From 13a3f5bc3e2d25fc76850f86070dc34efe60d77a Mon Sep 17 00:00:00 2001
From: James Moger <james.moger@gitblit.com>
Date: Fri, 07 Sep 2012 22:06:15 -0400
Subject: [PATCH] Draft project pages, project metadata, and RSS feeds

---
 src/com/gitblit/utils/StringUtils.java |   40 ++++++++++++++++++++++++++++++++++++----
 1 files changed, 36 insertions(+), 4 deletions(-)

diff --git a/src/com/gitblit/utils/StringUtils.java b/src/com/gitblit/utils/StringUtils.java
index baed5f0..08fd497 100644
--- a/src/com/gitblit/utils/StringUtils.java
+++ b/src/com/gitblit/utils/StringUtils.java
@@ -33,6 +33,8 @@
 import java.util.LinkedHashSet;
 import java.util.List;
 import java.util.Set;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
 import java.util.regex.PatternSyntaxException;
 
 /**
@@ -76,7 +78,7 @@
 	 * @return plain text escaped for html
 	 */
 	public static String escapeForHtml(String inStr, boolean changeSpace) {
-		StringBuffer retStr = new StringBuffer();
+		StringBuilder retStr = new StringBuilder();
 		int i = 0;
 		while (i < inStr.length()) {
 			if (inStr.charAt(i) == '&') {
@@ -117,7 +119,7 @@
 	 * @return properly escaped url
 	 */
 	public static String encodeURL(String inStr) {
-		StringBuffer retStr = new StringBuffer();
+		StringBuilder retStr = new StringBuilder();
 		int i = 0;
 		while (i < inStr.length()) {
 			if (inStr.charAt(i) == '/') {
@@ -575,13 +577,15 @@
 		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 +594,34 @@
 				// ignore unsupported charsets
 			}
 		}
-		return new String(content, Charset.forName("UTF-8"));
+		if (value.startsWith("\uFEFF")) {
+			// strip UTF-8 BOM
+            return value.substring(1);
+        }
+		return value;
+	}
+	
+	/**
+	 * Attempt to extract a repository name from a given url using regular
+	 * expressions.  If no match is made, then return whatever trails after
+	 * the final / character.
+	 * 
+	 * @param regexUrls
+	 * @return a repository path
+	 */
+	public static String extractRepositoryPath(String url, String... urlpatterns) {
+		for (String urlPattern : urlpatterns) {
+			Pattern p = Pattern.compile(urlPattern);
+			Matcher m = p.matcher(url);
+			while (m.find()) {
+				String repositoryPath = m.group(1);
+				return repositoryPath;
+			}
+		}
+		// last resort
+		if (url.lastIndexOf('/') > -1) {
+			return url.substring(url.lastIndexOf('/') + 1);
+		}
+		return url;
 	}
 }
\ No newline at end of file

--
Gitblit v1.9.1