@mailwoman/corpus 10.0.0 → 10.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +120 -34
- 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 +791 -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 +31 -37
- package/lib/adapters/gleif/adapter.ts +829 -0
- package/lib/adapters/libpostal-dictionary.ts +37 -0
- package/lib/adapters/openaddresses/adapter.ts +52 -55
- package/lib/adapters/osm/adapter.ts +162 -83
- package/lib/adapters/overture/adapter.ts +52 -43
- package/lib/adapters/po-box/adapter.ts +207 -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 +136 -0
- package/lib/adapters/wof/admin/json/adapter.ts +50 -35
- package/lib/adapters/wof/json-rows.ts +57 -26
- package/lib/adapters/wof/postalcode-json/adapter.ts +63 -61
- package/lib/adapters.ts +230 -0
- package/lib/au/adapters/gnaf/adapter.ts +36 -44
- package/lib/au/adapters/gnaf/assemble.ts +31 -51
- package/lib/be/adapters/brussels/adapter.ts +566 -0
- package/lib/be/adapters/vlaanderen/adapter.ts +667 -0
- package/lib/be/adapters/wallonie/adapter.ts +537 -0
- package/lib/be/tools/fetch/brussels.ts +242 -0
- package/lib/be/tools/fetch/wallonie.ts +275 -0
- package/lib/build/adapters.ts +111 -0
- package/lib/build/align.ts +365 -0
- package/lib/build/checkpoint.ts +133 -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 +234 -0
- package/lib/build.ts +127 -315
- package/lib/cn/recipes/organizational-units.ts +20 -41
- package/lib/cz/adapters/cuzk/adapter.ts +320 -0
- package/lib/cz/recipes/pcfirst-preposition.ts +40 -27
- package/lib/cz/tools/fetch/cuzk.ts +710 -0
- package/lib/de/recipes/locale.ts +69 -59
- package/lib/directory.ts +31 -0
- package/lib/dk/adapters/inspire/adapter.ts +345 -0
- package/lib/dk/tools/fetch/inspire.ts +323 -0
- package/lib/ee/adapters/ads/adapter.ts +240 -0
- package/lib/ee/tools/fetch/ads.ts +272 -0
- package/lib/env.ts +6 -2
- package/lib/es/adapters/bizkaia/adapter.ts +388 -0
- package/lib/es/adapters/catastro/adapter.ts +345 -0
- package/lib/es/adapters/gipuzkoa/adapter.ts +256 -0
- package/lib/es/adapters/navarra/adapter.ts +290 -0
- package/lib/es/cadastre.ts +194 -0
- package/lib/es/tools/fetch/bizkaia.ts +752 -0
- package/lib/es/tools/fetch/catastro.ts +765 -0
- package/lib/es/tools/fetch/gipuzkoa.ts +338 -0
- package/lib/es/tools/fetch/navarra.ts +496 -0
- package/lib/fi/adapters/ryhti/adapter.ts +319 -0
- package/lib/fi/tools/fetch/ryhti.ts +476 -0
- package/lib/fingerprints.ts +154 -0
- package/lib/fr/adapters/annuaire-education/adapter.ts +600 -0
- package/lib/fr/adapters/ban/adapter.ts +87 -59
- package/lib/fr/adapters/finess/adapter.ts +619 -0
- package/lib/fr/adapters/finess/postal-lines.ts +157 -0
- package/lib/fr/adapters/finess/voie-type.ts +201 -0
- package/lib/fr/insee-country.ts +62 -0
- package/lib/fr/recipes/admin-split.ts +38 -60
- package/lib/fr/recipes/bare-street.ts +37 -50
- package/lib/fr/recipes/fragment.ts +59 -142
- package/lib/fr/recipes/lieudit.ts +111 -73
- package/lib/fr/recipes/order.ts +32 -59
- package/lib/fr/{adapters/ban/street-decompose.ts → street-decompose.ts} +4 -3
- package/lib/fr/tools/fetch/annuaire-education.ts +309 -0
- package/lib/fr/tools/fetch/ban.ts +30 -20
- package/lib/fr/tools/fetch/finess.ts +353 -0
- package/lib/gauntlet-inputs.ts +92 -0
- package/lib/index.ts +9 -3
- package/lib/inspire/address.ts +465 -0
- package/lib/inspire/archive.ts +44 -0
- package/lib/inspire/errors.ts +72 -0
- package/lib/inspire/stream.ts +265 -0
- package/lib/international/recipes/locale.ts +146 -184
- package/lib/it/adapters/anac/adapter.ts +527 -0
- package/lib/it/tools/fetch/anac.ts +391 -0
- package/lib/jp/adapters/wof-admin/adapter.ts +29 -23
- package/lib/jp/tools/fetch/houjin.ts +19 -21
- package/lib/kr/adapters/juso/label-rows.ts +24 -44
- package/lib/kr/adapters/localdata/align.ts +20 -31
- package/lib/kr/adapters/localdata/key-index.ts +17 -25
- package/lib/kr/adapters/localdata/permit-rows.ts +34 -27
- package/lib/kr/tools/fetch/juso.ts +19 -21
- package/lib/kr/tools/fetch/localdata.ts +29 -30
- package/lib/lu/adapters/bd-adresses/adapter.ts +240 -0
- package/lib/lu/tools/fetch/bd-adresses.ts +353 -0
- package/lib/lv/adapters/varis/adapter.ts +500 -0
- package/lib/lv/tools/fetch/varis.ts +215 -0
- package/lib/nl/adapters/kadaster/adapter.ts +386 -0
- package/lib/nl/recipes/postcode.ts +46 -24
- package/lib/nl/tools/fetch/kadaster.ts +302 -0
- package/lib/no/adapters/matrikkelen/adapter.ts +188 -0
- package/lib/no/recipes/fragment.ts +34 -58
- package/lib/no/recipes/street/led.ts +44 -25
- package/lib/no/recipes/{street/index.ts → street.ts} +29 -11
- package/lib/no/tools/fetch/matrikkelen.ts +531 -0
- package/lib/parquet/duckdb.ts +147 -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 +452 -0
- package/lib/pl/adapters/emuia/adapter.ts +202 -0
- package/lib/pl/tools/fetch/emuia.ts +361 -0
- package/lib/recipes/anchor-absorption.ts +30 -19
- package/lib/recipes/bare/country.ts +24 -32
- package/lib/recipes/bare/postcode/eval.ts +1 -1
- package/lib/recipes/bare/postcode.ts +346 -0
- package/lib/recipes/boundary-stress.ts +37 -20
- package/lib/recipes/country-balanced.ts +66 -86
- package/lib/recipes/house-venue.ts +36 -14
- package/lib/recipes/intersection.ts +84 -62
- package/lib/recipes/po/box/cedex/au-nz.ts +3 -3
- package/lib/recipes/po/box/cedex/ca.ts +3 -2
- package/lib/recipes/po/box/cedex/fr.ts +4 -3
- package/lib/recipes/po/box/cedex/phrases.ts +7 -6
- package/lib/recipes/po/box/cedex/recipe.ts +31 -19
- package/lib/recipes/po/box/cedex/sources.ts +16 -4
- package/lib/recipes/po/box/cedex/us.ts +7 -2
- package/lib/recipes/po/{box/index.ts → box.ts} +39 -18
- package/lib/recipes/scaffold.ts +267 -158
- package/lib/recipes/sources.ts +412 -0
- package/lib/recipes/street/affix.ts +54 -154
- package/lib/recipes/street/bare.ts +30 -17
- package/lib/recipes/street.ts +35 -9
- package/lib/recipes/sub/venue/context.ts +32 -23
- package/lib/recipes/sub/venue/render.ts +170 -0
- package/lib/recipes/sub/venue/sources.ts +92 -248
- package/lib/recipes/sub/venue.ts +795 -0
- package/lib/recipes/trailing-region.ts +75 -87
- package/lib/recipes/unit/sources.ts +44 -0
- package/lib/recipes/unit.ts +101 -89
- package/lib/recipes/venue.ts +347 -0
- package/lib/{recipes/index.ts → recipes.ts} +15 -11
- package/lib/registers.ts +280 -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 +221 -84
- package/lib/sg/recipes/register.ts +47 -53
- package/lib/sg/tools/fetch/acra.ts +23 -28
- package/lib/si/recipes/bare-village.ts +34 -17
- package/lib/sk/adapters/inspire/adapter.ts +393 -0
- package/lib/sk/tools/fetch/inspire.ts +403 -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 +589 -0
- package/lib/source-register.ts +71 -0
- package/lib/south-asia/recipes/register.ts +45 -26
- package/lib/subvenue/harvest.ts +251 -0
- package/lib/{tools/sub/venue → subvenue}/promotions.ts +33 -70
- package/lib/subvenue/surfaces.ts +94 -0
- package/lib/subvenue/table.ts +264 -0
- package/lib/surfaces/locale.ts +248 -0
- package/lib/synthesizers/anchor-absorption.ts +56 -91
- package/lib/synthesizers/boundary-stress.ts +67 -155
- package/lib/synthesizers/house-venue.ts +65 -127
- package/lib/synthesizers/no-street.ts +71 -119
- package/lib/synthesizers/po-box.ts +93 -105
- package/lib/synthesizers/tail.ts +55 -0
- package/lib/synthesizers/utils.ts +82 -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 +117 -120
- package/lib/tools/corpus-stats.ts +45 -31
- package/lib/tools/fetch/atom.ts +164 -0
- package/lib/tools/fetch/cordis.ts +320 -0
- package/lib/tools/fetch/download/manifest.ts +36 -23
- package/lib/tools/fetch/download/network.ts +55 -31
- package/lib/tools/fetch/download/retry.ts +30 -29
- package/lib/tools/fetch/geonames/dump.ts +75 -55
- package/lib/tools/fetch/geonames/postal.ts +27 -62
- package/lib/tools/fetch/gleif.ts +362 -0
- package/lib/tools/fetch/header.ts +71 -0
- package/lib/tools/fetch/inspire-addresses.ts +500 -0
- package/lib/tools/fetch/openaddresses.ts +23 -112
- package/lib/tools/fetch/ourairports.ts +18 -51
- package/lib/tools/fetch/ppd.ts +10 -8
- package/lib/tools/fetch/vlaanderen-ad.ts +435 -0
- package/lib/tools/fetch/wfs-harvest.ts +954 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +45 -145
- package/lib/tools/fetch/zip-archive.ts +100 -0
- package/lib/tools/fetch.ts +101 -0
- package/lib/tools/golden/expand.ts +75 -44
- package/lib/tools/golden/promote.ts +47 -34
- package/lib/tools/golden/relabel-street/directory.ts +67 -39
- package/lib/tools/golden/relabel-street/row.ts +32 -109
- package/lib/tools/ingest-csv.ts +48 -51
- package/lib/tools/jsonl-to-parquet.ts +59 -98
- package/lib/tools/lint/recipe-output/vocab.ts +371 -0
- package/lib/tools/lint/{slice/index.ts → recipe-output.ts} +130 -126
- 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/{slice → overlay}/kryptonite.ts +47 -39
- package/lib/tools/overlay/manifest.ts +409 -0
- package/lib/tools/overlay/merge-source.ts +139 -0
- package/lib/tools/overlay/split-slice.ts +144 -0
- package/lib/tools/overlay/translit.ts +236 -0
- package/lib/tools/overture-subvenue.ts +18 -91
- package/lib/tools/postcode-triples.ts +284 -212
- package/lib/tools/source-register/build.ts +822 -0
- package/lib/tools/sub/venue/head-nouns.ts +38 -75
- package/lib/tools/sub/venue/lexicon.ts +71 -110
- package/lib/tools/sub/venue/wikidata.ts +13 -10
- package/lib/tw/tools/fetch/gcis.ts +21 -20
- package/lib/types.ts +305 -101
- package/lib/us/adapters/fcc-bdc/adapter.ts +26 -41
- package/lib/us/adapters/state/hi-schools/adapter.ts +28 -17
- package/lib/us/adapters/state/hi-schools/workbook.ts +8 -3
- package/lib/us/adapters/state/ia-contractors/adapter.ts +27 -15
- package/lib/us/adapters/state/ny-notaries/adapter.ts +24 -25
- package/lib/us/adapters/state/tx-notaries/adapter.ts +21 -15
- package/lib/us/adapters/tiger/adapter.ts +19 -44
- package/lib/us/adapters/tiger/street-decompose.ts +7 -17
- package/lib/us/adapters/usgov/hrsa-fqhc/adapter.ts +49 -34
- package/lib/us/adapters/usgov/imls-pls/adapter.ts +25 -19
- package/lib/us/adapters/usgov/irs-bmf/adapter.ts +32 -23
- package/lib/us/adapters/usgov/nad/adapter.ts +61 -122
- package/lib/us/adapters/usgov/nppes/adapter.ts +72 -35
- package/lib/us/adapters/usgov/samhsa-treatment-locator/adapter.ts +47 -34
- package/lib/us/fips-state.ts +19 -10
- package/lib/{synthesizers → us/synthesizers}/intersection.ts +45 -35
- package/lib/{synthesizers → us/synthesizers}/street.ts +56 -43
- package/lib/us/tools/fetch/hrsa.ts +7 -8
- package/lib/us/tools/fetch/imls-pls.ts +18 -36
- package/lib/us/tools/fetch/nad.ts +51 -33
- package/lib/us/tools/fetch/nppes.ts +27 -39
- package/lib/us/tools/fetch/state/hi-schools.ts +24 -17
- package/lib/us/tools/fetch/state/sources.ts +12 -12
- package/lib/us/tools/fetch/tiger-full.ts +22 -74
- package/lib/utils/align.ts +52 -59
- package/lib/utils/{slice-stats.ts → cooccurrence-stats.ts} +22 -16
- package/lib/utils/golden.ts +36 -51
- package/lib/utils/license.ts +239 -27
- package/lib/utils/split.ts +209 -88
- package/lib/utils/tokenize.ts +25 -56
- package/lib/utils/wof-json.ts +130 -77
- package/lib/{utils/index.ts → utils.ts} +0 -1
- package/lib/ve/recipes/reviewed-postcode-tail.ts +40 -13
- package/out/adapters/cordis/adapter.d.ts +326 -0
- package/out/adapters/cordis/adapter.d.ts.map +1 -0
- package/out/adapters/cordis/adapter.js +622 -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 +14 -27
- package/out/adapters/geonames/postal/adapter.d.ts.map +1 -1
- package/out/adapters/geonames/postal/adapter.js +30 -35
- package/out/adapters/geonames/postal/adapter.js.map +1 -1
- 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 +685 -0
- package/out/adapters/gleif/adapter.js.map +1 -0
- package/out/adapters/libpostal-dictionary.d.ts +20 -0
- package/out/adapters/libpostal-dictionary.d.ts.map +1 -0
- package/out/adapters/libpostal-dictionary.js +34 -0
- package/out/adapters/libpostal-dictionary.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts +29 -43
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -1
- package/out/adapters/openaddresses/adapter.js +34 -46
