@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
|
@@ -22,7 +22,7 @@
|
|
|
22
22
|
* non-US countries; for US, the postcode-last sources are the right order. License:
|
|
23
23
|
* `"CC-BY-4.0"` per row (attribute "GeoNames").
|
|
24
24
|
*/
|
|
25
|
-
import type { CorpusAdapter } from "
|
|
25
|
+
import type { CorpusAdapter } from "@mailwoman/corpus/types";
|
|
26
26
|
/**
|
|
27
27
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
28
28
|
* it came from.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/geonames-postal/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/geonames-postal/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAGH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,yBAAyB,CAAA;AAI1F;;;GAGG;AACH,eAAO,MAAM,0BAA0B,oBAAoB,CAAA;AAC3D;;;GAGG;AACH,eAAO,MAAM,+BAA+B,cAAc,CAAA;AAO1D,wBAAgB,2BAA2B,IAAI,aAAa,CAkE3D;AAED;;GAEG;AACH,eAAO,MAAM,qBAAqB,eAAgC,CAAA"}
|
|
@@ -22,10 +22,9 @@
|
|
|
22
22
|
* non-US countries; for US, the postcode-last sources are the right order. License:
|
|
23
23
|
* `"CC-BY-4.0"` per row (attribute "GeoNames").
|
|
24
24
|
*/
|
|
25
|
-
import {
|
|
26
|
-
import {
|
|
27
|
-
import {
|
|
28
|
-
import { reconcileComponents } from "../../format.js";
|
|
25
|
+
import { stableSourceID } from "@mailwoman/corpus/adapters/utils";
|
|
26
|
+
import { reconcileComponents } from "@mailwoman/formatter";
|
|
27
|
+
import { TSVSpliterator } from "spliterator";
|
|
29
28
|
/**
|
|
30
29
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
31
30
|
* it came from.
|
|
@@ -46,59 +45,55 @@ export function createGeonamesPostalAdapter() {
|
|
|
46
45
|
defaultLicense: GEONAMES_POSTAL_DEFAULT_LICENSE,
|
|
47
46
|
description: "GeoNames postal codes (CC-BY-4.0) — multi-locale postcode→locality→region, names inline; international postcode-first order.",
|
|
48
47
|
async *rows(opts) {
|
|
49
|
-
|
|
50
|
-
|
|
48
|
+
// `header: false` — the GeoNames postal dump is headerless, and the spliterator would
|
|
49
|
+
// otherwise consume row 1 as column names and lose its first postcode.
|
|
50
|
+
const rows = TSVSpliterator.fromAsync(opts.inputPath, { header: false });
|
|
51
51
|
let emitted = 0;
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
|
|
52
|
+
for await (const rec of rows) {
|
|
53
|
+
if (opts.signal?.aborted)
|
|
54
|
+
break;
|
|
55
|
+
if (opts.limit !== undefined && emitted >= opts.limit)
|
|
56
|
+
break;
|
|
57
|
+
const cc = (rec[COL.country] ?? "").trim();
|
|
58
|
+
if (!cc)
|
|
59
|
+
continue;
|
|
60
|
+
if (opts.country && cc !== opts.country)
|
|
61
|
+
continue;
|
|
62
|
+
const postcode = (rec[COL.postcode] ?? "").trim();
|
|
63
|
+
const locality = (rec[COL.place] ?? "").trim();
|
|
64
|
+
if (!postcode || !locality)
|
|
65
|
+
continue;
|
|
66
|
+
const region = (rec[COL.admin1Name] ?? "").trim();
|
|
67
|
+
// Postcode-first (international) variants. Skip the region variant when admin1 just
|
|
68
|
+
// repeats the place (common for city-states / micro-admin) to avoid "X X" noise.
|
|
69
|
+
const variants = [
|
|
70
|
+
{ slot: "pl", comp: { postcode, locality }, raw: `${postcode} ${locality}` },
|
|
71
|
+
];
|
|
72
|
+
if (region && region.toLowerCase() !== locality.toLowerCase()) {
|
|
73
|
+
variants.push({
|
|
74
|
+
slot: "plr",
|
|
75
|
+
comp: { postcode, locality, region },
|
|
76
|
+
raw: `${postcode} ${locality}, ${region}`,
|
|
77
|
+
});
|
|
78
|
+
}
|
|
79
|
+
for (const v of variants) {
|
|
56
80
|
if (opts.limit !== undefined && emitted >= opts.limit)
|
|
57
81
|
break;
|
|
58
|
-
const
|
|
59
|
-
if (
|
|
60
|
-
continue;
|
|
61
|
-
if (opts.country && cc !== opts.country)
|
|
82
|
+
const aligned = reconcileComponents(v.comp, v.raw);
|
|
83
|
+
if (Object.keys(aligned).length < 2)
|
|
62
84
|
continue;
|
|
63
|
-
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
|
|
70
|
-
|
|
71
|
-
|
|
72
|
-
|
|
73
|
-
if (region && region.toLowerCase() !== locality.toLowerCase()) {
|
|
74
|
-
variants.push({
|
|
75
|
-
slot: "plr",
|
|
76
|
-
comp: { postcode, locality, region },
|
|
77
|
-
raw: `${postcode} ${locality}, ${region}`,
|
|
78
|
-
});
|
|
79
|
-
}
|
|
80
|
-
for (const v of variants) {
|
|
81
|
-
if (opts.limit !== undefined && emitted >= opts.limit)
|
|
82
|
-
break;
|
|
83
|
-
const aligned = reconcileComponents(v.comp, v.raw);
|
|
84
|
-
if (Object.keys(aligned).length < 2)
|
|
85
|
-
continue;
|
|
86
|
-
yield {
|
|
87
|
-
raw: v.raw,
|
|
88
|
-
components: aligned,
|
|
89
|
-
country: cc,
|
|
90
|
-
source: GEONAMES_POSTAL_ADAPTER_ID,
|
|
91
|
-
source_id: `${stableSourceID(GEONAMES_POSTAL_ADAPTER_ID, aligned)}-${v.slot}`,
|
|
92
|
-
corpus_version: "",
|
|
93
|
-
license: GEONAMES_POSTAL_DEFAULT_LICENSE,
|
|
94
|
-
};
|
|
95
|
-
emitted++;
|
|
96
|
-
}
|
|
85
|
+
yield {
|
|
86
|
+
raw: v.raw,
|
|
87
|
+
components: aligned,
|
|
88
|
+
country: cc,
|
|
89
|
+
source: GEONAMES_POSTAL_ADAPTER_ID,
|
|
90
|
+
source_id: `${stableSourceID(GEONAMES_POSTAL_ADAPTER_ID, aligned)}-${v.slot}`,
|
|
91
|
+
corpus_version: "",
|
|
92
|
+
license: GEONAMES_POSTAL_DEFAULT_LICENSE,
|
|
93
|
+
};
|
|
94
|
+
emitted++;
|
|
97
95
|
}
|
|
98
96
|
}
|
|
99
|
-
finally {
|
|
100
|
-
stream.destroy();
|
|
101
|
-
}
|
|
102
97
|
},
|
|
103
98
|
};
|
|
104
99
|
