Java Code Examples for sun.text.normalizer.UCharacterIterator#getText()
The following examples show how to use
sun.text.normalizer.UCharacterIterator#getText() .
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: StringPrep.java From Bytecoder with Apache License 2.0 | 4 votes |
|
private StringBuffer map( UCharacterIterator iter, int options)
throws ParseException {
Values val = new Values();
char result = 0;
int ch = UCharacterIterator.DONE;
StringBuffer dest = new StringBuffer();
boolean allowUnassigned = ((options & ALLOW_UNASSIGNED)>0);
while((ch=iter.nextCodePoint())!= UCharacterIterator.DONE){
result = getCodePointValue(ch);
getValues(result,val);
// check if the source codepoint is unassigned
if(val.type == UNASSIGNED && allowUnassigned == false){
throw new ParseException("An unassigned code point was found in the input " +
iter.getText(), iter.getIndex());
}else if((val.type == MAP)){
int index, length;
if(val.isIndex){
index = val.value;
if(index >= indexes[ONE_UCHAR_MAPPING_INDEX_START] &&
index < indexes[TWO_UCHARS_MAPPING_INDEX_START]){
length = 1;
}else if(index >= indexes[TWO_UCHARS_MAPPING_INDEX_START] &&
index < indexes[THREE_UCHARS_MAPPING_INDEX_START]){
length = 2;
}else if(index >= indexes[THREE_UCHARS_MAPPING_INDEX_START] &&
index < indexes[FOUR_UCHARS_MAPPING_INDEX_START]){
length = 3;
}else{
length = mappingData[index++];
}
/* copy mapping to destination */
dest.append(mappingData,index,length);
continue;
}else{
ch -= val.value;
}
}else if(val.type == DELETE){
// just consume the codepoint and contine
continue;
}
//copy the source into destination
UTF16.append(dest,ch);
}
return dest;
}
Example 2
| Source File: StringPrep.java From openjdk-8-source 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 3
| Source File: StringPrep.java From openjdk-8-source with GNU General Public License v2.0 | 4 votes |
|
private StringBuffer map( UCharacterIterator iter, int options)
throws ParseException {
Values val = new Values();
char result = 0;
int ch = UCharacterIterator.DONE;
StringBuffer dest = new StringBuffer();
boolean allowUnassigned = ((options & ALLOW_UNASSIGNED)>0);
while((ch=iter.nextCodePoint())!= UCharacterIterator.DONE){
result = getCodePointValue(ch);
getValues(result,val);
// check if the source codepoint is unassigned
if(val.type == UNASSIGNED && allowUnassigned == false){
throw new ParseException("An unassigned code point was found in the input " +
iter.getText(), iter.getIndex());
}else if((val.type == MAP)){
int index, length;
if(val.isIndex){
index = val.value;
if(index >= indexes[ONE_UCHAR_MAPPING_INDEX_START] &&
index < indexes[TWO_UCHARS_MAPPING_INDEX_START]){
length = 1;
}else if(index >= indexes[TWO_UCHARS_MAPPING_INDEX_START] &&
index < indexes[THREE_UCHARS_MAPPING_INDEX_START]){
length = 2;
}else if(index >= indexes[THREE_UCHARS_MAPPING_INDEX_START] &&
index < indexes[FOUR_UCHARS_MAPPING_INDEX_START]){
length = 3;
}else{
length = mappingData[index++];
}
/* copy mapping to destination */
dest.append(mappingData,index,length);
continue;
}else{
ch -= val.value;
}
}else if(val.type == DELETE){
// just consume the codepoint and contine
continue;
}
//copy the source into destination
UTF16.append(dest,ch);
}
return dest;
}
Example 4
| Source File: StringPrep.java From jdk8u-dev-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 5
| Source File: StringPrep.java From hottub with GNU General Public License v2.0 | 4 votes |
|
private StringBuffer map( UCharacterIterator iter, int options)
throws ParseException {
Values val = new Values();
char result = 0;
int ch = UCharacterIterator.DONE;
StringBuffer dest = new StringBuffer();
boolean allowUnassigned = ((options & ALLOW_UNASSIGNED)>0);
while((ch=iter.nextCodePoint())!= UCharacterIterator.DONE){
result = getCodePointValue(ch);
getValues(result,val);
// check if the source codepoint is unassigned
if(val.type == UNASSIGNED && allowUnassigned == false){