- package/out/adapters/openaddresses/adapter.js.map +1 -1
- package/out/adapters/osm/adapter.d.ts +59 -52
- package/out/adapters/osm/adapter.d.ts.map +1 -1
- package/out/adapters/osm/adapter.js +119 -69
- package/out/adapters/osm/adapter.js.map +1 -1
- package/out/adapters/overture/adapter.d.ts +11 -37
- package/out/adapters/overture/adapter.d.ts.map +1 -1
- package/out/adapters/overture/adapter.js +45 -42
- package/out/adapters/overture/adapter.js.map +1 -1
- package/out/adapters/po-box/adapter.d.ts +66 -0
- package/out/adapters/po-box/adapter.d.ts.map +1 -0
- package/out/adapters/{synth-po-box → po-box}/adapter.js +48 -47
- 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 +103 -0
- package/out/adapters/street-line.d.ts.map +1 -0
- package/out/adapters/street-line.js +118 -0
- package/out/adapters/street-line.js.map +1 -0
- package/out/adapters/wof/admin/json/adapter.d.ts +27 -18
- package/out/adapters/wof/admin/json/adapter.d.ts.map +1 -1
- package/out/adapters/wof/admin/json/adapter.js +48 -32
- package/out/adapters/wof/admin/json/adapter.js.map +1 -1
- package/out/adapters/wof/json-rows.d.ts +36 -19
- package/out/adapters/wof/json-rows.d.ts.map +1 -1
- package/out/adapters/wof/json-rows.js +35 -15
- package/out/adapters/wof/json-rows.js.map +1 -1
- package/out/adapters/wof/postalcode-json/adapter.d.ts +22 -38
- package/out/adapters/wof/postalcode-json/adapter.d.ts.map +1 -1
- package/out/adapters/wof/postalcode-json/adapter.js +60 -58
- package/out/adapters/wof/postalcode-json/adapter.js.map +1 -1
- 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 +15 -27
- package/out/au/adapters/gnaf/adapter.d.ts.map +1 -1
- package/out/au/adapters/gnaf/adapter.js +35 -43
- package/out/au/adapters/gnaf/adapter.js.map +1 -1
- package/out/au/adapters/gnaf/assemble.d.ts +15 -26
- package/out/au/adapters/gnaf/assemble.d.ts.map +1 -1
- package/out/au/adapters/gnaf/assemble.js +26 -46
- package/out/au/adapters/gnaf/assemble.js.map +1 -1
- 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 +230 -0
- package/out/be/adapters/vlaanderen/adapter.d.ts.map +1 -0
- package/out/be/adapters/vlaanderen/adapter.js +418 -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 +122 -0
- package/out/be/tools/fetch/brussels.d.ts.map +1 -0
- package/out/be/tools/fetch/brussels.js +148 -0
- package/out/be/tools/fetch/brussels.js.map +1 -0
- package/out/be/tools/fetch/wallonie.d.ts +120 -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 +69 -0
- package/out/build/adapters.js.map +1 -0
- package/out/build/align.d.ts +74 -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 +61 -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 +222 -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 +5 -22
- package/out/cn/recipes/organizational-units.d.ts.map +1 -1
- package/out/cn/recipes/organizational-units.js +20 -41
- package/out/cn/recipes/organizational-units.js.map +1 -1
- 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 +269 -0
- package/out/cz/adapters/cuzk/adapter.js.map +1 -0
- package/out/cz/recipes/pcfirst-preposition.d.ts +7 -11
- package/out/cz/recipes/pcfirst-preposition.d.ts.map +1 -1
- package/out/cz/recipes/pcfirst-preposition.js +36 -27
- package/out/cz/recipes/pcfirst-preposition.js.map +1 -1
- package/out/cz/tools/fetch/cuzk.d.ts +281 -0
- package/out/cz/tools/fetch/cuzk.d.ts.map +1 -0
- package/out/cz/tools/fetch/cuzk.js +448 -0
- package/out/cz/tools/fetch/cuzk.js.map +1 -0
- package/out/de/recipes/locale.d.ts +24 -26
- package/out/de/recipes/locale.d.ts.map +1 -1
- package/out/de/recipes/locale.js +67 -57
- package/out/de/recipes/locale.js.map +1 -1
- 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 +153 -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 +101 -0
- package/out/dk/tools/fetch/inspire.d.ts.map +1 -0
- package/out/dk/tools/fetch/inspire.js +232 -0
- package/out/dk/tools/fetch/inspire.js.map +1 -0
- package/out/ee/adapters/ads/adapter.d.ts +102 -0
- package/out/ee/adapters/ads/adapter.d.ts.map +1 -0
- package/out/ee/adapters/ads/adapter.js +185 -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 +197 -0
- package/out/ee/tools/fetch/ads.js.map +1 -0
- package/out/env.d.ts +6 -2
- 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 +103 -0
- package/out/es/adapters/catastro/adapter.d.ts.map +1 -0
- package/out/es/adapters/catastro/adapter.js +290 -0
- package/out/es/adapters/catastro/adapter.js.map +1 -0
- package/out/es/adapters/gipuzkoa/adapter.d.ts +84 -0
- package/out/es/adapters/gipuzkoa/adapter.d.ts.map +1 -0
- package/out/es/adapters/gipuzkoa/adapter.js +218 -0
- package/out/es/adapters/gipuzkoa/adapter.js.map +1 -0
- package/out/es/adapters/navarra/adapter.d.ts +106 -0
- package/out/es/adapters/navarra/adapter.d.ts.map +1 -0
- package/out/es/adapters/navarra/adapter.js +242 -0
- package/out/es/adapters/navarra/adapter.js.map +1 -0
- package/out/es/cadastre.d.ts +110 -0
- package/out/es/cadastre.d.ts.map +1 -0
- package/out/es/cadastre.js +128 -0
- package/out/es/cadastre.js.map +1 -0
- package/out/es/tools/fetch/bizkaia.d.ts +281 -0
- package/out/es/tools/fetch/bizkaia.d.ts.map +1 -0
- package/out/es/tools/fetch/bizkaia.js +478 -0
- package/out/es/tools/fetch/bizkaia.js.map +1 -0
- package/out/es/tools/fetch/catastro.d.ts +280 -0
- package/out/es/tools/fetch/catastro.d.ts.map +1 -0
- package/out/es/tools/fetch/catastro.js +491 -0
- package/out/es/tools/fetch/catastro.js.map +1 -0
- package/out/es/tools/fetch/gipuzkoa.d.ts +164 -0
- package/out/es/tools/fetch/gipuzkoa.d.ts.map +1 -0
- package/out/es/tools/fetch/gipuzkoa.js +210 -0
- package/out/es/tools/fetch/gipuzkoa.js.map +1 -0
- package/out/es/tools/fetch/navarra.d.ts +194 -0
- package/out/es/tools/fetch/navarra.d.ts.map +1 -0
- package/out/es/tools/fetch/navarra.js +321 -0
- package/out/es/tools/fetch/navarra.js.map +1 -0
- package/out/fi/adapters/ryhti/adapter.d.ts +111 -0
- package/out/fi/adapters/ryhti/adapter.d.ts.map +1 -0
- package/out/fi/adapters/ryhti/adapter.js +240 -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 +324 -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 +477 -0
- package/out/fr/adapters/annuaire-education/adapter.js.map +1 -0
- package/out/fr/adapters/ban/adapter.d.ts +19 -25
- package/out/fr/adapters/ban/adapter.d.ts.map +1 -1
- package/out/fr/adapters/ban/adapter.js +65 -54
- package/out/fr/adapters/ban/adapter.js.map +1 -1
- package/out/fr/adapters/finess/adapter.d.ts +277 -0
- package/out/fr/adapters/finess/adapter.d.ts.map +1 -0
- package/out/fr/adapters/finess/adapter.js +520 -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 +173 -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 +4 -27
- package/out/fr/recipes/admin-split.d.ts.map +1 -1
- package/out/fr/recipes/admin-split.js +36 -58
- package/out/fr/recipes/admin-split.js.map +1 -1
- package/out/fr/recipes/bare-street.d.ts +2 -17
- package/out/fr/recipes/bare-street.d.ts.map +1 -1
- package/out/fr/recipes/bare-street.js +35 -50
- package/out/fr/recipes/bare-street.js.map +1 -1
- package/out/fr/recipes/fragment.d.ts +6 -65
- package/out/fr/recipes/fragment.d.ts.map +1 -1
- package/out/fr/recipes/fragment.js +55 -135
- package/out/fr/recipes/fragment.js.map +1 -1
- package/out/fr/recipes/lieudit.d.ts +17 -19
- package/out/fr/recipes/lieudit.d.ts.map +1 -1
- package/out/fr/recipes/lieudit.js +89 -68
- package/out/fr/recipes/lieudit.js.map +1 -1
- package/out/fr/recipes/order.d.ts +4 -27
- package/out/fr/recipes/order.d.ts.map +1 -1
- package/out/fr/recipes/order.js +31 -58
- package/out/fr/recipes/order.js.map +1 -1
- package/out/fr/{adapters/ban/street-decompose.d.ts → street-decompose.d.ts} +3 -2
- package/out/fr/street-decompose.d.ts.map +1 -0
- package/out/fr/{adapters/ban/street-decompose.js → street-decompose.js} +4 -3
- package/out/fr/street-decompose.js.map +1 -0
- package/out/fr/tools/fetch/annuaire-education.d.ts +133 -0
- package/out/fr/tools/fetch/annuaire-education.d.ts.map +1 -0
- package/out/fr/tools/fetch/annuaire-education.js +198 -0
- package/out/fr/tools/fetch/annuaire-education.js.map +1 -0
- package/out/fr/tools/fetch/ban.d.ts +9 -7
- package/out/fr/tools/fetch/ban.d.ts.map +1 -1
- package/out/fr/tools/fetch/ban.js +29 -19
- package/out/fr/tools/fetch/ban.js.map +1 -1
- 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 +229 -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 +9 -3
- package/out/index.d.ts.map +1 -1
- package/out/index.js +9 -3
- package/out/index.js.map +1 -1
- package/out/inspire/address.d.ts +261 -0
- package/out/inspire/address.d.ts.map +1 -0
- package/out/inspire/address.js +395 -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 +56 -0
- package/out/inspire/errors.d.ts.map +1 -0
- package/out/inspire/errors.js +65 -0
- package/out/inspire/errors.js.map +1 -0
- package/out/inspire/stream.d.ts +140 -0
- package/out/inspire/stream.d.ts.map +1 -0
- package/out/inspire/stream.js +123 -0
- package/out/inspire/stream.js.map +1 -0
- package/out/international/recipes/locale.d.ts +40 -86
- package/out/international/recipes/locale.d.ts.map +1 -1
- package/out/international/recipes/locale.js +122 -157
- package/out/international/recipes/locale.js.map +1 -1
- package/out/it/adapters/anac/adapter.d.ts +269 -0
- package/out/it/adapters/anac/adapter.d.ts.map +1 -0
- package/out/it/adapters/anac/adapter.js +434 -0
- package/out/it/adapters/anac/adapter.js.map +1 -0
- package/out/it/tools/fetch/anac.d.ts +171 -0
- package/out/it/tools/fetch/anac.d.ts.map +1 -0
- package/out/it/tools/fetch/anac.js +269 -0
- package/out/it/tools/fetch/anac.js.map +1 -0
- package/out/jp/adapters/wof-admin/adapter.d.ts +14 -11
- package/out/jp/adapters/wof-admin/adapter.d.ts.map +1 -1
- package/out/jp/adapters/wof-admin/adapter.js +27 -16
- package/out/jp/adapters/wof-admin/adapter.js.map +1 -1
- package/out/jp/tools/fetch/houjin.d.ts +7 -4
- package/out/jp/tools/fetch/houjin.d.ts.map +1 -1
- package/out/jp/tools/fetch/houjin.js +17 -13
- package/out/jp/tools/fetch/houjin.js.map +1 -1
- package/out/kr/adapters/juso/label-rows.d.ts +17 -31
- package/out/kr/adapters/juso/label-rows.d.ts.map +1 -1
- package/out/kr/adapters/juso/label-rows.js +19 -41
- package/out/kr/adapters/juso/label-rows.js.map +1 -1
- package/out/kr/adapters/localdata/align.d.ts +4 -16
- package/out/kr/adapters/localdata/align.d.ts.map +1 -1
- package/out/kr/adapters/localdata/align.js +19 -30
- package/out/kr/adapters/localdata/align.js.map +1 -1
- package/out/kr/adapters/localdata/key-index.d.ts +13 -22
- package/out/kr/adapters/localdata/key-index.d.ts.map +1 -1
- package/out/kr/adapters/localdata/key-index.js +15 -21
- package/out/kr/adapters/localdata/key-index.js.map +1 -1
- package/out/kr/adapters/localdata/permit-rows.d.ts +21 -14
- package/out/kr/adapters/localdata/permit-rows.d.ts.map +1 -1
- package/out/kr/adapters/localdata/permit-rows.js +31 -26
- package/out/kr/adapters/localdata/permit-rows.js.map +1 -1
- package/out/kr/tools/fetch/juso.d.ts +11 -8
- package/out/kr/tools/fetch/juso.d.ts.map +1 -1
- package/out/kr/tools/fetch/juso.js +15 -14
- package/out/kr/tools/fetch/juso.js.map +1 -1
- package/out/kr/tools/fetch/localdata.d.ts +16 -9
- package/out/kr/tools/fetch/localdata.d.ts.map +1 -1
- package/out/kr/tools/fetch/localdata.js +24 -16
- package/out/kr/tools/fetch/localdata.js.map +1 -1
- 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 +165 -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 +284 -0
- package/out/lv/adapters/varis/adapter.d.ts.map +1 -0
- package/out/lv/adapters/varis/adapter.js +405 -0
- package/out/lv/adapters/varis/adapter.js.map +1 -0
- package/out/lv/tools/fetch/varis.d.ts +81 -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 +309 -0
- package/out/nl/adapters/kadaster/adapter.js.map +1 -0
- package/out/nl/recipes/postcode.d.ts +12 -14
- package/out/nl/recipes/postcode.d.ts.map +1 -1
- package/out/nl/recipes/postcode.js +42 -24
- package/out/nl/recipes/postcode.js.map +1 -1
- package/out/nl/tools/fetch/kadaster.d.ts +159 -0
- package/out/nl/tools/fetch/kadaster.d.ts.map +1 -0
- package/out/nl/tools/fetch/kadaster.js +182 -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 +1 -33
