file2md 1.0.3

package/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 file2md contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/README.md

@@ -0,0 +1,293 @@
+# file2md
+
+[![npm version](https://badge.fury.io/js/file2md.svg)](https://badge.fury.io/js/file2md)
+[![TypeScript](https://img.shields.io/badge/TypeScript-Ready-blue.svg)](https://www.typescriptlang.org/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+A modern TypeScript library for converting various document types (PDF, DOCX, XLSX, PPTX) into Markdown with **advanced layout preservation**, **image extraction**, and **chart conversion**.
+
+## ✨ Features
+
+- 🔄 **Multiple Format Support**: PDF, DOCX, XLSX, PPTX
+- 🎨 **Layout Preservation**: Maintains document structure, tables, and formatting  
+- 🖼️ **Image Extraction**: Automatically extracts and references images
+- 📊 **Chart Conversion**: Converts charts to Markdown tables
+- 📝 **List & Table Support**: Proper nested lists and complex tables
+- 🔒 **Type Safety**: Full TypeScript support with comprehensive types
+- ⚡ **Modern ESM**: ES2022 modules with CommonJS compatibility
+- 🚀 **Zero Config**: Works out of the box
+
+## 📦 Installation
+
+```bash
+npm install file2md
+```
+
+## 🚀 Quick Start
+
+### TypeScript / ES Modules
+
+```typescript
+import { convert } from 'file2md';
+
+// Convert from file path
+const result = await convert('./document.pdf');
+console.log(result.markdown);
+
+// Convert with options
+const result = await convert('./presentation.pptx', {
+  imageDir: 'extracted-images',
+  preserveLayout: true,
+  extractCharts: true
+});
+
+console.log(`✅ Converted successfully!`);
+console.log(`📄 Markdown length: ${result.markdown.length}`);
+console.log(`🖼️ Images extracted: ${result.images.length}`);
+console.log(`📊 Charts found: ${result.charts.length}`);
+```
+
+### CommonJS
+
+```javascript
+const { convert } = require('file2md');
+
+const result = await convert('./document.docx');
+console.log(result.markdown);
+```
+
+### From Buffer
+
+```typescript
+import { convert } from 'file2md';
+import { readFile } from 'fs/promises';
+
+const buffer = await readFile('./document.xlsx');
+const result = await convert(buffer, {
+  imageDir: 'spreadsheet-images'
+});
+```
+
+## 📋 API Reference
+
+### `convert(input, options?)`
+
+**Parameters:**
+- `input: string | Buffer` - File path or buffer containing document data
+- `options?: ConvertOptions` - Conversion options
+
+**Returns:** `Promise<ConversionResult>`
+
+### Options
+
+```typescript
+interface ConvertOptions {
+  imageDir?: string;        // Directory for extracted images (default: 'images')
+  preserveLayout?: boolean; // Maintain document layout (default: true)
+  extractCharts?: boolean;  // Convert charts to tables (default: true)
+  extractImages?: boolean;  // Extract embedded images (default: true)
+  maxPages?: number;        // Max pages for PDFs (default: unlimited)
+}
+```
+
+### Result
+
+```typescript
+interface ConversionResult {
+  markdown: string;           // Generated Markdown content
+  images: ImageData[];        // Extracted image information
+  charts: ChartData[];        // Extracted chart data
+  metadata: DocumentMetadata; // Document metadata
+}
+```
