cdmlib-commons/src/main/java/eu/etaxonomy/cdm/common/UrlUtf8Coder.java

   1 /**
   2  * Provides a method to encode any string into a URL-safe
   3  * form.
   4  * Non-ASCII characters are first encoded as sequences of
   5  * two or three bytes, using the UTF-8 algorithm, before being
   6  * encoded as %HH escapes.
   7  *
   8  * Created: 17 April 1997
   9  * Author: Bert Bos <bert@w3.org>
  10  *
  11  * URLUTF8Encoder: http://www.w3.org/International/URLUTF8Encoder.java
  12  *
  13  * Copyright © 1997 World Wide Web Consortium, (Massachusetts
  14  * Institute of Technology, European Research Consortium for
  15  * Informatics and Mathematics, Keio University). All Rights Reserved.
  16  * This work is distributed under the W3C® Software License [1] in the
  17  * hope that it will be useful, but WITHOUT ANY WARRANTY; without even
  18  * the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR
  19  * PURPOSE.
  20  *
  21  * [1] http://www.w3.org/Consortium/Legal/2002/copyright-software-20021231
  22  */
  23 package eu.etaxonomy.cdm.common;
  24
  25 public class UrlUtf8Coder{
  26
  27   final static String[] hex = {
  28     "%00", "%01", "%02", "%03", "%04", "%05", "%06", "%07",
  29     "%08", "%09", "%0a", "%0b", "%0c", "%0d", "%0e", "%0f",
  30     "%10", "%11", "%12", "%13", "%14", "%15", "%16", "%17",
  31     "%18", "%19", "%1a", "%1b", "%1c", "%1d", "%1e", "%1f",
  32     "%20", "%21", "%22", "%23", "%24", "%25", "%26", "%27",
  33     "%28", "%29", "%2a", "%2b", "%2c", "%2d", "%2e", "%2f",
  34     "%30", "%31", "%32", "%33", "%34", "%35", "%36", "%37",
  35     "%38", "%39", "%3a", "%3b", "%3c", "%3d", "%3e", "%3f",
  36     "%40", "%41", "%42", "%43", "%44", "%45", "%46", "%47",
  37     "%48", "%49", "%4a", "%4b", "%4c", "%4d", "%4e", "%4f",
  38     "%50", "%51", "%52", "%53", "%54", "%55", "%56", "%57",
  39     "%58", "%59", "%5a", "%5b", "%5c", "%5d", "%5e", "%5f",
  40     "%60", "%61", "%62", "%63", "%64", "%65", "%66", "%67",
  41     "%68", "%69", "%6a", "%6b", "%6c", "%6d", "%6e", "%6f",
  42     "%70", "%71", "%72", "%73", "%74", "%75", "%76", "%77",
  43     "%78", "%79", "%7a", "%7b", "%7c", "%7d", "%7e", "%7f",
  44     "%80", "%81", "%82", "%83", "%84", "%85", "%86", "%87",
  45     "%88", "%89", "%8a", "%8b", "%8c", "%8d", "%8e", "%8f",
  46     "%90", "%91", "%92", "%93", "%94", "%95", "%96", "%97",
  47     "%98", "%99", "%9a", "%9b", "%9c", "%9d", "%9e", "%9f",
  48     "%a0", "%a1", "%a2", "%a3", "%a4", "%a5", "%a6", "%a7",
  49     "%a8", "%a9", "%aa", "%ab", "%ac", "%ad", "%ae", "%af",
  50     "%b0", "%b1", "%b2", "%b3", "%b4", "%b5", "%b6", "%b7",
  51     "%b8", "%b9", "%ba", "%bb", "%bc", "%bd", "%be", "%bf",
  52     "%c0", "%c1", "%c2", "%c3", "%c4", "%c5", "%c6", "%c7",
  53     "%c8", "%c9", "%ca", "%cb", "%cc", "%cd", "%ce", "%cf",
  54     "%d0", "%d1", "%d2", "%d3", "%d4", "%d5", "%d6", "%d7",
  55     "%d8", "%d9", "%da", "%db", "%dc", "%dd", "%de", "%df",
  56     "%e0", "%e1", "%e2", "%e3", "%e4", "%e5", "%e6", "%e7",
  57     "%e8", "%e9", "%ea", "%eb", "%ec", "%ed", "%ee", "%ef",
  58     "%f0", "%f1", "%f2", "%f3", "%f4", "%f5", "%f6", "%f7",
  59     "%f8", "%f9", "%fa", "%fb", "%fc", "%fd", "%fe", "%ff"
  60   };
  61
  62   /**
  63    * Encode a string to the "x-www-form-urlencoded" form, enhanced
  64    * with the UTF-8-in-URL proposal. This is what happens:
  65    *
  66    * <ul>
  67    * <li><p>The ASCII characters 'a' through 'z', 'A' through 'Z',
  68    *        and '0' through '9' remain the same.
  69    *
  70    * <li><p>The unreserved characters - _ . ! ~ * ' ( ) remain the same.
  71    *
  72    * <li><p>The space character ' ' is converted into a plus sign '+'.
  73    *
  74    * <li><p>All other ASCII characters are converted into the
  75    *        3-character string "%xy", where xy is
  76    *        the two-digit hexadecimal representation of the character
  77    *        code
  78    *
  79    * <li><p>All non-ASCII characters are encoded in two steps: first
  80    *        to a sequence of 2 or 3 bytes, using the UTF-8 algorithm;
  81    *        secondly each of these bytes is encoded as "%xx".
