@mailwoman/corpus 8.6.0 → 9.1.0
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 +214 -0
- package/data/sub-venue-lexicon.json +18269 -0
- package/out/src/adapters/ban/adapter.d.ts +5 -4
- package/out/src/adapters/ban/adapter.d.ts.map +1 -1
- package/out/src/adapters/ban/adapter.js +62 -69
- package/out/src/adapters/ban/adapter.js.map +1 -1
- package/out/src/adapters/ban/street-decompose.d.ts.map +1 -1
- package/out/src/adapters/ban/street-decompose.js +18 -25
- package/out/src/adapters/ban/street-decompose.js.map +1 -1
- package/out/src/adapters/fcc-bdc/adapter.d.ts +1 -7
- package/out/src/adapters/fcc-bdc/adapter.d.ts.map +1 -1
- package/out/src/adapters/fcc-bdc/adapter.js +4 -26
- 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 +72 -78
- 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 +46 -51
- 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 +6 -9
- package/out/src/adapters/gnaf/adapter.js.map +1 -1
- package/out/src/adapters/gnaf/assemble.d.ts.map +1 -1
- package/out/src/adapters/gnaf/assemble.js +7 -12
- 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 +5 -10
- 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 +5 -9
- 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 +57 -75
- 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 +60 -78
- 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 +69 -87
- 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 +71 -89
- 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 +10 -18
- 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/tiger/street-decompose.d.ts.map +1 -1
- package/out/src/adapters/tiger/street-decompose.js +18 -27
- package/out/src/adapters/tiger/street-decompose.js.map +1 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +4 -4
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +64 -82
- 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 +62 -84
- 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 +59 -66
- 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 +6 -9
- 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 +60 -78
- 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 +53 -73
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -1
- package/out/src/{adapter.d.ts → adapters/utils/index.d.ts} +43 -2
- package/out/src/adapters/utils/index.d.ts.map +1 -0
- package/out/src/{adapter.js → adapters/utils/index.js} +47 -2
- 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 +24 -6
- package/out/src/adapters/wof-admin-jp/adapter.js.map +1 -1
- package/out/src/adapters/wof-admin-json/adapter.d.ts +2 -2
- package/out/src/adapters/wof-admin-json/adapter.d.ts.map +1 -1
- package/out/src/adapters/wof-admin-json/adapter.js +2 -2
- package/out/src/adapters/wof-admin-json/adapter.js.map +1 -1
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts +2 -2
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +1 -1
- package/out/src/adapters/wof-postalcode-json/adapter.js +2 -2
- package/out/src/adapters/wof-postalcode-json/adapter.js.map +1 -1
- package/out/src/build.d.ts +3 -4
- package/out/src/build.d.ts.map +1 -1
- package/out/src/build.js +6 -8
- 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 +8 -0
- package/out/src/parquet-wrapper/reader.d.ts.map +1 -1
- package/out/src/parquet-wrapper/reader.js +16 -0
- package/out/src/parquet-wrapper/reader.js.map +1 -1
- package/out/src/parquet-wrapper/schema.d.ts +4 -0
- package/out/src/parquet-wrapper/schema.d.ts.map +1 -1
- package/out/src/parquet-wrapper/schema.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 +5 -4
- package/out/src/shard-recipes/anchor-absorption.js.map +1 -1
- 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 +75 -75
- package/out/src/shard-recipes/country-balanced.js.map +1 -1
- package/out/src/shard-recipes/fr-admin-split.js +2 -2
- package/out/src/shard-recipes/fr-admin-split.js.map +1 -1
- package/out/src/shard-recipes/fr-fragment.d.ts.map +1 -1
- package/out/src/shard-recipes/fr-fragment.js +8 -5
- package/out/src/shard-recipes/fr-fragment.js.map +1 -1
- package/out/src/shard-recipes/fr-lieudit.js +2 -2
- 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 +18 -72
- 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 +17 -70
- 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 +4 -1
- package/out/src/shard-recipes/index.js.map +1 -1
- package/out/src/shard-recipes/intersection.d.ts +2 -2
- package/out/src/shard-recipes/intersection.d.ts.map +1 -1
- package/out/src/shard-recipes/intersection.js +28 -72
- 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 +25 -35
- package/out/src/shard-recipes/locale.js.map +1 -1
- package/out/src/shard-recipes/no-fragment.d.ts.map +1 -1
- package/out/src/shard-recipes/no-fragment.js +8 -5
- package/out/src/shard-recipes/no-fragment.js.map +1 -1
- package/out/src/shard-recipes/no-street-led.d.ts.map +1 -1
- package/out/src/shard-recipes/no-street-led.js +8 -5
- package/out/src/shard-recipes/no-street-led.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 +3 -3
- package/out/src/shard-recipes/po-box-cedex.d.ts.map +1 -1
- package/out/src/shard-recipes/po-box-cedex.js +101 -127
- 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/scaffold.d.ts +58 -9
- package/out/src/shard-recipes/scaffold.d.ts.map +1 -1
- package/out/src/shard-recipes/scaffold.js +87 -29
- 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 +253 -111
- 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 +228 -0
- package/out/src/shard-recipes/sub-venue-sources.d.ts.map +1 -0
- package/out/src/shard-recipes/sub-venue-sources.js +664 -0
- package/out/src/shard-recipes/sub-venue-sources.js.map +1 -0
- package/out/src/shard-recipes/sub-venue.d.ts +269 -0
- package/out/src/shard-recipes/sub-venue.d.ts.map +1 -0
- package/out/src/shard-recipes/sub-venue.js +709 -0
- package/out/src/shard-recipes/sub-venue.js.map +1 -0
- package/out/src/shard-recipes/unit.d.ts +1 -1
- package/out/src/shard-recipes/unit.d.ts.map +1 -1
- package/out/src/shard-recipes/unit.js +26 -74
- 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} +4 -4
- 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} +2 -2
- 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} +4 -15
- 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 +4 -8
- package/out/src/tools/align-shard.js.map +1 -1
- package/out/src/tools/audit.d.ts.map +1 -1
- package/out/src/tools/audit.js +4 -4
- package/out/src/tools/audit.js.map +1 -1
- package/out/src/tools/corpus-stats.d.ts +2 -2
- package/out/src/tools/corpus-stats.d.ts.map +1 -1
- package/out/src/tools/corpus-stats.js +18 -31
- package/out/src/tools/corpus-stats.js.map +1 -1
- package/out/src/tools/fetch/download.d.ts.map +1 -1
- package/out/src/tools/fetch/download.js +5 -6
- package/out/src/tools/fetch/download.js.map +1 -1
- package/out/src/tools/fetch/imls-pls.d.ts.map +1 -1
- package/out/src/tools/fetch/imls-pls.js +3 -15
- package/out/src/tools/fetch/imls-pls.js.map +1 -1
- package/out/src/tools/fetch/index.d.ts +14 -1
- package/out/src/tools/fetch/index.d.ts.map +1 -1
- package/out/src/tools/fetch/index.js +14 -1
- package/out/src/tools/fetch/index.js.map +1 -1
- package/out/src/tools/fetch/nad.d.ts +1 -1
- package/out/src/tools/fetch/nad.js +1 -1
- package/out/src/tools/fetch/nppes.d.ts.map +1 -1
- package/out/src/tools/fetch/nppes.js +8 -14
- package/out/src/tools/fetch/nppes.js.map +1 -1
- package/out/src/tools/fetch/openaddresses.d.ts +1 -1
- package/out/src/tools/fetch/openaddresses.js +1 -1
- package/out/src/tools/fetch/ourairports.d.ts +45 -0
- package/out/src/tools/fetch/ourairports.d.ts.map +1 -0
- package/out/src/tools/fetch/ourairports.js +123 -0
- package/out/src/tools/fetch/ourairports.js.map +1 -0
- package/out/src/tools/fetch/wikidata-subvenue.d.ts +171 -0
- package/out/src/tools/fetch/wikidata-subvenue.d.ts.map +1 -0
- package/out/src/tools/fetch/wikidata-subvenue.js +275 -0
- package/out/src/tools/fetch/wikidata-subvenue.js.map +1 -0
- package/out/src/tools/golden-expand.d.ts.map +1 -1
- package/out/src/tools/golden-expand.js +18 -16
- package/out/src/tools/golden-expand.js.map +1 -1
- package/out/src/tools/golden-promote.d.ts.map +1 -1
- package/out/src/tools/golden-promote.js +12 -6
