officeparser 6.1.1 → 7.0.1

package/dist/OfficeParser.js

@@ -12,6 +12,9 @@
  * - ODT, ODP, ODS (OpenDocument formats)
  * - PDF (Portable Document Format)
  * - RTF (Rich Text Format)
+ * - CSV (Comma-Separated Values)
+ * - MD (Markdown)
+ * - HTML (HyperText Markup Language)
  *
  * **Usage:**
  * ```typescript
@@ -35,13 +38,18 @@
  */
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.OfficeParser = void 0;
-const envUtils_js_1 = require("./utils/envUtils.js");
+const CsvParser_js_1 = require("./parsers/CsvParser.js");
 const ExcelParser_js_1 = require("./parsers/ExcelParser.js");
+const HtmlParser_js_1 = require("./parsers/HtmlParser.js");
+const MarkdownParser_js_1 = require("./parsers/MarkdownParser.js");
 const OpenOfficeParser_js_1 = require("./parsers/OpenOfficeParser.js");
 const PdfParser_js_1 = require("./parsers/PdfParser.js");
 const PowerPointParser_js_1 = require("./parsers/PowerPointParser.js");
 const RtfParser_js_1 = require("./parsers/RtfParser.js");
 const WordParser_js_1 = require("./parsers/WordParser.js");
+const types_js_1 = require("./types.js");
+const configUtils_js_1 = require("./utils/configUtils.js");
+const envUtils_js_1 = require("./utils/envUtils.js");
 const errorUtils_js_1 = require("./utils/errorUtils.js");
 const moduleLoader_js_1 = require("./utils/moduleLoader.js");
 const ocrUtils_js_1 = require("./utils/ocrUtils.js");
@@ -72,6 +80,9 @@ class OfficeParser {
      * - `.odt`, `.odp`, `.ods` → OpenOfficeParser (ODF)
      * - `.pdf` → PdfParser (PDF.js)
      * - `.rtf` → RtfParser (custom RTF parser)
+     * - `.csv` → CsvParser
+     * - `.md` → MarkdownParser
+     * - `.html` → HtmlParser
      *
      * @param file - File path (string), Buffer, or ArrayBuffer containing the document
      * @param config - Optional configuration object (defaults applied for all omitted options)
@@ -107,28 +118,20 @@ class OfficeParser {
         else {
             actualConfig = configOrCallback || {};
         }
-        const internalConfig = {
-            ignoreNotes: false,
-            newlineDelimiter: '\n',
-            putNotesAtLast: false,
-            outputErrorToConsole: false,
-            extractAttachments: false,
-            ocr: false,
-            ocrLanguage: 'eng',
-            includeRawContent: false,
-            serializeRawContent: true,
-            preserveXmlWhitespace: false,
-            pdfWorkerSrc: '',
-            ocrConfig: {},
-            includeBreakNodes: false,
-            ...actualConfig
+        const internalConfig = (0, configUtils_js_1.resolveParserConfig)(actualConfig);
+        const parsingWarnings = [];
+        const originalOnWarning = internalConfig.onWarning;
+        internalConfig.onWarning = (issue) => {
+            parsingWarnings.push(issue);
+            if (originalOnWarning)
+                originalOnWarning(issue);
         };
         let buffer = Buffer.alloc(0);
-        let ext = '';
+        let ext = internalConfig.fileType ?? '';
         let filePath;
         try {
             if (!file) {
-                throw (0, errorUtils_js_1.getOfficeError)(errorUtils_js_1.OfficeErrorType.IMPROPER_ARGUMENTS, internalConfig);
+                throw (0, errorUtils_js_1.getOfficeError)(types_js_1.OfficeErrorType.IMPROPER_ARGUMENTS, internalConfig);
             }
             if (file instanceof ArrayBuffer) {
                 buffer = Buffer.from(file);
@@ -144,29 +147,59 @@ class OfficeParser {
                 // shim 'fs' so it won't crash at build time.
