@kreuzberg/node 4.2.15 → 4.3.0

package/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=v4.2.15" alt="Go">
+    <img src="https://img.shields.io/github/v/tag/kreuzberg-dev/kreuzberg?label=Go&color=007ec6&filter=v4.3.0" 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#">
@@ -55,7 +55,7 @@
 </div>
 
 
-Extract text, tables, images, and metadata from 62+ file formats including PDF, Office documents, and images. Native NAPI-RS bindings for Node.js with superior performance, async/await support, and TypeScript type definitions.
+Extract text, tables, images, and metadata from 75+ file formats including PDF, Office documents, and images. Native NAPI-RS bindings for Node.js with superior performance, async/await support, and TypeScript type definitions.
 
 
 ## Installation
@@ -95,15 +95,13 @@ yarn add @kreuzberg/node
 ### System Requirements
 
 - **Node.js 22+** required (NAPI-RS native bindings)
-- Optional: [ONNX Runtime](https://github.com/microsoft/onnxruntime/releases) version 1.22.x for embeddings support
+- Optional: [ONNX Runtime](https://github.com/microsoft/onnxruntime/releases) version 1.24+ for embeddings support
 - Optional: [Tesseract OCR](https://github.com/tesseract-ocr/tesseract) for OCR functionality
 
-- Optional: [LibreOffice](https://www.libreoffice.org/download/download/) for legacy Office formats (DOC, XLS, PPT, RTF, ODT, ODS, ODP)
-
 **Format Support Notes:**
-- Modern Office formats (DOCX, XLSX, PPTX) work without LibreOffice
-- Legacy formats (DOC, XLS, PPT) require LibreOffice installation
-- WASM binding supports DOCX, XLSX, PPTX, and ODT (no LibreOffice required)
+- Legacy formats (DOC, XLS, PPT) are now extracted natively without external tools
+- Modern Office formats (DOCX, XLSX, PPTX) are fully supported
+- WASM binding supports all document formats via in-memory parsing
 
 
 
@@ -322,9 +320,9 @@ This binding uses NAPI-RS to provide native Node.js bindings with:
 
 ## Features
 
-### Supported File Formats (62+)
+### Supported File Formats (75+)
 
-62+ file formats across 8 major categories with intelligent format detection and comprehensive metadata extraction.
+75+ file formats across 8 major categories with intelligent format detection and comprehensive metadata extraction.
 
 #### Office Documents
 
@@ -409,7 +407,7 @@ Kreuzberg supports multiple OCR backends for extracting text from scanned docume
 
 - **Tesseract**
 
-- **Guten**
+- **Paddleocr**
 
 
 ### OCR Configuration Example

package/dist/errors.d.mts

@@ -332,7 +332,6 @@ declare class PluginError extends KreuzbergError {
  * Error thrown when a required system dependency is missing.
  *
  * Missing dependency errors occur when external tools or libraries are not available, such as:
- * - LibreOffice (for DOC/PPT/XLS files)
  * - Tesseract OCR (for OCR processing)
  * - ImageMagick (for image processing)
  * - Poppler (for PDF rendering)
@@ -342,11 +341,11 @@ declare class PluginError extends KreuzbergError {
  * import { extractFile, MissingDependencyError } from '@kreuzberg/node';
  *
  * try {
- *   const result = await extractFile('document.doc');
+ *   const result = await extractFile('document.pdf');
  * } catch (error) {
  *   if (error instanceof MissingDependencyError) {
  *     console.error('Missing dependency:', error.message);
- *     console.log('Please install LibreOffice to process DOC files');
+ *     console.log('Please install Tesseract OCR for image processing');
  *   }
  * }
  * ```

package/dist/errors.d.ts

@@ -332,7 +332,6 @@ declare class PluginError extends KreuzbergError {
  * Error thrown when a required system dependency is missing.
  *
  * Missing dependency errors occur when external tools or libraries are not available, such as:
- * - LibreOffice (for DOC/PPT/XLS files)
  * - Tesseract OCR (for OCR processing)
  * - ImageMagick (for image processing)
  * - Poppler (for PDF rendering)
@@ -342,11 +341,11 @@ declare class PluginError extends KreuzbergError {
  * import { extractFile, MissingDependencyError } from '@kreuzberg/node';
  *
  * try {
- *   const result = await extractFile('document.doc');
+ *   const result = await extractFile('document.pdf');
  * } catch (error) {
  *   if (error instanceof MissingDependencyError) {
  *     console.error('Missing dependency:', error.message);
- *     console.log('Please install LibreOffice to process DOC files');
+ *     console.log('Please install Tesseract OCR for image processing');
  *   }
  * }
  * ```

