@kreuzberg/wasm 4.0.0-rc.10

package/dist/index.d.cts

@@ -0,0 +1,466 @@
+import { E as ExtractionConfig, a as ExtractionResult } from './types-CKjcIYcX.cjs';
+export { C as Chunk, c as ChunkMetadata, b as ChunkingConfig, d as ExtractedImage, I as ImageExtractionConfig, L as LanguageDetectionConfig, M as Metadata, O as OcrBackendProtocol, e as OcrConfig, P as PageContent, f as PageExtractionConfig, g as PdfConfig, h as PostProcessorConfig, T as Table, i as TesseractConfig, j as TokenReductionConfig } from './types-CKjcIYcX.cjs';
+export { configToJS, fileToUint8Array, isValidExtractionResult, jsToExtractionResult, wrapWasmError } from './adapters/wasm-adapter.cjs';
+export { clearOcrBackends, getOcrBackend, listOcrBackends, registerOcrBackend, unregisterOcrBackend } from './ocr/registry.cjs';
+export { TesseractWasmBackend } from './ocr/tesseract-wasm-backend.cjs';
+export { RuntimeType, WasmCapabilities, detectRuntime, getRuntimeInfo, getRuntimeVersion, getWasmCapabilities, hasBigInt, hasBlob, hasFileApi, hasModuleWorkers, hasSharedArrayBuffer, hasWasm, hasWasmStreaming, hasWorkers, isBrowser, isBun, isDeno, isNode, isServerEnvironment, isWebEnvironment } from './runtime.cjs';
+
+/**
+ * Kreuzberg - WebAssembly Bindings for Browser and Runtime Environments
+ *
+ * This module provides WebAssembly bindings for Kreuzberg document intelligence,
+ * enabling high-performance document extraction in browser and JavaScript runtime environments.
+ *
+ * ## Features
+ *
+ * - Extract text, metadata, and tables from documents
+ * - Support for multiple document formats (PDF, Office, images, etc.)
+ * - Browser and runtime-compatible WASM bindings
+ * - Type-safe TypeScript interfaces
+ * - Runtime detection and feature capability checking
+ * - Automatic type conversion and error handling
+ *
+ * ## Installation
+ *
+ * ```bash
+ * npm install @kreuzberg/wasm
+ * ```
+ *
+ * ## Basic Usage
+ *
+ * ```typescript
+ * import { extractBytes, initWasm } from '@kreuzberg/wasm';
+ *
+ * // Initialize WASM module once at app startup
+ * await initWasm();
+ *
+ * // Extract from bytes
+ * const bytes = new Uint8Array(buffer);
+ * const result = await extractBytes(bytes, 'application/pdf');
+ * console.log(result.content);
+ * ```
+ *
+ * ## Browser Usage with File Input
+ *
+ * ```typescript
+ * import { extractBytes, initWasm } from '@kreuzberg/wasm';
+ * import { fileToUint8Array } from '@kreuzberg/wasm/adapters/wasm-adapter';
+ *
+ * // Initialize once at app startup
+ * await initWasm();
+ *
+ * // Handle file input
+ * const fileInput = document.getElementById('file');
+ * fileInput.addEventListener('change', async (e) => {
+ *   const file = e.target.files?.[0];
+ *   if (file) {
+ *     const bytes = await fileToUint8Array(file);
+ *     const result = await extractBytes(bytes, file.type);
+ *     console.log(result.content);
+ *   }
+ * });
+ * ```
+ *
+ * ## Runtime Detection
+ *
+ * ```typescript
+ * import { detectRuntime, getWasmCapabilities } from '@kreuzberg/wasm/runtime';
+ *
+ * const runtime = detectRuntime();
+ * const caps = getWasmCapabilities();
+ *
+ * if (caps.hasWorkers) {
+ *   // Can use Web Workers for parallel processing
+ * }
+ * ```
+ *
+ * ## Configuration
+ *
+ * ```typescript
+ * import { extractBytes, initWasm } from '@kreuzberg/wasm';
+ * import type { ExtractionConfig } from '@kreuzberg/wasm';
+ *
+ * await initWasm();
+ *
+ * const config: ExtractionConfig = {
+ *   ocr: {
+ *     backend: 'tesseract',
+ *     language: 'eng'
+ *   },
+ *   chunking: {
+ *     maxChars: 1000,
+ *     chunkOverlap: 100
+ *   },
+ *   images: {
+ *     extractImages: true,
+ *     targetDpi: 150
+ *   }
+ * };
+ *
+ * const result = await extractBytes(bytes, 'application/pdf', config);
+ * ```
+ */
+
+/**
+ * Initialize the WASM module
+ *
+ * This function must be called once before using any extraction functions.
