officeparser 7.0.3 → 7.2.0

package/README.md

@@ -100,7 +100,7 @@ npx officeparser document.pdf --format=chunks
 |------|--------|---------|-------------|
 | `--format` | `json\|text\|md\|html\|csv\|rtf\|pdf\|chunks` | `json` | Output format |
 | `--output` | path | — | Write output to a file |
-| `--toText` | `true\|false` | `false` | **Deprecated.** Use `--format=text` |
+| ~~`--toText`~~ | `true\|false` | `false` | **Deprecated.** Use `--format=text` |
 | `--ignoreNotes` | `true\|false` | `false` | Ignore speaker notes (PPTX/ODP) |
 | `--putNotesAtLast` | `true\|false` | `false` | Collect notes at end of output |
 | `--newlineDelimiter` | string | `\n` | Delimiter between lines |
@@ -108,7 +108,7 @@ npx officeparser document.pdf --format=chunks
 | `--ocr` | `true\|false` | `false` | Enable OCR for images |
 | `--includeRawContent` | `true\|false` | `false` | Include raw XML/RTF in nodes |
 | `--includeBreakNodes` | `true\|false` | `false` | Include break nodes (DOCX only) |
-| `--outputErrorToConsole` | `true\|false` | `false` | **Deprecated.** Use `onWarning` callback |
+| ~~`--outputErrorToConsole`~~ | `true\|false` | `false` | **Deprecated.** Use `onWarning` callback |
 | `--verbose` | `true\|false` | `false` | Show full error stack traces |
 
 ---
@@ -178,6 +178,60 @@ const ast = await officeParser.parseOffice(buffer);
 > const ast = await officeParser.parseOffice(markdownBuffer, { fileType: 'md' });
 > ```
 
+### Cancellation with AbortSignal
+
+You can pass a standard `AbortSignal` (e.g. from an `AbortController`) to cancel an active parse operation. This is especially useful for setting request-level timeouts or canceling long-running parses (like large PDFs with OCR).
+
+```js
+const controller = new AbortController();
+
+// Cancel parsing if it takes longer than 5 seconds
+setTimeout(() => controller.abort(), 5000);
+
+try {
+    const ast = await officeParser.parseOffice('large_scanned_file.pdf', {
+        abortSignal: controller.signal,
+        ocr: true
+    });
+} catch (err) {
+    if (err.name === 'AbortError') {
+        console.log('Parsing was cancelled.');
+    } else {
+        console.error('Parsing failed:', err);
+    }
+}
+```
+
+> [!IMPORTANT]
+> **AbortError Propagation**
+> When parsing is cancelled via `AbortSignal`, the parser rejects with a standard `AbortError` (a `DOMException` or an Error with `name: 'AbortError'`).
+> This error is *not* wrapped in standard OfficeParser error types so that you can reliably detect cancellation using `error.name === 'AbortError'`.
+
+> [!NOTE]
+> **Worker Cleanup on Abort**
+> If an OCR job is actively running in the background when the signal is aborted, `officeParser` automatically terminates the Tesseract worker process immediately and removes it from the pool to prevent thread/memory leaks.
+
+### Custom OCR Timeouts
+
+To prevent the parser from hanging indefinitely due to slow network connections (when downloading Tesseract language datasets) or complex image processing, you can configure granular timeouts under `ocrConfig.timeout`.
+
+```js
+const ast = await officeParser.parseOffice('scanned_document.pdf', {
+    ocr: true,
+    ocrConfig: {
+        timeout: {
+            workerLoad: 30000,    // 30s max to load worker & download language training files
+            recognition: 15000,   // 15s max per image text recognition
+            autoTerminate: 10000  // 10s of inactivity before terminating idle workers
+        }
+    }
+});
+```
+
+> [!TIP]
+> **Non-Fatal Timeout Recovery**
+> If `workerLoad` or `recognition` timeouts are exceeded, the parser will log a warning in `ast.warnings` and **continue parsing the rest of the document**. The overall promise resolves successfully with the text extracted from the document layers (rather than failing the entire parse).
+
 ### `ast.to()` — Generate from AST
 
 The preferred way to convert a parsed AST to another format. Returns a `ConversionResult`.
