Source for org.jfree.formula.util.URLEncoder

   1: /**
   2:  * =========================================
   3:  * LibFormula : a free Java formula library
   4:  * =========================================
   5:  *
   6:  * Project Info:  http://reporting.pentaho.org/libformula/
   7:  *
   8:  * (C) Copyright 2006-2007, by Pentaho Corporation and Contributors.
   9:  *
  10:  * This library is free software; you can redistribute it and/or modify it under the terms
  11:  * of the GNU Lesser General Public License as published by the Free Software Foundation;
  12:  * either version 2.1 of the License, or (at your option) any later version.
  13:  *
  14:  * This library is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY;
  15:  * without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
  16:  * See the GNU Lesser General Public License for more details.
  17:  *
  18:  * You should have received a copy of the GNU Lesser General Public License along with this
  19:  * library; if not, write to the Free Software Foundation, Inc., 59 Temple Place, Suite 330,
  20:  * Boston, MA 02111-1307, USA.
  21:  *
  22:  * [Java is a trademark or registered trademark of Sun Microsystems, Inc.
  23:  * in the United States and other countries.]
  24:  *
  25:  *
  26:  * ------------
  27:  * $Id: URLEncoder.java,v 1.2 2007/04/01 13:51:58 taqua Exp $
  28:  * ------------
  29:  * (C) Copyright 2006-2007, by Pentaho Corporation.
  30:  */
  31: 
  32: package org.jfree.formula.util;
  33: 
  34: import java.io.UnsupportedEncodingException;
  35: 
  36: /**
  37:  * Creation-Date: Jan 22, 2007, 4:36:38 PM
  38:  *
  39:  * @author Thomas Morgner
  40:  */
  41: public class URLEncoder
  42: {
  43:   private URLEncoder()
  44:   {
  45:   }
  46: 
  47:   private final static String[] hex = {
  48:     "%00", "%01", "%02", "%03", "%04", "%05", "%06", "%07",
  49:     "%08", "%09", "%0A", "%0B", "%0C", "%0D", "%0E", "%0F",
  50:     "%10", "%11", "%12", "%13", "%14", "%15", "%16", "%17",
  51:     "%18", "%19", "%1A", "%1B", "%1C", "%1D", "%1E", "%1F",
  52:     "%20", "%21", "%22", "%23", "%24", "%25", "%26", "%27",
  53:     "%28", "%29", "%2A", "%2B", "%2C", "%2D", "%2E", "%2F",
  54:     "%30", "%31", "%32", "%33", "%34", "%35", "%36", "%37",
  55:     "%38", "%39", "%3A", "%3B", "%3C", "%3D", "%3E", "%3F",
  56:     "%40", "%41", "%42", "%43", "%44", "%45", "%46", "%47",
  57:     "%48", "%49", "%4A", "%4B", "%4C", "%4D", "%4E", "%4F",
  58:     "%50", "%51", "%52", "%53", "%54", "%55", "%56", "%57",
  59:     "%58", "%59", "%5A", "%5B", "%5C", "%5D", "%5E", "%5F",
  60:     "%60", "%61", "%62", "%63", "%64", "%65", "%66", "%67",
  61:     "%68", "%69", "%6A", "%6B", "%6C", "%6D", "%6E", "%6F",
  62:     "%70", "%71", "%72", "%73", "%74", "%75", "%76", "%77",
  63:     "%78", "%79", "%7A", "%7B", "%7C", "%7D", "%7E", "%7F",
  64:     "%80", "%81", "%82", "%83", "%84", "%85", "%86", "%87",
  65:     "%88", "%89", "%8A", "%8B", "%8C", "%8D", "%8E", "%8F",
  66:     "%90", "%91", "%92", "%93", "%94", "%95", "%96", "%97",
  67:     "%98", "%99", "%9A", "%9B", "%9C", "%9D", "%9E", "%9F",
  68:     "%A0", "%A1", "%A2", "%A3", "%A4", "%A5", "%A6", "%A7",
  69:     "%A8", "%A9", "%AA", "%AB", "%AC", "%AD", "%AE", "%AF",
  70:     "%B0", "%B1", "%B2", "%B3", "%B4", "%B5", "%B6", "%B7",
  71:     "%B8", "%B9", "%BA", "%BB", "%BC", "%BD", "%BE", "%BF",
  72:     "%C0", "%C1", "%C2", "%C3", "%C4", "%C5", "%C6", "%C7",
  73:     "%C8", "%C9", "%CA", "%CB", "%CC", "%CD", "%CE", "%CF",
  74:     "%D0", "%D1", "%D2", "%D3", "%D4", "%D5", "%D6", "%D7",
  75:     "%D8", "%D9", "%DA", "%DB", "%DC", "%DD", "%DE", "%DF",
  76:     "%E0", "%E1", "%E2", "%E3", "%E4", "%E5", "%E6", "%E7",
  77:     "%E8", "%E9", "%EA", "%EB", "%EC", "%ED", "%EE", "%EF",
  78:     "%F0", "%F1", "%F2", "%F3", "%F4", "%F5", "%F6", "%F7",
  79:     "%F8", "%F9", "%FA", "%FB", "%FC", "%FD", "%FE", "%FF"
  80:   };
  81: 
  82:   /**
  83:    * Encode a string according to RFC 1738.