}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/geonames-postal/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAEH,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/geonames-postal/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AAEH,OAAO,EAAE,cAAc,EAAE,MAAM,kCAAkC,CAAA;AAEjE,OAAO,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AAC1D,OAAO,EAAE,cAAc,EAAE,MAAM,aAAa,CAAA;AAE5C;;;GAGG;AACH,MAAM,CAAC,MAAM,0BAA0B,GAAG,iBAAiB,CAAA;AAC3D;;;GAGG;AACH,MAAM,CAAC,MAAM,+BAA+B,GAAG,WAAW,CAAA;AAE1D;;GAEG;AACH,MAAM,GAAG,GAAG,EAAE,OAAO,EAAE,CAAC,EAAE,QAAQ,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,UAAU,EAAE,CAAC,EAAW,CAAA;AAEzE,MAAM,UAAU,2BAA2B;IAC1C,OAAO;QACN,EAAE,EAAE,0BAA0B;QAC9B,cAAc,EAAE,+BAA+B;QAC/C,WAAW,EACV,8HAA8H;QAE/H,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,sFAAsF;YACtF,uEAAuE;YACvE,MAAM,IAAI,GAAG,cAAc,CAAC,SAAS,CAAC,IAAI,CAAC,SAAS,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,CAAC,CAAA;YAExE,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,IAA+B,EAAE,CAAC;gBACzD,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;oBAAE,MAAK;gBAE/B,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;oBAAE,MAAK;gBAE5D,MAAM,EAAE,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAE1C,IAAI,CAAC,EAAE;oBAAE,SAAQ;gBAEjB,IAAI,IAAI,CAAC,OAAO,IAAI,EAAE,KAAK,IAAI,CAAC,OAAO;oBAAE,SAAQ;gBAEjD,MAAM,QAAQ,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBACjD,MAAM,QAAQ,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAE9C,IAAI,CAAC,QAAQ,IAAI,CAAC,QAAQ;oBAAE,SAAQ;gBACpC,MAAM,MAAM,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,UAAU,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;gBAEjD,oFAAoF;gBACpF,iFAAiF;gBACjF,MAAM,QAAQ,GAA2E;oBACxF,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,EAAE,QAAQ,EAAE,QAAQ,EAAE,EAAE,GAAG,EAAE,GAAG,QAAQ,IAAI,QAAQ,EAAE,EAAE;iBAC5E,CAAA;gBAED,IAAI,MAAM,IAAI,MAAM,CAAC,WAAW,EAAE,KAAK,QAAQ,CAAC,WAAW,EAAE,EAAE,CAAC;oBAC/D,QAAQ,CAAC,IAAI,CAAC;wBACb,IAAI,EAAE,KAAK;wBACX,IAAI,EAAE,EAAE,QAAQ,EAAE,QAAQ,EAAE,MAAM,EAAE;wBACpC,GAAG,EAAE,GAAG,QAAQ,IAAI,QAAQ,KAAK,MAAM,EAAE;qBACzC,CAAC,CAAA;gBACH,CAAC;gBAED,KAAK,MAAM,CAAC,IAAI,QAAQ,EAAE,CAAC;oBAC1B,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;wBAAE,MAAK;oBAC5D,MAAM,OAAO,GAAG,mBAAmB,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,GAAG,CAAC,CAAA;oBAElD,IAAI,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM,GAAG,CAAC;wBAAE,SAAQ;oBAE7C,MAAM;wBACL,GAAG,EAAE,CAAC,CAAC,GAAG;wBACV,UAAU,EAAE,OAAO;wBACnB,OAAO,EAAE,EAAE;wBACX,MAAM,EAAE,0BAA0B;wBAClC,SAAS,EAAE,GAAG,cAAc,CAAC,0BAA0B,EAAE,OAAO,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE;wBAC7E,cAAc,EAAE,EAAE;wBAClB,OAAO,EAAE,+BAA+B;qBACxC,CAAA;oBAED,OAAO,EAAE,CAAA;gBACV,CAAC;YACF,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,qBAAqB,GAAG,2BAA2B,EAAE,CAAA"}
|
|
@@ -27,7 +27,7 @@
|
|
|
27
27
|
* Input: the assembled component JSONL (one `{house_number,street,locality,region,postcode}` per
|
|
28
28
|
* line). Open G-NAF licence — attribute "Geoscape Australia".
|
|
29
29
|
*/
|
|
30
|
-
import type { CorpusAdapter } from "
|
|
30
|
+
import type { CorpusAdapter } from "@mailwoman/corpus/types";
|
|
31
31
|
/**
|
|
32
32
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
33
33
|
* it came from.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/gnaf/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/gnaf/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AAIH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,yBAAyB,CAAA;AAI1F;;;GAGG;AACH,eAAO,MAAM,eAAe,SAAS,CAAA;AACrC;;GAEG;AACH,eAAO,MAAM,oBAAoB,cAAc,CAAA;AA4B/C;;;GAGG;AACH,wBAAgB,iBAAiB,IAAI,aAAa,CAkEjD;AAED;;GAEG;AACH,eAAO,MAAM,WAAW,eAAsB,CAAA"}
|
|
@@ -27,9 +27,10 @@
|
|
|
27
27
|
* Input: the assembled component JSONL (one `{house_number,street,locality,region,postcode}` per
|
|
28
28
|
* line). Open G-NAF licence — attribute "Geoscape Australia".
|
|
29
29
|
*/
|
|
30
|
+
import { tryParsingJSON } from "@mailwoman/core/objects";
|
|
31
|
+
import { stableSourceID } from "@mailwoman/corpus/adapters/utils";
|
|
32
|
+
import { reconcileComponents } from "@mailwoman/formatter";
|
|
30
33
|
import { TextSpliterator } from "spliterator";
|
|
31
|
-
import { stableSourceID } from "../../adapter.js";
|
|
32
|
-
import { reconcileComponents } from "../../format.js";
|
|
33
34
|
/**
|
|
34
35
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
35
36
|
* it came from.
|
|
@@ -69,7 +70,7 @@ export function createGNAFAdapter() {
|
|
|
69
70
|
let idx = 0;
|
|
70
71
|
// Input is the assembled component JSONL (one tuple per line). TextSpliterator auto-disposes on
|
|
71
72
|
// loop completion and on an early `break` (abort / limit), so the old explicit handle teardown is
|
|
72
|
-
// gone;
|
|
73
|
+
// gone; the parse tolerates a trailing CR on CRLF sources and the `!line.trim()` guard skips blanks.
|
|
73
74
|
// The render order rotates (i % 3), matching v1.9.1's rerender.
|
|
74
75
|
for await (const line of TextSpliterator.fromAsync(opts.inputPath)) {
|
|
75
76
|
if (opts.signal?.aborted)
|
|
@@ -78,13 +79,9 @@ export function createGNAFAdapter() {
|
|
|
78
79
|
break;
|
|
79
80
|
if (!line.trim())
|
|
80
81
|
continue;
|
|
81
|
-
|
|
82
|
-
|
|
83
|
-
t = JSON.parse(line);
|
|
84
|
-
}
|
|
85
|
-
catch {
|
|
82
|
+
const t = tryParsingJSON(line);
|
|
83
|
+
if (t === null)
|
|
86
84
|
continue;
|
|
87
|
-
}
|
|
88
85
|
if (!t.house_number || !t.street || !t.locality || !t.postcode)
|
|
89
86
|
continue;
|
|
90
87
|
const orders = renderOrders(t);