                 const fs = await import('fs');
                 if (!fs.existsSync(file)) {
-                    throw (0, errorUtils_js_1.getOfficeError)(errorUtils_js_1.OfficeErrorType.FILE_DOES_NOT_EXIST, internalConfig, file);
+                    throw (0, errorUtils_js_1.getOfficeError)(types_js_1.OfficeErrorType.FILE_DOES_NOT_EXIST, internalConfig, file);
                 }
                 if (fs.lstatSync(file).isDirectory()) {
-                    throw (0, errorUtils_js_1.getOfficeError)(errorUtils_js_1.OfficeErrorType.LOCATION_NOT_FOUND, internalConfig, file);
+                    throw (0, errorUtils_js_1.getOfficeError)(types_js_1.OfficeErrorType.LOCATION_NOT_FOUND, internalConfig, file);
                 }
                 buffer = fs.readFileSync(file);
-                ext = file.split('.').pop()?.toLowerCase() || '';
+                ext = ext || file.split('.').pop() || '';
             }
             else {
-                throw (0, errorUtils_js_1.getOfficeError)(errorUtils_js_1.OfficeErrorType.INVALID_INPUT, internalConfig);
+                throw (0, errorUtils_js_1.getOfficeError)(types_js_1.OfficeErrorType.INVALID_INPUT, internalConfig);
             }
-            if (!ext) {
-                const { fileTypeFromBuffer } = await (0, moduleLoader_js_1.loadFileType)();
-                const type = await fileTypeFromBuffer(buffer);
-                if (type) {
-                    ext = type.ext.toLowerCase();
+            // Attempt to detect file type from buffer only if extension is unknown.
+            // This matches v6 behavior and prevents crashes in older Node environments
+            // where file-type 22.x might be incompatible.
+            if (buffer.length > 0 && !ext) {
+                try {
+                    const { fileTypeFromBuffer } = await (0, moduleLoader_js_1.loadFileType)();
+                    const type = await fileTypeFromBuffer(buffer);
+                    if (type) {
+                        ext = type.ext;
+                    }
+                    else {
+                        // If no extension could be detected and none was provided,
+                        // it might be a text-based format (csv, md, html) which 
+                        // lack magic bytes. We'll let the switch default handle it.
+                    }
+                }
+                catch (error) {
+                    // Log warning but don't crash; the switch below will handle unsupported/missing ext
+                    (0, errorUtils_js_1.logWarning)(types_js_1.OfficeWarningType.FILE_TYPE_DETECTION_FAILED, internalConfig, { error });
+                }
+            }
+            else if (buffer.length > 0 && ext) {
+                // If extension is known, we can optionally verify it, but we wrap it 
+                // in a try-catch to avoid breaking Node 18 if file-type fails to load.
+                try {
+                    const { fileTypeFromBuffer } = await (0, moduleLoader_js_1.loadFileType)();
+                    const type = await fileTypeFromBuffer(buffer);
+                    if (type && type.ext.toLowerCase() !== ext.toLowerCase()) {
+                        // Mismatch found between authoritative extension and detected content
+                        (0, errorUtils_js_1.logWarning)(types_js_1.OfficeWarningType.BUFFER_TYPE_MISMATCH, internalConfig, { detected: type.ext, expected: ext });
+                    }
                 }
-                else {
-                    throw (0, errorUtils_js_1.getOfficeError)(errorUtils_js_1.OfficeErrorType.IMPROPER_BUFFERS, internalConfig);
+                catch (error) {
+                    // Log warning so user knows verification could not be performed
+                    (0, errorUtils_js_1.logWarning)(types_js_1.OfficeWarningType.FILE_TYPE_DETECTION_FAILED, internalConfig, { error });
                 }
             }
+            if (!ext) {
+                throw (0, errorUtils_js_1.getOfficeError)(types_js_1.OfficeErrorType.IMPROPER_BUFFERS, internalConfig);
+            }
             let result;
-            switch (ext) {
+            switch (ext.toLowerCase()) {
                 case 'docx':
                     result = await (0, WordParser_js_1.parseWord)(buffer, internalConfig);
                     break;