@@ -366,13 +420,19 @@ interface OfficeChunk {
 ```text
 OfficeParserAST
 ├── type: 'docx' | 'pdf' | 'xlsx' | 'csv' | 'md' | ...  (11 formats)
-├── metadata: { author, title, created, modified, customProperties, styleMap, ... }
+├── metadata: { author, title, created, modified, keywords, customProperties, nativeProperties, styleMap, ... }
 ├── content: [ OfficeContentNode ]
-│   ├── type: 'paragraph' | 'heading' | 'table' | 'list' | 'image' | 'chart' | ...
+│   ├── type: 'paragraph' | 'heading' | 'table' | 'list' | 'image' | 'chart' | 'comment' | ...
 │   ├── text: string  (concatenated text of node + all descendants)
-│   ├── children: [ OfficeContentNode ]  (recursive)
+│   ├── children: [ OfficeContentNode ]  (recursive structural children)
+│   ├── notes: [ OfficeContentNode ]     (footnotes/endnotes/slide notes attached to this node)
+│   ├── comments: [ OfficeContentNode ] (inline comments attached to this node)
 │   ├── formatting: { bold, italic, underline, color, size, font, alignment, ... }
-│   └── metadata: { level, listId, row, col, rowSpan, colSpan, style, ... }
+│   └── metadata: { level, listId, row, col, rowSpan, colSpan, backgroundColor, style, ... }
+├── auxiliary?: OfficeAuxiliaryContent   (out-of-band layout elements)
+│   ├── headers?: OfficeContentNode[]   (DOCX headers)
+│   ├── footers?: OfficeContentNode[]   (DOCX footers)
+│   └── slideMasters?: OfficeContentNode[] (PPTX slide masters)
 ├── attachments: [ OfficeAttachment ]  (populated when extractAttachments: true)
 │   ├── type: 'image' | 'chart'
 │   ├── name: string
@@ -382,7 +442,7 @@ OfficeParserAST
 │   └── chartData?: { title, dataSets, labels }
 ├── warnings: OfficeIssue[]  (non-fatal issues from the parsing phase)
 ├── to(format, config?)  (format: 'html'|'md'|'text'|'csv'|'rtf'|'pdf'|'chunks', returns { value, messages })
-└── toText()             (Deprecated: use .to('text') instead)
+└── ~~toText()~~             (Deprecated: use .to('text') instead)
 ```
 
 ### `OfficeIssue` — Warning / Error Object
@@ -498,17 +558,21 @@ ast.metadata = {
     created?: Date
     modified?: Date
     description?: string
-    customProperties?: Record<string, any>  // user-defined metadata from the document
-    styleMap?: Record<string, TextFormatting>  // named styles → formatting definitions
-    formatting?: TextFormatting              // document-wide defaults
+    keywords?: string                            // NEW: Keywords from document properties
+    customProperties?: Record<string, any>       // User-defined metadata from the document
+    nativeProperties?: Record<string, any>       // NEW: All format-specific raw metadata
+    styleMap?: Record<string, TextFormatting>    // Named styles → formatting definitions
+    formatting?: TextFormatting                  // Document-wide defaults
 }
 ```
 
-**Accessing custom properties:**
+**Accessing native properties (format-specific metadata):**
 ```js
 const ast = await officeParser.parseOffice('contract.docx');
-console.log(ast.metadata.customProperties);
-// { "ProjectID": "ABC-123", "InternalReview": true }
+console.log(ast.metadata.nativeProperties);
+// DOCX: { Pages: 5, Application: 'Microsoft Word' }
+// HTML: { description: 'My page', 'og:title': 'Title' }
+// PDF:  { Title: 'Report', XMP: { ... } }
 ```
 
 ---
@@ -532,6 +596,61 @@ const headings = ast.content.filter(n => n.type === 'heading' && n.metadata?.lev
 console.log(headings.map(h => h.text));
 ```
 
+### Extract comments
+```ts
+// Comments can be attached to any nested node, so we must traverse recursively
+const printComments = (nodes: OfficeContentNode[]) => {
+    nodes.forEach(node => {
+        if (node.comments) {
+            node.comments.forEach(c => {
+                console.log(`Comment by ${c.metadata?.author}: ${c.text}`);
+            });
+        }
+        if (node.children) {
+            printComments(node.children);
+        }
+    });
+};
+
+printComments(ast.content);
+```
+
+Set `ignoreComments: true` to skip extraction.
