@xberg-io/xberg-wasm 1.0.12 → 1.1.1

package/README.md

@@ -1,8 +1,19 @@
+<!-- This file is auto-generated by alef — DO NOT EDIT. -->
+<!-- alef:hash:3ccb6772a03d9b6fcc002e6420f88eb8d105b0179169016db2e720b2f497b3f1 -->
+<!-- To regenerate: alef readme -->
+<!-- To verify freshness: alef verify -->
+
 # WebAssembly
 
 <div align="center" style="display: flex; flex-wrap: wrap; gap: 8px; justify-content: center; margin: 20px 0;">
+  <a href="https://github.com/xberg-io/xberg/actions/workflows/ci-rust.yaml">
+    <img src="https://github.com/xberg-io/xberg/actions/workflows/ci-rust.yaml/badge.svg?branch=main" alt="Rust CI">
+  </a>
+  <a href="https://codecov.io/gh/xberg-io/xberg">
+    <img src="https://codecov.io/gh/xberg-io/xberg/branch/main/graph/badge.svg" alt="Coverage">
+  </a>
   <a href="https://github.com/xberg-io/alef">
-    <img src="https://img.shields.io/badge/Bindings-alef%20%D7%90-007ec6" alt="Bindings">
+    <img src="https://img.shields.io/badge/built%20with-alef%20%D7%90-007ec6" alt="Built with alef">
   </a>
   <!-- Language Bindings -->
   <a href="https://crates.io/crates/xberg">
@@ -80,7 +91,7 @@
   </a>
 </div>
 
-Extract text, tables, images, metadata, and code intelligence from 101 file formats and 371 programming languages including PDF, Office documents, and images. WebAssembly bindings for browsers, Deno, and Cloudflare Workers with portable deployment and multi-threading support.
+Extract text, tables, images, and metadata from 107 file formats including PDF, Office documents, and images. WebAssembly bindings for browsers, Deno, and Cloudflare Workers with a single-threaded synchronous core and an async JavaScript surface.
 
 ## What This Package Provides
 
@@ -110,11 +121,11 @@ pnpm add @xberg-io/xberg-wasm
 
 Extract text, metadata, and structure from any supported document format:
 
-```ts
-import { ExtractInputKind, extract, initWasm } from "@xberg-io/xberg-wasm";
+```typescript title="Wasm"
+import init, { WasmExtractInputKind, extract } from "@xberg-io/xberg-wasm";
 
 async function main() {
-  await initWasm();
+  await init();
 
   const buffer = await fetch("document.pdf").then((r) => r.arrayBuffer());
   const bytes = new Uint8Array(buffer);
@@ -124,7 +135,7 @@ async function main() {
     bytes,
     mimeType: "application/pdf",
     filename: "document.pdf",
-  });
+  }, undefined);
 
   console.log("Extracted content:");
   console.log(output.results[0].content);
@@ -143,22 +154,17 @@ Most use cases benefit from configuration to control extraction behavior:
 
 **With OCR (for scanned documents):**
 
-```ts
-import { enableOcr, ExtractInputKind, extract, initWasm } from "@xberg-io/xberg-wasm";
+```typescript title="Wasm"
+import init, { WasmExtractInputKind, extract } from "@xberg-io/xberg-wasm";
 
 async function extractWithOcr() {
-  await initWasm();
-
-  try {
-    await enableOcr();
-    console.log("OCR enabled successfully");
-  } catch (error) {
-    console.error("Failed to enable OCR:", error);
-    return;
-  }
+  await init();
 
-  const bytes = new Uint8Array(await fetch("scanned-page.png").then((r) => r.arrayBuffer()));
+  const buffer = await fetch("scanned-page.png").then((response) => response.arrayBuffer());
+  const bytes = new Uint8Array(buffer);
 
+  // OCR is turned on per extraction through the `ocr` config block. There is no
+  // separate global "enable OCR" call — the backend is selected by name here.
   const output = await extract(
     {
       kind: "bytes",
@@ -168,7 +174,8 @@ async function extractWithOcr() {
     },
     {
       ocr: {
-        backend: "tesseract-wasm",
+        enabled: true,
+        backend: "tesseract",
         language: ["eng"],
       },
     },
@@ -187,8 +194,8 @@ See [Configuration Guide](https://docs.xberg.io/guides/configuration/) for table
 
