src.java.net.IDN Maven / Gradle / Ivy
Show all versions of android-all Show documentation
/*
* Copyright (C) 2014 The Android Open Source Project
* Copyright (c) 2005, 2013, 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 com.android.icu.text.ExtendedIDNA;
/**
* Provides methods to convert internationalized domain names (IDNs) between
* a normal Unicode representation and an ASCII Compatible Encoding (ACE) representation.
* Internationalized domain names can use characters from the entire range of
* Unicode, while traditional domain names are restricted to ASCII characters.
* ACE is an encoding of Unicode strings that uses only ASCII characters and
* can be used with software (such as the Domain Name System) that only
* understands traditional domain names.
*
* Internationalized domain names are defined in RFC 3490.
* RFC 3490 defines two operations: ToASCII and ToUnicode. These 2 operations employ
* Nameprep algorithm, which is a
* profile of Stringprep, and
* Punycode algorithm to convert
* domain name string back and forth.
*
*
The behavior of aforementioned conversion process can be adjusted by various flags:
*
* - If the ALLOW_UNASSIGNED flag is used, the domain name string to be converted
* can contain code points that are unassigned in Unicode 3.2, which is the
* Unicode version on which IDN conversion is based. If the flag is not used,
* the presence of such unassigned code points is treated as an error.
*
- If the USE_STD3_ASCII_RULES flag is used, ASCII strings are checked against RFC 1122 and RFC 1123.
* It is an error if they don't meet the requirements.
*
* These flags can be logically OR'ed together.
*
* The security consideration is important with respect to internationalization
* domain name support. For example, English domain names may be homographed
* - maliciously misspelled by substitution of non-Latin letters.
* Unicode Technical Report #36
* discusses security issues of IDN support as well as possible solutions.
* Applications are responsible for taking adequate security measures when using
* international domain names.
*
* @author Edward Wang
* @since 1.6
*
*/
public final class IDN {
/**
* Flag to allow processing of unassigned code points
*/
public static final int ALLOW_UNASSIGNED = 0x01;
/**
* Flag to turn on the check against STD-3 ASCII rules
*/
public static final int USE_STD3_ASCII_RULES = 0x02;
/**
* Translates a string from Unicode to ASCII Compatible Encoding (ACE),
* as defined by the ToASCII operation of RFC 3490.
*
*
ToASCII operation can fail. ToASCII fails if any step of it fails.
* If ToASCII operation fails, an IllegalArgumentException will be thrown.
* In this case, the input string should not be used in an internationalized domain name.
*
*
A label is an individual part of a domain name. The original ToASCII operation,
* as defined in RFC 3490, only operates on a single label. This method can handle
* both label and entire domain name, by assuming that labels in a domain name are
* always separated by dots. The following characters are recognized as dots:
* \u002E (full stop), \u3002 (ideographic full stop), \uFF0E (fullwidth full stop),
* and \uFF61 (halfwidth ideographic full stop). if dots are
* used as label separators, this method also changes all of them to \u002E (full stop)
* in output translated string.
*
* @param input the string to be processed
* @param flag process flag; can be 0 or any logical OR of possible flags
*
* @return the translated {@code String}
*
* @throws IllegalArgumentException if the input string doesn't conform to RFC 3490 specification
*/
public static String toASCII(String input, int flag) {
// BEGIN Android-changed: Use ICU4J implementation.
try {
return ExtendedIDNA.convertIDNToASCII(input, flag).toString();
} catch (android.icu.text.StringPrepParseException e) {
// b/113787610: "." is a valid IDN but is rejected by ICU.
// Usage is relatively uncommon, so only check for it if ICU throws.
if (".".equals(input)) {
return input;
}
throw new IllegalArgumentException("Invalid input to toASCII: " + input, e);
}
// END Android-changed: Use ICU4J implementation.
}
/**
* Translates a string from Unicode to ASCII Compatible Encoding (ACE),
* as defined by the ToASCII operation of RFC 3490.
*
*
This convenience method works as if by invoking the
* two-argument counterpart as follows:
*
* {@link #toASCII(String, int) toASCII}(input, 0);
*
*
* @param input the string to be processed
*
* @return the translated {@code String}
*
* @throws IllegalArgumentException if the input string doesn't conform to RFC 3490 specification
*/
public static String toASCII(String input) {
return toASCII(input, 0);
}
/**
* Translates a string from ASCII Compatible Encoding (ACE) to Unicode,
* as defined by the ToUnicode operation of RFC 3490.
*
* ToUnicode never fails. In case of any error, the input string is returned unmodified.
