/**
 * @copyright Sister Software
 * @license AGPL-3.0
 * @author Teffen Ellis, et al.
 *
 * Harvests Estonia's INSPIRE Addresses (AD) theme into the newline-delimited JSON file that
 * `#ee/adapters/ads/adapter` reads.
 *
 * Maa- ja Ruumiamet publishes the Aadressiandmete süsteem through GeoServer at
 * {@linkcode EE_ADS_WFS}. The service's dataset record states Creative Commons CC0 1.0 in
 * `otherConstraints`, which the address-source register elected under `spdx` `CC0-1.0`. CC0 reserves
 * no act, so paging the service and storing what it returns is granted and the harvest needs no
 * attribution clause.
 *
 * `#tools/fetch/inspire-addresses` owns the capabilities read and the GeoJSON page read, and
 * `#tools/fetch/wfs-harvest` owns the appending, the manifest and the resumption. This module states
 * what is particular to Estonia, which is four measurements taken on 2026-10-02:
 *
 * 1. The payload needs no component resolution. GeoServer flattens the application schema here, so
 *    each `component<n>_xlink_href` has a sibling `component<n>_xlink_title` carrying the referenced
 *    feature's value, and the adapter reads the titles. The harvest therefore takes one feature type
 *    rather than the five a harmonized INSPIRE service splits an address across.
 * 2. `resultType=hits` at `startIndex=1` reports `numberMatched="729973"` and a feature page reports
 *    the same number, so this service's count is real. It is read through
 *    `readCheckedWFSFeatureCount`, which proves the number against a page before a caller uses it,
 *    and no count is written into this file.
 * 3. The service honors a sort. `ImplementsSorting` is `TRUE`, `sortBy=gml_id` answers HTTP 200 and
 *    `sortBy=gml_id D` returns the type's last features first, which is what proves the parameter is
 *    applied rather than accepted and dropped. `sortBy=gml:identifier` and `sortBy=inspireId` answer
 *    HTTP 400 `Illegal property name`, so the sort property is one of the flattened names.
 * 4. A `count=10000` page of `application/json` is 31,198,909 bytes and takes about 6 seconds. At
 *    729,973 features that is 73 pages and about 2.3 GB, plus three requests for the capabilities and
 *    the checked count.
 *
 * The harvest writes one feature per line, which is what lets the adapter stream the whole extract
 * without holding a page. The `FeatureCollection` envelope is dropped: its counts describe one page
 * and the manifest records them per page instead.
 */
import { type APIClient } from "@mailwoman/core/api";
import type { PathBuilderLike } from "path-ts";
import type { BaseFetchOptions, FetchSummary } from "#tools/fetch/download";
import { type WFSHarvestManifest } from "#tools/fetch/wfs-harvest";
/**
 * The service this module harvests.
 */
export declare const EE_ADS_WFS = "https://inspire.geoportaal.ee/geoserver/AD_Address/wfs";
/**
 * The qualified name the service publishes its addresses under.
 *
 * Read from the capabilities document per run.
 * This constant is the name a refusal quotes when the document stops publishing an Addresses type.
 */
export declare const EE_ADS_TYPE_NAME = "AD_Address:AD.Address";
/**
 * The property the pages are ordered by.
 *
 * A flattened property name, because the service refuses `gml:identifier`
 * and `inspireId` with HTTP 400 `Illegal property name`.
 */
export declare const EE_ADS_SORT_BY = "gml_id";
/**
 * Features per page.
 *
 * The service's `CountDefault` is 1,000,000 and it honors `count=10000`, which is where the page
 * size is set: a 10,000-feature page is 31,198,909 bytes, and a larger page buys fewer requests
 * at the cost of holding a larger body in memory and losing more work when one request fails.
 */
export declare const EE_ADS_PAGE_SIZE = 10000;
/**
 * The file the adapter's `inputPath` points at, inside the harvest directory.
 */
export declare const EE_ADS_HARVEST_FILE = "address.jsonl";
/**
 * One page of features as newline-delimited JSON, one feature per line.
 *
 * A trailing newline on a non-empty page, so the next page's first feature starts its own line.
 */
export declare function featuresAsJSONL(features: readonly unknown[]): string;
export interface HarvestADSOptions {
    /**
     * Where the harvest is written.
     *
     * The adapter reads {@linkcode EE_ADS_HARVEST_FILE} inside it.
     */
    outputDir: PathBuilderLike;
    /**
     * Features per page, defaulting to {@linkcode EE_ADS_PAGE_SIZE}.
     */
    pageSize?: number;
    /**
     * Stop once the manifest holds this many pages, for a probe rather than a full harvest.
     */
    maxPages?: number;
    signal?: AbortSignal;
    report?: (line: string) => void;
}
/**
 * Harvests the service into `options.outputDir` and writes the manifest beside the data file.
 *
 * The capabilities document is read first, so the type name, the JSON format
 * and the paging support come from the service rather than from this file.
 * A service that stops publishing any of the three raises here rather than
 * producing a harvest of the wrong thing.
 *
 * @returns The manifest as written.
 */
export declare function harvestADSEE(client: Pick<APIClient, "fetch">, options: HarvestADSOptions): Promise<WFSHarvestManifest>;
export type FetchADSEEOptions = BaseFetchOptions & Pick<HarvestADSOptions, "maxPages" | "pageSize" | "signal"> & {
    /**
     * An injected client, for a test that supplies its own transport.
     *
     * A caller that leaves it out gets a paced client of this module's own.
     */
    client?: Pick<APIClient, "fetch">;
};
/**
 * Harvests Estonia's addresses under `<outRoot>/ads/`, for `mailwoman corpus fetch ads-ee`.
 *
 * Re-runnable: a complete harvest whose file still hashes to the manifest's digest makes
 * no request, and an interrupted one resumes at the page after the last that reached disk.
 */
export declare function fetchADSEE(options: FetchADSEEOptions, report?: (line: string) => void): Promise<FetchSummary>;
//# sourceMappingURL=ads.d.ts.map