+
+### Extract footnotes, endnotes & slide notes
+```ts
+// Slide speaker notes (PPTX) live on the slide node itself
+const slide = ast.content.find(n => n.type === 'slide');
+console.log(slide?.notes?.map(n => n.text));
+
+// Footnotes and endnotes (DOCX/RTF) can be deeply nested, so we traverse recursively:
+const printNotes = (nodes: OfficeContentNode[]) => {
+    nodes.forEach(node => {
+        if (node.notes) {
+            node.notes.forEach(note => console.log(note.text));
+        }
+        if (node.children) {
+            printNotes(node.children);
+        }
+    });
+};
+
+printNotes(ast.content);
+```
+
+> [!IMPORTANT]
+> `putNotesAtLast` is **deprecated**. Notes are always attached via `node.notes` — this flag has no effect and will be removed in a future major version.
+
+### Access headers, footers & slide masters
+```ts
+// These are NOT in ast.content — use ast.auxiliary
+console.log(ast.auxiliary?.headers?.map(h => h.text));   // DOCX headers
+console.log(ast.auxiliary?.footers?.map(f => f.text));   // DOCX footers
+console.log(ast.auxiliary?.slideMasters?.length);         // PPTX slide masters
+```
+
+Set `ignoreHeadersAndFooters: true` or `ignoreSlideMasters: true` to skip extraction.
+
 ### Extract images with OCR text
 ```js
 const ast = await officeParser.parseOffice('report.docx', { extractAttachments: true, ocr: true });
@@ -596,8 +715,11 @@ Pass as the second argument to `parseOffice(file, config)`.
 | Option | Type | Default | Description |
 |--------|------|---------|-------------|
 | `newlineDelimiter` | `string` | `'\n'` | Delimiter inserted between lines in text output |
-| `ignoreNotes` | `boolean` | `false` | Ignore speaker notes (PPTX/ODP) |
-| `putNotesAtLast` | `boolean` | `false` | Collect all notes at the end instead of inline |
+| `ignoreNotes` | `boolean` | `false` | Ignore footnotes/endnotes (DOCX, RTF) and speaker notes (PPTX/ODP) |
+| `ignoreComments` | `boolean` | `false` | **New**: Ignore inline comments/annotations (DOCX, XLSX, PPTX) — by default attached via `node.comments[]` |
+| `ignoreHeadersAndFooters` | `boolean` | `false` | **New**: Skip DOCX headers & footers (populated in `ast.auxiliary.headers/footers` by default) |
+| `ignoreSlideMasters` | `boolean` | `false` | **New**: Skip PPTX slide masters (populated in `ast.auxiliary.slideMasters` by default) |
+| ~~`putNotesAtLast`~~ | `boolean` | `false` | **Deprecated**: Notes are now attached via `node.notes[]`. This flag has no effect |
 | `extractAttachments` | `boolean` | `false` | Populate `ast.attachments` with Base64 images/charts |
 | `ocr` | `boolean` | `false` | Run Tesseract OCR on images (requires `extractAttachments: true`) |
 | `ocrConfig` | `OcrConfig` | `{}` | OCR worker pool settings — see [OCR section](#ocr-scheduler--resource-management) |
@@ -610,7 +732,8 @@ Pass as the second argument to `parseOffice(file, config)`.
 | `csvDelimiter` | `string` | `','` | Input delimiter when parsing CSV files |
 | `pdfWorkerSrc` | `string` | CDN (jsDelivr) | Path/URL to `pdf.worker.min.mjs` (required in browser) |
 | `onWarning` | `(issue: OfficeIssue) => void` | — | Callback for non-fatal parsing issues |
-| `outputErrorToConsole` | `boolean` | `false` | **Deprecated.** Use `onWarning` instead |
+| `abortSignal` | `AbortSignal \| null` | `null` | Optional signal to cancel parsing (rejects with AbortError) |
+| ~~`outputErrorToConsole`~~ | `boolean` | `false` | **Deprecated.** Use `onWarning` instead |
 
 ---
 
@@ -630,6 +753,7 @@ Options shared by all generator formats. Pass to `OfficeGenerator.generate(ast,
 | `styleMap` | `string[] \| StructuredStyleMapping[]` | `[]` | Custom semantic style mappings |
 | `onNode` | `(node) => string \| false \| void` | — | Per-node callback for filtering, overriding, or mutating |
 | `onWarning` | `(issue: OfficeIssue) => void` | — | Callback for non-fatal generation issues |
+| `abortSignal` | `AbortSignal \| null` | `null` | Optional signal to cancel the generation operation (rejects with AbortError) |
 
 ---
 
@@ -708,6 +832,12 @@ Pass as `htmlConfig` inside `GeneratorConfig`.