- package/out/no/recipes/fragment.d.ts.map +1 -1
- package/out/no/recipes/fragment.js +23 -57
- package/out/no/recipes/fragment.js.map +1 -1
- package/out/no/recipes/street/led.d.ts +9 -12
- package/out/no/recipes/street/led.d.ts.map +1 -1
- package/out/no/recipes/street/led.js +34 -24
- package/out/no/recipes/street/led.js.map +1 -1
- package/out/no/recipes/street.d.ts +19 -0
- package/out/no/recipes/street.d.ts.map +1 -0
- package/out/no/recipes/{street/index.js → street.js} +28 -12
- package/out/no/recipes/street.js.map +1 -0
- package/out/no/tools/fetch/matrikkelen.d.ts +263 -0
- package/out/no/tools/fetch/matrikkelen.d.ts.map +1 -0
- package/out/no/tools/fetch/matrikkelen.js +353 -0
- package/out/no/tools/fetch/matrikkelen.js.map +1 -0
- package/out/parquet/duckdb.d.ts +103 -0
- package/out/parquet/duckdb.d.ts.map +1 -0
- package/out/parquet/duckdb.js +93 -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 +252 -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 +166 -0
- package/out/pl/tools/fetch/emuia.d.ts.map +1 -0
- package/out/pl/tools/fetch/emuia.js +261 -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 +2 -20
- package/out/recipes/bare/country.d.ts.map +1 -1
- package/out/recipes/bare/country.js +20 -31
- package/out/recipes/bare/country.js.map +1 -1
- package/out/recipes/bare/postcode/eval.d.ts +1 -1
- package/out/recipes/bare/postcode/eval.js +1 -1
- package/out/recipes/bare/postcode.d.ts +41 -0
- package/out/recipes/bare/postcode.d.ts.map +1 -0
- package/out/recipes/bare/{postcode/index.js → postcode.js} +92 -80
- 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 +37 -20
- 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 +33 -14
- 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 +67 -55
- package/out/recipes/intersection.js.map +1 -1
- package/out/recipes/po/box/cedex/au-nz.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/au-nz.js +3 -3
- package/out/recipes/po/box/cedex/au-nz.js.map +1 -1
- package/out/recipes/po/box/cedex/ca.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/ca.js +2 -2
- package/out/recipes/po/box/cedex/ca.js.map +1 -1
- package/out/recipes/po/box/cedex/fr.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/fr.js +3 -3
- package/out/recipes/po/box/cedex/fr.js.map +1 -1
- package/out/recipes/po/box/cedex/phrases.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/phrases.js +7 -6
- package/out/recipes/po/box/cedex/phrases.js.map +1 -1
- package/out/recipes/po/box/cedex/recipe.d.ts +1 -1
- package/out/recipes/po/box/cedex/recipe.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/recipe.js +27 -16
- package/out/recipes/po/box/cedex/recipe.js.map +1 -1
- package/out/recipes/po/box/cedex/sources.d.ts +20 -14
- package/out/recipes/po/box/cedex/sources.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/sources.js +2 -2
- package/out/recipes/po/box/cedex/sources.js.map +1 -1
- package/out/recipes/po/box/cedex/us.d.ts.map +1 -1
- package/out/recipes/po/box/cedex/us.js +5 -2
- package/out/recipes/po/box/cedex/us.js.map +1 -1
- package/out/recipes/po/box.d.ts +18 -0
- package/out/recipes/po/box.d.ts.map +1 -0
- package/out/recipes/po/{box/index.js → box.js} +37 -19
- package/out/recipes/po/box.js.map +1 -0
- package/out/recipes/scaffold.d.ts +223 -141
- package/out/recipes/scaffold.d.ts.map +1 -1
- package/out/recipes/scaffold.js +75 -65
- 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 +361 -0
- package/out/recipes/sources.js.map +1 -0
- package/out/recipes/street/affix.d.ts +20 -50
- package/out/recipes/street/affix.d.ts.map +1 -1
- package/out/recipes/street/affix.js +45 -133
- package/out/recipes/street/affix.js.map +1 -1
- package/out/recipes/street/bare.d.ts +9 -7
- package/out/recipes/street/bare.d.ts.map +1 -1
- package/out/recipes/street/bare.js +27 -16
- package/out/recipes/street/bare.js.map +1 -1
- package/out/recipes/street.d.ts +6 -4
- package/out/recipes/street.d.ts.map +1 -1
- package/out/recipes/street.js +32 -9
- package/out/recipes/street.js.map +1 -1
- package/out/recipes/sub/venue/context.d.ts +12 -9
- package/out/recipes/sub/venue/context.d.ts.map +1 -1
- package/out/recipes/sub/venue/context.js +23 -17
- package/out/recipes/sub/venue/context.js.map +1 -1
- 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 +53 -93
- package/out/recipes/sub/venue/sources.d.ts.map +1 -1
- package/out/recipes/sub/venue/sources.js +57 -197
- package/out/recipes/sub/venue/sources.js.map +1 -1
- package/out/recipes/sub/venue.d.ts +173 -0
- package/out/recipes/sub/venue.d.ts.map +1 -0
- package/out/recipes/sub/venue.js +558 -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 +61 -86
- 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/venue.d.ts +119 -0
- package/out/recipes/venue.d.ts.map +1 -0
- package/out/recipes/venue.js +245 -0
- package/out/recipes/venue.js.map +1 -0
- package/out/recipes.d.ts +26 -0
- package/out/recipes.d.ts.map +1 -0
- package/out/{recipes/index.js → recipes.js} +16 -12
- package/out/recipes.js.map +1 -0
- package/out/registers.d.ts +279 -0
- package/out/registers.d.ts.map +1 -0
- package/out/registers.js +275 -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 +121 -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 +18 -32
- package/out/sg/recipes/register.d.ts.map +1 -1
- package/out/sg/recipes/register.js +45 -50
- package/out/sg/recipes/register.js.map +1 -1
- package/out/sg/tools/fetch/acra.d.ts +11 -14
- package/out/sg/tools/fetch/acra.d.ts.map +1 -1
- package/out/sg/tools/fetch/acra.js +18 -21
- package/out/sg/tools/fetch/acra.js.map +1 -1
- package/out/si/recipes/bare-village.d.ts +12 -13
- package/out/si/recipes/bare-village.d.ts.map +1 -1
- package/out/si/recipes/bare-village.js +31 -17
- package/out/si/recipes/bare-village.js.map +1 -1
- 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 +196 -0
- package/out/sk/tools/fetch/inspire.d.ts.map +1 -0
- package/out/sk/tools/fetch/inspire.js +281 -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 +538 -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 +20 -17
- package/out/south-asia/recipes/register.d.ts.map +1 -1
- package/out/south-asia/recipes/register.js +44 -24
- package/out/south-asia/recipes/register.js.map +1 -1
- 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/{tools/sub/venue → subvenue}/promotions.js +15 -55
- 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 +138 -0
- package/out/surfaces/locale.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +22 -30
- 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 +18 -49
- package/out/synthesizers/boundary-stress.d.ts.map +1 -1
- package/out/synthesizers/boundary-stress.js +45 -142
- package/out/synthesizers/boundary-stress.js.map +1 -1
- package/out/synthesizers/house-venue.d.ts +23 -25
- package/out/synthesizers/house-venue.d.ts.map +1 -1
- package/out/synthesizers/house-venue.js +47 -118
- package/out/synthesizers/house-venue.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 +48 -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/tail.d.ts +36 -0
- package/out/synthesizers/tail.d.ts.map +1 -0
- package/out/synthesizers/tail.js +32 -0
- package/out/synthesizers/tail.js.map +1 -0
- package/out/synthesizers/utils.d.ts +33 -129
- package/out/synthesizers/utils.d.ts.map +1 -1
- package/out/synthesizers/utils.js +71 -167
- 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 +19 -11
- package/out/tools/audit.d.ts.map +1 -1
- package/out/tools/audit.js +89 -97
- 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 +34 -30
- 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 +83 -0
- package/out/tools/fetch/atom.js.map +1 -0
- package/out/tools/fetch/cordis.d.ts +124 -0
- package/out/tools/fetch/cordis.d.ts.map +1 -0
- package/out/tools/fetch/cordis.js +210 -0
- package/out/tools/fetch/cordis.js.map +1 -0
- package/out/tools/fetch/download/manifest.d.ts +27 -18
- package/out/tools/fetch/download/manifest.d.ts.map +1 -1
- package/out/tools/fetch/download/manifest.js +22 -14
- package/out/tools/fetch/download/manifest.js.map +1 -1
- package/out/tools/fetch/download/network.d.ts +48 -27
- package/out/tools/fetch/download/network.d.ts.map +1 -1
- package/out/tools/fetch/download/network.js +26 -16
- package/out/tools/fetch/download/network.js.map +1 -1
- package/out/tools/fetch/download/retry.d.ts +16 -15
- package/out/tools/fetch/download/retry.d.ts.map +1 -1
- package/out/tools/fetch/download/retry.js +28 -28
- package/out/tools/fetch/download/retry.js.map +1 -1
- package/out/tools/fetch/{download/index.d.ts → download.d.ts} +1 -1
- package/out/tools/fetch/download.d.ts.map +1 -0
- package/out/tools/fetch/{download/index.js → download.js} +1 -1
- package/out/tools/fetch/download.js.map +1 -0
- package/out/tools/fetch/geonames/dump.d.ts +51 -32
- package/out/tools/fetch/geonames/dump.d.ts.map +1 -1
- package/out/tools/fetch/geonames/dump.js +54 -43
- package/out/tools/fetch/geonames/dump.js.map +1 -1
- package/out/tools/fetch/geonames/postal.d.ts +14 -49
- package/out/tools/fetch/geonames/postal.d.ts.map +1 -1
- package/out/tools/fetch/geonames/postal.js +17 -56
- package/out/tools/fetch/geonames/postal.js.map +1 -1
- package/out/tools/fetch/gleif.d.ts +138 -0
- package/out/tools/fetch/gleif.d.ts.map +1 -0
- package/out/tools/fetch/gleif.js +222 -0
- package/out/tools/fetch/gleif.js.map +1 -0
- package/out/tools/fetch/header.d.ts +43 -0
- package/out/tools/fetch/header.d.ts.map +1 -0
- package/out/tools/fetch/header.js +61 -0
- package/out/tools/fetch/header.js.map +1 -0
- package/out/tools/fetch/inspire-addresses.d.ts +254 -0
- package/out/tools/fetch/inspire-addresses.d.ts.map +1 -0
- package/out/tools/fetch/inspire-addresses.js +277 -0
- package/out/tools/fetch/inspire-addresses.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +1 -4
- package/out/tools/fetch/openaddresses.d.ts.map +1 -1
- package/out/tools/fetch/openaddresses.js +20 -99
- package/out/tools/fetch/openaddresses.js.map +1 -1
- package/out/tools/fetch/ourairports.d.ts +6 -33
- package/out/tools/fetch/ourairports.d.ts.map +1 -1
- package/out/tools/fetch/ourairports.js +14 -47
- 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 -7
- 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 +420 -0
- package/out/tools/fetch/wfs-harvest.d.ts.map +1 -0
- package/out/tools/fetch/wfs-harvest.js +525 -0
- package/out/tools/fetch/wfs-harvest.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +32 -100
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -1
- package/out/tools/fetch/wikidata-subvenue.js +27 -122
- 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 +99 -0
- package/out/tools/fetch.d.ts.map +1 -0
- package/out/tools/fetch.js +95 -0
- package/out/tools/fetch.js.map +1 -0
- package/out/tools/golden/expand.d.ts +28 -13
- package/out/tools/golden/expand.d.ts.map +1 -1
- package/out/tools/golden/expand.js +51 -37
- package/out/tools/golden/expand.js.map +1 -1
- package/out/tools/golden/promote.d.ts +13 -8
- package/out/tools/golden/promote.d.ts.map +1 -1
- package/out/tools/golden/promote.js +38 -30
- package/out/tools/golden/promote.js.map +1 -1
- package/out/tools/golden/relabel-street/directory.d.ts +25 -10
- package/out/tools/golden/relabel-street/directory.d.ts.map +1 -1
- package/out/tools/golden/relabel-street/directory.js +44 -32
- package/out/tools/golden/relabel-street/directory.js.map +1 -1
- package/out/tools/golden/relabel-street/row.d.ts +18 -69
- package/out/tools/golden/relabel-street/row.d.ts.map +1 -1
- package/out/tools/golden/relabel-street/row.js +19 -77
- package/out/tools/golden/relabel-street/row.js.map +1 -1
- package/out/tools/golden/{relabel-street/index.d.ts → relabel-street.d.ts} +1 -1
- package/out/tools/golden/relabel-street.d.ts.map +1 -0
- package/out/tools/golden/{relabel-street/index.js → relabel-street.js} +1 -1
- 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 +42 -46
- 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 +82 -0
- package/out/tools/lint/recipe-output/vocab.d.ts.map +1 -0
- package/out/tools/lint/{slice → recipe-output}/vocab.js +54 -69
