@mailwoman/corpus 9.2.0 → 9.4.0
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 +22 -22
- package/data/PROVENANCE.md +7 -7
- package/lib/adapters/ban/adapter.ts +190 -0
- package/lib/adapters/ban/street-decompose.ts +66 -0
- package/lib/adapters/fcc-bdc/adapter.ts +174 -0
- package/lib/adapters/geonames/adapter.ts +199 -0
- package/lib/adapters/geonames-postal/adapter.ts +122 -0
- package/lib/adapters/gnaf/adapter.ts +149 -0
- package/lib/adapters/gnaf/assemble.ts +225 -0
- package/lib/adapters/index.ts +153 -0
- package/lib/adapters/openaddresses/adapter.ts +251 -0
- package/lib/adapters/overture/adapter.ts +162 -0
- package/lib/adapters/state-hi-schools/adapter.ts +170 -0
- package/lib/adapters/state-hi-schools/workbook.ts +35 -0
- package/lib/adapters/synth-po-box/adapter.ts +204 -0
- package/lib/adapters/tiger/adapter.ts +252 -0
- package/lib/adapters/tiger/street-decompose.ts +83 -0
- package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +167 -0
- package/lib/adapters/usgov-imls-pls/adapter.ts +143 -0
- package/lib/adapters/usgov-irs-bmf/adapter.ts +151 -0
- package/lib/adapters/usgov-nad/adapter.ts +334 -0
- package/lib/adapters/usgov-nppes/adapter.ts +151 -0
- package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +193 -0
- package/lib/adapters/utils/index.ts +307 -0
- package/lib/adapters/wof-admin-jp/adapter.ts +214 -0
- package/lib/adapters/wof-admin-json/adapter.ts +231 -0
- package/lib/adapters/wof-json-rows.ts +129 -0
- package/lib/adapters/wof-postalcode-json/adapter.ts +176 -0
- package/lib/build.ts +378 -0
- package/lib/env.ts +50 -0
- package/lib/index.ts +13 -0
- package/lib/recipes/anchor-absorption.ts +101 -0
- package/lib/recipes/bare-country.ts +95 -0
- package/lib/recipes/boundary-stress.ts +102 -0
- package/lib/recipes/cn-organizational-units.ts +199 -0
- package/lib/recipes/country-balanced.ts +510 -0
- package/lib/recipes/cz-pcfirst-preposition.ts +112 -0
- package/lib/recipes/fr-admin-split.ts +243 -0
- package/lib/recipes/fr-bare-street.ts +171 -0
- package/lib/recipes/fr-fragment.ts +334 -0
- package/lib/recipes/fr-lieudit.ts +301 -0
- package/lib/recipes/fr-order.ts +246 -0
- package/lib/recipes/german.ts +360 -0
- package/lib/recipes/house-venue.ts +93 -0
- package/lib/recipes/index.ts +97 -0
- package/lib/recipes/intersection.ts +619 -0
- package/lib/recipes/locale.ts +600 -0
- package/lib/recipes/nl-postcode.ts +117 -0
- package/lib/recipes/no-fragment.ts +213 -0
- package/lib/recipes/no-street-led.ts +135 -0
- package/lib/recipes/no-street.ts +91 -0
- package/lib/recipes/po-box-cedex.ts +976 -0
- package/lib/recipes/po-box.ts +124 -0
- package/lib/recipes/reviewed-postcode-tail.ts +190 -0
- package/lib/recipes/scaffold.ts +468 -0
- package/lib/recipes/si-bare-village.ts +99 -0
- package/lib/recipes/street-affix.ts +805 -0
- package/lib/recipes/street-bare.ts +102 -0
- package/lib/recipes/street.ts +83 -0
- package/lib/recipes/sub-venue-sources.ts +878 -0
- package/lib/recipes/sub-venue.ts +998 -0
- package/lib/recipes/trailing-region.ts +178 -0
- package/lib/recipes/unit.ts +304 -0
- package/lib/runner.ts +312 -0
- package/lib/synthesizers/anchor-absorption.ts +288 -0
- package/lib/synthesizers/boundary-stress.ts +532 -0
- package/lib/synthesizers/german.ts +260 -0
- package/lib/synthesizers/house-venue.ts +308 -0
- package/lib/synthesizers/intersection.ts +233 -0
- package/lib/synthesizers/no-street.ts +327 -0
- package/lib/synthesizers/po-box.ts +323 -0
- package/lib/synthesizers/street.ts +269 -0
- package/lib/synthesizers/utils.ts +993 -0
- package/lib/test-kit/corpus-recipe.ts +86 -0
- package/lib/test-kit/index.ts +100 -0
- package/lib/tools/align-slice.ts +68 -0
- package/lib/tools/audit.ts +403 -0
- package/lib/tools/corpus-stats.ts +136 -0
- package/lib/tools/fetch/acra-sg.ts +174 -0
- package/lib/tools/fetch/ban.ts +289 -0
- package/lib/tools/fetch/download.ts +477 -0
- package/lib/tools/fetch/gcis-tw.ts +175 -0
- package/lib/tools/fetch/geonames-dump.ts +257 -0
- package/lib/tools/fetch/geonames-postal.ts +180 -0
- package/lib/tools/fetch/houjin-jp.ts +135 -0
- package/lib/tools/fetch/hrsa.ts +59 -0
- package/lib/tools/fetch/imls-pls.ts +149 -0
- package/lib/tools/fetch/index.ts +174 -0
- package/lib/tools/fetch/juso-kr.ts +165 -0
- package/lib/tools/fetch/localdata-kr.ts +194 -0
- package/lib/tools/fetch/nad.ts +341 -0
- package/lib/tools/fetch/nppes.ts +165 -0
- package/lib/tools/fetch/openaddresses.ts +347 -0
- package/lib/tools/fetch/ourairports.ts +170 -0
- package/lib/tools/fetch/ppd.ts +121 -0
- package/lib/tools/fetch/state-hi-schools.ts +161 -0
- package/lib/tools/fetch/state-sources.ts +146 -0
- package/lib/tools/fetch/tiger-full.ts +308 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +384 -0
- package/lib/tools/golden-expand.ts +574 -0
- package/lib/tools/golden-promote.ts +337 -0
- package/lib/tools/golden-relabel-street.ts +686 -0
- package/lib/tools/index.ts +28 -0
- package/lib/tools/ingest-csv.ts +378 -0
- package/lib/tools/jsonl-to-parquet.ts +207 -0
- package/lib/tools/lint-slice-vocab.ts +388 -0
- package/lib/tools/lint-slice.ts +496 -0
- package/lib/tools/overlay-manifest.ts +148 -0
- package/lib/tools/overture-subvenue.ts +209 -0
- package/lib/tools/postcode-triples.ts +363 -0
- package/lib/tools/slice-kryptonite.ts +137 -0
- package/lib/tools/slice-translit.ts +218 -0
- package/lib/tools/sub-venue/harvest.ts +234 -0
- package/lib/tools/sub-venue/head-nouns.ts +245 -0
- package/lib/tools/sub-venue/surfaces.ts +95 -0
- package/lib/tools/sub-venue/table.ts +281 -0
- package/lib/tools/sub-venue/wikidata.ts +85 -0
- package/lib/tools/sub-venue-lexicon.ts +429 -0
- package/lib/tools/sub-venue-promotions.ts +330 -0
- package/lib/types.ts +247 -0
- package/lib/utils/align.ts +330 -0
- package/lib/utils/golden.ts +189 -0
- package/lib/utils/index.ts +14 -0
- package/lib/utils/parquet.ts +582 -0
- package/lib/utils/slice-stats.ts +95 -0
- package/lib/utils/split.ts +279 -0
- package/lib/utils/tokenize.ts +120 -0
- package/lib/utils/wof-json.ts +247 -0
- package/out/adapters/ban/adapter.d.ts.map +1 -0
- package/out/adapters/ban/adapter.js +149 -0
- package/out/adapters/ban/adapter.js.map +1 -0
- package/out/adapters/ban/street-decompose.d.ts.map +1 -0
- package/out/adapters/ban/street-decompose.js +51 -0
- package/out/adapters/ban/street-decompose.js.map +1 -0
- package/out/adapters/fcc-bdc/adapter.d.ts.map +1 -0
- package/out/adapters/fcc-bdc/adapter.js +144 -0
- package/out/adapters/fcc-bdc/adapter.js.map +1 -0
- package/out/adapters/geonames/adapter.d.ts.map +1 -0
- package/out/adapters/geonames/adapter.js +176 -0
- package/out/adapters/geonames/adapter.js.map +1 -0
- package/out/adapters/geonames-postal/adapter.d.ts +54 -0
- package/out/adapters/geonames-postal/adapter.d.ts.map +1 -0
- package/out/adapters/geonames-postal/adapter.js +107 -0
- package/out/adapters/geonames-postal/adapter.js.map +1 -0
- package/out/adapters/gnaf/adapter.d.ts +49 -0
- package/out/adapters/gnaf/adapter.d.ts.map +1 -0
- package/out/adapters/gnaf/adapter.js +124 -0
- package/out/adapters/gnaf/adapter.js.map +1 -0
- package/out/adapters/gnaf/assemble.d.ts +65 -0
- package/out/adapters/gnaf/assemble.d.ts.map +1 -0
- package/out/adapters/gnaf/assemble.js +154 -0
- package/out/adapters/gnaf/assemble.js.map +1 -0
- package/out/adapters/index.d.ts +51 -0
- package/out/adapters/index.d.ts.map +1 -0
- package/out/adapters/index.js +95 -0
- package/out/adapters/index.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -0
- package/out/adapters/openaddresses/adapter.js +186 -0
- package/out/adapters/openaddresses/adapter.js.map +1 -0
- package/out/adapters/overture/adapter.d.ts +48 -0
- package/out/adapters/overture/adapter.d.ts.map +1 -0
- package/out/adapters/overture/adapter.js +125 -0
- package/out/adapters/overture/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/adapter.d.ts +46 -0
- package/out/adapters/state-hi-schools/adapter.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/adapter.js +145 -0
- package/out/adapters/state-hi-schools/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/workbook.d.ts +29 -0
- package/out/adapters/state-hi-schools/workbook.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/workbook.js +20 -0
- package/out/adapters/state-hi-schools/workbook.js.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
- package/out/adapters/synth-po-box/adapter.d.ts.map +1 -0
- package/out/adapters/synth-po-box/adapter.js +140 -0
- package/out/adapters/synth-po-box/adapter.js.map +1 -0
- package/out/adapters/tiger/adapter.d.ts +55 -0
- package/out/adapters/tiger/adapter.d.ts.map +1 -0
- package/out/adapters/tiger/adapter.js +201 -0
- package/out/adapters/tiger/adapter.js.map +1 -0
- package/out/adapters/tiger/street-decompose.d.ts.map +1 -0
- package/out/adapters/tiger/street-decompose.js +68 -0
- package/out/adapters/tiger/street-decompose.js.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +56 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js +132 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts +36 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.js +114 -0
- package/out/adapters/usgov-imls-pls/adapter.js.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts +37 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.js +120 -0
- package/out/adapters/usgov-irs-bmf/adapter.js.map +1 -0
- package/out/adapters/usgov-nad/adapter.d.ts +48 -0
- package/out/adapters/usgov-nad/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nad/adapter.js +249 -0
- package/out/adapters/usgov-nad/adapter.js.map +1 -0
- package/out/adapters/usgov-nppes/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nppes/adapter.js +118 -0
- package/out/adapters/usgov-nppes/adapter.js.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +154 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -0
- package/out/adapters/utils/index.d.ts +191 -0
- package/out/adapters/utils/index.d.ts.map +1 -0
- package/out/adapters/utils/index.js +206 -0
- package/out/adapters/utils/index.js.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.js +161 -0
- package/out/adapters/wof-admin-jp/adapter.js.map +1 -0
- package/out/adapters/wof-admin-json/adapter.d.ts +79 -0
- package/out/adapters/wof-admin-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-json/adapter.js +197 -0
- package/out/adapters/wof-admin-json/adapter.js.map +1 -0
- package/out/adapters/wof-json-rows.d.ts +62 -0
- package/out/adapters/wof-json-rows.d.ts.map +1 -0
- package/out/adapters/wof-json-rows.js +83 -0
- package/out/adapters/wof-json-rows.js.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts +65 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.js +151 -0
- package/out/adapters/wof-postalcode-json/adapter.js.map +1 -0
- package/out/build.d.ts +132 -0
- package/out/build.d.ts.map +1 -0
- package/out/build.js +245 -0
- package/out/build.js.map +1 -0
- package/out/codex/us-fips-state.d.ts.map +1 -0
- package/out/codex/us-fips-state.js.map +1 -0
- package/out/env.d.ts +46 -0
- package/out/env.d.ts.map +1 -0
- package/out/env.js +46 -0
- package/out/env.js.map +1 -0
- package/out/index.d.ts +13 -0
- package/out/index.d.ts.map +1 -0
- package/out/index.js +13 -0
- package/out/index.js.map +1 -0
- package/out/recipes/anchor-absorption.d.ts +20 -0
- package/out/recipes/anchor-absorption.d.ts.map +1 -0
- package/out/recipes/anchor-absorption.js +82 -0
- package/out/recipes/anchor-absorption.js.map +1 -0
- package/out/recipes/bare-country.d.ts +25 -0
- package/out/recipes/bare-country.d.ts.map +1 -0
- package/out/recipes/bare-country.js +88 -0
- package/out/recipes/bare-country.js.map +1 -0
- package/out/recipes/boundary-stress.d.ts +20 -0
- package/out/recipes/boundary-stress.d.ts.map +1 -0
- package/out/recipes/boundary-stress.js +84 -0
- package/out/recipes/boundary-stress.js.map +1 -0
- package/out/recipes/cn-organizational-units.d.ts +36 -0
- package/out/recipes/cn-organizational-units.d.ts.map +1 -0
- package/out/recipes/cn-organizational-units.js +159 -0
- package/out/recipes/cn-organizational-units.js.map +1 -0
- package/out/recipes/country-balanced.d.ts +32 -0
- package/out/recipes/country-balanced.d.ts.map +1 -0
- package/out/recipes/country-balanced.js +394 -0
- package/out/recipes/country-balanced.js.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts +22 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.js +101 -0
- package/out/recipes/cz-pcfirst-preposition.js.map +1 -0
- package/out/recipes/fr-admin-split.d.ts +38 -0
- package/out/recipes/fr-admin-split.d.ts.map +1 -0
- package/out/recipes/fr-admin-split.js +192 -0
- package/out/recipes/fr-admin-split.js.map +1 -0
- package/out/recipes/fr-bare-street.d.ts +28 -0
- package/out/recipes/fr-bare-street.d.ts.map +1 -0
- package/out/recipes/fr-bare-street.js +144 -0
- package/out/recipes/fr-bare-street.js.map +1 -0
- package/out/recipes/fr-fragment.d.ts +77 -0
- package/out/recipes/fr-fragment.d.ts.map +1 -0
- package/out/recipes/fr-fragment.js +277 -0
- package/out/recipes/fr-fragment.js.map +1 -0
- package/out/recipes/fr-lieudit.d.ts +32 -0
- package/out/recipes/fr-lieudit.d.ts.map +1 -0
- package/out/recipes/fr-lieudit.js +227 -0
- package/out/recipes/fr-lieudit.js.map +1 -0
- package/out/recipes/fr-order.d.ts +38 -0
- package/out/recipes/fr-order.d.ts.map +1 -0
- package/out/recipes/fr-order.js +198 -0
- package/out/recipes/fr-order.js.map +1 -0
- package/out/recipes/german.d.ts +44 -0
- package/out/recipes/german.d.ts.map +1 -0
- package/out/recipes/german.js +289 -0
- package/out/recipes/german.js.map +1 -0
- package/out/recipes/house-venue.d.ts +18 -0
- package/out/recipes/house-venue.d.ts.map +1 -0
- package/out/recipes/house-venue.js +74 -0
- package/out/recipes/house-venue.js.map +1 -0
- package/out/recipes/index.d.ts +24 -0
- package/out/recipes/index.d.ts.map +1 -0
- package/out/recipes/index.js +91 -0
- package/out/recipes/index.js.map +1 -0
- package/out/recipes/intersection.d.ts +42 -0
- package/out/recipes/intersection.d.ts.map +1 -0
- package/out/recipes/intersection.js +453 -0
- package/out/recipes/intersection.js.map +1 -0
- package/out/recipes/locale.d.ts +136 -0
- package/out/recipes/locale.d.ts.map +1 -0
- package/out/recipes/locale.js +460 -0
- package/out/recipes/locale.js.map +1 -0
- package/out/recipes/nl-postcode.d.ts +26 -0
- package/out/recipes/nl-postcode.d.ts.map +1 -0
- package/out/recipes/nl-postcode.js +103 -0
- package/out/recipes/nl-postcode.js.map +1 -0
- package/out/recipes/no-fragment.d.ts +43 -0
- package/out/recipes/no-fragment.d.ts.map +1 -0
- package/out/recipes/no-fragment.js +183 -0
- package/out/recipes/no-fragment.js.map +1 -0
- package/out/recipes/no-street-led.d.ts +24 -0
- package/out/recipes/no-street-led.d.ts.map +1 -0
- package/out/recipes/no-street-led.js +114 -0
- package/out/recipes/no-street-led.js.map +1 -0
- package/out/recipes/no-street.d.ts +18 -0
- package/out/recipes/no-street.d.ts.map +1 -0
- package/out/recipes/no-street.js +72 -0
- package/out/recipes/no-street.js.map +1 -0
- package/out/recipes/po-box-cedex.d.ts +38 -0
- package/out/recipes/po-box-cedex.d.ts.map +1 -0
- package/out/recipes/po-box-cedex.js +768 -0
- package/out/recipes/po-box-cedex.js.map +1 -0
- package/out/recipes/po-box.d.ts +17 -0
- package/out/recipes/po-box.d.ts.map +1 -0