*
*
A label is an individual part of a domain name. The original ToUnicode operation,
* as defined in RFC 3490, only operates on a single label. This method can handle
* both label and entire domain name, by assuming that labels in a domain name are
* always separated by dots. The following characters are recognized as dots:
* \u002E (full stop), \u3002 (ideographic full stop), \uFF0E (fullwidth full stop),
* and \uFF61 (halfwidth ideographic full stop).
*
* @param input the string to be processed
* @param flag process flag; can be 0 or any logical OR of possible flags
*
* @return the translated {@code String}
*/
public static String toUnicode(String input, int flag) {
// BEGIN Android-changed: Use ICU4J implementation.
try {
// ICU only translates separators to ASCII for toASCII.
// Java expects the translation for toUnicode too.
return convertFullStop(ExtendedIDNA.convertIDNToUnicode(input, flag)).toString();
} catch (android.icu.text.StringPrepParseException e) {
// The RI documentation explicitly states that if the conversion was unsuccessful
// the original string is returned.
return input;
}
// END Android-changed: Use ICU4J implementation.
}
// BEGIN Android-added: Use ICU4J implementation.
private static boolean isLabelSeperator(char c) {
return (c == '\u3002' || c == '\uff0e' || c == '\uff61');
}
private static StringBuffer convertFullStop(StringBuffer input) {
for (int i = 0; i < input.length(); i++) {
if (isLabelSeperator(input.charAt(i))) {
input.setCharAt(i, '.');
}
}
return input;
}
// END Android-added: Use ICU4J implementation.
/**
* Translates a string from ASCII Compatible Encoding (ACE) to Unicode,
* as defined by the ToUnicode operation of RFC 3490.
*
*
This convenience method works as if by invoking the
* two-argument counterpart as follows:
*
* {@link #toUnicode(String, int) toUnicode}(input, 0);
*
*
* @param input the string to be processed
*
* @return the translated {@code String}
*/
public static String toUnicode(String input) {
return toUnicode(input, 0);
}
/* ---------------- Private members -------------- */
// Android-removed: Private helper methods, unused because we use ICU.
/*
// ACE Prefix is "xn--"
private static final String ACE_PREFIX = "xn--";
private static final int ACE_PREFIX_LENGTH = ACE_PREFIX.length();
private static final int MAX_LABEL_LENGTH = 63;
// single instance of nameprep
private static StringPrep namePrep = null;
static {
InputStream stream = null;
try {
final String IDN_PROFILE = "uidna.spp";
if (System.getSecurityManager() != null) {
stream = AccessController.doPrivileged(new PrivilegedAction() {
public InputStream run() {
return StringPrep.class.getResourceAsStream(IDN_PROFILE);
}
});
} else {
stream = StringPrep.class.getResourceAsStream(IDN_PROFILE);
}
namePrep = new StringPrep(stream);
stream.close();
} catch (IOException e) {
// should never reach here
assert false;
}
}
*/
/* ---------------- Private operations -------------- */
//
// to suppress the default zero-argument constructor
//
private IDN() {}
// Android-removed: Private helper methods, unused because we use ICU.
/*
//
// toASCII operation; should only apply to a single label
//
private static String toASCIIInternal(String label, int flag)
{
// step 1
// Check if the string contains code points outside the ASCII range 0..0x7c.
boolean isASCII = isAllASCII(label);
StringBuffer dest;
// step 2
// perform the nameprep operation; flag ALLOW_UNASSIGNED is used here
if (!isASCII) {
UCharacterIterator iter = UCharacterIterator.getInstance(label);
try {
dest = namePrep.prepare(iter, flag);
} catch (java.text.ParseException e) {
throw new IllegalArgumentException(e);
}
} else {
dest = new StringBuffer(label);
}
// step 8, move forward to check the smallest number of the code points
// the length must be inside 1..63
if (dest.length() == 0) {
throw new IllegalArgumentException(
"Empty label is not a legal name");
}
// step 3
// Verify the absence of non-LDH ASCII code points
// 0..0x2c, 0x2e..0x2f, 0x3a..0x40, 0x5b..0x60, 0x7b..0x7f
// Verify the absence of leading and trailing hyphen
boolean useSTD3ASCIIRules = ((flag & USE_STD3_ASCII_RULES) != 0);
if (useSTD3ASCIIRules) {
for (int i = 0; i < dest.length(); i++) {
int c = dest.charAt(i);
if (isNonLDHAsciiCodePoint(c)) {
throw new IllegalArgumentException(
"Contains non-LDH ASCII characters");
}
}
if (dest.charAt(0) == '-' ||