package/dist/errors.js.map

@@ -1 +1 @@
-{"version":3,"sources":["../typescript/errors.ts"],"sourcesContent":["/**\n * Error types for Kreuzberg document intelligence framework.\n *\n * These error classes mirror the Rust core error types and provide\n * type-safe error handling for TypeScript consumers.\n *\n * ## Error Hierarchy\n *\n * ```\n * Error (JavaScript built-in)\n *   └── KreuzbergError (base class)\n *       ├── ValidationError\n *       ├── ParsingError\n *       ├── OcrError\n *       ├── CacheError\n *       ├── ImageProcessingError\n *       ├── PluginError\n *       ├── MissingDependencyError\n *       └── ... (other error types)\n * ```\n *\n * @module errors\n */\n\n/**\n * FFI error codes matching kreuzberg-ffi C library error types.\n *\n * @example\n * ```typescript\n * import { ErrorCode, getLastErrorCode } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   const code = getLastErrorCode();\n *   if (code === ErrorCode.Panic) {\n *     console.error('A panic occurred in the native library');\n *   }\n * }\n * ```\n */\nexport enum ErrorCode {\n\t/**\n\t * No error (success)\n\t */\n\tSuccess = 0,\n\t/**\n\t * Generic error\n\t */\n\tGenericError = 1,\n\t/**\n\t * Panic occurred in native code\n\t */\n\tPanic = 2,\n\t/**\n\t * Invalid argument provided\n\t */\n\tInvalidArgument = 3,\n\t/**\n\t * I/O error (file system, network, etc.)\n\t */\n\tIoError = 4,\n\t/**\n\t * Error parsing document content\n\t */\n\tParsingError = 5,\n\t/**\n\t * Error in OCR processing\n\t */\n\tOcrError = 6,\n\t/**\n\t * Required system dependency is missing\n\t */\n\tMissingDependency = 7,\n}\n\n/**\n * Context information for panics in native code.\n *\n * Contains file location, line number, function name, panic message,\n * and timestamp for debugging native library issues.\n *\n * @example\n * ```typescript\n * import { KreuzbergError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof KreuzbergError && error.panicContext) {\n *     console.error('Panic occurred:');\n *     console.error(`File: ${error.panicContext.file}`);\n *     console.error(`Line: ${error.panicContext.line}`);\n *     console.error(`Function: ${error.panicContext.function}`);\n *     console.error(`Message: ${error.panicContext.message}`);\n *   }\n * }\n * ```\n */\nexport interface PanicContext {\n\t/**\n\t * Source file where panic occurred\n\t */\n\tfile: string;\n\t/**\n\t * Line number in source file\n\t */\n\tline: number;\n\t/**\n\t * Function name where panic occurred\n\t */\n\tfunction: string;\n\t/**\n\t * Panic message\n\t */\n\tmessage: string;\n\t/**\n\t * Unix timestamp (seconds since epoch)\n\t */\n\ttimestamp_secs: number;\n}\n\n/**\n * Base error class for all Kreuzberg errors.\n *\n * All error types thrown by Kreuzberg extend this class, allowing\n * consumers to catch all Kreuzberg-specific errors with a single catch block.\n *\n * @example\n * ```typescript\n * import { extractFile, KreuzbergError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof KreuzbergError) {\n *     console.error('Kreuzberg error:', error.message);\n *     if (error.panicContext) {\n *       console.error('Panic at:', error.panicContext.file + ':' + error.panicContext.line);\n *     }\n *   } else {\n *     throw error; // Re-throw non-Kreuzberg errors\n *   }\n * }\n * ```\n */\nexport class KreuzbergError extends Error {\n\t/**\n\t * Panic context if error was caused by a panic in native code.\n\t * Will be null for non-panic errors.\n\t */\n\tpublic readonly panicContext: PanicContext | null;\n\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message);\n\t\tthis.name = \"KreuzbergError\";\n\t\tthis.panicContext = panicContext ?? null;\n\t\tObject.setPrototypeOf(this, KreuzbergError.prototype);\n\t}\n\n\ttoJSON() {\n\t\treturn {\n\t\t\tname: this.name,\n\t\t\tmessage: this.message,\n\t\t\tpanicContext: this.panicContext,\n\t\t\tstack: this.stack,\n\t\t};\n\t}\n}\n\n/**\n * Error thrown when document validation fails.\n *\n * Validation errors occur when a document doesn't meet specified criteria,\n * such as minimum content length, required metadata fields, or quality thresholds.\n *\n * @example\n * ```typescript\n * import { extractFile, ValidationError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof ValidationError) {\n *     console.error('Document validation failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class ValidationError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ValidationError\";\n\t\tObject.setPrototypeOf(this, ValidationError.prototype);\n\t}\n}\n\n/**\n * Error thrown when document parsing fails.\n *\n * Parsing errors occur when a document is corrupted, malformed, or cannot\n * be processed by the extraction engine. This includes issues like:\n * - Corrupted PDF files\n * - Invalid XML/JSON syntax\n * - Unsupported file format versions\n * - Encrypted documents without valid passwords\n *\n * @example\n * ```typescript\n * import { extractFile, ParsingError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('corrupted.pdf');\n * } catch (error) {\n *   if (error instanceof ParsingError) {\n *     console.error('Failed to parse document:', error.message);\n *   }\n * }\n * ```\n */\nexport class ParsingError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ParsingError\";\n\t\tObject.setPrototypeOf(this, ParsingError.prototype);\n\t}\n}\n\n/**\n * Error thrown when OCR processing fails.\n *\n * OCR errors occur during optical character recognition, such as:\n * - OCR backend initialization failures\n * - Image preprocessing errors\n * - Language model loading issues\n * - OCR engine crashes\n *\n * @example\n * ```typescript\n * import { extractFile, OcrError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('scanned.pdf', null, {\n *     ocr: { backend: 'tesseract', language: 'eng' }\n *   });\n * } catch (error) {\n *   if (error instanceof OcrError) {\n *     console.error('OCR processing failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class OcrError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"OcrError\";\n\t\tObject.setPrototypeOf(this, OcrError.prototype);\n\t}\n}\n\n/**\n * Error thrown when cache operations fail.\n *\n * Cache errors are typically non-fatal and occur during caching operations, such as:\n * - Cache directory creation failures\n * - Disk write errors\n * - Cache entry corruption\n * - Insufficient disk space\n *\n * These errors are usually logged but don't prevent extraction from completing.\n *\n * @example\n * ```typescript\n * import { extractFile, CacheError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf', null, {\n *     useCache: true\n *   });\n * } catch (error) {\n *   if (error instanceof CacheError) {\n *     console.warn('Cache operation failed, continuing without cache:', error.message);\n *   }\n * }\n * ```\n */\nexport class CacheError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"CacheError\";\n\t\tObject.setPrototypeOf(this, CacheError.prototype);\n\t}\n}\n\n/**\n * Error thrown when image processing operations fail.\n *\n * Image processing errors occur during image manipulation, such as:\n * - Image decoding failures\n * - Unsupported image formats\n * - Image resizing/scaling errors\n * - DPI adjustment failures\n * - Color space conversion issues\n *\n * @example\n * ```typescript\n * import { extractFile, ImageProcessingError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf', null, {\n *     images: {\n *       extractImages: true,\n *       targetDpi: 300\n *     }\n *   });\n * } catch (error) {\n *   if (error instanceof ImageProcessingError) {\n *     console.error('Image processing failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class ImageProcessingError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ImageProcessingError\";\n\t\tObject.setPrototypeOf(this, ImageProcessingError.prototype);\n\t}\n}\n\n/**\n * Error thrown when a plugin operation fails.