- package/out/recipes/po-box.js +101 -0
- package/out/recipes/po-box.js.map +1 -0
- package/out/recipes/reviewed-postcode-tail.d.ts +47 -0
- package/out/recipes/reviewed-postcode-tail.d.ts.map +1 -0
- package/out/recipes/reviewed-postcode-tail.js +125 -0
- package/out/recipes/reviewed-postcode-tail.js.map +1 -0
- package/out/recipes/scaffold.d.ts +323 -0
- package/out/recipes/scaffold.d.ts.map +1 -0
- package/out/recipes/scaffold.js +174 -0
- package/out/recipes/scaffold.js.map +1 -0
- package/out/recipes/si-bare-village.d.ts +32 -0
- package/out/recipes/si-bare-village.d.ts.map +1 -0
- package/out/recipes/si-bare-village.js +89 -0
- package/out/recipes/si-bare-village.js.map +1 -0
- package/out/recipes/street-affix.d.ts +89 -0
- package/out/recipes/street-affix.d.ts.map +1 -0
- package/out/recipes/street-affix.js +563 -0
- package/out/recipes/street-affix.js.map +1 -0
- package/out/recipes/street-bare.d.ts +25 -0
- package/out/recipes/street-bare.d.ts.map +1 -0
- package/out/recipes/street-bare.js +87 -0
- package/out/recipes/street-bare.js.map +1 -0
- package/out/recipes/street.d.ts +15 -0
- package/out/recipes/street.d.ts.map +1 -0
- package/out/recipes/street.js +70 -0
- package/out/recipes/street.js.map +1 -0
- package/out/recipes/sub-venue-sources.d.ts +229 -0
- package/out/recipes/sub-venue-sources.d.ts.map +1 -0
- package/out/recipes/sub-venue-sources.js +654 -0
- package/out/recipes/sub-venue-sources.js.map +1 -0
- package/out/recipes/sub-venue.d.ts +269 -0
- package/out/recipes/sub-venue.d.ts.map +1 -0
- package/out/recipes/sub-venue.js +726 -0
- package/out/recipes/sub-venue.js.map +1 -0
- package/out/recipes/trailing-region.d.ts +74 -0
- package/out/recipes/trailing-region.d.ts.map +1 -0
- package/out/recipes/trailing-region.js +158 -0
- package/out/recipes/trailing-region.js.map +1 -0
- package/out/recipes/unit.d.ts +29 -0
- package/out/recipes/unit.d.ts.map +1 -0
- package/out/recipes/unit.js +231 -0
- package/out/recipes/unit.js.map +1 -0
- package/out/runner.d.ts +130 -0
- package/out/runner.d.ts.map +1 -0
- package/out/runner.js +185 -0
- package/out/runner.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +63 -0
- package/out/synthesizers/anchor-absorption.d.ts.map +1 -0
- package/out/synthesizers/anchor-absorption.js +221 -0
- package/out/synthesizers/anchor-absorption.js.map +1 -0
- package/out/synthesizers/boundary-stress.d.ts +78 -0
- package/out/synthesizers/boundary-stress.d.ts.map +1 -0
- package/out/synthesizers/boundary-stress.js +455 -0
- package/out/synthesizers/boundary-stress.js.map +1 -0
- package/out/synthesizers/german.d.ts +115 -0
- package/out/synthesizers/german.d.ts.map +1 -0
- package/out/synthesizers/german.js +149 -0
- package/out/synthesizers/german.js.map +1 -0
- package/out/synthesizers/house-venue.d.ts +56 -0
- package/out/synthesizers/house-venue.d.ts.map +1 -0
- package/out/synthesizers/house-venue.js +247 -0
- package/out/synthesizers/house-venue.js.map +1 -0
- package/out/synthesizers/intersection.d.ts +52 -0
- package/out/synthesizers/intersection.d.ts.map +1 -0
- package/out/synthesizers/intersection.js +175 -0
- package/out/synthesizers/intersection.js.map +1 -0
- package/out/synthesizers/no-street.d.ts +72 -0
- package/out/synthesizers/no-street.d.ts.map +1 -0
- package/out/synthesizers/no-street.js +262 -0
- package/out/synthesizers/no-street.js.map +1 -0
- package/out/synthesizers/po-box.d.ts +108 -0
- package/out/synthesizers/po-box.d.ts.map +1 -0
- package/out/synthesizers/po-box.js +250 -0
- package/out/synthesizers/po-box.js.map +1 -0
- package/out/synthesizers/street.d.ts +54 -0
- package/out/synthesizers/street.d.ts.map +1 -0
- package/out/synthesizers/street.js +218 -0
- package/out/synthesizers/street.js.map +1 -0
- package/out/synthesizers/utils.d.ts +241 -0
- package/out/synthesizers/utils.d.ts.map +1 -0
- package/out/synthesizers/utils.js +776 -0
- package/out/synthesizers/utils.js.map +1 -0
- package/out/test-kit/corpus-recipe.d.ts +59 -0
- package/out/test-kit/corpus-recipe.d.ts.map +1 -0
- package/out/test-kit/corpus-recipe.js +39 -0
- package/out/test-kit/corpus-recipe.js.map +1 -0
- package/out/test-kit/index.d.ts +48 -0
- package/out/test-kit/index.d.ts.map +1 -0
- package/out/test-kit/index.js +78 -0
- package/out/test-kit/index.js.map +1 -0
- package/out/tools/align-slice.d.ts +7 -0
- package/out/tools/align-slice.d.ts.map +1 -0
- package/out/tools/align-slice.js +55 -0
- package/out/tools/align-slice.js.map +1 -0
- package/out/tools/audit.d.ts +29 -0
- package/out/tools/audit.d.ts.map +1 -0
- package/out/tools/audit.js +282 -0
- package/out/tools/audit.js.map +1 -0
- package/out/tools/corpus-stats.d.ts +44 -0
- package/out/tools/corpus-stats.d.ts.map +1 -0
- package/out/tools/corpus-stats.js +102 -0
- package/out/tools/corpus-stats.js.map +1 -0
- package/out/tools/fetch/acra-sg.d.ts +23 -0
- package/out/tools/fetch/acra-sg.d.ts.map +1 -0
- package/out/tools/fetch/acra-sg.js +126 -0
- package/out/tools/fetch/acra-sg.js.map +1 -0
- package/out/tools/fetch/ban.d.ts +31 -0
- package/out/tools/fetch/ban.d.ts.map +1 -0
- package/out/tools/fetch/ban.js +239 -0
- package/out/tools/fetch/ban.js.map +1 -0
- package/out/tools/fetch/download.d.ts +182 -0
- package/out/tools/fetch/download.d.ts.map +1 -0
- package/out/tools/fetch/download.js +318 -0
- package/out/tools/fetch/download.js.map +1 -0
- package/out/tools/fetch/gcis-tw.d.ts +23 -0
- package/out/tools/fetch/gcis-tw.d.ts.map +1 -0
- package/out/tools/fetch/gcis-tw.js +135 -0
- package/out/tools/fetch/gcis-tw.js.map +1 -0
- package/out/tools/fetch/geonames-dump.d.ts +91 -0
- package/out/tools/fetch/geonames-dump.d.ts.map +1 -0
- package/out/tools/fetch/geonames-dump.js +171 -0
- package/out/tools/fetch/geonames-dump.js.map +1 -0
- package/out/tools/fetch/geonames-postal.d.ts +76 -0
- package/out/tools/fetch/geonames-postal.d.ts.map +1 -0
- package/out/tools/fetch/geonames-postal.js +126 -0
- package/out/tools/fetch/geonames-postal.js.map +1 -0
- package/out/tools/fetch/houjin-jp.d.ts +24 -0
- package/out/tools/fetch/houjin-jp.d.ts.map +1 -0
- package/out/tools/fetch/houjin-jp.js +102 -0
- package/out/tools/fetch/houjin-jp.js.map +1 -0
- package/out/tools/fetch/hrsa.d.ts +18 -0
- package/out/tools/fetch/hrsa.d.ts.map +1 -0
- package/out/tools/fetch/hrsa.js +46 -0
- package/out/tools/fetch/hrsa.js.map +1 -0
- package/out/tools/fetch/imls-pls.d.ts +25 -0
- package/out/tools/fetch/imls-pls.d.ts.map +1 -0
- package/out/tools/fetch/imls-pls.js +108 -0
- package/out/tools/fetch/imls-pls.js.map +1 -0
- package/out/tools/fetch/index.d.ts +171 -0
- package/out/tools/fetch/index.d.ts.map +1 -0
- package/out/tools/fetch/index.js +170 -0
- package/out/tools/fetch/index.js.map +1 -0
- package/out/tools/fetch/juso-kr.d.ts +30 -0
- package/out/tools/fetch/juso-kr.d.ts.map +1 -0
- package/out/tools/fetch/juso-kr.js +120 -0
- package/out/tools/fetch/juso-kr.js.map +1 -0
- package/out/tools/fetch/localdata-kr.d.ts +30 -0
- package/out/tools/fetch/localdata-kr.d.ts.map +1 -0
- package/out/tools/fetch/localdata-kr.js +139 -0
- package/out/tools/fetch/localdata-kr.js.map +1 -0
- package/out/tools/fetch/nad.d.ts +70 -0
- package/out/tools/fetch/nad.d.ts.map +1 -0
- package/out/tools/fetch/nad.js +234 -0
- package/out/tools/fetch/nad.js.map +1 -0
- package/out/tools/fetch/nppes.d.ts +26 -0
- package/out/tools/fetch/nppes.d.ts.map +1 -0
- package/out/tools/fetch/nppes.js +126 -0
- package/out/tools/fetch/nppes.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +9 -0
- package/out/tools/fetch/openaddresses.d.ts.map +1 -0
- package/out/tools/fetch/openaddresses.js +279 -0
- package/out/tools/fetch/openaddresses.js.map +1 -0
- package/out/tools/fetch/ourairports.d.ts +45 -0
- package/out/tools/fetch/ourairports.d.ts.map +1 -0
- package/out/tools/fetch/ourairports.js +128 -0
- package/out/tools/fetch/ourairports.js.map +1 -0
- package/out/tools/fetch/ppd.d.ts.map +1 -0
- package/out/tools/fetch/ppd.js +85 -0
- package/out/tools/fetch/ppd.js.map +1 -0
- package/out/tools/fetch/state-hi-schools.d.ts +26 -0
- package/out/tools/fetch/state-hi-schools.d.ts.map +1 -0
- package/out/tools/fetch/state-hi-schools.js +112 -0
- package/out/tools/fetch/state-hi-schools.js.map +1 -0
- package/out/tools/fetch/state-sources.d.ts +26 -0
- package/out/tools/fetch/state-sources.d.ts.map +1 -0
- package/out/tools/fetch/state-sources.js +111 -0
- package/out/tools/fetch/state-sources.js.map +1 -0
- package/out/tools/fetch/tiger-full.d.ts +22 -0
- package/out/tools/fetch/tiger-full.d.ts.map +1 -0
- package/out/tools/fetch/tiger-full.js +217 -0
- package/out/tools/fetch/tiger-full.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +171 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.js +274 -0
- package/out/tools/fetch/wikidata-subvenue.js.map +1 -0
- package/out/tools/gb-title-case.d.ts.map +1 -0
- package/out/tools/gb-title-case.js.map +1 -0
- package/out/tools/golden-expand.d.ts +90 -0
- package/out/tools/golden-expand.d.ts.map +1 -0
- package/out/tools/golden-expand.js +406 -0
- package/out/tools/golden-expand.js.map +1 -0
- package/out/tools/golden-promote.d.ts.map +1 -0
- package/out/tools/golden-promote.js +240 -0
- package/out/tools/golden-promote.js.map +1 -0
- package/out/tools/golden-relabel-street.d.ts +196 -0
- package/out/tools/golden-relabel-street.d.ts.map +1 -0
- package/out/tools/golden-relabel-street.js +439 -0
- package/out/tools/golden-relabel-street.js.map +1 -0
- package/out/tools/index.d.ts +28 -0
- package/out/tools/index.d.ts.map +1 -0
- package/out/tools/index.js +28 -0
- package/out/tools/index.js.map +1 -0
- package/out/tools/ingest-csv.d.ts.map +1 -0
- package/out/tools/ingest-csv.js +265 -0
- package/out/tools/ingest-csv.js.map +1 -0
- package/out/tools/jsonl-to-parquet.d.ts +61 -0
- package/out/tools/jsonl-to-parquet.d.ts.map +1 -0
- package/out/tools/jsonl-to-parquet.js +150 -0
- package/out/tools/jsonl-to-parquet.js.map +1 -0
- package/out/tools/lint-slice-vocab.d.ts +90 -0
- package/out/tools/lint-slice-vocab.d.ts.map +1 -0
- package/out/tools/lint-slice-vocab.js +267 -0
- package/out/tools/lint-slice-vocab.js.map +1 -0
- package/out/tools/lint-slice.d.ts +93 -0
- package/out/tools/lint-slice.d.ts.map +1 -0
- package/out/tools/lint-slice.js +322 -0
- package/out/tools/lint-slice.js.map +1 -0
- package/out/tools/overlay-manifest.d.ts +39 -0
- package/out/tools/overlay-manifest.d.ts.map +1 -0
- package/out/tools/overlay-manifest.js +90 -0
- package/out/tools/overlay-manifest.js.map +1 -0
- package/out/tools/overture-subvenue.d.ts +112 -0
- package/out/tools/overture-subvenue.d.ts.map +1 -0
- package/out/tools/overture-subvenue.js +139 -0
- package/out/tools/overture-subvenue.js.map +1 -0
- package/out/tools/postcode-triples.d.ts +174 -0
- package/out/tools/postcode-triples.d.ts.map +1 -0
- package/out/tools/postcode-triples.js +292 -0
- package/out/tools/postcode-triples.js.map +1 -0
- package/out/tools/slice-kryptonite.d.ts +32 -0
- package/out/tools/slice-kryptonite.d.ts.map +1 -0
- package/out/tools/slice-kryptonite.js +99 -0
- package/out/tools/slice-kryptonite.js.map +1 -0
- package/out/tools/slice-translit.d.ts +51 -0
- package/out/tools/slice-translit.d.ts.map +1 -0
- package/out/tools/slice-translit.js +166 -0
- package/out/tools/slice-translit.js.map +1 -0
- package/out/tools/sub-venue/harvest.d.ts +100 -0
- package/out/tools/sub-venue/harvest.d.ts.map +1 -0
- package/out/tools/sub-venue/harvest.js +168 -0
- package/out/tools/sub-venue/harvest.js.map +1 -0
- package/out/tools/sub-venue/head-nouns.d.ts +50 -0
- package/out/tools/sub-venue/head-nouns.d.ts.map +1 -0
- package/out/tools/sub-venue/head-nouns.js +213 -0
- package/out/tools/sub-venue/head-nouns.js.map +1 -0
- package/out/tools/sub-venue/surfaces.d.ts +45 -0
- package/out/tools/sub-venue/surfaces.d.ts.map +1 -0
- package/out/tools/sub-venue/surfaces.js +77 -0
- package/out/tools/sub-venue/surfaces.js.map +1 -0
- package/out/tools/sub-venue/table.d.ts +229 -0
- package/out/tools/sub-venue/table.d.ts.map +1 -0
- package/out/tools/sub-venue/table.js +108 -0
- package/out/tools/sub-venue/table.js.map +1 -0
- package/out/tools/sub-venue/wikidata.d.ts +26 -0
- package/out/tools/sub-venue/wikidata.d.ts.map +1 -0
- package/out/tools/sub-venue/wikidata.js +62 -0
- package/out/tools/sub-venue/wikidata.js.map +1 -0
- package/out/tools/sub-venue-lexicon.d.ts +156 -0
- package/out/tools/sub-venue-lexicon.d.ts.map +1 -0
- package/out/tools/sub-venue-lexicon.js +283 -0
- package/out/tools/sub-venue-lexicon.js.map +1 -0
- package/out/tools/sub-venue-promotions.d.ts +94 -0
- package/out/tools/sub-venue-promotions.d.ts.map +1 -0
- package/out/tools/sub-venue-promotions.js +266 -0
- package/out/tools/sub-venue-promotions.js.map +1 -0
- package/out/types.d.ts +221 -0
- package/out/types.d.ts.map +1 -0
- package/out/types.js.map +1 -0
- package/out/utils/align.d.ts +93 -0
- package/out/utils/align.d.ts.map +1 -0
- package/out/utils/align.js +234 -0
- package/out/utils/align.js.map +1 -0
- package/out/utils/golden.d.ts +85 -0
- package/out/utils/golden.d.ts.map +1 -0
- package/out/utils/golden.js +127 -0
- package/out/utils/golden.js.map +1 -0
- package/out/utils/index.d.ts +14 -0
- package/out/utils/index.d.ts.map +1 -0
- package/out/utils/index.js +14 -0
- package/out/utils/index.js.map +1 -0
- package/out/utils/license.d.ts.map +1 -0
- package/out/utils/license.js.map +1 -0
- package/out/utils/parquet.d.ts +178 -0
- package/out/utils/parquet.d.ts.map +1 -0
- package/out/utils/parquet.js +371 -0
- package/out/utils/parquet.js.map +1 -0
- package/out/utils/slice-stats.d.ts +52 -0
- package/out/utils/slice-stats.d.ts.map +1 -0
- package/out/utils/slice-stats.js +58 -0
- package/out/utils/slice-stats.js.map +1 -0
- package/out/utils/split.d.ts +128 -0
- package/out/utils/split.d.ts.map +1 -0
- package/out/utils/split.js +204 -0
- package/out/utils/split.js.map +1 -0
- package/out/utils/tokenize.d.ts +64 -0
- package/out/utils/tokenize.d.ts.map +1 -0
- package/out/utils/tokenize.js +82 -0
- package/out/utils/tokenize.js.map +1 -0
- package/out/utils/wof-json.d.ts +113 -0
- package/out/utils/wof-json.d.ts.map +1 -0
- package/out/utils/wof-json.js +173 -0
- package/out/utils/wof-json.js.map +1 -0
- package/package.json +259 -194
- package/out/src/adapters/ban/adapter.d.ts.map +0 -1
- package/out/src/adapters/ban/adapter.js +0 -149
- package/out/src/adapters/ban/adapter.js.map +0 -1
- package/out/src/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/ban/street-decompose.js +0 -75
- package/out/src/adapters/ban/street-decompose.js.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.d.ts.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.js +0 -144
- package/out/src/adapters/fcc-bdc/adapter.js.map +0 -1
- package/out/src/adapters/geonames/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames/adapter.js +0 -176
- package/out/src/adapters/geonames/adapter.js.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.d.ts +0 -41
- package/out/src/adapters/geonames-postal/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.js +0 -104
- package/out/src/adapters/geonames-postal/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/adapter.d.ts +0 -49
- package/out/src/adapters/gnaf/adapter.d.ts.map +0 -1
- package/out/src/adapters/gnaf/adapter.js +0 -124
