Java Code Examples for sun.text.normalizer.UCharacterIterator#getInstance()
The following examples show how to use
sun.text.normalizer.UCharacterIterator#getInstance() .
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
| Source File: NFS4StringPrep.java From hottub with GNU General Public License v2.0 | 6 votes |
|
public static byte[] mixed_prepare(byte[] src)
throws IOException, ParseException, UnsupportedEncodingException{
String s = new String(src, "UTF-8");
int index = s.indexOf(AT_SIGN);
StringBuffer out = new StringBuffer();
if(index > -1){
/* special prefixes must not be followed by suffixes! */
String prefixString = s.substring(0,index);
int i= findStringIndex(special_prefixes, prefixString);
String suffixString = s.substring(index+1, s.length());
if(i>-1 && !suffixString.equals("")){
throw new ParseException("Suffix following a special index", -1);
}
UCharacterIterator prefix = UCharacterIterator.getInstance(prefixString);
UCharacterIterator suffix = UCharacterIterator.getInstance(suffixString);
out.append(prep.nfsmxp.prepare(prefix,StringPrep.DEFAULT));
out.append(AT_SIGN); // add the delimiter
out.append(prep.nfsmxs.prepare(suffix, StringPrep.DEFAULT));
}else{
UCharacterIterator iter = UCharacterIterator.getInstance(s);
out.append(prep.nfsmxp.prepare(iter,StringPrep.DEFAULT));
}
return out.toString().getBytes("UTF-8");
}
Example 2
| Source File: NFS4StringPrep.java From jdk8u-dev-jdk with GNU General Public License v2.0 | 6 votes |
|
public static byte[] mixed_prepare(byte[] src)
throws IOException, ParseException, UnsupportedEncodingException{
String s = new String(src, "UTF-8");
int index = s.indexOf(AT_SIGN);
StringBuffer out = new StringBuffer();
if(index > -1){
/* special prefixes must not be followed by suffixes! */
String prefixString = s.substring(0,index);
int i= findStringIndex(special_prefixes, prefixString);
String suffixString = s.substring(index+1, s.length());
if(i>-1 && !suffixString.equals("")){
throw new ParseException("Suffix following a special index", -1);
}
UCharacterIterator prefix = UCharacterIterator.getInstance(prefixString);
UCharacterIterator suffix = UCharacterIterator.getInstance(suffixString);
out.append(prep.nfsmxp.prepare(prefix,StringPrep.DEFAULT));
out.append(AT_SIGN); // add the delimiter
out.append(prep.nfsmxs.prepare(suffix, StringPrep.DEFAULT));
}else{
UCharacterIterator iter = UCharacterIterator.getInstance(s);
out.append(prep.nfsmxp.prepare(iter,StringPrep.DEFAULT));
}
return out.toString().getBytes("UTF-8");
}
Example 3
| Source File: NFS4StringPrep.java From openjdk-jdk8u-backup with GNU General Public License v2.0 | 6 votes |
|
public static byte[] mixed_prepare(byte[] src)
throws IOException, ParseException, UnsupportedEncodingException{
String s = new String(src, "UTF-8");
int index = s.indexOf(AT_SIGN);
StringBuffer out = new StringBuffer();
if(index > -1){
/* special prefixes must not be followed by suffixes! */
String prefixString = s.substring(0,index);
int i= findStringIndex(special_prefixes, prefixString);
String suffixString = s.substring(index+1, s.length());
if(i>-1 && !suffixString.equals("")){
throw new ParseException("Suffix following a special index", -1);
}
UCharacterIterator prefix = UCharacterIterator.getInstance(prefixString);
UCharacterIterator suffix = UCharacterIterator.getInstance(suffixString);
out.append(prep.nfsmxp.prepare(prefix,StringPrep.DEFAULT));
out.append(AT_SIGN); // add the delimiter
out.append(prep.nfsmxs.prepare(suffix, StringPrep.DEFAULT));
}else{
UCharacterIterator iter = UCharacterIterator.getInstance(s);
out.append(prep.nfsmxp.prepare(iter,StringPrep.DEFAULT));