\n *\n * Plugin errors occur in custom plugins (postprocessors, validators, OCR backends), such as:\n * - Plugin initialization failures\n * - Plugin processing errors\n * - Plugin crashes or timeouts\n * - Invalid plugin configuration\n *\n * The error message includes the plugin name to help identify which plugin failed.\n *\n * @example\n * ```typescript\n * import { extractFile, PluginError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof PluginError) {\n *     console.error(`Plugin '${error.pluginName}' failed:`, error.message);\n *   }\n * }\n * ```\n */\nexport class PluginError extends KreuzbergError {\n\t/**\n\t * Name of the plugin that threw the error.\n\t */\n\tpublic readonly pluginName: string;\n\n\tconstructor(message: string, pluginName: string, panicContext?: PanicContext | null) {\n\t\tsuper(`Plugin error in '${pluginName}': ${message}`, panicContext);\n\t\tthis.name = \"PluginError\";\n\t\tthis.pluginName = pluginName;\n\t\tObject.setPrototypeOf(this, PluginError.prototype);\n\t}\n\n\toverride toJSON() {\n\t\treturn {\n\t\t\tname: this.name,\n\t\t\tmessage: this.message,\n\t\t\tpluginName: this.pluginName,\n\t\t\tpanicContext: this.panicContext,\n\t\t\tstack: this.stack,\n\t\t};\n\t}\n}\n\n/**\n * Error thrown when a required system dependency is missing.\n *\n * Missing dependency errors occur when external tools or libraries are not available, such as:\n * - LibreOffice (for DOC/PPT/XLS files)\n * - Tesseract OCR (for OCR processing)\n * - ImageMagick (for image processing)\n * - Poppler (for PDF rendering)\n *\n * @example\n * ```typescript\n * import { extractFile, MissingDependencyError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.doc');\n * } catch (error) {\n *   if (error instanceof MissingDependencyError) {\n *     console.error('Missing dependency:', error.message);\n *     console.log('Please install LibreOffice to process DOC files');\n *   }\n * }\n * ```\n */\nexport class MissingDependencyError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"MissingDependencyError\";\n\t\tObject.setPrototypeOf(this, MissingDependencyError.prototype);\n\t}\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAyCO,IAAK,YAAL,kBAAKA,eAAL;AAIN,EAAAA,sBAAA,aAAU,KAAV;AAIA,EAAAA,sBAAA,kBAAe,KAAf;AAIA,EAAAA,sBAAA,WAAQ,KAAR;AAIA,EAAAA,sBAAA,qBAAkB,KAAlB;AAIA,EAAAA,sBAAA,aAAU,KAAV;AAIA,EAAAA,sBAAA,kBAAe,KAAf;AAIA,EAAAA,sBAAA,cAAW,KAAX;AAIA,EAAAA,sBAAA,uBAAoB,KAApB;AAhCW,SAAAA;AAAA,GAAA;AAyGL,IAAM,iBAAN,MAAM,wBAAuB,MAAM;AAAA;AAAA;AAAA;AAAA;AAAA,EAKzB;AAAA,EAEhB,YAAY,SAAiB,cAAoC;AAChE,UAAM,OAAO;AACb,SAAK,OAAO;AACZ,SAAK,eAAe,gBAAgB;AACpC,WAAO,eAAe,MAAM,gBAAe,SAAS;AAAA,EACrD;AAAA,EAEA,SAAS;AACR,WAAO;AAAA,MACN,MAAM,KAAK;AAAA,MACX,SAAS,KAAK;AAAA,MACd,cAAc,KAAK;AAAA,MACnB,OAAO,KAAK;AAAA,IACb;AAAA,EACD;AACD;AAqBO,IAAM,kBAAN,MAAM,yBAAwB,eAAe;AAAA,EACnD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,iBAAgB,SAAS;AAAA,EACtD;AACD;AAyBO,IAAM,eAAN,MAAM,sBAAqB,eAAe;AAAA,EAChD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,cAAa,SAAS;AAAA,EACnD;AACD;AA0BO,IAAM,WAAN,MAAM,kBAAiB,eAAe;AAAA,EAC5C,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,UAAS,SAAS;AAAA,EAC/C;AACD;AA4BO,IAAM,aAAN,MAAM,oBAAmB,eAAe;AAAA,EAC9C,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,YAAW,SAAS;AAAA,EACjD;AACD;AA8BO,IAAM,uBAAN,MAAM,8BAA6B,eAAe;AAAA,EACxD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,sBAAqB,SAAS;AAAA,EAC3D;AACD;AA0BO,IAAM,cAAN,MAAM,qBAAoB,eAAe;AAAA;AAAA;AAAA;AAAA,EAI/B;AAAA,EAEhB,YAAY,SAAiB,YAAoB,cAAoC;AACpF,UAAM,oBAAoB,UAAU,MAAM,OAAO,IAAI,YAAY;AACjE,SAAK,OAAO;AACZ,SAAK,aAAa;AAClB,WAAO,eAAe,MAAM,aAAY,SAAS;AAAA,EAClD;AAAA,EAES,SAAS;AACjB,WAAO;AAAA,MACN,MAAM,KAAK;AAAA,MACX,SAAS,KAAK;AAAA,MACd,YAAY,KAAK;AAAA,MACjB,cAAc,KAAK;AAAA,MACnB,OAAO,KAAK;AAAA,IACb;AAAA,EACD;AACD;AAyBO,IAAM,yBAAN,MAAM,gCAA+B,eAAe;AAAA,EAC1D,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,wBAAuB,SAAS;AAAA,EAC7D;AACD;","names":["ErrorCode"]}
+{"version":3,"sources":["../typescript/errors.ts"],"sourcesContent":["/**\n * Error types for Kreuzberg document intelligence framework.\n *\n * These error classes mirror the Rust core error types and provide\n * type-safe error handling for TypeScript consumers.\n *\n * ## Error Hierarchy\n *\n * ```\n * Error (JavaScript built-in)\n *   └── KreuzbergError (base class)\n *       ├── ValidationError\n *       ├── ParsingError\n *       ├── OcrError\n *       ├── CacheError\n *       ├── ImageProcessingError\n *       ├── PluginError\n *       ├── MissingDependencyError\n *       └── ... (other error types)\n * ```\n *\n * @module errors\n */\n\n/**\n * FFI error codes matching kreuzberg-ffi C library error types.\n *\n * @example\n * ```typescript\n * import { ErrorCode, getLastErrorCode } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   const code = getLastErrorCode();\n *   if (code === ErrorCode.Panic) {\n *     console.error('A panic occurred in the native library');\n *   }\n * }\n * ```\n */\nexport enum ErrorCode {\n\t/**\n\t * No error (success)\n\t */\n\tSuccess = 0,\n\t/**\n\t * Generic error\n\t */\n\tGenericError = 1,\n\t/**\n\t * Panic occurred in native code\n\t */\n\tPanic = 2,\n\t/**\n\t * Invalid argument provided\n\t */\n\tInvalidArgument = 3,\n\t/**\n\t * I/O error (file system, network, etc.)\n\t */\n\tIoError = 4,\n\t/**\n\t * Error parsing document content\n\t */\n\tParsingError = 5,\n\t/**\n\t * Error in OCR processing\n\t */\n\tOcrError = 6,\n\t/**\n\t * Required system dependency is missing\n\t */\n\tMissingDependency = 7,\n}\n\n/**\n * Context information for panics in native code.\n *\n * Contains file location, line number, function name, panic message,\n * and timestamp for debugging native library issues.\n *\n * @example\n * ```typescript\n * import { KreuzbergError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof KreuzbergError && error.panicContext) {\n *     console.error('Panic occurred:');\n *     console.error(`File: ${error.panicContext.file}`);\n *     console.error(`Line: ${error.panicContext.line}`);\n *     console.error(`Function: ${error.panicContext.function}`);\n *     console.error(`Message: ${error.panicContext.message}`);\n *   }\n * }\n * ```\n */\nexport interface PanicContext {\n\t/**\n\t * Source file where panic occurred\n\t */\n\tfile: string;\n\t/**\n\t * Line number in source file\n\t */\n\tline: number;\n\t/**\n\t * Function name where panic occurred\n\t */\n\tfunction: string;\n\t/**\n\t * Panic message\n\t */\n\tmessage: string;\n\t/**\n\t * Unix timestamp (seconds since epoch)\n\t */\n\ttimestamp_secs: number;\n}\n\n/**\n * Base error class for all Kreuzberg errors.\n *\n * All error types thrown by Kreuzberg extend this class, allowing\n * consumers to catch all Kreuzberg-specific errors with a single catch block.\n *\n * @example\n * ```typescript\n * import { extractFile, KreuzbergError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof KreuzbergError) {\n *     console.error('Kreuzberg error:', error.message);\n *     if (error.panicContext) {\n *       console.error('Panic at:', error.panicContext.file + ':' + error.panicContext.line);\n *     }\n *   } else {\n *     throw error; // Re-throw non-Kreuzberg errors\n *   }\n * }\n * ```\n */\nexport class KreuzbergError extends Error {\n\t/**\n\t * Panic context if error was caused by a panic in native code.\n\t * Will be null for non-panic errors.\n\t */\n\tpublic readonly panicContext: PanicContext | null;\n\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message);\n\t\tthis.name = \"KreuzbergError\";\n\t\tthis.panicContext = panicContext ?? null;\n\t\tObject.setPrototypeOf(this, KreuzbergError.prototype);\n\t}\n\n\ttoJSON() {\n\t\treturn {\n\t\t\tname: this.name,\n\t\t\tmessage: this.message,\n\t\t\tpanicContext: this.panicContext,\n\t\t\tstack: this.stack,\n\t\t};\n\t}\n}\n\n/**\n * Error thrown when document validation fails.