@mailwoman/corpus 9.4.0 → 10.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +134 -32
- package/data/PROVENANCE.md +623 -17
- package/data/address-source-register.json +14249 -0
- package/data/builds/v0.7.0-de-holdout/inputs.json +22 -0
- package/data/builds/v0.8.0-registers/inputs.json +92 -0
- package/data/license-decisions.json +1603 -0
- package/data/licenses/PROVENANCE.md +65 -0
- package/data/licenses/cdla-permissive-2.0.md +43 -0
- package/data/licenses/geonames-publication.md +34 -0
- package/data/licenses/licence-ouverte-2.0.md +36 -0
- package/data/licenses/national-address-database.md +46 -0
- package/data/licenses/nlod-2.0.md +90 -0
- package/data/licenses/sirene-publication.md +38 -0
- package/data/licenses/whosonfirst-licenses.md +65 -0
- package/data/source-resolutions.json +804 -0
- package/data/sub-venue-lexicon.json +1 -1
- package/data/training-manifests/v0.7.0-de-holdout.effective.json +477 -0
- package/data/training-manifests/v0.7.0-de-holdout.json +78 -0
- package/lib/adapters/cordis/adapter.ts +785 -0
- package/lib/adapters/dedup-key.ts +40 -0
- package/lib/adapters/errors.ts +21 -0
- package/lib/adapters/geonames/adapter.ts +43 -53
- package/lib/adapters/geonames/postal/adapter.ts +116 -0
- package/lib/adapters/gleif/adapter.ts +828 -0
- package/lib/adapters/libpostal-dictionary.ts +39 -0
- package/lib/adapters/openaddresses/adapter.ts +54 -61
- package/lib/adapters/osm/adapter.ts +356 -0
- package/lib/adapters/overture/adapter.ts +65 -41
- package/lib/adapters/po-box/adapter.ts +202 -0
- package/lib/adapters/registry.ts +79 -0
- package/lib/adapters/sha256-stream.ts +49 -0
- package/lib/adapters/source-id.ts +49 -0
- package/lib/adapters/street-line.ts +135 -0
- package/lib/adapters/wof/admin/json/adapter.ts +254 -0
- package/lib/adapters/wof/json-rows.ts +211 -0
- package/lib/adapters/wof/postalcode-json/adapter.ts +194 -0
- package/lib/adapters.ts +230 -0
- package/lib/au/adapters/gnaf/adapter.ts +144 -0
- package/lib/au/adapters/gnaf/assemble.ts +205 -0
- package/lib/be/adapters/brussels/adapter.ts +566 -0
- package/lib/be/adapters/vlaanderen/adapter.ts +670 -0
- package/lib/be/adapters/wallonie/adapter.ts +537 -0
- package/lib/be/tools/fetch/brussels.ts +239 -0
- package/lib/be/tools/fetch/wallonie.ts +274 -0
- package/lib/build/adapters.ts +110 -0
- package/lib/build/align.ts +364 -0
- package/lib/build/checkpoint.ts +131 -0
- package/lib/build/eligibility.ts +96 -0
- package/lib/build/heap.ts +53 -0
- package/lib/build/inputs.ts +81 -0
- package/lib/build/rows.ts +21 -0
- package/lib/build/types.ts +232 -0
- package/lib/build.ts +127 -315
- package/lib/cn/recipes/organizational-units.ts +178 -0
- package/lib/cz/adapters/cuzk/adapter.ts +317 -0
- package/lib/cz/recipes/pcfirst-preposition.ts +125 -0
- package/lib/cz/tools/fetch/cuzk.ts +699 -0
- package/lib/de/recipes/locale.ts +370 -0
- package/lib/directory.ts +31 -0
- package/lib/dk/adapters/inspire/adapter.ts +345 -0
- package/lib/dk/tools/fetch/inspire.ts +321 -0
- package/lib/ee/adapters/ads/adapter.ts +246 -0
- package/lib/ee/tools/fetch/ads.ts +270 -0
- package/lib/env.ts +6 -2
- package/lib/es/adapters/bizkaia/adapter.ts +388 -0
- package/lib/es/adapters/catastro/adapter.ts +343 -0
- package/lib/es/adapters/gipuzkoa/adapter.ts +263 -0
- package/lib/es/adapters/navarra/adapter.ts +289 -0
- package/lib/es/cadastre.ts +194 -0
- package/lib/es/tools/fetch/bizkaia.ts +748 -0
- package/lib/es/tools/fetch/catastro.ts +754 -0
- package/lib/es/tools/fetch/gipuzkoa.ts +336 -0
- package/lib/es/tools/fetch/navarra.ts +488 -0
- package/lib/fi/adapters/ryhti/adapter.ts +323 -0
- package/lib/fi/tools/fetch/ryhti.ts +476 -0
- package/lib/fingerprints.ts +154 -0
- package/lib/fr/adapters/annuaire-education/adapter.ts +598 -0
- package/lib/fr/adapters/ban/adapter.ts +187 -0
- package/lib/fr/adapters/finess/adapter.ts +618 -0
- package/lib/fr/adapters/finess/postal-lines.ts +157 -0
- package/lib/fr/adapters/finess/voie-type.ts +200 -0
- package/lib/fr/insee-country.ts +62 -0
- package/lib/fr/recipes/admin-split.ts +221 -0
- package/lib/fr/recipes/bare-street.ts +158 -0
- package/lib/fr/recipes/fragment.ts +251 -0
- package/lib/fr/recipes/lieudit.ts +310 -0
- package/lib/fr/recipes/order.ts +219 -0
- package/lib/fr/street-decompose.ts +67 -0
- package/lib/fr/tools/fetch/annuaire-education.ts +306 -0
- package/lib/fr/tools/fetch/ban.ts +298 -0
- package/lib/fr/tools/fetch/finess.ts +352 -0
- package/lib/gauntlet-inputs.ts +92 -0
- package/lib/index.ts +10 -4
- package/lib/inspire/address.ts +457 -0
- package/lib/inspire/archive.ts +44 -0
- package/lib/inspire/errors.ts +71 -0
- package/lib/inspire/stream.ts +262 -0
- package/lib/international/recipes/locale.ts +556 -0
- package/lib/it/adapters/anac/adapter.ts +522 -0
- package/lib/it/tools/fetch/anac.ts +394 -0
- package/lib/jp/adapters/wof-admin/adapter.ts +224 -0
- package/lib/jp/tools/fetch/houjin.ts +139 -0
- package/lib/kr/adapters/juso/label-rows.ts +239 -0
- package/lib/kr/adapters/localdata/align.ts +288 -0
- package/lib/kr/adapters/localdata/key-index.ts +177 -0
- package/lib/kr/adapters/localdata/permit-rows.ts +193 -0
- package/lib/kr/tools/fetch/juso.ts +170 -0
- package/lib/kr/tools/fetch/localdata.ts +205 -0
- package/lib/lu/adapters/bd-adresses/adapter.ts +240 -0
- package/lib/lu/tools/fetch/bd-adresses.ts +351 -0
- package/lib/lv/adapters/varis/adapter.ts +499 -0
- package/lib/lv/tools/fetch/varis.ts +214 -0
- package/lib/nl/adapters/kadaster/adapter.ts +386 -0
- package/lib/nl/recipes/postcode.ts +139 -0
- package/lib/nl/tools/fetch/kadaster.ts +298 -0
- package/lib/no/adapters/matrikkelen/adapter.ts +187 -0
- package/lib/no/recipes/fragment.ts +189 -0
- package/lib/no/recipes/street/led.ts +154 -0
- package/lib/no/recipes/street.ts +109 -0
- package/lib/no/tools/fetch/matrikkelen.ts +519 -0
- package/lib/parquet/duckdb.ts +144 -0
- package/lib/parquet/readers.ts +86 -0
- package/lib/parquet/schema.ts +214 -0
- package/lib/parquet/shuffle.ts +59 -0
- package/lib/parquet/span-sql.ts +54 -0
- package/lib/parquet/streams.ts +113 -0
- package/lib/parquet/writers.ts +451 -0
- package/lib/pl/adapters/emuia/adapter.ts +202 -0
- package/lib/pl/tools/fetch/emuia.ts +360 -0
- package/lib/recipes/anchor-absorption.ts +30 -19
- package/lib/recipes/bare/country.ts +87 -0
- package/lib/recipes/bare/postcode/eval.ts +99 -0
- package/lib/recipes/bare/postcode.ts +346 -0
- package/lib/recipes/boundary-stress.ts +36 -19
- package/lib/recipes/country-balanced.ts +67 -87
- package/lib/recipes/house-venue.ts +31 -13
- package/lib/recipes/intersection.ts +83 -61
- package/lib/recipes/po/box/cedex/au-nz.ts +82 -0
- package/lib/recipes/po/box/cedex/ca.ts +59 -0
- package/lib/recipes/po/box/cedex/fr.ts +77 -0
- package/lib/recipes/po/box/cedex/phrases.ts +109 -0
- package/lib/recipes/po/box/cedex/recipe.ts +215 -0
- package/lib/recipes/po/box/cedex/sources.ts +189 -0
- package/lib/recipes/po/box/cedex/types.ts +35 -0
- package/lib/recipes/po/box/cedex/us.ts +74 -0
- package/lib/recipes/po/box/cedex/vocabulary.ts +106 -0
- package/lib/recipes/po/box/cedex.ts +9 -0
- package/lib/recipes/po/box.ts +149 -0
- package/lib/recipes/scaffold.ts +258 -182
- package/lib/recipes/sources.ts +399 -0
- package/lib/recipes/street/affix.ts +707 -0
- package/lib/recipes/street/bare.ts +115 -0
- package/lib/recipes/street.ts +32 -8
- package/lib/recipes/sub/venue/context.ts +156 -0
- package/lib/recipes/sub/venue/render.ts +170 -0
- package/lib/recipes/sub/venue/sources.ts +588 -0
- package/lib/recipes/sub/venue.ts +801 -0
- package/lib/recipes/trailing-region.ts +70 -81
- package/lib/recipes/unit/sources.ts +44 -0
- package/lib/recipes/unit.ts +102 -90
- package/lib/recipes.ts +106 -0
- package/lib/registers.ts +278 -0
- package/lib/ro/adapters/retea-scolara/adapter.ts +264 -0
- package/lib/ro/tools/fetch/retea-scolara.ts +187 -0
- package/lib/runner.ts +220 -84
- package/lib/sg/recipes/register.ts +264 -0
- package/lib/sg/tools/fetch/acra.ts +174 -0
- package/lib/si/recipes/bare-village.ts +116 -0
- package/lib/sk/adapters/inspire/adapter.ts +395 -0
- package/lib/sk/tools/fetch/inspire.ts +402 -0
- package/lib/source-register/effective-manifest.ts +659 -0
- package/lib/source-register/register.ts +539 -0
- package/lib/source-register/training-manifest.ts +218 -0
- package/lib/source-register/types.ts +590 -0
- package/lib/source-register.ts +71 -0
- package/lib/south-asia/recipes/register.ts +233 -0
- package/lib/subvenue/harvest.ts +251 -0
- package/lib/subvenue/promotions.ts +293 -0
- package/lib/subvenue/surfaces.ts +94 -0
- package/lib/subvenue/table.ts +264 -0
- package/lib/surfaces/locale.ts +246 -0
- package/lib/synthesizers/anchor-absorption.ts +55 -91
- package/lib/synthesizers/boundary-stress.ts +49 -131
- package/lib/synthesizers/house-venue.ts +44 -102
- package/lib/synthesizers/intersection.ts +37 -26
- package/lib/synthesizers/no-street.ts +70 -119
- package/lib/synthesizers/po-box.ts +90 -105
- package/lib/synthesizers/street.ts +47 -35
- package/lib/synthesizers/utils.ts +65 -219
- package/lib/test-kit/corpus-recipe.ts +45 -28
- package/lib/test-kit.ts +116 -0
- package/lib/tools/align-canonical.ts +64 -0
- package/lib/tools/audit.ts +114 -118
- package/lib/tools/corpus-stats.ts +46 -32
- package/lib/tools/fetch/atom.ts +164 -0
- package/lib/tools/fetch/cordis.ts +318 -0
- package/lib/tools/fetch/download/manifest.ts +114 -0
- package/lib/tools/fetch/download/network.ts +250 -0
- package/lib/tools/fetch/download/retry.ts +174 -0
- package/lib/tools/fetch/download.ts +4 -471
- package/lib/tools/fetch/geonames/dump.ts +275 -0
- package/lib/tools/fetch/geonames/postal.ts +145 -0
- package/lib/tools/fetch/gleif.ts +360 -0
- package/lib/tools/fetch/header.ts +69 -0
- package/lib/tools/fetch/inspire-addresses.ts +495 -0
- package/lib/tools/fetch/openaddresses.ts +20 -109
- package/lib/tools/fetch/ourairports.ts +16 -49
- package/lib/tools/fetch/ppd.ts +10 -10
- package/lib/tools/fetch/vlaanderen-ad.ts +435 -0
- package/lib/tools/fetch/wfs-harvest.ts +943 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +43 -143
- package/lib/tools/fetch/zip-archive.ts +100 -0
- package/lib/tools/fetch.ts +143 -0
- package/lib/tools/golden/expand.ts +605 -0
- package/lib/tools/golden/promote.ts +349 -0
- package/lib/tools/golden/relabel-street/directory.ts +367 -0
- package/lib/tools/golden/relabel-street/row.ts +283 -0
- package/lib/tools/golden/relabel-street.ts +9 -0
- package/lib/tools/ingest-csv.ts +45 -50
- package/lib/tools/jsonl-to-parquet.ts +59 -98
- package/lib/tools/lint/recipe-output/vocab.ts +366 -0
- package/lib/tools/lint/recipe-output.ts +482 -0
- package/lib/tools/migrate/overlay-parquet.ts +173 -0
- package/lib/tools/migrate/recipe-output.ts +153 -0
- package/lib/tools/migrate/source-names.ts +161 -0
- package/lib/tools/overlay/kryptonite.ts +144 -0
- package/lib/tools/overlay/manifest.ts +407 -0
- package/lib/tools/overlay/merge-source.ts +138 -0
- package/lib/tools/overlay/split-slice.ts +144 -0
- package/lib/tools/overlay/translit.ts +234 -0
- package/lib/tools/overture-subvenue.ts +18 -91
- package/lib/tools/postcode-triples.ts +362 -167
- package/lib/tools/source-register/build.ts +819 -0
- package/lib/tools/sub/venue/head-nouns.ts +208 -0
- package/lib/tools/sub/venue/lexicon.ts +394 -0
- package/lib/tools/sub/venue/wikidata.ts +88 -0
- package/lib/tools.ts +31 -0
- package/lib/tw/tools/fetch/gcis.ts +181 -0
- package/lib/types.ts +304 -101
- package/lib/us/adapters/fcc-bdc/adapter.ts +158 -0
- package/lib/us/adapters/state/hi-schools/adapter.ts +171 -0
- package/lib/us/adapters/state/hi-schools/workbook.ts +40 -0
- package/lib/us/adapters/state/ia-contractors/adapter.ts +148 -0
- package/lib/us/adapters/state/ny-notaries/adapter.ts +132 -0
- package/lib/us/adapters/state/tx-notaries/adapter.ts +155 -0
- package/lib/us/adapters/tiger/adapter.ts +225 -0
- package/lib/us/adapters/tiger/street-decompose.ts +73 -0
- package/lib/us/adapters/usgov/hrsa-fqhc/adapter.ts +171 -0
- package/lib/us/adapters/usgov/imls-pls/adapter.ts +140 -0
- package/lib/us/adapters/usgov/irs-bmf/adapter.ts +154 -0
- package/lib/us/adapters/usgov/nad/adapter.ts +263 -0
- package/lib/us/adapters/usgov/nppes/adapter.ts +180 -0
- package/lib/us/adapters/usgov/samhsa-treatment-locator/adapter.ts +195 -0
- package/lib/us/fips-state.ts +122 -0
- package/lib/us/tools/fetch/hrsa.ts +58 -0
- package/lib/us/tools/fetch/imls-pls.ts +131 -0
- package/lib/us/tools/fetch/nad.ts +359 -0
- package/lib/us/tools/fetch/nppes.ts +153 -0
- package/lib/us/tools/fetch/state/hi-schools.ts +167 -0
- package/lib/us/tools/fetch/state/sources.ts +146 -0
- package/lib/us/tools/fetch/tiger-full.ts +256 -0
- package/lib/utils/align.ts +43 -53
- package/lib/utils/cooccurrence-stats.ts +101 -0
- package/lib/utils/golden.ts +39 -50
- package/lib/utils/license.ts +238 -26
- package/lib/utils/split.ts +205 -88
- package/lib/utils/tokenize.ts +22 -34
- package/lib/utils/wof-json.ts +134 -87
- package/lib/utils.ts +13 -0
- package/lib/ve/recipes/reviewed-postcode-tail.ts +217 -0
- package/out/adapters/cordis/adapter.d.ts +324 -0
- package/out/adapters/cordis/adapter.d.ts.map +1 -0
- package/out/adapters/cordis/adapter.js +616 -0
- package/out/adapters/cordis/adapter.js.map +1 -0
- package/out/adapters/dedup-key.d.ts +30 -0
- package/out/adapters/dedup-key.d.ts.map +1 -0
- package/out/adapters/dedup-key.js +35 -0
- package/out/adapters/dedup-key.js.map +1 -0
- package/out/adapters/errors.d.ts +17 -0
- package/out/adapters/errors.d.ts.map +1 -0
- package/out/adapters/errors.js +20 -0
- package/out/adapters/errors.js.map +1 -0
- package/out/adapters/geonames/adapter.d.ts +26 -28
- package/out/adapters/geonames/adapter.d.ts.map +1 -1
- package/out/adapters/geonames/adapter.js +40 -50
- package/out/adapters/geonames/adapter.js.map +1 -1
- package/out/adapters/geonames/postal/adapter.d.ts +41 -0
- package/out/adapters/geonames/postal/adapter.d.ts.map +1 -0
- package/out/adapters/geonames/postal/adapter.js +102 -0
- package/out/adapters/geonames/postal/adapter.js.map +1 -0
- package/out/adapters/gleif/adapter.d.ts +293 -0
- package/out/adapters/gleif/adapter.d.ts.map +1 -0
- package/out/adapters/gleif/adapter.js +684 -0
- package/out/adapters/gleif/adapter.js.map +1 -0
- package/out/adapters/libpostal-dictionary.d.ts +22 -0
- package/out/adapters/libpostal-dictionary.d.ts.map +1 -0
- package/out/adapters/libpostal-dictionary.js +36 -0
- package/out/adapters/libpostal-dictionary.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts +28 -43
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -1
- package/out/adapters/openaddresses/adapter.js +37 -51
- package/out/adapters/openaddresses/adapter.js.map +1 -1
- package/out/adapters/osm/adapter.d.ts +101 -0
- package/out/adapters/osm/adapter.d.ts.map +1 -0
- package/out/adapters/osm/adapter.js +260 -0
- package/out/adapters/osm/adapter.js.map +1 -0
- package/out/adapters/overture/adapter.d.ts +14 -30
- package/out/adapters/overture/adapter.d.ts.map +1 -1
- package/out/adapters/overture/adapter.js +57 -41
- package/out/adapters/overture/adapter.js.map +1 -1
- package/out/adapters/po-box/adapter.d.ts +63 -0
- package/out/adapters/po-box/adapter.d.ts.map +1 -0
- package/out/adapters/po-box/adapter.js +139 -0
- package/out/adapters/po-box/adapter.js.map +1 -0
- package/out/adapters/registry.d.ts +55 -0
- package/out/adapters/registry.d.ts.map +1 -0
- package/out/adapters/registry.js +43 -0
- package/out/adapters/registry.js.map +1 -0
- package/out/adapters/sha256-stream.d.ts +26 -0
- package/out/adapters/sha256-stream.d.ts.map +1 -0
- package/out/adapters/sha256-stream.js +34 -0
- package/out/adapters/sha256-stream.js.map +1 -0
- package/out/adapters/source-id.d.ts +33 -0
- package/out/adapters/source-id.d.ts.map +1 -0
- package/out/adapters/source-id.js +42 -0
- package/out/adapters/source-id.js.map +1 -0
- package/out/adapters/street-line.d.ts +102 -0
- package/out/adapters/street-line.d.ts.map +1 -0
- package/out/adapters/street-line.js +117 -0
- package/out/adapters/street-line.js.map +1 -0
- package/out/adapters/wof/admin/json/adapter.d.ts +88 -0
- package/out/adapters/wof/admin/json/adapter.d.ts.map +1 -0
- package/out/adapters/wof/admin/json/adapter.js +220 -0
- package/out/adapters/wof/admin/json/adapter.js.map +1 -0
- package/out/adapters/wof/json-rows.d.ts +89 -0
- package/out/adapters/wof/json-rows.d.ts.map +1 -0
- package/out/adapters/wof/json-rows.js +135 -0
- package/out/adapters/wof/json-rows.js.map +1 -0
- package/out/adapters/wof/postalcode-json/adapter.d.ts +49 -0
- package/out/adapters/wof/postalcode-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof/postalcode-json/adapter.js +165 -0
- package/out/adapters/wof/postalcode-json/adapter.js.map +1 -0
- package/out/adapters.d.ts +75 -0
- package/out/adapters.d.ts.map +1 -0
- package/out/adapters.js +167 -0
- package/out/adapters.js.map +1 -0
- package/out/au/adapters/gnaf/adapter.d.ts +37 -0
- package/out/au/adapters/gnaf/adapter.d.ts.map +1 -0
- package/out/au/adapters/gnaf/adapter.js +119 -0
- package/out/au/adapters/gnaf/adapter.js.map +1 -0
- package/out/au/adapters/gnaf/assemble.d.ts +54 -0
- package/out/au/adapters/gnaf/assemble.d.ts.map +1 -0
- package/out/au/adapters/gnaf/assemble.js +134 -0
- package/out/au/adapters/gnaf/assemble.js.map +1 -0