- package/out/src/adapters/gnaf/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/assemble.d.ts +0 -65
- package/out/src/adapters/gnaf/assemble.d.ts.map +0 -1
- package/out/src/adapters/gnaf/assemble.js +0 -154
- package/out/src/adapters/gnaf/assemble.js.map +0 -1
- package/out/src/adapters/index.d.ts +0 -51
- package/out/src/adapters/index.d.ts.map +0 -1
- package/out/src/adapters/index.js +0 -95
- package/out/src/adapters/index.js.map +0 -1
- package/out/src/adapters/openaddresses/adapter.d.ts.map +0 -1
- package/out/src/adapters/openaddresses/adapter.js +0 -186
- package/out/src/adapters/openaddresses/adapter.js.map +0 -1
- package/out/src/adapters/overture/adapter.d.ts +0 -48
- package/out/src/adapters/overture/adapter.d.ts.map +0 -1
- package/out/src/adapters/overture/adapter.js +0 -125
- package/out/src/adapters/overture/adapter.js.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.d.ts +0 -47
- package/out/src/adapters/state-hi-schools/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.js +0 -133
- package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.d.ts.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.js +0 -140
- package/out/src/adapters/synth-po-box/adapter.js.map +0 -1
- package/out/src/adapters/tiger/adapter.d.ts +0 -55
- package/out/src/adapters/tiger/adapter.d.ts.map +0 -1
- package/out/src/adapters/tiger/adapter.js +0 -201
- package/out/src/adapters/tiger/adapter.js.map +0 -1
- package/out/src/adapters/tiger/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/tiger/street-decompose.js +0 -90
- package/out/src/adapters/tiger/street-decompose.js.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -47
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +0 -139
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts +0 -36
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.js +0 -114
- package/out/src/adapters/usgov-imls-pls/adapter.js.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.js +0 -124
- package/out/src/adapters/usgov-irs-bmf/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.d.ts +0 -48
- package/out/src/adapters/usgov-nad/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.js +0 -252
- package/out/src/adapters/usgov-nad/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.js +0 -116
- package/out/src/adapters/usgov-nppes/adapter.js.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -156
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
- package/out/src/adapters/utils/index.d.ts +0 -150
- package/out/src/adapters/utils/index.d.ts.map +0 -1
- package/out/src/adapters/utils/index.js +0 -159
- package/out/src/adapters/utils/index.js.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.js +0 -164
- package/out/src/adapters/wof-admin-jp/adapter.js.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.d.ts +0 -82
- package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.js +0 -224
- package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
- package/out/src/adapters/wof-json-rows.d.ts +0 -32
- package/out/src/adapters/wof-json-rows.d.ts.map +0 -1
- package/out/src/adapters/wof-json-rows.js +0 -45
- package/out/src/adapters/wof-json-rows.js.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -65
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.js +0 -160
- package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
- package/out/src/build.d.ts +0 -132
- package/out/src/build.d.ts.map +0 -1
- package/out/src/build.js +0 -251
- package/out/src/build.js.map +0 -1
- package/out/src/codex/us-fips-state.d.ts.map +0 -1
- package/out/src/codex/us-fips-state.js.map +0 -1
- package/out/src/index.d.ts +0 -14
- package/out/src/index.d.ts.map +0 -1
- package/out/src/index.js +0 -14
- package/out/src/index.js.map +0 -1
- package/out/src/name-prone-us-suffixes.d.ts +0 -12
- package/out/src/name-prone-us-suffixes.d.ts.map +0 -1
- package/out/src/name-prone-us-suffixes.js +0 -12
- package/out/src/name-prone-us-suffixes.js.map +0 -1
- package/out/src/parquet-wrapper/index.d.ts +0 -9
- package/out/src/parquet-wrapper/index.d.ts.map +0 -1
- package/out/src/parquet-wrapper/index.js +0 -9
- package/out/src/parquet-wrapper/index.js.map +0 -1
- package/out/src/parquet-wrapper/reader.d.ts +0 -34
- package/out/src/parquet-wrapper/reader.d.ts.map +0 -1
- package/out/src/parquet-wrapper/reader.js +0 -69
- package/out/src/parquet-wrapper/reader.js.map +0 -1
- package/out/src/parquet-wrapper/schema.d.ts +0 -49
- package/out/src/parquet-wrapper/schema.d.ts.map +0 -1
- package/out/src/parquet-wrapper/schema.js +0 -55
- package/out/src/parquet-wrapper/schema.js.map +0 -1
- package/out/src/parquet-wrapper/writer.d.ts +0 -46
- package/out/src/parquet-wrapper/writer.d.ts.map +0 -1
- package/out/src/parquet-wrapper/writer.js +0 -76
- package/out/src/parquet-wrapper/writer.js.map +0 -1
- package/out/src/runner.d.ts +0 -126
- package/out/src/runner.d.ts.map +0 -1
- package/out/src/runner.js +0 -189
- package/out/src/runner.js.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.d.ts +0 -20
- package/out/src/shard-recipes/anchor-absorption.d.ts.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.js +0 -82
- package/out/src/shard-recipes/anchor-absorption.js.map +0 -1
- package/out/src/shard-recipes/bare-country.d.ts +0 -25
- package/out/src/shard-recipes/bare-country.d.ts.map +0 -1
- package/out/src/shard-recipes/bare-country.js +0 -87
- package/out/src/shard-recipes/bare-country.js.map +0 -1
- package/out/src/shard-recipes/boundary-stress.d.ts +0 -20
- package/out/src/shard-recipes/boundary-stress.d.ts.map +0 -1
- package/out/src/shard-recipes/boundary-stress.js +0 -83
- package/out/src/shard-recipes/boundary-stress.js.map +0 -1
- package/out/src/shard-recipes/country-balanced.d.ts +0 -32
- package/out/src/shard-recipes/country-balanced.d.ts.map +0 -1
- package/out/src/shard-recipes/country-balanced.js +0 -406
- package/out/src/shard-recipes/country-balanced.js.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts +0 -22
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.js +0 -100
- package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.d.ts +0 -38
- package/out/src/shard-recipes/fr-admin-split.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.js +0 -188
- package/out/src/shard-recipes/fr-admin-split.js.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.d.ts +0 -28
- package/out/src/shard-recipes/fr-bare-street.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.js +0 -143
- package/out/src/shard-recipes/fr-bare-street.js.map +0 -1
- package/out/src/shard-recipes/fr-fragment.d.ts +0 -77
- package/out/src/shard-recipes/fr-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-fragment.js +0 -276
- package/out/src/shard-recipes/fr-fragment.js.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.d.ts +0 -32
- package/out/src/shard-recipes/fr-lieudit.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.js +0 -226
- package/out/src/shard-recipes/fr-lieudit.js.map +0 -1
- package/out/src/shard-recipes/fr-order.d.ts +0 -38
- package/out/src/shard-recipes/fr-order.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-order.js +0 -208
- package/out/src/shard-recipes/fr-order.js.map +0 -1
- package/out/src/shard-recipes/german.d.ts +0 -23
- package/out/src/shard-recipes/german.d.ts.map +0 -1
- package/out/src/shard-recipes/german.js +0 -132
- package/out/src/shard-recipes/german.js.map +0 -1
- package/out/src/shard-recipes/house-venue.d.ts +0 -18
- package/out/src/shard-recipes/house-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/house-venue.js +0 -74
- package/out/src/shard-recipes/house-venue.js.map +0 -1
- package/out/src/shard-recipes/index.d.ts +0 -24
- package/out/src/shard-recipes/index.d.ts.map +0 -1
- package/out/src/shard-recipes/index.js +0 -89
- package/out/src/shard-recipes/index.js.map +0 -1
- package/out/src/shard-recipes/intersection.d.ts +0 -42
- package/out/src/shard-recipes/intersection.d.ts.map +0 -1
- package/out/src/shard-recipes/intersection.js +0 -460
- package/out/src/shard-recipes/intersection.js.map +0 -1
- package/out/src/shard-recipes/locale.d.ts +0 -135
- package/out/src/shard-recipes/locale.d.ts.map +0 -1
- package/out/src/shard-recipes/locale.js +0 -459
- package/out/src/shard-recipes/locale.js.map +0 -1
- package/out/src/shard-recipes/nl-postcode.d.ts +0 -26
- package/out/src/shard-recipes/nl-postcode.d.ts.map +0 -1
- package/out/src/shard-recipes/nl-postcode.js +0 -102
- package/out/src/shard-recipes/nl-postcode.js.map +0 -1
- package/out/src/shard-recipes/no-fragment.d.ts +0 -43
- package/out/src/shard-recipes/no-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/no-fragment.js +0 -188
- package/out/src/shard-recipes/no-fragment.js.map +0 -1
- package/out/src/shard-recipes/no-street-led.d.ts +0 -24
- package/out/src/shard-recipes/no-street-led.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street-led.js +0 -121
- package/out/src/shard-recipes/no-street-led.js.map +0 -1
- package/out/src/shard-recipes/no-street.d.ts +0 -18
- package/out/src/shard-recipes/no-street.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street.js +0 -72
- package/out/src/shard-recipes/no-street.js.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.d.ts +0 -38
- package/out/src/shard-recipes/po-box-cedex.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.js +0 -726
- package/out/src/shard-recipes/po-box-cedex.js.map +0 -1
- package/out/src/shard-recipes/po-box.d.ts +0 -17
- package/out/src/shard-recipes/po-box.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box.js +0 -101
- package/out/src/shard-recipes/po-box.js.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts +0 -47
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.js +0 -125
- package/out/src/shard-recipes/reviewed-postcode-tail.js.map +0 -1
- package/out/src/shard-recipes/scaffold.d.ts +0 -246
- package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
- package/out/src/shard-recipes/scaffold.js +0 -137
- package/out/src/shard-recipes/scaffold.js.map +0 -1
- package/out/src/shard-recipes/si-bare-village.d.ts +0 -32
- package/out/src/shard-recipes/si-bare-village.d.ts.map +0 -1
- package/out/src/shard-recipes/si-bare-village.js +0 -88
- package/out/src/shard-recipes/si-bare-village.js.map +0 -1
- package/out/src/shard-recipes/street-affix.d.ts +0 -89
- package/out/src/shard-recipes/street-affix.d.ts.map +0 -1
- package/out/src/shard-recipes/street-affix.js +0 -578
- package/out/src/shard-recipes/street-affix.js.map +0 -1
- package/out/src/shard-recipes/street-bare.d.ts +0 -25
- package/out/src/shard-recipes/street-bare.d.ts.map +0 -1
- package/out/src/shard-recipes/street-bare.js +0 -86
- package/out/src/shard-recipes/street-bare.js.map +0 -1
- package/out/src/shard-recipes/street.d.ts +0 -15
- package/out/src/shard-recipes/street.d.ts.map +0 -1
- package/out/src/shard-recipes/street.js +0 -69
- package/out/src/shard-recipes/street.js.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.d.ts +0 -228
- package/out/src/shard-recipes/sub-venue-sources.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.js +0 -664
- package/out/src/shard-recipes/sub-venue-sources.js.map +0 -1
- package/out/src/shard-recipes/sub-venue.d.ts +0 -269
- package/out/src/shard-recipes/sub-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue.js +0 -710
- package/out/src/shard-recipes/sub-venue.js.map +0 -1
- package/out/src/shard-recipes/trailing-region.d.ts +0 -74
- package/out/src/shard-recipes/trailing-region.d.ts.map +0 -1
- package/out/src/shard-recipes/trailing-region.js +0 -157
- package/out/src/shard-recipes/trailing-region.js.map +0 -1
- package/out/src/shard-recipes/unit.d.ts +0 -29
- package/out/src/shard-recipes/unit.d.ts.map +0 -1
- package/out/src/shard-recipes/unit.js +0 -243
- package/out/src/shard-recipes/unit.js.map +0 -1
- package/out/src/synthesizers/anchor-absorption.d.ts +0 -63
- package/out/src/synthesizers/anchor-absorption.d.ts.map +0 -1
- package/out/src/synthesizers/anchor-absorption.js +0 -223
- package/out/src/synthesizers/anchor-absorption.js.map +0 -1
- package/out/src/synthesizers/boundary-stress.d.ts +0 -78
- package/out/src/synthesizers/boundary-stress.d.ts.map +0 -1
- package/out/src/synthesizers/boundary-stress.js +0 -455
- package/out/src/synthesizers/boundary-stress.js.map +0 -1
- package/out/src/synthesizers/german.d.ts +0 -107
- package/out/src/synthesizers/german.d.ts.map +0 -1
- package/out/src/synthesizers/german.js +0 -148
- package/out/src/synthesizers/german.js.map +0 -1
- package/out/src/synthesizers/house-venue.d.ts +0 -56
- package/out/src/synthesizers/house-venue.d.ts.map +0 -1
- package/out/src/synthesizers/house-venue.js +0 -267
- package/out/src/synthesizers/house-venue.js.map +0 -1
- package/out/src/synthesizers/intersection.d.ts +0 -52
- package/out/src/synthesizers/intersection.d.ts.map +0 -1
- package/out/src/synthesizers/intersection.js +0 -175
- package/out/src/synthesizers/intersection.js.map +0 -1
- package/out/src/synthesizers/no-street.d.ts +0 -72
- package/out/src/synthesizers/no-street.d.ts.map +0 -1
- package/out/src/synthesizers/no-street.js +0 -282
- package/out/src/synthesizers/no-street.js.map +0 -1
- package/out/src/synthesizers/po-box.d.ts +0 -104
- package/out/src/synthesizers/po-box.d.ts.map +0 -1
- package/out/src/synthesizers/po-box.js +0 -266
- package/out/src/synthesizers/po-box.js.map +0 -1
- package/out/src/synthesizers/street.d.ts +0 -54
- package/out/src/synthesizers/street.d.ts.map +0 -1
- package/out/src/synthesizers/street.js +0 -221
- package/out/src/synthesizers/street.js.map +0 -1
- package/out/src/synthesizers/utils.d.ts +0 -203
- package/out/src/synthesizers/utils.d.ts.map +0 -1
- package/out/src/synthesizers/utils.js +0 -708
- package/out/src/synthesizers/utils.js.map +0 -1
- package/out/src/tools/align-shard.d.ts +0 -8
- package/out/src/tools/align-shard.d.ts.map +0 -1
- package/out/src/tools/align-shard.js +0 -56
- package/out/src/tools/align-shard.js.map +0 -1
- package/out/src/tools/audit.d.ts +0 -28
- package/out/src/tools/audit.d.ts.map +0 -1
- package/out/src/tools/audit.js +0 -285
- package/out/src/tools/audit.js.map +0 -1
- package/out/src/tools/corpus-stats.d.ts +0 -44
- package/out/src/tools/corpus-stats.d.ts.map +0 -1
- package/out/src/tools/corpus-stats.js +0 -138
- package/out/src/tools/corpus-stats.js.map +0 -1
- package/out/src/tools/fetch/ban.d.ts +0 -31
- package/out/src/tools/fetch/ban.d.ts.map +0 -1
- package/out/src/tools/fetch/ban.js +0 -239
- package/out/src/tools/fetch/ban.js.map +0 -1
- package/out/src/tools/fetch/download.d.ts +0 -78
- package/out/src/tools/fetch/download.d.ts.map +0 -1
- package/out/src/tools/fetch/download.js +0 -116
- package/out/src/tools/fetch/download.js.map +0 -1
- package/out/src/tools/fetch/geonames-dump.d.ts +0 -87
- package/out/src/tools/fetch/geonames-dump.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-dump.js +0 -178
- package/out/src/tools/fetch/geonames-dump.js.map +0 -1
- package/out/src/tools/fetch/geonames-postal.d.ts +0 -76
- package/out/src/tools/fetch/geonames-postal.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-postal.js +0 -125
- package/out/src/tools/fetch/geonames-postal.js.map +0 -1
- package/out/src/tools/fetch/hrsa.d.ts +0 -18
- package/out/src/tools/fetch/hrsa.d.ts.map +0 -1
- package/out/src/tools/fetch/hrsa.js +0 -46
