officeparser 7.2.0 → 7.2.2

package/dist/generators/RtfGenerator.js

@@ -221,6 +221,12 @@ class RtfGenerator extends BaseGenerator_js_1.BaseGenerator {
         for (const node of ast.content) {
             body += await this.processNodeRecursive(node, processor);
         }
+        if (this.collectedNotes.length > 0) {
+            body += '\\pard\\sb120\\sa120\\keepn{\\b Notes:}\\par\n';
+            for (const note of this.collectedNotes) {
+                body += await this.processNodeRecursive(note, processor);
+            }
+        }
         return body;
     }
     getColorIndex(hex) {

package/dist/generators/TextGenerator.js

@@ -62,6 +62,12 @@ class TextGenerator extends BaseGenerator_js_1.BaseGenerator {
         for (const node of this.ast.content) {
             output += await this.processNodeRecursive(node, processor);
         }
+        if (this.collectedNotes.length > 0) {
+            output += `${newline}${newline}--- Notes ---${newline}`;
+            for (const note of this.collectedNotes) {
+                output += await this.processNodeRecursive(note, processor);
+            }
+        }
         return {
             value: output.trim(),
             messages: this.messages

package/dist/officeparser.browser.d.ts

@@ -7,6 +7,8 @@
 export declare enum OfficeErrorType {
 	/** Unsupported file extension */
 	EXTENSION_UNSUPPORTED = "EXTENSION_UNSUPPORTED",
+	/** Unsupported output generator format */
+	FORMAT_UNSUPPORTED = "FORMAT_UNSUPPORTED",
 	/** File appears to be corrupted or malformed */
 	FILE_CORRUPTED = "FILE_CORRUPTED",
 	/** File could not be found at the specified path */
@@ -32,7 +34,15 @@ export declare enum OfficeErrorType {
 	/** Semantic chunking strategy is selected but no embedding function is provided */
 	MISSING_EMBEDDING_FUNCTION = "MISSING_EMBEDDING_FUNCTION",
 	/** The operation was aborted */
-	OPERATION_ABORTED = "OPERATION_ABORTED"
+	OPERATION_ABORTED = "OPERATION_ABORTED",
+	/** ZIP entry count exceeds limit */
+	ZIP_ENTRY_COUNT_LIMIT_EXCEEDED = "ZIP_ENTRY_COUNT_LIMIT_EXCEEDED",
+	/** ZIP entry missing a valid declared size */
+	ZIP_ENTRY_INVALID_SIZE = "ZIP_ENTRY_INVALID_SIZE",
+	/** ZIP uncompressed size limit exceeded */
+	ZIP_SIZE_LIMIT_EXCEEDED = "ZIP_SIZE_LIMIT_EXCEEDED",
+	/** Embedding call timed out */
+	EMBEDDING_TIMEOUT = "EMBEDDING_TIMEOUT"
 }
 /**
  * Standard warning types for OfficeParser.
@@ -347,6 +357,28 @@ export interface OfficeParserConfig {
 	 * Defaults to ',' but can be overridden (e.g., ';', '\t').
 	 */
 	csvDelimiter?: string;
+	/**
+	 * Limits and checks applied during ZIP extraction to protect against excessive
+	 * memory and resource usage.
+	 */
+	decompressionLimits?: DecompressionLimits;
+}
+/**
+ * Limits applied to ZIP archive decompression.
+ */
+export interface DecompressionLimits {
+	/**
+	 * Maximum allowed total uncompressed size (in bytes) of files extracted from a ZIP archive.
+	 * Applies to OOXML (DOCX, XLSX, PPTX) and ODF (ODT, ODP, ODS) formats.
+	 * Default is 536870912 (512 MB).
+	 */
+	maxUncompressedBytes?: number;
+	/**
+	 * Maximum allowed number of entries (files and directories) in a ZIP archive.
+	 * Applies to OOXML (DOCX, XLSX, PPTX) and ODF (ODT, ODP, ODS) formats.
+	 * Default is 10000.
+	 */
+	maxZipEntries?: number;
 }
 /**
  * Represents a single issue (warning, error, or info) generated during document processing.
@@ -397,7 +429,7 @@ export interface CommonGeneratorConfig {
 	 * 1. **Filter/Remove Nodes**: Return `false` to skip a node and all its children.
 	 * 2. **Override Rendering**: Return a `string` to use that exact text as the output, bypassing default logic and recursion.
 	 * 3. **Mutate Nodes**: Modify the `node` object directly (e.g., changing `node.text`) and return `void` to let the generator proceed with your changes.
-	 * 4. **Async Support**: The callback can be `async`, allowing you to fetch external data or perform complex logic during generation.
+	 * 4. **Async Support**: The callback can be `async`, allowing you to load external data or perform complex logic during generation.
 	 */
 	onNode?: (node: OfficeContentNode) => string | false | Promise<string | false | void> | void;
 	/**
@@ -1860,7 +1892,7 @@ export declare class OfficeParser {
 	 * });
 	 *
 	 * // Parse a Buffer with OCR enabled
-	 * const buffer = await fetch('document.pdf').then(r => r.arrayBuffer());
+	 * const buffer = await retrieveData('document.pdf').then(r => r.arrayBuffer());
 	 * const ast = await OfficeParser.parseOffice(buffer, {
 	 *   ocr: true,
 	 *   ocrLanguage: 'eng+fra'
@@ -1885,6 +1917,10 @@ export declare class OfficeParser {
  * Main generator class providing document conversion functionality.
  */
 export declare class OfficeGenerator {
+	/**
+	 * Normalizes format aliases (e.g., 'txt' to 'text', 'markdown' to 'md') to standard internal formats.
+	 */
+	static normalizeDestination(dest: string): UniversalGeneratorFormat;
 	/**
 	 * Generates a file of the specified type from an AST.
 	 * This is the single source of truth for generation logic.