- package/out/be/adapters/brussels/adapter.d.ts +212 -0
- package/out/be/adapters/brussels/adapter.d.ts.map +1 -0
- package/out/be/adapters/brussels/adapter.js +435 -0
- package/out/be/adapters/brussels/adapter.js.map +1 -0
- package/out/be/adapters/vlaanderen/adapter.d.ts +233 -0
- package/out/be/adapters/vlaanderen/adapter.d.ts.map +1 -0
- package/out/be/adapters/vlaanderen/adapter.js +416 -0
- package/out/be/adapters/vlaanderen/adapter.js.map +1 -0
- package/out/be/adapters/wallonie/adapter.d.ts +196 -0
- package/out/be/adapters/wallonie/adapter.d.ts.map +1 -0
- package/out/be/adapters/wallonie/adapter.js +437 -0
- package/out/be/adapters/wallonie/adapter.js.map +1 -0
- package/out/be/tools/fetch/brussels.d.ts +119 -0
- package/out/be/tools/fetch/brussels.d.ts.map +1 -0
- package/out/be/tools/fetch/brussels.js +146 -0
- package/out/be/tools/fetch/brussels.js.map +1 -0
- package/out/be/tools/fetch/wallonie.d.ts +119 -0
- package/out/be/tools/fetch/wallonie.d.ts.map +1 -0
- package/out/be/tools/fetch/wallonie.js +167 -0
- package/out/be/tools/fetch/wallonie.js.map +1 -0
- package/out/build/adapters.d.ts +33 -0
- package/out/build/adapters.d.ts.map +1 -0
- package/out/build/adapters.js +68 -0
- package/out/build/adapters.js.map +1 -0
- package/out/build/align.d.ts +73 -0
- package/out/build/align.d.ts.map +1 -0
- package/out/build/align.js +226 -0
- package/out/build/align.js.map +1 -0
- package/out/build/checkpoint.d.ts +94 -0
- package/out/build/checkpoint.d.ts.map +1 -0
- package/out/build/checkpoint.js +59 -0
- package/out/build/checkpoint.js.map +1 -0
- package/out/build/eligibility.d.ts +47 -0
- package/out/build/eligibility.d.ts.map +1 -0
- package/out/build/eligibility.js +80 -0
- package/out/build/eligibility.js.map +1 -0
- package/out/build/heap.d.ts +28 -0
- package/out/build/heap.d.ts.map +1 -0
- package/out/build/heap.js +47 -0
- package/out/build/heap.js.map +1 -0
- package/out/build/inputs.d.ts +52 -0
- package/out/build/inputs.d.ts.map +1 -0
- package/out/build/inputs.js +49 -0
- package/out/build/inputs.js.map +1 -0
- package/out/build/rows.d.ts +16 -0
- package/out/build/rows.d.ts.map +1 -0
- package/out/build/rows.js +19 -0
- package/out/build/rows.js.map +1 -0
- package/out/build/types.d.ts +220 -0
- package/out/build/types.d.ts.map +1 -0
- package/out/build/types.js +34 -0
- package/out/build/types.js.map +1 -0
- package/out/build.d.ts +6 -121
- package/out/build.d.ts.map +1 -1
- package/out/build.js +112 -207
- package/out/build.js.map +1 -1
- package/out/cn/recipes/organizational-units.d.ts +19 -0
- package/out/cn/recipes/organizational-units.d.ts.map +1 -0
- package/out/cn/recipes/organizational-units.js +138 -0
- package/out/cn/recipes/organizational-units.js.map +1 -0
- package/out/cz/adapters/cuzk/adapter.d.ts +52 -0
- package/out/cz/adapters/cuzk/adapter.d.ts.map +1 -0
- package/out/cz/adapters/cuzk/adapter.js +266 -0
- package/out/cz/adapters/cuzk/adapter.js.map +1 -0
- package/out/cz/recipes/pcfirst-preposition.d.ts +18 -0
- package/out/cz/recipes/pcfirst-preposition.d.ts.map +1 -0
- package/out/cz/recipes/pcfirst-preposition.js +110 -0
- package/out/cz/recipes/pcfirst-preposition.js.map +1 -0
- package/out/cz/tools/fetch/cuzk.d.ts +272 -0
- package/out/cz/tools/fetch/cuzk.d.ts.map +1 -0
- package/out/cz/tools/fetch/cuzk.js +446 -0
- package/out/cz/tools/fetch/cuzk.js.map +1 -0
- package/out/de/recipes/locale.d.ts +42 -0
- package/out/de/recipes/locale.d.ts.map +1 -0
- package/out/de/recipes/locale.js +299 -0
- package/out/de/recipes/locale.js.map +1 -0
- package/out/directory.d.ts +20 -0
- package/out/directory.d.ts.map +1 -0
- package/out/directory.js +27 -0
- package/out/directory.js.map +1 -0
- package/out/dk/adapters/inspire/adapter.d.ts +154 -0
- package/out/dk/adapters/inspire/adapter.d.ts.map +1 -0
- package/out/dk/adapters/inspire/adapter.js +258 -0
- package/out/dk/adapters/inspire/adapter.js.map +1 -0
- package/out/dk/tools/fetch/inspire.d.ts +100 -0
- package/out/dk/tools/fetch/inspire.d.ts.map +1 -0
- package/out/dk/tools/fetch/inspire.js +230 -0
- package/out/dk/tools/fetch/inspire.js.map +1 -0
- package/out/ee/adapters/ads/adapter.d.ts +109 -0
- package/out/ee/adapters/ads/adapter.d.ts.map +1 -0
- package/out/ee/adapters/ads/adapter.js +191 -0
- package/out/ee/adapters/ads/adapter.js.map +1 -0
- package/out/ee/tools/fetch/ads.d.ts +123 -0
- package/out/ee/tools/fetch/ads.d.ts.map +1 -0
- package/out/ee/tools/fetch/ads.js +195 -0
- package/out/ee/tools/fetch/ads.js.map +1 -0
- package/out/env.d.ts +7 -3
- package/out/env.d.ts.map +1 -1
- package/out/env.js +6 -2
- package/out/env.js.map +1 -1
- package/out/es/adapters/bizkaia/adapter.d.ts +143 -0
- package/out/es/adapters/bizkaia/adapter.d.ts.map +1 -0
- package/out/es/adapters/bizkaia/adapter.js +332 -0
- package/out/es/adapters/bizkaia/adapter.js.map +1 -0
- package/out/es/adapters/catastro/adapter.d.ts +104 -0
- package/out/es/adapters/catastro/adapter.d.ts.map +1 -0
- package/out/es/adapters/catastro/adapter.js +288 -0
- package/out/es/adapters/catastro/adapter.js.map +1 -0
- package/out/es/adapters/gipuzkoa/adapter.d.ts +91 -0
- package/out/es/adapters/gipuzkoa/adapter.d.ts.map +1 -0
- package/out/es/adapters/gipuzkoa/adapter.js +225 -0
- package/out/es/adapters/gipuzkoa/adapter.js.map +1 -0
- package/out/es/adapters/navarra/adapter.d.ts +105 -0
- package/out/es/adapters/navarra/adapter.d.ts.map +1 -0
- package/out/es/adapters/navarra/adapter.js +241 -0
- package/out/es/adapters/navarra/adapter.js.map +1 -0
- package/out/es/cadastre.d.ts +109 -0
- package/out/es/cadastre.d.ts.map +1 -0
- package/out/es/cadastre.js +130 -0
- package/out/es/cadastre.js.map +1 -0
- package/out/es/tools/fetch/bizkaia.d.ts +278 -0
- package/out/es/tools/fetch/bizkaia.d.ts.map +1 -0
- package/out/es/tools/fetch/bizkaia.js +477 -0
- package/out/es/tools/fetch/bizkaia.js.map +1 -0
- package/out/es/tools/fetch/catastro.d.ts +272 -0
- package/out/es/tools/fetch/catastro.d.ts.map +1 -0
- package/out/es/tools/fetch/catastro.js +486 -0
- package/out/es/tools/fetch/catastro.js.map +1 -0
- package/out/es/tools/fetch/gipuzkoa.d.ts +162 -0
- package/out/es/tools/fetch/gipuzkoa.d.ts.map +1 -0
- package/out/es/tools/fetch/gipuzkoa.js +209 -0
- package/out/es/tools/fetch/gipuzkoa.js.map +1 -0
- package/out/es/tools/fetch/navarra.d.ts +189 -0
- package/out/es/tools/fetch/navarra.d.ts.map +1 -0
- package/out/es/tools/fetch/navarra.js +316 -0
- package/out/es/tools/fetch/navarra.js.map +1 -0
- package/out/fi/adapters/ryhti/adapter.d.ts +115 -0
- package/out/fi/adapters/ryhti/adapter.d.ts.map +1 -0
- package/out/fi/adapters/ryhti/adapter.js +244 -0
- package/out/fi/adapters/ryhti/adapter.js.map +1 -0
- package/out/fi/tools/fetch/ryhti.d.ts +206 -0
- package/out/fi/tools/fetch/ryhti.d.ts.map +1 -0
- package/out/fi/tools/fetch/ryhti.js +327 -0
- package/out/fi/tools/fetch/ryhti.js.map +1 -0
- package/out/fingerprints.d.ts +68 -0
- package/out/fingerprints.d.ts.map +1 -0
- package/out/fingerprints.js +130 -0
- package/out/fingerprints.js.map +1 -0
- package/out/fr/adapters/annuaire-education/adapter.d.ts +236 -0
- package/out/fr/adapters/annuaire-education/adapter.d.ts.map +1 -0
- package/out/fr/adapters/annuaire-education/adapter.js +475 -0
- package/out/fr/adapters/annuaire-education/adapter.js.map +1 -0
- package/out/fr/adapters/ban/adapter.d.ts +38 -0
- package/out/fr/adapters/ban/adapter.d.ts.map +1 -0
- package/out/fr/adapters/ban/adapter.js +134 -0
- package/out/fr/adapters/ban/adapter.js.map +1 -0
- package/out/fr/adapters/finess/adapter.d.ts +276 -0
- package/out/fr/adapters/finess/adapter.d.ts.map +1 -0
- package/out/fr/adapters/finess/adapter.js +519 -0
- package/out/fr/adapters/finess/adapter.js.map +1 -0
- package/out/fr/adapters/finess/postal-lines.d.ts +61 -0
- package/out/fr/adapters/finess/postal-lines.d.ts.map +1 -0
- package/out/fr/adapters/finess/postal-lines.js +114 -0
- package/out/fr/adapters/finess/postal-lines.js.map +1 -0
- package/out/fr/adapters/finess/voie-type.d.ts +77 -0
- package/out/fr/adapters/finess/voie-type.d.ts.map +1 -0
- package/out/fr/adapters/finess/voie-type.js +172 -0
- package/out/fr/adapters/finess/voie-type.js.map +1 -0
- package/out/fr/insee-country.d.ts +45 -0
- package/out/fr/insee-country.d.ts.map +1 -0
- package/out/fr/insee-country.js +60 -0
- package/out/fr/insee-country.js.map +1 -0
- package/out/fr/recipes/admin-split.d.ts +15 -0
- package/out/fr/recipes/admin-split.d.ts.map +1 -0
- package/out/fr/recipes/admin-split.js +170 -0
- package/out/fr/recipes/admin-split.js.map +1 -0
- package/out/fr/recipes/bare-street.d.ts +13 -0
- package/out/fr/recipes/bare-street.d.ts.map +1 -0
- package/out/fr/recipes/bare-street.js +129 -0
- package/out/fr/recipes/bare-street.js.map +1 -0
- package/out/fr/recipes/fragment.d.ts +18 -0
- package/out/fr/recipes/fragment.d.ts.map +1 -0
- package/out/fr/recipes/fragment.js +197 -0
- package/out/fr/recipes/fragment.js.map +1 -0
- package/out/fr/recipes/lieudit.d.ts +30 -0
- package/out/fr/recipes/lieudit.d.ts.map +1 -0
- package/out/fr/recipes/lieudit.js +231 -0
- package/out/fr/recipes/lieudit.js.map +1 -0
- package/out/fr/recipes/order.d.ts +15 -0
- package/out/fr/recipes/order.d.ts.map +1 -0
- package/out/fr/recipes/order.js +171 -0
- package/out/fr/recipes/order.js.map +1 -0
- package/out/fr/street-decompose.d.ts +29 -0
- package/out/fr/street-decompose.d.ts.map +1 -0
- package/out/fr/street-decompose.js +52 -0
- package/out/fr/street-decompose.js.map +1 -0
- package/out/fr/tools/fetch/annuaire-education.d.ts +130 -0
- package/out/fr/tools/fetch/annuaire-education.d.ts.map +1 -0
- package/out/fr/tools/fetch/annuaire-education.js +196 -0
- package/out/fr/tools/fetch/annuaire-education.js.map +1 -0
- package/out/fr/tools/fetch/ban.d.ts +33 -0
- package/out/fr/tools/fetch/ban.d.ts.map +1 -0
- package/out/fr/tools/fetch/ban.js +248 -0
- package/out/fr/tools/fetch/ban.js.map +1 -0
- package/out/fr/tools/fetch/finess.d.ts +145 -0
- package/out/fr/tools/fetch/finess.d.ts.map +1 -0
- package/out/fr/tools/fetch/finess.js +228 -0
- package/out/fr/tools/fetch/finess.js.map +1 -0
- package/out/gauntlet-inputs.d.ts +42 -0
- package/out/gauntlet-inputs.d.ts.map +1 -0
- package/out/gauntlet-inputs.js +78 -0
- package/out/gauntlet-inputs.js.map +1 -0
- package/out/index.d.ts +10 -4
- package/out/index.d.ts.map +1 -1
- package/out/index.js +10 -4
- package/out/index.js.map +1 -1
- package/out/inspire/address.d.ts +251 -0
- package/out/inspire/address.d.ts.map +1 -0
- package/out/inspire/address.js +384 -0
- package/out/inspire/address.js.map +1 -0
- package/out/inspire/archive.d.ts +36 -0
- package/out/inspire/archive.d.ts.map +1 -0
- package/out/inspire/archive.js +42 -0
- package/out/inspire/archive.js.map +1 -0
- package/out/inspire/errors.d.ts +55 -0
- package/out/inspire/errors.d.ts.map +1 -0
- package/out/inspire/errors.js +64 -0
- package/out/inspire/errors.js.map +1 -0
- package/out/inspire/stream.d.ts +137 -0
- package/out/inspire/stream.d.ts.map +1 -0
- package/out/inspire/stream.js +125 -0
- package/out/inspire/stream.js.map +1 -0
- package/out/international/recipes/locale.d.ts +90 -0
- package/out/international/recipes/locale.d.ts.map +1 -0
- package/out/international/recipes/locale.js +419 -0
- package/out/international/recipes/locale.js.map +1 -0
- package/out/it/adapters/anac/adapter.d.ts +267 -0
- package/out/it/adapters/anac/adapter.d.ts.map +1 -0
- package/out/it/adapters/anac/adapter.js +429 -0
- package/out/it/adapters/anac/adapter.js.map +1 -0
- package/out/it/tools/fetch/anac.d.ts +174 -0
- package/out/it/tools/fetch/anac.d.ts.map +1 -0
- package/out/it/tools/fetch/anac.js +272 -0
- package/out/it/tools/fetch/anac.js.map +1 -0
- package/out/jp/adapters/wof-admin/adapter.d.ts +68 -0
- package/out/jp/adapters/wof-admin/adapter.d.ts.map +1 -0
- package/out/jp/adapters/wof-admin/adapter.js +172 -0
- package/out/jp/adapters/wof-admin/adapter.js.map +1 -0
- package/out/jp/tools/fetch/houjin.d.ts +27 -0
- package/out/jp/tools/fetch/houjin.d.ts.map +1 -0
- package/out/jp/tools/fetch/houjin.js +106 -0
- package/out/jp/tools/fetch/houjin.js.map +1 -0
- package/out/kr/adapters/juso/label-rows.d.ts +62 -0
- package/out/kr/adapters/juso/label-rows.d.ts.map +1 -0
- package/out/kr/adapters/juso/label-rows.js +172 -0
- package/out/kr/adapters/juso/label-rows.js.map +1 -0
- package/out/kr/adapters/localdata/align.d.ts +31 -0
- package/out/kr/adapters/localdata/align.d.ts.map +1 -0
- package/out/kr/adapters/localdata/align.js +212 -0
- package/out/kr/adapters/localdata/align.js.map +1 -0
- package/out/kr/adapters/localdata/key-index.d.ts +62 -0
- package/out/kr/adapters/localdata/key-index.d.ts.map +1 -0
- package/out/kr/adapters/localdata/key-index.js +127 -0
- package/out/kr/adapters/localdata/key-index.js.map +1 -0
- package/out/kr/adapters/localdata/permit-rows.d.ts +73 -0
- package/out/kr/adapters/localdata/permit-rows.d.ts.map +1 -0
- package/out/kr/adapters/localdata/permit-rows.js +136 -0
- package/out/kr/adapters/localdata/permit-rows.js.map +1 -0
- package/out/kr/tools/fetch/juso.d.ts +33 -0
- package/out/kr/tools/fetch/juso.d.ts.map +1 -0
- package/out/kr/tools/fetch/juso.js +121 -0
- package/out/kr/tools/fetch/juso.js.map +1 -0
- package/out/kr/tools/fetch/localdata.d.ts +37 -0
- package/out/kr/tools/fetch/localdata.d.ts.map +1 -0
- package/out/kr/tools/fetch/localdata.js +147 -0
- package/out/kr/tools/fetch/localdata.js.map +1 -0
- package/out/lu/adapters/bd-adresses/adapter.d.ts +109 -0
- package/out/lu/adapters/bd-adresses/adapter.d.ts.map +1 -0
- package/out/lu/adapters/bd-adresses/adapter.js +196 -0
- package/out/lu/adapters/bd-adresses/adapter.js.map +1 -0
- package/out/lu/tools/fetch/bd-adresses.d.ts +163 -0
- package/out/lu/tools/fetch/bd-adresses.d.ts.map +1 -0
- package/out/lu/tools/fetch/bd-adresses.js +223 -0
- package/out/lu/tools/fetch/bd-adresses.js.map +1 -0
- package/out/lv/adapters/varis/adapter.d.ts +283 -0
- package/out/lv/adapters/varis/adapter.d.ts.map +1 -0
- package/out/lv/adapters/varis/adapter.js +404 -0
- package/out/lv/adapters/varis/adapter.js.map +1 -0
- package/out/lv/tools/fetch/varis.d.ts +80 -0
- package/out/lv/tools/fetch/varis.d.ts.map +1 -0
- package/out/lv/tools/fetch/varis.js +133 -0
- package/out/lv/tools/fetch/varis.js.map +1 -0
- package/out/nl/adapters/kadaster/adapter.d.ts +125 -0
- package/out/nl/adapters/kadaster/adapter.d.ts.map +1 -0
- package/out/nl/adapters/kadaster/adapter.js +310 -0
- package/out/nl/adapters/kadaster/adapter.js.map +1 -0
- package/out/nl/recipes/postcode.d.ts +24 -0
- package/out/nl/recipes/postcode.d.ts.map +1 -0
- package/out/nl/recipes/postcode.js +121 -0
- package/out/nl/recipes/postcode.js.map +1 -0
- package/out/nl/tools/fetch/kadaster.d.ts +155 -0
- package/out/nl/tools/fetch/kadaster.d.ts.map +1 -0
- package/out/nl/tools/fetch/kadaster.js +179 -0
- package/out/nl/tools/fetch/kadaster.js.map +1 -0
- package/out/no/adapters/matrikkelen/adapter.d.ts +44 -0
- package/out/no/adapters/matrikkelen/adapter.d.ts.map +1 -0
- package/out/no/adapters/matrikkelen/adapter.js +143 -0
- package/out/no/adapters/matrikkelen/adapter.js.map +1 -0
- package/out/no/recipes/fragment.d.ts +11 -0
- package/out/no/recipes/fragment.d.ts.map +1 -0
- package/out/no/recipes/fragment.js +149 -0
- package/out/no/recipes/fragment.js.map +1 -0
- package/out/no/recipes/street/led.d.ts +21 -0
- package/out/no/recipes/street/led.d.ts.map +1 -0
- package/out/no/recipes/street/led.js +124 -0
- package/out/no/recipes/street/led.js.map +1 -0
- package/out/no/recipes/street.d.ts +19 -0
- package/out/no/recipes/street.d.ts.map +1 -0
- package/out/no/recipes/street.js +88 -0
- package/out/no/recipes/street.js.map +1 -0
- package/out/no/tools/fetch/matrikkelen.d.ts +251 -0
- package/out/no/tools/fetch/matrikkelen.d.ts.map +1 -0
- package/out/no/tools/fetch/matrikkelen.js +345 -0
- package/out/no/tools/fetch/matrikkelen.js.map +1 -0
- package/out/parquet/duckdb.d.ts +100 -0
- package/out/parquet/duckdb.d.ts.map +1 -0
- package/out/parquet/duckdb.js +92 -0
- package/out/parquet/duckdb.js.map +1 -0
- package/out/parquet/readers.d.ts +44 -0
- package/out/parquet/readers.d.ts.map +1 -0
- package/out/parquet/readers.js +69 -0
- package/out/parquet/readers.js.map +1 -0
- package/out/parquet/schema.d.ts +95 -0
- package/out/parquet/schema.d.ts.map +1 -0
- package/out/parquet/schema.js +157 -0
- package/out/parquet/schema.js.map +1 -0
- package/out/parquet/shuffle.d.ts +25 -0
- package/out/parquet/shuffle.d.ts.map +1 -0
- package/out/parquet/shuffle.js +44 -0
- package/out/parquet/shuffle.js.map +1 -0
- package/out/parquet/span-sql.d.ts +49 -0
- package/out/parquet/span-sql.d.ts.map +1 -0
- package/out/parquet/span-sql.js +53 -0
- package/out/parquet/span-sql.js.map +1 -0
- package/out/parquet/streams.d.ts +47 -0
- package/out/parquet/streams.d.ts.map +1 -0
- package/out/parquet/streams.js +78 -0
- package/out/parquet/streams.js.map +1 -0
- package/out/parquet/writers.d.ts +124 -0
- package/out/parquet/writers.d.ts.map +1 -0
- package/out/parquet/writers.js +251 -0
- package/out/parquet/writers.js.map +1 -0
- package/out/pl/adapters/emuia/adapter.d.ts +81 -0
- package/out/pl/adapters/emuia/adapter.d.ts.map +1 -0
- package/out/pl/adapters/emuia/adapter.js +178 -0
- package/out/pl/adapters/emuia/adapter.js.map +1 -0
- package/out/pl/tools/fetch/emuia.d.ts +165 -0
- package/out/pl/tools/fetch/emuia.d.ts.map +1 -0
