see history

History.md

@@ -1,3 +1,9 @@
+1.5.4
+=====
+2018-08-29
+
+Fixed #62 fail gracefully on commandline extraction of XML if none is present.
+New public function: ZUGFeRDImporter.getUTF8 returns raw XML without Byte Order Mark, if one had been used.
 
 1.5.3
 =====

src/main/java/org/mustangproject/ZUGFeRD/ZUGFeRDImporter.java

@@ -495,7 +495,37 @@ public String getMeta() {
 		return new String(rawXML);
 	}
 
+
 	/**
+	 * 
+	 * @return return UTF8 XML (without BOM) of the invoice
+	 */
+	public String getUTF8() {
+		if (rawXML == null) {
+			return null;
+		}
+		if (rawXML.length<3) {
+			return new String(rawXML);
+		}
+
+
+		byte[] bomlessData;
+
+	    if ((rawXML[0] == (byte) 0xEF)
+	                    && (rawXML[1] == (byte) 0xBB)
+	                    && (rawXML[2] == (byte) 0xBF)) {
+	            // I don't like BOMs, lets remove it
+	            bomlessData = new byte[rawXML.length - 3];
+	            System.arraycopy(rawXML, 3, bomlessData, 0,
+	            		rawXML.length - 3);
+	    } else {
+	    		bomlessData = rawXML;
+	    }
+
+		return new String(bomlessData);
+	}
+
+   /**
 	 * Returns the raw XML data as extracted from the ZUGFeRD PDF file.
 	 */
 	public byte[] getRawXML() {

src/main/java/org/mustangproject/toecount/Toecount.java

@@ -368,11 +368,17 @@ else if (((directoryName != null) && (directoryName.length() > 0)) || filesFromS
 
 				zi.extract(pdfName);
 				try {
-					Files.write(Paths.get(xmlName), zi.getRawXML());
+					byte[] XMLContent=zi.getRawXML();
+					if (XMLContent==null) {
+						System.err.println("No ZUGFeRD XML found in PDF file");
+
+					} else {
+						Files.write(Paths.get(xmlName), XMLContent);
+						System.out.println("Written to " + xmlName);
+					}
 				} catch (IOException e) {
 					e.printStackTrace();
 				}
-				System.out.println("Written to " + xmlName);
 
 			} else if (a3only) {
 				/*