@mailwoman/corpus 9.2.0 → 9.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +22 -22
- package/data/PROVENANCE.md +7 -7
- package/lib/adapters/ban/adapter.ts +190 -0
- package/lib/adapters/ban/street-decompose.ts +66 -0
- package/lib/adapters/fcc-bdc/adapter.ts +174 -0
- package/lib/adapters/geonames/adapter.ts +199 -0
- package/lib/adapters/geonames-postal/adapter.ts +122 -0
- package/lib/adapters/gnaf/adapter.ts +149 -0
- package/lib/adapters/gnaf/assemble.ts +225 -0
- package/lib/adapters/index.ts +153 -0
- package/lib/adapters/openaddresses/adapter.ts +251 -0
- package/lib/adapters/overture/adapter.ts +162 -0
- package/lib/adapters/state-hi-schools/adapter.ts +170 -0
- package/lib/adapters/state-hi-schools/workbook.ts +35 -0
- package/lib/adapters/synth-po-box/adapter.ts +204 -0
- package/lib/adapters/tiger/adapter.ts +252 -0
- package/lib/adapters/tiger/street-decompose.ts +83 -0
- package/lib/adapters/usgov-hrsa-fqhc/adapter.ts +167 -0
- package/lib/adapters/usgov-imls-pls/adapter.ts +143 -0
- package/lib/adapters/usgov-irs-bmf/adapter.ts +151 -0
- package/lib/adapters/usgov-nad/adapter.ts +334 -0
- package/lib/adapters/usgov-nppes/adapter.ts +151 -0
- package/lib/adapters/usgov-samhsa-treatment-locator/adapter.ts +193 -0
- package/lib/adapters/utils/index.ts +307 -0
- package/lib/adapters/wof-admin-jp/adapter.ts +214 -0
- package/lib/adapters/wof-admin-json/adapter.ts +231 -0
- package/lib/adapters/wof-json-rows.ts +129 -0
- package/lib/adapters/wof-postalcode-json/adapter.ts +176 -0
- package/lib/build.ts +378 -0
- package/lib/env.ts +50 -0
- package/lib/index.ts +13 -0
- package/lib/name-prone-us-suffixes.ts +12 -0
- package/lib/recipes/anchor-absorption.ts +101 -0
- package/lib/recipes/bare-country.ts +95 -0
- package/lib/recipes/boundary-stress.ts +100 -0
- package/lib/recipes/cn-organizational-units.ts +199 -0
- package/lib/recipes/country-balanced.ts +509 -0
- package/lib/recipes/cz-pcfirst-preposition.ts +111 -0
- package/lib/recipes/fr-admin-split.ts +242 -0
- package/lib/recipes/fr-bare-street.ts +170 -0
- package/lib/recipes/fr-fragment.ts +333 -0
- package/lib/recipes/fr-lieudit.ts +301 -0
- package/lib/recipes/fr-order.ts +245 -0
- package/lib/recipes/german.ts +359 -0
- package/lib/recipes/house-venue.ts +92 -0
- package/lib/recipes/index.ts +97 -0
- package/lib/recipes/intersection.ts +618 -0
- package/lib/recipes/locale.ts +599 -0
- package/lib/recipes/nl-postcode.ts +115 -0
- package/lib/recipes/no-fragment.ts +219 -0
- package/lib/recipes/no-street-led.ts +141 -0
- package/lib/recipes/no-street.ts +90 -0
- package/lib/recipes/po-box-cedex.ts +976 -0
- package/lib/recipes/po-box.ts +123 -0
- package/lib/recipes/reviewed-postcode-tail.ts +190 -0
- package/lib/recipes/scaffold.ts +469 -0
- package/lib/recipes/si-bare-village.ts +97 -0
- package/lib/recipes/street-affix.ts +804 -0
- package/lib/recipes/street-bare.ts +100 -0
- package/lib/recipes/street.ts +81 -0
- package/lib/recipes/sub-venue-sources.ts +877 -0
- package/lib/recipes/sub-venue.ts +997 -0
- package/lib/recipes/trailing-region.ts +183 -0
- package/lib/recipes/unit.ts +304 -0
- package/lib/runner.ts +312 -0
- package/lib/synthesizers/anchor-absorption.ts +288 -0
- package/lib/synthesizers/boundary-stress.ts +532 -0
- package/lib/synthesizers/german.ts +260 -0
- package/lib/synthesizers/house-venue.ts +308 -0
- package/lib/synthesizers/intersection.ts +233 -0
- package/lib/synthesizers/no-street.ts +327 -0
- package/lib/synthesizers/po-box.ts +323 -0
- package/lib/synthesizers/street.ts +269 -0
- package/lib/synthesizers/utils.ts +993 -0
- package/lib/test-kit/corpus-recipe.ts +86 -0
- package/lib/test-kit/index.ts +100 -0
- package/lib/tools/align-slice.ts +68 -0
- package/lib/tools/audit.ts +403 -0
- package/lib/tools/corpus-stats.ts +136 -0
- package/lib/tools/fetch/ban.ts +289 -0
- package/lib/tools/fetch/download.ts +262 -0
- package/lib/tools/fetch/geonames-dump.ts +257 -0
- package/lib/tools/fetch/geonames-postal.ts +180 -0
- package/lib/tools/fetch/hrsa.ts +59 -0
- package/lib/tools/fetch/imls-pls.ts +149 -0
- package/lib/tools/fetch/index.ts +147 -0
- package/lib/tools/fetch/nad.ts +341 -0
- package/lib/tools/fetch/nppes.ts +165 -0
- package/lib/tools/fetch/openaddresses.ts +347 -0
- package/lib/tools/fetch/ourairports.ts +170 -0
- package/lib/tools/fetch/ppd.ts +121 -0
- package/lib/tools/fetch/state-hi-schools.ts +161 -0
- package/lib/tools/fetch/state-sources.ts +146 -0
- package/lib/tools/fetch/tiger-full.ts +308 -0
- package/lib/tools/fetch/wikidata-subvenue.ts +384 -0
- package/lib/tools/golden-expand.ts +574 -0
- package/lib/tools/golden-promote.ts +337 -0
- package/lib/tools/golden-relabel-street.ts +683 -0
- package/lib/tools/index.ts +28 -0
- package/lib/tools/ingest-csv.ts +378 -0
- package/lib/tools/jsonl-to-parquet.ts +207 -0
- package/lib/tools/lint-slice-vocab.ts +388 -0
- package/lib/tools/lint-slice.ts +496 -0
- package/lib/tools/overlay-manifest.ts +148 -0
- package/lib/tools/overture-subvenue.ts +209 -0
- package/lib/tools/postcode-triples.ts +363 -0
- package/lib/tools/slice-kryptonite.ts +137 -0
- package/lib/tools/slice-translit.ts +218 -0
- package/lib/tools/sub-venue/harvest.ts +234 -0
- package/lib/tools/sub-venue/head-nouns.ts +245 -0
- package/lib/tools/sub-venue/surfaces.ts +95 -0
- package/lib/tools/sub-venue/table.ts +281 -0
- package/lib/tools/sub-venue/wikidata.ts +85 -0
- package/lib/tools/sub-venue-lexicon.ts +429 -0
- package/lib/tools/sub-venue-promotions.ts +330 -0
- package/lib/types.ts +247 -0
- package/lib/utils/align.ts +330 -0
- package/lib/utils/golden.ts +189 -0
- package/lib/utils/index.ts +14 -0
- package/lib/utils/parquet.ts +582 -0
- package/lib/utils/slice-stats.ts +95 -0
- package/lib/utils/split.ts +279 -0
- package/lib/utils/tokenize.ts +120 -0
- package/lib/utils/wof-json.ts +247 -0
- package/out/adapters/ban/adapter.d.ts.map +1 -0
- package/out/adapters/ban/adapter.js +149 -0
- package/out/adapters/ban/adapter.js.map +1 -0
- package/out/adapters/ban/street-decompose.d.ts.map +1 -0
- package/out/adapters/ban/street-decompose.js +51 -0
- package/out/adapters/ban/street-decompose.js.map +1 -0
- package/out/adapters/fcc-bdc/adapter.d.ts.map +1 -0
- package/out/adapters/fcc-bdc/adapter.js +144 -0
- package/out/adapters/fcc-bdc/adapter.js.map +1 -0
- package/out/adapters/geonames/adapter.d.ts.map +1 -0
- package/out/adapters/geonames/adapter.js +176 -0
- package/out/adapters/geonames/adapter.js.map +1 -0
- package/out/adapters/geonames-postal/adapter.d.ts +54 -0
- package/out/adapters/geonames-postal/adapter.d.ts.map +1 -0
- package/out/adapters/geonames-postal/adapter.js +107 -0
- package/out/adapters/geonames-postal/adapter.js.map +1 -0
- package/out/adapters/gnaf/adapter.d.ts +49 -0
- package/out/adapters/gnaf/adapter.d.ts.map +1 -0
- package/out/adapters/gnaf/adapter.js +124 -0
- package/out/adapters/gnaf/adapter.js.map +1 -0
- package/out/adapters/gnaf/assemble.d.ts +65 -0
- package/out/adapters/gnaf/assemble.d.ts.map +1 -0
- package/out/adapters/gnaf/assemble.js +154 -0
- package/out/adapters/gnaf/assemble.js.map +1 -0
- package/out/adapters/index.d.ts +51 -0
- package/out/adapters/index.d.ts.map +1 -0
- package/out/adapters/index.js +95 -0
- package/out/adapters/index.js.map +1 -0
- package/out/adapters/openaddresses/adapter.d.ts.map +1 -0
- package/out/adapters/openaddresses/adapter.js +186 -0
- package/out/adapters/openaddresses/adapter.js.map +1 -0
- package/out/adapters/overture/adapter.d.ts +48 -0
- package/out/adapters/overture/adapter.d.ts.map +1 -0
- package/out/adapters/overture/adapter.js +125 -0
- package/out/adapters/overture/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/adapter.d.ts +46 -0
- package/out/adapters/state-hi-schools/adapter.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/adapter.js +145 -0
- package/out/adapters/state-hi-schools/adapter.js.map +1 -0
- package/out/adapters/state-hi-schools/workbook.d.ts +29 -0
- package/out/adapters/state-hi-schools/workbook.d.ts.map +1 -0
- package/out/adapters/state-hi-schools/workbook.js +20 -0
- package/out/adapters/state-hi-schools/workbook.js.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.d.ts.map +1 -0
- package/out/adapters/state-ia-contractors/adapter.js.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-ny-notaries/adapter.js.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.d.ts.map +1 -0
- package/out/adapters/state-tx-notaries/adapter.js.map +1 -0
- package/out/adapters/synth-po-box/adapter.d.ts.map +1 -0
- package/out/adapters/synth-po-box/adapter.js +140 -0
- package/out/adapters/synth-po-box/adapter.js.map +1 -0
- package/out/adapters/tiger/adapter.d.ts +55 -0
- package/out/adapters/tiger/adapter.d.ts.map +1 -0
- package/out/adapters/tiger/adapter.js +201 -0
- package/out/adapters/tiger/adapter.js.map +1 -0
- package/out/adapters/tiger/street-decompose.d.ts.map +1 -0
- package/out/adapters/tiger/street-decompose.js +68 -0
- package/out/adapters/tiger/street-decompose.js.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts +56 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js +132 -0
- package/out/adapters/usgov-hrsa-fqhc/adapter.js.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts +36 -0
- package/out/adapters/usgov-imls-pls/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-imls-pls/adapter.js +114 -0
- package/out/adapters/usgov-imls-pls/adapter.js.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts +37 -0
- package/out/adapters/usgov-irs-bmf/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-irs-bmf/adapter.js +120 -0
- package/out/adapters/usgov-irs-bmf/adapter.js.map +1 -0
- package/out/adapters/usgov-nad/adapter.d.ts +48 -0
- package/out/adapters/usgov-nad/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nad/adapter.js +249 -0
- package/out/adapters/usgov-nad/adapter.js.map +1 -0
- package/out/adapters/usgov-nppes/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-nppes/adapter.js +118 -0
- package/out/adapters/usgov-nppes/adapter.js.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +1 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js +154 -0
- package/out/adapters/usgov-samhsa-treatment-locator/adapter.js.map +1 -0
- package/out/adapters/utils/index.d.ts +191 -0
- package/out/adapters/utils/index.d.ts.map +1 -0
- package/out/adapters/utils/index.js +206 -0
- package/out/adapters/utils/index.js.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-jp/adapter.js +161 -0
- package/out/adapters/wof-admin-jp/adapter.js.map +1 -0
- package/out/adapters/wof-admin-json/adapter.d.ts +79 -0
- package/out/adapters/wof-admin-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-admin-json/adapter.js +197 -0
- package/out/adapters/wof-admin-json/adapter.js.map +1 -0
- package/out/adapters/wof-json-rows.d.ts +62 -0
- package/out/adapters/wof-json-rows.d.ts.map +1 -0
- package/out/adapters/wof-json-rows.js +83 -0
- package/out/adapters/wof-json-rows.js.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts +65 -0
- package/out/adapters/wof-postalcode-json/adapter.d.ts.map +1 -0
- package/out/adapters/wof-postalcode-json/adapter.js +151 -0
- package/out/adapters/wof-postalcode-json/adapter.js.map +1 -0
- package/out/build.d.ts +132 -0
- package/out/build.d.ts.map +1 -0
- package/out/build.js +245 -0
- package/out/build.js.map +1 -0
- package/out/codex/us-fips-state.d.ts.map +1 -0
- package/out/codex/us-fips-state.js.map +1 -0
- package/out/env.d.ts +46 -0
- package/out/env.d.ts.map +1 -0
- package/out/env.js +46 -0
- package/out/env.js.map +1 -0
- package/out/index.d.ts +13 -0
- package/out/index.d.ts.map +1 -0
- package/out/index.js +13 -0
- package/out/index.js.map +1 -0
- package/out/name-prone-us-suffixes.d.ts +12 -0
- package/out/name-prone-us-suffixes.d.ts.map +1 -0
- package/out/name-prone-us-suffixes.js +12 -0
- package/out/name-prone-us-suffixes.js.map +1 -0
- package/out/recipes/anchor-absorption.d.ts +20 -0
- package/out/recipes/anchor-absorption.d.ts.map +1 -0
- package/out/recipes/anchor-absorption.js +81 -0
- package/out/recipes/anchor-absorption.js.map +1 -0
- package/out/recipes/bare-country.d.ts +25 -0
- package/out/recipes/bare-country.d.ts.map +1 -0
- package/out/recipes/bare-country.js +87 -0
- package/out/recipes/bare-country.js.map +1 -0
- package/out/recipes/boundary-stress.d.ts +20 -0
- package/out/recipes/boundary-stress.d.ts.map +1 -0
- package/out/recipes/boundary-stress.js +83 -0
- package/out/recipes/boundary-stress.js.map +1 -0
- package/out/recipes/cn-organizational-units.d.ts +36 -0
- package/out/recipes/cn-organizational-units.d.ts.map +1 -0
- package/out/recipes/cn-organizational-units.js +159 -0
- package/out/recipes/cn-organizational-units.js.map +1 -0
- package/out/recipes/country-balanced.d.ts +32 -0
- package/out/recipes/country-balanced.d.ts.map +1 -0
- package/out/recipes/country-balanced.js +393 -0
- package/out/recipes/country-balanced.js.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts +22 -0
- package/out/recipes/cz-pcfirst-preposition.d.ts.map +1 -0
- package/out/recipes/cz-pcfirst-preposition.js +100 -0
- package/out/recipes/cz-pcfirst-preposition.js.map +1 -0
- package/out/recipes/fr-admin-split.d.ts +38 -0
- package/out/recipes/fr-admin-split.d.ts.map +1 -0
- package/out/recipes/fr-admin-split.js +192 -0
- package/out/recipes/fr-admin-split.js.map +1 -0
- package/out/recipes/fr-bare-street.d.ts +28 -0
- package/out/recipes/fr-bare-street.d.ts.map +1 -0
- package/out/recipes/fr-bare-street.js +143 -0
- package/out/recipes/fr-bare-street.js.map +1 -0
- package/out/recipes/fr-fragment.d.ts +77 -0
- package/out/recipes/fr-fragment.d.ts.map +1 -0
- package/out/recipes/fr-fragment.js +276 -0
- package/out/recipes/fr-fragment.js.map +1 -0
- package/out/recipes/fr-lieudit.d.ts +32 -0
- package/out/recipes/fr-lieudit.d.ts.map +1 -0
- package/out/recipes/fr-lieudit.js +227 -0
- package/out/recipes/fr-lieudit.js.map +1 -0
- package/out/recipes/fr-order.d.ts +38 -0
- package/out/recipes/fr-order.d.ts.map +1 -0
- package/out/recipes/fr-order.js +197 -0
- package/out/recipes/fr-order.js.map +1 -0
- package/out/recipes/german.d.ts +44 -0
- package/out/recipes/german.d.ts.map +1 -0
- package/out/recipes/german.js +288 -0
- package/out/recipes/german.js.map +1 -0
- package/out/recipes/house-venue.d.ts +18 -0
- package/out/recipes/house-venue.d.ts.map +1 -0
- package/out/recipes/house-venue.js +73 -0
- package/out/recipes/house-venue.js.map +1 -0
- package/out/recipes/index.d.ts +24 -0
- package/out/recipes/index.d.ts.map +1 -0
- package/out/recipes/index.js +91 -0
- package/out/recipes/index.js.map +1 -0
- package/out/recipes/intersection.d.ts +42 -0
- package/out/recipes/intersection.d.ts.map +1 -0
- package/out/recipes/intersection.js +452 -0
- package/out/recipes/intersection.js.map +1 -0
- package/out/recipes/locale.d.ts +136 -0
- package/out/recipes/locale.d.ts.map +1 -0
- package/out/recipes/locale.js +460 -0
- package/out/recipes/locale.js.map +1 -0
- package/out/recipes/nl-postcode.d.ts +26 -0
- package/out/recipes/nl-postcode.d.ts.map +1 -0
- package/out/recipes/nl-postcode.js +102 -0
- package/out/recipes/nl-postcode.js.map +1 -0
- package/out/recipes/no-fragment.d.ts +43 -0
- package/out/recipes/no-fragment.d.ts.map +1 -0
- package/out/recipes/no-fragment.js +182 -0
- package/out/recipes/no-fragment.js.map +1 -0
- package/out/recipes/no-street-led.d.ts +24 -0
- package/out/recipes/no-street-led.d.ts.map +1 -0
- package/out/recipes/no-street-led.js +113 -0
- package/out/recipes/no-street-led.js.map +1 -0
- package/out/recipes/no-street.d.ts +18 -0
- package/out/recipes/no-street.d.ts.map +1 -0
- package/out/recipes/no-street.js +71 -0