dest.charAt(dest.length() - 1) == '-') {
throw new IllegalArgumentException(
"Has leading or trailing hyphen");
}
}
if (!isASCII) {
// step 4
// If all code points are inside 0..0x7f, skip to step 8
if (!isAllASCII(dest.toString())) {
// step 5
// verify the sequence does not begin with ACE prefix
if(!startsWithACEPrefix(dest)){
// step 6
// encode the sequence with punycode
try {
dest = Punycode.encode(dest, null);
} catch (java.text.ParseException e) {
throw new IllegalArgumentException(e);
}
dest = toASCIILower(dest);
// step 7
// prepend the ACE prefix
dest.insert(0, ACE_PREFIX);
} else {
throw new IllegalArgumentException("The input starts with the ACE Prefix");
}
}
}
// step 8
// the length must be inside 1..63
if (dest.length() > MAX_LABEL_LENGTH) {
throw new IllegalArgumentException("The label in the input is too long");
}
return dest.toString();
}
//
// toUnicode operation; should only apply to a single label
//
private static String toUnicodeInternal(String label, int flag) {
boolean[] caseFlags = null;
StringBuffer dest;
// step 1
// find out if all the codepoints in input are ASCII
boolean isASCII = isAllASCII(label);
if(!isASCII){
// step 2
// perform the nameprep operation; flag ALLOW_UNASSIGNED is used here
try {
UCharacterIterator iter = UCharacterIterator.getInstance(label);
dest = namePrep.prepare(iter, flag);
} catch (Exception e) {
// toUnicode never fails; if any step fails, return the input string
return label;
}
} else {
dest = new StringBuffer(label);
}
// step 3
// verify ACE Prefix
if(startsWithACEPrefix(dest)) {
// step 4
// Remove the ACE Prefix
String temp = dest.substring(ACE_PREFIX_LENGTH, dest.length());
try {
// step 5
// Decode using punycode
StringBuffer decodeOut = Punycode.decode(new StringBuffer(temp), null);
// step 6
// Apply toASCII
String toASCIIOut = toASCII(decodeOut.toString(), flag);
// step 7
// verify
if (toASCIIOut.equalsIgnoreCase(dest.toString())) {
// step 8
// return output of step 5
return decodeOut.toString();
}
} catch (Exception ignored) {
// no-op
}
}
// just return the input
return label;
}
//
// LDH stands for "letter/digit/hyphen", with characters restricted to the
// 26-letter Latin alphabet , the digits <0-9>, and the hyphen
// <->.
// Non LDH refers to characters in the ASCII range, but which are not
// letters, digits or the hypen.
//
// non-LDH = 0..0x2C, 0x2E..0x2F, 0x3A..0x40, 0x5B..0x60, 0x7B..0x7F
//
private static boolean isNonLDHAsciiCodePoint(int ch){
return (0x0000 <= ch && ch <= 0x002C) ||
(0x002E <= ch && ch <= 0x002F) ||
(0x003A <= ch && ch <= 0x0040) ||
(0x005B <= ch && ch <= 0x0060) ||
(0x007B <= ch && ch <= 0x007F);
}
//
// search dots in a string and return the index of that character;
// or if there is no dots, return the length of input string
// dots might be: \u002E (full stop), \u3002 (ideographic full stop), \uFF0E (fullwidth full stop),
// and \uFF61 (halfwidth ideographic full stop).
//
private static int searchDots(String s, int start) {
int i;
for (i = start; i < s.length(); i++) {
if (isLabelSeparator(s.charAt(i))) {
break;
}
}
return i;
}
//
// to check if a string is a root label, ".".
//
private static boolean isRootLabel(String s) {
return (s.length() == 1 && isLabelSeparator(s.charAt(0)));
}
//
// to check if a character is a label separator, i.e. a dot character.
//
private static boolean isLabelSeparator(char c) {
return (c == '.' || c == '\u3002' || c == '\uFF0E' || c == '\uFF61');
}
//
// to check if a string only contains US-ASCII code point
//
private static boolean isAllASCII(String input) {
boolean isASCII = true;
for (int i = 0; i < input.length(); i++) {
int c = input.charAt(i);
if (c > 0x7F) {
isASCII = false;
break;
}
}
return isASCII;
}
//
// to check if a string starts with ACE-prefix
//
private static boolean startsWithACEPrefix(StringBuffer input){
boolean startsWithPrefix = true;
if(input.length() < ACE_PREFIX_LENGTH){
return false;
}
for(int i = 0; i < ACE_PREFIX_LENGTH; i++){
if(toASCIILower(input.charAt(i)) != ACE_PREFIX.charAt(i)){
startsWithPrefix = false;
}
}
return startsWithPrefix;
}
private static char toASCIILower(char ch){
if('A' <= ch && ch <= 'Z'){
return (char)(ch + 'a' - 'A');
}
return ch;
}
private static StringBuffer toASCIILower(StringBuffer input){
StringBuffer dest = new StringBuffer();
for(int i = 0; i < input.length();i++){
dest.append(toASCIILower(input.charAt(i)));
}
return dest;
}
*/
}