  82    * </ul>
  83    *
  84    * @param s The string to be encoded
  85    * @return The encoded string
  86    */
  87   public static String encode(String s)
  88   {
  89     StringBuffer sbuf = new StringBuffer();
  90     int len = s.length();
  91     for (int i = 0; i < len; i++) {
  92       int ch = s.charAt(i);
  93       if ('A' <= ch && ch <= 'Z') {             // 'A'..'Z'
  94         sbuf.append((char)ch);
  95       } else if ('a' <= ch && ch <= 'z') {      // 'a'..'z'
  96                sbuf.append((char)ch);
  97       } else if ('0' <= ch && ch <= '9') {      // '0'..'9'
  98                sbuf.append((char)ch);
  99       } else if (ch == ' ') {                   // space
 100                sbuf.append(hex[ch]);     //Note: changed from + to %20 for use according to http://www.doi.org/doi_handbook/2_Numbering.html#2.5.2.4
 101       } else if (ch == '-' || ch == '_'         // unreserved
 102           || ch == '.' || ch == '!'
 103           || ch == '~' || ch == '*'
 104           || ch == '\'' || ch == '('
 105           || ch == ')') {
 106         sbuf.append((char)ch);
 107       } else if (ch <= 0x007f) {                // other ASCII
 108                sbuf.append(hex[ch]);
 109       } else if (ch <= 0x07FF) {                // non-ASCII <= 0x7FF
 110                sbuf.append(hex[0xc0 | (ch >> 6)]);
 111                sbuf.append(hex[0x80 | (ch & 0x3F)]);
 112       } else {                                  // 0x7FF < ch <= 0xFFFF
 113                sbuf.append(hex[0xe0 | (ch >> 12)]);
 114                sbuf.append(hex[0x80 | ((ch >> 6) & 0x3F)]);
 115                sbuf.append(hex[0x80 | (ch & 0x3F)]);
 116       }
 117     }
 118     return sbuf.toString();
 119   }
 120
 121         /*
 122          * Created: 17 April 1997
 123          * Author: Bert Bos <bert@w3.org>
 124          *
 125          * unescape: http://www.w3.org/International/unescape.java
 126          *
 127          * Copyright © 1997 World Wide Web Consortium, (Massachusetts
 128          * Institute of Technology, European Research Consortium for
 129          * Informatics and Mathematics, Keio University). All Rights Reserved.
 130          * This work is distributed under the W3C® Software License [1] in the
 131          * hope that it will be useful, but WITHOUT ANY WARRANTY; without even
 132          * the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR
 133          * PURPOSE.
 134          *
 135          * [1] http://www.w3.org/Consortium/Legal/2002/copyright-software-20021231
 136          */
 137   public static String unescape(String s) {
 138             StringBuffer sbuf = new StringBuffer () ;
 139             int l  = s.length() ;
 140             int ch = -1 ;
 141             int b, sumb = 0;
 142             for (int i = 0, more = -1 ; i < l ; i++) {
 143               /* Get next byte b from URL segment s */
 144               switch (ch = s.charAt(i)) {
 145                 case '%':
 146                   ch = s.charAt (++i) ;
 147                   int hb = (Character.isDigit ((char) ch)
 148                             ? ch - '0'
 149                             : 10+Character.toLowerCase((char) ch) - 'a') & 0xF ;
 150                   ch = s.charAt (++i) ;
 151                   int lb = (Character.isDigit ((char) ch)
 152                             ? ch - '0'
 153                             : 10+Character.toLowerCase ((char) ch)-'a') & 0xF ;
 154                   b = (hb << 4) | lb ;
 155                   break ;
 156                 case '+':
 157                   b = ' ' ;
 158                   break ;
 159                 default:
 160                   b = ch ;
 161               }
 162               /* Decode byte b as UTF-8, sumb collects incomplete chars */
 163               if ((b & 0xc0) == 0x80) {                 // 10xxxxxx (continuation byte)
 164                 sumb = (sumb << 6) | (b & 0x3f) ;       // Add 6 bits to sumb
 165                 if (--more == 0) sbuf.append((char) sumb) ; // Add char to sbuf
 166               } else if ((b & 0x80) == 0x00) {          // 0xxxxxxx (yields 7 bits)
 167                 sbuf.append((char) b) ;                 // Store in sbuf
 168               } else if ((b & 0xe0) == 0xc0) {          // 110xxxxx (yields 5 bits)
 169                 sumb = b & 0x1f;
 170                 more = 1;                               // Expect 1 more byte
 171               } else if ((b & 0xf0) == 0xe0) {          // 1110xxxx (yields 4 bits)
 172                 sumb = b & 0x0f;
 173                 more = 2;                               // Expect 2 more bytes
 174               } else if ((b & 0xf8) == 0xf0) {          // 11110xxx (yields 3 bits)
 175                 sumb = b & 0x07;
 176                 more = 3;                               // Expect 3 more bytes
 177               } else if ((b & 0xfc) == 0xf8) {          // 111110xx (yields 2 bits)
 178                 sumb = b & 0x03;
 179                 more = 4;                               // Expect 4 more bytes
 180               } else /*if ((b & 0xfe) == 0xfc)*/ {      // 1111110x (yields 1 bit)
 181                 sumb = b & 0x01;
 182                 more = 5;                               // Expect 5 more bytes
 183               }
 184               /* We don't test if the UTF-8 encoding is well-formed */
 185             }
 186             return sbuf.toString() ;
 187           }
 188
 189 }