@@ -187,9 +220,19 @@ class OfficeParser {
                 case 'rtf':
                     result = await (0, RtfParser_js_1.parseRtf)(buffer, internalConfig);
                     break;
+                case 'csv':
+                    result = await (0, CsvParser_js_1.parseCsv)(buffer, internalConfig);
+                    break;
+                case 'html':
+                    result = await (0, HtmlParser_js_1.parseHtml)(buffer, internalConfig);
+                    break;
+                case 'md':
+                    result = await (0, MarkdownParser_js_1.parseMarkdown)(buffer, internalConfig);
+                    break;
                 default:
-                    throw (0, errorUtils_js_1.getOfficeError)(errorUtils_js_1.OfficeErrorType.EXTENSION_UNSUPPORTED, internalConfig, ext);
+                    throw (0, errorUtils_js_1.getOfficeError)(types_js_1.OfficeErrorType.EXTENSION_UNSUPPORTED, internalConfig, ext);
             }
+            result.warnings = parsingWarnings;
             if (callback)
                 callback(result);
             return result;

package/dist/cli.d.ts

@@ -8,7 +8,9 @@
  *   officeparser file.docx --ocr=true --extractAttachments=true
  *
  * Options (--key=value):
- *   --toText=true             Output plain text instead of JSON AST
+ *   --format=json|text|md|html|csv|rtf|pdf|chunks  Convert AST to specified format
+ *   --output=path             Save result to a file
+ *   --toText=true             Legacy flag for plain text output
  *   --ocr=true                Enable OCR for images
  *   --ocrLanguage=eng         OCR language (default: eng)
  *   --extractAttachments=true Extract embedded attachments

package/dist/cli.js

@@ -9,7 +9,9 @@
  *   officeparser file.docx --ocr=true --extractAttachments=true
  *
  * Options (--key=value):
- *   --toText=true             Output plain text instead of JSON AST
+ *   --format=json|text|md|html|csv|rtf|pdf|chunks  Convert AST to specified format
+ *   --output=path             Save result to a file
+ *   --toText=true             Legacy flag for plain text output
  *   --ocr=true                Enable OCR for images
  *   --ocrLanguage=eng         OCR language (default: eng)
  *   --extractAttachments=true Extract embedded attachments
@@ -18,12 +20,49 @@
  *   --includeRawContent=true  Include raw content in AST
  *   --outputErrorToConsole=true  Log errors to console
  */
+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 () {
+    var ownKeys = function(o) {
+        ownKeys = Object.getOwnPropertyNames || function (o) {
+            var ar = [];
+            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
+            return ar;
+        };
+        return ownKeys(o);
+    };
+    return function (mod) {
+        if (mod && mod.__esModule) return mod;
+        var result = {};
+        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
+        __setModuleDefault(result, mod);
+        return result;
+    };
+})();
 Object.defineProperty(exports, "__esModule", { value: true });
 const OfficeParser_js_1 = require("./OfficeParser.js");
+const OfficeGenerator_js_1 = require("./OfficeGenerator.js");
+const fs = __importStar(require("fs"));
 const args = process.argv.slice(2);
 let fileArg;
 let toText = false;
 let verbose = false;
+let outputFormat;
+let outputFile;
 const configArgs = [];
 function isConfigOption(arg) {
     return arg.startsWith('--') && arg.includes('=');
@@ -43,34 +82,75 @@ if (fileArg) {
         const cleanKey = key.replace('--', '');
         const lowerValue = value.toLowerCase();
         const boolValue = lowerValue === 'true' ? true : (lowerValue === 'false' ? false : undefined);
-        if (cleanKey === 'toText') {
-            if (boolValue !== undefined)
-                toText = boolValue;
-            else
-                console.warn(`Invalid value for toText: ${value}`);
+        const knownBooleans = new Set([
+            'toText', 'ocr', 'extractAttachments', 'ignoreNotes', 'putNotesAtLast',
+            'includeRawContent', 'outputErrorToConsole', 'serializeRawContent',
+            'preserveXmlWhitespace', 'includeBreakNodes', 'verbose'
+        ]);
+        if (cleanKey === 'format') {
+            outputFormat = value;
         }
-        else if (cleanKey === 'verbose') {
-            if (boolValue !== undefined)
