@kreuzberg/wasm 4.3.8 → 4.4.0

package/dist/pkg/README.md

@@ -22,7 +22,7 @@
     <img src="https://img.shields.io/maven-central/v/dev.kreuzberg/kreuzberg?label=Java&color=007ec6" alt="Java">
   </a>
   <a href="https://github.com/kreuzberg-dev/kreuzberg/releases">
-    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go&color=007ec6&filter=v4.3.8" alt="Go">
+    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go&color=007ec6&filter=v4.4.0" alt="Go">
   </a>
   <a href="https://www.nuget.org/packages/Kreuzberg/">
     <img src="https://img.shields.io/nuget/v/Kreuzberg?label=C%23&color=007ec6" alt="C#">
@@ -57,6 +57,8 @@
 
 Extract text, tables, images, and metadata from 75+ file formats including PDF, Office documents, and images. WebAssembly bindings for browsers, Deno, and Cloudflare Workers with portable deployment and multi-threading support.
 
+> **Full Feature Parity** — The WASM package supports all extraction capabilities at full parity with native bindings: PDF (via PDFium), Excel/spreadsheets (via Calamine), archives (ZIP, TAR, 7z, GZIP), and OCR (via built-in Tesseract-WASM). No external dependencies required.
+
 
 ## Installation
 
@@ -95,7 +97,7 @@ yarn add @kreuzberg/wasm
 ### System Requirements
 
 - Modern browser with WebAssembly support, or Deno 1.0+, or Cloudflare Workers
-- Optional: [Tesseract WASM](https://github.com/naptha/tesseract.js) for OCR functionality
+- OCR is built-in via Tesseract-WASM (enable at runtime with `enableOcr()`)
 
 
 
@@ -174,6 +176,40 @@ extractWithOcr().catch(console.error);
 See [Table Extraction Guide](https://kreuzberg.dev/features/table-extraction/) for detailed examples.
 
 
+#### Excel/Spreadsheet Extraction
+
+Extract structured data from Excel files directly in the browser or server-side runtimes:
+
+```ts
+import { extractBytes, initWasm } from "@kreuzberg/wasm";
+
+async function extractSpreadsheet() {
+	await initWasm();
+
+	const bytes = new Uint8Array(
+		await fetch("report.xlsx").then((r) => r.arrayBuffer()),
+	);
+
+	const result = await extractBytes(
+		bytes,
+		"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+	);
+
+	console.log("Spreadsheet content:");
+	console.log(result.content);
+
+	if (result.tables && result.tables.length > 0) {
+		result.tables.forEach((table, index) => {
+			console.log(`\nSheet ${index + 1}:`);
+			console.log(table.markdown);
+		});
+	}
+}
+
+extractSpreadsheet().catch(console.error);
+```
+
+
 
 #### Processing Multiple Files
 
@@ -318,14 +354,10 @@ extractDocuments(fileBytes, mimes)
 - **Metadata Extraction** - Retrieve document properties, creation date, author, etc.
 - **Table Extraction** - Parse tables with structure and cell content preservation
 - **Image Extraction** - Extract embedded images and render page previews
-- **OCR Support** - Integrate multiple OCR backends for scanned documents
-
+- **OCR Support** - Built-in Tesseract-WASM for scanned documents and images
+- **Full Feature Parity** - All extraction capabilities at parity with native bindings: PDF, Excel, archives, OCR, and 75+ formats
 - **Async/Await** - Non-blocking document processing with concurrent operations
-
-
 - **Plugin System** - Extensible post-processing for custom text transformation
-
-
 - **Batch Processing** - Efficiently process multiple documents in parallel
 - **Memory Efficient** - Stream large files without loading entirely into memory
 - **Language Detection** - Detect and support multiple languages in documents

package/dist/pkg/kreuzberg_wasm.d.ts

@@ -185,6 +185,31 @@ export function clear_post_processors(): void;
  */
 export function clear_validators(): void;
 
+/**
+ * Compresses multiple entries into a 7z archive in WebAssembly environment.
+ *
+ * This function creates a compressed archive from multiple file entries,
+ * designed specifically for WASM targets.
+ *
+ * # Arguments
+ * * `entries` - Vector of JavaScript strings representing file names/paths
+ * * `datas` - Vector of Uint8Arrays containing the file data corresponding to entries
+ */
+export function compress(entries: string[], datas: Uint8Array[]): Uint8Array;
+
+/**
+ * Decompresses a 7z archive in WebAssembly environment.
+ *
+ * This function is specifically designed for WASM targets and uses JavaScript interop
+ * to handle the decompression process with a callback function.
+ *
+ * # Arguments
+ * * `src` - Uint8Array containing the compressed archive data
+ * * `pwd` - Password string for encrypted archives (use empty string for unencrypted)
+ * * `f` - JavaScript callback function to handle extracted entries
+ */
+export function decompress(src: Uint8Array, pwd: string, f: Function): void;
+
 /**
  * Detect MIME type from raw file bytes.
  *
@@ -600,6 +625,61 @@ export function loadConfigFromString(content: string, format: string): any;
  */
 export function normalizeMimeType(mime_type: string): string;
 