 |--------|------|---------|-------------|
 | `standalone` | `boolean` | `true` | Wrap output in a full `<html>` document with CSS |
 | `chartJsSrc` | `string` | jsDelivr CDN | URL for the Chart.js library |
+| `containerWidth` | `string \| number` | `'auto'` | Max width of the content container. Positive number (px), CSS length string (`'900px'`, `'100%'`, `'60vw'`), or `'auto'`. Invalid values fall back to `'auto'` with an `INVALID_CONTAINER_WIDTH` warning |
+| `customCss` | `string` | `''` | Raw CSS injected into the `<style>` block — use to override built-in styles |
+| `injections.headStart` | `string` | `''` | Raw HTML injected after `<head>` |
+| `injections.headEnd` | `string` | `''` | Raw HTML injected before `</head>` |
+| `injections.bodyStart` | `string` | `''` | Raw HTML injected after `<body>` |
+| `injections.bodyEnd` | `string` | `''` | Raw HTML injected before `</body>` |
 
 ### MdGeneratorConfig
 
@@ -724,6 +854,8 @@ Pass as `pdfConfig` inside `GeneratorConfig`. Requires the optional `puppeteer`
 | Option | Type | Default | Description |
 |--------|------|---------|-------------|
 | `format` | `string` | `'A4'` | Paper format (`'A4'`, `'Letter'`, `'Legal'`, etc.) |
+| `width` | `string \| number` | `''` | Paper width (e.g., `'5in'`, `'3cm'`) or pixels |
+| `height` | `string \| number` | `''` | Paper height (e.g., `'5in'`, `'3cm'`) or pixels |
 | `landscape` | `boolean` | `false` | Landscape page orientation |
 | `printBackground` | `boolean` | `true` | Print background graphics |
 | `margin` | `object` | `{0,0,0,0}` | Page margins (`top`, `right`, `bottom`, `left`) |
@@ -732,6 +864,7 @@ Pass as `pdfConfig` inside `GeneratorConfig`. Requires the optional `puppeteer`
 | `footerTemplate` | `string` | `''` | HTML template for the print footer |
 | `scale` | `number` | `1` | Rendering scale factor |
 | `launchOptions` | `object` | headless defaults | Puppeteer launch options (e.g., `executablePath`) |
+| `timeout` | `number` | `30000` | PDF rendering timeout in milliseconds. Set to `0` to disable. |
 
 ### CsvGeneratorConfig
 
@@ -807,6 +940,7 @@ Configuration for `OfficeConverter.convert(file, format, config)`.
 | `maxChunkSize` | `number` | `2000` | Max characters even if similarity stays high |
 | `bufferSize` | `number` | `1` | Surrounding sentences used when computing similarity |
 | `embeddingBatchSize` | `number` | `50` | Sentences per embedding API batch |
+| `timeout` | `number` | `10000` | Timeout in milliseconds for individual embedding API calls. Set to `0` to disable. |
 
 ---
 
@@ -826,7 +960,8 @@ When `ocr: true` is set, `officeParser` maintains an intelligent **Smart Worker
 | `workerPath` | `string` | `''` | Custom path to Tesseract worker script |
 | `corePath` | `string` | `''` | Custom path to Tesseract core script |
 | `langPath` | `string` | `''` | Custom path for language data files |
-| `autoTerminateTimeout` | `number` | `10000` | Inactivity timeout in ms before auto-teardown (0 = disabled) |
+| `timeout` | `OcrTimeoutConfig` | `{}` | Consolidated timeouts: `autoTerminate`, `workerLoad`, `recognition` |
+| ~~`autoTerminateTimeout`~~ | `number` | `10000` | **Deprecated.** Use `timeout.autoTerminate` instead |
 
 See all language codes at [tesseract-ocr.github.io](https://tesseract-ocr.github.io/tessdoc/Data-Files).