-                verbose = boolValue;
-            else
-                console.warn(`Invalid value for verbose: ${value}`);
+        else if (cleanKey === 'output') {
+            outputFile = value;
         }
         else {
-            // @ts-ignore
-            if (boolValue !== undefined)
-                config[cleanKey] = boolValue;
-            // @ts-ignore
-            else
+            if (boolValue !== undefined) {
+                if (cleanKey === 'toText')
+                    toText = boolValue;
+                else if (cleanKey === 'verbose') {
+                    verbose = boolValue;
+                    if (verbose)
+                        config.outputErrorToConsole = true;
+                }
+                else {
+                    // @ts-ignore
+                    config[cleanKey] = boolValue;
+                }
+            }
+            else if (knownBooleans.has(cleanKey)) {
+                console.warn(`Invalid boolean value for --${cleanKey}: ${value}. Using default.`);
+            }
+            else {
+                // @ts-ignore
                 config[cleanKey] = value;
+            }
         }
     });
     OfficeParser_js_1.OfficeParser.parseOffice(fileArg, config)
         .then(async (ast) => {
-        if (toText) {
-            process.stdout.write(ast.toText() + '\n');
+        let output;
+        if (outputFormat) {
+            const result = await OfficeGenerator_js_1.OfficeGenerator.generate(ast, outputFormat);
+            if (Array.isArray(result.value)) {
+                output = JSON.stringify(result.value, null, 2);
+            }
+            else {
+                output = result.value;
+            }
+        }
+        else if (toText) {
+            output = ast.toText();
+        }
+        else {
+            output = JSON.stringify(ast, null, 2);
+        }
+        if (outputFile) {
+            if (output instanceof Uint8Array) {
+                fs.writeFileSync(outputFile, output);
+            }
+            else {
+                fs.writeFileSync(outputFile, output, 'utf8');
+            }
+            if (verbose)
+                console.log(`Output written to ${outputFile}`);
         }
         else {
-            process.stdout.write(JSON.stringify(ast, null, 2) + '\n');
+            if (output instanceof Uint8Array) {
+                process.stdout.write(output);
+            }
+            else {
+                process.stdout.write(output + '\n');
+            }
         }
         // Ensure OCR workers are terminated for clean CLI exit
         if (config.ocr) {
@@ -97,7 +177,9 @@ else {
     console.log('Usage: officeparser <file> [--option=value]');
     console.log('');
     console.log('Options:');
-    console.log('  --toText=true                Output plain text instead of JSON AST');
+    console.log('  --format=json|md|html|rtf|csv|text|pdf|chunks  Convert to specified format');
+    console.log('  --output=file.ext            Save output to file instead of stdout');
+    console.log('  --toText=true                Output plain text instead of JSON AST (legacy)');
     console.log('  --ocr=true                   Enable OCR for images');
     console.log('  --ocrLanguage=eng            OCR language (default: eng)');
     console.log('  --extractAttachments=true    Extract embedded attachments');
@@ -111,7 +193,9 @@ else {
     console.log('');
     console.log('Examples:');
     console.log('  officeparser document.docx');
-    console.log('  officeparser document.docx --toText=true');
-    console.log('  officeparser report.pdf --ocr=true --extractAttachments=true');
+    console.log('  officeparser document.docx --format=html --output=doc.html');
+    console.log('  officeparser document.docx --format=md');
+    console.log('  officeparser report.pdf --ocr=true --format=text');
+    console.log('  officeparser data.xlsx --format=csv --output=data.csv');
     console.log('  officeparser complex.docx --serializeRawContent=false --includeRawContent=true');
 }

package/dist/defaults.d.ts

@@ -0,0 +1,41 @@
+import { DeepRequired, DocumentStructureChunkingConfig, FixedSizeChunkingConfig, FullGeneratorConfig, OfficeParserConfig, SemanticChunkingConfig } from './types.js';
+/**
+ * The default regex used for identifying sentence boundaries.
