added Ustr code and Java 5 support to mutable-string branch

git-svn-id: http://svn.codehaus.org/jruby/branches/mutable-string@2238 961051c9-f516-0410-bf72-c9f7e237a7b7
iconara · Sep 26, 2006 · e2380cd · e2380cd
1 parent e336029
commit e2380cd
Show file tree

Hide file tree

Showing 5 changed files with 1,535 additions and 8 deletions.
diff --git a/.settings/org.eclipse.jdt.core.prefs b/.settings/org.eclipse.jdt.core.prefs
@@ -1,12 +1,12 @@
-#Mon Jan 02 00:48:54 CST 2006
+#Mon Sep 25 23:02:20 CDT 2006
 eclipse.preferences.version=1
-org.eclipse.jdt.core.compiler.codegen.inlineJsrBytecode=disabled
-org.eclipse.jdt.core.compiler.codegen.targetPlatform=1.4
+org.eclipse.jdt.core.compiler.codegen.inlineJsrBytecode=enabled
+org.eclipse.jdt.core.compiler.codegen.targetPlatform=1.5
 org.eclipse.jdt.core.compiler.codegen.unusedLocal=preserve
-org.eclipse.jdt.core.compiler.compliance=1.4
+org.eclipse.jdt.core.compiler.compliance=1.5
 org.eclipse.jdt.core.compiler.debug.lineNumber=generate
 org.eclipse.jdt.core.compiler.debug.localVariable=generate
 org.eclipse.jdt.core.compiler.debug.sourceFile=generate
 org.eclipse.jdt.core.compiler.problem.assertIdentifier=error
-org.eclipse.jdt.core.compiler.problem.enumIdentifier=warning
-org.eclipse.jdt.core.compiler.source=1.4
+org.eclipse.jdt.core.compiler.problem.enumIdentifier=error
+org.eclipse.jdt.core.compiler.source=1.5
diff --git a/.settings/org.eclipse.jdt.ui.prefs b/.settings/org.eclipse.jdt.ui.prefs
@@ -1,3 +1,3 @@
-#Thu Sep 29 15:25:20 CDT 2005
+#Mon Sep 25 23:02:20 CDT 2006
 eclipse.preferences.version=1
-internal.default.compliance=user
+internal.default.compliance=default
diff --git a/src/org/jruby/util/string/UcharIterator.java b/src/org/jruby/util/string/UcharIterator.java
@@ -0,0 +1,78 @@
+package org.jruby.util.string;
+
+/**
+ * UcharIterator - an Iterator on Unicode characters in a UTF-8 byte array.
+ *
+ * <p>A conventional Iterator, remove() is not supported, and there's an extra
+ * nextChar() method that returns a naked int as opposed to a wrapped Integer.
+ * </p>
+ *
+ * @author Tim Bray
+ * @see org.jruby.util.string.Ustr
+ */
+
+public class UcharIterator implements java.util.Iterator, java.io.Serializable {
+  private Ustr u;
+  private int next;
+
+  /**
+   * Creates a new UcharIterator starting at an offset in a buffer.
+   *
+   * @param s the byte array containing UTF-8-encoded Unicode characters.
+   * @param offset how far into the array to start iterating.
+   */
+  public UcharIterator(byte[] s, int offset) {
+    u = new Ustr(s, offset);
+    u.prepareNext();
+    next = u.nextChar();
+  }
+
+  /**
+   * Tests whether there are any more characters in the buffer.
+   *
+   * @return true or false depending on whether there are more characters.
+   */
+  public boolean hasNext() {
+    return (next != 0);
+  }
+
+  /**
+   * Retrieve the next Unicode character from a UTF-8 byte buffer, wrapped
+   * in an Integer object. Throws NoSuchElementException if hasNext
+   * would return false.
+   *
+   * @return the next Unicode character as a java.lang.Integer
+   * @throws NoSuchElementException
+   */
+  public Object next() {
+    if (next == 0)
+      throw new java.util.NoSuchElementException("Ran off end of array");
+    Integer i = new Integer(next);
+    next = u.nextChar();
+    return i;
+  }
+
+  /**
+   * Retrieve the next Unicode character from a UTF-8 byte buffer and return
+   * it as an int.  Once the null-termination is hit, returns 0 as many times
+   * as you want to call it.
+   *
+   * @return the next Unicode character as an int, 0 on end-of-string.
+   */
+  public int nextChar() {
+    int i = next;
+    if (i != 0)
+      next = u.nextChar();
+    return i;
+  }
+
+  /**
+   * Throws an UnsupportedOperationException.
+   *
+   * @throws UnsupportedOperationException
+   */
+  public void remove() {
+    throw new UnsupportedOperationException("UcharIterator doesn't remove");
+  }
+
+}