/**
 * Search indexes, derived from `manifest.searchables` (#827).
 *
 * The declaration has been in the manifest since the beginning and nothing read
 * it — `kernel-design.md` §"Search backends" deferred the decision "to first
 * search consumer". This is that consumer, and it takes the FTS half only:
 * `vec0` is rejected by Durable Object SQLite today, so semantic search stays
 * deferred rather than half-built.
 *
 * ## Why the kernel owns the index rather than the module
 *
 * Three reasons, in order of how much they'd hurt to get wrong.
 *
 * 1. **Rule 4 makes it the only legal home for a cross-entity search.** A module
 *    may not reference another module's tables, so a palette searching customers
 *    *and* orders cannot be written by either module. A kernel-owned index over
 *    declared entities can answer it without anyone reading anyone's tables.
 * 2. **Triggers keep the `ctx.sql`-only rule intact.** The index is maintained by
 *    SQL triggers generated from the declaration, so it stays correct no matter
 *    who writes the row — no new write path, no module opting in per `INSERT`,
 *    and nothing to forget. A module that never hears about the index cannot
 *    desynchronise it.
 * 3. **It stays read-after-write correct.** Indexing from the event spine instead
 *    would be eventually consistent, which is why Stripe has to warn "don't use
 *    search for read-after-write flows". Create a customer, then find it in the
 *    picker in the same breath: with triggers that simply works, and a picker
 *    that cannot see what the user just created is the bug report.
 *
 * ## What is derived, and from where
 *
 * Everything. `searchables` names an entity and its fields; `manifestEntities()`
 * enriches that with the entity's `table` and single-column key from the same
 * registry the fields are checked against. So there is no second description of
 * where a customer lives — the model already said it.
 */
import type { DerivedObject } from './derived-object.js';
import type { SqlMigration } from './scope-host.js';
import type { EntityStateName } from '@substrat-run/contracts';
/** How a declared searchable is matched. `prefix` unless it says otherwise. */
export type SearchTokenizer = 'prefix' | 'substring';
/**
 * One `manifest.searchables` entry, as the kernel needs it.
 *
 * `table` and `idColumn` are not authored — `manifestEntities()` fills them in
 * from the entity registry. A hand-written manifest that declares a searchable
 * without a table is refused rather than guessed at.
 */
export interface SearchableDeclaration {
    readonly entityType: string;
    readonly fields: readonly string[];
    readonly table?: string;
    readonly idColumn?: string;
    readonly tokenizer?: SearchTokenizer;
}
/** A resolved searchable: everything the DDL and the query need, nothing optional. */
export interface SearchIndexPlan {
    readonly moduleId: string;
    readonly entityType: string;
    readonly table: string;
    readonly idColumn: string;
    readonly fields: readonly string[];
    readonly tokenizer: SearchTokenizer;
    /** The FTS5 table. Kernel-owned: `_substrat_*`, which module code may read and never write. */
    readonly indexTable: string;
}
/** One hit. Ids only — the caller hydrates through its own read path. */
export interface SearchHit {
    readonly entityType: string;
    readonly id: string;
    /** FTS5 bm25: lower is better. Carried so a caller can merge two entity types into one list. */
    readonly rank: number;
}
export interface SearchOptions {
    /** Defaults to `DEFAULT_SEARCH_LIMIT`, capped at `MAX_SEARCH_LIMIT`. */
    readonly limit?: number;
    /**
     * Which rows (#119): `active` when unset, so an archived or trashed row never surfaces in a
     * picker nobody asked to show it in. `archived` asks for the archive. The bin is not here —
     * `ctx.searchTrashed` reads it, checking the declared trash key per hit.
     */
    readonly view?: Exclude<EntityStateName, 'trashed'>;
}
/**
 * A typeahead wants ten rows, not ten thousand. The cap is the design: a ranked
 * result set has no stable sort key, so it has no honest cursor either — Stripe
 * documents that paginating a ranked search "can reorder some records, causing
 * them to be missing or duplicated on a page". Capping sidesteps that instead of
 * shipping a cursor that lies. Deep paging over search is #811's `Page<T>` over a
 * declared sort, which is a different question with a different answer.
 */
export declare const DEFAULT_SEARCH_LIMIT = 20;
export declare const MAX_SEARCH_LIMIT = 100;
/** Raised for a term the index cannot answer. Distinguishable from a crash at the seam. */
export declare class SearchTermTooShort extends Error {
    readonly minimum: number;
    constructor(minimum: number);
}
/** Raised for an entity type no registered module declares searchable. */
export declare class NotSearchable extends Error {
    readonly entityType: string;
    constructor(entityType: string);
}
/**
 * Is this table part of a derived search index?
 *
 * True for the FTS5 table AND its shadow tables (`…_data`, `…_idx`, `…_config`,
 * `…_docsize`), which SQLite names by prefixing the virtual table's own name.
 *
 * **Used to keep the index OUT of a scope dump.** A dump replays DDL and then
 * inserts rows, and a shadow table refuses both — workerd answers "object name
 * reserved for internal use", and D1's exporter refuses a whole database that
 * merely contains an fts5 table (cloudflare/workers-sdk#9519). Excluding it is
 * also just correct: an index is derived data, and the import rebuilds it from
 * the content tables it just loaded. Nothing is lost that was not recomputable.