+
+## 🎯 Format-Specific Features
+
+### 📄 PDF
+- ✅ **Text extraction** with layout enhancement
+- ✅ **Table detection** and formatting
+- ✅ **List recognition** (bullets, numbers)
+- ✅ **Heading detection** (ALL CAPS, colons)
+- ✅ **Page-to-image fallback** for complex layouts
+
+### 📝 DOCX  
+- ✅ **Heading hierarchy** (H1-H6)
+- ✅ **Text formatting** (bold, italic)
+- ✅ **Complex tables** with merged cells
+- ✅ **Nested lists** with proper indentation
+- ✅ **Embedded images** and charts
+- ✅ **Cell styling** (alignment, colors)
+
+### 📊 XLSX
+- ✅ **Multiple worksheets** as separate sections
+- ✅ **Cell formatting** (bold, colors, alignment)
+- ✅ **Data type preservation** 
+- ✅ **Chart extraction** to data tables
+- ✅ **Conditional formatting** notes
+
+### 🎬 PPTX
+- ✅ **Slide-by-slide** organization
+- ✅ **Text positioning** and layout
+- ✅ **Image placement** per slide
+- ✅ **Table extraction** from slides
+- ✅ **Multi-column layouts**
+
+## 🖼️ Image Handling
+
+Images are automatically extracted and saved to the specified directory:
+
+```typescript
+const result = await convert('./presentation.pptx', {
+  imageDir: 'my-images'
+});
+
+// Result structure:
+// my-images/
+// ├── image_1.png
+// ├── image_2.jpg
+// └── chart_1.png
+
+// Markdown will contain:
+// ![Slide 1 Image](my-images/image_1.png)
+```
+
+## 📊 Chart Conversion
+
+Charts are converted to Markdown tables:
+
+```markdown
+#### Chart 1: Sales Data
+
+| Category | Q1 | Q2 | Q3 | Q4 |
+| --- | --- | --- | --- | --- |
+| Revenue | 100 | 150 | 200 | 250 |
+| Profit | 20 | 30 | 45 | 60 |
+```
+
+## 🛡️ Error Handling
+
+```typescript
+import { 
+  convert, 
+  UnsupportedFormatError, 
+  FileNotFoundError,
+  ParseError 
+} from 'file2md';
+
+try {
+  const result = await convert('./document.pdf');
+} catch (error) {
+  if (error instanceof UnsupportedFormatError) {
+    console.error('Unsupported file format');
+  } else if (error instanceof FileNotFoundError) {
+    console.error('File not found');
+  } else if (error instanceof ParseError) {
+    console.error('Failed to parse document:', error.message);
+  }
+}
+```
+
+## 🧪 Advanced Usage
+
+### Custom Error Handling
+
+```typescript
+import { convert, ConversionError } from 'file2md';
+
+try {
+  const result = await convert('./complex-document.docx');
+} catch (error) {
+  if (error instanceof ConversionError) {
+    console.error(`Conversion failed [${error.code}]:`, error.message);
+    if (error.originalError) {
+      console.error('Original error:', error.originalError);
+    }
+  }
+}
+```
+
+### Batch Processing
+
+```typescript
+import { convert } from 'file2md';
+import { readdir } from 'fs/promises';
+
+async function convertFolder(folderPath: string) {
+  const files = await readdir(folderPath);
+  const results = [];
+  
+  for (const file of files) {
+    if (file.match(/\.(pdf|docx|xlsx|pptx)$/i)) {
+      try {
+        const result = await convert(`${folderPath}/${file}`);
+        results.push({ file, success: true, result });
+      } catch (error) {
+        results.push({ file, success: false, error });
+      }
+    }
+  }
+  
+  return results;
+}
+```
+
+## 🏗️ Development
+
+### Build from Source
+
+```bash