- package/out/src/tools/golden-promote.js.map +1 -1
- package/out/src/tools/golden-relabel-street.d.ts +196 -0
- package/out/src/tools/golden-relabel-street.d.ts.map +1 -0
- package/out/src/tools/golden-relabel-street.js +440 -0
- package/out/src/tools/golden-relabel-street.js.map +1 -0
- package/out/src/tools/index.d.ts +4 -0
- package/out/src/tools/index.d.ts.map +1 -1
- package/out/src/tools/index.js +4 -0
- package/out/src/tools/index.js.map +1 -1
- package/out/src/tools/jsonl-to-parquet.d.ts.map +1 -1
- package/out/src/tools/jsonl-to-parquet.js +3 -2
- package/out/src/tools/jsonl-to-parquet.js.map +1 -1
- package/out/src/tools/lint-shard-vocab.d.ts.map +1 -1
- package/out/src/tools/lint-shard-vocab.js +3 -2
- package/out/src/tools/lint-shard-vocab.js.map +1 -1
- package/out/src/tools/lint-shard.d.ts +3 -3
- package/out/src/tools/lint-shard.d.ts.map +1 -1
- package/out/src/tools/lint-shard.js +23 -32
- package/out/src/tools/lint-shard.js.map +1 -1
- package/out/src/tools/overlay-manifest.d.ts.map +1 -1
- package/out/src/tools/overlay-manifest.js +2 -1
- package/out/src/tools/overlay-manifest.js.map +1 -1
- package/out/src/tools/overture-subvenue.d.ts +112 -0
- package/out/src/tools/overture-subvenue.d.ts.map +1 -0
- package/out/src/tools/overture-subvenue.js +144 -0
- package/out/src/tools/overture-subvenue.js.map +1 -0
- package/out/src/tools/shard-kryptonite.d.ts +1 -1
- package/out/src/tools/shard-kryptonite.d.ts.map +1 -1
- package/out/src/tools/shard-kryptonite.js +6 -6
- package/out/src/tools/shard-kryptonite.js.map +1 -1
- package/out/src/tools/shard-translit.d.ts +6 -3
- package/out/src/tools/shard-translit.d.ts.map +1 -1
- package/out/src/tools/shard-translit.js +9 -8
- package/out/src/tools/shard-translit.js.map +1 -1
- package/out/src/tools/sub-venue-lexicon.d.ts +507 -0
- package/out/src/tools/sub-venue-lexicon.d.ts.map +1 -0
- package/out/src/tools/sub-venue-lexicon.js +817 -0
- package/out/src/tools/sub-venue-lexicon.js.map +1 -0
- package/out/src/tools/sub-venue-promotions.d.ts +94 -0
- package/out/src/tools/sub-venue-promotions.d.ts.map +1 -0
- package/out/src/tools/sub-venue-promotions.js +266 -0
- package/out/src/tools/sub-venue-promotions.js.map +1 -0
- 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/{golden.d.ts → utils/golden.d.ts} +5 -0
- package/out/src/utils/golden.d.ts.map +1 -0
- package/out/src/{golden.js → utils/golden.js} +24 -10
- 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/utils/license.js.map +1 -0
- package/out/src/{parquet.d.ts → utils/parquet.d.ts} +2 -2
- package/out/src/utils/parquet.d.ts.map +1 -0
- package/out/src/{parquet.js → utils/parquet.js} +3 -15
- package/out/src/utils/parquet.js.map +1 -0
- package/out/src/{split.d.ts → utils/split.d.ts} +8 -1
- package/out/src/utils/split.d.ts.map +1 -0
- package/out/src/{split.js → utils/split.js} +7 -0
- 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/{wof-json.d.ts → utils/wof-json.d.ts} +2 -2
- package/out/src/utils/wof-json.d.ts.map +1 -0
- package/out/src/{wof-json.js → utils/wof-json.js} +5 -8
- package/out/src/utils/wof-json.js.map +1 -0
- package/package.json +66 -20
- package/src/adapters/ban/adapter.ts +58 -68
- package/src/adapters/ban/street-decompose.ts +17 -25
- package/src/adapters/fcc-bdc/adapter.ts +5 -36
- package/src/adapters/geonames/adapter.ts +67 -76
- package/src/adapters/geonames-postal/adapter.ts +45 -54
- package/src/adapters/gnaf/adapter.ts +7 -11
- package/src/adapters/gnaf/assemble.ts +7 -11
- package/src/adapters/index.ts +3 -2
- package/src/adapters/openaddresses/adapter.ts +6 -12
- package/src/adapters/overture/adapter.ts +6 -10
- package/src/adapters/state-hi-schools/adapter.ts +53 -77
- package/src/adapters/state-ia-contractors/adapter.ts +55 -80
- package/src/adapters/state-ny-notaries/adapter.ts +64 -89
- package/src/adapters/state-tx-notaries/adapter.ts +63 -88
- package/src/adapters/synth-po-box/adapter.ts +12 -23
- package/src/adapters/tiger/adapter.ts +4 -3
- package/src/adapters/tiger/street-decompose.ts +21 -31
- package/src/adapters/usgov-hrsa-fqhc/adapter.ts +64 -88
- package/src/adapters/usgov-imls-pls/adapter.ts +57 -86
- package/src/adapters/usgov-irs-bmf/adapter.ts +55 -66
- package/src/adapters/usgov-nad/adapter.ts +7 -11
- package/src/adapters/usgov-nppes/adapter.ts +54 -79
- package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +48 -75
- package/src/{adapter.ts → adapters/utils/index.ts} +59 -3
- package/src/adapters/wof-admin-jp/adapter.ts +35 -9
- package/src/adapters/wof-admin-json/adapter.ts +3 -4
- package/src/adapters/wof-postalcode-json/adapter.ts +3 -4
- package/src/build.ts +12 -11
- package/src/index.ts +3 -17
- package/src/name-prone-us-suffixes.ts +12 -0
- package/src/parquet-wrapper/reader.ts +19 -0
- package/src/parquet-wrapper/schema.ts +4 -0
- package/src/runner.ts +7 -2
- package/src/shard-recipes/anchor-absorption.ts +5 -4
- package/src/shard-recipes/boundary-stress.ts +6 -2
- package/src/shard-recipes/country-balanced.ts +77 -91
- package/src/shard-recipes/fr-admin-split.ts +3 -3
- package/src/shard-recipes/fr-fragment.ts +10 -7
- package/src/shard-recipes/fr-lieudit.ts +3 -3
- package/src/shard-recipes/fr-order.ts +18 -83
- package/src/shard-recipes/german.ts +17 -80
- package/src/shard-recipes/house-venue.ts +2 -1
- package/src/shard-recipes/index.ts +4 -1
- package/src/shard-recipes/intersection.ts +37 -74
- package/src/shard-recipes/locale.ts +31 -39
- package/src/shard-recipes/no-fragment.ts +10 -7
- package/src/shard-recipes/no-street-led.ts +10 -7
- package/src/shard-recipes/no-street.ts +2 -1
- package/src/shard-recipes/po-box-cedex.ts +127 -161
- package/src/shard-recipes/po-box.ts +6 -1
- package/src/shard-recipes/scaffold.ts +125 -27
- package/src/shard-recipes/street-affix.ts +335 -134
- 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 +895 -0
- package/src/shard-recipes/sub-venue.ts +982 -0
- package/src/shard-recipes/unit.ts +27 -85
- package/src/{synthesize-boundary-stress.ts → synthesizers/boundary-stress.ts} +2 -2
- package/src/{synthesize-german.ts → synthesizers/german.ts} +2 -2
- package/src/{synthesize-house-venue.ts → synthesizers/house-venue.ts} +4 -4
- 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} +2 -2
- package/src/{synthesize.ts → synthesizers/utils.ts} +4 -18
- package/src/tools/align-shard.ts +4 -7
- package/src/tools/audit.ts +6 -5
- package/src/tools/corpus-stats.ts +25 -33
- package/src/tools/fetch/download.ts +7 -5
- package/src/tools/fetch/imls-pls.ts +4 -18
- package/src/tools/fetch/index.ts +14 -1
- package/src/tools/fetch/nad.ts +1 -1
- package/src/tools/fetch/nppes.ts +9 -16
- package/src/tools/fetch/openaddresses.ts +1 -1
- package/src/tools/fetch/ourairports.ts +166 -0
- package/src/tools/fetch/wikidata-subvenue.ts +386 -0
- package/src/tools/golden-expand.ts +18 -13
- package/src/tools/golden-promote.ts +15 -6
- package/src/tools/golden-relabel-street.ts +685 -0
- package/src/tools/index.ts +4 -0
- package/src/tools/jsonl-to-parquet.ts +3 -2
- package/src/tools/lint-shard-vocab.ts +3 -2
- package/src/tools/lint-shard.ts +33 -36
- package/src/tools/overlay-manifest.ts +2 -1
- package/src/tools/overture-subvenue.ts +215 -0
- package/src/tools/shard-kryptonite.ts +8 -9
- package/src/tools/shard-translit.ts +22 -11
- package/src/tools/sub-venue-lexicon.ts +1250 -0
- package/src/tools/sub-venue-promotions.ts +330 -0
- package/src/{align.ts → utils/align.ts} +1 -1
- package/src/{golden.ts → utils/golden.ts} +25 -11
- package/src/utils/index.ts +14 -0
- package/src/{parquet.ts → utils/parquet.ts} +5 -19
- package/src/{split.ts → utils/split.ts} +8 -2
- package/src/{wof-json.ts → utils/wof-json.ts} +5 -8
- 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/{license.d.ts → utils/license.d.ts} +0 -0
- /package/out/src/{license.js → utils/license.js} +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/src/{synthesize-anchor-absorption.ts → synthesizers/anchor-absorption.ts} +0 -0
- /package/src/{license.ts → utils/license.ts} +0 -0
- /package/src/{tokenize.ts → utils/tokenize.ts} +0 -0
|
@@ -14,11 +14,10 @@
|
|
|
14
14
|
*
|
|
15
15
|
* License: stamped `"Public Domain"` per Texas state government open-data terms.