 
@@ -927,7 +1062,6 @@ For a full debugging guide, visit the [Live Documentation](https://harshankur.gi
 
 1. **ODT/ODS Charts**: May show inaccurate data when the chart references external cell ranges or uses complex layout-based data.
 2. **PDF Images (Browser)**: Extracted as BMP files for cross-platform compatibility. Conversion is automatic.
-3. **RTF Notes**: `putNotesAtLast` has no effect for RTF files; footnotes and endnotes are always appended at the end.
 
 ---
 

package/dist/OfficeGenerator.d.ts

@@ -15,5 +15,5 @@ export declare class OfficeGenerator {
      */
     static generate<T extends SupportedFileType, D extends SupportedDestination<T>>(ast: OfficeParserAST & {
         type: T;
-    }, destination: D, config?: GeneratorConfig<D>): Promise<ConversionResult>;
+    }, destination: D, config?: GeneratorConfig<D>): Promise<ConversionResult<D>>;
 }

package/dist/OfficeGenerator.js

@@ -25,24 +25,33 @@ class OfficeGenerator {
      * @throws {Error} If the destination format is unsupported
      */
     static async generate(ast, destination, config) {
+        let generator;
         switch (destination.toLowerCase()) {
             case 'text':
-                return new TextGenerator_js_1.TextGenerator(ast, config).generate();
+                generator = new TextGenerator_js_1.TextGenerator(ast, config);
+                break;
             case 'md':
-                return new MarkdownGenerator_js_1.MarkdownGenerator(ast, config).generate();
+                generator = new MarkdownGenerator_js_1.MarkdownGenerator(ast, config);
+                break;
             case 'html':
-                return new HtmlGenerator_js_1.HtmlGenerator(ast, config).generate();
+                generator = new HtmlGenerator_js_1.HtmlGenerator(ast, config);
+                break;
             case 'pdf':
-                return new PdfGenerator_js_1.PdfGenerator(ast, config).generate();
+                generator = new PdfGenerator_js_1.PdfGenerator(ast, config);
+                break;
             case 'csv':
-                return new CsvGenerator_js_1.CsvGenerator(ast, config).generate();
+                generator = new CsvGenerator_js_1.CsvGenerator(ast, config);
+                break;
             case 'rtf':
-                return new RtfGenerator_js_1.RtfGenerator(ast, config).generate();
+                generator = new RtfGenerator_js_1.RtfGenerator(ast, config);
+                break;
             case 'chunks':
-                return new ChunkingGenerator_js_1.ChunkingGenerator(ast, config).generate();
+                generator = new ChunkingGenerator_js_1.ChunkingGenerator(ast, config);
+                break;
             default:
                 throw (0, errorUtils_js_1.getOfficeError)(types_js_1.OfficeErrorType.EXTENSION_UNSUPPORTED, undefined, destination);
         }
+        return generator.generate();
     }
 }
 exports.OfficeGenerator = OfficeGenerator;

package/dist/OfficeParser.js

@@ -241,6 +241,12 @@ class OfficeParser {
             return result;
         }
         catch (error) {
+            // AbortError must pass through untouched so callers can distinguish a
+            // deliberate cancellation (err.name === 'AbortError') from a real parse failure.
+            // getWrappedError always creates a plain new Error(), which would strip the
+            // AbortError identity and break any instanceof / name checks on the caller side.