throw new ParseException("An unassigned code point was found in the input " +
iter.getText(), iter.getIndex());
}else if((val.type == MAP)){
int index, length;
if(val.isIndex){
index = val.value;
if(index >= indexes[ONE_UCHAR_MAPPING_INDEX_START] &&
index < indexes[TWO_UCHARS_MAPPING_INDEX_START]){
length = 1;
}else if(index >= indexes[TWO_UCHARS_MAPPING_INDEX_START] &&
index < indexes[THREE_UCHARS_MAPPING_INDEX_START]){
length = 2;
}else if(index >= indexes[THREE_UCHARS_MAPPING_INDEX_START] &&
index < indexes[FOUR_UCHARS_MAPPING_INDEX_START]){
length = 3;
}else{
length = mappingData[index++];
}
/* copy mapping to destination */
dest.append(mappingData,index,length);
continue;
}else{
ch -= val.value;
}
}else if(val.type == DELETE){
// just consume the codepoint and contine
continue;
}
//copy the source into destination
UTF16.append(dest,ch);
}
return dest;
}
Example 6
| Source File: StringPrep.java From jdk8u-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 7
| 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 8
| 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 9
| Source File: StringPrep.java From openjdk-jdk9 with GNU General Public License v2.0 | 4 votes |
|
private StringBuffer map( UCharacterIterator iter, int options)
throws ParseException {
Values val = new Values();
char result = 0;
int ch = UCharacterIterator.DONE;
StringBuffer dest = new StringBuffer();
boolean allowUnassigned = ((options & ALLOW_UNASSIGNED)>0);
while((ch=iter.nextCodePoint())!= UCharacterIterator.DONE){
result = getCodePointValue(ch);
getValues(result,val);
// check if the source codepoint is unassigned
if(val.type == UNASSIGNED && allowUnassigned == false){
throw new ParseException("An unassigned code point was found in the input " +
iter.getText(), iter.getIndex());
}else if((val.type == MAP)){
int index, length;
if(val.isIndex){
index = val.value;
if(index >= indexes[ONE_UCHAR_MAPPING_INDEX_START] &&
index < indexes[TWO_UCHARS_MAPPING_INDEX_START]){
length = 1;
}else if(index >= indexes[TWO_UCHARS_MAPPING_INDEX_START] &&
index < indexes[THREE_UCHARS_MAPPING_INDEX_START]){
length = 2;
}else if(index >= indexes[THREE_UCHARS_MAPPING_INDEX_START] &&
index < indexes[FOUR_UCHARS_MAPPING_INDEX_START]){
length = 3;
}else{
length = mappingData[index++];
}
/* copy mapping to destination */
dest.append(mappingData,index,length);
continue;
}else{
ch -= val.value;
}
}else if(val.type == DELETE){
// just consume the codepoint and contine
continue;
}
//copy the source into destination
UTF16.append(dest,ch);
}
return dest;
}
Example 10
| Source File: StringPrep.java From Bytecoder with Apache License 2.0 | 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 11
| Source File: StringPrep.java From jdk8u_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 12
| Source File: StringPrep.java From openjdk-jdk8u-backup 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: StringPrep.java From openjdk-jdk8u-backup with GNU General Public License v2.0 | 4 votes |
|
private StringBuffer map( UCharacterIterator iter, int options)
throws ParseException {
Values val = new Values();
char result = 0;
int ch = UCharacterIterator.DONE;
StringBuffer dest = new StringBuffer();
boolean allowUnassigned = ((options & ALLOW_UNASSIGNED)>0);
while((ch=iter.nextCodePoint())!= UCharacterIterator.DONE){
result = getCodePointValue(ch);
getValues(result,val);
// check if the source codepoint is unassigned
if(val.type == UNASSIGNED && allowUnassigned == false){
throw new ParseException("An unassigned code point was found in the input " +
iter.getText(), iter.getIndex());
}else if((val.type == MAP)){
int index, length;
if(val.isIndex){
index = val.value;
if(index >= indexes[ONE_UCHAR_MAPPING_INDEX_START] &&
index < indexes[TWO_UCHARS_MAPPING_INDEX_START]){
length = 1;
}else if(index >= indexes[TWO_UCHARS_MAPPING_INDEX_START] &&
index < indexes[THREE_UCHARS_MAPPING_INDEX_START]){
length = 2;
