socraticode/dist/services/chunk-split.d.ts

SocratiCode — MCP server for local codebase indexing, semantic search, and code dependency graphs. All private, all local via Docker.

/**
 * Splitting text at the per-chunk character cap, and the chunk ids that split
 * produces.
 *
 * Shared by the two chunkers — `chunkFileContent` for source files and
 * `chunkArtifactContent` for context artifacts — which both cut by line count
 * and then have to honour a cap counted in characters. It lives in its own
 * module because indexer.ts already imports context-artifacts.ts, so the shared
 * helper cannot live in either of them.
 */
/**
 * The index format version from which the character cap splits instead of
 * truncating.
 *
 * A collection stores the profile it was created with, and keeps it. One stored
 * below this version keeps truncating — for files that changed and for files
 * discovered after an upgrade alike — so that what is written never drifts from
 * what its persisted effective profile says.
 */
export declare const SPLITTING_INDEX_FORMAT_VERSION = 2;
/** Format a sha256 digest as a valid UUID (required by Qdrant): 8-4-4-4-12 */
export declare function uuidFromSeed(seed: string): string;
/**
 * Derive the id of a continuation piece from the id of the chunk it was split
 * out of.
 *
 * Seeded from the parent id rather than from the position it starts at, because
 * position does not identify a chunk on every path: `chunkByCharacters` gives
 * every chunk of a single-line minified file the same startLine, and an
 * artifact chunk is identified by the line its parent began on. Re-deriving
 * from position would collide across the continuations of one parent, and
 * Qdrant's upsert would silently keep only the last. Seeding from the parent id
 * is unique wherever the parent is.
 */
export declare function continuationId(parentId: string, part: number): string;
/** One piece of a split. Line numbers are 1-based within the text given. */
export interface TextPiece {
    text: string;
    startLine: number;
    endLine: number;
}
/** Boundaries considered while looking backwards inside one capped window. */
export type TextBoundaryMode = "newline" | "code-token";
/**
 * Split text into pieces of at most `maxChunkChars` characters — one more only
 * where a surrogate pair or a CRLF would otherwise be divided.
 *
 * Every character of the input appears in exactly one piece, in order:
 * concatenating `text` across the result reproduces the input.
 *
 * By default each piece ends at the last newline at or before the cap, so a
 * line is never divided and the line range stored on the chunk stays true.
 * Minified code can instead select `code-token`, which also accepts the
 * released chunker's space, tab, semicolon and comma boundaries so identifiers
 * are not divided where a safe boundary exists inside the capped window. When
 * the span holds no eligible boundary, the piece ends at the cap.
 *
 * Text at or below the cap comes back as a single piece, so callers can use
 * this unconditionally.
 */
export declare function splitTextToCharCap(content: string, maxChunkChars: number, boundaryMode?: TextBoundaryMode): TextPiece[];
//# sourceMappingURL=chunk-split.d.ts.map