officeparser 5.2.2 → 6.0.2

package/dist/OfficeParser.d.ts

@@ -0,0 +1,90 @@
+/**
+ * Office Parser - Main Entry Point
+ *
+ * This module provides the main `OfficeParser` class with a single static method
+ * that automatically detects file types and routes to the appropriate parser.
+ *
+ * **Supported Formats:**
+ * - DOCX (Word documents)
+ * - XLSX (Excel spreadsheets)
+ * - PPTX (PowerPoint presentations)
+ * - ODT, ODP, ODS (OpenDocument formats)
+ * - PDF (Portable Document Format)
+ * - RTF (Rich Text Format)
+ *
+ * **Usage:**
+ * ```typescript
+ * import { OfficeParser } from 'officeparser';
+ *
+ * // Parse from file path
+ * const ast = await OfficeParser.parseOffice('document.docx', {
+ *   extractAttachments: true,
+ *   ocr: true
+ * });
+ *
+ * // Parse from Buffer
+ * const buffer = fs.readFileSync('document.pdf');
+ * const ast = await OfficeParser.parseOffice(buffer);
+ *
+ * // Get plain text
+ * console.log(ast.toText());
+ * ```
+ *
+ * @module OfficeParser
+ */
+/// <reference types="node" />
+import { OfficeParserAST, OfficeParserConfig } from './types';
+/**
+ * Main parser class providing office document parsing functionality.
+ *
+ * This class contains a single static method `parseOffice` that serves as the
+ * universal entry point for parsing any supported office document format.
+ */
+export declare class OfficeParser {
+    /**
+     * Parses an office document and returns a structured AST.
+     *
+     * This method:
+     * 1. Accepts a file path, Buffer, or ArrayBuffer
+     * 2. Detects the file type (from extension or content)
+     * 3. Routes to the appropriate format-specific parser
+     * 4. Returns a unified AST structure
+     *
+     * **File Type Detection:**
+     * - If a file path is provided, uses the file extension
+     * - If a Buffer is provided, uses magic bytes detection (file-type library)
+     *
+     * **Supported Formats and Routes:**
+     * - `.docx` → WordParser (OOXML)
+     * - `.xlsx` → ExcelParser (OOXML)
+     * - `.pptx` → PowerPointParser (OOXML)
+     * - `.odt`, `.odp`, `.ods` → OpenOfficeParser (ODF)
+     * - `.pdf` → PdfParser (PDF.js)
+     * - `.rtf` → RtfParser (custom RTF parser)
+     *
+     * @param file - File path (string), Buffer, or ArrayBuffer containing the document
+     * @param config - Optional configuration object (defaults applied for all omitted options)
+     * @returns A promise resolving to the parsed OfficeParserAST
+     * @throws {Error} If file doesn't exist, format is unsupported, or parsing fails
+     *
+     * @example
+     * ```typescript
+     * // Parse a DOCX file
+     * const ast = await OfficeParser.parseOffice('report.docx', {
+     *   extractAttachments: true,
+     *   includeRawContent: false
+     * });
+     *
+     * // Parse a Buffer with OCR enabled
+     * const buffer = await fetch('document.pdf').then(r => r.arrayBuffer());
+     * const ast = await OfficeParser.parseOffice(buffer, {
+     *   ocr: true,
+     *   ocrLanguage: 'eng+fra'
+     * });
+     *
+     * // Extract text
+     * const text = ast.toText();
+     * ```
+     */
+    static parseOffice(file: string | Buffer | ArrayBuffer, configOrCallback?: OfficeParserConfig | ((ast: OfficeParserAST, err?: any) => void), config?: OfficeParserConfig): Promise<OfficeParserAST>;
+}

