/*
* Copyright (c) 1998, 2017, Oracle and/or its affiliates. All rights reserved.
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 only, as
* published by the Free Software Foundation. Oracle designates this
* particular file as subject to the "Classpath" exception as provided
* by Oracle in the LICENSE file that accompanied this code.
*
* This code is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
* version 2 for more details (a copy is included in the LICENSE file that
* accompanied this code).
*
* You should have received a copy of the GNU General Public License version
* 2 along with this work; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
* or visit www.oracle.com if you need additional information or have any
* questions.
*/
package java.net;
import java.io.*;
import java.nio.charset.Charset;
import java.nio.charset.IllegalCharsetNameException;
import java.nio.charset.UnsupportedCharsetException;
import java.util.Objects;
Utility class for HTML form decoding. This class contains static methods
for decoding a String from the application/x-www-form-urlencoded
MIME format.
The conversion process is the reverse of that used by the URLEncoder class. It is assumed that all characters in the encoded string are one of the following: "a" through "z", "A" through "Z", "0" through "9", and "-", "_", ".", and "*". The character "%" is allowed but is interpreted as the start of a special escaped sequence.
The following rules are applied in the conversion:
- The alphanumeric characters "
a" through "z", "A" through "Z" and "0" through "9" remain the same. - The special characters "
.", "-", "*", and "_" remain the same. - The plus sign "
+" is converted into a space character " " . - A sequence of the form "
%xy" will be
treated as representing a byte where xy is the two-digit
hexadecimal representation of the 8 bits. Then, all substrings
that contain one or more of these byte sequences consecutively
will be replaced by the character(s) whose encoding would result
in those consecutive bytes.
The encoding scheme used to decode these characters may be specified,
or if unspecified, the default encoding of the platform will be used.
There are two possible ways in which this decoder could deal with illegal strings. It could either leave illegal characters alone or it could throw an IllegalArgumentException. Which approach the decoder takes is left to the implementation.
Author: Mark Chamness, Michael McCloskey Since: 1.2
/**
* Utility class for HTML form decoding. This class contains static methods
* for decoding a String from the <CODE>application/x-www-form-urlencoded</CODE>
* MIME format.
* <p>
* The conversion process is the reverse of that used by the URLEncoder class. It is assumed
* that all characters in the encoded string are one of the following:
* "{@code a}" through "{@code z}",
* "{@code A}" through "{@code Z}",
* "{@code 0}" through "{@code 9}", and
* "{@code -}", "{@code _}",
* "{@code .}", and "{@code *}". The
* character "{@code %}" is allowed but is interpreted
* as the start of a special escaped sequence.
* <p>
* The following rules are applied in the conversion:
*
* <ul>
* <li>The alphanumeric characters "{@code a}" through
* "{@code z}", "{@code A}" through
* "{@code Z}" and "{@code 0}"
* through "{@code 9}" remain the same.
* <li>The special characters "{@code .}",
* "{@code -}", "{@code *}", and
* "{@code _}" remain the same.
* <li>The plus sign "{@code +}" is converted into a
* space character " " .
* <li>A sequence of the form "<i>{@code %xy}</i>" will be
* treated as representing a byte where <i>xy</i> is the two-digit
* hexadecimal representation of the 8 bits. Then, all substrings
* that contain one or more of these byte sequences consecutively
* will be replaced by the character(s) whose encoding would result
* in those consecutive bytes.
* The encoding scheme used to decode these characters may be specified,
* or if unspecified, the default encoding of the platform will be used.
* </ul>
* <p>
* There are two possible ways in which this decoder could deal with
* illegal strings. It could either leave illegal characters alone or
* it could throw an {@link java.lang.IllegalArgumentException}.
* Which approach the decoder takes is left to the
* implementation.
*
* @author Mark Chamness
* @author Michael McCloskey
* @since 1.2
*/
public class URLDecoder {
// The platform default encoding
static String dfltEncName = URLEncoder.dfltEncName;
Decodes a x-www-form-urlencoded string. The platform's default encoding is used to determine what characters are represented by any consecutive sequences of the form "%xy".
Params: - s – the
String to decode
Deprecated: The resulting string may vary depending on the platform's
default encoding. Instead, use the decode(String,String) method
to specify the encoding. Returns: the newly decoded String
/**
* Decodes a {@code x-www-form-urlencoded} string.
* The platform's default encoding is used to determine what characters
* are represented by any consecutive sequences of the form
* "<i>{@code %xy}</i>".
* @param s the {@code String} to decode
* @deprecated The resulting string may vary depending on the platform's
* default encoding. Instead, use the decode(String,String) method
* to specify the encoding.
* @return the newly decoded {@code String}
*/
@Deprecated
public static String decode(String s) {
String str = null;
try {
str = decode(s, dfltEncName);
} catch (UnsupportedEncodingException e) {
// The system should always have the platform default
}
return str;
}
Decodes an application/x-www-form-urlencoded string using a specific encoding scheme. This method behaves the same as decode(String s, Charset charset) except that it will look up the charset using the given encoding name.
