1 files changed, 115 insertions, 13 deletions

diff --git a/java/lang/String.java b/java/lang/String.java
index b8a3a6627..74a9a61cb 100644
--- a/java/lang/String.java
+++ b/java/lang/String.java
@@ -101,7 +101,7 @@ public final class String
 
   /**
    * Stores unicode multi-character uppercase expansion table.
-   * @see #toUpperCase(char)
+   * @see #toUpperCase(Locale)
    * @see CharData#UPPER_EXPAND
    */
   private static final char[] upperExpand
@@ -142,7 +142,7 @@ public final class String
   final int offset;
 
   /**
-   * An implementation for {@link CASE_INSENSITIVE_ORDER}.
+   * An implementation for {@link #CASE_INSENSITIVE_ORDER}.
    * This must be {@link Serializable}. The class name is dictated by
    * compatibility with Sun's JDK.
    */
@@ -557,6 +557,40 @@ public final class String
   }
 
   /**
+   * Get the code point at the specified index.  This is like #charAt(int),
+   * but if the character is the start of a surrogate pair, and the
+   * following character completes the pair, then the corresponding
+   * supplementary code point is returned.
+   * @param index the index of the codepoint to get, starting at 0
+   * @return the codepoint at the specified index
+   * @throws IndexOutOfBoundsException if index is negative or >= length()
+   * @since 1.5
+   */
+  public synchronized int codePointAt(int index)
+  {
+    // Use the CharSequence overload as we get better range checking
+    // this way.
+    return Character.codePointAt(this, index);
+  }
+
+  /**
+   * Get the code point before the specified index.  This is like
+   * #codePointAt(int), but checks the characters at <code>index-1</code> and
+   * <code>index-2</code> to see if they form a supplementary code point.
+   * @param index the index just past the codepoint to get, starting at 0
+   * @return the codepoint at the specified index
+   * @throws IndexOutOfBoundsException if index is negative or &gt;= length()
+   *         (while unspecified, this is a StringIndexOutOfBoundsException)
+   * @since 1.5
+   */
+  public synchronized int codePointBefore(int index)
+  {
+    // Use the CharSequence overload as we get better range checking
+    // this way.
+    return Character.codePointBefore(this, index);
+  }
+
+  /**
    * Copies characters from this String starting at a specified start index,
    * ending at a specified stop index, to a character array starting at
    * a specified destination begin index.
@@ -631,21 +665,26 @@ public final class String
 	ByteBuffer bbuf = cse.encode(CharBuffer.wrap(value, offset, count));
 	if(bbuf.hasArray())
 	  return bbuf.array();
-
+	
 	// Doubt this will happen. But just in case.
 	byte[] bytes = new byte[bbuf.remaining()];
 	bbuf.get(bytes);
 	return bytes;
-
-      } catch(IllegalCharsetNameException e){
-	  throw new UnsupportedEncodingException("Encoding: "+enc+
-						 " not found.");
-      } catch(UnsupportedCharsetException e){
-	  throw new UnsupportedEncodingException("Encoding: "+enc+
-						 " not found.");
-      } catch(CharacterCodingException e){
-	  // XXX - Ignore coding exceptions? They shouldn't really happen.
-	  return null;
+      } 
+    catch(IllegalCharsetNameException e)
+      {
+	throw new UnsupportedEncodingException("Encoding: " + enc
+					       + " not found.");
+      } 
+    catch(UnsupportedCharsetException e)
+      {
+	throw new UnsupportedEncodingException("Encoding: " + enc
+					       + " not found.");
+      } 
+    catch(CharacterCodingException e)
+      {
+	// This shouldn't ever happen.
+	throw (InternalError) new InternalError().initCause(e);
       }	  
   }
 
@@ -729,6 +768,26 @@ public final class String
   }
 
   /**
+   * Compares the given CharSequence to this String. This is true if
+   * the CharSequence has the same content as this String at this
+   * moment.
+   *
+   * @param seq the CharSequence to compare to
+   * @return true if CharSequence has the same character sequence
+   * @throws NullPointerException if the given CharSequence is null
+   * @since 1.5
+   */
+  public boolean contentEquals(CharSequence seq)
+  {
+    if (seq.length() != count)
+      return false;
+    for (int i = 0; i < count; ++i)
+      if (value[offset + i] != seq.charAt(i))
+	return false;
+    return true;
+  }
+
+  /**
    * Compares a String to this String, ignoring case. This does not handle
    * multi-character capitalization exceptions; instead the comparison is
    * made on a character-by-character basis, and is true if:<br><ul>
@@ -1664,6 +1723,49 @@ public final class String
   }
 
   /**
+   * Return the number of code points between two indices in the
+   * <code>StringBuffer</code>.  An unpaired surrogate counts as a
+   * code point for this purpose.  Characters outside the indicated
+   * range are not examined, even if the range ends in the middle of a
+   * surrogate pair.
+   *
+   * @param start the starting index
+   * @param end one past the ending index
+   * @return the number of code points
+   * @since 1.5
+   */
+  public synchronized int codePointCount(int start, int end)
+  {
+    if (start < 0 || end >= count || start > end)
+      throw new StringIndexOutOfBoundsException();
+
+    start += offset;
+    end += offset;
+    int count = 0;
+    while (start < end)
+      {
+	char base = value[start];
+	if (base < Character.MIN_HIGH_SURROGATE
+	    || base > Character.MAX_HIGH_SURROGATE
+	    || start == end
+	    || start == count
+	    || value[start + 1] < Character.MIN_LOW_SURROGATE
+	    || value[start + 1] > Character.MAX_LOW_SURROGATE)
+	  {
+	    // Nothing.
+	  }
+	else
+	  {
+	    // Surrogate pair.
+	    ++start;
+	  }
+	++start;
+	++count;
+      }
+    return count;
+  }
+
+  /**
    * Helper function used to detect which characters have a multi-character
    * uppercase expansion. Note that this is only used in locations which
    * track one-to-many capitalization (java.lang.Character does not do this).