Java UTF16 Convert UTF16toUTF8(CharSequence s, int offset, int len, byte[] result, int resultOffset)

Description

Writes UTF8 into the byte array, starting at offset.

License

Apache License

Return

the number of bytes written

Declaration

public static int UTF16toUTF8(CharSequence s, int offset, int len,
        byte[] result, int resultOffset) 

Method Source Code

//package com.java2s;
/*/*from   w  w w . j  ava2  s .  c  o  m*/
 * 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.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

public class Main {
    /** Writes UTF8 into the byte array, starting at offset.  The caller should ensure that
     * there is enough space for the worst-case scenario.
     * @return the number of bytes written
     */
    public static int UTF16toUTF8(CharSequence s, int offset, int len,
            byte[] result, int resultOffset) {
        final int end = offset + len;

        int upto = resultOffset;
        for (int i = offset; i < end; i++) {
            final int code = (int) s.charAt(i);

            if (code < 0x80)
                result[upto++] = (byte) code;
            else if (code < 0x800) {
                result[upto++] = (byte) (0xC0 | (code >> 6));
                result[upto++] = (byte) (0x80 | (code & 0x3F));
            } else if (code < 0xD800 || code > 0xDFFF) {
                result[upto++] = (byte) (0xE0 | (code >> 12));
                result[upto++] = (byte) (0x80 | ((code >> 6) & 0x3F));
                result[upto++] = (byte) (0x80 | (code & 0x3F));
            } else {
                // surrogate pair
                // confirm valid high surrogate
                if (code < 0xDC00 && (i < end - 1)) {
                    int utf32 = (int) s.charAt(i + 1);
                    // confirm valid low surrogate and write pair
                    if (utf32 >= 0xDC00 && utf32 <= 0xDFFF) {
                        utf32 = ((code - 0xD7C0) << 10) + (utf32 & 0x3FF);
                        i++;
                        result[upto++] = (byte) (0xF0 | (utf32 >> 18));
                        result[upto++] = (byte) (0x80 | ((utf32 >> 12) & 0x3F));
                        result[upto++] = (byte) (0x80 | ((utf32 >> 6) & 0x3F));
                        result[upto++] = (byte) (0x80 | (utf32 & 0x3F));
                        continue;
                    }
                }
                // replace unpaired surrogate or out-of-order low surrogate
                // with substitution character
                result[upto++] = (byte) 0xEF;
                result[upto++] = (byte) 0xBF;
                result[upto++] = (byte) 0xBD;
            }
        }

        return upto - resultOffset;
    }
}

Related

1. toUTF16LEString(String input)