 #### Processing Multiple Files
 
-```ts
-import { extractBatch, initWasm } from "@xberg-io/xberg-wasm";
+```typescript title="Wasm"
+import init, { WasmExtractInput, extractBatch } from "@xberg-io/xberg-wasm";
 
 interface DocumentJob {
   name: string;
@@ -197,19 +204,15 @@ interface DocumentJob {
 }
 
 async function _processBatch(documents: DocumentJob[], concurrency: number = 3) {
-  await initWasm();
+  await init();
 
   const results: Record<string, string> = {};
 
   for (let index = 0; index < documents.length; index += concurrency) {
     const batch = documents.slice(index, index + concurrency);
     const output = await extractBatch(
-      batch.map((doc) => ({
-        kind: "bytes",
-        bytes: doc.bytes,
-        mimeType: doc.mimeType,
-        filename: doc.name,
-      })),
+      batch.map((doc) => WasmExtractInput.fromBytes(doc.bytes, doc.mimeType, doc.name)),
+      undefined,
     );
 
     output.results.forEach((result, resultIndex) => {
@@ -224,24 +227,19 @@ async function _processBatch(documents: DocumentJob[], concurrency: number = 3)
 
 For non-blocking document processing:
 
-```ts
-import { extract, getWasmCapabilities, initWasm } from "@xberg-io/xberg-wasm";
+```typescript title="Wasm"
+import init, { extract } from "@xberg-io/xberg-wasm";
 
 async function extractDocuments(files: Uint8Array[], mimeTypes: string[]) {
-  const caps = getWasmCapabilities();
-  if (!caps.hasWasm) {
-    throw new Error("WebAssembly not supported");
-  }
-
-  await initWasm();
+  await init();
 
   const results = await Promise.all(
-    files.map((bytes, index) => extract({ kind: "bytes", bytes, mimeType: mimeTypes[index] })),
+    files.map((bytes, index) => extract({ kind: "bytes", bytes, mimeType: mimeTypes[index] }, undefined)),
   );
 
   return results.map((r) => ({
-    content: r.content,
-    pageCount: r.metadata?.pageCount,
+    content: r.results[0].content,
+    metadata: r.results[0].metadata,
   }));
 }
 
@@ -256,15 +254,15 @@ extractDocuments(fileBytes, mimes)
 ### Next Steps
 
 - **[Installation Guide](https://docs.xberg.io/getting-started/installation/)** - Platform-specific setup
-- **[API Documentation](https://docs.xberg.io/reference/api-python/)** - Complete API reference
+- **[API Documentation](https://docs.xberg.io/reference/api-wasm/)** - Complete API reference
 - **[Examples & Guides](https://docs.xberg.io/)** - Full code examples and usage guides
 - **[Configuration Guide](https://docs.xberg.io/guides/configuration/)** - Advanced configuration options
 
 ## Features
 
-### Supported File Formats (101 formats · 115 file extensions)
+### Supported File Formats (107 formats · 141 file extensions · 56 MIME aliases)
 
-101 formats across 115 file extensions in 8 major categories with intelligent format detection and comprehensive metadata extraction.
+107 formats across 140 unique file extensions, with 56 compatibility MIME aliases, intelligent format detection, and comprehensive metadata extraction.
 