- package/out/pl/tools/fetch/emuia.js +260 -0
- package/out/pl/tools/fetch/emuia.js.map +1 -0
- package/out/recipes/anchor-absorption.d.ts +9 -9
- package/out/recipes/anchor-absorption.d.ts.map +1 -1
- package/out/recipes/anchor-absorption.js +29 -19
- package/out/recipes/anchor-absorption.js.map +1 -1
- package/out/recipes/bare/country.d.ts +7 -0
- package/out/recipes/bare/country.d.ts.map +1 -0
- package/out/recipes/bare/country.js +77 -0
- package/out/recipes/bare/country.js.map +1 -0
- package/out/recipes/bare/postcode/eval.d.ts +29 -0
- package/out/recipes/bare/postcode/eval.d.ts.map +1 -0
- package/out/recipes/bare/postcode/eval.js +85 -0
- package/out/recipes/bare/postcode/eval.js.map +1 -0
- package/out/recipes/bare/postcode.d.ts +41 -0
- package/out/recipes/bare/postcode.d.ts.map +1 -0
- package/out/recipes/bare/postcode.js +279 -0
- package/out/recipes/bare/postcode.js.map +1 -0
- package/out/recipes/boundary-stress.d.ts +8 -8
- package/out/recipes/boundary-stress.d.ts.map +1 -1
- package/out/recipes/boundary-stress.js +36 -19
- package/out/recipes/boundary-stress.js.map +1 -1
- package/out/recipes/country-balanced.d.ts +3 -21
- package/out/recipes/country-balanced.d.ts.map +1 -1
- package/out/recipes/country-balanced.js +58 -76
- package/out/recipes/country-balanced.js.map +1 -1
- package/out/recipes/house-venue.d.ts +8 -6
- package/out/recipes/house-venue.d.ts.map +1 -1
- package/out/recipes/house-venue.js +29 -13
- package/out/recipes/house-venue.js.map +1 -1
- package/out/recipes/intersection.d.ts +20 -20
- package/out/recipes/intersection.d.ts.map +1 -1
- package/out/recipes/intersection.js +65 -53
- package/out/recipes/intersection.js.map +1 -1
- package/out/recipes/po/box/cedex/au-nz.d.ts +7 -0
- package/out/recipes/po/box/cedex/au-nz.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/au-nz.js +56 -0
- package/out/recipes/po/box/cedex/au-nz.js.map +1 -0
- package/out/recipes/po/box/cedex/ca.d.ts +7 -0
- package/out/recipes/po/box/cedex/ca.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/ca.js +38 -0
- package/out/recipes/po/box/cedex/ca.js.map +1 -0
- package/out/recipes/po/box/cedex/fr.d.ts +7 -0
- package/out/recipes/po/box/cedex/fr.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/fr.js +57 -0
- package/out/recipes/po/box/cedex/fr.js.map +1 -0
- package/out/recipes/po/box/cedex/phrases.d.ts +8 -0
- package/out/recipes/po/box/cedex/phrases.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/phrases.js +77 -0
- package/out/recipes/po/box/cedex/phrases.js.map +1 -0
- package/out/recipes/po/box/cedex/recipe.d.ts +9 -0
- package/out/recipes/po/box/cedex/recipe.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/recipe.js +163 -0
- package/out/recipes/po/box/cedex/recipe.js.map +1 -0
- package/out/recipes/po/box/cedex/sources.d.ts +86 -0
- package/out/recipes/po/box/cedex/sources.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/sources.js +143 -0
- package/out/recipes/po/box/cedex/sources.js.map +1 -0
- package/out/recipes/po/box/cedex/types.d.ts +31 -0
- package/out/recipes/po/box/cedex/types.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/types.js +5 -0
- package/out/recipes/po/box/cedex/types.js.map +1 -0
- package/out/recipes/po/box/cedex/us.d.ts +7 -0
- package/out/recipes/po/box/cedex/us.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/us.js +54 -0
- package/out/recipes/po/box/cedex/us.js.map +1 -0
- package/out/recipes/po/box/cedex/vocabulary.d.ts +68 -0
- package/out/recipes/po/box/cedex/vocabulary.d.ts.map +1 -0
- package/out/recipes/po/box/cedex/vocabulary.js +90 -0
- package/out/recipes/po/box/cedex/vocabulary.js.map +1 -0
- package/out/recipes/po/box/cedex.d.ts +9 -0
- package/out/recipes/po/box/cedex.d.ts.map +1 -0
- package/out/recipes/po/box/cedex.js +9 -0
- package/out/recipes/po/box/cedex.js.map +1 -0
- package/out/recipes/po/box.d.ts +18 -0
- package/out/recipes/po/box.d.ts.map +1 -0
- package/out/recipes/po/box.js +123 -0
- package/out/recipes/po/box.js.map +1 -0
- package/out/recipes/scaffold.d.ts +214 -121
- package/out/recipes/scaffold.d.ts.map +1 -1
- package/out/recipes/scaffold.js +78 -88
- package/out/recipes/scaffold.js.map +1 -1
- package/out/recipes/sources.d.ts +178 -0
- package/out/recipes/sources.d.ts.map +1 -0
- package/out/recipes/sources.js +348 -0
- package/out/recipes/sources.js.map +1 -0
- package/out/recipes/street/affix.d.ts +59 -0
- package/out/recipes/street/affix.d.ts.map +1 -0
- package/out/recipes/street/affix.js +477 -0
- package/out/recipes/street/affix.js.map +1 -0
- package/out/recipes/street/bare.d.ts +27 -0
- package/out/recipes/street/bare.d.ts.map +1 -0
- package/out/recipes/street/bare.js +98 -0
- package/out/recipes/street/bare.js.map +1 -0
- package/out/recipes/street.d.ts +6 -4
- package/out/recipes/street.d.ts.map +1 -1
- package/out/recipes/street.js +29 -8
- package/out/recipes/street.js.map +1 -1
- package/out/recipes/sub/venue/context.d.ts +32 -0
- package/out/recipes/sub/venue/context.d.ts.map +1 -0
- package/out/recipes/sub/venue/context.js +110 -0
- package/out/recipes/sub/venue/context.js.map +1 -0
- package/out/recipes/sub/venue/render.d.ts +58 -0
- package/out/recipes/sub/venue/render.d.ts.map +1 -0
- package/out/recipes/sub/venue/render.js +118 -0
- package/out/recipes/sub/venue/render.js.map +1 -0
- package/out/recipes/sub/venue/sources.d.ts +166 -0
- package/out/recipes/sub/venue/sources.d.ts.map +1 -0
- package/out/recipes/sub/venue/sources.js +419 -0
- package/out/recipes/sub/venue/sources.js.map +1 -0
- package/out/recipes/sub/venue.d.ts +176 -0
- package/out/recipes/sub/venue.d.ts.map +1 -0
- package/out/recipes/sub/venue.js +562 -0
- package/out/recipes/sub/venue.js.map +1 -0
- package/out/recipes/trailing-region.d.ts +9 -61
- package/out/recipes/trailing-region.d.ts.map +1 -1
- package/out/recipes/trailing-region.js +56 -81
- package/out/recipes/trailing-region.js.map +1 -1
- package/out/recipes/unit/sources.d.ts +28 -0
- package/out/recipes/unit/sources.d.ts.map +1 -0
- package/out/recipes/unit/sources.js +30 -0
- package/out/recipes/unit/sources.js.map +1 -0
- package/out/recipes/unit.d.ts +30 -17
- package/out/recipes/unit.d.ts.map +1 -1
- package/out/recipes/unit.js +90 -79
- package/out/recipes/unit.js.map +1 -1
- package/out/recipes.d.ts +26 -0
- package/out/recipes.d.ts.map +1 -0
- package/out/recipes.js +100 -0
- package/out/recipes.js.map +1 -0
- package/out/registers.d.ts +277 -0
- package/out/registers.d.ts.map +1 -0
- package/out/registers.js +273 -0
- package/out/registers.js.map +1 -0
- package/out/ro/adapters/retea-scolara/adapter.d.ts +114 -0
- package/out/ro/adapters/retea-scolara/adapter.d.ts.map +1 -0
- package/out/ro/adapters/retea-scolara/adapter.js +209 -0
- package/out/ro/adapters/retea-scolara/adapter.js.map +1 -0
- package/out/ro/tools/fetch/retea-scolara.d.ts +69 -0
- package/out/ro/tools/fetch/retea-scolara.d.ts.map +1 -0
- package/out/ro/tools/fetch/retea-scolara.js +117 -0
- package/out/ro/tools/fetch/retea-scolara.js.map +1 -0
- package/out/runner.d.ts +120 -60
- package/out/runner.d.ts.map +1 -1
- package/out/runner.js +130 -56
- package/out/runner.js.map +1 -1
- package/out/sg/recipes/register.d.ts +55 -0
- package/out/sg/recipes/register.d.ts.map +1 -0
- package/out/sg/recipes/register.js +206 -0
- package/out/sg/recipes/register.js.map +1 -0
- package/out/sg/tools/fetch/acra.d.ts +20 -0
- package/out/sg/tools/fetch/acra.d.ts.map +1 -0
- package/out/sg/tools/fetch/acra.js +123 -0
- package/out/sg/tools/fetch/acra.js.map +1 -0
- package/out/si/recipes/bare-village.d.ts +31 -0
- package/out/si/recipes/bare-village.d.ts.map +1 -0
- package/out/si/recipes/bare-village.js +103 -0
- package/out/si/recipes/bare-village.js.map +1 -0
- package/out/sk/adapters/inspire/adapter.d.ts +119 -0
- package/out/sk/adapters/inspire/adapter.d.ts.map +1 -0
- package/out/sk/adapters/inspire/adapter.js +318 -0
- package/out/sk/adapters/inspire/adapter.js.map +1 -0
- package/out/sk/tools/fetch/inspire.d.ts +195 -0
- package/out/sk/tools/fetch/inspire.d.ts.map +1 -0
- package/out/sk/tools/fetch/inspire.js +280 -0
- package/out/sk/tools/fetch/inspire.js.map +1 -0
- package/out/source-register/effective-manifest.d.ts +355 -0
- package/out/source-register/effective-manifest.d.ts.map +1 -0
- package/out/source-register/effective-manifest.js +355 -0
- package/out/source-register/effective-manifest.js.map +1 -0
- package/out/source-register/register.d.ts +79 -0
- package/out/source-register/register.d.ts.map +1 -0
- package/out/source-register/register.js +400 -0
- package/out/source-register/register.js.map +1 -0
- package/out/source-register/training-manifest.d.ts +111 -0
- package/out/source-register/training-manifest.d.ts.map +1 -0
- package/out/source-register/training-manifest.js +120 -0
- package/out/source-register/training-manifest.js.map +1 -0
- package/out/source-register/types.d.ts +539 -0
- package/out/source-register/types.d.ts.map +1 -0
- package/out/source-register/types.js +263 -0
- package/out/source-register/types.js.map +1 -0
- package/out/source-register.d.ts +19 -0
- package/out/source-register.d.ts.map +1 -0
- package/out/source-register.js +16 -0
- package/out/source-register.js.map +1 -0
- package/out/south-asia/recipes/register.d.ts +54 -0
- package/out/south-asia/recipes/register.d.ts.map +1 -0
- package/out/south-asia/recipes/register.js +174 -0
- package/out/south-asia/recipes/register.js.map +1 -0
- package/out/subvenue/harvest.d.ts +117 -0
- package/out/subvenue/harvest.d.ts.map +1 -0
- package/out/subvenue/harvest.js +172 -0
- package/out/subvenue/harvest.js.map +1 -0
- package/out/subvenue/promotions.d.ts +65 -0
- package/out/subvenue/promotions.d.ts.map +1 -0
- package/out/subvenue/promotions.js +226 -0
- package/out/subvenue/promotions.js.map +1 -0
- package/out/subvenue/surfaces.d.ts +39 -0
- package/out/subvenue/surfaces.d.ts.map +1 -0
- package/out/subvenue/surfaces.js +75 -0
- package/out/subvenue/surfaces.js.map +1 -0
- package/out/subvenue/table.d.ts +212 -0
- package/out/subvenue/table.d.ts.map +1 -0
- package/out/subvenue/table.js +94 -0
- package/out/subvenue/table.js.map +1 -0
- package/out/surfaces/locale.d.ts +113 -0
- package/out/surfaces/locale.d.ts.map +1 -0
- package/out/surfaces/locale.js +136 -0
- package/out/surfaces/locale.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +22 -31
- package/out/synthesizers/anchor-absorption.d.ts.map +1 -1
- package/out/synthesizers/anchor-absorption.js +30 -85
- package/out/synthesizers/anchor-absorption.js.map +1 -1
- package/out/synthesizers/boundary-stress.d.ts +17 -48
- package/out/synthesizers/boundary-stress.d.ts.map +1 -1
- package/out/synthesizers/boundary-stress.js +27 -121
- package/out/synthesizers/boundary-stress.js.map +1 -1
- package/out/synthesizers/house-venue.d.ts +22 -25
- package/out/synthesizers/house-venue.d.ts.map +1 -1
- package/out/synthesizers/house-venue.js +28 -97
- package/out/synthesizers/house-venue.js.map +1 -1
- package/out/synthesizers/intersection.d.ts +10 -8
- package/out/synthesizers/intersection.d.ts.map +1 -1
- package/out/synthesizers/intersection.js +33 -26
- package/out/synthesizers/intersection.js.map +1 -1
- package/out/synthesizers/no-street.d.ts +7 -37
- package/out/synthesizers/no-street.d.ts.map +1 -1
- package/out/synthesizers/no-street.js +55 -111
- package/out/synthesizers/no-street.js.map +1 -1
- package/out/synthesizers/po-box.d.ts +46 -45
- package/out/synthesizers/po-box.d.ts.map +1 -1
- package/out/synthesizers/po-box.js +57 -97
- package/out/synthesizers/po-box.js.map +1 -1
- package/out/synthesizers/street.d.ts +18 -12
- package/out/synthesizers/street.d.ts.map +1 -1
- package/out/synthesizers/street.js +37 -30
- package/out/synthesizers/street.js.map +1 -1
- package/out/synthesizers/utils.d.ts +32 -129
- package/out/synthesizers/utils.d.ts.map +1 -1
- package/out/synthesizers/utils.js +54 -166
- package/out/synthesizers/utils.js.map +1 -1
- package/out/test-kit/corpus-recipe.d.ts +29 -23
- package/out/test-kit/corpus-recipe.d.ts.map +1 -1
- package/out/test-kit/corpus-recipe.js +28 -13
- package/out/test-kit/corpus-recipe.js.map +1 -1
- package/out/test-kit.d.ts +63 -0
- package/out/test-kit.d.ts.map +1 -0
- package/out/test-kit.js +88 -0
- package/out/test-kit.js.map +1 -0
- package/out/tools/align-canonical.d.ts +7 -0
- package/out/tools/align-canonical.d.ts.map +1 -0
- package/out/tools/align-canonical.js +52 -0
- package/out/tools/align-canonical.js.map +1 -0
- package/out/tools/audit.d.ts +18 -11
- package/out/tools/audit.d.ts.map +1 -1
- package/out/tools/audit.js +87 -95
- package/out/tools/audit.js.map +1 -1
- package/out/tools/corpus-stats.d.ts +24 -15
- package/out/tools/corpus-stats.d.ts.map +1 -1
- package/out/tools/corpus-stats.js +35 -31
- package/out/tools/corpus-stats.js.map +1 -1
- package/out/tools/fetch/atom.d.ts +115 -0
- package/out/tools/fetch/atom.d.ts.map +1 -0
- package/out/tools/fetch/atom.js +84 -0
- package/out/tools/fetch/atom.js.map +1 -0
- package/out/tools/fetch/cordis.d.ts +123 -0
- package/out/tools/fetch/cordis.d.ts.map +1 -0
- package/out/tools/fetch/cordis.js +208 -0
- package/out/tools/fetch/cordis.js.map +1 -0
- package/out/tools/fetch/download/manifest.d.ts +56 -0
- package/out/tools/fetch/download/manifest.d.ts.map +1 -0
- package/out/tools/fetch/download/manifest.js +81 -0
- package/out/tools/fetch/download/manifest.js.map +1 -0
- package/out/tools/fetch/download/network.d.ts +126 -0
- package/out/tools/fetch/download/network.d.ts.map +1 -0
- package/out/tools/fetch/download/network.js +140 -0
- package/out/tools/fetch/download/network.js.map +1 -0
- package/out/tools/fetch/download/retry.d.ts +46 -0
- package/out/tools/fetch/download/retry.d.ts.map +1 -0
- package/out/tools/fetch/download/retry.js +136 -0
- package/out/tools/fetch/download/retry.js.map +1 -0
- package/out/tools/fetch/download.d.ts +4 -176
- package/out/tools/fetch/download.d.ts.map +1 -1
- package/out/tools/fetch/download.js +4 -312
- package/out/tools/fetch/download.js.map +1 -1
- package/out/tools/fetch/geonames/dump.d.ts +109 -0
- package/out/tools/fetch/geonames/dump.d.ts.map +1 -0
- package/out/tools/fetch/geonames/dump.js +181 -0
- package/out/tools/fetch/geonames/dump.js.map +1 -0
- package/out/tools/fetch/geonames/postal.d.ts +41 -0
- package/out/tools/fetch/geonames/postal.d.ts.map +1 -0
- package/out/tools/fetch/geonames/postal.js +87 -0
- package/out/tools/fetch/geonames/postal.js.map +1 -0
- package/out/tools/fetch/gleif.d.ts +137 -0
- package/out/tools/fetch/gleif.d.ts.map +1 -0
- package/out/tools/fetch/gleif.js +220 -0
- package/out/tools/fetch/gleif.js.map +1 -0
- package/out/tools/fetch/header.d.ts +41 -0
- package/out/tools/fetch/header.d.ts.map +1 -0
- package/out/tools/fetch/header.js +59 -0
- package/out/tools/fetch/header.js.map +1 -0
- package/out/tools/fetch/inspire-addresses.d.ts +249 -0
- package/out/tools/fetch/inspire-addresses.d.ts.map +1 -0
- package/out/tools/fetch/inspire-addresses.js +276 -0
- package/out/tools/fetch/inspire-addresses.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +0 -3
- package/out/tools/fetch/openaddresses.d.ts.map +1 -1
- package/out/tools/fetch/openaddresses.js +18 -97
- package/out/tools/fetch/openaddresses.js.map +1 -1
- package/out/tools/fetch/ourairports.d.ts +5 -32
- package/out/tools/fetch/ourairports.d.ts.map +1 -1
- package/out/tools/fetch/ourairports.js +13 -46
- package/out/tools/fetch/ourairports.js.map +1 -1
- package/out/tools/fetch/ppd.d.ts +4 -3
- package/out/tools/fetch/ppd.d.ts.map +1 -1
- package/out/tools/fetch/ppd.js +10 -9
- package/out/tools/fetch/ppd.js.map +1 -1
- package/out/tools/fetch/vlaanderen-ad.d.ts +131 -0
- package/out/tools/fetch/vlaanderen-ad.d.ts.map +1 -0
- package/out/tools/fetch/vlaanderen-ad.js +293 -0
- package/out/tools/fetch/vlaanderen-ad.js.map +1 -0
- package/out/tools/fetch/wfs-harvest.d.ts +410 -0
- package/out/tools/fetch/wfs-harvest.d.ts.map +1 -0
- package/out/tools/fetch/wfs-harvest.js +522 -0
- package/out/tools/fetch/wfs-harvest.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +31 -99
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -1
- package/out/tools/fetch/wikidata-subvenue.js +26 -121
- package/out/tools/fetch/wikidata-subvenue.js.map +1 -1
- package/out/tools/fetch/zip-archive.d.ts +54 -0
- package/out/tools/fetch/zip-archive.d.ts.map +1 -0
- package/out/tools/fetch/zip-archive.js +58 -0
- package/out/tools/fetch/zip-archive.js.map +1 -0
- package/out/tools/fetch.d.ts +140 -0
- package/out/tools/fetch.d.ts.map +1 -0
- package/out/tools/fetch.js +136 -0
- package/out/tools/fetch.js.map +1 -0
- package/out/tools/golden/expand.d.ts +105 -0
- package/out/tools/golden/expand.d.ts.map +1 -0
- package/out/tools/golden/expand.js +420 -0
- package/out/tools/golden/expand.js.map +1 -0
- package/out/tools/golden/promote.d.ts +77 -0
- package/out/tools/golden/promote.d.ts.map +1 -0
- package/out/tools/golden/promote.js +248 -0
- package/out/tools/golden/promote.js.map +1 -0
- package/out/tools/golden/relabel-street/directory.d.ts +98 -0
- package/out/tools/golden/relabel-street/directory.d.ts.map +1 -0
- package/out/tools/golden/relabel-street/directory.js +227 -0
- package/out/tools/golden/relabel-street/directory.js.map +1 -0
- package/out/tools/golden/relabel-street/row.d.ts +69 -0