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/gnaf/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AAEH,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/gnaf/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA4BG;AAEH,OAAO,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAA;AACxD,OAAO,EAAE,cAAc,EAAE,MAAM,kCAAkC,CAAA;AAEjE,OAAO,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AAC1D,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C;;;GAGG;AACH,MAAM,CAAC,MAAM,eAAe,GAAG,MAAM,CAAA;AACrC;;GAEG;AACH,MAAM,CAAC,MAAM,oBAAoB,GAAG,WAAW,CAAA;AAU/C;;;;GAIG;AACH,SAAS,YAAY,CAAC,CAAY;IACjC,MAAM,MAAM,GAAG,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,EAAE,CAAA;IAE7C,OAAO;QACN,yGAAyG;QACzG,GAAG,CAAC,CAAC,YAAY,IAAI,CAAC,CAAC,MAAM,KAAK,CAAC,CAAC,QAAQ,GAAG,MAAM,IAAI,CAAC,CAAC,QAAQ,EAAE;QACrE,yEAAyE;QACzE,GAAG,CAAC,CAAC,QAAQ,IAAI,CAAC,CAAC,QAAQ,KAAK,CAAC,CAAC,MAAM,IAAI,CAAC,CAAC,YAAY,EAAE;QAC5D,mDAAmD;QACnD,GAAG,CAAC,CAAC,QAAQ,KAAK,CAAC,CAAC,QAAQ,KAAK,CAAC,CAAC,MAAM,IAAI,CAAC,CAAC,YAAY,EAAE;KAC7D,CAAA;AACF,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,iBAAiB;IAChC,OAAO;QACN,EAAE,EAAE,eAAe;QACnB,cAAc,EAAE,oBAAoB;QACpC,WAAW,EACV,4KAA4K;QAE7K,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,IAAI,OAAO,GAAG,CAAC,CAAA;YACf,IAAI,GAAG,GAAG,CAAC,CAAA;YAEX,gGAAgG;YAChG,kGAAkG;YAClG,qGAAqG;YACrG,gEAAgE;YAChE,IAAI,KAAK,EAAE,MAAM,IAAI,IAAI,eAAe,CAAC,SAAS,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,CAAC;gBACpE,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;oBAAE,MAAK;gBAE/B,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;oBAAE,MAAK;gBAE5D,IAAI,CAAC,IAAI,CAAC,IAAI,EAAE;oBAAE,SAAQ;gBAE1B,MAAM,CAAC,GAAG,cAAc,CAAY,IAAI,CAAC,CAAA;gBAEzC,IAAI,CAAC,KAAK,IAAI;oBAAE,SAAQ;gBAExB,IAAI,CAAC,CAAC,CAAC,YAAY,IAAI,CAAC,CAAC,CAAC,MAAM,IAAI,CAAC,CAAC,CAAC,QAAQ,IAAI,CAAC,CAAC,CAAC,QAAQ;oBAAE,SAAQ;gBAExE,MAAM,MAAM,GAAG,YAAY,CAAC,CAAC,CAAC,CAAA;gBAC9B,MAAM,KAAK,GAAG,GAAG,GAAG,MAAM,CAAC,MAAM,CAAA;gBAEjC,GAAG,EAAE,CAAA;gBACL,MAAM,GAAG,GAAG,MAAM,CAAC,KAAK,CAAE,CAAA;gBAE1B,MAAM,UAAU,GAA+B;oBAC9C,YAAY,EAAE,CAAC,CAAC,YAAY;oBAC5B,MAAM,EAAE,CAAC,CAAC,MAAM;oBAChB,QAAQ,EAAE,CAAC,CAAC,QAAQ;oBACpB,QAAQ,EAAE,CAAC,CAAC,QAAQ;iBACpB,CAAA;gBAED,yFAAyF;gBACzF,qFAAqF;gBACrF,IAAI,KAAK,KAAK,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,CAAC;oBAC7B,UAAU,CAAC,MAAM,GAAG,CAAC,CAAC,MAAM,CAAA;gBAC7B,CAAC;gBAED,MAAM,OAAO,GAAG,mBAAmB,CAAC,UAAU,EAAE,GAAG,CAAC,CAAA;gBAEpD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM;oBAAE,SAAQ;gBAE1C,MAAM;oBACL,GAAG;oBACH,UAAU,EAAE,OAAO;oBACnB,OAAO,EAAE,IAAI;oBACb,MAAM,EAAE,OAAO;oBACf,MAAM,EAAE,eAAe;oBACvB,SAAS,EAAE,GAAG,cAAc,CAAC,eAAe,EAAE,OAAO,CAAC,KAAK,KAAK,EAAE;oBAClE,cAAc,EAAE,EAAE;oBAClB,OAAO,EAAE,oBAAoB;iBAC7B,CAAA;gBAED,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,WAAW,GAAG,iBAAiB,EAAE,CAAA"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"assemble.d.ts","sourceRoot":"","sources":["../../../../src/adapters/gnaf/assemble.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;GA0BG;
|
|
1
|
+
{"version":3,"file":"assemble.d.ts","sourceRoot":"","sources":["../../../../src/adapters/gnaf/assemble.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;GA0BG;AASH,MAAM,WAAW,mBAAmB;IACnC;;OAEG;IACH,WAAW,EAAE,MAAM,CAAA;IACnB;;OAEG;IACH,UAAU,EAAE,MAAM,CAAA;IAClB;;OAEG;IACH,GAAG,EAAE,MAAM,CAAA;IACX;;OAEG;IACH,WAAW,CAAC,EAAE,MAAM,CAAA;IACpB;;OAEG;IACH,UAAU,CAAC,EAAE,CAAC,OAAO,EAAE,MAAM,KAAK,IAAI,CAAA;CACtC;AAED,MAAM,WAAW,kBAAkB;IAClC,OAAO,EAAE,MAAM,CAAA;IACf,IAAI,EAAE,MAAM,CAAA;IACZ,OAAO,EAAE,MAAM,CAAA;IACf,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;CAC/B;AAED;;GAEG;AACH,wBAAgB,SAAS,CAAC,CAAC,EAAE,MAAM,GAAG,MAAM,CAK3C;AAED;;GAEG;AACH,wBAAgB,cAAc,CAAC,MAAM,EAAE,MAAM,EAAE,QAAQ,EAAE,MAAM,EAAE,QAAQ,EAAE,MAAM,GAAG,MAAM,CAEzF;AA8CD,wBAAsB,YAAY,CAAC,IAAI,EAAE,mBAAmB,GAAG,OAAO,CAAC,kBAAkB,CAAC,CAmGzF"}
|
|
@@ -26,9 +26,10 @@
|
|
|
26
26
|
* excluded by (street, locality, postcode) so the training shard never overlaps the benchmark.
|
|
27
27
|
*/
|
|
28
28
|
import { createWriteStream } from "node:fs";
|
|
29
|
-
import { readdir
|
|
29
|
+
import { readdir } from "node:fs/promises";
|
|
30
30
|
import { join } from "node:path";
|
|
31
|
-
import {
|
|
31
|
+
import { tryParsingJSON } from "@mailwoman/core/objects";
|
|
32
|
+
import { PSVSpliterator, TextSpliterator } from "spliterator";
|
|
32
33
|
/**
|
|
33
34
|
* UPPERCASE → Title Case, preserving intra-word apostrophes/hyphens (O'Brien, Coff's Harbour).
|
|
34
35
|
*/
|
|
@@ -67,18 +68,12 @@ async function loadMap(paths, keyCol, pick) {
|
|
|
67
68
|
*/
|
|
68
69
|
async function loadHoldout(path) {
|
|
69
70
|
const keys = new Set();
|
|
70
|
-
const
|
|
71
|
-
for (const line of text.split("\n")) {
|
|
71
|
+
for await (const line of TextSpliterator.fromAsync(path)) {
|
|
72
72
|
if (!line.trim())
|
|
73
73
|
continue;
|
|
74
|
-
|
|
75
|
-
|
|
76
|
-
|
|
77
|
-
keys.add(gnafHoldoutKey(c.street, c.locality, c.postcode));
|
|
78
|
-
}
|
|
79
|
-
}
|
|
80
|
-
catch {
|
|
81
|
-
/* skip malformed */
|
|
74
|
+
const c = tryParsingJSON(line)?.components;
|
|
75
|
+
if (c?.street && c?.locality && c?.postcode) {
|
|
76
|
+
keys.add(gnafHoldoutKey(c.street, c.locality, c.postcode));
|
|
82
77
|
}
|
|
83
78
|
}
|
|
84
79
|
return keys;
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"assemble.js","sourceRoot":"","sources":["../../../../src/adapters/gnaf/assemble.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;GA0BG;AAEH,OAAO,EAAE,iBAAiB,EAAE,MAAM,SAAS,CAAA;AAC3C,OAAO,EAAE,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"assemble.js","sourceRoot":"","sources":["../../../../src/adapters/gnaf/assemble.