Java URL Decode percentDecode(String str, boolean plusToSpace)

Description

Decodes strings that have been <a href="http://tools.ietf.org/html/rfc3986#section-2.1">percent encoded</a>.

License

Open Source License

Parameter

Parameter	Description
str	the input string to decode
plusToSpace	true if the plus sign ("+") should be converted to a single space (" ")

Return

the decoded string. If no changes need to be made to str , it will be returned as is.

Declaration

public static String percentDecode(String str, boolean plusToSpace)

Method Source Code

//package com.java2s;
/* Copyright (C) 2013-2014 Ian Teune <ian.teune@gmail.com>
 * //from  w w  w  .  j a v  a 2s  . com
 * Permission is hereby granted, free of charge, to any person obtaining
 * a copy of this software and associated documentation files (the
 * "Software"), to deal in the Software without restriction, including
 * without limitation the rights to use, copy, modify, merge, publish,
 * distribute, sublicense, and/or sell copies of the Software, and to
 * permit persons to whom the Software is furnished to do so, subject to
 * the following conditions:
 * 
 * The above copyright notice and this permission notice shall be
 * included in all copies or substantial portions of the Software.
 * 
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
 * LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
 * OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
 * WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 */

public class Main {
    private static final byte[] BYTES = new byte[16];

    /**
     * Same as
     * {@link #percentDecode(String, boolean) percentDecode(str, false)}.
     */
    public static String percentDecode(String str) {
        return percentDecode(str, false);
    }

    /**
     * Decodes strings that have been
     * <a href="http://tools.ietf.org/html/rfc3986#section-2.1">percent
     * encoded</a>. Decoding is always performed using {@code UTF-8} (there is
     * currently no way of changing this).
     * <p>
     * Invalid percent encoded sequences or sequences that represent invalid
     * {@code UTF-8} will cause an {@code IllegalArgumentException} to be
     * thrown. The only exception to this are
     * <a href="http://en.wikipedia.org/wiki/UTF-8#Overlong_encodings">overlong
     * encodings</a>, which are permitted and will be decoded correctly.
     * <p>
     * This method is very similar to
     * {@link java.net.URLDecoder#decode(String, String) URLDecoder.decode(...)},
     * but differs in the following ways:
     * <ul>
     * <li>Decoding <i>always</i> uses {@code UTF-8}, whereas {@code URLDecoder}
     * allows any encoding.</li>
     * <li>The plus ("+") character is converted to a space (" ") <i>only</i>
     * if {@code plusToSpace} is true, whereas {@code URLDecoder} always
     * converts a plus into a space.</li>
     * <li>For heavily percent encoded input, this method will likely perform
     * better than {@code URLDecoder} as this method directly decodes the
     * {@code UTF-8}.</li>
     * </ul>
     *
     * @param str the input string to decode
     * @param plusToSpace true if the plus sign ("+") should be converted to a
     * single space (" ")
     * @return the decoded string. If no changes need to be made to {@code str},
     * it will be returned as is.
     */
    public static String percentDecode(String str, boolean plusToSpace) {
        char[] buf = null;
        int count = 0; //current index in buf
        final int len = str.length();
        for (int i = 0; i < len;) {
            char c = str.charAt(i);
            if (c == '%') {
                if (i + 2 >= len) {
                    throw new IllegalArgumentException();
                }
                if (buf == null) {
                    buf = new char[len];
                    str.getChars(0, i, buf, 0);
                    count = i;
                }
                int b = (toDigit(str.charAt(i + 1)) << 4) | toDigit(str.charAt(i + 2));
                i += 3;
                if (b > 0x7F) {
                    int bytes = BYTES[(b >> 3) & 0x0F];
                    if (bytes == 0) {
                        throw new IllegalArgumentException();
                    }
                    assert bytes >= 2 : bytes;

                    b &= (0x80 >> bytes) - 1;
                    b <<= (bytes - 1) * 6;

                    for (bytes--; bytes > 0; bytes--) {
                        if (i + 2 >= len || str.charAt(i) != '%') {
                            throw new IllegalArgumentException();
                        }
                        int n = (toDigit(str.charAt(i + 1)) << 4) | toDigit(str.charAt(i + 2));
                        if ((n & 0xC0) != 0x80) {
                            throw new IllegalArgumentException();
                        }

                        b |= (n & 0x3F) << ((bytes - 1) * 6);
                        i += 3;
                    }
                }
                count += Character.toChars(b, buf, count);
            } else {
                if (c == '+' && plusToSpace) {
                    if (buf == null) {
                        buf = new char[len];
                        str.getChars(0, i, buf, 0);
                        count = i;
                    }
                    buf[count++] = ' ';
                } else if (buf != null) {
                    buf[count++] = c;
                }
                i++;
            }
        }

        return buf != null ? new String(buf, 0, count) : str;
    }

    private static int toDigit(int c) {
        if (c > '9') {
            if (c > 'F') {
                if (c >= 'a' && c <= 'f') {
                    return c - 'a' + 10;
                }
            } else if (c >= 'A') {
                return c - 'A' + 10;
            }
        } else if (c >= '0') {
            return c - '0';
        }
        throw new IllegalArgumentException();
    }
}