Trouble Percent-Encoding Spaces in Java

Posted by behrk2 on Stack Overflow See other posts from Stack Overflow or by behrk2
Published on 2010-03-26T17:49:36Z Indexed on 2010/03/26 17:53 UTC
Read the original article Hit count: 368

Filed under:
|
|
|

Hi Everyone,

I am using the URLUTF8Encoder.java class from W3C (www.w3.org/International/URLUTF8Encoder.java).

Currently, it will encode any blank spaces ' ' into plus signs '+'.

I am having difficulty modifying the code to percent-encode the blank space into '%20'. Unfortunately, I am not too familiar with hex. Can anyone help me out? I need to modify this snippet...

else if (ch == ' ') { // space
                sbuf.append('+');

in the following code:

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

public static String encode(String s) {
        StringBuffer sbuf = new StringBuffer();
        int len = s.length();
        for (int i = 0; i < len; i++) {
            int ch = s.charAt(i);
            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('+');
            } 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();
    }

Thanks!

© Stack Overflow or respective owner

Related posts about java

Related posts about percent