由 dawei
最近需要将一些python代码转成java，遇到url编码
urllib.quote(str,safe='/')
但java中URLEncoder.encode(arg,Constant.UTF_8)会将'/'转成%2F
网上查了一下 java没见到类似的safe方式，只好自己实现一个类
<span style="color: #0000ff;">public <span style="color: #0000ff;">class<span style="color: #000000;"> UrlSafeEncoder {
</span><span style="color: #0000ff;">static</span><span style="color: #000000;"> BitSet dontNeedEncoding;
</span><span style="color: #0000ff;">static</span> <span style="color: #0000ff;">final</span> <span style="color: #0000ff;">int</span> caseDiff = ('a' - 'A'<span style="color: #000000;">);
</span><span style="color: #0000ff;">static</span> String dfltEncName = <span style="color: #0000ff;">null</span><span style="color: #000000;">;
</span><span style="color: #0000ff;">static</span><span style="color: #000000;"> {
</span><span style="color: #008000;">/*</span><span style="color: #008000;"> 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.
*
</span><span style="color: #008000;">*/</span><span style="color: #000000;">
dontNeedEncoding </span>= <span style="color: #0000ff;">new</span> BitSet(256<span style="color: #000000;">);
</span><span style="color: #0000ff;">int</span><span style="color: #000000;"> i;
</span><span style="color: #0000ff;">for</span> (i = 'a'; i <= 'z'; i++<span style="color: #000000;">) {
dontNeedEncoding.set(i);
}
</span><span style="color: #0000ff;">for</span> (i = 'A'; i <= 'Z'; i++<span style="color: #000000;">) {
dontNeedEncoding.set(i);
}
</span><span style="color: #0000ff;">for</span> (i = '0'; i <= '9'; i++<span style="color: #000000;">) {
dontNeedEncoding.set(i);
}
dontNeedEncoding.set(</span>' '); <span style="color: #008000;">/*</span><span style="color: #008000;"> encoding a space to a + is done
* in the encode() method </span><span style="color: #008000;">*/</span><span style="color: #000000;">
dontNeedEncoding.set(</span>'-'<span style="color: #000000;">);
dontNeedEncoding.set(</span>'_'<span style="color: #000000;">);
dontNeedEncoding.set(</span>'.'<span style="color: #000000;">);
dontNeedEncoding.set(</span>'*'<span style="color: #000000;">);
dfltEncName </span>=<span style="color: #000000;"> AccessController.doPrivileged(
</span><span style="color: #0000ff;">new</span> GetPropertyAction("file.encoding"<span style="color: #000000;">)
);
}
</span><span style="color: #008000;">/**</span><span style="color: #008000;">
* You can't call the constructor.
</span><span style="color: #008000;">*/</span>
<span style="color: #0000ff;">private</span><span style="color: #000000;"> UrlSafeEncoder() { }
</span><span style="color: #008000;">/**</span><span style="color: #008000;">
* Translates a string into {</span><span style="color: #808080;">@code</span><span style="color: #008000;"> application/x-www-form-urlencoded}
* format using a specific encoding scheme. This method uses the
* supplied encoding scheme to obtain the bytes for unsafe
* characters.
* <p>
* <em><strong>Note:</strong> The <a href=
* "</span><span style="color: #008000; text-decoration: underline;">http://www.w3.org/TR/html40/appendix/notes.html</span><span style="color: #008000;">#non-ascii-chars">
* World Wide Web Consortium Recommendation</a> states that
* UTF-8 should be used. Not doing so may introduce
* incompatibilities.</em>
*
* </span><span style="color: #808080;">@param</span><span style="color: #008000;"> s {</span><span style="color: #808080;">@code</span><span style="color: #008000;"> String} to be translated.
* </span><span style="color: #808080;">@param</span><span style="color: #008000;"> enc The name of a supported
* <a href="../lang/package-summary.html#charenc">character
* encoding</a>.
* </span><span style="color: #808080;">@return</span><span style="color: #008000;"> the translated {</span><span style="color: #808080;">@code</span><span style="color: #008000;"> String}.