- package/out/recipes/no-street.js.map +1 -0
- package/out/recipes/po-box-cedex.d.ts +38 -0
- package/out/recipes/po-box-cedex.d.ts.map +1 -0
- package/out/recipes/po-box-cedex.js +767 -0
- package/out/recipes/po-box-cedex.js.map +1 -0
- package/out/recipes/po-box.d.ts +17 -0
- package/out/recipes/po-box.d.ts.map +1 -0
- package/out/recipes/po-box.js +100 -0
- package/out/recipes/po-box.js.map +1 -0
- package/out/recipes/reviewed-postcode-tail.d.ts +47 -0
- package/out/recipes/reviewed-postcode-tail.d.ts.map +1 -0
- package/out/recipes/reviewed-postcode-tail.js +125 -0
- package/out/recipes/reviewed-postcode-tail.js.map +1 -0
- package/out/recipes/scaffold.d.ts +324 -0
- package/out/recipes/scaffold.d.ts.map +1 -0
- package/out/recipes/scaffold.js +186 -0
- package/out/recipes/scaffold.js.map +1 -0
- package/out/recipes/si-bare-village.d.ts +32 -0
- package/out/recipes/si-bare-village.d.ts.map +1 -0
- package/out/recipes/si-bare-village.js +88 -0
- package/out/recipes/si-bare-village.js.map +1 -0
- package/out/recipes/street-affix.d.ts +89 -0
- package/out/recipes/street-affix.d.ts.map +1 -0
- package/out/recipes/street-affix.js +563 -0
- package/out/recipes/street-affix.js.map +1 -0
- package/out/recipes/street-bare.d.ts +25 -0
- package/out/recipes/street-bare.d.ts.map +1 -0
- package/out/recipes/street-bare.js +86 -0
- package/out/recipes/street-bare.js.map +1 -0
- package/out/recipes/street.d.ts +15 -0
- package/out/recipes/street.d.ts.map +1 -0
- package/out/recipes/street.js +69 -0
- package/out/recipes/street.js.map +1 -0
- package/out/recipes/sub-venue-sources.d.ts +229 -0
- package/out/recipes/sub-venue-sources.d.ts.map +1 -0
- package/out/recipes/sub-venue-sources.js +653 -0
- package/out/recipes/sub-venue-sources.js.map +1 -0
- package/out/recipes/sub-venue.d.ts +269 -0
- package/out/recipes/sub-venue.d.ts.map +1 -0
- package/out/recipes/sub-venue.js +725 -0
- package/out/recipes/sub-venue.js.map +1 -0
- package/out/recipes/trailing-region.d.ts +74 -0
- package/out/recipes/trailing-region.d.ts.map +1 -0
- package/out/recipes/trailing-region.js +157 -0
- package/out/recipes/trailing-region.js.map +1 -0
- package/out/recipes/unit.d.ts +29 -0
- package/out/recipes/unit.d.ts.map +1 -0
- package/out/recipes/unit.js +230 -0
- package/out/recipes/unit.js.map +1 -0
- package/out/runner.d.ts +130 -0
- package/out/runner.d.ts.map +1 -0
- package/out/runner.js +185 -0
- package/out/runner.js.map +1 -0
- package/out/synthesizers/anchor-absorption.d.ts +63 -0
- package/out/synthesizers/anchor-absorption.d.ts.map +1 -0
- package/out/synthesizers/anchor-absorption.js +221 -0
- package/out/synthesizers/anchor-absorption.js.map +1 -0
- package/out/synthesizers/boundary-stress.d.ts +78 -0
- package/out/synthesizers/boundary-stress.d.ts.map +1 -0
- package/out/synthesizers/boundary-stress.js +455 -0
- package/out/synthesizers/boundary-stress.js.map +1 -0
- package/out/synthesizers/german.d.ts +115 -0
- package/out/synthesizers/german.d.ts.map +1 -0
- package/out/synthesizers/german.js +149 -0
- package/out/synthesizers/german.js.map +1 -0
- package/out/synthesizers/house-venue.d.ts +56 -0
- package/out/synthesizers/house-venue.d.ts.map +1 -0
- package/out/synthesizers/house-venue.js +247 -0
- package/out/synthesizers/house-venue.js.map +1 -0
- package/out/synthesizers/intersection.d.ts +52 -0
- package/out/synthesizers/intersection.d.ts.map +1 -0
- package/out/synthesizers/intersection.js +175 -0
- package/out/synthesizers/intersection.js.map +1 -0
- package/out/synthesizers/no-street.d.ts +72 -0
- package/out/synthesizers/no-street.d.ts.map +1 -0
- package/out/synthesizers/no-street.js +262 -0
- package/out/synthesizers/no-street.js.map +1 -0
- package/out/synthesizers/po-box.d.ts +108 -0
- package/out/synthesizers/po-box.d.ts.map +1 -0
- package/out/synthesizers/po-box.js +250 -0
- package/out/synthesizers/po-box.js.map +1 -0
- package/out/synthesizers/street.d.ts +54 -0
- package/out/synthesizers/street.d.ts.map +1 -0
- package/out/synthesizers/street.js +218 -0
- package/out/synthesizers/street.js.map +1 -0
- package/out/synthesizers/utils.d.ts +241 -0
- package/out/synthesizers/utils.d.ts.map +1 -0
- package/out/synthesizers/utils.js +776 -0
- package/out/synthesizers/utils.js.map +1 -0
- package/out/test-kit/corpus-recipe.d.ts +59 -0
- package/out/test-kit/corpus-recipe.d.ts.map +1 -0
- package/out/test-kit/corpus-recipe.js +39 -0
- package/out/test-kit/corpus-recipe.js.map +1 -0
- package/out/test-kit/index.d.ts +48 -0
- package/out/test-kit/index.d.ts.map +1 -0
- package/out/test-kit/index.js +78 -0
- package/out/test-kit/index.js.map +1 -0
- package/out/tools/align-slice.d.ts +7 -0
- package/out/tools/align-slice.d.ts.map +1 -0
- package/out/tools/align-slice.js +55 -0
- package/out/tools/align-slice.js.map +1 -0
- package/out/tools/audit.d.ts +29 -0
- package/out/tools/audit.d.ts.map +1 -0
- package/out/tools/audit.js +282 -0
- package/out/tools/audit.js.map +1 -0
- package/out/tools/corpus-stats.d.ts +44 -0
- package/out/tools/corpus-stats.d.ts.map +1 -0
- package/out/tools/corpus-stats.js +102 -0
- package/out/tools/corpus-stats.js.map +1 -0
- package/out/tools/fetch/ban.d.ts +31 -0
- package/out/tools/fetch/ban.d.ts.map +1 -0
- package/out/tools/fetch/ban.js +239 -0
- package/out/tools/fetch/ban.js.map +1 -0
- package/out/tools/fetch/download.d.ts +117 -0
- package/out/tools/fetch/download.d.ts.map +1 -0
- package/out/tools/fetch/download.js +160 -0
- package/out/tools/fetch/download.js.map +1 -0
- package/out/tools/fetch/geonames-dump.d.ts +91 -0
- package/out/tools/fetch/geonames-dump.d.ts.map +1 -0
- package/out/tools/fetch/geonames-dump.js +171 -0
- package/out/tools/fetch/geonames-dump.js.map +1 -0
- package/out/tools/fetch/geonames-postal.d.ts +76 -0
- package/out/tools/fetch/geonames-postal.d.ts.map +1 -0
- package/out/tools/fetch/geonames-postal.js +126 -0
- package/out/tools/fetch/geonames-postal.js.map +1 -0
- package/out/tools/fetch/hrsa.d.ts +18 -0
- package/out/tools/fetch/hrsa.d.ts.map +1 -0
- package/out/tools/fetch/hrsa.js +46 -0
- package/out/tools/fetch/hrsa.js.map +1 -0
- package/out/tools/fetch/imls-pls.d.ts +25 -0
- package/out/tools/fetch/imls-pls.d.ts.map +1 -0
- package/out/tools/fetch/imls-pls.js +108 -0
- package/out/tools/fetch/imls-pls.js.map +1 -0
- package/out/tools/fetch/index.d.ts +144 -0
- package/out/tools/fetch/index.d.ts.map +1 -0
- package/out/tools/fetch/index.js +143 -0
- package/out/tools/fetch/index.js.map +1 -0
- package/out/tools/fetch/nad.d.ts +70 -0
- package/out/tools/fetch/nad.d.ts.map +1 -0
- package/out/tools/fetch/nad.js +234 -0
- package/out/tools/fetch/nad.js.map +1 -0
- package/out/tools/fetch/nppes.d.ts +26 -0
- package/out/tools/fetch/nppes.d.ts.map +1 -0
- package/out/tools/fetch/nppes.js +126 -0
- package/out/tools/fetch/nppes.js.map +1 -0
- package/out/tools/fetch/openaddresses.d.ts +9 -0
- package/out/tools/fetch/openaddresses.d.ts.map +1 -0
- package/out/tools/fetch/openaddresses.js +279 -0
- package/out/tools/fetch/openaddresses.js.map +1 -0
- package/out/tools/fetch/ourairports.d.ts +45 -0
- package/out/tools/fetch/ourairports.d.ts.map +1 -0
- package/out/tools/fetch/ourairports.js +128 -0
- package/out/tools/fetch/ourairports.js.map +1 -0
- package/out/tools/fetch/ppd.d.ts.map +1 -0
- package/out/tools/fetch/ppd.js +85 -0
- package/out/tools/fetch/ppd.js.map +1 -0
- package/out/tools/fetch/state-hi-schools.d.ts +26 -0
- package/out/tools/fetch/state-hi-schools.d.ts.map +1 -0
- package/out/tools/fetch/state-hi-schools.js +112 -0
- package/out/tools/fetch/state-hi-schools.js.map +1 -0
- package/out/tools/fetch/state-sources.d.ts +26 -0
- package/out/tools/fetch/state-sources.d.ts.map +1 -0
- package/out/tools/fetch/state-sources.js +111 -0
- package/out/tools/fetch/state-sources.js.map +1 -0
- package/out/tools/fetch/tiger-full.d.ts +22 -0
- package/out/tools/fetch/tiger-full.d.ts.map +1 -0
- package/out/tools/fetch/tiger-full.js +217 -0
- package/out/tools/fetch/tiger-full.js.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts +171 -0
- package/out/tools/fetch/wikidata-subvenue.d.ts.map +1 -0
- package/out/tools/fetch/wikidata-subvenue.js +274 -0
- package/out/tools/fetch/wikidata-subvenue.js.map +1 -0
- package/out/tools/gb-title-case.d.ts.map +1 -0
- package/out/tools/gb-title-case.js.map +1 -0
- package/out/tools/golden-expand.d.ts +90 -0
- package/out/tools/golden-expand.d.ts.map +1 -0
- package/out/tools/golden-expand.js +406 -0
- package/out/tools/golden-expand.js.map +1 -0
- package/out/tools/golden-promote.d.ts.map +1 -0
- package/out/tools/golden-promote.js +240 -0
- package/out/tools/golden-promote.js.map +1 -0
- package/out/tools/golden-relabel-street.d.ts +196 -0
- package/out/tools/golden-relabel-street.d.ts.map +1 -0
- package/out/tools/golden-relabel-street.js +440 -0
- package/out/tools/golden-relabel-street.js.map +1 -0
- package/out/tools/index.d.ts +28 -0
- package/out/tools/index.d.ts.map +1 -0
- package/out/tools/index.js +28 -0
- package/out/tools/index.js.map +1 -0
- package/out/tools/ingest-csv.d.ts.map +1 -0
- package/out/tools/ingest-csv.js +265 -0
- package/out/tools/ingest-csv.js.map +1 -0
- package/out/tools/jsonl-to-parquet.d.ts +61 -0
- package/out/tools/jsonl-to-parquet.d.ts.map +1 -0
- package/out/tools/jsonl-to-parquet.js +150 -0
- package/out/tools/jsonl-to-parquet.js.map +1 -0
- package/out/tools/lint-slice-vocab.d.ts +90 -0
- package/out/tools/lint-slice-vocab.d.ts.map +1 -0
- package/out/tools/lint-slice-vocab.js +267 -0
- package/out/tools/lint-slice-vocab.js.map +1 -0
- package/out/tools/lint-slice.d.ts +93 -0
- package/out/tools/lint-slice.d.ts.map +1 -0
- package/out/tools/lint-slice.js +322 -0
- package/out/tools/lint-slice.js.map +1 -0
- package/out/tools/overlay-manifest.d.ts +39 -0
- package/out/tools/overlay-manifest.d.ts.map +1 -0
- package/out/tools/overlay-manifest.js +90 -0
- package/out/tools/overlay-manifest.js.map +1 -0
- package/out/tools/overture-subvenue.d.ts +112 -0
- package/out/tools/overture-subvenue.d.ts.map +1 -0
- package/out/tools/overture-subvenue.js +139 -0
- package/out/tools/overture-subvenue.js.map +1 -0
- package/out/tools/postcode-triples.d.ts +174 -0
- package/out/tools/postcode-triples.d.ts.map +1 -0
- package/out/tools/postcode-triples.js +292 -0
- package/out/tools/postcode-triples.js.map +1 -0
- package/out/tools/slice-kryptonite.d.ts +32 -0
- package/out/tools/slice-kryptonite.d.ts.map +1 -0
- package/out/tools/slice-kryptonite.js +99 -0
- package/out/tools/slice-kryptonite.js.map +1 -0
- package/out/tools/slice-translit.d.ts +51 -0
- package/out/tools/slice-translit.d.ts.map +1 -0
- package/out/tools/slice-translit.js +166 -0
- package/out/tools/slice-translit.js.map +1 -0
- package/out/tools/sub-venue/harvest.d.ts +100 -0
- package/out/tools/sub-venue/harvest.d.ts.map +1 -0
- package/out/tools/sub-venue/harvest.js +168 -0
- package/out/tools/sub-venue/harvest.js.map +1 -0
- package/out/tools/sub-venue/head-nouns.d.ts +50 -0
- package/out/tools/sub-venue/head-nouns.d.ts.map +1 -0
- package/out/tools/sub-venue/head-nouns.js +213 -0
- package/out/tools/sub-venue/head-nouns.js.map +1 -0
- package/out/tools/sub-venue/surfaces.d.ts +45 -0
- package/out/tools/sub-venue/surfaces.d.ts.map +1 -0
- package/out/tools/sub-venue/surfaces.js +77 -0
- package/out/tools/sub-venue/surfaces.js.map +1 -0
- package/out/tools/sub-venue/table.d.ts +229 -0
- package/out/tools/sub-venue/table.d.ts.map +1 -0
- package/out/tools/sub-venue/table.js +108 -0
- package/out/tools/sub-venue/table.js.map +1 -0
- package/out/tools/sub-venue/wikidata.d.ts +26 -0
- package/out/tools/sub-venue/wikidata.d.ts.map +1 -0
- package/out/tools/sub-venue/wikidata.js +62 -0
- package/out/tools/sub-venue/wikidata.js.map +1 -0
- package/out/tools/sub-venue-lexicon.d.ts +156 -0
- package/out/tools/sub-venue-lexicon.d.ts.map +1 -0
- package/out/tools/sub-venue-lexicon.js +283 -0
- package/out/tools/sub-venue-lexicon.js.map +1 -0
- package/out/tools/sub-venue-promotions.d.ts +94 -0
- package/out/tools/sub-venue-promotions.d.ts.map +1 -0
- package/out/tools/sub-venue-promotions.js +266 -0
- package/out/tools/sub-venue-promotions.js.map +1 -0
- package/out/types.d.ts +221 -0
- package/out/types.d.ts.map +1 -0
- package/out/types.js.map +1 -0
- package/out/utils/align.d.ts +93 -0
- package/out/utils/align.d.ts.map +1 -0
- package/out/utils/align.js +234 -0
- package/out/utils/align.js.map +1 -0
- package/out/utils/golden.d.ts +85 -0
- package/out/utils/golden.d.ts.map +1 -0
- package/out/utils/golden.js +127 -0
- package/out/utils/golden.js.map +1 -0
- package/out/utils/index.d.ts +14 -0
- package/out/utils/index.d.ts.map +1 -0
- package/out/utils/index.js +14 -0
- package/out/utils/index.js.map +1 -0
- package/out/utils/license.d.ts.map +1 -0
- package/out/utils/license.js.map +1 -0
- package/out/utils/parquet.d.ts +178 -0
- package/out/utils/parquet.d.ts.map +1 -0
- package/out/utils/parquet.js +371 -0
- package/out/utils/parquet.js.map +1 -0
- package/out/utils/slice-stats.d.ts +52 -0
- package/out/utils/slice-stats.d.ts.map +1 -0
- package/out/utils/slice-stats.js +58 -0
- package/out/utils/slice-stats.js.map +1 -0
- package/out/utils/split.d.ts +128 -0
- package/out/utils/split.d.ts.map +1 -0
- package/out/utils/split.js +204 -0
- package/out/utils/split.js.map +1 -0
- package/out/utils/tokenize.d.ts +64 -0
- package/out/utils/tokenize.d.ts.map +1 -0
- package/out/utils/tokenize.js +82 -0
- package/out/utils/tokenize.js.map +1 -0
- package/out/utils/wof-json.d.ts +113 -0
- package/out/utils/wof-json.d.ts.map +1 -0
- package/out/utils/wof-json.js +173 -0
- package/out/utils/wof-json.js.map +1 -0
- package/package.json +259 -194
- package/out/src/adapters/ban/adapter.d.ts.map +0 -1
- package/out/src/adapters/ban/adapter.js +0 -149
- package/out/src/adapters/ban/adapter.js.map +0 -1
- package/out/src/adapters/ban/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/ban/street-decompose.js +0 -75
- package/out/src/adapters/ban/street-decompose.js.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.d.ts.map +0 -1
- package/out/src/adapters/fcc-bdc/adapter.js +0 -144
- package/out/src/adapters/fcc-bdc/adapter.js.map +0 -1
- package/out/src/adapters/geonames/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames/adapter.js +0 -176
- package/out/src/adapters/geonames/adapter.js.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.d.ts +0 -41
- package/out/src/adapters/geonames-postal/adapter.d.ts.map +0 -1
- package/out/src/adapters/geonames-postal/adapter.js +0 -104
- package/out/src/adapters/geonames-postal/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/adapter.d.ts +0 -49
- package/out/src/adapters/gnaf/adapter.d.ts.map +0 -1
- package/out/src/adapters/gnaf/adapter.js +0 -124
- package/out/src/adapters/gnaf/adapter.js.map +0 -1
- package/out/src/adapters/gnaf/assemble.d.ts +0 -65
- package/out/src/adapters/gnaf/assemble.d.ts.map +0 -1
- package/out/src/adapters/gnaf/assemble.js +0 -154
- package/out/src/adapters/gnaf/assemble.js.map +0 -1
- package/out/src/adapters/index.d.ts +0 -51
- package/out/src/adapters/index.d.ts.map +0 -1
- package/out/src/adapters/index.js +0 -95
- package/out/src/adapters/index.js.map +0 -1
- package/out/src/adapters/openaddresses/adapter.d.ts.map +0 -1
- package/out/src/adapters/openaddresses/adapter.js +0 -186
- package/out/src/adapters/openaddresses/adapter.js.map +0 -1
- package/out/src/adapters/overture/adapter.d.ts +0 -48
- package/out/src/adapters/overture/adapter.d.ts.map +0 -1
- package/out/src/adapters/overture/adapter.js +0 -125
- package/out/src/adapters/overture/adapter.js.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.d.ts +0 -47