+/**
+ * Check if OCR support is available in this WASM build.
+ *
+ * Returns `true` if the `ocr-wasm` feature was enabled at build time.
+ */
+export function ocrIsAvailable(): boolean;
+
+/**
+ * Perform OCR on encoded image bytes (PNG, JPEG, BMP, GIF, TIFF).
+ *
+ * Automatically decodes the image to RGB pixels before running Tesseract.
+ * This is the primary function for OCR in WASM - it handles image decoding
+ * internally so the caller doesn't need browser APIs like `createImageBitmap`.
+ *
+ * # Arguments
+ *
+ * * `image_bytes` - Encoded image data (PNG, JPEG, BMP, GIF, TIFF)
+ * * `tessdata` - Raw `.traineddata` file content loaded into memory
+ * * `language` - Tesseract language code (e.g., "eng")
+ *
+ * # Returns
+ *
+ * The recognized text as a string.
+ */
+export function ocrRecognize(image_bytes: Uint8Array, tessdata: Uint8Array, language: string): string;
+
+/**
+ * Perform OCR on raw image pixel data using Tesseract.
+ *
+ * This function accepts pre-decoded image pixels (RGB format) along with
+ * tessdata loaded into memory. No filesystem access is needed.
+ *
+ * # Arguments
+ *
+ * * `image_data` - Raw pixel data in RGB format (3 bytes per pixel)
+ * * `width` - Image width in pixels
+ * * `height` - Image height in pixels
+ * * `bytes_per_pixel` - Bytes per pixel (typically 3 for RGB, 1 for grayscale)
+ * * `bytes_per_line` - Bytes per scan line (typically width * bytes_per_pixel)
+ * * `tessdata` - Raw `.traineddata` file content loaded into memory
+ * * `language` - Tesseract language code (e.g., "eng")
+ *
+ * # Returns
+ *
+ * The recognized text as a string.
+ */
+export function ocrRecognizeRaw(image_data: Uint8Array, width: number, height: number, bytes_per_pixel: number, bytes_per_line: number, tessdata: Uint8Array, language: string): string;
+
+/**
+ * Get the Tesseract version string compiled into this WASM binary.
+ *
+ * Returns the version of the statically linked Tesseract library.
+ */
+export function ocrTesseractVersion(): string;
+
 /**
  * A callback function that can be invoked by Pdfium's `FPDF_LoadCustomDocument()` function,
  * wrapping around `crate::utils::files::read_block_from_callback()` to shuffle data buffers
@@ -773,81 +853,3 @@ export function version(): string;
  * from Pdfium's WASM memory heap to our WASM memory heap as they are written.
  */
 export function write_block_from_callback_wasm(param: number, buf: number, size: number): number;
-
-export type InitInput = RequestInfo | URL | Response | BufferSource | WebAssembly.Module;
-
-export interface InitOutput {
-    readonly memory: WebAssembly.Memory;
-    readonly __wbg_moduleinfo_free: (a: number, b: number) => void;
-    readonly batchExtractBytes: (a: number, b: number, c: number, d: number, e: number) => any;
-    readonly batchExtractBytesSync: (a: number, b: number, c: number, d: number, e: number) => [number, number, number];
-    readonly batchExtractFiles: (a: number, b: number, c: number) => any;
-    readonly batchExtractFilesSync: () => [number, number, number];
-    readonly clear_ocr_backends: () => [number, number];
-    readonly clear_post_processors: () => [number, number];
-    readonly clear_validators: () => [number, number];
-    readonly detectMimeFromBytes: (a: any) => [number, number, number, number];
-    readonly discoverConfig: () => [number, number, number];
-    readonly extractBytes: (a: any, b: number, c: number, d: number) => any;
-    readonly extractBytesSync: (a: any, b: number, c: number, d: number) => [number, number, number];
-    readonly extractFile: (a: any, b: number, c: number, d: number) => any;
-    readonly extractFileSync: () => [number, number, number];
-    readonly getExtensionsForMime: (a: number, b: number) => [number, number, number];
-    readonly getMimeFromExtension: (a: number, b: number) => [number, number];
-    readonly get_module_info: () => number;
-    readonly initThreadPool: (a: number) => any;
-    readonly init_thread_pool_safe: (a: number) => number;
