClient, pluckResponseData } from "@mailwoman/core/api";
|
|
29
|
+
import { extractZipEntry, listZipEntries } from "@mailwoman/core/fs/zip";
|
|
30
30
|
import { sha256File } from "@mailwoman/core/utils";
|
|
31
|
-
import { TextSpliterator } from "spliterator";
|
|
32
31
|
import { downloadToFile, readManifest, writeManifest } from "./download.js";
|
|
33
|
-
const execFileAsync = promisify(execFile);
|
|
34
32
|
const INDEX_URL = "https://download.cms.gov/nppes/NPI_Files.html";
|
|
35
33
|
const BASE_URL = "https://download.cms.gov/nppes";
|
|
36
34
|
const SLUG = "usgov-nppes";
|
|
@@ -39,13 +37,14 @@ const SLUG = "usgov-nppes";
|
|
|
39
37
|
* `NPPES_Data_Dissemination_<Month>_<Year>*.zip`; weekly files carry a `MMDDYY_MMDDYY` date range, which we exclude.
|
|
40
38
|
*/
|
|
41
39
|
async function discoverLatestZip() {
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
|
|
46
|
-
|
|
47
|
-
|
|
48
|
-
|
|
40
|
+
// `responseType: "text"` — the index is HTML, scraped by regex below.
|
|
41
|
+
const html = await new APIClient({
|
|
42
|
+
displayName: "nppes-index",
|
|
43
|
+
retry: true,
|
|
44
|
+
axios: { headers: { "Accept-Encoding": "gzip, br" } },
|
|
45
|
+
})
|
|
46
|
+
.fetch({ url: INDEX_URL, responseType: "text", timeout: 60_000 })
|
|
47
|
+
.then(pluckResponseData);
|
|
49
48
|
for (const match of html.matchAll(/NPPES_Data_Dissemination_[A-Za-z]+_\d{4}[^"]*\.zip/g)) {
|
|
50
49
|
const name = match[0];
|
|
51
50
|
if (name && !/\d{6}_\d{6}/.test(name))
|
|
@@ -54,16 +53,12 @@ async function discoverLatestZip() {
|
|
|
54
53
|
return undefined;
|
|
55
54
|
}
|
|
56
55
|
/**
|
|
57
|
-
*
|
|
56
|
+
* The main registry CSV (npidata_pfile_*.csv), which the archive also carries alongside a header file and a per-month
|
|
57
|
+
* change file.
|
|
58
58
|
*/
|
|
59
59
|
async function findNpidataCSV(zipPath) {
|
|
60
|
-
const
|
|
61
|
-
|
|
62
|
-
const match = /npidata_pfile\S+\.csv/i.exec(line);
|
|
63
|
-
if (match?.[0])
|
|
64
|
-
return match[0];
|
|
65
|
-
}
|
|
66
|
-
return undefined;
|
|
60
|
+
const entries = await listZipEntries(zipPath);
|
|
61
|
+
return entries.find((entry) => /npidata_pfile\S+\.csv/i.test(entry.name))?.name;
|
|
67
62
|
}
|
|
68
63
|
export async function fetchNPPES(options, report) {
|
|
69
64
|
const destDir = join(options.outRoot, SLUG);
|
|
@@ -107,8 +102,8 @@ export async function fetchNPPES(options, report) {
|
|
|
107
102
|
return { fetched: 0, skipped: 0, failed: 1, failedCodes: [SLUG] };
|
|
108
103
|
}
|
|
109
104
|
report?.(` Extracting: ${csvName}`);
|
|
110
|
-
|
|
111
|
-
|
|
105
|
+
const csvDest = join(destDir, basename(csvName));
|
|
106
|
+
await extractZipEntry(zipDest, csvName, csvDest);
|
|
112
107
|
const csvSize = statSync(csvDest).size;
|
|
113
108
|
const csvSha = await sha256File(csvDest);
|
|
114
109
|
report?.(` CSV size: ${(csvSize / 1024 / 1024).toFixed(1)} MB`);
