@mailwoman/corpus 8.0.0 → 8.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/out/src/adapter.d.ts +15 -5
- package/out/src/adapter.d.ts.map +1 -1
- package/out/src/adapter.js +11 -9
- package/out/src/adapter.js.map +1 -1
- package/out/src/adapters/ban/adapter.d.ts +7 -0
- package/out/src/adapters/ban/adapter.d.ts.map +1 -1
- package/out/src/adapters/ban/adapter.js +9 -2
- 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 +5 -1
- package/out/src/adapters/ban/street-decompose.js.map +1 -1
- package/out/src/adapters/fcc-bdc/adapter.d.ts +14 -1
- package/out/src/adapters/fcc-bdc/adapter.d.ts.map +1 -1
- package/out/src/adapters/fcc-bdc/adapter.js +15 -2
- package/out/src/adapters/fcc-bdc/adapter.js.map +1 -1
- package/out/src/adapters/geonames/adapter.d.ts +11 -0
- package/out/src/adapters/geonames/adapter.d.ts.map +1 -1
- package/out/src/adapters/geonames/adapter.js +24 -5
- package/out/src/adapters/geonames/adapter.js.map +1 -1
- package/out/src/adapters/geonames-postal/adapter.d.ts +11 -0
- package/out/src/adapters/geonames-postal/adapter.d.ts.map +1 -1
- package/out/src/adapters/geonames-postal/adapter.js +14 -1
- package/out/src/adapters/geonames-postal/adapter.js.map +1 -1
- package/out/src/adapters/gnaf/adapter.d.ts +10 -1
- package/out/src/adapters/gnaf/adapter.d.ts.map +1 -1
- package/out/src/adapters/gnaf/adapter.js +11 -2
- package/out/src/adapters/gnaf/adapter.js.map +1 -1
- package/out/src/adapters/gnaf/assemble.d.ts +18 -6
- package/out/src/adapters/gnaf/assemble.d.ts.map +1 -1
- package/out/src/adapters/gnaf/assemble.js +16 -6
- package/out/src/adapters/gnaf/assemble.js.map +1 -1
- package/out/src/adapters/index.d.ts.map +1 -1
- package/out/src/adapters/index.js.map +1 -1
- package/out/src/adapters/openaddresses/adapter.d.ts +11 -0
- package/out/src/adapters/openaddresses/adapter.d.ts.map +1 -1
- package/out/src/adapters/openaddresses/adapter.js +18 -3
- package/out/src/adapters/openaddresses/adapter.js.map +1 -1
- package/out/src/adapters/overture/adapter.d.ts +11 -0
- package/out/src/adapters/overture/adapter.d.ts.map +1 -1
- package/out/src/adapters/overture/adapter.js +12 -1
- package/out/src/adapters/overture/adapter.js.map +1 -1
- package/out/src/adapters/state-hi-schools/adapter.d.ts +11 -0
- package/out/src/adapters/state-hi-schools/adapter.d.ts.map +1 -1
- package/out/src/adapters/state-hi-schools/adapter.js +11 -0
- package/out/src/adapters/state-hi-schools/adapter.js.map +1 -1
- package/out/src/adapters/state-ia-contractors/adapter.d.ts +11 -0
- package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +1 -1
- package/out/src/adapters/state-ia-contractors/adapter.js +11 -0
- package/out/src/adapters/state-ia-contractors/adapter.js.map +1 -1
- package/out/src/adapters/state-ny-notaries/adapter.d.ts +11 -0
- package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +1 -1
- package/out/src/adapters/state-ny-notaries/adapter.js +11 -0
- package/out/src/adapters/state-ny-notaries/adapter.js.map +1 -1
- package/out/src/adapters/state-tx-notaries/adapter.d.ts +11 -0
- package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +1 -1
- package/out/src/adapters/state-tx-notaries/adapter.js +15 -2
- package/out/src/adapters/state-tx-notaries/adapter.js.map +1 -1
- package/out/src/adapters/synth-po-box/adapter.d.ts +11 -0
- package/out/src/adapters/synth-po-box/adapter.d.ts.map +1 -1
- package/out/src/adapters/synth-po-box/adapter.js +13 -2
- package/out/src/adapters/synth-po-box/adapter.js.map +1 -1
- package/out/src/adapters/tiger/adapter.d.ts +14 -1
- package/out/src/adapters/tiger/adapter.d.ts.map +1 -1
- package/out/src/adapters/tiger/adapter.js +19 -4
- 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.map +1 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +11 -0
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +12 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -1
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts +11 -0
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +1 -1
- package/out/src/adapters/usgov-imls-pls/adapter.js +11 -0
- package/out/src/adapters/usgov-imls-pls/adapter.js.map +1 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +11 -0
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.js +17 -2
- package/out/src/adapters/usgov-irs-bmf/adapter.js.map +1 -1
- package/out/src/adapters/usgov-nad/adapter.d.ts +11 -0
- package/out/src/adapters/usgov-nad/adapter.d.ts.map +1 -1
- package/out/src/adapters/usgov-nad/adapter.js +12 -1
- package/out/src/adapters/usgov-nad/adapter.js.map +1 -1
- package/out/src/adapters/usgov-nppes/adapter.d.ts +11 -0
- package/out/src/adapters/usgov-nppes/adapter.d.ts.map +1 -1
- package/out/src/adapters/usgov-nppes/adapter.js +11 -0
- package/out/src/adapters/usgov-nppes/adapter.js.map +1 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts +11 -0
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +15 -2
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -1
- package/out/src/adapters/wof-admin-jp/adapter.d.ts +7 -0
- package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +1 -1
- package/out/src/adapters/wof-admin-jp/adapter.js +18 -3
- package/out/src/adapters/wof-admin-jp/adapter.js.map +1 -1
- package/out/src/adapters/wof-admin-json/adapter.d.ts +13 -3
- package/out/src/adapters/wof-admin-json/adapter.d.ts.map +1 -1
- package/out/src/adapters/wof-admin-json/adapter.js +15 -5
- package/out/src/adapters/wof-admin-json/adapter.js.map +1 -1
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts +7 -0
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +1 -1
- package/out/src/adapters/wof-postalcode-json/adapter.js +9 -2
- package/out/src/adapters/wof-postalcode-json/adapter.js.map +1 -1
- package/out/src/align.d.ts +12 -4
- package/out/src/align.d.ts.map +1 -1
- package/out/src/align.js +9 -5
- package/out/src/align.js.map +1 -1
- package/out/src/build.d.ts +24 -8
- package/out/src/build.d.ts.map +1 -1
- package/out/src/build.js +3 -3
- package/out/src/build.js.map +1 -1
- package/out/src/codex/us-fips-state.d.ts +6 -2
- package/out/src/codex/us-fips-state.d.ts.map +1 -1
- package/out/src/codex/us-fips-state.js +3 -1
- package/out/src/codex/us-fips-state.js.map +1 -1
- package/out/src/golden.d.ts +21 -7
- package/out/src/golden.d.ts.map +1 -1
- package/out/src/golden.js +18 -10
- package/out/src/golden.js.map +1 -1
- package/out/src/license.d.ts +3 -1
- package/out/src/license.d.ts.map +1 -1
- package/out/src/license.js +4 -2
- package/out/src/license.js.map +1 -1
- package/out/src/parquet-wrapper/reader.d.ts +4 -2
- package/out/src/parquet-wrapper/reader.d.ts.map +1 -1
- package/out/src/parquet-wrapper/reader.js +5 -4
- package/out/src/parquet-wrapper/reader.js.map +1 -1
- package/out/src/parquet-wrapper/schema.d.ts +14 -10
- package/out/src/parquet-wrapper/schema.d.ts.map +1 -1
- package/out/src/parquet-wrapper/schema.js +6 -2
- package/out/src/parquet-wrapper/schema.js.map +1 -1
- package/out/src/parquet-wrapper/writer.d.ts +12 -4
- package/out/src/parquet-wrapper/writer.d.ts.map +1 -1
- package/out/src/parquet-wrapper/writer.js +12 -4
- package/out/src/parquet-wrapper/writer.js.map +1 -1
- package/out/src/parquet.d.ts +21 -7
- package/out/src/parquet.d.ts.map +1 -1
- package/out/src/parquet.js +15 -4
- package/out/src/parquet.js.map +1 -1
- package/out/src/runner.d.ts +39 -13
- package/out/src/runner.d.ts.map +1 -1
- package/out/src/runner.js +7 -3
- package/out/src/runner.js.map +1 -1
- package/out/src/shard-recipes/anchor-absorption.d.ts +4 -0
- package/out/src/shard-recipes/anchor-absorption.d.ts.map +1 -1
- package/out/src/shard-recipes/anchor-absorption.js +14 -5
- package/out/src/shard-recipes/anchor-absorption.js.map +1 -1
- package/out/src/shard-recipes/boundary-stress.d.ts +4 -0
- package/out/src/shard-recipes/boundary-stress.d.ts.map +1 -1
- package/out/src/shard-recipes/boundary-stress.js +13 -7
- package/out/src/shard-recipes/boundary-stress.js.map +1 -1
- package/out/src/shard-recipes/country-balanced.d.ts +4 -0
- package/out/src/shard-recipes/country-balanced.d.ts.map +1 -1
- package/out/src/shard-recipes/country-balanced.js +39 -11
- package/out/src/shard-recipes/country-balanced.js.map +1 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts +4 -0
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +1 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.js +4 -0
- package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +1 -1
- package/out/src/shard-recipes/fr-admin-split.d.ts +4 -0
- package/out/src/shard-recipes/fr-admin-split.d.ts.map +1 -1
- package/out/src/shard-recipes/fr-admin-split.js +14 -3
- package/out/src/shard-recipes/fr-admin-split.js.map +1 -1
- package/out/src/shard-recipes/fr-bare-street.d.ts +4 -0
- package/out/src/shard-recipes/fr-bare-street.d.ts.map +1 -1
- package/out/src/shard-recipes/fr-bare-street.js +4 -0
- package/out/src/shard-recipes/fr-bare-street.js.map +1 -1
- package/out/src/shard-recipes/fr-fragment.d.ts +4 -0
- package/out/src/shard-recipes/fr-fragment.d.ts.map +1 -1
- package/out/src/shard-recipes/fr-fragment.js +25 -8
- package/out/src/shard-recipes/fr-fragment.js.map +1 -1
- package/out/src/shard-recipes/fr-lieudit.d.ts +4 -0
- package/out/src/shard-recipes/fr-lieudit.d.ts.map +1 -1
- package/out/src/shard-recipes/fr-lieudit.js +21 -8
- package/out/src/shard-recipes/fr-lieudit.js.map +1 -1
- package/out/src/shard-recipes/fr-order.d.ts +4 -0
- package/out/src/shard-recipes/fr-order.d.ts.map +1 -1
- package/out/src/shard-recipes/fr-order.js +27 -8
- package/out/src/shard-recipes/fr-order.js.map +1 -1
- package/out/src/shard-recipes/german.d.ts +4 -0
- package/out/src/shard-recipes/german.d.ts.map +1 -1
- package/out/src/shard-recipes/german.js +16 -6
- package/out/src/shard-recipes/german.js.map +1 -1
- package/out/src/shard-recipes/house-venue.d.ts +4 -0
- package/out/src/shard-recipes/house-venue.d.ts.map +1 -1
- package/out/src/shard-recipes/house-venue.js +4 -0
- package/out/src/shard-recipes/house-venue.js.map +1 -1
- package/out/src/shard-recipes/index.d.ts +9 -3
- package/out/src/shard-recipes/index.d.ts.map +1 -1
- package/out/src/shard-recipes/index.js +12 -4
- package/out/src/shard-recipes/index.js.map +1 -1
- package/out/src/shard-recipes/intersection.d.ts +4 -0
- package/out/src/shard-recipes/intersection.d.ts.map +1 -1
- package/out/src/shard-recipes/intersection.js +27 -13
- package/out/src/shard-recipes/intersection.js.map +1 -1
- package/out/src/shard-recipes/locale.d.ts +4 -0
- package/out/src/shard-recipes/locale.d.ts.map +1 -1
- package/out/src/shard-recipes/locale.js +9 -4
- package/out/src/shard-recipes/locale.js.map +1 -1
- package/out/src/shard-recipes/nl-postcode.d.ts +4 -0
- package/out/src/shard-recipes/nl-postcode.d.ts.map +1 -1
- package/out/src/shard-recipes/nl-postcode.js +8 -2
- package/out/src/shard-recipes/nl-postcode.js.map +1 -1
- package/out/src/shard-recipes/no-fragment.d.ts +4 -0
- package/out/src/shard-recipes/no-fragment.d.ts.map +1 -1
- package/out/src/shard-recipes/no-fragment.js +8 -2
- package/out/src/shard-recipes/no-fragment.js.map +1 -1
- package/out/src/shard-recipes/no-street-led.d.ts +4 -0
- package/out/src/shard-recipes/no-street-led.d.ts.map +1 -1
- package/out/src/shard-recipes/no-street-led.js +5 -1
- package/out/src/shard-recipes/no-street-led.js.map +1 -1
- package/out/src/shard-recipes/no-street.d.ts +4 -0
- package/out/src/shard-recipes/no-street.d.ts.map +1 -1
- package/out/src/shard-recipes/no-street.js +4 -0
- package/out/src/shard-recipes/no-street.js.map +1 -1
- package/out/src/shard-recipes/po-box-cedex.d.ts +4 -0
- package/out/src/shard-recipes/po-box-cedex.d.ts.map +1 -1
- package/out/src/shard-recipes/po-box-cedex.js +99 -43
- package/out/src/shard-recipes/po-box-cedex.js.map +1 -1
- package/out/src/shard-recipes/po-box.d.ts +4 -0
- package/out/src/shard-recipes/po-box.d.ts.map +1 -1
- package/out/src/shard-recipes/po-box.js +4 -0
- package/out/src/shard-recipes/po-box.js.map +1 -1
- package/out/src/shard-recipes/scaffold.d.ts +48 -16
- package/out/src/shard-recipes/scaffold.d.ts.map +1 -1
- package/out/src/shard-recipes/scaffold.js +10 -6
- package/out/src/shard-recipes/scaffold.js.map +1 -1
- package/out/src/shard-recipes/si-bare-village.d.ts +4 -0
- package/out/src/shard-recipes/si-bare-village.d.ts.map +1 -1
- package/out/src/shard-recipes/si-bare-village.js +4 -0
- package/out/src/shard-recipes/si-bare-village.js.map +1 -1
- package/out/src/shard-recipes/street-affix.d.ts +4 -0
- package/out/src/shard-recipes/street-affix.d.ts.map +1 -1
- package/out/src/shard-recipes/street-affix.js +29 -10
- package/out/src/shard-recipes/street-affix.js.map +1 -1
- package/out/src/shard-recipes/street-bare.d.ts +4 -0
- package/out/src/shard-recipes/street-bare.d.ts.map +1 -1
- package/out/src/shard-recipes/street-bare.js +4 -0
- package/out/src/shard-recipes/street-bare.js.map +1 -1
- package/out/src/shard-recipes/street.d.ts +4 -0
- package/out/src/shard-recipes/street.d.ts.map +1 -1
- package/out/src/shard-recipes/street.js +4 -0
- package/out/src/shard-recipes/street.js.map +1 -1
- package/out/src/shard-recipes/unit.d.ts +4 -0
- package/out/src/shard-recipes/unit.d.ts.map +1 -1
- package/out/src/shard-recipes/unit.js +45 -14
- package/out/src/shard-recipes/unit.js.map +1 -1
- package/out/src/split.d.ts +18 -6
- package/out/src/split.d.ts.map +1 -1