- package/out/src/adapters/state-hi-schools/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-hi-schools/adapter.js +0 -133
- package/out/src/adapters/state-hi-schools/adapter.js.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ia-contractors/adapter.js.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-ny-notaries/adapter.js.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.d.ts.map +0 -1
- package/out/src/adapters/state-tx-notaries/adapter.js.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.d.ts.map +0 -1
- package/out/src/adapters/synth-po-box/adapter.js +0 -140
- package/out/src/adapters/synth-po-box/adapter.js.map +0 -1
- package/out/src/adapters/tiger/adapter.d.ts +0 -55
- package/out/src/adapters/tiger/adapter.d.ts.map +0 -1
- package/out/src/adapters/tiger/adapter.js +0 -201
- package/out/src/adapters/tiger/adapter.js.map +0 -1
- package/out/src/adapters/tiger/street-decompose.d.ts.map +0 -1
- package/out/src/adapters/tiger/street-decompose.js +0 -90
- package/out/src/adapters/tiger/street-decompose.js.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts +0 -47
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js +0 -139
- package/out/src/adapters/usgov-hrsa-fqhc/adapter.js.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts +0 -36
- package/out/src/adapters/usgov-imls-pls/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-imls-pls/adapter.js +0 -114
- package/out/src/adapters/usgov-imls-pls/adapter.js.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts +0 -37
- package/out/src/adapters/usgov-irs-bmf/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-irs-bmf/adapter.js +0 -124
- package/out/src/adapters/usgov-irs-bmf/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.d.ts +0 -48
- package/out/src/adapters/usgov-nad/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nad/adapter.js +0 -252
- package/out/src/adapters/usgov-nad/adapter.js.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-nppes/adapter.js +0 -116
- package/out/src/adapters/usgov-nppes/adapter.js.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.d.ts.map +0 -1
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js +0 -156
- package/out/src/adapters/usgov-samhsa-treatment-locator/adapter.js.map +0 -1
- package/out/src/adapters/utils/index.d.ts +0 -150
- package/out/src/adapters/utils/index.d.ts.map +0 -1
- package/out/src/adapters/utils/index.js +0 -159
- package/out/src/adapters/utils/index.js.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-jp/adapter.js +0 -164
- package/out/src/adapters/wof-admin-jp/adapter.js.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.d.ts +0 -82
- package/out/src/adapters/wof-admin-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-admin-json/adapter.js +0 -224
- package/out/src/adapters/wof-admin-json/adapter.js.map +0 -1
- package/out/src/adapters/wof-json-rows.d.ts +0 -32
- package/out/src/adapters/wof-json-rows.d.ts.map +0 -1
- package/out/src/adapters/wof-json-rows.js +0 -45
- package/out/src/adapters/wof-json-rows.js.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts +0 -65
- package/out/src/adapters/wof-postalcode-json/adapter.d.ts.map +0 -1
- package/out/src/adapters/wof-postalcode-json/adapter.js +0 -160
- package/out/src/adapters/wof-postalcode-json/adapter.js.map +0 -1
- package/out/src/build.d.ts +0 -132
- package/out/src/build.d.ts.map +0 -1
- package/out/src/build.js +0 -251
- package/out/src/build.js.map +0 -1
- package/out/src/codex/us-fips-state.d.ts.map +0 -1
- package/out/src/codex/us-fips-state.js.map +0 -1
- package/out/src/index.d.ts +0 -14
- package/out/src/index.d.ts.map +0 -1
- package/out/src/index.js +0 -14
- package/out/src/index.js.map +0 -1
- package/out/src/name-prone-us-suffixes.d.ts +0 -12
- package/out/src/name-prone-us-suffixes.d.ts.map +0 -1
- package/out/src/name-prone-us-suffixes.js +0 -12
- package/out/src/name-prone-us-suffixes.js.map +0 -1
- package/out/src/parquet-wrapper/index.d.ts +0 -9
- package/out/src/parquet-wrapper/index.d.ts.map +0 -1
- package/out/src/parquet-wrapper/index.js +0 -9
- package/out/src/parquet-wrapper/index.js.map +0 -1
- package/out/src/parquet-wrapper/reader.d.ts +0 -34
- package/out/src/parquet-wrapper/reader.d.ts.map +0 -1
- package/out/src/parquet-wrapper/reader.js +0 -69
- package/out/src/parquet-wrapper/reader.js.map +0 -1
- package/out/src/parquet-wrapper/schema.d.ts +0 -49
- package/out/src/parquet-wrapper/schema.d.ts.map +0 -1
- package/out/src/parquet-wrapper/schema.js +0 -55
- package/out/src/parquet-wrapper/schema.js.map +0 -1
- package/out/src/parquet-wrapper/writer.d.ts +0 -46
- package/out/src/parquet-wrapper/writer.d.ts.map +0 -1
- package/out/src/parquet-wrapper/writer.js +0 -76
- package/out/src/parquet-wrapper/writer.js.map +0 -1
- package/out/src/runner.d.ts +0 -126
- package/out/src/runner.d.ts.map +0 -1
- package/out/src/runner.js +0 -189
- package/out/src/runner.js.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.d.ts +0 -20
- package/out/src/shard-recipes/anchor-absorption.d.ts.map +0 -1
- package/out/src/shard-recipes/anchor-absorption.js +0 -82
- package/out/src/shard-recipes/anchor-absorption.js.map +0 -1
- package/out/src/shard-recipes/bare-country.d.ts +0 -25
- package/out/src/shard-recipes/bare-country.d.ts.map +0 -1
- package/out/src/shard-recipes/bare-country.js +0 -87
- package/out/src/shard-recipes/bare-country.js.map +0 -1
- package/out/src/shard-recipes/boundary-stress.d.ts +0 -20
- package/out/src/shard-recipes/boundary-stress.d.ts.map +0 -1
- package/out/src/shard-recipes/boundary-stress.js +0 -83
- package/out/src/shard-recipes/boundary-stress.js.map +0 -1
- package/out/src/shard-recipes/country-balanced.d.ts +0 -32
- package/out/src/shard-recipes/country-balanced.d.ts.map +0 -1
- package/out/src/shard-recipes/country-balanced.js +0 -406
- package/out/src/shard-recipes/country-balanced.js.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts +0 -22
- package/out/src/shard-recipes/cz-pcfirst-preposition.d.ts.map +0 -1
- package/out/src/shard-recipes/cz-pcfirst-preposition.js +0 -100
- package/out/src/shard-recipes/cz-pcfirst-preposition.js.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.d.ts +0 -38
- package/out/src/shard-recipes/fr-admin-split.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-admin-split.js +0 -188
- package/out/src/shard-recipes/fr-admin-split.js.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.d.ts +0 -28
- package/out/src/shard-recipes/fr-bare-street.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-bare-street.js +0 -143
- package/out/src/shard-recipes/fr-bare-street.js.map +0 -1
- package/out/src/shard-recipes/fr-fragment.d.ts +0 -77
- package/out/src/shard-recipes/fr-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-fragment.js +0 -276
- package/out/src/shard-recipes/fr-fragment.js.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.d.ts +0 -32
- package/out/src/shard-recipes/fr-lieudit.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-lieudit.js +0 -226
- package/out/src/shard-recipes/fr-lieudit.js.map +0 -1
- package/out/src/shard-recipes/fr-order.d.ts +0 -38
- package/out/src/shard-recipes/fr-order.d.ts.map +0 -1
- package/out/src/shard-recipes/fr-order.js +0 -208
- package/out/src/shard-recipes/fr-order.js.map +0 -1
- package/out/src/shard-recipes/german.d.ts +0 -23
- package/out/src/shard-recipes/german.d.ts.map +0 -1
- package/out/src/shard-recipes/german.js +0 -132
- package/out/src/shard-recipes/german.js.map +0 -1
- package/out/src/shard-recipes/house-venue.d.ts +0 -18
- package/out/src/shard-recipes/house-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/house-venue.js +0 -74
- package/out/src/shard-recipes/house-venue.js.map +0 -1
- package/out/src/shard-recipes/index.d.ts +0 -24
- package/out/src/shard-recipes/index.d.ts.map +0 -1
- package/out/src/shard-recipes/index.js +0 -89
- package/out/src/shard-recipes/index.js.map +0 -1
- package/out/src/shard-recipes/intersection.d.ts +0 -42
- package/out/src/shard-recipes/intersection.d.ts.map +0 -1
- package/out/src/shard-recipes/intersection.js +0 -460
- package/out/src/shard-recipes/intersection.js.map +0 -1
- package/out/src/shard-recipes/locale.d.ts +0 -135
- package/out/src/shard-recipes/locale.d.ts.map +0 -1
- package/out/src/shard-recipes/locale.js +0 -459
- package/out/src/shard-recipes/locale.js.map +0 -1
- package/out/src/shard-recipes/nl-postcode.d.ts +0 -26
- package/out/src/shard-recipes/nl-postcode.d.ts.map +0 -1
- package/out/src/shard-recipes/nl-postcode.js +0 -102
- package/out/src/shard-recipes/nl-postcode.js.map +0 -1
- package/out/src/shard-recipes/no-fragment.d.ts +0 -43
- package/out/src/shard-recipes/no-fragment.d.ts.map +0 -1
- package/out/src/shard-recipes/no-fragment.js +0 -188
- package/out/src/shard-recipes/no-fragment.js.map +0 -1
- package/out/src/shard-recipes/no-street-led.d.ts +0 -24
- package/out/src/shard-recipes/no-street-led.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street-led.js +0 -121
- package/out/src/shard-recipes/no-street-led.js.map +0 -1
- package/out/src/shard-recipes/no-street.d.ts +0 -18
- package/out/src/shard-recipes/no-street.d.ts.map +0 -1
- package/out/src/shard-recipes/no-street.js +0 -72
- package/out/src/shard-recipes/no-street.js.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.d.ts +0 -38
- package/out/src/shard-recipes/po-box-cedex.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box-cedex.js +0 -726
- package/out/src/shard-recipes/po-box-cedex.js.map +0 -1
- package/out/src/shard-recipes/po-box.d.ts +0 -17
- package/out/src/shard-recipes/po-box.d.ts.map +0 -1
- package/out/src/shard-recipes/po-box.js +0 -101
- package/out/src/shard-recipes/po-box.js.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts +0 -47
- package/out/src/shard-recipes/reviewed-postcode-tail.d.ts.map +0 -1
- package/out/src/shard-recipes/reviewed-postcode-tail.js +0 -125
- package/out/src/shard-recipes/reviewed-postcode-tail.js.map +0 -1
- package/out/src/shard-recipes/scaffold.d.ts +0 -246
- package/out/src/shard-recipes/scaffold.d.ts.map +0 -1
- package/out/src/shard-recipes/scaffold.js +0 -137
- package/out/src/shard-recipes/scaffold.js.map +0 -1
- package/out/src/shard-recipes/si-bare-village.d.ts +0 -32
- package/out/src/shard-recipes/si-bare-village.d.ts.map +0 -1
- package/out/src/shard-recipes/si-bare-village.js +0 -88
- package/out/src/shard-recipes/si-bare-village.js.map +0 -1
- package/out/src/shard-recipes/street-affix.d.ts +0 -89
- package/out/src/shard-recipes/street-affix.d.ts.map +0 -1
- package/out/src/shard-recipes/street-affix.js +0 -578
- package/out/src/shard-recipes/street-affix.js.map +0 -1
- package/out/src/shard-recipes/street-bare.d.ts +0 -25
- package/out/src/shard-recipes/street-bare.d.ts.map +0 -1
- package/out/src/shard-recipes/street-bare.js +0 -86
- package/out/src/shard-recipes/street-bare.js.map +0 -1
- package/out/src/shard-recipes/street.d.ts +0 -15
- package/out/src/shard-recipes/street.d.ts.map +0 -1
- package/out/src/shard-recipes/street.js +0 -69
- package/out/src/shard-recipes/street.js.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.d.ts +0 -228
- package/out/src/shard-recipes/sub-venue-sources.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue-sources.js +0 -664
- package/out/src/shard-recipes/sub-venue-sources.js.map +0 -1
- package/out/src/shard-recipes/sub-venue.d.ts +0 -269
- package/out/src/shard-recipes/sub-venue.d.ts.map +0 -1
- package/out/src/shard-recipes/sub-venue.js +0 -710
- package/out/src/shard-recipes/sub-venue.js.map +0 -1
- package/out/src/shard-recipes/trailing-region.d.ts +0 -74
- package/out/src/shard-recipes/trailing-region.d.ts.map +0 -1
- package/out/src/shard-recipes/trailing-region.js +0 -157
- package/out/src/shard-recipes/trailing-region.js.map +0 -1
- package/out/src/shard-recipes/unit.d.ts +0 -29
- package/out/src/shard-recipes/unit.d.ts.map +0 -1
- package/out/src/shard-recipes/unit.js +0 -243
- package/out/src/shard-recipes/unit.js.map +0 -1
- package/out/src/synthesizers/anchor-absorption.d.ts +0 -63
- package/out/src/synthesizers/anchor-absorption.d.ts.map +0 -1
- package/out/src/synthesizers/anchor-absorption.js +0 -223
- package/out/src/synthesizers/anchor-absorption.js.map +0 -1
- package/out/src/synthesizers/boundary-stress.d.ts +0 -78
- package/out/src/synthesizers/boundary-stress.d.ts.map +0 -1
- package/out/src/synthesizers/boundary-stress.js +0 -455
- package/out/src/synthesizers/boundary-stress.js.map +0 -1
- package/out/src/synthesizers/german.d.ts +0 -107
- package/out/src/synthesizers/german.d.ts.map +0 -1
- package/out/src/synthesizers/german.js +0 -148
- package/out/src/synthesizers/german.js.map +0 -1
- package/out/src/synthesizers/house-venue.d.ts +0 -56
- package/out/src/synthesizers/house-venue.d.ts.map +0 -1
- package/out/src/synthesizers/house-venue.js +0 -267
- package/out/src/synthesizers/house-venue.js.map +0 -1
- package/out/src/synthesizers/intersection.d.ts +0 -52
- package/out/src/synthesizers/intersection.d.ts.map +0 -1
- package/out/src/synthesizers/intersection.js +0 -175
- package/out/src/synthesizers/intersection.js.map +0 -1
- package/out/src/synthesizers/no-street.d.ts +0 -72
- package/out/src/synthesizers/no-street.d.ts.map +0 -1
- package/out/src/synthesizers/no-street.js +0 -282
- package/out/src/synthesizers/no-street.js.map +0 -1
- package/out/src/synthesizers/po-box.d.ts +0 -104
- package/out/src/synthesizers/po-box.d.ts.map +0 -1
- package/out/src/synthesizers/po-box.js +0 -266
- package/out/src/synthesizers/po-box.js.map +0 -1
- package/out/src/synthesizers/street.d.ts +0 -54
- package/out/src/synthesizers/street.d.ts.map +0 -1
- package/out/src/synthesizers/street.js +0 -221
- package/out/src/synthesizers/street.js.map +0 -1
- package/out/src/synthesizers/utils.d.ts +0 -203
- package/out/src/synthesizers/utils.d.ts.map +0 -1
- package/out/src/synthesizers/utils.js +0 -708
- package/out/src/synthesizers/utils.js.map +0 -1
- package/out/src/tools/align-shard.d.ts +0 -8
- package/out/src/tools/align-shard.d.ts.map +0 -1
- package/out/src/tools/align-shard.js +0 -56
- package/out/src/tools/align-shard.js.map +0 -1
- package/out/src/tools/audit.d.ts +0 -28
- package/out/src/tools/audit.d.ts.map +0 -1
- package/out/src/tools/audit.js +0 -285
- package/out/src/tools/audit.js.map +0 -1
- package/out/src/tools/corpus-stats.d.ts +0 -44
- package/out/src/tools/corpus-stats.d.ts.map +0 -1
- package/out/src/tools/corpus-stats.js +0 -138
- package/out/src/tools/corpus-stats.js.map +0 -1
- package/out/src/tools/fetch/ban.d.ts +0 -31
- package/out/src/tools/fetch/ban.d.ts.map +0 -1
- package/out/src/tools/fetch/ban.js +0 -239
- package/out/src/tools/fetch/ban.js.map +0 -1
- package/out/src/tools/fetch/download.d.ts +0 -78
- package/out/src/tools/fetch/download.d.ts.map +0 -1
- package/out/src/tools/fetch/download.js +0 -116
- package/out/src/tools/fetch/download.js.map +0 -1
- package/out/src/tools/fetch/geonames-dump.d.ts +0 -87
- package/out/src/tools/fetch/geonames-dump.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-dump.js +0 -178
- package/out/src/tools/fetch/geonames-dump.js.map +0 -1
- package/out/src/tools/fetch/geonames-postal.d.ts +0 -76
- package/out/src/tools/fetch/geonames-postal.d.ts.map +0 -1
- package/out/src/tools/fetch/geonames-postal.js +0 -125
- package/out/src/tools/fetch/geonames-postal.js.map +0 -1
- package/out/src/tools/fetch/hrsa.d.ts +0 -18
- package/out/src/tools/fetch/hrsa.d.ts.map +0 -1
- package/out/src/tools/fetch/hrsa.js +0 -46
- package/out/src/tools/fetch/hrsa.js.map +0 -1
- package/out/src/tools/fetch/imls-pls.d.ts +0 -25
- package/out/src/tools/fetch/imls-pls.d.ts.map +0 -1
