解决java中对URL编码的问题
首先查看javascript中的encodeURI和encodeURLComponent方法的区别.
encodeURI:不会对 ASCII 字母和数字进行编码，也不会对这些 ASCII 标点符号进行编码： - _ . ! ~ * ' ( ) 也不会对以下在 URI 中具有特殊含义的 ASCII 标点符 号，encodeURI() 函数是不会进行转义的：;/?:@&=+$,#
encodeURLComponent:不会对 ASCII 字母和数字进行编码，也不会对这些 ASCII 标点符号进行编码： - _ . ! ~ * ' ( )
而java中,URLEncoder.encode(string content,String enc) 方法:
不会对 ASCII 字母和数字进行编码，也不会对这些 ASCII 标点符号进行编码： - _ . *
参考代码如下:
dontNeedEncoding = new BitSet(256); int i; for (i = 'a'; i <= 'z'; i++) { dontNeedEncoding.set(i); } for (i = 'A'; i <= 'Z'; i++) { dontNeedEncoding.set(i); } for (i = '0'; i <= '9'; i++) { dontNeedEncoding.set(i); } dontNeedEncoding.set(' '); /* encoding a space to a + is done * in the encode() method */ dontNeedEncoding.set('-'); dontNeedEncoding.set('_'); dontNeedEncoding.set('.'); dontNeedEncoding.set('*');
如果我想要在java中对一个url进行编码,但是不对URI 中具有特殊含义的 ASCII 标点符号进行编码,需要在dontNeedEncoding中添加相关字符,创建自己的编码类MyURIEncode:
package com.sitech.solr.util; import java.io.CharArrayWriter; import java.io.UnsupportedEncodingException; import java.nio.charset.Charset; import java.nio.charset.IllegalCharsetNameException; import java.nio.charset.UnsupportedCharsetException; import java.security.AccessController; import java.util.BitSet; import sun.security.action.GetPropertyAction; public class MyURIEncoder { static BitSet dontNeedEncoding; static final int caseDiff = ('a' - 'A'); static String dfltEncName = null; static { /* The list of characters that are not encoded has been * determined as follows: * * RFC 2396 states: * ----- * Data characters that are allowed in a URI but do not have a * reserved purpose are called unreserved. These include upper * and lower case letters, decimal digits, and a limited set of * punctuation marks and symbols. * * unreserved = alphanum | mark * * mark = "-" | "_" | "." | "!" | "~" | "*" | "'" | "(" | ")" * * Unreserved characters can be escaped without changing the * semantics of the URI, but this should not be done unless the * URI is being used in a context that does not allow the * unescaped character to appear. * ----- * * It appears that both Netscape and Internet Explorer escape * all special characters from this list with the exception * of "-", "_", ".", "*". While it is not clear why they are * escaping the other characters, perhaps it is safest to * assume that there might be contexts in which the others * are unsafe if not escaped. Therefore, we will use the same * list. It is also noteworthy that this is consistent with * O'Reilly's "HTML: The Definitive Guide" (page 164). * * As a last note, Intenet Explorer does not encode the "@" * character which is clearly not unreserved according to the * RFC. We are being consistent with the RFC in this matter, * as is Netscape. * */ dontNeedEncoding = new BitSet(256); int i; for (i = 'a'; i <= 'z'; i++) { dontNeedEncoding.set(i); } for (i = 'A'; i <= 'Z'; i++) { dontNeedEncoding.set(i); } for (i = '0'; i <= '9'; i++) { dontNeedEncoding.set(i); } dontNeedEncoding.set(' '); /* encoding a space to a + is done * in the encode() method */ dontNeedEncoding.set('-'); dontNeedEncoding.set('_'); dontNeedEncoding.set('.'); dontNeedEncoding.set('*'); //对以下在 URI 中具有特殊含义的 ASCII 标点符号 ;/?:@&=+$,# 不需要转义 dontNeedEncoding.set(';'); dontNeedEncoding.set('/'); dontNeedEncoding.set('?'); dontNeedEncoding.set(':'); dontNeedEncoding.set('@'); dontNeedEncoding.set('&'); dontNeedEncoding.set('='); dontNeedEncoding.set('+'); dontNeedEncoding.set('$'); dontNeedEncoding.set(','); dontNeedEncoding.set('#'); dfltEncName = AccessController.doPrivileged( new GetPropertyAction("file.encoding") ); } /** * You can't call the constructor. */ private MyURIEncoder() { } public static String encode(String s, String enc) throws UnsupportedEncodingException { boolean needToChange = false; StringBuffer out = new StringBuffer(s.length()); Charset charset; CharArrayWriter charArrayWriter = new CharArrayWriter(); if (enc == null) throw new NullPointerException("charsetName"); try { charset = Charset.forName(enc); } catch (IllegalCharsetNameException e) { throw new UnsupportedEncodingException(enc); } catch (UnsupportedCharsetException e) { throw new UnsupportedEncodingException(enc); } for (int i = 0; i < s.length();) { int c = (int) s.charAt(i); //System.out.println("Examining character: " + c); if (dontNeedEncoding.get(c)) { if (c == ' ') { c = '+'; needToChange = true; } //System.out.println("Storing: " + c); out.append((char)c); i++; } else { // convert to external encoding before hex conversion do { charArrayWriter.write(c); /* * If this character represents the start of a Unicode * surrogate pair, then pass in two characters. It's not * clear what should be done if a bytes reserved in the * surrogate pairs range occurs outside of a legal * surrogate pair. For now, just treat it as if it were * any other character. */ if (c >= 0xD800 && c <= 0xDBFF) { /* System.out.println(Integer.toHexString(c) + " is high surrogate"); */ if ( (i+1) < s.length()) { int d = (int) s.charAt(i+1); /* System.out.println("\tExamining " + Integer.toHexString(d)); */ if (d >= 0xDC00 && d <= 0xDFFF) { /* System.out.println("\t" + Integer.toHexString(d) + " is low surrogate"); */ charArrayWriter.write(d); i++; } } } i++; } while (i < s.length() && !dontNeedEncoding.get((c = (int) s.charAt(i)))); charArrayWriter.flush(); String str = new String(charArrayWriter.toCharArray()); byte[] ba = str.getBytes(charset); for (int j = 0; j < ba.length; j++) { out.append('%'); char ch = Character.forDigit((ba[j] >> 4) & 0xF, 16); // converting to use uppercase letter as part of // the hex value if ch is a letter. if (Character.isLetter(ch)) { ch -= caseDiff; } out.append(ch); ch = Character.forDigit(ba[j] & 0xF, 16); if (Character.isLetter(ch)) { ch -= caseDiff; } out.append(ch); } charArrayWriter.reset(); needToChange = true; } } return (needToChange? out.toString() : s); } }