+git clone https://github.com/yourusername/file2md.git
+cd file2md
+npm install
+npm run build
+```
+
+### Testing
+
+```bash
+npm test           # Run tests
+npm run test:watch # Watch mode
+npm run test:coverage # Coverage report
+```
+
+### Linting
+
+```bash
+npm run lint       # Check code style
+npm run lint:fix   # Fix issues
+```
+
+## 🤝 Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+1. Fork the repository
+2. Create your feature branch (`git checkout -b feature/amazing-feature`)
+3. Commit your changes (`git commit -m 'Add amazing feature'`)
+4. Push to the branch (`git push origin feature/amazing-feature`)
+5. Open a Pull Request
+
+## 📄 License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## 🔗 Links
+
+- [npm package](https://www.npmjs.com/package/file2md)
+- [GitHub repository](https://github.com/yourusername/file2md)
+- [Issues & Bug Reports](https://github.com/yourusername/file2md/issues)
+
+## 📊 Supported Formats
+
+| Format | Extension | Layout | Images | Charts | Tables | Lists |
+|--------|-----------|---------|---------|---------|---------|--------|
+| PDF    | `.pdf`    | ✅     | ✅*    | ❌     | ✅     | ✅    |
+| Word   | `.docx`   | ✅     | ✅     | ✅     | ✅     | ✅    |
+| Excel  | `.xlsx`   | ✅     | ❌     | ✅     | ✅     | ❌    |
+| PowerPoint | `.pptx` | ✅   | ✅     | ✅     | ✅     | ❌    |
+
+*PDF images via page-to-image conversion
+
+---
+
+**Made with ❤️ and TypeScript**

package/dist/index.d.ts

@@ -0,0 +1,33 @@
+import type { ConvertInput, ConvertOptions, ConversionResult } from './types/index.js';
+/**
+ * Convert a document (PDF, DOCX, XLSX, PPTX) to Markdown format
+ *
+ * @param input - File path (string) or Buffer containing the document data
+ * @param options - Conversion options
+ * @returns Promise resolving to conversion result with markdown and metadata
+ *
+ * @throws {FileNotFoundError} When file path doesn't exist
+ * @throws {UnsupportedFormatError} When file format is not supported
+ * @throws {InvalidFileError} When file is corrupted or invalid
+ * @throws {ParseError} When document parsing fails
+ *
+ * @example
+ * ```typescript
+ * // Convert from file path
+ * const result = await convert('./document.pdf');
+ * console.log(result.markdown);
+ *
+ * // Convert from buffer with options
+ * const buffer = await fs.readFile('./document.docx');
+ * const result = await convert(buffer, {
+ *   imageDir: 'extracted-images',
+ *   preserveLayout: true
+ * });
+ * ```
+ */
+export declare function convert(input: ConvertInput, options?: ConvertOptions): Promise<ConversionResult>;
+export type * from './types/index.js';
+export { ImageExtractor } from './utils/image-extractor.js';
+export { ChartExtractor } from './utils/chart-extractor.js';
+export { LayoutParser } from './utils/layout-parser.js';
+//# sourceMappingURL=index.d.ts.map

package/dist/index.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAWA,OAAO,KAAK,EACV,YAAY,EACZ,cAAc,EACd,gBAAgB,EAGjB,MAAM,kBAAkB,CAAC;AAS1B;;;;;;;;;;;;;;;;;;;;;;;;;GAyBG;AACH,wBAAsB,OAAO,CAAC,KAAK,EAAE,YAAY,EAAE,OAAO,GAAE,cAAmB,GAAG,OAAO,CAAC,gBAAgB,CAAC,CAmI1G;AAGD,mBAAmB,kBAAkB,CAAC;AAGtC,OAAO,EAAE,cAAc,EAAE,MAAM,4BAA4B,CAAC;AAC5D,OAAO,EAAE,cAAc,EAAE,MAAM,4BAA4B,CAAC;AAC5D,OAAO,EAAE,YAAY,EAAE,MAAM,0BAA0B,CAAC"}