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;GA0BG;AAEH,OAAO,EAAE,iBAAiB,EAAE,MAAM,SAAS,CAAA;AAC3C,OAAO,EAAE,OAAO,EAAE,MAAM,kBAAkB,CAAA;AAC1C,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAEhC,OAAO,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAA;AACxD,OAAO,EAAE,cAAc,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAgC7D;;GAEG;AACH,MAAM,UAAU,SAAS,CAAC,CAAS;IAClC,OAAO,CAAC;SACN,WAAW,EAAE;SACb,UAAU,CAAC,sBAAsB,EAAE,CAAC,EAAE,EAAE,CAAS,EAAE,CAAS,EAAE,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,WAAW,EAAE,CAAC;SACrF,IAAI,EAAE,CAAA;AACT,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,cAAc,CAAC,MAAc,EAAE,QAAgB,EAAE,QAAgB;IAChF,OAAO,GAAG,MAAM,IAAI,QAAQ,IAAI,QAAQ,EAAE,CAAC,WAAW,EAAE,CAAA;AACzD,CAAC;AAID,KAAK,SAAS,CAAC,CAAC,UAAU,CAAC,IAAY;IACtC,KAAK,CAAC,CAAC,cAAc,CAAC,SAAS,CAAC,IAAI,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,MAAM,EAAE,IAAI,EAAE,CAAuB,CAAA;AAC9F,CAAC;AAED;;GAEG;AACH,KAAK,UAAU,OAAO,CAAI,KAAe,EAAE,MAAc,EAAE,IAAmB;IAC7E,MAAM,CAAC,GAAG,IAAI,GAAG,EAAa,CAAA;IAE9B,KAAK,MAAM,CAAC,IAAI,KAAK,EAAE,CAAC;QACvB,IAAI,KAAK,EAAE,MAAM,CAAC,IAAI,UAAU,CAAC,CAAC,CAAC,EAAE,CAAC;YACrC,MAAM,CAAC,GAAG,CAAC,CAAC,MAAM,CAAC,CAAA;YAEnB,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,KAAK,EAAE,EAAE,CAAC;gBAC3B,CAAC,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,IAAI,CAAC,CAAC,CAAC,CAAC,CAAA;YAC1B,CAAC;QACF,CAAC;IACF,CAAC;IAED,OAAO,CAAC,CAAA;AACT,CAAC;AAED;;GAEG;AACH,KAAK,UAAU,WAAW,CAAC,IAAY;IACtC,MAAM,IAAI,GAAG,IAAI,GAAG,EAAU,CAAA;IAE9B,IAAI,KAAK,EAAE,MAAM,IAAI,IAAI,eAAe,CAAC,SAAS,CAAC,IAAI,CAAC,EAAE,CAAC;QAC1D,IAAI,CAAC,IAAI,CAAC,IAAI,EAAE;YAAE,SAAQ;QAE1B,MAAM,CAAC,GAAG,cAAc,CAA0C,IAAI,CAAC,EAAE,UAAU,CAAA;QAEnF,IAAI,CAAC,EAAE,MAAM,IAAI,CAAC,EAAE,QAAQ,IAAI,CAAC,EAAE,QAAQ,EAAE,CAAC;YAC7C,IAAI,CAAC,GAAG,CAAC,cAAc,CAAC,CAAC,CAAC,MAAM,EAAE,CAAC,CAAC,QAAQ,EAAE,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAA;QAC3D,CAAC;IACF,CAAC;IAED,OAAO,IAAI,CAAA;AACZ,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,YAAY,CAAC,IAAyB;IAC3D,MAAM,QAAQ,GAAG,IAAI,CAAC,UAAU,IAAI,CAAC,GAAG,EAAE,GAAE,CAAC,CAAC,CAAA;IAC9C,MAAM,KAAK,GAAG,MAAM,OAAO,CAAC,IAAI,CAAC,WAAW,CAAC,CAAA;IAE7C,MAAM,IAAI,GAAG,CAAC,EAAU,EAAE,OAAgB,EAAE,EAAE,CAC7C,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,EAAE,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,OAAO,IAAI,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,IAAI,CAAC,IAAI,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,CAAA;IAEvG,+FAA+F;IAC/F,MAAM,WAAW,GAAG,IAAI,CAAC,4BAA4B,CAAC,CAAA;IACtD,MAAM,aAAa,GAAG,IAAI,CAAC,qBAAqB,EAAE,4BAA4B,CAAC,CAAA;IAC/E,MAAM,YAAY,GAAG,IAAI,CAAC,2BAA2B,CAAC,CAAA;IAEtD,MAAM,OAAO,GAAG,IAAI,CAAC,WAAW,CAAC,CAAC,CAAC,MAAM,WAAW,CAAC,IAAI,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC,IAAI,GAAG,EAAU,CAAA;IAE1F,IAAI,IAAI,CAAC,WAAW,EAAE,CAAC;QACtB,QAAQ,CAAC,uBAAuB,OAAO,CAAC,IAAI,EAAE,CAAC,CAAA;IAChD,CAAC;IAED,QAAQ,CAAC,4BAA4B,WAAW,CAAC,MAAM,uBAAuB,aAAa,CAAC,MAAM,IAAI,CAAC,CAAA;IAEvG,MAAM,SAAS,GAAG,MAAM,OAAO,CAAC,WAAW,EAAE,qBAAqB,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC;QAC3E,IAAI,EAAE,MAAM,CAAC,CAAC,CAAC,WAAW,IAAI,EAAE,CAAC;QACjC,IAAI,EAAE,MAAM,CAAC,CAAC,CAAC,gBAAgB,IAAI,EAAE,CAAC;QACtC,MAAM,EAAE,MAAM,CAAC,CAAC,CAAC,kBAAkB,IAAI,EAAE,CAAC;KAC1C,CAAC,CAAC,CAAA;IAEH,MAAM,WAAW,GAAG,MAAM,OAAO,CAAC,aAAa,EAAE,cAAc,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,MAAM,CAAC,CAAC,CAAC,aAAa,IAAI,EAAE,CAAC,CAAC,CAAA;IACtG,QAAQ,CAAC,WAAW,SAAS,CAAC,IAAI,CAAC,cAAc,EAAE,eAAe,WAAW,CAAC,IAAI,CAAC,cAAc,EAAE,EAAE,CAAC,CAAA;IAEtG,MAAM,SAAS,GACd,EAAE,CAAA;IAEH,IAAI,IAAI,GAAG,CAAC,CAAA;IACZ,IAAI,OAAO,GAAG,CAAC,CAAA;IAEf,KAAK,MAAM,CAAC,IAAI,YAAY,EAAE,CAAC;QAC9B,MAAM,KAAK,GAAG,CAAC,CAAC,CAAC,KAAK,CAAC,2BAA2B,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAA;QAEnE,IAAI,KAAK,EAAE,MAAM,CAAC,IAAI,UAAU,CAAC,CAAC,CAAC,EAAE,CAAC;YACrC,MAAM,WAAW,GAAG,MAAM,CAAC,CAAC,CAAC,YAAY,IAAI,EAAE,CAAC,CAAA;YAEhD,IAAI,CAAC,WAAW,IAAI,CAAC,CAAC,YAAY,IAAI,CAAC,CAAC,CAAC,QAAQ;gBAAE,SAAQ;YAC3D,MAAM,EAAE,GAAG,SAAS,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,mBAAmB,IAAI,EAAE,CAAC,CAAC,CAAA;YAC7D,MAAM,SAAS,GAAG,WAAW,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,YAAY,IAAI,EAAE,CAAC,CAAC,CAAA;YAE/D,IAAI,CAAC,EAAE,EAAE,IAAI,IAAI,CAAC,SAAS;gBAAE,SAAQ;YACrC,MAAM,MAAM,GAAG,GAAG,SAAS,CAAC,EAAE,CAAC,IAAI,CAAC,IAAI,SAAS,CAAC,EAAE,CAAC,IAAI,CAAC,GAAG,EAAE,CAAC,MAAM,CAAC,CAAC,CAAC,GAAG,GAAG,SAAS,CAAC,EAAE,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,IAAI,EAAE,CAAA;YACjH,MAAM,QAAQ,GAAG,SAAS,CAAC,SAAS,CAAC,CAAA;YACrC,MAAM,QAAQ,GAAG,MAAM,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAA;YAEnC,IAAI,OAAO,CAAC,GAAG,CAAC,cAAc,CAAC,MAAM,EAAE,QAAQ,EAAE,QAAQ,CAAC,CAAC,EAAE,CAAC;gBAC7D,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,IAAI,KAAK,GAAG,WAAW,GAAG,CAAC,CAAC,CAAC,mBAAmB,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,mBAAmB,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAA;YAEtF,IAAI,CAAC,CAAC,WAAW,EAAE,CAAC;gBACnB,KAAK,GAAG,GAAG,KAAK,IAAI,MAAM,CAAC,CAAC,CAAC,WAAW,CAAC,EAAE,CAAA;YAC5C,CAAC;YAED,IAAI,CAAC,CAAC,WAAW,EAAE,CAAC;gBACnB,KAAK,GAAG,GAAG,MAAM,CAAC,CAAC,CAAC,WAAW,CAAC,IAAI,KAAK,EAAE,CAAA;YAC5C,CAAC;YAED,MAAM,KAAK,GAAG,EAAE,YAAY,EAAE,KAAK,EAAE,MAAM,EAAE,QAAQ,EAAE,MAAM,EAAE,KAAK,EAAE,QAAQ,EAAE,CAAA;YAEhF,IAAI,EAAE,CAAA;YAEN,IAAI,SAAS,CAAC,MAAM,GAAG,IAAI,CAAC,UAAU,EAAE,CAAC;gBACxC,SAAS,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;YACtB,CAAC;iBAAM,CAAC;gBACP,MAAM,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,MAAM,EAAE,GAAG,IAAI,CAAC,CAAA;gBAE1C,IAAI,CAAC,GAAG,IAAI,CAAC,UAAU,EAAE,CAAC;oBACzB,SAAS,CAAC,CAAC,CAAC,GAAG,KAAK,CAAA;gBACrB,CAAC;YACF,CAAC;QACF,CAAC;QAED,QAAQ,CAAC,GAAG,KAAK,KAAK,IAAI,CAAC,cAAc,EAAE,sBAAsB,CAAC,CAAA;IACnE,CAAC;IAED,MAAM,GAAG,GAAG,iBAAiB,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;IACvC,MAAM,OAAO,GAA2B,EAAE,CAAA;IAE1C,KAAK,MAAM,CAAC,IAAI,SAAS,EAAE,CAAC;QAC3B,GAAG,CAAC,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,CAAA;QACnC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAA;IACjD,CAAC;IAED,MAAM,IAAI,OAAO,CAAO,CAAC,GAAG,EAAE,EAAE;QAC/B,GAAG,CAAC,GAAG,CAAC,GAAG,CAAC,CAAA;IACb,CAAC,CAAC,CAAA;IAEF,QAAQ,CAAC,SAAS,SAAS,CAAC,MAAM,CAAC,cAAc,EAAE,aAAa,IAAI,CAAC,GAAG,EAAE,CAAC,CAAA;IAE3E,OAAO,EAAE,OAAO,EAAE,SAAS,CAAC,MAAM,EAAE,IAAI,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;AAC7D,CAAC"}
|
|
@@ -18,7 +18,7 @@
|
|
|
18
18
|
* JSON-bundle pivot (`./wof-admin-json/` and `./wof-postalcode-json/` directories hold the
|
|
19
19
|
* implementations; the registered ids are unchanged).