- 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/{slice/index.js → recipe-output.js} +93 -96
- 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/{slice → overlay}/kryptonite.js +39 -29
- package/out/tools/overlay/kryptonite.js.map +1 -0
- package/out/tools/overlay/manifest.d.ts +143 -0
- package/out/tools/overlay/manifest.d.ts.map +1 -0
- package/out/tools/overlay/manifest.js +261 -0
- package/out/tools/overlay/manifest.js.map +1 -0
- package/out/tools/overlay/merge-source.d.ts +74 -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 +55 -0
- package/out/tools/overlay/translit.d.ts.map +1 -0
- package/out/tools/{slice → overlay}/translit.js +61 -49
- 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 +78 -127
- package/out/tools/postcode-triples.d.ts.map +1 -1
- package/out/tools/postcode-triples.js +200 -193
- package/out/tools/postcode-triples.js.map +1 -1
- package/out/tools/source-register/build.d.ts +147 -0
- package/out/tools/source-register/build.d.ts.map +1 -0
- package/out/tools/source-register/build.js +517 -0
- package/out/tools/source-register/build.js.map +1 -0
- package/out/tools/sub/venue/head-nouns.d.ts +9 -38
- package/out/tools/sub/venue/head-nouns.d.ts.map +1 -1
- package/out/tools/sub/venue/head-nouns.js +37 -74
- package/out/tools/sub/venue/head-nouns.js.map +1 -1
- package/out/tools/sub/venue/lexicon.d.ts +53 -84
- package/out/tools/sub/venue/lexicon.d.ts.map +1 -1
- package/out/tools/sub/venue/lexicon.js +42 -90
- package/out/tools/sub/venue/lexicon.js.map +1 -1
- package/out/tools/sub/venue/wikidata.d.ts +8 -6
- package/out/tools/sub/venue/wikidata.d.ts.map +1 -1
- package/out/tools/sub/venue/wikidata.js +12 -9
- package/out/tools/sub/venue/wikidata.js.map +1 -1
- package/out/tw/tools/fetch/gcis.d.ts +9 -3
- package/out/tw/tools/fetch/gcis.d.ts.map +1 -1
- package/out/tw/tools/fetch/gcis.js +19 -13
- package/out/tw/tools/fetch/gcis.js.map +1 -1
- package/out/types.d.ts +271 -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 +18 -36
- package/out/us/adapters/fcc-bdc/adapter.d.ts.map +1 -1
- package/out/us/adapters/fcc-bdc/adapter.js +25 -38
- package/out/us/adapters/fcc-bdc/adapter.js.map +1 -1
- package/out/us/adapters/state/hi-schools/adapter.d.ts +12 -11
- package/out/us/adapters/state/hi-schools/adapter.d.ts.map +1 -1
- package/out/us/adapters/state/hi-schools/adapter.js +26 -16
- package/out/us/adapters/state/hi-schools/adapter.js.map +1 -1
- package/out/us/adapters/state/hi-schools/workbook.d.ts +8 -3
- package/out/us/adapters/state/hi-schools/workbook.d.ts.map +1 -1
- package/out/us/adapters/state/hi-schools/workbook.js +3 -1
- package/out/us/adapters/state/hi-schools/workbook.js.map +1 -1
- package/out/us/adapters/state/ia-contractors/adapter.d.ts +13 -6
- package/out/us/adapters/state/ia-contractors/adapter.d.ts.map +1 -1
- package/out/us/adapters/state/ia-contractors/adapter.js +27 -14
- package/out/us/adapters/state/ia-contractors/adapter.js.map +1 -1
- package/out/us/adapters/state/ny-notaries/adapter.d.ts +7 -6
- package/out/us/adapters/state/ny-notaries/adapter.d.ts.map +1 -1
- package/out/us/adapters/state/ny-notaries/adapter.js +24 -22
- package/out/us/adapters/state/ny-notaries/adapter.js.map +1 -1
- package/out/us/adapters/state/tx-notaries/adapter.d.ts +8 -7
- package/out/us/adapters/state/tx-notaries/adapter.d.ts.map +1 -1
- package/out/us/adapters/state/tx-notaries/adapter.js +21 -14
- package/out/us/adapters/state/tx-notaries/adapter.js.map +1 -1
- package/out/us/adapters/tiger/adapter.d.ts +10 -34
- package/out/us/adapters/tiger/adapter.d.ts.map +1 -1
- package/out/us/adapters/tiger/adapter.js +18 -42
- package/out/us/adapters/tiger/adapter.js.map +1 -1
- package/out/us/adapters/tiger/street-decompose.d.ts +6 -13
- package/out/us/adapters/tiger/street-decompose.d.ts.map +1 -1
- package/out/us/adapters/tiger/street-decompose.js +7 -17
- package/out/us/adapters/tiger/street-decompose.js.map +1 -1
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts +26 -20
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.js +41 -29
- package/out/us/adapters/usgov/hrsa-fqhc/adapter.js.map +1 -1
- package/out/us/adapters/usgov/imls-pls/adapter.d.ts +8 -7
- package/out/us/adapters/usgov/imls-pls/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/imls-pls/adapter.js +25 -18
- package/out/us/adapters/usgov/imls-pls/adapter.js.map +1 -1
- package/out/us/adapters/usgov/irs-bmf/adapter.d.ts +11 -10
- package/out/us/adapters/usgov/irs-bmf/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/irs-bmf/adapter.js +32 -22
- package/out/us/adapters/usgov/irs-bmf/adapter.js.map +1 -1
- package/out/us/adapters/usgov/nad/adapter.d.ts +11 -31
- package/out/us/adapters/usgov/nad/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/nad/adapter.js +57 -111
- package/out/us/adapters/usgov/nad/adapter.js.map +1 -1
- package/out/us/adapters/usgov/nppes/adapter.d.ts +12 -22
- package/out/us/adapters/usgov/nppes/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/nppes/adapter.js +62 -32
- package/out/us/adapters/usgov/nppes/adapter.js.map +1 -1
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts +16 -15
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.d.ts.map +1 -1
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js +38 -28
- package/out/us/adapters/usgov/samhsa-treatment-locator/adapter.js.map +1 -1
- package/out/us/fips-state.d.ts +19 -10
- package/out/us/fips-state.d.ts.map +1 -1
- package/out/us/fips-state.js +17 -8
- package/out/us/fips-state.js.map +1 -1
- package/out/{synthesizers → us/synthesizers}/intersection.d.ts +10 -8
- package/out/us/synthesizers/intersection.d.ts.map +1 -0
- package/out/{synthesizers → us/synthesizers}/intersection.js +46 -35
- package/out/us/synthesizers/intersection.js.map +1 -0
- package/out/{synthesizers → us/synthesizers}/street.d.ts +19 -12
- package/out/us/synthesizers/street.d.ts.map +1 -0
- package/out/{synthesizers → us/synthesizers}/street.js +45 -38
- package/out/us/synthesizers/street.js.map +1 -0
- package/out/us/tools/fetch/hrsa.d.ts +3 -3
- package/out/us/tools/fetch/hrsa.d.ts.map +1 -1
- package/out/us/tools/fetch/hrsa.js +6 -7
- package/out/us/tools/fetch/hrsa.js.map +1 -1
- package/out/us/tools/fetch/imls-pls.d.ts +5 -16
- package/out/us/tools/fetch/imls-pls.d.ts.map +1 -1
- package/out/us/tools/fetch/imls-pls.js +17 -34
- package/out/us/tools/fetch/imls-pls.js.map +1 -1
- package/out/us/tools/fetch/nad.d.ts +22 -10
- package/out/us/tools/fetch/nad.d.ts.map +1 -1
- package/out/us/tools/fetch/nad.js +30 -25
- package/out/us/tools/fetch/nad.js.map +1 -1
- package/out/us/tools/fetch/nppes.d.ts +6 -16
- package/out/us/tools/fetch/nppes.d.ts.map +1 -1
- package/out/us/tools/fetch/nppes.js +24 -36
- package/out/us/tools/fetch/nppes.js.map +1 -1
- package/out/us/tools/fetch/state/hi-schools.d.ts +9 -5
- package/out/us/tools/fetch/state/hi-schools.d.ts.map +1 -1
- package/out/us/tools/fetch/state/hi-schools.js +16 -14
- package/out/us/tools/fetch/state/hi-schools.js.map +1 -1
- package/out/us/tools/fetch/state/sources.d.ts +8 -7
- package/out/us/tools/fetch/state/sources.d.ts.map +1 -1
- package/out/us/tools/fetch/state/sources.js +8 -9
- package/out/us/tools/fetch/state/sources.js.map +1 -1
- package/out/us/tools/fetch/tiger-full.d.ts +1 -14
- package/out/us/tools/fetch/tiger-full.d.ts.map +1 -1
- package/out/us/tools/fetch/tiger-full.js +16 -55
- package/out/us/tools/fetch/tiger-full.js.map +1 -1
- package/out/utils/align.d.ts +26 -19
- package/out/utils/align.d.ts.map +1 -1
- package/out/utils/align.js +32 -47
- 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 +21 -31
- package/out/utils/golden.d.ts.map +1 -1
- package/out/utils/golden.js +30 -46
- package/out/utils/golden.js.map +1 -1
- package/out/utils/license.d.ts +159 -22
- 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 +162 -69
- package/out/utils/split.js.map +1 -1
- package/out/utils/tokenize.d.ts +15 -44
- 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 +77 -56
- package/out/utils/wof-json.js.map +1 -1
- package/out/{utils/index.js → utils.d.ts} +1 -2
- package/out/utils.d.ts.map +1 -0
- package/out/{utils/index.d.ts → utils.js} +1 -2
- package/out/utils.js.map +1 -0
- package/out/ve/recipes/reviewed-postcode-tail.d.ts +25 -7
- package/out/ve/recipes/reviewed-postcode-tail.d.ts.map +1 -1
- package/out/ve/recipes/reviewed-postcode-tail.js +33 -12
- package/out/ve/recipes/reviewed-postcode-tail.js.map +1 -1
- package/package.json +45 -488
- package/lib/adapters/index.ts +0 -160
- package/lib/adapters/synth-po-box/adapter.ts +0 -204
- package/lib/adapters/utils/index.ts +0 -307
- package/lib/recipes/bare/postcode/index.ts +0 -327
- package/lib/recipes/sub/venue/index.ts +0 -997
- package/lib/synthesizers/locale.ts +0 -261
- package/lib/test-kit/index.ts +0 -100
- package/lib/tools/align-slice.ts +0 -68
- package/lib/tools/fetch/index.ts +0 -174
- package/lib/tools/gb-title-case.ts +0 -69
- package/lib/tools/index.ts +0 -28
- package/lib/tools/lint/slice/vocab.ts +0 -376
- package/lib/tools/overlay-manifest.ts +0 -215
- package/lib/tools/slice/translit.ts +0 -218
- package/lib/tools/sub/venue/harvest.ts +0 -234
- package/lib/tools/sub/venue/surfaces.ts +0 -95
- package/lib/tools/sub/venue/table.ts +0 -281
- package/lib/utils/parquet.ts +0 -582
- package/out/adapters/index.d.ts +0 -51
- package/out/adapters/index.d.ts.map +0 -1
- package/out/adapters/index.js +0 -97
- package/out/adapters/index.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.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/fr/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/fr/adapters/ban/street-decompose.js.map +0 -1
- package/out/no/recipes/street/index.d.ts +0 -18
- package/out/no/recipes/street/index.d.ts.map +0 -1
- package/out/no/recipes/street/index.js.map +0 -1
- package/out/recipes/bare/postcode/index.d.ts +0 -62
- package/out/recipes/bare/postcode/index.d.ts.map +0 -1
- package/out/recipes/bare/postcode/index.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.map +0 -1
- package/out/recipes/po/box/index.d.ts +0 -17
- package/out/recipes/po/box/index.d.ts.map +0 -1
- package/out/recipes/po/box/index.js.map +0 -1
- package/out/recipes/sub/venue/index.d.ts +0 -270
- package/out/recipes/sub/venue/index.d.ts.map +0 -1
- package/out/recipes/sub/venue/index.js +0 -728
- package/out/recipes/sub/venue/index.js.map +0 -1
- package/out/synthesizers/intersection.d.ts.map +0 -1
- package/out/synthesizers/intersection.js.map +0 -1
- package/out/synthesizers/locale.d.ts +0 -116
- package/out/synthesizers/locale.d.ts.map +0 -1
- package/out/synthesizers/locale.js +0 -150
- package/out/synthesizers/locale.js.map +0 -1
- package/out/synthesizers/street.d.ts.map +0 -1
- package/out/synthesizers/street.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/download/index.d.ts.map +0 -1
- package/out/tools/fetch/download/index.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/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/relabel-street/index.d.ts.map +0 -1
- package/out/tools/golden/relabel-street/index.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/index.d.ts +0 -93
- package/out/tools/lint/slice/index.d.ts.map +0 -1
- package/out/tools/lint/slice/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.map +0 -1
- package/out/tools/overlay-manifest.d.ts +0 -89
- package/out/tools/overlay-manifest.d.ts.map +0 -1
- package/out/tools/overlay-manifest.js +0 -131
- 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.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.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/promotions.d.ts +0 -94
- package/out/tools/sub/venue/promotions.d.ts.map +0 -1
- package/out/tools/sub/venue/promotions.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/utils/index.d.ts.map +0 -1
- 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
- /package/lib/tools/fetch/{download/index.ts → download.ts} +0 -0
- /package/lib/tools/golden/{relabel-street/index.ts → relabel-street.ts} +0 -0
|
@@ -0,0 +1,355 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
* @file What reached the trainer, as distinct from what the corpus holds.
