/**
 * F5 CLI - PDF Document Processor
 * Extract content from PDF files with optional OCR
 *
 * @module @f5/cli/core/pdf-processor
 * @version 1.0.0
 */
export interface PdfProcessorOptions {
    enableOcr?: boolean;
    ocrLanguage?: string;
    maxPages?: number;
    extractImages?: boolean;
    imagesOutputDir?: string;
}
export interface PdfSection {
    type: 'text' | 'table' | 'heading';
    content: string;
    page: number;
    confidence?: number;
}
export interface PdfPage {
    pageNumber: number;
    text: string;
    hasImages: boolean;
}
export interface PdfParseResult {
    fileName: string;
    title: string | null;
    sections: PdfSection[];
    pages: PdfPage[];
    metadata: {
        pageCount: number;
        wordCount: number;
        author?: string;
        creationDate?: Date;
        modificationDate?: Date;
        isScanned: boolean;
        ocrApplied: boolean;
    };
}
export declare class PdfProcessor {
    private options;
    constructor(options?: PdfProcessorOptions);
    /**
     * Parse PDF document using pdf-parse v2 API
     */
    parseFile(filePath: string): Promise<PdfParseResult>;
    /**
     * Build pages array from getText result or by splitting text
     */
    private buildPagesArray;
    /**
     * Parse PDF date format (D:YYYYMMDDHHmmSS)
     */
    private parsePdfDate;
    /**
     * Apply OCR to scanned PDF
     */
    private applyOcr;
    /**
     * Parse text into structured sections
     */
    private parseTextToSections;
    /**
     * Split text into pages (heuristic)
     */
    private splitIntoPages;
    /**
     * Extract title from text
     */
    private extractTitle;
    /**
     * Convert to Markdown
     */
    toMarkdown(result: PdfParseResult): string;
}