- package/out/src/tools/fetch/imls-pls.js +0 -108
- package/out/src/tools/fetch/imls-pls.js.map +0 -1
- package/out/src/tools/fetch/index.d.ts +0 -144
- package/out/src/tools/fetch/index.d.ts.map +0 -1
- package/out/src/tools/fetch/index.js +0 -143
- package/out/src/tools/fetch/index.js.map +0 -1
- package/out/src/tools/fetch/nad.d.ts +0 -70
- package/out/src/tools/fetch/nad.d.ts.map +0 -1
- package/out/src/tools/fetch/nad.js +0 -234
- package/out/src/tools/fetch/nad.js.map +0 -1
- package/out/src/tools/fetch/nppes.d.ts +0 -26
- package/out/src/tools/fetch/nppes.d.ts.map +0 -1
- package/out/src/tools/fetch/nppes.js +0 -126
- package/out/src/tools/fetch/nppes.js.map +0 -1
- package/out/src/tools/fetch/openaddresses.d.ts +0 -61
- package/out/src/tools/fetch/openaddresses.d.ts.map +0 -1
- package/out/src/tools/fetch/openaddresses.js +0 -317
- package/out/src/tools/fetch/openaddresses.js.map +0 -1
- package/out/src/tools/fetch/ourairports.d.ts +0 -45
- package/out/src/tools/fetch/ourairports.d.ts.map +0 -1
- package/out/src/tools/fetch/ourairports.js +0 -128
- package/out/src/tools/fetch/ourairports.js.map +0 -1
- package/out/src/tools/fetch/ppd.d.ts.map +0 -1
- package/out/src/tools/fetch/ppd.js +0 -100
- package/out/src/tools/fetch/ppd.js.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.d.ts +0 -25
- package/out/src/tools/fetch/state-hi-schools.d.ts.map +0 -1
- package/out/src/tools/fetch/state-hi-schools.js +0 -162
- package/out/src/tools/fetch/state-hi-schools.js.map +0 -1
- package/out/src/tools/fetch/state-sources.d.ts +0 -26
- package/out/src/tools/fetch/state-sources.d.ts.map +0 -1
- package/out/src/tools/fetch/state-sources.js +0 -111
- package/out/src/tools/fetch/state-sources.js.map +0 -1
- package/out/src/tools/fetch/tiger-full.d.ts +0 -42
- package/out/src/tools/fetch/tiger-full.d.ts.map +0 -1
- package/out/src/tools/fetch/tiger-full.js +0 -248
- package/out/src/tools/fetch/tiger-full.js.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.d.ts +0 -171
- package/out/src/tools/fetch/wikidata-subvenue.d.ts.map +0 -1
- package/out/src/tools/fetch/wikidata-subvenue.js +0 -275
- package/out/src/tools/fetch/wikidata-subvenue.js.map +0 -1
- package/out/src/tools/gb-title-case.d.ts.map +0 -1
- package/out/src/tools/gb-title-case.js.map +0 -1
- package/out/src/tools/golden-expand.d.ts +0 -90
- package/out/src/tools/golden-expand.d.ts.map +0 -1
- package/out/src/tools/golden-expand.js +0 -413
- package/out/src/tools/golden-expand.js.map +0 -1
- package/out/src/tools/golden-promote.d.ts.map +0 -1
- package/out/src/tools/golden-promote.js +0 -244
- package/out/src/tools/golden-promote.js.map +0 -1
- package/out/src/tools/golden-relabel-street.d.ts +0 -196
- package/out/src/tools/golden-relabel-street.d.ts.map +0 -1
- package/out/src/tools/golden-relabel-street.js +0 -440
- package/out/src/tools/golden-relabel-street.js.map +0 -1
- package/out/src/tools/index.d.ts +0 -28
- package/out/src/tools/index.d.ts.map +0 -1
- package/out/src/tools/index.js +0 -28
- package/out/src/tools/index.js.map +0 -1
- package/out/src/tools/ingest-csv.d.ts.map +0 -1
- package/out/src/tools/ingest-csv.js +0 -296
- package/out/src/tools/ingest-csv.js.map +0 -1
- package/out/src/tools/jsonl-to-parquet.d.ts +0 -61
- package/out/src/tools/jsonl-to-parquet.d.ts.map +0 -1
- package/out/src/tools/jsonl-to-parquet.js +0 -164
- package/out/src/tools/jsonl-to-parquet.js.map +0 -1
- package/out/src/tools/lint-shard-vocab.d.ts +0 -90
- package/out/src/tools/lint-shard-vocab.d.ts.map +0 -1
- package/out/src/tools/lint-shard-vocab.js +0 -281
- package/out/src/tools/lint-shard-vocab.js.map +0 -1
- package/out/src/tools/lint-shard.d.ts +0 -93
- package/out/src/tools/lint-shard.d.ts.map +0 -1
- package/out/src/tools/lint-shard.js +0 -354
- package/out/src/tools/lint-shard.js.map +0 -1
- package/out/src/tools/overlay-manifest.d.ts +0 -39
- package/out/src/tools/overlay-manifest.d.ts.map +0 -1
- package/out/src/tools/overlay-manifest.js +0 -98
- package/out/src/tools/overlay-manifest.js.map +0 -1
- package/out/src/tools/overture-subvenue.d.ts +0 -112
- package/out/src/tools/overture-subvenue.d.ts.map +0 -1
- package/out/src/tools/overture-subvenue.js +0 -144
- package/out/src/tools/overture-subvenue.js.map +0 -1
- package/out/src/tools/postcode-triples.d.ts +0 -175
- package/out/src/tools/postcode-triples.d.ts.map +0 -1
- package/out/src/tools/postcode-triples.js +0 -304
- package/out/src/tools/postcode-triples.js.map +0 -1
- package/out/src/tools/shard-kryptonite.d.ts +0 -32
- package/out/src/tools/shard-kryptonite.d.ts.map +0 -1
- package/out/src/tools/shard-kryptonite.js +0 -100
- package/out/src/tools/shard-kryptonite.js.map +0 -1
- package/out/src/tools/shard-translit.d.ts +0 -51
- package/out/src/tools/shard-translit.d.ts.map +0 -1
- package/out/src/tools/shard-translit.js +0 -175
- package/out/src/tools/shard-translit.js.map +0 -1
- package/out/src/tools/sub-venue/harvest.d.ts +0 -100
- package/out/src/tools/sub-venue/harvest.d.ts.map +0 -1
- package/out/src/tools/sub-venue/harvest.js +0 -168
- package/out/src/tools/sub-venue/harvest.js.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.d.ts +0 -50
- package/out/src/tools/sub-venue/head-nouns.d.ts.map +0 -1
- package/out/src/tools/sub-venue/head-nouns.js +0 -210
- package/out/src/tools/sub-venue/head-nouns.js.map +0 -1
- package/out/src/tools/sub-venue/surfaces.d.ts +0 -45
- package/out/src/tools/sub-venue/surfaces.d.ts.map +0 -1
- package/out/src/tools/sub-venue/surfaces.js +0 -77
- package/out/src/tools/sub-venue/surfaces.js.map +0 -1
- package/out/src/tools/sub-venue/table.d.ts +0 -229
- package/out/src/tools/sub-venue/table.d.ts.map +0 -1
- package/out/src/tools/sub-venue/table.js +0 -108
- package/out/src/tools/sub-venue/table.js.map +0 -1
- package/out/src/tools/sub-venue/wikidata.d.ts +0 -26
- package/out/src/tools/sub-venue/wikidata.d.ts.map +0 -1
- package/out/src/tools/sub-venue/wikidata.js +0 -62
- package/out/src/tools/sub-venue/wikidata.js.map +0 -1
- package/out/src/tools/sub-venue-lexicon.d.ts +0 -156
- package/out/src/tools/sub-venue-lexicon.d.ts.map +0 -1
- package/out/src/tools/sub-venue-lexicon.js +0 -282
- package/out/src/tools/sub-venue-lexicon.js.map +0 -1
- package/out/src/tools/sub-venue-promotions.d.ts +0 -94
- package/out/src/tools/sub-venue-promotions.d.ts.map +0 -1
- package/out/src/tools/sub-venue-promotions.js +0 -266
- package/out/src/tools/sub-venue-promotions.js.map +0 -1
- package/out/src/types.d.ts +0 -221
- package/out/src/types.d.ts.map +0 -1
- package/out/src/types.js.map +0 -1
- package/out/src/utils/align.d.ts +0 -93
- package/out/src/utils/align.d.ts.map +0 -1
- package/out/src/utils/align.js +0 -234
- package/out/src/utils/align.js.map +0 -1
- package/out/src/utils/golden.d.ts +0 -69
- package/out/src/utils/golden.d.ts.map +0 -1
- package/out/src/utils/golden.js +0 -127
- package/out/src/utils/golden.js.map +0 -1
- package/out/src/utils/index.d.ts +0 -14
- package/out/src/utils/index.d.ts.map +0 -1
- package/out/src/utils/index.js +0 -14
- package/out/src/utils/index.js.map +0 -1
- package/out/src/utils/license.d.ts.map +0 -1
- package/out/src/utils/license.js.map +0 -1
- package/out/src/utils/parquet.d.ts +0 -162
- package/out/src/utils/parquet.d.ts.map +0 -1
- package/out/src/utils/parquet.js +0 -262
- package/out/src/utils/parquet.js.map +0 -1
- package/out/src/utils/split.d.ts +0 -127
- package/out/src/utils/split.d.ts.map +0 -1
- package/out/src/utils/split.js +0 -204
- package/out/src/utils/split.js.map +0 -1
- package/out/src/utils/tokenize.d.ts +0 -56
- package/out/src/utils/tokenize.d.ts.map +0 -1
- package/out/src/utils/tokenize.js +0 -48
- package/out/src/utils/tokenize.js.map +0 -1
- package/out/src/utils/wof-json.d.ts +0 -109
- package/out/src/utils/wof-json.d.ts.map +0 -1
- package/out/src/utils/wof-json.js +0 -173
- package/out/src/utils/wof-json.js.map +0 -1
- package/src/adapters/ban/adapter.ts +0 -191
- package/src/adapters/ban/street-decompose.ts +0 -96
- package/src/adapters/fcc-bdc/adapter.ts +0 -174
- package/src/adapters/geonames/adapter.ts +0 -200
- package/src/adapters/geonames-postal/adapter.ts +0 -119
- package/src/adapters/gnaf/adapter.ts +0 -149
- package/src/adapters/gnaf/assemble.ts +0 -226
- package/src/adapters/index.ts +0 -149
- package/src/adapters/openaddresses/adapter.ts +0 -251
- package/src/adapters/overture/adapter.ts +0 -162
- package/src/adapters/state-hi-schools/adapter.ts +0 -164
- package/src/adapters/synth-po-box/adapter.ts +0 -204
- package/src/adapters/tiger/adapter.ts +0 -253
- package/src/adapters/tiger/street-decompose.ts +0 -111
- package/src/adapters/usgov-hrsa-fqhc/adapter.ts +0 -183
- package/src/adapters/usgov-imls-pls/adapter.ts +0 -143
- package/src/adapters/usgov-irs-bmf/adapter.ts +0 -163
- package/src/adapters/usgov-nad/adapter.ts +0 -348
- package/src/adapters/usgov-nppes/adapter.ts +0 -159
- package/src/adapters/usgov-samhsa-treatment-locator/adapter.ts +0 -204
- package/src/adapters/utils/index.ts +0 -233
- package/src/adapters/wof-admin-jp/adapter.ts +0 -216
- package/src/adapters/wof-admin-json/adapter.ts +0 -256
- package/src/adapters/wof-json-rows.ts +0 -79
- package/src/adapters/wof-postalcode-json/adapter.ts +0 -183
- package/src/build.ts +0 -386
- package/src/index.ts +0 -14
- package/src/name-prone-us-suffixes.ts +0 -12
- package/src/parquet-wrapper/index.ts +0 -9
- package/src/parquet-wrapper/reader.ts +0 -97
- package/src/parquet-wrapper/schema.ts +0 -88
- package/src/parquet-wrapper/writer.ts +0 -110
- package/src/runner.ts +0 -317
- package/src/shard-recipes/anchor-absorption.ts +0 -103
- package/src/shard-recipes/bare-country.ts +0 -95
- package/src/shard-recipes/boundary-stress.ts +0 -101
- package/src/shard-recipes/country-balanced.ts +0 -524
- package/src/shard-recipes/cz-pcfirst-preposition.ts +0 -111
- package/src/shard-recipes/fr-admin-split.ts +0 -239
- package/src/shard-recipes/fr-bare-street.ts +0 -170
- package/src/shard-recipes/fr-fragment.ts +0 -332
- package/src/shard-recipes/fr-lieudit.ts +0 -302
- package/src/shard-recipes/fr-order.ts +0 -258
- package/src/shard-recipes/german.ts +0 -170
- package/src/shard-recipes/house-venue.ts +0 -88
- package/src/shard-recipes/index.ts +0 -95
- package/src/shard-recipes/intersection.ts +0 -630
- package/src/shard-recipes/locale.ts +0 -599
- package/src/shard-recipes/nl-postcode.ts +0 -115
- package/src/shard-recipes/no-fragment.ts +0 -219
- package/src/shard-recipes/no-street-led.ts +0 -143
- package/src/shard-recipes/no-street.ts +0 -86
- package/src/shard-recipes/po-box-cedex.ts +0 -920
- package/src/shard-recipes/po-box.ts +0 -119
- package/src/shard-recipes/reviewed-postcode-tail.ts +0 -189
- package/src/shard-recipes/scaffold.ts +0 -360
- package/src/shard-recipes/si-bare-village.ts +0 -97
- package/src/shard-recipes/street-affix.ts +0 -826
- package/src/shard-recipes/street-bare.ts +0 -101
- package/src/shard-recipes/street.ts +0 -82
- package/src/shard-recipes/sub-venue-sources.ts +0 -885
- package/src/shard-recipes/sub-venue.ts +0 -984
- package/src/shard-recipes/trailing-region.ts +0 -183
- package/src/shard-recipes/unit.ts +0 -321
- package/src/synthesizers/anchor-absorption.ts +0 -290
- package/src/synthesizers/boundary-stress.ts +0 -531
- package/src/synthesizers/german.ts +0 -251
- package/src/synthesizers/house-venue.ts +0 -330
- package/src/synthesizers/intersection.ts +0 -232
- package/src/synthesizers/no-street.ts +0 -349
- package/src/synthesizers/po-box.ts +0 -339
- package/src/synthesizers/street.ts +0 -274
- package/src/synthesizers/utils.ts +0 -903
- package/src/tools/align-shard.ts +0 -70
- package/src/tools/audit.ts +0 -399
- package/src/tools/corpus-stats.ts +0 -184
- package/src/tools/fetch/ban.ts +0 -290
- package/src/tools/fetch/download.ts +0 -176
- package/src/tools/fetch/geonames-dump.ts +0 -267
- package/src/tools/fetch/geonames-postal.ts +0 -180
- package/src/tools/fetch/hrsa.ts +0 -68
- package/src/tools/fetch/imls-pls.ts +0 -158
- package/src/tools/fetch/index.ts +0 -147
- package/src/tools/fetch/nad.ts +0 -342
- package/src/tools/fetch/nppes.ts +0 -174
- package/src/tools/fetch/openaddresses.ts +0 -404
- package/src/tools/fetch/ourairports.ts +0 -171
- package/src/tools/fetch/ppd.ts +0 -137
- package/src/tools/fetch/state-hi-schools.ts +0 -208
- package/src/tools/fetch/state-sources.ts +0 -155
- package/src/tools/fetch/tiger-full.ts +0 -354
- package/src/tools/fetch/wikidata-subvenue.ts +0 -386
- package/src/tools/golden-expand.ts +0 -584
- package/src/tools/golden-promote.ts +0 -353
- package/src/tools/golden-relabel-street.ts +0 -685
- package/src/tools/index.ts +0 -28
- package/src/tools/ingest-csv.ts +0 -422
- package/src/tools/jsonl-to-parquet.ts +0 -221
- package/src/tools/lint-shard-vocab.ts +0 -409
- package/src/tools/lint-shard.ts +0 -543
- package/src/tools/overlay-manifest.ts +0 -157
- package/src/tools/overture-subvenue.ts +0 -215
- package/src/tools/postcode-triples.ts +0 -375
- package/src/tools/shard-kryptonite.ts +0 -139
- package/src/tools/shard-translit.ts +0 -245
- package/src/tools/sub-venue/harvest.ts +0 -235
- package/src/tools/sub-venue/head-nouns.ts +0 -242
- package/src/tools/sub-venue/surfaces.ts +0 -95
- package/src/tools/sub-venue/table.ts +0 -281
- package/src/tools/sub-venue/wikidata.ts +0 -85
- package/src/tools/sub-venue-lexicon.ts +0 -431
- package/src/tools/sub-venue-promotions.ts +0 -330
- package/src/types.ts +0 -247
- package/src/utils/align.ts +0 -331
- package/src/utils/golden.ts +0 -176
- package/src/utils/index.ts +0 -14
- package/src/utils/parquet.ts +0 -391
- package/src/utils/split.ts +0 -279
- package/src/utils/tokenize.ts +0 -78
- package/src/utils/wof-json.ts +0 -244
- /package/{src → lib}/adapters/state-ia-contractors/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-ny-notaries/adapter.ts +0 -0
- /package/{src → lib}/adapters/state-tx-notaries/adapter.ts +0 -0
- /package/{src → lib}/codex/us-fips-state.ts +0 -0
- /package/{src → lib}/tools/gb-title-case.ts +0 -0
- /package/{src → lib}/utils/license.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/ban/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/fcc-bdc/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/geonames/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/openaddresses/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ia-contractors/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-ny-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/state-tx-notaries/adapter.js +0 -0
- /package/out/{src/adapters → adapters}/synth-po-box/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/tiger/street-decompose.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-nppes/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/usgov-samhsa-treatment-locator/adapter.d.ts +0 -0
- /package/out/{src/adapters → adapters}/wof-admin-jp/adapter.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.d.ts +0 -0
- /package/out/{src/codex → codex}/us-fips-state.js +0 -0
- /package/out/{src/tools → tools}/fetch/ppd.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.d.ts +0 -0
- /package/out/{src/tools → tools}/gb-title-case.js +0 -0
- /package/out/{src/tools → tools}/golden-promote.d.ts +0 -0
- /package/out/{src/tools → tools}/ingest-csv.d.ts +0 -0
- /package/out/{src/types.js → types.js} +0 -0
- /package/out/{src/utils → utils}/license.d.ts +0 -0
- /package/out/{src/utils → utils}/license.js +0 -0
