src/java.xml/share/classes/com/sun/org/apache/xerces/internal/impl/dv/xs/TypeValidator.java

@@ -1,8 +1,7 @@
 /*
- * reserved comment block
- * DO NOT REMOVE OR ALTER!
+ * Copyright (c) 2013, 2019, Oracle and/or its affiliates. All rights reserved.
  */
 /*
  * Licensed to the Apache Software Foundation (ASF) under one or more
  * contributor license agreements.  See the NOTICE file distributed with
  * this work for additional information regarding copyright ownership.

@@ -21,10 +20,12 @@
 
 package com.sun.org.apache.xerces.internal.impl.dv.xs;
 
 import com.sun.org.apache.xerces.internal.impl.dv.InvalidDatatypeValueException;
 import com.sun.org.apache.xerces.internal.impl.dv.ValidationContext;
+import com.sun.org.apache.xerces.internal.util.XMLChar;
+import jdk.xml.internal.SecuritySupport;
 
 /**
  * All primitive types plus ID/IDREF/ENTITY/INTEGER are derived from this abstract
  * class. It provides extra information XSSimpleTypeDecl requires from each
  * type: allowed facets, converting String to actual value, check equality,

@@ -33,13 +34,18 @@
  * @xerces.internal
  *
  * @author Neeraj Bajaj, Sun Microsystems, inc.
  * @author Sandy Gao, IBM
  *
+ * @LastModified: Apr 2019
  */
 public abstract class TypeValidator {
 
+    private static final boolean USE_CODE_POINT_COUNT_FOR_STRING_LENGTH =
+            Boolean.parseBoolean(SecuritySupport.getSystemProperty(
+                    "com.sun.org.apache.xerces.internal.impl.dv.xs.useCodePointCountForStringLength", "false"));
+
     // which facets are allowed for this type
     public abstract short getAllowedFacets();
 
     // convert a string to an actual value. for example,
     // for number types (decimal, double, float, and types derived from them),

@@ -80,11 +86,18 @@
     }
 
     // get the length of the value
     // the parameters are in compiled form (from getActualValue)
     public int getDataLength(Object value) {
-        return (value instanceof String) ? ((String)value).length() : -1;
+        if (value instanceof String) {
+            final String str = (String)value;
+            if (!USE_CODE_POINT_COUNT_FOR_STRING_LENGTH) {
+                return str.length();
+            }
+            return getCodePointLength(str);
+        }
+        return -1;
     }
 
     // get the number of digits of the value
     // the parameters are in compiled form (from getActualValue)
     public int getTotalDigits(Object value) {

@@ -95,10 +108,29 @@
     // the parameters are in compiled form (from getActualValue)
     public int getFractionDigits(Object value) {
         return -1;
     }
 
+    // Returns the length of the string in Unicode code points.
+    private int getCodePointLength(String value) {
+        // Count the number of surrogate pairs, and subtract them from
+        // the total length.
+        final int len = value.length();
+        int surrogatePairCount = 0;
+        for (int i = 0; i < len - 1; ++i) {
+            if (XMLChar.isHighSurrogate(value.charAt(i))) {
+                if (XMLChar.isLowSurrogate(value.charAt(++i))) {
+                    ++surrogatePairCount;
+                }
+                else {
+                    --i;
+                }
+            }
+        }
+        return len - surrogatePairCount;
+    }
+
     // check whether the character is in the range 0x30 ~ 0x39
     public static final boolean isDigit(char ch) {
         return ch >= '0' && ch <= '9';
     }