- package/out/src/split.js +4 -2
- package/out/src/split.js.map +1 -1
- package/out/src/synthesize-anchor-absorption.d.ts +7 -1
- package/out/src/synthesize-anchor-absorption.d.ts.map +1 -1
- package/out/src/synthesize-anchor-absorption.js +28 -14
- package/out/src/synthesize-anchor-absorption.js.map +1 -1
- package/out/src/synthesize-boundary-stress.d.ts +3 -1
- package/out/src/synthesize-boundary-stress.d.ts.map +1 -1
- package/out/src/synthesize-boundary-stress.js +35 -28
- package/out/src/synthesize-boundary-stress.js.map +1 -1
- package/out/src/synthesize-german.d.ts +15 -5
- package/out/src/synthesize-german.d.ts.map +1 -1
- package/out/src/synthesize-german.js +9 -3
- package/out/src/synthesize-german.js.map +1 -1
- package/out/src/synthesize-house-venue.d.ts.map +1 -1
- package/out/src/synthesize-house-venue.js +15 -15
- package/out/src/synthesize-house-venue.js.map +1 -1
- package/out/src/synthesize-intersection.d.ts +9 -3
- package/out/src/synthesize-intersection.d.ts.map +1 -1
- package/out/src/synthesize-intersection.js +25 -6
- package/out/src/synthesize-intersection.js.map +1 -1
- package/out/src/synthesize-no-street.d.ts +3 -1
- package/out/src/synthesize-no-street.d.ts.map +1 -1
- package/out/src/synthesize-no-street.js +5 -6
- package/out/src/synthesize-no-street.js.map +1 -1
- package/out/src/synthesize-po-box.d.ts +15 -5
- package/out/src/synthesize-po-box.d.ts.map +1 -1
- package/out/src/synthesize-po-box.js +21 -7
- package/out/src/synthesize-po-box.js.map +1 -1
- package/out/src/synthesize-street.d.ts +3 -1
- package/out/src/synthesize-street.d.ts.map +1 -1
- package/out/src/synthesize-street.js +6 -1
- package/out/src/synthesize-street.js.map +1 -1
- package/out/src/synthesize.d.ts +39 -13
- package/out/src/synthesize.d.ts.map +1 -1
- package/out/src/synthesize.js +66 -36
- package/out/src/synthesize.js.map +1 -1
- package/out/src/tokenize.d.ts +15 -5
- package/out/src/tokenize.d.ts.map +1 -1
- package/out/src/tokenize.js.map +1 -1
- package/out/src/tools/align-shard.d.ts.map +1 -1
- package/out/src/tools/align-shard.js +3 -1
- 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 +20 -8
- package/out/src/tools/audit.js.map +1 -1
- package/out/src/tools/corpus-stats.d.ts.map +1 -1
- package/out/src/tools/corpus-stats.js.map +1 -1
- package/out/src/tools/fetch/ban.d.ts.map +1 -1
- package/out/src/tools/fetch/ban.js +17 -10
- package/out/src/tools/fetch/ban.js.map +1 -1
- package/out/src/tools/fetch/download.d.ts +30 -10
- package/out/src/tools/fetch/download.d.ts.map +1 -1
- package/out/src/tools/fetch/download.js +26 -6
- package/out/src/tools/fetch/download.js.map +1 -1
- package/out/src/tools/fetch/hrsa.d.ts.map +1 -1
- package/out/src/tools/fetch/hrsa.js.map +1 -1
- package/out/src/tools/fetch/imls-pls.d.ts.map +1 -1
- package/out/src/tools/fetch/imls-pls.js +18 -18
- package/out/src/tools/fetch/imls-pls.js.map +1 -1
- package/out/src/tools/fetch/index.d.ts +3 -1
- package/out/src/tools/fetch/index.d.ts.map +1 -1
- package/out/src/tools/fetch/index.js +3 -1
- package/out/src/tools/fetch/index.js.map +1 -1
- package/out/src/tools/fetch/nad.d.ts +21 -7
- package/out/src/tools/fetch/nad.d.ts.map +1 -1
- package/out/src/tools/fetch/nad.js +5 -5
- package/out/src/tools/fetch/nad.js.map +1 -1
- package/out/src/tools/fetch/nppes.d.ts.map +1 -1
- package/out/src/tools/fetch/nppes.js +9 -15
- package/out/src/tools/fetch/nppes.js.map +1 -1
- package/out/src/tools/fetch/openaddresses.d.ts +3 -1
- package/out/src/tools/fetch/openaddresses.d.ts.map +1 -1
- package/out/src/tools/fetch/openaddresses.js +32 -23
- package/out/src/tools/fetch/openaddresses.js.map +1 -1
- package/out/src/tools/fetch/ppd.d.ts +3 -1
- package/out/src/tools/fetch/ppd.d.ts.map +1 -1
- package/out/src/tools/fetch/ppd.js +14 -3
- package/out/src/tools/fetch/ppd.js.map +1 -1
- package/out/src/tools/fetch/state-hi-schools.d.ts.map +1 -1
- package/out/src/tools/fetch/state-hi-schools.js +13 -6
- package/out/src/tools/fetch/state-hi-schools.js.map +1 -1
- package/out/src/tools/fetch/state-sources.d.ts.map +1 -1
- package/out/src/tools/fetch/state-sources.js +8 -3
- package/out/src/tools/fetch/state-sources.js.map +1 -1
- package/out/src/tools/fetch/tiger-full.d.ts +9 -3
- package/out/src/tools/fetch/tiger-full.d.ts.map +1 -1
- package/out/src/tools/fetch/tiger-full.js +35 -20
- package/out/src/tools/fetch/tiger-full.js.map +1 -1
- package/out/src/tools/gb-title-case.d.ts.map +1 -1
- package/out/src/tools/gb-title-case.js.map +1 -1
- package/out/src/tools/golden-expand.d.ts +24 -8
- package/out/src/tools/golden-expand.d.ts.map +1 -1
- package/out/src/tools/golden-expand.js +20 -12
- package/out/src/tools/golden-expand.js.map +1 -1
- package/out/src/tools/golden-promote.d.ts +18 -6
- package/out/src/tools/golden-promote.d.ts.map +1 -1
- package/out/src/tools/golden-promote.js +22 -7
- package/out/src/tools/golden-promote.js.map +1 -1
- package/out/src/tools/ingest-csv.d.ts +3 -1
- package/out/src/tools/ingest-csv.d.ts.map +1 -1
- package/out/src/tools/ingest-csv.js +17 -19
- package/out/src/tools/ingest-csv.js.map +1 -1
- package/out/src/tools/jsonl-to-parquet.d.ts +18 -6
- package/out/src/tools/jsonl-to-parquet.d.ts.map +1 -1
- package/out/src/tools/jsonl-to-parquet.js +11 -5
- package/out/src/tools/jsonl-to-parquet.js.map +1 -1
- package/out/src/tools/lint-shard-vocab.d.ts +36 -12
- package/out/src/tools/lint-shard-vocab.d.ts.map +1 -1
- package/out/src/tools/lint-shard-vocab.js +25 -11
- package/out/src/tools/lint-shard-vocab.js.map +1 -1
- package/out/src/tools/lint-shard.d.ts +30 -10
- package/out/src/tools/lint-shard.d.ts.map +1 -1
- package/out/src/tools/lint-shard.js +33 -20
- 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 +6 -4
- package/out/src/tools/overlay-manifest.js.map +1 -1
- package/out/src/tools/shard-kryptonite.d.ts +6 -2
- package/out/src/tools/shard-kryptonite.d.ts.map +1 -1
- package/out/src/tools/shard-kryptonite.js +1 -1
- package/out/src/tools/shard-kryptonite.js.map +1 -1
- package/out/src/tools/shard-translit.d.ts +9 -3
- package/out/src/tools/shard-translit.d.ts.map +1 -1
- package/out/src/tools/shard-translit.js +2 -2
- package/out/src/tools/shard-translit.js.map +1 -1
- package/out/src/types.d.ts +51 -17
- package/out/src/types.d.ts.map +1 -1
- package/out/src/wof-json.d.ts +9 -3
- package/out/src/wof-json.d.ts.map +1 -1
- package/out/src/wof-json.js +6 -4
- package/out/src/wof-json.js.map +1 -1
- package/package.json +7 -6
- package/src/adapter.ts +24 -13
- package/src/adapters/ban/adapter.ts +12 -2
- package/src/adapters/ban/street-decompose.ts +7 -1
- package/src/adapters/fcc-bdc/adapter.ts +19 -3
- package/src/adapters/geonames/adapter.ts +28 -5
- package/src/adapters/geonames-postal/adapter.ts +17 -1
- package/src/adapters/gnaf/adapter.ts +15 -2
- package/src/adapters/gnaf/assemble.ts +40 -10
- package/src/adapters/index.ts +13 -0
- package/src/adapters/openaddresses/adapter.ts +22 -3
- package/src/adapters/overture/adapter.ts +18 -2
- package/src/adapters/state-hi-schools/adapter.ts +15 -0
- package/src/adapters/state-ia-contractors/adapter.ts +15 -0
- package/src/adapters/state-ny-notaries/adapter.ts +15 -0
- package/src/adapters/state-tx-notaries/adapter.ts +18 -2
- package/src/adapters/synth-po-box/adapter.ts +19 -2
- package/src/adapters/tiger/adapter.ts +23 -4
- package/src/adapters/tiger/street-decompose.ts +1 -0
- package/src/adapters/usgov-hrsa-fqhc/adapter.ts +18 -2
- package/src/adapters/usgov-imls-pls/adapter.ts +15 -0
- package/src/adapters/usgov-irs-bmf/adapter.ts +19 -2
- package/src/adapters/usgov-nad/adapter.ts +14 -1
- package/src/adapters/usgov-nppes/adapter.ts +13 -0
- package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +21 -3
- package/src/adapters/wof-admin-jp/adapter.ts +20 -3
- package/src/adapters/wof-admin-json/adapter.ts +22 -7
- package/src/adapters/wof-postalcode-json/adapter.ts +10 -2
- package/src/align.ts +21 -8
- package/src/build.ts +48 -11
- package/src/codex/us-fips-state.ts +6 -2
- package/src/golden.ts +28 -13
- package/src/license.ts +4 -2
- package/src/parquet-wrapper/reader.ts +6 -4
- package/src/parquet-wrapper/schema.ts +14 -10
- package/src/parquet-wrapper/writer.ts +12 -4
- package/src/parquet.ts +39 -8
- package/src/runner.ts +49 -15
- package/src/shard-recipes/anchor-absorption.ts +21 -5
- package/src/shard-recipes/boundary-stress.ts +20 -7
- package/src/shard-recipes/country-balanced.ts +78 -13
- package/src/shard-recipes/cz-pcfirst-preposition.ts +9 -0
- package/src/shard-recipes/fr-admin-split.ts +30 -5
- package/src/shard-recipes/fr-bare-street.ts +10 -0
- package/src/shard-recipes/fr-fragment.ts +33 -8
- package/src/shard-recipes/fr-lieudit.ts +35 -9
- package/src/shard-recipes/fr-order.ts +47 -9
- package/src/shard-recipes/german.ts +32 -6
- package/src/shard-recipes/house-venue.ts +7 -0
- package/src/shard-recipes/index.ts +12 -4
- package/src/shard-recipes/intersection.ts +63 -14
- package/src/shard-recipes/locale.ts +37 -4
- package/src/shard-recipes/nl-postcode.ts +12 -2
- package/src/shard-recipes/no-fragment.ts +12 -2
- package/src/shard-recipes/no-street-led.ts +11 -1
- package/src/shard-recipes/no-street.ts +7 -0
- package/src/shard-recipes/po-box-cedex.ts +145 -45
- package/src/shard-recipes/po-box.ts +7 -0
- package/src/shard-recipes/scaffold.ts +52 -20
- package/src/shard-recipes/si-bare-village.ts +9 -0
- package/src/shard-recipes/street-affix.ts +88 -13
- package/src/shard-recipes/street-bare.ts +10 -0
- package/src/shard-recipes/street.ts +7 -0
- package/src/shard-recipes/unit.ts +79 -16
- package/src/split.ts +28 -7
- package/src/synthesize-anchor-absorption.ts +41 -14
- package/src/synthesize-boundary-stress.ts +57 -30
- package/src/synthesize-german.ts +30 -7
- package/src/synthesize-house-venue.ts +22 -16
- package/src/synthesize-intersection.ts +34 -7
- package/src/synthesize-no-street.ts +18 -10
- package/src/synthesize-po-box.ts +42 -10
- package/src/synthesize-street.ts +10 -2
- package/src/synthesize.ts +81 -38
- package/src/tokenize.ts +15 -5
- package/src/tools/align-shard.ts +6 -1
- package/src/tools/audit.ts +57 -11
- package/src/tools/corpus-stats.ts +9 -0
- package/src/tools/fetch/ban.ts +32 -10
- package/src/tools/fetch/download.ts +49 -12
- package/src/tools/fetch/hrsa.ts +3 -0
- package/src/tools/fetch/imls-pls.ts +28 -18
- package/src/tools/fetch/index.ts +3 -1
- package/src/tools/fetch/nad.ts +39 -12
- package/src/tools/fetch/nppes.ts +17 -15
- package/src/tools/fetch/openaddresses.ts +52 -24
- package/src/tools/fetch/ppd.ts +22 -3
- package/src/tools/fetch/state-hi-schools.ts +17 -6
- package/src/tools/fetch/state-sources.ts +16 -3
- package/src/tools/fetch/tiger-full.ts +66 -23
- package/src/tools/gb-title-case.ts +1 -0
- package/src/tools/golden-expand.ts +64 -20
- package/src/tools/golden-promote.ts +53 -13
- package/src/tools/ingest-csv.ts +41 -26
- package/src/tools/jsonl-to-parquet.ts +30 -10
- package/src/tools/lint-shard-vocab.ts +75 -24
- package/src/tools/lint-shard.ts +75 -31
- package/src/tools/overlay-manifest.ts +7 -4
- package/src/tools/shard-kryptonite.ts +11 -3
- package/src/tools/shard-translit.ts +20 -5
- package/src/types.ts +51 -17
- package/src/wof-json.ts +18 -7
|
@@ -190,6 +190,7 @@ export async function readTuples(part, rng) {
|
|
|
190
190
|
})) {
|
|
191
191
|
if (header === null) {
|
|
192
192
|
header = cells.map((h) => h.trim().toLowerCase());
|
|
193
|
+
// oxlint-disable-next-line no-loop-func -- the binding is per-iteration (for-of/for-await) and the batch is awaited before the next
|
|
193
194
|
const ix = (name) => header.indexOf(name);
|
|
194
195
|
// `cnigRaw` (ES pedanía only): the RAW CNIG header has no NUMBER/STREET/CITY/DISTRICT/REGION/POSTCODE
|
|
195
196
|
// at all — `numero`/`nombre_via`/`poblacion`/`municipio`/`comunidad_autonoma`/`cod_postal` instead.
|
|
@@ -291,8 +292,8 @@ export async function readTuples(part, rng) {
|
|
|
291
292
|
}
|
|
292
293
|
}
|
|
293
294
|
}
|
|
294
|
-
catch (
|
|
295
|
-
console.error(` WARN: read failed for ${part.path ?? part.zip}: ${
|
|
295
|
+
catch (error) {
|
|
296
|
+
console.error(` WARN: read failed for ${part.path ?? part.zip}: ${error.message}`);
|
|
296
297
|
return [];
|
|
297
298
|
}
|
|
298
299
|
console.error(` ${part.path ?? part.csv}: ${reservoir.length} sampled of ${seen} rows (${dropped} city-noise drops)`);
|
|
@@ -335,6 +336,10 @@ export function applyDistrictAsLocalityOverride(part, override) {
|
|
|
335
336
|
export function resolveLocaleParts(countrySource, override) {
|
|
336
337
|
return override === true && countrySource.pedaniaParts ? countrySource.pedaniaParts : countrySource.parts;
|
|
337
338
|
}
|
|
339
|
+
/**
|
|
340
|
+
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
341
|
+
* and `description` below for the surface form it generates.
|
|
342
|
+
*/
|
|
338
343
|
export const localeRecipe = {
|
|
339
344
|
name: "locale",
|
|
340
345
|
description: "Per-locale coverage rows (DE/FR/NL/IT/ES/NZ/GB) from real OA tuples, both orders → synthesizeLocaleRow",
|
|
@@ -382,14 +387,14 @@ export const localeRecipe = {
|
|
|
382
387
|
for (let pi = 0; pi < parts.length; pi++) {
|
|
383
388
|
// A reservoir PRNG per part, seeded but independent of the emit loop's `random`, so the sample is
|
|
384
389
|
// reproducible without perturbing the synth/order draws.