- package/out/tools/golden/relabel-street/row.d.ts.map +1 -0
- package/out/tools/golden/relabel-street/row.js +174 -0
- package/out/tools/golden/relabel-street/row.js.map +1 -0
- package/out/tools/golden/relabel-street.d.ts +9 -0
- package/out/tools/golden/relabel-street.d.ts.map +1 -0
- package/out/tools/golden/relabel-street.js +9 -0
- package/out/tools/golden/relabel-street.js.map +1 -0
- package/out/tools/ingest-csv.d.ts +19 -15
- package/out/tools/ingest-csv.d.ts.map +1 -1
- package/out/tools/ingest-csv.js +39 -45
- package/out/tools/ingest-csv.js.map +1 -1
- package/out/tools/jsonl-to-parquet.d.ts +15 -28
- package/out/tools/jsonl-to-parquet.d.ts.map +1 -1
- package/out/tools/jsonl-to-parquet.js +49 -91
- package/out/tools/jsonl-to-parquet.js.map +1 -1
- package/out/tools/lint/recipe-output/vocab.d.ts +77 -0
- package/out/tools/lint/recipe-output/vocab.d.ts.map +1 -0
- package/out/tools/lint/recipe-output/vocab.js +239 -0
- package/out/tools/lint/recipe-output/vocab.js.map +1 -0
- package/out/tools/lint/recipe-output.d.ts +73 -0
- package/out/tools/lint/recipe-output.d.ts.map +1 -0
- package/out/tools/lint/recipe-output.js +302 -0
- package/out/tools/lint/recipe-output.js.map +1 -0
- package/out/tools/migrate/overlay-parquet.d.ts +30 -0
- package/out/tools/migrate/overlay-parquet.d.ts.map +1 -0
- package/out/tools/migrate/overlay-parquet.js +141 -0
- package/out/tools/migrate/overlay-parquet.js.map +1 -0
- package/out/tools/migrate/recipe-output.d.ts +35 -0
- package/out/tools/migrate/recipe-output.d.ts.map +1 -0
- package/out/tools/migrate/recipe-output.js +124 -0
- package/out/tools/migrate/recipe-output.js.map +1 -0
- package/out/tools/migrate/source-names.d.ts +52 -0
- package/out/tools/migrate/source-names.d.ts.map +1 -0
- package/out/tools/migrate/source-names.js +105 -0
- package/out/tools/migrate/source-names.js.map +1 -0
- package/out/tools/overlay/kryptonite.d.ts +33 -0
- package/out/tools/overlay/kryptonite.d.ts.map +1 -0
- package/out/tools/overlay/kryptonite.js +108 -0
- package/out/tools/overlay/kryptonite.js.map +1 -0
- package/out/tools/overlay/manifest.d.ts +142 -0
- package/out/tools/overlay/manifest.d.ts.map +1 -0
- package/out/tools/overlay/manifest.js +260 -0
- package/out/tools/overlay/manifest.js.map +1 -0
- package/out/tools/overlay/merge-source.d.ts +73 -0
- package/out/tools/overlay/merge-source.d.ts.map +1 -0
- package/out/tools/overlay/merge-source.js +63 -0
- package/out/tools/overlay/merge-source.js.map +1 -0
- package/out/tools/overlay/split-slice.d.ts +66 -0
- package/out/tools/overlay/split-slice.d.ts.map +1 -0
- package/out/tools/overlay/split-slice.js +78 -0
- package/out/tools/overlay/split-slice.js.map +1 -0
- package/out/tools/overlay/translit.d.ts +54 -0
- package/out/tools/overlay/translit.d.ts.map +1 -0
- package/out/tools/overlay/translit.js +177 -0
- package/out/tools/overlay/translit.js.map +1 -0
- package/out/tools/overture-subvenue.d.ts +17 -76
- package/out/tools/overture-subvenue.d.ts.map +1 -1
- package/out/tools/overture-subvenue.js +7 -74
- package/out/tools/overture-subvenue.js.map +1 -1
- package/out/tools/postcode-triples.d.ts +96 -109
- package/out/tools/postcode-triples.d.ts.map +1 -1
- package/out/tools/postcode-triples.js +237 -152
- package/out/tools/postcode-triples.js.map +1 -1
- package/out/tools/source-register/build.d.ts +145 -0
- package/out/tools/source-register/build.d.ts.map +1 -0
- package/out/tools/source-register/build.js +515 -0
- package/out/tools/source-register/build.js.map +1 -0
- package/out/tools/sub/venue/head-nouns.d.ts +21 -0
- package/out/tools/sub/venue/head-nouns.d.ts.map +1 -0
- package/out/tools/sub/venue/head-nouns.js +176 -0
- package/out/tools/sub/venue/head-nouns.js.map +1 -0
- package/out/tools/sub/venue/lexicon.d.ts +129 -0
- package/out/tools/sub/venue/lexicon.d.ts.map +1 -0
- package/out/tools/sub/venue/lexicon.js +239 -0
- package/out/tools/sub/venue/lexicon.js.map +1 -0
- package/out/tools/sub/venue/wikidata.d.ts +28 -0
- package/out/tools/sub/venue/wikidata.d.ts.map +1 -0
- package/out/tools/sub/venue/wikidata.js +65 -0
- package/out/tools/sub/venue/wikidata.js.map +1 -0
- package/out/tools.d.ts +31 -0
- package/out/tools.d.ts.map +1 -0
- package/out/tools.js +31 -0
- package/out/tools.js.map +1 -0
- package/out/tw/tools/fetch/gcis.d.ts +29 -0
- package/out/tw/tools/fetch/gcis.d.ts.map +1 -0
- package/out/tw/tools/fetch/gcis.js +141 -0
- package/out/tw/tools/fetch/gcis.js.map +1 -0
- package/out/types.d.ts +270 -101
- package/out/types.d.ts.map +1 -1
- package/out/types.js +133 -9
- package/out/types.js.map +1 -1
- package/out/us/adapters/fcc-bdc/adapter.d.ts +50 -0
- package/out/us/adapters/fcc-bdc/adapter.d.ts.map +1 -0
- package/out/us/adapters/fcc-bdc/adapter.js +129 -0
- package/out/us/adapters/fcc-bdc/adapter.js.map +1 -0
- package/out/us/adapters/state/hi-schools/adapter.d.ts +47 -0
- package/out/us/adapters/state/hi-schools/adapter.d.ts.map +1 -0
- package/out/us/adapters/state/hi-schools/adapter.js +146 -0
- package/out/us/adapters/state/hi-schools/adapter.js.map +1 -0
- package/out/us/adapters/state/hi-schools/workbook.d.ts +34 -0
- package/out/us/adapters/state/hi-schools/workbook.d.ts.map +1 -0
- package/out/us/adapters/state/hi-schools/workbook.js +22 -0
- package/out/us/adapters/state/hi-schools/workbook.js.map +1 -0
- package/out/us/adapters/state/ia-contractors/adapter.d.ts +41 -0
- package/out/us/adapters/state/ia-contractors/adapter.d.ts.map +1 -0
- package/out/us/adapters/state/ia-contractors/adapter.js +117 -0
- package/out/us/adapters/state/ia-contractors/adapter.js.map +1 -0
- package/out/us/adapters/state/ny-notaries/adapter.d.ts +33 -0
- package/out/us/adapters/state/ny-notaries/adapter.d.ts.map +1 -0
- package/out/us/adapters/state/ny-notaries/adapter.js +114 -0
- package/out/us/adapters/state/ny-notaries/adapter.js.map +1 -0
- package/out/us/adapters/state/tx-notaries/adapter.d.ts +34 -0
- package/out/us/adapters/state/tx-notaries/adapter.d.ts.map +1 -0
- package/out/us/adapters/state/tx-notaries/adapter.js +125 -0
- package/out/us/adapters/state/tx-notaries/adapter.js.map +1 -0
- package/out/us/adapters/tiger/adapter.d.ts +31 -0
- package/out/us/adapters/tiger/adapter.d.ts.map +1 -0
- package/out/us/adapters/tiger/adapter.js +173 -0
- package/out/us/adapters/tiger/adapter.js.map +1 -0
- package/out/us/adapters/tiger/street-decompose.d.ts +23 -0
- package/out/us/adapters/tiger/street-decompose.d.ts.map +1 -0
- package/out/us/adapters/tiger/street-decompose.js +58 -0
- package/out/us/adapters/tiger/street-decompose.js.map +1 -0
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts +62 -0
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.js +133 -0
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.js.map +1 -0
- package/out/us/adapters/usgov/imls-pls/adapter.d.ts +37 -0
- package/out/us/adapters/usgov/imls-pls/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/imls-pls/adapter.js +113 -0
- package/out/us/adapters/usgov/imls-pls/adapter.js.map +1 -0
- package/out/us/adapters/usgov/irs-bmf/adapter.d.ts +38 -0
- package/out/us/adapters/usgov/irs-bmf/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/irs-bmf/adapter.js +126 -0
- package/out/us/adapters/usgov/irs-bmf/adapter.js.map +1 -0
- package/out/us/adapters/usgov/nad/adapter.d.ts +28 -0
- package/out/us/adapters/usgov/nad/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/nad/adapter.js +185 -0
- package/out/us/adapters/usgov/nad/adapter.js.map +1 -0
- package/out/us/adapters/usgov/nppes/adapter.d.ts +29 -0
- package/out/us/adapters/usgov/nppes/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/nppes/adapter.js +140 -0
- package/out/us/adapters/usgov/nppes/adapter.js.map +1 -0
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts +47 -0
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts.map +1 -0
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js +153 -0
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js.map +1 -0
- package/out/us/fips-state.d.ts +50 -0
- package/out/us/fips-state.d.ts.map +1 -0
- package/out/us/fips-state.js +109 -0
- package/out/us/fips-state.js.map +1 -0
- package/out/us/tools/fetch/hrsa.d.ts +18 -0
- package/out/us/tools/fetch/hrsa.d.ts.map +1 -0
- package/out/us/tools/fetch/hrsa.js +45 -0
- package/out/us/tools/fetch/hrsa.js.map +1 -0
- package/out/us/tools/fetch/imls-pls.d.ts +14 -0
- package/out/us/tools/fetch/imls-pls.d.ts.map +1 -0
- package/out/us/tools/fetch/imls-pls.js +91 -0
- package/out/us/tools/fetch/imls-pls.js.map +1 -0
- package/out/us/tools/fetch/nad.d.ts +82 -0
- package/out/us/tools/fetch/nad.d.ts.map +1 -0
- package/out/us/tools/fetch/nad.js +239 -0
- package/out/us/tools/fetch/nad.js.map +1 -0
- package/out/us/tools/fetch/nppes.d.ts +16 -0
- package/out/us/tools/fetch/nppes.d.ts.map +1 -0
- package/out/us/tools/fetch/nppes.js +114 -0
- package/out/us/tools/fetch/nppes.js.map +1 -0
- package/out/us/tools/fetch/state/hi-schools.d.ts +29 -0
- package/out/us/tools/fetch/state/hi-schools.d.ts.map +1 -0
- package/out/us/tools/fetch/state/hi-schools.js +114 -0
- package/out/us/tools/fetch/state/hi-schools.js.map +1 -0
- package/out/us/tools/fetch/state/sources.d.ts +27 -0
- package/out/us/tools/fetch/state/sources.d.ts.map +1 -0
- package/out/us/tools/fetch/state/sources.js +110 -0
- package/out/us/tools/fetch/state/sources.js.map +1 -0
- package/out/us/tools/fetch/tiger-full.d.ts +9 -0
- package/out/us/tools/fetch/tiger-full.d.ts.map +1 -0
- package/out/us/tools/fetch/tiger-full.js +178 -0
- package/out/us/tools/fetch/tiger-full.js.map +1 -0
- package/out/utils/align.d.ts +25 -20
- package/out/utils/align.d.ts.map +1 -1
- package/out/utils/align.js +27 -42
- package/out/utils/align.js.map +1 -1
- package/out/utils/cooccurrence-stats.d.ts +58 -0
- package/out/utils/cooccurrence-stats.d.ts.map +1 -0
- package/out/utils/cooccurrence-stats.js +62 -0
- package/out/utils/cooccurrence-stats.js.map +1 -0
- package/out/utils/golden.d.ts +23 -29
- package/out/utils/golden.d.ts.map +1 -1
- package/out/utils/golden.js +33 -45
- package/out/utils/golden.js.map +1 -1
- package/out/utils/license.d.ts +158 -21
- package/out/utils/license.d.ts.map +1 -1
- package/out/utils/license.js +156 -26
- package/out/utils/license.js.map +1 -1
- package/out/utils/split.d.ts +66 -70
- package/out/utils/split.d.ts.map +1 -1
- package/out/utils/split.js +158 -69
- package/out/utils/split.js.map +1 -1
- package/out/utils/tokenize.d.ts +16 -28
- package/out/utils/tokenize.d.ts.map +1 -1
- package/out/utils/tokenize.js +18 -31
- package/out/utils/tokenize.js.map +1 -1
- package/out/utils/wof-json.d.ts +88 -62
- package/out/utils/wof-json.d.ts.map +1 -1
- package/out/utils/wof-json.js +81 -65
- package/out/utils/wof-json.js.map +1 -1
- package/out/utils.d.ts +13 -0
- package/out/utils.d.ts.map +1 -0
- package/out/utils.js +13 -0
- package/out/utils.js.map +1 -0
- package/out/ve/recipes/reviewed-postcode-tail.d.ts +65 -0
- package/out/ve/recipes/reviewed-postcode-tail.d.ts.map +1 -0
- package/out/ve/recipes/reviewed-postcode-tail.js +146 -0
- package/out/ve/recipes/reviewed-postcode-tail.js.map +1 -0
- package/package.json +46 -330
- package/lib/adapters/ban/adapter.ts +0 -190
- package/lib/adapters/ban/street-decompose.ts +0 -66
- package/lib/adapters/fcc-bdc/adapter.ts +0 -174
- package/lib/adapters/geonames-postal/adapter.ts +0 -122
- package/lib/adapters/gnaf/adapter.ts +0 -149
- package/lib/adapters/gnaf/assemble.ts +0 -225
- package/lib/adapters/index.ts +0 -153
- package/lib/adapters/state-hi-schools/adapter.ts +0 -170
- package/lib/adapters/state-hi-schools/workbook.ts +0 -35
- package/lib/adapters/state-ia-contractors/adapter.ts +0 -144
- package/lib/adapters/state-ny-notaries/adapter.ts +0 -141
- package/lib/adapters/state-tx-notaries/adapter.ts +0 -157
- package/lib/adapters/synth-po-box/adapter.ts +0 -204
- package/lib/adapters/tiger/adapter.ts +0 -252
- package/lib/adapters/tiger/street-decompose.ts +0 -83
- package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +0 -167
- package/lib/adapters/usgov-imls-pls/adapter.ts +0 -143
- package/lib/adapters/usgov-irs-bmf/adapter.ts +0 -151
- package/lib/adapters/usgov-nad/adapter.ts +0 -334
- package/lib/adapters/usgov-nppes/adapter.ts +0 -151
- package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -193
- package/lib/adapters/utils/index.ts +0 -307
- package/lib/adapters/wof-admin-jp/adapter.ts +0 -214
- package/lib/adapters/wof-admin-json/adapter.ts +0 -231
- package/lib/adapters/wof-json-rows.ts +0 -129
- package/lib/adapters/wof-postalcode-json/adapter.ts +0 -176
- package/lib/codex/us-fips-state.ts +0 -113
- package/lib/recipes/bare-country.ts +0 -95
- package/lib/recipes/cn-organizational-units.ts +0 -199
- package/lib/recipes/cz-pcfirst-preposition.ts +0 -112
- package/lib/recipes/fr-admin-split.ts +0 -243
- package/lib/recipes/fr-bare-street.ts +0 -171
- package/lib/recipes/fr-fragment.ts +0 -334
- package/lib/recipes/fr-lieudit.ts +0 -301
- package/lib/recipes/fr-order.ts +0 -246
- package/lib/recipes/german.ts +0 -360
- package/lib/recipes/index.ts +0 -97
- package/lib/recipes/locale.ts +0 -600
- package/lib/recipes/nl-postcode.ts +0 -117
- package/lib/recipes/no-fragment.ts +0 -213
- package/lib/recipes/no-street-led.ts +0 -135
- package/lib/recipes/no-street.ts +0 -91
- package/lib/recipes/po-box-cedex.ts +0 -976
- package/lib/recipes/po-box.ts +0 -124
- package/lib/recipes/reviewed-postcode-tail.ts +0 -190
- package/lib/recipes/si-bare-village.ts +0 -99
- package/lib/recipes/street-affix.ts +0 -805
- package/lib/recipes/street-bare.ts +0 -102
- package/lib/recipes/sub-venue-sources.ts +0 -878
- package/lib/recipes/sub-venue.ts +0 -998
- package/lib/synthesizers/german.ts +0 -260
- package/lib/test-kit/index.ts +0 -100
- package/lib/tools/align-slice.ts +0 -68
- package/lib/tools/fetch/acra-sg.ts +0 -174
- package/lib/tools/fetch/ban.ts +0 -289
- package/lib/tools/fetch/gcis-tw.ts +0 -175
- package/lib/tools/fetch/geonames-dump.ts +0 -257
- package/lib/tools/fetch/geonames-postal.ts +0 -180
- package/lib/tools/fetch/houjin-jp.ts +0 -135
- package/lib/tools/fetch/hrsa.ts +0 -59
- package/lib/tools/fetch/imls-pls.ts +0 -149
- package/lib/tools/fetch/index.ts +0 -174
- package/lib/tools/fetch/juso-kr.ts +0 -165
- package/lib/tools/fetch/localdata-kr.ts +0 -194
- package/lib/tools/fetch/nad.ts +0 -341
- package/lib/tools/fetch/nppes.ts +0 -165
- package/lib/tools/fetch/state-hi-schools.ts +0 -161
- package/lib/tools/fetch/state-sources.ts +0 -146
- package/lib/tools/fetch/tiger-full.ts +0 -308
- package/lib/tools/gb-title-case.ts +0 -69
- package/lib/tools/golden-expand.ts +0 -574
- package/lib/tools/golden-promote.ts +0 -337
- package/lib/tools/golden-relabel-street.ts +0 -686
- package/lib/tools/index.ts +0 -28
- package/lib/tools/lint-slice-vocab.ts +0 -388
- package/lib/tools/lint-slice.ts +0 -496
- package/lib/tools/overlay-manifest.ts +0 -148
- package/lib/tools/slice-kryptonite.ts +0 -137
- package/lib/tools/slice-translit.ts +0 -218
- package/lib/tools/sub-venue/harvest.ts +0 -234
- package/lib/tools/sub-venue/head-nouns.ts +0 -245
- package/lib/tools/sub-venue/surfaces.ts +0 -95
- package/lib/tools/sub-venue/table.ts +0 -281
- package/lib/tools/sub-venue/wikidata.ts +0 -85
- package/lib/tools/sub-venue-lexicon.ts +0 -429
- package/lib/tools/sub-venue-promotions.ts +0 -330
- package/lib/utils/index.ts +0 -14
- package/lib/utils/parquet.ts +0 -582
- package/lib/utils/slice-stats.ts +0 -95
- package/out/adapters/ban/adapter.d.ts +0 -44
- package/out/adapters/ban/adapter.d.ts.map +0 -1
- package/out/adapters/ban/adapter.js +0 -149
- package/out/adapters/ban/adapter.js.map +0 -1
- package/out/adapters/ban/street-decompose.d.ts +0 -28
- package/out/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/adapters/ban/street-decompose.js +0 -51
- package/out/adapters/ban/street-decompose.js.map +0 -1
- package/out/adapters/fcc-bdc/adapter.d.ts +0 -68
- package/out/adapters/fcc-bdc/adapter.d.ts.map +0 -1
- package/out/adapters/fcc-bdc/adapter.js +0 -144
- package/out/adapters/fcc-bdc/adapter.js.map +0 -1
- package/out/adapters/geonames-postal/adapter.d.ts +0 -54
- package/out/adapters/geonames-postal/adapter.d.ts.map +0 -1
- package/out/adapters/geonames-postal/adapter.js +0 -107
- package/out/adapters/geonames-postal/adapter.js.map +0 -1
- package/out/adapters/gnaf/adapter.d.ts +0 -49
- package/out/adapters/gnaf/adapter.d.ts.map +0 -1
- package/out/adapters/gnaf/adapter.js +0 -124
- package/out/adapters/gnaf/adapter.js.map +0 -1
- package/out/adapters/gnaf/assemble.d.ts +0 -65
- package/out/adapters/gnaf/assemble.d.ts.map +0 -1
- package/out/adapters/gnaf/assemble.js +0 -154
- package/out/adapters/gnaf/assemble.js.map +0 -1
- package/out/adapters/index.d.ts +0 -51
- package/out/adapters/index.d.ts.map +0 -1
- package/out/adapters/index.js +0 -95
- package/out/adapters/index.js.map +0 -1
- package/out/adapters/state-hi-schools/adapter.d.ts +0 -46
- package/out/adapters/state-hi-schools/adapter.d.ts.map +0 -1
- package/out/adapters/state-hi-schools/adapter.js +0 -145
- package/out/adapters/state-hi-schools/adapter.js.map +0 -1
- package/out/adapters/state-hi-schools/workbook.d.ts +0 -29
- package/out/adapters/state-hi-schools/workbook.d.ts.map +0 -1
- package/out/adapters/state-hi-schools/workbook.js +0 -20
- package/out/adapters/state-hi-schools/workbook.js.map +0 -1