+ * When this default is used, the generator employs a high-fidelity "robust"
+ * segmenter that accounts for common abbreviations (Mr., Dr., etc.).
+ */
+export declare const DEFAULT_SENTENCE_BOUNDARY_REGEX: RegExp;
+/**
+ * Common abbreviations that should not trigger a sentence split when followed by a period.
+ */
+export declare const DEFAULT_ABBREVIATIONS: string[];
+/**
+ * Default configuration for the OfficeParser.
+ */
+export declare const DEFAULT_OFFICE_PARSER_CONFIG: DeepRequired<OfficeParserConfig>;
+/**
+ * Default configuration for Fixed-Size chunking.
+ */
+export declare const DEFAULT_FIXED_SIZE_CHUNKING_CONFIG: Required<Omit<FixedSizeChunkingConfig, 'embeddingFunction' | 'sentenceBoundaryRegex' | 'abbreviations'>> & {
+    sentenceBoundaryRegex: string | RegExp;
+    abbreviations: string[];
+};
+/**
+ * Default configuration for Document-Structure chunking.
+ */
+export declare const DEFAULT_DOCUMENT_STRUCTURE_CHUNKING_CONFIG: Required<Omit<DocumentStructureChunkingConfig, 'sentenceBoundaryRegex' | 'abbreviations'>> & {
+    sentenceBoundaryRegex: string | RegExp;
+    abbreviations: string[];
+};
+/**
+ * Default configuration for Semantic chunking.
+ * Note: `embeddingFunction` has no meaningful default and must be provided by the user.
+ */
+export declare const DEFAULT_SEMANTIC_CHUNKING_CONFIG: Required<Omit<SemanticChunkingConfig, 'embeddingFunction' | 'sentenceBoundaryRegex' | 'abbreviations'>> & {
+    sentenceBoundaryRegex: string | RegExp;
+    abbreviations: string[];
+};
+/**
+ * Default configuration for the OfficeGenerator.
+ */
+export declare const DEFAULT_GENERATOR_CONFIG: FullGeneratorConfig;

package/dist/defaults.js

@@ -0,0 +1,172 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.DEFAULT_GENERATOR_CONFIG = exports.DEFAULT_SEMANTIC_CHUNKING_CONFIG = exports.DEFAULT_DOCUMENT_STRUCTURE_CHUNKING_CONFIG = exports.DEFAULT_FIXED_SIZE_CHUNKING_CONFIG = exports.DEFAULT_OFFICE_PARSER_CONFIG = exports.DEFAULT_ABBREVIATIONS = exports.DEFAULT_SENTENCE_BOUNDARY_REGEX = void 0;
+const PDFJS_VERSION = '5.6.205';
+const DEFAULT_PDF_WORKER_SRC = `https://cdn.jsdelivr.net/npm/pdfjs-dist@${PDFJS_VERSION}/build/pdf.worker.min.mjs`;
+/**
+ * The default regex used for identifying sentence boundaries.
+ * When this default is used, the generator employs a high-fidelity "robust"
+ * segmenter that accounts for common abbreviations (Mr., Dr., etc.).
+ */
+exports.DEFAULT_SENTENCE_BOUNDARY_REGEX = /[.!?。！？]/;
+/**
+ * Common abbreviations that should not trigger a sentence split when followed by a period.
+ */
+exports.DEFAULT_ABBREVIATIONS = ['Mr', 'Dr', 'Ms', 'Inc', 'Ltd', 'Prof', 'Sr', 'Jr', 'vs', 'etc'];
+/**
+ * Default configuration for OCR.
+ */
+const DEFAULT_OCR_CONFIG = {
+    language: 'eng',
+    workerPath: '',
+    corePath: '',
+    langPath: '',
+    autoTerminateTimeout: 10000,
+};
+/**
+ * Default configuration for the OfficeParser.