|
|
385
|
-
const reservoirRng = makeMulberry32((opts.seed ^ (
|
|
390
|
+
const reservoirRng = makeMulberry32((opts.seed ^ (0x9e_37_79_b9 * (pi + 1))) >>> 0);
|
|
386
391
|
const effectivePart = applyDistrictAsLocalityOverride(parts[pi], districtAsLocalityOverride);
|
|
387
392
|
const t = await readTuples(effectivePart, reservoirRng);
|
|
388
393
|
for (const x of t) {
|
|
389
394
|
pool.push(x);
|
|
390
395
|
} // NOT pool.push(...t) — spreading huge arrays overflows the stack
|
|
391
396
|
}
|
|
392
|
-
if (pool.length
|
|
397
|
+
if (!pool.length) {
|
|
393
398
|
throw new Error(`No ${country} tuples found — are the source CSVs/zips present? (see COUNTRY_SOURCES)`);
|
|
394
399
|
}
|
|
395
400
|
let emitted = 0;
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"locale.js","sourceRoot":"","sources":["../../../src/shard-recipes/locale.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;GAyBG;AAEH,OAAO,EAAE,KAAK,EAAE,MAAM,oBAAoB,CAAA;AAC1C,OAAO,EAAE,gBAAgB,EAAE,MAAM,SAAS,CAAA;AAE1C,OAAO,EAAE,qBAAqB,EAAE,MAAM,0BAA0B,CAAA;AAChE,OAAO,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAA;AACpD,OAAO,EAAE,cAAc,EAAE,MAAM,aAAa,CAAA;AAE5C,OAAO,EAAE,cAAc,EAAE,MAAM,eAAe,CAAA;AAC9C,OAAO,EAAE,QAAQ,EAAE,MAAM,aAAa,CAAA;AACtC,OAAO,EAAmD,mBAAmB,EAAE,MAAM,yBAAyB,CAAA;AAC9G,OAAO,EAAE,cAAc,EAAoB,MAAM,eAAe,CAAA;AAkDhE;;;;;;;GAOG;AACH,MAAM,eAAe,GAAwC;IAC5D,EAAE,EAAE;QACH,MAAM,EAAE,cAAc;QACtB,aAAa,EAAE,OAAO;QACtB,KAAK,EAAE;YACN,EAAE,GAAG,EAAE,8BAA8B,EAAE,GAAG,EAAE,eAAe,EAAE,MAAM,EAAE,QAAQ,EAAE;YAC/E,EAAE,GAAG,EAAE,qCAAqC,EAAE,GAAG,EAAE,qBAAqB,EAAE,MAAM,EAAE,SAAS,EAAE;SAC7F;KACD;IACD,EAAE,EAAE;QACH,MAAM,EAAE,UAAU;QAClB,aAAa,EAAE,OAAO;QACtB,KAAK,EAAE,CAAC,EAAE,GAAG,EAAE,mCAAmC,EAAE,GAAG,EAAE,oBAAoB,EAAE,CAAC;KAChF;IACD,EAAE,EAAE;QACH,MAAM,EAAE,UAAU;QAClB,aAAa,EAAE,OAAO;QACtB,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,YAAY,CAAC,eAAe,EAAE,WAAW,EAAE,IAAI,EAAE,iBAAiB,CAAC,EAAE,CAAC;KACtF;IACD,EAAE,EAAE;QACH,MAAM,EAAE,UAAU;QAClB,aAAa,EAAE,OAAO;QACtB,KAAK,EAAE,CAAC,EAAE,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,qBAAqB,CAAC,EAAE,GAAG,EAAE,oBAAoB,EAAE,CAAC;KAC5F;IACD,EAAE,EAAE;QACH,MAAM,EAAE,UAAU;QAClB,aAAa,EAAE,OAAO;QACtB,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,YAAY,CAAC,eAAe,EAAE,WAAW,EAAE,IAAI,EAAE,iBAAiB,CAAC,EAAE,CAAC;QACtF,yGAAyG;QACzG,2GAA2G;QAC3G,wGAAwG;QACxG,yEAAyE;QACzE,YAAY,EAAE;YACb;gBACC,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,qBAAqB,CAAC;gBACpD,GAAG,EAAE,kBAAkB;gBACvB,OAAO,EAAE,IAAI;gBACb,kBAAkB,EAAE,IAAI;aACxB;SACD;KACD;IACD,EAAE,EAAE;QACH,mGAAmG;QACnG,wGAAwG;QACxG,MAAM,EAAE,UAAU;QAClB,aAAa,EAAE,OAAO;QACtB,6GAA6G;QAC7G,4GAA4G;QAC5G,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,YAAY,CAAC,eAAe,EAAE,WAAW,EAAE,IAAI,EAAE,iBAAiB,CAAC,EAAE,kBAAkB,EAAE,IAAI,EAAE,CAAC;KAChH;IACD,EAAE,EAAE;QACH,wGAAwG;QACxG,yGAAyG;QACzG,wGAAwG;QACxG,yGAAyG;QACzG,wCAAwC;QACxC,MAAM,EAAE,UAAU;QAClB,aAAa,EAAE,OAAO;QACtB,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,YAAY,CAAC,KAAK,EAAE,YAAY,EAAE,eAAe,CAAC,EAAE,kBAAkB,EAAE,IAAI,EAAE,CAAC;KAC/F;CACD,CAAA;AAED;;;;GAIG;AACH,MAAM,aAAa,GAAG,SAAS,CAAA;AAE/B;;;;GAIG;AACH,MAAM,sBAAsB,GAAG,GAAG,CAAA;AAElC;;;;GAIG;AACH,MAAM,0BAA0B,GAAG,GAAG,CAAA;AAEtC;;;;;;;;;;;;;;;;;;;;;;GAsBG;AACH,MAAM,UAAU,cAAc,CAAC,IAAY;IAC1C,IAAI,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC;QAAE,OAAO,IAAI,CAAA;IAErC,MAAM,QAAQ,GAAG,IAAI,CAAC,OAAO,CAAC,wBAAwB,EAAE,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;IAElE,OAAO,QAAQ,IAAI,IAAI,CAAA;AACxB,CAAC;AAgBD;;;;;;;;GAQG;AACH,MAAM,CAAC,KAAK,UAAU,UAAU,CAAC,IAAgB,EAAE,GAAiB;IACnE,IAAI,KAA4B,CAAA;IAEhC,IAAI,IAAI,CAAC,IAAI,EAAE,CAAC;QACf,8FAA8F;QAC9F,qEAAqE;QACrE,KAAK,GAAG,gBAAgB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;IACpC,CAAC;SAAM,CAAC;QACP,MAAM,KAAK,GAAG,KAAK,CAAC,OAAO,EAAE,CAAC,IAAI,EAAE,IAAI,CAAC,GAAI,EAAE,IAAI,CAAC,GAAI,CAAC,CAAC,CAAA;QAC1D,KAAK,CAAC,EAAE,CAAC,OAAO,EAAE,CAAC,GAAG,EAAE,EAAE;YACzB,OAAO,CAAC,KAAK,CAAC,4BAA4B,IAAI,CAAC,GAAG,KAAK,GAAG,CAAC,OAAO,EAAE,CAAC,CAAA;QACtE,CAAC,CAAC,CAAA;QACF,KAAK,GAAG,KAAK,CAAC,MAAO,CAAA;IACtB,CAAC;IACD,MAAM,GAAG,GAAG,CAAC,KAAe,EAAE,CAAS,EAAU,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,CAAA;IAC/G,MAAM,SAAS,GAAsB,EAAE,CAAA;IACvC,IAAI,IAAI,GAAuB,IAAI,CAAA;IACnC,IAAI,MAAM,GAAoB,IAAI,CAAA;IAClC,IAAI,IAAI,GAAG,CAAC,CAAA;IACZ,IAAI,OAAO,GAAG,CAAC,CAAA;IAEf,IAAI,CAAC;QACJ,gGAAgG;QAChG,iGAAiG;QACjG,mGAAmG;QACnG,sGAAsG;QACtG,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,cAAc,CAAC,SAAS,CAAW,KAAK,EAAE;YACnE,IAAI,EAAE,OAAO;YACb,MAAM,EAAE,KAAK;YACb,mBAAmB,EAAE,IAAI;SACzB,CAAC,EAAE,CAAC;YACJ,IAAI,MAAM,KAAK,IAAI,EAAE,CAAC;gBACrB,MAAM,GAAG,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAC,CAAA;gBACjD,MAAM,EAAE,GAAG,CAAC,IAAY,EAAU,EAAE,CAAC,MAAO,CAAC,OAAO,CAAC,IAAI,CAAC,CAAA;gBAC1D,sGAAsG;gBACtG,oGAAoG;gBACpG,kCAAkC;gBAClC,IAAI,GAAG,IAAI,CAAC,OAAO;oBAClB,CAAC,CAAC;wBACA,GAAG,EAAE,EAAE,CAAC,QAAQ,CAAC;wBACjB,MAAM,EAAE,EAAE,CAAC,YAAY,CAAC;wBACxB,QAAQ,EAAE,EAAE,CAAC,WAAW,CAAC;wBACzB,IAAI,EAAE,EAAE,CAAC,WAAW,CAAC;wBACrB,QAAQ,EAAE,EAAE,CAAC,WAAW,CAAC;wBACzB,MAAM,EAAE,EAAE,CAAC,oBAAoB,CAAC;wBAChC,IAAI,EAAE,EAAE,CAAC,YAAY,CAAC;qBACtB;oBACF,CAAC,CAAC;wBACA,GAAG,EAAE,EAAE,CAAC,QAAQ,CAAC;wBACjB,MAAM,EAAE,EAAE,CAAC,QAAQ,CAAC;wBACpB,QAAQ,EAAE,CAAC,CAAC;wBACZ,IAAI,EAAE,EAAE,CAAC,MAAM,CAAC;wBAChB,QAAQ,EAAE,EAAE,CAAC,UAAU,CAAC;wBACxB,MAAM,EAAE,EAAE,CAAC,QAAQ,CAAC;wBACpB,IAAI,EAAE,EAAE,CAAC,UAAU,CAAC;qBACpB,CAAA;gBAEH,SAAQ;YACT,CAAC;YAED,IAAI,IAAI,KAAK,IAAI;gBAAE,SAAQ;YAC3B,gGAAgG;YAChG,qGAAqG;YACrG,kGAAkG;YAClG,iFAAiF;YACjF,MAAM,MAAM,GACX,IAAI,CAAC,QAAQ,IAAI,CAAC;gBACjB,CAAC,CAAC,CAAC,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,QAAQ,CAAC,EAAE,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC;gBAChF,CAAC,CAAC,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,MAAM,CAAC,CAAA;YAC3B,MAAM,OAAO,GAAG,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,IAAI,CAAC,CAAA;YAErC,IAAI,CAAC,MAAM;gBAAE,SAAQ;YAErB,qGAAqG;YACrG,2FAA2F;YAC3F,qGAAqG;YACrG,sGAAsG;YACtG,qGAAqG;YACrG,sGAAsG;YACtG,2EAA2E;YAC3E,yCAAyC;YACzC,IAAI,QAAuB,CAAA;YAC3B,IAAI,kBAAsC,CAAA;YAE1C,IAAI,IAAI,CAAC,kBAAkB,EAAE,CAAC;gBAC7B,MAAM,WAAW,GAAG,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,QAAQ,CAAC,CAAA;gBAE7C,IAAI,CAAC,OAAO,IAAI,CAAC,WAAW;oBAAE,SAAQ;gBAEtC,MAAM,eAAe,GAAG,cAAc,CAAC,WAAW,CAAC,CAAA;gBAEnD,IAAI,eAAe,EAAE,CAAC;oBACrB,QAAQ,GAAG,eAAe,CAAA;oBAC1B,MAAM,WAAW,GAAG,cAAc,CAAC,OAAO,CAAC,CAAA;oBAC3C,4FAA4F;oBAC5F,6FAA6F;oBAC7F,uFAAuF;oBACvF,2FAA2F;oBAC3F,4FAA4F;oBAC5F,2FAA2F;oBAC3F,8DAA8D;oBAC9D,kBAAkB;wBACjB,WAAW,IAAI,WAAW,CAAC,aAAa,CAAC,QAAQ,EAAE,SAAS,EAAE,EAAE,WAAW,EAAE,MAAM,EAAE,CAAC,KAAK,CAAC;4BAC3F,CAAC,CAAC,WAAW;4BACb,CAAC,CAAC,SAAS,CAAA;gBACd,CAAC;qBAAM,CAAC;oBACP,QAAQ,GAAG,cAAc,CAAC,OAAO,CAAC,CAAA;gBACnC,CAAC;YACF,CAAC;iBAAM,CAAC;gBACP,IAAI,CAAC,OAAO;oBAAE,SAAQ;gBACtB,QAAQ,GAAG,cAAc,CAAC,OAAO,CAAC,CAAA;YACnC,CAAC;YAED,IAAI,CAAC,QAAQ,EAAE,CAAC;gBACf,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YACD,MAAM,KAAK,GAAoB;gBAC9B,YAAY,EAAE,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,GAAG,CAAC;gBAClC,MAAM;gBACN,QAAQ;gBACR,MAAM,EAAE,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,MAAM,CAAC,IAAI,IAAI,CAAC,MAAM,IAAI,EAAE;gBACpD,QAAQ,EAAE,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,IAAI,CAAC;gBAC/B,GAAG,CAAC,kBAAkB,CAAC,CAAC,CAAC,EAAE,kBAAkB,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;aACrD,CAAA;YACD,IAAI,EAAE,CAAA;YAEN,IAAI,SAAS,CAAC,MAAM,GAAG,aAAa,EAAE,CAAC;gBACtC,SAAS,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;YACtB,CAAC;iBAAM,CAAC;gBACP,MAAM,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,GAAG,EAAE,GAAG,IAAI,CAAC,CAAA;gBAElC,cAAc;gBACd,IAAI,CAAC,GAAG,aAAa,EAAE,CAAC;oBACvB,SAAS,CAAC,CAAC,CAAC,GAAG,KAAK,CAAA;gBACrB,CAAC;YACF,CAAC;QACF,CAAC;IACF,CAAC;IAAC,OAAO,GAAG,EAAE,CAAC;QACd,OAAO,CAAC,KAAK,CAAC,2BAA2B,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,GAAG,KAAM,GAAa,CAAC,OAAO,EAAE,CAAC,CAAA;QAE5F,OAAO,EAAE,CAAA;IACV,CAAC;IAED,OAAO,CAAC,KAAK,CAAC,KAAK,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,GAAG,KAAK,SAAS,CAAC,MAAM,eAAe,IAAI,UAAU,OAAO,oBAAoB,CAAC,CAAA;IAEtH,OAAO,SAAS,CAAA;AACjB,CAAC;AAED;;;;;;;GAOG;AACH,MAAM,UAAU,kBAAkB,CACjC,KAA2B,EAC3B,OAAe,EACf,eAAuB,EACvB,MAAoB;IAEpB,IAAI,eAAe,GAAG,CAAC,IAAI,MAAM,EAAE,GAAG,eAAe,EAAE,CAAC;QACvD,MAAM,KAAK,GAAG,qBAAqB,CAAC,OAA6C,CAAC,CAAA;QAElF,IAAI,CAAC,KAAK,EAAE,MAAM,EAAE,CAAC;YACpB,2FAA2F;YAC3F,+FAA+F;YAC/F,MAAM,IAAI,KAAK,CACd,sCAAsC,OAAO,uEAAuE,CACpH,CAAA;QACF,CAAC;QAED,MAAM,IAAI,GAAG,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,KAAK,CAAC,MAAM,CAAC,CAAE,CAAA;QACxD,KAAK,CAAC,GAAG,GAAG,GAAG,KAAK,CAAC,GAAG,KAAK,IAAI,EAAE,CAAA;QACnC,KAAK,CAAC,UAAU,GAAG,EAAE,GAAG,KAAK,CAAC,UAAU,EAAE,OAAO,EAAE,IAAI,EAAE,CAAA;IAC1D,CAAC;AACF,CAAC;AAED;;;;GAIG;AACH,MAAM,UAAU,+BAA+B,CAAC,IAAgB,EAAE,QAA6B;IAC9F,OAAO,QAAQ,KAAK,SAAS,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,GAAG,IAAI,EAAE,kBAAkB,EAAE,QAAQ,EAAE,CAAA;AACjF,CAAC;AAED;;;;GAIG;AACH,MAAM,UAAU,kBAAkB,CAAC,aAAkC,EAAE,QAA6B;IACnG,OAAO,QAAQ,KAAK,IAAI,IAAI,aAAa,CAAC,YAAY,CAAC,CAAC,CAAC,aAAa,CAAC,YAAY,CAAC,CAAC,CAAC,aAAa,CAAC,KAAK,CAAA;AAC1G,CAAC;AAED,MAAM,CAAC,MAAM,YAAY,GAAgB;IACxC,IAAI,EAAE,QAAQ;IACd,WAAW,EAAE,wGAAwG;IACrH,IAAI,EAAE,UAAU;IAChB,OAAO,EAAE;QACR,EAAE,IAAI,EAAE,gBAAgB,EAAE,WAAW,EAAE,mDAAmD,EAAE;QAC5F,EAAE,IAAI,EAAE,qBAAqB,EAAE,WAAW,EAAE,oDAAoD,EAAE;QAClG;YACC,IAAI,EAAE,wBAAwB;YAC9B,WAAW,EACV,uLAAuL;SACxL;QACD;YACC,IAAI,EAAE,oDAAoD;YAC1D,WAAW,EACV,qUAAqU;SACtU;KACD;IACD,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,kGAAkG;QAClG,0FAA0F;QAC1F,MAAM,MAAM,GAAG,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACxC,MAAM,OAAO,GAAG,CAAC,IAAI,CAAC,OAAO,IAAI,IAAI,CAAC,CAAC,WAAW,EAAE,CAAA;QACpD,MAAM,aAAa,GAAG,eAAe,CAAC,OAAO,CAAC,CAAA;QAE9C,IAAI,CAAC,aAAa,EAAE,CAAC;YACpB,MAAM,IAAI,KAAK,CACd,0CAA0C,OAAO,YAAY,MAAM,CAAC,IAAI,CAAC,eAAe,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,CACvG,CAAA;QACF,CAAC;QACD,MAAM,YAAY,GAAG,IAAI,CAAC,YAAY,IAAI,GAAG,CAAA;QAE7C,IAAI,CAAC,CAAC,YAAY,IAAI,CAAC,IAAI,YAAY,IAAI,CAAC,CAAC,EAAE,CAAC;YAC/C,MAAM,IAAI,KAAK,CAAC,0CAA0C,YAAY,EAAE,CAAC,CAAA;QAC1E,CAAC;QACD,kGAAkG;QAClG,qGAAqG;QACrG,MAAM,eAAe,GAAG,IAAI,CAAC,eAAe,IAAI,CAAC,CAAA;QAEjD,IAAI,CAAC,CAAC,eAAe,IAAI,CAAC,IAAI,eAAe,IAAI,CAAC,CAAC,EAAE,CAAC;YACrD,MAAM,IAAI,KAAK,CAAC,6CAA6C,eAAe,EAAE,CAAC,CAAA;QAChF,CAAC;QACD,MAAM,MAAM,GAAG,IAAI,CAAC,UAAU,IAAI,aAAa,CAAC,MAAM,CAAA;QACtD,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,IAAI,IAAI,CAAA;QAChC,uGAAuG;QACvG,2GAA2G;QAC3G,0GAA0G;QAC1G,2FAA2F;QAC3F,MAAM,0BAA0B,GAAG,IAAI,CAAC,kBAAkB,CAAA;QAC1D,MAAM,KAAK,GAAG,kBAAkB,CAAC,aAAa,EAAE,0BAA0B,CAAC,CAAA;QAE3E,MAAM,IAAI,GAAsB,EAAE,CAAA;QAElC,KAAK,IAAI,EAAE,GAAG,CAAC,EAAE,EAAE,GAAG,KAAK,CAAC,MAAM,EAAE,EAAE,EAAE,EAAE,CAAC;YAC1C,kGAAkG;YAClG,yDAAyD;YACzD,MAAM,YAAY,GAAG,cAAc,CAAC,CAAC,IAAI,CAAC,IAAI,GAAG,CAAC,UAAU,GAAG,CAAC,EAAE,GAAG,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAA;YAChF,MAAM,aAAa,GAAG,+BAA+B,CAAC,KAAK,CAAC,EAAE,CAAE,EAAE,0BAA0B,CAAC,CAAA;YAC7F,MAAM,CAAC,GAAG,MAAM,UAAU,CAAC,aAAa,EAAE,YAAY,CAAC,CAAA;YAEvD,KAAK,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC;gBACnB,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;YACb,CAAC,CAAC,kEAAkE;QACrE,CAAC;QAED,IAAI,IAAI,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACvB,MAAM,IAAI,KAAK,CAAC,MAAM,OAAO,yEAAyE,CAAC,CAAA;QACxG,CAAC;QAED,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,KAAK,GAAG,CAAC,CAAA;QACb,MAAM,CAAC,GAAG,IAAI,CAAC,MAAM,CAAA;QAErB,OAAO,OAAO,GAAG,KAAK,IAAI,KAAK,EAAE,GAAG,KAAK,GAAG,CAAC,EAAE,CAAC;YAC/C,MAAM,IAAI,GAAG,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,CAAE,CAAA;YAC5C,MAAM,KAAK,GAAG,MAAM,EAAE,GAAG,YAAY,CAAC,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,QAAQ,CAAA;YAClE,6FAA6F;YAC7F,6DAA6D;YAC7D,MAAM,eAAe,GACpB,OAAO,KAAK,IAAI,CAAC,CAAC,CAAC,CAAC,MAAM,EAAE,GAAG,sBAAsB,CAAC,CAAC,CAAE,OAAiB,CAAC,CAAC,CAAE,UAAoB,CAAC,CAAC,CAAC,CAAC,SAAS,CAAA;YAChH,MAAM,aAAa,GAClB,OAAO,KAAK,IAAI;gBACf,CAAC,CAAC,MAAM,EAAE,GAAG,0BAA0B;oBACtC,CAAC,CAAE,WAAqB;oBACxB,CAAC,CAAE,cAAwB;gBAC5B,CAAC,CAAC,SAAS,CAAA;YACb,MAAM,KAAK,GAAG,mBAAmB,CAAC,IAAI,EAAE,OAAO,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,eAAe,EAAE,aAAa,EAAE,CAAC,CAAA;YAEnG,IAAI,CAAC,KAAK,EAAE,CAAC;gBACZ,OAAO,EAAE,CAAA;gBACT,SAAQ;YACT,CAAC;YACD,kBAAkB,CAAC,KAAK,EAAE,OAAO,EAAE,eAAe,EAAE,MAAM,CAAC,CAAA;YAE3D,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC;gBACjB,8FAA8F;gBAC9F,gGAAgG;gBAChG,MAAM,eAAe,GAAG;oBACvB,GAAG,EAAE,KAAK,CAAC,GAAG;oBACd,UAAU,EAAE,KAAK,CAAC,UAAU;oBAC5B,OAAO;oBACP,MAAM,EAAE,KAAK,CAAC,MAAM;oBACpB,MAAM;oBACN,SAAS,EAAE,oBAAoB;iBAC/B,CAAA;gBACD,MAAM,aAAa,GAAG,QAAQ,CAAC,eAAiD,CAAC,CAAA;gBAEjF,IAAI,aAAa,CAAC,IAAI,KAAK,SAAS,IAAI,CAAC,aAAa,CAAC,GAAG,EAAE,CAAC;oBAC5D,OAAO,EAAE,CAAA;oBACT,SAAQ;gBACT,CAAC;gBACD,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,GAAG,EAAE,KAAK,CAAC,GAAG,EAAE,UAAU,EAAE,KAAK,CAAC,UAAU,EAAE,OAAO,EAAE,KAAK,EAAE,CAAC,GAAG,IAAI,CAAC,CAAA;gBAC9F,OAAO,EAAE,CAAA;gBACT,SAAQ;YACT,CAAC;YACD,MAAM,QAAQ,GAAG,cAAc,CAAC,MAAM,EAAE;gBACvC,MAAM,EAAE,KAAK,CAAC,UAAU,CAAC,MAAM;gBAC/B,YAAY,EAAE,KAAK,CAAC,UAAU,CAAC,YAAY;gBAC3C,QAAQ,EAAE,KAAK,CAAC,UAAU,CAAC,QAAQ;gBACnC,QAAQ,EAAE,KAAK,CAAC,UAAU,CAAC,QAAQ;aACnC,CAAC,CAAA;YACF,MAAM,SAAS,GAAG;gBACjB,GAAG,EAAE,KAAK,CAAC,GAAG;gBACd,UAAU,EAAE,KAAK,CAAC,UAAU;gBAC5B,OAAO;gBACP,MAAM,EAAE,KAAK,CAAC,MAAM;gBACpB,MAAM;gBACN,SAAS,EAAE,QAAQ;gBACnB,cAAc,EAAE,aAAa,CAAC,aAAa;gBAC3C,OAAO,EAAE,iBAAiB,OAAO,qBAAqB,KAAK,6BAA6B;aACxF,CAAA;YACD,MAAM,OAAO,GAAG,QAAQ,CAAC,SAA2C,CAAC,CAAA;YAErE,IAAI,OAAO,CAAC,IAAI,KAAK,SAAS,IAAI,CAAC,OAAO,CAAC,GAAG,EAAE,CAAC;gBAChD,OAAO,EAAE,CAAA;gBACT,SAAQ;YACT,CAAC;YACD,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,GAAG,OAAO,CAAC,GAAG,EAAE,YAAY,EAAE,MAAM,EAAE,WAAW,EAAE,KAAK,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,GAAG,IAAI,CAAC,CAAA;YAC/G,OAAO,EAAE,CAAA;QACV,CAAC;QAED,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;IAC5B,CAAC;CACD,CAAA"}
|
|
1
|
+
{"version":3,"file":"locale.js","sourceRoot":"","sources":["../../../src/shard-recipes/locale.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;GAyBG;AAEH,OAAO,EAAE,KAAK,EAAE,MAAM,oBAAoB,CAAA;AAC1C,OAAO,EAAE,gBAAgB,EAAE,MAAM,SAAS,CAAA;AAE1C,OAAO,EAAE,qBAAqB,EAAE,MAAM,0BAA0B,CAAA;AAChE,OAAO,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAA;AACpD,OAAO,EAAE,cAAc,EAAE,MAAM,aAAa,CAAA;AAE5C,OAAO,EAAE,cAAc,EAAE,MAAM,eAAe,CAAA;AAC9C,OAAO,EAAE,QAAQ,EAAE,MAAM,aAAa,CAAA;AACtC,OAAO,EAAmD,mBAAmB,EAAE,MAAM,yBAAyB,CAAA;AAC9G,OAAO,EAAE,cAAc,EAAoB,MAAM,eAAe,CAAA;AAkDhE;;;;;;;GAOG;AACH,MAAM,eAAe,GAAwC;IAC5D,EAAE,EAAE;QACH,MAAM,EAAE,cAAc;QACtB,aAAa,EAAE,OAAO;QACtB,KAAK,EAAE;YACN,EAAE,GAAG,EAAE,8BAA8B,EAAE,GAAG,EAAE,eAAe,EAAE,MAAM,EAAE,QAAQ,EAAE;YAC/E,EAAE,GAAG,EAAE,qCAAqC,EAAE,GAAG,EAAE,qBAAqB,EAAE,MAAM,EAAE,SAAS,EAAE;SAC7F;KACD;IACD,EAAE,EAAE;QACH,MAAM,EAAE,UAAU;QAClB,aAAa,EAAE,OAAO;QACtB,KAAK,EAAE,CAAC,EAAE,GAAG,EAAE,mCAAmC,EAAE,GAAG,EAAE,oBAAoB,EAAE,CAAC;KAChF;IACD,EAAE,EAAE;QACH,MAAM,EAAE,UAAU;QAClB,aAAa,EAAE,OAAO;QACtB,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,YAAY,CAAC,eAAe,EAAE,WAAW,EAAE,IAAI,EAAE,iBAAiB,CAAC,EAAE,CAAC;KACtF;IACD,EAAE,EAAE;QACH,MAAM,EAAE,UAAU;QAClB,aAAa,EAAE,OAAO;QACtB,KAAK,EAAE,CAAC,EAAE,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,qBAAqB,CAAC,EAAE,GAAG,EAAE,oBAAoB,EAAE,CAAC;KAC5F;IACD,EAAE,EAAE;QACH,MAAM,EAAE,UAAU;QAClB,aAAa,EAAE,OAAO;QACtB,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,YAAY,CAAC,eAAe,EAAE,WAAW,EAAE,IAAI,EAAE,iBAAiB,CAAC,EAAE,CAAC;QACtF,yGAAyG;QACzG,2GAA2G;QAC3G,wGAAwG;QACxG,yEAAyE;QACzE,YAAY,EAAE;YACb;gBACC,GAAG,EAAE,YAAY,CAAC,UAAU,EAAE,qBAAqB,CAAC;gBACpD,GAAG,EAAE,kBAAkB;gBACvB,OAAO,EAAE,IAAI;gBACb,kBAAkB,EAAE,IAAI;aACxB;SACD;KACD;IACD,EAAE,EAAE;QACH,mGAAmG;QACnG,wGAAwG;QACxG,MAAM,EAAE,UAAU;QAClB,aAAa,EAAE,OAAO;QACtB,6GAA6G;QAC7G,4GAA4G;QAC5G,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,YAAY,CAAC,eAAe,EAAE,WAAW,EAAE,IAAI,EAAE,iBAAiB,CAAC,EAAE,kBAAkB,EAAE,IAAI,EAAE,CAAC;KAChH;IACD,EAAE,EAAE;QACH,wGAAwG;QACxG,yGAAyG;QACzG,wGAAwG;QACxG,yGAAyG;QACzG,wCAAwC;QACxC,MAAM,EAAE,UAAU;QAClB,aAAa,EAAE,OAAO;QACtB,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,YAAY,CAAC,KAAK,EAAE,YAAY,EAAE,eAAe,CAAC,EAAE,kBAAkB,EAAE,IAAI,EAAE,CAAC;KAC/F;CACD,CAAA;AAED;;;;GAIG;AACH,MAAM,aAAa,GAAG,SAAS,CAAA;AAE/B;;;;GAIG;AACH,MAAM,sBAAsB,GAAG,GAAG,CAAA;AAElC;;;;GAIG;AACH,MAAM,0BAA0B,GAAG,GAAG,CAAA;AAEtC;;;;;;;;;;;;;;;;;;;;;;GAsBG;AACH,MAAM,UAAU,cAAc,CAAC,IAAY;IAC1C,IAAI,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC;QAAE,OAAO,IAAI,CAAA;IAErC,MAAM,QAAQ,GAAG,IAAI,CAAC,OAAO,CAAC,wBAAwB,EAAE,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;IAElE,OAAO,QAAQ,IAAI,IAAI,CAAA;AACxB,CAAC;AAgBD;;;;;;;;GAQG;AACH,MAAM,CAAC,KAAK,UAAU,UAAU,CAAC,IAAgB,EAAE,GAAiB;IACnE,IAAI,KAA4B,CAAA;IAEhC,IAAI,IAAI,CAAC,IAAI,EAAE,CAAC;QACf,8FAA8F;QAC9F,qEAAqE;QACrE,KAAK,GAAG,gBAAgB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;IACpC,CAAC;SAAM,CAAC;QACP,MAAM,KAAK,GAAG,KAAK,CAAC,OAAO,EAAE,CAAC,IAAI,EAAE,IAAI,CAAC,GAAI,EAAE,IAAI,CAAC,GAAI,CAAC,CAAC,CAAA;QAE1D,KAAK,CAAC,EAAE,CAAC,OAAO,EAAE,CAAC,GAAG,EAAE,EAAE;YACzB,OAAO,CAAC,KAAK,CAAC,4BAA4B,IAAI,CAAC,GAAG,KAAK,GAAG,CAAC,OAAO,EAAE,CAAC,CAAA;QACtE,CAAC,CAAC,CAAA;QAEF,KAAK,GAAG,KAAK,CAAC,MAAO,CAAA;IACtB,CAAC;IAED,MAAM,GAAG,GAAG,CAAC,KAAe,EAAE,CAAS,EAAU,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC,CAAA;IAC/G,MAAM,SAAS,GAAsB,EAAE,CAAA;IACvC,IAAI,IAAI,GAAuB,IAAI,CAAA;IACnC,IAAI,MAAM,GAAoB,IAAI,CAAA;IAClC,IAAI,IAAI,GAAG,CAAC,CAAA;IACZ,IAAI,OAAO,GAAG,CAAC,CAAA;IAEf,IAAI,CAAC;QACJ,gGAAgG;QAChG,iGAAiG;QACjG,mGAAmG;QACnG,sGAAsG;QACtG,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,cAAc,CAAC,SAAS,CAAW,KAAK,EAAE;YACnE,IAAI,EAAE,OAAO;YACb,MAAM,EAAE,KAAK;YACb,mBAAmB,EAAE,IAAI;SACzB,CAAC,EAAE,CAAC;YACJ,IAAI,MAAM,KAAK,IAAI,EAAE,CAAC;gBACrB,MAAM,GAAG,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAC,CAAA;gBACjD,oIAAoI;gBACpI,MAAM,EAAE,GAAG,CAAC,IAAY,EAAU,EAAE,CAAC,MAAO,CAAC,OAAO,CAAC,IAAI,CAAC,CAAA;gBAE1D,sGAAsG;gBACtG,oGAAoG;gBACpG,kCAAkC;gBAClC,IAAI,GAAG,IAAI,CAAC,OAAO;oBAClB,CAAC,CAAC;wBACA,GAAG,EAAE,EAAE,CAAC,QAAQ,CAAC;wBACjB,MAAM,EAAE,EAAE,CAAC,YAAY,CAAC;wBACxB,QAAQ,EAAE,EAAE,CAAC,WAAW,CAAC;wBACzB,IAAI,EAAE,EAAE,CAAC,WAAW,CAAC;wBACrB,QAAQ,EAAE,EAAE,CAAC,WAAW,CAAC;wBACzB,MAAM,EAAE,EAAE,CAAC,oBAAoB,CAAC;wBAChC,IAAI,EAAE,EAAE,CAAC,YAAY,CAAC;qBACtB;oBACF,CAAC,CAAC;wBACA,GAAG,EAAE,EAAE,CAAC,QAAQ,CAAC;wBACjB,MAAM,EAAE,EAAE,CAAC,QAAQ,CAAC;wBACpB,QAAQ,EAAE,CAAC,CAAC;wBACZ,IAAI,EAAE,EAAE,CAAC,MAAM,CAAC;wBAChB,QAAQ,EAAE,EAAE,CAAC,UAAU,CAAC;wBACxB,MAAM,EAAE,EAAE,CAAC,QAAQ,CAAC;wBACpB,IAAI,EAAE,EAAE,CAAC,UAAU,CAAC;qBACpB,CAAA;gBAEH,SAAQ;YACT,CAAC;YAED,IAAI,IAAI,KAAK,IAAI;gBAAE,SAAQ;YAE3B,gGAAgG;YAChG,qGAAqG;YACrG,kGAAkG;YAClG,iFAAiF;YACjF,MAAM,MAAM,GACX,IAAI,CAAC,QAAQ,IAAI,CAAC;gBACjB,CAAC,CAAC,CAAC,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,QAAQ,CAAC,EAAE,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC;gBAChF,CAAC,CAAC,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,MAAM,CAAC,CAAA;YAE3B,MAAM,OAAO,GAAG,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,IAAI,CAAC,CAAA;YAErC,IAAI,CAAC,MAAM;gBAAE,SAAQ;YAErB,qGAAqG;YACrG,2FAA2F;YAC3F,qGAAqG;YACrG,sGAAsG;YACtG,qGAAqG;YACrG,sGAAsG;YACtG,2EAA2E;YAC3E,yCAAyC;YACzC,IAAI,QAAuB,CAAA;YAC3B,IAAI,kBAAsC,CAAA;YAE1C,IAAI,IAAI,CAAC,kBAAkB,EAAE,CAAC;gBAC7B,MAAM,WAAW,GAAG,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,QAAQ,CAAC,CAAA;