\n *\n * Validation errors occur when a document doesn't meet specified criteria,\n * such as minimum content length, required metadata fields, or quality thresholds.\n *\n * @example\n * ```typescript\n * import { extractFile, ValidationError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof ValidationError) {\n *     console.error('Document validation failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class ValidationError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ValidationError\";\n\t\tObject.setPrototypeOf(this, ValidationError.prototype);\n\t}\n}\n\n/**\n * Error thrown when document parsing fails.\n *\n * Parsing errors occur when a document is corrupted, malformed, or cannot\n * be processed by the extraction engine. This includes issues like:\n * - Corrupted PDF files\n * - Invalid XML/JSON syntax\n * - Unsupported file format versions\n * - Encrypted documents without valid passwords\n *\n * @example\n * ```typescript\n * import { extractFile, ParsingError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('corrupted.pdf');\n * } catch (error) {\n *   if (error instanceof ParsingError) {\n *     console.error('Failed to parse document:', error.message);\n *   }\n * }\n * ```\n */\nexport class ParsingError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ParsingError\";\n\t\tObject.setPrototypeOf(this, ParsingError.prototype);\n\t}\n}\n\n/**\n * Error thrown when OCR processing fails.\n *\n * OCR errors occur during optical character recognition, such as:\n * - OCR backend initialization failures\n * - Image preprocessing errors\n * - Language model loading issues\n * - OCR engine crashes\n *\n * @example\n * ```typescript\n * import { extractFile, OcrError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('scanned.pdf', null, {\n *     ocr: { backend: 'tesseract', language: 'eng' }\n *   });\n * } catch (error) {\n *   if (error instanceof OcrError) {\n *     console.error('OCR processing failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class OcrError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"OcrError\";\n\t\tObject.setPrototypeOf(this, OcrError.prototype);\n\t}\n}\n\n/**\n * Error thrown when cache operations fail.\n *\n * Cache errors are typically non-fatal and occur during caching operations, such as:\n * - Cache directory creation failures\n * - Disk write errors\n * - Cache entry corruption\n * - Insufficient disk space\n *\n * These errors are usually logged but don't prevent extraction from completing.\n *\n * @example\n * ```typescript\n * import { extractFile, CacheError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf', null, {\n *     useCache: true\n *   });\n * } catch (error) {\n *   if (error instanceof CacheError) {\n *     console.warn('Cache operation failed, continuing without cache:', error.message);\n *   }\n * }\n * ```\n */\nexport class CacheError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"CacheError\";\n\t\tObject.setPrototypeOf(this, CacheError.prototype);\n\t}\n}\n\n/**\n * Error thrown when image processing operations fail.\n *\n * Image processing errors occur during image manipulation, such as:\n * - Image decoding failures\n * - Unsupported image formats\n * - Image resizing/scaling errors\n * - DPI adjustment failures\n * - Color space conversion issues\n *\n * @example\n * ```typescript\n * import { extractFile, ImageProcessingError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf', null, {\n *     images: {\n *       extractImages: true,\n *       targetDpi: 300\n *     }\n *   });\n * } catch (error) {\n *   if (error instanceof ImageProcessingError) {\n *     console.error('Image processing failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class ImageProcessingError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ImageProcessingError\";\n\t\tObject.setPrototypeOf(this, ImageProcessingError.prototype);\n\t}\n}\n\n/**\n * Error thrown when a plugin operation fails.\n *\n * Plugin errors occur in custom plugins (postprocessors, validators, OCR backends), such as:\n * - Plugin initialization failures\n * - Plugin processing errors\n * - Plugin crashes or timeouts\n * - Invalid plugin configuration\n *\n * The error message includes the plugin name to help identify which plugin failed.\n *\n * @example\n * ```typescript\n * import { extractFile, PluginError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof PluginError) {\n *     console.error(`Plugin '${error.pluginName}' failed:`, error.message);\n *   }\n * }\n * ```\n */\nexport class PluginError extends KreuzbergError {\n\t/**\n\t * Name of the plugin that threw the error.\n\t */\n\tpublic readonly pluginName: string;\n\n\tconstructor(message: string, pluginName: string, panicContext?: PanicContext | null) {\n\t\tsuper(`Plugin error in '${pluginName}': ${message}`, panicContext);\n\t\tthis.name = \"PluginError\";\n\t\tthis.pluginName = pluginName;\n\t\tObject.setPrototypeOf(this, PluginError.prototype);\n\t}\n\n\toverride toJSON() {\n\t\treturn {\n\t\t\tname: this.name,\n\t\t\tmessage: this.message,\n\t\t\tpluginName: this.pluginName,\n\t\t\tpanicContext: this.panicContext,\n\t\t\tstack: this.stack,\n\t\t};\n\t}\n}\n\n/**\n * Error thrown when a required system dependency is missing.\n *\n * Missing dependency errors occur when external tools or libraries are not available, such as:\n * - Tesseract OCR (for OCR processing)\n * - ImageMagick (for image processing)\n * - Poppler (for PDF rendering)\n *\n * @example\n * ```typescript\n * import { extractFile, MissingDependencyError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof MissingDependencyError) {\n *     console.error('Missing dependency:', error.message);\n *     console.log('Please install Tesseract OCR for image processing');\n *   }\n * }\n * ```\n */\nexport class MissingDependencyError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"MissingDependencyError\";\n\t\tObject.setPrototypeOf(this, MissingDependencyError.prototype);\n\t}\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAyCO,IAAK,YAAL,kBAAKA,eAAL;AAIN,EAAAA,sBAAA,aAAU,KAAV;AAIA,EAAAA,sBAAA,kBAAe,KAAf;AAIA,EAAAA,sBAAA,WAAQ,KAAR;AAIA,EAAAA,sBAAA,qBAAkB,KAAlB;AAIA,EAAAA,sBAAA,aAAU,KAAV;AAIA,EAAAA,sBAAA,kBAAe,KAAf;AAIA,EAAAA,sBAAA,cAAW,KAAX;AAIA,EAAAA,sBAAA,uBAAoB,KAApB;AAhCW,SAAAA;AAAA,GAAA;AAyGL,IAAM,iBAAN,MAAM,wBAAuB,MAAM;AAAA;AAAA;AAAA;AAAA;AAAA,EAKzB;AAAA,EAEhB,YAAY,SAAiB,cAAoC;AAChE,UAAM,OAAO;AACb,SAAK,OAAO;AACZ,SAAK,eAAe,gBAAgB;AACpC,WAAO,eAAe,MAAM,gBAAe,SAAS;AAAA,EACrD;AAAA,EAEA,SAAS;AACR,WAAO;AAAA,MACN,MAAM,KAAK;AAAA,MACX,SAAS,KAAK;AAAA,MACd,cAAc,KAAK;AAAA,MACnB,OAAO,KAAK;AAAA,IACb;AAAA,EACD;AACD;AAqBO,IAAM,kBAAN,MAAM,yBAAwB,eAAe;AAAA,EACnD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,iBAAgB,SAAS;AAAA,EACtD;AACD;AAyBO,IAAM,eAAN,MAAM,sBAAqB,eAAe;AAAA,EAChD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,cAAa,SAAS;AAAA,EACnD;AACD;AA0BO,IAAM,WAAN,MAAM,kBAAiB,eAAe;AAAA,EAC5C,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,UAAS,SAAS;AAAA,EAC/C;AACD;AA4BO,IAAM,aAAN,MAAM,oBAAmB,eAAe;AAAA,EAC9C,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,YAAW,SAAS;AAAA,EACjD;AACD;AA8BO,IAAM,uBAAN,MAAM,8BAA6B,eAAe;AAAA,EACxD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,sBAAqB,SAAS;AAAA,EAC3D;AACD;AA0BO,IAAM,cAAN,MAAM,qBAAoB,eAAe;AAAA;AAAA;AAAA;AAAA,EAI/B;AAAA,EAEhB,YAAY,SAAiB,YAAoB,cAAoC;AACpF,UAAM,oBAAoB,UAAU,MAAM,OAAO,IAAI,YAAY;AACjE,SAAK,OAAO;AACZ,SAAK,aAAa;AAClB,WAAO,eAAe,MAAM,aAAY,SAAS;AAAA,EAClD;AAAA,EAES,SAAS;AACjB,WAAO;AAAA,MACN,MAAM,KAAK;AAAA,MACX,SAAS,KAAK;AAAA,MACd,YAAY,KAAK;AAAA,MACjB,cAAc,KAAK;AAAA,MACnB,OAAO,KAAK;AAAA,IACb;AAAA,EACD;AACD;AAwBO,IAAM,yBAAN,MAAM,gCAA+B,eAAe;AAAA,EAC1D,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,wBAAuB,SAAS;AAAA,EAC7D;AACD;","names":["ErrorCode"]}

