/** * @copyright Sister Software * @license AGPL-3.0 * @author Teffen Ellis, et al. * * Fetch the National Tax Agency's corporate-number register (法人番号公表サイト 全件データ): every * corporation assigned a number, about 5,000,000 rows, with the head-office address as one string * (国内所在地) plus the prefecture and municipality split out and the postcode. The nationwide CSV * in Unicode is one zip of about 255 MB. This is the NOISY source for Japanese addresses; the * Overture rows the JP corpus is built from are the LABEL half. * * The agency states the three published fields may be used freely by anyone ("どなたでも自由にご利用 * いただくことができます"), with no attribution condition on the download page. * * The file sits behind a form: the page hands out a per-session token, and a POST with that token, * `event=download` and the file number of the nationwide Unicode CSV answers the zip. The file * number is read off the page rather than pinned, because the agency re-issues the files monthly. * * Invoke via `mailwoman corpus fetch houjin-jp --out-root `. */ import type { BaseFetchOptions, FetchSummary } from "#tools/fetch/download/index"; export type FetchHoujinJPOptions = BaseFetchOptions; export declare function fetchHoujinJP(options: FetchHoujinJPOptions, report?: (line: string) => void): Promise; //# sourceMappingURL=houjin.d.ts.map