}
return out.toString().getBytes("UTF-8");
}
Example 4
| Source File: TestStringPrep.java From dragonwell8_jdk with GNU General Public License v2.0 | 6 votes |
|
public static void TestNamePrepConformance() throws Exception {
InputStream stream = StringPrep.class.getResourceAsStream("uidna.spp");
StringPrep namePrep = new StringPrep(stream);
stream.close();
int i;
for(i=0; i<TestData.conformanceTestCases.length;i++){
TestData.ConformanceTestCase testCase = TestData.conformanceTestCases[i];
try{
UCharacterIterator iter = UCharacterIterator.getInstance(testCase.input);
StringBuffer output = namePrep.prepare(iter, testCase.flags);
if(testCase.output !=null && output!=null && !testCase.output.equals(output.toString())){
fail("Did not get the expected output. Expected: " + prettify(testCase.output)+
" Got: "+ prettify(output.toString()) );
}
} catch(ParseException ex) {
if (testCase.expected == null) {
fail("get the unexpected exception for source: " +testCase.input +" Got: "+ ex.toString());
}
}
}
System.out.println("Nameprep test count: " + i);
}
Example 5
| Source File: TestStringPrep.java From openjdk-jdk8u-backup with GNU General Public License v2.0 | 6 votes |
|
public static void TestNamePrepConformance() throws Exception {
InputStream stream = StringPrep.class.getResourceAsStream("uidna.spp");
StringPrep namePrep = new StringPrep(stream);
stream.close();
int i;
for(i=0; i<TestData.conformanceTestCases.length;i++){
TestData.ConformanceTestCase testCase = TestData.conformanceTestCases[i];
try{
UCharacterIterator iter = UCharacterIterator.getInstance(testCase.input);
StringBuffer output = namePrep.prepare(iter, testCase.flags);
if(testCase.output !=null && output!=null && !testCase.output.equals(output.toString())){
fail("Did not get the expected output. Expected: " + prettify(testCase.output)+
" Got: "+ prettify(output.toString()) );
}
} catch(ParseException ex) {
if (testCase.expected == null) {
fail("get the unexpected exception for source: " +testCase.input +" Got: "+ ex.toString());
}
}
}
System.out.println("Nameprep test count: " + i);
}
Example 6
| Source File: TestStringPrep.java From jdk8u60 with GNU General Public License v2.0 | 6 votes |
|
public static void TestNamePrepConformance() throws Exception {
InputStream stream = StringPrep.class.getResourceAsStream("uidna.spp");
StringPrep namePrep = new StringPrep(stream);
stream.close();
int i;
for(i=0; i<TestData.conformanceTestCases.length;i++){
TestData.ConformanceTestCase testCase = TestData.conformanceTestCases[i];
try{
UCharacterIterator iter = UCharacterIterator.getInstance(testCase.input);
StringBuffer output = namePrep.prepare(iter, testCase.flags);
if(testCase.output !=null && output!=null && !testCase.output.equals(output.toString())){
fail("Did not get the expected output. Expected: " + prettify(testCase.output)+
" Got: "+ prettify(output.toString()) );
}
} catch(ParseException ex) {
if (testCase.expected == null) {
fail("get the unexpected exception for source: " +testCase.input +" Got: "+ ex.toString());
}
}
}
System.out.println("Nameprep test count: " + i);
}
Example 7
| Source File: NFS4StringPrep.java From jdk8u60 with GNU General Public License v2.0 | 6 votes |
|
public static byte[] mixed_prepare(byte[] src)
throws IOException, ParseException, UnsupportedEncodingException{
String s = new String(src, "UTF-8");
int index = s.indexOf(AT_SIGN);
StringBuffer out = new StringBuffer();
if(index > -1){
/* special prefixes must not be followed by suffixes! */
String prefixString = s.substring(0,index);
int i= findStringIndex(special_prefixes, prefixString);
