import type { Document as MupdfDocument } from 'mupdf';
import type { HeadingAnchor } from '../utils/source-context.js';
import { type EmbedderInterface, type FilteredTextFragment } from './pdf-filter.js';
interface StextBbox {
    x: number;
    y: number;
    w: number;
    h: number;
}
/** The part of mupdf's structured-text JSON this module reads. */
interface StextJson {
    blocks: Array<{
        type: string;
        /** Present on image blocks; the visual detector reads it to locate rasters. */
        bbox?: StextBbox;
        lines?: Array<{
            text: string;
            x: number;
            y: number;
            bbox?: StextBbox;
            font: {
                size: number;
                name?: string;
                weight?: string;
            };
        }>;
    }>;
}
/**
 * `text` is post-header/footer-filtering; `stextJson` is the raw mupdf JSON,
 * kept for the downstream visual detector.
 */
interface ExtractedPage {
    headings: HeadingAnchor[];
    pageNum: number;
    text: string;
    textFragments: FilteredTextFragment[];
    stextJson: StextJson;
}
/** Result returned by `extractPdfPages`. */
interface ExtractedPdf {
    pages: ExtractedPage[];
    metadataTitle: string | undefined;
    page1FontHint: {
        text: string;
        fontSize: number;
    } | undefined;
}
export declare function extractPdfPages(doc: MupdfDocument, embedder: EmbedderInterface, stextOptions: string): Promise<ExtractedPdf>;
export {};
//# sourceMappingURL=pdf-extract.d.ts.map