package/dist/index.js

@@ -0,0 +1,153 @@
+import { promises as fs } from 'node:fs';
+import { Buffer } from 'node:buffer';
+const fileType = require('file-type');
+import { ImageExtractor } from './utils/image-extractor.js';
+import { ChartExtractor } from './utils/chart-extractor.js';
+import { parsePdf } from './parsers/pdf-parser.js';
+import { parseDocx } from './parsers/docx-parser.js';
+import { parseXlsx } from './parsers/xlsx-parser.js';
+import { parsePptx } from './parsers/pptx-parser.js';
+import { FileNotFoundError, UnsupportedFormatError, InvalidFileError, SUPPORTED_MIME_TYPES } from './types/index.js';
+/**
+ * Convert a document (PDF, DOCX, XLSX, PPTX) to Markdown format
+ *
+ * @param input - File path (string) or Buffer containing the document data
+ * @param options - Conversion options
+ * @returns Promise resolving to conversion result with markdown and metadata
+ *
+ * @throws {FileNotFoundError} When file path doesn't exist
+ * @throws {UnsupportedFormatError} When file format is not supported
+ * @throws {InvalidFileError} When file is corrupted or invalid
+ * @throws {ParseError} When document parsing fails
+ *
+ * @example
+ * ```typescript
+ * // Convert from file path
+ * const result = await convert('./document.pdf');
+ * console.log(result.markdown);
+ *
+ * // Convert from buffer with options
+ * const buffer = await fs.readFile('./document.docx');
+ * const result = await convert(buffer, {
+ *   imageDir: 'extracted-images',
+ *   preserveLayout: true
+ * });
+ * ```
+ */
+export async function convert(input, options = {}) {
+    const startTime = Date.now();
+    try {
+        let buffer;
+        // Handle input type
+        if (typeof input === 'string') {
+            try {
+                buffer = await fs.readFile(input);
+            }
+            catch (error) {
+                if (error?.code === 'ENOENT') {
+                    throw new FileNotFoundError(input);
+                }
+                throw new InvalidFileError(`Failed to read file: ${input}`, error);
+            }
+        }
+        else if (Buffer.isBuffer(input)) {
+            buffer = input;
+        }
+        else {
+            throw new InvalidFileError('Input must be a file path (string) or Buffer');
+        }
+        // Detect file type
+        const detectedType = await fileType.fromBuffer(buffer);
+        if (!detectedType) {
+            throw new UnsupportedFormatError('unknown');
+        }
+        // Validate supported format
+        const supportedMimeTypes = Object.values(SUPPORTED_MIME_TYPES);
+        if (!supportedMimeTypes.includes(detectedType.mime)) {
+            throw new UnsupportedFormatError(detectedType.mime);
+        }
+        // Setup extractors
+        const { imageDir = 'images', preserveLayout = true, extractCharts = true, extractImages = true, maxPages } = options;
+        const imageExtractor = new ImageExtractor(imageDir);
+        const chartExtractor = new ChartExtractor(imageExtractor);
+        // Parse document based on type
+        let markdown;
+        let images = [];
+        let charts = [];
+        let pageCount = 1;
+        let additionalMetadata = {};
+        switch (detectedType.mime) {