String suffixString = s.substring(index+1, s.length());
if(i>-1 && !suffixString.equals("")){
throw new ParseException("Suffix following a special index", -1);
}
UCharacterIterator prefix = UCharacterIterator.getInstance(prefixString);
UCharacterIterator suffix = UCharacterIterator.getInstance(suffixString);
out.append(prep.nfsmxp.prepare(prefix,StringPrep.DEFAULT));
out.append(AT_SIGN); // add the delimiter
out.append(prep.nfsmxs.prepare(suffix, StringPrep.DEFAULT));
}else{
UCharacterIterator iter = UCharacterIterator.getInstance(s);
out.append(prep.nfsmxp.prepare(iter,StringPrep.DEFAULT));
}
return out.toString().getBytes("UTF-8");
}
Example 8
| Source File: TestStringPrep.java From jdk8u_jdk with GNU General Public License v2.0 | 6 votes |
|
public static void TestNamePrepConformance() throws Exception {
InputStream stream = StringPrep.class.getResourceAsStream("uidna.spp");
StringPrep namePrep = new StringPrep(stream);
stream.close();
int i;
for(i=0; i<TestData.conformanceTestCases.length;i++){
TestData.ConformanceTestCase testCase = TestData.conformanceTestCases[i];
try{
UCharacterIterator iter = UCharacterIterator.getInstance(testCase.input);
StringBuffer output = namePrep.prepare(iter, testCase.flags);
if(testCase.output !=null && output!=null && !testCase.output.equals(output.toString())){
fail("Did not get the expected output. Expected: " + prettify(testCase.output)+
" Got: "+ prettify(output.toString()) );
}
} catch(ParseException ex) {
if (testCase.expected == null) {
fail("get the unexpected exception for source: " +testCase.input +" Got: "+ ex.toString());
}
}
}
System.out.println("Nameprep test count: " + i);
}
Example 9
| Source File: NFS4StringPrep.java From dragonwell8_jdk with GNU General Public License v2.0 | 5 votes |
|
private static byte[] prepare(byte[] src, StringPrep prep)
throws ParseException, UnsupportedEncodingException{
String s = new String(src, "UTF-8");
UCharacterIterator iter = UCharacterIterator.getInstance(s);
StringBuffer out = prep.prepare(iter,StringPrep.DEFAULT);
return out.toString().getBytes("UTF-8");
}
Example 10
| Source File: NFS4StringPrep.java From TencentKona-8 with GNU General Public License v2.0 | 5 votes |
|
private static byte[] prepare(byte[] src, StringPrep prep)
throws ParseException, UnsupportedEncodingException{
String s = new String(src, "UTF-8");
UCharacterIterator iter = UCharacterIterator.getInstance(s);
StringBuffer out = prep.prepare(iter,StringPrep.DEFAULT);
return out.toString().getBytes("UTF-8");
}
Example 11
| Source File: NFS4StringPrep.java From jdk8u-jdk with GNU General Public License v2.0 | 5 votes |
|
private static byte[] prepare(byte[] src, StringPrep prep)
throws ParseException, UnsupportedEncodingException{
String s = new String(src, "UTF-8");
UCharacterIterator iter = UCharacterIterator.getInstance(s);
StringBuffer out = prep.prepare(iter,StringPrep.DEFAULT);
return out.toString().getBytes("UTF-8");
}
Example 12
| Source File: StringPrep.java From openjdk-8 with GNU General Public License v2.0 | 4 votes |
|
/**
* Prepare the input buffer for use in applications with the given profile. This operation maps, normalizes(NFKC),
* checks for prohited and BiDi characters in the order defined by RFC 3454
* depending on the options specified in the profile.
*
* @param src A UCharacterIterator object containing the source string
* @param options A bit set of options:
*
* - StringPrep.NONE Prohibit processing of unassigned code points in the input
*
* - StringPrep.ALLOW_UNASSIGNED Treat the unassigned code points are in the input
* as normal Unicode code points.
