fix(pdfbox): remove character \u0009 (tabluator) before operate on font

Reason: will not be supported by fonts and must be replaced with blank before rendering

2 files changed, 35 insertions, 5 deletions

diff --git a/pdf-as-common/src/main/java/at/gv/egiz/pdfas/common/utils/StringUtils.java b/pdf-as-common/src/main/java/at/gv/egiz/pdfas/common/utils/StringUtils.java
index 7156a97b..70344f78 100644
--- a/pdf-as-common/src/main/java/at/gv/egiz/pdfas/common/utils/StringUtils.java
+++ b/pdf-as-common/src/main/java/at/gv/egiz/pdfas/common/utils/StringUtils.java
@@ -23,13 +23,13 @@
  ******************************************************************************/
 package at.gv.egiz.pdfas.common.utils;
 
-import org.slf4j.Logger;
-import org.slf4j.LoggerFactory;
-
 import java.io.UnsupportedEncodingException;
 import java.net.URLEncoder;
 import java.util.Formatter;
 
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
 /**
  * Created with IntelliJ IDEA. User: afitzek Date: 8/28/13 Time: 12:42 PM To
  * change this template use File | Settings | File Templates.
@@ -38,6 +38,7 @@ public class StringUtils {
 
 	private static final Logger logger = LoggerFactory
 			.getLogger(StringUtils.class);
+  private static final CharSequence TABULATOR = '\u0009'+"";
 
 	public static String bytesToHexString(byte[] bytes) {
 		StringBuilder sb = new StringBuilder(bytes.length * 2);
@@ -75,10 +76,17 @@ public class StringUtils {
 			// Cannot encode String with CP1252 have to use URL encoding ...
 			return URLEncoder.encode(value, "UTF-8");
 		}
-		return value;
+		
+		return replaceSpecialCharacters(value);
+		
 	}
 
-	public static byte[] applyWinAnsiEncoding(String text)
+	private static String replaceSpecialCharacters(String value) {
+	  return value.replace(TABULATOR, " ");
+	  
+  }
+
+  public static byte[] applyWinAnsiEncoding(String text)
 			throws UnsupportedEncodingException {
 		byte[] replace_bytes;
 		replace_bytes = text.getBytes("windows-1252");// CP1252 =
diff --git a/pdf-as-common/src/test/java/at/gv/egiz/pdfas/common/test/utils/StringUtilsTest.java b/pdf-as-common/src/test/java/at/gv/egiz/pdfas/common/test/utils/StringUtilsTest.java
new file mode 100644
index 00000000..6c6ee654
--- /dev/null
+++ b/pdf-as-common/src/test/java/at/gv/egiz/pdfas/common/test/utils/StringUtilsTest.java
@@ -0,0 +1,22 @@
+package at.gv.egiz.pdfas.common.test.utils;
+
+import static org.junit.Assert.assertEquals;
+
+import java.io.UnsupportedEncodingException;
+
+import org.junit.Test;
+import org.junit.runner.RunWith;
+import org.junit.runners.BlockJUnit4ClassRunner;
+
+import at.gv.egiz.pdfas.common.utils.StringUtils;
+
+@RunWith(BlockJUnit4ClassRunner.class)
+public class StringUtilsTest {
+
+  @Test    
+  public void checkTabulatorReplacing() throws UnsupportedEncodingException {    
+    assertEquals("asdfsaf asdfsafsafwer", StringUtils.convertStringToPDFFormat("asdfsaf\u0009asdfsafsafwer"));
+    
+  }
+  
+}