/**
 * Word Document Processing Utility
 *
 * Handles downloading, validating, and processing Word (.docx, .doc) files.
 * Uses mammoth library to extract text and HTML content from Word documents.
 *
 * Features:
 * - DOCX format validation via ZIP/PK signature check
 * - Text extraction using mammoth.extractRawText()
 * - HTML conversion using mammoth.convertToHtml()
 * - Warning collection from mammoth processing
 * - Support for both URL downloads and direct buffer input
 *
 * @module processors/document/WordProcessor
 *
 * @example
 * ```typescript
 * import { wordProcessor, processWord, isWordFile } from "./WordProcessor.js";
 *
 * // Check if file is supported
 * if (isWordFile(file.mimetype, file.name)) {
 *   const result = await processWord(fileInfo, {
 *     authHeaders: { Authorization: "Bearer token" },
 *   });
 *
 *   if (result.success) {
 *     console.log("Text:", result.data.textContent);
 *     console.log("HTML:", result.data.htmlContent);
 *     console.log("Warnings:", result.data.warnings);
 *   }
 * }
 * ```
 */
import { BaseFileProcessor } from "../base/BaseFileProcessor.js";
import type { FileInfo, ProcessorFileProcessingResult, ProcessOptions, ProcessedWord } from "../../types/index.js";
/**
 * Word Processor - handles .docx and .doc files
 *
 * Uses mammoth library for both text and HTML extraction. The processor
 * validates DOCX files by checking for the ZIP/PK signature (since DOCX
 * files are actually ZIP archives).
 *
 * @example
 * ```typescript
 * const processor = new WordProcessor();
 *
 * // Check if file is supported
 * if (processor.isFileSupported("application/msword", "report.doc")) {
 *   const result = await processor.processFile(fileInfo);
 *   if (result.success) {
 *     console.log("Extracted text:", result.data.textContent);
 *   }
 * }
 * ```
 */
export declare class WordProcessor extends BaseFileProcessor<ProcessedWord> {
    constructor();
    /**
     * Validate downloaded Word document has correct magic bytes.
     * DOCX files are ZIP archives starting with PK signature (0x50 0x4B).
     *
     * @param buffer - Downloaded file content
     * @param fileInfo - Original file information
     * @returns null if valid, error message if invalid
     */
    protected validateDownloadedFile(buffer: Buffer, _fileInfo: FileInfo): Promise<string | null>;
    /**
     * Build processed Word result with extracted text and HTML content.
     * This is a stub that returns an empty result - actual processing
     * happens in the overridden processFile method since mammoth
     * operations are asynchronous.
     *
     * @param buffer - Downloaded file content
     * @param fileInfo - Original file information
     * @returns Processed Word result (placeholder)
     */
    protected buildProcessedResult(buffer: Buffer, fileInfo: FileInfo): ProcessedWord;
    /**
     * Override processFile for async mammoth extraction.
     *
     * The mammoth library's extractRawText and convertToHtml methods are
     * asynchronous, so we need to override the entire processFile method
     * rather than just buildProcessedResult.
     *
     * Processing steps:
     * 1. Validate file type and size
     * 2. Get buffer (download from URL or use provided buffer)
     * 3. Validate downloaded file (check PK signature)
     * 4. Extract text with mammoth.extractRawText()
     * 5. Convert to HTML with mammoth.convertToHtml()
     * 6. Collect any warnings from mammoth
     * 7. Return structured result
     *
     * @param fileInfo - File information with URL or buffer
     * @param options - Optional processing options
     * @returns Processing result with text, HTML, and warnings
     */
    processFile(fileInfo: FileInfo, options?: ProcessOptions): Promise<ProcessorFileProcessingResult<ProcessedWord>>;
}
/**
 * Singleton Word processor instance.
 * Use this for most use cases to avoid creating multiple instances.
 */
export declare const wordProcessor: WordProcessor;
/**
 * Check if a file is a Word document (.docx or .doc).
 *
 * @param mimetype - MIME type of the file
 * @param filename - Filename (for extension-based detection)
 * @returns true if the file is a supported Word document
 *
 * @example
 * ```typescript
 * if (isWordFile(file.mimetype, file.name)) {
 *   const result = await processWord(file);
 * }
 * ```
 */
export declare function isWordFile(mimetype: string, filename: string): boolean;
/**
 * Validate Word document size against configured limit.
 *
 * @param sizeBytes - File size in bytes
 * @returns true if size is within the allowed limit
 *
 * @example
 * ```typescript
 * if (!validateWordSize(file.size)) {
 *   throw new Error(`File exceeds ${SIZE_LIMITS.WORD_MAX_MB}MB limit`);
 * }
 * ```
 */
export declare function validateWordSize(sizeBytes: number): boolean;
/**
 * Process a single Word document.
 *
 * Convenience function that uses the singleton wordProcessor instance.
 *
 * @param fileInfo - File information with URL or buffer
 * @param options - Optional processing options (auth headers, timeout, retry config)
 * @returns Processing result with extracted text, HTML, and warnings
 *
 * @example
 * ```typescript
 * const result = await processWord({
 *   id: "doc-123",
 *   name: "report.docx",
 *   mimetype: "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
 *   size: 12345,
 *   url: "https://example.com/files/report.docx",
 * }, {
 *   authHeaders: { Authorization: "Bearer token" },
 * });
 *
 * if (result.success) {
 *   console.log("Text content:", result.data.textContent);
 *   console.log("HTML content:", result.data.htmlContent);
 *   if (result.data.warnings.length > 0) {
 *     console.warn("Warnings:", result.data.warnings);
 *   }
 * } else {
 *   console.error("Failed:", result.error.userMessage);
 * }
 * ```
 */
export declare function processWord(fileInfo: FileInfo, options?: ProcessOptions): Promise<ProcessorFileProcessingResult<ProcessedWord>>;