From db71db17c90fd93bcf38cdf87e16a371c39708e0 Mon Sep 17 00:00:00 2001
From: Mrbytes <eguervos@msn.com>
Date: Thu, 13 Sep 2012 18:13:48 -0400
Subject: [PATCH] Merge branch 'master' of https://github.com/gitblit/gitblit
---
src/com/gitblit/utils/StringUtils.java | 76 ++++++++++++++++++++++++++++++++++++--
1 files changed, 72 insertions(+), 4 deletions(-)
diff --git a/src/com/gitblit/utils/StringUtils.java b/src/com/gitblit/utils/StringUtils.java
index baed5f0..e440790 100644
--- a/src/com/gitblit/utils/StringUtils.java
+++ b/src/com/gitblit/utils/StringUtils.java
@@ -15,6 +15,7 @@
*/
package com.gitblit.utils;
+import java.io.ByteArrayOutputStream;
import java.io.UnsupportedEncodingException;
import java.nio.ByteBuffer;
import java.nio.CharBuffer;
@@ -33,6 +34,8 @@
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 +79,7 @@
* @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 +120,7 @@
* @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 +578,15 @@
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 +595,69 @@
// 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;
+ }
+
+ /**
+ * Converts a string with \nnn sequences into a UTF-8 encoded string.
+ * @param input
+ * @return
+ */
+ public static String convertOctal(String input) {
+ try {
+ ByteArrayOutputStream bytes = new ByteArrayOutputStream();
+ Pattern p = Pattern.compile("(\\\\\\d{3})");
+ Matcher m = p.matcher(input);
+ int i = 0;
+ while (m.find()) {
+ bytes.write(input.substring(i, m.start()).getBytes("UTF-8"));
+ // replace octal encoded value
+ // strip leading \ character
+ String oct = m.group().substring(1);
+ bytes.write(Integer.parseInt(oct, 8));
+ i = m.end();
+ }
+ if (bytes.size() == 0) {
+ // no octal matches
+ return input;
+ } else {
+ if (i < input.length()) {
+ // add remainder of string
+ bytes.write(input.substring(i).getBytes("UTF-8"));
+ }
+ }
+ return bytes.toString("UTF-8");
+ } catch (Exception e) {
+ e.printStackTrace();
+ }
+ return input;
}
}
\ No newline at end of file
--
Gitblit v1.9.1