|
|
16
16
|
*/
|
|
17
|
-
import {
|
|
18
|
-
import {
|
|
19
|
-
import {
|
|
20
|
-
import {
|
|
21
|
-
import { reconcileComponents } from "../../format.js";
|
|
17
|
+
import { splitStreetLine, stableSourceID } from "@mailwoman/corpus/adapters/utils";
|
|
18
|
+
import { lookupStateAbbreviation } from "@mailwoman/corpus/codex/us-fips-state";
|
|
19
|
+
import { reconcileComponents } from "@mailwoman/formatter";
|
|
20
|
+
import { CSVSpliterator } from "spliterator";
|
|
22
21
|
/**
|
|
23
22
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
24
23
|
* it came from.
|
|
@@ -29,20 +28,10 @@ export const STATE_TX_NOTARIES_ADAPTER_ID = "state-tx-notaries";
|
|
|
29
28
|
* than having to look them up.
|
|
30
29
|
*/
|
|
31
30
|
export const STATE_TX_NOTARIES_DEFAULT_LICENSE = "Public Domain";
|
|
32
|
-
const HOUSE_NUMBER_PREFIX = /^(\d+(?:-\d+)?[A-Za-z]?)\s+(.+)$/;
|
|
33
31
|
/**
|
|
34
32
|
* Match trailing "CITY, ST ZIP" or "CITY, ST" at the end of an address line.
|
|
35
33
|
*/
|
|
36
34
|
const CITY_STATE_ZIP_SUFFIX = /[,]?\s*([^,]+),\s*([A-Z]{2})\s*(\d{5}(?:-\d{4})?)?\s*$/i;
|
|
37
|
-
function splitAddress(address) {
|
|
38
|
-
const trimmed = address.trim();
|
|
39
|
-
if (!trimmed)
|
|
40
|
-
return null;
|
|
41
|
-
const m = HOUSE_NUMBER_PREFIX.exec(trimmed);
|
|
42
|
-
if (m)
|
|
43
|
-
return { house_number: m[1], street: m[2].trim() };
|
|
44
|
-
return { street: trimmed };
|
|
45
|
-
}
|
|
46
35
|
export function createStateTxNotariesAdapter() {
|
|
47
36
|
return {
|
|
48
37
|
id: STATE_TX_NOTARIES_ADAPTER_ID,
|
|
@@ -52,81 +41,74 @@ export function createStateTxNotariesAdapter() {
|
|
|
52
41
|
if (opts.country && opts.country !== "US") {
|
|
53
42
|
throw new Error(`state-tx-notaries adapter: only US supported, got country=${opts.country}`);
|
|
54
43
|
}
|
|
55
|
-
const
|
|
56
|
-
|
|
57
|
-
|
|
58
|
-
|
|
59
|
-
|
|
60
|
-
relax_column_count: true,
|
|
61
|
-
}));
|
|
44
|
+
const rows = CSVSpliterator.fromAsync(opts.inputPath, {
|
|
45
|
+
mode: "object",
|
|
46
|
+
normalizeKeys: false,
|
|
47
|
+
enableQuoteHandling: true,
|
|
48
|
+
});
|
|
62
49
|
let emitted = 0;
|
|
63
|
-
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
|
|
70
|
-
|
|
71
|
-
|
|
72
|
-
|
|
73
|
-
|
|
74
|
-
|
|
75
|
-
|
|
76
|
-
|
|
77
|
-
|
|
78
|
-
|
|
79
|
-
|
|
80
|
-
|
|
81
|
-
|
|
82
|
-
|
|
83
|
-
|
|
84
|
-
|
|
85
|
-
|
|
86
|
-
|
|
87
|
-
|
|
88
|
-
|
|
89
|
-
|
|
90
|
-
|
|
91
|
-
|
|
92
|
-
|
|
93
|
-
|
|
94
|
-
|
|
95
|
-
|
|
96
|
-
|
|
97
|
-
|
|
98
|
-
|
|
99
|
-
|
|
100
|
-
|
|
101
|
-
|
|
102
|
-
|
|
103
|
-
|
|
104
|
-
|
|
105
|
-
|
|
106
|
-
|
|
107
|
-
|
|
108
|
-
|
|
109
|
-
|
|
110
|
-
|
|
111
|
-
|
|
112
|
-
|
|
113
|
-
|
|
114
|
-
|
|
115
|
-
|
|
116
|
-
|
|
117
|
-
|
|
118
|
-
|
|
119
|
-
|
|
120
|
-
|
|
121
|
-
|
|
122
|
-
|
|
123
|
-
|
|
124
|
-
|
|
125
|
-
emitted++;
|
|
126
|
-
}
|
|
127
|
-
}
|
|
128
|
-
finally {
|
|
129
|
-
stream.destroy();
|
|
50
|
+
for await (const record of rows) {
|
|
51
|
+
if (opts.signal?.aborted)
|
|
52
|
+
break;
|
|
53
|
+
if (opts.limit !== undefined && emitted >= opts.limit)
|
|
54
|
+
break;
|
|
55
|
+
const rawAddress = (record.Address ?? "").trim();
|
|
56
|
+
if (!rawAddress)
|
|
57
|
+
continue;
|
|
58
|
+
const firstName = (record["First Name"] ?? "").trim();
|
|
59
|
+
const lastName = (record["Last Name"] ?? "").trim();
|
|
60
|
+
const notaryID = (record["Notary ID"] ?? "").trim();
|
|
61
|
+
// Parse embedded city/state/zip from the trailing portion of the address.