 *
 * **The attachment text tables share the prefix on purpose (#1575).**
 * `_substrat_search__attachment_text` holds text extracted from attachment BYTES, and a
 * dump carries an attachment's metadata row and never its bytes. Keeping the text out of
 * the dump keeps it wherever the bytes are; a load re-queues extraction for the rows it
 * brought back (`reconcileAttachmentText`) instead of carrying a plaintext copy of every
 * file into every exported dump and backup.
 */
export declare function isSearchIndexTable(name: string): boolean;
/**
 * Resolve one module's declarations into plans.
 *
 * Refuses rather than skips. A `searchables` entry that cannot become an index is
 * a declaration the author believes is live, and the failure mode of skipping is
 * a search box that returns nothing with no error anywhere — the exact silence
 * this feature exists to end.
 */
export declare function searchIndexPlans(moduleId: string, searchables: readonly SearchableDeclaration[] | undefined): SearchIndexPlan[];
/**
 * The DDL for one plan: an external-content FTS5 table, the three triggers that
 * keep it in step, and a rebuild.
 *
 * **External content, not a copy.** The index stores terms and points at the
 * source table's `rowid`; the text itself is not duplicated. That also makes
 * `rebuild` the whole backfill story — it reads the content table.
 *
 * **Drop-then-create, every time the declaration changes.** The version below is
 * the declaration itself, so adding a field re-runs this, and re-running has to
 * produce an index matching the NEW declaration rather than silently keeping the
 * old columns. Nothing is lost by dropping: an index is derived data, and the
 * rebuild at the end reconstructs it from rows that never moved.
 */
export declare function searchIndexDdl(plan: SearchIndexPlan): string;
/**
 * What `searchIndexDdl` creates, each with its CREATE statement: the FTS table, then the three
 * triggers that keep it in step (insert, delete, update).
 */
export declare function searchIndexObjects(plan: SearchIndexPlan): DerivedObject[];
/**
 * The migrations that provision a module's declared indexes, journaled like any
 * other so a scope applies them once and a changed declaration re-applies.
 *
 * **The version IS the declaration.** `search/customer:prefix:name+number` says
 * everything that decides the DDL, so adding a field or switching a tokenizer
 * produces a new version and re-runs; changing nothing produces the same version
 * and does not. A hash would say the same thing less legibly in the one place an
 * operator reads when a scope is stuck (`_substrat_migrations`).
 *
 * Appended AFTER the module's own migrations by the adapter, which is what makes
 * the content table exist by the time the trigger references it.
 */
export declare function searchIndexMigrations(moduleId: string, searchables: readonly SearchableDeclaration[] | undefined): SqlMigration[];
/** One plan's migration version — the declaration itself, as above. */
export declare const searchIndexVersion: (plan: SearchIndexPlan) => string;
/**
 * Turn what a person typed into an FTS5 MATCH expression.
 *
 * **Everything is quoted, always.** FTS5's query syntax has operators (`AND`,
 * `OR`, `NOT`, `*`, `^`, `:`, `"`) and a picker's input is a name, not a query —
 * someone searching for `AND Sons` or `O"Brien` must get rows, not a syntax
 * error, and must not be able to steer the match. So the input is split into
 * bare terms and each is re-emitted as a quoted string.
 *
 * **In prefix mode every term is a prefix, not just the last.** The obvious rule
 * — only the final token is still being typed — was measured against a real index
 * and is wrong: `unicode61` tokenizes "Andersson Fastigheter AB" into whole
 * words, so someone typing "anders fast" matched NOTHING while "anders" alone
 * matched. In a picker every token is plausibly half-typed. Prefixing all of them
 * can only widen the result set, and the set is ranked and capped anyway.
 *
 * **In substring mode nothing is appended, and short terms are dropped.** Trigram
 * matching is already inside-the-word, and appending `*` there is a documented
 * trap that changes the results rather than widening them. A term below the
 * trigram floor is silently ignored BY THE INDEX (measured: `"AND" "x" "OR"`
 * matched "Andersson" — the `x` constrained nothing), so it is dropped here
 * instead, where the behaviour is written down rather than inferred from a match
 * that looks wrong.
 */
export declare function searchMatchExpression(term: string, tokenizer: SearchTokenizer): string;
/**
 * The read: ids and ranks, joined back to the content table for the declared id.
 *
 * Ids ONLY, deliberately. The row shape a caller wants is its own — its
 * projections, its joins, its permission narrowing — and returning rows here
 * would be a second read path with a second answer to "what is a customer".
 * Hydrating through the module's own query keeps that one code path, at the cost
 * of one extra `WHERE id IN (…)` the caller was going to write anyway.
 *
 * **The FTS table is not aliased, and cannot be.** `MATCH` and `bm25()` both take
 * the table's own name — that name IS the hidden column being matched — so
 * aliasing it to `idx` and writing `WHERE idx MATCH ?` fails at prepare time with
 * "no such column: idx". Found by running the emitted SQL rather than reading it.
 */
export declare function searchQuery(plan: SearchIndexPlan, match: string, limit: number, 
/**
 * A further predicate over the source row, aliased `src` — the archive/trash view (#119).
 * Applied BEFORE the limit, so hiding rows never shortens a ranked top-N.
 */
where?: string): {
    sql: string;
    params: [string, number];
};
/** Clamp a caller's `limit` into the range the index will answer. */
export declare function searchLimit(requested: number | undefined): number;
//# sourceMappingURL=search-index.d.ts.map