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

package com.ppc.spider.fc.util;import java.io.ByteArrayOutputStream;import java.io.BufferedWriter;import java.io.OutputStreamWriter;import java.io.IOException;import java.io.UnsupportedEncodingException;import java.net.URLDecoder;import java.io.CharArrayWriter;import java.nio.charset.Charset;import java.nio.charset.IllegalCharsetNameException;import java.nio.charset.UnsupportedCharsetException ;import java.util.BitSet;import java.security.AccessController;import sun.security.action.GetPropertyAction;publicclass UrlSafeEncoder {

static BitSet dontNeedEncoding;

staticfinalintcaseDiff = ('a' - 'A');

staticString 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 =newBitSet(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('*');

dfltEncName = AccessController.doPrivileged(

newGetPropertyAction("file.encoding")

);

}

/** * You can't call the constructor.

*/private UrlSafeEncoder() { }

/** * Translates a string into {@code 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=

* "http://www.w3.org/TR/html40/appendix/notes.html#non-ascii-chars">

* World Wide Web Consortium Recommendation</a> states that

* UTF-8 should be used. Not doing so may introduce

* incompatibilities.</em>

*

* @param s {@code String} to be translated.

* @param enc The name of a supported

* <a href="../lang/package-summary.html#charenc">character

* encoding</a>.

* @return the translated {@code String}.

* @exception UnsupportedEncodingException

* If the named encoding is not supported

* @see URLDecoder#decode(java.lang.String, java.lang.String)

* @since 1.4

*/publicstaticString encode(String s, String enc,char safe)

throws UnsupportedEncodingException {

dontNeedEncoding.set(safe);

booleanneedToChange =false;

StringBuffer out =new StringBuffer(s.length());

Charset charset;

CharArrayWriter charArrayWriter =new CharArrayWriter();

if(enc ==null)

thrownewNullPointerException("charsetName");

try {

charset = Charset.forName(enc);

} catch (IllegalCharsetNameException e) {

thrownew UnsupportedEncodingException(enc);

} catch (UnsupportedCharsetException e) {

thrownew UnsupportedEncodingException(enc);

}

for(inti = 0; i

intc = (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 conversiondo {

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)

intd = (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

charArrayWriter.flush();

String str =new String(charArrayWriter.toCharArray());

byte[] ba = str.getBytes(charset);

for(intj = 0; j < ba.length; j++) {

out.append('%');

charch = 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);

}

}

验证下 基本ok