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"golden-relabel-street.js","sourceRoot":"","sources":["../../lib/tools/golden-relabel-street.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAwDG;AAEH,OAAO,EAAE,wBAAwB,EAAE,mBAAmB,EAAuB,MAAM,qBAAqB,CAAA;AACxG,OAAO,EAAE,UAAU,EAAE,oBAAoB,EAAE,eAAe,EAAE,iBAAiB,EAAE,MAAM,4BAA4B,CAAA;AACjH,OAAO,EAAE,eAAe,EAAE,cAAc,EAAE,kBAAkB,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAA;AACpH,OAAO,EAAE,UAAU,EAAE,MAAM,sBAAsB,CAAA;AACjD,OAAO,EAAE,eAAe,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAA;AACtE,OAAO,EAAE,SAAS,EAAE,MAAM,yBAAyB,CAAA;AACnD,OAAO,EAAE,YAAY,EAAE,MAAM,gCAAgC,CAAA;AAC7D,OAAO,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,SAAS,CAAA;AACxC,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C,OAAO,EAAE,sBAAsB,EAAE,MAAM,yBAAyB,CAAA;AAkFhE;;;;GAIG;AACH,SAAS,aAAa,CAAC,CAAS;IAC/B,IAAI,CAAC,KAAK,CAAC,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;QAAE,OAAO,IAAI,CAAA;IACrC,MAAM,KAAK,GAAG,oBAAoB,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IAE1C,IAAI,CAAC,KAAK;QAAE,OAAO,IAAI,CAAA;IAEvB,OAAO,EAAE,IAAI,EAAE,KAAK,CAAC,CAAC,CAAE,EAAE,GAAG,EAAE,KAAK,CAAC,CAAC,CAAE,EAAE,IAAI,EAAE,KAAK,CAAC,CAAC,CAAE,EAAE,CAAA;AAC5D,CAAC;AAED;;;GAGG;AACH,SAAS,cAAc,CAAC,CAAS;IAChC,IAAI,CAAC,KAAK,CAAC,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;QAAE,OAAO,IAAI,CAAA;IACrC,MAAM,KAAK,GAAG,oBAAoB,CAAC,IAAI,CAAC,CAAC,CAAC,CAAA;IAE1C,IAAI,CAAC,KAAK;QAAE,OAAO,IAAI,CAAA;IAEvB,OAAO,EAAE,IAAI,EAAE,KAAK,CAAC,CAAC,CAAE,EAAE,GAAG,EAAE,KAAK,CAAC,CAAC,CAAE,EAAE,IAAI,EAAE,KAAK,CAAC,CAAC,CAAE,EAAE,CAAA;AAC5D,CAAC;AAED,8EAA8E;AAE9E;;;GAGG;AACH,SAAS,eAAe,CACvB,UAAkC,EAClC,KAA2D;IAE3D,MAAM,GAAG,GAA2B,EAAE,CAAA;IAEtC,KAAK,MAAM,CAAC,GAAG,EAAE,KAAK,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,UAAU,CAAC,EAAE,CAAC;QACvD,IAAI,GAAG,KAAK,QAAQ,EAAE,CAAC;YACtB,IAAI,KAAK,CAAC,MAAM,EAAE,CAAC;gBAClB,GAAG,CAAC,aAAa,GAAG,KAAK,CAAC,MAAM,CAAA;YACjC,CAAC;YAED,GAAG,CAAC,MAAM,GAAG,KAAK,CAAC,MAAM,CAAA;YAEzB,IAAI,KAAK,CAAC,MAAM,EAAE,CAAC;gBAClB,GAAG,CAAC,aAAa,GAAG,KAAK,CAAC,MAAM,CAAA;YACjC,CAAC;YAED,SAAQ;QACT,CAAC;QAED,IAAI,GAAG,KAAK,eAAe,IAAI,GAAG,KAAK,eAAe;YAAE,SAAQ;QAChE,GAAG,CAAC,GAAG,CAAC,GAAG,KAAK,CAAA;IACjB,CAAC;IAED,OAAO,GAAG,CAAA;AACX,CAAC;AAiBD;;;GAGG;AACH,MAAM,UAAU,sBAAsB,CACrC,GAAoB,EACpB,UAAmC,EAAE;IAErC,MAAM,WAAW,GAAG,OAAO,CAAC,WAAW,IAAI,IAAI,CAAA;IAE/C,MAAM,IAAI,GAAG,CAAC,QAA4B,EAAuB,EAAE,CAAC,CAAC;QACpE,GAAG;QACH,OAAO,EAAE,KAAK;QACd,QAAQ;QACR,KAAK,EAAE,EAAE;QACT,WAAW,EAAE,KAAK;KAClB,CAAC,CAAA;IAEF,IAAI,CAAC,GAAG,CAAC,OAAO,IAAI,EAAE,CAAC,CAAC,WAAW,EAAE,KAAK,IAAI;QAAE,OAAO,IAAI,CAAC,QAAQ,CAAC,CAAA;IACrE,MAAM,MAAM,GAAG,GAAG,CAAC,UAAU,CAAC,MAAM,CAAA;IAEpC,IAAI,CAAC,MAAM;QAAE,OAAO,IAAI,CAAC,WAAW,CAAC,CAAA;IAErC,IAAI,GAAG,CAAC,UAAU,CAAC,aAAa;QAAE,OAAO,IAAI,CAAC,eAAe,CAAC,CAAA;IAE9D,IAAI,MAAM,KAAK,MAAM,CAAC,IAAI,EAAE;QAAE,OAAO,IAAI,CAAC,kBAAkB,CAAC,CAAA;IAE7D,MAAM,KAAK,GAAwB,EAAE,CAAA;IACrC,IAAI,QAA4B,CAAA;IAChC,IAAI,IAAI,GAAG,MAAM,CAAA;IACjB,IAAI,MAA0B,CAAA;IAC9B,IAAI,SAAS,GAAG,EAAE,CAAA;IAClB,IAAI,SAAqC,CAAA;IAEzC,MAAM,KAAK,GAAG,aAAa,CAAC,MAAM,CAAC,CAAA;IAEnC,IAAI,CAAC,KAAK,EAAE,CAAC;QACZ,QAAQ,GAAG,mBAAmB,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,oBAAoB,CAAC,CAAC,CAAC,cAAc,CAAA;IAC/E,CAAC;SAAM,IAAI,wBAAwB,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,CAAC;QACjD,kGAAkG;QAClG,uEAAuE;QACvE,MAAM,KAAK,GAAG,aAAa,CAAC,KAAK,CAAC,IAAI,CAAC,CAAA;QACvC,MAAM,SAAS,GAAG,KAAK,CAAC,CAAC,CAAC,mBAAmB,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,IAAI,CAAA;QAEhE,IAAI,CAAC,KAAK,IAAI,CAAC,SAAS,EAAE,CAAC;YAC1B,QAAQ,GAAG,2BAA2B,CAAA;QACvC,CAAC;aAAM,CAAC;YACP,QAAQ,GAAG,8BAA8B,CAAA;YACzC,IAAI,GAAG,KAAK,CAAC,IAAI,CAAA;YACjB,MAAM,GAAG,GAAG,KAAK,CAAC,IAAI,GAAG,KAAK,CAAC,GAAG,GAAG,KAAK,CAAC,IAAI,EAAE,CAAA;YACjD,SAAS,GAAG,KAAK,CAAC,GAAG,CAAA;YACrB,SAAS,GAAG,SAAS,CAAC,SAAS,CAAA;QAChC,CAAC;IACF,CAAC;SAAM,CAAC;QACP,MAAM,SAAS,GAAG,mBAAmB,CAAC,MAAM,CAAC,CAAA;QAE7C,IAAI,CAAC,SAAS,EAAE,CAAC;YAChB,QAAQ,GAAG,iBAAiB,CAAA;QAC7B,CAAC;aAAM,CAAC;YACP,QAAQ,GAAG,cAAc,CAAA;YACzB,IAAI,GAAG,KAAK,CAAC,IAAI,CAAA;YACjB,MAAM,GAAG,KAAK,CAAC,IAAI,CAAA;YACnB,SAAS,GAAG,KAAK,CAAC,GAAG,CAAA;YACrB,SAAS,GAAG,SAAS,CAAC,SAAS,CAAA;QAChC,CAAC;IACF,CAAC;IAED,qGAAqG;IACrG,kEAAkE;IAClE,IAAI,MAA0B,CAAA;IAC9B,IAAI,SAAS,GAAG,EAAE,CAAA;IAElB,IAAI,WAAW,IAAI,CAAC,GAAG,CAAC,UAAU,CAAC,aAAa,EAAE,CAAC;QAClD,MAAM,IAAI,GAAG,cAAc,CAAC,IAAI,CAAC,CAAA;QAEjC,IAAI,IAAI,IAAI,wBAAwB,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC;YACjD,MAAM,GAAG,IAAI,CAAC,IAAI,CAAA;YAClB,SAAS,GAAG,IAAI,CAAC,GAAG,CAAA;YACpB,IAAI,GAAG,IAAI,CAAC,IAAI,CAAA;QACjB,CAAC;IACF,CAAC;IAED,IAAI,CAAC,MAAM,IAAI,CAAC,MAAM;QAAE,OAAO,IAAI,CAAC,QAAQ,CAAC,CAAA;IAE7C,IAAI,CAAC,MAAM,EAAE,CAAC;QACb,QAAQ,GAAG,mBAAmB,CAAA;IAC/B,CAAC;IAED,sGAAsG;IACtG,kEAAkE;IAClE,MAAM,OAAO,GAAG,GAAG,MAAM,CAAC,CAAC,CAAC,MAAM,GAAG,SAAS,CAAC,CAAC,CAAC,EAAE,GAAG,IAAI,GAAG,MAAM,CAAC,CAAC,CAAC,SAAS,GAAG,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAA;IAE/F,IAAI,OAAO,KAAK,MAAM,EAAE,CAAC;QACxB,MAAM,IAAI,KAAK,CAAC,kDAAkD,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,EAAE,CAAC,CAAA;IAC5F,CAAC;IAED,IAAI,SAAS,IAAI,sBAAsB,CAAC,GAAG,CAAC,SAAS,CAAC,EAAE,CAAC;QACxD,KAAK,CAAC,IAAI,CAAC;YACV,IAAI,EAAE,mBAAmB;YACzB,MAAM,EAAE,GAAG,SAAS,8CAA8C;SAClE,CAAC,CAAA;IACH,CAAC;IAED,MAAM,KAAK,GAAG,GAAG,CAAC,UAAU,CAAC,KAAK,CAAA;IAElC,IAAI,MAAM,IAAI,KAAK,IAAI,IAAI,MAAM,CAAC,UAAU,YAAY,CAAC,MAAM,CAAC,SAAS,EAAE,GAAG,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,EAAE,CAAC;QAC7F,KAAK,CAAC,IAAI,CAAC;YACV,IAAI,EAAE,eAAe;YACrB,MAAM,EAAE,SAAS,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,iBAAiB,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,EAAE;SAC/E,CAAC,CAAA;IACH,CAAC;IAED,qGAAqG;IACrG,sGAAsG;IACtG,uGAAuG;IACvG,2BAA2B;IAC3B,IAAI,wBAAwB,CAAC,IAAI,CAAC,EAAE,CAAC;QACpC,KAAK,CAAC,IAAI,CAAC;YACV,IAAI,EAAE,oBAAoB;YAC1B,MAAM,EAAE,4CAA4C,IAAI,CAAC,SAAS,CAAC,IAAI,CAAC,EAAE;SAC1E,CAAC,CAAA;IACH,CAAC;IAED,OAAO;QACN,GAAG,EAAE;YACJ,GAAG,GAAG;YACN,UAAU,EAAE,eAAe,CAAC,GAAG,CAAC,UAAU,EAAE;gBAC3C,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC,UAAU,CAAC,aAAa,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,GAAG,CAAC,UAAU,CAAC,aAAa,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;gBACvG,MAAM,EAAE,IAAI;gBACZ,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;aAC7B,CAAC;SACF;QACD,OAAO,EAAE,IAAI;QACb,QAAQ;QACR,KAAK;QACL,WAAW,EAAE,OAAO,CAAC,MAAM,CAAC;QAC5B,YAAY,EAAE,MAAM;KACpB,CAAA;AACF,CAAC;AAkED,MAAM,YAAY,GAAG,GAAwB,EAAE,CAAC,CAAC;IAChD,cAAc,EAAE,CAAC;IACjB,8BAA8B,EAAE,CAAC;IACjC,mBAAmB,EAAE,CAAC;IACtB,eAAe,EAAE,CAAC;IAClB,cAAc,EAAE,CAAC;IACjB,oBAAoB,EAAE,CAAC;IACvB,2BAA2B,EAAE,CAAC;IAC9B,iBAAiB,EAAE,CAAC;IACpB,WAAW,EAAE,CAAC;IACd,QAAQ,EAAE,CAAC;IACX,kBAAkB,EAAE,CAAC;CACrB,CAAC,CAAA;AAEF;;;GAGG;AACH,MAAM,qBAAqB,GAAoC,IAAI,GAAG,CAAC;IACtE,oBAAoB;IACpB,2BAA2B;IAC3B,kBAAkB;CAClB,CAAC,CAAA;AAEF;;;;GAIG;AACH,MAAM,CAAC,KAAK,UAAU,sBAAsB,CAC3C,OAA6B,EAC7B,SAAiC,OAAO,CAAC,GAAG;IAE5C,MAAM,EAAE,KAAK,EAAE,MAAM,EAAE,GAAG,OAAO,CAAA;IACjC,MAAM,QAAQ,GAAG,OAAO,CAAC,IAAI,IAAI,IAAI,CAAC,MAAM,EAAE,mBAAmB,CAAC,CAAA;IAClE,MAAM,eAAe,CAAC,MAAM,CAAC,CAAA;IAE7B,MAAM,IAAI,GAA6B,EAAE,CAAA;IACzC,MAAM,KAAK,GAAiC,EAAE,CAAA;IAE9C,MAAM,IAAI,GAAG,KAAK,EAAE,KAAa,EAAE,MAAc,EAAE,MAAc,EAAiB,EAAE;QACnF,MAAM,eAAe,CAAC,MAAM,CAAC,CAAA;QAE7B,KAAK,MAAM,IAAI,IAAI,MAAM,oBAAoB,CAAC,KAAK,CAAC,EAAE,CAAC;YACtD,MAAM,IAAI,GAAG,IAAI,CAAC,KAAK,EAAE,IAAI,CAAC,IAAI,CAAC,CAAA;YACnC,MAAM,EAAE,GAAG,IAAI,CAAC,MAAM,EAAE,IAAI,CAAC,IAAI,CAAC,CAAA;YAElC,IAAI,IAAI,CAAC,WAAW,EAAE,EAAE,CAAC;gBACxB,MAAM,IAAI,CAAC,IAAI,EAAE,EAAE,EAAE,GAAG,MAAM,GAAG,IAAI,CAAC,IAAI,GAAG,CAAC,CAAA;gBAE9C,SAAQ;YACT,CAAC;YAED,IAAI,CAAC,IAAI,CAAC,IAAI,CAAC,QAAQ,CAAC,QAAQ,CAAC,EAAE,CAAC;gBACnC,uFAAuF;gBACvF,IAAI,IAAI,CAAC,IAAI,KAAK,eAAe,EAAE,CAAC;oBACnC,MAAM,cAAc,CAAC,MAAM,eAAe,CAAC,IAAI,CAAC,EAAE,EAAE,CAAC,CAAA;gBACtD,CAAC;gBAED,SAAQ;YACT,CAAC;YAED,MAAM,MAAM,GAAG,YAAY,EAAE,CAAA;YAC7B,IAAI,OAAO,GAAG,CAAC,CAAA;YACf,IAAI,OAAO,GAAG,CAAC,CAAA;YACf,IAAI,WAAW,GAAG,CAAC,CAAA;YACnB,MAAM,GAAG,GAAa,EAAE,CAAA;YACxB,IAAI,UAAU,GAAG,CAAC,CAAA;YAElB,KAAK,MAAM,IAAI,IAAI,eAAe,CAAC,IAAI,CAAC,MAAM,iBAAiB,CAAC,IAAI,CAAC,CAAC,EAAE,CAAC;gBACxE,IAAI,CAAC,IAAI,CAAC,IAAI,EAAE;oBAAE,SAAQ;gBAE1B,UAAU,EAAE,CAAA;gBACZ,2FAA2F;gBAC3F,yEAAyE;gBACzE,MAAM,GAAG,GAAG,eAAe,CAAkB,IAAI,CAAC,CAAA;gBAClD,MAAM,MAAM,GAAG,sBAAsB,CAAC,GAAG,EAAE,EAAE,WAAW,EAAE,OAAO,CAAC,WAAW,IAAI,IAAI,EAAE,CAAC,CAAA;gBAExF,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,EAAE,CAAA;gBAEzB,IAAI,MAAM,CAAC,OAAO,EAAE,CAAC;oBACpB,OAAO,EAAE,CAAA;gBACV,CAAC;gBAED,IAAI,MAAM,CAAC,WAAW,EAAE,CAAC;oBACxB,WAAW,EAAE,CAAA;gBACd,CAAC;gBAED,IAAI,MAAM,CAAC,KAAK,CAAC,MAAM,EAAE,CAAC;oBACzB,OAAO,EAAE,CAAA;gBACV,CAAC;gBAED,IAAI,MAAM,CAAC,OAAO,IAAI,qBAAqB,CAAC,GAAG,CAAC,MAAM,CAAC,QAAQ,CAAC,EAAE,CAAC;oBAClE,IAAI,CAAC,IAAI,CAAC;wBACT,IAAI,EAAE,GAAG,MAAM,GAAG,IAAI,CAAC,IAAI,EAAE;wBAC7B,IAAI,EAAE,UAAU;wBAChB,GAAG,EAAE,GAAG,CAAC,GAAG;wBACZ,QAAQ,EAAE,MAAM,CAAC,QAAQ;wBACzB,MAAM,EAAE,GAAG,CAAC,UAAU;wBACtB,KAAK,EAAE,MAAM,CAAC,GAAG,CAAC,UAAU;wBAC5B,KAAK,EAAE,MAAM,CAAC,KAAK;qBACnB,CAAC,CAAA;gBACH,CAAC;gBAED,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAA;YACrC,CAAC;YAED,MAAM,kBAAkB,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,IAAI,EAAE,EAAE,CAAC,CAAA;YACnD,KAAK,CAAC,GAAG,MAAM,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC,GAAG,EAAE,OAAO,EAAE,UAAU,EAAE,OAAO,EAAE,OAAO,EAAE,WAAW,EAAE,MAAM,EAAE,CAAA;YAE/F,MAAM,CACL,KAAK,MAAM,GAAG,IAAI,CAAC,IAAI,KAAK,UAAU,UAAU,OAAO,aAAa,WAAW,yBAAyB,OAAO,UAAU,CACzH,CAAA;QACF,CAAC;IACF,CAAC,CAAA;IAED,MAAM,CAAC,WAAW,KAAK,MAAM,MAAM,EAAE,CAAC,CAAA;IACtC,MAAM,IAAI,CAAC,KAAK,EAAE,MAAM,EAAE,EAAE,CAAC,CAAA;IAE7B,MAAM,kBAAkB,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,IAAI,EAAE,QAAQ,CAAC,CAAA;IAChG,MAAM,cAAc,CAAC,kBAAkB,CAAC,IAAI,EAAE,QAAQ,CAAC,KAAK,CAAC,EAAE,QAAQ,CAAC,MAAM,CAAC,CAAC,EAAE,QAAQ,CAAC,OAAO,CAAC,UAAU,EAAE,KAAK,CAAC,CAAC,CAAA;IAEtH,MAAM,aAAa,GAGf,EAAE,CAAA;IAEN,KAAK,MAAM,CAAC,IAAI,EAAE,KAAK,CAAC,IAAI,MAAM,CAAC,OAAO,CAAC,KAAK,CAAC,EAAE,CAAC;QACnD,aAAa,CAAC,IAAI,CAAC,GAAG;YACrB,OAAO,EAAE,KAAK,CAAC,OAAO;YACtB,MAAM,EAAE,MAAM,UAAU,CAAC,IAAI,CAAC,MAAM,EAAE,IAAI,CAAC,CAAC;YAC5C,OAAO,EAAE,KAAK,CAAC,OAAO;YACtB,OAAO,EAAE,KAAK,CAAC,OAAO;YACtB,YAAY,EAAE,KAAK,CAAC,WAAW;SAC/B,CAAA;IACF,CAAC;IAED,MAAM,YAAY,GAAG,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,CAAC,CAAC,CAAA;IAC5E,MAAM,YAAY,GAAG,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,CAAC,CAAC,CAAA;IAE5E,MAAM,QAAQ,GAAG;QAChB,OAAO,EAAE,QAAQ,CAAC,MAAM,CAAC;QACzB,MAAM,EAAE,OAAO,CAAC,WAAW,IAAI,QAAQ,CAAC,KAAK,CAAC;QAC9C,YAAY,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;QACtC,IAAI,EAAE,6EAA6E;QACnF,GAAG,CAAC,OAAO,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,MAAM,EAAE,OAAO,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;QACrD,UAAU,EAAE;YACX,iBAAiB,EAAE,EAAE,EAAE,EAAE,OAAO,EAAE,GAAG,EAAE,QAAQ,EAAE;YACjD,QAAQ,EACP,uGAAuG;gBACvG,0GAA0G;gBAC1G,qGAAqG;gBACrG,oGAAoG;gBACpG,aAAa;YACd,UAAU,EACT,mFAAmF;gBACnF,+CAA+C;YAChD,WAAW,EACV,wGAAwG;gBACxG,uDAAuD;YACxD,YAAY,EAAE,OAAO,CAAC,WAAW,IAAI,IAAI;SACzC;QACD,MAAM,EAAE;YACP,OAAO,EAAE,YAAY;YACrB,OAAO,EAAE,YAAY;YACrB,YAAY,EAAE,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,WAAW,EAAE,CAAC,CAAC;YACzE,QAAQ,EAAE,MAAM,CAAC,WAAW,CAAC,MAAM,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,EAAE,KAAK,CAAC,EAAE,EAAE,CAAC,CAAC,IAAI,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC,CAAC;SAChG;QACD,KAAK,EAAE,aAAa;QACpB,WAAW,EAAE,QAAQ,CAAC,QAAQ,CAAC;KAC/B,CAAA;IAED,MAAM,kBAAkB,CAAC,QAAQ,EAAE,IAAI,CAAC,MAAM,EAAE,eAAe,CAAC,CAAC,CAAA;IACjE,MAAM,CAAC,KAAK,YAAY,gBAAgB,YAAY,sBAAsB,QAAQ,EAAE,CAAC,CAAA;IAErF,OAAO,EAAE,KAAK,EAAE,QAAQ,EAAE,SAAS,EAAE,MAAM,EAAE,YAAY,EAAE,YAAY,EAAE,CAAA;AAC1E,CAAC;AAED;;;;GAIG;AACH,SAAS,kBAAkB,CAAC,IAA8B,EAAE,MAAc,EAAE,OAAe;IAC1F,MAAM,IAAI,GAAG,CAAC,UAAkC,EAAU,EAAE,CAC3D,CAAC,UAAU,CAAC,aAAa,EAAE,UAAU,CAAC,MAAM,EAAE,UAAU,CAAC,aAAa,CAAC;SACrE,MAAM,CAAC,SAAS,CAAC;SACjB,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,CAAC,CAAC;SAC7B,IAAI,CAAC,KAAK,CAAC,CAAA;IAEd,mGAAmG;IACnG,MAAM,GAAG,GAAG,IAAI,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,CAAA;IAC7D,MAAM,OAAO,GAAG,GAAG,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,KAAK,CAAC,MAAM,CAAC,CAAA;IACzD,MAAM,MAAM,GAAG,GAAG,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,YAAY,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC,CAAA;IAClE,MAAM,KAAK,GAAG,GAAG,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC,KAAK,CAAC,KAAK,CAAC,MAAM,IAAI,CAAC,YAAY,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC,CAAA;IAEzF,MAAM,IAAI,GAAG,CAAC,OAAiC,EAAU,EAAE,CAC1D,OAAO;SACL,GAAG,CACH,CAAC,KAAK,EAAE,EAAE,CACT,KAAK,KAAK,CAAC,IAAI,IAAI,KAAK,CAAC,IAAI,MAAM,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,MAAM,KAAK,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,IAAI,GAAG,MAAM,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,GAAG,CAAC,IAAI,CACtK;SACA,IAAI,CAAC,IAAI,CAAC,CAAA;IAEb,MAAM,MAAM,GAAG,+DAA+D,CAAA;IAE9E,OAAO;QACN,gDAAgD,MAAM,MAAM,OAAO,EAAE;QACrE,EAAE;QACF,mFAAmF;QACnF,sFAAsF;QACtF,EAAE;QACF,eAAe,OAAO,CAAC,MAAM,oBAAoB;QACjD,EAAE;QACF,MAAM;QACN,IAAI,CAAC,OAAO,CAAC;QACb,EAAE;QACF,mBAAmB,MAAM,CAAC,MAAM,sCAAsC;QACtE,EAAE;QACF,MAAM;QACN,IAAI,CAAC,MAAM,CAAC;QACZ,EAAE;QACF,4BAA4B,KAAK,CAAC,MAAM,6CAA6C;QACrF,EAAE;QACF,MAAM;QACN,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC,EAAE,GAAG,CAAC,CAAC;QACzB,EAAE;KACF,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;AACb,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,YAAY,CAAC,QAA4B;IACxD,OAAO,QAAQ,KAAK,cAAc,IAAI,QAAQ,KAAK,8BAA8B,IAAI,QAAQ,KAAK,mBAAmB,CAAA;AACtH,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,0BAA0B,CAAC,GAAW;IAC3D,KAAK,MAAM,SAAS,IAAI,CAAC,IAAI,CAAC,GAAG,EAAE,eAAe,CAAC,EAAE,IAAI,CAAC,GAAG,EAAE,IAAI,EAAE,eAAe,CAAC,CAAC,EAAE,CAAC;QACxF,IAAI,CAAC,CAAC,MAAM,UAAU,CAAC,SAAS,CAAC,CAAC;YAAE,SAAQ;QAE5C,MAAM,QAAQ,GAAG,cAAc,CAC9B,MAAM,iBAAiB,CAAC,SAAS,CAAC,CAClC,CAAA;QAED,IAAI,QAAQ,EAAE,UAAU,EAAE,iBAAiB,EAAE,EAAE,KAAK,OAAO;YAAE,OAAO,IAAI,CAAA;IACzE,CAAC;IAED,OAAO,KAAK,CAAA;AACb,CAAC"}
|
|
@@ -0,0 +1,28 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Corpus operator tools — the `run()`-style modules behind `mailwoman corpus …` commands. No argv,
|
|
7
|
+
* no `process.exit`: commands own parsing, rendering, and exit codes.
|
|
8
|
+
*/
|
|
9
|
+
export * from "#tools/align-slice";
|
|
10
|
+
export * from "#tools/audit";
|
|
11
|
+
export * from "#tools/corpus-stats";
|
|
12
|
+
export * from "#tools/ingest-csv";
|
|
13
|
+
export * from "#tools/overlay-manifest";
|
|
14
|
+
export * from "#tools/fetch/download";
|
|
15
|
+
export * from "#tools/fetch/index";
|
|
16
|
+
export * from "#tools/golden-expand";
|
|
17
|
+
export * from "#tools/golden-promote";
|
|
18
|
+
export * from "#tools/golden-relabel-street";
|
|
19
|
+
export * from "#tools/jsonl-to-parquet";
|
|
20
|
+
export * from "#tools/lint-slice";
|
|
21
|
+
export * from "#tools/lint-slice-vocab";
|
|
22
|
+
export * from "#tools/slice-kryptonite";
|
|
23
|
+
export * from "#tools/overture-subvenue";
|
|
24
|
+
export * from "#tools/postcode-triples";
|
|
25
|
+
export * from "#tools/sub-venue-lexicon";
|
|
26
|
+
export * from "#tools/sub-venue-promotions";
|
|
27
|
+
export * from "#tools/slice-translit";
|
|
28
|
+
//# sourceMappingURL=index.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../lib/tools/index.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAEH,cAAc,oBAAoB,CAAA;AAClC,cAAc,cAAc,CAAA;AAC5B,cAAc,qBAAqB,CAAA;AACnC,cAAc,mBAAmB,CAAA;AACjC,cAAc,yBAAyB,CAAA;AACvC,cAAc,uBAAuB,CAAA;AACrC,cAAc,oBAAoB,CAAA;AAClC,cAAc,sBAAsB,CAAA;AACpC,cAAc,uBAAuB,CAAA;AACrC,cAAc,8BAA8B,CAAA;AAC5C,cAAc,yBAAyB,CAAA;AACvC,cAAc,mBAAmB,CAAA;AACjC,cAAc,yBAAyB,CAAA;AACvC,cAAc,yBAAyB,CAAA;AACvC,cAAc,0BAA0B,CAAA;AACxC,cAAc,yBAAyB,CAAA;AACvC,cAAc,0BAA0B,CAAA;AACxC,cAAc,6BAA6B,CAAA;AAC3C,cAAc,uBAAuB,CAAA"}
|
|
@@ -0,0 +1,28 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Corpus operator tools — the `run()`-style modules behind `mailwoman corpus …` commands. No argv,
|
|
7
|
+
* no `process.exit`: commands own parsing, rendering, and exit codes.