  84:    * <p/>
  85:    * <quote> "...Only alphanumerics [0-9a-zA-Z], the special characters "$-_.+!*'()," [not
  86:    * including the quotes - ed], and reserved characters used for their reserved purposes
  87:    * may be used unencoded within a URL."</quote>
  88:    * <p/>
  89:    * <ul> <li><p>The ASCII characters 'a' through 'z', 'A' through 'Z', and '0' through
  90:    * '9' remain the same.
  91:    * <p/>
  92:    * <li><p>The unreserved characters - _ . ! ~ * ' ( ) remain the same.
  93:    * <p/>
  94:    * <li><p>All other ASCII characters are converted into the 3-character string "%xy",
  95:    * where xy is the two-digit hexadecimal representation of the character code
  96:    * <p/>
  97:    * <li><p>All non-ASCII characters are encoded in two steps: first to a sequence of 2 or
  98:    * 3 bytes, using the UTF-8 algorithm; secondly each of these bytes is encoded as "%xx".
  99:    * </ul>
 100:    *
 101:    * @param s The string to be encoded
 102:    * @return The encoded string
 103:    */
 104:   public static String encodeUTF8 (final String s)
 105:   {
 106:     final StringBuffer sbuf = new StringBuffer();
 107:     final char[] sChars = s.toCharArray();
 108:     final int len = sChars.length;
 109:     for (int i = 0; i < len; i++)
 110:     {
 111:       final int ch = sChars[i];
 112:       if ('A' <= ch && ch <= 'Z')
 113:       {        // 'A'..'Z'
 114:         sbuf.append((char) ch);
 115:       }
 116:       else if ('a' <= ch && ch <= 'z')
 117:       {    // 'a'..'z'
 118:         sbuf.append((char) ch);
 119:       }
 120:       else if ('0' <= ch && ch <= '9')
 121:       {    // '0'..'9'
 122:         sbuf.append((char) ch);
 123:       }
 124:       else if (ch == '-' || ch == '_'        // unreserved
 125:               || ch == '.' || ch == '!'
 126:               || ch == '~' || ch == '*'
 127:               || ch == '\'' || ch == '('
 128:               || ch == ')')
 129:       {
 130:         sbuf.append((char) ch);
 131:       }
 132:       else if (ch <= 0x007f)
 133:       {        // other ASCII
 134:         sbuf.append(hex[ch]);
 135:       }
 136:       else if (ch <= 0x07FF)
 137:       {        // non-ASCII <= 0x7FF
 138:         sbuf.append(hex[0xc0 | (ch >> 6)]);
 139:         sbuf.append(hex[0x80 | (ch & 0x3F)]);
 140:       }
 141:       else
 142:       {                    // 0x7FF < ch <= 0xFFFF
 143:         sbuf.append(hex[0xe0 | (ch >> 12)]);
 144:         sbuf.append(hex[0x80 | ((ch >> 6) & 0x3F)]);
 145:         sbuf.append(hex[0x80 | (ch & 0x3F)]);
 146:       }
 147:     }
 148:     return sbuf.toString();
 149:   }
 150: 
 151:   private static String encodeBytes (final byte[] s)
 152:   {
 153:     final StringBuffer sbuf = new StringBuffer();
 154:     final int len = s.length;
 155:     for (int i = 0; i < len; i++)
 156:     {
 157:       final int ch = (s[i] & 0xff);
 158:       if ('A' <= ch && ch <= 'Z')
 159:       {        // 'A'..'Z'
 160:         sbuf.append((char) ch);
 161:       }
 162:       else if ('a' <= ch && ch <= 'z')
 163:       {    // 'a'..'z'
 164:         sbuf.append((char) ch);
 165:       }
 166:       else if ('0' <= ch && ch <= '9')
 167:       {    // '0'..'9'
 168:         sbuf.append((char) ch);
 169:       }
 170:       else if (ch == '-' || ch == '_'        // unreserved
 171:               || ch == '.' || ch == '!'
 172:               || ch == '~' || ch == '*'
 173:               || ch == '\'' || ch == '('
 174:               || ch == ')')
 175:       {
 176:         sbuf.append((char) ch);
 177:       }
 178:       else
 179:       {        // other ASCII
 180:         sbuf.append(hex[ch]);
 181:       }
 182:     }
 183:     return sbuf.toString();
 184:   }
 185: 
 186:   public static String encode (final String s, final String encoding)
 187:           throws UnsupportedEncodingException
 188:   {
 189:     if (encoding.equalsIgnoreCase("utf-8"))
 190:     {
 191:       return encodeUTF8(s);
 192:     }
 193: 
 194:     return encodeBytes(s.getBytes(encoding));
 195:   }
 196: 
 197: }