|
|
62
|
+
// Addresses look like: "1215 MCMILLAN DR\nCEDAR HILL, TX 75104"
|
|
63
|
+
const addrSingleLine = rawAddress.replaceAll("\n", ", ");
|
|
64
|
+
const cszMatch = CITY_STATE_ZIP_SUFFIX.exec(addrSingleLine);
|
|
65
|
+
if (!cszMatch)
|
|
66
|
+
continue;
|
|
67
|
+
const city = (cszMatch[1] ?? "").trim();
|
|
68
|
+
const stateAbbr = (cszMatch[2] ?? "").trim();
|
|
69
|
+
const zip = (cszMatch[3] ?? "").trim();
|
|
70
|
+
if (!city || !stateAbbr)
|
|
71
|
+
continue;
|
|
72
|
+
const state = lookupStateAbbreviation(stateAbbr);
|
|
73
|
+
if (!state)
|
|
74
|
+
continue;
|
|
75
|
+
// Extract the street portion (everything before the city/state/zip)
|
|
76
|
+
const streetPortion = addrSingleLine.slice(0, cszMatch.index).replace(/,\s*$/, "").trim();
|
|
77
|
+
if (!streetPortion)
|
|
78
|
+
continue;
|
|
79
|
+
const split = splitStreetLine(streetPortion);
|
|
80
|
+
if (!split)
|
|
81
|
+
continue;
|
|
82
|
+
const venue = [firstName, lastName].filter(Boolean).join(" ") || undefined;
|
|
83
|
+
const components = {
|
|
84
|
+
...(venue ? { venue } : {}),
|
|
85
|
+
...(split.house_number ? { house_number: split.house_number } : {}),
|
|
86
|
+
street: split.street,
|
|
87
|
+
locality: city,
|
|
88
|
+
region: state.abbreviation,
|
|
89
|
+
...(zip ? { postcode: zip } : {}),
|
|
90
|
+
};
|
|
91
|
+
const streetPart = [split.house_number, split.street].filter(Boolean).join(" ").trim();
|
|
92
|
+
const raw = [venue, streetPart, [city, [stateAbbr, zip].filter(Boolean).join(" ")].filter(Boolean).join(", ")]
|
|
93
|
+
.filter(Boolean)
|
|
94
|
+
.join(", ");
|
|
95
|
+
const aligned = reconcileComponents(components, raw);
|
|
96
|
+
if (Object.keys(aligned).length <= 2)
|
|
97
|
+
continue;
|
|
98
|
+
const sourceID = notaryID
|
|
99
|
+
? `${STATE_TX_NOTARIES_ADAPTER_ID}-${notaryID}`
|
|
100
|
+
: stableSourceID(STATE_TX_NOTARIES_ADAPTER_ID, aligned);
|
|
101
|
+
yield {
|
|
102
|
+
raw,
|
|
103
|
+
components: aligned,
|
|
104
|
+
country: "US",
|
|
105
|
+
locale: "en-US",
|
|
106
|
+
source: STATE_TX_NOTARIES_ADAPTER_ID,
|
|
107
|
+
source_id: sourceID,
|
|
108
|
+
corpus_version: "",
|
|
109
|
+
license: STATE_TX_NOTARIES_DEFAULT_LICENSE,
|
|
110
|
+
};
|
|
111
|
+
emitted++;
|
|
130
112
|
}
|
|
131
113
|
},
|
|
132
114
|
};
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/state-tx-notaries/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;GAeG;AAEH,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/state-tx-notaries/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;GAeG;AAEH,OAAO,EAAE,eAAe,EAAE,cAAc,EAAE,MAAM,kCAAkC,CAAA;AAClF,OAAO,EAAE,uBAAuB,EAAE,MAAM,uCAAuC,CAAA;AAE/E,OAAO,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AAC1D,OAAO,EAAE,cAAc,EAAE,MAAM,aAAa,CAAA;AAE5C;;;GAGG;AACH,MAAM,CAAC,MAAM,4BAA4B,GAAG,mBAAmB,CAAA;AAC/D;;;GAGG;AACH,MAAM,CAAC,MAAM,iCAAiC,GAAG,eAAe,CAAA;AAEhE;;GAEG;AACH,MAAM,qBAAqB,GAAG,yDAAyD,CAAA;AASvF,MAAM,UAAU,4BAA4B;IAC3C,OAAO;QACN,EAAE,EAAE,4BAA4B;QAChC,cAAc,EAAE,iCAAiC;QACjD,WAAW,EACV,wGAAwG;QAEzG,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,6DAA6D,IAAI,CAAC,OAAO,EAAE,CAAC,CAAA;YAC7F,CAAC;YAED,MAAM,IAAI,GAAG,cAAc,CAAC,SAAS,CAAC,IAAI,CAAC,SAAS,EAAE;gBACrD,IAAI,EAAE,QAAQ;gBACd,aAAa,EAAE,KAAK;gBACpB,mBAAmB,EAAE,IAAI;aACzB,CAAC,CAAA;YAEF,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,KAAK,EAAE,MAAM,MAAM,IAAI,IAAkC,EAAE,CAAC;gBAC/D,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;oBAAE,MAAK;gBAE/B,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;oBAAE,MAAK;gBAE5D,MAAM,UAAU,GAAG,CAAC,MAAM,CAAC,OAAO,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAEhD,IAAI,CAAC,UAAU;oBAAE,SAAQ;gBAEzB,MAAM,SAAS,GAAG,CAAC,MAAM,CAAC,YAAY,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBACrD,MAAM,QAAQ,GAAG,CAAC,MAAM,CAAC,WAAW,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBACnD,MAAM,QAAQ,GAAG,CAAC,MAAM,CAAC,WAAW,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAEnD,0EAA0E;gBAC1E,gEAAgE;gBAChE,MAAM,cAAc,GAAG,UAAU,CAAC,UAAU,CAAC,IAAI,EAAE,IAAI,CAAC,CAAA;gBACxD,MAAM,QAAQ,GAAG,qBAAqB,CAAC,IAAI,CAAC,cAAc,CAAC,CAAA;gBAE3D,IAAI,CAAC,QAAQ;oBAAE,SAAQ;gBAEvB,MAAM,IAAI,GAAG,CAAC,QAAQ,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBACvC,MAAM,SAAS,GAAG,CAAC,QAAQ,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAC5C,MAAM,GAAG,GAAG,CAAC,QAAQ,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAEtC,IAAI,CAAC,IAAI,IAAI,CAAC,SAAS;oBAAE,SAAQ;gBAEjC,MAAM,KAAK,GAAG,uBAAuB,CAAC,SAAS,CAAC,CAAA;gBAEhD,IAAI,CAAC,KAAK;oBAAE,SAAQ;gBAEpB,oEAAoE;gBACpE,MAAM,aAAa,GAAG,cAAc,CAAC,KAAK,CAAC,CAAC,EAAE,QAAQ,CAAC,KAAK,CAAC,CAAC,OAAO,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAEzF,IAAI,CAAC,aAAa;oBAAE,SAAQ;gBAE5B,MAAM,KAAK,GAAG,eAAe,CAAC,aAAa,CAAC,CAAA;gBAE5C,IAAI,CAAC,KAAK;oBAAE,SAAQ;gBAEpB,MAAM,KAAK,GAAG,CAAC,SAAS,EAAE,QAAQ,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,SAAS,CAAA;gBAE1E,MAAM,UAAU,GAA+B;oBAC9C,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,EAAE,KAAK,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;oBAC3B,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,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,QAAQ,EAAE,GAAG,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;iBACjC,CAAA;gBAED,MAAM,UAAU,GAAG,CAAC,KAAK,CAAC,YAAY,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;gBAEtF,MAAM,GAAG,GAAG,CAAC,KAAK,EAAE,UAAU,EAAE,CAAC,IAAI,EAAE,CAAC,SAAS,EAAE,GAAG,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;qBAC5G,MAAM,CAAC,OAAO,CAAC;qBACf,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,QAAQ,GAAG,QAAQ;oBACxB,CAAC,CAAC,GAAG,4BAA4B,IAAI,QAAQ,EAAE;oBAC/C,CAAC,CAAC,cAAc,CAAC,4BAA4B,EAAE,OAAO,CAAC,CAAA;gBAExD,MAAM;oBACL,GAAG;oBACH,UAAU,EAAE,OAAO;oBACnB,OAAO,EAAE,IAAI;oBACb,MAAM,EAAE,OAAO;oBACf,MAAM,EAAE,4BAA4B;oBACpC,SAAS,EAAE,QAAQ;oBACnB,cAAc,EAAE,EAAE;oBAClB,OAAO,EAAE,iCAAiC;iBAC1C,CAAA;gBAED,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,sBAAsB,GAAG,4BAA4B,EAAE,CAAA"}
|
|
@@ -7,7 +7,7 @@
|
|
|
7
7
|
*
|
|
8
8
|
* Consumes a JSONL stream of (locality, region, postcode, country) tuples — typically extracted
|
|
9
9
|
* from existing corpus output (TIGER/NAD/BAN/WOF) — and emits synthetic PO box training rows. See
|
|
10
|
-
*
|
|
10
|
+
* `@mailwoman/corpus/synthesizers/po-box` for the per-locale templates and number-noise logic.
|
|
11
11
|
*
|
|
12
12
|
* Why an adapter and not an augmenter:
|
|
13
13
|
*
|
|
@@ -19,8 +19,8 @@
|
|
|
19
19
|
* ARE valid (CMRA addresses). Those are produced when `pmbRatio > 0` AND the input tuple
|
|
20
20
|
* carries a `street` field.