package/dist/errors.mjs.map

@@ -1 +1 @@
-{"version":3,"sources":["../typescript/errors.ts"],"sourcesContent":["/**\n * Error types for Kreuzberg document intelligence framework.\n *\n * These error classes mirror the Rust core error types and provide\n * type-safe error handling for TypeScript consumers.\n *\n * ## Error Hierarchy\n *\n * ```\n * Error (JavaScript built-in)\n *   └── KreuzbergError (base class)\n *       ├── ValidationError\n *       ├── ParsingError\n *       ├── OcrError\n *       ├── CacheError\n *       ├── ImageProcessingError\n *       ├── PluginError\n *       ├── MissingDependencyError\n *       └── ... (other error types)\n * ```\n *\n * @module errors\n */\n\n/**\n * FFI error codes matching kreuzberg-ffi C library error types.\n *\n * @example\n * ```typescript\n * import { ErrorCode, getLastErrorCode } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   const code = getLastErrorCode();\n *   if (code === ErrorCode.Panic) {\n *     console.error('A panic occurred in the native library');\n *   }\n * }\n * ```\n */\nexport enum ErrorCode {\n\t/**\n\t * No error (success)\n\t */\n\tSuccess = 0,\n\t/**\n\t * Generic error\n\t */\n\tGenericError = 1,\n\t/**\n\t * Panic occurred in native code\n\t */\n\tPanic = 2,\n\t/**\n\t * Invalid argument provided\n\t */\n\tInvalidArgument = 3,\n\t/**\n\t * I/O error (file system, network, etc.)\n\t */\n\tIoError = 4,\n\t/**\n\t * Error parsing document content\n\t */\n\tParsingError = 5,\n\t/**\n\t * Error in OCR processing\n\t */\n\tOcrError = 6,\n\t/**\n\t * Required system dependency is missing\n\t */\n\tMissingDependency = 7,\n}\n\n/**\n * Context information for panics in native code.\n *\n * Contains file location, line number, function name, panic message,\n * and timestamp for debugging native library issues.\n *\n * @example\n * ```typescript\n * import { KreuzbergError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof KreuzbergError && error.panicContext) {\n *     console.error('Panic occurred:');\n *     console.error(`File: ${error.panicContext.file}`);\n *     console.error(`Line: ${error.panicContext.line}`);\n *     console.error(`Function: ${error.panicContext.function}`);\n *     console.error(`Message: ${error.panicContext.message}`);\n *   }\n * }\n * ```\n */\nexport interface PanicContext {\n\t/**\n\t * Source file where panic occurred\n\t */\n\tfile: string;\n\t/**\n\t * Line number in source file\n\t */\n\tline: number;\n\t/**\n\t * Function name where panic occurred\n\t */\n\tfunction: string;\n\t/**\n\t * Panic message\n\t */\n\tmessage: string;\n\t/**\n\t * Unix timestamp (seconds since epoch)\n\t */\n\ttimestamp_secs: number;\n}\n\n/**\n * Base error class for all Kreuzberg errors.\n *\n * All error types thrown by Kreuzberg extend this class, allowing\n * consumers to catch all Kreuzberg-specific errors with a single catch block.\n *\n * @example\n * ```typescript\n * import { extractFile, KreuzbergError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof KreuzbergError) {\n *     console.error('Kreuzberg error:', error.message);\n *     if (error.panicContext) {\n *       console.error('Panic at:', error.panicContext.file + ':' + error.panicContext.line);\n *     }\n *   } else {\n *     throw error; // Re-throw non-Kreuzberg errors\n *   }\n * }\n * ```\n */\nexport class KreuzbergError extends Error {\n\t/**\n\t * Panic context if error was caused by a panic in native code.\n\t * Will be null for non-panic errors.\n\t */\n\tpublic readonly panicContext: PanicContext | null;\n\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message);\n\t\tthis.name = \"KreuzbergError\";\n\t\tthis.panicContext = panicContext ?? null;\n\t\tObject.setPrototypeOf(this, KreuzbergError.prototype);\n\t}\n\n\ttoJSON() {\n\t\treturn {\n\t\t\tname: this.name,\n\t\t\tmessage: this.message,\n\t\t\tpanicContext: this.panicContext,\n\t\t\tstack: this.stack,\n\t\t};\n\t}\n}\n\n/**\n * Error thrown when document validation fails.\n *\n * Validation errors occur when a document doesn't meet specified criteria,\n * such as minimum content length, required metadata fields, or quality thresholds.\n *\n * @example\n * ```typescript\n * import { extractFile, ValidationError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof ValidationError) {\n *     console.error('Document validation failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class ValidationError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ValidationError\";\n\t\tObject.setPrototypeOf(this, ValidationError.prototype);\n\t}\n}\n\n/**\n * Error thrown when document parsing fails.\n *\n * Parsing errors occur when a document is corrupted, malformed, or cannot\n * be processed by the extraction engine. This includes issues like:\n * - Corrupted PDF files\n * - Invalid XML/JSON syntax\n * - Unsupported file format versions\n * - Encrypted documents without valid passwords\n *\n * @example\n * ```typescript\n * import { extractFile, ParsingError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('corrupted.pdf');\n * } catch (error) {\n *   if (error instanceof ParsingError) {\n *     console.error('Failed to parse document:', error.message);\n *   }\n * }\n * ```\n */\nexport class ParsingError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ParsingError\";\n\t\tObject.setPrototypeOf(this, ParsingError.prototype);\n\t}\n}\n\n/**\n * Error thrown when OCR processing fails.\n *\n * OCR errors occur during optical character recognition, such as:\n * - OCR backend initialization failures\n * - Image preprocessing errors\n * - Language model loading issues\n * - OCR engine crashes\n *\n * @example\n * ```typescript\n * import { extractFile, OcrError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('scanned.pdf', null, {\n *     ocr: { backend: 'tesseract', language: 'eng' }\n *   });\n * } catch (error) {\n *   if (error instanceof OcrError) {\n *     console.error('OCR processing failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class OcrError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"OcrError\";\n\t\tObject.setPrototypeOf(this, OcrError.prototype);\n\t}\n}\n\n/**\n * Error thrown when cache operations fail.\n *\n * Cache errors are typically non-fatal and occur during caching operations, such as:\n * - Cache directory creation failures\n * - Disk write errors\n * - Cache entry corruption\n * - Insufficient disk space\n *\n * These errors are usually logged but don't prevent extraction from completing.\n *\n * @example\n * ```typescript\n * import { extractFile, CacheError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf', null, {\n *     useCache: true\n *   });\n * } catch (error) {\n *   if (error instanceof CacheError) {\n *     console.warn('Cache operation failed, continuing without cache:', error.message);\n *   }\n * }\n * ```\n */\nexport class CacheError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"CacheError\";\n\t\tObject.setPrototypeOf(this, CacheError.prototype);\n\t}\n}\n\n/**\n * Error thrown when image processing operations fail.\n *\n * Image processing errors occur during image manipulation, such as:\n * - Image decoding failures\n * - Unsupported image formats\n * - Image resizing/scaling errors\n * - DPI adjustment failures\n * - Color space conversion issues\n *\n * @example\n * ```typescript\n * import { extractFile, ImageProcessingError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf', null, {\n *     images: {\n *       extractImages: true,\n *       targetDpi: 300\n *     }\n *   });\n * } catch (error) {\n *   if (error instanceof ImageProcessingError) {\n *     console.error('Image processing failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class ImageProcessingError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ImageProcessingError\";\n\t\tObject.setPrototypeOf(this, ImageProcessingError.prototype);\n\t}\n}\n\n/**\n * Error thrown when a plugin operation fails.