commit 0ea3fce219464b97046d2494e76b9876003521a8
author kprobst@google.com <kprobst@google.com@8db76d5a-ed1c-0410-87a9-c151d255dfc7> Mon Dec 21 14:55:18 2009 +0000
committer kprobst@google.com <kprobst@google.com@8db76d5a-ed1c-0410-87a9-c151d255dfc7> Mon Dec 21 14:55:18 2009 +0000
tree 0af025bba68a3d351cac1f598f2feca1af82775a
parent 003c0c86856673af4c3f49658f4e27ec1de4d5c1

Fixes two XML issues in the Compile Report: some unicode characters slipped through, and some invalid XML characters were not escaped.

Review by: spoon



git-svn-id: https://google-web-toolkit.googlecode.com/svn/trunk@7342 8db76d5a-ed1c-0410-87a9-c151d255dfc7

dev/core/src/com/google/gwt/core/ext/soyc/impl/SizeMapRecorder.java

diff --git a/dev/core/src/com/google/gwt/core/ext/soyc/impl/SizeMapRecorder.java b/dev/core/src/com/google/gwt/core/ext/soyc/impl/SizeMapRecorder.java
index d1543ef..0c23027 100644
--- a/dev/core/src/com/google/gwt/core/ext/soyc/impl/SizeMapRecorder.java
+++ b/dev/core/src/com/google/gwt/core/ext/soyc/impl/SizeMapRecorder.java
@@ -56,6 +56,22 @@
   }
 
   /**
+   * Returns the hexadecimal representation of a character
+   */
+  public static StringBuilder charToHex(char c) {
+    char hexDigit[] = { '0', '1', '2', '3', '4', '5', '6', '7', '8', '9',
+      'A', 'B', 'C', 'D', 'E', 'F' };
+    StringBuilder toReturn = new StringBuilder();
+    byte charByte = (byte) (c >>> 8);
+    toReturn.append(hexDigit[(charByte >> 4) & 0x0F]);
+    toReturn.append(hexDigit[charByte & 0x0F]);
+    charByte = (byte) (c & 0xFF);
+    toReturn.append(hexDigit[(charByte >> 4) & 0x0F]);
+    toReturn.append(hexDigit[charByte & 0x0F]);
+    return toReturn;
+  }
+
+  /**
    * Escapes '&', '<', '>', '"', and '\'' to their XML entity equivalents.
    */
   public static String escapeXml(String unescaped) {
@@ -78,36 +94,40 @@
    * @param builder a StringBuilder to be appended with the output.
    */
   public static void escapeXml(String code, int start, int end,
-      boolean quoteApostrophe, StringBuilder builder) {
+    boolean quoteApostrophe, StringBuilder builder) {
+    // See http://www.w3.org/TR/2006/REC-xml11-20060816/#charsets.
     int lastIndex = 0;
     int len = end - start;
     char[] c = new char[len];
 
     code.getChars(start, end, c, 0);
     for (int i = 0; i < len; i++) {
-      if ((c[i] >= '\uD800') && (c[i] <= '\uDBFF')) {
+      if ((c[i] < '\u0020')) {
         builder.append(c, lastIndex, i - lastIndex);
-        builder.append("(non-valid utf-8 character)");
+        if (c[i] == '\u0000') {
+         builder.append("\\0");
+        }
+        else if (c[i] == '\u0009') {
+         builder.append("\\t");
+        }
+        else if (c[i] == '\n') {
+         builder.append("\\n");
+        }
+        else if (c[i] == '\r') {
+         builder.append("\\r");
+        }
+        else {
+            builder.append("(invalid xml character: \\u" + charToHex(c[i]) + ")");
+        }
         lastIndex = i + 1;
-        break;
-      } else if ((c[i] >= '\uDC00') && (c[i] <= '\uDFFF')) {
+      } else if (((c[i] >= '\u007F') && (c[i] <= '\u0084')) ||
+            ((c[i] >= '\u0086') && (c[i] <= '\u009F')) ||
+            ((c[i] >= '\uD800') && (c[i] <= '\uDBFF')) || 
+            ((c[i] >= '\uDC00') && (c[i] <= '\uDFFF')) ||
+            ((c[i] >= '\uFDD0') && (c[i] <= '\uFDDF')) ||
+            (c[i] == '\u00A0') || (c[i] == '\uFFFF') || (c[i] == '\uFFFE')) {
         builder.append(c, lastIndex, i - lastIndex);
-        builder.append("(non-valid utf-8 character)");
-        lastIndex = i + 1;
-        break;
-      } else if (c[i] == '\0') {
-        builder.append(c, lastIndex, i - lastIndex);
-        builder.append("(null)");
-        lastIndex = i + 1;
-        break;
-      } else if (c[i] == '\uffff') {
-        builder.append(c, lastIndex, i - lastIndex);
-        builder.append("(uffff)");
-        lastIndex = i + 1;
-        break;
-      } else if (c[i] == '\ufffe') {
-        builder.append(c, lastIndex, i - lastIndex);
-        builder.append("(ufffe)");
+        builder.append("(invalid xml character: \\u" + charToHex(c[i]) + ")");
         lastIndex = i + 1;
       } else if (c[i] == '&') {
         builder.append(c, lastIndex, i - lastIndex);
@@ -131,6 +151,10 @@
           builder.append("&apos;");
           lastIndex = i + 1;
         }
+      } else if (c[i] > '\u007F') {
+        builder.append(c, lastIndex, i - lastIndex);
+        builder.append("&#x" + charToHex(c[i]) + ";");
+        lastIndex = i + 1;
       }
     }
     builder.append(c, lastIndex, len - lastIndex);

dev/core/src/com/google/gwt/soyc/MakeTopLevelHtmlForPerm.java

diff --git a/dev/core/src/com/google/gwt/soyc/MakeTopLevelHtmlForPerm.java b/dev/core/src/com/google/gwt/soyc/MakeTopLevelHtmlForPerm.java
index a301c2c..6b322f9 100644
--- a/dev/core/src/com/google/gwt/soyc/MakeTopLevelHtmlForPerm.java
+++ b/dev/core/src/com/google/gwt/soyc/MakeTopLevelHtmlForPerm.java
@@ -16,6 +16,7 @@
 
 package com.google.gwt.soyc;
 
+import com.google.gwt.core.ext.soyc.impl.SizeMapRecorder;
 import com.google.gwt.dev.util.Util;
 import com.google.gwt.soyc.io.OutputDirectory;
 
@@ -106,12 +107,7 @@
   private static final Pattern PATTERN_SP_INT = Pattern.compile("sp([0-9]+)");
 
   private static String escapeXml(String unescaped) {
-    String escaped = unescaped.replaceAll("\\&", "&");
-    escaped = escaped.replaceAll("\\<", "&lt;");
-    escaped = escaped.replaceAll("\\>", "&gt;");
-    escaped = escaped.replaceAll("\\\"", "&quot;");
-    escaped = escaped.replaceAll("\\'", "&apos;");
-    return escaped;
+      return SizeMapRecorder.escapeXml(unescaped);
   }
 
   public static void makeTopLevelHtmlForAllPerms(