From 9102b422bf606cca54e8015f029c9e2223c6f301 Mon Sep 17 00:00:00 2001
From: Romain Pelisse <rpelisse@users.sourceforge.net>
Date: Fri, 23 Sep 2011 17:55:34 +0000
Subject: [PATCH] apply patch 3084292: character reference in xml report -
 thanks to Seko

git-svn-id: https://pmd.svn.sourceforge.net/svnroot/pmd/trunk@7319 51baf565-9d33-0410-a72c-fc3788e3496d
---
 pmd/etc/changelog.txt                         |   1 +
 .../sourceforge/pmd/util/StringUtilTest.java  |   4 +-
 .../net/sourceforge/pmd/util/StringUtil.java  | 143 ++++++++----------
 3 files changed, 69 insertions(+), 79 deletions(-)

diff --git a/pmd/etc/changelog.txt b/pmd/etc/changelog.txt
index 36005f9488..db79143b88 100644
--- a/pmd/etc/changelog.txt
+++ b/pmd/etc/changelog.txt
@@ -439,6 +439,7 @@ The RuleSet XML Schema is located in the source at: etc/ruleset_2_0_0.xsd
 The RuleSet DTD is located in the source at: etc/ruleset_2_0_0.dtd
 Improved include/exclude pattern matching performance for ends-with type patterns.
 Modify (and hopefully fixed) CPD algorithm thanks to a patch from Juan Jesús García de Soria.
+Fixed character reference in xml report - thanks to Seko
 
 New Java rules:
 
diff --git a/pmd/regress/test/net/sourceforge/pmd/util/StringUtilTest.java b/pmd/regress/test/net/sourceforge/pmd/util/StringUtilTest.java
index 9899e3fd39..58e48d4d0d 100644
--- a/pmd/regress/test/net/sourceforge/pmd/util/StringUtilTest.java
+++ b/pmd/regress/test/net/sourceforge/pmd/util/StringUtilTest.java
@@ -37,7 +37,7 @@ public class StringUtilTest {
     /**
      * Usually you would set the system property "net.sourceforge.pmd.supportUTF8" to either "no" or "yes", to
      * switch UTF8 support.
-     * 
+     *
      * e.g.
      * <code>System.setProperty("net.sourceforge.pmd.supportUTF8","yes");</code>
      */
@@ -46,7 +46,7 @@ public class StringUtilTest {
     	StringBuilder sb = new StringBuilder();
         String test = "é";
         StringUtil.appendXmlEscaped(sb, test, false);
-        assertEquals("&#233;", sb.toString());
+        assertEquals("&#xe9;", sb.toString());
     }
 
     @Test
diff --git a/pmd/src/net/sourceforge/pmd/util/StringUtil.java b/pmd/src/net/sourceforge/pmd/util/StringUtil.java
index ae527ca4df..9fbae1760a 100644
--- a/pmd/src/net/sourceforge/pmd/util/StringUtil.java
+++ b/pmd/src/net/sourceforge/pmd/util/StringUtil.java
@@ -9,118 +9,111 @@ import java.util.List;
 
 /**
  * A number of String-specific utility methods for use by PMD or its IDE plugins.
- * 
+ *
  * @author br
  */
 public final class StringUtil {
 
 	public static final String[] EMPTY_STRINGS = new String[0];
     private static final boolean SUPPORTS_UTF8 = System.getProperty("net.sourceforge.pmd.supportUTF8", "no").equals("yes");
-    private static final String[] ENTITIES;
 
-    static {
-        ENTITIES = new String[256 - 126];
-        for (int i = 126; i <= 255; i++) {
-            ENTITIES[i - 126] = "&#" + i + ';';
-        }
-    }
 
