import { PDFRawStream } from '../../../plugins.js';
/**
 * Base class for PDF XML extractors with common functionality
 */
export declare abstract class BaseXMLExtractor {
    /**
     * Known XML file names for different invoice formats
     */
    protected readonly knownFileNames: string[];
    /**
     * Known XML formats to validate extracted content
     */
    protected readonly knownFormats: string[];
    /**
     * Known XML end tags for extracting content from strings
     */
    protected readonly knownEndTags: string[];
    /**
     * Extract XML from a PDF buffer
     * @param pdfBuffer PDF buffer
     * @returns XML content or null if not found
     */
    abstract extractXml(pdfBuffer: Uint8Array | Buffer): Promise<string | null>;
    /**
     * Check if an XML string is valid
     * @param xmlString XML string to check
     * @returns True if the XML is valid
     */
    protected isValidXml(xmlString: string): boolean;
    /**
     * Check if the XML string contains a known element
     * @param xmlString XML string to check
     * @returns True if the XML contains a known element
     */
    protected hasKnownXmlElement(xmlString: string): boolean;
    /**
     * Check if the XML string contains a known format
     * @param xmlString XML string to check
     * @returns True if the XML contains a known format
     */
    protected hasKnownFormat(xmlString: string): boolean;
    /**
     * Check if the XML string has a proper structure
     * @param xmlString XML string to check
     * @returns True if the XML has a proper structure
     */
    protected hasProperXmlStructure(xmlString: string): boolean;
    /**
     * Check if the XML string contains binary data
     * @param xmlString XML string to check
     * @returns True if the XML contains binary data
     */
    protected hasBinaryData(xmlString: string): boolean;
    /**
     * Extract XML from a string
     * @param text Text to extract XML from
     * @param startIndex Index to start extraction from
     * @returns XML content or null if not found
     */
    protected extractXmlFromString(text: string, startIndex?: number): string | null;
    /**
     * Decompress and decode XML content from a PDF stream
     * @param stream PDF stream containing XML data
     * @param fileName Name of the file (for logging)
     * @returns XML content or null if not valid
     */
    protected extractXmlFromStream(stream: PDFRawStream, fileName: string): Promise<string | null>;
    /**
     * Try to decompress a buffer using different methods
     * @param buffer Buffer to decompress
     * @returns Decompressed buffer or null if decompression failed
     */
    protected tryDecompress(buffer: Uint8Array): Uint8Array | null;
    /**
     * Try to decode a buffer to a string using different encodings
     * @param buffer Buffer to decode
     * @returns Decoded string or null if decoding failed
     */
    protected tryDecodeBuffer(buffer: Uint8Array): string | null;
    /**
     * Decode a buffer using ISO-8859-1 (Latin1) encoding
     * @param buffer Buffer to decode
     * @returns Decoded string
     */
    protected decodeLatin1(buffer: Uint8Array): string;
    /**
     * Check if a string is plausibly XML (quick check before validation)
     * @param content String to check
     * @returns True if the string is plausibly XML
     */
    protected isPlausibleXml(content: string): boolean;
}