@fin.cx/einvoice/dist_ts/formats/pdf/extractors/text.extractor.d.ts

A TypeScript module for creating, manipulating, and embedding XML data within PDF files specifically tailored for electronic invoice (einvoice) packages.

import { BaseXMLExtractor } from './base.extractor.js';
/**
 * Text-based XML extractor for PDF documents
 * Extracts XML by searching for XML patterns in the PDF text
 * Used as a fallback when other extraction methods fail
 */
export declare class TextXMLExtractor extends BaseXMLExtractor {
    private readonly CHUNK_SIZE;
    private readonly MAX_CHUNKS;
    private readonly XML_PATTERNS;
    /**
     * Extract XML from a PDF buffer by searching for XML patterns in the text
     * Uses a chunked approach to handle large files efficiently
     * @param pdfBuffer PDF buffer
     * @returns XML content or null if not found
     */
    extractXml(pdfBuffer: Uint8Array | Buffer): Promise<string | null>;
    /**
     * Extract XML from buffer using a chunked approach
     * This helps avoid memory issues with large PDFs
     * @param buffer Buffer to search in
     * @returns XML content or null if not found
     */
    private extractXmlFromBufferChunked;
    /**
     * Process a single chunk of the PDF buffer
     * @param chunk Chunk buffer to process
     * @param chunkOffset Offset position of the chunk in the original buffer
     * @returns XML content or null if not found
     */
    private processChunk;
    /**
     * Safely decode a buffer to string using the specified encoding
     * @param buffer Buffer to decode
     * @param encoding Encoding to use ('utf-8' or 'latin1')
     * @returns Decoded string
     */
    private decodeBufferToString;
    /**
     * Search for XML patterns in a string
     * @param content String to search in
     * @returns XML content or null if not found
     */
    private searchForXmlInString;
}