Params: - s – the
String to decode - enc – The name of a supported
character
encoding.
Throws: - UnsupportedEncodingException –
If character encoding needs to be consulted, but
named character encoding is not supported
See Also: Implementation Note: This implementation will throw an IllegalArgumentException when illegal strings are encountered. Returns: the newly decoded String Since: 1.4
/**
* Decodes an {@code application/x-www-form-urlencoded} string using
* a specific encoding scheme.
*
* <p>
* This method behaves the same as {@linkplain decode(String s, Charset charset)}
* except that it will {@linkplain java.nio.charset.Charset#forName look up the charset}
* using the given encoding name.
*
* @implNote This implementation will throw an {@link java.lang.IllegalArgumentException}
* when illegal strings are encountered.
*
* @param s the {@code String} to decode
* @param enc The name of a supported
* <a href="../lang/package-summary.html#charenc">character
* encoding</a>.
* @return the newly decoded {@code String}
* @throws UnsupportedEncodingException
* If character encoding needs to be consulted, but
* named character encoding is not supported
* @see URLEncoder#encode(java.lang.String, java.lang.String)
* @since 1.4
*/
public static String decode(String s, String enc) throws UnsupportedEncodingException {
if (enc.isEmpty()) {
throw new UnsupportedEncodingException ("URLDecoder: empty string enc parameter");
}
try {
Charset charset = Charset.forName(enc);
return decode(s, charset);
} catch (IllegalCharsetNameException | UnsupportedCharsetException e) {
throw new UnsupportedEncodingException(enc);
}
}
Decodes an application/x-www-form-urlencoded string using a specific Charset. The supplied charset is used to determine what characters are represented by any consecutive sequences of the form "%xy".
Note: The
World Wide Web Consortium Recommendation states that
UTF-8 should be used. Not doing so may introduce
incompatibilities.
Params: - s – the
String to decode - charset – the given charset
Throws: - NullPointerException – if
s or charset is null - IllegalArgumentException – if the implementation encounters illegal
characters
See Also: Implementation Note: This implementation will throw an IllegalArgumentException when illegal strings are encountered. Returns: the newly decoded String Since: 10
/**
* Decodes an {@code application/x-www-form-urlencoded} string using
* a specific {@linkplain java.nio.charset.Charset Charset}.
* The supplied charset is used to determine
* what characters are represented by any consecutive sequences of the
* form "<i>{@code %xy}</i>".
* <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>
*
* @implNote This implementation will throw an {@link java.lang.IllegalArgumentException}
* when illegal strings are encountered.
*
* @param s the {@code String} to decode
* @param charset the given charset
* @return the newly decoded {@code String}
* @throws NullPointerException if {@code s} or {@code charset} is {@code null}
* @throws IllegalArgumentException if the implementation encounters illegal
* characters
* @see URLEncoder#encode(java.lang.String, java.nio.charset.Charset)
* @since 10
*/
public static String decode(String s, Charset charset) {
Objects.requireNonNull(charset, "Charset");
boolean needToChange = false;
int numChars = s.length();
StringBuilder sb = new StringBuilder(numChars > 500 ? numChars / 2 : numChars);
int i = 0;
char c;
byte[] bytes = null;
while (i < numChars) {
c = s.charAt(i);
switch (c) {
case '+':
sb.append(' ');
i++;
needToChange = true;
break;
case '%':
/*
* Starting with this instance of %, process all
* consecutive substrings of the form %xy. Each
* substring %xy will yield a byte. Convert all
* consecutive bytes obtained this way to whatever
* character(s) they represent in the provided
* encoding.
*/
try {
// (numChars-i)/3 is an upper bound for the number
// of remaining bytes
if (bytes == null)
bytes = new byte[(numChars-i)/3];
int pos = 0;
while ( ((i+2) < numChars) &&
(c=='%')) {
int v = Integer.parseInt(s, i + 1, i + 3, 16);
if (v < 0)
throw new IllegalArgumentException(
"URLDecoder: Illegal hex characters in escape "
+ "(%) pattern - negative value");
bytes[pos++] = (byte) v;
i+= 3;
if (i < numChars)
c = s.charAt(i);
}
// A trailing, incomplete byte encoding such as
// "%x" will cause an exception to be thrown
if ((i < numChars) && (c=='%'))
throw new IllegalArgumentException(
"URLDecoder: Incomplete trailing escape (%) pattern");
sb.append(new String(bytes, 0, pos, charset));
} catch (NumberFormatException e) {
throw new IllegalArgumentException(
"URLDecoder: Illegal hex characters in escape (%) pattern - "
+ e.getMessage());
}
needToChange = true;
break;
default:
sb.append(c);
i++;
break;
}
}
return (needToChange? sb.toString() : s);
}
}