+            case SUPPORTED_MIME_TYPES.PDF: {
+                const result = await parsePdf(buffer, imageExtractor, { maxPages, preserveLayout });
+                markdown = result.markdown;
+                images = result.images || [];
+                pageCount = result.pageCount || 1;
+                additionalMetadata = result.metadata || {};
+                break;
+            }
+            case SUPPORTED_MIME_TYPES.DOCX: {
+                const result = await parseDocx(buffer, imageExtractor, chartExtractor, { preserveLayout, extractImages, extractCharts });
+                markdown = result.markdown;
+                images = result.images || [];
+                charts = result.charts || [];
+                additionalMetadata = result.metadata || {};
+                break;
+            }
+            case SUPPORTED_MIME_TYPES.XLSX: {
+                const result = await parseXlsx(buffer, imageExtractor, chartExtractor, { preserveLayout, extractCharts });
+                markdown = result.markdown;
+                charts = result.charts || [];
+                pageCount = result.sheetCount || 1;
+                additionalMetadata = result.metadata || {};
+                break;
+            }
+            case SUPPORTED_MIME_TYPES.PPTX: {
+                const result = await parsePptx(buffer, imageExtractor, chartExtractor, { preserveLayout, extractImages, extractCharts });
+                markdown = result.markdown;
+                images = result.images || [];
+                charts = result.charts || [];
+                pageCount = result.slideCount || 1;
+                additionalMetadata = result.metadata || {};
+                break;
+            }
+            default: {
+                // This should never happen due to earlier validation, but TypeScript requires it
+                const exhaustiveCheck = detectedType.mime;
+                throw new UnsupportedFormatError(exhaustiveCheck);
+            }
+        }
+        const endTime = Date.now();
+        // Build metadata
+        const metadata = {
+            fileType: detectedType.ext.toUpperCase(),
+            mimeType: detectedType.mime,
+            pageCount,
+            imageCount: images.length,
+            chartCount: charts.length,
+            processingTime: endTime - startTime,
+            additional: additionalMetadata
+        };
+        return {
+            markdown,
+            images,
+            charts,
+            metadata
+        };
+    }
+    catch (error) {
+        // Re-throw known errors
+        if (error instanceof FileNotFoundError ||
+            error instanceof UnsupportedFormatError ||
+            error instanceof InvalidFileError) {
+            throw error;
+        }
+        // Wrap unknown errors
+        const message = error instanceof Error ? error.message : 'Unknown conversion error';
+        throw new InvalidFileError(`Conversion failed: ${message}`, error);
+    }
+}
+// Export utility classes for advanced usage
+export { ImageExtractor } from './utils/image-extractor.js';
+export { ChartExtractor } from './utils/chart-extractor.js';
+export { LayoutParser } from './utils/layout-parser.js';
+//# sourceMappingURL=index.js.map