|
|
20
20
|
*/
|
|
21
|
-
import type { CorpusAdapter } from "
|
|
21
|
+
import type { CorpusAdapter } from "@mailwoman/corpus/types";
|
|
22
22
|
/**
|
|
23
23
|
* Built-in adapters. Order is significant: `corpus build` iterates this list to drive every adapter in turn.
|
|
24
24
|
* Coarse-first (admin → postcode), then street-level (BAN FR, TIGER US, OpenAddresses global), then adversarial-source
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/adapters/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;GAmBG;AAGH,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,
|
|
1
|
+
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/adapters/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;GAmBG;AAGH,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,yBAAyB,CAAA;AAsB5D;;;;;;;;;GASG;AACH,eAAO,MAAM,gBAAgB,EAAE,SAAS,aAAa,EAoBpD,CAAA;AAQD,OAAO,EAAE,cAAc,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAA;AAC7D,OAAO,EAAE,kBAAkB,EAAE,uBAAuB,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAA;AAEjG,OAAO,EACN,0BAA0B,EAC1B,+BAA+B,EAC/B,qBAAqB,GACrB,MAAM,8BAA8B,CAAA;AAErC,OAAO,EAAE,mBAAmB,EAAE,wBAAwB,EAAE,eAAe,EAAE,MAAM,uBAAuB,CAAA;AAEtG,OAAO,EACN,wBAAwB,EACxB,6BAA6B,EAC7B,oBAAoB,GACpB,MAAM,4BAA4B,CAAA;AAEnC,OAAO,EACN,2BAA2B,EAC3B,gCAAgC,EAChC,qBAAqB,GACrB,MAAM,+BAA+B,CAAA;AAEtC,OAAO,EACN,+BAA+B,EAC/B,oCAAoC,EACpC,yBAAyB,GACzB,MAAM,mCAAmC,CAAA;AAE1C,OAAO,EACN,4BAA4B,EAC5B,iCAAiC,EACjC,sBAAsB,GACtB,MAAM,gCAAgC,CAAA;AAEvC,OAAO,EACN,4BAA4B,EAC5B,iCAAiC,EACjC,sBAAsB,GACtB,MAAM,gCAAgC,CAAA;AAEvC,OAAO,EAAE,gBAAgB,EAAE,qBAAqB,EAAE,YAAY,EAAE,MAAM,oBAAoB,CAAA;AAE1F,OAAO,EACN,0BAA0B,EAC1B,+BAA+B,EAC/B,oBAAoB,GACpB,MAAM,8BAA8B,CAAA;AAErC,OAAO,EACN,yBAAyB,EACzB,8BAA8B,EAC9B,mBAAmB,GACnB,MAAM,6BAA6B,CAAA;AAEpC,OAAO,EAAE,wBAAwB,EAAE,6BAA6B,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAA;AACxH,OAAO,EAAE,oBAAoB,EAAE,yBAAyB,EAAE,eAAe,EAAE,MAAM,wBAAwB,CAAA;AACzG,OAAO,EAAE,sBAAsB,EAAE,2BAA2B,EAAE,iBAAiB,EAAE,MAAM,0BAA0B,CAAA;AAEjH,OAAO,EACN,uBAAuB,EACvB,4BAA4B,EAC5B,kCAAkC,GAClC,MAAM,6CAA6C,CAAA;AAEpD,OAAO,EAAE,oBAAoB,EAAE,eAAe,EAAE,MAAM,6BAA6B,CAAA;AACnF,OAAO,EAAE,yBAAyB,EAAE,oBAAoB,EAAE,MAAM,kCAAkC,CAAA"}
|
|
@@ -18,7 +18,7 @@
|
|
|
18
18
|
* JSON-bundle pivot (`./wof-admin-json/` and `./wof-postalcode-json/` directories hold the
|
|
19
19
|
* implementations; the registered ids are unchanged).
|
|
20
20
|
*/
|
|
21
|
-
import { defaultAdapterRegistry } from "
|
|
21
|
+
import { defaultAdapterRegistry } from "@mailwoman/corpus/adapters/utils";
|
|
22
22
|
import { banAdapter } from "./ban/adapter.js";
|
|
23
23
|
import { fccBdcAdapter } from "./fcc-bdc/adapter.js";
|
|
24
24
|
import { geonamesPostalAdapter } from "./geonames-postal/adapter.js";
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/adapters/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;GAmBG;AAEH,OAAO,EAAE,sBAAsB,EAAE,MAAM,
|
|
1
|
+
{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/adapters/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;GAmBG;AAEH,OAAO,EAAE,sBAAsB,EAAE,MAAM,kCAAkC,CAAA;AAGzE,OAAO,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAA;AAC7C,OAAO,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAA;AACpD,OAAO,EAAE,qBAAqB,EAAE,MAAM,8BAA8B,CAAA;AACpE,OAAO,EAAE,eAAe,EAAE,MAAM,uBAAuB,CAAA;AACvD,OAAO,EAAE,WAAW,EAAE,MAAM,mBAAmB,CAAA;AAC/C,OAAO,EAAE,oBAAoB,EAAE,MAAM,4BAA4B,CAAA;AACjE,OAAO,EAAE,eAAe,EAAE,MAAM,uBAAuB,CAAA;AACvD,OAAO,EAAE,qBAAqB,EAAE,MAAM,+BAA+B,CAAA;AACrE,OAAO,EAAE,yBAAyB,EAAE,MAAM,mCAAmC,CAAA;AAC7E,OAAO,EAAE,sBAAsB,EAAE,MAAM,gCAAgC,CAAA;AACvE,OAAO,EAAE,sBAAsB,EAAE,MAAM,gCAAgC,CAAA;AACvE,OAAO,EAAE,YAAY,EAAE,MAAM,oBAAoB,CAAA;AACjD,OAAO,EAAE,oBAAoB,EAAE,MAAM,8BAA8B,CAAA;AACnE,OAAO,EAAE,mBAAmB,EAAE,MAAM,6BAA6B,CAAA;AACjE,OAAO,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAA;AAC/D,OAAO,EAAE,eAAe,EAAE,MAAM,wBAAwB,CAAA;AACxD,OAAO,EAAE,iBAAiB,EAAE,MAAM,0BAA0B