|
|
6
|
+
*
|
|
7
|
+
* `freezeTrainingManifest` records the sources that contributed rows to a corpus. A run reads that
|
|
8
|
+
* corpus through a config. Four stages between them remove rows: `country_weights` rejects a row
|
|
9
|
+
* whose country it does not list. `source_weights` draws only the sources it lists. A source set to `0.0`
|
|
10
|
+
* is drawn zero times. `augment_exclude_sources` withholds a source from augmentation. A model card
|
|
11
|
+
* quoting the corpus manifest therefore attributes sources the checkpoint never saw.
|
|
12
|
+
*
|
|
13
|
+
* Measured over `v0.6.0-register-surface` with `v6.0.0-register-surface-60k.yaml` on 2026-09-28: the corpus's
|
|
14
|
+
* frozen manifest names 11 sources. The audited epoch emitted 9 of those sources and 48 sources
|
|
15
|
+
* in total. The config admits 136 countries. Forty countries drew rows, so 96 admitted countries drew zero of
|
|
16
|
+
* the 1,000,000 rows the epoch emitted.
|
|
17
|
+
*
|
|
18
|
+
* **What this establishes and what it does not.** The counts come from one audited epoch at one seed.
|
|
19
|
+
* A source drawn zero times here is one the sampler did not reach in that epoch. The measurement does not show
|
|
20
|
+
* that no epoch can reach it. The audit reports its seed and draw count. This record stores both. A source the corpus holds
|
|
21
|
+
* and the config omits is excluded by construction. The record reports that exclusion instead of a zero draw.
|
|
22
|
+
*/
|
|
23
|
+
import { dataRootPath } from "@mailwoman/core/data-root";
|
|
24
|
+
import { sha256Hex } from "@mailwoman/core/hash";
|
|
25
|
+
import { stringifyJSON } from "@mailwoman/core/json";
|
|
26
|
+
import { LicenseObligation, summarizeLicense } from "@mailwoman/core/license/obligations";
|
|
27
|
+
import { OSM_ATTRIBUTION, OSM_LICENSE } from "#adapters/osm/adapter";
|
|
28
|
+
/**
|
|
29
|
+
* Where an `audit_epoch_mixture --json` output for one config is looked for.
|
|
30
|
+
*
|
|
31
|
+
* Under the data root rather than committed because the file is a measurement of one
|
|
32
|
+
* corpus at one seed and takes about ten minutes to produce.
|
|
33
|
+
* The config determines the filename so two training arms' audits stay apart.
|
|
34
|
+
*
|
|
35
|
+
* This avoids the mismatch {@linkcode deriveEffectiveTrainingManifest} refuses.
|
|
36
|
+
*/
|
|
37
|
+
export function epochMixtureAuditPath(configPath) {
|
|
38
|
+
const name = configPath
|
|
39
|
+
.split("/")
|
|
40
|
+
.at(-1)
|
|
41
|
+
?.replace(/\.ya?ml$/u, "") ?? configPath;
|
|
42
|
+
return dataRootPath("corpus", "epoch-mixture", `${name}.json`);
|
|
43
|
+
}
|
|
44
|
+
/**
|
|
45
|
+
* Why a source the corpus holds contributed no row to the audited epoch.
|
|
46
|
+
*/
|
|
47
|
+
export const ExclusionReason = {
|
|
48
|
+
/**
|
|
49
|
+
* The config's `source_weights` map does not name the source, so the sampler never considers it.
|
|
50
|
+
*/
|
|
51
|
+
UnweightedSource: "unweighted-source",
|
|
52
|
+
/**
|
|
53
|
+
* `source_weights` names the source at `0.0`.
|
|
54
|
+
*/
|
|
55
|
+
ZeroWeight: "zero-weight",
|
|
56
|
+
/**
|
|
57
|
+
* The source is weighted and the audited epoch drew zero of its rows.
|
|
58
|
+
*
|
|
59
|
+
* This is a statement about one seed and one epoch length rather than about the source.
|
|
60
|
+
*/
|
|
61
|
+
DrewZeroRows: "drew-zero-rows",
|
|
62
|
+
};
|
|
63
|
+
/**
|
|
64
|
+
* Which stage of the draw chain a manifest's row counts come from.
|
|
65
|
+
*
|
|
66
|
+
* The chain runs eligible rows, requested mixture, expected draws, realized draws, checkpoint.
|
|
67
|
+
* A manifest records the last stage it could read, and a reader treats an earlier
|
|
68
|
+
* stage as an estimate of the later ones rather than as the fact.
|
|
69
|
+
*/
|
|
70
|
+
export const DrawEvidence = {
|
|
71
|
+
/**
|
|
72
|
+
* The epoch-mixture audit replays epoch 1 of the sampler with the trainer's seed.
|
|
73
|
+
*
|
|
74
|
+
* It reconstructs the draw.
|
|
75
|
+
* The trainer's own count is {@link DrawEvidence.TrainerLogged}.
|
|
76
|
+
*/
|
|
77
|
+
ReplayedEpochAudit: "replayed-epoch-audit",
|
|
78
|
+
/**
|
|
79
|
+
* The trainer's `exposure-realized-from-<step>.json`, which counts the rows of every batch it trained on.
|
|
80
|
+
*/
|
|
81
|
+
TrainerLogged: "trainer-logged",
|
|
82
|
+
};
|
|
83
|
+
/**
|
|
84
|
+
* Recorded attribution statements, keyed by license.
|
|
85
|
+
*
|
|
86
|
+
* A license appears here only when one statement covers every source carrying it.
|
|
87
|
+
* OSM's statement covers every OSM-derived row.
|
|
88
|
+
*
|
|
89
|
+
* A CC BY source credits its own publisher, so its statement comes from the register.
|
|
90
|
+
*/
|
|
91
|
+
const ATTRIBUTION_STATEMENTS = {
|
|
92
|
+
[OSM_LICENSE]: OSM_ATTRIBUTION,
|
|
93
|
+
};
|
|
94
|
+
/**
|
|
95
|
+
* The attributions owed by the sources that reached the trainer, grouped by license.
|
|
96
|
+
*
|
|
97
|
+
* Only `trainingSources` are read, so a source the corpus holds and the run never drew owes no attribution.
|
|
98
|
+
* A license is included when `summarizeLicense` records an attribution obligation for it, or
|
|
99
|
+
* when it is unrecognized, since an unrecognized license's obligations are unknown rather than absent.
|
|
100
|
+
*/
|
|
101
|
+
export function requiredAttributions(sources) {
|
|
102
|
+
const byLicense = new Map();
|
|
103
|
+
for (const record of sources) {
|
|
104
|
+
if (record.emittedRows <= 0)
|
|
105
|
+
continue;
|
|
106
|
+
const summary = summarizeLicense(record.license);
|
|
107
|
+
if (summary.recognized && !summary.obligations.includes(LicenseObligation.Attribution))
|
|
108
|
+
continue;
|
|
109
|
+
byLicense.set(record.license, [...(byLicense.get(record.license) ?? []), record.source]);
|
|
110
|
+
}
|
|
111
|
+
return [...byLicense]
|
|
112
|
+
.toSorted(([a], [b]) => a.localeCompare(b))
|
|
113
|
+
.map(([license, licensed]) => ({
|
|
114
|
+
license,
|
|
115
|
+
sources: licensed.toSorted(),
|
|
116
|
+
statement: ATTRIBUTION_STATEMENTS[license] ?? null,
|
|
117
|
+
}));
|
|
118
|
+
}
|
|
119
|
+
/**
|
|
120
|
+
* Read `data.source_weights` and `data.augment_exclude_sources` from a training config.
|
|
121
|
+
*
|
|
122
|
+
* A line scanner instead of a YAML parse.
|
|
123
|
+
* `corpus audit` already reads these blocks this way.
|
|
124
|
+
*
|
|
125
|
+
* The `wire-identifiers` check uses the same approach.
|
|
126
|
+
* The configs use a small hand-written subset: two-space indentation, one entry per line and `#` comments.
|
|
127
|
+
* They contain no flow syntax.
|
|
128
|
+
*
|
|
129
|
+
* YAML 1.1 coerces the bare key `NO` to boolean false.
|
|
130
|
+
* Norway is a `country_weights` key, so a parser would drop it.
|
|
131
|
+
*
|
|
132
|
+
* @throws When the text contains no `source_weights` block.
|
|
133
|
+
* That map decides which sources the sampler considers.
|
|
134
|
+
* A config without one is a truncated file rather than a config drawing from every source.
