/**
 * PDF Extractor - Extract text and structured data from PDF files
 *
 * Useful for:
 * - Processing government PDF documents
 * - Extracting text from official forms and regulations
 * - Handling downloadable visa requirement documents
 */
export interface PDFExtractResult {
    text: string;
    numPages: number;
    info: {
        title?: string;
        author?: string;
        subject?: string;
        keywords?: string;
        creationDate?: Date;
        modificationDate?: Date;
    };
    metadata?: Record<string, unknown>;
}
export interface PDFPageContent {
    pageNumber: number;
    text: string;
}
/**
 * Extract text content from a PDF buffer
 */
export declare function extractPDFText(pdfBuffer: Buffer): Promise<PDFExtractResult>;
/**
 * Extract text from a PDF URL
 */
export declare function extractPDFFromURL(url: string): Promise<PDFExtractResult>;
/**
 * Extract text from a PDF file path
 */
export declare function extractPDFFromFile(filePath: string): Promise<PDFExtractResult>;
/**
 * Extract structured sections from PDF text
 * Attempts to identify headers, paragraphs, and lists
 */
export declare function structurePDFContent(text: string): {
    sections: {
        heading: string;
        content: string;
    }[];
    lists: string[][];
};
/**
 * Extract key-value pairs from PDF (common in forms)
 */
export declare function extractKeyValuePairs(text: string): Map<string, string>;
/**
 * Check if a URL points to a PDF
 */
export declare function isPDFUrl(url: string): boolean;
export type { PDFFormField, PDFFormSection, PDFDocumentRequirement, PDFFormExtractionResult, PDFFormExtractionOptions, PDFFormFieldType, PDFFormInfo, } from '../types/pdf-forms.js';
/**
 * PDF extractor class for stateful operations
 */
export declare class PDFExtractor {
    private cache;
    /**
     * Extract with caching
     */
    extract(source: string | Buffer): Promise<PDFExtractResult>;
    /**
     * Clear cache
     */
    clearCache(): void;
    /**
     * Get structured content
     */
    extractStructured(source: string | Buffer): Promise<{
        result: PDFExtractResult;
        sections: {
            heading: string;
            content: string;
        }[];
        lists: string[][];
        keyValues: Map<string, string>;
    }>;
    /**
     * Extract form fields from PDF (INT-017)
     *
     * Extracts fillable form fields (AcroForms) from PDFs using pdf-lib.
     * Also extracts document requirements from text content.
     *
     * @example
     * ```typescript
     * const extractor = new PDFExtractor();
     * const result = await extractor.extractFormFields('https://example.gov/form.pdf', {
     *   language: 'es',
     *   extractDocumentRequirements: true,
     * });
     * console.log(`Found ${result.fields.length} form fields`);
     * ```
     */
    extractFormFields(source: string | Buffer, options?: import('../types/pdf-forms.js').PDFFormExtractionOptions): Promise<import('../types/pdf-forms.js').PDFFormExtractionResult>;
    /**
     * Get buffer from source (URL or file path)
     */
    private getBuffer;
}
export declare const pdfExtractor: PDFExtractor;
//# sourceMappingURL=pdf-extractor.d.ts.map