,CAAA;AAC5D,OAAO,EAAE,eAAe,EAAE,MAAM,6BAA6B,CAAA;AAC7D,OAAO,EAAE,oBAAoB,EAAE,MAAM,kCAAkC,CAAA;AAEvE;;;;;;;;;GASG;AACH,MAAM,CAAC,MAAM,gBAAgB,GAA6B;IACzD,eAAe;IACf,oBAAoB;IACpB,eAAe;IACf,qBAAqB;IACrB,UAAU;IACV,YAAY;IACZ,oBAAoB;IACpB,eAAe;IACf,WAAW;IACX,aAAa;IACb,oBAAoB;IACpB,iBAAiB;IACjB,eAAe;IACf,mBAAmB;IACnB,kBAAkB;IAClB,yBAAyB;IACzB,sBAAsB;IACtB,sBAAsB;IACtB,qBAAqB;CACrB,CAAA;AAED,KAAK,MAAM,OAAO,IAAI,gBAAgB,EAAE,CAAC;IACxC,IAAI,CAAC,sBAAsB,CAAC,GAAG,CAAC,OAAO,CAAC,EAAE,CAAC,EAAE,CAAC;QAC7C,sBAAsB,CAAC,QAAQ,CAAC,OAAO,CAAC,CAAA;IACzC,CAAC;AACF,CAAC;AAED,OAAO,EAAE,cAAc,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAA;AAC7D,OAAO,EAAE,kBAAkB,EAAE,uBAAuB,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAA;AAEjG,OAAO,EACN,0BAA0B,EAC1B,+BAA+B,EAC/B,qBAAqB,GACrB,MAAM,8BAA8B,CAAA;AAErC,OAAO,EAAE,mBAAmB,EAAE,wBAAwB,EAAE,eAAe,EAAE,MAAM,uBAAuB,CAAA;AAEtG,OAAO,EACN,wBAAwB,EACxB,6BAA6B,EAC7B,oBAAoB,GACpB,MAAM,4BAA4B,CAAA;AAEnC,OAAO,EACN,2BAA2B,EAC3B,gCAAgC,EAChC,qBAAqB,GACrB,MAAM,+BAA+B,CAAA;AAEtC,OAAO,EACN,+BAA+B,EAC/B,oCAAoC,EACpC,yBAAyB,GACzB,MAAM,mCAAmC,CAAA;AAE1C,OAAO,EACN,4BAA4B,EAC5B,iCAAiC,EACjC,sBAAsB,GACtB,MAAM,gCAAgC,CAAA;AAEvC,OAAO,EACN,4BAA4B,EAC5B,iCAAiC,EACjC,sBAAsB,GACtB,MAAM,gCAAgC,CAAA;AAEvC,OAAO,EAAE,gBAAgB,EAAE,qBAAqB,EAAE,YAAY,EAAE,MAAM,oBAAoB,CAAA;AAE1F,OAAO,EACN,0BAA0B,EAC1B,+BAA+B,EAC/B,oBAAoB,GACpB,MAAM,8BAA8B,CAAA;AAErC,OAAO,EACN,yBAAyB,EACzB,8BAA8B,EAC9B,mBAAmB,GACnB,MAAM,6BAA6B,CAAA;AAEpC,OAAO,EAAE,wBAAwB,EAAE,6BAA6B,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAA;AACxH,OAAO,EAAE,oBAAoB,EAAE,yBAAyB,EAAE,eAAe,EAAE,MAAM,wBAAwB,CAAA;AACzG,OAAO,EAAE,sBAAsB,EAAE,2BAA2B,EAAE,iBAAiB,EAAE,MAAM,0BAA0B,CAAA;AAEjH,OAAO,EACN,uBAAuB,EACvB,4BAA4B,EAC5B,kCAAkC,GAClC,MAAM,6CAA6C,CAAA;AAEpD,OAAO,EAAE,oBAAoB,EAAE,eAAe,EAAE,MAAM,6BAA6B,CAAA;AACnF,OAAO,EAAE,yBAAyB,EAAE,oBAAoB,EAAE,MAAM,kCAAkC,CAAA"}
|
|
@@ -35,7 +35,7 @@
|
|
|
35
35
|
* inflate alignment quarantine because postal addresses don't include it. Phase 6+ may revisit
|
|
36
36
|
* for non-US locales where district names DO appear on the envelope.
|
|
37
37
|
*/
|
|
38
|
-
import type { CorpusAdapter } from "
|
|
38
|
+
import type { CorpusAdapter } from "@mailwoman/corpus/types";
|
|
39
39
|
/**
|
|
40
40
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
41
41
|
* it came from.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/openaddresses/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAoCG;
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/openaddresses/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAoCG;AAIH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,yBAAyB,CAAA;AAK1F;;;GAGG;AACH,eAAO,MAAM,wBAAwB,kBAAkB,CAAA;AACvD;;;GAGG;AACH,eAAO,MAAM,6BAA6B,cAAc,CAAA;AAsDxD,MAAM,WAAW,2BAA2B;IAC3C;;;OAGG;IACH,cAAc,CAAC,EAAE,MAAM,CAAA;IAEvB;;;;;OAKG;IACH,eAAe,CAAC,EAAE,OAAO,CAAA;CACzB;AAED;;;GAGG;AACH,wBAAgB,0BAA0B,CAAC,IAAI,GAAE,2BAAgC,GAAG,aAAa,CAoHhG;AAED;;GAEG;AACH,eAAO,MAAM,oBAAoB,eAA+B,CAAA"}
|
|
@@ -35,10 +35,11 @@
|
|
|
35
35
|
* inflate alignment quarantine because postal addresses don't include it. Phase 6+ may revisit
|
|
36
36
|
* for non-US locales where district names DO appear on the envelope.
|
|
37
37
|
*/
|
|
38
|
+
import { tryParsingJSON } from "@mailwoman/core/objects";
|
|
39
|
+
import { stableSourceID } from "@mailwoman/corpus/adapters/utils";
|
|
40
|
+
import { SHARE_ALIKE_PATTERN } from "@mailwoman/corpus/utils";
|
|
41
|
+
import { formatAddress, reconcileComponents } from "@mailwoman/formatter";
|
|
38
42
|
import { TextSpliterator } from "spliterator";
|
|
39
|
-
import { stableSourceID } from "../../adapter.js";
|
|
40
|
-
import { formatAddress, reconcileComponents } from "../../format.js";
|
|
41
|
-
import { SHARE_ALIKE_PATTERN } from "../../license.js";
|
|
42
43
|
/**
|
|
43
44
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
44
45
|
* it came from.