|
|
135
|
+
*/
|
|
136
|
+
export function readConfigView(text) {
|
|
137
|
+
const sourceWeights = {};
|
|
138
|
+
const augmentExcludeSources = [];
|
|
139
|
+
let field = null;
|
|
140
|
+
let fieldIndent = -1;
|
|
141
|
+
let sawWeights = false;
|
|
142
|
+
// oxlint-disable-next-line mailwoman/prefer-spliterator -- one training config, a few hundred lines read whole
|
|
143
|
+
for (const raw of text.split("\n")) {
|
|
144
|
+
if (/^[\t ]*(#|$)/.test(raw))
|
|
145
|
+
continue;
|
|
146
|
+
const indent = /^[\t ]*/.exec(raw)[0].length;
|
|
147
|
+
if (field && indent <= fieldIndent) {
|
|
148
|
+
field = null;
|
|
149
|
+
}
|
|
150
|
+
if (!field) {
|
|
151
|
+
const opener = /^([\t ]*)(source_weights|augment_exclude_sources):\s*(#.*)?$/.exec(raw);
|
|
152
|
+
if (opener) {
|
|
153
|
+
field = opener[2];
|
|
154
|
+
fieldIndent = opener[1].length;
|
|
155
|
+
if (field === "source_weights") {
|
|
156
|
+
sawWeights = true;
|
|
157
|
+
}
|
|
158
|
+
}
|
|
159
|
+
continue;
|
|
160
|
+
}
|
|
161
|
+
if (field === "source_weights") {
|
|
162
|
+
const entry = /^[\t ]+([\w-]+):\s*([\d.]+)/.exec(raw);
|
|
163
|
+
if (entry) {
|
|
164
|
+
sourceWeights[entry[1]] = Number.parseFloat(entry[2]);
|
|
165
|
+
}
|
|
166
|
+
continue;
|
|
167
|
+
}
|
|
168
|
+
const item = /^[\t ]+-\s*([\w-]+)\s*(#.*)?$/.exec(raw);
|
|
169
|
+
if (item) {
|
|
170
|
+
augmentExcludeSources.push(item[1]);
|
|
171
|
+
}
|
|
172
|
+
}
|
|
173
|
+
if (!sawWeights) {
|
|
174
|
+
throw new Error("the config carries no `data.source_weights` block. That map decides which sources the sampler " +
|
|
175
|
+
"considers, so a config without one is a truncated file rather than a config drawing from every source.");
|
|
176
|
+
}
|
|
177
|
+
return { sourceWeights, augmentExcludeSources };
|
|
178
|
+
}
|
|
179
|
+
/**
|
|
180
|
+
* The digest a manifest should include, computed over the manifest with its digest field emptied.
|
|
181
|
+
*/
|
|
182
|
+
export function effectiveManifestDigest(manifest) {
|
|
183
|
+
return sha256Hex(stringifyJSON({ ...manifest, contentDigest: "" }));
|
|
184
|
+
}
|
|
185
|
+
/**
|
|
186
|
+
* Derive what reached the trainer from the corpus's frozen manifest, one audited epoch and the config.
|
|
187
|
+
*
|
|
188
|
+
* @throws When the audit contains no `emitted_level.totals`.
|
|
189
|
+
* That field answers the question.
|
|
190
|
+
* An audit without it is either a different report or a truncated one.
|
|
191
|
+
* A derivation from only `draw_level` would attribute rows augmentation removed.
|
|
192
|
+
* @throws When the audit ran under a different config file than the one supplied, because the two are
|
|
193
|
+
* two training arms and one record over both would report a source one of them never weighted.
|
|
194
|
+
*/
|
|
195
|
+
export function deriveEffectiveTrainingManifest(input) {
|
|
196
|
+
const emitted = input.audit.emitted_level?.totals;
|
|
197
|
+
if (!emitted) {
|
|
198
|
+
throw new Error("the audit carries no `emitted_level.totals`, which is the field that says what reached the trainer. " +
|
|
199
|
+
"Deriving from `draw_level` alone would attribute the rows augmentation removed.");
|
|
200
|
+
}
|
|
201
|
+
const audited = input.audit.meta?.config?.split("/").at(-1);
|
|
202
|
+
const wanted = input.configPath.split("/").at(-1);
|
|
203
|
+
if (audited && wanted && audited !== wanted) {
|
|
204
|
+
throw new Error(`the audit ran under ${audited} and the config supplied is ${wanted}. Those are two training arms, and ` +
|
|
205
|
+
`one record over both would report a source one of them never weighted.`);
|
|
206
|
+
}
|
|
207
|
+
const drawn = input.audit.draw_level?.totals ?? {};
|
|
208
|
+
const admittedDrawn = input.audit.draw_level?.admitted_countries_drawn ?? {};
|
|
209
|
+
const drawingZero = input.audit.draw_level?.admitted_countries_drawing_nothing ?? [];
|
|
210
|
+
const augmentExcluded = new Set(input.config.augmentExcludeSources);
|
|
211
|
+
const sources = input.corpusManifest.sources.map((record) => {
|
|
212
|
+
const weight = Object.hasOwn(input.config.sourceWeights, record.source)
|
|
213
|
+
? input.config.sourceWeights[record.source]
|
|
214
|
+
: null;
|
|
215
|
+
const drawnRows = drawn[record.source] ?? 0;
|
|
216
|
+
const emittedRows = emitted[record.source] ?? 0;
|
|
217
|
+
const excludedBecause = emittedRows > 0
|
|
218
|
+
? null
|
|
219
|
+
: weight === null
|
|
220
|
+
? ExclusionReason.UnweightedSource
|
|
221
|
+
: weight === 0
|
|
222
|
+
? ExclusionReason.ZeroWeight
|
|
223
|
+
: ExclusionReason.DrewZeroRows;
|
|
224
|
+
return {
|
|
225
|
+
source: record.source,
|
|
226
|
+
corpusRows: record.rows,
|
|
227
|
+
license: record.license,
|
|
228
|
+
weight,
|
|
229
|
+
drawnRows,
|
|
230
|
+
emittedRows,
|
|
231
|
+
augmentExcluded: augmentExcluded.has(record.source),
|
|
232
|
+
excludedBecause,
|
|
233
|
+
};
|
|
234
|
+
});
|
|
235
|
+
sources.sort((a, b) => b.emittedRows - a.emittedRows);
|
|
236
|
+
const excludedSources = {};
|
|
237
|
+
for (const record of sources) {
|
|
238
|
+
if (record.excludedBecause) {
|
|
239
|
+
excludedSources[record.source] = record.excludedBecause;
|
|
240
|
+
}
|
|
241
|
+
}
|
|
242
|
+
const recorded = new Set(input.corpusManifest.sources.map((record) => record.source));
|
|
243
|
+
const perSource = input.audit.draw_level?.per_source ?? {};
|
|
244
|
+
const emittedButUnrecorded = {};
|
|
245
|
+
const unrecordedSourceStages = {};
|
|
246
|
+
for (const [source, rows] of Object.entries(emitted)) {
|
|
247
|
+
if (rows > 0 && !recorded.has(source)) {
|
|
248
|
+
emittedButUnrecorded[source] = rows;
|
|
249
|
+
unrecordedSourceStages[source] = {
|
|
250
|
+
// `-1` records that the audit reported no corpus row count for this source.
|
|
251
|
+
// A 0 would say the corpus holds no row for this source.
|
|
252
|
+
// That contradicts its emitted rows.
|
|
253
|
+
corpusRows: perSource[source]?.rows ?? -1,
|
|
254
|
+
drawnRows: drawn[source] ?? 0,
|
|
255
|
+
emittedRows: rows,
|
|
256
|
+
};
|
|
257
|
+
}
|
|
258
|
+
}
|
|
259
|
+
const manifest = {
|
|
260
|
+
manifestID: "corpus-effective-training-manifest",
|
|
261
|
+
schemaVersion: 2,
|
|
262
|
+
drawEvidence: DrawEvidence.ReplayedEpochAudit,
|
|
263
|
+
labelSet: input.labelSet ?? null,
|
|
264
|
+
requiredAttributions: requiredAttributions(sources),
|
|
265
|
+
corpusVersion: input.corpusManifest.corpusVersion,
|
|
266
|
+
corpusManifestDigest: input.corpusManifest.contentDigest,
|
|
267
|
+
config: input.configPath,
|
|
268
|
+
seed: input.audit.meta?.seed ?? -1,
|
|
269
|
+
drawsRequested: input.audit.meta?.draws_requested ?? 0,
|
|
270
|
+
drawsRealized: input.audit.meta?.draws_realized ?? 0,
|
|
271
|
+
admittedCountries: Object.keys(admittedDrawn).length,
|
|
272
|
+
countriesDrawingRows: Object.values(admittedDrawn).filter((count) => count > 0).length,
|
|
273
|
+
admittedCountriesDrawingZero: [...drawingZero].toSorted(),
|
|
274
|
+
sources,
|
|
275
|
+
trainingSources: sources.filter((record) => record.emittedRows > 0).map((record) => record.source),
|
|
276
|
+
excludedSources,
|
|
277
|
+
emittedButUnrecorded,
|
|
278
|
+
unrecordedSourceStages,
|
|
279
|
+
totalEmittedRows: Object.values(emitted).reduce((sum, count) => sum + count, 0),
|
|
280
|
+
contentDigest: "",
|
|
281
|
+
};
|
|
282
|
+
return { ...manifest, contentDigest: effectiveManifestDigest(manifest) };
|
|
283
|
+
}
|
|
284
|
+
/**
|
|
285
|
+
* Sources a record declares as training data that the audited epoch never reached,
|
|
286
|
+
* plus the reverse mismatch.
|
|
287
|
+
*
|
|
288
|
+
* A release reads both directions.
|
|
289
|
+
* A declared source the checkpoint never saw overstates what the model learned from.
|
|
290
|
+
*
|
|
291
|
+
* An emitted source the record omits is an attribution a consumer never receives.
|
|
292
|
+
*/
|
|
293
|
+
export function provenanceDisagreement(manifest, declared) {
|
|
294
|
+
const trained = new Set(manifest.trainingSources);
|
|
295
|
+
const named = new Set(declared);
|
|
296
|
+
return {
|
|
297
|
+
declaredButNotTrained: [...named].filter((source) => !trained.has(source)).toSorted(),
|
|
298
|
+
trainedButNotDeclared: [...trained].filter((source) => !named.has(source)).toSorted(),
|
|
299
|
+
};
|
|
300
|
+
}
|
|
301
|
+
/**
|
|
302
|
+
* Why a release may not assert that a model's declared provenance equals what trained it.
|
|
303
|
+
*
|
|
304
|
+
* An empty array is the only value a caller may read as agreement.
|
|
305
|
+
* It is reachable only when the effective manifest covers every emitted source.
|
|
306
|
+
*
|
|
307
|
+
* A `null` manifest means no release read one at all.
|
|
308
|
+
* The function reports it rather than passing it.
|
|
309
|
+
*
|
|
310
|
+
* `declared` is a list of corpus source ids.
|
|
311
|
+
* A caller holding a model card's attribution entries passes `null`.
|
|
312
|
+
*
|
|
313
|
+
* Those entries are prose naming publishers.
|
|
314
|
+
* Every field of the card contains prose rather than a source id, so comparing the two
|
|
315
|
+
* lists as strings reports every entry as a source the epoch never drew.
|
|
316
|
+
*
|
|
317
|
+
* The refusal list then records the coverage refusal and one line recording the comparison as unmeasured.