- package/out/src/tools/fetch/hrsa.js.map +0 -1
- package/out/src/tools/fetch/imls-pls.d.ts +0 -25
- package/out/src/tools/fetch/imls-pls.d.ts.map +0 -1
- package/out/src/tools/fetch/imls-pls.js +0 -108
- package/out/src/tools/fetch/imls-pls.js.map +0 -1
- package/out/src/tools/fetch/index.d.ts +0 -144
- package/out/src/tools/fetch/index.d.ts.map +0 -1
- package/out/src/tools/fetch/index.js +0 -143
- package/out/src/tools/fetch/index.js.map +0 -1
- package/out/src/tools/fetch/nad.d.ts +0 -70
- package/out/src/tools/fetch/nad.d.ts.map +0 -1
- package/out/src/tools/fetch/nad.js +0 -234
- package/out/src/tools/fetch/nad.js.map +0 -1
- package/out/src/tools/fetch/nppes.d.ts +0 -26
- package/out/src/tools/fetch/nppes.d.ts.map +0 -1
- package/out/src/tools/fetch/nppes.js +0 -126
- package/out/src/tools/fetch/nppes.js.map +0 -1
- package/out/src/tools/fetch/openaddresses.d.ts +0 -61
- package/out/src/tools/fetch/openaddresses.d.ts.map +0 -1
- package/out/src/tools/fetch/openaddresses.js +0 -317
- package/out/src/tools/fetch/openaddresses.js.map +0 -1
- package/out/src/tools/fetch/ourairports.d.ts +0 -45
- package/out/src/tools/fetch/ourairports.d.ts.map +0 -1
- package/out/src/tools/fetch/ourairports.js +0 -128
- package/out/src/tools/fetch/ourairports.js.map +0 -1
- package/out/src/tools/fetch/ppd.d.ts.map +0 -1
- package/out/src/tools/fetch/ppd.js +0 -100
- package/out/src/tools/fetch/ppd.js.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.d.ts +0 -25
- package/out/src/tools/fetch/state-hi-schools.d.ts.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.js +0 -162
- package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
- package/out/src/tools/fetch/state-sources.d.ts +0 -26
- package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
- package/out/src/tools/fetch/state-sources.js +0 -111
- package/out/src/tools/fetch/state-sources.js.map +0 -1
- package/out/src/tools/fetch/tiger-full.d.ts +0 -42
- package/out/src/tools/fetch/tiger-full.d.ts.map +0 -1
- package/out/src/tools/fetch/tiger-full.js +0 -248
- package/out/src/tools/fetch/tiger-full.js.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.d.ts +0 -171
- package/out/src/tools/fetch/wikidata-subvenue.d.ts.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.js +0 -275
- package/out/src/tools/fetch/wikidata-subvenue.js.map +0 -1
- package/out/src/tools/gb-title-case.d.ts.map +0 -1
- package/out/src/tools/gb-title-case.js.map +0 -1
- package/out/src/tools/golden-expand.d.ts +0 -90
- package/out/src/tools/golden-expand.d.ts.map +0 -1
- package/out/src/tools/golden-expand.js +0 -413
- package/out/src/tools/golden-expand.js.map +0 -1
- package/out/src/tools/golden-promote.d.ts.map +0 -1
- package/out/src/tools/golden-promote.js +0 -244
- package/out/src/tools/golden-promote.js.map +0 -1
- package/out/src/tools/golden-relabel-street.d.ts +0 -196
- package/out/src/tools/golden-relabel-street.d.ts.map +0 -1
- package/out/src/tools/golden-relabel-street.js +0 -440
- package/out/src/tools/golden-relabel-street.js.map +0 -1
- package/out/src/tools/index.d.ts +0 -28
- package/out/src/tools/index.d.ts.map +0 -1
- package/out/src/tools/index.js +0 -28
- package/out/src/tools/index.js.map +0 -1
- package/out/src/tools/ingest-csv.d.ts.map +0 -1
- package/out/src/tools/ingest-csv.js +0 -296
- package/out/src/tools/ingest-csv.js.map +0 -1
- package/out/src/tools/jsonl-to-parquet.d.ts +0 -61
- package/out/src/tools/jsonl-to-parquet.d.ts.map +0 -1
- package/out/src/tools/jsonl-to-parquet.js +0 -164
- package/out/src/tools/jsonl-to-parquet.js.map +0 -1
- package/out/src/tools/lint-shard-vocab.d.ts +0 -90
- package/out/src/tools/lint-shard-vocab.d.ts.map +0 -1
- package/out/src/tools/lint-shard-vocab.js +0 -281
- package/out/src/tools/lint-shard-vocab.js.map +0 -1
- package/out/src/tools/lint-shard.d.ts +0 -93
- package/out/src/tools/lint-shard.d.ts.map +0 -1
- package/out/src/tools/lint-shard.js +0 -354
- package/out/src/tools/lint-shard.js.map +0 -1
- package/out/src/tools/overlay-manifest.d.ts +0 -39
- package/out/src/tools/overlay-manifest.d.ts.map +0 -1
- package/out/src/tools/overlay-manifest.js +0 -98
- package/out/src/tools/overlay-manifest.js.map +0 -1
- package/out/src/tools/overture-subvenue.d.ts +0 -112
- package/out/src/tools/overture-subvenue.d.ts.map +0 -1
- package/out/src/tools/overture-subvenue.js +0 -144
- package/out/src/tools/overture-subvenue.js.map +0 -1
- package/out/src/tools/postcode-triples.d.ts +0 -175
- package/out/src/tools/postcode-triples.d.ts.map +0 -1
- package/out/src/tools/postcode-triples.js +0 -304
- package/out/src/tools/postcode-triples.js.map +0 -1
- package/out/src/tools/shard-kryptonite.d.ts +0 -32
- package/out/src/tools/shard-kryptonite.d.ts.map +0 -1
- package/out/src/tools/shard-kryptonite.js +0 -100
- package/out/src/tools/shard-kryptonite.js.map +0 -1
- package/out/src/tools/shard-translit.d.ts +0 -51
- package/out/src/tools/shard-translit.d.ts.map +0 -1
- package/out/src/tools/shard-translit.js +0 -175
- package/out/src/tools/shard-translit.js.map +0 -1
- package/out/src/tools/sub-venue/harvest.d.ts +0 -100
- package/out/src/tools/sub-venue/harvest.d.ts.map +0 -1
- package/out/src/tools/sub-venue/harvest.js +0 -168
- package/out/src/tools/sub-venue/harvest.js.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.d.ts +0 -50
- package/out/src/tools/sub-venue/head-nouns.d.ts.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.js +0 -210
- package/out/src/tools/sub-venue/head-nouns.js.map +0 -1
- package/out/src/tools/sub-venue/surfaces.d.ts +0 -45
- package/out/src/tools/sub-venue/surfaces.d.ts.map +0 -1
- package/out/src/tools/sub-venue/surfaces.js +0 -77
- package/out/src/tools/sub-venue/surfaces.js.map +0 -1
- package/out/src/tools/sub-venue/table.d.ts +0 -229
- package/out/src/tools/sub-venue/table.d.ts.map +0 -1
- package/out/src/tools/sub-venue/table.js +0 -108
- package/out/src/tools/sub-venue/table.js.map +0 -1
- package/out/src/tools/sub-venue/wikidata.d.ts +0 -26
- package/out/src/tools/sub-venue/wikidata.d.ts.map +0 -1
- package/out/src/tools/sub-venue/wikidata.js +0 -62
- package/out/src/tools/sub-venue/wikidata.js.map +0 -1
- package/out/src/tools/sub-venue-lexicon.d.ts +0 -156
- package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
- package/out/src/tools/sub-venue-lexicon.js +0 -282
- package/out/src/tools/sub-venue-lexicon.js.map +0 -1
- package/out/src/tools/sub-venue-promotions.d.ts +0 -94
- package/out/src/tools/sub-venue-promotions.d.ts.map +0 -1
- package/out/src/tools/sub-venue-promotions.js +0 -266
- package/out/src/tools/sub-venue-promotions.js.map +0 -1
- package/out/src/types.d.ts +0 -221
- package/out/src/types.d.ts.map +0 -1
- package/out/src/types.js.map +0 -1
- package/out/src/utils/align.d.ts +0 -93
- package/out/src/utils/align.d.ts.map +0 -1
- package/out/src/utils/align.js +0 -234
- package/out/src/utils/align.js.map +0 -1
- package/out/src/utils/golden.d.ts +0 -69
- package/out/src/utils/golden.d.ts.map +0 -1
- package/out/src/utils/golden.js +0 -127
- package/out/src/utils/golden.js.map +0 -1
- package/out/src/utils/index.d.ts +0 -14
- package/out/src/utils/index.d.ts.map +0 -1
- package/out/src/utils/index.js +0 -14
- package/out/src/utils/index.js.map +0 -1
- package/out/src/utils/license.d.ts.map +0 -1
- package/out/src/utils/license.js.map +0 -1
- package/out/src/utils/parquet.d.ts +0 -162
- package/out/src/utils/parquet.d.ts.map +0 -1
- package/out/src/utils/parquet.js +0 -262
- package/out/src/utils/parquet.js.map +0 -1
- package/out/src/utils/split.d.ts +0 -127
- package/out/src/utils/split.d.ts.map +0 -1
- package/out/src/utils/split.js +0 -204
- package/out/src/utils/split.js.map +0 -1
- package/out/src/utils/tokenize.d.ts +0 -56
- package/out/src/utils/tokenize.d.ts.map +0 -1
- package/out/src/utils/tokenize.js +0 -48
- package/out/src/utils/tokenize.js.map +0 -1
- package/out/src/utils/wof-json.d.ts +0 -109
- package/out/src/utils/wof-json.d.ts.map +0 -1
- package/out/src/utils/wof-json.js +0 -173
- package/out/src/utils/wof-json.js.map +0 -1
- package/src/adapters/ban/adapter.ts +0 -191
- package/src/adapters/ban/street-decompose.ts +0 -96
- package/src/adapters/fcc-bdc/adapter.ts +0 -174
- package/src/adapters/geonames/adapter.ts +0 -200
- package/src/adapters/geonames-postal/adapter.ts +0 -119
- package/src/adapters/gnaf/adapter.ts +0 -149
- package/src/adapters/gnaf/assemble.ts +0 -226
- package/src/adapters/index.ts +0 -149
- package/src/adapters/openaddresses/adapter.ts +0 -251
- package/src/adapters/overture/adapter.ts +0 -162
- package/src/adapters/state-hi-schools/adapter.ts +0 -164
- package/src/adapters/synth-po-box/adapter.ts +0 -204
- package/src/adapters/tiger/adapter.ts +0 -253
- package/src/adapters/tiger/street-decompose.ts +0 -111
- package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -183
- package/src/adapters/usgov-imls-pls/adapter.ts +0 -143
- package/src/adapters/usgov-irs-bmf/adapter.ts +0 -163
- package/src/adapters/usgov-nad/adapter.ts +0 -348
- package/src/adapters/usgov-nppes/adapter.ts +0 -159
- package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -204
- package/src/adapters/utils/index.ts +0 -233
- package/src/adapters/wof-admin-jp/adapter.ts +0 -216
- package/src/adapters/wof-admin-json/adapter.ts +0 -256
- package/src/adapters/wof-json-rows.ts +0 -79
- package/src/adapters/wof-postalcode-json/adapter.ts +0 -183
- package/src/build.ts +0 -386
- package/src/index.ts +0 -14
- package/src/name-prone-us-suffixes.ts +0 -12
- package/src/parquet-wrapper/index.ts +0 -9
- package/src/parquet-wrapper/reader.ts +0 -97
- package/src/parquet-wrapper/schema.ts +0 -88
- package/src/parquet-wrapper/writer.ts +0 -110
- package/src/runner.ts +0 -317
- package/src/shard-recipes/anchor-absorption.ts +0 -103
- package/src/shard-recipes/bare-country.ts +0 -95
- package/src/shard-recipes/boundary-stress.ts +0 -101
- package/src/shard-recipes/country-balanced.ts +0 -524
- package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -111
- package/src/shard-recipes/fr-admin-split.ts +0 -239
- package/src/shard-recipes/fr-bare-street.ts +0 -170
- package/src/shard-recipes/fr-fragment.ts +0 -332
- package/src/shard-recipes/fr-lieudit.ts +0 -302
- package/src/shard-recipes/fr-order.ts +0 -258
- package/src/shard-recipes/german.ts +0 -170
- package/src/shard-recipes/house-venue.ts +0 -88
- package/src/shard-recipes/index.ts +0 -95
- package/src/shard-recipes/intersection.ts +0 -630
- package/src/shard-recipes/locale.ts +0 -599
- package/src/shard-recipes/nl-postcode.ts +0 -115
- package/src/shard-recipes/no-fragment.ts +0 -219
- package/src/shard-recipes/no-street-led.ts +0 -143
- package/src/shard-recipes/no-street.ts +0 -86
- package/src/shard-recipes/po-box-cedex.ts +0 -920
- package/src/shard-recipes/po-box.ts +0 -119
- package/src/shard-recipes/reviewed-postcode-tail.ts +0 -189
- package/src/shard-recipes/scaffold.ts +0 -360
- package/src/shard-recipes/si-bare-village.ts +0 -97
- package/src/shard-recipes/street-affix.ts +0 -826
- package/src/shard-recipes/street-bare.ts +0 -101
- package/src/shard-recipes/street.ts +0 -82
- package/src/shard-recipes/sub-venue-sources.ts +0 -885
- package/src/shard-recipes/sub-venue.ts +0 -984
- package/src/shard-recipes/trailing-region.ts +0 -183
- package/src/shard-recipes/unit.ts +0 -321
- package/src/synthesizers/anchor-absorption.ts +0 -290
- package/src/synthesizers/boundary-stress.ts +0 -531
- package/src/synthesizers/german.ts +0 -251
- package/src/synthesizers/house-venue.ts +0 -330
- package/src/synthesizers/intersection.ts +0 -232
- package/src/synthesizers/no-street.ts +0 -349
- package/src/synthesizers/po-box.ts +0 -339
- package/src/synthesizers/street.ts +0 -274
- package/src/synthesizers/utils.ts +0 -903
- package/src/tools/align-shard.ts +0 -70
- package/src/tools/audit.ts +0 -399
- package/src/tools/corpus-stats.ts +0 -184
- package/src/tools/fetch/ban.ts +0 -290
- package/src/tools/fetch/download.ts +0 -176
- package/src/tools/fetch/geonames-dump.ts +0 -267
- package/src/tools/fetch/geonames-postal.ts +0 -180
- package/src/tools/fetch/hrsa.ts +0 -68
- package/src/tools/fetch/imls-pls.ts +0 -158
- package/src/tools/fetch/index.ts +0 -147
- package/src/tools/fetch/nad.ts +0 -342
- package/src/tools/fetch/nppes.ts +0 -174
- package/src/tools/fetch/openaddresses.ts +0 -404
- package/src/tools/fetch/ourairports.ts +0 -171
- package/src/tools/fetch/ppd.ts +0 -137
- package/src/tools/fetch/state-hi-schools.ts +0 -208
- package/src/tools/fetch/state-sources.ts +0 -155
- package/src/tools/fetch/tiger-full.ts +0 -354
- package/src/tools/fetch/wikidata-subvenue.ts +0 -386
- package/src/tools/golden-expand.ts +0 -584
- package/src/tools/golden-promote.ts +0 -353
- package/src/tools/golden-relabel-street.ts +0 -685
- package/src/tools/index.ts +0 -28
- package/src/tools/ingest-csv.ts +0 -422
- package/src/tools/jsonl-to-parquet.ts +0 -221
- package/src/tools/lint-shard-vocab.ts +0 -409
- package/src/tools/lint-shard.ts +0 -543
- package/src/tools/overlay-manifest.ts +0 -157
- package/src/tools/overture-subvenue.ts +0 -215
- package/src/tools/postcode-triples.ts +0 -375
- package/src/tools/shard-kryptonite.ts +0 -139
- package/src/tools/shard-translit.ts +0 -245
- package/src/tools/sub-venue/harvest.ts +0 -235
- package/src/tools/sub-venue/head-nouns.ts +0 -242
- package/src/tools/sub-venue/surfaces.ts +0 -95
- package/src/tools/sub-venue/table.ts +0 -281
- package/src/tools/sub-venue/wikidata.ts +0 -85
- package/src/tools/sub-venue-lexicon.ts +0 -431
- package/src/tools/sub-venue-promotions.ts +0 -330
- package/src/types.ts +0 -247
- package/src/utils/align.ts +0 -331
- package/src/utils/golden.ts +0 -176
- package/src/utils/index.ts +0 -14
- package/src/utils/parquet.ts +0 -391
- package/src/utils/split.ts +0 -279
- package/src/utils/tokenize.ts +0 -78
- package/src/utils/wof-json.ts +0 -244
- /package/{src → lib}/adapters/state-ia-contractors/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-ny-notaries/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-tx-notaries/adapter.ts +0 -0
- /package/{src → lib}/codex/us-fips-state.ts +0 -0
- /package/{src → lib}/tools/gb-title-case.ts +0 -0
- /package/{src → lib}/utils/license.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/fcc-bdc/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/geonames/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/openaddresses/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/synth-po-box/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/tiger/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-nppes/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-samhsa-treatment-locator/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/wof-admin-jp/adapter.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.js +0 -0
- /package/out/{src/tools → tools}/fetch/ppd.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.js +0 -0
- /package/out/{src/tools → tools}/golden-promote.d.ts +0 -0
- /package/out/{src/tools → tools}/ingest-csv.d.ts +0 -0
- /package/out/{src/types.js → types.js} +0 -0
- /package/out/{src/utils → utils}/license.d.ts +0 -0
- /package/out/{src/utils → utils}/license.js +0 -0
|
@@ -1,276 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `fr-fragment` shard recipe (#727 T2) — the HOUSE-NUMBER-LICENCE lever.