gBAE7C,IAAI,CAAC,OAAO,IAAI,CAAC,WAAW;oBAAE,SAAQ;gBAEtC,MAAM,eAAe,GAAG,cAAc,CAAC,WAAW,CAAC,CAAA;gBAEnD,IAAI,eAAe,EAAE,CAAC;oBACrB,QAAQ,GAAG,eAAe,CAAA;oBAC1B,MAAM,WAAW,GAAG,cAAc,CAAC,OAAO,CAAC,CAAA;oBAE3C,4FAA4F;oBAC5F,6FAA6F;oBAC7F,uFAAuF;oBACvF,2FAA2F;oBAC3F,4FAA4F;oBAC5F,2FAA2F;oBAC3F,8DAA8D;oBAC9D,kBAAkB;wBACjB,WAAW,IAAI,WAAW,CAAC,aAAa,CAAC,QAAQ,EAAE,SAAS,EAAE,EAAE,WAAW,EAAE,MAAM,EAAE,CAAC,KAAK,CAAC;4BAC3F,CAAC,CAAC,WAAW;4BACb,CAAC,CAAC,SAAS,CAAA;gBACd,CAAC;qBAAM,CAAC;oBACP,QAAQ,GAAG,cAAc,CAAC,OAAO,CAAC,CAAA;gBACnC,CAAC;YACF,CAAC;iBAAM,CAAC;gBACP,IAAI,CAAC,OAAO;oBAAE,SAAQ;gBACtB,QAAQ,GAAG,cAAc,CAAC,OAAO,CAAC,CAAA;YACnC,CAAC;YAED,IAAI,CAAC,QAAQ,EAAE,CAAC;gBACf,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,MAAM,KAAK,GAAoB;gBAC9B,YAAY,EAAE,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,GAAG,CAAC;gBAClC,MAAM;gBACN,QAAQ;gBACR,MAAM,EAAE,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,MAAM,CAAC,IAAI,IAAI,CAAC,MAAM,IAAI,EAAE;gBACpD,QAAQ,EAAE,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,IAAI,CAAC;gBAC/B,GAAG,CAAC,kBAAkB,CAAC,CAAC,CAAC,EAAE,kBAAkB,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;aACrD,CAAA;YAED,IAAI,EAAE,CAAA;YAEN,IAAI,SAAS,CAAC,MAAM,GAAG,aAAa,EAAE,CAAC;gBACtC,SAAS,CAAC,IAAI,CAAC,KAAK,CAAC,CAAA;YACtB,CAAC;iBAAM,CAAC;gBACP,MAAM,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,GAAG,EAAE,GAAG,IAAI,CAAC,CAAA;gBAElC,cAAc;gBACd,IAAI,CAAC,GAAG,aAAa,EAAE,CAAC;oBACvB,SAAS,CAAC,CAAC,CAAC,GAAG,KAAK,CAAA;gBACrB,CAAC;YACF,CAAC;QACF,CAAC;IACF,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QAChB,OAAO,CAAC,KAAK,CAAC,2BAA2B,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,GAAG,KAAM,KAAe,CAAC,OAAO,EAAE,CAAC,CAAA;QAE9F,OAAO,EAAE,CAAA;IACV,CAAC;IAED,OAAO,CAAC,KAAK,CAAC,KAAK,IAAI,CAAC,IAAI,IAAI,IAAI,CAAC,GAAG,KAAK,SAAS,CAAC,MAAM,eAAe,IAAI,UAAU,OAAO,oBAAoB,CAAC,CAAA;IAEtH,OAAO,SAAS,CAAA;AACjB,CAAC;AAED;;;;;;;GAOG;AACH,MAAM,UAAU,kBAAkB,CACjC,KAA2B,EAC3B,OAAe,EACf,eAAuB,EACvB,MAAoB;IAEpB,IAAI,eAAe,GAAG,CAAC,IAAI,MAAM,EAAE,GAAG,eAAe,EAAE,CAAC;QACvD,MAAM,KAAK,GAAG,qBAAqB,CAAC,OAA6C,CAAC,CAAA;QAElF,IAAI,CAAC,KAAK,EAAE,MAAM,EAAE,CAAC;YACpB,2FAA2F;YAC3F,+FAA+F;YAC/F,MAAM,IAAI,KAAK,CACd,sCAAsC,OAAO,uEAAuE,CACpH,CAAA;QACF,CAAC;QAED,MAAM,IAAI,GAAG,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,KAAK,CAAC,MAAM,CAAC,CAAE,CAAA;QACxD,KAAK,CAAC,GAAG,GAAG,GAAG,KAAK,CAAC,GAAG,KAAK,IAAI,EAAE,CAAA;QACnC,KAAK,CAAC,UAAU,GAAG,EAAE,GAAG,KAAK,CAAC,UAAU,EAAE,OAAO,EAAE,IAAI,EAAE,CAAA;IAC1D,CAAC;AACF,CAAC;AAED;;;;GAIG;AACH,MAAM,UAAU,+BAA+B,CAAC,IAAgB,EAAE,QAA6B;IAC9F,OAAO,QAAQ,KAAK,SAAS,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,GAAG,IAAI,EAAE,kBAAkB,EAAE,QAAQ,EAAE,CAAA;AACjF,CAAC;AAED;;;;GAIG;AACH,MAAM,UAAU,kBAAkB,CAAC,aAAkC,EAAE,QAA6B;IACnG,OAAO,QAAQ,KAAK,IAAI,IAAI,aAAa,CAAC,YAAY,CAAC,CAAC,CAAC,aAAa,CAAC,YAAY,CAAC,CAAC,CAAC,aAAa,CAAC,KAAK,CAAA;AAC1G,CAAC;AAED;;;GAGG;AACH,MAAM,CAAC,MAAM,YAAY,GAAgB;IACxC,IAAI,EAAE,QAAQ;IACd,WAAW,EAAE,wGAAwG;IACrH,IAAI,EAAE,UAAU;IAChB,OAAO,EAAE;QACR,EAAE,IAAI,EAAE,gBAAgB,EAAE,WAAW,EAAE,mDAAmD,EAAE;QAC5F,EAAE,IAAI,EAAE,qBAAqB,EAAE,WAAW,EAAE,oDAAoD,EAAE;QAClG;YACC,IAAI,EAAE,wBAAwB;YAC9B,WAAW,EACV,uLAAuL;SACxL;QACD;YACC,IAAI,EAAE,oDAAoD;YAC1D,WAAW,EACV,qUAAqU;SACtU;KACD;IACD,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,kGAAkG;QAClG,0FAA0F;QAC1F,MAAM,MAAM,GAAG,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACxC,MAAM,OAAO,GAAG,CAAC,IAAI,CAAC,OAAO,IAAI,IAAI,CAAC,CAAC,WAAW,EAAE,CAAA;QACpD,MAAM,aAAa,GAAG,eAAe,CAAC,OAAO,CAAC,CAAA;QAE9C,IAAI,CAAC,aAAa,EAAE,CAAC;YACpB,MAAM,IAAI,KAAK,CACd,0CAA0C,OAAO,YAAY,MAAM,CAAC,IAAI,CAAC,eAAe,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,CACvG,CAAA;QACF,CAAC;QAED,MAAM,YAAY,GAAG,IAAI,CAAC,YAAY,IAAI,GAAG,CAAA;QAE7C,IAAI,CAAC,CAAC,YAAY,IAAI,CAAC,IAAI,YAAY,IAAI,CAAC,CAAC,EAAE,CAAC;YAC/C,MAAM,IAAI,KAAK,CAAC,0CAA0C,YAAY,EAAE,CAAC,CAAA;QAC1E,CAAC;QAED,kGAAkG;QAClG,qGAAqG;QACrG,MAAM,eAAe,GAAG,IAAI,CAAC,eAAe,IAAI,CAAC,CAAA;QAEjD,IAAI,CAAC,CAAC,eAAe,IAAI,CAAC,IAAI,eAAe,IAAI,CAAC,CAAC,EAAE,CAAC;YACrD,MAAM,IAAI,KAAK,CAAC,6CAA6C,eAAe,EAAE,CAAC,CAAA;QAChF,CAAC;QAED,MAAM,MAAM,GAAG,IAAI,CAAC,UAAU,IAAI,aAAa,CAAC,MAAM,CAAA;QACtD,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,IAAI,IAAI,CAAA;QAChC,uGAAuG;QACvG,2GAA2G;QAC3G,0GAA0G;QAC1G,2FAA2F;QAC3F,MAAM,0BAA0B,GAAG,IAAI,CAAC,kBAAkB,CAAA;QAC1D,MAAM,KAAK,GAAG,kBAAkB,CAAC,aAAa,EAAE,0BAA0B,CAAC,CAAA;QAE3E,MAAM,IAAI,GAAsB,EAAE,CAAA;QAElC,KAAK,IAAI,EAAE,GAAG,CAAC,EAAE,EAAE,GAAG,KAAK,CAAC,MAAM,EAAE,EAAE,EAAE,EAAE,CAAC;YAC1C,kGAAkG;YAClG,yDAAyD;YACzD,MAAM,YAAY,GAAG,cAAc,CAAC,CAAC,IAAI,CAAC,IAAI,GAAG,CAAC,aAAa,GAAG,CAAC,EAAE,GAAG,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAA;YACnF,MAAM,aAAa,GAAG,+BAA+B,CAAC,KAAK,CAAC,EAAE,CAAE,EAAE,0BAA0B,CAAC,CAAA;YAC7F,MAAM,CAAC,GAAG,MAAM,UAAU,CAAC,aAAa,EAAE,YAAY,CAAC,CAAA;YAEvD,KAAK,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC;gBACnB,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;YACb,CAAC,CAAC,kEAAkE;QACrE,CAAC;QAED,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,CAAC;YAClB,MAAM,IAAI,KAAK,CAAC,MAAM,OAAO,yEAAyE,CAAC,CAAA;QACxG,CAAC;QAED,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,KAAK,GAAG,CAAC,CAAA;QACb,MAAM,CAAC,GAAG,IAAI,CAAC,MAAM,CAAA;QAErB,OAAO,OAAO,GAAG,KAAK,IAAI,KAAK,EAAE,GAAG,KAAK,GAAG,CAAC,EAAE,CAAC;YAC/C,MAAM,IAAI,GAAG,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,CAAE,CAAA;YAC5C,MAAM,KAAK,GAAG,MAAM,EAAE,GAAG,YAAY,CAAC,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,QAAQ,CAAA;YAElE,6FAA6F;YAC7F,6DAA6D;YAC7D,MAAM,eAAe,GACpB,OAAO,KAAK,IAAI,CAAC,CAAC,CAAC,CAAC,MAAM,EAAE,GAAG,sBAAsB,CAAC,CAAC,CAAE,OAAiB,CAAC,CAAC,CAAE,UAAoB,CAAC,CAAC,CAAC,CAAC,SAAS,CAAA;YAEhH,MAAM,aAAa,GAClB,OAAO,KAAK,IAAI;gBACf,CAAC,CAAC,MAAM,EAAE,GAAG,0BAA0B;oBACtC,CAAC,CAAE,WAAqB;oBACxB,CAAC,CAAE,cAAwB;gBAC5B,CAAC,CAAC,SAAS,CAAA;YAEb,MAAM,KAAK,GAAG,mBAAmB,CAAC,IAAI,EAAE,OAAO,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE,eAAe,EAAE,aAAa,EAAE,CAAC,CAAA;YAEnG,IAAI,CAAC,KAAK,EAAE,CAAC;gBACZ,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,kBAAkB,CAAC,KAAK,EAAE,OAAO,EAAE,eAAe,EAAE,MAAM,CAAC,CAAA;YAE3D,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC;gBACjB,8FAA8F;gBAC9F,gGAAgG;gBAChG,MAAM,eAAe,GAAG;oBACvB,GAAG,EAAE,KAAK,CAAC,GAAG;oBACd,UAAU,EAAE,KAAK,CAAC,UAAU;oBAC5B,OAAO;oBACP,MAAM,EAAE,KAAK,CAAC,MAAM;oBACpB,MAAM;oBACN,SAAS,EAAE,oBAAoB;iBAC/B,CAAA;gBAED,MAAM,aAAa,GAAG,QAAQ,CAAC,eAAiD,CAAC,CAAA;gBAEjF,IAAI,aAAa,CAAC,IAAI,KAAK,SAAS,IAAI,CAAC,aAAa,CAAC,GAAG,EAAE,CAAC;oBAC5D,OAAO,EAAE,CAAA;oBAET,SAAQ;gBACT,CAAC;gBAED,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,GAAG,EAAE,KAAK,CAAC,GAAG,EAAE,UAAU,EAAE,KAAK,CAAC,UAAU,EAAE,OAAO,EAAE,KAAK,EAAE,CAAC,GAAG,IAAI,CAAC,CAAA;gBAE9F,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,MAAM,QAAQ,GAAG,cAAc,CAAC,MAAM,EAAE;gBACvC,MAAM,EAAE,KAAK,CAAC,UAAU,CAAC,MAAM;gBAC/B,YAAY,EAAE,KAAK,CAAC,UAAU,CAAC,YAAY;gBAC3C,QAAQ,EAAE,KAAK,CAAC,UAAU,CAAC,QAAQ;gBACnC,QAAQ,EAAE,KAAK,CAAC,UAAU,CAAC,QAAQ;aACnC,CAAC,CAAA;YAEF,MAAM,SAAS,GAAG;gBACjB,GAAG,EAAE,KAAK,CAAC,GAAG;gBACd,UAAU,EAAE,KAAK,CAAC,UAAU;gBAC5B,OAAO;gBACP,MAAM,EAAE,KAAK,CAAC,MAAM;gBACpB,MAAM;gBACN,SAAS,EAAE,QAAQ;gBACnB,cAAc,EAAE,aAAa,CAAC,aAAa;gBAC3C,OAAO,EAAE,iBAAiB,OAAO,qBAAqB,KAAK,6BAA6B;aACxF,CAAA;YAED,MAAM,OAAO,GAAG,QAAQ,CAAC,SAA2C,CAAC,CAAA;YAErE,IAAI,OAAO,CAAC,IAAI,KAAK,SAAS,IAAI,CAAC,OAAO,CAAC,GAAG,EAAE,CAAC;gBAChD,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,KAAK,CAAC,IAAI,CAAC,SAAS,CAAC,EAAE,GAAG,OAAO,CAAC,GAAG,EAAE,YAAY,EAAE,MAAM,EAAE,WAAW,EAAE,KAAK,EAAE,aAAa,EAAE,IAAI,EAAE,CAAC,GAAG,IAAI,CAAC,CAAA;YAE/G,OAAO,EAAE,CAAA;QACV,CAAC;QAED,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;IAC5B,CAAC;CACD,CAAA"}
|
|
@@ -18,5 +18,9 @@
|
|
|
18
18
|
* keep polarity balanced (the v1.9.9 lesson).
|
|
19
19
|
*/
|
|
20
20
|
import { type ShardRecipe } from "./scaffold.ts";
|
|
21
|
+
/**
|
|
22
|
+
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
23
|
+
* and `description` below for the surface form it generates.
|
|
24
|
+
*/
|
|
21
25
|
export declare const nlPostcodeRecipe: ShardRecipe;
|
|
22
26
|
//# sourceMappingURL=nl-postcode.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"nl-postcode.d.ts","sourceRoot":"","sources":["../../../src/shard-recipes/nl-postcode.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;GAkBG;AAEH,OAAO,EAA6C,KAAK,WAAW,EAAiB,MAAM,eAAe,CAAA;
|
|
1
|
+
{"version":3,"file":"nl-postcode.d.ts","sourceRoot":"","sources":["../../../src/shard-recipes/nl-postcode.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;GAkBG;AAEH,OAAO,EAA6C,KAAK,WAAW,EAAiB,MAAM,eAAe,CAAA;AAS1G;;;GAGG;AACH,eAAO,MAAM,gBAAgB,EAAE,WAiF9B,CAAA"}
|
|
@@ -18,10 +18,16 @@
|
|
|
18
18
|
* keep polarity balanced (the v1.9.9 lesson).
|
|
19
19
|
*/
|
|
20
20
|
import { alignAndWrite, makeMulberry32, readTuples, shardSourceID } from "./scaffold.js";
|
|
21
|
-
/**
|
|
21
|
+
/**
|
|
22
|
+
* "1012LG" → "1012 LG". The tuples carry the unspaced OA form; the spaced form is the failing case.
|
|
23
|
+
*/
|
|
22
24
|
function spacePostcode(pc) {
|
|
23
25
|
return pc.replace(/^(\d{4})([A-Z]{2})$/, "$1 $2");
|
|
24
26
|
}
|
|
27
|
+
/**
|
|
28
|
+
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
29
|
+
* and `description` below for the surface form it generates.
|
|
30
|
+
*/
|
|
25
31
|
export const nlPostcodeRecipe = {
|
|
26
32
|
name: "nl-postcode",
|
|
27
33
|
description: "NL full-form postcode (#924): teach '\\d{4} [A-Z]{2}' = postcode, not house#+street — spaced + unspaced, 3 orders",
|
|
@@ -39,7 +45,7 @@ export const nlPostcodeRecipe = {
|
|
|
39
45
|
const rawPostcode = String(t.postcode ?? "")
|
|
40
46
|
.trim()
|
|
41
47
|
.toUpperCase()
|
|
42
|
-
.