+            if (error?.name === 'AbortError')
+                throw error;
             const wrappedError = (0, errorUtils_js_1.getWrappedError)(error, internalConfig, filePath);
             if (callback)
                 callback(undefined, wrappedError);

package/dist/cli.d.ts

@@ -15,6 +15,10 @@
  *   --ocrLanguage=eng         OCR language (default: eng)
  *   --extractAttachments=true Extract embedded attachments
  *   --ignoreNotes=true        Ignore footnotes/endnotes
+ *   --ignoreComments=true     Ignore inline comments
+ *   --ignoreHeadersAndFooters=true Ignore headers and footers
+ *   --ignoreSlideMasters=true Ignore slide masters
+ *   --ignoreInternalLinks=true Ignore internal links
  *   --putNotesAtLast=true     Move notes to end of document
  *   --includeRawContent=true  Include raw content in AST
  *   --outputErrorToConsole=true  Log errors to console

package/dist/cli.js

@@ -16,6 +16,10 @@
  *   --ocrLanguage=eng         OCR language (default: eng)
  *   --extractAttachments=true Extract embedded attachments
  *   --ignoreNotes=true        Ignore footnotes/endnotes
+ *   --ignoreComments=true     Ignore inline comments
+ *   --ignoreHeadersAndFooters=true Ignore headers and footers
+ *   --ignoreSlideMasters=true Ignore slide masters
+ *   --ignoreInternalLinks=true Ignore internal links
  *   --putNotesAtLast=true     Move notes to end of document
  *   --includeRawContent=true  Include raw content in AST
  *   --outputErrorToConsole=true  Log errors to console
@@ -83,9 +87,10 @@ if (fileArg) {
         const lowerValue = value.toLowerCase();
         const boolValue = lowerValue === 'true' ? true : (lowerValue === 'false' ? false : undefined);
         const knownBooleans = new Set([
-            'toText', 'ocr', 'extractAttachments', 'ignoreNotes', 'putNotesAtLast',
-            'includeRawContent', 'outputErrorToConsole', 'serializeRawContent',
-            'preserveXmlWhitespace', 'includeBreakNodes', 'verbose'
+            'toText', 'ocr', 'extractAttachments', 'ignoreNotes', 'ignoreComments',
+            'ignoreHeadersAndFooters', 'ignoreSlideMasters', 'ignoreInternalLinks',
+            'putNotesAtLast', 'includeRawContent', 'outputErrorToConsole',
+            'serializeRawContent', 'preserveXmlWhitespace', 'includeBreakNodes', 'verbose'
         ]);
         if (cleanKey === 'format') {
             outputFormat = value;
@@ -184,6 +189,10 @@ else {
     console.log('  --ocrLanguage=eng            OCR language (default: eng)');
     console.log('  --extractAttachments=true    Extract embedded attachments');
     console.log('  --ignoreNotes=true           Ignore footnotes/endnotes');
+    console.log('  --ignoreComments=true        Ignore inline comments');
+    console.log('  --ignoreHeadersAndFooters=true Ignore headers and footers');
+    console.log('  --ignoreSlideMasters=true    Ignore slide masters');
+    console.log('  --ignoreInternalLinks=true   Ignore internal links');
     console.log('  --putNotesAtLast=true        Move notes to end of document');
     console.log('  --includeRawContent=true     Include raw content in AST');
     console.log('  --serializeRawContent=true   Serialize raw XML content (default: true)');

package/dist/defaults.js

@@ -13,6 +13,12 @@ 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 timeout values for OCR */
+const DEFAULT_OCR_TIMEOUT = {
+    autoTerminate: 10000,
+    workerLoad: 60000,
+    recognition: 30000,
+};
 /**
  * Default configuration for OCR.
  */
@@ -21,7 +27,12 @@ const DEFAULT_OCR_CONFIG = {
     workerPath: '',
     corePath: '',
     langPath: '',
-    autoTerminateTimeout: 10000,
+    // Preferred: consolidated timeout object.  New code should always read from here.
+    timeout: DEFAULT_OCR_TIMEOUT,
+    // Kept for backward compatibility.  When timeout.autoTerminate is set (as above),
+    // the ocrUtils resolution logic will prefer timeout.autoTerminate over this flat field.
+    autoTerminateTimeout: DEFAULT_OCR_TIMEOUT.autoTerminate,
+    abortSignal: null,
 };
 /**
  * Default configuration for the OfficeParser.