|
|
7
|
-
*
|
|
8
|
-
* The measured problem (T1c, `2026-07-16-t1c-fragment-board-verdict.md`): the shipped model scores
|
|
9
|
-
* **0.925** on `<n> Rue X` and **0.215** on `Rue X`. Same streets, same model; the only difference
|
|
10
|
-
* is a leading number. It has learned that a house number LICENSES a street reading at all — strip
|
|
11
|
-
* it and a designator-led phrase parses as a locality, designator included:
|
|
12
|
-
*
|
|
13
|
-
* ```
|
|
14
|
-
* "Rue Montmartre" -> locality="Rue Montmartre"
|
|
15
|
-
* "Allee Poque" -> locality="Allee Poque"
|
|
16
|
-
* ```
|
|
17
|
-
*
|
|
18
|
-
* `Rue` can only mean street in French. The model is not mislabelling an ambiguous toponym; it is
|
|
19
|
-
* mislabelling `Rue`.
|
|
20
|
-
*
|
|
21
|
-
* WHY THE EXISTING RECIPE DOESN'T COVER THIS. {@link frBareStreetRecipe} (#251) mints
|
|
22
|
-
* `<n> Rue <name>, <City>` — the bare COMMA form, no postcode. It targets postcode-anchoring
|
|
23
|
-
* imbalance, and every row it emits still carries a house number AND a locality. It cannot teach
|
|
24
|
-
* the class above, because it never shows the model a street standing alone.
|
|
25
|
-
*
|
|
26
|
-
* WHAT THIS MINTS. Five street forms — the first three carry NO house number and NO locality, which
|
|
27
|
-
* is the whole point — plus the counter-distribution:
|
|
28
|
-
*
|
|
29
|
-
* 1. `bare-street` "Rue Montmartre"
|
|
30
|
-
* 2. `street-particle` "Rue de la Paix"
|
|
31
|
-
* 3. `date-name` "Allee du 11 Novembre 1918"
|
|
32
|
-
* 4. `street-housenumber` "12 Rue Montmartre" — the anchor, so the licence isn't UNLEARNED
|
|
33
|
-
* 5. `alnum-housenumber` "12 bis Rue Montmartre"
|
|
34
|
-
* 6. `bare-locality` "Mery-sur-Oise" — NEGATIVE: a bare toponym that IS a locality
|
|
35
|
-
*
|
|
36
|
-
* The **admin/street homonym** class (`Rue de Rome`) is deliberately NOT a separate form. Homonym
|
|
37
|
-
* streets are already in the register and fall into 1–3 naturally; there is nothing different to
|
|
38
|
-
* teach about them, because the lesson is identical — the designator makes it a street. The
|
|
39
|
-
* fragment board scores them separately (they need measuring, not minting), and the recipe would
|
|
40
|
-
* need a second pass over the commune set to label them, buying a `synth_method` string and no
|
|
41
|
-
* training signal.
|
|
42
|
-
*
|
|
43
|
-
* FORM 7 IS NOT OPTIONAL. T1c's standing prediction: the board's `bare-locality` cell reads 0.980
|
|
44
|
-
* for the WRONG REASON — the model calls everything without a house number a locality, and on bare
|
|
45
|
-
* localities that is accidentally right. Teach bare streets alone and the model has every incentive
|
|
46
|
-
* to flip that default rather than learn the distinction, trading a 0.215 for a 0.980. The shard
|
|
47
|
-
* must show BOTH bare forms so the discriminating evidence is the designator, which is the only
|
|
48
|
-
* thing that actually distinguishes them. This is the same counter-distribution principle
|
|
49
|
-
* {@link noStreetRecipe} established after synth-street pushed the model into "decompose mode".
|
|
50
|
-
*
|
|
51
|
-
* SPLIT. `--exclude-surfaces` takes the fragment board's reserved surface list
|
|
52
|
-
* (`mailwoman/eval-harness/fixtures/ban-fragments-fr.surfaces.txt`). Every listed surface is
|
|
53
|
-
* skipped — source-disjoint by normalized street SURFACE, never by record row. Row-disjoint leaks
|
|
54
|
-
* the surface across the boundary and measures memorization of `Rue de Rivoli` while claiming
|
|
55
|
-
* generalization to unseen streets. The recipe REFUSES to run without the list rather than
|
|
56
|
-
* silently minting a contaminated shard.
|
|
57
|
-
*
|
|
58
|
-
* MIX. The shard is ~145K rows off a 120K-tuple draw; the intended corpus mix is **5–10%**, set at
|
|
59
|
-
* assembly time by shard weight rather than by row count. Keep the cap: a shard that fixes fragments
|
|
60
|
-
* by degrading full addresses has moved the failure, not fixed it — which is what
|
|
61
|
-
* `street-housenumber` / `alnum-housenumber` on the fragment board and the global parity floor are
|
|
62
|
-
* there to catch. `date-name` is ~0.5% of the shard because BAN only holds ~1,418 date-name streets
|
|
63
|
-
* after filtering and the tuple extractor already takes every one; if that class needs more, the
|
|
64
|
-
* lever is shard weight, not invented data.
|
|
65
|
-
*
|
|
66
|
-
* ⚠ Convention loss-mask: like {@link frBareStreetRecipe}, this recipe TEACHES FR `street_prefix`.
|
|
67
|
-
* The conventions loss-mask forbids it for FR and will `-inf` these gold labels (the v1.6.0 ~7M-loss
|
|
68
|
-
* blow-up). Disable that mask for any run including this shard.
|
|
69
|
-
*/
|
|
70
|
-
import { TextSpliterator } from "spliterator";
|
|
71
|
-
import { decomposeFrStreet } from "../adapters/ban/street-decompose.js";
|
|
72
|
-
import { alignAndWrite, makeMulberry32, readTuples, shardSourceID } from "./scaffold.js";
|
|
73
|
-
/**
|
|
74
|
-
* House numbers, weighted toward the small values that dominate real BAN rows.
|
|
75
|
-
*/
|
|
76
|
-
/* oxlint-disable sister-software/no-unnamed-threshold -- the bare decimals below are weighted-sampler
|
|
77
|
-
cutoffs, not thresholds: `const r = random()` followed by a cascade of `r < 0.4` branches IS the
|
|
78
|
-
output distribution, and reading the cascade top-to-bottom is how you see it. Naming each cutoff
|
|
79
|
-
would hide the distribution behind a wall of identifiers. Genuine thresholds in these files are
|
|
80
|
-
extracted as named constants above. */
|
|
81
|
-
const HOUSE_NUMBERS = [
|
|
82
|
-
1, 1, 2, 2, 3, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 15, 16, 18, 20, 21, 24, 27, 30, 33, 42, 57, 68, 84, 102, 115, 140,
|
|
83
|
-
];
|
|
84
|
-
/**
|
|
85
|
-
* FR alphanumeric house-number forms. `bis`/`ter` are separated; a bare letter is suffixed.
|
|
86
|
-
*/
|
|
87
|
-
const ALNUM_SUFFIXES = ["bis", "ter", "A", "B"];
|
|
88
|
-
const norm = (value) => value
|
|
89
|
-
.normalize("NFD")
|
|
90
|
-
.replaceAll(/[̀-ͯ]/g, "")
|
|
91
|
-
.toLowerCase()
|
|
92
|
-
.replaceAll(/\s+/g, " ")
|
|
93
|
-
.trim();
|
|
94
|
-
/**
|
|
95
|
-
* French commune convention: capitalize each element, leave the joining particles lowercase. `saint-jean-de-luz` →
|
|
96
|
-
* `Saint-Jean-de-Luz`, not `Saint-Jean-De-Luz`.
|
|
97
|
-
*
|
|
98
|
-
* Needed because BAN's sharded DBs keep only `locality_base` — normalized, lowercase, accent-stripped. Emitting that
|
|
99
|
-
* verbatim would teach the counter-distribution that a lowercase accent-stripped string is a locality, which is not a
|
|
100
|
-
* fact about French and would not match the fragment board (which reconstructs the same casing). The accents are gone
|
|
101
|
-
* from the source and cannot be recovered here; the casing can.
|
|
102
|
-
*/
|
|
103
|
-
const FR_LOWER = new Set([
|
|
104
|
-
"le",
|
|
105
|
-
"la",
|
|
106
|
-
"les",
|
|
107
|
-
"de",
|
|
108
|
-
"du",
|
|
109
|
-
"des",
|
|
110
|
-
"d",
|
|
111
|
-
"l",
|
|
112
|
-
"sur",
|
|
113
|
-
"sous",
|
|
114
|
-
"en",
|
|
115
|
-
"aux",
|
|
116
|
-
"au",
|
|
117
|
-
"et",
|
|
118
|
-
"lez",
|
|
119
|
-
]);
|
|
120
|
-
export function frTitleCase(value) {
|
|
121
|
-
const cap = (token, first) => !first && FR_LOWER.has(token) ? token : token.charAt(0).toUpperCase() + token.slice(1);
|
|
122
|
-
return value
|
|
123
|
-
.split(" ")
|
|
124
|
-
.map((word, wordIndex) => word
|
|
125
|
-
.split("-")
|
|
126
|
-
.map((bit, bitIndex) => cap(bit, wordIndex === 0 && bitIndex === 0))
|
|
127
|
-
.join("-"))
|
|
128
|
-
.join(" ");
|
|
129
|
-
}
|
|
130
|
-
/**
|
|
131
|
-
* Does the street name carry a particle? Decides the particle vs bare classification.
|
|
132
|
-
*/
|
|
133
|
-
const PARTICLE = /\b(de la|de l'|du|des|de|d'|le|la|les)\b/i;
|
|
134
|
-
/**
|
|
135
|
-
* Does the street name carry date material (a year, or a day + French month)?
|
|
136
|
-
*/
|
|
137
|
-
const DATEISH = /\b(1[0-9]|20)\d{2}\b|\b\d{1,2}\s+(janvier|f[ée]vrier|mars|avril|mai|juin|juillet|ao[ûu]t|septembre|octobre|novembre|d[ée]cembre)\b/i;
|
|
138
|
-
/**
|
|
139
|
-
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
140
|
-
* and `description` below for the surface form it generates.
|
|
141
|
-
*/
|
|
142
|
-
export const frFragmentRecipe = {
|
|
143
|
-
name: "fr-fragment",
|
|
144
|
-
description: "FR street fragments with NO house number (#727 T2): the house-number-licence lever — bare/particle/date-name/homonym + the bare-locality counter",
|
|
145
|
-
mode: "tuples",
|
|
146
|
-
options: [
|
|
147
|
-
{
|
|
148
|
-
flag: "--exclude-surfaces <path>",
|
|
149
|
-
description: "REQUIRED. The fragment board's reserved surface list; every listed street is skipped.",
|
|
150
|
-
},
|
|
151
|
-
{
|
|
152
|
-
flag: "--hn-prob <n>",
|
|
153
|
-
description: "Share of rows carrying a house number (default 0.35 — the anchor, not the point)",
|
|
154
|
-
},
|
|
155
|
-
{
|
|
156
|
-
flag: "--bare-prob <n>",
|
|
157
|
-
description: "Share of NO-house-number rows that are bare LOCALITIES (default 0.25 — the counter)",
|
|
158
|
-
},
|
|
159
|
-
],
|
|
160
|
-
async run(opts, write) {
|
|
161
|
-
const random = makeMulberry32(opts.seed);
|
|
162
|
-
const excludePath = opts.excludeSurfaces;
|
|
163
|
-
if (!excludePath) {
|
|
164
|
-
throw new Error("fr-fragment: --exclude-surfaces is REQUIRED. Pass the fragment board's reserved list " +
|
|
165
|
-
"(mailwoman/eval-harness/fixtures/ban-fragments-fr.surfaces.txt) or this shard trains on its own eval set. " +
|
|
166
|
-
"Source-disjoint by street SURFACE is the split discipline; there is no safe default.");
|
|
167
|
-
}
|
|
168
|
-
const excluded = new Set();
|
|
169
|
-
for await (const line of TextSpliterator.fromAsync(excludePath)) {
|
|
170
|
-
const trimmed = line.trim();
|
|
171
|
-
if (trimmed && !trimmed.startsWith("#")) {
|
|
172
|
-
excluded.add(trimmed);
|
|
173
|
-
}
|
|
174
|
-
}
|
|
175
|
-
if (!excluded.size)
|
|
176
|
-
throw new Error(`fr-fragment: --exclude-surfaces "${excludePath}" listed no surfaces`);
|
|
177
|
-
const hnProb = opts.hnProb ?? 0.35;
|
|
178
|
-
const bareLocalityProb = opts.bareProb ?? 0.25;
|
|
179
|
-
// The locality pool is harvested from the tuples themselves — every BAN row carries its
|
|
180
|
-
// commune, so the counter-distribution needs no second source.