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"nppes.js","sourceRoot":"","sources":["../../../../src/tools/fetch/nppes.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;GAqBG;AAEH;kGACkG;AAElG,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"nppes.js","sourceRoot":"","sources":["../../../../src/tools/fetch/nppes.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;GAqBG;AAEH;kGACkG;AAElG,OAAO,EAAE,UAAU,EAAE,SAAS,EAAE,QAAQ,EAAE,MAAM,SAAS,CAAA;AACzD,OAAO,EAAE,EAAE,EAAE,MAAM,kBAAkB,CAAA;AACrC,OAAO,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAE1C,OAAO,EAAE,SAAS,EAAE,iBAAiB,EAAE,MAAM,qBAAqB,CAAA;AAClE,OAAO,EAAE,eAAe,EAAE,cAAc,EAAE,MAAM,wBAAwB,CAAA;AACxE,OAAO,EAAE,UAAU,EAAE,MAAM,uBAAuB,CAAA;AAGlD,OAAO,EAAE,cAAc,EAAE,YAAY,EAAE,aAAa,EAAE,MAAM,eAAe,CAAA;AAE3E,MAAM,SAAS,GAAG,+CAA+C,CAAA;AACjE,MAAM,QAAQ,GAAG,gCAAgC,CAAA;AACjD,MAAM,IAAI,GAAG,aAAa,CAAA;AAY1B;;;GAGG;AACH,KAAK,UAAU,iBAAiB;IAC/B,sEAAsE;IACtE,MAAM,IAAI,GAAG,MAAM,IAAI,SAAS,CAAC;QAChC,WAAW,EAAE,aAAa;QAC1B,KAAK,EAAE,IAAI;QACX,KAAK,EAAE,EAAE,OAAO,EAAE,EAAE,iBAAiB,EAAE,UAAU,EAAE,EAAE;KACrD,CAAC;SACA,KAAK,CAAS,EAAE,GAAG,EAAE,SAAS,EAAE,YAAY,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC;SACxE,IAAI,CAAC,iBAAiB,CAAC,CAAA;IAEzB,KAAK,MAAM,KAAK,IAAI,IAAI,CAAC,QAAQ,CAAC,qDAAqD,CAAC,EAAE,CAAC;QAC1F,MAAM,IAAI,GAAG,KAAK,CAAC,CAAC,CAAC,CAAA;QAErB,IAAI,IAAI,IAAI,CAAC,aAAa,CAAC,IAAI,CAAC,IAAI,CAAC;YAAE,OAAO,IAAI,CAAA;IACnD,CAAC;IAED,OAAO,SAAS,CAAA;AACjB,CAAC;AAED;;;GAGG;AACH,KAAK,UAAU,cAAc,CAAC,OAAe;IAC5C,MAAM,OAAO,GAAG,MAAM,cAAc,CAAC,OAAO,CAAC,CAAA;IAE7C,OAAO,OAAO,CAAC,IAAI,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,wBAAwB,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,EAAE,IAAI,CAAA;AAChF,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,UAAU,CAAC,OAA0B,EAAE,MAA+B;IAC3F,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,CAAC,OAAO,EAAE,IAAI,CAAC,CAAA;IAC3C,SAAS,CAAC,OAAO,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;IACvC,MAAM,YAAY,GAAG,IAAI,CAAC,OAAO,EAAE,eAAe,CAAC,CAAA;IAEnD,MAAM,EAAE,CAAC,OAAO,IAAI,EAAE,CAAC,CAAA;IACvB,MAAM,EAAE,CAAC,kDAAkD,SAAS,MAAM,CAAC,CAAA;IAE3E,MAAM,WAAW,GAAG,MAAM,iBAAiB,EAAE,CAAA;IAE7C,IAAI,CAAC,WAAW,EAAE,CAAC;QAClB,MAAM,EAAE,CAAC,4CAA4C,SAAS,EAAE,CAAC,CAAA;QAEjE,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,WAAW,EAAE,CAAC,IAAI,CAAC,EAAE,CAAA;IAClE,CAAC;IAED,MAAM,MAAM,GAAG,GAAG,QAAQ,IAAI,WAAW,EAAE,CAAA;IAC3C,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,EAAE,WAAW,CAAC,CAAA;IAC1C,MAAM,EAAE,CAAC,uBAAuB,WAAW,EAAE,CAAC,CAAA;IAE9C,qEAAqE;IACrE,oBAAoB;IACpB,MAAM,QAAQ,GAAG,MAAM,YAAY,CAA0B,YAAY,CAAC,CAAA;IAE1E,IAAI,QAAQ,EAAE,MAAM,IAAI,QAAQ,CAAC,QAAQ,EAAE,CAAC;QAC3C,MAAM,YAAY,GAAG,IAAI,CAAC,OAAO,EAAE,QAAQ,CAAC,QAAQ,CAAC,CAAA;QAErD,IAAI,UAAU,CAAC,YAAY,CAAC,IAAI,CAAC,MAAM,UAAU,CAAC,YAAY,CAAC,CAAC,KAAK,QAAQ,CAAC,MAAM,EAAE,CAAC;YACtF,MAAM,EAAE,CAAC,oEAAoE,CAAC,CAAA;YAE9E,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,WAAW,EAAE,EAAE,EAAE,CAAA;QAC9D,CAAC;IACF,CAAC;IAED,gDAAgD;IAEhD,MAAM,EAAE,CAAC,iBAAiB,MAAM,MAAM,CAAC,CAAA;IAEvC,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,GAAG,MAAM,cAAc,CAAC;QAC/C,GAAG,EAAE,MAAM;QACX,IAAI,EAAE,OAAO;QACb,SAAS,EAAE,SAAS;QACpB,OAAO,EAAE,EAAE,iBAAiB,EAAE,UAAU,EAAE;QAC1C,MAAM;KACN,CAAC,CAAA;IAEF,MAAM,EAAE,CAAC,iBAAiB,CAAC,OAAO,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,KAAK,CAAC,CAAA;IAElE,iEAAiE;IAEjE,MAAM,EAAE,CAAC,6CAA6C,CAAC,CAAA;IACvD,MAAM,OAAO,GAAG,MAAM,cAAc,CAAC,OAAO,CAAC,CAAA;IAE7C,IAAI,CAAC,OAAO,EAAE,CAAC;QACd,MAAM,EAAE,CAAC,iDAAiD,CAAC,CAAA;QAE3D,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,WAAW,EAAE,CAAC,IAAI,CAAC,EAAE,CAAA;IAClE,CAAC;IAED,MAAM,EAAE,CAAC,iBAAiB,OAAO,EAAE,CAAC,CAAA;IAEpC,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,EAAE,QAAQ,CAAC,OAAO,CAAC,CAAC,CAAA;IAEhD,MAAM,eAAe,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC,CAAA;IAChD,MAAM,OAAO,GAAG,QAAQ,CAAC,OAAO,CAAC,CAAC,IAAI,CAAA;IACtC,MAAM,MAAM,GAAG,MAAM,UAAU,CAAC,OAAO,CAAC,CAAA;IACxC,MAAM,EAAE,CAAC,eAAe,CAAC,OAAO,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,KAAK,CAAC,CAAA;IAEhE,wCAAwC;IAExC,MAAM,EAAE,CAAC,OAAO,EAAE,EAAE,KAAK,EAAE,IAAI,EAAE,CAAC,CAAA;IAClC,MAAM,EAAE,CAAC,0BAA0B,CAAC,CAAA;IAEpC,gEAAgE;IAEhE,MAAM,QAAQ,GAAmB;QAChC,UAAU,EAAE,MAAM;QAClB,aAAa,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;QACvC,QAAQ,EAAE,OAAO;QACjB,MAAM,EAAE,MAAM;QACd,KAAK,EAAE,OAAO;KACd,CAAA;IAED,MAAM,aAAa,CAAC,YAAY,EAAE,QAAQ,CAAC,CAAA;IAE3C,MAAM,EAAE,CAAC,OAAO,CAAC,OAAO,GAAG,IAAI,GAAG,IAAI,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe,MAAM,EAAE,CAAC,CAAA;IAC1E,MAAM,EAAE,CAAC,yBAAyB,YAAY,EAAE,CAAC,CAAA;IAEjD,OAAO,EAAE,OAAO,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,MAAM,EAAE,CAAC,EAAE,WAAW,EAAE,EAAE,EAAE,CAAA;AAC9D,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"openaddresses.d.ts","sourceRoot":"","sources":["../../../../src/tools/fetch/openaddresses.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAmDG;
|
|
1
|
+
{"version":3,"file":"openaddresses.d.ts","sourceRoot":"","sources":["../../../../src/tools/fetch/openaddresses.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAmDG;AAkBH,OAAO,KAAK,EAAE,gBAAgB,EAAE,YAAY,EAAE,MAAM,eAAe,CAAA;AAkCnE,MAAM,WAAW,yBAA0B,SAAQ,gBAAgB;IAClE;;OAEG;IACH,OAAO,CAAC,EAAE,MAAM,CAAA;CAChB;AA6FD,wBAAsB,kBAAkB,CACvC,OAAO,EAAE,yBAAyB,EAClC,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,YAAY,CAAC,CAuMvB"}
|
|
@@ -59,7 +59,9 @@ import { Readable } from "node:stream";
|
|
|
59
59
|
import { pipeline } from "node:stream/promises";
|
|
60
60
|
import { setTimeout as sleep } from "node:timers/promises";
|
|
61
61
|
import { promisify } from "node:util";
|
|
62
|
+
import { APIClient, isSuccessStatus } from "@mailwoman/core/api";
|
|
62
63
|
import { $private } from "@mailwoman/core/env";
|
|
64
|
+
import { ByteFormatter } from "@mailwoman/core/fs/utils";
|
|
63
65
|
import { sha256File } from "@mailwoman/core/utils";
|
|
64
66
|
import { isTransientStatus, writeManifest } from "./download.js";
|
|
65
67
|
/**
|
|
@@ -74,7 +76,6 @@ const HTTP_OK = 200;
|
|
|
74
76
|
* Smallest plausible OpenAddresses shard. Below 10 KiB the file is a stub or an error body.
