8183743: Umbrella: add overloads that take a Charset parameter

Reviewed-by: alanb, rriggs
This commit is contained in:
Joe Wang 2017-12-12 11:10:12 -08:00
parent f065141ddc
commit 4f080a83af
28 changed files with 1959 additions and 131 deletions

View file

@ -1,5 +1,5 @@
/*
* Copyright (c) 1998, 2013, Oracle and/or its affiliates. All rights reserved.
* 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
@ -26,6 +26,10 @@
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
@ -108,7 +112,43 @@ public class URLDecoder {
/**
* Decodes an {@code application/x-www-form-urlencoded} string using
* a specific encoding scheme.
* The supplied encoding is used to determine
*
* <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.length() == 0) {
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 {@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>
@ -118,29 +158,25 @@ public class URLDecoder {
* 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 enc The name of a supported
* <a href="../lang/package-summary.html#charenc">character
* encoding</a>.
* @param charset the given charset
* @return the newly decoded {@code String}
* @exception 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
* @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, String enc)
throws UnsupportedEncodingException{
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;
if (enc.length() == 0) {
throw new UnsupportedEncodingException ("URLDecoder: empty string enc parameter");
}
char c;
byte[] bytes = null;
while (i < numChars) {
@ -173,7 +209,9 @@ public class URLDecoder {
(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");
throw new IllegalArgumentException(
"URLDecoder: Illegal hex characters in escape "
+ "(%) pattern - negative value");
bytes[pos++] = (byte) v;
i+= 3;
if (i < numChars)
@ -187,7 +225,7 @@ public class URLDecoder {
throw new IllegalArgumentException(
"URLDecoder: Incomplete trailing escape (%) pattern");
sb.append(new String(bytes, 0, pos, enc));
sb.append(new String(bytes, 0, pos, charset));
} catch (NumberFormatException e) {
throw new IllegalArgumentException(
"URLDecoder: Illegal hex characters in escape (%) pattern - "

View file

@ -1,5 +1,5 @@
/*
* Copyright (c) 1995, 2013, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 1995, 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
@ -31,6 +31,7 @@ import java.nio.charset.Charset;
import java.nio.charset.IllegalCharsetNameException;
import java.nio.charset.UnsupportedCharsetException ;
import java.util.BitSet;
import java.util.Objects;
import sun.security.action.GetPropertyAction;
/**
@ -168,45 +169,61 @@ public class URLEncoder {
/**
* 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.
* format using a specific encoding scheme.
* <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>
* This method behaves the same as {@linkplain encode(String s, Charset charset)}
* except that it will {@linkplain java.nio.charset.Charset#forName look up the charset}
* using the given encoding name.
*
* @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
* @throws 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 {
if (enc == null) {
throw new NullPointerException("charsetName");
}
try {
Charset charset = Charset.forName(enc);
return encode(s, charset);
} catch (IllegalCharsetNameException | UnsupportedCharsetException e) {
throw new UnsupportedEncodingException(enc);
}
}
/**
* Translates a string into {@code application/x-www-form-urlencoded}
* format using a specific {@linkplain java.nio.charset.Charset Charset}.
* This method uses the supplied charset 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 charset the given charset
* @return the translated {@code String}.
* @throws NullPointerException if {@code s} or {@code charset} is {@code null}.
* @see URLDecoder#decode(java.lang.String, java.nio.charset.Charset)
* @since 10
*/
public static String encode(String s, Charset charset) {
Objects.requireNonNull(charset, "charset");
boolean needToChange = false;
StringBuilder out = new StringBuilder(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);