* </span><span style="color: #808080;">@exception</span><span style="color: #008000;"> UnsupportedEncodingException
* If the named encoding is not supported
* </span><span style="color: #808080;">@see</span><span style="color: #008000;"> URLDecoder#decode(java.lang.String,java.lang.String)
* </span><span style="color: #808080;">@since</span><span style="color: #008000;"> 1.4
</span><span style="color: #008000;">*/</span>
<span style="color: #0000ff;">public</span> <span style="color: #0000ff;">static</span> String encode(String s,String enc,<span style="color: #0000ff;">char</span><span style="color: #000000;"> safe)
</span><span style="color: #0000ff;">throws</span><span style="color: #000000;"> UnsupportedEncodingException {
dontNeedEncoding.set(safe);
</span><span style="color: #0000ff;">boolean</span> needToChange = <span style="color: #0000ff;">false</span><span style="color: #000000;">;
StringBuffer out </span>= <span style="color: #0000ff;">new</span><span style="color: #000000;"> StringBuffer(s.length());
Charset charset;
CharArrayWriter charArrayWriter </span>= <span style="color: #0000ff;">new</span><span style="color: #000000;"> CharArrayWriter();
</span><span style="color: #0000ff;">if</span> (enc == <span style="color: #0000ff;">null</span><span style="color: #000000;">)
</span><span style="color: #0000ff;">throw</span> <span style="color: #0000ff;">new</span> NullPointerException("charsetName"<span style="color: #000000;">);
</span><span style="color: #0000ff;">try</span><span style="color: #000000;"> {
charset </span>=<span style="color: #000000;"> Charset.forName(enc);
} </span><span style="color: #0000ff;">catch</span><span style="color: #000000;"> (IllegalCharsetNameException e) {
</span><span style="color: #0000ff;">throw</span> <span style="color: #0000ff;">new</span><span style="color: #000000;"> UnsupportedEncodingException(enc);
} </span><span style="color: #0000ff;">catch</span><span style="color: #000000;"> (UnsupportedCharsetException e) {
</span><span style="color: #0000ff;">throw</span> <span style="color: #0000ff;">new</span><span style="color: #000000;"> UnsupportedEncodingException(enc);
}
</span><span style="color: #0000ff;">for</span> (<span style="color: #0000ff;">int</span> i = 0; i <<span style="color: #000000;"> s.length();) {
</span><span style="color: #0000ff;">int</span> c = (<span style="color: #0000ff;">int</span><span style="color: #000000;">) s.charAt(i);
</span><span style="color: #008000;">//</span><span style="color: #008000;">System.out.println("Examining character: " + c);</span>
<span style="color: #0000ff;">if</span><span style="color: #000000;"> (dontNeedEncoding.get(c)) {
</span><span style="color: #0000ff;">if</span> (c == ' '<span style="color: #000000;">) {
c </span>= '+'<span style="color: #000000;">;
needToChange </span>= <span style="color: #0000ff;">true</span><span style="color: #000000;">;
}
</span><span style="color: #008000;">//</span><span style="color: #008000;">System.out.println("Storing: " + c);</span>
out.append((<span style="color: #0000ff;">char</span><span style="color: #000000;">)c);
i</span>++<span style="color: #000000;">;
} </span><span style="color: #0000ff;">else</span><span style="color: #000000;"> {
</span><span style="color: #008000;">//</span><span style="color: #008000;"> convert to external encoding before hex conversion</span>
<span style="color: #0000ff;">do</span><span style="color: #000000;"> {
charArrayWriter.write(c);
</span><span style="color: #008000;">/*</span><span style="color: #008000;">
* 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.
</span><span style="color: #008000;">*/</span>
<span style="color: #0000ff;">if</span> (c >= 0xD800 && c <= 0xDBFF<span style="color: #000000;">) {
</span><span style="color: #008000;">/*</span><span style="color: #008000;">
System.out.println(Integer.toHexString(c)
+ " is high surrogate");
</span><span style="color: #008000;">*/</span>
<span style="color: #0000ff;">if</span> ( (i+1) <<span style="color: #000000;"> s.length()) {
</span><span style="color: #0000ff;">int</span> d = (<span style="color: #0000ff;">int</span>) s.charAt(i+1<span style="color: #000000;">);
</span><span style="color: #008000;">/*</span><span style="color: #008000;">
System.out.println("\tExamining "
+ Integer.toHexString(d));
</span><span style="color: #008000;">*/</span>
<span style="color: #0000ff;">if</span> (d >= 0xDC00 && d <= 0xDFFF<span style="color: #000000;">) {
</span><span style="color: #008000;">/*</span><span style="color: #008000;">
System.out.println("\t"
+ Integer.toHexString(d)
+ " is low surrogate");
</span><span style="color: #008000;">*/</span><span style="color: #000000;">
charArrayWriter.write(d);
i</span>++<span style="color: #000000;">;
}
}
}
i</span>++<span style="color: #000000;">;
} </span><span style="color: #0000ff;">while</span> (i < s.length() && !dontNeedEncoding.get((c = (<span style="color: #0000ff;">int</span><span style="color: #000000;">) s.charAt(i))));
charArrayWriter.flush();
String str </span>= <span style="color: #0000ff;">new</span><span style="color: #000000;"> String(charArrayWriter.toCharArray());
</span><span style="color: #0000ff;">byte</span>[] ba =<span style="color: #000000;"> str.getBytes(charset);
</span><span style="color: #0000ff;">for</span> (<span style="color: #0000ff;">int</span> j = 0; j < ba.length; j++<span style="color: #000000;">) {
out.append(</span>'%'<span style="color: #000000;">);
</span><span style="color: #0000ff;">char</span> ch = Character.forDigit((ba[j] >> 4) & 0xF,16<span style="color: #000000;">);
</span><span style="color: #008000;">//</span><span style="color: #008000;"> converting to use uppercase letter as part of
</span><span style="color: #008000;">//</span><span style="color: #008000;"> the hex value if ch is a letter.</span>
<span style="color: #0000ff;">if</span><span style="color: #000000;"> (Character.isLetter(ch)) {
ch </span>-=<span style="color: #000000;"> caseDiff;
}
out.append(ch);
ch </span>= Character.forDigit(ba[j] & 0xF,16<span style="color: #000000;">);
</span><span style="color: #0000ff;">if</span><span style="color: #000000;"> (Character.isLetter(ch)) {
ch </span>-=<span style="color: #000000;"> caseDiff;
}
out.append(ch);
}
charArrayWriter.reset();
needToChange </span>= <span style="color: #0000ff;">true</span><span style="color: #000000;">;
}
}
</span><span style="color: #0000ff;">return</span> (needToChange?<span style="color: #000000;"> out.toString() : s);
}}
验证下 基本ok