- package/out/adapters/state-ia-contractors/adapter.d.ts +0 -34
- package/out/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
- package/out/adapters/state-ia-contractors/adapter.js +0 -111
- package/out/adapters/state-ia-contractors/adapter.js.map +0 -1
- package/out/adapters/state-ny-notaries/adapter.d.ts +0 -32
- package/out/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
- package/out/adapters/state-ny-notaries/adapter.js +0 -119
- package/out/adapters/state-ny-notaries/adapter.js.map +0 -1
- package/out/adapters/state-tx-notaries/adapter.d.ts +0 -33
- package/out/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
- package/out/adapters/state-tx-notaries/adapter.js +0 -125
- package/out/adapters/state-tx-notaries/adapter.js.map +0 -1
- package/out/adapters/synth-po-box/adapter.d.ts +0 -67
- package/out/adapters/synth-po-box/adapter.d.ts.map +0 -1
- package/out/adapters/synth-po-box/adapter.js +0 -140
- package/out/adapters/synth-po-box/adapter.js.map +0 -1
- package/out/adapters/tiger/adapter.d.ts +0 -55
- package/out/adapters/tiger/adapter.d.ts.map +0 -1
- package/out/adapters/tiger/adapter.js +0 -201
- package/out/adapters/tiger/adapter.js.map +0 -1
- package/out/adapters/tiger/street-decompose.d.ts +0 -30
- package/out/adapters/tiger/street-decompose.d.ts.map +0 -1
- package/out/adapters/tiger/street-decompose.js +0 -68
- package/out/adapters/tiger/street-decompose.js.map +0 -1
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -56
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-hrsa-fqhc/adapter.js +0 -132
- package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
- package/out/adapters/usgov-imls-pls/adapter.d.ts +0 -36
- package/out/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-imls-pls/adapter.js +0 -114
- package/out/adapters/usgov-imls-pls/adapter.js.map +0 -1
- package/out/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
- package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-irs-bmf/adapter.js +0 -120
- package/out/adapters/usgov-irs-bmf/adapter.js.map +0 -1
- package/out/adapters/usgov-nad/adapter.d.ts +0 -48
- package/out/adapters/usgov-nad/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-nad/adapter.js +0 -249
- package/out/adapters/usgov-nad/adapter.js.map +0 -1
- package/out/adapters/usgov-nppes/adapter.d.ts +0 -39
- package/out/adapters/usgov-nppes/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-nppes/adapter.js +0 -118
- package/out/adapters/usgov-nppes/adapter.js.map +0 -1
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts +0 -46
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -154
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
- package/out/adapters/utils/index.d.ts +0 -191
- package/out/adapters/utils/index.d.ts.map +0 -1
- package/out/adapters/utils/index.js +0 -206
- package/out/adapters/utils/index.js.map +0 -1
- package/out/adapters/wof-admin-jp/adapter.d.ts +0 -65
- package/out/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
- package/out/adapters/wof-admin-jp/adapter.js +0 -161
- package/out/adapters/wof-admin-jp/adapter.js.map +0 -1
- package/out/adapters/wof-admin-json/adapter.d.ts +0 -79
- package/out/adapters/wof-admin-json/adapter.d.ts.map +0 -1
- package/out/adapters/wof-admin-json/adapter.js +0 -197
- package/out/adapters/wof-admin-json/adapter.js.map +0 -1
- package/out/adapters/wof-json-rows.d.ts +0 -62
- package/out/adapters/wof-json-rows.d.ts.map +0 -1
- package/out/adapters/wof-json-rows.js +0 -83
- package/out/adapters/wof-json-rows.js.map +0 -1
- package/out/adapters/wof-postalcode-json/adapter.d.ts +0 -65
- package/out/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
- package/out/adapters/wof-postalcode-json/adapter.js +0 -151
- package/out/adapters/wof-postalcode-json/adapter.js.map +0 -1
- package/out/codex/us-fips-state.d.ts +0 -41
- package/out/codex/us-fips-state.d.ts.map +0 -1
- package/out/codex/us-fips-state.js +0 -100
- package/out/codex/us-fips-state.js.map +0 -1
- package/out/recipes/bare-country.d.ts +0 -25
- package/out/recipes/bare-country.d.ts.map +0 -1
- package/out/recipes/bare-country.js +0 -88
- package/out/recipes/bare-country.js.map +0 -1
- package/out/recipes/cn-organizational-units.d.ts +0 -36
- package/out/recipes/cn-organizational-units.d.ts.map +0 -1
- package/out/recipes/cn-organizational-units.js +0 -159
- package/out/recipes/cn-organizational-units.js.map +0 -1
- package/out/recipes/cz-pcfirst-preposition.d.ts +0 -22
- package/out/recipes/cz-pcfirst-preposition.d.ts.map +0 -1
- package/out/recipes/cz-pcfirst-preposition.js +0 -101
- package/out/recipes/cz-pcfirst-preposition.js.map +0 -1
- package/out/recipes/fr-admin-split.d.ts +0 -38
- package/out/recipes/fr-admin-split.d.ts.map +0 -1
- package/out/recipes/fr-admin-split.js +0 -192
- package/out/recipes/fr-admin-split.js.map +0 -1
- package/out/recipes/fr-bare-street.d.ts +0 -28
- package/out/recipes/fr-bare-street.d.ts.map +0 -1
- package/out/recipes/fr-bare-street.js +0 -144
- package/out/recipes/fr-bare-street.js.map +0 -1
- package/out/recipes/fr-fragment.d.ts +0 -77
- package/out/recipes/fr-fragment.d.ts.map +0 -1
- package/out/recipes/fr-fragment.js +0 -277
- package/out/recipes/fr-fragment.js.map +0 -1
- package/out/recipes/fr-lieudit.d.ts +0 -32
- package/out/recipes/fr-lieudit.d.ts.map +0 -1
- package/out/recipes/fr-lieudit.js +0 -227
- package/out/recipes/fr-lieudit.js.map +0 -1
- package/out/recipes/fr-order.d.ts +0 -38
- package/out/recipes/fr-order.d.ts.map +0 -1
- package/out/recipes/fr-order.js +0 -198
- package/out/recipes/fr-order.js.map +0 -1
- package/out/recipes/german.d.ts +0 -44
- package/out/recipes/german.d.ts.map +0 -1
- package/out/recipes/german.js +0 -289
- package/out/recipes/german.js.map +0 -1
- package/out/recipes/index.d.ts +0 -24
- package/out/recipes/index.d.ts.map +0 -1
- package/out/recipes/index.js +0 -91
- package/out/recipes/index.js.map +0 -1
- package/out/recipes/locale.d.ts +0 -136
- package/out/recipes/locale.d.ts.map +0 -1
- package/out/recipes/locale.js +0 -460
- package/out/recipes/locale.js.map +0 -1
- package/out/recipes/nl-postcode.d.ts +0 -26
- package/out/recipes/nl-postcode.d.ts.map +0 -1
- package/out/recipes/nl-postcode.js +0 -103
- package/out/recipes/nl-postcode.js.map +0 -1
- package/out/recipes/no-fragment.d.ts +0 -43
- package/out/recipes/no-fragment.d.ts.map +0 -1
- package/out/recipes/no-fragment.js +0 -183
- package/out/recipes/no-fragment.js.map +0 -1
- package/out/recipes/no-street-led.d.ts +0 -24
- package/out/recipes/no-street-led.d.ts.map +0 -1
- package/out/recipes/no-street-led.js +0 -114
- package/out/recipes/no-street-led.js.map +0 -1
- package/out/recipes/no-street.d.ts +0 -18
- package/out/recipes/no-street.d.ts.map +0 -1
- package/out/recipes/no-street.js +0 -72
- package/out/recipes/no-street.js.map +0 -1
- package/out/recipes/po-box-cedex.d.ts +0 -38
- package/out/recipes/po-box-cedex.d.ts.map +0 -1
- package/out/recipes/po-box-cedex.js +0 -768
- package/out/recipes/po-box-cedex.js.map +0 -1
- package/out/recipes/po-box.d.ts +0 -17
- package/out/recipes/po-box.d.ts.map +0 -1
- package/out/recipes/po-box.js +0 -101
- package/out/recipes/po-box.js.map +0 -1
- package/out/recipes/reviewed-postcode-tail.d.ts +0 -47
- package/out/recipes/reviewed-postcode-tail.d.ts.map +0 -1
- package/out/recipes/reviewed-postcode-tail.js +0 -125
- package/out/recipes/reviewed-postcode-tail.js.map +0 -1
- package/out/recipes/si-bare-village.d.ts +0 -32
- package/out/recipes/si-bare-village.d.ts.map +0 -1
- package/out/recipes/si-bare-village.js +0 -89
- package/out/recipes/si-bare-village.js.map +0 -1
- package/out/recipes/street-affix.d.ts +0 -89
- package/out/recipes/street-affix.d.ts.map +0 -1
- package/out/recipes/street-affix.js +0 -563
- package/out/recipes/street-affix.js.map +0 -1
- package/out/recipes/street-bare.d.ts +0 -25
- package/out/recipes/street-bare.d.ts.map +0 -1
- package/out/recipes/street-bare.js +0 -87
- package/out/recipes/street-bare.js.map +0 -1
- package/out/recipes/sub-venue-sources.d.ts +0 -229
- package/out/recipes/sub-venue-sources.d.ts.map +0 -1
- package/out/recipes/sub-venue-sources.js +0 -654
- package/out/recipes/sub-venue-sources.js.map +0 -1
- package/out/recipes/sub-venue.d.ts +0 -269
- package/out/recipes/sub-venue.d.ts.map +0 -1
- package/out/recipes/sub-venue.js +0 -726
- package/out/recipes/sub-venue.js.map +0 -1
- package/out/synthesizers/german.d.ts +0 -115
- package/out/synthesizers/german.d.ts.map +0 -1
- package/out/synthesizers/german.js +0 -149
- package/out/synthesizers/german.js.map +0 -1
- package/out/test-kit/index.d.ts +0 -48
- package/out/test-kit/index.d.ts.map +0 -1
- package/out/test-kit/index.js +0 -78
- package/out/test-kit/index.js.map +0 -1
- package/out/tools/align-slice.d.ts +0 -7
- package/out/tools/align-slice.d.ts.map +0 -1
- package/out/tools/align-slice.js +0 -55
- package/out/tools/align-slice.js.map +0 -1
- package/out/tools/fetch/acra-sg.d.ts +0 -23
- package/out/tools/fetch/acra-sg.d.ts.map +0 -1
- package/out/tools/fetch/acra-sg.js +0 -126
- package/out/tools/fetch/acra-sg.js.map +0 -1
- package/out/tools/fetch/ban.d.ts +0 -31
- package/out/tools/fetch/ban.d.ts.map +0 -1
- package/out/tools/fetch/ban.js +0 -239
- package/out/tools/fetch/ban.js.map +0 -1
- package/out/tools/fetch/gcis-tw.d.ts +0 -23
- package/out/tools/fetch/gcis-tw.d.ts.map +0 -1
- package/out/tools/fetch/gcis-tw.js +0 -135
- package/out/tools/fetch/gcis-tw.js.map +0 -1
- package/out/tools/fetch/geonames-dump.d.ts +0 -91
- package/out/tools/fetch/geonames-dump.d.ts.map +0 -1
- package/out/tools/fetch/geonames-dump.js +0 -171
- package/out/tools/fetch/geonames-dump.js.map +0 -1
- package/out/tools/fetch/geonames-postal.d.ts +0 -76
- package/out/tools/fetch/geonames-postal.d.ts.map +0 -1
- package/out/tools/fetch/geonames-postal.js +0 -126
- package/out/tools/fetch/geonames-postal.js.map +0 -1
- package/out/tools/fetch/houjin-jp.d.ts +0 -24
- package/out/tools/fetch/houjin-jp.d.ts.map +0 -1
- package/out/tools/fetch/houjin-jp.js +0 -102
- package/out/tools/fetch/houjin-jp.js.map +0 -1
- package/out/tools/fetch/hrsa.d.ts +0 -18
- package/out/tools/fetch/hrsa.d.ts.map +0 -1
- package/out/tools/fetch/hrsa.js +0 -46
- package/out/tools/fetch/hrsa.js.map +0 -1
- package/out/tools/fetch/imls-pls.d.ts +0 -25
- package/out/tools/fetch/imls-pls.d.ts.map +0 -1
- package/out/tools/fetch/imls-pls.js +0 -108
- package/out/tools/fetch/imls-pls.js.map +0 -1
- package/out/tools/fetch/index.d.ts +0 -171
- package/out/tools/fetch/index.d.ts.map +0 -1
- package/out/tools/fetch/index.js +0 -170
- package/out/tools/fetch/index.js.map +0 -1
- package/out/tools/fetch/juso-kr.d.ts +0 -30
- package/out/tools/fetch/juso-kr.d.ts.map +0 -1
- package/out/tools/fetch/juso-kr.js +0 -120
- package/out/tools/fetch/juso-kr.js.map +0 -1
- package/out/tools/fetch/localdata-kr.d.ts +0 -30
- package/out/tools/fetch/localdata-kr.d.ts.map +0 -1
- package/out/tools/fetch/localdata-kr.js +0 -139
- package/out/tools/fetch/localdata-kr.js.map +0 -1
- package/out/tools/fetch/nad.d.ts +0 -70
- package/out/tools/fetch/nad.d.ts.map +0 -1
- package/out/tools/fetch/nad.js +0 -234
- package/out/tools/fetch/nad.js.map +0 -1
- package/out/tools/fetch/nppes.d.ts +0 -26
- package/out/tools/fetch/nppes.d.ts.map +0 -1
- package/out/tools/fetch/nppes.js +0 -126
- package/out/tools/fetch/nppes.js.map +0 -1
- package/out/tools/fetch/state-hi-schools.d.ts +0 -26
- package/out/tools/fetch/state-hi-schools.d.ts.map +0 -1
- package/out/tools/fetch/state-hi-schools.js +0 -112
- package/out/tools/fetch/state-hi-schools.js.map +0 -1
- package/out/tools/fetch/state-sources.d.ts +0 -26
- package/out/tools/fetch/state-sources.d.ts.map +0 -1
- package/out/tools/fetch/state-sources.js +0 -111
- package/out/tools/fetch/state-sources.js.map +0 -1
- package/out/tools/fetch/tiger-full.d.ts +0 -22
- package/out/tools/fetch/tiger-full.d.ts.map +0 -1
- package/out/tools/fetch/tiger-full.js +0 -217
- package/out/tools/fetch/tiger-full.js.map +0 -1
- package/out/tools/gb-title-case.d.ts +0 -2
- package/out/tools/gb-title-case.d.ts.map +0 -1
- package/out/tools/gb-title-case.js +0 -65
- package/out/tools/gb-title-case.js.map +0 -1
- package/out/tools/golden-expand.d.ts +0 -90
- package/out/tools/golden-expand.d.ts.map +0 -1
- package/out/tools/golden-expand.js +0 -406
- package/out/tools/golden-expand.js.map +0 -1
- package/out/tools/golden-promote.d.ts +0 -72
- package/out/tools/golden-promote.d.ts.map +0 -1
- package/out/tools/golden-promote.js +0 -240
- package/out/tools/golden-promote.js.map +0 -1
- package/out/tools/golden-relabel-street.d.ts +0 -196
- package/out/tools/golden-relabel-street.d.ts.map +0 -1
- package/out/tools/golden-relabel-street.js +0 -439
- package/out/tools/golden-relabel-street.js.map +0 -1
- package/out/tools/index.d.ts +0 -28
- package/out/tools/index.d.ts.map +0 -1
- package/out/tools/index.js +0 -28
- package/out/tools/index.js.map +0 -1
- package/out/tools/lint-slice-vocab.d.ts +0 -90
- package/out/tools/lint-slice-vocab.d.ts.map +0 -1
- package/out/tools/lint-slice-vocab.js +0 -267
- package/out/tools/lint-slice-vocab.js.map +0 -1
- package/out/tools/lint-slice.d.ts +0 -93
- package/out/tools/lint-slice.d.ts.map +0 -1
- package/out/tools/lint-slice.js +0 -322
- package/out/tools/lint-slice.js.map +0 -1
- package/out/tools/overlay-manifest.d.ts +0 -39
- package/out/tools/overlay-manifest.d.ts.map +0 -1
- package/out/tools/overlay-manifest.js +0 -90
- package/out/tools/overlay-manifest.js.map +0 -1
- package/out/tools/slice-kryptonite.d.ts +0 -32
- package/out/tools/slice-kryptonite.d.ts.map +0 -1
- package/out/tools/slice-kryptonite.js +0 -99
- package/out/tools/slice-kryptonite.js.map +0 -1
- package/out/tools/slice-translit.d.ts +0 -51
- package/out/tools/slice-translit.d.ts.map +0 -1
- package/out/tools/slice-translit.js +0 -166
- package/out/tools/slice-translit.js.map +0 -1
- package/out/tools/sub-venue/harvest.d.ts +0 -100
- package/out/tools/sub-venue/harvest.d.ts.map +0 -1
- package/out/tools/sub-venue/harvest.js +0 -168
- package/out/tools/sub-venue/harvest.js.map +0 -1
- package/out/tools/sub-venue/head-nouns.d.ts +0 -50
- package/out/tools/sub-venue/head-nouns.d.ts.map +0 -1
- package/out/tools/sub-venue/head-nouns.js +0 -213
- package/out/tools/sub-venue/head-nouns.js.map +0 -1
- package/out/tools/sub-venue/surfaces.d.ts +0 -45
- package/out/tools/sub-venue/surfaces.d.ts.map +0 -1
- package/out/tools/sub-venue/surfaces.js +0 -77
- package/out/tools/sub-venue/surfaces.js.map +0 -1
- package/out/tools/sub-venue/table.d.ts +0 -229
- package/out/tools/sub-venue/table.d.ts.map +0 -1
- package/out/tools/sub-venue/table.js +0 -108
- package/out/tools/sub-venue/table.js.map +0 -1
- package/out/tools/sub-venue/wikidata.d.ts +0 -26
- package/out/tools/sub-venue/wikidata.d.ts.map +0 -1
- package/out/tools/sub-venue/wikidata.js +0 -62
- package/out/tools/sub-venue/wikidata.js.map +0 -1
- package/out/tools/sub-venue-lexicon.d.ts +0 -156
- package/out/tools/sub-venue-lexicon.d.ts.map +0 -1
- package/out/tools/sub-venue-lexicon.js +0 -283
- package/out/tools/sub-venue-lexicon.js.map +0 -1
- package/out/tools/sub-venue-promotions.d.ts +0 -94
- package/out/tools/sub-venue-promotions.d.ts.map +0 -1
- package/out/tools/sub-venue-promotions.js +0 -266
- package/out/tools/sub-venue-promotions.js.map +0 -1
- package/out/utils/index.d.ts +0 -14
- package/out/utils/index.d.ts.map +0 -1
- package/out/utils/index.js +0 -14
- package/out/utils/index.js.map +0 -1
- package/out/utils/parquet.d.ts +0 -178
- package/out/utils/parquet.d.ts.map +0 -1
- package/out/utils/parquet.js +0 -371
- package/out/utils/parquet.js.map +0 -1
- package/out/utils/slice-stats.d.ts +0 -52
- package/out/utils/slice-stats.d.ts.map +0 -1
- package/out/utils/slice-stats.js +0 -58
- package/out/utils/slice-stats.js.map +0 -1
|
@@ -0,0 +1,124 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
* @file Convert a recipe output written before `recipe`/`register`/`surface` to the current row schema.
|
|
6
|
+
*
|
|
7
|
+
* `recipe` and `base_source_id` are renames of `synth_method` and `synth_base_id`, so they assert no new claim.
|
|
8
|
+
* `register` is `mailwoman-derived-tuples` for every row, because naming a publisher would record inference as fact.
|
|
9
|
+
*/
|
|
10
|
+
import { openWriteStream } from "@mailwoman/core/fs/streams";
|
|
11
|
+
import { parseJSONStrict, stringifyJSON } from "@mailwoman/core/json";
|
|
12
|
+
import { once } from "@mailwoman/core/utils/events";
|
|
13
|
+
import { TextSpliterator } from "spliterator";
|
|
14
|
+
import { retiredSourceName } from "#recipes/sources";
|
|
15
|
+
import { SourceRegister } from "#registers";
|
|
16
|
+
import { SurfaceOrigin } from "#types";
|
|
17
|
+
/**
|
|
18
|
+
* How each source id's recipe produced its surface.
|
|
19
|
+
*
|
|
20
|
+
* A source absent from this table refuses rather than taking a default.
|
|
21
|
+
*/
|
|
22
|
+
export const RECIPE_SURFACES = {
|
|
23
|
+
// Assembled from template tables.
|
|
24
|
+
// No register asserts the address exists.
|
|
25
|
+
"synth-intersection": SurfaceOrigin.Invented,
|
|
26
|
+
"synth-po-box-cedex": SurfaceOrigin.Invented,
|
|
27
|
+
"synth-house-venue": SurfaceOrigin.Invented,
|
|
28
|
+
"deepseek-kryptonite": SurfaceOrigin.Invented,
|
|
29
|
+
// A real record's fields, written in an order the recipe chose.
