officeparser 7.0.0 → 7.0.2

package/dist/OfficeConverter.d.ts

@@ -34,10 +34,11 @@ export declare class OfficeConverter {
      * // Convert Word to Markdown with a single call
      * const { value: markdown } = await OfficeConverter.convert('report.docx', 'md');
      *
-     * // Convert PDF to HTML with OCR enabled for images
+     * // Convert PDF to HTML (Note: OCR is disabled in this one-step API)
      * const { value: html } = await OfficeConverter.convert(buffer, 'html', {
-     *   ocr: true,
-     *   includeImages: true
+     *   generatorConfig: {
+     *     includeImages: true
+     *   }
      * });
      * ```
      */

package/dist/OfficeConverter.js

@@ -34,10 +34,11 @@ class OfficeConverter {
      * // Convert Word to Markdown with a single call
      * const { value: markdown } = await OfficeConverter.convert('report.docx', 'md');
      *
-     * // Convert PDF to HTML with OCR enabled for images
+     * // Convert PDF to HTML (Note: OCR is disabled in this one-step API)
      * const { value: html } = await OfficeConverter.convert(buffer, 'html', {
-     *   ocr: true,
-     *   includeImages: true
+     *   generatorConfig: {
+     *     includeImages: true
+     *   }
      * });
      * ```
      */

package/dist/OfficeParser.d.ts

@@ -30,7 +30,7 @@
  * const ast = await OfficeParser.parseOffice(buffer);
  *
  * // Get plain text
- * console.log(ast.toText());
+ * console.log((await ast.to('text')).value);
  * ```
  *
  * @module OfficeParser

package/dist/OfficeParser.js

@@ -31,7 +31,7 @@
  * const ast = await OfficeParser.parseOffice(buffer);
  *
  * // Get plain text
- * console.log(ast.toText());
+ * console.log((await ast.to('text')).value);
  * ```
  *
  * @module OfficeParser
@@ -158,12 +158,13 @@ class OfficeParser {
             else {
                 throw (0, errorUtils_js_1.getOfficeError)(types_js_1.OfficeErrorType.INVALID_INPUT, internalConfig);
             }
-            // Always attempt to detect file type from buffer if it exists, 
-            // but respect the authoritative 'ext' if it was already set.
-            if (buffer.length > 0) {
-                const { fileTypeFromBuffer } = await (0, moduleLoader_js_1.loadFileType)();
-                const type = await fileTypeFromBuffer(buffer);
-                if (!ext) {
+            // 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;
                     }
@@ -173,9 +174,25 @@ class OfficeParser {
                         // lack magic bytes. We'll let the switch default handle it.
                     }
                 }
-                else 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 });
+                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 });
+                    }
+                }
+                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) {

package/dist/officeparser.browser.d.ts

@@ -63,6 +63,8 @@ export declare enum OfficeWarningType {
 	SHEET_RANGE_NOT_FOUND = "SHEET_RANGE_NOT_FOUND",
 	/** Buffer content type does not match the provided or expected file extension */
 	BUFFER_TYPE_MISMATCH = "BUFFER_TYPE_MISMATCH",
+	/** Failed to detect file type from buffer due to library error or incompatibility */
+	FILE_TYPE_DETECTION_FAILED = "FILE_TYPE_DETECTION_FAILED",
 	/** No chunks were generated for the document given the current strategy */
 	EMPTY_CHUNK_GENERATED = "EMPTY_CHUNK_GENERATED",
 	/** A node was skipped because it only contained whitespace */
@@ -1608,10 +1610,11 @@ export declare class OfficeConverter {
 	 * // Convert Word to Markdown with a single call
 	 * const { value: markdown } = await OfficeConverter.convert('report.docx', 'md');
 	 *
-	 * // Convert PDF to HTML with OCR enabled for images
+	 * // Convert PDF to HTML (Note: OCR is disabled in this one-step API)
 	 * const { value: html } = await OfficeConverter.convert(buffer, 'html', {
-	 *   ocr: true,
-	 *   includeImages: true
+	 *   generatorConfig: {
+	 *     includeImages: true
+	 *   }
 	 * });
 	 * ```
 	 */