|
|
8
|
+
*/
|
|
9
|
+
export * from "#tools/align-slice";
|
|
10
|
+
export * from "#tools/audit";
|
|
11
|
+
export * from "#tools/corpus-stats";
|
|
12
|
+
export * from "#tools/ingest-csv";
|
|
13
|
+
export * from "#tools/overlay-manifest";
|
|
14
|
+
export * from "#tools/fetch/download";
|
|
15
|
+
export * from "#tools/fetch/index";
|
|
16
|
+
export * from "#tools/golden-expand";
|
|
17
|
+
export * from "#tools/golden-promote";
|
|
18
|
+
export * from "#tools/golden-relabel-street";
|
|
19
|
+
export * from "#tools/jsonl-to-parquet";
|
|
20
|
+
export * from "#tools/lint-slice";
|
|
21
|
+
export * from "#tools/lint-slice-vocab";
|
|
22
|
+
export * from "#tools/slice-kryptonite";
|
|
23
|
+
export * from "#tools/overture-subvenue";
|
|
24
|
+
export * from "#tools/postcode-triples";
|
|
25
|
+
export * from "#tools/sub-venue-lexicon";
|
|
26
|
+
export * from "#tools/sub-venue-promotions";
|
|
27
|
+
export * from "#tools/slice-translit";
|
|
28
|
+
//# sourceMappingURL=index.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"index.js","sourceRoot":"","sources":["../../lib/tools/index.ts"],"names":[],"mappings":"AAAA;;;;;;;GAOG;AAEH,cAAc,oBAAoB,CAAA;AAClC,cAAc,cAAc,CAAA;AAC5B,cAAc,qBAAqB,CAAA;AACnC,cAAc,mBAAmB,CAAA;AACjC,cAAc,yBAAyB,CAAA;AACvC,cAAc,uBAAuB,CAAA;AACrC,cAAc,oBAAoB,CAAA;AAClC,cAAc,sBAAsB,CAAA;AACpC,cAAc,uBAAuB,CAAA;AACrC,cAAc,8BAA8B,CAAA;AAC5C,cAAc,yBAAyB,CAAA;AACvC,cAAc,mBAAmB,CAAA;AACjC,cAAc,yBAAyB,CAAA;AACvC,cAAc,yBAAyB,CAAA;AACvC,cAAc,0BAA0B,CAAA;AACxC,cAAc,yBAAyB,CAAA;AACvC,cAAc,0BAA0B,CAAA;AACxC,cAAc,6BAA6B,CAAA;AAC3C,cAAc,uBAAuB,CAAA"}
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"ingest-csv.d.ts","sourceRoot":"","sources":["../../lib/tools/ingest-csv.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;GAyBG;AAyTH;;GAEG;AACH,MAAM,WAAW,gBAAgB;IAChC,KAAK,EAAE,MAAM,CAAA;IACb,KAAK,CAAC,EAAE,MAAM,CAAA;IACd,MAAM,CAAC,EAAE,MAAM,CAAA;IACf,MAAM,CAAC,EAAE,MAAM,CAAA;IACf,SAAS,CAAC,EAAE,MAAM,CAAA;IAClB,IAAI,CAAC,EAAE,MAAM,CAAA;IACb,QAAQ,CAAC,EAAE,OAAO,CAAA;IAClB,MAAM,CAAC,EAAE,OAAO,CAAA;CAChB;AAED;;;;;GAKG;AACH,wBAAsB,SAAS,CAAC,OAAO,EAAE,gBAAgB,GAAG,OAAO,CAAC,IAAI,CAAC,CAiBxE"}
|
|
@@ -0,0 +1,265 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* CSV → SQLite ingestion utility. Ported from isp-nexus's `sdk/data/csv.ts`.
|
|
7
|
+
*
|
|
8
|
+
* Reads a CSV file, infers column types from a sample of rows, creates a SQLite table, and imports
|
|
9
|
+
* the data. Handles quoted fields, NULL normalization, and duplicate column name disambiguation.
|
|
10
|
+
*
|
|
11
|
+
* ## Usage
|
|
12
|
+
*
|
|
13
|
+
* ```sh
|
|
14
|
+
* mailwoman corpus ingest-csv \
|
|
15
|
+
* --input /data/corpus/sources/usgov-nppes/npidata_pfile.csv \
|
|
16
|
+
* --table nppes_providers \
|
|
17
|
+
* --output /data/corpus/sources/usgov-nppes/nppes.db
|
|
18
|
+
* ```
|
|
19
|
+
*
|
|
20
|
+
* Options: --input <path> CSV file to ingest (required) --table <name> SQLite table name (default:
|
|
21
|
+
* derived from input filename) --output <path> SQLite database path (default: input dir /
|
|
22
|
+
* table.db) --sample <n> Rows to sample for type inference (default: 100) --separator <char>
|
|
23
|
+
* Field separator (default: ,) --skip <n> Lines to skip before header (default: 0) --no-header
|
|
24
|
+
* CSV has no header row — columns will be col_0, col_1, etc. --dry-run Infer schema and print
|
|
25
|
+
* CREATE TABLE, but don't import
|
|
26
|
+
*/
|
|
27
|
+
import { ByteFormatter } from "@mailwoman/core/fs/formatters";
|
|
28
|
+
import { tryStat, pathExists } from "@mailwoman/core/fs/readers";
|
|
29
|
+
import { makeDirectories, writeLocalJSONFile } from "@mailwoman/core/fs/writers";
|
|
30
|
+
import { basename, dirname, extname, join } from "path-ts";
|
|
31
|
+
import { CSVSpliterator } from "spliterator";
|
|
32
|
+
//#region Column name normalization
|
|
33
|
+
/**
|
|
34
|
+
* @deprecated belongs in core, if really needed. spliterator should handle this.
|
|
35
|
+
*/
|
|
36
|
+
function normalizeColumnName(raw) {
|
|
37
|
+
return (raw
|
|
38
|
+
.trim()
|
|
39
|
+
.replaceAll(/^"+|"+$/g, "")
|
|
40
|
+
.toLowerCase()
|
|
41
|
+
.replaceAll(/[^a-z0-9]+/g, "_")
|
|
42
|
+
.replaceAll(/^_|_$/g, "") || "unnamed");
|
|
43
|
+
}
|
|
44
|
+
function dedupColumns(names) {
|
|
45
|
+
const seen = new Map();
|
|
46
|
+
return names.map((name) => {
|
|
47
|
+
const count = seen.get(name) ?? 0;
|
|
48
|
+
seen.set(name, count + 1);
|
|
49
|
+
return count === 0 ? name : `${name}_${count + 1}`;
|
|
50
|
+
});
|
|
51
|
+
}
|
|
52
|
+
function normalizeField(raw) {
|
|
53
|
+
let s = raw.trim();
|
|
54
|
+
if (s.length >= 2 && s.startsWith('"') && s.endsWith('"')) {
|
|
55
|
+
s = s.slice(1, -1).replaceAll('""', '"');
|
|
56
|
+
}
|
|
57
|
+
// Normalize common null-like values
|
|
58
|
+
if (!s || s === "null" || s === "NULL" || s === "N/A" || s === "n/a" || s === "-" || s === "<UNAVAIL>") {
|
|
59
|
+
return null;
|
|
60
|
+
}
|
|
61
|
+
return s;
|
|
62
|
+
}
|
|
63
|
+
function inferColumnType(samples) {
|
|
64
|
+
let nullCount = 0;
|
|
65
|
+
let intCount = 0;
|
|
66
|
+
let realCount = 0;
|
|
67
|
+
let textCount = 0;
|
|
68
|
+
for (const s of samples) {
|
|
69
|
+
if (s === null) {
|
|
70
|
+
nullCount++;
|
|
71
|
+
continue;
|
|
72
|
+
}
|
|
73
|
+
if (/^-?\d+$/.test(s)) {
|
|
74
|
+
intCount++;
|
|
75
|
+
}
|
|
76
|
+
else if (/^-?\d+\.?\d+$/.test(s)) {
|
|
77
|
+
realCount++;
|
|
78
|
+
}
|
|
79
|
+
else {
|
|
80
|
+
textCount++;
|
|
81
|
+
}
|
|
82
|
+
}
|
|
83
|
+
const total = samples.length;
|
|
84
|
+
const type = realCount / total >= 0.5 ? "REAL" : intCount / total >= 0.5 ? "INTEGER" : "TEXT";
|
|
85
|
+
return { name: "", type, nullable: nullCount / total >= 0.5 };
|
|
86
|
+
}
|
|
87
|
+
async function runIngest(opts) {
|
|
88
|
+
// `header: false` with `drop` is what expresses `--skip N`: the spliterator's own header handling consumes the
|
|
89
|
+
// FIRST row as the header, and `drop` counts from the row after it, so a preamble before the header has to be
|
|
90
|
+
// dropped here and the header row taken by hand. Quote handling is end-to-end (quoted delimiters, doubled quotes);
|
|
91
|
+
// `skipEmpty` drops blank lines that readline would have turned into all-null rows. The early `break` closes the
|
|
92
|
+
// file descriptor.
|
|
93
|
+
const rows = () => CSVSpliterator.fromAsync(opts.inputPath, {
|
|
94
|
+
mode: "array",
|
|
95
|
+
header: false,
|
|
96
|
+
columnDelimiter: opts.separator,
|
|
97
|
+
drop: opts.skipLines,
|
|
98
|
+
enableQuoteHandling: true,
|
|
99
|
+
});
|
|
100
|
+
// --- Pass 1: read header + sample rows for type inference ---
|
|
101
|
+
process.stderr.write(`Reading ${opts.inputPath} for schema inference...\n`);
|
|
102
|
+
let headerRow = null;
|
|
103
|
+
const sampleRows = [];
|
|
104
|
+
for await (const row of rows()) {
|
|
105
|
+
if (!headerRow && opts.hasHeader) {
|
|
106
|
+
headerRow = row;
|
|
107
|
+
continue;
|
|
108
|
+
}
|
|
109
|
+
if (sampleRows.length < opts.sampleSize) {
|
|
110
|
+
sampleRows.push(row);
|
|
111
|
+
}
|
|
112
|
+
else {
|
|
113
|
+
break;
|
|
114
|
+
}
|
|
115
|
+
}
|
|
116
|
+
if (!headerRow && opts.hasHeader) {
|
|
117
|
+
throw new Error("No header line found in CSV");
|
|
118
|
+
}
|
|
119
|
+
// --- Determine column names ---
|
|
120
|
+
let rawHeaders;
|
|
121
|
+
if (opts.hasHeader && headerRow) {
|
|
122
|
+
rawHeaders = headerRow;
|
|
123
|
+
}
|
|
124
|
+
else {
|
|
125
|
+
// Auto-generate column names: col_0, col_1, ...
|
|
126
|
+
const numCols = sampleRows[0]?.length ?? 0;
|
|
127
|
+
rawHeaders = Array.from({ length: numCols }, (_, i) => `col_${i}`);
|
|
128
|
+
}
|
|
129
|
+
const colNames = dedupColumns(rawHeaders.map(normalizeColumnName));
|
|
130
|
+
// --- Infer column types ---
|
|
131
|
+
const columns = colNames.map((name, i) => {
|
|
132
|
+
const samples = sampleRows.map((row) => {
|
|
133
|
+
const raw = row[i] ?? "";
|
|
134
|
+
return normalizeField(raw);
|
|
135
|
+
});
|
|
136
|
+
const info = inferColumnType(samples);
|
|
137
|
+
info.name = name;
|
|
138
|
+
return info;
|
|
139
|
+
});
|
|
140
|
+
// --- Generate SQL ---
|
|
141
|
+
const colDefs = columns.map((c) => `"${c.name}" ${c.type}`).join(",\n ");
|
|
142
|
+
// Raw DDL by design: the column set + types are INFERRED from the CSV at runtime (colDefs above),
|
|
143
|
+
// so a Kysely builder loop would just wrap the same dynamic strings with ceremony and no type safety.
|
|
144
|
+
const createTableSQL = `CREATE TABLE IF NOT EXISTS "${opts.tableName}" (\n ${colDefs}\n);`;
|
|
145
|
+
const tempCols = columns.map((c) => `"${c.name}"`).join(", ");
|
|
146
|
+
process.stderr.write(`\nSchema inferred from ${sampleRows.length} sample rows:\n`);
|
|
147
|
+
process.stderr.write(`${createTableSQL}\n\n`);
|
|
148
|
+
if (opts.dryRun) {
|
|
149
|
+
process.stderr.write("--dry-run: stopping before import\n");
|
|
150
|
+
return;
|
|
151
|
+
}
|
|
152
|
+
// --- Create database + import ---
|
|
153
|
+
const { DatabaseClient } = await import("@mailwoman/sqlite/client");
|
|
154
|
+
await makeDirectories(dirname(opts.outputPath));
|
|
155
|
+
// `Database` — the EMPTY schema — deliberately, not by default: `createTableSQL` is built from the columns and
|
|
156
|
+
// types inferred from the CSV at runtime, so there is no table this file could name at compile time. Every write
|
|
157
|
+
// below goes through `exec`/`prepare` for the same reason.
|
|
158
|
+
using db = new DatabaseClient(opts.outputPath);
|
|
159
|
+
db.exec("PRAGMA journal_mode = OFF"); // faster for bulk import
|
|
160
|
+
db.exec("PRAGMA synchronous = OFF");
|
|
161
|
+
db.exec(createTableSQL);
|
|
162
|
+
// Use the .import approach via a temp table, then INSERT INTO ... SELECT to handle
|
|
163
|
+
// NULL normalization and type coercion.
|
|
164
|
+
// better-sqlite3 doesn't support .import natively, so we use a different approach:
|
|
165
|
+
// Read the CSV line-by-line and INSERT in a transaction.
|
|
166
|
+
process.stderr.write(`Importing rows...\n`);
|
|
167
|
+
const insertStmt = db.prepare(`INSERT INTO "${opts.tableName}" (${tempCols}) VALUES (${columns.map(() => "?").join(", ")})`);
|
|
168
|
+
let imported = 0;
|
|
169
|
+
let headerSkipped = false;
|
|
170
|
+
// node:sqlite has no `db.transaction(fn)` wrapper; use raw BEGIN/COMMIT around the batch.
|
|
171
|
+
const doInsert = () => {
|
|
172
|
+
db.exec("BEGIN");
|
|
173
|
+
try {
|
|
174
|
+
for (const row of batch) {
|
|
175
|
+
insertStmt.run(...row);
|
|
176
|
+
}
|
|
177
|
+
db.exec("COMMIT");
|
|
178
|
+
}
|
|
179
|
+
catch (error) {
|
|
180
|
+
db.exec("ROLLBACK");
|
|
181
|
+
throw error;
|
|
182
|
+
}
|
|
183
|
+
};
|
|
184
|
+
const batch = [];
|
|
185
|
+
const BATCH_SIZE = 10_000;
|
|
186
|
+
for await (const fields of rows()) {
|
|
187
|
+
if (opts.hasHeader && !headerSkipped) {
|
|
188
|
+
headerSkipped = true;
|
|
189
|
+
continue;
|
|
190
|
+
}
|
|
191
|
+
const values = fields.map((f, i) => {
|
|
192
|
+
const v = normalizeField(f);
|
|
193
|
+
if (v === null)
|
|
194
|
+
return null;
|
|
195
|
+
const col = columns[i];
|
|
196
|
+
if (col?.type === "INTEGER" && /^-?\d+$/.test(v))
|
|
197
|
+
return Number.parseInt(v, 10);
|
|
198
|
+
if (col?.type === "REAL" && /^-?\d+\.?\d+$/.test(v))
|
|
199
|
+
return Number.parseFloat(v);
|
|
200
|
+
return v;
|
|
201
|
+
});
|
|
202
|
+
// Pad or truncate to column count
|
|
203
|
+
while (values.length < columns.length) {
|
|
204
|
+
values.push(null);
|
|
205
|
+
}
|
|
206
|
+
values.length = columns.length;
|
|
207
|
+
batch.push(values);
|
|
208
|
+
if (batch.length >= BATCH_SIZE) {
|
|
209
|
+
doInsert();
|
|
210
|
+
imported += batch.length;
|
|
211
|
+
batch.length = 0;
|
|
212
|
+
if (imported % 100_000 === 0) {
|
|
213
|
+
process.stderr.write(` ${(imported / 1_000_000).toFixed(1)}M rows...\n`);
|
|
214
|
+
}
|
|
215
|
+
}
|
|
216
|
+
}
|
|
217
|
+
// Flush remaining
|
|
218
|
+
if (batch.length) {
|
|
219
|
+
doInsert();
|
|
220
|
+
imported += batch.length;
|
|
221
|
+
}
|
|
222
|
+
process.stderr.write(` Imported ${imported.toLocaleString()} rows into "${opts.tableName}"\n`);
|
|
223
|
+
// Build a basic index on the first TEXT column (likely the primary key)
|
|
224
|
+
const firstTextCol = columns.find((c) => c.type === "TEXT");
|
|
225
|
+
if (firstTextCol) {
|
|
226
|
+
process.stderr.write(`Building index on "${firstTextCol.name}"...\n`);
|
|
227
|
+
db.exec(`CREATE INDEX IF NOT EXISTS idx_${opts.tableName}_${firstTextCol.name} ON "${opts.tableName}"("${firstTextCol.name}");`);
|
|
228
|
+
}
|
|
229
|
+
const stat = await tryStat(opts.outputPath);
|
|
230
|
+
const manifest = {
|
|
231
|
+
ingested_at: new Date().toISOString(),
|
|
232
|
+
source_csv: basename(opts.inputPath),
|
|
233
|
+
table_name: opts.tableName,
|
|
234
|
+
columns: columns.map((c) => ({ name: c.name, type: c.type, nullable: c.nullable })),
|
|
235
|
+
row_count: imported,
|
|
236
|
+
db_bytes: stat.size,
|
|
237
|
+
};
|
|
238
|
+
const manifestPath = opts.outputPath.replace(/\.db$/, ".manifest.json");
|
|
239
|
+
await writeLocalJSONFile(manifest, manifestPath);
|
|
240
|
+
process.stderr.write(`Done. ${imported.toLocaleString()} rows → ${opts.outputPath} (${ByteFormatter.formatIEC(stat.size)})\n`);
|
|
241
|
+
}
|
|
242
|
+
/**
|
|
243
|
+
* Ingest a CSV into SQLite: infer column types from a sample, create the table, import the rows. Throws when `input` is
|
|
244
|
+
* missing. NOTE(phase1): progress narration still writes stderr directly — this predates the report-callback contract
|
|
245
|
+
* and the write sites are deep in the type-inference helpers; thread a report param if a caller ever needs to capture
|
|
246
|
+
* it.