+ * It loads and initializes the WASM module in the current runtime environment,
+ * automatically selecting the appropriate WASM variant for the detected runtime.
+ *
+ * Multiple calls to initWasm() are safe and will return immediately if already initialized.
+ *
+ * @throws {Error} If WASM module fails to load or is not supported in the current environment
+ *
+ * @example Basic Usage
+ * ```typescript
+ * import { initWasm } from '@kreuzberg/wasm';
+ *
+ * async function main() {
+ *   await initWasm();
+ *   // Now you can use extraction functions
+ * }
+ *
+ * main().catch(console.error);
+ * ```
+ *
+ * @example With Error Handling
+ * ```typescript
+ * import { initWasm, getWasmCapabilities } from '@kreuzberg/wasm';
+ *
+ * async function initializeKreuzberg() {
+ *   const caps = getWasmCapabilities();
+ *   if (!caps.hasWasm) {
+ *     throw new Error('WebAssembly is not supported in this environment');
+ *   }
+ *
+ *   try {
+ *     await initWasm();
+ *     console.log('Kreuzberg initialized successfully');
+ *   } catch (error) {
+ *     console.error('Failed to initialize Kreuzberg:', error);
+ *     throw error;
+ *   }
+ * }
+ * ```
+ */
+declare function initWasm(): Promise<void>;
+/**
+ * Check if WASM module is initialized
+ *
+ * @returns True if WASM module is initialized, false otherwise
+ *
+ * @example
+ * ```typescript
+ * if (!isInitialized()) {
+ *   await initWasm();
+ * }
+ * ```
+ */
+declare function isInitialized(): boolean;
+/**
+ * Get WASM module version
+ *
+ * @throws {Error} If WASM module is not initialized
+ * @returns The version string of the WASM module
+ *
+ * @example
+ * ```typescript
+ * const version = getVersion();
+ * console.log(`Using Kreuzberg ${version}`);
+ * ```
+ */
+declare function getVersion(): string;
+/**
+ * Get initialization error if module failed to load
+ *
+ * @returns The error that occurred during initialization, or null if no error
+ *
+ * @internal
+ */
+declare function getInitializationError(): Error | null;
+/**
+ * Extract content from bytes (document data)
+ *
+ * Extracts text, metadata, tables, images, and other content from document bytes.
+ * Automatically detects document type from MIME type and applies appropriate extraction logic.
+ *
+ * @param data - The document bytes to extract from
+ * @param mimeType - MIME type of the document (e.g., 'application/pdf', 'image/jpeg')
+ * @param config - Optional extraction configuration
+ * @returns Promise resolving to the extraction result
+ * @throws {Error} If WASM module is not initialized or extraction fails
+ *
+ * @example Extract PDF
+ * ```typescript
+ * const bytes = new Uint8Array(buffer);
+ * const result = await extractBytes(bytes, 'application/pdf');
+ * console.log(result.content);
+ * console.log(result.tables);
+ * ```
+ *
+ * @example Extract with Configuration
+ * ```typescript
+ * const result = await extractBytes(bytes, 'application/pdf', {
+ *   ocr: {
+ *     backend: 'tesseract',
+ *     language: 'deu' // German
+ *   },
+ *   images: {
+ *     extractImages: true,
+ *     targetDpi: 200
+ *   }
+ * });
+ * ```
+ *
+ * @example Extract from File
+ * ```typescript
+ * const file = inputEvent.target.files[0];
+ * const bytes = await fileToUint8Array(file);
+ * const result = await extractBytes(bytes, file.type);
+ * ```
+ */
+declare function extractBytes(data: Uint8Array, mimeType: string, config?: ExtractionConfig | null): Promise<ExtractionResult>;
+/**
+ * Extract content from a file on the file system
+ *
+ * Node.js and Deno specific function that reads a file from the file system
+ * and extracts content from it. Automatically detects MIME type if not provided.