|
|
30
|
+
"synth-affix": SurfaceOrigin.Composed,
|
|
31
|
+
"synth-fr-order": SurfaceOrigin.Composed,
|
|
32
|
+
"synth-fr-bare-street": SurfaceOrigin.Composed,
|
|
33
|
+
"synth-fr-lieudit": SurfaceOrigin.Composed,
|
|
34
|
+
"synth-suffix-boundary": SurfaceOrigin.Composed,
|
|
35
|
+
"synth-unit": SurfaceOrigin.Composed,
|
|
36
|
+
"synth-unit-v30": SurfaceOrigin.Composed,
|
|
37
|
+
"synth-trailing-region": SurfaceOrigin.Composed,
|
|
38
|
+
"synth-trailing-region-us": SurfaceOrigin.Composed,
|
|
39
|
+
"synth-trailing-region-structured": SurfaceOrigin.Composed,
|
|
40
|
+
"synth-trailing-region-ca-bare": SurfaceOrigin.Composed,
|
|
41
|
+
"synth-trailing-region-es-v28": SurfaceOrigin.Composed,
|
|
42
|
+
"synth-cz-pcfirst-preposition": SurfaceOrigin.Composed,
|
|
43
|
+
"synth-cz-pcfirst-preposition-v21": SurfaceOrigin.Composed,
|
|
44
|
+
"synth-fr-bare-street-v22": SurfaceOrigin.Composed,
|
|
45
|
+
"synth-si-bare-village": SurfaceOrigin.Composed,
|
|
46
|
+
"synth-no-street-led": SurfaceOrigin.Composed,
|
|
47
|
+
"synth-no-fragment": SurfaceOrigin.Composed,
|
|
48
|
+
"synth-fr-fragment": SurfaceOrigin.Composed,
|
|
49
|
+
"synth-fragment": SurfaceOrigin.Composed,
|
|
50
|
+
"synth-fr-admin-split": SurfaceOrigin.Composed,
|
|
51
|
+
"synth-nl-postcode": SurfaceOrigin.Composed,
|
|
52
|
+
"synth-sub-venue": SurfaceOrigin.Composed,
|
|
53
|
+
"synth-german": SurfaceOrigin.Composed,
|
|
54
|
+
"synth-nz": SurfaceOrigin.Composed,
|
|
55
|
+
"synth-es": SurfaceOrigin.Composed,
|
|
56
|
+
"synth-gb": SurfaceOrigin.Composed,
|
|
57
|
+
"synth-sg-register": SurfaceOrigin.Composed,
|
|
58
|
+
"synth-pk-register": SurfaceOrigin.Composed,
|
|
59
|
+
"synth-bd-register": SurfaceOrigin.Composed,
|
|
60
|
+
"synth-reviewed-postcode-tail": SurfaceOrigin.Composed,
|
|
61
|
+
// The publisher's own string, preserved by an adapter rather than a recipe.
|
|
62
|
+
overture: SurfaceOrigin.Attested,
|
|
63
|
+
"overture-latam": SurfaceOrigin.Attested,
|
|
64
|
+
gnaf: SurfaceOrigin.Attested,
|
|
65
|
+
osm: SurfaceOrigin.Attested,
|
|
66
|
+
// Written from this repository's own tables.
|
|
67
|
+
// They publish the string verbatim.
|
|
68
|
+
"synth-bare-country": SurfaceOrigin.Attested,
|
|
69
|
+
"synth-bare-postcode": SurfaceOrigin.Attested,
|
|
70
|
+
// Drawn rather than read: the box number, the anchor and the venue are the recipe's.
|
|
71
|
+
"synth-po-box-military": SurfaceOrigin.Invented,
|
|
72
|
+
"synth-anchor-absorption": SurfaceOrigin.Invented,
|
|
73
|
+
};
|
|
74
|
+
/**
|
|
75
|
+
* The surface for one source id, refusing a source the table does not name.
|
|
76
|
+
*/
|
|
77
|
+
export function surfaceForSource(source) {
|
|
78
|
+
// The table keys on the retired spelling.
|
|
79
|
+
// A corpus that uses the current spelling needs the retired key for this lookup.
|
|
80
|
+
// Otherwise each row fails as though it had no surface.
|
|
81
|
+
// That failure misstates a renamed source as an unrecorded one.
|
|
82
|
+
const surface = RECIPE_SURFACES[retiredSourceName(source)];
|
|
83
|
+
if (!surface) {
|
|
84
|
+
throw new Error(`No surface recorded for source ${stringifyJSON(source)}. Read the recipe that writes it, ` +
|
|
85
|
+
`add it to RECIPE_SURFACES, and say there whether it renders a real record or assembles one.`);
|
|
86
|
+
}
|
|
87
|
+
return surface;
|
|
88
|
+
}
|
|
89
|
+
/**
|
|
90
|
+
* Rewrite one recipe output onto the current row schema, passing an already-migrated
|
|
91
|
+
* row through untouched so a half-migrated file converges.
|
|
92
|
+
*/
|
|
93
|
+
export async function migrateRecipeOutput(input, output) {
|
|
94
|
+
const summary = { rows: 0, bySource: {}, alreadyMigrated: 0 };
|
|
95
|
+
const sink = openWriteStream(output, { encoding: "utf8" });
|
|
96
|
+
for await (const line of TextSpliterator.fromAsync(input)) {
|
|
97
|
+
const row = parseJSONStrict(line);
|
|
98
|
+
summary.rows++;
|
|
99
|
+
const source = String(row["source"] ?? "");
|
|
100
|
+
summary.bySource[source] = (summary.bySource[source] ?? 0) + 1;
|
|
101
|
+
if (row["surface"]) {
|
|
102
|
+
summary.alreadyMigrated++;
|
|
103
|
+
if (!sink.write(`${line}\n`)) {
|
|
104
|
+
await once(sink, "drain");
|
|
105
|
+
}
|
|
106
|
+
continue;
|
|
107
|
+
}
|
|
108
|
+
const { synth_method: recipe, synth_base_id: baseSourceID, ...rest } = row;
|
|
109
|
+
const migrated = {
|
|
110
|
+
...rest,
|
|
111
|
+
recipe: recipe ?? null,
|
|
112
|
+
base_source_id: baseSourceID ?? null,
|
|
113
|
+
register: SourceRegister.DerivedTuples,
|
|
114
|
+
surface: surfaceForSource(source),
|
|
115
|
+
};
|
|
116
|
+
if (!sink.write(`${stringifyJSON(migrated)}\n`)) {
|
|
117
|
+
await once(sink, "drain");
|
|
118
|
+
}
|
|
119
|
+
}
|
|
120
|
+
sink.end();
|
|
121
|
+
await once(sink, "finish");
|
|
122
|
+
return summary;
|
|
123
|
+
}
|
|
124
|
+
//# sourceMappingURL=recipe-output.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"recipe-output.js","sourceRoot":"","sources":["../../../lib/tools/migrate/recipe-output.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AAEH,OAAO,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAA;AAC5D,OAAO,EAAE,eAAe,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAA;AACrE,OAAO,EAAE,IAAI,EAAE,MAAM,8BAA8B,CAAA;AAEnD,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C,OAAO,EAAE,iBAAiB,EAAE,MAAM,kBAAkB,CAAA;AACpD,OAAO,EAAE,cAAc,EAAE,MAAM,YAAY,CAAA;AAC3C,OAAO,EAAE,aAAa,EAAE,MAAM,QAAQ,CAAA;AAEtC;;;;GAIG;AACH,MAAM,CAAC,MAAM,eAAe,GAAkC;IAC7D,kCAAkC;IAClC,0CAA0C;IAC1C,oBAAoB,EAAE,aAAa,CAAC,QAAQ;IAC5C,oBAAoB,EAAE,aAAa,CAAC,QAAQ;IAC5C,mBAAmB,EAAE,aAAa,CAAC,QAAQ;IAC3C,qBAAqB,EAAE,aAAa,CAAC,QAAQ;IAC7C,gEAAgE;IAChE,aAAa,EAAE,aAAa,CAAC,QAAQ;IACrC,gBAAgB,EAAE,aAAa,CAAC,QAAQ;IACxC,sBAAsB,EAAE,aAAa,CAAC,QAAQ;IAC9C,kBAAkB,EAAE,aAAa,CAAC,QAAQ;IAC1C,uBAAuB,EAAE,aAAa,CAAC,QAAQ;IAC/C,YAAY,EAAE,aAAa,CAAC,QAAQ;IACpC,gBAAgB,EAAE,aAAa,CAAC,QAAQ;IACxC,uBAAuB,EAAE,aAAa,CAAC,QAAQ;IAC/C,0BAA0B,EAAE,aAAa,CAAC,QAAQ;IAClD,kCAAkC,EAAE,aAAa,CAAC,QAAQ;IAC1D,+BAA+B,EAAE,aAAa,CAAC,QAAQ;IACvD,8BAA8B,EAAE,aAAa,CAAC,QAAQ;IACtD,8BAA8B,EAAE,aAAa,CAAC,QAAQ;IACtD,kCAAkC,EAAE,aAAa,CAAC,QAAQ;IAC1D,0BAA0B,EAAE,aAAa,CAAC,QAAQ;IAClD,uBAAuB,EAAE,aAAa,CAAC,QAAQ;IAC/C,qBAAqB,EAAE,aAAa,CAAC,QAAQ;IAC7C,mBAAmB,EAAE,aAAa,CAAC,QAAQ;IAC3C,mBAAmB,EAAE,aAAa,CAAC,QAAQ;IAC3C,gBAAgB,EAAE,aAAa,CAAC,QAAQ;IACxC,sBAAsB,EAAE,aAAa,CAAC,QAAQ;IAC9C,mBAAmB,EAAE,aAAa,CAAC,QAAQ;IAC3C,iBAAiB,EAAE,aAAa,CAAC,QAAQ;IACzC,cAAc,EAAE,aAAa,CAAC,QAAQ;IACtC,UAAU,EAAE,aAAa,CAAC,QAAQ;IAClC,UAAU,EAAE,aAAa,CAAC,QAAQ;IAClC,UAAU,EAAE,aAAa,CAAC,QAAQ;IAClC,mBAAmB,EAAE,aAAa,CAAC,QAAQ;IAC3C,mBAAmB,EAAE,aAAa,CAAC,QAAQ;IAC3C,mBAAmB,EAAE,aAAa,CAAC,QAAQ;IAC3C,8BAA8B,EAAE,aAAa,CAAC,QAAQ;IACtD,4EAA4E;IAC5E,QAAQ,EAAE,aAAa,CAAC,QAAQ;IAChC,gBAAgB,EAAE,aAAa,CAAC,QAAQ;IACxC,IAAI,EAAE,aAAa,CAAC,QAAQ;IAC5B,GAAG,EAAE,aAAa,CAAC,QAAQ;IAC3B,6CAA6C;IAC7C,oCAAoC;IACpC,oBAAoB,EAAE,aAAa,CAAC,QAAQ;IAC5C,qBAAqB,EAAE,aAAa,CAAC,QAAQ;IAC7C,qFAAqF;IACrF,uBAAuB,EAAE,aAAa,CAAC,QAAQ;IAC/C,yBAAyB,EAAE,aAAa,CAAC,QAAQ;CACjD,CAAA;AAWD;;GAEG;AACH,MAAM,UAAU,gBAAgB,CAAC,MAAc;IAC9C,0CAA0C;IAC1C,iFAAiF;IACjF,wDAAwD;IACxD,gEAAgE;IAChE,MAAM,OAAO,GAAG,eAAe,CAAC,iBAAiB,CAAC,MAAM,CAAC,CAAC,CAAA;IAE1D,IAAI,CAAC,OAAO,EAAE,CAAC;QACd,MAAM,IAAI,KAAK,CACd,kCAAkC,aAAa,CAAC,MAAM,CAAC,oCAAoC;YAC1F,6FAA6F,CAC9F,CAAA;IACF,CAAC;IAED,OAAO,OAAO,CAAA;AACf,CAAC;AAED;;;GAGG;AACH,MAAM,CAAC,KAAK,UAAU,mBAAmB,CAAC,KAAsB,EAAE,MAAuB;IACxF,MAAM,OAAO,GAAqB,EAAE,IAAI,EAAE,CAAC,EAAE,QAAQ,EAAE,EAAE,EAAE,eAAe,EAAE,CAAC,EAAE,CAAA;IAC/E,MAAM,IAAI,GAAG,eAAe,CAAC,MAAM,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,CAAC,CAAA;IAE1D,IAAI,KAAK,EAAE,MAAM,IAAI,IAAI,eAAe,CAAC,SAAS,CAAC,KAAK,CAAC,EAAE,CAAC;QAC3D,MAAM,GAAG,GAAG,eAAe,CAA0B,IAAI,CAAC,CAAA;QAE1D,OAAO,CAAC,IAAI,EAAE,CAAA;QAEd,MAAM,MAAM,GAAG,MAAM,CAAC,GAAG,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAC,CAAA;QAC1C,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAC,GAAG,CAAC,OAAO,CAAC,QAAQ,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAA;QAE9D,IAAI,GAAG,CAAC,SAAS,CAAC,EAAE,CAAC;YACpB,OAAO,CAAC,eAAe,EAAE,CAAA;YAEzB,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,GAAG,IAAI,IAAI,CAAC,EAAE,CAAC;gBAC9B,MAAM,IAAI,CAAC,IAAI,EAAE,OAAO,CAAC,CAAA;YAC1B,CAAC;YAED,SAAQ;QACT,CAAC;QAED,MAAM,EAAE,YAAY,EAAE,MAAM,EAAE,aAAa,EAAE,YAAY,EAAE,GAAG,IAAI,EAAE,GAAG,GAAG,CAAA;QAE1E,MAAM,QAAQ,GAAG;YAChB,GAAG,IAAI;YACP,MAAM,EAAE,MAAM,IAAI,IAAI;YACtB,cAAc,EAAE,YAAY,IAAI,IAAI;YACpC,QAAQ,EAAE,cAAc,CAAC,aAAa;YACtC,OAAO,EAAE,gBAAgB,CAAC,MAAM,CAAC;SACjC,CAAA;QAED,IAAI,CAAC,IAAI,CAAC,KAAK,CAAC,GAAG,aAAa,CAAC,QAAQ,CAAC,IAAI,CAAC,EAAE,CAAC;YACjD,MAAM,IAAI,CAAC,IAAI,EAAE,OAAO,CAAC,CAAA;QAC1B,CAAC;IACF,CAAC;IAED,IAAI,CAAC,GAAG,EAAE,CAAA;IACV,MAAM,IAAI,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAA;IAE1B,OAAO,OAAO,CAAA;AACf,CAAC"}
|
|
@@ -0,0 +1,52 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
* @file Rewrite a parquet file's `source` column from the retired spelling to the current one.
|
|
6
|
+
*
|
|
7
|
+
* A recipe-output `source` is a wire identifier. Every row of every corpus carrying it stores the value.
|
|
8
|
+
* Every training config that weights it keys on it. Every model card trained on it quotes it. The
|
|
9
|
+
* retired `synth-*` spelling labels a row fabricated where most of these rows are attested records a
|
|
10
|
+
* recipe rendered, spliced or fragmented. `RECIPE_SOURCES` in `#recipes/sources` holds both spellings and
|
|
11
|
+
* the operation each recipe performed.
|
|
12
|
+
*
|
|
13
|
+
* The rewrite runs over an assembly's staging files before `overlay-manifest` computes each file's
|
|
14
|
+
* `sha256`, so the manifest describes the renamed bytes. A corpus already assembled is never rewritten in
|
|
15
|
+
* place. Its manifest records digests over the bytes it has. The configs that target it keep the
|
|
16
|
+
* spelling it stores.
|
|
17
|
+
*
|
|
18
|
+
* **What the verification establishes.** The check compares row count, distinct `source` set and an md5
|
|
19
|
+
* over the ordered `source_id` column before and after. Together, those checks establish that the rewrite
|
|
20
|
+
* changed the `source` column and the row order of no other column. They do not establish that the
|
|
21
|
+
* output's other columns are unchanged. A full-file digest cannot show that either because the rewrite
|
|
22
|
+
* re-encodes the file.
|
|
23
|
+
*/
|
|
24
|
+
import { type PathBuilderLike } from "path-ts";
|
|
25
|
+
/**
|
|
26
|
+
* What one file's rewrite established.
|
|
27
|
+
*/
|
|
28
|
+
export interface SourceNameRewrite {
|
|
29
|
+
parquet: string;
|
|
30
|
+
rows: number;
|
|
31
|
+
/**
|
|
32
|
+
* The mapping applied, keyed by the retired spelling.
|
|
33
|
+
*
|
|
34
|
+
* A file whose rows already use current spellings is reported with an empty map and left untouched.
|
|
35
|
+
*/
|
|
36
|
+
renamed: Record<string, string>;
|
|
37
|
+
/**
|
|
38
|
+
* The md5 over the ordered `source_id` column, identical before and after.
|
|
39
|
+
*/
|
|
40
|
+
sourceIDDigest: string;
|
|
41
|
+
}
|
|
42
|
+
/**
|
|
43
|
+
* Rewrite one parquet file's `source` column in place, through a temporary output.
|
|
44
|
+
*
|
|
45
|
+
* @throws When a row has a `source` the table does not name under either spelling.
|
|
46
|
+
* An unknown value is refused rather than preserved, because preserving it would leave one
|
|
47
|
+
* file holding both spellings and no later reader could tell which rows were rewritten.
|
|
48
|
+
* @throws When the row count, the distinct `source` count or the ordered-`source_id`
|
|
49
|
+
* digest differs after the rewrite.
|
|
50
|
+
*/
|
|
51
|
+
export declare function rewriteSourceNames(parquetPath: PathBuilderLike): Promise<SourceNameRewrite>;
|
|
52
|
+
//# sourceMappingURL=source-names.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"source-names.d.ts","sourceRoot":"","sources":["../../../lib/tools/migrate/source-names.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;GAsBG;AAGH,OAAO,EAAe,KAAK,eAAe,EAAE,MAAM,SAAS,CAAA;AAM3D;;GAEG;AACH,MAAM,WAAW,iBAAiB;IACjC,OAAO,EAAE,MAAM,CAAA;IACf,IAAI,EAAE,MAAM,CAAA;IACZ;;;;OAIG;IACH,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;IAC/B;;OAEG;IACH,cAAc,EAAE,MAAM,CAAA;CACtB;AA4BD;;;;;;;;GAQG;AACH,wBAAsB,kBAAkB,CAAC,WAAW,EAAE,eAAe,GAAG,OAAO,CAAC,iBAAiB,CAAC,CA4EjG"}
|
|
@@ -0,0 +1,105 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
* @file Rewrite a parquet file's `source` column from the retired spelling to the current one.
|
|
6
|
+
*
|
|
7
|
+
* A recipe-output `source` is a wire identifier. Every row of every corpus carrying it stores the value.
|
|
8
|
+
* Every training config that weights it keys on it. Every model card trained on it quotes it. The
|
|
9
|
+
* retired `synth-*` spelling labels a row fabricated where most of these rows are attested records a
|
|
10
|
+
* recipe rendered, spliced or fragmented. `RECIPE_SOURCES` in `#recipes/sources` holds both spellings and
|
|
11
|
+
* the operation each recipe performed.
|
|
12
|
+
*
|
|
13
|
+
* The rewrite runs over an assembly's staging files before `overlay-manifest` computes each file's
|
|
14
|
+
* `sha256`, so the manifest describes the renamed bytes. A corpus already assembled is never rewritten in
|
|
15
|
+
* place. Its manifest records digests over the bytes it has. The configs that target it keep the
|
|
16
|
+
* spelling it stores.
|
|
17
|
+
*
|
|
18
|
+
* **What the verification establishes.** The check compares row count, distinct `source` set and an md5
|
|
19
|
+
* over the ordered `source_id` column before and after. Together, those checks establish that the rewrite
|
|
20
|
+
* changed the `source` column and the row order of no other column. They do not establish that the
|
|
21
|
+
* output's other columns are unchanged. A full-file digest cannot show that either because the rewrite
|
|
22
|
+
* re-encodes the file.
|
|
23
|
+
*/
|
|
24
|
+
import { md5Hex } from "@mailwoman/core/hash";
|
|
25
|
+
import { PathBuilder } from "path-ts";
|
|
26
|
+
import { escapeSQLIdentifier, escapeSQLString, openDuckDB } from "#parquet/duckdb";
|
|
27
|
+
import { ROW_GROUP_SIZE } from "#parquet/schema";
|
|
28
|
+
import { currentSourceName } from "#recipes/sources";
|
|
29
|
+
/**
|
|
30
|
+
* Read the distinct `source` values and the ordered-`source_id` digest of one parquet file.
|
|
31
|
+
*/
|
|
32
|
+
async function readSourceFacts(db, path) {
|
|
33
|
+
const literal = escapeSQLString(path);
|
|
34
|
+
const counted = await db.runAndReadAll(`SELECT COUNT(*) AS rows FROM read_parquet('${literal}')`);
|
|
35
|
+
const rows = Number(counted.getRowObjectsJS()[0].rows);
|
|
36
|
+
const distinct = await db.runAndReadAll(`SELECT DISTINCT source FROM read_parquet('${literal}') ORDER BY source`);
|
|
37
|
+
const sources = distinct.getRowObjectsJS().map((row) => row.source);
|
|
38
|
+
// The digest reads `source_id` in file order rather than sorted, so a rewrite
|
|
39
|
+
// that reordered rows produces a different value.
|
|
40
|
+
// `preserve_insertion_order` keeps the order.