     private StringUtil() {}
-    
+
     /**
      * Return whether the non-null text arg starts with any of the prefix
-     * values. 
-     * 
+     * values.
+     *
      * @param text
      * @param prefixes
      * @return
      */
     public static boolean startsWithAny(String text, String... prefixes) {
-    	
+
     	for (String prefix : prefixes) {
     		if (text.startsWith(prefix)) return true;
     	}
-    	
+
     	return false;
     }
-    
+
     /**
      * Returns whether the non-null text arg matches any of the test values.
-     * 
+     *
      * @param text
      * @param tests
      * @return
      */
     public static boolean isAnyOf(String text, String... tests) {
-    	
+
     	for (String test : tests) {
     		if (text.equals(test)) return true;
     	}
-    	
+
     	return false;
     }
-    
+
     /**
      * Checks for the existence of any of the listed prefixes on the
      * non-null text and removes them.
-     * 
+     *
      * @param text
      * @param prefixes
      * @return
      */
     public static String withoutPrefixes(String text, String... prefixes) {
-    	
+
     	for (String prefix : prefixes) {
     		if (text.startsWith(prefix)) {
     			return text.substring(prefix.length());
     		}
     	}
-    	
+
     	return text;
     }
-    
+
     /**
      * Returns true if the value arg is either null, empty, or full of whitespace characters.
      * More efficient that calling (string).trim().length() == 0
-     * 
+     *
      * @param value
      * @return <code>true</code> if the value is empty, <code>false</code> otherwise.
      */
     public static boolean isEmpty(String value) {
-    	
+
     	if (value == null || "".equals(value)) {
     		return true;
     	}
-    	
+
     	for (int i=0; i<value.length(); i++) {
     		if (!Character.isWhitespace(value.charAt(i))) {
     		    return false;
     		}
     	}
-    	
+
     	return true;
     }
-    
+
     public static boolean isNotEmpty(String value) {
     	return !isEmpty(value);
     }
-    
+
     /**
      * Returns true if both strings are effectively null or whitespace,
      * returns false otherwise if they have actual text that differs.
-     * 
+     *
      * @param a
      * @param b
      * @return boolean
      */
 	public static boolean areSemanticEquals(String a, String b) {
-		
+
 		if (a==null) { return isEmpty(b); }
 		if (b==null) { return isEmpty(a); }
-		
+
 		return a.equals(b);
 	}
-    
+
     public static String replaceString(final String original, char oldChar, final String newString) {
 		int index = original.indexOf(oldChar);
 		if (index < 0) {
@@ -175,18 +168,18 @@ public final class StringUtil {
         encoded = replaceString(encoded, '<', "&lt;");
         return replaceString(encoded, '>', "&gt;");
     }
-    
+
     /**
-     * 
+     *
      * @param buf
      * @param src
      * @param supportUTF8 override the default setting, whether special characters should be replaced
      * with entities (<code>false</code>) or should be included as is (<code>true</code>).
-     * 
+     *
      * @see #appendXmlEscaped(StringBuffer, String)
-     * 
+     *
      * TODO - unify the method above with the one below
-     * 
+     *
      * public to support unit testing - make this package private, once the unit test classes are in the same package.
      */
     public static void appendXmlEscaped(StringBuilder buf, String src, boolean supportUTF8) {
@@ -195,11 +188,7 @@ public final class StringUtil {
             c = src.charAt(i);
             if (c > '~') {// 126
                 if (!supportUTF8) {
-                    if (c <= 255) {
-                        buf.append(ENTITIES[c - 126]);
-                    } else {
-                        buf.append("&u").append(Integer.toHexString(c)).append(';');
-                    }
+                    buf.append("&#x").append(Integer.toHexString(c)).append(';');
                 } else {
                     buf.append(c);
                 }
@@ -233,7 +222,7 @@ public final class StringUtil {
 		if (source == null || source.length() == 0) {
             return EMPTY_STRINGS;
         }
-		
+
 		int delimiterCount = 0;
 		int length = source.length();
 		char[] chars = source.toCharArray();
@@ -264,16 +253,16 @@ public final class StringUtil {
 