|
|
247
|
+
*/
|
|
248
|
+
export async function ingestCSV(options) {
|
|
249
|
+
if (!(await pathExists(options.input))) {
|
|
250
|
+
throw new Error(`File not found: ${options.input}`);
|
|
251
|
+
}
|
|
252
|
+
const csvName = basename(options.input, extname(options.input));
|
|
253
|
+
await runIngest({
|
|
254
|
+
inputPath: options.input,
|
|
255
|
+
tableName: options.table ?? csvName.replaceAll(/[^a-zA-Z0-9_]/g, "_"),
|
|
256
|
+
outputPath: options.output ?? join(dirname(options.input), csvName + ".db"),
|
|
257
|
+
sampleSize: options.sample ?? 100,
|
|
258
|
+
separator: options.separator ?? ",",
|
|
259
|
+
skipLines: options.skip ?? 0,
|
|
260
|
+
hasHeader: !options.noHeader,
|
|
261
|
+
dryRun: options.dryRun ?? false,
|
|
262
|
+
});
|
|
263
|
+
}
|
|
264
|
+
//#endregion
|
|
265
|
+
//# sourceMappingURL=ingest-csv.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"ingest-csv.js","sourceRoot":"","sources":["../../lib/tools/ingest-csv.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;GAyBG;AAEH,OAAO,EAAE,aAAa,EAAE,MAAM,+BAA+B,CAAA;AAC7D,OAAO,EAAE,OAAO,EAAE,UAAU,EAAE,MAAM,4BAA4B,CAAA;AAChE,OAAO,EAAE,eAAe,EAAE,kBAAkB,EAAE,MAAM,4BAA4B,CAAA;AAGhF,OAAO,EAAE,QAAQ,EAAE,OAAO,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,SAAS,CAAA;AAC1D,OAAO,EAAE,cAAc,EAAE,MAAM,aAAa,CAAA;AAE5C,mCAAmC;AAEnC;;GAEG;AACH,SAAS,mBAAmB,CAAC,GAAW;IACvC,OAAO,CACN,GAAG;SACD,IAAI,EAAE;SACN,UAAU,CAAC,UAAU,EAAE,EAAE,CAAC;SAC1B,WAAW,EAAE;SACb,UAAU,CAAC,aAAa,EAAE,GAAG,CAAC;SAC9B,UAAU,CAAC,QAAQ,EAAE,EAAE,CAAC,IAAI,SAAS,CACvC,CAAA;AACF,CAAC;AAED,SAAS,YAAY,CAAC,KAAe;IACpC,MAAM,IAAI,GAAG,IAAI,GAAG,EAAkB,CAAA;IAEtC,OAAO,KAAK,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE;QACzB,MAAM,KAAK,GAAG,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACjC,IAAI,CAAC,GAAG,CAAC,IAAI,EAAE,KAAK,GAAG,CAAC,CAAC,CAAA;QAEzB,OAAO,KAAK,KAAK,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,GAAG,IAAI,IAAI,KAAK,GAAG,CAAC,EAAE,CAAA;IACnD,CAAC,CAAC,CAAA;AACH,CAAC;AAcD,SAAS,cAAc,CAAC,GAAW;IAClC,IAAI,CAAC,GAAG,GAAG,CAAC,IAAI,EAAE,CAAA;IAElB,IAAI,CAAC,CAAC,MAAM,IAAI,CAAC,IAAI,CAAC,CAAC,UAAU,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,QAAQ,CAAC,GAAG,CAAC,EAAE,CAAC;QAC3D,CAAC,GAAG,CAAC,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,UAAU,CAAC,IAAI,EAAE,GAAG,CAAC,CAAA;IACzC,CAAC;IAED,oCAAoC;IACpC,IAAI,CAAC,CAAC,IAAI,CAAC,KAAK,MAAM,IAAI,CAAC,KAAK,MAAM,IAAI,CAAC,KAAK,KAAK,IAAI,CAAC,KAAK,KAAK,IAAI,CAAC,KAAK,GAAG,IAAI,CAAC,KAAK,WAAW,EAAE,CAAC;QACxG,OAAO,IAAI,CAAA;IACZ,CAAC;IAED,OAAO,CAAC,CAAA;AACT,CAAC;AAED,SAAS,eAAe,CAAC,OAA0B;IAClD,IAAI,SAAS,GAAG,CAAC,CAAA;IACjB,IAAI,QAAQ,GAAG,CAAC,CAAA;IAChB,IAAI,SAAS,GAAG,CAAC,CAAA;IACjB,IAAI,SAAS,GAAG,CAAC,CAAA;IAEjB,KAAK,MAAM,CAAC,IAAI,OAAO,EAAE,CAAC;QACzB,IAAI,CAAC,KAAK,IAAI,EAAE,CAAC;YAChB,SAAS,EAAE,CAAA;YAEX,SAAQ;QACT,CAAC;QAED,IAAI,SAAS,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC;YACvB,QAAQ,EAAE,CAAA;QACX,CAAC;aAAM,IAAI,eAAe,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC;YACpC,SAAS,EAAE,CAAA;QACZ,CAAC;aAAM,CAAC;YACP,SAAS,EAAE,CAAA;QACZ,CAAC;IACF,CAAC;IAED,MAAM,KAAK,GAAG,OAAO,CAAC,MAAM,CAAA;IAC5B,MAAM,IAAI,GAAkB,SAAS,GAAG,KAAK,IAAI,GAAG,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,QAAQ,GAAG,KAAK,IAAI,GAAG,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,MAAM,CAAA;IAE5G,OAAO,EAAE,IAAI,EAAE,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,SAAS,GAAG,KAAK,IAAI,GAAG,EAAE,CAAA;AAC9D,CAAC;AAiBD,KAAK,UAAU,SAAS,CAAC,IAAmB;IAC3C,+GAA+G;IAC/G,8GAA8G;IAC9G,mHAAmH;IACnH,iHAAiH;IACjH,mBAAmB;IACnB,MAAM,IAAI,GAAG,GAA4B,EAAE,CAC1C,cAAc,CAAC,SAAS,CAAW,IAAI,CAAC,SAAS,EAAE;QAClD,IAAI,EAAE,OAAO;QACb,MAAM,EAAE,KAAK;QACb,eAAe,EAAE,IAAI,CAAC,SAAS;QAC/B,IAAI,EAAE,IAAI,CAAC,SAAS;QACpB,mBAAmB,EAAE,IAAI;KACzB,CAAC,CAAA;IAEH,+DAA+D;IAC/D,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,WAAW,IAAI,CAAC,SAAS,4BAA4B,CAAC,CAAA;IAE3E,IAAI,SAAS,GAAoB,IAAI,CAAA;IACrC,MAAM,UAAU,GAAe,EAAE,CAAA;IAEjC,IAAI,KAAK,EAAE,MAAM,GAAG,IAAI,IAAI,EAAE,EAAE,CAAC;QAChC,IAAI,CAAC,SAAS,IAAI,IAAI,CAAC,SAAS,EAAE,CAAC;YAClC,SAAS,GAAG,GAAG,CAAA;YAEf,SAAQ;QACT,CAAC;QAED,IAAI,UAAU,CAAC,MAAM,GAAG,IAAI,CAAC,UAAU,EAAE,CAAC;YACzC,UAAU,CAAC,IAAI,CAAC,GAAG,CAAC,CAAA;QACrB,CAAC;aAAM,CAAC;YACP,MAAK;QACN,CAAC;IACF,CAAC;IAED,IAAI,CAAC,SAAS,IAAI,IAAI,CAAC,SAAS,EAAE,CAAC;QAClC,MAAM,IAAI,KAAK,CAAC,6BAA6B,CAAC,CAAA;IAC/C,CAAC;IAED,iCAAiC;IACjC,IAAI,UAAoB,CAAA;IAExB,IAAI,IAAI,CAAC,SAAS,IAAI,SAAS,EAAE,CAAC;QACjC,UAAU,GAAG,SAAS,CAAA;IACvB,CAAC;SAAM,CAAC;QACP,gDAAgD;QAChD,MAAM,OAAO,GAAG,UAAU,CAAC,CAAC,CAAC,EAAE,MAAM,IAAI,CAAC,CAAA;QAC1C,UAAU,GAAG,KAAK,CAAC,IAAI,CAAC,EAAE,MAAM,EAAE,OAAO,EAAE,EAAE,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,OAAO,CAAC,EAAE,CAAC,CAAA;IACnE,CAAC;IAED,MAAM,QAAQ,GAAG,YAAY,CAAC,UAAU,CAAC,GAAG,CAAC,mBAAmB,CAAC,CAAC,CAAA;IAElE,6BAA6B;IAC7B,MAAM,OAAO,GAAiB,QAAQ,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC,EAAE,EAAE;QACtD,MAAM,OAAO,GAAG,UAAU,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE;YACtC,MAAM,GAAG,GAAG,GAAG,CAAC,CAAC,CAAC,IAAI,EAAE,CAAA;YAExB,OAAO,cAAc,CAAC,GAAG,CAAC,CAAA;QAC3B,CAAC,CAAC,CAAA;QAEF,MAAM,IAAI,GAAG,eAAe,CAAC,OAAO,CAAC,CAAA;QACrC,IAAI,CAAC,IAAI,GAAG,IAAI,CAAA;QAEhB,OAAO,IAAI,CAAA;IACZ,CAAC,CAAC,CAAA;IAEF,uBAAuB;IACvB,MAAM,OAAO,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,IAAI,CAAC,CAAC,IAAI,KAAK,CAAC,CAAC,IAAI,EAAE,CAAC,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;IACzE,kGAAkG;IAClG,sGAAsG;IACtG,MAAM,cAAc,GAAG,+BAA+B,IAAI,CAAC,SAAS,UAAU,OAAO,MAAM,CAAA;IAE3F,MAAM,QAAQ,GAAG,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,IAAI,CAAC,CAAC,IAAI,GAAG,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;IAE7D,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,0BAA0B,UAAU,CAAC,MAAM,iBAAiB,CAAC,CAAA;IAClF,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,GAAG,cAAc,MAAM,CAAC,CAAA;IAE7C,IAAI,IAAI,CAAC,MAAM,EAAE,CAAC;QACjB,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,qCAAqC,CAAC,CAAA;QAE3D,OAAM;IACP,CAAC;IAED,mCAAmC;IACnC,MAAM,EAAE,cAAc,EAAE,GAAG,MAAM,MAAM,CAAC,0BAA0B,CAAC,CAAA;IACnE,MAAM,eAAe,CAAC,OAAO,CAAC,IAAI,CAAC,UAAU,CAAC,CAAC,CAAA;IAE/C,+GAA+G;IAC/G,iHAAiH;IACjH,2DAA2D;IAC3D,MAAM,EAAE,GAAG,IAAI,cAAc,CAAW,IAAI,CAAC,UAAU,CAAC,CAAA;IACxD,EAAE,CAAC,IAAI,CAAC,2BAA2B,CAAC,CAAA,CAAC,yBAAyB;IAC9D,EAAE,CAAC,IAAI,CAAC,0BAA0B,CAAC,CAAA;IAEnC,EAAE,CAAC,IAAI,CAAC,cAAc,CAAC,CAAA;IAEvB,mFAAmF;IACnF,wCAAwC;IACxC,mFAAmF;IACnF,yDAAyD;IACzD,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,qBAAqB,CAAC,CAAA;IAE3C,MAAM,UAAU,GAAG,EAAE,CAAC,OAAO,CAC5B,gBAAgB,IAAI,CAAC,SAAS,MAAM,QAAQ,aAAa,OAAO,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,GAAG,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,CAC7F,CAAA;IAED,IAAI,QAAQ,GAAG,CAAC,CAAA;IAChB,IAAI,aAAa,GAAG,KAAK,CAAA;IAEzB,0FAA0F;IAC1F,MAAM,QAAQ,GAAG,GAAG,EAAE;QACrB,EAAE,CAAC,IAAI,CAAC,OAAO,CAAC,CAAA;QAEhB,IAAI,CAAC;YACJ,KAAK,MAAM,GAAG,IAAI,KAAK,EAAE,CAAC;gBACzB,UAAU,CAAC,GAAG,CAAC,GAAG,GAAG,CAAC,CAAA;YACvB,CAAC;YAED,EAAE,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAA;QAClB,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YAChB,EAAE,CAAC,IAAI,CAAC,UAAU,CAAC,CAAA;YACnB,MAAM,KAAK,CAAA;QACZ,CAAC;IACF,CAAC,CAAA;IAED,MAAM,KAAK,GAAsB,EAAE,CAAA;IACnC,MAAM,UAAU,GAAG,MAAM,CAAA;IAEzB,IAAI,KAAK,EAAE,MAAM,MAAM,IAAI,IAAI,EAAE,EAAE,CAAC;QACnC,IAAI,IAAI,CAAC,SAAS,IAAI,CAAC,aAAa,EAAE,CAAC;YACtC,aAAa,GAAG,IAAI,CAAA;YAEpB,SAAQ;QACT,CAAC;QAED,MAAM,MAAM,GAAG,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE;YAClC,MAAM,CAAC,GAAG,cAAc,CAAC,CAAC,CAAC,CAAA;YAE3B,IAAI,CAAC,KAAK,IAAI;gBAAE,OAAO,IAAI,CAAA;YAC3B,MAAM,GAAG,GAAG,OAAO,CAAC,CAAC,CAAC,CAAA;YAEtB,IAAI,GAAG,EAAE,IAAI,KAAK,SAAS,IAAI,SAAS,CAAC,IAAI,CAAC,CAAC,CAAC;gBAAE,OAAO,MAAM,CAAC,QAAQ,CAAC,CAAC,EAAE,EAAE,CAAC,CAAA;YAE/E,IAAI,GAAG,EAAE,IAAI,KAAK,MAAM,IAAI,eAAe,CAAC,IAAI,CAAC,CAAC,CAAC;gBAAE,OAAO,MAAM,CAAC,UAAU,CAAC,CAAC,CAAC,CAAA;YAEhF,OAAO,CAAC,CAAA;QACT,CAAC,CAAC,CAAA;QAEF,kCAAkC;QAClC,OAAO,MAAM,CAAC,MAAM,GAAG,OAAO,CAAC,MAAM,EAAE,CAAC;YACvC,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QAClB,CAAC;QAED,MAAM,CAAC,MAAM,GAAG,OAAO,CAAC,MAAM,CAAA;QAE9B,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,CAAA;QAElB,IAAI,KAAK,CAAC,MAAM,IAAI,UAAU,EAAE,CAAC;YAChC,QAAQ,EAAE,CAAA;YACV,QAAQ,IAAI,KAAK,CAAC,MAAM,CAAA;YACxB,KAAK,CAAC,MAAM,GAAG,CAAC,CAAA;YAEhB,IAAI,QAAQ,GAAG,OAAO,KAAK,CAAC,EAAE,CAAC;gBAC9B,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,KAAK,CAAC,QAAQ,GAAG,SAAS,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,aAAa,CAAC,CAAA;YAC1E,CAAC;QACF,CAAC;IACF,CAAC;IAED,kBAAkB;IAClB,IAAI,KAAK,CAAC,MAAM,EAAE,CAAC;QAClB,QAAQ,EAAE,CAAA;QACV,QAAQ,IAAI,KAAK,CAAC,MAAM,CAAA;IACzB,CAAC;IAED,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,cAAc,QAAQ,CAAC,cAAc,EAAE,eAAe,IAAI,CAAC,SAAS,KAAK,CAAC,CAAA;IAE/F,wEAAwE;IACxE,MAAM,YAAY,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,KAAK,MAAM,CAAC,CAAA;IAE3D,IAAI,YAAY,EAAE,CAAC;QAClB,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,sBAAsB,YAAY,CAAC,IAAI,QAAQ,CAAC,CAAA;QAErE,EAAE,CAAC,IAAI,CACN,kCAAkC,IAAI,CAAC,SAAS,IAAI,YAAY,CAAC,IAAI,QAAQ,IAAI,CAAC,SAAS,MAAM,YAAY,CAAC,IAAI,KAAK,CACvH,CAAA;IACF,CAAC;IAED,MAAM,IAAI,GAAG,MAAM,OAAO,CAAC,IAAI,CAAC,UAAU,CAAC,CAAA;IAE3C,MAAM,QAAQ,GAAG;QAChB,WAAW,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;QACrC,UAAU,EAAE,QAAQ,CAAC,IAAI,CAAC,SAAS,CAAC;QACpC,UAAU,EAAE,IAAI,CAAC,SAAS;QAC1B,OAAO,EAAE,OAAO,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,EAAE,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE,QAAQ,EAAE,CAAC,CAAC,QAAQ,EAAE,CAAC,CAAC;QACnF,SAAS,EAAE,QAAQ;QACnB,QAAQ,EAAE,IAAK,CAAC,IAAI;KACpB,CAAA;IAED,MAAM,YAAY,GAAG,IAAI,CAAC,UAAU,CAAC,OAAO,CAAC,OAAO,EAAE,gBAAgB,CAAC,CAAA;IACvE,MAAM,kBAAkB,CAAC,QAAQ,EAAE,YAAY,CAAC,CAAA;IAEhD,OAAO,CAAC,MAAM,CAAC,KAAK,CACnB,SAAS,QAAQ,CAAC,cAAc,EAAE,WAAW,IAAI,CAAC,UAAU,KAAK,aAAa,CAAC,SAAS,CAAC,IAAK,CAAC,IAAI,CAAC,KAAK,CACzG,CAAA;AACF,CAAC;AAgBD;;;;;GAKG;AACH,MAAM,CAAC,KAAK,UAAU,SAAS,CAAC,OAAyB;IACxD,IAAI,CAAC,CAAC,MAAM,UAAU,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC;QACxC,MAAM,IAAI,KAAK,CAAC,mBAAmB,OAAO,CAAC,KAAK,EAAE,CAAC,CAAA;IACpD,CAAC;IAED,MAAM,OAAO,GAAG,QAAQ,CAAC,OAAO,CAAC,KAAK,EAAE,OAAO,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC,CAAA;IAE/D,MAAM,SAAS,CAAC;QACf,SAAS,EAAE,OAAO,CAAC,KAAK;QACxB,SAAS,EAAE,OAAO,CAAC,KAAK,IAAI,OAAO,CAAC,UAAU,CAAC,gBAAgB,EAAE,GAAG,CAAC;QACrE,UAAU,EAAE,OAAO,CAAC,MAAM,IAAI,IAAI,CAAC,OAAO,CAAC,OAAO,CAAC,KAAK,CAAC,EAAE,OAAO,GAAG,KAAK,CAAC;QAC3E,UAAU,EAAE,OAAO,CAAC,MAAM,IAAI,GAAG;QACjC,SAAS,EAAE,OAAO,CAAC,SAAS,IAAI,GAAG;QACnC,SAAS,EAAE,OAAO,CAAC,IAAI,IAAI,CAAC;QAC5B,SAAS,EAAE,CAAC,OAAO,CAAC,QAAQ;QAC5B,MAAM,EAAE,OAAO,CAAC,MAAM,IAAI,KAAK;KAC/B,CAAC,CAAA;AACH,CAAC;AAED,YAAY"}
|
|
@@ -0,0 +1,61 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Convert a JSONL of LabeledRow objects to a Parquet slice matching the v0.5.0 schema.
|
|
7
|
+
*
|
|
8
|
+
* Ported faithfully from scripts/jsonl-to-parquet.py. The Python original wrote Parquet through
|
|
9
|
+
* PyArrow; this writes it through DuckDB (`@duckdb/node-api`) — `read_json` with an EXPLICIT
|
|
10
|
+
* `columns` type map projects the validated rows to the v0.5.0 schema, then `COPY … TO … (FORMAT
|
|
11
|
+
* PARQUET, COMPRESSION SNAPPY, ROW_GROUP_SIZE …)` emits the slice. DuckDB reproduces the exact
|
|
12
|
+
* logical schema PyArrow did — `VARCHAR` (UTF8) scalars, `VARCHAR[]` (LIST<UTF8>) for the string
|
|
13
|
+
* arrays, and `INTEGER[]` (LIST<INT32>) for the span offsets — in the exact column order below.
|
|
14
|
+
* Verified field-for-field against the PyArrow original (same column order, same logical types,
|
|
15
|
+
* same `list<element: …>` child naming, same values), so a PyArrow reader sees an identical
|
|
16
|
+
* table. The trainer in any case reads slices by column name (`pq.read_table(...).to_pylist()`),
|
|
17
|
+
* which is blind to physical layout. INT32 matches the corpus's native TS writer
|
|
18
|
+
* (`@mailwoman/corpus` `LABELED_ROW_SCHEMA`), which already writes the base slices this overlay
|
|
19
|
+
* rides alongside.
|
|
20
|
+
*
|
|
21
|
+
* Schema: raw, tokens, labels, span_starts, span_ends, span_tags, country, locale, source,
|
|
22
|
+
* source_id, corpus_version, license, synth_method, synth_base_id.
|
|
23
|
+
*
|
|
24
|
+
* The span triple (#519, v0.5.0 char-offset labels) is REQUIRED on every row: `alignRow` emits it
|
|
25
|
+
* on every labeled row, so a row arriving without it came from a producer that hasn't migrated —
|
|
26
|
+
* writing it would silently drop the v0.5.0 labels from the slice. Loud failure, naming the row
|
|
27
|
+
* number, instead.
|
|
28
|
+
*
|
|
29
|
+
* Usage: mailwoman dev jsonl-to-parquet --input /tmp/po-box-labeled.jsonl --output
|
|
30
|
+
* /tmp/part-po-box.parquet
|
|
31
|
+
*/
|
|
32
|
+
/**
|
|
33
|
+
* Options for {@linkcode jsonlToParquet}.
|
|
34
|
+
*/
|
|
35
|
+
export interface JSONLToParquetOptions {
|
|
36
|
+
/**
|
|
37
|
+
* The labeled-row JSONL to convert.
|
|
38
|
+
*/
|
|
39
|
+
input: string;
|
|
40
|
+
/**
|
|
41
|
+
* The parquet slice to write.
|
|
42
|
+
*/
|
|
43
|
+
output: string;
|
|
44
|
+
/**
|
|
45
|
+
* Parquet row-group size. Default 50000.
|
|
46
|
+
*/
|
|
47
|
+
rowGroupSize?: number;
|
|
48
|
+
}
|
|
49
|
+
/**
|
|
50
|
+
* Summary returned by {@linkcode jsonlToParquet}.
|
|
51
|
+
*/
|
|
52
|
+
export interface JSONLToParquetSummary {
|
|
53
|
+
read: number;
|
|
54
|
+
written: number;
|
|
55
|
+
outPath: string;
|
|
56
|
+
}
|
|
57
|
+
/**
|
|
58
|
+
* Convert a labeled-row JSONL to a v0.5.0-schema Parquet slice.