+ *
+ * @param path - Path to the file to extract from
+ * @param mimeType - Optional MIME type of the file. If not provided, will attempt to detect
+ * @param config - Optional extraction configuration
+ * @returns Promise resolving to the extraction result
+ * @throws {Error} If WASM module is not initialized, file doesn't exist, or extraction fails
+ *
+ * @example Extract with auto-detection
+ * ```typescript
+ * const result = await extractFile('./document.pdf');
+ * console.log(result.content);
+ * ```
+ *
+ * @example Extract with explicit MIME type
+ * ```typescript
+ * const result = await extractFile('./document.docx', 'application/vnd.openxmlformats-officedocument.wordprocessingml.document');
+ * ```
+ *
+ * @example Extract from Node.js with config
+ * ```typescript
+ * import { extractFile } from '@kreuzberg/wasm';
+ * import { readFile } from 'fs/promises';
+ *
+ * const result = await extractFile('./report.xlsx', null, {
+ *   chunking: {
+ *     maxChars: 1000
+ *   }
+ * });
+ * ```
+ */
+declare function extractFile(path: string, mimeType?: string | null, config?: ExtractionConfig | null): Promise<ExtractionResult>;
+/**
+ * Extract content from a File or Blob (browser-friendly wrapper)
+ *
+ * Convenience function that wraps fileToUint8Array and extractBytes,
+ * providing a streamlined API for browser applications handling file inputs.
+ *
+ * @param file - The File or Blob to extract from
+ * @param mimeType - Optional MIME type. If not provided, uses file.type if available
+ * @param config - Optional extraction configuration
+ * @returns Promise resolving to the extraction result
+ * @throws {Error} If WASM module is not initialized or extraction fails
+ *
+ * @example Simple file extraction
+ * ```typescript
+ * const fileInput = document.getElementById('file');
+ * fileInput.addEventListener('change', async (e) => {
+ *   const file = e.target.files?.[0];
+ *   if (file) {
+ *     const result = await extractFromFile(file);
+ *     console.log(result.content);
+ *   }
+ * });
+ * ```
+ *
+ * @example With configuration
+ * ```typescript
+ * const result = await extractFromFile(file, file.type, {
+ *   chunking: { maxChars: 1000 },
+ *   images: { extractImages: true }
+ * });
+ * ```
+ */
+declare function extractFromFile(file: File | Blob, mimeType?: string | null, config?: ExtractionConfig | null): Promise<ExtractionResult>;
+/**
+ * Extract content from bytes synchronously
+ *
+ * Synchronous version of extractBytes. Performs extraction without async operations.
+ * Note: Some extraction features may still be async internally, but the wrapper is synchronous.
+ *
+ * @param data - The document bytes to extract from
+ * @param mimeType - MIME type of the document
+ * @param config - Optional extraction configuration
+ * @returns The extraction result
+ * @throws {Error} If WASM module is not initialized or extraction fails
+ *
+ * @example
+ * ```typescript
+ * const bytes = new Uint8Array(buffer);
+ * const result = extractBytesSync(bytes, 'application/pdf');
+ * console.log(result.content);
+ * ```
+ */
+declare function extractBytesSync(data: Uint8Array, mimeType: string, config?: ExtractionConfig | null): ExtractionResult;
+/**
+ * Batch extract content from multiple byte arrays asynchronously
+ *
+ * Extracts content from multiple documents in a single batch operation,
+ * allowing for more efficient processing of multiple files.
+ *
+ * @param files - Array of objects containing data (Uint8Array) and mimeType (string)
+ * @param config - Optional extraction configuration applied to all files
+ * @returns Promise resolving to array of extraction results
+ * @throws {Error} If WASM module is not initialized or extraction fails
+ *
+ * @example
+ * ```typescript
+ * const files = [
+ *   { data: pdfBytes, mimeType: 'application/pdf' },
+ *   { data: docxBytes, mimeType: 'application/vnd.openxmlformats-officedocument.wordprocessingml.document' }
+ * ];
+ * const results = await batchExtractBytes(files);
+ * results.forEach((result) => console.log(result.content));
+ * ```
+ */
+declare function batchExtractBytes(files: Array<{
+    data: Uint8Array;
+    mimeType: string;
+}>, config?: ExtractionConfig | null): Promise<ExtractionResult[]>;
+/**
+ * Batch extract content from multiple byte arrays synchronously
+ *
+ * Synchronous version of batchExtractBytes. Extracts content from multiple documents
+ * in a single batch operation without async operations.