 		return results;
 	}
-	
+
 	/**
 	 * Much more efficient than StringTokenizer.
-	 * 
+	 *
 	 * @param str String
 	 * @param separator char
 	 * @return String[]
 	 */
 	  public static String[] substringsOf(String str, String separator) {
-		  
+
 	        if (str == null || str.length() == 0) {
 	            return EMPTY_STRINGS;
 	        }
@@ -294,8 +283,8 @@ public final class StringUtil {
 	        list.add(str.substring(currPos));
 	        return list.toArray(new String[list.size()]);
 	    }
-	
-	
+
+
 	/**
 	 * Copies the elements returned by the iterator onto the string buffer
 	 * each delimited by the separator.
@@ -305,11 +294,11 @@ public final class StringUtil {
 	 * @param separator String
 	 */
 	public static void asStringOn(StringBuffer sb, Iterator<?> iter, String separator) {
-		
+
 	    if (!iter.hasNext()) { return;  }
-	    
+
 	    sb.append(iter.next());
-	    
+
 	    while (iter.hasNext()) {
 	    	sb.append(separator);
 	        sb.append(iter.next());
@@ -317,46 +306,46 @@ public final class StringUtil {
 	}
 	/**
 	 * Return the length of the shortest string in the array.
-	 * If the collection is empty or any one of them is 
+	 * If the collection is empty or any one of them is
 	 * null then it returns 0.
-	 * 
+	 *
 	 * @param strings String[]
 	 * @return int
 	 */
 	public static int lengthOfShortestIn(String[] strings) {
-		
+
 	    if (CollectionUtil.isEmpty(strings)) { return 0; }
-	    
+
 		int minLength = Integer.MAX_VALUE;
-		
+
 		for (int i=0; i<strings.length; i++) {
 			if (strings[i] == null) {
 			    return 0;
 			}
 			minLength = Math.min(minLength, strings[i].length());
 		}
-		
+
 		return minLength;
 	}
-	
+
 	/**
 	 * Determine the maximum number of common leading whitespace characters
 	 * the strings share in the same sequence. Useful for determining how
 	 * many leading characters can be removed to shift all the text in the
 	 * strings to the left without misaligning them.
-	 * 
+	 *
 	 * @param strings String[]
 	 * @return int
 	 */
 	public static int maxCommonLeadingWhitespaceForAll(String[] strings) {
-		
+
 		int shortest = lengthOfShortestIn(strings);
 		if (shortest == 0) {
 		    return 0;
 		}
-		
+
 		char[] matches = new char[shortest];
-		
+
 		String str;
 		for (int m=0; m<matches.length; m++) {
 			matches[m] = strings[0].charAt(m);
@@ -366,35 +355,35 @@ public final class StringUtil {
 			for (int i=0; i<strings.length; i++) {
 				str = strings[i];
 				if (str.charAt(m) != matches[m]) {
-				    return m; 
+				    return m;
 				}
 				}
 		}
-		
+
 		return shortest;
 	}
-	
+
 	/**
-	 * Trims off the leading characters off the strings up to the trimDepth 
+	 * Trims off the leading characters off the strings up to the trimDepth
 	 * specified. Returns the same strings if trimDepth = 0
-	 * 
+	 *
 	 * @param strings
 	 * @param trimDepth
 	 * @return String[]
 	 */
 	public static String[] trimStartOn(String[] strings, int trimDepth) {
-		
+
 		if (trimDepth == 0) {
 		    return strings;
 		}
-		
+
 		String[] results = new String[strings.length];
 		for (int i=0; i<strings.length; i++) {
 			results[i] = strings[i].substring(trimDepth);
 		}
 		return results;
    }
-	
+
     /**
      * Left pads a string.
      * @param s The String to pad
@@ -410,14 +399,14 @@ public final class StringUtil {
          }
          return res;
     }
-    
+
     /**
      * Are the two String values the same.
      * The Strings can be optionally trimmed before checking.
      * The Strings can be optionally compared ignoring case.
      * The Strings can be have embedded whitespace standardized before comparing.
      * Two null values are treated as equal.
-     * 
+     *
      * @param s1 The first String.
      * @param s2 The second String.
      * @param trim Indicates if the Strings should be trimmed before comparison.
@@ -444,25 +433,25 @@ public final class StringUtil {
 			return ignoreCase ? s1.equalsIgnoreCase(s2) : s1.equals(s2);
 		}
     }
-    
+
 	/**
 	 * Formats all items onto a string with separators if more than one
 	 * exists, return an empty string if the items are null or empty.
-	 * 
+	 *
 	 * @param items Object[]
 	 * @param separator String
 	 * @return String
 	 */
 	public static String asString(Object[] items, String separator) {
-		
+
 		if (items == null || items.length == 0) { return ""; }
 		if (items.length == 1) { return items[0].toString(); }
-		
+
 		StringBuilder sb = new StringBuilder(items[0].toString());
 		for (int i=1; i<items.length; i++) {
 			sb.append(separator).append(items[i]);
 		}
-		
+
 		return sb.toString();
 	}
 }