|
|
48
|
+
.replaceAll(/\s+/g, "");
|
|
43
49
|
if (!street || !city || !number || !/^\d{4}[A-Z]{2}$/.test(rawPostcode)) {
|
|
44
50
|
skipped++;
|
|
45
51
|
continue;
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"nl-postcode.js","sourceRoot":"","sources":["../../../src/shard-recipes/nl-postcode.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;GAkBG;AAEH,OAAO,EAAE,aAAa,EAAE,cAAc,EAAE,UAAU,EAAoB,aAAa,EAAE,MAAM,eAAe,CAAA;AAE1G
|
|
1
|
+
{"version":3,"file":"nl-postcode.js","sourceRoot":"","sources":["../../../src/shard-recipes/nl-postcode.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;GAkBG;AAEH,OAAO,EAAE,aAAa,EAAE,cAAc,EAAE,UAAU,EAAoB,aAAa,EAAE,MAAM,eAAe,CAAA;AAE1G;;GAEG;AACH,SAAS,aAAa,CAAC,EAAU;IAChC,OAAO,EAAE,CAAC,OAAO,CAAC,qBAAqB,EAAE,OAAO,CAAC,CAAA;AAClD,CAAC;AAED;;;GAGG;AACH,MAAM,CAAC,MAAM,gBAAgB,GAAgB;IAC5C,IAAI,EAAE,aAAa;IACnB,WAAW,EACV,mHAAmH;IACpH,IAAI,EAAE,QAAQ;IACd,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACzB,IAAI,IAAI,GAAG,CAAC,CAAA;QACZ,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QAEf,IAAI,KAAK,EAAE,MAAM,CAAC,IAAI,UAAU,CAAC,IAAI,CAAC,KAAM,CAAC,EAAE,CAAC;YAC/C,IAAI,EAAE,CAAA;YACN,MAAM,MAAM,GAAG,MAAM,CAAC,CAAC,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAC5C,MAAM,IAAI,GAAG,MAAM,CAAC,CAAC,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAC5C,MAAM,MAAM,GAAG,MAAM,CAAC,CAAC,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAE5C,MAAM,WAAW,GAAG,MAAM,CAAC,CAAC,CAAC,QAAQ,IAAI,EAAE,CAAC;iBAC1C,IAAI,EAAE;iBACN,WAAW,EAAE;iBACb,UAAU,CAAC,MAAM,EAAE,EAAE,CAAC,CAAA;YAExB,IAAI,CAAC,MAAM,IAAI,CAAC,IAAI,IAAI,CAAC,MAAM,IAAI,CAAC,iBAAiB,CAAC,IAAI,CAAC,WAAW,CAAC,EAAE,CAAC;gBACzE,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,4FAA4F;YAC5F,sFAAsF;YACtF,MAAM,MAAM,GAAG,IAAI,GAAG,CAAC,KAAK,CAAC,CAAA;YAC7B,MAAM,QAAQ,GAAG,MAAM,CAAC,CAAC,CAAC,aAAa,CAAC,WAAW,CAAC,CAAC,CAAC,CAAC,WAAW,CAAA;YAElE,yFAAyF;YACzF,sFAAsF;YACtF,MAAM,KAAK,GAAG,IAAI,GAAG,CAAC,CAAA;YACtB,IAAI,GAAW,CAAA;YAEf,IAAI,KAAK,KAAK,CAAC,EAAE,CAAC;gBACjB,GAAG,GAAG,GAAG,MAAM,IAAI,MAAM,KAAK,QAAQ,IAAI,IAAI,EAAE,CAAA;YACjD,CAAC;iBAAM,IAAI,KAAK,KAAK,CAAC,EAAE,CAAC;gBACxB,GAAG,GAAG,GAAG,QAAQ,IAAI,IAAI,KAAK,MAAM,IAAI,MAAM,EAAE,CAAA;YACjD,CAAC;iBAAM,CAAC;gBACP,GAAG,GAAG,GAAG,IAAI,KAAK,QAAQ,KAAK,MAAM,IAAI,MAAM,EAAE,CAAA;YAClD,CAAC;YAED,MAAM,UAAU,GAA2B;gBAC1C,MAAM;gBACN,YAAY,EAAE,MAAM;gBACpB,QAAQ;gBACR,QAAQ,EAAE,IAAI;aACd,CAAA;YAED,MAAM,SAAS,GAAG,aAAa,CAAC,mBAAmB,EAAE;gBACpD,GAAG,UAAU;gBACb,CAAC,EAAE,MAAM,CAAC,KAAK,CAAC;gBAChB,CAAC,EAAE,MAAM,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,GAAG;gBACrB,CAAC,EAAE,MAAM,CAAC,IAAI,CAAC;aACf,CAAC,CAAA;YAEF,MAAM,SAAS,GAAG;gBACjB,GAAG;gBACH,UAAU;gBACV,OAAO,EAAE,IAAI;gBACb,MAAM,EAAE,OAAO;gBACf,MAAM,EAAE,mBAAmB;gBAC3B,SAAS;gBACT,cAAc,EAAE,QAAQ;gBACxB,OAAO,EACN,4HAA4H;aAC7H,CAAA;YAED,IAAI,aAAa,CAAC,KAAK,EAAE,SAAS,EAAE,aAAa,CAAC,EAAE,CAAC;gBACpD,OAAO,EAAE,CAAA;YACV,CAAC;iBAAM,CAAC;gBACP,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;QAED,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;IAClC,CAAC;CACD,CAAA"}
|
|
@@ -35,5 +35,9 @@
|
|
|
35
35
|
* list. Diacritic-KEEPING normalizer, matching the board (see the norm docstring).
|
|
36
36
|
*/
|
|
37
37
|
import { type ShardRecipe } from "./scaffold.ts";
|
|
38
|
+
/**
|
|
39
|
+
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
40
|
+
* and `description` below for the surface form it generates.
|
|
41
|
+
*/
|
|
38
42
|
export declare const noFragmentRecipe: ShardRecipe;
|
|
39
43
|
//# sourceMappingURL=no-fragment.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"no-fragment.d.ts","sourceRoot":"","sources":["../../../src/shard-recipes/no-fragment.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAmCG;AAIH,OAAO,EAA6C,KAAK,WAAW,EAAiB,MAAM,eAAe,CAAA;
|
|
1
|
+
{"version":3,"file":"no-fragment.d.ts","sourceRoot":"","sources":["../../../src/shard-recipes/no-fragment.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAmCG;AAIH,OAAO,EAA6C,KAAK,WAAW,EAAiB,MAAM,eAAe,CAAA;AAkB1G;;;GAGG;AACH,eAAO,MAAM,gBAAgB,EAAE,WA0J9B,CAAA"}
|
|
@@ -41,12 +41,18 @@ import { alignAndWrite, makeMulberry32, readTuples, shardSourceID } from "./scaf
|
|
|
41
41
|
* collapse whitespace, KEEP diacritics. Stripping them (fr-fragment's norm) would fold `Tømmerlien` -> `tommerlien`,
|
|
42
42
|
* miss the board's reserved `tømmerlien`, and leak the surface.
|
|
43
43
|
*/
|
|
44
|
-
const norm = (value) => value.normalize("NFC").toLowerCase().
|
|
45
|
-
/**
|
|
44
|
+
const norm = (value) => value.normalize("NFC").toLowerCase().replaceAll(/\s+/g, " ").trim();
|
|
45
|
+
/**
|
|
46
|
+
* Title-case a Kartverket ALL-CAPS locality (HELLVIK -> Hellvik); #690, all-caps is OOD.
|
|
47
|
+
*/
|
|
46
48
|
const titleNO = (value) => value
|
|
47
49
|
.split(/\s+/)
|
|
48
50
|
.map((w) => (w ? w[0].toUpperCase() + w.slice(1).toLowerCase() : w))
|
|
49
51
|
.join(" ");
|
|
52
|
+
/**
|
|
53
|
+
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
54
|
+
* and `description` below for the surface form it generates.
|
|
55
|
+
*/
|
|
50
56
|
export const noFragmentRecipe = {
|
|
51
57
|
name: "no-fragment",
|
|
52
58
|
description: "NO street fragments — the house-number-licence lever (Track B): '«st» «n»' / bare «st» with NO postcode partner, + bare-locality & bare-postcode counters",
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"no-fragment.js","sourceRoot":"","sources":["../../../src/shard-recipes/no-fragment.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAmCG;AAEH,OAAO,EAAE,YAAY,EAAE,MAAM,SAAS,CAAA;AAEtC,OAAO,EAAE,aAAa,EAAE,cAAc,EAAE,UAAU,EAAoB,aAAa,EAAE,MAAM,eAAe,CAAA;AAE1G;;;;GAIG;AACH,MAAM,IAAI,GAAG,CAAC,KAAa,EAAU,EAAE,CAAC,KAAK,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,WAAW,EAAE,CAAC,
|
|
1
|
+
{"version":3,"file":"no-fragment.js","sourceRoot":"","sources":["../../../src/shard-recipes/no-fragment.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAmCG;AAEH,OAAO,EAAE,YAAY,EAAE,MAAM,SAAS,CAAA;AAEtC,OAAO,EAAE,aAAa,EAAE,cAAc,EAAE,UAAU,EAAoB,aAAa,EAAE,MAAM,eAAe,CAAA;AAE1G;;;;GAIG;AACH,MAAM,IAAI,GAAG,CAAC,KAAa,EAAU,EAAE,CAAC,KAAK,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,WAAW,EAAE,CAAC,UAAU,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;AAE3G;;GAEG;AACH,MAAM,OAAO,GAAG,CAAC,KAAa,EAAU,EAAE,CACzC,KAAK;KACH,KAAK,CAAC,KAAK,CAAC;KACZ,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAE,CAAC,WAAW,EAAE,GAAG,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,WAAW,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;KACpE,IAAI,CAAC,GAAG,CAAC,CAAA;AAEZ;;;GAGG;AACH,MAAM,CAAC,MAAM,gBAAgB,GAAgB;IAC5C,IAAI,EAAE,aAAa;IACnB,WAAW,EACV,2JAA2J;IAC5J,IAAI,EAAE,QAAQ;IACd,OAAO,EAAE;QACR;YACC,IAAI,EAAE,2BAA2B;YACjC,WAAW,EACV,gHAAgH;SACjH;QACD;YACC,IAAI,EAAE,wBAAwB;YAC9B,WAAW,EAAE,mGAAmG;SAChH;QACD;YACC,IAAI,EAAE,oBAAoB;YAC1B,WAAW,EAAE,iGAAiG;SAC9G;QACD;YACC,IAAI,EAAE,yBAAyB;YAC/B,WAAW,EACV,kMAAkM;SACnM;QACD;YACC,IAAI,EAAE,8BAA8B;YACpC,WAAW,EAAE,+EAA+E;SAC5F;KACD;IACD,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,MAAM,MAAM,GAAG,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACxC,MAAM,WAAW,GAAG,IAAI,CAAC,eAAe,CAAA;QAExC,IAAI,CAAC,WAAW,EAAE,CAAC;YAClB,MAAM,IAAI,KAAK,CACd,uFAAuF;gBACtF,qGAAqG;gBACrG,sFAAsF,CACvF,CAAA;QACF,CAAC;QAED,MAAM,QAAQ,GAAG,IAAI,GAAG,CACvB,YAAY,CAAC,WAAW,EAAE,MAAM,CAAC;aAC/B,KAAK,CAAC,IAAI,CAAC;aACX,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC;aAC1B,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,IAAI,CAAC,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,CAAC,CACjD,CAAA;QAED,IAAI,CAAC,QAAQ,CAAC,IAAI;YAAE,MAAM,IAAI,KAAK,CAAC,oCAAoC,WAAW,sBAAsB,CAAC,CAAA;QAE1G,MAAM,cAAc,GAAG,IAAI,CAAC,QAAQ,IAAI,GAAG,CAAA;QAC3C,MAAM,WAAW,GAAG,IAAI,CAAC,WAAW,IAAI,GAAG,CAAA;QAC3C,MAAM,eAAe,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,eAAe,IAAI,CAAC,CAAC,CAAC,CAAA;QAC1E,MAAM,mBAAmB,GAAG,IAAI,CAAC,mBAAmB,IAAI,CAAC,CAAA;QAEzD,yFAAyF;QACzF,yCAAyC;QACzC,MAAM,UAAU,GAAG,IAAI,GAAG,EAAU,CAAA;QACpC,MAAM,SAAS,GAAG,IAAI,GAAG,EAAU,CAAA;QAEnC,IAAI,IAAI,GAAG,CAAC,CAAA;QACZ,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,YAAY,GAAG,CAAC,CAAA;QACpB,IAAI,OAAO,GAAG,CAAC,CAAA;QAEf,MAAM,IAAI,GAAG,CAAC,GAAW,EAAE,UAAkC,EAAE,KAAa,EAAQ,EAAE;YACrF,wFAAwF;YACxF,kGAAkG;YAClG,MAAM,SAAS,GAAG,aAAa,CAAC,mBAAmB,EAAE,EAAE,GAAG,UAAU,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,GAAG,IAAI,IAAI,OAAO,EAAE,EAAE,EAAE,CAAC,CAAA;YAE5G,MAAM,SAAS,GAAG;gBACjB,GAAG;gBACH,UAAU;gBACV,OAAO,EAAE,IAAI;gBACb,MAAM,EAAE,OAAO;gBACf,MAAM,EAAE,mBAAmB;gBAC3B,SAAS;gBACT,cAAc,EAAE,QAAQ;gBACxB,OAAO,EAAE,8FAA8F;aACvG,CAAA;YAED,IAAI,aAAa,CAAC,KAAK,EAAE,SAAS,EAAE,aAAa,CAAC,EAAE,CAAC;gBACpD,OAAO,EAAE,CAAA;YACV,CAAC;iBAAM,CAAC;gBACP,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC,CAAA;QAED,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,UAAU,CAAC,IAAI,CAAC,KAAM,CAAC,EAAE,CAAC;YACnD,IAAI,EAAE,CAAA;YACN,MAAM,MAAM,GAAG,MAAM,CAAC,KAAK,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAChD,MAAM,QAAQ,GAAG,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAC,CAAA;YAC7D,MAAM,MAAM,GAAG,MAAM,CAAC,KAAK,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAChD,MAAM,QAAQ,GAAG,MAAM,CAAC,KAAK,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAEpD,IAAI,QAAQ,EAAE,CAAC;gBACd,UAAU,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAA;YACzB,CAAC;YAED,IAAI,QAAQ,EAAE,CAAC;gBACd,SAAS,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAA;YACxB,CAAC;YAED,IAAI,CAAC,MAAM,EAAE,CAAC;gBACb,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,iEAAiE;YACjE,IAAI,QAAQ,CAAC,GAAG,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,EAAE,CAAC;gBAChC,YAAY,EAAE,CAAA;gBAEd,SAAQ;YACT,CAAC;YAED,0FAA0F;YAC1F,2FAA2F;YAC3F,0EAA0E;YAC1E,IAAI,MAAM,EAAE,GAAG,WAAW,EAAE,CAAC;gBAC5B,IAAI,MAAM,EAAE,GAAG,GAAG,IAAI,UAAU,CAAC,IAAI,EAAE,CAAC;oBACvC,MAAM,GAAG,GAAG,CAAC,GAAG,UAAU,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,UAAU,CAAC,IAAI,CAAC,CAAE,CAAA;oBAEpE,IAAI,CAAC,GAAG,EAAE,EAAE,QAAQ,EAAE,GAAG,EAAE,EAAE,uBAAuB,CAAC,CAAA;gBACtD,CAAC;qBAAM,IAAI,SAAS,CAAC,IAAI,EAAE,CAAC;oBAC3B,MAAM,EAAE,GAAG,CAAC,GAAG,SAAS,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,SAAS,CAAC,IAAI,CAAC,CAAE,CAAA;oBAEjE,IAAI,CAAC,EAAE,EAAE,EAAE,QAAQ,EAAE,EAAE,EAAE,EAAE,uBAAuB,CAAC,CAAA;gBACpD,CAAC;gBAED,SAAQ;YACT,CAAC;YAED,0FAA0F;YAC1F,8FAA8F;YAC9F,IAAI,CAAC,MAAM,IAAI,MAAM,EAAE,GAAG,cAAc,EAAE,CAAC;gBAC1C,IAAI,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,EAAE,aAAa,CAAC,CAAA;YACxC,CAAC;iBAAM,CAAC;gBACP,MAAM,KAAK,GAAG,MAAM,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,WAAW,CAAA;gBAC7D,0FAA0F;gBAC1F,wFAAwF;gBACxF,2FAA2F;gBAC3F,MAAM,MAAM,GAAG,CAAC,MAAM,CAAC,KAAK,CAAC,KAAK,CAAC,IAAI,EAAE,CAAC,CAAC,MAAM,CAAA;gBACjD,MAAM,MAAM,GAAG,MAAM,IAAI,mBAAmB,CAAC,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,CAAC,CAAA;gBAElE,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;oBACjC,IAAI,CAAC,GAAG,MAAM,IAAI,MAAM,EAAE,EAAE,EAAE,MAAM,EAAE,YAAY,EAAE,MAAM,EAAE,EAAE,KAAK,CAAC,CAAA;gBACrE,CAAC;YACF,CAAC;QACF,CAAC;QAED,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,OAAO,EAAE,YAAY,EAAE,CAAA;IAChD,CAAC;CACD,CAAA"}
|
|
@@ -16,5 +16,9 @@
|
|
|
16
16
|
* 3. pc-first "«pc» «city», «st» «n»" (the 7% floor — the anchor the others converge to)
|
|
17
17
|
*/
|
|
18
18
|
import { type ShardRecipe } from "./scaffold.ts";
|
|
19
|
+
/**
|
|
20
|
+
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
21
|
+
* and `description` below for the surface form it generates.