|
|
318
|
+
*/
|
|
319
|
+
export function provenanceRefusals(input) {
|
|
320
|
+
if (!input.manifest) {
|
|
321
|
+
return [
|
|
322
|
+
`${input.packageName}: no effective training manifest was read, so whether its declared provenance ` +
|
|
323
|
+
`equals what trained it is unmeasured. \`effective-manifest.run.ts\` writes one from the corpus's ` +
|
|
324
|
+
`frozen manifest and an audit_epoch_mixture output.`,
|
|
325
|
+
];
|
|
326
|
+
}
|
|
327
|
+
const refusals = [];
|
|
328
|
+
const unrecorded = Object.entries(input.manifest.emittedButUnrecorded);
|
|
329
|
+
if (unrecorded.length) {
|
|
330
|
+
const total = unrecorded.reduce((sum, [, rows]) => sum + rows, 0);
|
|
331
|
+
refusals.push(`${input.packageName}: the audited epoch emitted ${unrecorded.length} source(s) the corpus's frozen ` +
|
|
332
|
+
`manifest does not name, ${total.toLocaleString()} rows in total, so the effective manifest covers ` +
|
|
333
|
+
`part of what trained the model. Those sources reached the corpus through an overlay merged after ` +
|
|
334
|
+
`the frozen manifest was written: ${unrecorded.map(([source]) => source).join(", ")}.`);
|
|
335
|
+
}
|
|
336
|
+
if (!input.declared) {
|
|
337
|
+
refusals.push(`${input.packageName}: whether its declared provenance equals the ${input.manifest.trainingSources.length} ` +
|
|
338
|
+
`source(s) the audited epoch drew from is unmeasured. The model card states its attribution as prose ` +
|
|
339
|
+
`naming publishers, and an effective manifest states corpus source ids, so the two carry no common key.`);
|
|
340
|
+
return refusals;
|
|
341
|
+
}
|
|
342
|
+
const { declaredButNotTrained, trainedButNotDeclared } = provenanceDisagreement(input.manifest, input.declared);
|
|
343
|
+
if (declaredButNotTrained.length) {
|
|
344
|
+
refusals.push(`${input.packageName} declares ${declaredButNotTrained.length} source(s) the audited epoch drew zero ` +
|
|
345
|
+
`rows from: ${declaredButNotTrained.join(", ")}. Attributing them says the model learned from rows ` +
|
|
346
|
+
`it never saw.`);
|
|
347
|
+
}
|
|
348
|
+
if (trainedButNotDeclared.length) {
|
|
349
|
+
refusals.push(`${input.packageName} omits ${trainedButNotDeclared.length} source(s) the audited epoch emitted: ` +
|
|
350
|
+
`${trainedButNotDeclared.join(", ")}. A consumer installing this package receives those rows' ` +
|
|
351
|
+
`contribution without their attribution.`);
|
|
352
|
+
}
|
|
353
|
+
return refusals;
|
|
354
|
+
}
|
|
355
|
+
//# sourceMappingURL=effective-manifest.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"effective-manifest.js","sourceRoot":"","sources":["../../lib/source-register/effective-manifest.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;GAqBG;AAEH,OAAO,EAAE,YAAY,EAAE,MAAM,2BAA2B,CAAA;AACxD,OAAO,EAAE,SAAS,EAAE,MAAM,sBAAsB,CAAA;AAChD,OAAO,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAA;AACpD,OAAO,EAAE,iBAAiB,EAAE,gBAAgB,EAAE,MAAM,qCAAqC,CAAA;AAGzF,OAAO,EAAE,eAAe,EAAE,WAAW,EAAE,MAAM,uBAAuB,CAAA;AAGpE;;;;;;;;GAQG;AACH,MAAM,UAAU,qBAAqB,CAAC,UAAkB;IACvD,MAAM,IAAI,GACT,UAAU;SACR,KAAK,CAAC,GAAG,CAAC;SACV,EAAE,CAAC,CAAC,CAAC,CAAC;QACP,EAAE,OAAO,CAAC,WAAW,EAAE,EAAE,CAAC,IAAI,UAAU,CAAA;IAE1C,OAAO,YAAY,CAAC,QAAQ,EAAE,eAAe,EAAE,GAAG,IAAI,OAAO,CAAC,CAAA;AAC/D,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,MAAM,eAAe,GAAG;IAC9B;;OAEG;IACH,gBAAgB,EAAE,mBAAmB;IAErC;;OAEG;IACH,UAAU,EAAE,aAAa;IAEzB;;;;OAIG;IACH,YAAY,EAAE,gBAAgB;CACrB,CAAA;AA2CV;;;;;;GAMG;AACH,MAAM,CAAC,MAAM,YAAY,GAAG;IAC3B;;;;;OAKG;IACH,kBAAkB,EAAE,sBAAsB;IAC1C;;OAEG;IACH,aAAa,EAAE,gBAAgB;CACtB,CAAA;AAiCV;;;;;;;GAOG;AACH,MAAM,sBAAsB,GAAqC;IAChE,CAAC,WAAW,CAAC,EAAE,eAAe;CAC9B,CAAA;AAED;;;;;;GAMG;AACH,MAAM,UAAU,oBAAoB,CAAC,OAAyC;IAC7E,MAAM,SAAS,GAAG,IAAI,GAAG,EAAoB,CAAA;IAE7C,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;QAC9B,IAAI,MAAM,CAAC,WAAW,IAAI,CAAC;YAAE,SAAQ;QAErC,MAAM,OAAO,GAAG,gBAAgB,CAAC,MAAM,CAAC,OAAO,CAAC,CAAA;QAEhD,IAAI,OAAO,CAAC,UAAU,IAAI,CAAC,OAAO,CAAC,WAAW,CAAC,QAAQ,CAAC,iBAAiB,CAAC,WAAW,CAAC;YAAE,SAAQ;QAEhG,SAAS,CAAC,GAAG,CAAC,MAAM,CAAC,OAAO,EAAE,CAAC,GAAG,CAAC,SAAS,CAAC,GAAG,CAAC,MAAM,CAAC,OAAO,CAAC,IAAI,EAAE,CAAC,EAAE,MAAM,CAAC,MAAM,CAAC,CAAC,CAAA;IACzF,CAAC;IAED,OAAO,CAAC,GAAG,SAAS,CAAC;SACnB,QAAQ,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,aAAa,CAAC,CAAC,CAAC,CAAC;SAC1C,GAAG,CAAC,CAAC,CAAC,OAAO,EAAE,QAAQ,CAAC,EAAE,EAAE,CAAC,CAAC;QAC9B,OAAO;QACP,OAAO,EAAE,QAAQ,CAAC,QAAQ,EAAE;QAC5B,SAAS,EAAE,sBAAsB,CAAC,OAAO,CAAC,IAAI,IAAI;KAClD,CAAC,CAAC,CAAA;AACL,CAAC;AAgJD;;;;;;;;;;;;;;;;GAgBG;AACH,MAAM,UAAU,cAAc,CAAC,IAAY;IAC1C,MAAM,aAAa,GAA2B,EAAE,CAAA;IAChD,MAAM,qBAAqB,GAAa,EAAE,CAAA;IAI1C,IAAI,KAAK,GAAuB,IAAI,CAAA;IACpC,IAAI,WAAW,GAAG,CAAC,CAAC,CAAA;IACpB,IAAI,UAAU,GAAG,KAAK,CAAA;IAEtB,+GAA+G;IAC/G,KAAK,MAAM,GAAG,IAAI,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC;QACpC,IAAI,cAAc,CAAC,IAAI,CAAC,GAAG,CAAC;YAAE,SAAQ;QAEtC,MAAM,MAAM,GAAG,SAAS,CAAC,IAAI,CAAC,GAAG,CAAE,CAAC,CAAC,CAAC,CAAC,MAAM,CAAA;QAE7C,IAAI,KAAK,IAAI,MAAM,IAAI,WAAW,EAAE,CAAC;YACpC,KAAK,GAAG,IAAI,CAAA;QACb,CAAC;QAED,IAAI,CAAC,KAAK,EAAE,CAAC;YACZ,MAAM,MAAM,GAAG,8DAA8D,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;YAEvF,IAAI,MAAM,EAAE,CAAC;gBACZ,KAAK,GAAG,MAAM,CAAC,CAAC,CAAgB,CAAA;gBAChC,WAAW,GAAG,MAAM,CAAC,CAAC,CAAE,CAAC,MAAM,CAAA;gBAE/B,IAAI,KAAK,KAAK,gBAAgB,EAAE,CAAC;oBAChC,UAAU,GAAG,IAAI,CAAA;gBAClB,CAAC;YACF,CAAC;YAED,SAAQ;QACT,CAAC;QAED,IAAI,KAAK,KAAK,gBAAgB,EAAE,CAAC;YAChC,MAAM,KAAK,GAAG,6BAA6B,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;YAErD,IAAI,KAAK,EAAE,CAAC;gBACX,aAAa,CAAC,KAAK,CAAC,CAAC,CAAE,CAAC,GAAG,MAAM,CAAC,UAAU,CAAC,KAAK,CAAC,CAAC,CAAE,CAAC,CAAA;YACxD,CAAC;YAED,SAAQ;QACT,CAAC;QAED,MAAM,IAAI,GAAG,+BAA+B,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;QAEtD,IAAI,IAAI,EAAE,CAAC;YACV,qBAAqB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAE,CAAC,CAAA;QACrC,CAAC;IACF,CAAC;IAED,IAAI,CAAC,UAAU,EAAE,CAAC;QACjB,MAAM,IAAI,KAAK,CACd,gGAAgG;YAC/F,wGAAwG,CACzG,CAAA;IACF,CAAC;IAED,OAAO,EAAE,aAAa,EAAE,qBAAqB,EAAE,CAAA;AAChD,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,uBAAuB,CAAC,QAAmC;IAC1E,OAAO,SAAS,CAAC,aAAa,CAAC,EAAE,GAAG,QAAQ,EAAE,aAAa,EAAE,EAAE,EAAE,CAAC,CAAC,CAAA;AACpE,CAAC;AAED;;;;;;;;;GASG;AACH,MAAM,UAAU,+BAA+B,CAAC,KAM/C;IACA,MAAM,OAAO,GAAG,KAAK,CAAC,KAAK,CAAC,aAAa,EAAE,MAAM,CAAA;IAEjD,IAAI,CAAC,OAAO,EAAE,CAAC;QACd,MAAM,IAAI,KAAK,CACd,sGAAsG;YACrG,iFAAiF,CAClF,CAAA;IACF,CAAC;IAED,MAAM,OAAO,GAAG,KAAK,CAAC,KAAK,CAAC,IAAI,EAAE,MAAM,EAAE,KAAK,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,CAAA;IAC3D,MAAM,MAAM,GAAG,KAAK,CAAC,UAAU,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,CAAA;IAEjD,IAAI,OAAO,IAAI,MAAM,IAAI,OAAO,KAAK,MAAM,EAAE,CAAC;QAC7C,MAAM,IAAI,KAAK,CACd,uBAAuB,OAAO,+BAA+B,MAAM,qCAAqC;YACvG,wEAAwE,CACzE,CAAA;IACF,CAAC;IAED,MAAM,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,UAAU,EAAE,MAAM,IAAI,EAAE,CAAA;IAClD,MAAM,aAAa,GAAG,KAAK,CAAC,KAAK,CAAC,UAAU,EAAE,wBAAwB,IAAI,EAAE,CAAA;IAC5E,MAAM,WAAW,GAAG,KAAK,CAAC,KAAK,CAAC,UAAU,EAAE,kCAAkC,IAAI,EAAE,CAAA;IACpF,MAAM,eAAe,GAAG,IAAI,GAAG,CAAC,KAAK,CAAC,MAAM,CAAC,qBAAqB,CAAC,CAAA;IAEnE,MAAM,OAAO,GAA4B,KAAK,CAAC,cAAc,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE;QACpF,MAAM,MAAM,GAAG,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,MAAM,CAAC,aAAa,EAAE,MAAM,CAAC,MAAM,CAAC;YACtE,CAAC,CAAC,KAAK,CAAC,MAAM,CAAC,aAAa,CAAC,MAAM,CAAC,MAAM,CAAE;YAC5C,CAAC,CAAC,IAAI,CAAA;QAEP,MAAM,SAAS,GAAG,KAAK,CAAC,MAAM,CAAC,MAAM,CAAC,IAAI,CAAC,CAAA;QAC3C,MAAM,WAAW,GAAG,OAAO,CAAC,MAAM,CAAC,MAAM,CAAC,IAAI,CAAC,CAAA;QAE/C,MAAM,eAAe,GACpB,WAAW,GAAG,CAAC;YACd,CAAC,CAAC,IAAI;YACN,CAAC,CAAC,MAAM,KAAK,IAAI;gBAChB,CAAC,CAAC,eAAe,CAAC,gBAAgB;gBAClC,CAAC,CAAC,MAAM,KAAK,CAAC;oBACb,CAAC,CAAC,eAAe,CAAC,UAAU;oBAC5B,CAAC,CAAC,eAAe,CAAC,YAAY,CAAA;QAElC,OAAO;YACN,MAAM,EAAE,MAAM,CAAC,MAAM;YACrB,UAAU,EAAE,MAAM,CAAC,IAAI;YACvB,OAAO,EAAE,MAAM,CAAC,OAAO;YACvB,MAAM;YACN,SAAS;YACT,WAAW;YACX,eAAe,EAAE,eAAe,CAAC,GAAG,CAAC,MAAM,CAAC,MAAM,CAAC;YACnD,eAAe;SACf,CAAA;IACF,CAAC,CAAC,CAAA;IAEF,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,WAAW,GAAG,CAAC,CAAC,WAAW,CAAC,CAAA;IAErD,MAAM,eAAe,GAAoC,EAAE,CAAA;IAE3D,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;QAC9B,IAAI,MAAM,CAAC,eAAe,EAAE,CAAC;YAC5B,eAAe,CAAC,MAAM,CAAC,MAAM,CAAC,GAAG,MAAM,CAAC,eAAe,CAAA;QACxD,CAAC;IACF,CAAC;IAED,MAAM,QAAQ,GAAG,IAAI,GAAG,CAAC,KAAK,CAAC,cAAc,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,CAAA;IACrF,MAAM,SAAS,GAAG,KAAK,CAAC,KAAK,CAAC,UAAU,EAAE,UAAU,IAAI,EAAE,CAAA;IAC1D,MAAM,oBAAoB,GAA2B,EAAE,CAAA;IACvD,MAAM,sBAAsB,GAAwD,EAAE,CAAA;IAEtF,KAAK,MAAM,CAAC,MAAM,EAAE,IAAI,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,OAAO,CAAC,EAAE,CAAC;QACtD,IAAI,IAAI,GAAG,CAAC,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC;YACvC,oBAAoB,CAAC,MAAM,CAAC,GAAG,IAAI,CAAA;YAEnC,sBAAsB,CAAC,MAAM,CAAC,GAAG;gBAChC,4EAA4E;gBAC5E,yDAAyD;gBACzD,qCAAqC;gBACrC,UAAU,EAAE,SAAS,CAAC,MAAM,CAAC,EAAE,IAAI,IAAI,CAAC,CAAC;gBACzC,SAAS,EAAE,KAAK,CAAC,MAAM,CAAC,IAAI,CAAC;gBAC7B,WAAW,EAAE,IAAI;aACjB,CAAA;QACF,CAAC;IACF,CAAC;IAED,MAAM,QAAQ,GAA8B;QAC3C,UAAU,EAAE,oCAAoC;QAChD,aAAa,EAAE,CAAC;QAChB,YAAY,EAAE,YAAY,CAAC,kBAAkB;QAC7C,QAAQ,EAAE,KAAK,CAAC,QAAQ,IAAI,IAAI;QAChC,oBAAoB,EAAE,oBAAoB,CAAC,OAAO,CAAC;QACnD,aAAa,EAAE,KAAK,CAAC,cAAc,CAAC,aAAa;QACjD,oBAAoB,EAAE,KAAK,CAAC,cAAc,CAAC,aAAa;QACxD,MAAM,EAAE,KAAK,CAAC,UAAU;QACxB,IAAI,EAAE,KAAK,CAAC,KAAK,CAAC,IAAI,EAAE,IAAI,IAAI,CAAC,CAAC;QAClC,cAAc,EAAE,KAAK,CAAC,KAAK,CAAC,IAAI,EAAE,eAAe,IAAI,CAAC;QACtD,aAAa,EAAE,KAAK,CAAC,KAAK,CAAC,IAAI,EAAE,cAAc,IAAI,CAAC;QACpD,iBAAiB,EAAE,MAAM,CAAC,IAAI,CAAC,aAAa,CAAC,CAAC,MAAM;QACpD,oBAAoB,EAAE,MAAM,CAAC,MAAM,CAAC,aAAa,CAAC,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC,MAAM;QACtF,4BAA4B,EAAE,CAAC,GAAG,WAAW,CAAC,CAAC,QAAQ,EAAE;QACzD,OAAO;QACP,eAAe,EAAE,OAAO,CAAC,MAAM,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,CAAC,WAAW,GAAG,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,CAAC,MAAM,CAAC;QAClG,eAAe;QACf,oBAAoB;QACpB,sBAAsB;QACtB,gBAAgB,EAAE,MAAM,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,KAAK,EAAE,EAAE,CAAC,GAAG,GAAG,KAAK,EAAE,CAAC,CAAC;QAC/E,aAAa,EAAE,EAAE;KACjB,CAAA;IAED,OAAO,EAAE,GAAG,QAAQ,EAAE,aAAa,EAAE,uBAAuB,CAAC,QAAQ,CAAC,EAAE,CAAA;AACzE,CAAC;AAED;;;;;;;;GAQG;AACH,MAAM,UAAU,sBAAsB,CACrC,QAAmC,EACnC,QAA2B;IAE3B,MAAM,OAAO,GAAG,IAAI,GAAG,CAAC,QAAQ,CAAC,eAAe,CAAC,CAAA;IACjD,MAAM,KAAK,GAAG,IAAI,GAAG,CAAC,QAAQ,CAAC,CAAA;IAE/B,OAAO;QACN,qBAAqB,EAAE,CAAC,GAAG,KAAK,CAAC,CAAC,MAAM,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,QAAQ,EAAE;QACrF,qBAAqB,EAAE,CAAC,GAAG,OAAO,CAAC,CAAC,MAAM,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,QAAQ,EAAE;KACrF,CAAA;AACF,CAAC;AAED;;;;;;;;;;;;;;;;;GAiBG;AACH,MAAM,UAAU,kBAAkB,CAAC,KAIlC;IACA,IAAI,CAAC,KAAK,CAAC,QAAQ,EAAE,CAAC;QACrB,OAAO;YACN,GAAG,KAAK,CAAC,WAAW,gFAAgF;gBACnG,mGAAmG;gBACnG,oDAAoD;SACrD,CAAA;IACF,CAAC;IAED,MAAM,QAAQ,GAAa,EAAE,CAAA;IAC7B,MAAM,UAAU,GAAG,MAAM,CAAC,OAAO,CAAC,KAAK,CAAC,QAAQ,CAAC,oBAAoB,CAAC,CAAA;IAEtE,IAAI,UAAU,CAAC,MAAM,EAAE,CAAC;QACvB,MAAM,KAAK,GAAG,UAAU,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,CAAC,EAAE,IAAI,CAAC,EAAE,EAAE,CAAC,GAAG,GAAG,IAAI,EAAE,CAAC,CAAC,CAAA;QAEjE,QAAQ,CAAC,IAAI,CACZ,GAAG,KAAK,CAAC,WAAW,+BAA+B,UAAU,CAAC,MAAM,iCAAiC;YACpG,2BAA2B,KAAK,CAAC,cAAc,EAAE,mDAAmD;YACpG,mGAAmG;YACnG,oCAAoC,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,MAAM,CAAC,EAAE,EAAE,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,CACvF,CAAA;IACF,CAAC;IAED,IAAI,CAAC,KAAK,CAAC,QAAQ,EAAE,CAAC;QACrB,QAAQ,CAAC,IAAI,CACZ,GAAG,KAAK,CAAC,WAAW,gDAAgD,KAAK,CAAC,QAAQ,CAAC,eAAe,CAAC,MAAM,GAAG;YAC3G,sGAAsG;YACtG,wGAAwG,CACzG,CAAA;QAED,OAAO,QAAQ,CAAA;IAChB,CAAC;IAED,MAAM,EAAE,qBAAqB,EAAE,qBAAqB,EAAE,GAAG,sBAAsB,CAAC,KAAK,CAAC,QAAQ,EAAE,KAAK,CAAC,QAAQ,CAAC,CAAA;IAE/G,IAAI,qBAAqB,CAAC,MAAM,EAAE,CAAC;QAClC,QAAQ,CAAC,IAAI,CACZ,GAAG,KAAK,CAAC,WAAW,aAAa,qBAAqB,CAAC,MAAM,yCAAyC;YACrG,cAAc,qBAAqB,CAAC,IAAI,CAAC,IAAI,CAAC,sDAAsD;YACpG,eAAe,CAChB,CAAA;IACF,CAAC;IAED,IAAI,qBAAqB,CAAC,MAAM,EAAE,CAAC;QAClC,QAAQ,CAAC,IAAI,CACZ,GAAG,KAAK,CAAC,WAAW,UAAU,qBAAqB,CAAC,MAAM,wCAAwC;YACjG,GAAG,qBAAqB,CAAC,IAAI,CAAC,IAAI,CAAC,4DAA4D;YAC/F,yCAAyC,CAC1C,CAAA;IACF,CAAC;IAED,OAAO,QAAQ,CAAA;AAChB,CAAC"}
|
|
@@ -0,0 +1,79 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Reads and audits the address-source register.
|
|
7
|
+
*/
|
|
8
|
+
import type { PathBuilderLike } from "path-ts";
|
|
9
|
+
import { SourceOperation, type AddressSourceRecord, type AddressSourceRegister, type LicenseDecision, type OperationDecision } from "#source-register/types";
|
|
10
|
+
/**
|
|
11
|
+
* Resolves the path of the committed register through the package's `./data/*` export.
|
|
12
|
+
*
|
|
13
|
+
* Resolution happens on call so that importing this module works before the build has written the register.
|
|
14
|
+
*/
|
|
15
|
+
export declare function addressSourceRegisterPath(): string;
|
|
16
|
+
/**
|
|
17
|
+
* Returns the license label that the exclude filter in `@mailwoman/corpus/utils/license` matches by prefix.
|
|
18
|
+
*
|
|
19
|
+
* The function returns `null` until someone has elected terms for the decision.
|
|
20
|
+
*/
|
|
21
|
+
export declare function electedLicenseLabel(decision: LicenseDecision): string | null;
|
|
22
|
+
/**
|
|
23
|
+
* Replaces generated license decisions with recorded ones that share a license id.
|
|
24
|
+
*
|
|
25
|
+
* The build generates an `unchecked` decision for each license and rewrites the register
|
|
26
|
+
* whole, so reviewed decisions live in a separate input and merge here.
|
|
27
|
+
*
|
|
28
|
+
* @throws When a recorded decision refers to a license that the generated set lacks.
|
|
29
|
+
* Such a decision is a typo or refers to a removed source.
|
|
30
|
+
*/
|
|
31
|
+
export declare function applyLicenseDecisions(generated: readonly LicenseDecision[], recorded: ReadonlyMap<string, LicenseDecision>): LicenseDecision[];
|
|
32
|
+
/**
|
|
33
|
+
* The operations that ingesting a source into the corpus performs.
|
|
34
|
+
*
|
|
35
|
+
* Redistribution and commercial sublicensing happen at release, so this list omits them.
|
|
36
|
+
*/
|
|
37
|
+
export declare const INGEST_OPERATIONS: readonly SourceOperation[];
|
|
38
|
+
/**
|
|
39
|
+
* The operations that releasing a model trained on a source adds to {@link INGEST_OPERATIONS}.
|
|
40
|
+
*/
|
|
41
|
+
export declare const MODEL_RELEASE_OPERATIONS: readonly SourceOperation[];
|
|
42
|
+
/**
|
|
43
|
+
* Returns the recorded permission for one operation under a license decision.
|
|
44
|
+
*
|
|
45
|
+
* The result is `unreviewed` when the decision is not elected or does not mention the operation.
|
|
46
|
+
* The selected terms establish which terms apply.
|
|
47
|
+
* Each operation still needs its own review.
|
|
48
|
+
*/
|
|
49
|
+
export declare function permissionFor(decision: LicenseDecision, operation: SourceOperation): OperationDecision;
|
|
50
|
+
/**
|
|
51
|
+
* Returns every reason that a source may not enter a training corpus, or an empty array when it may.
|
|
52
|
+
*
|
|
53
|
+
* The function returns reasons so that callers can tell the different blockers apart.
|
|
54
|
+
*/
|
|
55
|
+
export declare function ingestEligibilityProblems(source: AddressSourceRecord, register: AddressSourceRegister, operations?: readonly SourceOperation[]): readonly string[];
|
|
56
|
+
/**
|
|
57
|
+
* Returns one message for each structural problem in a register.
|
|
58
|
+
*
|
|
59
|
+
* The content digest is checked separately on read, because the build audits registers
|
|
60
|
+
* before it writes a digest.
|
|
61
|
+
*/
|
|
62
|
+
export declare function auditAddressSourceRegister(register: AddressSourceRegister): string[];
|
|
63
|
+
/**
|
|
64
|
+
* Computes the SHA-256 digest of the register without its `contentDigest` field.
|
|
65
|
+
*
|
|
66
|
+
* The build and the read audit share this function so that they serialize identically.
|
|
67
|
+
* The digest covers the parsed object, so reformatting the file keeps it valid.
|
|
68
|
+
*
|
|
69
|
+
* Key order is part of the serialization, so reordering keys by hand changes the digest.
|
|
70
|
+
*/
|
|
71
|
+
export declare function registerContentDigest(register: AddressSourceRegister): string;
|
|
72
|
+
/**
|
|
73
|
+
* Reads the committed register and checks its digest and structure.
|
|
74
|
+
*
|
|
75
|
+
* @throws When the file does not parse or the audit reports a problem.
|
|
76
|
+
* The message lists every problem.
|
|
77
|
+
*/
|
|
78
|
+
export declare function readAddressSourceRegister(path?: PathBuilderLike): Promise<AddressSourceRegister>;
|
|
79
|
+
//# sourceMappingURL=register.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"register.d.ts","sourceRoot":"","sources":["../../lib/source-register/register.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAOH,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,SAAS,CAAA;AAE9C,OAAO,EAQN,eAAe,EAGf,KAAK,mBAAmB,EACxB,KAAK,qBAAqB,EAE1B,KAAK,eAAe,EACpB,KAAK,iBAAiB,EACtB,MAAM,wBAAwB,CAAA;AAG/B;;;;GAIG;AACH,wBAAgB,yBAAyB,IAAI,MAAM,CAElD;AAWD;;;;GAIG;AACH,wBAAgB,mBAAmB,CAAC,QAAQ,EAAE,eAAe,GAAG,MAAM,GAAG,IAAI,CAI5E;AAED;;;;;;;;GAQG;AACH,wBAAgB,qBAAqB,CACpC,SAAS,EAAE,SAAS,eAAe,EAAE,EACrC,QAAQ,EAAE,WAAW,CAAC,MAAM,EAAE,eAAe,CAAC,GAC5C,eAAe,EAAE,CAanB;AAED;;;;GAIG;AACH,eAAO,MAAM,iBAAiB,EAAE,SAAS,eAAe,EAKvD,CAAA;AAED;;GAEG;AACH,eAAO,MAAM,wBAAwB,EAAE,SAAS,eAAe,EAG9D,CAAA;AAED;;;;;;GAMG;AACH,wBAAgB,aAAa,CAAC,QAAQ,EAAE,eAAe,EAAE,SAAS,EAAE,eAAe,GAAG,iBAAiB,CActG;AAED;;;;GAIG;AACH,wBAAgB,yBAAyB,CACxC,MAAM,EAAE,mBAAmB,EAC3B,QAAQ,EAAE,qBAAqB,EAC/B,UAAU,GAAE,SAAS,eAAe,EAAsB,GACxD,SAAS,MAAM,EAAE,CA2CnB;AAyBD;;;;;GAKG;AACH,wBAAgB,0BAA0B,CAAC,QAAQ,EAAE,qBAAqB,GAAG,MAAM,EAAE,CAiBpF;AAED;;;;;;;GAOG;AACH,wBAAgB,qBAAqB,CAAC,QAAQ,EAAE,qBAAqB,GAAG,MAAM,CAI7E;AAmRD;;;;;GAKG;AACH,wBAAsB,yBAAyB,CAAC,IAAI,CAAC,EAAE,eAAe,GAAG,OAAO,CAAC,qBAAqB,CAAC,CAUtG"}
|