*
* @return StringBuffer A StringBuffer containing the output
* @throws ParseException
* @draft ICU 2.8
*/
public StringBuffer prepare(UCharacterIterator src, int options)
throws ParseException{
// map
StringBuffer mapOut = map(src,options);
StringBuffer normOut = mapOut;// initialize
if(doNFKC){
// normalize
normOut = normalize(mapOut);
}
int ch;
char result;
UCharacterIterator iter = UCharacterIterator.getInstance(normOut);
Values val = new Values();
int direction=UCharacterDirection.CHAR_DIRECTION_COUNT,
firstCharDir=UCharacterDirection.CHAR_DIRECTION_COUNT;
int rtlPos=-1, ltrPos=-1;
boolean rightToLeft=false, leftToRight=false;
while((ch=iter.nextCodePoint())!= UCharacterIterator.DONE){
result = getCodePointValue(ch);
getValues(result,val);
if(val.type == PROHIBITED ){
throw new ParseException("A prohibited code point was found in the input" +
iter.getText(), val.value);
}
direction = UCharacter.getDirection(ch);
if(firstCharDir == UCharacterDirection.CHAR_DIRECTION_COUNT){
firstCharDir = direction;
}
if(direction == UCharacterDirection.LEFT_TO_RIGHT){
leftToRight = true;
ltrPos = iter.getIndex()-1;
}
if(direction == UCharacterDirection.RIGHT_TO_LEFT || direction == UCharacterDirection.RIGHT_TO_LEFT_ARABIC){
rightToLeft = true;
rtlPos = iter.getIndex()-1;
}
}
if(checkBiDi == true){
// satisfy 2
if( leftToRight == true && rightToLeft == true){
throw new ParseException("The input does not conform to the rules for BiDi code points." +
iter.getText(),
(rtlPos>ltrPos) ? rtlPos : ltrPos);
}
//satisfy 3
if( rightToLeft == true &&
!((firstCharDir == UCharacterDirection.RIGHT_TO_LEFT || firstCharDir == UCharacterDirection.RIGHT_TO_LEFT_ARABIC) &&
(direction == UCharacterDirection.RIGHT_TO_LEFT || direction == UCharacterDirection.RIGHT_TO_LEFT_ARABIC))
){
throw new ParseException("The input does not conform to the rules for BiDi code points." +
iter.getText(),
(rtlPos>ltrPos) ? rtlPos : ltrPos);
}
}
return normOut;
}
Example 13
| Source File: IDN.java From Bytecoder with Apache License 2.0 | 4 votes |
|
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;
}
Example 14
| Source File: StringPrep.java From openjdk-jdk9 with GNU General Public License v2.0 | 4 votes |
|
/**
* Prepare the input buffer for use in applications with the given profile. This operation maps, normalizes(NFKC),
* checks for prohited and BiDi characters in the order defined by RFC 3454
* depending on the options specified in the profile.
*
* @param src A UCharacterIterator object containing the source string
* @param options A bit set of options:
*
* - StringPrep.NONE Prohibit processing of unassigned code points in the input
*
* - StringPrep.ALLOW_UNASSIGNED Treat the unassigned code points are in the input
* as normal Unicode code points.
