com.sshtools.common.util.URLUTF8Encoder Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of maverick-utils Show documentation
Utililty classes for Maverick Synergy and Maverick Legacy SSH APIs
The newest version!
package com.sshtools.common.util;

/*-
 * #%L
 * Utils
 * %%
 * Copyright (C) 2002 - 2024 JADAPTIVE Limited
 * %%
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU Lesser General Public License as
 * published by the Free Software Foundation, either version 3 of the
 * License, or (at your option) any later version.
 * 
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Lesser Public License for more details.
 * 
 * You should have received a copy of the GNU General Lesser Public
 * License along with this program.  If not, see
 * .
 * #L%
 */

/**
 * Provides a method to encode any string into a URL-safe form. Non-ASCII
 * characters are first encoded as sequences of two or three bytes, using the
 * UTF-8 algorithm, before being encoded as %HH escapes.
 */
public class URLUTF8Encoder {

    final static String[] hex = { "%00", "%01", "%02", "%03", "%04", "%05", "%06", "%07", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%08", "%09", "%0A", "%0B", "%0C", "%0D", "%0E", "%0F", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%10", "%11", "%12", "%13", "%14", "%15", "%16", "%17", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%18", "%19", "%1A", "%1B", "%1C", "%1D", "%1E", "%1F", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%20", "%21", "%22", "%23", "%24", "%25", "%26", "%27", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%28", "%29", "%2A", "%2B", "%2C", "%2D", "%2E", "%2F", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%30", "%31", "%32", "%33", "%34", "%35", "%36", "%37", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%38", "%39", "%3A", "%3B", "%3C", "%3D", "%3E", "%3F", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%40", "%41", "%42", "%43", "%44", "%45", "%46", "%47", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%48", "%49", "%4A", "%4B", "%4C", "%4D", "%4E", "%4F", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%50", "%51", "%52", "%53", "%54", "%55", "%56", "%57", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%58", "%59", "%5A", "%5B", "%5C", "%5D", "%5E", "%5F", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%60", "%61", "%62", "%63", "%64", "%65", "%66", "%67", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%68", "%69", "%6A", "%6B", "%6C", "%6D", "%6E", "%6F", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%70", "%71", "%72", "%73", "%74", "%75", "%76", "%77", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%78", "%79", "%7A", "%7B", "%7C", "%7D", "%7E", "%7F", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%80", "%81", "%82", "%83", "%84", "%85", "%86", "%87", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%88", "%89", "%8A", "%8B", "%8C", "%8D", "%8E", "%8F", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%90", "%91", "%92", "%93", "%94", "%95", "%96", "%97", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%98", "%99", "%9A", "%9B", "%9C", "%9D", "%9E", "%9F", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%A0", "%A1", "%A2", "%A3", "%A4", "%A5", "%A6", "%A7", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%A8", "%A9", "%AA", "%AB", "%AC", "%AD", "%AE", "%AF", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%B0", "%B1", "%B2", "%B3", "%B4", "%B5", "%B6", "%B7", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%B8", "%B9", "%BA", "%BB", "%BC", "%BD", "%BE", "%BF", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%C0", "%C1", "%C2", "%C3", "%C4", "%C5", "%C6", "%C7", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%C8", "%C9", "%CA", "%CB", "%CC", "%CD", "%CE", "%CF", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%D0", "%D1", "%D2", "%D3", "%D4", "%D5", "%D6", "%D7", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%D8", "%D9", "%DA", "%DB", "%DC", "%DD", "%DE", "%DF", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%E0", "%E1", "%E2", "%E3", "%E4", "%E5", "%E6", "%E7", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%E8", "%E9", "%EA", "%EB", "%EC", "%ED", "%EE", "%EF", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%F0", "%F1", "%F2", "%F3", "%F4", "%F5", "%F6", "%F7", //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
        "%F8", "%F9", "%FA", "%FB", "%FC", "%FD", "%FE", "%FF" //$NON-NLS-1$ //$NON-NLS-2$ //$NON-NLS-3$ //$NON-NLS-4$ //$NON-NLS-5$ //$NON-NLS-6$ //$NON-NLS-7$ //$NON-NLS-8$
    };

    /**
     * Encode a string to the "x-www-form-urlencoded" form, enhanced with the
     * UTF-8-in-URL proposal. This is what happens:
     * 
     * 
     * 
     * 
     * The ASCII characters 'a' through 'z', 'A' through 'Z', and '0' through
     * '9' remain the same.
     * 
     * 

     * 
     * The unreserved characters - _ . ! ~ * ' ( ) remain the same.
     * 
     * 