\n *\n * Plugin errors occur in custom plugins (postprocessors, validators, OCR backends), such as:\n * - Plugin initialization failures\n * - Plugin processing errors\n * - Plugin crashes or timeouts\n * - Invalid plugin configuration\n *\n * The error message includes the plugin name to help identify which plugin failed.\n *\n * @example\n * ```typescript\n * import { extractFile, PluginError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof PluginError) {\n *     console.error(`Plugin '${error.pluginName}' failed:`, error.message);\n *   }\n * }\n * ```\n */\nexport class PluginError extends KreuzbergError {\n\t/**\n\t * Name of the plugin that threw the error.\n\t */\n\tpublic readonly pluginName: string;\n\n\tconstructor(message: string, pluginName: string, panicContext?: PanicContext | null) {\n\t\tsuper(`Plugin error in '${pluginName}': ${message}`, panicContext);\n\t\tthis.name = \"PluginError\";\n\t\tthis.pluginName = pluginName;\n\t\tObject.setPrototypeOf(this, PluginError.prototype);\n\t}\n\n\toverride toJSON() {\n\t\treturn {\n\t\t\tname: this.name,\n\t\t\tmessage: this.message,\n\t\t\tpluginName: this.pluginName,\n\t\t\tpanicContext: this.panicContext,\n\t\t\tstack: this.stack,\n\t\t};\n\t}\n}\n\n/**\n * Error thrown when a required system dependency is missing.\n *\n * Missing dependency errors occur when external tools or libraries are not available, such as:\n * - LibreOffice (for DOC/PPT/XLS files)\n * - Tesseract OCR (for OCR processing)\n * - ImageMagick (for image processing)\n * - Poppler (for PDF rendering)\n *\n * @example\n * ```typescript\n * import { extractFile, MissingDependencyError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.doc');\n * } catch (error) {\n *   if (error instanceof MissingDependencyError) {\n *     console.error('Missing dependency:', error.message);\n *     console.log('Please install LibreOffice to process DOC files');\n *   }\n * }\n * ```\n */\nexport class MissingDependencyError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"MissingDependencyError\";\n\t\tObject.setPrototypeOf(this, MissingDependencyError.prototype);\n\t}\n}\n"],"mappings":";AAyCO,IAAK,YAAL,kBAAKA,eAAL;AAIN,EAAAA,sBAAA,aAAU,KAAV;AAIA,EAAAA,sBAAA,kBAAe,KAAf;AAIA,EAAAA,sBAAA,WAAQ,KAAR;AAIA,EAAAA,sBAAA,qBAAkB,KAAlB;AAIA,EAAAA,sBAAA,aAAU,KAAV;AAIA,EAAAA,sBAAA,kBAAe,KAAf;AAIA,EAAAA,sBAAA,cAAW,KAAX;AAIA,EAAAA,sBAAA,uBAAoB,KAApB;AAhCW,SAAAA;AAAA,GAAA;AAyGL,IAAM,iBAAN,MAAM,wBAAuB,MAAM;AAAA;AAAA;AAAA;AAAA;AAAA,EAKzB;AAAA,EAEhB,YAAY,SAAiB,cAAoC;AAChE,UAAM,OAAO;AACb,SAAK,OAAO;AACZ,SAAK,eAAe,gBAAgB;AACpC,WAAO,eAAe,MAAM,gBAAe,SAAS;AAAA,EACrD;AAAA,EAEA,SAAS;AACR,WAAO;AAAA,MACN,MAAM,KAAK;AAAA,MACX,SAAS,KAAK;AAAA,MACd,cAAc,KAAK;AAAA,MACnB,OAAO,KAAK;AAAA,IACb;AAAA,EACD;AACD;AAqBO,IAAM,kBAAN,MAAM,yBAAwB,eAAe;AAAA,EACnD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,iBAAgB,SAAS;AAAA,EACtD;AACD;AAyBO,IAAM,eAAN,MAAM,sBAAqB,eAAe;AAAA,EAChD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,cAAa,SAAS;AAAA,EACnD;AACD;AA0BO,IAAM,WAAN,MAAM,kBAAiB,eAAe;AAAA,EAC5C,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,UAAS,SAAS;AAAA,EAC/C;AACD;AA4BO,IAAM,aAAN,MAAM,oBAAmB,eAAe;AAAA,EAC9C,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,YAAW,SAAS;AAAA,EACjD;AACD;AA8BO,IAAM,uBAAN,MAAM,8BAA6B,eAAe;AAAA,EACxD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,sBAAqB,SAAS;AAAA,EAC3D;AACD;AA0BO,IAAM,cAAN,MAAM,qBAAoB,eAAe;AAAA;AAAA;AAAA;AAAA,EAI/B;AAAA,EAEhB,YAAY,SAAiB,YAAoB,cAAoC;AACpF,UAAM,oBAAoB,UAAU,MAAM,OAAO,IAAI,YAAY;AACjE,SAAK,OAAO;AACZ,SAAK,aAAa;AAClB,WAAO,eAAe,MAAM,aAAY,SAAS;AAAA,EAClD;AAAA,EAES,SAAS;AACjB,WAAO;AAAA,MACN,MAAM,KAAK;AAAA,MACX,SAAS,KAAK;AAAA,MACd,YAAY,KAAK;AAAA,MACjB,cAAc,KAAK;AAAA,MACnB,OAAO,KAAK;AAAA,IACb;AAAA,EACD;AACD;AAyBO,IAAM,yBAAN,MAAM,gCAA+B,eAAe;AAAA,EAC1D,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,wBAAuB,SAAS;AAAA,EAC7D;AACD;","names":["ErrorCode"]}
+{"version":3,"sources":["../typescript/errors.ts"],"sourcesContent":["/**\n * Error types for Kreuzberg document intelligence framework.\n *\n * These error classes mirror the Rust core error types and provide\n * type-safe error handling for TypeScript consumers.\n *\n * ## Error Hierarchy\n *\n * ```\n * Error (JavaScript built-in)\n *   └── KreuzbergError (base class)\n *       ├── ValidationError\n *       ├── ParsingError\n *       ├── OcrError\n *       ├── CacheError\n *       ├── ImageProcessingError\n *       ├── PluginError\n *       ├── MissingDependencyError\n *       └── ... (other error types)\n * ```\n *\n * @module errors\n */\n\n/**\n * FFI error codes matching kreuzberg-ffi C library error types.\n *\n * @example\n * ```typescript\n * import { ErrorCode, getLastErrorCode } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   const code = getLastErrorCode();\n *   if (code === ErrorCode.Panic) {\n *     console.error('A panic occurred in the native library');\n *   }\n * }\n * ```\n */\nexport enum ErrorCode {\n\t/**\n\t * No error (success)\n\t */\n\tSuccess = 0,\n\t/**\n\t * Generic error\n\t */\n\tGenericError = 1,\n\t/**\n\t * Panic occurred in native code\n\t */\n\tPanic = 2,\n\t/**\n\t * Invalid argument provided\n\t */\n\tInvalidArgument = 3,\n\t/**\n\t * I/O error (file system, network, etc.)\n\t */\n\tIoError = 4,\n\t/**\n\t * Error parsing document content\n\t */\n\tParsingError = 5,\n\t/**\n\t * Error in OCR processing\n\t */\n\tOcrError = 6,\n\t/**\n\t * Required system dependency is missing\n\t */\n\tMissingDependency = 7,\n}\n\n/**\n * Context information for panics in native code.\n *\n * Contains file location, line number, function name, panic message,\n * and timestamp for debugging native library issues.\n *\n * @example\n * ```typescript\n * import { KreuzbergError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof KreuzbergError && error.panicContext) {\n *     console.error('Panic occurred:');\n *     console.error(`File: ${error.panicContext.file}`);\n *     console.error(`Line: ${error.panicContext.line}`);\n *     console.error(`Function: ${error.panicContext.function}`);\n *     console.error(`Message: ${error.panicContext.message}`);\n *   }\n * }\n * ```\n */\nexport interface PanicContext {\n\t/**\n\t * Source file where panic occurred\n\t */\n\tfile: string;\n\t/**\n\t * Line number in source file\n\t */\n\tline: number;\n\t/**\n\t * Function name where panic occurred\n\t */\n\tfunction: string;\n\t/**\n\t * Panic message\n\t */\n\tmessage: string;\n\t/**\n\t * Unix timestamp (seconds since epoch)\n\t */\n\ttimestamp_secs: number;\n}\n\n/**\n * Base error class for all Kreuzberg errors.\n *\n * All error types thrown by Kreuzberg extend this class, allowing\n * consumers to catch all Kreuzberg-specific errors with a single catch block.\n *\n * @example\n * ```typescript\n * import { extractFile, KreuzbergError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof KreuzbergError) {\n *     console.error('Kreuzberg error:', error.message);\n *     if (error.panicContext) {\n *       console.error('Panic at:', error.panicContext.file + ':' + error.panicContext.line);\n *     }\n *   } else {\n *     throw error; // Re-throw non-Kreuzberg errors\n *   }\n * }\n * ```\n */\nexport class KreuzbergError extends Error {\n\t/**\n\t * Panic context if error was caused by a panic in native code.\n\t * Will be null for non-panic errors.\n\t */\n\tpublic readonly panicContext: PanicContext | null;\n\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message);\n\t\tthis.name = \"KreuzbergError\";\n\t\tthis.panicContext = panicContext ?? null;\n\t\tObject.setPrototypeOf(this, KreuzbergError.prototype);\n\t}\n\n\ttoJSON() {\n\t\treturn {\n\t\t\tname: this.name,\n\t\t\tmessage: this.message,\n\t\t\tpanicContext: this.panicContext,\n\t\t\tstack: this.stack,\n\t\t};\n\t}\n}\n\n/**\n * Error thrown when document validation fails.