package/dist/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,IAAI,EAAE,EAAE,MAAM,SAAS,CAAC;AACzC,OAAO,EAAE,MAAM,EAAE,MAAM,aAAa,CAAC;AACrC,MAAM,QAAQ,GAAG,OAAO,CAAC,WAAW,CAAC,CAAC;AAEtC,OAAO,EAAE,cAAc,EAAE,MAAM,4BAA4B,CAAC;AAC5D,OAAO,EAAE,cAAc,EAAE,MAAM,4BAA4B,CAAC;AAC5D,OAAO,EAAE,QAAQ,EAAE,MAAM,yBAAyB,CAAC;AACnD,OAAO,EAAE,SAAS,EAAE,MAAM,0BAA0B,CAAC;AACrD,OAAO,EAAE,SAAS,EAAE,MAAM,0BAA0B,CAAC;AACrD,OAAO,EAAE,SAAS,EAAE,MAAM,0BAA0B,CAAC;AAUrD,OAAO,EACL,iBAAiB,EACjB,sBAAsB,EACtB,gBAAgB,EAChB,oBAAoB,EACrB,MAAM,kBAAkB,CAAC;AAE1B;;;;;;;;;;;;;;;;;;;;;;;;;GAyBG;AACH,MAAM,CAAC,KAAK,UAAU,OAAO,CAAC,KAAmB,EAAE,UAA0B,EAAE;IAC7E,MAAM,SAAS,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC;IAE7B,IAAI,CAAC;QACH,IAAI,MAAc,CAAC;QAEnB,oBAAoB;QACpB,IAAI,OAAO,KAAK,KAAK,QAAQ,EAAE,CAAC;YAC9B,IAAI,CAAC;gBACH,MAAM,GAAG,MAAM,EAAE,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC;YACpC,CAAC;YAAC,OAAO,KAAc,EAAE,CAAC;gBACxB,IAAK,KAAa,EAAE,IAAI,KAAK,QAAQ,EAAE,CAAC;oBACtC,MAAM,IAAI,iBAAiB,CAAC,KAAK,CAAC,CAAC;gBACrC,CAAC;gBACD,MAAM,IAAI,gBAAgB,CAAC,wBAAwB,KAAK,EAAE,EAAE,KAAc,CAAC,CAAC;YAC9E,CAAC;QACH,CAAC;aAAM,IAAI,MAAM,CAAC,QAAQ,CAAC,KAAK,CAAC,EAAE,CAAC;YAClC,MAAM,GAAG,KAAK,CAAC;QACjB,CAAC;aAAM,CAAC;YACN,MAAM,IAAI,gBAAgB,CAAC,8CAA8C,CAAC,CAAC;QAC7E,CAAC;QAED,mBAAmB;QACnB,MAAM,YAAY,GAAG,MAAM,QAAQ,CAAC,UAAU,CAAC,MAAM,CAAC,CAAC;QAEvD,IAAI,CAAC,YAAY,EAAE,CAAC;YAClB,MAAM,IAAI,sBAAsB,CAAC,SAAS,CAAC,CAAC;QAC9C,CAAC;QAED,4BAA4B;QAC5B,MAAM,kBAAkB,GAAG,MAAM,CAAC,MAAM,CAAC,oBAAoB,CAAC,CAAC;QAC/D,IAAI,CAAC,kBAAkB,CAAC,QAAQ,CAAC,YAAY,CAAC,IAAyB,CAAC,EAAE,CAAC;YACzE,MAAM,IAAI,sBAAsB,CAAC,YAAY,CAAC,IAAI,CAAC,CAAC;QACtD,CAAC;QAED,mBAAmB;QACnB,MAAM,EACJ,QAAQ,GAAG,QAAQ,EACnB,cAAc,GAAG,IAAI,EACrB,aAAa,GAAG,IAAI,EACpB,aAAa,GAAG,IAAI,EACpB,QAAQ,EACT,GAAG,OAAO,CAAC;QAEZ,MAAM,cAAc,GAAG,IAAI,cAAc,CAAC,QAAQ,CAAC,CAAC;QACpD,MAAM,cAAc,GAAG,IAAI,cAAc,CAAC,cAAc,CAAC,CAAC;QAE1D,+BAA+B;QAC/B,IAAI,QAAgB,CAAC;QACrB,IAAI,MAAM,GAAyD,EAAE,CAAC;QACtE,IAAI,MAAM,GAAyD,EAAE,CAAC;QACtE,IAAI,SAAS,GAAG,CAAC,CAAC;QAClB,IAAI,kBAAkB,GAA4B,EAAE,CAAC;QAErD,QAAQ,YAAY,CAAC,IAAyB,EAAE,CAAC;YAC/C,KAAK,oBAAoB,CAAC,GAAG,CAAC,CAAC,CAAC;gBAC9B,MAAM,MAAM,GAAG,MAAM,QAAQ,CAAC,MAAM,EAAE,cAAc,EAAE,EAAE,QAAQ,EAAE,cAAc,EAAE,CAAC,CAAC;gBACpF,QAAQ,GAAG,MAAM,CAAC,QAAQ,CAAC;gBAC3B,MAAM,GAAG,MAAM,CAAC,MAAM,IAAI,EAAE,CAAC;gBAC7B,SAAS,GAAG,MAAM,CAAC,SAAS,IAAI,CAAC,CAAC;gBAClC,kBAAkB,GAAG,MAAM,CAAC,QAAQ,IAAI,EAAE,CAAC;gBAC3C,MAAM;YACR,CAAC;YAED,KAAK,oBAAoB,CAAC,IAAI,CAAC,CAAC,CAAC;gBAC/B,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,MAAM,EAAE,cAAc,EAAE,cAAc,EAAE,EAAE,cAAc,EAAE,aAAa,EAAE,aAAa,EAAE,CAAC,CAAC;gBACzH,QAAQ,GAAG,MAAM,CAAC,QAAQ,CAAC;gBAC3B,MAAM,GAAG,MAAM,CAAC,MAAM,IAAI,EAAE,CAAC;gBAC7B,MAAM,GAAG,MAAM,CAAC,MAAM,IAAI,EAAE,CAAC;gBAC7B,kBAAkB,GAAG,MAAM,CAAC,QAAQ,IAAI,EAAE,CAAC;gBAC3C,MAAM;YACR,CAAC;YAED,KAAK,oBAAoB,CAAC,IAAI,CAAC,CAAC,CAAC;gBAC/B,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,MAAM,EAAE,cAAc,EAAE,cAAc,EAAE,EAAE,cAAc,EAAE,aAAa,EAAE,CAAC,CAAC;gBAC1G,QAAQ,GAAG,MAAM,CAAC,QAAQ,CAAC;gBAC3B,MAAM,GAAG,MAAM,CAAC,MAAM,IAAI,EAAE,CAAC;gBAC7B,SAAS,GAAG,MAAM,CAAC,UAAU,IAAI,CAAC,CAAC;gBACnC,kBAAkB,GAAG,MAAM,CAAC,QAAQ,IAAI,EAAE,CAAC;gBAC3C,MAAM;YACR,CAAC;YAED,KAAK,oBAAoB,CAAC,IAAI,CAAC,CAAC,CAAC;gBAC/B,MAAM,MAAM,GAAG,MAAM,SAAS,CAAC,MAAM,EAAE,cAAc