swallow characters that are illegal in XML documents.

PR: 6351


git-svn-id: https://svn.apache.org/repos/asf/ant/core/trunk@272312 13f79535-47bb-0310-9956-ffa450edef68

docs/manual/OptionalTasks/junit.html

@@ -225,6 +225,10 @@ for all test cases.  Custom formatters that need to implement
 <code>org.apache.tools.ant.taskdefs.optional.junit.JUnitResultFormatter</code>
 can be specified.</p>
 
+<p>If you use the XML formatter, it may not include the same output
+that your tests have written as some characters are illegal in XML
+documents and will be dropped.</p>
+
 <table border="1" cellpadding="2" cellspacing="0">
 <tr>
   <td width="12%" valign="top"><b>Attribute</b></td>

src/main/org/apache/tools/ant/taskdefs/optional/junit/XMLResultAggregator.java

@@ -231,7 +231,7 @@ public class XMLResultAggregator extends Task implements XMLConstants {
         try {
             out = new FileOutputStream( file );
             wri = new PrintWriter(new OutputStreamWriter(out, "UTF8"));
-            wri.write("<?xml version=\"1.0\"?>\n");
+            wri.write("<?xml version=\"1.0\" encoding=\"UTF-8\" ?>\n");
             (new DOMElementWriter()).write(doc.getDocumentElement(), wri, 0, "  ");
             wri.flush();
             // writers do not throw exceptions, so check for them.

src/main/org/apache/tools/ant/util/DOMElementWriter.java

@@ -201,8 +201,8 @@ public class DOMElementWriter {
     }
 
     /**
-     * Escape <, > & ', " and control characters
-     * < 0x20 as their entities.
+     * Escape <, > & ', " as their entities and
+     * drop characters that are illegal in XML documents.
      */
     public String encode(String value) {
         sb.setLength(0);
@@ -230,17 +230,8 @@ public class DOMElementWriter {
                     sb.append('&');
                 }
                 break;
-            case '\t':
-            case '\n':
-            case '\r':
-                sb.append(c);
-                break;
             default:
-                if (c < 0x20) {
-                    sb.append("&#x");
-                    sb.append(Integer.toHexString(c));
-                    sb.append(';');
-                } else {
+                if (isLegalCharacter(c)) {
                     sb.append(c);
                 }
                 break;
@@ -250,7 +241,7 @@ public class DOMElementWriter {
     }
 
     /**
-     * Escape control characters &lt; x20 as their entities.
+     * Drop characters that are illegal in XML documents.
      *
      * <p>See XML 1.0 2.2 <a
      * href="http://www.w3.org/TR/1998/REC-xml-19980210#charsets">http://www.w3.org/TR/1998/REC-xml-19980210#charsets</a>.</p>
@@ -259,22 +250,8 @@ public class DOMElementWriter {
         sb.setLength(0);
         for (int i = 0; i < value.length(); ++i) {
             char c = value.charAt(i);
-            switch (c) {
-            case '\t':
-            case '\n':
-            case '\r':
+            if (isLegalCharacter(c)) {
                 sb.append(c);
-                break;
-                
-            default:
-                if (c < 0x20) {
-                    sb.append("&#x");
-                    sb.append(Integer.toHexString(c));
-                    sb.append(';');
-                } else {
-                    sb.append(c);
-                }
-                break;
             }
         }
         return sb.toString();
@@ -314,4 +291,27 @@ public class DOMElementWriter {
         }
         return false;
     }
+
+    /**
+     * Is the given character allowed inside an XML document?
+     *
+     * <p>See XML 1.0 2.2 <a
+     * href="http://www.w3.org/TR/1998/REC-xml-19980210#charsets">http://www.w3.org/TR/1998/REC-xml-19980210#charsets</a>.</p>
+     *
+     * @since 1.10, Ant 1.5
+     */
+    public boolean isLegalCharacter(char c) {
+        if (c == 0x9 || c == 0xA || c == 0xD) {
+            return true;
+        } else if (c < 0x20) {
+            return false;
+        } else if (c <= 0xD7FF) {
+            return true;
+        } else if (c < 0xE000) {
+            return false;
+        } else if (c <= 0xFFFD) {
+            return true;
+        }
+        return false;
+    }
 }

src/testcases/org/apache/tools/ant/util/DOMElementWriterTest.java

@@ -1,7 +1,7 @@
 /*
  * The Apache Software License, Version 1.1
  *
- * Copyright (c) 2000-2001 The Apache Software Foundation.  All rights
+ * Copyright (c) 2000-2002 The Apache Software Foundation.  All rights
  * reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -100,8 +100,23 @@ public class DOMElementWriterTest extends TestCase {
         assertEquals(""", w.encode("\""));
         assertEquals("&lt;", w.encode("<"));
         assertEquals("&amp;", w.encode("&"));
-        assertEquals("&#x17;", w.encode("\u0017"));
+        assertEquals("", w.encode("\u0017"));
         assertEquals("&#20;\"20;&", w.encodedata("&#20;\"20;&"));
-        assertEquals("&#x17;", w.encodedata("\u0017"));
+        assertEquals("", w.encodedata("\u0017"));
+    }
+
+    public void testIsLegalCharacter() {
+        assertTrue("0x00", !w.isLegalCharacter('\u0000'));
+        assertTrue("0x09", w.isLegalCharacter('\t'));
+        assertTrue("0x0A", w.isLegalCharacter('\n'));
+        assertTrue("0x0C", w.isLegalCharacter('\r'));
+        assertTrue("0x1F", !w.isLegalCharacter('\u001F'));
+        assertTrue("0x20", w.isLegalCharacter('\u0020'));
+        assertTrue("0xD7FF", w.isLegalCharacter('\uD7FF'));
+        assertTrue("0xD800", !w.isLegalCharacter('\uD800'));
+        assertTrue("0xDFFF", !w.isLegalCharacter('\uDFFF'));
+        assertTrue("0xE000", w.isLegalCharacter('\uE000'));
+        assertTrue("0xFFFD", w.isLegalCharacter('\uFFFD'));
+        assertTrue("0xFFFE", !w.isLegalCharacter('\uFFFE'));
     }
 }