working

ts/formats/pdf/pdf.extractor.ts

@@ -79,16 +79,29 @@ export class PDFExtractor {
       }
 
       // Decompress and decode the XML content
-      const xmlCompressedBytes = xmlFile.getContents().buffer;
-      const xmlBytes = pako.inflate(xmlCompressedBytes);
-      const xmlContent = new TextDecoder('utf-8').decode(xmlBytes);
+      try {
+        const xmlCompressedBytes = xmlFile.getContents().buffer;
+        const xmlBytes = pako.inflate(xmlCompressedBytes);
+        const xmlContent = new TextDecoder('utf-8').decode(xmlBytes);
 
-      console.log(`Successfully extracted XML from PDF file. File name: ${xmlFileName}`);
-      
-      return xmlContent;
+        console.log(`Successfully extracted XML from PDF file. File name: ${xmlFileName}`);
+        return xmlContent;
+      } catch (decompressError) {
+        // Try without decompression
+        console.log('Decompression failed, trying without decompression...');
+        try {
+          const xmlBytes = xmlFile.getContents();
+          const xmlContent = new TextDecoder('utf-8').decode(xmlBytes);
+          console.log(`Successfully extracted uncompressed XML from PDF file. File name: ${xmlFileName}`);
+          return xmlContent;
+        } catch (decodeError) {
+          console.error('Error decoding XML content:', decodeError);
+          return null;
+        }
+      }
     } catch (error) {
       console.error('Error extracting or parsing embedded XML from PDF:', error);
-      throw error;
+      return null;
     }
   }
 }