package/dist/OfficeParser.js

@@ -0,0 +1,217 @@
+"use strict";
+/**
+ * Office Parser - Main Entry Point
+ *
+ * This module provides the main `OfficeParser` class with a single static method
+ * that automatically detects file types and routes to the appropriate parser.
+ *
+ * **Supported Formats:**
+ * - DOCX (Word documents)
+ * - XLSX (Excel spreadsheets)
+ * - PPTX (PowerPoint presentations)
+ * - ODT, ODP, ODS (OpenDocument formats)
+ * - PDF (Portable Document Format)
+ * - RTF (Rich Text Format)
+ *
+ * **Usage:**
+ * ```typescript
+ * import { OfficeParser } from 'officeparser';
+ *
+ * // Parse from file path
+ * const ast = await OfficeParser.parseOffice('document.docx', {
+ *   extractAttachments: true,
+ *   ocr: true
+ * });
+ *
+ * // Parse from Buffer
+ * const buffer = fs.readFileSync('document.pdf');
+ * const ast = await OfficeParser.parseOffice(buffer);
+ *
+ * // Get plain text
+ * console.log(ast.toText());
+ * ```
+ *
+ * @module OfficeParser
+ */
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
+    }
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
+    Object.defineProperty(o, "default", { enumerable: true, value: v });
+}) : function(o, v) {
+    o["default"] = v;
+});
+var __importStar = (this && this.__importStar) || function (mod) {
+    if (mod && mod.__esModule) return mod;
+    var result = {};
+    if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
+    __setModuleDefault(result, mod);
+    return result;
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.OfficeParser = void 0;
+const fileType = __importStar(require("file-type"));
+const fs = __importStar(require("fs"));
+const ExcelParser_1 = require("./parsers/ExcelParser");
+const OpenOfficeParser_1 = require("./parsers/OpenOfficeParser");
+const PdfParser_1 = require("./parsers/PdfParser");
+const PowerPointParser_1 = require("./parsers/PowerPointParser");
+const RtfParser_1 = require("./parsers/RtfParser");
+const WordParser_1 = require("./parsers/WordParser");
+const errorUtils_1 = require("./utils/errorUtils");
+/**
+ * Main parser class providing office document parsing functionality.
+ *
+ * This class contains a single static method `parseOffice` that serves as the
+ * universal entry point for parsing any supported office document format.
+ */
+class OfficeParser {
+    /**
+     * Parses an office document and returns a structured AST.
+     *
+     * This method:
+     * 1. Accepts a file path, Buffer, or ArrayBuffer
+     * 2. Detects the file type (from extension or content)
+     * 3. Routes to the appropriate format-specific parser
+     * 4. Returns a unified AST structure
+     *
+     * **File Type Detection:**
+     * - If a file path is provided, uses the file extension
+     * - If a Buffer is provided, uses magic bytes detection (file-type library)
+     *
+     * **Supported Formats and Routes:**
+     * - `.docx` → WordParser (OOXML)
+     * - `.xlsx` → ExcelParser (OOXML)
+     * - `.pptx` → PowerPointParser (OOXML)
+     * - `.odt`, `.odp`, `.ods` → OpenOfficeParser (ODF)
+     * - `.pdf` → PdfParser (PDF.js)
+     * - `.rtf` → RtfParser (custom RTF parser)
+     *
+     * @param file - File path (string), Buffer, or ArrayBuffer containing the document
+     * @param config - Optional configuration object (defaults applied for all omitted options)
+     * @returns A promise resolving to the parsed OfficeParserAST
+     * @throws {Error} If file doesn't exist, format is unsupported, or parsing fails
+     *
+     * @example
+     * ```typescript
+     * // Parse a DOCX file
+     * const ast = await OfficeParser.parseOffice('report.docx', {
+     *   extractAttachments: true,
+     *   includeRawContent: false
+     * });
+     *
+     * // Parse a Buffer with OCR enabled
+     * const buffer = await fetch('document.pdf').then(r => r.arrayBuffer());
+     * const ast = await OfficeParser.parseOffice(buffer, {
+     *   ocr: true,
+     *   ocrLanguage: 'eng+fra'
+     * });
+     *
+     * // Extract text
+     * const text = ast.toText();
+     * ```
+     */
+    static async parseOffice(file, configOrCallback, config) {
+        let callback;
+        let actualConfig = {};
+        if (typeof configOrCallback === 'function') {
+            callback = configOrCallback;
+            actualConfig = config || {};
+        }
+        else {
+            actualConfig = configOrCallback || {};
+        }
+        const internalConfig = {
+            ignoreNotes: false,
+            newlineDelimiter: '\n',
+            putNotesAtLast: false,
+            outputErrorToConsole: false,
+            extractAttachments: false,
+            ocr: false,
+            ocrLanguage: 'eng',
+            includeRawContent: false,
+            pdfWorkerSrc: '',
+            ...actualConfig
+        };
+        let buffer = Buffer.alloc(0);
+        let ext = '';
+        let filePath;
+        try {
+            if (!file) {
+                throw (0, errorUtils_1.getOfficeError)(errorUtils_1.OfficeErrorType.IMPROPER_ARGUMENTS, internalConfig);
+            }
+            if (file instanceof ArrayBuffer) {
+                buffer = Buffer.from(file);
+            }
+            else if (Buffer.isBuffer(file)) {
+                buffer = file;
+            }
+            else if (typeof file === 'string') {
+                filePath = file;
+                if (!fs.existsSync(file)) {
+                    throw (0, errorUtils_1.getOfficeError)(errorUtils_1.OfficeErrorType.FILE_DOES_NOT_EXIST, internalConfig, file);
+                }
+                if (fs.lstatSync(file).isDirectory()) {
+                    throw (0, errorUtils_1.getOfficeError)(errorUtils_1.OfficeErrorType.LOCATION_NOT_FOUND, internalConfig, file);
+                }
+                buffer = fs.readFileSync(file);
+                ext = file.split('.').pop()?.toLowerCase() || '';
+            }
+            else {
+                throw (0, errorUtils_1.getOfficeError)(errorUtils_1.OfficeErrorType.INVALID_INPUT, internalConfig);
+            }
+            if (!ext) {
+                const type = await fileType.fromBuffer(buffer);
+                if (type) {
+                    ext = type.ext.toLowerCase();
+                }
+                else {
+                    throw (0, errorUtils_1.getOfficeError)(errorUtils_1.OfficeErrorType.IMPROPER_BUFFERS, internalConfig);
+                }
+            }
+            let result;
+            switch (ext) {
+                case 'docx':
+                    result = await (0, WordParser_1.parseWord)(buffer, internalConfig);
+                    break;
+                case 'pptx':
+                    result = await (0, PowerPointParser_1.parsePowerPoint)(buffer, internalConfig);
+                    break;
+                case 'xlsx':
+                    result = await (0, ExcelParser_1.parseExcel)(buffer, internalConfig);
+                    break;
+                case 'odt':
+                case 'odp':
+                case 'ods':
+                    result = await (0, OpenOfficeParser_1.parseOpenOffice)(buffer, internalConfig);
+                    break;
+                case 'pdf':
+                    result = await (0, PdfParser_1.parsePdf)(buffer, internalConfig);
+                    break;
+                case 'rtf':
+                    result = await (0, RtfParser_1.parseRtf)(buffer, internalConfig);
+                    break;
+                default:
+                    throw (0, errorUtils_1.getOfficeError)(errorUtils_1.OfficeErrorType.EXTENSION_UNSUPPORTED, internalConfig, ext);
+            }
+            if (callback)
+                callback(result);
+            return result;
+        }
+        catch (error) {
+            const wrappedError = (0, errorUtils_1.getWrappedError)(error, internalConfig, filePath);
+            if (callback)
+                callback(undefined, wrappedError);
+            throw wrappedError;
+        }
+    }
+}
+exports.OfficeParser = OfficeParser;