\n *\n * Validation errors occur when a document doesn't meet specified criteria,\n * such as minimum content length, required metadata fields, or quality thresholds.\n *\n * @example\n * ```typescript\n * import { extractFile, ValidationError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof ValidationError) {\n *     console.error('Document validation failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class ValidationError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ValidationError\";\n\t\tObject.setPrototypeOf(this, ValidationError.prototype);\n\t}\n}\n\n/**\n * Error thrown when document parsing fails.\n *\n * Parsing errors occur when a document is corrupted, malformed, or cannot\n * be processed by the extraction engine. This includes issues like:\n * - Corrupted PDF files\n * - Invalid XML/JSON syntax\n * - Unsupported file format versions\n * - Encrypted documents without valid passwords\n *\n * @example\n * ```typescript\n * import { extractFile, ParsingError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('corrupted.pdf');\n * } catch (error) {\n *   if (error instanceof ParsingError) {\n *     console.error('Failed to parse document:', error.message);\n *   }\n * }\n * ```\n */\nexport class ParsingError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ParsingError\";\n\t\tObject.setPrototypeOf(this, ParsingError.prototype);\n\t}\n}\n\n/**\n * Error thrown when OCR processing fails.\n *\n * OCR errors occur during optical character recognition, such as:\n * - OCR backend initialization failures\n * - Image preprocessing errors\n * - Language model loading issues\n * - OCR engine crashes\n *\n * @example\n * ```typescript\n * import { extractFile, OcrError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('scanned.pdf', null, {\n *     ocr: { backend: 'tesseract', language: 'eng' }\n *   });\n * } catch (error) {\n *   if (error instanceof OcrError) {\n *     console.error('OCR processing failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class OcrError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"OcrError\";\n\t\tObject.setPrototypeOf(this, OcrError.prototype);\n\t}\n}\n\n/**\n * Error thrown when cache operations fail.\n *\n * Cache errors are typically non-fatal and occur during caching operations, such as:\n * - Cache directory creation failures\n * - Disk write errors\n * - Cache entry corruption\n * - Insufficient disk space\n *\n * These errors are usually logged but don't prevent extraction from completing.\n *\n * @example\n * ```typescript\n * import { extractFile, CacheError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf', null, {\n *     useCache: true\n *   });\n * } catch (error) {\n *   if (error instanceof CacheError) {\n *     console.warn('Cache operation failed, continuing without cache:', error.message);\n *   }\n * }\n * ```\n */\nexport class CacheError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"CacheError\";\n\t\tObject.setPrototypeOf(this, CacheError.prototype);\n\t}\n}\n\n/**\n * Error thrown when image processing operations fail.\n *\n * Image processing errors occur during image manipulation, such as:\n * - Image decoding failures\n * - Unsupported image formats\n * - Image resizing/scaling errors\n * - DPI adjustment failures\n * - Color space conversion issues\n *\n * @example\n * ```typescript\n * import { extractFile, ImageProcessingError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf', null, {\n *     images: {\n *       extractImages: true,\n *       targetDpi: 300\n *     }\n *   });\n * } catch (error) {\n *   if (error instanceof ImageProcessingError) {\n *     console.error('Image processing failed:', error.message);\n *   }\n * }\n * ```\n */\nexport class ImageProcessingError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"ImageProcessingError\";\n\t\tObject.setPrototypeOf(this, ImageProcessingError.prototype);\n\t}\n}\n\n/**\n * Error thrown when a plugin operation fails.\n *\n * Plugin errors occur in custom plugins (postprocessors, validators, OCR backends), such as:\n * - Plugin initialization failures\n * - Plugin processing errors\n * - Plugin crashes or timeouts\n * - Invalid plugin configuration\n *\n * The error message includes the plugin name to help identify which plugin failed.\n *\n * @example\n * ```typescript\n * import { extractFile, PluginError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof PluginError) {\n *     console.error(`Plugin '${error.pluginName}' failed:`, error.message);\n *   }\n * }\n * ```\n */\nexport class PluginError extends KreuzbergError {\n\t/**\n\t * Name of the plugin that threw the error.\n\t */\n\tpublic readonly pluginName: string;\n\n\tconstructor(message: string, pluginName: string, panicContext?: PanicContext | null) {\n\t\tsuper(`Plugin error in '${pluginName}': ${message}`, panicContext);\n\t\tthis.name = \"PluginError\";\n\t\tthis.pluginName = pluginName;\n\t\tObject.setPrototypeOf(this, PluginError.prototype);\n\t}\n\n\toverride toJSON() {\n\t\treturn {\n\t\t\tname: this.name,\n\t\t\tmessage: this.message,\n\t\t\tpluginName: this.pluginName,\n\t\t\tpanicContext: this.panicContext,\n\t\t\tstack: this.stack,\n\t\t};\n\t}\n}\n\n/**\n * Error thrown when a required system dependency is missing.\n *\n * Missing dependency errors occur when external tools or libraries are not available, such as:\n * - Tesseract OCR (for OCR processing)\n * - ImageMagick (for image processing)\n * - Poppler (for PDF rendering)\n *\n * @example\n * ```typescript\n * import { extractFile, MissingDependencyError } from '@kreuzberg/node';\n *\n * try {\n *   const result = await extractFile('document.pdf');\n * } catch (error) {\n *   if (error instanceof MissingDependencyError) {\n *     console.error('Missing dependency:', error.message);\n *     console.log('Please install Tesseract OCR for image processing');\n *   }\n * }\n * ```\n */\nexport class MissingDependencyError extends KreuzbergError {\n\tconstructor(message: string, panicContext?: PanicContext | null) {\n\t\tsuper(message, panicContext);\n\t\tthis.name = \"MissingDependencyError\";\n\t\tObject.setPrototypeOf(this, MissingDependencyError.prototype);\n\t}\n}\n"],"mappings":";AAyCO,IAAK,YAAL,kBAAKA,eAAL;AAIN,EAAAA,sBAAA,aAAU,KAAV;AAIA,EAAAA,sBAAA,kBAAe,KAAf;AAIA,EAAAA,sBAAA,WAAQ,KAAR;AAIA,EAAAA,sBAAA,qBAAkB,KAAlB;AAIA,EAAAA,sBAAA,aAAU,KAAV;AAIA,EAAAA,sBAAA,kBAAe,KAAf;AAIA,EAAAA,sBAAA,cAAW,KAAX;AAIA,EAAAA,sBAAA,uBAAoB,KAApB;AAhCW,SAAAA;AAAA,GAAA;AAyGL,IAAM,iBAAN,MAAM,wBAAuB,MAAM;AAAA;AAAA;AAAA;AAAA;AAAA,EAKzB;AAAA,EAEhB,YAAY,SAAiB,cAAoC;AAChE,UAAM,OAAO;AACb,SAAK,OAAO;AACZ,SAAK,eAAe,gBAAgB;AACpC,WAAO,eAAe,MAAM,gBAAe,SAAS;AAAA,EACrD;AAAA,EAEA,SAAS;AACR,WAAO;AAAA,MACN,MAAM,KAAK;AAAA,MACX,SAAS,KAAK;AAAA,MACd,cAAc,KAAK;AAAA,MACnB,OAAO,KAAK;AAAA,IACb;AAAA,EACD;AACD;AAqBO,IAAM,kBAAN,MAAM,yBAAwB,eAAe;AAAA,EACnD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,iBAAgB,SAAS;AAAA,EACtD;AACD;AAyBO,IAAM,eAAN,MAAM,sBAAqB,eAAe;AAAA,EAChD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,cAAa,SAAS;AAAA,EACnD;AACD;AA0BO,IAAM,WAAN,MAAM,kBAAiB,eAAe;AAAA,EAC5C,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,UAAS,SAAS;AAAA,EAC/C;AACD;AA4BO,IAAM,aAAN,MAAM,oBAAmB,eAAe;AAAA,EAC9C,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,YAAW,SAAS;AAAA,EACjD;AACD;AA8BO,IAAM,uBAAN,MAAM,8BAA6B,eAAe;AAAA,EACxD,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,sBAAqB,SAAS;AAAA,EAC3D;AACD;AA0BO,IAAM,cAAN,MAAM,qBAAoB,eAAe;AAAA;AAAA;AAAA;AAAA,EAI/B;AAAA,EAEhB,YAAY,SAAiB,YAAoB,cAAoC;AACpF,UAAM,oBAAoB,UAAU,MAAM,OAAO,IAAI,YAAY;AACjE,SAAK,OAAO;AACZ,SAAK,aAAa;AAClB,WAAO,eAAe,MAAM,aAAY,SAAS;AAAA,EAClD;AAAA,EAES,SAAS;AACjB,WAAO;AAAA,MACN,MAAM,KAAK;AAAA,MACX,SAAS,KAAK;AAAA,MACd,YAAY,KAAK;AAAA,MACjB,cAAc,KAAK;AAAA,MACnB,OAAO,KAAK;AAAA,IACb;AAAA,EACD;AACD;AAwBO,IAAM,yBAAN,MAAM,gCAA+B,eAAe;AAAA,EAC1D,YAAY,SAAiB,cAAoC;AAChE,UAAM,SAAS,YAAY;AAC3B,SAAK,OAAO;AACZ,WAAO,eAAe,MAAM,wBAAuB,SAAS;AAAA,EAC7D;AACD;","names":["ErrorCode"]}