}else if(index >= indexes[THREE_UCHARS_MAPPING_INDEX_START] &&
index < indexes[FOUR_UCHARS_MAPPING_INDEX_START]){
length = 3;
}else{
length = mappingData[index++];
}
/* copy mapping to destination */
dest.append(mappingData,index,length);
continue;
}else{
ch -= val.value;
}
}else if(val.type == DELETE){
// just consume the codepoint and contine
continue;
}
//copy the source into destination
UTF16.append(dest,ch);
}
return dest;
}
Example 14
| Source File: StringPrep.java From jdk8u-jdk with GNU General Public License v2.0 | 4 votes |
|
private StringBuffer map( UCharacterIterator iter, int options)
throws ParseException {
Values val = new Values();
char result = 0;
int ch = UCharacterIterator.DONE;
StringBuffer dest = new StringBuffer();
boolean allowUnassigned = ((options & ALLOW_UNASSIGNED)>0);
while((ch=iter.nextCodePoint())!= UCharacterIterator.DONE){
result = getCodePointValue(ch);
getValues(result,val);
// check if the source codepoint is unassigned
if(val.type == UNASSIGNED && allowUnassigned == false){
throw new ParseException("An unassigned code point was found in the input " +
iter.getText(), iter.getIndex());
}else if((val.type == MAP)){
int index, length;
if(val.isIndex){
index = val.value;
if(index >= indexes[ONE_UCHAR_MAPPING_INDEX_START] &&
index < indexes[TWO_UCHARS_MAPPING_INDEX_START]){
length = 1;
}else if(index >= indexes[TWO_UCHARS_MAPPING_INDEX_START] &&
index < indexes[THREE_UCHARS_MAPPING_INDEX_START]){
length = 2;
}else if(index >= indexes[THREE_UCHARS_MAPPING_INDEX_START] &&
index < indexes[FOUR_UCHARS_MAPPING_INDEX_START]){
length = 3;
}else{
length = mappingData[index++];
}
/* copy mapping to destination */
dest.append(mappingData,index,length);
continue;
}else{
ch -= val.value;
}
}else if(val.type == DELETE){
// just consume the codepoint and contine
continue;
}
//copy the source into destination
UTF16.append(dest,ch);
}
return dest;
}
Example 15
| Source File: StringPrep.java From openjdk-jdk8u with GNU General Public License v2.0 | 4 votes |
|
private StringBuffer map( UCharacterIterator iter, int options)
throws ParseException {
Values val = new Values();
char result = 0;
int ch = UCharacterIterator.DONE;
StringBuffer dest = new StringBuffer();
boolean allowUnassigned = ((options & ALLOW_UNASSIGNED)>0);
while((ch=iter.nextCodePoint())!= UCharacterIterator.DONE){
result = getCodePointValue(ch);
getValues(result,val);
// check if the source codepoint is unassigned
if(val.type == UNASSIGNED && allowUnassigned == false){
throw new ParseException("An unassigned code point was found in the input " +
iter.getText(), iter.getIndex());
}else if((val.type == MAP)){
int index, length;
if(val.isIndex){
index = val.value;
if(index >= indexes[ONE_UCHAR_MAPPING_INDEX_START] &&
index < indexes[TWO_UCHARS_MAPPING_INDEX_START]){
length = 1;
}else if(index >= indexes[TWO_UCHARS_MAPPING_INDEX_START] &&
index < indexes[THREE_UCHARS_MAPPING_INDEX_START]){
length = 2;
}else if(index >= indexes[THREE_UCHARS_MAPPING_INDEX_START] &&
index < indexes[FOUR_UCHARS_MAPPING_INDEX_START]){
length = 3;
}else{
length = mappingData[index++];
}
/* copy mapping to destination */
dest.append(mappingData,index,length);
continue;
}else{
ch -= val.value;
}
}else if(val.type == DELETE){
// just consume the codepoint and contine
continue;
}
//copy the source into destination
UTF16.append(dest,ch);
}
return dest;
}
Example 16
| Source File: StringPrep.java From openjdk-8 with GNU General Public License v2.0 | 4 votes |
|
private StringBuffer map( UCharacterIterator iter, int options)
throws ParseException {
Values val = new Values();
char result = 0;
int ch = UCharacterIterator.DONE;
StringBuffer dest = new StringBuffer();
boolean allowUnassigned = ((options & ALLOW_UNASSIGNED)>0);
while((ch=iter.nextCodePoint())!= UCharacterIterator.DONE){
result = getCodePointValue(ch);
getValues(result,val);
// check if the source codepoint is unassigned
if(val.type == UNASSIGNED && allowUnassigned == false){