|
|
75
77
|
*/
|
|
76
78
|
const MIN_PLAUSIBLE_SHARD_BYTES = 10_240;
|
|
77
|
-
const BYTES_PER_KIB = 1024;
|
|
78
79
|
const execFileAsync = promisify(execFile);
|
|
79
80
|
const OA_BASE = "https://batch.openaddresses.io";
|
|
80
81
|
/**
|
|
@@ -103,16 +104,6 @@ async function countLines(path) {
|
|
|
103
104
|
}
|
|
104
105
|
return count;
|
|
105
106
|
}
|
|
106
|
-
function humanBytes(bytes) {
|
|
107
|
-
const units = ["B", "KiB", "MiB", "GiB", "TiB"];
|
|
108
|
-
let value = bytes;
|
|
109
|
-
let unit = 0;
|
|
110
|
-
while (value >= BYTES_PER_KIB && unit < units.length - 1) {
|
|
111
|
-
value /= 1024;
|
|
112
|
-
unit++;
|
|
113
|
-
}
|
|
114
|
-
return `${value.toFixed(unit === 0 ? 0 : 1)}${units[unit]}`;
|
|
115
|
-
}
|
|
116
107
|
/**
|
|
117
108
|
* Stream an HTTP download to disk, returning the final HTTP status (0 on network error after retries). Follows
|
|
118
109
|
* redirects (the OA download endpoint 302s to a pre-signed S3 URL).
|
|
@@ -198,15 +189,25 @@ The Canada collection (ca) is ~2 GiB compressed / ~7 GiB uncompressed
|
|
|
198
189
|
let collectionID = OA_COLLECTION_IDS[country];
|
|
199
190
|
if (collectionID === undefined) {
|
|
200
191
|
report?.(`Unknown country code '${country}'. Fetching collection list to find ID...`);
|
|
201
|
-
|
|
202
|
-
|
|
203
|
-
|
|
192
|
+
// The collections API only. The COLLECTION ARCHIVES stay on raw `fetch` — they stream multi-gigabyte
|
|
193
|
+
// bodies straight to disk, where response caching is nonsense and axios would buffer them in memory.
|
|
194
|
+
const res = await new APIClient({
|
|
195
|
+
displayName: "openaddresses-api",
|
|
196
|
+
retry: true,
|
|
197
|
+
axios: { headers: { Authorization: `Bearer ${token}`, "Accept-Encoding": "gzip, br" } },
|
|
198
|
+
})
|
|
199
|
+
// `validateStatus` keeps a non-2xx as a RESPONSE rather than a throw: the caller reports the status and
|
|
200
|
+
// returns `fail(country)`, a graceful path this must not turn into an exception.
|
|
201
|
+
.fetch({
|
|
202
|
+
url: `${OA_BASE}/api/collections`,
|
|
203
|
+
timeout: 30_000,
|
|
204
|
+
validateStatus: () => true,
|
|
204
205
|
});
|
|
205
|
-
if (!res.
|
|
206
|
+
if (!isSuccessStatus(res.status)) {
|
|
206
207
|
report?.(`ERROR: GET /api/collections returned HTTP ${res.status}.`);
|
|
207
208
|
return fail(country);
|
|
208
209
|
}
|
|
209
|
-
const collections =
|
|
210
|
+
const collections = res.data;
|
|
210
211
|
const match = collections.find((item) => item.name === country);
|
|
211
212
|
if (match?.id === undefined) {
|
|
212
213
|
report?.(`ERROR: Could not find a collection named '${country}' in GET /api/collections.`);
|
|
@@ -303,7 +304,7 @@ URL tried: ${OA_BASE}/api/collections/${collectionID}/download
|
|
|
303
304
|
notes: "batch.openaddresses.io requires a free registered account for downloads. License is mixed per-row; use the openaddresses adapter with allowShareAlike=false (default) to filter Tier-C rows.",
|
|
304
305
|
};
|
|
305
306
|
await writeManifest(manifestPath, manifest);
|
|
306
|
-
report?.(` ✓ ${
|
|
307
|
+
report?.(` ✓ ${ByteFormatter.formatIEC(size)} rows=${rowCount} sha256=${sha}`);
|
|
307
308
|
report?.(` MANIFEST written to ${manifestPath}`);
|
|
308
309
|
report?.(`=== done`);
|
|
309
310
|
report?.(`Feed to the adapter:`);
|