|
|
181
|
-
const localities = new Set();
|
|
182
|
-
let read = 0;
|
|
183
|
-
let emitted = 0;
|
|
184
|
-
let skipped = 0;
|
|
185
|
-
let contaminated = 0;
|
|
186
|
-
for await (const tuple of readTuples(opts.input)) {
|
|
187
|
-
read++;
|
|
188
|
-
const fullStreet = String(tuple.street ?? "").trim();
|
|
189
|
-
const locality = String(tuple.locality ?? "").trim();
|
|
190
|
-
if (locality) {
|
|
191
|
-
localities.add(locality);
|
|
192
|
-
}
|
|
193
|
-
if (!fullStreet) {
|
|
194
|
-
skipped++;
|
|
195
|
-
continue;
|
|
196
|
-
}
|
|
197
|
-
// THE SPLIT. A surface on the fragment board never enters training.
|
|
198
|
-
if (excluded.has(norm(fullStreet))) {
|
|
199
|
-
contaminated++;
|
|
200
|
-
continue;
|
|
201
|
-
}
|
|
202
|
-
const { prefix, street } = decomposeFrStreet(fullStreet);
|
|
203
|
-
// The failing class is the designator-led street. A no-prefix nom_voie ("La Ville Mois")
|
|
204
|
-
// is a different problem and would muddy the signal.
|
|
205
|
-
if (!prefix || !street) {
|
|
206
|
-
skipped++;
|
|
207
|
-
continue;
|
|
208
|
-
}
|
|
209
|
-
const carriesNumber = random() < hnProb;
|
|
210
|
-
const components = { street_prefix: prefix, street };
|
|
211
|
-
let raw = `${prefix} ${street}`;
|
|
212
|
-
let klass = DATEISH.test(street) ? "date-name" : PARTICLE.test(street) ? "street-particle" : "bare-street";
|
|
213
|
-
if (carriesNumber) {
|
|
214
|
-
const number = HOUSE_NUMBERS[Math.floor(random() * HOUSE_NUMBERS.length)];
|
|
215
|
-
const alnum = random() < 0.25;
|
|
216
|
-
const suffix = ALNUM_SUFFIXES[Math.floor(random() * ALNUM_SUFFIXES.length)];
|
|
217
|
-
const houseNumber = alnum
|
|
218
|
-
? suffix === "bis" || suffix === "ter"
|
|
219
|
-
? `${number} ${suffix}`
|
|
220
|
-
: `${number}${suffix}`
|
|
221
|
-
: String(number);
|
|
222
|
-
components.house_number = houseNumber;
|
|
223
|
-
raw = `${houseNumber} ${prefix} ${street}`;
|
|
224
|
-
klass = alnum ? "alnum-housenumber" : "street-housenumber";
|
|
225
|
-
}
|
|
226
|
-
const sourceID = shardSourceID("synth-fr-fragment", { ...components, v: String(read) });
|
|
227
|
-
if (alignAndWrite(write, {
|
|
228
|
-
raw,
|
|
229
|
-
components,
|
|
230
|
-
country: "FR",
|
|
231
|
-
locale: "fr-FR",
|
|
232
|
-
source: "synth-fr-fragment",
|
|
233
|
-
source_id: sourceID,
|
|
234
|
-
corpus_version: "0.9.4",
|
|
235
|
-
license: "Synthetic — fr-fragment; (street, commune) from BAN (Base Adresse Nationale, Licence Ouverte)",
|
|
236
|
-
}, `fr-fragment:${klass}`)) {
|
|
237
|
-
emitted++;
|
|
238
|
-
}
|
|
239
|
-
else {
|
|
240
|
-
skipped++;
|
|
241
|
-
}
|
|
242
|
-
}
|
|
243
|
-
// MARK: counter-distribution — bare localities
|
|
244
|
-
// Minted last so the locality pool is complete. Without these the model can satisfy every row
|
|
245
|
-
// above by flipping its default from "bare => locality" to "bare => street", which trades one
|
|
246
|
-
// broken prior for another and would show up as bare-locality collapsing on the board.
|
|
247
|
-
const pool = [...localities].toSorted();
|
|
248
|
-
const wanted = Math.round((emitted / Math.max(1, 1 - bareLocalityProb)) * bareLocalityProb);
|
|
249
|
-
for (let i = 0; i < wanted && pool.length; i++) {
|
|
250
|
-
// BAN gives `locality_base` normalized; restore the casing the fragment board also
|
|
251
|
-
// reconstructs, so train and eval show the model the same shape of French.
|
|
252
|
-
const name = frTitleCase(pool[Math.floor(random() * pool.length)]);
|
|
253
|
-
const sourceID = shardSourceID("synth-fr-fragment", { locality: name, v: `neg-${i}` });
|
|
254
|
-
if (alignAndWrite(write, {
|
|
255
|
-
raw: name,
|
|
256
|
-
components: { locality: name },
|
|
257
|
-
country: "FR",
|
|
258
|
-
locale: "fr-FR",
|
|
259
|
-
source: "synth-fr-fragment",
|
|
260
|
-
source_id: sourceID,
|
|
261
|
-
corpus_version: "0.9.4",
|
|
262
|
-
license: "Synthetic — fr-fragment counter-distribution; commune from BAN (Licence Ouverte)",
|
|
263
|
-
}, "fr-fragment:bare-locality")) {
|
|
264
|
-
emitted++;
|
|
265
|
-
}
|
|
266
|
-
else {
|
|
267
|
-
skipped++;
|
|
268
|
-
}
|
|
269
|
-
}
|
|
270
|
-
if (contaminated) {
|
|
271
|
-
console.error(`fr-fragment: skipped ${contaminated} rows whose street surface is reserved by the fragment board`);
|
|
272
|
-
}
|
|
273
|
-
return { read, emitted, skipped };
|
|
274
|
-
},
|
|
275
|
-
};
|
|
276
|
-
//# sourceMappingURL=fr-fragment.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"fr-fragment.js","sourceRoot":"","sources":["../../../src/shard-recipes/fr-fragment.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAoEG;AAEH,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C,OAAO,EAAE,iBAAiB,EAAE,MAAM,qCAAqC,CAAA;AACvE,OAAO,EAAE,aAAa,EAAE,cAAc,EAAE,UAAU,EAAoB,aAAa,EAAE,MAAM,eAAe,CAAA;AAE1G;;GAEG;AACH;;;;yCAIyC;AAEzC,MAAM,aAAa,GAAG;IACrB,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,CAAC,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG;CACrH,CAAA;AAED;;GAEG;AACH,MAAM,cAAc,GAAG,CAAC,KAAK,EAAE,KAAK,EAAE,GAAG,EAAE,GAAG,CAAC,CAAA;AAE/C,MAAM,IAAI,GAAG,CAAC,KAAa,EAAU,EAAE,CACtC,KAAK;KACH,SAAS,CAAC,KAAK,CAAC;KAChB,UAAU,CAAC,QAAQ,EAAE,EAAE,CAAC;KACxB,WAAW,EAAE;KACb,UAAU,CAAC,MAAM,EAAE,GAAG,CAAC;KACvB,IAAI,EAAE,CAAA;AAET;;;;;;;;GAQG;AACH,MAAM,QAAQ,GAAG,IAAI,GAAG,CAAC;IACxB,IAAI;IACJ,IAAI;IACJ,KAAK;IACL,IAAI;IACJ,IAAI;IACJ,KAAK;IACL,GAAG;IACH,GAAG;IACH,KAAK;IACL,MAAM;IACN,IAAI;IACJ,KAAK;IACL,IAAI;IACJ,IAAI;IACJ,KAAK;CACL,CAAC,CAAA;AAEF,MAAM,UAAU,WAAW,CAAC,KAAa;IACxC,MAAM,GAAG,GAAG,CAAC,KAAa,EAAE,KAAc,EAAU,EAAE,CACrD,CAAC,KAAK,IAAI,QAAQ,CAAC,GAAG,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,WAAW,EAAE,GAAG,KAAK,CAAC,KAAK,CAAC,CAAC,CAAC,CAAA;IAEvF,OAAO,KAAK;SACV,KAAK,CAAC,GAAG,CAAC;SACV,GAAG,CAAC,CAAC,IAAI,EAAE,SAAS,EAAE,EAAE,CACxB,IAAI;SACF,KAAK,CAAC,GAAG,CAAC;SACV,GAAG,CAAC,CAAC,GAAG,EAAE,QAAQ,EAAE,EAAE,CAAC,GAAG,CAAC,GAAG,EAAE,SAAS,KAAK,CAAC,IAAI,QAAQ,KAAK,CAAC,CAAC,CAAC;SACnE,IAAI,CAAC,GAAG,CAAC,CACX;SACA,IAAI,CAAC,GAAG,CAAC,CAAA;AACZ,CAAC;AAED;;GAEG;AACH,MAAM,QAAQ,GAAG,2CAA2C,CAAA;AAE5D;;GAEG;AACH,MAAM,OAAO,GACZ,qIAAqI,CAAA;AAEtI;;;GAGG;AACH,MAAM,CAAC,MAAM,gBAAgB,GAAgB;IAC5C,IAAI,EAAE,aAAa;IACnB,WAAW,EACV,kJAAkJ;IACnJ,IAAI,EAAE,QAAQ;IACd,OAAO,EAAE;QACR;YACC,IAAI,EAAE,2BAA2B;YACjC,WAAW,EAAE,uFAAuF;SACpG;QACD;YACC,IAAI,EAAE,eAAe;YACrB,WAAW,EAAE,kFAAkF;SAC/F;QACD;YACC,IAAI,EAAE,iBAAiB;YACvB,WAAW,EAAE,qFAAqF;SAClG;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,4GAA4G;gBAC5G,sFAAsF,CACvF,CAAA;QACF,CAAC;QAED,MAAM,QAAQ,GAAG,IAAI,GAAG,EAAU,CAAA;QAElC,IAAI,KAAK,EAAE,MAAM,IAAI,IAAI,eAAe,CAAC,SAAS,CAAC,WAAW,CAAC,EAAE,CAAC;YACjE,MAAM,OAAO,GAAG,IAAI,CAAC,IAAI,EAAE,CAAA;YAE3B,IAAI,OAAO,IAAI,CAAC,OAAO,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC;gBACzC,QAAQ,CAAC,GAAG,CAAC,OAAO,CAAC,CAAA;YACtB,CAAC;QACF,CAAC;QAED,IAAI,CAAC,QAAQ,CAAC,IAAI;YAAE,MAAM,IAAI,KAAK,CAAC,oCAAoC,WAAW,sBAAsB,CAAC,CAAA;QAE1G,MAAM,MAAM,GAAG,IAAI,CAAC,MAAM,IAAI,IAAI,CAAA;QAClC,MAAM,gBAAgB,GAAG,IAAI,CAAC,QAAQ,IAAI,IAAI,CAAA;QAE9C,wFAAwF;QACxF,+DAA+D;QAC/D,MAAM,UAAU,GAAG,IAAI,GAAG,EAAU,CAAA;QAEpC,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,KAAK,IAAI,UAAU,CAAC,IAAI,CAAC,KAAM,CAAC,EAAE,CAAC;YACnD,IAAI,EAAE,CAAA;YACN,MAAM,UAAU,GAAG,MAAM,CAAC,KAAK,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,CAAA;YACpD,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,CAAC,UAAU,EAAE,CAAC;gBACjB,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,oEAAoE;YACpE,IAAI,QAAQ,CAAC,GAAG,CAAC,IAAI,CAAC,UAAU,CAAC,CAAC,EAAE,CAAC;gBACpC,YAAY,EAAE,CAAA;gBAEd,SAAQ;YACT,CAAC;YAED,MAAM,EAAE,MAAM,EAAE,MAAM,EAAE,GAAG,iBAAiB,CAAC,UAAU,CAAC,CAAA;YAExD,yFAAyF;YACzF,qDAAqD;YACrD,IAAI,CAAC,MAAM,IAAI,CAAC,MAAM,EAAE,CAAC;gBACxB,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,MAAM,aAAa,GAAG,MAAM,EAAE,GAAG,MAAM,CAAA;YACvC,MAAM,UAAU,GAA2B,EAAE,aAAa,EAAE,MAAM,EAAE,MAAM,EAAE,CAAA;YAC5E,IAAI,GAAG,GAAG,GAAG,MAAM,IAAI,MAAM,EAAE,CAAA;YAC/B,IAAI,KAAK,GAAG,OAAO,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,WAAW,CAAC,CAAC,CAAC,QAAQ,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,iBAAiB,CAAC,CAAC,CAAC,aAAa,CAAA;YAE1G,IAAI,aAAa,EAAE,CAAC;gBACnB,MAAM,MAAM,GAAG,aAAa,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,aAAa,CAAC,MAAM,CAAC,CAAE,CAAA;gBAC1E,MAAM,KAAK,GAAG,MAAM,EAAE,GAAG,IAAI,CAAA;gBAC7B,MAAM,MAAM,GAAG,cAAc,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,cAAc,CAAC,MAAM,CAAC,CAAE,CAAA;gBAE5E,MAAM,WAAW,GAAG,KAAK;oBACxB,CAAC,CAAC,MAAM,KAAK,KAAK,IAAI,MAAM,KAAK,KAAK;wBACrC,CAAC,CAAC,GAAG,MAAM,IAAI,MAAM,EAAE;wBACvB,CAAC,CAAC,GAAG,MAAM,GAAG,MAAM,EAAE;oBACvB,CAAC,CAAC,MAAM,CAAC,MAAM,CAAC,CAAA;gBAEjB,UAAU,CAAC,YAAY,GAAG,WAAW,CAAA;gBACrC,GAAG,GAAG,GAAG,WAAW,IAAI,MAAM,IAAI,MAAM,EAAE,CAAA;gBAC1C,KAAK,GAAG,KAAK,CAAC,CAAC,CAAC,mBAAmB,CAAC,CAAC,CAAC,oBAAoB,CAAA;YAC3D,CAAC;YAED,MAAM,QAAQ,GAAG,aAAa,CAAC,mBAAmB,EAAE,EAAE,GAAG,UAAU,EAAE,CAAC,EAAE,MAAM,CAAC,IAAI,CAAC,EAAE,CAAC,CAAA;YAEvF,IACC,aAAa,CACZ,KAAK,EACL;gBACC,GAAG;gBACH,UAAU;gBACV,OAAO,EAAE,IAAI;gBACb,MAAM,EAAE,OAAO;gBACf,MAAM,EAAE,mBAAmB;gBAC3B,SAAS,EAAE,QAAQ;gBACnB,cAAc,EAAE,OAAO;gBACvB,OAAO,EAAE,+FAA+F;aACxG,EACD,eAAe,KAAK,EAAE,CACtB,EACA,CAAC;gBACF,OAAO,EAAE,CAAA;YACV,CAAC;iBAAM,CAAC;gBACP,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;QAED,+CAA+C;QAC/C,8FAA8F;QAC9F,8FAA8F;QAC9F,uFAAuF;QACvF,MAAM,IAAI,GAAG,CAAC,GAAG,UAAU,CAAC,CAAC,QAAQ,EAAE,CAAA;QACvC,MAAM,MAAM,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,OAAO,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,GAAG,gBAAgB,CAAC,CAAC,GAAG,gBAAgB,CAAC,CAAA;QAE3F,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,MAAM,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;YAChD,mFAAmF;YACnF,2EAA2E;YAC3E,MAAM,IAAI,GAAG,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,IAAI,CAAC,MAAM,CAAC,CAAE,CAAC,CAAA;YACnE,MAAM,QAAQ,GAAG,aAAa,CAAC,mBAAmB,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE,CAAC,EAAE,OAAO,CAAC,EAAE,EAAE,CAAC,CAAA;YAEtF,IACC,aAAa,CACZ,KAAK,EACL;gBACC,GAAG,EAAE,IAAI;gBACT,UAAU,EAAE,EAAE,QAAQ,EAAE,IAAI,EAAE;gBAC9B,OAAO,EAAE,IAAI;gBACb,MAAM,EAAE,OAAO;gBACf,MAAM,EAAE,mBAAmB;gBAC3B,SAAS,EAAE,QAAQ;gBACnB,cAAc,EAAE,OAAO;gBACvB,OAAO,EAAE,kFAAkF;aAC3F,EACD,2BAA2B,CAC3B,EACA,CAAC;gBACF,OAAO,EAAE,CAAA;YACV,CAAC;iBAAM,CAAC;gBACP,OAAO,EAAE,CAAA;YACV,CAAC;QACF,CAAC;QAED,IAAI,YAAY,EAAE,CAAC;YAClB,OAAO,CAAC,KAAK,CAAC,wBAAwB,YAAY,8DAA8D,CAAC,CAAA;QAClH,CAAC;QAED,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;IAClC,CAAC;CACD,CAAA"}
|
|
@@ -1,32 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `fr-lieudit` shard recipe — FR lieu-dit (hamlet/place) `dependent_locality` coverage
|
|
7
|
-
* (`.superpowers/sdd/deploc-world-survey.md`, FR section, 2026-07-22). Streams every BAN
|
|
8
|
-
* `adresses-<dept>.csv` dump under `--ban-dir` through `@mailwoman/ban/sdk`'s
|
|
9
|
-
* `extractBANAddrPoints`, which now surfaces a cleaned `lieuDit` per record (junk/dup filtering
|
|
10
|
-
* lives in `ban/sdk/extract.ts`'s `cleanLieuDit`, not duplicated here). Only rows carrying a clean
|
|
11
|
-
* lieu-dit survive into the pool; the existing `ban`/`synth-fr` sources and their emitted rows are
|
|
12
|
-
* untouched — this recipe reads the SAME raw CSVs but emits under its own source name.