|
|
21
21
|
*/
|
|
22
|
-
import { type PoBoxBaseTuple } from "
|
|
23
|
-
import type { CorpusAdapter } from "
|
|
22
|
+
import { type PoBoxBaseTuple } from "@mailwoman/corpus/synthesizers/po-box";
|
|
23
|
+
import type { CorpusAdapter } from "@mailwoman/corpus/types";
|
|
24
24
|
/**
|
|
25
25
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
26
26
|
* it came from.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/synth-po-box/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;GAoBG;AAKH,OAAO,EAKN,KAAK,cAAc,EACnB,MAAM,
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/synth-po-box/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;GAoBG;AAKH,OAAO,EAKN,KAAK,cAAc,EACnB,MAAM,uCAAuC,CAAA;AAC9C,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,yBAAyB,CAAA;AAG1F;;;GAGG;AACH,eAAO,MAAM,uBAAuB,iBAAiB,CAAA;AACrD;;;GAGG;AACH,eAAO,MAAM,oBAAoB,qEAAgE,CAAA;AAEjG,MAAM,WAAW,aAAc,SAAQ,cAAc;IACpD,MAAM,CAAC,EAAE,MAAM,CAAA;IACf,WAAW,CAAC,EAAE,MAAM,CAAA;CACpB;AAED,MAAM,WAAW,wBAAwB;IACxC;;;OAGG;IACH,gBAAgB,CAAC,EAAE,MAAM,CAAA;IACzB;;;OAGG;IACH,QAAQ,CAAC,EAAE,MAAM,CAAA;IACjB;;OAEG;IACH,IAAI,CAAC,EAAE,MAAM,CAAA;IACb;;;;;;OAMG;IACH,aAAa,CAAC,EAAE,MAAM,CAAA;CACtB;AAED,wBAAgB,uBAAuB,CAAC,IAAI,GAAE,wBAA6B,GAAG,aAAa,CAyH1F;AAED;;GAEG;AACH,eAAO,MAAM,iBAAiB,eAA4B,CAAA"}
|
|
@@ -7,7 +7,7 @@
|
|
|
7
7
|
*
|
|
8
8
|
* Consumes a JSONL stream of (locality, region, postcode, country) tuples — typically extracted
|
|
9
9
|
* from existing corpus output (TIGER/NAD/BAN/WOF) — and emits synthetic PO box training rows. See
|
|
10
|
-
*
|
|
10
|
+
* `@mailwoman/corpus/synthesizers/po-box` for the per-locale templates and number-noise logic.
|
|
11
11
|
*
|
|
12
12
|
* Why an adapter and not an augmenter:
|
|
13
13
|
*
|
|
@@ -19,9 +19,11 @@
|
|
|
19
19
|
* ARE valid (CMRA addresses). Those are produced when `pmbRatio > 0` AND the input tuple
|
|
20
20
|
* carries a `street` field.
|
|
21
21
|
*/
|
|
22
|
+
import { tryParsingJSON } from "@mailwoman/core/objects";
|
|
23
|
+
import { makeLcg } from "@mailwoman/core/utils";
|
|
24
|
+
import { stableSourceID } from "@mailwoman/corpus/adapters/utils";
|
|
25
|
+
import { countryToLocale, REGION_OPTIONAL_LOCALES, synthesizeMilitaryPoBoxRow, synthesizePoBoxRow, } from "@mailwoman/corpus/synthesizers/po-box";
|
|
22
26
|
import { TextSpliterator } from "spliterator";
|
|
23
|
-
import { stableSourceID } from "../../adapter.js";
|
|
24
|
-
import { countryToLocale, REGION_OPTIONAL_LOCALES, synthesizeMilitaryPoBoxRow, synthesizePoBoxRow, } from "../../synthesize-po-box.js";
|
|
25
27
|
/**
|
|
26
28
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
27
29
|
* it came from.
|
|
@@ -32,13 +34,6 @@ export const SYNTH_PO_BOX_ADAPTER_ID = "synth-po-box";
|
|
|
32
34
|
* derived from, so the attribution travels with it.
|
|
33
35
|
*/
|
|
34
36
|
export const SYNTH_PO_BOX_LICENSE = "Synthetic — derived from CC-BY / public-domain input tuples";
|
|
35
|
-
function makeRandom(seed) {
|
|
36
|
-
let s = seed;
|
|
37
|
-
return () => {
|
|
38
|
-
s = (s * 1_664_525 + 1_013_904_223) % 4_294_967_296;
|
|
39
|
-
return s / 4_294_967_296;
|
|
40
|
-
};
|
|
41
|
-
}
|
|
42
37
|
export function createSynthPoBoxAdapter(opts = {}) {
|
|
43
38
|
const variantsPerInput = opts.variantsPerInput ?? 1;
|
|
44
39
|
const pmbRatio = opts.pmbRatio ?? 0.15;
|
|
@@ -48,9 +43,9 @@ export function createSynthPoBoxAdapter(opts = {}) {
|
|
|
48
43
|
defaultLicense: SYNTH_PO_BOX_LICENSE,
|
|
49
44
|
description: "Synthetic PO box / PMB / Apartado / Boîte Postale rows. Consumes JSONL of (locality, region, postcode, country) tuples and emits locale-appropriate PO box variants.",
|
|
50
45
|
async *rows(options) {
|
|
51
|
-
const random =
|
|
52
|
-
// TextSpliterator streams string lines; the per-line
|
|
53
|
-
// tolerant of malformed rows (skipped++), so TextSpliterator +
|
|
46
|
+
const random = makeLcg(opts.seed ?? Date.now());
|
|
47
|
+
// TextSpliterator streams string lines; the per-line tryParsingJSON below keeps this reader
|
|
48
|
+
// tolerant of malformed rows (skipped++), so TextSpliterator + a non-throwing parse — not
|
|
54
49
|
// JSONSpliterator, which would throw on the first bad line.
|
|
55
50
|
const lines = TextSpliterator.fromAsync(options.inputPath);
|
|
56
51
|
let emitted = 0;
|
|
@@ -64,11 +59,8 @@ export function createSynthPoBoxAdapter(opts = {}) {
|
|
|
64
59
|
const trimmed = line.trim();
|
|
65
60
|
if (!trimmed)
|
|
66
61
|
continue;
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
input = JSON.parse(trimmed);
|
|
70
|
-
}
|
|
71
|
-
catch {
|
|
62
|
+
const input = tryParsingJSON(trimmed);
|
|
63
|
+
if (input === null) {
|
|
72
64
|
skipped++;
|
|
73
65
|
continue;
|
|
74
66
|
}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/synth-po-box/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;GAoBG;AAEH,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/synth-po-box/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;GAoBG;AAEH,OAAO,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAA;AACxD,OAAO,EAAE,OAAO,EAAE,MAAM,uBAAuB,CAAA;AAC/C,OAAO,EAAE,cAAc,EAAE,MAAM,kCAAkC,CAAA;AACjE,OAAO,EACN,eAAe,EACf,uBAAuB,EACvB,0BAA0B,EAC1B,kBAAkB,GAElB,MAAM,uCAAuC,CAAA;AAE9C,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C;;;GAGG;AACH,MAAM,CAAC,MAAM,uBAAuB,GAAG,cAAc,CAAA;AACrD;;;GAGG;AACH,MAAM,CAAC,MAAM,oBAAoB,GAAG,6DAA6D,CAAA;AAgCjG,MAAM,UAAU,uBAAuB,CAAC,OAAiC,EAAE;IAC1E,MAAM,gBAAgB,GAAG,IAAI,CAAC,gBAAgB,IAAI,CAAC,CAAA;IACnD,MAAM,QAAQ,GAAG,IAAI,CAAC,QAAQ,IAAI,IAAI,CAAA;IACtC,MAAM,aAAa,GAAG,IAAI,CAAC,aAAa,IAAI,CAAC,CAAA;