src/weibo4android/util/URLEncodeUtils.java

   1 package weibo4android.util;
   2 import java.io.UnsupportedEncodingException;
   3 import java.net.URLDecoder;
   4 import java.net.URLEncoder;
   5 import java.util.BitSet;
   6 /**
   7  * @author yuanming
   8  *
   9  */
  10 public class URLEncodeUtils {
  11
  12         static BitSet dontNeedEncoding;
  13
  14         static {
  15
  16                 /*
  17                  * The list of characters that are not encoded has been determined as
  18                  * follows:
  19                  *
  20                  * RFC 2396 states: ----- Data characters that are allowed in a URI but
  21                  * do not have a reserved purpose are called unreserved. These include
  22                  * upper and lower case letters, decimal digits, and a limited set of
  23                  * punctuation marks and symbols.
  24                  *
  25                  * unreserved = alphanum | mark
  26                  *
  27                  * mark = "-" | "_" | "." | "!" | "~" | "*" | "'" | "(" | ")"
  28                  *
  29                  * Unreserved characters can be escaped without changing the semantics
  30                  * of the URI, but this should not be done unless the URI is being used
  31                  * in a context that does not allow the unescaped character to appear.
  32                  * -----
  33                  *
  34                  * It appears that both Netscape and Internet Explorer escape all
  35                  * special characters from this list with the exception of "-", "_",
  36                  * ".", "*". While it is not clear why they are escaping the other
  37                  * characters, perhaps it is safest to assume that there might be
  38                  * contexts in which the others are unsafe if not escaped. Therefore, we
  39                  * will use the same list. It is also noteworthy that this is consistent
  40                  * with O'Reilly's "HTML: The Definitive Guide" (page 164).
  41                  *
  42                  * As a last note, Intenet Explorer does not encode the "@" character
  43                  * which is clearly not unreserved according to the RFC. We are being
  44                  * consistent with the RFC in this matter, as is Netscape.
  45                  */
  46
  47                 dontNeedEncoding = new BitSet(256);
  48                 int i;
  49                 for (i = 'a'; i <= 'z'; i++) {
  50                         dontNeedEncoding.set(i);
  51                 }
  52                 for (i = 'A'; i <= 'Z'; i++) {
  53                         dontNeedEncoding.set(i);
  54                 }
  55                 for (i = '0'; i <= '9'; i++) {
  56                         dontNeedEncoding.set(i);
  57                 }
  58                 dontNeedEncoding.set(' '); /*
  59                                                                          * encoding a space to a + is done in the
  60                                                                          * encode() method
  61                                                                          */
  62                 dontNeedEncoding.set('-');
  63                 dontNeedEncoding.set('_');
  64                 dontNeedEncoding.set('.');
  65                 dontNeedEncoding.set('*');
  66
  67                 dontNeedEncoding.set('+');
  68                 dontNeedEncoding.set('%');
  69
  70         }
  71
  72         /**
  73          * 判断段落文本是否被urlencode过
  74          *
  75          * @param str
  76          * @return
  77          */
  78         public static final boolean isURLEncoded(String str) {
  79                 if (str==null||"".equals(str)) {
  80                         return false;
  81                 }
  82                 char[] chars = str.toCharArray();
  83                 boolean containsPercent = false;
  84                 for (char c : chars) {
  85                         if (Character.isWhitespace(c)) {
  86                                 return false;
  87                         }
  88                         if (!dontNeedEncoding.get(c)) {
  89                                 return false;
  90                         }
  91                         if(c == '%'){
  92                                 containsPercent = true;
  93                         }
  94                 }
  95                 if(!containsPercent){
  96                         return false;
  97                 }
  98                 return true;
  99         }
 100
 101         public static final String encodeURL(String str) {
 102                 try {
 103                         return URLEncoder.encode(str, "utf-8");
 104                 } catch (UnsupportedEncodingException e) {
 105                         throw new RuntimeException(e);
 106                 }
 107         }
 108         public static final String decodeURL(String str) {
 109                 try {
 110                         return URLDecoder.decode(str, "utf-8");
 111                 } catch (UnsupportedEncodingException e) {
 112                         throw new RuntimeException(e);
 113                 }
 114         }
 115
 116 }