*
* @return StringBuffer A StringBuffer containing the output
* @throws ParseException
* @draft ICU 2.8
*/
public StringBuffer prepare(UCharacterIterator src, int options)
throws ParseException{
// map
StringBuffer mapOut = map(src,options);
StringBuffer normOut = mapOut;// initialize
if(doNFKC){
// normalize
normOut = normalize(mapOut);
}
int ch;
char result;
UCharacterIterator iter = UCharacterIterator.getInstance(normOut);
Values val = new Values();
int direction=UCharacterDirection.CHAR_DIRECTION_COUNT,
firstCharDir=UCharacterDirection.CHAR_DIRECTION_COUNT;
int rtlPos=-1, ltrPos=-1;
boolean rightToLeft=false, leftToRight=false;
while((ch=iter.nextCodePoint())!= UCharacterIterator.DONE){
result = getCodePointValue(ch);
getValues(result,val);
if(val.type == PROHIBITED ){
throw new ParseException("A prohibited code point was found in the input" +
iter.getText(), val.value);
}
direction = UCharacter.getDirection(ch);
if(firstCharDir == UCharacterDirection.CHAR_DIRECTION_COUNT){
firstCharDir = direction;
}
if(direction == UCharacterDirection.LEFT_TO_RIGHT){
leftToRight = true;
ltrPos = iter.getIndex()-1;
}
if(direction == UCharacterDirection.RIGHT_TO_LEFT || direction == UCharacterDirection.RIGHT_TO_LEFT_ARABIC){
rightToLeft = true;
rtlPos = iter.getIndex()-1;
}
}
if(checkBiDi == true){
// satisfy 2
if( leftToRight == true && rightToLeft == true){
throw new ParseException("The input does not conform to the rules for BiDi code points." +
iter.getText(),
(rtlPos>ltrPos) ? rtlPos : ltrPos);
}
//satisfy 3
if( rightToLeft == true &&
!((firstCharDir == UCharacterDirection.RIGHT_TO_LEFT || firstCharDir == UCharacterDirection.RIGHT_TO_LEFT_ARABIC) &&
(direction == UCharacterDirection.RIGHT_TO_LEFT || direction == UCharacterDirection.RIGHT_TO_LEFT_ARABIC))
){
throw new ParseException("The input does not conform to the rules for BiDi code points." +
iter.getText(),
(rtlPos>ltrPos) ? rtlPos : ltrPos);
}
}
return normOut;
}
Example 15
| Source File: IDN.java From jdk8u60 with GNU General Public License v2.0 | 4 votes |
|
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;
}
Example 16
| Source File: IDN.java From Java8CN with Apache License 2.0 | 4 votes |
|
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;
}
Example 17
| Source File: StringPrep.java From TencentKona-8 with GNU General Public License v2.0 | 4 votes |
|
/**
* Prepare the input buffer for use in applications with the given profile. This operation maps, normalizes(NFKC),
* checks for prohited and BiDi characters in the order defined by RFC 3454
* depending on the options specified in the profile.
*
* @param src A UCharacterIterator object containing the source string
* @param options A bit set of options:
*
* - StringPrep.NONE Prohibit processing of unassigned code points in the input
*
* - StringPrep.ALLOW_UNASSIGNED Treat the unassigned code points are in the input
* as normal Unicode code points.
*
* @return StringBuffer A StringBuffer containing the output
* @throws ParseException
* @draft ICU 2.8
*/
public StringBuffer prepare(UCharacterIterator src, int options)
throws ParseException{
// map
StringBuffer mapOut = map(src,options);
StringBuffer normOut = mapOut;// initialize
if(doNFKC){
// normalize
normOut = normalize(mapOut);
}
int ch;
char result;
UCharacterIterator iter = UCharacterIterator.getInstance(normOut);
Values val = new Values();
int direction=UCharacterDirection.CHAR_DIRECTION_COUNT,
firstCharDir=UCharacterDirection.CHAR_DIRECTION_COUNT;
int rtlPos=-1, ltrPos=-1;
boolean rightToLeft=false, leftToRight=false;
while((ch=iter.nextCodePoint())!= UCharacterIterator.DONE){
result = getCodePointValue(ch);
getValues(result,val);
if(val.type == PROHIBITED ){
throw new ParseException("A prohibited code point was found in the input" +
iter.getText(), val.value);
}
direction = UCharacter.getDirection(ch);
if(firstCharDir == UCharacterDirection.CHAR_DIRECTION_COUNT){
firstCharDir = direction;
}
if(direction == UCharacterDirection.LEFT_TO_RIGHT){
leftToRight = true;
ltrPos = iter.getIndex()-1;
}
if(direction == UCharacterDirection.RIGHT_TO_LEFT || direction == UCharacterDirection.RIGHT_TO_LEFT_ARABIC){
rightToLeft = true;
rtlPos = iter.getIndex()-1;
}
}
if(checkBiDi == true){
// satisfy 2
if( leftToRight == true && rightToLeft == true){
throw new ParseException("The input does not conform to the rules for BiDi code points." +
iter.getText(),
(rtlPos>ltrPos) ? rtlPos : ltrPos);
}
//satisfy 3
if( rightToLeft == true &&
!((firstCharDir == UCharacterDirection.RIGHT_TO_LEFT || firstCharDir == UCharacterDirection.RIGHT_TO_LEFT_ARABIC) &&
(direction == UCharacterDirection.RIGHT_TO_LEFT || direction == UCharacterDirection.RIGHT_TO_LEFT_ARABIC))
){
throw new ParseException("The input does not conform to the rules for BiDi code points." +
iter.getText(),
(rtlPos>ltrPos) ? rtlPos : ltrPos);
}
}
return normOut;
}
Example 18
| Source File: IDN.java From openjdk-8-source with GNU General Public License v2.0 | 4 votes |
|
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;
}
Example 19
| Source File: StringPrep.java From dragonwell8_jdk with GNU General Public License v2.0 | 4 votes |
|
/**
* Prepare the input buffer for use in applications with the given profile. This operation maps, normalizes(NFKC),
* checks for prohited and BiDi characters in the order defined by RFC 3454
* depending on the options specified in the profile.