package/dist/index.d.mts

@@ -2,7 +2,6 @@ import { ErrorClassification, ExtractionConfig, ExtractionResult, WorkerPool, Wo
 export { Chunk, ChunkingConfig, ExtractedImage, HtmlConversionOptions, HtmlPreprocessingOptions, ImageExtractionConfig, KeywordConfig, LanguageDetectionConfig, OcrConfig, PageContent, PageExtractionConfig, PdfConfig, PostProcessorConfig, Table, TesseractConfig, TokenReductionConfig } from './types.mjs';
 import { PanicContext } from './errors.mjs';
 export { CacheError, ErrorCode, ImageProcessingError, KreuzbergError, MissingDependencyError, OcrError, ParsingError, PluginError, ValidationError } from './errors.mjs';
-export { GutenOcrBackend } from './ocr/guten-ocr.mjs';
 
 /**
  * Get the error code for the last FFI error.
@@ -797,19 +796,11 @@ declare function listValidators(): string[];
  *
  * @example
  * ```typescript
- * import { GutenOcrBackend } from '@kreuzberg/node/ocr/guten-ocr';
- * import { registerOcrBackend, extractFile } from '@kreuzberg/node';
- *
- * // Create and initialize backend
- * const backend = new GutenOcrBackend();
- * await backend.initialize();
- *
- * // Register with Kreuzberg
- * registerOcrBackend(backend);
+ * import { extractFile } from '@kreuzberg/node';
  *
- * // Use in extraction
+ * // PaddleOCR is built into the native Rust core - just use the backend name
  * const result = await extractFile('scanned.pdf', null, {
- *   ocr: { backend: 'guten-ocr', language: 'en' }
+ *   ocr: { backend: 'paddle-ocr', language: 'en' }
  * });
  * console.log(result.content);
  * ```
@@ -1176,7 +1167,7 @@ declare function __resetBindingForTests(): void;
  *
  * ## Supported Formats
  *
- * - **Documents**: PDF, DOCX, PPTX, XLSX, DOC, PPT (with LibreOffice)
+ * - **Documents**: PDF, DOCX, PPTX, XLSX, DOC, PPT
  * - **Text**: Markdown, Plain Text, XML
  * - **Web**: HTML (converted to Markdown)
  * - **Data**: JSON, YAML, TOML
@@ -1200,6 +1191,6 @@ declare function __resetBindingForTests(): void;
  * @module @kreuzberg/node
  */
 
-declare const __version__ = "4.2.15";
+declare const __version__ = "4.3.0";
 
 export { type EmbeddingPreset, ErrorClassification, ExtractionConfig, ExtractionResult, OcrBackendProtocol, PanicContext, PostProcessorProtocol, ValidatorProtocol, WorkerPool, WorkerPoolStats, __resetBindingForTests, __setBindingForTests, __version__, batchExtractBytes, batchExtractBytesSync, batchExtractFiles, batchExtractFilesInWorker, batchExtractFilesSync, classifyError, clearDocumentExtractors, clearOcrBackends, clearPostProcessors, clearValidators, closeWorkerPool, createWorkerPool, detectMimeType, detectMimeTypeFromPath, extractBytes, extractBytesSync, extractFile, extractFileInWorker, extractFileSync, getEmbeddingPreset, getErrorCodeDescription, getErrorCodeName, getExtensionsForMime, getLastErrorCode, getLastPanicContext, getWorkerPoolStats, listDocumentExtractors, listEmbeddingPresets, listOcrBackends, listPostProcessors, listValidators, loadConfigFile, loadConfigFromPath, registerOcrBackend, registerPostProcessor, registerValidator, unregisterDocumentExtractor, unregisterOcrBackend, unregisterPostProcessor, unregisterValidator, validateMimeType };

package/dist/index.d.ts

@@ -2,7 +2,6 @@ import { ErrorClassification, ExtractionConfig, ExtractionResult, WorkerPool, Wo
 export { Chunk, ChunkingConfig, ExtractedImage, HtmlConversionOptions, HtmlPreprocessingOptions, ImageExtractionConfig, KeywordConfig, LanguageDetectionConfig, OcrConfig, PageContent, PageExtractionConfig, PdfConfig, PostProcessorConfig, Table, TesseractConfig, TokenReductionConfig } from './types.js';
 import { PanicContext } from './errors.js';
 export { CacheError, ErrorCode, ImageProcessingError, KreuzbergError, MissingDependencyError, OcrError, ParsingError, PluginError, ValidationError } from './errors.js';
-export { GutenOcrBackend } from './ocr/guten-ocr.js';
 
 /**
  * Get the error code for the last FFI error.
@@ -797,19 +796,11 @@ declare function listValidators(): string[];
  *
  * @example
  * ```typescript
- * import { GutenOcrBackend } from '@kreuzberg/node/ocr/guten-ocr';
- * import { registerOcrBackend, extractFile } from '@kreuzberg/node';
- *
- * // Create and initialize backend
- * const backend = new GutenOcrBackend();
- * await backend.initialize();
- *
- * // Register with Kreuzberg
- * registerOcrBackend(backend);
+ * import { extractFile } from '@kreuzberg/node';
  *
- * // Use in extraction
+ * // PaddleOCR is built into the native Rust core - just use the backend name
  * const result = await extractFile('scanned.pdf', null, {
- *   ocr: { backend: 'guten-ocr', language: 'en' }
+ *   ocr: { backend: 'paddle-ocr', language: 'en' }
  * });
  * console.log(result.content);
  * ```
@@ -1176,7 +1167,7 @@ declare function __resetBindingForTests(): void;
  *
  * ## Supported Formats
  *
- * - **Documents**: PDF, DOCX, PPTX, XLSX, DOC, PPT (with LibreOffice)
+ * - **Documents**: PDF, DOCX, PPTX, XLSX, DOC, PPT
  * - **Text**: Markdown, Plain Text, XML
  * - **Web**: HTML (converted to Markdown)
  * - **Data**: JSON, YAML, TOML
@@ -1200,6 +1191,6 @@ declare function __resetBindingForTests(): void;
  * @module @kreuzberg/node
  */
 
-declare const __version__ = "4.2.15";
+declare const __version__ = "4.3.0";
 
 export { type EmbeddingPreset, ErrorClassification, ExtractionConfig, ExtractionResult, OcrBackendProtocol, PanicContext, PostProcessorProtocol, ValidatorProtocol, WorkerPool, WorkerPoolStats, __resetBindingForTests, __setBindingForTests, __version__, batchExtractBytes, batchExtractBytesSync, batchExtractFiles, batchExtractFilesInWorker, batchExtractFilesSync, classifyError, clearDocumentExtractors, clearOcrBackends, clearPostProcessors, clearValidators, closeWorkerPool, createWorkerPool, detectMimeType, detectMimeTypeFromPath, extractBytes, extractBytesSync, extractFile, extractFileInWorker, extractFileSync, getEmbeddingPreset, getErrorCodeDescription, getErrorCodeName, getExtensionsForMime, getLastErrorCode, getLastPanicContext, getWorkerPoolStats, listDocumentExtractors, listEmbeddingPresets, listOcrBackends, listPostProcessors, listValidators, loadConfigFile, loadConfigFromPath, registerOcrBackend, registerPostProcessor, registerValidator, unregisterDocumentExtractor, unregisterOcrBackend, unregisterPostProcessor, unregisterValidator, validateMimeType };