/**
 * @copyright Sister Software
 * @license AGPL-3.0
 * @author Teffen Ellis, et al.
 *
 *   `bare-postcode` — a postcode standing ALONE, in the form its country writes.
 *
 *   The shape is absent from the corpus. A census of the 685,187,151 rows the v0.29.0 mixture reads
 *   found ZERO two-token rows of `NNN NN` and one of `NNNN LL`, so `100 00` and `1012 LG` are out of
 *   distribution and every model's answer for them is generalization off longer lines. That
 *   generalization is what moved: held-out CZ/SK codes read 31/32 as a postcode under v5.0.0, v5.2.0
 *   AND v5.3.0 — a seed pair agreeing, so not training noise — and 0/32 under v5.4.0, whose added
 *   OpenStreetMap PK/BD/VN rows raise the leading-digit-is-a-house-number evidence at that opening
 *   from 393 to 444 samples per epoch.
 *
 *   Neither existing repair reaches it. `nl-postcode` and `cz-pcfirst-preposition` teach the same
 *   postcodes IN CONTEXT — every row they emit carries a street, a number and a city — and the
 *   12,759 in-context `NNN NN` rows do not transfer to the bare input. The deterministic half,
 *   `buildEmissionPriors`, caps near 0.95 at the default `biasScale` against a measured 1.67-to-3.78
 *   nat deficit.
 *
 *   So this recipe emits the postcode and NOTHING else, which is the one thing no sibling does.
 *
 *   VERIFIED AGAINST THE PRIOR, NOT MERELY MATCHED TO IT. Every surface is run through
 *   `detectKnownFormats` and refused unless the detector calls it a postcode. The recipe's rendering
 *   table and `known-formats.ts`'s patterns have to agree, and matched constants would not prove
 *   they do — the trained surface and the prior that boosts it come from one check.
 */
import { type CorpusRecipe } from "#recipes/scaffold";
/**
 * Choose distinct postcodes without inheriting the publisher's row order.
 *
 * Sorting first makes the result independent of input-file order; the seeded sample then gives a reproducible spread
 * across the complete set instead of taking the first municipality or numeric prefix that happens to fill the cap.
 */
export declare function selectPostcodes(codes: Iterable<string>, limit: number, seed: number): string[];
/**
 * Return every required input path that is absent, preserving declaration order for diagnostics.
 */
export declare function findMissingPostcodeSources(paths: readonly string[], exists?: (path: string) => Promise<boolean>): Promise<string[]>;
/**
 * Every surface a country writes for one postcode, spaced form first, or `[]` when this recipe carries no form for that
 * country or the code does not fit the one it carries.
 *
 * Exported because it is the half of the recipe a test can reach: `run` reads a 500 MB archive from the data root, and
 * the contract worth pinning — that every surface this renders is one {@linkcode detectedAsPostcode} accepts — needs
 * neither.
 */
export declare function renderBarePostcode(country: string, postcode: string): string[];
/**
 * Whether `known-formats.ts` reads this surface as a postcode across its whole span.
 *
 * A surface the detector does not recognize would train the model on a string the query-shape prior cannot then
 * support, which is the divergence this recipe exists to close rather than widen.
 */
export declare function detectedAsPostcode(surface: string): boolean;
/**
 * Slice recipe registered with the corpus builder — see the file header for the parse behaviour it exists to exercise,
 * and `description` below for the surface form it generates.
 */
export declare const barePostcodeRecipe: CorpusRecipe;
//# sourceMappingURL=index.d.ts.map