|
|
22
|
+
*/
|
|
19
23
|
export declare const noStreetLedRecipe: ShardRecipe;
|
|
20
24
|
//# sourceMappingURL=no-street-led.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"no-street-led.d.ts","sourceRoot":"","sources":["../../../src/shard-recipes/no-street-led.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAIH,OAAO,EAA6C,KAAK,WAAW,EAAiB,MAAM,eAAe,CAAA;AAW1G,eAAO,MAAM,iBAAiB,EAAE,
|
|
1
|
+
{"version":3,"file":"no-street-led.d.ts","sourceRoot":"","sources":["../../../src/shard-recipes/no-street-led.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAIH,OAAO,EAA6C,KAAK,WAAW,EAAiB,MAAM,eAAe,CAAA;AAW1G;;;GAGG;AACH,eAAO,MAAM,iBAAiB,EAAE,WAwG/B,CAAA"}
|
|
@@ -24,7 +24,11 @@ import { alignAndWrite, makeMulberry32, readTuples, shardSourceID } from "./scaf
|
|
|
24
24
|
* check would never match the board's reserved `tømmerlien` and the split would leak silently. Diacritic street heads
|
|
25
25
|
* (…vegen/…veien with ø/å/æ) are the whole point of this shard's boundary; folding them away is not an option.
|
|
26
26
|
*/
|
|
27
|
-
const norm = (value) => value.normalize("NFC").toLowerCase().
|
|
27
|
+
const norm = (value) => value.normalize("NFC").toLowerCase().replaceAll(/\s+/g, " ").trim();
|
|
28
|
+
/**
|
|
29
|
+
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
30
|
+
* and `description` below for the surface form it generates.
|
|
31
|
+
*/
|
|
28
32
|
export const noStreetLedRecipe = {
|
|
29
33
|
name: "no-street-led",
|
|
30
34
|
description: "NO street-led boundary form (#901 family): '«st» «n», «pc» «city»' — diacritic street heads",
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"no-street-led.js","sourceRoot":"","sources":["../../../src/shard-recipes/no-street-led.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAEH,OAAO,EAAE,YAAY,EAAE,MAAM,SAAS,CAAA;AAEtC,OAAO,EAAE,aAAa,EAAE,cAAc,EAAE,UAAU,EAAoB,aAAa,EAAE,MAAM,eAAe,CAAA;AAE1G;;;;;;GAMG;AACH,MAAM,IAAI,GAAG,CAAC,KAAa,EAAU,EAAE,CAAC,KAAK,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,WAAW,EAAE,CAAC,
|
|
1
|
+
{"version":3,"file":"no-street-led.js","sourceRoot":"","sources":["../../../src/shard-recipes/no-street-led.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAEH,OAAO,EAAE,YAAY,EAAE,MAAM,SAAS,CAAA;AAEtC,OAAO,EAAE,aAAa,EAAE,cAAc,EAAE,UAAU,EAAoB,aAAa,EAAE,MAAM,eAAe,CAAA;AAE1G;;;;;;GAMG;AACH,MAAM,IAAI,GAAG,CAAC,KAAa,EAAU,EAAE,CAAC,KAAK,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,WAAW,EAAE,CAAC,UAAU,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;AAE3G;;;GAGG;AACH,MAAM,CAAC,MAAM,iBAAiB,GAAgB;IAC7C,IAAI,EAAE,eAAe;IACrB,WAAW,EAAE,6FAA6F;IAC1G,IAAI,EAAE,QAAQ;IACd,OAAO,EAAE;QACR;YACC,IAAI,EAAE,2BAA2B;YACjC,WAAW,EACV,uDAAuD;gBACvD,2FAA2F;SAC5F;KACD;IACD,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QAEzB,2FAA2F;QAC3F,yFAAyF;QACzF,6FAA6F;QAC7F,yFAAyF;QACzF,MAAM,WAAW,GAAG,IAAI,CAAC,eAAe,CAAA;QAExC,IAAI,CAAC,WAAW,EAAE,CAAC;YAClB,MAAM,IAAI,KAAK,CACd,yFAAyF;gBACxF,qGAAqG;gBACrG,sFAAsF,CACvF,CAAA;QACF,CAAC;QAED,MAAM,QAAQ,GAAG,IAAI,GAAG,CACvB,YAAY,CAAC,WAAW,EAAE,MAAM,CAAC;aAC/B,KAAK,CAAC,IAAI,CAAC;aACX,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,IAAI,EAAE,CAAC;aAC1B,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,IAAI,CAAC,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,CAAC,CACjD,CAAA;QAED,IAAI,CAAC,QAAQ,CAAC,IAAI;YAAE,MAAM,IAAI,KAAK,CAAC,sCAAsC,WAAW,sBAAsB,CAAC,CAAA;QAE5G,IAAI,IAAI,GAAG,CAAC,CAAA;QACZ,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,YAAY,GAAG,CAAC,CAAA;QAEpB,IAAI,KAAK,EAAE,MAAM,CAAC,IAAI,UAAU,CAAC,IAAI,CAAC,KAAM,CAAC,EAAE,CAAC;YAC/C,IAAI,EAAE,CAAA;YACN,MAAM,MAAM,GAAG,MAAM,CAAC,CAAC,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAC5C,MAAM,IAAI,GAAG,MAAM,CAAC,CAAC,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAC5C,MAAM,MAAM,GAAG,MAAM,CAAC,CAAC,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAC5C,MAAM,QAAQ,GAAG,MAAM,CAAC,CAAC,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YAEhD,IAAI,CAAC,MAAM,IAAI,CAAC,IAAI,IAAI,CAAC,MAAM,IAAI,CAAC,QAAQ,EAAE,CAAC;gBAC9C,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,sDAAsD;YACtD,IAAI,QAAQ,CAAC,GAAG,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,EAAE,CAAC;gBAChC,YAAY,EAAE,CAAA;gBAEd,SAAQ;YACT,CAAC;YAED,MAAM,KAAK,GAAG,IAAI,GAAG,CAAC,CAAA;YACtB,IAAI,GAAW,CAAA;YAEf,MAAM,UAAU,GAA2B;gBAC1C,MAAM;gBACN,YAAY,EAAE,MAAM;gBACpB,QAAQ;gBACR,QAAQ,EAAE,IAAI;aACd,CAAA;YAED,IAAI,KAAK,KAAK,CAAC,EAAE,CAAC;gBACjB,GAAG,GAAG,GAAG,MAAM,IAAI,MAAM,KAAK,QAAQ,IAAI,IAAI,EAAE,CAAA;YACjD,CAAC;iBAAM,IAAI,KAAK,KAAK,CAAC,EAAE,CAAC;gBACxB,GAAG,GAAG,GAAG,IAAI,KAAK,QAAQ,KAAK,MAAM,IAAI,MAAM,EAAE,CAAA;YAClD,CAAC;iBAAM,CAAC;gBACP,GAAG,GAAG,GAAG,QAAQ,IAAI,IAAI,KAAK,MAAM,IAAI,MAAM,EAAE,CAAA;YACjD,CAAC;YAED,MAAM,SAAS,GAAG,aAAa,CAAC,qBAAqB,EAAE,EAAE,GAAG,UAAU,EAAE,CAAC,EAAE,MAAM,CAAC,KAAK,CAAC,EAAE,CAAC,EAAE,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC,CAAA;YAE5G,MAAM,SAAS,GAAG;gBACjB,GAAG;gBACH,UAAU;gBACV,OAAO,EAAE,IAAI;gBACb,MAAM,EAAE,OAAO;gBACf,MAAM,EAAE,qBAAqB;gBAC7B,SAAS;gBACT,cAAc,EAAE,QAAQ;gBACxB,OAAO,EACN,8HAA8H;aAC/H,CAAA;YAED,IAAI,aAAa,CAAC,KAAK,EAAE,SAAS,EAAE,eAAe,CAAC,EAAE,CAAC;gBACtD,OAAO,EAAE,CAAA;YACV,CAAC;iBAAM,CAAC;gBACP,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;QAED,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,OAAO,EAAE,YAAY,EAAE,CAAA;IAChD,CAAC;CACD,CAAA"}
|
|
@@ -10,5 +10,9 @@
|
|
|
10
10
|
* scripts/build-no-street-shard.mjs.
|
|
11
11
|
*/
|
|
12
12
|
import { type ShardRecipe } from "./scaffold.ts";
|
|
13
|
+
/**
|
|
14
|
+
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
15
|
+
* and `description` below for the surface form it generates.
|
|
16
|
+
*/
|
|
13
17
|
export declare const noStreetRecipe: ShardRecipe;
|
|
14
18
|
//# sourceMappingURL=no-street.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"no-street.d.ts","sourceRoot":"","sources":["../../../src/shard-recipes/no-street.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;GAUG;AAGH,OAAO,EAAqD,KAAK,WAAW,EAAE,MAAM,eAAe,CAAA;AAInG,eAAO,MAAM,cAAc,EAAE,
|
|
1
|
+
{"version":3,"file":"no-street.d.ts","sourceRoot":"","sources":["../../../src/shard-recipes/no-street.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;GAUG;AAGH,OAAO,EAAqD,KAAK,WAAW,EAAE,MAAM,eAAe,CAAA;AAInG;;;GAGG;AACH,eAAO,MAAM,cAAc,EAAE,WA+D5B,CAAA"}
|
|
@@ -12,6 +12,10 @@
|
|
|
12
12
|
import { synthesizeNoStreetRow } from "../synthesize-no-street.js";
|
|
13
13
|
import { alignAndWrite, makeLcg, readTuples, shardSourceID } from "./scaffold.js";
|
|
14
14
|
const LICENSE = "Synthetic — derived from CC-BY / public-domain input tuples";
|
|
15
|
+
/**
|
|
16
|
+
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
17
|
+
* and `description` below for the surface form it generates.
|
|
18
|
+
*/
|
|
15
19
|
export const noStreetRecipe = {
|
|
16
20
|
name: "no-street",
|
|
17
21
|
description: "No-street counter-example rows: tuples → synthesizeNoStreetRow → aligned LabeledRow",
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"no-street.js","sourceRoot":"","sources":["../../../src/shard-recipes/no-street.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;GAUG;AAEH,OAAO,EAAE,qBAAqB,EAA0B,MAAM,4BAA4B,CAAA;AAC1F,OAAO,EAAE,aAAa,EAAE,OAAO,EAAE,UAAU,EAAE,aAAa,EAAoB,MAAM,eAAe,CAAA;AAEnG,MAAM,OAAO,GAAG,6DAA6D,CAAA;AAE7E,MAAM,CAAC,MAAM,cAAc,GAAgB;IAC1C,IAAI,EAAE,WAAW;IACjB,WAAW,EAAE,qFAAqF;IAClG,IAAI,EAAE,QAAQ;IACd,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,IAAI,CAAC,IAAI,CAAC,KAAK;YAAE,MAAM,IAAI,KAAK,CAAC,kDAAkD,CAAC,CAAA;QACpF,wFAAwF;QACxF,MAAM,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACjC,MAAM,MAAM,GAAG,IAAI,CAAC,UAAU,IAAI,iBAAiB,CAAA;QACnD,IAAI,IAAI,GAAG,CAAC,CAAA;QACZ,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QAEf,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,UAAU,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;YAClD,IAAI,EAAE,CAAA;YAEN,IAAI,CAAC,KAAK,CAAC,QAAQ,IAAI,CAAC,KAAK,CAAC,MAAM,IAAI,CAAC,KAAK,CAAC,QAAQ,IAAI,CAAC,KAAK,CAAC,OAAO,EAAE,CAAC;gBAC3E,OAAO,EAAE,CAAA;
|
|
1
|
+
{"version":3,"file":"no-street.js","sourceRoot":"","sources":["../../../src/shard-recipes/no-street.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;GAUG;AAEH,OAAO,EAAE,qBAAqB,EAA0B,MAAM,4BAA4B,CAAA;AAC1F,OAAO,EAAE,aAAa,EAAE,OAAO,EAAE,UAAU,EAAE,aAAa,EAAoB,MAAM,eAAe,CAAA;AAEnG,MAAM,OAAO,GAAG,6DAA6D,CAAA;AAE7E;;;GAGG;AACH,MAAM,CAAC,MAAM,cAAc,GAAgB;IAC1C,IAAI,EAAE,WAAW;IACjB,WAAW,EAAE,qFAAqF;IAClG,IAAI,EAAE,QAAQ;IACd,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,IAAI,CAAC,IAAI,CAAC,KAAK;YAAE,MAAM,IAAI,KAAK,CAAC,kDAAkD,CAAC,CAAA;QACpF,wFAAwF;QACxF,MAAM,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACjC,MAAM,MAAM,GAAG,IAAI,CAAC,UAAU,IAAI,iBAAiB,CAAA;QACnD,IAAI,IAAI,GAAG,CAAC,CAAA;QACZ,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QAEf,IAAI,KAAK,EAAE,MAAM,KAAK,IAAI,UAAU,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;YAClD,IAAI,EAAE,CAAA;YAEN,IAAI,CAAC,KAAK,CAAC,QAAQ,IAAI,CAAC,KAAK,CAAC,MAAM,IAAI,CAAC,KAAK,CAAC,QAAQ,IAAI,CAAC,KAAK,CAAC,OAAO,EAAE,CAAC;gBAC3E,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,QAAQ,EAAE,CAAC,EAAE,EAAE,CAAC;gBACxC,MAAM,KAAK,GAAG,qBAAqB,CAAC,KAA0B,EAAE,EAAE,MAAM,EAAE,CAAC,CAAA;gBAE3E,IAAI,CAAC,KAAK,EAAE,CAAC;oBACZ,OAAO,EAAE,CAAA;oBAET,SAAQ;gBACT,CAAC;gBAED,MAAM,EAAE,GAAG,aAAa,CACvB,KAAK,EACL;oBACC,GAAG,EAAE,KAAK,CAAC,GAAG;oBACd,UAAU,EAAE,KAAK,CAAC,UAAU;oBAC5B,OAAO,EAAE,KAAK,CAAC,OAAO;oBACtB,MAAM,EAAE,KAAK,CAAC,MAAM;oBACpB,MAAM;oBACN,SAAS,EAAE,aAAa,CAAC,MAAM,EAAE;wBAChC,QAAQ,EAAE,KAAK,CAAC,QAAQ;wBACxB,MAAM,EAAE,KAAK,CAAC,MAAM;wBACpB,QAAQ,EAAE,KAAK,CAAC,QAAQ;wBACxB,OAAO,EAAE,KAAK,CAAC,OAAO;wBACtB,QAAQ,EAAE,KAAK,CAAC,QAAQ;wBACxB,CAAC,EAAE,MAAM,CAAC,CAAC,CAAC;qBACZ,CAAC;oBACF,cAAc,EAAE,OAAO;oBACvB,OAAO,EAAE,OAAO;iBAChB,EACD,KAAK,CAAC,QAAQ,CACd,CAAA;gBAED,IAAI,EAAE,EAAE,CAAC;oBACR,OAAO,EAAE,CAAA;gBACV,CAAC;qBAAM,CAAC;oBACP,OAAO,EAAE,CAAA;gBACV,CAAC;YACF,CAAC;QACF,CAAC;QAED,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;IAClC,CAAC;CACD,CAAA"}
|
|
@@ -30,5 +30,9 @@
|
|
|
30
30
|
* reproduces the legacy run byte-for-byte.
|
|
31
31
|
*/
|
|
32
32
|
import { type ShardRecipe } from "./scaffold.ts";
|
|
33
|
+
/**
|
|
34
|
+
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
35
|
+
* and `description` below for the surface form it generates.
|
|
36
|
+
*/
|
|
33
37
|
export declare const poBoxCedexRecipe: ShardRecipe;
|
|
34
38
|
//# sourceMappingURL=po-box-cedex.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"po-box-cedex.d.ts","sourceRoot":"","sources":["../../../src/shard-recipes/po-box-cedex.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8BG;AAiBH,OAAO,EAAyD,KAAK,WAAW,EAAE,MAAM,eAAe,CAAA;
|
|
1
|
+
{"version":3,"file":"po-box-cedex.d.ts","sourceRoot":"","sources":["../../../src/shard-recipes/po-box-cedex.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8BG;AAiBH,OAAO,EAAyD,KAAK,WAAW,EAAE,MAAM,eAAe,CAAA;AA4tBvG;;;GAGG;AACH,eAAO,MAAM,gBAAgB,EAAE,WAyK9B,CAAA"}
|
|
@@ -42,6 +42,11 @@ import { makeMulberry32, shardSourceID } from "./scaffold.js";
|
|
|
42
42
|
// Same OA cache as the unit/affix shards. US train = every NON-Vermont state; US eval = Vermont (the
|
|
43
43
|
// corpus defaultHoldout). FR comes from the BAN-derived countrywide extract (stride-sampled — the
|
|
44
44
|
// file is 2.5 GB and insee-ordered, so a head-only read would be all département 01).
|
|
45
|
+
/* oxlint-disable sister-software/no-unnamed-threshold -- the bare decimals below are weighted-sampler
|
|
46
|
+
cutoffs, not thresholds: `const r = random()` followed by a cascade of `r < 0.4` branches IS the
|
|
47
|
+
output distribution, and reading the cascade top-to-bottom is how you see it. Naming each cutoff
|
|
48
|
+
would hide the distribution behind a wall of identifiers. Genuine thresholds in these files are
|
|
49
|
+
extracted as named constants above. */
|
|
45
50
|
const US_TRAIN_SOURCES = [
|
|
46
51
|
{ zip: "/tmp/oa-cache/us__ca__berkeley.zip", csv: "us/ca/berkeley.csv", region: "CA" },
|
|
47
52
|
{ zip: "/tmp/oa-cache/us__ca__marin.zip", csv: "us/ca/marin.csv", region: "CA" },
|
|
@@ -56,41 +61,74 @@ const FR_SOURCE = { zip: "/tmp/oa-cache/fr__countrywide.zip", csv: "fr/countrywi
|
|
|
56
61
|
const GEONAMES_CA = "/tmp/geonames-cache/CA.zip";
|
|
57
62
|
const GEONAMES_POSTAL_AU = { zip: "/tmp/geonames-cache/AU-postal.zip", txt: "AU.txt" };
|
|
58
63
|
const GEONAMES_POSTAL_NZ = { zip: "/tmp/geonames-cache/NZ-postal.zip", txt: "NZ.txt" };
|
|
59
|
-
|
|
64
|
+
/**
|
|
65
|
+
* ── Surface vocabulary (codex + corpus templates — see the header) ──────────────────────────────.