 #### Office Documents
 
@@ -272,10 +270,10 @@ extractDocuments(fileBytes, mimes)
 |----------|---------|--------------|
 | **Word Processing** | `.docx`, `.docm`, `.doc`, `.dotx`, `.dotm`, `.dot`, `.odt`, `.pages`, `.wpd`, `.wp`, `.wp5`, `.wp6` | Full text, tables, images, metadata, styles |
 | **Spreadsheets** | `.xlsx`, `.xlsm`, `.xlsb`, `.xls`, `.xla`, `.xlam`, `.xltm`, `.xltx`, `.xlt`, `.ods`, `.numbers` | Sheet data, formulas, cell metadata, charts |
-| **Presentations** | `.pptx`, `.pptm`, `.ppt`, `.ppsx`, `.potx`, `.potm`, `.pot`, `.odp`, `.key` | Slides, speaker notes, images, metadata |
+| **Presentations** | `.pptx`, `.pptm`, `.ppt`, `.pps`, `.ppsx`, `.potx`, `.potm`, `.pot`, `.odp`, `.key` | Slides, speaker notes, images, metadata |
 | **PDF** | `.pdf` | Text, tables, images, metadata, OCR support |
 | **eBooks** | `.epub`, `.fb2` | Chapters, metadata, embedded resources |
-| **Database** | `.dbf` | Table data extraction, field type support |
+| **Database** | `.dbf`, `.sqlite`, `.sqlite3`, `.db`, `.gpkg`, `.gpkx` | Bounded table extraction, schema metadata, GeoPackage detection |
 | **Hangul** | `.hwp`, `.hwpx` | Korean document format, text extraction |
 
 #### Images (OCR-Enabled)
@@ -283,16 +281,16 @@ extractDocuments(fileBytes, mimes)
 | Category | Formats | Features |
 |----------|---------|----------|
 | **Raster** | `.png`, `.jpg`, `.jpeg`, `.gif`, `.webp`, `.bmp`, `.tiff`, `.tif` | OCR, table detection, EXIF metadata, dimensions, color space |
-| **Advanced** | `.jp2`, `.jpx`, `.jpm`, `.mj2`, `.jbig2`, `.jb2`, `.pnm`, `.pbm`, `.pgm`, `.ppm` | OCR via hayro-jpeg2000 (pure Rust decoder), JBIG2 support, table detection, format-specific metadata |
+| **Advanced** | `.jp2`, `.jpg2`, `.j2c`, `.j2k`, `.jpc`, `.jbig2`, `.jb2`, `.pnm`, `.pbm`, `.pgm`, `.ppm` | OCR via hayro-jpeg2000 (pure Rust decoder), JBIG2 support, table detection, format-specific metadata |
 | **Vector** | `.svg` | DOM parsing, embedded text, graphics metadata |
 
 #### Web & Data
 
 | Category | Formats | Features |
 |----------|---------|----------|
-| **Markup** | `.html`, `.htm`, `.xhtml`, `.xml`, `.svg` | DOM parsing, metadata (Open Graph, Twitter Card), link extraction |
-| **Structured Data** | `.json`, `.yaml`, `.yml`, `.toml`, `.csv`, `.tsv` | Schema detection, nested structures, validation |
-| **Text & Markdown** | `.txt`, `.md`, `.markdown`, `.djot`, `.mdx`, `.rst`, `.org`, `.rtf` | CommonMark, GFM, Djot, MDX, reStructuredText, Org Mode |
+| **Markup** | `.html`, `.htm`, `.xhtml`, `.xht`, `.xml`, `.kml`, `.svg` | DOM parsing, metadata (Open Graph, Twitter Card), link extraction |
+| **Structured Data** | `.json`, `.geojson`, `.jsonl`, `.ndjson`, `.yaml`, `.yml`, `.toml`, `.csv`, `.tsv` | Schema detection, nested structures, validation |
+| **Text & Markdown** | `.txt`, `.adoc`, `.asciidoc`, `.vtt`, `.md`, `.markdown`, `.commonmark`, `.qmd`, `.rmd`, `.djot`, `.dj`, `.mdx`, `.doctags`, `.rst`, `.org`, `.rtf` | AsciiDoc, CommonMark, MyST Markdown, Quarto, R Markdown, Djot, MDX, DocTags, reStructuredText, Org Mode |
 