|
|
59
|
+
*/
|
|
60
|
+
export declare function jsonlToParquet(options: JSONLToParquetOptions, report?: (line: string) => void): Promise<JSONLToParquetSummary>;
|
|
61
|
+
//# sourceMappingURL=jsonl-to-parquet.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"jsonl-to-parquet.d.ts","sourceRoot":"","sources":["../../lib/tools/jsonl-to-parquet.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8BG;AAsDH;;GAEG;AACH,MAAM,WAAW,qBAAqB;IACrC;;OAEG;IACH,KAAK,EAAE,MAAM,CAAA;IACb;;OAEG;IACH,MAAM,EAAE,MAAM,CAAA;IACd;;OAEG;IACH,YAAY,CAAC,EAAE,MAAM,CAAA;CACrB;AAED;;GAEG;AACH,MAAM,WAAW,qBAAqB;IACrC,IAAI,EAAE,MAAM,CAAA;IACZ,OAAO,EAAE,MAAM,CAAA;IACf,OAAO,EAAE,MAAM,CAAA;CACf;AA8BD;;GAEG;AACH,wBAAsB,cAAc,CACnC,OAAO,EAAE,qBAAqB,EAC9B,MAAM,CAAC,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAC7B,OAAO,CAAC,qBAAqB,CAAC,CA6DhC"}
|
|
@@ -0,0 +1,150 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* @copyright Sister Software
|
|
3
|
+
* @license AGPL-3.0
|
|
4
|
+
* @author Teffen Ellis, et al.
|
|
5
|
+
*
|
|
6
|
+
* Convert a JSONL of LabeledRow objects to a Parquet slice matching the v0.5.0 schema.
|
|
7
|
+
*
|
|
8
|
+
* Ported faithfully from scripts/jsonl-to-parquet.py. The Python original wrote Parquet through
|
|
9
|
+
* PyArrow; this writes it through DuckDB (`@duckdb/node-api`) — `read_json` with an EXPLICIT
|
|
10
|
+
* `columns` type map projects the validated rows to the v0.5.0 schema, then `COPY … TO … (FORMAT
|
|
11
|
+
* PARQUET, COMPRESSION SNAPPY, ROW_GROUP_SIZE …)` emits the slice. DuckDB reproduces the exact
|
|
12
|
+
* logical schema PyArrow did — `VARCHAR` (UTF8) scalars, `VARCHAR[]` (LIST<UTF8>) for the string
|
|
13
|
+
* arrays, and `INTEGER[]` (LIST<INT32>) for the span offsets — in the exact column order below.
|
|
14
|
+
* Verified field-for-field against the PyArrow original (same column order, same logical types,
|
|
15
|
+
* same `list<element: …>` child naming, same values), so a PyArrow reader sees an identical
|
|
16
|
+
* table. The trainer in any case reads slices by column name (`pq.read_table(...).to_pylist()`),
|
|
17
|
+
* which is blind to physical layout. INT32 matches the corpus's native TS writer
|
|
18
|
+
* (`@mailwoman/corpus` `LABELED_ROW_SCHEMA`), which already writes the base slices this overlay
|
|
19
|
+
* rides alongside.
|
|
20
|
+
*
|
|
21
|
+
* Schema: raw, tokens, labels, span_starts, span_ends, span_tags, country, locale, source,
|
|
22
|
+
* source_id, corpus_version, license, synth_method, synth_base_id.
|
|
23
|
+
*
|
|
24
|
+
* The span triple (#519, v0.5.0 char-offset labels) is REQUIRED on every row: `alignRow` emits it
|
|
25
|
+
* on every labeled row, so a row arriving without it came from a producer that hasn't migrated —
|
|
26
|
+
* writing it would silently drop the v0.5.0 labels from the slice. Loud failure, naming the row
|
|
27
|
+
* number, instead.
|
|
28
|
+
*
|
|
29
|
+
* Usage: mailwoman dev jsonl-to-parquet --input /tmp/po-box-labeled.jsonl --output
|
|
30
|
+
* /tmp/part-po-box.parquet
|
|
31
|
+
*/
|
|
32
|
+
import { openWriteStream } from "@mailwoman/core/fs/streams";
|
|
33
|
+
import { temporaryDirectory } from "@mailwoman/core/fs/temporary";
|
|
34
|
+
import { parseJSONStrict } from "@mailwoman/core/json";
|
|
35
|
+
import { join } from "path-ts";
|
|
36
|
+
import { TextSpliterator } from "spliterator";
|
|
37
|
+
import { connectDuckDB, escapeSQLString } from "#utils/parquet";
|
|
38
|
+
const REQUIRED_COLUMNS = [
|
|
39
|
+
"raw",
|
|
40
|
+
"tokens",
|
|
41
|
+
"labels",
|
|
42
|
+
"span_starts",
|
|
43
|
+
"span_ends",
|
|
44
|
+
"span_tags",
|
|
45
|
+
"country",
|
|
46
|
+
"locale",
|
|
47
|
+
"source",
|
|
48
|
+
"source_id",
|
|
49
|
+
"corpus_version",
|
|
50
|
+
"license",
|
|
51
|
+
"synth_method",
|
|
52
|
+
"synth_base_id",
|
|
53
|
+
];
|
|
54
|
+
const SPAN_COLUMNS = ["span_starts", "span_ends", "span_tags"];
|
|
55
|
+
/**
|
|
56
|
+
* The v0.5.0 DuckDB type for each column, in {@link REQUIRED_COLUMNS} order.
|
|
57
|
+
*
|
|
58
|
+
* Mirrors the PyArrow schema the Python original declared: `pa.string()` → `VARCHAR`, `pa.list_(pa.string())` →
|
|
59
|
+
* `VARCHAR[]`, `pa.list_(pa.int32())` → `INTEGER[]`. The span offsets are INT32 (#519): parallel arrays over `raw`
|
|
60
|
+
* (UTF-16 code units, `[start, end)` exclusive-end, sorted, non-overlapping); `raw` is a short address string, so INT32
|
|
61
|
+
* round-trips as a plain integer where INT64 would surface as bigint.
|
|
62
|
+
*/
|
|
63
|
+
const COLUMN_TYPES = {
|
|
64
|
+
raw: "VARCHAR",
|
|
65
|
+
tokens: "VARCHAR[]",
|
|
66
|
+
labels: "VARCHAR[]",
|
|
67
|
+
span_starts: "INTEGER[]",
|
|
68
|
+
span_ends: "INTEGER[]",
|
|
69
|
+
span_tags: "VARCHAR[]",
|
|
70
|
+
country: "VARCHAR",
|
|
71
|
+
locale: "VARCHAR",
|
|
72
|
+
source: "VARCHAR",
|
|
73
|
+
source_id: "VARCHAR",
|
|
74
|
+
corpus_version: "VARCHAR",
|
|
75
|
+
license: "VARCHAR",
|
|
76
|
+
synth_method: "VARCHAR",
|
|
77
|
+
synth_base_id: "VARCHAR",
|
|
78
|
+
};
|
|
79
|
+
/**
|
|
80
|
+
* Enforce the #519 span contract per row: all three present, parallel lengths.
|
|
81
|
+
*
|
|
82
|
+
* A row with span_starts but no span_tags is a corrupt row — never a silent fallback.
|
|
83
|
+
*/
|
|
84
|
+
function assertSpanTriple(row, lineNo) {
|
|
85
|
+
const present = SPAN_COLUMNS.filter((c) => row[c] != null);
|
|
86
|
+
if (present.length !== SPAN_COLUMNS.length) {
|
|
87
|
+
const missing = SPAN_COLUMNS.filter((c) => row[c] == null);
|
|
88
|
+
throw new Error(`line ${lineNo}: row is missing the char-offset span triple (#519): ` +
|
|
89
|
+
`missing ${JSON.stringify(missing)} (source_id=${JSON.stringify(row.source_id ?? null)}). Every parquet-bound row ` +
|
|
90
|
+
"must carry span_starts/span_ends/span_tags; re-emit this slice through alignRow.");
|
|
91
|
+
}
|
|
92
|
+
const n = row.span_starts.length;
|
|
93
|
+
if (row.span_ends.length !== n || row.span_tags.length !== n) {
|
|
94
|
+
throw new Error(`line ${lineNo}: span triple arrays are not parallel — ` +
|
|
95
|
+
`starts=${row.span_starts.length} ends=${row.span_ends.length} ` +
|
|
96
|
+
`tags=${row.span_tags.length} (source_id=${JSON.stringify(row.source_id ?? null)})`);
|
|
97
|
+
}
|
|
98
|
+
}
|
|
99
|
+
/**
|
|
100
|
+
* Convert a labeled-row JSONL to a v0.5.0-schema Parquet slice.
|
|
101
|
+
*/
|
|
102
|
+
export async function jsonlToParquet(options, report) {
|
|
103
|
+
const rowGroupSize = options.rowGroupSize ?? 50_000;
|
|
104
|
+
if (!Number.isInteger(rowGroupSize) || rowGroupSize <= 0) {
|
|
105
|
+
throw new Error(`rowGroupSize must be a positive integer (got ${JSON.stringify(rowGroupSize)})`);
|
|
106
|
+
}
|
|
107
|
+
// Stage the validated rows to a temp NDJSON, then let DuckDB type + write them. Streaming keeps
|
|
108
|
+
// memory O(1) on the Node side (the Python original buffered every column into memory first). The
|
|
109
|
+
// staging directory owns the write stream, so it is closed before the directory is removed — and a
|
|
110
|
+
// mid-stream span-triple failure leaves no orphan.
|
|
111
|
+
await using staging = await temporaryDirectory("mw-jsonl-to-parquet-");
|
|
112
|
+
const stagePath = join(staging.path, "rows.ndjson");
|
|
113
|
+
const stage = staging.use(openWriteStream(stagePath, { encoding: "utf8" }));
|
|
114
|
+
let rows = 0;
|
|
115
|
+
let lineNo = 0;
|
|
116
|
+
// TextSpliterator, not JSONSpliterator: the staging write below streams the RAW line bytes to
|
|
117
|
+
// DuckDB verbatim (the parse here only validates), so a re-serialized JSONSpliterator row would
|
|
118
|
+
// defeat the point. CRLF is handled by the existing `rawLine.trim()` (strips a trailing \r),
|
|
119
|
+
// same as readline's crlfDelay:Infinity did.
|
|
120
|
+
for await (const rawLine of TextSpliterator.fromAsync(options.input)) {
|
|
121
|
+
lineNo++;
|
|
122
|
+
const line = rawLine.trim();
|
|
123
|
+
if (!line)
|
|
124
|
+
continue;
|
|
125
|
+
const row = parseJSONStrict(line);
|
|
126
|
+
assertSpanTriple(row, lineNo);
|
|
127
|
+
// Write the validated line verbatim; DuckDB's `read_json` projects to the explicit `columns`
|
|
128
|
+
// map below (extra keys dropped, absent keys → NULL — matching the Python `row.get(c)`).
|
|
129
|
+
stage.write(line + "\n");
|
|
130
|
+
rows++;
|
|
131
|
+
}
|
|
132
|
+
await new Promise((resolve, reject) => {
|
|
133
|
+
stage.end((err) => (err ? reject(err) : resolve()));
|
|
134
|
+
});
|
|
135
|
+
report?.(`Read ${rows} rows from ${options.input}`);
|
|
136
|
+
const columnsLiteral = "{" + REQUIRED_COLUMNS.map((c) => `'${c}': '${COLUMN_TYPES[c]}'`).join(", ") + "}";
|
|
137
|
+
const selectList = REQUIRED_COLUMNS.join(", ");
|
|
138
|
+
const db = await connectDuckDB();
|
|
139
|
+
// Row order is required: the overlay-manifest assembler records first/last source_id from
|
|
140
|
+
// slice order. `preserve_insertion_order` (DuckDB default) keeps output order = input order.
|
|
141
|
+
await db.run("SET preserve_insertion_order=true");
|
|
142
|
+
await db.run(`COPY (SELECT ${selectList} FROM read_json('${escapeSQLString(stagePath)}', ` +
|
|
143
|
+
`columns = ${columnsLiteral}, format = 'newline_delimited')) ` +
|
|
144
|
+
`TO '${escapeSQLString(options.output)}' (FORMAT PARQUET, COMPRESSION SNAPPY, ROW_GROUP_SIZE ${rowGroupSize})`);
|
|
145
|
+
const counted = await db.runAndReadAll(`SELECT count(*) AS n FROM read_parquet('${escapeSQLString(options.output)}')`);
|
|
146
|
+
const written = Number(counted.getRowObjects()[0].n);
|
|
147
|
+
report?.(`Wrote ${written} rows to ${options.output}`);
|
|
148
|
+
return { read: rows, written, outPath: options.output };
|
|
149
|
+
}
|
|
150
|
+
//# sourceMappingURL=jsonl-to-parquet.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"jsonl-to-parquet.js","sourceRoot":"","sources":["../../lib/tools/jsonl-to-parquet.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA8BG;AAEH,OAAO,EAAE,eAAe,EAAE,MAAM,4BAA4B,CAAA;AAC5D,OAAO,EAAE,kBAAkB,EAAE,MAAM,8BAA8B,CAAA;AACjE,OAAO,EAAE,eAAe,EAAE,MAAM,sBAAsB,CAAA;AACtD,OAAO,EAAE,IAAI,EAAE,MAAM,SAAS,CAAA;AAC9B,OAAO,EAAE,eAAe,EAAE,MAAM,aAAa,CAAA;AAE7C,OAAO,EAAE,aAAa,EAAE,eAAe,EAAE,MAAM,gBAAgB,CAAA;AAE/D,MAAM,gBAAgB,GAAG;IACxB,KAAK;IACL,QAAQ;IACR,QAAQ;IACR,aAAa;IACb,WAAW;IACX,WAAW;IACX,SAAS;IACT,QAAQ;IACR,QAAQ;IACR,WAAW;IACX,gBAAgB;IAChB,SAAS;IACT,cAAc;IACd,eAAe;CACN,CAAA;AAEV,MAAM,YAAY,GAAG,CAAC,aAAa,EAAE,WAAW,EAAE,WAAW,CAAU,CAAA;AAEvE;;;;;;;GAOG;AACH,MAAM,YAAY,GAAsD;IACvE,GAAG,EAAE,SAAS;IACd,MAAM,EAAE,WAAW;IACnB,MAAM,EAAE,WAAW;IACnB,WAAW,EAAE,WAAW;IACxB,SAAS,EAAE,WAAW;IACtB,SAAS,EAAE,WAAW;IACtB,OAAO,EAAE,SAAS;IAClB,MAAM,EAAE,SAAS;IACjB,MAAM,EAAE,SAAS;IACjB,SAAS,EAAE,SAAS;IACpB,cAAc,EAAE,SAAS;IACzB,OAAO,EAAE,SAAS;IAClB,YAAY,EAAE,SAAS;IACvB,aAAa,EAAE,SAAS;CACxB,CAAA;AA6BD;;;;GAIG;AACH,SAAS,gBAAgB,CAAC,GAA4B,EAAE,MAAc;IACrE,MAAM,OAAO,GAAG,YAAY,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,IAAI,CAAC,CAAA;IAE1D,IAAI,OAAO,CAAC,MAAM,KAAK,YAAY,CAAC,MAAM,EAAE,CAAC;QAC5C,MAAM,OAAO,GAAG,YAAY,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,GAAG,CAAC,CAAC,CAAC,IAAI,IAAI,CAAC,CAAA;QAC1D,MAAM,IAAI,KAAK,CACd,QAAQ,MAAM,uDAAuD;YACpE,WAAW,IAAI,CAAC,SAAS,CAAC,OAAO,CAAC,eAAe,IAAI,CAAC,SAAS,CAAC,GAAG,CAAC,SAAS,IAAI,IAAI,CAAC,6BAA6B;YACnH,kFAAkF,CACnF,CAAA;IACF,CAAC;IAED,MAAM,CAAC,GAAI,GAAG,CAAC,WAAyB,CAAC,MAAM,CAAA;IAE/C,IAAK,GAAG,CAAC,SAAuB,CAAC,MAAM,KAAK,CAAC,IAAK,GAAG,CAAC,SAAuB,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QAC5F,MAAM,IAAI,KAAK,CACd,QAAQ,MAAM,0CAA0C;YACvD,UAAW,GAAG,CAAC,WAAyB,CAAC,MAAM,SAAU,GAAG,CAAC,SAAuB,CAAC,MAAM,GAAG;YAC9F,QAAS,GAAG,CAAC,SAAuB,CAAC,MAAM,eAAe,IAAI,CAAC,SAAS,CAAC,GAAG,CAAC,SAAS,IAAI,IAAI,CAAC,GAAG,CACnG,CAAA;IACF,CAAC;AACF,CAAC;AAED;;GAEG;AACH,MAAM,CAAC,KAAK,UAAU,cAAc,CACnC,OAA8B,EAC9B,MAA+B;IAE/B,MAAM,YAAY,GAAG,OAAO,CAAC,YAAY,IAAI,MAAM,CAAA;IAEnD,IAAI,CAAC,MAAM,CAAC,SAAS,CAAC,YAAY,CAAC,IAAI,YAAY,IAAI,CAAC,EAAE,CAAC;QAC1D,MAAM,IAAI,KAAK,CAAC,gDAAgD,IAAI,CAAC,SAAS,CAAC,YAAY,CAAC,GAAG,CAAC,CAAA;IACjG,CAAC;IAED,gGAAgG;IAChG,kGAAkG;IAClG,mGAAmG;IACnG,mDAAmD;IACnD,YAAY,OAAO,GAAG,MAAM,kBAAkB,CAAC,sBAAsB,CAAC,CAAA;IACtE,MAAM,SAAS,GAAG,IAAI,CAAC,OAAO,CAAC,IAAI,EAAE,aAAa,CAAC,CAAA;IACnD,MAAM,KAAK,GAAG,OAAO,CAAC,GAAG,CAAC,eAAe,CAAC,SAAS,EAAE,EAAE,QAAQ,EAAE,MAAM,EAAE,CAAC,CAAC,CAAA;IAE3E,IAAI,IAAI,GAAG,CAAC,CAAA;IACZ,IAAI,MAAM,GAAG,CAAC,CAAA;IAEd,8FAA8F;IAC9F,gGAAgG;IAChG,6FAA6F;IAC7F,6CAA6C;IAC7C,IAAI,KAAK,EAAE,MAAM,OAAO,IAAI,eAAe,CAAC,SAAS,CAAC,OAAO,CAAC,KAAK,CAAC,EAAE,CAAC;QACtE,MAAM,EAAE,CAAA;QACR,MAAM,IAAI,GAAG,OAAO,CAAC,IAAI,EAAE,CAAA;QAE3B,IAAI,CAAC,IAAI;YAAE,SAAQ;QACnB,MAAM,GAAG,GAAG,eAAe,CAA0B,IAAI,CAAC,CAAA;QAC1D,gBAAgB,CAAC,GAAG,EAAE,MAAM,CAAC,CAAA;QAC7B,6FAA6F;QAC7F,yFAAyF;QACzF,KAAK,CAAC,KAAK,CAAC,IAAI,GAAG,IAAI,CAAC,CAAA;QAExB,IAAI,EAAE,CAAA;IACP,CAAC;IAED,MAAM,IAAI,OAAO,CAAO,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE;QAC3C,KAAK,CAAC,GAAG,CAAC,CAAC,GAAkB,EAAE,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,OAAO,EAAE,CAAC,CAAC,CAAA;IACnE,CAAC,CAAC,CAAA;IAEF,MAAM,EAAE,CAAC,QAAQ,IAAI,cAAc,OAAO,CAAC,KAAK,EAAE,CAAC,CAAA;IAEnD,MAAM,cAAc,GAAG,GAAG,GAAG,gBAAgB,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,IAAI,CAAC,OAAO,YAAY,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG,GAAG,CAAA;IACzG,MAAM,UAAU,GAAG,gBAAgB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;IAE9C,MAAM,EAAE,GAAG,MAAM,aAAa,EAAE,CAAA;IAChC,0FAA0F;IAC1F,6FAA6F;IAC7F,MAAM,EAAE,CAAC,GAAG,CAAC,mCAAmC,CAAC,CAAA;IAEjD,MAAM,EAAE,CAAC,GAAG,CACX,gBAAgB,UAAU,oBAAoB,eAAe,CAAC,SAAS,CAAC,KAAK;QAC5E,aAAa,cAAc,mCAAmC;QAC9D,OAAO,eAAe,CAAC,OAAO,CAAC,MAAM,CAAC,yDAAyD,YAAY,GAAG,CAC/G,CAAA;IAED,MAAM,OAAO,GAAG,MAAM,EAAE,CAAC,aAAa,CAAC,2CAA2C,eAAe,CAAC,OAAO,CAAC,MAAM,CAAC,IAAI,CAAC,CAAA;IACtH,MAAM,OAAO,GAAG,MAAM,CAAC,OAAO,CAAC,aAAa,EAAE,CAAC,CAAC,CAAE,CAAC,CAAC,CAAC,CAAA;IACrD,MAAM,EAAE,CAAC,SAAS,OAAO,YAAY,OAAO,CAAC,MAAM,EAAE,CAAC,CAAA;IAEtD,OAAO,EAAE,IAAI,EAAE,IAAI,EAAE,OAAO,EAAE,OAAO,EAAE,OAAO,CAAC,MAAM,EAAE,CAAA;AACxD,CAAC"}
|