-    readonly list_ocr_backends: () => [number, number, number];
-    readonly list_post_processors: () => [number, number, number];
-    readonly list_validators: () => [number, number, number];
-    readonly loadConfigFromString: (a: number, b: number, c: number, d: number) => [number, number, number];
-    readonly moduleinfo_name: (a: number) => [number, number];
-    readonly moduleinfo_version: (a: number) => [number, number];
-    readonly normalizeMimeType: (a: number, b: number) => [number, number];
-    readonly register_ocr_backend: (a: any) => [number, number];
-    readonly register_post_processor: (a: any) => [number, number];
-    readonly register_validator: (a: any) => [number, number];
-    readonly unregister_ocr_backend: (a: number, b: number) => [number, number];
-    readonly unregister_post_processor: (a: number, b: number) => [number, number];
-    readonly unregister_validator: (a: number, b: number) => [number, number];
-    readonly version: () => [number, number];
-    readonly init: () => void;
-    readonly initialize_pdfium_render: (a: any, b: any, c: number) => number;
-    readonly read_block_from_callback_wasm: (a: number, b: number, c: number, d: number) => number;
-    readonly write_block_from_callback_wasm: (a: number, b: number, c: number) => number;
-    readonly wasm_bindgen_62eaabd966a5dd3b___closure__destroy___dyn_core_dde6c4b55a98adc4___ops__function__FnMut__wasm_bindgen_62eaabd966a5dd3b___JsValue____Output_______: (a: number, b: number) => void;
-    readonly wasm_bindgen_62eaabd966a5dd3b___closure__destroy___dyn_core_dde6c4b55a98adc4___ops__function__FnMut__wasm_bindgen_62eaabd966a5dd3b___JsValue____Output___core_dde6c4b55a98adc4___result__Result_____wasm_bindgen_62eaabd966a5dd3b___JsError___: (a: number, b: number) => void;
-    readonly wasm_bindgen_62eaabd966a5dd3b___convert__closures_____invoke___wasm_bindgen_62eaabd966a5dd3b___JsValue__core_dde6c4b55a98adc4___result__Result_____wasm_bindgen_62eaabd966a5dd3b___JsError__: (a: number, b: number, c: any) => [number, number];
-    readonly wasm_bindgen_62eaabd966a5dd3b___convert__closures_____invoke___js_sys_3747b0537fa588d4___Function_fn_wasm_bindgen_62eaabd966a5dd3b___JsValue_____wasm_bindgen_62eaabd966a5dd3b___sys__Undefined___js_sys_3747b0537fa588d4___Function_fn_wasm_bindgen_62eaabd966a5dd3b___JsValue_____wasm_bindgen_62eaabd966a5dd3b___sys__Undefined______: (a: number, b: number, c: any, d: any) => void;
-    readonly wasm_bindgen_62eaabd966a5dd3b___convert__closures_____invoke___wasm_bindgen_62eaabd966a5dd3b___JsValue_____: (a: number, b: number, c: any) => void;
-    readonly __wbindgen_externrefs: WebAssembly.Table;
-    readonly __wbindgen_malloc: (a: number, b: number) => number;
-    readonly __wbindgen_realloc: (a: number, b: number, c: number, d: number) => number;
-    readonly __wbindgen_exn_store: (a: number) => void;
-    readonly __externref_table_alloc: () => number;
-    readonly __wbindgen_free: (a: number, b: number, c: number) => void;
-    readonly __externref_table_dealloc: (a: number) => void;
-    readonly __wbindgen_start: () => void;
-}
-
-export type SyncInitInput = BufferSource | WebAssembly.Module;
-
-/**
- * Instantiates the given `module`, which can either be bytes or
- * a precompiled `WebAssembly.Module`.
- *
- * @param {{ module: SyncInitInput }} module - Passing `SyncInitInput` directly is deprecated.
- *
- * @returns {InitOutput}
- */
-export function initSync(module: { module: SyncInitInput } | SyncInitInput): InitOutput;
-
-/**
- * If `module_or_path` is {RequestInfo} or {URL}, makes a request and
- * for everything else, calls `WebAssembly.instantiate` directly.
- *
- * @param {{ module_or_path: InitInput | Promise<InitInput> }} module_or_path - Passing `InitInput` directly is deprecated.
- *
- * @returns {Promise<InitOutput>}
- */
-export default function __wbg_init (module_or_path?: { module_or_path: InitInput | Promise<InitInput> } | InitInput | Promise<InitInput>): Promise<InitOutput>;