package/dist/index.d.ts

@@ -0,0 +1,51 @@
+#!/usr/bin/env node
+/**
+ * officeparser - Universal Office Document Parser
+ *
+ * A comprehensive Node.js library for parsing Microsoft Office and OpenDocument files
+ * into structured Abstract Syntax Trees (AST) with full formatting information.
+ *
+ * **Supported Formats:**
+ * - Microsoft Office: DOCX, XLSX, PPTX (Office Open XML)
+ * - OpenDocument: ODT, ODP, ODS (ODF)
+ * - Legacy: RTF (Rich Text Format)
+ * - Portable: PDF
+ *
+ * **Key Features:**
+ * - Unified AST output across all formats
+ * - Rich text formatting (bold, italic, colors, fonts, etc.)
+ * - Document structure (headings, lists, tables)
+ * - Image extraction with optional OCR
+ * - Metadata extraction
+ * - TypeScript support with full type definitions
+ *
+ * **Quick Start:**
+ * ```typescript
+ * import { OfficeParser } from 'officeparser';
+ *
+ * const ast = await OfficeParser.parseOffice('document.docx', {
+ *   extractAttachments: true,
+ *   ocr: true,
+ *   includeRawContent: false
+ * });
+ *
+ * console.log(ast.toText()); // Plain text output
+ * console.log(ast.content);  // Structured content tree
+ * console.log(ast.metadata); // Document metadata
+ * ```
+ *
+ * **Main Exports:**
+ * - `OfficeParser` - Main parser class
+ * - `OfficeParserConfig` - Configuration interface
+ * - `OfficeParserAST` - AST result interface
+ * - `OfficeContentNode` - Content tree node interface
+ * - All type definitions
+ *
+ * @packageDocumentation
+ * @module officeparser
+ */
+import { OfficeParser } from './OfficeParser';
+import { OfficeParserConfig, OfficeParserAST, OfficeContentNode, OfficeAttachment, OfficeMetadata, TextFormatting, SupportedFileType, OfficeContentNodeType, OfficeMimeType, SlideMetadata, SheetMetadata, HeadingMetadata, ListMetadata, CellMetadata, ImageMetadata, PageMetadata, ContentMetadata } from './types';
+declare const parseOffice: typeof OfficeParser.parseOffice;
+export { OfficeParser, parseOffice, OfficeParserConfig, OfficeParserAST, OfficeContentNode, OfficeAttachment, OfficeMetadata, TextFormatting, SupportedFileType, OfficeContentNodeType, OfficeMimeType, SlideMetadata, SheetMetadata, HeadingMetadata, ListMetadata, CellMetadata, ImageMetadata, PageMetadata, ContentMetadata };
+export default OfficeParser;