|
|
13
|
-
*
|
|
14
|
-
* Mapping: lieu-dit → `dependent_locality`, commune → `locality`. Rendered to match the formatter's
|
|
15
|
-
* FR `place`-slot convention (`fix(formatter): render dependent_locality for neither-slot templates`,
|
|
16
|
-
* b1edc1b7, verified via a `formatAddress` smoke call): house+street on line 1, the lieu-dit ALONE on
|
|
17
|
-
* line 2, postcode+commune on line 3 — French postal convention (La Poste's line 5).
|
|
18
|
-
*
|
|
19
|
-
* ~1.69M clean rows survive the filter nationally (26M total BAN rows, 1.81M raw `nom_ld` fills, ~6.6%
|
|
20
|
-
* junk/dup). The pool is read in full (small string tuples only — no coordinates needed) and
|
|
21
|
-
* Fisher-Yates shuffled with the seeded PRNG before slicing to `--count`, rather than sampled WITH
|
|
22
|
-
* replacement — at a `--count` a sizeable fraction of the pool, with-replacement draws would produce a
|
|
23
|
-
* large duplicate rate (birthday-paradox math: ~190k expected collisions at count=800k over a 1.69M
|
|
24
|
-
* pool).
|
|
25
|
-
*/
|
|
26
|
-
import { type ShardRecipe } from "./scaffold.ts";
|
|
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
|
-
*/
|
|
31
|
-
export declare const frLieuditRecipe: ShardRecipe;
|
|
32
|
-
//# sourceMappingURL=fr-lieudit.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"fr-lieudit.d.ts","sourceRoot":"","sources":["../../../src/shard-recipes/fr-lieudit.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;GAwBG;AAgBH,OAAO,EAAkB,KAAK,WAAW,EAAE,MAAM,eAAe,CAAA;AA2IhE;;;GAGG;AACH,eAAO,MAAM,eAAe,EAAE,WAsH7B,CAAA"}
|
|
@@ -1,226 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `fr-lieudit` shard recipe — FR lieu-dit (hamlet/place) `dependent_locality` coverage
|
|
7
|
-
* (`.superpowers/sdd/deploc-world-survey.md`, FR section, 2026-07-22). Streams every BAN
|
|
8
|
-
* `adresses-<dept>.csv` dump under `--ban-dir` through `@mailwoman/ban/sdk`'s
|
|
9
|
-
* `extractBANAddrPoints`, which now surfaces a cleaned `lieuDit` per record (junk/dup filtering
|
|
10
|
-
* lives in `ban/sdk/extract.ts`'s `cleanLieuDit`, not duplicated here). Only rows carrying a clean
|
|
11
|
-
* lieu-dit survive into the pool; the existing `ban`/`synth-fr` sources and their emitted rows are
|
|
12
|
-
* untouched — this recipe reads the SAME raw CSVs but emits under its own source name.
|
|
13
|
-
*
|
|
14
|
-
* Mapping: lieu-dit → `dependent_locality`, commune → `locality`. Rendered to match the formatter's
|
|
15
|
-
* FR `place`-slot convention (`fix(formatter): render dependent_locality for neither-slot templates`,
|
|
16
|
-
* b1edc1b7, verified via a `formatAddress` smoke call): house+street on line 1, the lieu-dit ALONE on
|
|
17
|
-
* line 2, postcode+commune on line 3 — French postal convention (La Poste's line 5).
|
|
18
|
-
*
|
|
19
|
-
* ~1.69M clean rows survive the filter nationally (26M total BAN rows, 1.81M raw `nom_ld` fills, ~6.6%
|
|
20
|
-
* junk/dup). The pool is read in full (small string tuples only — no coordinates needed) and
|
|
21
|
-
* Fisher-Yates shuffled with the seeded PRNG before slicing to `--count`, rather than sampled WITH
|
|
22
|
-
* replacement — at a `--count` a sizeable fraction of the pool, with-replacement draws would produce a
|
|
23
|
-
* large duplicate rate (birthday-paradox math: ~190k expected collisions at count=800k over a 1.69M
|
|
24
|
-
* pool).
|
|
25
|
-
*/
|
|
26
|
-
import { readdirSync } from "node:fs";
|
|
27
|
-
import { join } from "node:path";
|
|
28
|
-
import { extractBANAddrPoints } from "@mailwoman/ban/sdk";
|
|
29
|
-
import { COUNTRY_SURFACE_FORMS } from "@mailwoman/codex/country";
|
|
30
|
-
import { isPresent } from "@mailwoman/core/objects";
|
|
31
|
-
import { dataRootPath } from "@mailwoman/core/utils";
|
|
32
|
-
import { stableSourceID } from "#adapters/utils";
|
|
33
|
-
import { alignRow } from "#utils";
|
|
34
|
-
import { decomposeFrStreet } from "../adapters/ban/street-decompose.js";
|
|
35
|
-
import { makeMulberry32 } from "./scaffold.js";
|
|
36
|
-
/**
|
|
37
|
-
* Matches the `ban` adapter's Tier-B election for BAN data.
|
|
38
|
-
*/
|
|
39
|
-
const DEFAULT_LICENSE = "Licence Ouverte 2.0";
|
|
40
|
-
/**
|
|
41
|
-
* Enumerate `adresses-<dept>.csv[.gz]` files in `banDir`, ONE path per département. Excludes the `merged`/`france`
|
|
42
|
-
* aggregates (they duplicate the per-département rows) and, when both a `.csv` and a `.csv.gz` exist for the same dept
|
|
43
|
-
* (observed on disk for 13/2A/48/69/75 — a stale re-fetch artifact), prefers the uncompressed `.csv` — mirrors
|
|
44
|
-
* `ban/scripts/build-address-point-shard.ts`'s `departementFiles`, which hit and fixed this exact double-count trap
|
|
45
|
-
* first.
|
|
46
|
-
*/
|
|
47
|
-
function departementFiles(banDir) {
|
|
48
|
-
const byDept = new Map();
|
|
49
|
-
for (const name of readdirSync(banDir).toSorted()) {
|
|
50
|
-
const m = /^adresses-(.+?)\.csv(\.gz)?$/.exec(name);
|
|
51
|
-
if (!m)
|
|
52
|
-
continue;
|
|
53
|
-
const dept = m[1];
|
|
54
|
-
if (dept === "merged" || dept === "france")
|
|
55
|
-
continue;
|
|
56
|
-
const existing = byDept.get(dept);
|
|
57
|
-
if (!existing || (existing.endsWith(".gz") && !name.endsWith(".gz"))) {
|
|
58
|
-
byDept.set(dept, join(banDir, name));
|
|
59
|
-
}
|
|
60
|
-
}
|
|
61
|
-
return [...byDept.keys()].toSorted().map((dept) => byDept.get(dept));
|
|
62
|
-
}
|
|
63
|
-
/**
|
|
64
|
-
* Stream every département file, keeping only rows with a clean `lieuDit` (junk/dup filtering lives in `ban/sdk`).
|
|
65
|
-
*/
|
|
66
|
-
async function readLieuDitPool(banDir) {
|
|
67
|
-
const files = departementFiles(banDir);
|
|
68
|
-
if (!files.length) {
|
|
69
|
-
throw new Error(`No BAN adresses-<dept>.csv files found in ${banDir} — fetch BAN first (\`mailwoman corpus fetch ban\`).`);
|
|
70
|
-
}
|
|
71
|
-
const pool = [];
|
|
72
|
-
let scanned = 0;
|
|
73
|
-
for (const path of files) {
|
|
74
|
-
let deptCount = 0;
|
|
75
|
-
for await (const rec of extractBANAddrPoints(path)) {
|
|
76
|
-
scanned++;
|
|
77
|
-
if (!rec.lieuDit || !rec.city)
|
|
78
|
-
continue;
|
|
79
|
-
pool.push({
|
|
80
|
-
numero: rec.numero,
|
|
81
|
-
rep: rec.rep,
|
|
82
|
-
street: rec.street,
|
|
83
|
-
postcode: rec.postcode,
|
|
84
|
-
locality: rec.city,
|
|
85
|
-
dependentLocality: rec.lieuDit,
|
|
86
|
-
});
|
|
87
|
-
deptCount++;
|
|
88
|
-
}
|
|
89
|
-
console.error(` ${path}: ${deptCount.toLocaleString()} clean lieu-dit rows`);
|
|
90
|
-
}
|
|
91
|
-
console.error(` scanned ${scanned.toLocaleString()} BAN rows across ${files.length} départements → pool=${pool.length.toLocaleString()}`);
|
|
92
|
-
return pool;
|
|
93
|
-
}
|
|
94
|
-
/**
|
|
95
|
-
* `house_number` = `numero` + folded `rep` ("10 bis"), matching the `ban` adapter's own composition.
|
|
96
|
-
*/
|
|
97
|
-
function composeHouseNumber(numero, rep) {
|
|
98
|
-
return rep ? `${numero} ${rep}` : numero;
|
|
99
|
-
}
|
|
100
|
-
/**
|
|
101
|
-
* Render the raw address string: house+street line, the lieu-dit ALONE on its own line, postcode+commune line — the
|
|
102
|
-
* exact shape `formatAddress` produces for FR's `place`-slot mapping (verified via a smoke call before this recipe was
|
|
103
|
-
* written; see the module docstring).
|
|
104
|
-
*/
|
|
105
|
-
function composeRaw(house, street, dependentLocality, postcode, locality) {
|
|
106
|
-
const lines = [];
|
|
107
|
-
const streetLine = `${house} ${street}`.trim();
|
|
108
|
-
if (streetLine) {
|
|
109
|
-
lines.push(streetLine);
|
|
110
|
-
}
|
|
111
|
-
lines.push(dependentLocality);
|
|
112
|
-
const cityLine = [postcode, locality].filter(isPresent).join(" ").trim();
|
|
113
|
-
if (cityLine) {
|
|
114
|
-
lines.push(cityLine);
|
|
115
|
-
}
|
|
116
|
-
return lines.join("\n");
|
|
117
|
-
}
|
|
118
|
-
/**
|
|
119
|
-
* Fisher-Yates shuffle, in place, with the recipe's seeded PRNG — reproducible sampling without replacement.
|
|
120
|
-
*/
|
|
121
|
-
function shuffleInPlace(arr, random) {
|
|
122
|
-
for (let i = arr.length - 1; i > 0; i--) {
|
|
123
|
-
const j = Math.floor(random() * (i + 1));
|
|
124
|
-
[arr[i], arr[j]] = [arr[j], arr[i]];
|
|
125
|
-
}
|
|
126
|
-
}
|
|
127
|
-
/**
|
|
128
|
-
* Shard recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
|
|
129
|
-
* and `description` below for the surface form it generates.
|
|
130
|
-
*/
|
|
131
|
-
export const frLieuditRecipe = {
|
|
132
|
-
name: "fr-lieudit",
|
|
133
|
-
description: "FR lieu-dit rows: BAN nom_ld → dependent_locality (commune → locality), lieu-dit on its own line",
|
|
134
|
-
mode: "generate",
|
|
135
|
-
options: [
|
|
136
|
-
{
|
|
137
|
-
flag: "--ban-dir <dir>",
|
|
138
|
-
description: "BAN adresses-<dept>.csv directory. Default $MAILWOMAN_DATA_ROOT/corpus/sources/ban",
|
|
139
|
-
},
|
|
140
|
-
{
|
|
141
|
-
flag: "--country-fraction <f>",
|
|
142
|
-
description: "Fraction of rows that append an explicit 'France' surface form + a `country` component. Default 0",
|
|
143
|
-
},
|
|
144
|
-
],
|
|
145
|
-
async run(opts, write) {
|
|
146
|
-
const random = makeMulberry32(opts.seed);
|
|
147
|
-
const source = opts.sourceName ?? "synth-fr-lieudit";
|
|
148
|
-
const count = opts.count ?? 800_000;
|
|
149
|
-
const banDir = opts.banDir ?? dataRootPath("corpus", "sources", "ban");
|
|
150
|
-
const countryFraction = opts.countryFraction ?? 0;
|
|
151
|
-
if (!(countryFraction >= 0 && countryFraction <= 1)) {
|
|
152
|
-
throw new Error(`--country-fraction must be in [0, 1], got ${countryFraction}`);
|
|
153
|
-
}
|
|
154
|
-
const pool = await readLieuDitPool(banDir);
|
|
155
|
-
if (!pool.length) {
|
|
156
|
-
throw new Error(`No clean lieu-dit rows found under ${banDir} — see ban/sdk/extract.ts's cleanLieuDit filter.`);
|
|
157
|
-
}
|
|
158
|
-
shuffleInPlace(pool, random);
|
|
159
|
-
const selected = pool.slice(0, Math.min(count, pool.length));
|
|
160
|
-
let emitted = 0;
|
|
161
|
-
let skipped = 0;
|
|
162
|
-
let countryAppended = 0;
|
|
163
|
-
for (const t of selected) {
|
|
164
|
-
const house = composeHouseNumber(t.numero, t.rep);
|
|
165
|
-
const decomposed = decomposeFrStreet(t.street);
|
|
166
|
-
const components = {
|
|
167
|
-
house_number: house,
|
|
168
|
-
dependent_locality: t.dependentLocality,
|
|
169
|
-
locality: t.locality,
|
|
170
|
-
};
|
|
171
|
-
if (decomposed.prefix) {
|
|
172
|
-
components.street_prefix = decomposed.prefix;
|
|
173
|
-
}
|
|
174
|
-
if (decomposed.street) {
|
|
175
|
-
components.street = decomposed.street;
|
|
176
|
-
}
|
|
177
|
-
if (t.postcode) {
|
|
178
|
-
components.postcode = t.postcode;
|
|
179
|
-
}
|
|
180
|
-
let raw = composeRaw(house, t.street, t.dependentLocality, t.postcode, t.locality);
|
|
181
|
-
if (!raw) {
|
|
182
|
-
skipped++;
|
|
183
|
-
continue;
|
|
184
|
-
}
|
|
185
|
-
// Country-append (the fr-admin-split #728 pattern, generalized): ~`countryFraction` of the time
|
|
186
|
-
// append an explicit "France" surface form onto the trailing (postcode+commune) line + a
|
|
187
|
-
// `country` component — the model relearns to emit country WHEN present without over-firing it
|
|
188
|
-
// on the (still-majority) country-less rows. `countryFraction <= 0` (the default) never draws
|
|
189
|
-
// from `random`, so the byte-stream is unaffected when the flag is unset.