|
|
66
|
+
*/
|
|
60
67
|
const T = Object.fromEntries(PO_BOX_LOCALE_TEMPLATES.map((t) => [t.locale, t]));
|
|
61
68
|
// US: the corpus en-US leaders carry the common mass; the codex-only USPS Pub-28 designators
|
|
62
69
|
// (Caller/Drawer/Lockbox — firm-holdout and rural forms) ride at low weight. "Box" is in both.
|
|
63
|
-
|
|
64
|
-
|
|
70
|
+
/**
|
|
71
|
+
* PO Box, P.O. Box, P.O.Box, PO BOX, POB, Post Office Box, Box.
|
|
72
|
+
*/
|
|
73
|
+
const US_LEADERS_COMMON = T["en-US"].leaders;
|
|
74
|
+
/**
|
|
75
|
+
* Codex US_PO_BOX_DESIGNATORS tail.
|
|
76
|
+
*/
|
|
77
|
+
const US_LEADERS_RARE = ["Caller", "Firm Caller", "Drawer", "Lockbox"];
|
|
65
78
|
// "#" EXCLUDED (v4.4.0 probe finding): bare "#N" is a secondary-unit designator per USPS Pub 28 and
|
|
66
79
|
// the shipped unit lever labels it `unit` — the corpus template's po_box reading CONTRADICTS a
|
|
67
80
|
// shipped convention. PMB stays — a genuine commercial-mail-receiving designator, no unit collision.
|
|
68
|
-
|
|
69
|
-
|
|
70
|
-
|
|
71
|
-
const
|
|
72
|
-
|
|
73
|
-
|
|
74
|
-
|
|
81
|
+
/**
|
|
82
|
+
* PMB.
|
|
83
|
+
*/
|
|
84
|
+
const US_PMB_LEADERS = T["en-US"].pmb.filter((l) => l !== "#");
|
|
85
|
+
/**
|
|
86
|
+
* BP, B.P., Boîte Postale, BP.
|
|
87
|
+
*/
|
|
88
|
+
const FR_LEADERS = T["fr-FR"].leaders;
|
|
89
|
+
/**
|
|
90
|
+
* CP, C.P., Case Postale, BP, B.P.
|
|
91
|
+
*/
|
|
92
|
+
const CA_FR_LEADERS = T["fr-CA"].leaders;
|
|
93
|
+
/**
|
|
94
|
+
* PO Box, P.O. Box, POB, Post Office Box.
|
|
95
|
+
*/
|
|
96
|
+
const CA_EN_LEADERS = T["en-CA"].leaders;
|
|
97
|
+
/**
|
|
98
|
+
* AU (#517): codex/au is the vocabulary truth. Current designators (live auspost.com.au pages) at full weight; the
|
|
99
|
+
* AMAS-legacy rural/community tail rides at the same 10% rare-dial as the US Caller/Drawer tail. Every emitted phrase
|
|
100
|
+
* must round-trip the codex matcher (makeAuNzPoBoxPhrase).
|
|
101
|
+
*/
|
|
75
102
|
const AU_LEADERS_CURRENT = ["PO Box", "P.O. Box", "Post Office Box", "GPO Box", "Locked Bag", "Private Bag"];
|
|
76
|
-
|
|
77
|
-
|
|
78
|
-
|
|
79
|
-
|
|
103
|
+
/**
|
|
104
|
+
* Codex legacy: true (recognize-only forms)
|
|
105
|
+
*/
|
|
106
|
+
const AU_LEADERS_LEGACY = ["RMB", "RSD", "CMB"];
|
|
107
|
+
/**
|
|
108
|
+
* NZ (#517): the ADV358 box/bag types that carry an identifier. CMB rides rare (its "CMB B99" identifier shape is
|
|
109
|
+
* alpha-led, covered by makeAuNzPoBoxPhrase). Counter Delivery / Poste Restante are identifier-less counter services —
|
|
110
|
+
* no number to learn, excluded from synthesis.
|
|
111
|
+
*/
|
|
80
112
|
const NZ_LEADERS_COMMON = ["PO Box", "Private Bag"];
|
|
81
113
|
const NZ_LEADERS_RARE = ["CMB"];
|
|
82
|
-
|
|
83
|
-
|
|
84
|
-
|
|
114
|
+
/**
|
|
115
|
+
* Canadian postcode synthesis: valid first letters per province from the codex FSA prior, interior letters per the
|
|
116
|
+
* codex pattern (excludes the visually ambiguous D F I O Q U). The LDU digits are random — the SHAPE is the training
|
|
117
|
+
* signal, not the (unknowable) live assignment.
|
|
118
|
+
*/
|
|
85
119
|
const QC_FSA_LETTERS = Object.entries(FSA_LETTER_TO_PROVINCE)
|
|
86
120
|
.filter(([, p]) => p === "QC")
|
|
87
|
-
.map(([l]) => l);
|
|
121
|
+
.map(([l]) => l);
|
|
122
|
+
// G H J
|
|
88
123
|
const ON_FSA_LETTERS = Object.entries(FSA_LETTER_TO_PROVINCE)
|
|
89
124
|
.filter(([, p]) => p === "ON")
|
|
90
|
-
.map(([l]) => l);
|
|
125
|
+
.map(([l]) => l);
|
|
126
|
+
// K L M N P
|
|
91
127
|
const CA_INTERIOR_LETTERS = "ABCEGHJKLMNPRSTVWXYZ";
|
|
92
|
-
|
|
93
|
-
|
|
128
|
+
/**
|
|
129
|
+
* Class mix — po_box mass leans US (the production arena), cedex gets a real block, and the CA-fr class exists because
|
|
130
|
+
* the #511 Montréal rows ("Case Postale 200, H3A 1B9 Montréal, QC") fail today.
|
|
131
|
+
*/
|
|
94
132
|
const CLASS_MIX = [
|
|
95
133
|
["po-box-us", 0.27],
|
|
96
134
|
["po-box-us-military", 0.05], // #517: CMR/PSC/Unit + Box, APO/FPO/DPO + AA/AE/AP — the arena's 0/3 class
|
|
@@ -102,11 +140,15 @@ const CLASS_MIX = [
|
|
|
102
140
|
["po-box-au", 0.12],
|
|
103
141
|
["po-box-nz", 0.06],
|
|
104
142
|
];
|
|
105
|
-
/**
|
|
143
|
+
/**
|
|
144
|
+
* Synthetic recipient/venue prefixes — the arena's "JOHN DOE, ACME INC, …" pattern.
|
|
145
|
+
*/
|
|
106
146
|
const VENUES_EN = ["John Doe", "Jane Smith", "Acme Inc", "Wayne Enterprises", "Maria Garcia", "Riverside Clinic"];
|
|
107
147
|
const VENUES_FR = ["Société Dupont", "Cabinet Martin", "Hôpital Central", "Mairie Annexe", "Imprimerie Moderne"];
|
|
108
148
|
// ── Holdout + CSV helpers ────────────────────────────────────────────────────────────────────────
|
|
109
|
-
/**
|
|
149
|
+
/**
|
|
150
|
+
* Stable locality hash for the FR/CA train↔golden split (djb2; hash%10===0 → golden-only).
|
|
151
|
+
*/
|
|
110
152
|
function localityHash(name) {
|
|
111
153
|
let h = 5381;
|
|
112
154
|
const s = name.toLowerCase();
|
|
@@ -116,7 +158,9 @@ function localityHash(name) {
|
|
|
116
158
|
return h;
|
|
117
159
|
}
|
|
118
160
|
const isHoldoutLocality = (name) => localityHash(name) % 10 === 0;
|
|
119
|
-
/**
|
|
161
|
+
/**
|
|
162
|
+
* Minimal RFC-4180-ish splitter (handles quoted fields).
|
|
163
|
+
*/
|
|
120
164
|
function splitCSV(line) {
|
|
121
165
|
const out = [];
|
|
122
166
|
let cur = "";
|
|
@@ -151,8 +195,11 @@ function splitCSV(line) {
|
|
|
151
195
|
out.push(cur);
|
|
152
196
|
return out;
|
|
153
197
|
}
|
|
154
|
-
const
|
|
155
|
-
|
|
198
|
+
const MAX_LOCALITY_LENGTH = 40;
|
|
199
|
+
const cleanLocality = (loc) => loc && loc.length <= MAX_LOCALITY_LENGTH && !/\d|,/.test(loc) && !/cedex/i.test(loc);
|
|
200
|
+
/**
|
|
201
|
+
* Stream real US tuples (number/street/city/postcode) out of a cached OA zip.
|
|
202
|
+
*/
|
|
156
203
|
function readUsTuples(source) {
|
|
157
204
|
const r = spawnSync("unzip", ["-p", source.zip, source.csv], { maxBuffer: 1024 * 1024 * 1024, encoding: "buffer" });
|
|
158
205
|
if (r.status !== 0) {
|
|
@@ -193,7 +240,7 @@ function readUsTuples(source) {
|
|
|
193
240
|
*/
|
|
194
241
|
function readFrTuples(limit) {
|
|
195
242
|
const r = spawnSync("bash", ["-c", `unzip -p "${FR_SOURCE.zip}" "${FR_SOURCE.csv}" | awk 'NR==1 || NR%211==3' | head -n ${limit + 1}`], { maxBuffer: 1024 * 1024 * 1024, encoding: "buffer" });
|
|
196
|
-
if (r.status !== 0 && r.stdout.length
|
|
243
|
+
if (r.status !== 0 && !r.stdout.length) {
|
|
197
244
|
console.error(` WARN: unzip failed for ${FR_SOURCE.zip}`);
|
|
198
245
|
return [];
|
|
199
246
|
}
|
|
@@ -272,7 +319,9 @@ function readPostalTuples(source, opts) {
|
|
|
272
319
|
return tuples;
|
|
273
320
|
}
|
|
274
321
|
// ── Rendering helpers ────────────────────────────────────────────────────────────────────────────
|
|
275
|
-
/**
|
|
322
|
+
/**
|
|
323
|
+
* Box-number distribution (mirrors the corpus defaultPickNumber bands: 70% are 1-3 digits).
|
|
324
|
+
*/
|
|
276
325
|
function pickBoxNumber(random) {
|
|
277
326
|
const r = random();
|
|
278
327
|
if (r < 0.3)
|
|
@@ -281,9 +330,11 @@ function pickBoxNumber(random) {
|
|
|
281
330
|
return String(100 + Math.floor(random() * 900));
|
|
282
331
|
if (r < 0.95)
|
|
283
332
|
return String(1000 + Math.floor(random() * 9000));
|
|
284
|
-
return String(
|
|
333
|
+
return String(10_000 + Math.floor(random() * 90_000));
|
|
285
334
|
}
|
|
286
|
-
/**
|
|
335
|
+
/**
|
|
336
|
+
* Case dial for the designator phrase: mostly template casing, sometimes UPPER, rarely lower.
|
|
337
|
+
*/
|
|
287
338
|
function caseDial(random, s) {
|
|
288
339
|
const r = random();
|
|
289
340
|
if (r < 0.7)
|
|
@@ -292,10 +343,14 @@ function caseDial(random, s) {
|
|
|
292
343
|
return s.toUpperCase();
|
|
293
344
|
return s.toLowerCase();
|
|
294
345
|
}
|
|
295
|
-
|
|
296
|
-
|
|
346
|
+
/**
|
|
347
|
+
* Leaders the codex PO_BOX_RE genuinely covers (everything en-US except "POB"; PMB/"#" are the corpus's CMRA forms,
|
|
348
|
+
* outside USPS Pub-28 §29). Used to scope the isPOBox round-trip assertion.
|
|
349
|
+
*/
|
|
297
350
|
const CODEX_COVERED_LEADERS = new Set(["PO Box", "P.O. Box", "P.O.Box", "PO BOX", "Post Office Box", "Box", ...US_LEADERS_RARE].map((l) => l.toLowerCase()));
|
|
298
|
-
/**
|
|
351
|
+
/**
|
|
352
|
+
* Compose a po_box phrase. "#" joins without a space ("#500", the golden PMB variant).
|
|
353
|
+
*/
|
|
299
354
|
function makePoBoxPhrase(random, leaders, rareLeaders) {
|
|
300
355
|
let leader = leaders[Math.floor(random() * leaders.length)];
|
|
301
356
|
if (rareLeaders && random() < 0.1) {
|
|
@@ -354,7 +409,9 @@ function makeAuNzPoBoxPhrase(random, leaders, rareLeaders, validate) {
|
|
|
354
409
|
}
|
|
355
410
|
return phrase;
|
|
356
411
|
}
|
|
357
|
-
/**
|
|
412
|
+
/**
|
|
413
|
+
* Synthesize a codex-valid Canadian postcode for a province's FSA letters ("H2X 3V4").
|
|
414
|
+
*/
|
|
358
415
|
function makeCaPostcode(random, fsaLetters) {
|
|
359
416
|
const L = () => CA_INTERIOR_LETTERS[Math.floor(random() * CA_INTERIOR_LETTERS.length)];
|
|
360
417
|
const D = () => String(Math.floor(random() * 10));
|
|
@@ -543,6 +600,10 @@ function orderComponents(components) {
|
|
|
543
600
|
}
|
|
544
601
|
return out;
|
|
545
602
|
}
|
|
603
|
+
/**
|
|
604
|
+
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
605
|
+
* and `description` below for the surface form it generates.
|
|
606
|
+
*/
|
|
546
607
|
export const poBoxCedexRecipe = {
|
|
547
608
|
name: "po-box-cedex",
|
|
548
609
|
description: "PO box / CEDEX coverage rows (US/FR/CA/AU/NZ) — self-generated from cached OA + GeoNames pools",
|
|
@@ -550,7 +611,7 @@ export const poBoxCedexRecipe = {
|
|
|
550
611
|
options: [{ flag: "--golden", description: "Emit the leakage-safe holdout variant ({raw, components, country})" }],
|
|
551
612
|
async run(opts, write) {
|
|
552
613
|
const random = makeMulberry32(opts.seed);
|
|
553
|
-
const count = opts.count ??
|
|
614
|
+
const count = opts.count ?? 50_000;
|
|
554
615
|
const source = opts.sourceName ?? "synth-po-box-cedex";
|
|
555
616
|
// US pool: VT only for golden, non-VT for train (the established geographic holdout).
|
|
556
617
|
const usPool = [];
|
|
@@ -562,7 +623,7 @@ export const poBoxCedexRecipe = {
|
|
|
562
623
|
}
|
|
563
624
|
}
|
|
564
625
|
// FR + CA pools: stable locality-hash holdout (golden gets hash%10==0, train the rest).
|
|
565
|
-
const frAll = readFrTuples(
|
|
626
|
+
const frAll = readFrTuples(80_000);
|
|
566
627
|
const frPool = frAll.filter((t) => isHoldoutLocality(t.locality) === opts.golden);
|
|
567
628
|
console.error(` ${FR_SOURCE.csv}: ${frAll.length} tuples (${frPool.length} after holdout split)`);
|
|
568
629
|
const qcAll = readCaLocalities("10");
|
|
@@ -576,12 +637,7 @@ export const poBoxCedexRecipe = {
|
|
|
576
637
|
const auPool = auAll.filter((t) => isHoldoutLocality(t.locality) === opts.golden);
|
|
577
638
|
const nzPool = nzAll.filter((t) => isHoldoutLocality(t.locality) === opts.golden);
|
|
578
639
|
console.error(` GeoNames postal: AU ${auAll.length}→${auPool.length}, NZ ${nzAll.length}→${nzPool.length}`);
|
|
579
|
-
if (usPool.length
|
|
580
|
-
frPool.length === 0 ||
|
|
581
|
-
qcPool.length === 0 ||
|
|
582
|
-
onPool.length === 0 ||
|
|
583
|
-
auPool.length === 0 ||
|
|
584
|
-
nzPool.length === 0) {
|
|
640
|
+
if (!usPool.length || !frPool.length || !qcPool.length || !onPool.length || !auPool.length || !nzPool.length) {
|
|
585
641
|
throw new Error("A base pool is empty — check /tmp/oa-cache and /tmp/geonames-cache (CA.zip, AU-postal.zip, NZ-postal.zip).");
|
|
586
642
|
}
|
|
587
643
|
const pickClass = (r) => {
|
|
@@ -591,7 +647,7 @@ export const poBoxCedexRecipe = {
|
|
|
591
647
|
if (r < acc)
|
|
592
648
|
return name;
|
|
593
649
|
}
|
|
594
|
-
return CLASS_MIX
|
|
650
|
+
return CLASS_MIX.at(-1)[0];
|
|
595
651
|
};
|
|
596
652
|
let emitted = 0;
|
|
597
653
|
let skipped = 0;
|