+ *
+ * @param files - Array of objects containing data (Uint8Array) and mimeType (string)
+ * @param config - Optional extraction configuration applied to all files
+ * @returns Array of extraction results
+ * @throws {Error} If WASM module is not initialized or extraction fails
+ *
+ * @example
+ * ```typescript
+ * const files = [
+ *   { data: pdfBytes, mimeType: 'application/pdf' },
+ *   { data: docxBytes, mimeType: 'application/vnd.openxmlformats-officedocument.wordprocessingml.document' }
+ * ];
+ * const results = batchExtractBytesSync(files);
+ * results.forEach((result) => console.log(result.content));
+ * ```
+ */
+declare function batchExtractBytesSync(files: Array<{
+    data: Uint8Array;
+    mimeType: string;
+}>, config?: ExtractionConfig | null): ExtractionResult[];
+/**
+ * Batch extract content from multiple File objects asynchronously
+ *
+ * Convenience function that converts File objects to Uint8Array and calls batchExtractBytes.
+ * Automatically uses the file.type as MIME type if available.
+ *
+ * @param files - Array of File objects to extract from
+ * @param config - Optional extraction configuration applied to all files
+ * @returns Promise resolving to array of extraction results
+ * @throws {Error} If WASM module is not initialized, files cannot be read, or extraction fails
+ *
+ * @example
+ * ```typescript
+ * const fileInput = document.getElementById('files');
+ * const files = Array.from(fileInput.files ?? []);
+ * const results = await batchExtractFiles(files);
+ * results.forEach((result, index) => {
+ *   console.log(`File ${index}: ${result.content.substring(0, 50)}...`);
+ * });
+ * ```
+ */
+declare function batchExtractFiles(files: File[], config?: ExtractionConfig | null): Promise<ExtractionResult[]>;
+/**
+ * Enable OCR functionality with tesseract-wasm backend
+ *
+ * Convenience function that automatically initializes and registers the Tesseract WASM backend.
+ * This is the recommended approach for enabling OCR in WASM-based applications.
+ *
+ * ## Browser Requirement
+ *
+ * This function requires a browser environment with support for:
+ * - WebWorkers (for Tesseract processing)
+ * - createImageBitmap (for image conversion)
+ * - Blob API
+ *
+ * ## Network Requirement
+ *
+ * Training data will be loaded from jsDelivr CDN on first use of each language.
+ * Ensure network access to cdn.jsdelivr.net is available.
+ *
+ * @throws {Error} If not in browser environment or tesseract-wasm is not available
+ *
+ * @example Basic Usage
+ * ```typescript
+ * import { enableOcr, extractBytes, initWasm } from '@kreuzberg/wasm';
+ *
+ * async function main() {
+ *   // Initialize WASM module
+ *   await initWasm();
+ *
+ *   // Enable OCR with tesseract-wasm
+ *   await enableOcr();
+ *
+ *   // Now you can use OCR in extraction
+ *   const imageBytes = new Uint8Array(buffer);
+ *   const result = await extractBytes(imageBytes, 'image/png', {
+ *     ocr: { backend: 'tesseract-wasm', language: 'eng' }
+ *   });
+ *
+ *   console.log(result.content); // Extracted text
+ * }
+ *
+ * main().catch(console.error);
+ * ```
+ *
+ * @example With Progress Tracking
+ * ```typescript
+ * import { enableOcr, TesseractWasmBackend } from '@kreuzberg/wasm';
+ *
+ * async function setupOcrWithProgress() {
+ *   const backend = new TesseractWasmBackend();
+ *   backend.setProgressCallback((progress) => {
+ *     console.log(`OCR Progress: ${progress}%`);
+ *     updateProgressBar(progress);
+ *   });
+ *
+ *   await backend.initialize();
+ *   registerOcrBackend(backend);
+ * }
+ *
+ * setupOcrWithProgress().catch(console.error);
+ * ```
+ *
+ * @example Multiple Languages
+ * ```typescript
+ * import { enableOcr, extractBytes, initWasm } from '@kreuzberg/wasm';
+ *
+ * await initWasm();
+ * await enableOcr();
+ *
+ * // Extract English text
+ * const englishResult = await extractBytes(engImageBytes, 'image/png', {
+ *   ocr: { backend: 'tesseract-wasm', language: 'eng' }
+ * });
+ *
+ * // Extract German text - model is cached after first use
+ * const germanResult = await extractBytes(deImageBytes, 'image/png', {
+ *   ocr: { backend: 'tesseract-wasm', language: 'deu' }
+ * });
+ * ```
+ */
+declare function enableOcr(): Promise<void>;
+
+export { ExtractionConfig, ExtractionResult, batchExtractBytes, batchExtractBytesSync, batchExtractFiles, enableOcr, extractBytes, extractBytesSync, extractFile, extractFromFile, getInitializationError, getVersion, initWasm, isInitialized };