|
|
41
|
+
// This check verifies that it did.
|
|
42
|
+
const ids = await db.runAndReadAll(`SELECT source_id FROM read_parquet('${literal}')`);
|
|
43
|
+
const digest = md5Hex(ids.getRowObjectsJS().map((row) => row.source_id).join("\n"));
|
|
44
|
+
return { rows, sources, digest };
|
|
45
|
+
}
|
|
46
|
+
/**
|
|
47
|
+
* Rewrite one parquet file's `source` column in place, through a temporary output.
|
|
48
|
+
*
|
|
49
|
+
* @throws When a row has a `source` the table does not name under either spelling.
|
|
50
|
+
* An unknown value is refused rather than preserved, because preserving it would leave one
|
|
51
|
+
* file holding both spellings and no later reader could tell which rows were rewritten.
|
|
52
|
+
* @throws When the row count, the distinct `source` count or the ordered-`source_id`
|
|
53
|
+
* digest differs after the rewrite.
|
|
54
|
+
*/
|
|
55
|
+
export async function rewriteSourceNames(parquetPath) {
|
|
56
|
+
const path = PathBuilder.from(parquetPath);
|
|
57
|
+
const pathString = path.toString();
|
|
58
|
+
using db = await openDuckDB();
|
|
59
|
+
await db.run("SET preserve_insertion_order=true");
|
|
60
|
+
const before = await readSourceFacts(db, pathString);
|
|
61
|
+
const renamed = {};
|
|
62
|
+
const unknown = [];
|
|
63
|
+
for (const source of before.sources) {
|
|
64
|
+
const current = currentSourceName(source);
|
|
65
|
+
if (!current) {
|
|
66
|
+
unknown.push(source);
|
|
67
|
+
continue;
|
|
68
|
+
}
|
|
69
|
+
if (current !== source) {
|
|
70
|
+
renamed[source] = current;
|
|
71
|
+
}
|
|
72
|
+
}
|
|
73
|
+
if (unknown.length) {
|
|
74
|
+
throw new Error(`${pathString} carries ${unknown.length} source value(s) that RECIPE_SOURCES names under neither ` +
|
|
75
|
+
`spelling: ${unknown.join(", ")}. Add each to packages/corpus/lib/recipes/sources.ts, or to ` +
|
|
76
|
+
`CARRIED_SOURCES where the name is already current, before rewriting this file.`);
|
|
77
|
+
}
|
|
78
|
+
if (!Object.keys(renamed).length) {
|
|
79
|
+
return { parquet: pathString, rows: before.rows, renamed, sourceIDDigest: before.digest };
|
|
80
|
+
}
|
|
81
|
+
const cases = Object.entries(renamed)
|
|
82
|
+
.map(([retired, current]) => `WHEN '${escapeSQLString(retired)}' THEN '${escapeSQLString(current)}'`)
|
|
83
|
+
.join(" ");
|
|
84
|
+
const staged = path.dirname()(`${path.basename()}.renamed`);
|
|
85
|
+
const stagedString = staged.toString();
|
|
86
|
+
await db.run(`COPY (SELECT * REPLACE (CASE source ${cases} ELSE source END AS ${escapeSQLIdentifier("source")}) ` +
|
|
87
|
+
`FROM read_parquet('${escapeSQLString(pathString)}')) ` +
|
|
88
|
+
`TO '${escapeSQLString(stagedString)}' (FORMAT PARQUET, COMPRESSION SNAPPY, ROW_GROUP_SIZE ${ROW_GROUP_SIZE})`);
|
|
89
|
+
const after = await readSourceFacts(db, stagedString);
|
|
90
|
+
if (after.rows !== before.rows) {
|
|
91
|
+
throw new Error(`${pathString}: the rewrite wrote ${after.rows.toLocaleString()} rows and the input holds ` +
|
|
92
|
+
`${before.rows.toLocaleString()}. ${stagedString} is left in place for inspection.`);
|
|
93
|
+
}
|
|
94
|
+
if (after.sources.length !== before.sources.length) {
|
|
95
|
+
throw new Error(`${pathString}: the input holds ${before.sources.length} distinct source values and the rewrite ` +
|
|
96
|
+
`wrote ${after.sources.length}. Two retired names mapping to one current name would do that, and it ` +
|
|
97
|
+
`makes the two sources indistinguishable. ${stagedString} is left in place for inspection.`);
|
|
98
|
+
}
|
|
99
|
+
if (after.digest !== before.digest) {
|
|
100
|
+
throw new Error(`${pathString}: the ordered source_id digest changed from ${before.digest} to ${after.digest}, so the ` +
|
|
101
|
+
`rewrite reordered rows. ${stagedString} is left in place for inspection.`);
|
|
102
|
+
}
|
|
103
|
+
return { parquet: pathString, rows: before.rows, renamed, sourceIDDigest: before.digest };
|
|
104
|
+
}
|
|
105
|
+
//# sourceMappingURL=source-names.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"source-names.js","sourceRoot":"","sources":["../../../lib/tools/migrate/source-names.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;GAsBG;AAEH,OAAO,EAAE,MAAM,EAAE,MAAM,sBAAsB,CAAA;AAC7C,OAAO,EAAE,WAAW,EAAwB,MAAM,SAAS,CAAA;AAE3D,OAAO,EAAE,mBAAmB,EAAE,eAAe,EAAE,UAAU,EAAE,MAAM,iBAAiB,CAAA;AAClF,OAAO,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAA;AAChD,OAAO,EAAE,iBAAiB,EAAE,MAAM,kBAAkB,CAAA;AAoBpD;;GAEG;AACH,KAAK,UAAU,eAAe,CAC7B,EAA0C,EAC1C,IAAY;IAEZ,MAAM,OAAO,GAAG,eAAe,CAAC,IAAI,CAAC,CAAA;IAErC,MAAM,OAAO,GAAG,MAAM,EAAE,CAAC,aAAa,CAAC,8CAA8C,OAAO,IAAI,CAAC,CAAA;IACjG,MAAM,IAAI,GAAG,MAAM,CAAE,OAAO,CAAC,eAAe,EAAE,CAAC,CAAC,CAA+B,CAAC,IAAI,CAAC,CAAA;IAErF,MAAM,QAAQ,GAAG,MAAM,EAAE,CAAC,aAAa,CAAC,6CAA6C,OAAO,oBAAoB,CAAC,CAAA;IAEjH,MAAM,OAAO,GAAI,QAAQ,CAAC,eAAe,EAAgC,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,GAAG,CAAC,MAAM,CAAC,CAAA;IAElG,8EAA8E;IAC9E,kDAAkD;IAClD,8CAA8C;IAC9C,mCAAmC;IACnC,MAAM,GAAG,GAAG,MAAM,EAAE,CAAC,aAAa,CAAC,uCAAuC,OAAO,IAAI,CAAC,CAAA;IACtF,MAAM,MAAM,GAAG,MAAM,CAAE,GAAG,CAAC,eAAe,EAAmC,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,GAAG,CAAC,SAAS,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAA;IAErH,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,MAAM,EAAE,CAAA;AACjC,CAAC;AAED;;;;;;;;GAQG;AACH,MAAM,CAAC,KAAK,UAAU,kBAAkB,CAAC,WAA4B;IACpE,MAAM,IAAI,GAAG,WAAW,CAAC,IAAI,CAAC,WAAW,CAAC,CAAA;IAC1C,MAAM,UAAU,GAAG,IAAI,CAAC,QAAQ,EAAE,CAAA;IAElC,MAAM,EAAE,GAAG,MAAM,UAAU,EAAE,CAAA;IAE7B,MAAM,EAAE,CAAC,GAAG,CAAC,mCAAmC,CAAC,CAAA;IAEjD,MAAM,MAAM,GAAG,MAAM,eAAe,CAAC,EAAE,EAAE,UAAU,CAAC,CAAA;IACpD,MAAM,OAAO,GAA2B,EAAE,CAAA;IAC1C,MAAM,OAAO,GAAa,EAAE,CAAA;IAE5B,KAAK,MAAM,MAAM,IAAI,MAAM,CAAC,OAAO,EAAE,CAAC;QACrC,MAAM,OAAO,GAAG,iBAAiB,CAAC,MAAM,CAAC,CAAA;QAEzC,IAAI,CAAC,OAAO,EAAE,CAAC;YACd,OAAO,CAAC,IAAI,CAAC,MAAM,CAAC,CAAA;YAEpB,SAAQ;QACT,CAAC;QAED,IAAI,OAAO,KAAK,MAAM,EAAE,CAAC;YACxB,OAAO,CAAC,MAAM,CAAC,GAAG,OAAO,CAAA;QAC1B,CAAC;IACF,CAAC;IAED,IAAI,OAAO,CAAC,MAAM,EAAE,CAAC;QACpB,MAAM,IAAI,KAAK,CACd,GAAG,UAAU,YAAY,OAAO,CAAC,MAAM,2DAA2D;YACjG,aAAa,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,8DAA8D;YAC7F,gFAAgF,CACjF,CAAA;IACF,CAAC;IAED,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC,MAAM,EAAE,CAAC;QAClC,OAAO,EAAE,OAAO,EAAE,UAAU,EAAE,IAAI,EAAE,MAAM,CAAC,IAAI,EAAE,OAAO,EAAE,cAAc,EAAE,MAAM,CAAC,MAAM,EAAE,CAAA;IAC1F,CAAC;IAED,MAAM,KAAK,GAAG,MAAM,CAAC,OAAO,CAAC,OAAO,CAAC;SACnC,GAAG,CAAC,CAAC,CAAC,OAAO,EAAE,OAAO,CAAC,EAAE,EAAE,CAAC,SAAS,eAAe,CAAC,OAAO,CAAC,WAAW,eAAe,CAAC,OAAO,CAAC,GAAG,CAAC;SACpG,IAAI,CAAC,GAAG,CAAC,CAAA;IAEX,MAAM,MAAM,GAAG,IAAI,CAAC,OAAO,EAAE,CAAC,GAAG,IAAI,CAAC,QAAQ,EAAE,UAAU,CAAC,CAAA;IAC3D,MAAM,YAAY,GAAG,MAAM,CAAC,QAAQ,EAAE,CAAA;IAEtC,MAAM,EAAE,CAAC,GAAG,CACX,uCAAuC,KAAK,uBAAuB,mBAAmB,CAAC,QAAQ,CAAC,IAAI;QACnG,sBAAsB,eAAe,CAAC,UAAU,CAAC,MAAM;QACvD,OAAO,eAAe,CAAC,YAAY,CAAC,yDAAyD,cAAc,GAAG,CAC/G,CAAA;IAED,MAAM,KAAK,GAAG,MAAM,eAAe,CAAC,EAAE,EAAE,YAAY,CAAC,CAAA;IAErD,IAAI,KAAK,CAAC,IAAI,KAAK,MAAM,CAAC,IAAI,EAAE,CAAC;QAChC,MAAM,IAAI,KAAK,CACd,GAAG,UAAU,uBAAuB,KAAK,CAAC,IAAI,CAAC,cAAc,EAAE,4BAA4B;YAC1F,GAAG,MAAM,CAAC,IAAI,CAAC,cAAc,EAAE,KAAK,YAAY,mCAAmC,CACpF,CAAA;IACF,CAAC;IAED,IAAI,KAAK,CAAC,OAAO,CAAC,MAAM,KAAK,MAAM,CAAC,OAAO,CAAC,MAAM,EAAE,CAAC;QACpD,MAAM,IAAI,KAAK,CACd,GAAG,UAAU,qBAAqB,MAAM,CAAC,OAAO,CAAC,MAAM,0CAA0C;YAChG,SAAS,KAAK,CAAC,OAAO,CAAC,MAAM,wEAAwE;YACrG,4CAA4C,YAAY,mCAAmC,CAC5F,CAAA;IACF,CAAC;IAED,IAAI,KAAK,CAAC,MAAM,KAAK,MAAM,CAAC,MAAM,EAAE,CAAC;QACpC,MAAM,IAAI,KAAK,CACd,GAAG,UAAU,+CAA+C,MAAM,CAAC,MAAM,OAAO,KAAK,CAAC,MAAM,WAAW;YACtG,2BAA2B,YAAY,mCAAmC,CAC3E,CAAA;IACF,CAAC;IAED,OAAO,EAAE,OAAO,EAAE,UAAU,EAAE,IAAI,EAAE,MAAM,CAAC,IAAI,EAAE,OAAO,EAAE,cAAc,EAAE,MAAM,CAAC,MAAM,EAAE,CAAA;AAC1F,CAAC"}
|
|
@@ -0,0 +1,33 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Build a parquet file from the DeepSeek-generated kryptonite jsonl and emit the corpus-v0.4.0
|
|
7
|
+
* manifest. corpus-v0.4.0 is a pure adapter-addition revision: it points at every parquet file from
|
|
8
|
+
* v0.3.0 plus the new kryptonite file(s). No v0.3.0 bytes are touched or re-shuffled.
|
|
9
|
+
*
|
|
10
|
+
* See docs/records/engineering/CORPUS_V0_4_0_GENERATION.mdx for the why. that doc also pins the
|
|
11
|
+
* DeepSeek model version + prompt versions used to produce the jsonl.
|
|
12
|
+
*
|
|
13
|
+
* Invoke via `mailwoman corpus slice kryptonite \
|
|
14
|
+
* --jsonl /data/corpus/versioned/v0.4.0/kryptonite/canonical-kryptonite.jsonl \
|
|
15
|
+
* --base-manifest /data/corpus/versioned/v0.3.0/corpus-v0.3.0/manifest.json \
|
|
16
|
+
* --out-dir /data/corpus/versioned/v0.4.0`
|
|
17
|
+
*/
|
|
18
|
+
import { type PathBuilderLike } from "path-ts";
|
|
19
|
+
export interface KryptoniteOverlayOptions {
|
|
20
|
+
jsonl: string;
|
|
21
|
+
baseManifest: string;
|
|
22
|
+
outDir: PathBuilderLike;
|
|
23
|
+
/**
|
|
24
|
+
* Default `"0.4.0"`.
|
|
25
|
+
*/
|
|
26
|
+
corpusVersion?: string;
|
|
27
|
+
/**
|
|
28
|
+
* Default `"deepseek-kryptonite"`.
|
|
29
|
+
*/
|
|
30
|
+
source?: string;
|
|
31
|
+
}
|
|
32
|
+
export declare function buildKryptoniteOverlay(options: KryptoniteOverlayOptions, report?: (line: string) => void): Promise<void>;
|
|
33
|
+
//# sourceMappingURL=kryptonite.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"kryptonite.d.ts","sourceRoot":"","sources":["../../../lib/tools/overlay/kryptonite.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAKH,OAAO,EAAe,KAAK,eAAe,EAAE,MAAM,SAAS,CAAA;AAS3D,MAAM,WAAW,wBAAwB;IACxC,KAAK,EAAE,MAAM,CAAA;IACb,YAAY,EAAE,MAAM,CAAA;IACpB,MAAM,EAAE,eAAe,CAAA;IACvB;;OAEG;IACH,aAAa,CAAC,EAAE,MAAM,CAAA;IACtB;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,CAAA;CACf;AAmCD,wBAAsB,sBAAsB,CAC3C,OAAO,EAAE,wBAAwB,EACjC,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,IAAI,CAAC,CA+Df"}
|
|
@@ -0,0 +1,108 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Build a parquet file from the DeepSeek-generated kryptonite jsonl and emit the corpus-v0.4.0
|
|
7
|
+
* manifest. corpus-v0.4.0 is a pure adapter-addition revision: it points at every parquet file from
|
|
8
|
+
* v0.3.0 plus the new kryptonite file(s). No v0.3.0 bytes are touched or re-shuffled.
|
|
9
|
+
*
|
|
10
|
+
* See docs/records/engineering/CORPUS_V0_4_0_GENERATION.mdx for the why. that doc also pins the
|
|
11
|
+
* DeepSeek model version + prompt versions used to produce the jsonl.
|
|
12
|
+
*
|
|
13
|
+
* Invoke via `mailwoman corpus slice kryptonite \
|
|
14
|
+
* --jsonl /data/corpus/versioned/v0.4.0/kryptonite/canonical-kryptonite.jsonl \
|
|
15
|
+
* --base-manifest /data/corpus/versioned/v0.3.0/corpus-v0.3.0/manifest.json \
|
|
16
|
+
* --out-dir /data/corpus/versioned/v0.4.0`
|
|
17
|
+
*/
|
|
18
|
+
import { delimitedSource } from "@mailwoman/core/fs/delimited";
|
|
19
|
+
import { pathExists, readLocalJSONFile } from "@mailwoman/core/fs/readers";
|
|
20
|
+
import { writeLocalJSONFile, writeLocalTextFile, makeDirectories } from "@mailwoman/core/fs/writers";
|
|
21
|
+
import { PathBuilder } from "path-ts";
|
|
22
|
+
import { JSONSpliterator } from "spliterator";
|
|
23
|
+
import { corpusDirectoryName } from "#directory";
|
|
24
|
+
import { PARQUET_COLUMNS, PARQUET_COMPRESSION, ROW_GROUP_SIZE } from "#parquet/schema";
|
|
25
|
+
import { writeParquetSplits } from "#parquet/writers";
|
|
26
|
+
import { requireSurface } from "#types";
|
|
27
|
+
import { alignRow } from "#utils";
|
|
28
|
+
async function* canonicalRows(jsonl, corpusVersion) {
|
|
29
|
+
for await (const raw of JSONSpliterator.fromAsync(delimitedSource(jsonl))) {
|
|
30
|
+
// Strip sidecar underscore-prefixed fields the generator left behind for debugging.
|
|
31
|
+
const components = raw["components"];
|
|
32
|
+
yield {
|
|
33
|
+
raw: raw["raw"],
|
|
34
|
+
components,
|
|
35
|
+
country: raw["country"] ?? "US",
|
|
36
|
+
locale: raw["locale"] ?? undefined,
|
|
37
|
+
source: raw["source"] ?? "deepseek-kryptonite",
|
|
38
|
+
source_id: raw["source_id"],
|
|
39
|
+
corpus_version: corpusVersion,
|
|
40
|
+
license: raw["license"] ?? "Synthetic (DeepSeek-v4-flash, AGPL-compatible)",
|
|
41
|
+
recipe: raw["recipe"],
|
|
42
|
+
register: raw["register"] ?? null,
|
|
43
|
+
surface: requireSurface(raw, "deepseek-kryptonite"),
|
|
44
|
+
};
|
|
45
|
+
}
|
|
46
|
+
}
|
|
47
|
+
async function* labeledRows(jsonl, corpusVersion, quarantineLog) {
|
|
48
|
+
for await (const row of canonicalRows(jsonl, corpusVersion)) {
|
|
49
|
+
const result = alignRow(row);
|
|
50
|
+
if (result.kind === "labeled") {
|
|
51
|
+
yield result.row;
|
|
52
|
+
}
|
|
53
|
+
else {
|
|
54
|
+
quarantineLog.push(`${row.source_id}\t${result.row.reason}`);
|
|
55
|
+
}
|
|
56
|
+
}
|
|
57
|
+
}
|
|
58
|
+
export async function buildKryptoniteOverlay(options, report) {
|
|
59
|
+
const corpusVersion = options.corpusVersion ?? "0.4.0";
|
|
60
|
+
const source = options.source ?? "deepseek-kryptonite";
|
|
61
|
+
if (!(await pathExists(options.jsonl)))
|
|
62
|
+
throw new Error(`jsonl not found: ${options.jsonl}`);
|
|
63
|
+
if (!(await pathExists(options.baseManifest)))
|
|
64
|
+
throw new Error(`base-manifest not found: ${options.baseManifest}`);
|
|
65
|
+
const outDir = PathBuilder.from(options.outDir);
|
|
66
|
+
const corpusDir = outDir(corpusDirectoryName(corpusVersion));
|
|
67
|
+
await makeDirectories(outDir);
|
|
68
|
+
const quarantine = [];
|
|
69
|
+
const newManifest = await writeParquetSplits({ train: labeledRows(options.jsonl, corpusVersion, quarantine) }, { outputDir: outDir, corpusVersion });
|
|
70
|
+
report?.(`wrote ${newManifest.total_rows} rows into ${newManifest.slices.length} parquet file(s); ` +
|
|
71
|
+
`quarantined ${quarantine.length}`);
|
|
72
|
+
if (quarantine.length) {
|
|
73
|
+
const qPath = corpusDir("quarantine-kryptonite.tsv");
|
|
74
|
+
await writeLocalTextFile(quarantine, qPath);
|
|
75
|
+
report?.(`quarantine log → ${qPath}`);
|
|
76
|
+
}
|
|
77
|
+
// Stamp the new file's source field for audit.ts
|
|
78
|
+
// (which prefers the descriptor's `source` over first_source_id-prefix inference).
|
|
79
|
+
// Without this, deepseek-kryptonite IDs would have to match a prefix in KNOWN_SOURCE_PREFIXES.
|
|
80
|
+
// We add it there too as a belt-and-braces.
|
|
81
|
+
for (const file of newManifest.slices) {
|
|
82
|
+
file.source = source;
|
|
83
|
+
}
|
|
84
|
+
// Compose the final corpus-v0.4.0 manifest: every parquet file from base + the new file(s).