|
|
@@ -73,13 +74,7 @@ function parseFeatureLine(line) {
|
|
|
73
74
|
const trimmed = line.trim();
|
|
74
75
|
if (!trimmed || trimmed.startsWith("#"))
|
|
75
76
|
return null;
|
|
76
|
-
|
|
77
|
-
try {
|
|
78
|
-
parsed = JSON.parse(trimmed);
|
|
79
|
-
}
|
|
80
|
-
catch {
|
|
81
|
-
return null;
|
|
82
|
-
}
|
|
77
|
+
const parsed = tryParsingJSON(trimmed);
|
|
83
78
|
if (!parsed || typeof parsed !== "object")
|
|
84
79
|
return null;
|
|
85
80
|
const obj = parsed;
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/openaddresses/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAoCG;AAEH,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/openaddresses/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAoCG;AAEH,OAAO,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAA;AACxD,OAAO,EAAE,cAAc,EAAE,MAAM,kCAAkC,CAAA;AAEjE,OAAO,EAAE,mBAAmB,EAAE,MAAM,yBAAyB,CAAA;AAC7D,OAAO,EAAE,aAAa,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AACzE,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C;;;GAGG;AACH,MAAM,CAAC,MAAM,wBAAwB,GAAG,eAAe,CAAA;AACvD;;;GAGG;AACH,MAAM,CAAC,MAAM,6BAA6B,GAAG,WAAW,CAAA;AAmBxD;;GAEG;AACH,SAAS,mBAAmB,CAAC,GAAY;IACxC,IAAI,CAAC,GAAG,IAAI,OAAO,GAAG,KAAK,QAAQ;QAAE,OAAO,EAAE,CAAA;IAC9C,MAAM,GAAG,GAA2B,EAAE,CAAA;IAEtC,KAAK,MAAM,CAAC,CAAC,EAAE,CAAC,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,GAA8B,CAAC,EAAE,CAAC;QACrE,IAAI,OAAO,CAAC,KAAK,QAAQ,EAAE,CAAC;YAC3B,GAAG,CAAC,CAAC,CAAC,WAAW,EAAE,CAAC,GAAG,CAAC,CAAA;QACzB,CAAC;aAAM,IAAI,OAAO,CAAC,KAAK,QAAQ,EAAE,CAAC;YAClC,GAAG,CAAC,CAAC,CAAC,WAAW,EAAE,CAAC,GAAG,MAAM,CAAC,CAAC,CAAC,CAAA;QACjC,CAAC;IACF,CAAC;IAED,OAAO,GAAmB,CAAA;AAC3B,CAAC;AAED;;GAEG;AACH,SAAS,gBAAgB,CAAC,IAAY;IACrC,MAAM,OAAO,GAAG,IAAI,CAAC,IAAI,EAAE,CAAA;IAE3B,IAAI,CAAC,OAAO,IAAI,OAAO,CAAC,UAAU,CAAC,GAAG,CAAC;QAAE,OAAO,IAAI,CAAA;IACpD,MAAM,MAAM,GAAG,cAAc,CAAC,OAAO,CAAC,CAAA;IAEtC,IAAI,CAAC,MAAM,IAAI,OAAO,MAAM,KAAK,QAAQ;QAAE,OAAO,IAAI,CAAA;IACtD,MAAM,GAAG,GAAG,MAAiD,CAAA;IAE7D,IAAI,GAAG,CAAC,IAAI,KAAK,SAAS;QAAE,OAAO,IAAI,CAAA;IAEvC,OAAO,mBAAmB,CAAC,GAAG,CAAC,UAAU,CAAC,CAAA;AAC3C,CAAC;AAkBD;;;GAGG;AACH,MAAM,UAAU,0BAA0B,CAAC,OAAoC,EAAE;IAChF,MAAM,cAAc,GAAG,IAAI,CAAC,cAAc,IAAI,6BAA6B,CAAA;IAC3E,MAAM,eAAe,GAAG,IAAI,CAAC,eAAe,IAAI,IAAI,CAAA;IAEpD,OAAO;QACN,EAAE,EAAE,wBAAwB;QAC5B,cAAc;QACd,WAAW,EAAE,6EAA6E;QAE1F,KAAK,CAAC,CAAC,IAAI,CAAC,WAA2B;YACtC,IAAI,CAAC,WAAW,CAAC,OAAO,EAAE,CAAC;gBAC1B,MAAM,IAAI,KAAK,CACd,0HAA0H,CAC1H,CAAA;YACF,CAAC;YAED,MAAM,OAAO,GAAG,WAAW,CAAC,OAAO,CAAA;YAEnC,qFAAqF;YACrF,yFAAyF;YACzF,kDAAkD;YAClD,MAAM,KAAK,GAAG,eAAe,CAAC,SAAS,CAAC,WAAW,CAAC,SAAS,CAAC,CAAA;YAE9D,IAAI,OAAO,GAAG,CAAC,CAAA;YACf,IAAI,iBAAiB,GAAG,CAAC,CAAA;YAEzB,IAAI,CAAC;gBACJ,IAAI,KAAK,EAAE,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;oBAChC,IAAI,WAAW,CAAC,MAAM,EAAE,OAAO;wBAAE,MAAK;oBAEtC,IAAI,WAAW,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,WAAW,CAAC,KAAK;wBAAE,MAAK;oBAE1E,MAAM,KAAK,GAAG,gBAAgB,CAAC,IAAI,CAAC,CAAA;oBAEpC,IAAI,CAAC,KAAK;wBAAE,SAAQ;oBAEpB,MAAM,WAAW,GAAG,KAAK,CAAC,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;oBAC9C,MAAM,MAAM,GAAG,KAAK,CAAC,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;oBACzC,MAAM,IAAI,GAAG,KAAK,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;oBACrC,MAAM,IAAI,GAAG,KAAK,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;oBACrC,MAAM,MAAM,GAAG,KAAK,CAAC,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;oBACzC,MAAM,QAAQ,GAAG,KAAK,CAAC,QAAQ,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;oBAE7C,iFAAiF;oBACjF,wDAAwD;oBACxD,IAAI,CAAC,MAAM;wBAAE,SAAQ;oBAErB,IAAI,CAAC,IAAI,IAAI,CAAC,QAAQ;wBAAE,SAAQ;oBAEhC,MAAM,OAAO,GAAG,CAAC,KAAK,CAAC,OAAO,EAAE,IAAI,EAAE,IAAI,cAAc,CAAC,CAAC,IAAI,EAAE,CAAA;oBAEhE,IAAI,CAAC,eAAe,IAAI,mBAAmB,CAAC,IAAI,CAAC,OAAO,CAAC,EAAE,CAAC;wBAC3D,iBAAiB,EAAE,CAAA;wBAEnB,SAAQ;oBACT,CAAC;oBAED,MAAM,UAAU,GAA+B,EAAE,CAAA;oBAEjD,IAAI,WAAW,EAAE,CAAC;wBACjB,UAAU,CAAC,YAAY,GAAG,WAAW,CAAA;oBACtC,CAAC;oBAED,IAAI,MAAM,EAAE,CAAC;wBACZ,UAAU,CAAC,MAAM,GAAG,MAAM,CAAA;oBAC3B,CAAC;oBAED,IAAI,IAAI,EAAE,CAAC;wBACV,UAAU,CAAC,IAAI,GAAG,IAAI,CAAA;oBACvB,CAAC;oBAED,IAAI,IAAI,EAAE,CAAC;wBACV,UAAU,CAAC,QAAQ,GAAG,IAAI,CAAA;oBAC3B,CAAC;oBAED,IAAI,MAAM,EAAE,CAAC;wBACZ,UAAU,CAAC,MAAM,GAAG,MAAM,CAAA;oBAC3B,CAAC;oBAED,IAAI,QAAQ,EAAE,CAAC;wBACd,UAAU,CAAC,QAAQ,GAAG,QAAQ,CAAA;oBAC/B,CAAC;oBAED,MAAM,GAAG,GAAG,aAAa,CAAC,UAAU,EAAE,OAAO,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;oBAEnE,IAAI,CAAC,GAAG;wBAAE,SAAQ;oBAElB,MAAM,OAAO,GAAG,mBAAmB,CAAC,UAAU,EAAE,GAAG,CAAC,CAAA;oBAEpD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM;wBAAE,SAAQ;oBAE1C,MAAM,YAAY,GAAG,KAAK,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,KAAK,CAAC,EAAE,EAAE,IAAI,EAAE,CAAA;oBAE3D,MAAM,QAAQ,GAAG,YAAY;wBAC5B,CAAC,CAAC,GAAG,wBAAwB,IAAI,YAAY,EAAE;wBAC/C,CAAC,CAAC,cAAc,CAAC,wBAAwB,EAAE,OAAO,CAAC,CAAA;oBAEpD,MAAM;wBACL,GAAG;wBACH,UAAU,EAAE,OAAO;wBACnB,OAAO;wBACP,MAAM,EAAE,wBAAwB;wBAChC,SAAS,EAAE,QAAQ;wBACnB,cAAc,EAAE,EAAE;wBAClB,OAAO;qBACP,CAAA;oBAED,OAAO,EAAE,CAAA;gBACV,CAAC;YACF,CAAC;oBAAS,CAAC;gBACV,IAAI,iBAAiB,GAAG,CAAC,EAAE,CAAC;oBAC3B,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,oBAAoB,iBAAiB,8BAA8B,OAAO,SAAS,CAAC,CAAA;gBAC1G,CAAC;YACF,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,oBAAoB,GAAG,0BAA0B,EAAE,CAAA"}
|
|
@@ -29,7 +29,7 @@
|
|
|
29
29
|
* (skipped when "S-N"/"S/N" = sin número) | | `unit` | `unit` (if non-empty) | | `postcode`|
|
|
30
30
|
* `postcode` | | `locality`| `locality` (Overture address_levels municipality, or postal_city) |
|
|
31
31
|
*/
|
|
32
|
-
import type { CorpusAdapter } from "
|
|
32
|
+
import type { CorpusAdapter } from "@mailwoman/corpus/types";
|
|
33
33
|
/**
|
|
34
34
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
35
35
|
* it came from.