,EAAE,cAAc,EAAE,EAAE,cAAc,EAAE,aAAa,EAAE,aAAa,EAAE,CAAC,CAAC;gBACzH,QAAQ,GAAG,MAAM,CAAC,QAAQ,CAAC;gBAC3B,MAAM,GAAG,MAAM,CAAC,MAAM,IAAI,EAAE,CAAC;gBAC7B,MAAM,GAAG,MAAM,CAAC,MAAM,IAAI,EAAE,CAAC;gBAC7B,SAAS,GAAG,MAAM,CAAC,UAAU,IAAI,CAAC,CAAC;gBACnC,kBAAkB,GAAG,MAAM,CAAC,QAAQ,IAAI,EAAE,CAAC;gBAC3C,MAAM;YACR,CAAC;YAED,OAAO,CAAC,CAAC,CAAC;gBACR,iFAAiF;gBACjF,MAAM,eAAe,GAAU,YAAY,CAAC,IAAa,CAAC;gBAC1D,MAAM,IAAI,sBAAsB,CAAC,eAAe,CAAC,CAAC;YACpD,CAAC;QACH,CAAC;QAED,MAAM,OAAO,GAAG,IAAI,CAAC,GAAG,EAAE,CAAC;QAE3B,iBAAiB;QACjB,MAAM,QAAQ,GAAqB;YACjC,QAAQ,EAAE,YAAY,CAAC,GAAG,CAAC,WAAW,EAAE;YACxC,QAAQ,EAAE,YAAY,CAAC,IAAI;YAC3B,SAAS;YACT,UAAU,EAAE,MAAM,CAAC,MAAM;YACzB,UAAU,EAAE,MAAM,CAAC,MAAM;YACzB,cAAc,EAAE,OAAO,GAAG,SAAS;YACnC,UAAU,EAAE,kBAAkB;SAC/B,CAAC;QAEF,OAAO;YACL,QAAQ;YACR,MAAM;YACN,MAAM;YACN,QAAQ;SACT,CAAC;IAEJ,CAAC;IAAC,OAAO,KAAc,EAAE,CAAC;QACxB,wBAAwB;QACxB,IAAI,KAAK,YAAY,iBAAiB;YAClC,KAAK,YAAY,sBAAsB;YACvC,KAAK,YAAY,gBAAgB,EAAE,CAAC;YACtC,MAAM,KAAK,CAAC;QACd,CAAC;QAED,sBAAsB;QACtB,MAAM,OAAO,GAAG,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,0BAA0B,CAAC;QACpF,MAAM,IAAI,gBAAgB,CAAC,sBAAsB,OAAO,EAAE,EAAE,KAAc,CAAC,CAAC;IAC9E,CAAC;AACH,CAAC;AAKD,4CAA4C;AAC5C,OAAO,EAAE,cAAc,EAAE,MAAM,4BAA4B,CAAC;AAC5D,OAAO,EAAE,cAAc,EAAE,MAAM,4BAA4B,CAAC;AAC5D,OAAO,EAAE,YAAY,EAAE,MAAM,0BAA0B,CAAC"}

package/dist/parsers/docx-parser.d.ts

@@ -0,0 +1,20 @@
+import type { Buffer } from 'node:buffer';
+import type { ImageExtractor } from '../utils/image-extractor.js';
+import type { ChartExtractor } from '../utils/chart-extractor.js';
+import type { ImageData, ChartData } from '../types/interfaces.js';
+export interface DocxParseOptions {
+    readonly preserveLayout?: boolean;
+    readonly extractImages?: boolean;
+    readonly extractCharts?: boolean;
+}
+export interface DocxParseResult {
+    readonly markdown: string;
+    readonly images: readonly ImageData[];
+    readonly charts: readonly ChartData[];
+    readonly metadata: Record<string, unknown>;
+}
+/**
+ * Parse DOCX buffer and convert to markdown with layout preservation
+ */
+export declare function parseDocx(buffer: Buffer, imageExtractor: ImageExtractor, chartExtractor: ChartExtractor, options?: DocxParseOptions): Promise<DocxParseResult>;
+//# sourceMappingURL=docx-parser.d.ts.map

package/dist/parsers/docx-parser.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"docx-parser.d.ts","sourceRoot":"","sources":["../../src/parsers/docx-parser.ts"],"names":[],"mappings":"AAEA,OAAO,KAAK,EAAE,MAAM,EAAE,MAAM,aAAa,CAAC;AAE1C,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,6BAA6B,CAAC;AAClE,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,6BAA6B,CAAC;AAGlE,OAAO,KAAK,EACV,SAAS,EACT,SAAS,EAKV,MAAM,wBAAwB,CAAC;AAEhC,MAAM,WAAW,gBAAgB;IAC/B,QAAQ,CAAC,cAAc,CAAC,EAAE,OAAO,CAAC;IAClC,QAAQ,CAAC,aAAa,CAAC,EAAE,OAAO,CAAC;IACjC,QAAQ,CAAC,aAAa,CAAC,EAAE,OAAO,CAAC;CAClC;AAED,MAAM,WAAW,eAAe;IAC9B,QAAQ,CAAC,QAAQ,EAAE,MAAM,CAAC;IAC1B,QAAQ,CAAC,MAAM,EAAE,SAAS,SAAS,EAAE,CAAC;IACtC,QAAQ,CAAC,MAAM,EAAE,SAAS,SAAS,EAAE,CAAC;IACtC,QAAQ,CAAC,QAAQ,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;CAC5C;AA4BD;;GAEG;AACH,wBAAsB,SAAS,CAC7B,MAAM,EAAE,MAAM,EACd,cAAc,EAAE,cAAc,EAC9B,cAAc,EAAE,cAAc,EAC9B,OAAO,GAAE,gBAAqB,GAC7B,OAAO,CAAC,eAAe,CAAC,CA6D1B"}