From 086c0447227a4075b66b976088542fee113b0d4f Mon Sep 17 00:00:00 2001
From: James Moger <james.moger@gitblit.com>
Date: Fri, 10 Aug 2012 17:34:47 -0400
Subject: [PATCH] Strip hidden UTF-8 BOM from string content
---
src/com/gitblit/utils/StringUtils.java | 11 +++++++++--
1 files changed, 9 insertions(+), 2 deletions(-)
diff --git a/src/com/gitblit/utils/StringUtils.java b/src/com/gitblit/utils/StringUtils.java
index baed5f0..412a920 100644
--- a/src/com/gitblit/utils/StringUtils.java
+++ b/src/com/gitblit/utils/StringUtils.java
@@ -575,13 +575,15 @@
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 @@
// 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
--
Gitblit v1.9.1