/**
 * Result of title extraction, including how the title was determined
 */
export interface TitleExtractionResult {
    title: string;
    source: 'metadata' | 'content' | 'filename';
}
/** `2024-annual-report.pdf` -> `2024 annual report`. */
export declare function fileNameToTitle(fileName: string): string;
/** Priority: YAML frontmatter title -> first `#` H1 -> file name. */
export declare function extractMarkdownTitle(text: string, fileName: string): TitleExtractionResult;
/** Priority: a first line followed by a blank line -> file name. */
export declare function extractTxtTitle(text: string, fileName: string): TitleExtractionResult;
/** Priority: Readability title -> file name. */
export declare function extractHtmlTitle(readabilityTitle: string, fileName: string): TitleExtractionResult;
/**
 * Priority: PDF metadata `/Title` -> page-1 chunk 0 -> file name.
 *
 * A metadata title that looks like a file path (contains `/` or `\`) is
 * rejected, since some producers write the source path there.
 */
export declare function extractPdfTitle(metadataTitle: string | undefined, firstPageChunkText: string | undefined, fileName: string, firstPageFontHint?: {
    text: string;
    fontSize: number;
}): TitleExtractionResult;
/** Priority: DOCX core title -> first non-empty `<h1>` -> file name. */
export declare function extractDocxTitle(document: Document, fileName: string, metadataTitle?: string): TitleExtractionResult;
//# sourceMappingURL=title-extractor.d.ts.map