@@ -31,12 +42,16 @@ exports.DEFAULT_OFFICE_PARSER_CONFIG = {
     onWarning: () => { },
     newlineDelimiter: '\n',
     ignoreNotes: false,
+    ignoreComments: false,
+    ignoreHeadersAndFooters: false,
+    ignoreSlideMasters: false,
     putNotesAtLast: false,
     extractAttachments: false,
     includeRawContent: false,
     ocr: false,
     ocrLanguage: 'eng',
     ocrConfig: DEFAULT_OCR_CONFIG,
+    abortSignal: null,
     serializeRawContent: true,
     preserveXmlWhitespace: false,
     pdfWorkerSrc: DEFAULT_PDF_WORKER_SRC,
@@ -51,6 +66,14 @@ exports.DEFAULT_OFFICE_PARSER_CONFIG = {
 const DEFAULT_HTML_GENERATOR_CONFIG = {
     standalone: true,
     chartJsSrc: 'https://cdn.jsdelivr.net/npm/chart.js',
+    containerWidth: 'auto',
+    customCss: '',
+    injections: {
+        headStart: '',
+        headEnd: '',
+        bodyStart: '',
+        bodyEnd: '',
+    }
 };
 /**
  * Default configuration for PDF generation.
@@ -75,6 +98,7 @@ const DEFAULT_PDF_GENERATOR_CONFIG = {
         headless: true,
         args: ['--no-sandbox', '--disable-setuid-sandbox']
     },
+    timeout: 30000,
 };
 /**
  * Default configuration for CSV generation.
@@ -143,6 +167,7 @@ exports.DEFAULT_SEMANTIC_CHUNKING_CONFIG = {
     lengthFunction: (text) => text.length,
     sentenceBoundaryRegex: exports.DEFAULT_SENTENCE_BOUNDARY_REGEX,
     abbreviations: exports.DEFAULT_ABBREVIATIONS,
+    timeout: 10000,
 };
 /**
  * The resolved default chunking config (uses document-structure as default strategy).
@@ -162,6 +187,7 @@ exports.DEFAULT_GENERATOR_CONFIG = {
     includeImages: true,
     includeCharts: true,
     ignoreInternalLinks: false,
+    abortSignal: null,
     htmlConfig: DEFAULT_HTML_GENERATOR_CONFIG,
     mdConfig: DEFAULT_MD_GENERATOR_CONFIG,
     pdfConfig: DEFAULT_PDF_GENERATOR_CONFIG,

package/dist/generators/BaseGenerator.d.ts

@@ -1,10 +1,10 @@
-import { OfficeIssue, ConversionResult, FullGeneratorConfig, GeneratorConfig, OfficeContentNode, OfficeParserAST, OfficeWarningType } from '../types.js';
+import { OfficeIssue, ConversionResult, FullGeneratorConfig, GeneratorConfig, OfficeContentNode, OfficeParserAST, OfficeWarningType, UniversalGeneratorFormat } 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> {
+export declare abstract class BaseGenerator<D extends UniversalGeneratorFormat = UniversalGeneratorFormat> {
     protected destination: D;
     protected config: FullGeneratorConfig;
     protected ast: OfficeParserAST;
@@ -24,7 +24,7 @@ export declare abstract class BaseGenerator<D extends string = string> {
     /**
      * Entry point for generation.
      */
-    abstract generate(): Promise<ConversionResult>;
+    abstract generate(): Promise<ConversionResult<D>>;
     /**
      * Centralized logic for handling the onNode callback.
      * Evaluates the callback and returns a result that tells the generator how to proceed.

package/dist/generators/ChunkingGenerator.js

@@ -39,6 +39,7 @@ class ChunkingGenerator extends BaseGenerator_js_1.BaseGenerator {
      * Note: ConversionResult.value is a JSON string of OfficeChunk[] for the 'chunks' destination.