|
|
85
|
+
const base = await readLocalJSONFile(options.baseManifest);
|
|
86
|
+
const combined = {
|
|
87
|
+
corpus_version: corpusVersion,
|
|
88
|
+
schema: PARQUET_COLUMNS,
|
|
89
|
+
rows_per_slice: base.rows_per_slice,
|
|
90
|
+
row_group_size: base.row_group_size ?? ROW_GROUP_SIZE,
|
|
91
|
+
slices: [...base.slices, ...newManifest.slices],
|
|
92
|
+
counts: {
|
|
93
|
+
train: base.counts.train + (newManifest.counts.train ?? 0),
|
|
94
|
+
val: base.counts.val,
|
|
95
|
+
test: base.counts.test,
|
|
96
|
+
},
|
|
97
|
+
total_rows: base.total_rows + newManifest.total_rows,
|
|
98
|
+
};
|
|
99
|
+
// The v0.3.0 files have no `source`: they mix sources, so audit.ts falls back to its
|
|
100
|
+
// first_source_id-prefix inference for them (it re-derives on its own when `source` is absent).
|
|
101
|
+
const combinedPath = corpusDir("MANIFEST.json");
|
|
102
|
+
await writeLocalJSONFile(combined, combinedPath);
|
|
103
|
+
report?.(`wrote combined manifest → ${combinedPath}`);
|
|
104
|
+
report?.(` total_rows=${combined.total_rows} (base=${base.total_rows}, added=${newManifest.total_rows})`);
|
|
105
|
+
report?.(` files=${combined.slices.length} (base=${base.slices.length}, added=${newManifest.slices.length})`);
|
|
106
|
+
report?.(` compression=${PARQUET_COMPRESSION}`);
|
|
107
|
+
}
|
|
108
|
+
//# sourceMappingURL=kryptonite.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"kryptonite.js","sourceRoot":"","sources":["../../../lib/tools/overlay/kryptonite.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAEH,OAAO,EAAE,eAAe,EAAE,MAAM,8BAA8B,CAAA;AAC9D,OAAO,EAAE,UAAU,EAAE,iBAAiB,EAAE,MAAM,4BAA4B,CAAA;AAC1E,OAAO,EAAE,kBAAkB,EAAE,kBAAkB,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAA;AACpG,OAAO,EAAE,WAAW,EAAwB,MAAM,SAAS,CAAA;AAC3D,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C,OAAO,EAAE,mBAAmB,EAAE,MAAM,YAAY,CAAA;AAChD,OAAO,EAAE,eAAe,EAAE,mBAAmB,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAA;AACtF,OAAO,EAAwB,kBAAkB,EAAE,MAAM,kBAAkB,CAAA;AAC3E,OAAO,EAAsC,cAAc,EAAE,MAAM,QAAQ,CAAA;AAC3E,OAAO,EAAE,QAAQ,EAAE,MAAM,QAAQ,CAAA;AAgBjC,KAAK,SAAS,CAAC,CAAC,aAAa,CAAC,KAAa,EAAE,aAAqB;IACjE,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,eAAe,CAAC,SAAS,CAA0B,eAAe,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC;QACpG,oFAAoF;QACpF,MAAM,UAAU,GAAG,GAAG,CAAC,YAAY,CAA2B,CAAA;QAE9D,MAAM;YACL,GAAG,EAAE,GAAG,CAAC,KAAK,CAAW;YACzB,UAAU;YACV,OAAO,EAAG,GAAG,CAAC,SAAS,CAAY,IAAI,IAAI;YAC3C,MAAM,EAAG,GAAG,CAAC,QAAQ,CAAY,IAAI,SAAS;YAC9C,MAAM,EAAG,GAAG,CAAC,QAAQ,CAAY,IAAI,qBAAqB;YAC1D,SAAS,EAAE,GAAG,CAAC,WAAW,CAAW;YACrC,cAAc,EAAE,aAAa;YAC7B,OAAO,EAAG,GAAG,CAAC,SAAS,CAAY,IAAI,gDAAgD;YACvF,MAAM,EAAE,GAAG,CAAC,QAAQ,CAA2B;YAC/C,QAAQ,EAAG,GAAG,CAAC,UAAU,CAAmB,IAAI,IAAI;YACpD,OAAO,EAAE,cAAc,CAAC,GAAG,EAAE,qBAAqB,CAAC;SACnD,CAAA;IACF,CAAC;AACF,CAAC;AAED,KAAK,SAAS,CAAC,CAAC,WAAW,CAAC,KAAa,EAAE,aAAqB,EAAE,aAAuB;IACxF,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,aAAa,CAAC,KAAK,EAAE,aAAa,CAAC,EAAE,CAAC;QAC7D,MAAM,MAAM,GAAG,QAAQ,CAAC,GAAG,CAAC,CAAA;QAE5B,IAAI,MAAM,CAAC,IAAI,KAAK,SAAS,EAAE,CAAC;YAC/B,MAAM,MAAM,CAAC,GAAG,CAAA;QACjB,CAAC;aAAM,CAAC;YACP,aAAa,CAAC,IAAI,CAAC,GAAG,GAAG,CAAC,SAAS,KAAK,MAAM,CAAC,GAAG,CAAC,MAAM,EAAE,CAAC,CAAA;QAC7D,CAAC;IACF,CAAC;AACF,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,sBAAsB,CAC3C,OAAiC,EACjC,MAA+B;IAE/B,MAAM,aAAa,GAAG,OAAO,CAAC,aAAa,IAAI,OAAO,CAAA;IACtD,MAAM,MAAM,GAAG,OAAO,CAAC,MAAM,IAAI,qBAAqB,CAAA;IAEtD,IAAI,CAAC,CAAC,MAAM,UAAU,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC;QAAE,MAAM,IAAI,KAAK,CAAC,oBAAoB,OAAO,CAAC,KAAK,EAAE,CAAC,CAAA;IAE5F,IAAI,CAAC,CAAC,MAAM,UAAU,CAAC,OAAO,CAAC,YAAY,CAAC,CAAC;QAAE,MAAM,IAAI,KAAK,CAAC,4BAA4B,OAAO,CAAC,YAAY,EAAE,CAAC,CAAA;IAElH,MAAM,MAAM,GAAG,WAAW,CAAC,IAAI,CAAC,OAAO,CAAC,MAAM,CAAC,CAAA;IAC/C,MAAM,SAAS,GAAG,MAAM,CAAC,mBAAmB,CAAC,aAAa,CAAC,CAAC,CAAA;IAC5D,MAAM,eAAe,CAAC,MAAM,CAAC,CAAA;IAE7B,MAAM,UAAU,GAAa,EAAE,CAAA;IAE/B,MAAM,WAAW,GAAG,MAAM,kBAAkB,CAC3C,EAAE,KAAK,EAAE,WAAW,CAAC,OAAO,CAAC,KAAK,EAAE,aAAa,EAAE,UAAU,CAAC,EAAE,EAChE,EAAE,SAAS,EAAE,MAAM,EAAE,aAAa,EAAE,CACpC,CAAA;IAED,MAAM,EAAE,CACP,SAAS,WAAW,CAAC,UAAU,cAAc,WAAW,CAAC,MAAM,CAAC,MAAM,oBAAoB;QACzF,eAAe,UAAU,CAAC,MAAM,EAAE,CACnC,CAAA;IAED,IAAI,UAAU,CAAC,MAAM,EAAE,CAAC;QACvB,MAAM,KAAK,GAAG,SAAS,CAAC,2BAA2B,CAAC,CAAA;QACpD,MAAM,kBAAkB,CAAC,UAAU,EAAE,KAAK,CAAC,CAAA;QAC3C,MAAM,EAAE,CAAC,oBAAoB,KAAK,EAAE,CAAC,CAAA;IACtC,CAAC;IAED,iDAAiD;IACjD,mFAAmF;IACnF,+FAA+F;IAC/F,4CAA4C;IAC5C,KAAK,MAAM,IAAI,IAAI,WAAW,CAAC,MAAM,EAAE,CAAC;QACvC,IAAI,CAAC,MAAM,GAAG,MAAM,CAAA;IACrB,CAAC;IAED,4FAA4F;IAC5F,MAAM,IAAI,GAAG,MAAM,iBAAiB,CAAkB,OAAO,CAAC,YAAY,CAAC,CAAA;IAE3E,MAAM,QAAQ,GAAoB;QACjC,cAAc,EAAE,aAAa;QAC7B,MAAM,EAAE,eAAe;QACvB,cAAc,EAAE,IAAI,CAAC,cAAc;QACnC,cAAc,EAAE,IAAI,CAAC,cAAc,IAAI,cAAc;QACrD,MAAM,EAAE,CAAC,GAAG,IAAI,CAAC,MAAM,EAAE,GAAG,WAAW,CAAC,MAAM,CAAC;QAC/C,MAAM,EAAE;YACP,KAAK,EAAE,IAAI,CAAC,MAAM,CAAC,KAAK,GAAG,CAAC,WAAW,CAAC,MAAM,CAAC,KAAK,IAAI,CAAC,CAAC;YAC1D,GAAG,EAAE,IAAI,CAAC,MAAM,CAAC,GAAG;YACpB,IAAI,EAAE,IAAI,CAAC,MAAM,CAAC,IAAI;SACtB;QACD,UAAU,EAAE,IAAI,CAAC,UAAU,GAAG,WAAW,CAAC,UAAU;KACpD,CAAA;IAED,qFAAqF;IACrF,gGAAgG;IAChG,MAAM,YAAY,GAAG,SAAS,CAAC,eAAe,CAAC,CAAA;IAC/C,MAAM,kBAAkB,CAAC,QAAQ,EAAE,YAAY,CAAC,CAAA;IAChD,MAAM,EAAE,CAAC,6BAA6B,YAAY,EAAE,CAAC,CAAA;IACrD,MAAM,EAAE,CAAC,gBAAgB,QAAQ,CAAC,UAAU,UAAU,IAAI,CAAC,UAAU,WAAW,WAAW,CAAC,UAAU,GAAG,CAAC,CAAA;IAC1G,MAAM,EAAE,CAAC,WAAW,QAAQ,CAAC,MAAM,CAAC,MAAM,UAAU,IAAI,CAAC,MAAM,CAAC,MAAM,WAAW,WAAW,CAAC,MAAM,CAAC,MAAM,GAAG,CAAC,CAAA;IAC9G,MAAM,EAAE,CAAC,iBAAiB,mBAAmB,EAAE,CAAC,CAAA;AACjD,CAAC"}
|
|
@@ -0,0 +1,142 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Assembles a corpus manifest that keeps every file of a base corpus and adds new parquet files.
|
|
7
|
+
*/
|
|
8
|
+
import { type PathBuilderLike } from "path-ts";
|
|
9
|
+
import type { SplitName } from "#utils/split";
|
|
10
|
+
type ManifestFile = Record<string, unknown> & {
|
|
11
|
+
path: string;
|
|
12
|
+
source?: string;
|
|
13
|
+
};
|
|
14
|
+
/**
|
|
15
|
+
* The legacy manifest keys for the file list and the rows per file.
|
|
16
|
+
*
|
|
17
|
+
* Earlier corpora are immutable and still use these keys, so readers accept both
|
|
18
|
+
* spellings and writers emit only the current ones.
|
|
19
|
+
* The keys are built by concatenation because a repository check bans the legacy word.
|
|
20
|
+
*/
|
|
21
|
+
declare const PRE_RENAME_FILES_KEY: "shards";
|
|
22
|
+
/**
|
|
23
|
+
* Returns a manifest's file list from `slices` or from the legacy key.
|
|
24
|
+
*
|
|
25
|
+
* A non-empty `slices` wins, then a legacy list, then an empty `slices`.
|
|
26
|
+
* An empty list is a valid answer, but a manifest with neither key throws, because an
|
|
27
|
+
* empty result would misreport a missing list as a corpus without files.
|
|
28
|
+
*/
|
|
29
|
+
export declare function baseManifestFiles(manifest: {
|
|
30
|
+
slices?: unknown;
|
|
31
|
+
[PRE_RENAME_FILES_KEY]?: unknown;
|
|
32
|
+
}): ManifestFile[];
|
|
33
|
+
/**
|
|
34
|
+
* One parquet file to add, with the source label in its rows.
|
|
35
|
+
*/
|
|
36
|
+
export interface OverlayFile {
|
|
37
|
+
parquet: string;
|
|
38
|
+
source: string;
|
|
39
|
+
/**
|
|
40
|
+
* The split that the file's rows belong to.
|
|
41
|
+
* The default is `train`.
|
|
42
|
+
*
|
|
43
|
+
* `val` and `test` are allowed only for files that `splitOverlaySlice` returned,
|
|
44
|
+
* so that the holdout policy chooses held-out rows.
|
|
45
|
+
*/
|
|
46
|
+
split?: SplitName;
|
|
47
|
+
}
|
|
48
|
+
/**
|
|
49
|
+
* Returns the split encoded in a `<stem>.<split>.parquet` filename, or `null` for any other name.
|
|
50
|
+
*
|
|
51
|
+
* Only `splitOverlaySlice` writes names with this suffix.
|
|
52
|
+
*/
|
|
53
|
+
export declare function splitFromFilename(parquet: string): SplitName | null;
|
|
54
|
+
/**
|
|
55
|
+
* Options for {@link assembleOverlayManifest}.
|
|
56
|
+
*/
|
|
57
|
+
/**
|
|
58
|
+
* The filename {@linkcode assembleOverlayManifest} writes its plan under, beside `MANIFEST.json`.
|
|
59
|
+
*/
|
|
60
|
+
export declare const OVERLAY_PLAN_FILE = "OVERLAY_PLAN.json";
|
|
61
|
+
/**
|
|
62
|
+
* What one overlay assembly was asked to add, written beside the manifest it produced.
|
|
63
|
+
*
|
|
64
|
+
* The next assembly on the same base reads this rather than reconstructing the file list.
|
|
65
|
+
* Reconstruction makes it possible for an overlay to contain a stale list of
|
|
66
|
+
* files into a later corpus version.
|
|
67
|
+
*/
|
|
68
|
+
export interface OverlayPlan {
|
|
69
|
+
corpusVersion: string;
|
|
70
|
+
overlayBase: string | null;
|
|
71
|
+
baseManifest: string;
|
|
72
|
+
modalRoot: string;
|
|
73
|
+
note: string;
|
|
74
|
+
appliedAt: string;
|
|
75
|
+
/**
|
|
76
|
+
* Each added file with the route its split came from.
|
|
77
|
+
*
|
|
78
|
+
* `route` reads `split-slice` when the filename includes the split suffix written by the command.
|
|
79
|
+
* `caller` reads the split supplied as an argument.
|
|
80
|
+
*
|
|
81
|
+
* A hand-placed split reached `v0.6.0-register-surface` through the second route
|
|
82
|
+
* and put 770 of DE's 3,987 validation `source_id`s in train.
|
|
83
|
+
* The filename was the only place that showed this (#2359).
|
|
84
|
+
*/
|
|
85
|
+
files: Array<{
|
|
86
|
+
parquet: string;
|
|
87
|
+
source: string;
|
|
88
|
+
split: SplitName;
|
|
89
|
+
route: SplitRoute;
|
|
90
|
+
}>;
|
|
91
|
+
}
|
|
92
|
+
/**
|
|
93
|
+
* How one overlay file's split was decided.
|
|
94
|
+
*/
|
|
95
|
+
export declare const SplitRoute: {
|
|
96
|
+
/**
|
|
97
|
+
* `corpus split-slice` applied `splitForRow` to every row and wrote the split into the filename.
|
|
98
|
+
*/
|
|
99
|
+
readonly SplitSlice: "split-slice";
|
|
100
|
+
/**
|
|
101
|
+
* The caller supplied the split.
|
|
102
|
+
* The holdout policy never saw these rows.
|
|
103
|
+
*/
|
|
104
|
+
readonly Caller: "caller";
|
|
105
|
+
};
|
|
106
|
+
export type SplitRoute = (typeof SplitRoute)[keyof typeof SplitRoute];
|
|
107
|
+
/**
|
|
108
|
+
* Which route decided one file's split.
|
|
109
|
+
*/
|
|
110
|
+
export declare function splitRouteFor(parquet: string): SplitRoute;
|
|
111
|
+
export interface OverlayManifestOptions {
|
|
112
|
+
base: string;
|
|
113
|
+
newDir: PathBuilderLike;
|
|
114
|
+
modalRoot: string;
|
|
115
|
+
version: string;
|
|
116
|
+
/**
|
|
117
|
+
* The parquet files to add, in the order in which they follow the base files.
|
|
118
|
+
*/
|
|
119
|
+
files: readonly OverlayFile[];
|
|
120
|
+
note: string;
|
|
121
|
+
}
|
|
122
|
+
/**
|
|
123
|
+
* Rewrites a base manifest's file path to its location in the corpus tree mounted on Modal at `/data`.
|
|
124
|
+
*/
|
|
125
|
+
export declare function rerootBaseFilePath(path: string, baseManifestPath: string): string;
|
|
126
|
+
/**
|
|
127
|
+
* Maps a Modal path under `/data/` to the same file under the local data root
|
|
128
|
+
* and returns any other path unchanged.
|
|
129
|
+
*/
|
|
130
|
+
export declare function localManifestFilePath(path: string): string;
|
|
131
|
+
/**
|
|
132
|
+
* Writes a corpus manifest that keeps every file of `args.base` and appends `args.files`.
|
|
133
|
+
*
|
|
134
|
+
* A `val` or `test` file must use the `.<split>.parquet` suffix written by `splitOverlaySlice`.
|
|
135
|
+
* The suffix shows that the holdout policy chose its rows.
|
|
136
|
+
* A `train` file has no naming requirement.
|
|
137
|
+
*
|
|
138
|
+
* @throws When the base lists no files or a held-out file lacks the matching filename suffix.
|
|
139
|
+
*/
|
|
140
|
+
export declare function assembleOverlayManifest(args: OverlayManifestOptions): Promise<void>;
|
|
141
|
+
export {};
|
|
142
|
+
//# sourceMappingURL=manifest.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"manifest.d.ts","sourceRoot":"","sources":["../../../lib/tools/overlay/manifest.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAOH,OAAO,EAAkC,KAAK,eAAe,EAAE,MAAM,SAAS,CAAA;AAG9E,OAAO,KAAK,EAAE,SAAS,EAAE,MAAM,cAAc,CAAA;AAe7C,KAAK,YAAY,GAAG,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG;IAAE,IAAI,EAAE,MAAM,CAAC;IAAC,MAAM,CAAC,EAAE,MAAM,CAAA;CAAE,CAAA;AAE/E;;;;;;GAMG;AACH,QAAA,MAAM,oBAAoB,UAAyB,CAAA;AAenD;;;;;;GAMG;AACH,wBAAgB,iBAAiB,CAAC,QAAQ,EAAE;IAAE,MAAM,CAAC,EAAE,OAAO,CAAC;IAAC,CAAC,oBAAoB,CAAC,CAAC,EAAE,OAAO,CAAA;CAAE,GAAG,YAAY,EAAE,CAclH;AASD;;GAEG;AACH,MAAM,WAAW,WAAW;IAC3B,OAAO,EAAE,MAAM,CAAA;IACf,MAAM,EAAE,MAAM,CAAA;IACd;;;;;;OAMG;IACH,KAAK,CAAC,EAAE,SAAS,CAAA;CACjB;AAED;;;;GAIG;AACH,wBAAgB,iBAAiB,CAAC,OAAO,EAAE,MAAM,GAAG,SAAS,GAAG,IAAI,CAInE;AA4DD;;GAEG;AACH;;GAEG;AACH,eAAO,MAAM,iBAAiB,sBAAsB,CAAA;AAEpD;;;;;;GAMG;AACH,MAAM,WAAW,WAAW;IAC3B,aAAa,EAAE,MAAM,CAAA;IACrB,WAAW,EAAE,MAAM,GAAG,IAAI,CAAA;IAC1B,YAAY,EAAE,MAAM,CAAA;IACpB,SAAS,EAAE,MAAM,CAAA;IACjB,IAAI,EAAE,MAAM,CAAA;IACZ,SAAS,EAAE,MAAM,CAAA;IACjB;;;;;;;;;OASG;IACH,KAAK,EAAE,KAAK,CAAC;QAAE,OAAO,EAAE,MAAM,CAAC;QAAC,MAAM,EAAE,MAAM,CAAC;QAAC,KAAK,EAAE,SAAS,CAAC;QAAC,KAAK,EAAE,UAAU,CAAA;KAAE,CAAC,CAAA;CACtF;AAED;;GAEG;AACH,eAAO,MAAM,UAAU;IACtB;;OAEG;aACH,UAAU,EAAE,aAAa;IAEzB;;;OAGG;aACH,MAAM,EAAE,QAAQ;CACP,CAAA;AAEV,MAAM,MAAM,UAAU,GAAG,CAAC,OAAO,UAAU,CAAC,CAAC,MAAM,OAAO,UAAU,CAAC,CAAA;AAErE;;GAEG;AACH,wBAAgB,aAAa,CAAC,OAAO,EAAE,MAAM,GAAG,UAAU,CAEzD;AAED,MAAM,WAAW,sBAAsB;IACtC,IAAI,EAAE,MAAM,CAAA;IACZ,MAAM,EAAE,eAAe,CAAA;IACvB,SAAS,EAAE,MAAM,CAAA;IACjB,OAAO,EAAE,MAAM,CAAA;IACf;;OAEG;IACH,KAAK,EAAE,SAAS,WAAW,EAAE,CAAA;IAC7B,IAAI,EAAE,MAAM,CAAA;CACZ;AAED;;GAEG;AACH,wBAAgB,kBAAkB,CAAC,IAAI,EAAE,MAAM,EAAE,gBAAgB,EAAE,MAAM,GAAG,MAAM,CAajF;AAED;;;GAGG;AACH,wBAAgB,qBAAqB,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM,CAE1D;AAED;;;;;;;;GAQG;AACH,wBAAsB,uBAAuB,CAAC,IAAI,EAAE,sBAAsB,GAAG,OAAO,CAAC,IAAI,CAAC,CAiIzF"}
|