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/overture/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8BG;
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/overture/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8BG;AAIH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,yBAAyB,CAAA;AAI1F;;;GAGG;AACH,eAAO,MAAM,mBAAmB,aAAa,CAAA;AAC7C;;;GAGG;AACH,eAAO,MAAM,wBAAwB,wBAAwB,CAAA;AAuB7D,wBAAgB,qBAAqB,IAAI,aAAa,CAqFrD;AAED;;GAEG;AACH,eAAO,MAAM,eAAe,eAA0B,CAAA"}
|
|
@@ -29,9 +29,10 @@
|
|
|
29
29
|
* (skipped when "S-N"/"S/N" = sin número) | | `unit` | `unit` (if non-empty) | | `postcode`|
|
|
30
30
|
* `postcode` | | `locality`| `locality` (Overture address_levels municipality, or postal_city) |
|
|
31
31
|
*/
|
|
32
|
+
import { tryParsingJSON } from "@mailwoman/core/objects";
|
|
33
|
+
import { stableSourceID } from "@mailwoman/corpus/adapters/utils";
|
|
34
|
+
import { formatAddress, reconcileComponents } from "@mailwoman/formatter";
|
|
32
35
|
import { TextSpliterator } from "spliterator";
|
|
33
|
-
import { stableSourceID } from "../../adapter.js";
|
|
34
|
-
import { formatAddress, reconcileComponents } from "../../format.js";
|
|
35
36
|
/**
|
|
36
37
|
* Registry id for this adapter. Stamped into every row it emits, so a corpus record can be traced back to the dataset
|
|
37
38
|
* it came from.
|
|
@@ -46,13 +47,8 @@ function parseLine(line) {
|
|
|
46
47
|
const t = line.trim();
|
|
47
48
|
if (!t || t.startsWith("#"))
|
|
48
49
|
return null;
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
return o && typeof o === "object" ? o : null;
|
|
52
|
-
}
|
|
53
|
-
catch {
|
|
54
|
-
return null;
|
|
55
|
-
}
|
|
50
|
+
const o = tryParsingJSON(t);
|
|
51
|
+
return o && typeof o === "object" ? o : null;
|
|
56
52
|
}
|
|
57
53
|
export function createOvertureAdapter() {
|
|
58
54
|
return {
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/overture/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8BG;AAEH,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"adapter.js","sourceRoot":"","sources":["../../../../src/adapters/overture/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8BG;AAEH,OAAO,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAA;AACxD,OAAO,EAAE,cAAc,EAAE,MAAM,kCAAkC,CAAA;AAEjE,OAAO,EAAE,aAAa,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAA;AACzE,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C;;;GAGG;AACH,MAAM,CAAC,MAAM,mBAAmB,GAAG,UAAU,CAAA;AAC7C;;;GAGG;AACH,MAAM,CAAC,MAAM,wBAAwB,GAAG,qBAAqB,CAAA;AAa7D,SAAS,SAAS,CAAC,IAAY;IAC9B,MAAM,CAAC,GAAG,IAAI,CAAC,IAAI,EAAE,CAAA;IAErB,IAAI,CAAC,CAAC,IAAI,CAAC,CAAC,UAAU,CAAC,GAAG,CAAC;QAAE,OAAO,IAAI,CAAA;IAExC,MAAM,CAAC,GAAG,cAAc,CAAC,CAAC,CAAC,CAAA;IAE3B,OAAO,CAAC,IAAI,OAAO,CAAC,KAAK,QAAQ,CAAC,CAAC,CAAE,CAAuB,CAAC,CAAC,CAAC,IAAI,CAAA;AACpE,CAAC;AAED,MAAM,UAAU,qBAAqB;IACpC,OAAO;QACN,EAAE,EAAE,mBAAmB;QACvB,cAAc,EAAE,wBAAwB;QACxC,WAAW,EAAE,yFAAyF;QAEtG,KAAK,CAAC,CAAC,IAAI,CAAC,IAAoB;YAC/B,IAAI,CAAC,IAAI,CAAC,OAAO,EAAE,CAAC;gBACnB,MAAM,IAAI,KAAK,CACd,2GAA2G,CAC3G,CAAA;YACF,CAAC;YAED,MAAM,OAAO,GAAG,IAAI,CAAC,OAAO,CAAA;YAE5B,uFAAuF;YACvF,wFAAwF;YACxF,iCAAiC;YACjC,MAAM,KAAK,GAAG,eAAe,CAAC,SAAS,CAAC,IAAI,CAAC,SAAS,CAAC,CAAA;YAEvD,IAAI,OAAO,GAAG,CAAC,CAAA;YAEf,IAAI,KAAK,EAAE,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;gBAChC,IAAI,IAAI,CAAC,MAAM,EAAE,OAAO;oBAAE,MAAK;gBAE/B,IAAI,IAAI,CAAC,KAAK,KAAK,SAAS,IAAI,OAAO,IAAI,IAAI,CAAC,KAAK;oBAAE,MAAK;gBAE5D,MAAM,CAAC,GAAG,SAAS,CAAC,IAAI,CAAC,CAAA;gBAEzB,IAAI,CAAC,CAAC;oBAAE,SAAQ;gBAEhB,MAAM,MAAM,GAAG,CAAC,CAAC,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;gBACrC,MAAM,MAAM,GAAG,CAAC,CAAC,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;gBACrC,MAAM,IAAI,GAAG,CAAC,CAAC,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;gBACjC,MAAM,QAAQ,GAAG,CAAC,CAAC,QAAQ,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;gBACzC,MAAM,QAAQ,GAAG,CAAC,CAAC,QAAQ,EAAE,IAAI,EAAE,IAAI,EAAE,CAAA;gBAEzC,yFAAyF;gBACzF,IAAI,CAAC,MAAM;oBAAE,SAAQ;gBAErB,IAAI,CAAC,QAAQ,IAAI,CAAC,QAAQ;oBAAE,SAAQ;gBAEpC,MAAM,UAAU,GAA+B,EAAE,CAAA;gBAEjD,8EAA8E;gBAC9E,IAAI,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,EAAE,CAAC;oBACxB,UAAU,CAAC,YAAY,GAAG,MAAM,CAAA;gBACjC,CAAC;gBAED,UAAU,CAAC,MAAM,GAAG,MAAM,CAAA;gBAE1B,IAAI,IAAI,EAAE,CAAC;oBACV,UAAU,CAAC,IAAI,GAAG,IAAI,CAAA;gBACvB,CAAC;gBAED,IAAI,QAAQ,EAAE,CAAC;oBACd,UAAU,CAAC,QAAQ,GAAG,QAAQ,CAAA;gBAC/B,CAAC;gBAED,IAAI,QAAQ,EAAE,CAAC;oBACd,UAAU,CAAC,QAAQ,GAAG,QAAQ,CAAA;gBAC/B,CAAC;gBAED,MAAM,GAAG,GAAG,aAAa,CAAC,UAAU,EAAE,OAAO,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAA;gBAEnE,IAAI,CAAC,GAAG;oBAAE,SAAQ;gBAElB,MAAM,OAAO,GAAG,mBAAmB,CAAC,UAAU,EAAE,GAAG,CAAC,CAAA;gBAEpD,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM;oBAAE,SAAQ;gBAE1C,MAAM;oBACL,GAAG;oBACH,UAAU,EAAE,OAAO;oBACnB,OAAO;oBACP,MAAM,EAAE,mBAAmB;oBAC3B,SAAS,EAAE,cAAc,CAAC,mBAAmB,EAAE,OAAO,CAAC;oBACvD,cAAc,EAAE,EAAE;oBAClB,OAAO,EAAE,wBAAwB;iBACjC,CAAA;gBAED,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;KACD,CAAA;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,eAAe,GAAG,qBAAqB,EAAE,CAAA"}
|
|
@@ -28,7 +28,7 @@
|
|
|
28
28
|
*
|
|
29
29
|
* License: stamped `"Public Domain"` per Hawaii state government open-data terms.
|
|
30
30
|
*/
|
|
31
|
-
import type { CorpusAdapter } from "
|
|
31
|
+
import type { CorpusAdapter } from "@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/state-hi-schools/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA6BG;
|
|
1
|
+
{"version":3,"file":"adapter.d.ts","sourceRoot":"","sources":["../../../../src/adapters/state-hi-schools/adapter.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA6BG;AAIH,OAAO,KAAK,EAAgC,aAAa,EAAE,MAAM,yBAAyB,CAAA;AAI1F;;;GAGG;AACH,eAAO,MAAM,2BAA2B,qBAAqB,CAAA;AAC7D;;;GAGG;AACH,eAAO,MAAM,gCAAgC,kBAAkB,CAAA;AAyB/D,wBAAgB,2BAA2B,IAAI,aAAa,CAqF3D;AAED;;GAEG;AACH,eAAO,MAAM,qBAAqB,eAAgC,CAAA"}
|