IAE7C,OAAO;QACN,EAAE,EAAE,uBAAuB;QAC3B,cAAc,EAAE,oBAAoB;QACpC,WAAW,EACV,sKAAsK;QAEvK,KAAK,CAAC,CAAC,IAAI,CAAC,OAAuB;YAClC,MAAM,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,GAAG,EAAE,CAAC,CAAA;YAE/C,4FAA4F;YAC5F,0FAA0F;YAC1F,4DAA4D;YAC5D,MAAM,KAAK,GAAG,eAAe,CAAC,SAAS,CAAC,OAAO,CAAC,SAAS,CAAC,CAAA;YAE1D,IAAI,OAAO,GAAG,CAAC,CAAA;YACf,IAAI,OAAO,GAAG,CAAC,CAAA;YACf,IAAI,WAAW,GAAG,CAAC,CAAA;YAEnB,IAAI,KAAK,EAAE,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;gBAChC,IAAI,OAAO,CAAC,MAAM,EAAE,OAAO;oBAAE,MAAK;gBAElC,IAAI,OAAO,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,OAAO,CAAC,KAAK;oBAAE,MAAK;gBAElE,MAAM,OAAO,GAAG,IAAI,CAAC,IAAI,EAAE,CAAA;gBAE3B,IAAI,CAAC,OAAO;oBAAE,SAAQ;gBAEtB,MAAM,KAAK,GAAG,cAAc,CAAgB,OAAO,CAAC,CAAA;gBAEpD,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;oBACpB,OAAO,EAAE,CAAA;oBAET,SAAQ;gBACT,CAAC;gBAED,yFAAyF;gBACzF,wFAAwF;gBACxF,qDAAqD;gBACrD,MAAM,cAAc,GAAG,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,uBAAuB,CAAC,GAAG,CAAC,eAAe,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAA;gBAE1G,IAAI,CAAC,KAAK,CAAC,QAAQ,IAAI,CAAC,KAAK,CAAC,QAAQ,IAAI,CAAC,KAAK,CAAC,OAAO,IAAI,CAAC,CAAC,KAAK,CAAC,MAAM,IAAI,CAAC,cAAc,CAAC,EAAE,CAAC;oBAChG,OAAO,EAAE,CAAA;oBAET,SAAQ;gBACT,CAAC;gBAED,IAAI,OAAO,CAAC,OAAO,IAAI,OAAO,CAAC,OAAO,KAAK,KAAK,CAAC,OAAO;oBAAE,SAAQ;gBAElE,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,gBAAgB,EAAE,CAAC,EAAE,EAAE,CAAC;oBAC3C,MAAM,KAAK,GAAG,kBAAkB,CAAC,KAAK,EAAE,EAAE,MAAM,EAAE,QAAQ,EAAE,CAAC,CAAA;oBAE7D,IAAI,CAAC,KAAK;wBAAE,SAAQ;oBAEpB,6EAA6E;oBAC7E,iDAAiD;oBACjD,MAAM,QAAQ,GAAG,cAAc,CAAC,uBAAuB,EAAE;wBACxD,QAAQ,EAAE,GAAG,KAAK,CAAC,QAAQ,IAAI,CAAC,EAAE;wBAClC,MAAM,EAAE,KAAK,CAAC,MAAM;wBACpB,QAAQ,EAAE,KAAK,CAAC,QAAQ;wBACxB,OAAO,EAAE,KAAK,CAAC,OAAO;qBACtB,CAAC,CAAA;oBAEF,MAAM;wBACL,GAAG,EAAE,KAAK,CAAC,GAAG;wBACd,UAAU,EAAE,KAAK,CAAC,UAAU;wBAC5B,OAAO,EAAE,KAAK,CAAC,OAAO;wBACtB,MAAM,EAAE,KAAK,CAAC,MAAM;wBACpB,MAAM,EAAE,uBAAuB;wBAC/B,SAAS,EAAE,QAAQ;wBACnB,cAAc,EAAE,EAAE;wBAClB,OAAO,EAAE,oBAAoB;qBAC7B,CAAA;oBAED,OAAO,EAAE,CAAA;oBAET,IAAI,OAAO,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,OAAO,CAAC,KAAK;wBAAE,MAAK;gBACnE,CAAC;gBAED,0FAA0F;gBAC1F,0FAA0F;gBAC1F,wFAAwF;gBACxF,2FAA2F;gBAC3F,kDAAkD;gBAClD,MAAM,eAAe,GAAG,CAAC,OAAO,CAAC,OAAO,IAAI,OAAO,CAAC,OAAO,KAAK,IAAI,CAAA;gBAEpE,IACC,aAAa,GAAG,CAAC;oBACjB,eAAe;oBACf,CAAC,OAAO,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,GAAG,OAAO,CAAC,KAAK,CAAC;oBACxD,MAAM,EAAE,GAAG,aAAa,EACvB,CAAC;oBACF,MAAM,GAAG,GAAG,0BAA0B,CAAC,EAAE,MAAM,EAAE,CAAC,CAAA;oBAElD,MAAM,QAAQ,GAAG,cAAc,CAAC,uBAAuB,EAAE;wBACxD,MAAM,EAAE,GAAG,GAAG,CAAC,UAAU,CAAC,MAAM,OAAO,WAAW,EAAE,EAAE;wBACtD,QAAQ,EAAE,GAAG,CAAC,UAAU,CAAC,QAAS;wBAClC,MAAM,EAAE,GAAG,CAAC,UAAU,CAAC,MAAO;wBAC9B,QAAQ,EAAE,GAAG,CAAC,UAAU,CAAC,QAAS;qBAClC,CAAC,CAAA;oBAEF,MAAM;wBACL,GAAG,EAAE,GAAG,CAAC,GAAG;wBACZ,UAAU,EAAE,GAAG,CAAC,UAAU;wBAC1B,OAAO,EAAE,IAAI;wBACb,MAAM,EAAE,GAAG,CAAC,MAAM;wBAClB,MAAM,EAAE,uBAAuB;wBAC/B,SAAS,EAAE,QAAQ;wBACnB,cAAc,EAAE,EAAE;wBAClB,OAAO,EAAE,oBAAoB;qBAC7B,CAAA;oBAED,OAAO,EAAE,CAAA;gBACV,CAAC;YACF,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,iBAAiB,GAAG,uBAAuB,EAAE,CAAA"}
|
|
@@ -33,7 +33,7 @@
|
|
|
33
33
|
* License: stamped `"Public Domain"` per Census Bureau guidance on TIGER/Line. No per-row override
|
|
34
34
|
* needed — every row in TIGER is the same license.
|
|
35
35
|
*/
|
|
36
|
-
import type { CorpusAdapter } from "
|
|
36
|
+
import type { CorpusAdapter } from "@mailwoman/corpus/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/tiger/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAkCG;
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/tiger/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAkCG;AAKH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,yBAAyB,CAAA;AAK1F;;;GAGG;AACH,eAAO,MAAM,gBAAgB,UAAU,CAAA;AACvC;;;GAGG;AACH,eAAO,MAAM,qBAAqB,kBAAkB,CAAA;AAiHpD;;GAEG;AACH,wBAAgB,kBAAkB,IAAI,aAAa,CA6ElD;AAED;;GAEG;AACH,eAAO,MAAM,YAAY,eAAuB,CAAA"}
|
|
@@ -34,8 +34,8 @@
|
|
|
34
34
|
* needed — every row in TIGER is the same license.
|
|
35
35
|
*/
|
|
36
36
|
import { DatabaseSync } from "node:sqlite";
|
|
37
|
-
import { lookupFipsState } from "
|
|
38
|
-
import { formatAddress, reconcileComponents } from "
|
|
37
|
+
import { lookupFipsState } from "@mailwoman/corpus/codex/us-fips-state";
|
|
38
|
+
import { formatAddress, reconcileComponents } from "@mailwoman/formatter";
|
|
39
39
|
import { decomposeStreet } from "./street-decompose.js";
|
|
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
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/tiger/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAkCG;AAEH,OAAO,EAAE,YAAY,EAAE,MAAM,aAAa,CAAA;AAE1C,OAAO,EAAE,eAAe,EAAE,MAAM,
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/tiger/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAkCG;AAEH,OAAO,EAAE,YAAY,EAAE,MAAM,aAAa,CAAA;AAE1C,OAAO,EAAE,eAAe,EAAE,MAAM,uCAAuC,CAAA;AAEvE,OAAO,EAAE,aAAa,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AAEzE,OAAO,EAAE,eAAe,EAAE,MAAM,uBAAuB,CAAA;AAEvD;;;GAGG;AACH,MAAM,CAAC,MAAM,gBAAgB,GAAG,OAAO,CAAA;AACvC;;;GAGG;AACH,MAAM,CAAC,MAAM,qBAAqB,GAAG,eAAe,CAAA;AAEpD;;;GAGG;AACH,MAAM,kBAAkB,GAAG,0BAA0B,CAAA;AAiBrD;;;;;;GAMG;AACH,QAAQ,CAAC,CAAC,cAAc,CAAC,GAAmB;IAI3C,MAAM,QAAQ,GAAG,GAAG,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAA;IAEpC,IAAI,CAAC,QAAQ;QAAE,OAAM;IACrB,MAAM,KAAK,GAAG,eAAe,CAAC,GAAG,CAAC,OAAO,CAAC,CAAA;IAE1C,IAAI,CAAC,KAAK;QAAE,OAAM;IAElB,MAAM,IAAI,GAAG,GAAG,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;IACnC,MAAM,IAAI,GAAG,GAAG,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