+ */
+exports.DEFAULT_OFFICE_PARSER_CONFIG = {
+    outputErrorToConsole: false,
+    onWarning: () => { },
+    newlineDelimiter: '\n',
+    ignoreNotes: false,
+    putNotesAtLast: false,
+    extractAttachments: false,
+    includeRawContent: false,
+    ocr: false,
+    ocrLanguage: 'eng',
+    ocrConfig: DEFAULT_OCR_CONFIG,
+    serializeRawContent: true,
+    preserveXmlWhitespace: false,
+    pdfWorkerSrc: DEFAULT_PDF_WORKER_SRC,
+    includeBreakNodes: false,
+    ignoreInternalLinks: false,
+    fileType: null,
+    csvDelimiter: ',',
+};
+/**
+ * Default configuration for HTML generation.
+ */
+const DEFAULT_HTML_GENERATOR_CONFIG = {
+    standalone: true,
+    chartJsSrc: 'https://cdn.jsdelivr.net/npm/chart.js',
+};
+/**
+ * Default configuration for PDF generation.
+ */
+const DEFAULT_PDF_GENERATOR_CONFIG = {
+    format: 'A4',
+    width: '',
+    height: '',
+    landscape: false,
+    printBackground: true,
+    scale: 1,
+    margin: {
+        top: 0,
+        right: 0,
+        bottom: 0,
+        left: 0
+    },
+    displayHeaderFooter: false,
+    headerTemplate: '',
+    footerTemplate: '',
+    launchOptions: {
+        headless: true,
+        args: ['--no-sandbox', '--disable-setuid-sandbox']
+    },
+};
+/**
+ * Default configuration for CSV generation.
+ */
+const DEFAULT_CSV_GENERATOR_CONFIG = {
+    sheets: '',
+    mergeSheets: true,
+    columnDelimiter: ',',
+};
+/**
+ * Default configuration for Markdown generation.
+ */
+const DEFAULT_MD_GENERATOR_CONFIG = {
+    fallbackToHtml: true,
+};
+/**
+ * Default configuration for plain text generation.
+ */
+const DEFAULT_TEXT_GENERATOR_CONFIG = {
+    newlineDelimiter: '\n',
+    preserveLayout: false,
+};
+/**
+ * Default configuration for Fixed-Size chunking.
+ */
+exports.DEFAULT_FIXED_SIZE_CHUNKING_CONFIG = {
+    strategy: 'fixed-size',
+    chunkSize: 1000,
+    chunkOverlap: 200,
+    separators: ['\n\n', '\n', ' ', ''],
+    stripWhitespace: true,
+    includeMetadata: true,
+    addStartIndex: false,
+    lengthFunction: (text) => text.length,
+    sentenceBoundaryRegex: exports.DEFAULT_SENTENCE_BOUNDARY_REGEX,
+    abbreviations: exports.DEFAULT_ABBREVIATIONS,
+};
+/**
+ * Default configuration for Document-Structure chunking.
+ */
+exports.DEFAULT_DOCUMENT_STRUCTURE_CHUNKING_CONFIG = {
+    strategy: 'document-structure',
+    splitBy: 'paragraph',
+    maxChunkSize: 1000,
+    tableSplitStrategy: 'row',
+    stripWhitespace: true,
+    includeMetadata: true,
+    addStartIndex: false,
+    lengthFunction: (text) => text.length,
+    sentenceBoundaryRegex: exports.DEFAULT_SENTENCE_BOUNDARY_REGEX,
+    abbreviations: exports.DEFAULT_ABBREVIATIONS,
+};
+/**
+ * Default configuration for Semantic chunking.
+ * Note: `embeddingFunction` has no meaningful default and must be provided by the user.
+ */
+exports.DEFAULT_SEMANTIC_CHUNKING_CONFIG = {
+    strategy: 'semantic',
+    similarityThreshold: 0.8,
+    maxChunkSize: 2000,
+    bufferSize: 1,
+    embeddingBatchSize: 50,
+    stripWhitespace: true,
+    includeMetadata: true,
+    addStartIndex: false,
+    lengthFunction: (text) => text.length,
+    sentenceBoundaryRegex: exports.DEFAULT_SENTENCE_BOUNDARY_REGEX,
+    abbreviations: exports.DEFAULT_ABBREVIATIONS,
+};
+/**
+ * The resolved default chunking config (uses document-structure as default strategy).
