/*
* @(#)URLEncoder.java 1.32 06/04/22
*
* Copyright 2006 Sun Microsystems, Inc. All rights reserved.
* SUN PROPRIETARY/CONFIDENTIAL. Use is subject to license terms.
*/
package java.net;
import java.io.ByteArrayOutputStream;
import java.io.BufferedWriter;
import java.io.OutputStreamWriter;
import java.io.IOException;
import java.io.UnsupportedEncodingException;
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 java.security.PrivilegedAction;
import sun.security.action.GetBooleanAction;
import sun.security.action.GetPropertyAction;
/**
* Utility class for HTML form encoding. This class contains static methods
* for converting a String to the <CODE>application/x-www-form-urlencoded</CODE> MIME
* format. For more information about HTML form encoding, consult the HTML
* <A HREF="http://www.w3.org/TR/html4/">specification</A>.
*
* <p>
* When encoding a String, the following rules apply:
*
* <p>
* <ul>
* <li>The alphanumeric characters "<code>a</code>" through
* "<code>z</code>", "<code>A</code>" through
* "<code>Z</code>" and "<code>0</code>"
* through "<code>9</code>" remain the same.
* <li>The special characters "<code>.</code>",
* "<code>-</code>", "<code>*</code>", and
* "<code>_</code>" remain the same.
* <li>The space character "<code> </code>" is
* converted into a plus sign "<code>+</code>".
* <li>All other characters are unsafe and are first converted into
* one or more bytes using some encoding scheme. Then each byte is
* represented by the 3-character string
* "<code>%<i>xy</i></code>", where <i>xy</i> is the
* two-digit hexadecimal representation of the byte.
* The recommended encoding scheme to use is UTF-8. However,
* for compatibility reasons, if an encoding is not specified,
* then the default encoding of the platform is used.
* </ul>
*
* <p>
* For example using UTF-8 as the encoding scheme the string "The
* string ü@foo-bar" would get converted to
* "The+string+%C3%BC%40foo-bar" because in UTF-8 the character
* ü is encoded as two bytes C3 (hex) and BC (hex), and the
* character @ is encoded as one byte 40 (hex).
*
* @author Herb Jellinek
* @version 1.32, 04/22/06
* @since JDK1.0
*/
public class URLEncoder {
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('*');
dfltEncName = (String)AccessController.doPrivileged (
new GetPropertyAction("file.encoding")
);
}
/**
* You can't call the constructor.
*/
private URLEncoder() { }
/**
* Translates a string into <code>x-www-form-urlencoded</code>
* format. This method uses the platform's default encoding
* as the encoding scheme to obtain the bytes for unsafe characters.
*
* @param s <code>String</code> to be translated.
* @deprecated The resulting string may vary depending on the platform's
* default encoding. Instead, use the encode(String,String)
* method to specify the encoding.
* @return the translated <code>String</code>.
*/
@Deprecated
public static String encode(String s) {
String str = null;
try {
str = encode(s, dfltEncName);
} catch (UnsupportedEncodingException e) {
// The system should always have the platform default
}
return str;
}
/**
* Translates a string into <code>application/x-www-form-urlencoded</code>
* 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
* incompatibilites.</em>
*
* @param s <code>String</code> 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</code>.
* @exception UnsupportedEncodingException
* If the named encoding is not supported
* @see URLDecoder#decode(java.lang.String, java.lang.String)
* @since 1.4
*/
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);
}
}