;IAEnC,MAAM,UAAU,GAAG,eAAe,CAAC,QAAQ,CAAC,CAAA;IAE5C,MAAM,cAAc,GAA+B;QAClD,MAAM,EAAE,KAAK,CAAC,YAAY;QAC1B,MAAM,EAAE,UAAU,CAAC,MAAM;KACzB,CAAA;IAED,IAAI,UAAU,CAAC,MAAM,EAAE,CAAC;QACvB,cAAc,CAAC,aAAa,GAAG,UAAU,CAAC,MAAM,CAAA;IACjD,CAAC;IAED,IAAI,UAAU,CAAC,MAAM,EAAE,CAAC;QACvB,cAAc,CAAC,aAAa,GAAG,UAAU,CAAC,MAAM,CAAA;IACjD,CAAC;IAED,IAAI,CAAC,IAAI,IAAI,CAAC,IAAI,EAAE,CAAC;QACpB,MAAM,EAAE,UAAU,EAAE,cAAc,EAAE,UAAU,EAAE,QAAQ,EAAE,CAAA;QAE1D,OAAM;IACP,CAAC;IAED,IAAI,IAAI,IAAI,IAAI,IAAI,IAAI,KAAK,IAAI,EAAE,CAAC;QACnC,MAAM;YACL,UAAU,EAAE,EAAE,GAAG,cAAc,EAAE,QAAQ,EAAE,IAAI,EAAE;YACjD,UAAU,EAAE,OAAO,IAAI,EAAE;SACzB,CAAA;QAED,OAAM;IACP,CAAC;IAED,IAAI,IAAI,EAAE,CAAC;QACV,MAAM,EAAE,UAAU,EAAE,EAAE,GAAG,cAAc,EAAE,QAAQ,EAAE,IAAI,EAAE,EAAE,UAAU,EAAE,QAAQ,IAAI,EAAE,EAAE,CAAA;IACxF,CAAC;IAED,IAAI,IAAI,IAAI,IAAI,KAAK,IAAI,EAAE,CAAC;QAC3B,MAAM,EAAE,UAAU,EAAE,EAAE,GAAG,cAAc,EAAE,QAAQ,EAAE,IAAI,EAAE,EAAE,UAAU,EAAE,QAAQ,IAAI,EAAE,EAAE,CAAA;IACxF,CAAC;AACF,CAAC;AAED;;GAEG;AACH,QAAQ,CAAC,CAAC,aAAa,CAAC,GAAkB;IAIzC,MAAM,IAAI,GAAG,GAAG,CAAC,IAAI,CAAC,IAAI,EAAE,CAAA;IAE5B,IAAI,CAAC,IAAI;QAAE,OAAM;IACjB,MAAM,KAAK,GAAG,eAAe,CAAC,GAAG,CAAC,OAAO,CAAC,CAAA;IAE1C,IAAI,CAAC,KAAK;QAAE,OAAM;IAElB,MAAM;QACL,UAAU,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE;QAC9B,UAAU,EAAE,eAAe;KAC3B,CAAA;IAED,MAAM;QACL,UAAU,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,CAAC,YAAY,EAAE;QAC1D,UAAU,EAAE,aAAa;KACzB,CAAA;IAED,MAAM;QACL,UAAU,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,CAAC,YAAY,EAAE,OAAO,EAAE,kBAAkB,EAAE;QACvF,UAAU,EAAE,qBAAqB;KACjC,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,kBAAkB;IACjC,OAAO;QACN,EAAE,EAAE,gBAAgB;QACpB,cAAc,EAAE,qBAAqB;QACrC,WAAW,EACV,8GAA8G;QAE/G,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,IAAI,IAAI,CAAC,OAAO,IAAI,IAAI,CAAC,OAAO,KAAK,IAAI,EAAE,CAAC;gBAC3C,MAAM,IAAI,KAAK,CAAC,iDAAiD,IAAI,CAAC,OAAO,EAAE,CAAC,CAAA;YACjF,CAAC;YAED,MAAM,EAAE,GAAG,IAAI,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,UAAU,GAAG,EAAE,CAAC,OAAO,CAAC,mEAAmE,CAAC,CAAA;gBAClG,MAAM,SAAS,GAAG,EAAE,CAAC,OAAO,CAAC,qDAAqD,CAAC,CAAA;gBAEnF,KAAK,MAAM,GAAG,IAAI,UAAU,CAAC,OAAO,EAAsC,EAAE,CAAC;oBAC5E,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;wBAAE,OAAM;oBAEhC,KAAK,MAAM,OAAO,IAAI,cAAc,CAAC,GAAG,CAAC,EAAE,CAAC;wBAC3C,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;4BAAE,OAAM;wBAC7D,MAAM,GAAG,GAAG,aAAa,CAAC,OAAO,CAAC,UAAU,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;wBAExE,IAAI,CAAC,GAAG;4BAAE,SAAQ;wBAClB,MAAM,OAAO,GAAG,mBAAmB,CAAC,OAAO,CAAC,UAAU,EAAE,GAAG,CAAC,CAAA;wBAE5D,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM;4BAAE,SAAQ;wBAE1C,MAAM;4BACL,GAAG;4BACH,UAAU,EAAE,OAAO;4BACnB,OAAO,EAAE,IAAI;4BACb,MAAM,EAAE,OAAO;4BACf,MAAM,EAAE,gBAAgB;4BACxB,SAAS,EAAE,GAAG,gBAAgB,OAAO,GAAG,CAAC,QAAQ,IAAI,OAAO,CAAC,UAAU,EAAE;4BACzE,cAAc,EAAE,EAAE;4BAClB,OAAO,EAAE,qBAAqB;yBAC9B,CAAA;wBAED,OAAO,EAAE,CAAA;oBACV,CAAC;gBACF,CAAC;gBAED,KAAK,MAAM,GAAG,IAAI,SAAS,CAAC,OAAO,EAAqC,EAAE,CAAC;oBAC1E,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;wBAAE,OAAM;oBAEhC,KAAK,MAAM,OAAO,IAAI,aAAa,CAAC,GAAG,CAAC,EAAE,CAAC;wBAC1C,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;4BAAE,OAAM;wBAC7D,MAAM,GAAG,GAAG,aAAa,CAAC,OAAO,CAAC,UAAU,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;wBAExE,IAAI,CAAC,GAAG;4BAAE,SAAQ;wBAClB,MAAM,OAAO,GAAG,mBAAmB,CAAC,OAAO,CAAC,UAAU,EAAE,GAAG,CAAC,CAAA;wBAE5D,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM;4BAAE,SAAQ;wBAE1C,MAAM;4BACL,GAAG;4BACH,UAAU,EAAE,OAAO;4BACnB,OAAO,EAAE,IAAI;4BACb,MAAM,EAAE,OAAO;4BACf,MAAM,EAAE,gBAAgB;4BACxB,SAAS,EAAE,GAAG,gBAAgB,OAAO,GAAG,CAAC,KAAK,IAAI,OAAO,CAAC,UAAU,EAAE;4BACtE,cAAc,EAAE,EAAE;4BAClB,OAAO,EAAE,qBAAqB;yBAC9B,CAAA;wBAED,OAAO,EAAE,CAAA;oBACV,CAAC;gBACF,CAAC;YACF,CAAC;oBAAS,CAAC;gBACV,EAAE,CAAC,KAAK,EAAE,CAAA;YACX,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,YAAY,GAAG,kBAAkB,EAAE,CAAA"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"street-decompose.d.ts","sourceRoot":"","sources":["../../../../src/adapters/tiger/street-decompose.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;
|
|
1
|
+
{"version":3,"file":"street-decompose.d.ts","sourceRoot":"","sources":["../../../../src/adapters/tiger/street-decompose.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAqCH,MAAM,WAAW,gBAAgB;IAChC,MAAM,EAAE,MAAM,GAAG,IAAI,CAAA;IACrB,MAAM,EAAE,MAAM,CAAA;IACd,MAAM,EAAE,MAAM,GAAG,IAAI,CAAA;CACrB;AAED;;;;;GAKG;AACH,wBAAgB,eAAe,CAAC,QAAQ,EAAE,MAAM,GAAG,gBAAgB,CA6ClE"}
|
|
@@ -16,38 +16,29 @@
|
|
|
16
16
|
* suffix: "Blvd" }
|
|
17
17
|
*/
|
|
18
18
|
import { readFileSync } from "node:fs";
|
|
19
|
-
import { resolve } from "node:path";
|
|
20
19
|
import { resourceDictionaryPath } from "@mailwoman/core/utils";
|
|
20
|
+
import { TextSpliterator } from "spliterator";
|
|
21
21
|
function loadDictionary(filename) {
|
|
22
|
-
//
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
const f = form.trim().toLowerCase();
|
|
39
|
-
if (f) {
|
|
40
|
-
set.add(f);
|
|
41
|
-
}
|
|
42
|
-
}
|
|
22
|
+
// `resourceDictionaryPath` already resolves both layouts — `core/data/...` from source and from the
|
|
23
|
+
// packaged `out/` tree. The candidate list this replaced named it TWICE and then guessed a third path
|
|
24
|
+
// off `process.cwd()`, and swallowed every error while probing, so a corrupt dictionary reported as a
|
|
25
|
+
// missing one.
|
|
26
|
+
const text = readFileSync(resourceDictionaryPath("libpostal", "en", filename), "utf8");
|
|
27
|
+
const set = new Set();
|
|
28
|
+
// The largest libpostal dictionary is 8.4 KB, and this runs once per process at module load.