|
|
190
|
-
if (countryFraction > 0 && random() < countryFraction) {
|
|
191
|
-
const forms = COUNTRY_SURFACE_FORMS.FR;
|
|
192
|
-
const form = forms[Math.floor(random() * forms.length)];
|
|
193
|
-
raw = `${raw}, ${form}`;
|
|
194
|
-
components.country = form;
|
|
195
|
-
countryAppended++;
|
|
196
|
-
}
|
|
197
|
-
const sourceID = stableSourceID(source, {
|
|
198
|
-
street: t.street,
|
|
199
|
-
house_number: house,
|
|
200
|
-
dependent_locality: t.dependentLocality,
|
|
201
|
-
locality: t.locality,
|
|
202
|
-
postcode: t.postcode ?? undefined,
|
|
203
|
-
});
|
|
204
|
-
const canonical = {
|
|
205
|
-
raw,
|
|
206
|
-
components,
|
|
207
|
-
country: "FR",
|
|
208
|
-
locale: "fr-FR",
|
|
209
|
-
source,
|
|
210
|
-
source_id: sourceID,
|
|
211
|
-
corpus_version: "",
|
|
212
|
-
license: DEFAULT_LICENSE,
|
|
213
|
-
};
|
|
214
|
-
const aligned = alignRow(canonical);
|
|
215
|
-
if (aligned.kind !== "labeled" || !aligned.row) {
|
|
216
|
-
skipped++;
|
|
217
|
-
continue;
|
|
218
|
-
}
|
|
219
|
-
write(JSON.stringify({ ...aligned.row, synth_method: source, synth_base_id: null }) + "\n");
|
|
220
|
-
emitted++;
|
|
221
|
-
}
|
|
222
|
-
console.error(` emitted=${emitted} skipped=${skipped} country-appended=${countryAppended} pool=${pool.length}`);
|
|
223
|
-
return { emitted, skipped };
|
|
224
|
-
},
|
|
225
|
-
};
|
|
226
|
-
//# sourceMappingURL=fr-lieudit.js.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"fr-lieudit.js","sourceRoot":"","sources":["../../../src/shard-recipes/fr-lieudit.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;GAwBG;AAEH,OAAO,EAAE,WAAW,EAAE,MAAM,SAAS,CAAA;AACrC,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAA;AAEhC,OAAO,EAAE,oBAAoB,EAAE,MAAM,oBAAoB,CAAA;AACzD,OAAO,EAAE,qBAAqB,EAAE,MAAM,0BAA0B,CAAA;AAChE,OAAO,EAAE,SAAS,EAAE,MAAM,yBAAyB,CAAA;AAEnD,OAAO,EAAE,YAAY,EAAE,MAAM,uBAAuB,CAAA;AAEpD,OAAO,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAA;AAEhD,OAAO,EAAE,QAAQ,EAAE,MAAM,QAAQ,CAAA;AAEjC,OAAO,EAAE,iBAAiB,EAAE,MAAM,qCAAqC,CAAA;AACvE,OAAO,EAAE,cAAc,EAAoB,MAAM,eAAe,CAAA;AAEhE;;GAEG;AACH,MAAM,eAAe,GAAG,qBAAqB,CAAA;AAc7C;;;;;;GAMG;AACH,SAAS,gBAAgB,CAAC,MAAc;IACvC,MAAM,MAAM,GAAG,IAAI,GAAG,EAAkB,CAAA;IAExC,KAAK,MAAM,IAAI,IAAI,WAAW,CAAC,MAAM,CAAC,CAAC,QAAQ,EAAE,EAAE,CAAC;QACnD,MAAM,CAAC,GAAG,8BAA8B,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QAEnD,IAAI,CAAC,CAAC;YAAE,SAAQ;QAEhB,MAAM,IAAI,GAAG,CAAC,CAAC,CAAC,CAAE,CAAA;QAElB,IAAI,IAAI,KAAK,QAAQ,IAAI,IAAI,KAAK,QAAQ;YAAE,SAAQ;QAEpD,MAAM,QAAQ,GAAG,MAAM,CAAC,GAAG,CAAC,IAAI,CAAC,CAAA;QAEjC,IAAI,CAAC,QAAQ,IAAI,CAAC,QAAQ,CAAC,QAAQ,CAAC,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC;YACtE,MAAM,CAAC,GAAG,CAAC,IAAI,EAAE,IAAI,CAAC,MAAM,EAAE,IAAI,CAAC,CAAC,CAAA;QACrC,CAAC;IACF,CAAC;IAED,OAAO,CAAC,GAAG,MAAM,CAAC,IAAI,EAAE,CAAC,CAAC,QAAQ,EAAE,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,MAAM,CAAC,GAAG,CAAC,IAAI,CAAE,CAAC,CAAA;AACtE,CAAC;AAED;;GAEG;AACH,KAAK,UAAU,eAAe,CAAC,MAAc;IAC5C,MAAM,KAAK,GAAG,gBAAgB,CAAC,MAAM,CAAC,CAAA;IAEtC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,CAAC;QACnB,MAAM,IAAI,KAAK,CACd,6CAA6C,MAAM,sDAAsD,CACzG,CAAA;IACF,CAAC;IAED,MAAM,IAAI,GAAmB,EAAE,CAAA;IAC/B,IAAI,OAAO,GAAG,CAAC,CAAA;IAEf,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;QAC1B,IAAI,SAAS,GAAG,CAAC,CAAA;QAEjB,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,oBAAoB,CAAC,IAAI,CAAC,EAAE,CAAC;YACpD,OAAO,EAAE,CAAA;YAET,IAAI,CAAC,GAAG,CAAC,OAAO,IAAI,CAAC,GAAG,CAAC,IAAI;gBAAE,SAAQ;YAEvC,IAAI,CAAC,IAAI,CAAC;gBACT,MAAM,EAAE,GAAG,CAAC,MAAM;gBAClB,GAAG,EAAE,GAAG,CAAC,GAAG;gBACZ,MAAM,EAAE,GAAG,CAAC,MAAM;gBAClB,QAAQ,EAAE,GAAG,CAAC,QAAQ;gBACtB,QAAQ,EAAE,GAAG,CAAC,IAAI;gBAClB,iBAAiB,EAAE,GAAG,CAAC,OAAO;aAC9B,CAAC,CAAA;YAEF,SAAS,EAAE,CAAA;QACZ,CAAC;QAED,OAAO,CAAC,KAAK,CAAC,KAAK,IAAI,KAAK,SAAS,CAAC,cAAc,EAAE,sBAAsB,CAAC,CAAA;IAC9E,CAAC;IAED,OAAO,CAAC,KAAK,CACZ,aAAa,OAAO,CAAC,cAAc,EAAE,oBAAoB,KAAK,CAAC,MAAM,wBAAwB,IAAI,CAAC,MAAM,CAAC,cAAc,EAAE,EAAE,CAC3H,CAAA;IAED,OAAO,IAAI,CAAA;AACZ,CAAC;AAED;;GAEG;AACH,SAAS,kBAAkB,CAAC,MAAc,EAAE,GAAkB;IAC7D,OAAO,GAAG,CAAC,CAAC,CAAC,GAAG,MAAM,IAAI,GAAG,EAAE,CAAC,CAAC,CAAC,MAAM,CAAA;AACzC,CAAC;AAED;;;;GAIG;AACH,SAAS,UAAU,CAClB,KAAa,EACb,MAAc,EACd,iBAAyB,EACzB,QAAuB,EACvB,QAAgB;IAEhB,MAAM,KAAK,GAAa,EAAE,CAAA;IAC1B,MAAM,UAAU,GAAG,GAAG,KAAK,IAAI,MAAM,EAAE,CAAC,IAAI,EAAE,CAAA;IAE9C,IAAI,UAAU,EAAE,CAAC;QAChB,KAAK,CAAC,IAAI,CAAC,UAAU,CAAC,CAAA;IACvB,CAAC;IAED,KAAK,CAAC,IAAI,CAAC,iBAAiB,CAAC,CAAA;IAC7B,MAAM,QAAQ,GAAG,CAAC,QAAQ,EAAE,QAAQ,CAAC,CAAC,MAAM,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,CAAA;IAExE,IAAI,QAAQ,EAAE,CAAC;QACd,KAAK,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAA;IACrB,CAAC;IAED,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;AACxB,CAAC;AAED;;GAEG;AACH,SAAS,cAAc,CAAI,GAAQ,EAAE,MAAoB;IACxD,KAAK,IAAI,CAAC,GAAG,GAAG,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC,GAAG,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC;QACzC,MAAM,CAAC,GAAG,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,CACvC;QAAA,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,GAAG,CAAC,CAAC,CAAE,EAAE,GAAG,CAAC,CAAC,CAAE,CAAC,CAAA;IACvC,CAAC;AACF,CAAC;AAED;;;GAGG;AACH,MAAM,CAAC,MAAM,eAAe,GAAgB;IAC3C,IAAI,EAAE,YAAY;IAClB,WAAW,EAAE,kGAAkG;IAC/G,IAAI,EAAE,UAAU;IAChB,OAAO,EAAE;QACR;YACC,IAAI,EAAE,iBAAiB;YACvB,WAAW,EAAE,oFAAoF;SACjG;QACD;YACC,IAAI,EAAE,wBAAwB;YAC9B,WAAW,EAAE,mGAAmG;SAChH;KACD;IACD,KAAK,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK;QACpB,MAAM,MAAM,GAAG,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACxC,MAAM,MAAM,GAAG,IAAI,CAAC,UAAU,IAAI,kBAAkB,CAAA;QACpD,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,IAAI,OAAO,CAAA;QACnC,MAAM,MAAM,GAAG,IAAI,CAAC,MAAM,IAAI,YAAY,CAAC,QAAQ,EAAE,SAAS,EAAE,KAAK,CAAC,CAAA;QACtE,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,IAAI,GAAG,MAAM,eAAe,CAAC,MAAM,CAAC,CAAA;QAE1C,IAAI,CAAC,IAAI,CAAC,MAAM,EAAE,CAAC;YAClB,MAAM,IAAI,KAAK,CAAC,sCAAsC,MAAM,kDAAkD,CAAC,CAAA;QAChH,CAAC;QAED,cAAc,CAAC,IAAI,EAAE,MAAM,CAAC,CAAA;QAC5B,MAAM,QAAQ,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,EAAE,IAAI,CAAC,GAAG,CAAC,KAAK,EAAE,IAAI,CAAC,MAAM,CAAC,CAAC,CAAA;QAE5D,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,OAAO,GAAG,CAAC,CAAA;QACf,IAAI,eAAe,GAAG,CAAC,CAAA;QAEvB,KAAK,MAAM,CAAC,IAAI,QAAQ,EAAE,CAAC;YAC1B,MAAM,KAAK,GAAG,kBAAkB,CAAC,CAAC,CAAC,MAAM,EAAE,CAAC,CAAC,GAAG,CAAC,CAAA;YACjD,MAAM,UAAU,GAAG,iBAAiB,CAAC,CAAC,CAAC,MAAM,CAAC,CAAA;YAE9C,MAAM,UAAU,GAA0C;gBACzD,YAAY,EAAE,KAAK;gBACnB,kBAAkB,EAAE,CAAC,CAAC,iBAAiB;gBACvC,QAAQ,EAAE,CAAC,CAAC,QAAQ;aACpB,CAAA;YAED,IAAI,UAAU,CAAC,MAAM,EAAE,CAAC;gBACvB,UAAU,CAAC,aAAa,GAAG,UAAU,CAAC,MAAM,CAAA;YAC7C,CAAC;YAED,IAAI,UAAU,CAAC,MAAM,EAAE,CAAC;gBACvB,UAAU,CAAC,MAAM,GAAG,UAAU,CAAC,MAAM,CAAA;YACtC,CAAC;YAED,IAAI,CAAC,CAAC,QAAQ,EAAE,CAAC;gBAChB,UAAU,CAAC,QAAQ,GAAG,CAAC,CAAC,QAAQ,CAAA;YACjC,CAAC;YAED,IAAI,GAAG,GAAG,UAAU,CAAC,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,CAAC,iBAAiB,EAAE,CAAC,CAAC,QAAQ,EAAE,CAAC,CAAC,QAAQ,CAAC,CAAA;YAElF,IAAI,CAAC,GAAG,EAAE,CAAC;gBACV,OAAO,EAAE,CAAA;gBAET,SAAQ;YACT,CAAC;YAED,gGAAgG;YAChG,yFAAyF;YACzF,+FAA+F;YAC/F,8FAA8F;YAC9F,0EAA0E;YAC1E,IAAI,eAAe,GAAG,CAAC,IAAI,MAAM,EAAE,GAAG,eAAe,EAAE,CAAC;gBACvD,MAAM,KAAK,GAAG,qBAAqB,CAAC,EAAE,CAAA;gBACtC,MAAM,IAAI,GAAG,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,EAAE,GAAG,KAAK,CAAC,MAAM,CAAC,CAAE,CAAA;gBACxD,GAAG,GAAG,GAAG,GAAG,KAAK,IAAI,EAAE,CAAA;gBACvB,UAAU,CAAC,OAAO,GAAG,IAAI,CAAA;gBAEzB,eAAe,EAAE,CAAA;YAClB,CAAC;YAED,MAAM,QAAQ,GAAG,cAAc,CAAC,MAAM,EAAE;gBACvC,MAAM,EAAE,CAAC,CAAC,MAAM;gBAChB,YAAY,EAAE,KAAK;gBACnB,kBAAkB,EAAE,CAAC,CAAC,iBAAiB;gBACvC,QAAQ,EAAE,CAAC,CAAC,QAAQ;gBACpB,QAAQ,EAAE,CAAC,CAAC,QAAQ,IAAI,SAAS;aACjC,CAAC,CAAA;YAEF,MAAM,SAAS,GAAiB;gBAC/B,GAAG;gBACH,UAAU;gBACV,OAAO,EAAE,IAAI;gBACb,MAAM,EAAE,OAAO;gBACf,MAAM;gBACN,SAAS,EAAE,QAAQ;gBACnB,cAAc,EAAE,EAAE;gBAClB,OAAO,EAAE,eAAe;aACxB,CAAA;YAED,MAAM,OAAO,GAAG,QAAQ,CAAC,SAAS,CAAC,CAAA;YAEnC,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,aAAa,EAAE,IAAI,EAAE,CAAC,GAAG,IAAI,CAAC,CAAA;YAE3F,OAAO,EAAE,CAAA;QACV,CAAC;QAED,OAAO,CAAC,KAAK,CAAC,aAAa,OAAO,YAAY,OAAO,qBAAqB,eAAe,SAAS,IAAI,CAAC,MAAM,EAAE,CAAC,CAAA;QAEhH,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,CAAA;IAC5B,CAAC;CACD,CAAA"}
|
|
@@ -1,38 +0,0 @@
|
|
|
1
|
-
/**
|
|
2
|
-
* @copyright Sister Software
|
|
3
|
-
* @license AGPL-3.0
|
|
4
|
-
* @author Teffen Ellis, et al.
|
|
5
|
-
*
|
|
6
|
-
* `fr-order` shard recipe — French reversed-order coverage (#560). Reads REAL OpenAddresses FR
|
|
7
|
-
* tuples (`fr/countrywide.csv` from the cached zip), then for each row picks — by
|
|
8
|
-
* `--reversed-fraction` (default 0.5) — whether to render in CANONICAL French order
|
|
9
|
-
* (number-street, postcode-city) or one of four REVERSED / postcode-first variants the
|
|
10
|
-
* v4.4.0→v0.5.0 regression exposed (the model misses house_number in every reversed one):
|
|
11
|
-
*
|
|
12
|
-
* - A: "47110 Sainte-Livrade-sur-Lot, 69 Allée du Bugatel" (postcode city, HN street)
|
|
13
|
-
* - B: "Sainte-Livrade-sur-Lot, 47110, 619 Impasse de la Rose" (city, postcode, HN street)
|
|
14
|
-
* - C: "Sainte-Livrade-sur-Lot 59 bis Rue des Ecuries 47110" (city HN street postcode — NO commas)
|
|
15
|
-
* - D: "47110, 6 rue de la république, Sainte-Livrade-sur-Lot" (postcode, HN street, city)
|
|
16
|
-
*
|
|
17
|
-
* Sub-modes ride alongside order: `bis`/`ter`/`quater` ordinal suffixes in house_number, and
|
|
18
|
-
* ALL-CAPS locality. `--golden` emits a held-out reversed-order eval slice with a different
|
|
19
|
-
* seed.
|
|
20
|
-
*
|
|
21
|
-
* The inline synthesis (the OA-CSV reader, the ordinal/all-caps tables, the canonical + reversed
|
|
22
|
-
* renderers) is ported faithfully from scripts/build-fr-order-shard.mjs. This is a
|
|
23
|
-
* `generate`-mode recipe that still reads REAL tuples off disk — `--count` bounds the OUTPUT, not
|
|
24
|
-
* the input. The passed `random` (the framework LCG) is consumed in the exact call order the
|
|
25
|
-
* legacy script used.
|
|
26
|
-
*
|
|
27
|
-
* NOT ported (diagnostic-only, no effect on emitted bytes): the post-run `runSpanCheck` self-check
|
|
28
|
-
* (it reads the finished file back with a separate PRNG and prints to stderr; the recipe's output
|
|
29
|
-
* stream is still open during `run`), and the dead `renderReversed` helper (the legacy `main`
|
|
30
|
-
* inlined the variant logic and never called it).
|
|
31
|
-
*/
|
|
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
|
-
*/
|
|
37
|
-
export declare const frOrderRecipe: ShardRecipe;
|
|
38
|
-
//# sourceMappingURL=fr-order.d.ts.map
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
{"version":3,"file":"fr-order.d.ts","sourceRoot":"","sources":["../../../src/shard-recipes/fr-order.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8BG;AAUH,OAAO,EAAwC,KAAK,WAAW,EAAE,MAAM,eAAe,CAAA;AAuFtF;;;GAGG;AACH,eAAO,MAAM,aAAa,EAAE,WA8H3B,CAAA"}
|