     * 
     * The space character ' ' is converted into a plus sign '+'.
     * 
     * 

     * 
     * All other ASCII characters are converted into the 3-character string
     * "%xy", where xy is the two-digit hexadecimal representation of the
     * character code
     * 
     * 

     * 
     * All non-ASCII characters are encoded in two steps: first to a sequence of
     * 2 or 3 bytes, using the UTF-8 algorithm; secondly each of these bytes is
     * encoded as "%xx".
     * 
     * 
     * @param s The string to be encoded
     * @return The encoded string
     */
    public static String encode(String s, boolean encodePathSeperator) {
        StringBuffer sbuf = new StringBuffer();
        int len = s.length();
        for (int i = 0; i < len; i++) {
            int ch = s.charAt(i);

            if (ch == '/' && !encodePathSeperator) {
                sbuf.append((char) ch);
                continue;
            }
            if ('A' <= ch && ch <= 'Z') { // 'A'..'Z'
                sbuf.append((char) ch);
            } else if ('a' <= ch && ch <= 'z') { // 'a'..'z'
                sbuf.append((char) ch);
            } else if ('0' <= ch && ch <= '9') { // '0'..'9'
                sbuf.append((char) ch);
            } else if (ch == ' ') { // space
                sbuf.append("%20"); //$NON-NLS-1$
            } else if (ch == '-' || ch == '_' // unreserved
                || ch == '.' || ch == '!' || ch == '~' || ch == '*' || ch == '\'' || ch == '(' || ch == ')') {
                sbuf.append((char) ch);
            } else if (ch <= 0x007f) { // other ASCII
                sbuf.append(hex[ch]);
            } else if (ch <= 0x07FF) { // non-ASCII <= 0x7FF
                sbuf.append(hex[0xc0 | (ch >> 6)]);
                sbuf.append(hex[0x80 | (ch & 0x3F)]);
            } else { // 0x7FF < ch <= 0xFFFF
                sbuf.append(hex[0xe0 | (ch >> 12)]);
                sbuf.append(hex[0x80 | ((ch >> 6) & 0x3F)]);
                sbuf.append(hex[0x80 | (ch & 0x3F)]);
            }
        }
        return sbuf.toString();
    }

    public static String decode(String s) {
        StringBuffer sbuf = new StringBuffer();
        int l = s.length();
        int ch = -1;
        int b, sumb = 0;
        for (int i = 0, more = -1; i < l; i++) {
            /* Get next byte b from URL segment s */
            switch (ch = s.charAt(i)) {
                case '%':
                    ch = s.charAt(++i);
                    int hb = (Character.isDigit((char) ch) ? ch - '0' : 10 + Character.toLowerCase((char) ch) - 'a') & 0xF;
                    ch = s.charAt(++i);
                    int lb = (Character.isDigit((char) ch) ? ch - '0' : 10 + Character.toLowerCase((char) ch) - 'a') & 0xF;
                    b = (hb << 4) | lb;
                    break;
                case '+':
                    b = ' ';
                    break;
                default:
                    b = ch;
            }
            /* Decode byte b as UTF-8, sumb collects incomplete chars */
            if ((b & 0xc0) == 0x80) { // 10xxxxxx (continuation byte)
                sumb = (sumb << 6) | (b & 0x3f); // Add 6 bits to sumb
                if (--more == 0)
                    sbuf.append((char) sumb); // Add char to sbuf
            } else if ((b & 0x80) == 0x00) { // 0xxxxxxx (yields 7 bits)
                sbuf.append((char) b); // Store in sbuf
            } else if ((b & 0xe0) == 0xc0) { // 110xxxxx (yields 5 bits)
                sumb = b & 0x1f;
                more = 1; // Expect 1 more byte
            } else if ((b & 0xf0) == 0xe0) { // 1110xxxx (yields 4 bits)
                sumb = b & 0x0f;
                more = 2; // Expect 2 more bytes
            } else if ((b & 0xf8) == 0xf0) { // 11110xxx (yields 3 bits)
                sumb = b & 0x07;
                more = 3; // Expect 3 more bytes
            } else if ((b & 0xfc) == 0xf8) { // 111110xx (yields 2 bits)
                sumb = b & 0x03;
                more = 4; // Expect 4 more bytes
            } else /* if ((b & 0xfe) == 0xfc) */{ // 1111110x (yields 1 bit)
                sumb = b & 0x01;
                more = 5; // Expect 5 more bytes
            }
            /* We don't test if the UTF-8 encoding is well-formed */
        }
        return sbuf.toString();
    }
}