com.sshtools.util.URLUTF8Encoder Maven / Gradle / Ivy
The newest version!
/**
* Copyright 2003-2016 SSHTOOLS Limited. All Rights Reserved.
*
* For product documentation visit https://www.sshtools.com/
*
* This file is part of J2SSH Maverick.
*
* J2SSH Maverick 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.
*
* J2SSH Maverick 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 Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with J2SSH Maverick. If not, see
* -
*
* 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();
}
}