package/dist/index.js

@@ -0,0 +1,108 @@
+#!/usr/bin/env node
+"use strict";
+/**
+ * officeparser - Universal Office Document Parser
+ *
+ * A comprehensive Node.js library for parsing Microsoft Office and OpenDocument files
+ * into structured Abstract Syntax Trees (AST) with full formatting information.
+ *
+ * **Supported Formats:**
+ * - Microsoft Office: DOCX, XLSX, PPTX (Office Open XML)
+ * - OpenDocument: ODT, ODP, ODS (ODF)
+ * - Legacy: RTF (Rich Text Format)
+ * - Portable: PDF
+ *
+ * **Key Features:**
+ * - Unified AST output across all formats
+ * - Rich text formatting (bold, italic, colors, fonts, etc.)
+ * - Document structure (headings, lists, tables)
+ * - Image extraction with optional OCR
+ * - Metadata extraction
+ * - TypeScript support with full type definitions
+ *
+ * **Quick Start:**
+ * ```typescript
+ * import { OfficeParser } from 'officeparser';
+ *
+ * const ast = await OfficeParser.parseOffice('document.docx', {
+ *   extractAttachments: true,
+ *   ocr: true,
+ *   includeRawContent: false
+ * });
+ *
+ * console.log(ast.toText()); // Plain text output
+ * console.log(ast.content);  // Structured content tree
+ * console.log(ast.metadata); // Document metadata
+ * ```
+ *
+ * **Main Exports:**
+ * - `OfficeParser` - Main parser class
+ * - `OfficeParserConfig` - Configuration interface
+ * - `OfficeParserAST` - AST result interface
+ * - `OfficeContentNode` - Content tree node interface
+ * - All type definitions
+ *
+ * @packageDocumentation
+ * @module officeparser
+ */
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.parseOffice = exports.OfficeParser = void 0;
+const OfficeParser_1 = require("./OfficeParser");
+Object.defineProperty(exports, "OfficeParser", { enumerable: true, get: function () { return OfficeParser_1.OfficeParser; } });
+const parseOffice = OfficeParser_1.OfficeParser.parseOffice;
+exports.parseOffice = parseOffice;
+// Default export for backward compatibility
+exports.default = OfficeParser_1.OfficeParser;
+// CLI handling - allows running as: node index.js file.docx
+if (typeof require !== 'undefined' && typeof module !== 'undefined' && require.main === module) {
+    const args = process.argv.slice(2);
+    let fileArg;
+    let toText = false;
+    const configArgs = [];
+    function isConfigOption(arg) {
+        return arg.startsWith('--') && arg.includes('=');
+    }
+    args.forEach(arg => {
+        if (isConfigOption(arg)) {
+            configArgs.push(arg);
+        }
+        else if (!fileArg) {
+            fileArg = arg;
+        }
+    });
+    if (fileArg) {
+        const config = {};
+        configArgs.forEach(arg => {
+            const [key, value] = arg.split('=');
+            const cleanKey = key.replace('--', '');
+            if (cleanKey === 'toText') {
+                if (value.toLowerCase() === 'true')
+                    toText = true;
+                else if (value.toLowerCase() === 'false')
+                    toText = false;
+                else
+                    console.log(`Invalid value for toText: ${value}`);
+            }
+            // @ts-ignore
+            else if (value.toLowerCase() === 'true')
+                config[cleanKey] = true;
+            // @ts-ignore
+            else if (value.toLowerCase() === 'false')
+                config[cleanKey] = false;
+            // @ts-ignore
+            else
+                config[cleanKey] = value;
+        });
+        OfficeParser_1.OfficeParser.parseOffice(fileArg, config)
+            .then((ast) => {
+            if (toText)
+                console.log(ast.toText());
+            else
+                console.log(JSON.stringify(ast, null, 2));
+        })
+            .catch(console.error);
+    }
+    else {
+        console.log("Usage: node officeparser [file] [--option=value]");
+    }
+}