Strip hidden UTF-8 BOM from string content

1 files changed, 9 insertions, 2 deletions

diff --git a/src/com/gitblit/utils/StringUtils.java b/src/com/gitblit/utils/StringUtils.java
index baed5f0c..412a920f 100644
--- a/src/com/gitblit/utils/StringUtils.java
+++ b/src/com/gitblit/utils/StringUtils.java
@@ -575,13 +575,15 @@ public class StringUtils {
 		if (!ArrayUtils.isEmpty(charsets)) {

 			sets.addAll(Arrays.asList(charsets));

 		}

+		String value = null;

 		sets.addAll(Arrays.asList("UTF-8", "ISO-8859-1", Charset.defaultCharset().name()));

 		for (String charset : sets) {

 			try {

 				Charset cs = Charset.forName(charset);

 				CharsetDecoder decoder = cs.newDecoder();

 				CharBuffer buffer = decoder.decode(ByteBuffer.wrap(content));

-				return buffer.toString();

+				value = buffer.toString();

+				break;

 			} catch (CharacterCodingException e) {

 				// ignore and advance to the next charset

 			} catch (IllegalCharsetNameException e) {

@@ -590,6 +592,11 @@ public class StringUtils {
 				// ignore unsupported charsets

 			}

 		}

-		return new String(content, Charset.forName("UTF-8"));

+		value = new String(content, Charset.forName("UTF-8"));

+		if (value.startsWith("\uFEFF")) {

+			// strip UTF-8 BOM

+            return value.substring(1);

+        }

+		return value;

 	}

 }
\ No newline at end of file