 #### Email & Archives
 
@@ -306,9 +304,9 @@ extractDocuments(fileBytes, mimes)
 | Category | Formats | Features |
 |----------|---------|----------|
 | **Citations** | `.bib`, `.ris`, `.nbib`, `.enw` | Structured parsing: RIS, PubMed/MEDLINE, EndNote XML, BibTeX/BibLaTeX, CSL JSON by MIME type |
-| **Scientific** | `.tex`, `.latex`, `.typ`, `.typst`, `.jats`, `.ipynb` | LaTeX, Typst, Jupyter notebooks, PubMed JATS |
+| **Scientific** | `.tex`, `.latex`, `.typ`, `.typst`, `.jats`, `.nxml` | LaTeX, Typst, PubMed JATS |
+| **Text notebooks** | `.ipynb`, `.md`, `.py`, `.R`, `.jl` | Jupyter, MyST-NB, Jupytext percent/light, saved outputs, cell visibility tags |
 | **Publishing** | `.fb2`, `.docbook`, `.dbk`, `.docbook4`, `.docbook5`, `.opml` | FictionBook, DocBook XML, OPML outlines |
-| **Documentation** | MIME-only POD, mdoc, troff | Technical documentation formats |
 
 #### Code Intelligence (371 Languages)
 
@@ -337,9 +335,8 @@ Powered by [tree-sitter-language-pack](https://github.com/xberg-io/tree-sitter-l
 - **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
-- **Code Intelligence** - Extract structure, imports, exports, symbols, and docstrings from [371 programming languages](https://docs.tree-sitter-language-pack.xberg.io) via tree-sitter
 - **Configuration** - Fine-grained control over extraction behavior
-- **Six Output Formats** - Plain text, Markdown, Djot, HTML, JSON tree structure, or Structured JSON with OCR metadata
+- **Six Output Formats** - Plain text, Markdown, Djot, HTML, JSON tree structure, or Docling DocTags
 
 ## OCR Support
 
@@ -347,24 +344,21 @@ Xberg supports multiple OCR backends for extracting text from scanned documents
 
 - **Tesseract-Wasm**
 
+- **Sceptre (Opt-In Worker Api)**
+
 ### OCR Configuration Example
 
-```ts
-import { enableOcr, ExtractInputKind, extract, initWasm } from "@xberg-io/xberg-wasm";
+```typescript title="Wasm"
+import init, { WasmExtractInputKind, extract } from "@xberg-io/xberg-wasm";
 
 async function extractWithOcr() {
-  await initWasm();
-
-  try {
-    await enableOcr();
-    console.log("OCR enabled successfully");
-  } catch (error) {
-    console.error("Failed to enable OCR:", error);
-    return;
-  }
+  await init();
 
-  const bytes = new Uint8Array(await fetch("scanned-page.png").then((r) => r.arrayBuffer()));
+  const buffer = await fetch("scanned-page.png").then((response) => response.arrayBuffer());
+  const bytes = new Uint8Array(buffer);
 
+  // OCR is turned on per extraction through the `ocr` config block. There is no
+  // separate global "enable OCR" call — the backend is selected by name here.
   const output = await extract(
     {
       kind: "bytes",
@@ -374,7 +368,8 @@ async function extractWithOcr() {
     },
     {
       ocr: {
-        backend: "tesseract-wasm",
+        enabled: true,
+        backend: "tesseract",
         language: ["eng"],
       },
     },
@@ -391,24 +386,19 @@ extractWithOcr().catch(console.error);
 
 This binding provides full async/await support for non-blocking document processing:
 
-```ts
-import { extract, getWasmCapabilities, initWasm } from "@xberg-io/xberg-wasm";
+```typescript title="Wasm"
+import init, { extract } from "@xberg-io/xberg-wasm";
 
 async function extractDocuments(files: Uint8Array[], mimeTypes: string[]) {
-  const caps = getWasmCapabilities();
-  if (!caps.hasWasm) {
-    throw new Error("WebAssembly not supported");
-  }
-
-  await initWasm();
+  await init();
 
   const results = await Promise.all(
-    files.map((bytes, index) => extract({ kind: "bytes", bytes, mimeType: mimeTypes[index] })),
+    files.map((bytes, index) => extract({ kind: "bytes", bytes, mimeType: mimeTypes[index] }, undefined)),
   );
 
   return results.map((r) => ({
-    content: r.content,
-    pageCount: r.metadata?.pageCount,
+    content: r.results[0].content,
+    metadata: r.results[0].metadata,
   }));
 }
 