*
* @param src A UCharacterIterator object containing the source string
* @param options A bit set of options:
*
* - StringPrep.NONE Prohibit processing of unassigned code points in the input
*
* - StringPrep.ALLOW_UNASSIGNED Treat the unassigned code points are in the input
* as normal Unicode code points.
*
* @return StringBuffer A StringBuffer containing the output
* @throws ParseException
* @draft ICU 2.8
*/
public StringBuffer prepare(UCharacterIterator src, int options)
throws ParseException{
// map
StringBuffer mapOut = map(src,options);
StringBuffer normOut = mapOut;// initialize
if(doNFKC){
// normalize
normOut = normalize(mapOut);
}
int ch;
char result;
UCharacterIterator iter = UCharacterIterator.getInstance(normOut);
Values val = new Values();
int direction=UCharacterDirection.CHAR_DIRECTION_COUNT,
firstCharDir=UCharacterDirection.CHAR_DIRECTION_COUNT;
int rtlPos=-1, ltrPos=-1;
boolean rightToLeft=false, leftToRight=false;
while((ch=iter.nextCodePoint())!= UCharacterIterator.DONE){
result = getCodePointValue(ch);
getValues(result,val);
if(val.type == PROHIBITED ){
throw new ParseException("A prohibited code point was found in the input" +
iter.getText(), val.value);
}
direction = UCharacter.getDirection(ch);
if(firstCharDir == UCharacterDirection.CHAR_DIRECTION_COUNT){
firstCharDir = direction;
}
if(direction == UCharacterDirection.LEFT_TO_RIGHT){
leftToRight = true;
ltrPos = iter.getIndex()-1;
}
if(direction == UCharacterDirection.RIGHT_TO_LEFT || direction == UCharacterDirection.RIGHT_TO_LEFT_ARABIC){
rightToLeft = true;
rtlPos = iter.getIndex()-1;
}
}
if(checkBiDi == true){
// satisfy 2
if( leftToRight == true && rightToLeft == true){
throw new ParseException("The input does not conform to the rules for BiDi code points." +
iter.getText(),
(rtlPos>ltrPos) ? rtlPos : ltrPos);
}
//satisfy 3
if( rightToLeft == true &&
!((firstCharDir == UCharacterDirection.RIGHT_TO_LEFT || firstCharDir == UCharacterDirection.RIGHT_TO_LEFT_ARABIC) &&
(direction == UCharacterDirection.RIGHT_TO_LEFT || direction == UCharacterDirection.RIGHT_TO_LEFT_ARABIC))
){
throw new ParseException("The input does not conform to the rules for BiDi code points." +
iter.getText(),
(rtlPos>ltrPos) ? rtlPos : ltrPos);
}
}
return normOut;
}
Example 20
| Source File: IDN.java From openjdk-8 with GNU General Public License v2.0 | 4 votes |
|
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;
}