|
|
29
|
+
for (const line of TextSpliterator.from(text)) {
|
|
30
|
+
const trimmed = line.trim();
|
|
31
|
+
if (!trimmed || trimmed.startsWith("#"))
|
|
32
|
+
continue;
|
|
33
|
+
// libpostal format: canonical|abbr|abbr|... — index all forms
|
|
34
|
+
for (const form of trimmed.split("|")) {
|
|
35
|
+
const f = form.trim().toLowerCase();
|
|
36
|
+
if (f) {
|
|
37
|
+
set.add(f);
|
|
43
38
|
}
|
|
44
|
-
return set;
|
|
45
|
-
}
|
|
46
|
-
catch {
|
|
47
|
-
// try next candidate
|
|
48
39
|
}
|
|
49
40
|
}
|
|
50
|
-
|
|
41
|
+
return set;
|
|
51
42
|
}
|
|
52
43
|
const DIRECTIONALS = loadDictionary("directionals.txt");
|
|
53
44
|
const STREET_TYPES = loadDictionary("street_types.txt");
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"street-decompose.js","sourceRoot":"","sources":["../../../../src/adapters/tiger/street-decompose.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAEH,OAAO,EAAE,YAAY,EAAE,MAAM,SAAS,CAAA;
|
|
1
|
+
{"version":3,"file":"street-decompose.js","sourceRoot":"","sources":["../../../../src/adapters/tiger/street-decompose.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAEH,OAAO,EAAE,YAAY,EAAE,MAAM,SAAS,CAAA;AAEtC,OAAO,EAAE,sBAAsB,EAAE,MAAM,uBAAuB,CAAA;AAC9D,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C,SAAS,cAAc,CAAC,QAAgB;IACvC,oGAAoG;IACpG,sGAAsG;IACtG,sGAAsG;IACtG,eAAe;IACf,MAAM,IAAI,GAAG,YAAY,CAAC,sBAAsB,CAAC,WAAW,EAAE,IAAI,EAAE,QAAQ,CAAC,EAAE,MAAM,CAAC,CAAA;IACtF,MAAM,GAAG,GAAG,IAAI,GAAG,EAAU,CAAA;IAE7B,6FAA6F;IAC7F,KAAK,MAAM,IAAI,IAAI,eAAe,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;QAC/C,MAAM,OAAO,GAAG,IAAI,CAAC,IAAI,EAAE,CAAA;QAE3B,IAAI,CAAC,OAAO,IAAI,OAAO,CAAC,UAAU,CAAC,GAAG,CAAC;YAAE,SAAQ;QAEjD,8DAA8D;QAC9D,KAAK,MAAM,IAAI,IAAI,OAAO,CAAC,KAAK,CAAC,GAAG,CAAC,EAAE,CAAC;YACvC,MAAM,CAAC,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAA;YAEnC,IAAI,CAAC,EAAE,CAAC;gBACP,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,CAAA;YACX,CAAC;QACF,CAAC;IACF,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC;AAED,MAAM,YAAY,GAAG,cAAc,CAAC,kBAAkB,CAAC,CAAA;AACvD,MAAM,YAAY,GAAG,cAAc,CAAC,kBAAkB,CAAC,CAAA;AAQvD;;;;;GAKG;AACH,MAAM,UAAU,eAAe,CAAC,QAAgB;IAC/C,MAAM,OAAO,GAAG,QAAQ,CAAC,IAAI,EAAE,CAAA;IAE/B,IAAI,CAAC,OAAO;QAAE,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,EAAE,EAAE,EAAE,MAAM,EAAE,IAAI,EAAE,CAAA;IAE/D,MAAM,MAAM,GAAG,OAAO,CAAC,KAAK,CAAC,KAAK,CAAC,CAAA;IAEnC,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC;QAAE,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,CAAA;IAE/E,MAAM,IAAI,GAAG,CAAC,CAAS,EAAE,EAAE,CAAC,CAAC,CAAC,WAAW,EAAE,CAAC,OAAO,CAAC,KAAK,EAAE,EAAE,CAAC,CAAA;IAE9D,IAAI,MAAM,GAAkB,IAAI,CAAA;IAChC,IAAI,MAAM,GAAkB,IAAI,CAAA;IAChC,IAAI,QAAQ,GAAG,CAAC,CAAA;IAChB,IAAI,MAAM,GAAG,MAAM,CAAC,MAAM,CAAA;IAE1B,6BAA6B;IAC7B,IAAI,YAAY,CAAC,GAAG,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,CAAE,CAAC,CAAC,IAAI,MAAM,CAAC,MAAM,IAAI,CAAC,EAAE,CAAC;QAC9D,MAAM,GAAG,MAAM,CAAC,CAAC,CAAE,CAAA;QACnB,QAAQ,GAAG,CAAC,CAAA;IACb,CAAC;IAED,mFAAmF;IACnF,MAAM,IAAI,GAAG,IAAI,CAAC,MAAM,CAAC,MAAM,GAAG,CAAC,CAAE,CAAC,CAAA;IACtC,MAAM,UAAU,GAAG,MAAM,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,MAAM,GAAG,CAAC,CAAE,CAAC,CAAC,CAAC,CAAC,EAAE,CAAA;IAE/D,IAAI,YAAY,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,YAAY,CAAC,GAAG,CAAC,UAAU,CAAC,EAAE,CAAC;QAC5D,MAAM,GAAG,MAAM,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,MAAM,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;QACnD,MAAM,IAAI,CAAC,CAAA;IACZ,CAAC;SAAM,IAAI,YAAY,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,MAAM,GAAG,QAAQ,IAAI,CAAC,EAAE,CAAC;QAC7D,MAAM,GAAG,MAAM,CAAC,MAAM,GAAG,CAAC,CAAE,CAAA;QAC5B,MAAM,IAAI,CAAC,CAAA;IACZ,CAAC;SAAM,IAAI,YAAY,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,MAAM,GAAG,QAAQ,IAAI,CAAC,EAAE,CAAC;QAC7D,gCAAgC;QAChC,MAAM,GAAG,MAAM,CAAC,MAAM,GAAG,CAAC,CAAE,CAAA;QAC5B,MAAM,IAAI,CAAC,CAAA;IACZ,CAAC;IAED,MAAM,MAAM,GAAG,MAAM,CAAC,KAAK,CAAC,QAAQ,EAAE,MAAM,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;IAE9D,IAAI,CAAC,MAAM,EAAE,CAAC;QACb,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,CAAA;IACvD,CAAC;IAED,OAAO,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,CAAA;AAClC,CAAC"}
|
|
@@ -8,9 +8,9 @@
|
|
|
8
8
|
* Federally Qualified Health Centers (FQHCs) are HRSA-funded community health programs that
|
|
9
9
|
* self-report site addresses to the HRSA Data Warehouse. The published CSV (`data.hrsa.gov`)
|
|
10
10
|
* carries the site name, the postal-formatted street address, and the locality/region/postcode
|
|
11
|
-
* quad.
|
|
12
|
-
*
|
|
13
|
-
*
|
|
11
|
+
* quad. The source earns its place on adversarial-value-per-row (#22): every facility name is a
|
|
12
|
+
* human-typed venue string and the addresses pass through enough hands to accumulate the
|
|
13
|
+
* abbreviation drift + suite designator chaos that pure gazetteer data does not.
|
|
14
14
|
*
|
|
15
15
|
* The adapter consumes a CSV file the operator pre-downloads. The HRSA data is published as a
|
|
16
16
|
* single national CSV (~10K rows), small enough that the operator can re-fetch on every corpus
|
|
@@ -28,7 +28,7 @@
|
|
|
28
28
|
* License: stamped `"Public Domain"` per the HRSA Data Warehouse's federal government distribution
|
|
29
29
|
* terms.
|
|
30
30
|
*/
|
|
31
|
-
import type { CorpusAdapter } from "
|
|
31
|
+
import type { CorpusAdapter } from "@mailwoman/corpus/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/usgov-hrsa-fqhc/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA6BG;
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/usgov-hrsa-fqhc/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA6BG;AAIH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,yBAAyB,CAAA;AAI1F;;;GAGG;AACH,eAAO,MAAM,0BAA0B,oBAAoB,CAAA;AAC3D;;;GAGG;AACH,eAAO,MAAM,+BAA+B,kBAAkB,CAAA;AAmD9D,wBAAgB,0BAA0B,IAAI,aAAa,CA8E1D;AAED;;GAEG;AACH,eAAO,MAAM,oBAAoB,eAA+B,CAAA"}
|