added Utf8

std/haxe/ImportAll.hx

@@ -139,6 +139,7 @@ import neko.Lib;
 import neko.Socket;
 import neko.Stack;
 import neko.Sys;
+import neko.Utf8;
 import neko.Web;
 
 import neko.db.Connection;

std/neko/Utf8.hx

@@ -0,0 +1,94 @@
+/*
+ * Copyright (c) 2005, The haXe Project Contributors
+ * All rights reserved.
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ *   - Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   - Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE HAXE PROJECT CONTRIBUTORS "AS IS" AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL THE HAXE PROJECT CONTRIBUTORS BE LIABLE FOR
+ * ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+ * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+ * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
+ */
+package neko;
+
+class Utf8 {
+
+	public static function encode( s : String ) : String {
+		s = untyped s.__s;
+		var sl = untyped __dollar__ssize(s);
+		var buf = utf8_buf_alloc( sl );
+		var i = 0;
+		while( i < sl ) {
+			utf8_buf_add(buf,untyped __dollar__sget(s,i));
+			i += 1;
+		}
+		return new String( utf8_buf_content(buf) );
+	}
+
+	public static function decode( s : String ) : String {
+		s = untyped s.__s;
+		var sl = untyped __dollar__ssize(s);
+		var ret = untyped __dollar__smake(sl);
+		var i = 0;
+		utf8_iter(s,function(c) {
+			// euro symbol
+			if( c == 8364 )
+				c = 164;
+			else if( c > 255 )
+				throw "Utf8::decode invalid character ("+c+")";
+			untyped __dollar__sset(ret,i,c);
+			i += 1;
+		});
+		return new String( untyped __dollar__ssub(ret,0,i) );
+	}
+
+	public static function iter( s : String, chars : Int -> Void ) {
+		utf8_iter(untyped s.__s,chars);
+	}
+
+	public static function charCodeAt( s : String, index : Int ) : Int {
+		return utf8_get(untyped s.__s,index);
+	}
+
+	public static function validate( s : String ) : Bool {
+		return utf8_validate(untyped s.__s);
+	}
+
+	public static function length( s : String ) : Int {
+		return utf8_length(untyped s.__s);
+	}
+
+	public static function compare( a : String, b : String ) : Int {
+		return utf8_compare(untyped a.__s,untyped b.__s);
+	}
+
+	public static function sub( s : String, pos : Int, len : Int ) : String {
+		return new String(utf8_sub(untyped s.__s,pos,len));
+	}
+
+	static var utf8_buf_alloc = Lib.load("std","utf8_buf_alloc",1);
+	static var utf8_buf_add = Lib.load("std","utf8_buf_add",2);
+	static var utf8_buf_content = Lib.load("std","utf8_buf_content",1);
+	static var utf8_buf_length = Lib.load("std","utf8_buf_length",1);
+	static var utf8_iter = Lib.load("std","utf8_iter",2);
+
+	static var utf8_get = Lib.load("std","utf8_get",2);
+	static var utf8_validate = Lib.load("std","utf8_validate",1);
+	static var utf8_length = Lib.load("std","utf8_length",1);
+	static var utf8_compare = Lib.load("std","utf8_compare",2);
+	static var utf8_sub = Lib.load("std","utf8_sub",3);
+
+}