+ */
+const DEFAULT_CHUNKING_CONFIG = exports.DEFAULT_DOCUMENT_STRUCTURE_CHUNKING_CONFIG;
+/**
+ * Default configuration for the OfficeGenerator.
+ */
+exports.DEFAULT_GENERATOR_CONFIG = {
+    onNode: () => { },
+    onWarning: () => { },
+    styleMap: [],
+    includeFormatting: true,
+    generateIds: true,
+    renderMetadata: false,
+    ignoreDefaultStyleMap: false,
+    includeImages: true,
+    includeCharts: true,
+    ignoreInternalLinks: false,
+    htmlConfig: DEFAULT_HTML_GENERATOR_CONFIG,
+    mdConfig: DEFAULT_MD_GENERATOR_CONFIG,
+    pdfConfig: DEFAULT_PDF_GENERATOR_CONFIG,
+    csvConfig: DEFAULT_CSV_GENERATOR_CONFIG,
+    textConfig: DEFAULT_TEXT_GENERATOR_CONFIG,
+    rtfConfig: {},
+    chunksConfig: DEFAULT_CHUNKING_CONFIG,
+};

package/dist/generators/BaseGenerator.d.ts

@@ -0,0 +1,58 @@
+import { OfficeIssue, ConversionResult, FullGeneratorConfig, GeneratorConfig, OfficeContentNode, OfficeParserAST, OfficeWarningType } from '../types.js';
+import { StyleMapper } from '../utils/styleMapper.js';
+/**
+ * Base class for all document generators.
+ * Provides common traversal logic and configuration handling.
+ */
+export declare abstract class BaseGenerator<D extends string = string> {
+    protected destination: D;
+    protected config: FullGeneratorConfig;
+    protected ast: OfficeParserAST;
+    protected messages: OfficeIssue[];
+    protected styleMapper: StyleMapper;
+    constructor(destination: D, ast: OfficeParserAST, config?: GeneratorConfig<D> | FullGeneratorConfig);
+    /**
+     * Retrieves the semantic mapping for a node, respecting the includeFormatting flag.
+     * Per design requirements: Style mapping is bypassed if formatting is disabled.
+     */
+    protected getSemanticMapping(node: OfficeContentNode): {
+        tag: string;
+        classes: string[];
+        attributes: Record<string, string>;
+        fresh: boolean;
+    } | undefined;
+    /**
+     * Entry point for generation.
+     */
+    abstract generate(): Promise<ConversionResult>;
+    /**
+     * Centralized logic for handling the onNode callback.
+     * Evaluates the callback and returns a result that tells the generator how to proceed.
+     *
+     * @returns
+     * - `string`: Use this as the node's output, skip default processing.
+     * - `false`: Skip this node and its subtree.
+     * - `void`: Proceed with default processing.
+     */
+    protected handleOnNode(node: OfficeContentNode): Promise<string | false | void>;
+    /**
+     * Recursively processes nodes and builds output.
+     *
+     * @param node - The current node being processed
+     * @param processor - A function that takes a node and its children's output and returns the node's output string.
+     * @returns The generated string for this node and its subtree.
+     */
+    protected processNodeRecursive(node: OfficeContentNode, processor: (node: OfficeContentNode, childrenOutput: string) => string | Promise<string>): Promise<string>;
+    /**
+     * Helper to generate a unique ID (slug) from text.
+     */
+    protected slugify(text: string): string;
+    /**
+     * Recursively extracts plain text from a node and its children.
+     */
+    protected getNodeText(node: OfficeContentNode): string;
+    /**
+     * Reports a warning to the user and collects it for the final result.
+     */
+    protected warn(type: OfficeWarningType, info?: any, node?: OfficeContentNode): void;
+}