@@ -430,8 +420,8 @@ For detailed plugin documentation, visit [Plugin System Guide](https://docs.xber
 
 Process multiple documents efficiently:
 
-```ts
-import { extractBatch, initWasm } from "@xberg-io/xberg-wasm";
+```typescript title="Wasm"
+import init, { WasmExtractInput, extractBatch } from "@xberg-io/xberg-wasm";
 
 interface DocumentJob {
   name: string;
@@ -440,19 +430,15 @@ interface DocumentJob {
 }
 
 async function _processBatch(documents: DocumentJob[], concurrency: number = 3) {
-  await initWasm();
+  await init();
 
   const results: Record<string, string> = {};
 
   for (let index = 0; index < documents.length; index += concurrency) {
     const batch = documents.slice(index, index + concurrency);
     const output = await extractBatch(
-      batch.map((doc) => ({
-        kind: "bytes",
-        bytes: doc.bytes,
-        mimeType: doc.mimeType,
-        filename: doc.name,
-      })),
+      batch.map((doc) => WasmExtractInput.fromBytes(doc.bytes, doc.mimeType, doc.name)),
+      undefined,
     );
 
     output.results.forEach((result, resultIndex) => {
@@ -472,15 +458,18 @@ For advanced configuration options including language detection, table extractio
 ## Documentation
 
 - **[Official Documentation](https://docs.xberg.io/)**
-- **[API Reference](https://docs.xberg.io/reference/api-python/)**
+- **[API Reference](https://docs.xberg.io/reference/api-wasm/)**
 - **[Examples & Guides](https://docs.xberg.io/)**
 
 ## Contributing
 
 Contributions are welcome! See [Contributing Guide](https://github.com/xberg-io/xberg/blob/main/CONTRIBUTING.md).
 
-## Part of Xberg.dev
+## Part of Xberg.io
 
+- [Xberg](https://github.com/xberg-io/xberg) — the open-source content-intelligence engine: text, tables, and metadata from 107 formats (141 file extensions), with OCR, transcription, and code intelligence. MIT.
+- [Xberg Pro](https://xberg.io) — a complete self-hosted content-intelligence backend in a single container. Commercial.
+- [Xberg Enterprise](https://xberg.io) — the distributed, governed content-intelligence platform, scaled on Kubernetes with team governance and support. Commercial.
 - [crawlberg](https://github.com/xberg-io/crawlberg) — web crawling and scraping with HTML→Markdown and headless-Chrome fallback.
 - [html-to-markdown](https://github.com/xberg-io/html-to-markdown) — fast, lossless HTML→Markdown engine.
 - [liter-llm](https://github.com/xberg-io/liter-llm) — universal LLM API client with native bindings for 14 languages and 165 providers.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@xberg-io/xberg-wasm",
-  "version": "1.0.12",
+  "version": "1.1.1",
   "private": false,
   "description": "High-performance document intelligence library",
   "license": "MIT",
@@ -13,13 +13,19 @@
     "access": "public"
   },
   "type": "module",
-  "files": [
-    "pkg/web",
-    "README.md"
-  ],
+  "files": ["pkg/web", "README.md"],
   "main": "pkg/web/xberg_wasm.js",
   "module": "pkg/web/xberg_wasm.js",
   "types": "pkg/web/xberg_wasm.d.ts",
+  "exports": {
+    ".": {
+      "types": "./pkg/web/xberg_wasm.d.ts",
+      "browser": "./pkg/web/xberg_wasm.js",
+      "import": "./pkg/web/xberg_wasm.js",
+      "require": "./pkg/web/xberg_wasm.js",
+      "default": "./pkg/web/xberg_wasm.js"
+    }
+  },
   "engines": {
     "node": ">= 22"
   },
@@ -32,5 +38,9 @@
     "test:watch": "vitest watch",
     "test:coverage": "vitest run --coverage",
     "clean": "rm -rf pkg dist"
+  },
+  "devDependencies": {
+    "vitest": "^4.1.11",
+    "@vitest/coverage-v8": "^4.1.11"
   }
 }