throw new ParseException("An unassigned code point was found in the input " +
iter.getText(), iter.getIndex());
}else if((val.type == MAP)){
int index, length;
if(val.isIndex){
index = val.value;
if(index >= indexes[ONE_UCHAR_MAPPING_INDEX_START] &&
index < indexes[TWO_UCHARS_MAPPING_INDEX_START]){
length = 1;
}else if(index >= indexes[TWO_UCHARS_MAPPING_INDEX_START] &&
index < indexes[THREE_UCHARS_MAPPING_INDEX_START]){
length = 2;
}else if(index >= indexes[THREE_UCHARS_MAPPING_INDEX_START] &&
index < indexes[FOUR_UCHARS_MAPPING_INDEX_START]){
length = 3;
}else{
length = mappingData[index++];
}
/* copy mapping to destination */
dest.append(mappingData,index,length);
continue;
}else{
ch -= val.value;
}
}else if(val.type == DELETE){
// just consume the codepoint and contine
continue;
}
//copy the source into destination
UTF16.append(dest,ch);
}
return dest;
}
Example 17
| Source File: StringPrep.java From jdk8u_jdk with GNU General Public License v2.0 | 4 votes |
|
private StringBuffer map( UCharacterIterator iter, int options)
throws ParseException {
Values val = new Values();
char result = 0;
int ch = UCharacterIterator.DONE;
StringBuffer dest = new StringBuffer();
boolean allowUnassigned = ((options & ALLOW_UNASSIGNED)>0);
while((ch=iter.nextCodePoint())!= UCharacterIterator.DONE){
result = getCodePointValue(ch);
getValues(result,val);
// check if the source codepoint is unassigned
if(val.type == UNASSIGNED && allowUnassigned == false){
throw new ParseException("An unassigned code point was found in the input " +
iter.getText(), iter.getIndex());
}else if((val.type == MAP)){
int index, length;
if(val.isIndex){
index = val.value;
if(index >= indexes[ONE_UCHAR_MAPPING_INDEX_START] &&
index < indexes[TWO_UCHARS_MAPPING_INDEX_START]){
length = 1;
}else if(index >= indexes[TWO_UCHARS_MAPPING_INDEX_START] &&
index < indexes[THREE_UCHARS_MAPPING_INDEX_START]){
length = 2;
}else if(index >= indexes[THREE_UCHARS_MAPPING_INDEX_START] &&
index < indexes[FOUR_UCHARS_MAPPING_INDEX_START]){
length = 3;
}else{
length = mappingData[index++];
}
/* copy mapping to destination */
dest.append(mappingData,index,length);
continue;
}else{
ch -= val.value;
}
}else if(val.type == DELETE){
// just consume the codepoint and contine
continue;
}
//copy the source into destination
UTF16.append(dest,ch);
}
return dest;
}
Example 18
| 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 19
| Source File: StringPrep.java From TencentKona-8 with GNU General Public License v2.0 | 4 votes |
|
private StringBuffer map( UCharacterIterator iter, int options)
throws ParseException {
Values val = new Values();
char result = 0;
int ch = UCharacterIterator.DONE;
StringBuffer dest = new StringBuffer();
boolean allowUnassigned = ((options & ALLOW_UNASSIGNED)>0);
while((ch=iter.nextCodePoint())!= UCharacterIterator.DONE){
result = getCodePointValue(ch);
getValues(result,val);
// check if the source codepoint is unassigned
if(val.type == UNASSIGNED && allowUnassigned == false){
throw new ParseException("An unassigned code point was found in the input " +
iter.getText(), iter.getIndex());
}else if((val.type == MAP)){
int index, length;
if(val.isIndex){
index = val.value;
if(index >= indexes[ONE_UCHAR_MAPPING_INDEX_START] &&
index < indexes[TWO_UCHARS_MAPPING_INDEX_START]){
length = 1;
}else if(index >= indexes[TWO_UCHARS_MAPPING_INDEX_START] &&
index < indexes[THREE_UCHARS_MAPPING_INDEX_START]){
length = 2;
}else if(index >= indexes[THREE_UCHARS_MAPPING_INDEX_START] &&
index < indexes[FOUR_UCHARS_MAPPING_INDEX_START]){
length = 3;
}else{
length = mappingData[index++];
}
/* copy mapping to destination */
dest.append(mappingData,index,length);
continue;
}else{
ch -= val.value;
}
}else if(val.type == DELETE){
// just consume the codepoint and contine
continue;
}
//copy the source into destination
UTF16.append(dest,ch);
}
return dest;
}
Example 20
| 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;
}