      */
     async generate() {
+        (0, errorUtils_js_1.checkAbortSignal)(this.config.abortSignal);
         let chunks;
         switch (this.chunkConfig.strategy) {
             case 'fixed-size':
@@ -186,6 +187,7 @@ class ChunkingGenerator extends BaseGenerator_js_1.BaseGenerator {
         return this.finalizeChunks(chunks, config);
     }
     async processNodeForStructure(node, config, splitBy, maxChunkSize, measure, chunks, contextStack) {
+        (0, errorUtils_js_1.checkAbortSignal)(this.config.abortSignal);
         // Check for node override or skip
         const override = await this.handleOnNode(node);
         if (override === false)
@@ -391,7 +393,14 @@ class ChunkingGenerator extends BaseGenerator_js_1.BaseGenerator {
                 renderedRows.push(row.text ?? '');
                 continue;
             }
-            const cells = row.children.map(cell => (cell.text ?? '').replace(/\n/g, ' ').trim());
+            const getCellText = (cell) => {
+                if (cell.text)
+                    return cell.text;
+                if (!cell.children || cell.children.length === 0)
+                    return '';
+                return cell.children.map(c => getCellText(c)).join(' ');
+            };
+            const cells = row.children.map(cell => getCellText(cell).replace(/\n/g, ' ').trim());
             renderedRows.push(`| ${cells.join(' | ')} |`);
         }
         return renderedRows.join('\n');
@@ -412,7 +421,7 @@ class ChunkingGenerator extends BaseGenerator_js_1.BaseGenerator {
         if (sentences.length === 0)
             return [];
         // Embed all sentences in batches to avoid rate limiting
-        const embeddings = await this.batchEmbeddings(sentences, config.embeddingFunction, batchSize);
+        const embeddings = await this.batchEmbeddings(sentences, config.embeddingFunction, batchSize, config.timeout);
         // Calculate cosine similarity between adjacent sentence windows
         const chunks = [];
         let currentSentences = [];
@@ -479,6 +488,7 @@ class ChunkingGenerator extends BaseGenerator_js_1.BaseGenerator {
         let currentPage;
         let currentSheet;
         const walk = async (node) => {
+            (0, errorUtils_js_1.checkAbortSignal)(this.config.abortSignal);
             const override = await this.handleOnNode(node);
             if (override === false)
                 return;
@@ -533,6 +543,7 @@ class ChunkingGenerator extends BaseGenerator_js_1.BaseGenerator {
         let currentPage;
         let currentSheet;
         const walk = async (node) => {
+            (0, errorUtils_js_1.checkAbortSignal)(this.config.abortSignal);
             const override = await this.handleOnNode(node);
             if (override === false)
                 return;
@@ -602,11 +613,27 @@ class ChunkingGenerator extends BaseGenerator_js_1.BaseGenerator {
     /**
      * Helper to process embeddings in sequential batches to avoid API rate limits and memory issues.
      */
-    async batchEmbeddings(sentences, embedFn, batchSize = 50) {
+    async batchEmbeddings(sentences, embedFn, batchSize = 50, timeoutMs) {
         const results = [];
         for (let i = 0; i < sentences.length; i += batchSize) {
+            (0, errorUtils_js_1.checkAbortSignal)(this.config.abortSignal);
             const batch = sentences.slice(i, i + batchSize);
-            const batchResults = await Promise.all(batch.map(s => embedFn(s.text)));
+            const batchPromises = batch.map(s => {
+                const call = embedFn(s.text);
+                if (timeoutMs !== undefined && timeoutMs > 0) {
+                    let timerId;
+                    const timeoutPromise = new Promise((_, reject) => {
+                        timerId = setTimeout(() => {
+                            reject(new Error(`Embedding call timed out after ${timeoutMs}ms`));
+                        }, timeoutMs);
+                    });
+                    return Promise.race([call, timeoutPromise]).finally(() => {
+                        clearTimeout(timerId);
+                    });
+                }
+                return call;
+            });
+            const batchResults = await Promise.all(batchPromises);
             results.push(...batchResults);
         }
         return results;

package/dist/generators/CsvGenerator.d.ts

@@ -10,7 +10,7 @@ export declare class CsvGenerator extends BaseGenerator<'csv'> {
      *
      * @returns A CSV string or a ZIP archive containing multiple CSVs
      */
-    generate(): Promise<ConversionResult>;
+    generate(): Promise<ConversionResult<'csv'>>;
     /**
      * Recursively finds all nodes that can be treated as sheets (sheet or table).
      */

package/dist/generators/HtmlGenerator.d.ts

@@ -12,7 +12,7 @@ export declare class HtmlGenerator extends BaseGenerator<'html'> {
      *
      * @returns An HTML string
      */
-    generate(): Promise<ConversionResult>;
+    generate(): Promise<ConversionResult<'html'>>;
     private renderMetaTags;
     private renderMetadataSummary;
     /**
@@ -33,5 +33,6 @@ export declare class HtmlGenerator extends BaseGenerator<'html'> {
     private getInlineStyles;
     private getPremiumStyles;
     protected slugify(text: string): string;
+    private getColumnLetter;
     private escape;
 }