Java UTF8 utf8StringSizeInBytes(String s)

Description

Compute the size in bytes of the given string encoded as utf8.

License

Open Source License

Declaration

public static int utf8StringSizeInBytes(String s) 

Method Source Code

//package com.java2s;
// Use of this source code is governed by a BSD-style license that can be

public class Main {
    /**//from www .java  2 s . c o m
     * Compute the size in bytes of the given string encoded as utf8.
     */
    public static int utf8StringSizeInBytes(String s) {
        int res = 0;
        for (int i = 0; i < s.length(); ++i) {
            char c = s.charAt(i);
            int codepoint = c;
            if (isSurrogate(c)) {
                i++;
                char c2 = s.charAt(i);
                codepoint = Character.toCodePoint(c, c2);
            }
            res += 1;
            if (codepoint > 0x7f) {
                res += 1;
                if (codepoint > 0x7ff) {
                    res += 1;
                    if (codepoint > 0xffff) {
                        res += 1;
                        if (codepoint > 0x1fffff) {
                            res += 1;
                            if (codepoint > 0x3ffffff) {
                                res += 1;
                            }
                        }
                    }
                }
            }
        }
        return res;
    }

    /**
     * Determines if the given {@code char} value is a Unicode <i>surrogate code unit</i>. See
     * {@link Character#isSurrogate}. Extracting here because the method only exists at API level
     * 19.
     */
    private static boolean isSurrogate(char c) {
        return c >= Character.MIN_SURROGATE
                && c < (Character.MAX_SURROGATE + 1);
    }
}

Related

1. utf8Length(byte[] buffer, int str, int len)
2. utf8Replace(String str)
3. utf8SafeCEscape(String src)
4. utf8String(String... strs)
5. utf8StringLength(final CharSequence sequence)
6. utf8StringToByteArray(String dataString)
7. utf8StringToBytes(String string)
8. utf8ToString(byte[] data)
9. utf8URLDecode(String input)